diff options
Diffstat (limited to 'fs')
222 files changed, 2751 insertions, 1442 deletions
diff --git a/fs/affs/file.c b/fs/affs/file.c index ba084b0b214b..82bb38370aa9 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -878,7 +878,7 @@ affs_truncate(struct inode *inode) if (inode->i_size > AFFS_I(inode)->mmu_private) { struct address_space *mapping = inode->i_mapping; struct page *page; - void *fsdata; + void *fsdata = NULL; loff_t isize = inode->i_size; int res; diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 59eb92484051..31055d71b788 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -887,7 +887,7 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry, static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) { struct afs_vnode *vnode, *dir; - struct afs_fid uninitialized_var(fid); + struct afs_fid fid; struct dentry *parent; struct inode *inode; struct key *key; diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c index fc6c42eeb659..ff21ce511f47 100644 --- a/fs/afs/dynroot.c +++ b/fs/afs/dynroot.c @@ -172,20 +172,9 @@ static int afs_dynroot_d_revalidate(struct dentry *dentry, unsigned int flags) return 1; } -/* - * Allow the VFS to enquire as to whether a dentry should be unhashed (mustn't - * sleep) - * - called from dput() when d_count is going to 0. - * - return 1 to request dentry be unhashed, 0 otherwise - */ -static int afs_dynroot_d_delete(const struct dentry *dentry) -{ - return d_really_is_positive(dentry); -} - const struct dentry_operations afs_dynroot_dentry_operations = { .d_revalidate = afs_dynroot_d_revalidate, - .d_delete = afs_dynroot_d_delete, + .d_delete = always_delete_dentry, .d_release = afs_d_release, .d_automount = afs_d_automount, }; diff --git a/fs/afs/security.c b/fs/afs/security.c index 66042b432baa..e12e532069ee 100644 --- a/fs/afs/security.c +++ b/fs/afs/security.c @@ -340,7 +340,7 @@ int afs_check_permit(struct afs_vnode *vnode, struct key *key, int afs_permission(struct inode *inode, int mask) { struct afs_vnode *vnode = AFS_FS_I(inode); - afs_access_t uninitialized_var(access); + afs_access_t access; struct key *key; int ret; @@ -332,6 +332,9 @@ static int aio_ring_mremap(struct vm_area_struct *vma) spin_lock(&mm->ioctx_lock); rcu_read_lock(); table = rcu_dereference(mm->ioctx_table); + if (!table) + goto out_unlock; + for (i = 0; i < table->nr; i++) { struct kioctx *ctx; @@ -345,6 +348,7 @@ static int aio_ring_mremap(struct vm_area_struct *vma) } } +out_unlock: rcu_read_unlock(); spin_unlock(&mm->ioctx_lock); return res; diff --git a/fs/attr.c b/fs/attr.c index 4d2541c1e68c..f064f08f5194 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -256,9 +256,25 @@ int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **de } if ((ia_valid & ATTR_MODE)) { - umode_t amode = attr->ia_mode; + /* + * Don't allow changing the mode of symlinks: + * + * (1) The vfs doesn't take the mode of symlinks into account + * during permission checking. + * (2) This has never worked correctly. Most major filesystems + * did return EOPNOTSUPP due to interactions with POSIX ACLs + * but did still updated the mode of the symlink. + * This inconsistency led system call wrapper providers such + * as libc to block changing the mode of symlinks with + * EOPNOTSUPP already. + * (3) To even do this in the first place one would have to use + * specific file descriptors and quite some effort. + */ + if (S_ISLNK(inode->i_mode)) + return -EOPNOTSUPP; + /* Flag setting protected by i_mutex */ - if (is_sxid(amode)) + if (is_sxid(attr->ia_mode)) inode->i_flags &= ~S_NOSEC; } diff --git a/fs/autofs/waitq.c b/fs/autofs/waitq.c index f6385c6ef0a5..44ba0cd4ebc4 100644 --- a/fs/autofs/waitq.c +++ b/fs/autofs/waitq.c @@ -35,8 +35,9 @@ void autofs_catatonic_mode(struct autofs_sb_info *sbi) wq->status = -ENOENT; /* Magic is gone - report failure */ kfree(wq->name.name); wq->name.name = NULL; - wq->wait_ctr--; wake_up_interruptible(&wq->queue); + if (!--wq->wait_ctr) + kfree(wq); wq = nwq; } fput(sbi->pipe); /* Close the pipe */ diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c index c3deb2e35f20..e7a9e8b56e71 100644 --- a/fs/binfmt_aout.c +++ b/fs/binfmt_aout.c @@ -244,6 +244,7 @@ static int load_aout_binary(struct linux_binprm * bprm) set_personality(PER_LINUX); #endif setup_new_exec(bprm); + install_exec_creds(bprm); current->mm->end_code = ex.a_text + (current->mm->start_code = N_TXTADDR(ex)); @@ -256,7 +257,6 @@ static int load_aout_binary(struct linux_binprm * bprm) if (retval < 0) return retval; - install_exec_creds(bprm); if (N_MAGIC(ex) == OMAGIC) { unsigned long text_addr, map_size; diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index b53bb3729ac1..a7c2efcd0a4a 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -349,14 +349,14 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm) /* there's now no turning back... the old userspace image is dead, * defunct, deceased, etc. */ + SET_PERSONALITY(exec_params.hdr); if (elf_check_fdpic(&exec_params.hdr)) - set_personality(PER_LINUX_FDPIC); - else - set_personality(PER_LINUX); + current->personality |= PER_LINUX_FDPIC; if (elf_read_implies_exec(&exec_params.hdr, executable_stack)) current->personality |= READ_IMPLIES_EXEC; setup_new_exec(bprm); + install_exec_creds(bprm); set_binfmt(&elf_fdpic_format); @@ -438,9 +438,9 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm) current->mm->start_stack = current->mm->start_brk + stack_size; #endif - install_exec_creds(bprm); - if (create_elf_fdpic_tables(bprm, current->mm, - &exec_params, &interp_params) < 0) + retval = create_elf_fdpic_tables(bprm, current->mm, &exec_params, + &interp_params); + if (retval < 0) goto error; kdebug("- start_code %lx", current->mm->start_code); diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c index a6f97d86fb80..a909743b1a0e 100644 --- a/fs/binfmt_flat.c +++ b/fs/binfmt_flat.c @@ -541,6 +541,7 @@ static int load_flat_file(struct linux_binprm *bprm, /* OK, This is the point of no return */ set_personality(PER_LINUX_32BIT); setup_new_exec(bprm); + install_exec_creds(bprm); } /* @@ -965,8 +966,6 @@ static int load_flat_binary(struct linux_binprm *bprm) } } - install_exec_creds(bprm); - set_binfmt(&flat_format); #ifdef CONFIG_MMU diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index 27a04f492541..8fe7edd2b001 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -42,10 +42,10 @@ static LIST_HEAD(entries); static int enabled = 1; enum {Enabled, Magic}; -#define MISC_FMT_PRESERVE_ARGV0 (1 << 31) -#define MISC_FMT_OPEN_BINARY (1 << 30) -#define MISC_FMT_CREDENTIALS (1 << 29) -#define MISC_FMT_OPEN_FILE (1 << 28) +#define MISC_FMT_PRESERVE_ARGV0 (1UL << 31) +#define MISC_FMT_OPEN_BINARY (1UL << 30) +#define MISC_FMT_CREDENTIALS (1UL << 29) +#define MISC_FMT_OPEN_FILE (1UL << 28) typedef struct { struct list_head list; diff --git a/fs/block_dev.c b/fs/block_dev.c index b34f76af59c4..5c6ff1572405 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -2041,21 +2041,26 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start, if ((start | len) & (bdev_logical_block_size(bdev) - 1)) return -EINVAL; - /* Invalidate the page cache, including dirty pages. */ + /* + * Invalidate the page cache, including dirty pages, for valid + * de-allocate mode calls to fallocate(). + */ mapping = bdev->bd_inode->i_mapping; - truncate_inode_pages_range(mapping, start, end); switch (mode) { case FALLOC_FL_ZERO_RANGE: case FALLOC_FL_ZERO_RANGE | FALLOC_FL_KEEP_SIZE: + truncate_inode_pages_range(mapping, start, end); error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9, GFP_KERNEL, BLKDEV_ZERO_NOUNMAP); break; case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE: + truncate_inode_pages_range(mapping, start, end); error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9, GFP_KERNEL, BLKDEV_ZERO_NOFALLBACK); break; case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE | FALLOC_FL_NO_HIDE_STALE: + truncate_inode_pages_range(mapping, start, end); error = blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_KERNEL, 0); break; diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 00dc1b5c8737..e48c6d7a860f 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -3590,6 +3590,8 @@ static noinline int split_node(struct btrfs_trans_handle *trans, ret = tree_mod_log_eb_copy(fs_info, split, c, 0, mid, c_nritems - mid); if (ret) { + btrfs_tree_unlock(split); + free_extent_buffer(split); btrfs_abort_transaction(trans, ret); return ret; } @@ -5151,10 +5153,12 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path) { struct btrfs_key key; + struct btrfs_key orig_key; struct btrfs_disk_key found_key; int ret; btrfs_item_key_to_cpu(path->nodes[0], &key, 0); + orig_key = key; if (key.offset > 0) { key.offset--; @@ -5171,8 +5175,36 @@ int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path) btrfs_release_path(path); ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); - if (ret < 0) + if (ret <= 0) return ret; + + /* + * Previous key not found. Even if we were at slot 0 of the leaf we had + * before releasing the path and calling btrfs_search_slot(), we now may + * be in a slot pointing to the same original key - this can happen if + * after we released the path, one of more items were moved from a + * sibling leaf into the front of the leaf we had due to an insertion + * (see push_leaf_right()). + * If we hit this case and our slot is > 0 and just decrement the slot + * so that the caller does not process the same key again, which may or + * may not break the caller, depending on its logic. + */ + if (path->slots[0] < btrfs_header_nritems(path->nodes[0])) { + btrfs_item_key(path->nodes[0], &found_key, path->slots[0]); + ret = comp_keys(&found_key, &orig_key); + if (ret == 0) { + if (path->slots[0] > 0) { + path->slots[0]--; + return 0; + } + /* + * At slot 0, same key as before, it means orig_key is + * the lowest, leftmost, key in the tree. We're done. + */ + return 1; + } + } + btrfs_item_key(path->nodes[0], &found_key, 0); ret = comp_keys(&found_key, &key); /* diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 1fbe2dee1e70..469a90b07d3f 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1171,20 +1171,33 @@ static int __btrfs_run_delayed_items(struct btrfs_trans_handle *trans, int nr) ret = __btrfs_commit_inode_delayed_items(trans, path, curr_node); if (ret) { - btrfs_release_delayed_node(curr_node); - curr_node = NULL; btrfs_abort_transaction(trans, ret); break; } prev_node = curr_node; curr_node = btrfs_next_delayed_node(curr_node); + /* + * See the comment below about releasing path before releasing + * node. If the commit of delayed items was successful the path + * should always be released, but in case of an error, it may + * point to locked extent buffers (a leaf at the very least). + */ + ASSERT(path->nodes[0] == NULL); btrfs_release_delayed_node(prev_node); } + /* + * Release the path to avoid a potential deadlock and lockdep splat when + * releasing the delayed node, as that requires taking the delayed node's + * mutex. If another task starts running delayed items before we take + * the mutex, it will first lock the mutex and then it may try to lock + * the same btree path (leaf). + */ + btrfs_free_path(path); + if (curr_node) btrfs_release_delayed_node(curr_node); - btrfs_free_path(path); trans->block_rsv = block_rsv; return ret; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 98f87cc47433..437ca4691967 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -4348,7 +4348,11 @@ static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root) */ inode = igrab(&btrfs_inode->vfs_inode); if (inode) { + unsigned int nofs_flag; + + nofs_flag = memalloc_nofs_save(); invalidate_inode_pages2(inode->i_mapping); + memalloc_nofs_restore(nofs_flag); iput(inode); } spin_lock(&root->delalloc_lock); @@ -4466,7 +4470,12 @@ static void btrfs_cleanup_bg_io(struct btrfs_block_group_cache *cache) inode = cache->io_ctl.inode; if (inode) { + unsigned int nofs_flag; + + nofs_flag = memalloc_nofs_save(); invalidate_inode_pages2(inode->i_mapping); + memalloc_nofs_restore(nofs_flag); + BTRFS_I(inode)->generation = 0; cache->io_ctl.inode = NULL; iput(inode); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index d71f800e8bf6..902ab00bfd7a 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -1549,6 +1549,11 @@ again: err = -ENOENT; goto out; } else if (WARN_ON(ret)) { + btrfs_print_leaf(path->nodes[0]); + btrfs_err(fs_info, +"extent item not found for insert, bytenr %llu num_bytes %llu parent %llu root_objectid %llu owner %llu offset %llu", + bytenr, num_bytes, parent, root_objectid, owner, + offset); err = -EIO; goto out; } @@ -2322,12 +2327,12 @@ static int run_delayed_tree_ref(struct btrfs_trans_handle *trans, parent = ref->parent; ref_root = ref->root; - if (node->ref_mod != 1) { + if (unlikely(node->ref_mod != 1)) { btrfs_err(trans->fs_info, - "btree block(%llu) has %d references rather than 1: action %d ref_root %llu parent %llu", + "btree block %llu has %d references rather than 1: action %d ref_root %llu parent %llu", node->bytenr, node->ref_mod, node->action, ref_root, parent); - return -EIO; + return -EUCLEAN; } if (node->action == BTRFS_ADD_DELAYED_REF && insert_reserved) { BUG_ON(!extent_op || !extent_op->update_flags); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index dabf153843e9..504d63fb81fa 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -3928,11 +3928,12 @@ retry: free_extent_buffer(eb); /* - * the filesystem may choose to bump up nr_to_write. + * The filesystem may choose to bump up nr_to_write. * We have to make sure to honor the new nr_to_write - * at any time + * at any time. */ - nr_to_write_done = wbc->nr_to_write <= 0; + nr_to_write_done = (wbc->sync_mode == WB_SYNC_NONE && + wbc->nr_to_write <= 0); } pagevec_release(&pvec); cond_resched(); diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 6511cb71986c..b623e9f3b4c4 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -783,15 +783,16 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode, } spin_lock(&ctl->tree_lock); ret = link_free_space(ctl, e); - ctl->total_bitmaps++; - ctl->op->recalc_thresholds(ctl); - spin_unlock(&ctl->tree_lock); if (ret) { + spin_unlock(&ctl->tree_lock); btrfs_err(fs_info, "Duplicate entries in free space cache, dumping"); kmem_cache_free(btrfs_free_space_cachep, e); goto free_cache; } + ctl->total_bitmaps++; + ctl->op->recalc_thresholds(ctl); + spin_unlock(&ctl->tree_lock); list_add_tail(&e->list, &bitmaps); } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index f314b2c2d148..e4a4074ef33d 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -6620,7 +6620,7 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry, if (IS_ERR(trans)) return PTR_ERR(trans); - err = btrfs_find_free_ino(root, &objectid); + err = btrfs_find_free_objectid(root, &objectid); if (err) goto out_unlock; @@ -6684,7 +6684,7 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry, if (IS_ERR(trans)) return PTR_ERR(trans); - err = btrfs_find_free_ino(root, &objectid); + err = btrfs_find_free_objectid(root, &objectid); if (err) goto out_unlock; @@ -6837,7 +6837,7 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) if (IS_ERR(trans)) return PTR_ERR(trans); - err = btrfs_find_free_ino(root, &objectid); + err = btrfs_find_free_objectid(root, &objectid); if (err) goto out_fail; @@ -9819,7 +9819,7 @@ static int btrfs_whiteout_for_rename(struct btrfs_trans_handle *trans, u64 objectid; u64 index; - ret = btrfs_find_free_ino(root, &objectid); + ret = btrfs_find_free_objectid(root, &objectid); if (ret) return ret; @@ -10316,7 +10316,7 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry, if (IS_ERR(trans)) return PTR_ERR(trans); - err = btrfs_find_free_ino(root, &objectid); + err = btrfs_find_free_objectid(root, &objectid); if (err) goto out_unlock; @@ -10600,7 +10600,7 @@ static int btrfs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) if (IS_ERR(trans)) return PTR_ERR(trans); - ret = btrfs_find_free_ino(root, &objectid); + ret = btrfs_find_free_objectid(root, &objectid); if (ret) goto out; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 752b5d265284..c76277ccf03b 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1789,6 +1789,15 @@ static noinline int btrfs_ioctl_snap_create_transid(struct file *file, * are limited to own subvolumes only */ ret = -EPERM; + } else if (btrfs_ino(BTRFS_I(src_inode)) != BTRFS_FIRST_FREE_OBJECTID) { + /* + * Snapshots must be made with the src_inode referring + * to the subvolume inode, otherwise the permission + * checking above is useless because we may have + * permission on a lower directory but not the subvol + * itself. + */ + ret = -EINVAL; } else { ret = btrfs_mksubvol(&file->f_path, name, namelen, BTRFS_I(src_inode)->root, @@ -2045,7 +2054,7 @@ static noinline int key_in_sk(struct btrfs_key *key, static noinline int copy_to_sk(struct btrfs_path *path, struct btrfs_key *key, struct btrfs_ioctl_search_key *sk, - size_t *buf_size, + u64 *buf_size, char __user *ubuf, unsigned long *sk_offset, int *num_found) @@ -2177,7 +2186,7 @@ out: static noinline int search_ioctl(struct inode *inode, struct btrfs_ioctl_search_key *sk, - size_t *buf_size, + u64 *buf_size, char __user *ubuf) { struct btrfs_fs_info *info = btrfs_sb(inode->i_sb); @@ -2249,7 +2258,7 @@ static noinline int btrfs_ioctl_tree_search(struct file *file, struct btrfs_ioctl_search_key sk; struct inode *inode; int ret; - size_t buf_size; + u64 buf_size; if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -2283,8 +2292,8 @@ static noinline int btrfs_ioctl_tree_search_v2(struct file *file, struct btrfs_ioctl_search_args_v2 args; struct inode *inode; int ret; - size_t buf_size; - const size_t buf_limit = SZ_16M; + u64 buf_size; + const u64 buf_limit = SZ_16M; if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -3234,13 +3243,10 @@ static long btrfs_ioctl_dev_info(struct btrfs_fs_info *fs_info, di_args->bytes_used = btrfs_device_get_bytes_used(dev); di_args->total_bytes = btrfs_device_get_total_bytes(dev); memcpy(di_args->uuid, dev->uuid, sizeof(di_args->uuid)); - if (dev->name) { - strncpy(di_args->path, rcu_str_deref(dev->name), - sizeof(di_args->path) - 1); - di_args->path[sizeof(di_args->path) - 1] = 0; - } else { + if (dev->name) + strscpy(di_args->path, rcu_str_deref(dev->name), sizeof(di_args->path)); + else di_args->path[0] = '\0'; - } out: rcu_read_unlock(); @@ -4529,7 +4535,7 @@ static void get_block_group_info(struct list_head *groups_list, static long btrfs_ioctl_space_info(struct btrfs_fs_info *fs_info, void __user *arg) { - struct btrfs_ioctl_space_args space_args; + struct btrfs_ioctl_space_args space_args = { 0 }; struct btrfs_ioctl_space_info space; struct btrfs_ioctl_space_info *dest; struct btrfs_ioctl_space_info *dest_orig; @@ -4725,6 +4731,11 @@ static long btrfs_ioctl_scrub(struct file *file, void __user *arg) if (IS_ERR(sa)) return PTR_ERR(sa); + if (sa->flags & ~BTRFS_SCRUB_SUPPORTED_FLAGS) { + ret = -EOPNOTSUPP; + goto out; + } + if (!(sa->flags & BTRFS_SCRUB_READONLY)) { ret = mnt_want_write_file(file); if (ret) @@ -5882,7 +5893,7 @@ static int _btrfs_ioctl_send(struct file *file, void __user *argp, bool compat) if (compat) { #if defined(CONFIG_64BIT) && defined(CONFIG_COMPAT) - struct btrfs_ioctl_send_args_32 args32; + struct btrfs_ioctl_send_args_32 args32 = { 0 }; ret = copy_from_user(&args32, argp, sizeof(args32)); if (ret) diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c index 4b217e9a581c..e3de0c4ecbfc 100644 --- a/fs/btrfs/print-tree.c +++ b/fs/btrfs/print-tree.c @@ -109,10 +109,10 @@ static void print_extent_item(struct extent_buffer *eb, int slot, int type) pr_cont("shared data backref parent %llu count %u\n", offset, btrfs_shared_data_ref_count(eb, sref)); /* - * offset is supposed to be a tree block which - * must be aligned to nodesize. + * Offset is supposed to be a tree block which must be + * aligned to sectorsize. */ - if (!IS_ALIGNED(offset, eb->fs_info->nodesize)) + if (!IS_ALIGNED(offset, eb->fs_info->sectorsize)) pr_info( "\t\t\t(parent %llu not aligned to sectorsize %u)\n", offset, eb->fs_info->sectorsize); diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 69b43df186a8..ef95525fa6cd 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1115,7 +1115,9 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info) goto end_trans; } + spin_lock(&fs_info->trans_lock); list_del("a_root->dirty_list); + spin_unlock(&fs_info->trans_lock); btrfs_tree_lock(quota_root->node); clean_tree_block(fs_info, quota_root->node); diff --git a/fs/btrfs/rcu-string.h b/fs/btrfs/rcu-string.h index a97dc74a4d3d..02f15321cecc 100644 --- a/fs/btrfs/rcu-string.h +++ b/fs/btrfs/rcu-string.h @@ -18,7 +18,11 @@ static inline struct rcu_string *rcu_string_strdup(const char *src, gfp_t mask) (len * sizeof(char)), mask); if (!ret) return ret; - strncpy(ret->str, src, len); + /* Warn if the source got unexpectedly truncated. */ + if (WARN_ON(strscpy(ret->str, src, len) < 0)) { + kfree(ret); + return NULL; + } return ret; } diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 06c6a66a991f..3b9318a3d421 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -2341,7 +2341,7 @@ again: list_splice(&reloc_roots, &rc->reloc_roots); if (!err) - btrfs_commit_transaction(trans); + err = btrfs_commit_transaction(trans); else btrfs_end_transaction(trans); return err; @@ -3930,8 +3930,12 @@ int prepare_to_relocate(struct reloc_control *rc) */ return PTR_ERR(trans); } - btrfs_commit_transaction(trans); - return 0; + + ret = btrfs_commit_transaction(trans); + if (ret) + unset_reloc_control(rc); + + return ret; } static noinline_for_stack int relocate_block_group(struct reloc_control *rc) @@ -4097,7 +4101,9 @@ restart: err = PTR_ERR(trans); goto out_free; } - btrfs_commit_transaction(trans); + ret = btrfs_commit_transaction(trans); + if (ret && !err) + err = ret; out_free: btrfs_free_block_rsv(fs_info, rc->block_rsv); btrfs_free_path(path); diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index eb2f8e84ffc9..cb584c044f8a 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -1306,6 +1306,7 @@ static int find_extent_clone(struct send_ctx *sctx, u64 disk_byte; u64 num_bytes; u64 extent_item_pos; + u64 extent_refs; u64 flags = 0; struct btrfs_file_extent_item *fi; struct extent_buffer *eb = path->nodes[0]; @@ -1373,14 +1374,22 @@ static int find_extent_clone(struct send_ctx *sctx, ei = btrfs_item_ptr(tmp_path->nodes[0], tmp_path->slots[0], struct btrfs_extent_item); + extent_refs = btrfs_extent_refs(tmp_path->nodes[0], ei); /* * Backreference walking (iterate_extent_inodes() below) is currently * too expensive when an extent has a large number of references, both * in time spent and used memory. So for now just fallback to write * operations instead of clone operations when an extent has more than * a certain amount of references. + * + * Also, if we have only one reference and only the send root as a clone + * source - meaning no clone roots were given in the struct + * btrfs_ioctl_send_args passed to the send ioctl - then it's our + * reference and there's no point in doing backref walking which is + * expensive, so exit early. */ - if (btrfs_extent_refs(tmp_path->nodes[0], ei) > SEND_MAX_EXTENT_REFS) { + if ((extent_refs == 1 && sctx->clone_roots_cnt == 1) || + extent_refs > SEND_MAX_EXTENT_REFS) { ret = -ENOENT; goto out; } @@ -6817,10 +6826,10 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg) /* * Check that we don't overflow at later allocations, we request * clone_sources_count + 1 items, and compare to unsigned long inside - * access_ok. + * access_ok. Also set an upper limit for allocation size so this can't + * easily exhaust memory. Max number of clone sources is about 200K. */ - if (arg->clone_sources_count > - ULONG_MAX / sizeof(struct clone_root) - 1) { + if (arg->clone_sources_count > SZ_8M / sizeof(struct clone_root)) { ret = -EINVAL; goto out; } @@ -6851,7 +6860,7 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg) sctx->flags = arg->flags; sctx->send_filp = fget(arg->send_fd); - if (!sctx->send_filp) { + if (!sctx->send_filp || !(sctx->send_filp->f_mode & FMODE_WRITE)) { ret = -EBADF; goto out; } diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 521f6c2091ad..a59543951851 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -2196,7 +2196,7 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) * calculated f_bavail. */ if (!mixed && block_rsv->space_info->full && - total_free_meta - thresh < block_rsv->size) + (total_free_meta < thresh || total_free_meta - thresh < block_rsv->size)) buf->f_bavail = 0; buf->f_type = BTRFS_SUPER_MAGIC; diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 049535115c9d..a34c0436ebb1 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -200,10 +200,11 @@ loop: spin_unlock(&fs_info->trans_lock); /* - * If we are ATTACH, we just want to catch the current transaction, - * and commit it. If there is no transaction, just return ENOENT. + * If we are ATTACH or TRANS_JOIN_NOSTART, we just want to catch the + * current transaction, and commit it. If there is no transaction, just + * return ENOENT. */ - if (type == TRANS_ATTACH) + if (type == TRANS_ATTACH || type == TRANS_JOIN_NOSTART) return -ENOENT; /* @@ -703,8 +704,13 @@ btrfs_attach_transaction_barrier(struct btrfs_root *root) trans = start_transaction(root, 0, TRANS_ATTACH, BTRFS_RESERVE_NO_FLUSH, true); - if (trans == ERR_PTR(-ENOENT)) - btrfs_wait_for_commit(root->fs_info, 0); + if (trans == ERR_PTR(-ENOENT)) { + int ret; + + ret = btrfs_wait_for_commit(root->fs_info, 0); + if (ret) + return ERR_PTR(ret); + } return trans; } diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 0fe32c567ed7..23ec766eeb0a 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -4236,7 +4236,7 @@ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans, struct extent_buffer *leaf; int slot; int ins_nr = 0; - int start_slot; + int start_slot = 0; int ret; if (!(inode->flags & BTRFS_INODE_PREALLOC)) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 2b4d33b58a68..ceced5e56c5a 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1418,7 +1418,7 @@ again: goto out; } - while (1) { + while (search_start < search_end) { l = path->nodes[0]; slot = path->slots[0]; if (slot >= btrfs_header_nritems(l)) { @@ -1441,6 +1441,9 @@ again: if (key.type != BTRFS_DEV_EXTENT_KEY) goto next; + if (key.offset > search_end) + break; + if (key.offset > search_start) { hole_size = key.offset - search_start; @@ -1515,6 +1518,7 @@ next: else ret = 0; + ASSERT(max_hole_start + max_hole_size <= search_end); out: btrfs_free_path(path); *start = max_hole_start; @@ -2756,7 +2760,7 @@ static struct extent_map *get_chunk_map(struct btrfs_fs_info *fs_info, return ERR_PTR(-EINVAL); } - if (em->start > logical || em->start + em->len < logical) { + if (em->start > logical || em->start + em->len <= logical) { btrfs_crit(fs_info, "found a bad mapping, wanted %llu-%llu, found %llu-%llu", logical, length, em->start, em->start + em->len); @@ -4102,8 +4106,7 @@ int btrfs_cancel_balance(struct btrfs_fs_info *fs_info) } } - BUG_ON(fs_info->balance_ctl || - test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags)); + ASSERT(!test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags)); atomic_dec(&fs_info->balance_cancel_req); mutex_unlock(&fs_info->balance_mutex); return 0; diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 6443ba1e60eb..fcfba2af5f98 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -1554,6 +1554,7 @@ void ceph_flush_snaps(struct ceph_inode_info *ci, struct inode *inode = &ci->vfs_inode; struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc; struct ceph_mds_session *session = NULL; + bool need_put = false; int mds; dout("ceph_flush_snaps %p\n", inode); @@ -1607,8 +1608,13 @@ out: } /* we flushed them all; remove this inode from the queue */ spin_lock(&mdsc->snap_flush_lock); + if (!list_empty(&ci->i_snap_flush_item)) + need_put = true; list_del_init(&ci->i_snap_flush_item); spin_unlock(&mdsc->snap_flush_lock); + + if (need_put) + iput(inode); } /* @@ -3279,6 +3285,15 @@ static void handle_cap_grant(struct inode *inode, } BUG_ON(cap->issued & ~cap->implemented); + /* don't let check_caps skip sending a response to MDS for revoke msgs */ + if (le32_to_cpu(grant->op) == CEPH_CAP_OP_REVOKE) { + cap->mds_wanted = 0; + if (cap == ci->i_auth_cap) + check_caps = 1; /* check auth cap only */ + else + check_caps = 2; /* check all caps */ + } + if (extra_info->inline_version > 0 && extra_info->inline_version >= ci->i_inline_version) { ci->i_inline_version = extra_info->inline_version; diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 5f041fede7aa..d6f181e3c1ac 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -631,9 +631,7 @@ int ceph_fill_file_size(struct inode *inode, int issued, ci->i_truncate_seq = truncate_seq; /* the MDS should have revoked these caps */ - WARN_ON_ONCE(issued & (CEPH_CAP_FILE_EXCL | - CEPH_CAP_FILE_RD | - CEPH_CAP_FILE_WR | + WARN_ON_ONCE(issued & (CEPH_CAP_FILE_RD | CEPH_CAP_FILE_LAZYIO)); /* * If we hold relevant caps, or in the case where we're diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index a5ef8275440d..4f727f2c98db 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -623,8 +623,10 @@ int __ceph_finish_cap_snap(struct ceph_inode_info *ci, capsnap->size); spin_lock(&mdsc->snap_flush_lock); - if (list_empty(&ci->i_snap_flush_item)) + if (list_empty(&ci->i_snap_flush_item)) { + ihold(inode); list_add_tail(&ci->i_snap_flush_item, &mdsc->snap_flush_list); + } spin_unlock(&mdsc->snap_flush_lock); return 1; /* caller may want to ceph_flush_snaps */ } @@ -976,6 +978,19 @@ skip_inode: continue; adjust_snap_realm_parent(mdsc, child, realm->ino); } + } else { + /* + * In the non-split case both 'num_split_inos' and + * 'num_split_realms' should be 0, making this a no-op. + * However the MDS happens to populate 'split_realms' list + * in one of the UPDATE op cases by mistake. + * + * Skip both lists just in case to ensure that 'p' is + * positioned at the start of realm info, as expected by + * ceph_update_snap_trace(). + */ + p += sizeof(u64) * num_split_inos; + p += sizeof(u64) * num_split_realms; } /* diff --git a/fs/char_dev.c b/fs/char_dev.c index 5fffd5050fb7..2c3d519b21c2 100644 --- a/fs/char_dev.c +++ b/fs/char_dev.c @@ -553,7 +553,7 @@ int cdev_device_add(struct cdev *cdev, struct device *dev) } rc = device_add(dev); - if (rc) + if (rc && dev->devt) cdev_del(cdev); return rc; diff --git a/fs/cifs/cifs_spnego.c b/fs/cifs/cifs_spnego.c index 7f01c6e60791..6eb65988321f 100644 --- a/fs/cifs/cifs_spnego.c +++ b/fs/cifs/cifs_spnego.c @@ -76,8 +76,8 @@ struct key_type cifs_spnego_key_type = { * strlen(";sec=ntlmsspi") */ #define MAX_MECH_STR_LEN 13 -/* strlen of "host=" */ -#define HOST_KEY_LEN 5 +/* strlen of ";host=" */ +#define HOST_KEY_LEN 6 /* strlen of ";ip4=" or ";ip6=" */ #define IP_KEY_LEN 5 diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 52b1524b40cd..7c9e5ed1644b 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -663,11 +663,6 @@ cifs_get_root(struct smb_vol *vol, struct super_block *sb) struct inode *dir = d_inode(dentry); struct dentry *child; - if (!dir) { - dput(dentry); - dentry = ERR_PTR(-ENOENT); - break; - } if (!S_ISDIR(dir->i_mode)) { dput(dentry); dentry = ERR_PTR(-ENOTDIR); @@ -684,7 +679,7 @@ cifs_get_root(struct smb_vol *vol, struct super_block *sb) while (*s && *s != sep) s++; - child = lookup_one_len_unlocked(p, dentry, s - p); + child = lookup_positive_unlocked(p, dentry, s - p); dput(dentry); dentry = child; } while (!IS_ERR(dentry)); @@ -975,6 +970,7 @@ const struct inode_operations cifs_file_inode_ops = { const struct inode_operations cifs_symlink_inode_ops = { .get_link = cifs_get_link, + .setattr = cifs_setattr, .permission = cifs_permission, .listxattr = cifs_listxattr, }; diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index f047e87871a1..c1d5daa4b351 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -121,7 +121,10 @@ extern const struct dentry_operations cifs_ci_dentry_ops; #ifdef CONFIG_CIFS_DFS_UPCALL extern struct vfsmount *cifs_dfs_d_automount(struct path *path); #else -#define cifs_dfs_d_automount NULL +static inline struct vfsmount *cifs_dfs_d_automount(struct path *path) +{ + return ERR_PTR(-EREMOTE); +} #endif /* Functions related to symlinks */ diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index cb70f0c6aa1b..d16fd8d1f291 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -4895,8 +4895,13 @@ CIFSGetDFSRefer(const unsigned int xid, struct cifs_ses *ses, return -ENODEV; getDFSRetry: - rc = smb_init(SMB_COM_TRANSACTION2, 15, ses->tcon_ipc, (void **) &pSMB, - (void **) &pSMBr); + /* + * Use smb_init_no_reconnect() instead of smb_init() as + * CIFSGetDFSRefer() may be called from cifs_reconnect_tcon() and thus + * causing an infinite recursion. + */ + rc = smb_init_no_reconnect(SMB_COM_TRANSACTION2, 15, ses->tcon_ipc, + (void **)&pSMB, (void **)&pSMBr); if (rc) return rc; diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index b5aba1c895cb..37e91f27f49b 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -429,7 +429,8 @@ cifs_reconnect(struct TCP_Server_Info *server) server->ssocket->state, server->ssocket->flags); sock_release(server->ssocket); server->ssocket = NULL; - } + } else if (cifs_rdma_enabled(server)) + smbd_destroy(server); server->sequence_number = 0; server->session_estab = false; kfree(server->session_key.response); @@ -799,10 +800,8 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server) wake_up_all(&server->request_q); /* give those requests time to exit */ msleep(125); - if (cifs_rdma_enabled(server) && server->smbd_conn) { - smbd_destroy(server->smbd_conn); - server->smbd_conn = NULL; - } + if (cifs_rdma_enabled(server)) + smbd_destroy(server); if (server->ssocket) { sock_release(server->ssocket); server->ssocket = NULL; @@ -2940,7 +2939,7 @@ cifs_set_cifscreds(struct smb_vol *vol __attribute__((unused)), static struct cifs_ses * cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb_vol *volume_info) { - int rc = -ENOMEM; + int rc = 0; unsigned int xid; struct cifs_ses *ses; struct sockaddr_in *addr = (struct sockaddr_in *)&server->dstaddr; @@ -2982,6 +2981,8 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb_vol *volume_info) return ses; } + rc = -ENOMEM; + cifs_dbg(FYI, "Existing smb sess not found\n"); ses = sesInfoAlloc(); if (ses == NULL) diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 7b482489bd22..0613b86cc3fd 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -3991,9 +3991,9 @@ static int cifs_readpage_worker(struct file *file, struct page *page, io_error: kunmap(page); - unlock_page(page); read_complete: + unlock_page(page); return rc; } diff --git a/fs/cifs/link.c b/fs/cifs/link.c index 5b1c33d9283a..f590149e21ba 100644 --- a/fs/cifs/link.c +++ b/fs/cifs/link.c @@ -481,6 +481,7 @@ smb3_create_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, oparms.disposition = FILE_CREATE; oparms.fid = &fid; oparms.reconnect = false; + oparms.mode = 0644; rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL, NULL); diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index dd67f56ea61e..c9ebfff5190a 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -338,6 +338,10 @@ checkSMB(char *buf, unsigned int total_read, struct TCP_Server_Info *server) cifs_dbg(VFS, "Length less than smb header size\n"); } return -EIO; + } else if (total_read < sizeof(*smb) + 2 * smb->WordCount) { + cifs_dbg(VFS, "%s: can't read BCC due to invalid WordCount(%u)\n", + __func__, smb->WordCount); + return -EIO; } /* otherwise, there is enough to get to the BCC */ diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index 7177720e822e..d3d5d2c6c401 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -302,6 +302,9 @@ static const bool has_smb2_data_area[NUMBER_OF_SMB2_COMMANDS] = { char * smb2_get_data_area_len(int *off, int *len, struct smb2_sync_hdr *shdr) { + const int max_off = 4096; + const int max_len = 128 * 1024; + *off = 0; *len = 0; @@ -369,29 +372,20 @@ smb2_get_data_area_len(int *off, int *len, struct smb2_sync_hdr *shdr) * Invalid length or offset probably means data area is invalid, but * we have little choice but to ignore the data area in this case. */ - if (*off > 4096) { - cifs_dbg(VFS, "offset %d too large, data area ignored\n", *off); - *len = 0; - *off = 0; - } else if (*off < 0) { - cifs_dbg(VFS, "negative offset %d to data invalid ignore data area\n", - *off); + if (unlikely(*off < 0 || *off > max_off || + *len < 0 || *len > max_len)) { + cifs_dbg(VFS, "%s: invalid data area (off=%d len=%d)\n", + __func__, *off, *len); *off = 0; *len = 0; - } else if (*len < 0) { - cifs_dbg(VFS, "negative data length %d invalid, data area ignored\n", - *len); - *len = 0; - } else if (*len > 128 * 1024) { - cifs_dbg(VFS, "data area larger than 128K: %d\n", *len); + } else if (*off == 0) { *len = 0; } /* return pointer to beginning of data area, ie offset from SMB start */ - if ((*off != 0) && (*len != 0)) + if (*off > 0 && *len > 0) return (char *)shdr + *off; - else - return NULL; + return NULL; } /* diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index f906984eb25b..01ab4496cb89 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -79,6 +79,7 @@ smb2_add_credits(struct TCP_Server_Info *server, const unsigned int add, *val = 65000; /* Don't get near 64K credits, avoid srv bugs */ printk_once(KERN_WARNING "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); @@ -475,7 +476,7 @@ SMB3_request_interfaces(const unsigned int xid, struct cifs_tcon *tcon) if (rc == -EOPNOTSUPP) { cifs_dbg(FYI, "server does not support query network interfaces\n"); - goto out; + ret_data_len = 0; } else if (rc != 0) { cifs_dbg(VFS, "error %d on ioctl to get interface list\n", rc); goto out; @@ -1180,7 +1181,7 @@ smb2_copychunk_range(const unsigned int xid, pcchunk->SourceOffset = cpu_to_le64(src_off); pcchunk->TargetOffset = cpu_to_le64(dest_off); pcchunk->Length = - cpu_to_le32(min_t(u32, len, tcon->max_bytes_chunk)); + cpu_to_le32(min_t(u64, len, tcon->max_bytes_chunk)); /* Request server copy to target from src identified by key */ kfree(retbuf); diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 3485b9bf970f..50c6405befc4 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -3152,12 +3152,15 @@ smb2_readv_callback(struct mid_q_entry *mid) (struct smb2_sync_hdr *)rdata->iov[0].iov_base; unsigned int credits_received = 0; struct smb_rqst rqst = { .rq_iov = &rdata->iov[1], - .rq_nvec = 1, - .rq_pages = rdata->pages, - .rq_offset = rdata->page_offset, - .rq_npages = rdata->nr_pages, - .rq_pagesz = rdata->pagesz, - .rq_tailsz = rdata->tailsz }; + .rq_nvec = 1, }; + + if (rdata->got_bytes) { + rqst.rq_pages = rdata->pages; + rqst.rq_offset = rdata->page_offset; + rqst.rq_npages = rdata->nr_pages; + rqst.rq_pagesz = rdata->pagesz; + rqst.rq_tailsz = rdata->tailsz; + } cifs_dbg(FYI, "%s: mid=%llu state=%d result=%d bytes=%u\n", __func__, mid->mid, mid->mid_state, rdata->result, diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index 8a44d59947b7..dd6e749b2400 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -610,7 +610,7 @@ struct smb2_tree_disconnect_rsp { #define SMB2_CREATE_SD_BUFFER "SecD" /* security descriptor */ #define SMB2_CREATE_DURABLE_HANDLE_REQUEST "DHnQ" #define SMB2_CREATE_DURABLE_HANDLE_RECONNECT "DHnC" -#define SMB2_CREATE_ALLOCATION_SIZE "AISi" +#define SMB2_CREATE_ALLOCATION_SIZE "AlSi" #define SMB2_CREATE_QUERY_MAXIMAL_ACCESS_REQUEST "MxAc" #define SMB2_CREATE_TIMEWARP_REQUEST "TWrp" #define SMB2_CREATE_QUERY_ON_DISK_ID "QFid" diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c index 784628ec4bc4..117dc475bea8 100644 --- a/fs/cifs/smbdirect.c +++ b/fs/cifs/smbdirect.c @@ -320,6 +320,9 @@ static int smbd_conn_upcall( info->transport_status = SMBD_DISCONNECTED; smbd_process_disconnected(info); + wake_up(&info->disconn_wait); + wake_up_interruptible(&info->wait_reassembly_queue); + wake_up_interruptible_all(&info->wait_send_queue); break; default: @@ -703,8 +706,13 @@ static struct rdma_cm_id *smbd_create_id( log_rdma_event(ERR, "rdma_resolve_addr() failed %i\n", rc); goto out; } - wait_for_completion_interruptible_timeout( + rc = wait_for_completion_interruptible_timeout( &info->ri_done, msecs_to_jiffies(RDMA_RESOLVE_TIMEOUT)); + /* e.g. if interrupted returns -ERESTARTSYS */ + if (rc < 0) { + log_rdma_event(ERR, "rdma_resolve_addr timeout rc: %i\n", rc); + goto out; + } rc = info->ri_rc; if (rc) { log_rdma_event(ERR, "rdma_resolve_addr() completed %i\n", rc); @@ -717,8 +725,13 @@ static struct rdma_cm_id *smbd_create_id( log_rdma_event(ERR, "rdma_resolve_route() failed %i\n", rc); goto out; } - wait_for_completion_interruptible_timeout( + rc = wait_for_completion_interruptible_timeout( &info->ri_done, msecs_to_jiffies(RDMA_RESOLVE_TIMEOUT)); + /* e.g. if interrupted returns -ERESTARTSYS */ + if (rc < 0) { + log_rdma_event(ERR, "rdma_resolve_addr timeout rc: %i\n", rc); + goto out; + } rc = info->ri_rc; if (rc) { log_rdma_event(ERR, "rdma_resolve_route() completed %i\n", rc); @@ -1478,21 +1491,102 @@ static void idle_connection_timer(struct work_struct *work) info->keep_alive_interval*HZ); } -/* Destroy this SMBD connection, called from upper layer */ -void smbd_destroy(struct smbd_connection *info) +/* + * Destroy the transport and related RDMA and memory resources + * Need to go through all the pending counters and make sure on one is using + * the transport while it is destroyed + */ +void smbd_destroy(struct TCP_Server_Info *server) { + struct smbd_connection *info = server->smbd_conn; + struct smbd_response *response; + unsigned long flags; + + if (!info) { + log_rdma_event(INFO, "rdma session already destroyed\n"); + return; + } + log_rdma_event(INFO, "destroying rdma session\n"); + if (info->transport_status != SMBD_DISCONNECTED) { + rdma_disconnect(server->smbd_conn->id); + log_rdma_event(INFO, "wait for transport being disconnected\n"); + wait_event( + info->disconn_wait, + info->transport_status == SMBD_DISCONNECTED); + } - /* Kick off the disconnection process */ - smbd_disconnect_rdma_connection(info); + log_rdma_event(INFO, "destroying qp\n"); + ib_drain_qp(info->id->qp); + rdma_destroy_qp(info->id); + + log_rdma_event(INFO, "cancelling idle timer\n"); + cancel_delayed_work_sync(&info->idle_timer_work); + log_rdma_event(INFO, "cancelling send immediate work\n"); + cancel_delayed_work_sync(&info->send_immediate_work); + + log_rdma_event(INFO, "wait for all send posted to IB to finish\n"); + wait_event(info->wait_send_pending, + atomic_read(&info->send_pending) == 0); + wait_event(info->wait_send_payload_pending, + atomic_read(&info->send_payload_pending) == 0); + + /* It's not posssible for upper layer to get to reassembly */ + log_rdma_event(INFO, "drain the reassembly queue\n"); + do { + spin_lock_irqsave(&info->reassembly_queue_lock, flags); + response = _get_first_reassembly(info); + if (response) { + list_del(&response->list); + spin_unlock_irqrestore( + &info->reassembly_queue_lock, flags); + put_receive_buffer(info, response); + } else + spin_unlock_irqrestore( + &info->reassembly_queue_lock, flags); + } while (response); + info->reassembly_data_length = 0; + + log_rdma_event(INFO, "free receive buffers\n"); + wait_event(info->wait_receive_queues, + info->count_receive_queue + info->count_empty_packet_queue + == info->receive_credit_max); + destroy_receive_buffers(info); + + /* + * For performance reasons, memory registration and deregistration + * are not locked by srv_mutex. It is possible some processes are + * blocked on transport srv_mutex while holding memory registration. + * Release the transport srv_mutex to allow them to hit the failure + * path when sending data, and then release memory registartions. + */ + log_rdma_event(INFO, "freeing mr list\n"); + wake_up_interruptible_all(&info->wait_mr); + while (atomic_read(&info->mr_used_count)) { + mutex_unlock(&server->srv_mutex); + msleep(1000); + mutex_lock(&server->srv_mutex); + } + destroy_mr_list(info); - log_rdma_event(INFO, "wait for transport being destroyed\n"); - wait_event(info->wait_destroy, - info->transport_status == SMBD_DESTROYED); + ib_free_cq(info->send_cq); + ib_free_cq(info->recv_cq); + ib_dealloc_pd(info->pd); + rdma_destroy_id(info->id); + + /* free mempools */ + mempool_destroy(info->request_mempool); + kmem_cache_destroy(info->request_cache); + + mempool_destroy(info->response_mempool); + kmem_cache_destroy(info->response_cache); + + info->transport_status = SMBD_DESTROYED; destroy_workqueue(info->workqueue); log_rdma_event(INFO, "rdma session destroyed\n"); kfree(info); + server->smbd_conn = NULL; } /* @@ -1514,17 +1608,9 @@ int smbd_reconnect(struct TCP_Server_Info *server) */ if (server->smbd_conn->transport_status == SMBD_CONNECTED) { log_rdma_event(INFO, "disconnecting transport\n"); - smbd_disconnect_rdma_connection(server->smbd_conn); + smbd_destroy(server); } - /* wait until the transport is destroyed */ - if (!wait_event_timeout(server->smbd_conn->wait_destroy, - server->smbd_conn->transport_status == SMBD_DESTROYED, 5*HZ)) - return -EAGAIN; - - destroy_workqueue(server->smbd_conn->workqueue); - kfree(server->smbd_conn); - create_conn: log_rdma_event(INFO, "creating rdma session\n"); server->smbd_conn = smbd_get_connection( @@ -1741,12 +1827,13 @@ static struct smbd_connection *_smbd_get_connection( conn_param.retry_count = SMBD_CM_RETRY; conn_param.rnr_retry_count = SMBD_CM_RNR_RETRY; conn_param.flow_control = 0; - init_waitqueue_head(&info->wait_destroy); log_rdma_event(INFO, "connecting to IP %pI4 port %d\n", &addr_in->sin_addr, port); init_waitqueue_head(&info->conn_wait); + init_waitqueue_head(&info->disconn_wait); + init_waitqueue_head(&info->wait_reassembly_queue); rc = rdma_connect(info->id, &conn_param); if (rc) { log_rdma_event(ERR, "rdma_connect() failed with %i\n", rc); @@ -1770,8 +1857,6 @@ static struct smbd_connection *_smbd_get_connection( } init_waitqueue_head(&info->wait_send_queue); - init_waitqueue_head(&info->wait_reassembly_queue); - INIT_DELAYED_WORK(&info->idle_timer_work, idle_connection_timer); INIT_DELAYED_WORK(&info->send_immediate_work, send_immediate_work); queue_delayed_work(info->workqueue, &info->idle_timer_work, @@ -1812,7 +1897,8 @@ static struct smbd_connection *_smbd_get_connection( allocate_mr_failed: /* At this point, need to a full transport shutdown */ - smbd_destroy(info); + server->smbd_conn = info; + smbd_destroy(server); return NULL; negotiation_failed: @@ -2378,6 +2464,7 @@ static int allocate_mr_list(struct smbd_connection *info) atomic_set(&info->mr_ready_count, 0); atomic_set(&info->mr_used_count, 0); init_waitqueue_head(&info->wait_for_mr_cleanup); + INIT_WORK(&info->mr_recovery_work, smbd_mr_recovery_work); /* Allocate more MRs (2x) than hardware responder_resources */ for (i = 0; i < info->responder_resources * 2; i++) { smbdirect_mr = kzalloc(sizeof(*smbdirect_mr), GFP_KERNEL); @@ -2406,13 +2493,13 @@ static int allocate_mr_list(struct smbd_connection *info) list_add_tail(&smbdirect_mr->list, &info->mr_list); atomic_inc(&info->mr_ready_count); } - INIT_WORK(&info->mr_recovery_work, smbd_mr_recovery_work); return 0; out: kfree(smbdirect_mr); list_for_each_entry_safe(smbdirect_mr, tmp, &info->mr_list, list) { + list_del(&smbdirect_mr->list); ib_dereg_mr(smbdirect_mr->mr); kfree(smbdirect_mr->sgl); kfree(smbdirect_mr); diff --git a/fs/cifs/smbdirect.h b/fs/cifs/smbdirect.h index b5c240ff2191..b0ca7df41454 100644 --- a/fs/cifs/smbdirect.h +++ b/fs/cifs/smbdirect.h @@ -71,6 +71,7 @@ struct smbd_connection { struct completion ri_done; wait_queue_head_t conn_wait; wait_queue_head_t wait_destroy; + wait_queue_head_t disconn_wait; struct completion negotiate_completion; bool negotiate_done; @@ -288,7 +289,7 @@ struct smbd_connection *smbd_get_connection( /* Reconnect SMBDirect session */ int smbd_reconnect(struct TCP_Server_Info *server); /* Destroy SMBDirect session */ -void smbd_destroy(struct smbd_connection *info); +void smbd_destroy(struct TCP_Server_Info *server); /* Interface for carrying upper layer I/O through send/recv */ int smbd_recv(struct smbd_connection *info, struct msghdr *msg); @@ -331,7 +332,7 @@ struct smbd_connection {}; static inline void *smbd_get_connection( struct TCP_Server_Info *server, struct sockaddr *dstaddr) {return NULL;} static inline int smbd_reconnect(struct TCP_Server_Info *server) {return -1; } -static inline void smbd_destroy(struct smbd_connection *info) {} +static inline void smbd_destroy(struct TCP_Server_Info *server) {} static inline int smbd_recv(struct smbd_connection *info, struct msghdr *msg) {return -1; } static inline int smbd_send(struct TCP_Server_Info *server, int num_rqst, struct smb_rqst *rqst) {return -1; } #endif diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index 4fce1da7db23..acdc802bfe9a 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -18,6 +18,7 @@ #include <linux/slab.h> #include <linux/atomic.h> #include <linux/device.h> +#include <linux/pm_runtime.h> #include <linux/poll.h> #include "internal.h" @@ -330,8 +331,8 @@ ssize_t debugfs_attr_read(struct file *file, char __user *buf, } EXPORT_SYMBOL_GPL(debugfs_attr_read); -ssize_t debugfs_attr_write(struct file *file, const char __user *buf, - size_t len, loff_t *ppos) +static ssize_t debugfs_attr_write_xsigned(struct file *file, const char __user *buf, + size_t len, loff_t *ppos, bool is_signed) { struct dentry *dentry = F_DENTRY(file); ssize_t ret; @@ -339,12 +340,28 @@ ssize_t debugfs_attr_write(struct file *file, const char __user *buf, ret = debugfs_file_get(dentry); if (unlikely(ret)) return ret; - ret = simple_attr_write(file, buf, len, ppos); + if (is_signed) + ret = simple_attr_write_signed(file, buf, len, ppos); + else + ret = simple_attr_write(file, buf, len, ppos); debugfs_file_put(dentry); return ret; } + +ssize_t debugfs_attr_write(struct file *file, const char __user *buf, + size_t len, loff_t *ppos) +{ + return debugfs_attr_write_xsigned(file, buf, len, ppos, false); +} EXPORT_SYMBOL_GPL(debugfs_attr_write); +ssize_t debugfs_attr_write_signed(struct file *file, const char __user *buf, + size_t len, loff_t *ppos) +{ + return debugfs_attr_write_xsigned(file, buf, len, ppos, true); +} +EXPORT_SYMBOL_GPL(debugfs_attr_write_signed); + static struct dentry *debugfs_create_mode_unsafe(const char *name, umode_t mode, struct dentry *parent, void *value, const struct file_operations *fops, @@ -742,11 +759,11 @@ static int debugfs_atomic_t_get(void *data, u64 *val) *val = atomic_read((atomic_t *)data); return 0; } -DEFINE_DEBUGFS_ATTRIBUTE(fops_atomic_t, debugfs_atomic_t_get, +DEFINE_DEBUGFS_ATTRIBUTE_SIGNED(fops_atomic_t, debugfs_atomic_t_get, debugfs_atomic_t_set, "%lld\n"); -DEFINE_DEBUGFS_ATTRIBUTE(fops_atomic_t_ro, debugfs_atomic_t_get, NULL, +DEFINE_DEBUGFS_ATTRIBUTE_SIGNED(fops_atomic_t_ro, debugfs_atomic_t_get, NULL, "%lld\n"); -DEFINE_DEBUGFS_ATTRIBUTE(fops_atomic_t_wo, NULL, debugfs_atomic_t_set, +DEFINE_DEBUGFS_ATTRIBUTE_SIGNED(fops_atomic_t_wo, NULL, debugfs_atomic_t_set, "%lld\n"); /** @@ -1068,7 +1085,14 @@ static int debugfs_show_regset32(struct seq_file *s, void *data) { struct debugfs_regset32 *regset = s->private; + if (regset->dev) + pm_runtime_get_sync(regset->dev); + debugfs_print_regs32(s, regset->regs, regset->nregs, regset->base, ""); + + if (regset->dev) + pm_runtime_put(regset->dev); + return 0; } diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 4661ecaf6741..1e4ae78f64a8 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -275,13 +275,9 @@ struct dentry *debugfs_lookup(const char *name, struct dentry *parent) if (!parent) parent = debugfs_mount->mnt_root; - dentry = lookup_one_len_unlocked(name, parent, strlen(name)); + dentry = lookup_positive_unlocked(name, parent, strlen(name)); if (IS_ERR(dentry)) return NULL; - if (!d_really_is_positive(dentry)) { - dput(dentry); - return NULL; - } return dentry; } EXPORT_SYMBOL_GPL(debugfs_lookup); diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c index d4e204473e76..0864481d8551 100644 --- a/fs/dlm/lock.c +++ b/fs/dlm/lock.c @@ -1858,7 +1858,7 @@ static void del_timeout(struct dlm_lkb *lkb) void dlm_scan_timeout(struct dlm_ls *ls) { struct dlm_rsb *r; - struct dlm_lkb *lkb; + struct dlm_lkb *lkb = NULL, *iter; int do_cancel, do_warn; s64 wait_us; @@ -1869,27 +1869,28 @@ void dlm_scan_timeout(struct dlm_ls *ls) do_cancel = 0; do_warn = 0; mutex_lock(&ls->ls_timeout_mutex); - list_for_each_entry(lkb, &ls->ls_timeout, lkb_time_list) { + list_for_each_entry(iter, &ls->ls_timeout, lkb_time_list) { wait_us = ktime_to_us(ktime_sub(ktime_get(), - lkb->lkb_timestamp)); + iter->lkb_timestamp)); - if ((lkb->lkb_exflags & DLM_LKF_TIMEOUT) && - wait_us >= (lkb->lkb_timeout_cs * 10000)) + if ((iter->lkb_exflags & DLM_LKF_TIMEOUT) && + wait_us >= (iter->lkb_timeout_cs * 10000)) do_cancel = 1; - if ((lkb->lkb_flags & DLM_IFL_WATCH_TIMEWARN) && + if ((iter->lkb_flags & DLM_IFL_WATCH_TIMEWARN) && wait_us >= dlm_config.ci_timewarn_cs * 10000) do_warn = 1; if (!do_cancel && !do_warn) continue; - hold_lkb(lkb); + hold_lkb(iter); + lkb = iter; break; } mutex_unlock(&ls->ls_timeout_mutex); - if (!do_cancel && !do_warn) + if (!lkb) break; r = lkb->lkb_resource; @@ -5243,21 +5244,18 @@ void dlm_recover_waiters_pre(struct dlm_ls *ls) static struct dlm_lkb *find_resend_waiter(struct dlm_ls *ls) { - struct dlm_lkb *lkb; - int found = 0; + struct dlm_lkb *lkb = NULL, *iter; mutex_lock(&ls->ls_waiters_mutex); - list_for_each_entry(lkb, &ls->ls_waiters, lkb_wait_reply) { - if (lkb->lkb_flags & DLM_IFL_RESEND) { - hold_lkb(lkb); - found = 1; + list_for_each_entry(iter, &ls->ls_waiters, lkb_wait_reply) { + if (iter->lkb_flags & DLM_IFL_RESEND) { + hold_lkb(iter); + lkb = iter; break; } } mutex_unlock(&ls->ls_waiters_mutex); - if (!found) - lkb = NULL; return lkb; } @@ -5916,37 +5914,36 @@ int dlm_user_adopt_orphan(struct dlm_ls *ls, struct dlm_user_args *ua_tmp, int mode, uint32_t flags, void *name, unsigned int namelen, unsigned long timeout_cs, uint32_t *lkid) { - struct dlm_lkb *lkb; + struct dlm_lkb *lkb = NULL, *iter; struct dlm_user_args *ua; int found_other_mode = 0; - int found = 0; int rv = 0; mutex_lock(&ls->ls_orphans_mutex); - list_for_each_entry(lkb, &ls->ls_orphans, lkb_ownqueue) { - if (lkb->lkb_resource->res_length != namelen) + list_for_each_entry(iter, &ls->ls_orphans, lkb_ownqueue) { + if (iter->lkb_resource->res_length != namelen) continue; - if (memcmp(lkb->lkb_resource->res_name, name, namelen)) + if (memcmp(iter->lkb_resource->res_name, name, namelen)) continue; - if (lkb->lkb_grmode != mode) { + if (iter->lkb_grmode != mode) { found_other_mode = 1; continue; } - found = 1; - list_del_init(&lkb->lkb_ownqueue); - lkb->lkb_flags &= ~DLM_IFL_ORPHAN; - *lkid = lkb->lkb_id; + lkb = iter; + list_del_init(&iter->lkb_ownqueue); + iter->lkb_flags &= ~DLM_IFL_ORPHAN; + *lkid = iter->lkb_id; break; } mutex_unlock(&ls->ls_orphans_mutex); - if (!found && found_other_mode) { + if (!lkb && found_other_mode) { rv = -EAGAIN; goto out; } - if (!found) { + if (!lkb) { rv = -ENOENT; goto out; } diff --git a/fs/dlm/netlink.c b/fs/dlm/netlink.c index 43a96c330570..ea50f59610e5 100644 --- a/fs/dlm/netlink.c +++ b/fs/dlm/netlink.c @@ -115,7 +115,7 @@ static void fill_data(struct dlm_lock_data *data, struct dlm_lkb *lkb) void dlm_timeout_warn(struct dlm_lkb *lkb) { - struct sk_buff *uninitialized_var(send_skb); + struct sk_buff *send_skb; struct dlm_lock_data *data; size_t size; int rv; diff --git a/fs/dlm/plock.c b/fs/dlm/plock.c index e0c05e08d8bf..c6079f6c6a79 100644 --- a/fs/dlm/plock.c +++ b/fs/dlm/plock.c @@ -22,20 +22,20 @@ static struct list_head recv_list; static wait_queue_head_t send_wq; static wait_queue_head_t recv_wq; -struct plock_op { - struct list_head list; - int done; - struct dlm_plock_info info; - int (*callback)(struct file_lock *fl, int result); -}; - -struct plock_xop { - struct plock_op xop; +struct plock_async_data { void *fl; void *file; struct file_lock flc; + int (*callback)(struct file_lock *fl, int result); }; +struct plock_op { + struct list_head list; + int done; + struct dlm_plock_info info; + /* if set indicates async handling */ + struct plock_async_data *data; +}; static inline void set_version(struct dlm_plock_info *info) { @@ -61,6 +61,12 @@ static int check_version(struct dlm_plock_info *info) return 0; } +static void dlm_release_plock_op(struct plock_op *op) +{ + kfree(op->data); + kfree(op); +} + static void send_op(struct plock_op *op) { set_version(&op->info); @@ -77,8 +83,7 @@ static void send_op(struct plock_op *op) abandoned waiter. So, we have to insert the unlock-close when the lock call is interrupted. */ -static void do_unlock_close(struct dlm_ls *ls, u64 number, - struct file *file, struct file_lock *fl) +static void do_unlock_close(const struct dlm_plock_info *info) { struct plock_op *op; @@ -87,15 +92,12 @@ static void do_unlock_close(struct dlm_ls *ls, u64 number, return; op->info.optype = DLM_PLOCK_OP_UNLOCK; - op->info.pid = fl->fl_pid; - op->info.fsid = ls->ls_global_id; - op->info.number = number; + op->info.pid = info->pid; + op->info.fsid = info->fsid; + op->info.number = info->number; op->info.start = 0; op->info.end = OFFSET_MAX; - if (fl->fl_lmops && fl->fl_lmops->lm_grant) - op->info.owner = (__u64) fl->fl_pid; - else - op->info.owner = (__u64)(long) fl->fl_owner; + op->info.owner = info->owner; op->info.flags |= DLM_PLOCK_FL_CLOSE; send_op(op); @@ -104,22 +106,21 @@ static void do_unlock_close(struct dlm_ls *ls, u64 number, int dlm_posix_lock(dlm_lockspace_t *lockspace, u64 number, struct file *file, int cmd, struct file_lock *fl) { + struct plock_async_data *op_data; struct dlm_ls *ls; struct plock_op *op; - struct plock_xop *xop; int rv; ls = dlm_find_lockspace_local(lockspace); if (!ls) return -EINVAL; - xop = kzalloc(sizeof(*xop), GFP_NOFS); - if (!xop) { + op = kzalloc(sizeof(*op), GFP_NOFS); + if (!op) { rv = -ENOMEM; goto out; } - op = &xop->xop; op->info.optype = DLM_PLOCK_OP_LOCK; op->info.pid = fl->fl_pid; op->info.ex = (fl->fl_type == F_WRLCK); @@ -128,35 +129,45 @@ int dlm_posix_lock(dlm_lockspace_t *lockspace, u64 number, struct file *file, op->info.number = number; op->info.start = fl->fl_start; op->info.end = fl->fl_end; + /* async handling */ if (fl->fl_lmops && fl->fl_lmops->lm_grant) { + op_data = kzalloc(sizeof(*op_data), GFP_NOFS); + if (!op_data) { + dlm_release_plock_op(op); + rv = -ENOMEM; + goto out; + } + /* fl_owner is lockd which doesn't distinguish processes on the nfs client */ op->info.owner = (__u64) fl->fl_pid; - op->callback = fl->fl_lmops->lm_grant; - locks_init_lock(&xop->flc); - locks_copy_lock(&xop->flc, fl); - xop->fl = fl; - xop->file = file; + op_data->callback = fl->fl_lmops->lm_grant; + locks_init_lock(&op_data->flc); + locks_copy_lock(&op_data->flc, fl); + op_data->fl = fl; + op_data->file = file; + + op->data = op_data; + + send_op(op); + rv = FILE_LOCK_DEFERRED; + goto out; } else { op->info.owner = (__u64)(long) fl->fl_owner; } send_op(op); - if (!op->callback) { - rv = wait_event_interruptible(recv_wq, (op->done != 0)); - if (rv == -ERESTARTSYS) { - log_debug(ls, "dlm_posix_lock: wait killed %llx", - (unsigned long long)number); - spin_lock(&ops_lock); - list_del(&op->list); - spin_unlock(&ops_lock); - kfree(xop); - do_unlock_close(ls, number, file, fl); - goto out; - } - } else { - rv = FILE_LOCK_DEFERRED; + rv = wait_event_killable(recv_wq, (op->done != 0)); + if (rv == -ERESTARTSYS) { + spin_lock(&ops_lock); + list_del(&op->list); + spin_unlock(&ops_lock); + log_debug(ls, "%s: wait interrupted %x %llx pid %d", + __func__, ls->ls_global_id, + (unsigned long long)number, op->info.pid); + dlm_release_plock_op(op); + do_unlock_close(&op->info); goto out; } @@ -176,7 +187,7 @@ int dlm_posix_lock(dlm_lockspace_t *lockspace, u64 number, struct file *file, (unsigned long long)number); } - kfree(xop); + dlm_release_plock_op(op); out: dlm_put_lockspace(ls); return rv; @@ -186,11 +197,11 @@ EXPORT_SYMBOL_GPL(dlm_posix_lock); /* Returns failure iff a successful lock operation should be canceled */ static int dlm_plock_callback(struct plock_op *op) { + struct plock_async_data *op_data = op->data; struct file *file; struct file_lock *fl; struct file_lock *flc; int (*notify)(struct file_lock *fl, int result) = NULL; - struct plock_xop *xop = (struct plock_xop *)op; int rv = 0; spin_lock(&ops_lock); @@ -202,10 +213,10 @@ static int dlm_plock_callback(struct plock_op *op) spin_unlock(&ops_lock); /* check if the following 2 are still valid or make a copy */ - file = xop->file; - flc = &xop->flc; - fl = xop->fl; - notify = op->callback; + file = op_data->file; + flc = &op_data->flc; + fl = op_data->fl; + notify = op_data->callback; if (op->info.rv) { notify(fl, op->info.rv); @@ -236,7 +247,7 @@ static int dlm_plock_callback(struct plock_op *op) } out: - kfree(xop); + dlm_release_plock_op(op); return rv; } @@ -306,7 +317,7 @@ int dlm_posix_unlock(dlm_lockspace_t *lockspace, u64 number, struct file *file, rv = 0; out_free: - kfree(op); + dlm_release_plock_op(op); out: dlm_put_lockspace(ls); fl->fl_flags = fl_flags; @@ -366,13 +377,15 @@ int dlm_posix_get(dlm_lockspace_t *lockspace, u64 number, struct file *file, locks_init_lock(fl); fl->fl_type = (op->info.ex) ? F_WRLCK : F_RDLCK; fl->fl_flags = FL_POSIX; - fl->fl_pid = -op->info.pid; + fl->fl_pid = op->info.pid; + if (op->info.nodeid != dlm_our_nodeid()) + fl->fl_pid = -fl->fl_pid; fl->fl_start = op->info.start; fl->fl_end = op->info.end; rv = 0; } - kfree(op); + dlm_release_plock_op(op); out: dlm_put_lockspace(ls); return rv; @@ -395,7 +408,7 @@ static ssize_t dev_read(struct file *file, char __user *u, size_t count, if (op->info.flags & DLM_PLOCK_FL_CLOSE) list_del(&op->list); else - list_move(&op->list, &recv_list); + list_move_tail(&op->list, &recv_list); memcpy(&info, &op->info, sizeof(info)); } spin_unlock(&ops_lock); @@ -408,7 +421,7 @@ static ssize_t dev_read(struct file *file, char __user *u, size_t count, (the process did not make an unlock call). */ if (op->info.flags & DLM_PLOCK_FL_CLOSE) - kfree(op); + dlm_release_plock_op(op); if (copy_to_user(u, &info, sizeof(info))) return -EFAULT; @@ -420,9 +433,9 @@ static ssize_t dev_read(struct file *file, char __user *u, size_t count, static ssize_t dev_write(struct file *file, const char __user *u, size_t count, loff_t *ppos) { + struct plock_op *op = NULL, *iter; struct dlm_plock_info info; - struct plock_op *op; - int found = 0, do_callback = 0; + int do_callback = 0; if (count != sizeof(info)) return -EINVAL; @@ -433,31 +446,63 @@ static ssize_t dev_write(struct file *file, const char __user *u, size_t count, if (check_version(&info)) return -EINVAL; + /* + * The results for waiting ops (SETLKW) can be returned in any + * order, so match all fields to find the op. The results for + * non-waiting ops are returned in the order that they were sent + * to userspace, so match the result with the first non-waiting op. + */ spin_lock(&ops_lock); - list_for_each_entry(op, &recv_list, list) { - if (op->info.fsid == info.fsid && - op->info.number == info.number && - op->info.owner == info.owner) { - list_del_init(&op->list); - memcpy(&op->info, &info, sizeof(info)); - if (op->callback) - do_callback = 1; - else - op->done = 1; - found = 1; - break; + if (info.wait) { + list_for_each_entry(iter, &recv_list, list) { + if (iter->info.fsid == info.fsid && + iter->info.number == info.number && + iter->info.owner == info.owner && + iter->info.pid == info.pid && + iter->info.start == info.start && + iter->info.end == info.end && + iter->info.ex == info.ex && + iter->info.wait) { + op = iter; + break; + } } + } else { + list_for_each_entry(iter, &recv_list, list) { + if (!iter->info.wait && + iter->info.fsid == info.fsid) { + op = iter; + break; + } + } + } + + if (op) { + /* Sanity check that op and info match. */ + if (info.wait) + WARN_ON(op->info.optype != DLM_PLOCK_OP_LOCK); + else + WARN_ON(op->info.number != info.number || + op->info.owner != info.owner || + op->info.optype != info.optype); + + list_del_init(&op->list); + memcpy(&op->info, &info, sizeof(info)); + if (op->data) + do_callback = 1; + else + op->done = 1; } spin_unlock(&ops_lock); - if (found) { + if (op) { if (do_callback) dlm_plock_callback(op); else wake_up(&recv_wq); } else - log_print("dev_write no op %x %llx", info.fsid, - (unsigned long long)info.number); + log_print("%s: no op %x %llx", __func__, + info.fsid, (unsigned long long)info.number); return count; } diff --git a/fs/dlm/recover.c b/fs/dlm/recover.c index ce2aa54ca2e2..98b710cc9cf3 100644 --- a/fs/dlm/recover.c +++ b/fs/dlm/recover.c @@ -734,10 +734,9 @@ void dlm_recovered_lock(struct dlm_rsb *r) static void recover_lvb(struct dlm_rsb *r) { - struct dlm_lkb *lkb, *high_lkb = NULL; + struct dlm_lkb *big_lkb = NULL, *iter, *high_lkb = NULL; uint32_t high_seq = 0; int lock_lvb_exists = 0; - int big_lock_exists = 0; int lvblen = r->res_ls->ls_lvblen; if (!rsb_flag(r, RSB_NEW_MASTER2) && @@ -753,37 +752,37 @@ static void recover_lvb(struct dlm_rsb *r) /* we are the new master, so figure out if VALNOTVALID should be set, and set the rsb lvb from the best lkb available. */ - list_for_each_entry(lkb, &r->res_grantqueue, lkb_statequeue) { - if (!(lkb->lkb_exflags & DLM_LKF_VALBLK)) + list_for_each_entry(iter, &r->res_grantqueue, lkb_statequeue) { + if (!(iter->lkb_exflags & DLM_LKF_VALBLK)) continue; lock_lvb_exists = 1; - if (lkb->lkb_grmode > DLM_LOCK_CR) { - big_lock_exists = 1; + if (iter->lkb_grmode > DLM_LOCK_CR) { + big_lkb = iter; goto setflag; } - if (((int)lkb->lkb_lvbseq - (int)high_seq) >= 0) { - high_lkb = lkb; - high_seq = lkb->lkb_lvbseq; + if (((int)iter->lkb_lvbseq - (int)high_seq) >= 0) { + high_lkb = iter; + high_seq = iter->lkb_lvbseq; } } - list_for_each_entry(lkb, &r->res_convertqueue, lkb_statequeue) { - if (!(lkb->lkb_exflags & DLM_LKF_VALBLK)) + list_for_each_entry(iter, &r->res_convertqueue, lkb_statequeue) { + if (!(iter->lkb_exflags & DLM_LKF_VALBLK)) continue; lock_lvb_exists = 1; - if (lkb->lkb_grmode > DLM_LOCK_CR) { - big_lock_exists = 1; + if (iter->lkb_grmode > DLM_LOCK_CR) { + big_lkb = iter; goto setflag; } - if (((int)lkb->lkb_lvbseq - (int)high_seq) >= 0) { - high_lkb = lkb; - high_seq = lkb->lkb_lvbseq; + if (((int)iter->lkb_lvbseq - (int)high_seq) >= 0) { + high_lkb = iter; + high_seq = iter->lkb_lvbseq; } } @@ -792,7 +791,7 @@ static void recover_lvb(struct dlm_rsb *r) goto out; /* lvb is invalidated if only NL/CR locks remain */ - if (!big_lock_exists) + if (!big_lkb) rsb_set_flag(r, RSB_VALNOTVALID); if (!r->res_lvbptr) { @@ -801,9 +800,9 @@ static void recover_lvb(struct dlm_rsb *r) goto out; } - if (big_lock_exists) { - r->res_lvbseq = lkb->lkb_lvbseq; - memcpy(r->res_lvbptr, lkb->lkb_lvbptr, lvblen); + if (big_lkb) { + r->res_lvbseq = big_lkb->lkb_lvbseq; + memcpy(r->res_lvbptr, big_lkb->lkb_lvbptr, lvblen); } else if (high_lkb) { r->res_lvbseq = high_lkb->lkb_lvbseq; memcpy(r->res_lvbptr, high_lkb->lkb_lvbptr, lvblen); diff --git a/fs/eventfd.c b/fs/eventfd.c index ce1d1711fbba..66864100b823 100644 --- a/fs/eventfd.c +++ b/fs/eventfd.c @@ -174,11 +174,14 @@ static __poll_t eventfd_poll(struct file *file, poll_table *wait) return events; } -static void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt) +void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt) { - *cnt = (ctx->flags & EFD_SEMAPHORE) ? 1 : ctx->count; + lockdep_assert_held(&ctx->wqh.lock); + + *cnt = ((ctx->flags & EFD_SEMAPHORE) && ctx->count) ? 1 : ctx->count; ctx->count -= *cnt; } +EXPORT_SYMBOL_GPL(eventfd_ctx_do_read); /** * eventfd_ctx_remove_wait_queue - Read the current counter and removes wait queue. diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index 00e759f05161..598dc2874808 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -68,10 +68,7 @@ struct mb_cache; * second extended-fs super-block data in memory */ struct ext2_sb_info { - unsigned long s_frag_size; /* Size of a fragment in bytes */ - unsigned long s_frags_per_block;/* Number of fragments per block */ unsigned long s_inodes_per_block;/* Number of inodes per block */ - unsigned long s_frags_per_group;/* Number of fragments in a group */ unsigned long s_blocks_per_group;/* Number of blocks in a group */ unsigned long s_inodes_per_group;/* Number of inodes in a group */ unsigned long s_itb_per_group; /* Number of inode table blocks per group */ @@ -177,6 +174,7 @@ static inline struct ext2_sb_info *EXT2_SB(struct super_block *sb) #define EXT2_MIN_BLOCK_SIZE 1024 #define EXT2_MAX_BLOCK_SIZE 4096 #define EXT2_MIN_BLOCK_LOG_SIZE 10 +#define EXT2_MAX_BLOCK_LOG_SIZE 16 #define EXT2_BLOCK_SIZE(s) ((s)->s_blocksize) #define EXT2_ADDR_PER_BLOCK(s) (EXT2_BLOCK_SIZE(s) / sizeof (__u32)) #define EXT2_BLOCK_SIZE_BITS(s) ((s)->s_blocksize_bits) @@ -185,15 +183,6 @@ static inline struct ext2_sb_info *EXT2_SB(struct super_block *sb) #define EXT2_FIRST_INO(s) (EXT2_SB(s)->s_first_ino) /* - * Macro-instructions used to manage fragments - */ -#define EXT2_MIN_FRAG_SIZE 1024 -#define EXT2_MAX_FRAG_SIZE 4096 -#define EXT2_MIN_FRAG_LOG_SIZE 10 -#define EXT2_FRAG_SIZE(s) (EXT2_SB(s)->s_frag_size) -#define EXT2_FRAGS_PER_BLOCK(s) (EXT2_SB(s)->s_frags_per_block) - -/* * Structure of a blocks group descriptor */ struct ext2_group_desc diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 44a1f356aca2..5c0af53f2e8f 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -691,10 +691,9 @@ static int ext2_setup_super (struct super_block * sb, es->s_max_mnt_count = cpu_to_le16(EXT2_DFL_MAX_MNT_COUNT); le16_add_cpu(&es->s_mnt_count, 1); if (test_opt (sb, DEBUG)) - ext2_msg(sb, KERN_INFO, "%s, %s, bs=%lu, fs=%lu, gc=%lu, " + ext2_msg(sb, KERN_INFO, "%s, %s, bs=%lu, gc=%lu, " "bpg=%lu, ipg=%lu, mo=%04lx]", EXT2FS_VERSION, EXT2FS_DATE, sb->s_blocksize, - sbi->s_frag_size, sbi->s_groups_count, EXT2_BLOCKS_PER_GROUP(sb), EXT2_INODES_PER_GROUP(sb), @@ -978,6 +977,13 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount; } + if (le32_to_cpu(es->s_log_block_size) > + (EXT2_MAX_BLOCK_LOG_SIZE - BLOCK_SIZE_BITS)) { + ext2_msg(sb, KERN_ERR, + "Invalid log block size: %u", + le32_to_cpu(es->s_log_block_size)); + goto failed_mount; + } blocksize = BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size); if (sbi->s_mount_opt & EXT2_MOUNT_DAX) { @@ -1033,14 +1039,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) } } - sbi->s_frag_size = EXT2_MIN_FRAG_SIZE << - le32_to_cpu(es->s_log_frag_size); - if (sbi->s_frag_size == 0) - goto cantfind_ext2; - sbi->s_frags_per_block = sb->s_blocksize / sbi->s_frag_size; - sbi->s_blocks_per_group = le32_to_cpu(es->s_blocks_per_group); - sbi->s_frags_per_group = le32_to_cpu(es->s_frags_per_group); sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group); if (EXT2_INODE_SIZE(sb) == 0) @@ -1068,11 +1067,10 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount; } - if (sb->s_blocksize != sbi->s_frag_size) { + if (es->s_log_frag_size != es->s_log_block_size) { ext2_msg(sb, KERN_ERR, - "error: fragsize %lu != blocksize %lu" - "(not supported yet)", - sbi->s_frag_size, sb->s_blocksize); + "error: fragsize log %u != blocksize log %u", + le32_to_cpu(es->s_log_frag_size), sb->s_blocksize_bits); goto failed_mount; } @@ -1082,12 +1080,6 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) sbi->s_blocks_per_group); goto failed_mount; } - if (sbi->s_frags_per_group > sb->s_blocksize * 8) { - ext2_msg(sb, KERN_ERR, - "error: #fragments per group too big: %lu", - sbi->s_frags_per_group); - goto failed_mount; - } if (sbi->s_inodes_per_group < sbi->s_inodes_per_block || sbi->s_inodes_per_group > sb->s_blocksize * 8) { ext2_msg(sb, KERN_ERR, diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c index bd1d68ff3a9f..437175bce22e 100644 --- a/fs/ext2/xattr.c +++ b/fs/ext2/xattr.c @@ -664,10 +664,10 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh, /* We need to allocate a new block */ ext2_fsblk_t goal = ext2_group_first_block_no(sb, EXT2_I(inode)->i_block_group); - int block = ext2_new_block(inode, goal, &error); + ext2_fsblk_t block = ext2_new_block(inode, goal, &error); if (error) goto cleanup; - ea_idebug(inode, "creating block %d", block); + ea_idebug(inode, "creating block %lu", block); new_bh = sb_getblk(sb, block); if (unlikely(!new_bh)) { diff --git a/fs/ext4/acl.h b/fs/ext4/acl.h index 9b63f5416a2f..7f3b25b3fa6d 100644 --- a/fs/ext4/acl.h +++ b/fs/ext4/acl.h @@ -67,6 +67,11 @@ extern int ext4_init_acl(handle_t *, struct inode *, struct inode *); static inline int ext4_init_acl(handle_t *handle, struct inode *inode, struct inode *dir) { + /* usually, the umask is applied by posix_acl_create(), but if + ext4 ACL support is disabled at compile time, we need to do + it here, because posix_acl_create() will never be called */ + inode->i_mode &= ~current_umask(); + return 0; } #endif /* CONFIG_EXT4_FS_POSIX_ACL */ diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index f9645de9d04c..9761aeb4b224 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -303,6 +303,22 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb, return desc; } +static ext4_fsblk_t ext4_valid_block_bitmap_padding(struct super_block *sb, + ext4_group_t block_group, + struct buffer_head *bh) +{ + ext4_grpblk_t next_zero_bit; + unsigned long bitmap_size = sb->s_blocksize * 8; + unsigned int offset = num_clusters_in_group(sb, block_group); + + if (bitmap_size <= offset) + return 0; + + next_zero_bit = ext4_find_next_zero_bit(bh->b_data, bitmap_size, offset); + + return (next_zero_bit < bitmap_size ? next_zero_bit : 0); +} + /* * Return the block number which was discovered to be invalid, or 0 if * the block bitmap is valid. @@ -395,6 +411,15 @@ static int ext4_validate_block_bitmap(struct super_block *sb, EXT4_GROUP_INFO_BBITMAP_CORRUPT); return -EFSCORRUPTED; } + blk = ext4_valid_block_bitmap_padding(sb, block_group, bh); + if (unlikely(blk != 0)) { + ext4_unlock_group(sb, block_group); + ext4_error(sb, "bg %u: block %llu: padding at end of block bitmap is not set", + block_group, blk); + ext4_mark_group_bitmap_corrupted(sb, block_group, + EXT4_GROUP_INFO_BBITMAP_CORRUPT); + return -EFSCORRUPTED; + } set_buffer_verified(bh); verified: ext4_unlock_group(sb, block_group); diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 6938dff9f04b..fa2579abea7d 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -503,7 +503,7 @@ enum { * * It's not paranoia if the Murphy's Law really *is* out to get you. :-) */ -#define TEST_FLAG_VALUE(FLAG) (EXT4_##FLAG##_FL == (1 << EXT4_INODE_##FLAG)) +#define TEST_FLAG_VALUE(FLAG) (EXT4_##FLAG##_FL == (1U << EXT4_INODE_##FLAG)) #define CHECK_FLAG_VALUE(FLAG) BUILD_BUG_ON(!TEST_FLAG_VALUE(FLAG)) static inline void ext4_check_flag_values(void) @@ -929,11 +929,13 @@ do { \ * where the second inode has larger inode number * than the first * I_DATA_SEM_QUOTA - Used for quota inodes only + * I_DATA_SEM_EA - Used for ea_inodes only */ enum { I_DATA_SEM_NORMAL = 0, I_DATA_SEM_OTHER, I_DATA_SEM_QUOTA, + I_DATA_SEM_EA }; @@ -1410,7 +1412,7 @@ struct ext4_sb_info { unsigned long s_commit_interval; u32 s_max_batch_time; u32 s_min_batch_time; - struct block_device *journal_bdev; + struct block_device *s_journal_bdev; #ifdef CONFIG_QUOTA /* Names of quota files with journalled quota */ char __rcu *s_qf_names[EXT4_MAXQUOTAS]; @@ -1498,7 +1500,7 @@ struct ext4_sb_info { struct task_struct *s_mmp_tsk; /* record the last minlen when FITRIM is called. */ - atomic_t s_last_trim_minblks; + unsigned long s_last_trim_minblks; /* Reference to checksum algorithm driver via cryptoapi */ struct crypto_shash *s_chksum_driver; diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 6c492fca60c4..d931252b7d0d 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -997,6 +997,11 @@ static int ext4_ext_insert_index(handle_t *handle, struct inode *inode, ix = curp->p_idx; } + if (unlikely(ix > EXT_MAX_INDEX(curp->p_hdr))) { + EXT4_ERROR_INODE(inode, "ix > EXT_MAX_INDEX!"); + return -EFSCORRUPTED; + } + len = EXT_LAST_INDEX(curp->p_hdr) - ix + 1; BUG_ON(len < 0); if (len > 0) { @@ -1006,11 +1011,6 @@ static int ext4_ext_insert_index(handle_t *handle, struct inode *inode, memmove(ix + 1, ix, len * sizeof(struct ext4_extent_idx)); } - if (unlikely(ix > EXT_MAX_INDEX(curp->p_hdr))) { - EXT4_ERROR_INODE(inode, "ix > EXT_MAX_INDEX!"); - return -EFSCORRUPTED; - } - ix->ei_block = cpu_to_le32(logical); ext4_idx_store_pblock(ix, ptr); le16_add_cpu(&curp->p_hdr->eh_entries, 1); diff --git a/fs/ext4/fsmap.c b/fs/ext4/fsmap.c index 6f3f245f3a80..69c76327792e 100644 --- a/fs/ext4/fsmap.c +++ b/fs/ext4/fsmap.c @@ -486,6 +486,8 @@ static int ext4_getfsmap_datadev(struct super_block *sb, keys[0].fmr_physical = bofs; if (keys[1].fmr_physical >= eofs) keys[1].fmr_physical = eofs - 1; + if (keys[1].fmr_physical < keys[0].fmr_physical) + return 0; start_fsb = keys[0].fmr_physical; end_fsb = keys[1].fmr_physical; @@ -574,8 +576,8 @@ static bool ext4_getfsmap_is_valid_device(struct super_block *sb, if (fm->fmr_device == 0 || fm->fmr_device == UINT_MAX || fm->fmr_device == new_encode_dev(sb->s_bdev->bd_dev)) return true; - if (EXT4_SB(sb)->journal_bdev && - fm->fmr_device == new_encode_dev(EXT4_SB(sb)->journal_bdev->bd_dev)) + if (EXT4_SB(sb)->s_journal_bdev && + fm->fmr_device == new_encode_dev(EXT4_SB(sb)->s_journal_bdev->bd_dev)) return true; return false; } @@ -645,9 +647,9 @@ int ext4_getfsmap(struct super_block *sb, struct ext4_fsmap_head *head, memset(handlers, 0, sizeof(handlers)); handlers[0].gfd_dev = new_encode_dev(sb->s_bdev->bd_dev); handlers[0].gfd_fn = ext4_getfsmap_datadev; - if (EXT4_SB(sb)->journal_bdev) { + if (EXT4_SB(sb)->s_journal_bdev) { handlers[1].gfd_dev = new_encode_dev( - EXT4_SB(sb)->journal_bdev->bd_dev); + EXT4_SB(sb)->s_journal_bdev->bd_dev); handlers[1].gfd_fn = ext4_getfsmap_logdev; } diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index a5442528a60d..9bf711d63368 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -148,6 +148,7 @@ static Indirect *ext4_get_branch(struct inode *inode, int depth, struct super_block *sb = inode->i_sb; Indirect *p = chain; struct buffer_head *bh; + unsigned int key; int ret = -EIO; *err = 0; @@ -156,7 +157,13 @@ static Indirect *ext4_get_branch(struct inode *inode, int depth, if (!p->key) goto no_block; while (--depth) { - bh = sb_getblk(sb, le32_to_cpu(p->key)); + key = le32_to_cpu(p->key); + if (key > ext4_blocks_count(EXT4_SB(sb)->s_es)) { + /* the block was out of range */ + ret = -EFSCORRUPTED; + goto failure; + } + bh = sb_getblk(sb, key); if (unlikely(!bh)) { ret = -ENOMEM; goto failure; @@ -635,6 +642,14 @@ int ext4_ind_map_blocks(handle_t *handle, struct inode *inode, ext4_update_inode_fsync_trans(handle, inode, 1); count = ar.len; + + /* + * Update reserved blocks/metadata blocks after successful block + * allocation which had been deferred till now. + */ + if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) + ext4_da_update_reserve_space(inode, count, 1); + got_it: map->m_flags |= EXT4_MAP_MAPPED; map->m_pblk = le32_to_cpu(chain[depth-1].key); diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index b1c6b9398eef..71bb3cfc5933 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -32,6 +32,7 @@ static int get_max_inline_xattr_value_size(struct inode *inode, struct ext4_xattr_ibody_header *header; struct ext4_xattr_entry *entry; struct ext4_inode *raw_inode; + void *end; int free, min_offs; if (!EXT4_INODE_HAS_XATTR_SPACE(inode)) @@ -55,14 +56,23 @@ static int get_max_inline_xattr_value_size(struct inode *inode, raw_inode = ext4_raw_inode(iloc); header = IHDR(inode, raw_inode); entry = IFIRST(header); + end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size; /* Compute min_offs. */ - for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) { + while (!IS_LAST_ENTRY(entry)) { + void *next = EXT4_XATTR_NEXT(entry); + + if (next >= end) { + EXT4_ERROR_INODE(inode, + "corrupt xattr in inline inode"); + return 0; + } if (!entry->e_value_inum && entry->e_value_size) { size_t offs = le16_to_cpu(entry->e_value_offs); if (offs < min_offs) min_offs = offs; } + entry = next; } free = min_offs - ((void *)entry - (void *)IFIRST(header)) - sizeof(__u32); @@ -157,7 +167,6 @@ int ext4_find_inline_data_nolock(struct inode *inode) (void *)ext4_raw_inode(&is.iloc)); EXT4_I(inode)->i_inline_size = EXT4_MIN_INLINE_DATA_SIZE + le32_to_cpu(is.s.here->e_value_size); - ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); } out: brelse(is.iloc.bh); @@ -207,7 +216,7 @@ out: /* * write the buffer to the inline inode. * If 'create' is set, we don't need to do the extra copy in the xattr - * value since it is already handled by ext4_xattr_ibody_inline_set. + * value since it is already handled by ext4_xattr_ibody_set. * That saves us one memcpy. */ static void ext4_write_inline_data(struct inode *inode, struct ext4_iloc *iloc, @@ -289,7 +298,7 @@ static int ext4_create_inline_data(handle_t *handle, BUG_ON(!is.s.not_found); - error = ext4_xattr_ibody_inline_set(handle, inode, &i, &is); + error = ext4_xattr_ibody_set(handle, inode, &i, &is); if (error) { if (error == -ENOSPC) ext4_clear_inode_state(inode, @@ -349,7 +358,7 @@ static int ext4_update_inline_data(handle_t *handle, struct inode *inode, error = ext4_xattr_ibody_get(inode, i.name_index, i.name, value, len); - if (error == -ENODATA) + if (error < 0) goto out; BUFFER_TRACE(is.iloc.bh, "get_write_access"); @@ -361,7 +370,7 @@ static int ext4_update_inline_data(handle_t *handle, struct inode *inode, i.value = value; i.value_len = len; - error = ext4_xattr_ibody_inline_set(handle, inode, &i, &is); + error = ext4_xattr_ibody_set(handle, inode, &i, &is); if (error) goto out; @@ -434,7 +443,7 @@ static int ext4_destroy_inline_data_nolock(handle_t *handle, if (error) goto out; - error = ext4_xattr_ibody_inline_set(handle, inode, &i, &is); + error = ext4_xattr_ibody_set(handle, inode, &i, &is); if (error) goto out; @@ -1978,8 +1987,7 @@ int ext4_inline_data_truncate(struct inode *inode, int *has_inline) i.value = value; i.value_len = i_size > EXT4_MIN_INLINE_DATA_SIZE ? i_size - EXT4_MIN_INLINE_DATA_SIZE : 0; - err = ext4_xattr_ibody_inline_set(handle, inode, - &i, &is); + err = ext4_xattr_ibody_set(handle, inode, &i, &is); if (err) goto out_error; } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 95139c992a54..646285fbc9fc 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -207,6 +207,8 @@ void ext4_evict_inode(struct inode *inode) trace_ext4_evict_inode(inode); + if (EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL) + ext4_evict_ea_inode(inode); if (inode->i_nlink) { /* * When journalling data dirty buffers are tracked only in the @@ -666,16 +668,6 @@ found: */ ext4_clear_inode_state(inode, EXT4_STATE_EXT_MIGRATE); } - - /* - * Update reserved blocks/metadata blocks after successful - * block allocation which had been deferred till now. We don't - * support fallocate for non extent files. So we can update - * reserve space here. - */ - if ((retval > 0) && - (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)) - ext4_da_update_reserve_space(inode, retval, 1); } if (retval > 0) { @@ -1426,7 +1418,8 @@ static int ext4_write_end(struct file *file, int inline_data = ext4_has_inline_data(inode); trace_ext4_write_end(inode, pos, len, copied); - if (inline_data) { + if (inline_data && + ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) { ret = ext4_write_inline_data_end(inode, pos, len, copied, page); if (ret < 0) { @@ -4549,7 +4542,7 @@ int ext4_truncate(struct inode *inode) trace_ext4_truncate_enter(inode); if (!ext4_can_truncate(inode)) - return 0; + goto out_trace; ext4_clear_inode_flag(inode, EXT4_INODE_EOFBLOCKS); @@ -4560,16 +4553,15 @@ int ext4_truncate(struct inode *inode) int has_inline = 1; err = ext4_inline_data_truncate(inode, &has_inline); - if (err) - return err; - if (has_inline) - return 0; + if (err || has_inline) + goto out_trace; } /* If we zero-out tail of the page, we have to create jinode for jbd2 */ if (inode->i_size & (inode->i_sb->s_blocksize - 1)) { - if (ext4_inode_attach_jinode(inode) < 0) - return 0; + err = ext4_inode_attach_jinode(inode); + if (err) + goto out_trace; } if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) @@ -4578,8 +4570,10 @@ int ext4_truncate(struct inode *inode) credits = ext4_blocks_for_truncate(inode); handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits); - if (IS_ERR(handle)) - return PTR_ERR(handle); + if (IS_ERR(handle)) { + err = PTR_ERR(handle); + goto out_trace; + } if (inode->i_size & (inode->i_sb->s_blocksize - 1)) ext4_block_truncate_page(handle, mapping, inode->i_size); @@ -4628,6 +4622,7 @@ out_stop: ext4_mark_inode_dirty(handle, inode); ext4_journal_stop(handle); +out_trace: trace_ext4_truncate_exit(inode); return err; } @@ -4663,9 +4658,17 @@ static int __ext4_get_inode_loc(struct inode *inode, inodes_per_block = EXT4_SB(sb)->s_inodes_per_block; inode_offset = ((inode->i_ino - 1) % EXT4_INODES_PER_GROUP(sb)); - block = ext4_inode_table(sb, gdp) + (inode_offset / inodes_per_block); iloc->offset = (inode_offset % inodes_per_block) * EXT4_INODE_SIZE(sb); + block = ext4_inode_table(sb, gdp); + if ((block <= le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) || + (block >= ext4_blocks_count(EXT4_SB(sb)->s_es))) { + ext4_error(sb, "Invalid inode table block %llu in " + "block_group %u", block, iloc->block_group); + return -EFSCORRUPTED; + } + block += (inode_offset / inodes_per_block); + bh = sb_getblk(sb, block); if (unlikely(!bh)) return -ENOMEM; @@ -4853,8 +4856,13 @@ static inline int ext4_iget_extra_inode(struct inode *inode, if (EXT4_INODE_HAS_XATTR_SPACE(inode) && *magic == cpu_to_le32(EXT4_XATTR_MAGIC)) { + int err; + ext4_set_inode_state(inode, EXT4_STATE_XATTR); - return ext4_find_inline_data_nolock(inode); + err = ext4_find_inline_data_nolock(inode); + if (!err && ext4_has_inline_data(inode)) + ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); + return err; } else EXT4_I(inode)->i_inline_off = 0; return 0; @@ -4930,13 +4938,6 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, goto bad_inode; raw_inode = ext4_raw_inode(&iloc); - if ((ino == EXT4_ROOT_INO) && (raw_inode->i_links_count == 0)) { - ext4_error_inode(inode, function, line, 0, - "iget: root inode unallocated"); - ret = -EFSCORRUPTED; - goto bad_inode; - } - if ((flags & EXT4_IGET_HANDLE) && (raw_inode->i_links_count == 0) && (raw_inode->i_mode == 0)) { ret = -ESTALE; @@ -5007,11 +5008,16 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, * NeilBrown 1999oct15 */ if (inode->i_nlink == 0) { - if ((inode->i_mode == 0 || + if ((inode->i_mode == 0 || flags & EXT4_IGET_SPECIAL || !(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS)) && ino != EXT4_BOOT_LOADER_INO) { - /* this inode is deleted */ - ret = -ESTALE; + /* this inode is deleted or unallocated */ + if (flags & EXT4_IGET_SPECIAL) { + ext4_error_inode(inode, function, line, 0, + "iget: special inode unallocated"); + ret = -EFSCORRUPTED; + } else + ret = -ESTALE; goto bad_inode; } /* The only unlinked inodes we let through here have @@ -6033,6 +6039,14 @@ static int __ext4_expand_extra_isize(struct inode *inode, return 0; } + /* + * We may need to allocate external xattr block so we need quotas + * initialized. Here we can be called with various locks held so we + * cannot affort to initialize quotas ourselves. So just bail. + */ + if (dquot_initialize_needed(inode)) + return -EAGAIN; + /* try to expand with EAs present */ error = ext4_expand_extra_isize_ea(inode, new_extra_isize, raw_inode, handle); diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 484cb68c34d9..43e036f0b661 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -169,7 +169,7 @@ static long swap_inode_boot_loader(struct super_block *sb, /* Protect extent tree against block allocations via delalloc */ ext4_double_down_write_data_sem(inode, inode_bl); - if (inode_bl->i_nlink == 0) { + if (is_bad_inode(inode_bl) || !S_ISREG(inode_bl->i_mode)) { /* this inode has never been used as a BOOT_LOADER */ set_nlink(inode_bl, 1); i_uid_write(inode_bl, 0); @@ -178,6 +178,7 @@ static long swap_inode_boot_loader(struct super_block *sb, ei_bl->i_flags = 0; inode_set_iversion(inode_bl, 1); i_size_write(inode_bl, 0); + EXT4_I(inode_bl)->i_disksize = inode_bl->i_size; inode_bl->i_mode = S_IFREG; if (ext4_has_feature_extents(sb)) { ext4_set_inode_flag(inode_bl, EXT4_INODE_EXTENTS); @@ -449,6 +450,10 @@ static int ext4_ioctl_setproject(struct file *filp, __u32 projid) if (ext4_is_quota_file(inode)) return err; + err = dquot_initialize(inode); + if (err) + return err; + err = ext4_get_inode_loc(inode, &iloc); if (err) return err; @@ -464,10 +469,6 @@ static int ext4_ioctl_setproject(struct file *filp, __u32 projid) brelse(iloc.bh); } - err = dquot_initialize(inode); - if (err) - return err; - handle = ext4_journal_start(inode, EXT4_HT_QUOTA, EXT4_QUOTA_INIT_BLOCKS(sb) + EXT4_QUOTA_DEL_BLOCKS(sb) + 3); @@ -560,6 +561,7 @@ static int ext4_shutdown(struct super_block *sb, unsigned long arg) { struct ext4_sb_info *sbi = EXT4_SB(sb); __u32 flags; + struct super_block *ret; if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -578,7 +580,9 @@ static int ext4_shutdown(struct super_block *sb, unsigned long arg) switch (flags) { case EXT4_GOING_FLAGS_DEFAULT: - freeze_bdev(sb->s_bdev); + ret = freeze_bdev(sb->s_bdev); + if (IS_ERR(ret)) + return PTR_ERR(ret); set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags); thaw_bdev(sb->s_bdev, sb); break; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 4ea4fe92eb8c..8875fac9f958 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -16,6 +16,7 @@ #include <linux/slab.h> #include <linux/nospec.h> #include <linux/backing-dev.h> +#include <linux/freezer.h> #include <trace/events/ext4.h> #ifdef CONFIG_EXT4_DEBUG @@ -3089,6 +3090,7 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac, struct ext4_allocation_request *ar) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); + struct ext4_super_block *es = sbi->s_es; int bsbits, max; ext4_lblk_t end; loff_t size, start_off; @@ -3179,6 +3181,10 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac, start = max(start, rounddown(ac->ac_o_ex.fe_logical, (ext4_lblk_t)EXT4_BLOCKS_PER_GROUP(ac->ac_sb))); + /* avoid unnecessary preallocation that may trigger assertions */ + if (start + size > EXT_MAX_BLOCKS) + size = EXT_MAX_BLOCKS - start; + /* don't cover already allocated blocks in selected range */ if (ar->pleft && start <= ar->lleft) { size -= ar->lleft + 1 - start; @@ -3269,18 +3275,21 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac, ac->ac_g_ex.fe_len = EXT4_NUM_B2C(sbi, size); /* define goal start in order to merge */ - if (ar->pright && (ar->lright == (start + size))) { + if (ar->pright && (ar->lright == (start + size)) && + ar->pright >= size && + ar->pright - size >= le32_to_cpu(es->s_first_data_block)) { /* merge to the right */ ext4_get_group_no_and_offset(ac->ac_sb, ar->pright - size, - &ac->ac_f_ex.fe_group, - &ac->ac_f_ex.fe_start); + &ac->ac_g_ex.fe_group, + &ac->ac_g_ex.fe_start); ac->ac_flags |= EXT4_MB_HINT_TRY_GOAL; } - if (ar->pleft && (ar->lleft + 1 == start)) { + if (ar->pleft && (ar->lleft + 1 == start) && + ar->pleft + 1 < ext4_blocks_count(es)) { /* merge to the left */ ext4_get_group_no_and_offset(ac->ac_sb, ar->pleft + 1, - &ac->ac_f_ex.fe_group, - &ac->ac_f_ex.fe_start); + &ac->ac_g_ex.fe_group, + &ac->ac_g_ex.fe_start); ac->ac_flags |= EXT4_MB_HINT_TRY_GOAL; } @@ -3372,6 +3381,7 @@ static void ext4_mb_use_inode_pa(struct ext4_allocation_context *ac, BUG_ON(start < pa->pa_pstart); BUG_ON(end > pa->pa_pstart + EXT4_C2B(sbi, pa->pa_len)); BUG_ON(pa->pa_free < len); + BUG_ON(ac->ac_b_ex.fe_len <= 0); pa->pa_free -= len; mb_debug(1, "use %llu/%u from inode pa %p\n", start, len, pa); @@ -3676,10 +3686,8 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) return -ENOMEM; if (ac->ac_b_ex.fe_len < ac->ac_g_ex.fe_len) { - int winl; - int wins; - int win; - int offs; + int new_bex_start; + int new_bex_end; /* we can't allocate as much as normalizer wants. * so, found space must get proper lstart @@ -3687,26 +3695,40 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) 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); - /* we're limited by original request in that - * logical block must be covered any way - * winl is window we can move our chunk within */ - winl = ac->ac_o_ex.fe_logical - ac->ac_g_ex.fe_logical; + /* + * Use the below logic for adjusting best extent as it keeps + * fragmentation in check while ensuring logical range of best + * extent doesn't overflow out of goal extent: + * + * 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 + * 3. Else, keep the best ex at start of original request. + */ + new_bex_end = ac->ac_g_ex.fe_logical + + EXT4_C2B(sbi, ac->ac_g_ex.fe_len); + new_bex_start = new_bex_end - EXT4_C2B(sbi, ac->ac_b_ex.fe_len); + if (ac->ac_o_ex.fe_logical >= new_bex_start) + goto adjust_bex; - /* also, we should cover whole original request */ - wins = EXT4_C2B(sbi, ac->ac_b_ex.fe_len - ac->ac_o_ex.fe_len); + new_bex_start = ac->ac_g_ex.fe_logical; + new_bex_end = + new_bex_start + EXT4_C2B(sbi, ac->ac_b_ex.fe_len); + if (ac->ac_o_ex.fe_logical < new_bex_end) + goto adjust_bex; - /* the smallest one defines real window */ - win = min(winl, wins); + new_bex_start = ac->ac_o_ex.fe_logical; + new_bex_end = + new_bex_start + EXT4_C2B(sbi, ac->ac_b_ex.fe_len); - offs = ac->ac_o_ex.fe_logical % - EXT4_C2B(sbi, ac->ac_b_ex.fe_len); - if (offs && offs < win) - win = offs; +adjust_bex: + ac->ac_b_ex.fe_logical = new_bex_start; - ac->ac_b_ex.fe_logical = ac->ac_o_ex.fe_logical - - EXT4_NUM_B2C(sbi, win); 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(new_bex_end > (ac->ac_g_ex.fe_logical + + EXT4_C2B(sbi, ac->ac_g_ex.fe_len))); } /* preallocation can change ac_b_ex, thus we store actually @@ -3893,7 +3915,11 @@ ext4_mb_release_group_pa(struct ext4_buddy *e4b, trace_ext4_mb_release_group_pa(sb, pa); BUG_ON(pa->pa_deleted == 0); ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, &bit); - BUG_ON(group != e4b->bd_group && pa->pa_len != 0); + if (unlikely(group != e4b->bd_group && pa->pa_len != 0)) { + ext4_warning(sb, "bad group: expected %u, group %u, pa_start %llu", + e4b->bd_group, group, pa->pa_pstart); + return 0; + } mb_free_blocks(pa->pa_inode, e4b, bit, pa->pa_len); atomic_add(pa->pa_len, &EXT4_SB(sb)->s_mb_discarded); trace_ext4_mballoc_discard(sb, NULL, group, bit, pa->pa_len); @@ -4927,8 +4953,8 @@ do_more: * them with group lock_held */ if (test_opt(sb, DISCARD)) { - err = ext4_issue_discard(sb, block_group, bit, count, - NULL); + err = ext4_issue_discard(sb, block_group, bit, + count_clusters, NULL); if (err && err != -EOPNOTSUPP) ext4_msg(sb, KERN_WARNING, "discard request in" " group:%d block:%d count:%lu failed" @@ -5128,19 +5154,19 @@ error_return: * @sb: super block for the file system * @start: starting block of the free extent in the alloc. group * @count: number of blocks to TRIM - * @group: alloc. group we are working with * @e4b: ext4 buddy for the group * * Trim "count" blocks starting at "start" in the "group". To assure that no * one will allocate those blocks, mark it as used in buddy bitmap. This must * be called with under the group lock. */ -static int ext4_trim_extent(struct super_block *sb, int start, int count, - ext4_group_t group, struct ext4_buddy *e4b) +static int ext4_trim_extent(struct super_block *sb, + int start, int count, struct ext4_buddy *e4b) __releases(bitlock) __acquires(bitlock) { struct ext4_free_extent ex; + ext4_group_t group = e4b->bd_group; int ret = 0; trace_ext4_trim_extent(sb, group, start, count); @@ -5163,6 +5189,71 @@ __acquires(bitlock) return ret; } +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); +} + +static bool ext4_trim_interrupted(void) +{ + return fatal_signal_pending(current) || freezing(current); +} + +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; + bool set_trimmed = false; + void *bitmap; + + bitmap = e4b->bd_bitmap; + if (start == 0 && max >= ext4_last_grp_cluster(sb, e4b->bd_group)) + set_trimmed = true; + start = max(e4b->bd_info->bb_first_free, start); + count = 0; + free_count = 0; + + while (start <= max) { + start = mb_find_next_zero_bit(bitmap, max + 1, start); + if (start > max) + break; + next = mb_find_next_bit(bitmap, max + 1, start); + + if ((next - start) >= minblocks) { + int ret = ext4_trim_extent(sb, start, next - start, e4b); + + if (ret && ret != -EOPNOTSUPP) + return count; + count += next - start; + } + free_count += next - start; + start = next + 1; + + if (ext4_trim_interrupted()) + return count; + + if (need_resched()) { + ext4_unlock_group(sb, e4b->bd_group); + cond_resched(); + ext4_lock_group(sb, e4b->bd_group); + } + + if ((e4b->bd_info->bb_free - free_count) < minblocks) + break; + } + + if (set_trimmed) + EXT4_MB_GRP_SET_TRIMMED(e4b->bd_info); + + return count; +} + /** * ext4_trim_all_free -- function to trim all free space in alloc. group * @sb: super block for file system @@ -5186,10 +5277,8 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group, ext4_grpblk_t start, ext4_grpblk_t max, ext4_grpblk_t minblocks) { - void *bitmap; - ext4_grpblk_t next, count = 0, free_count = 0; struct ext4_buddy e4b; - int ret = 0; + int ret; trace_ext4_trim_all_free(sb, group, start, max); @@ -5199,58 +5288,20 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group, ret, group); return ret; } - bitmap = e4b.bd_bitmap; ext4_lock_group(sb, group); - if (EXT4_MB_GRP_WAS_TRIMMED(e4b.bd_info) && - minblocks >= atomic_read(&EXT4_SB(sb)->s_last_trim_minblks)) - goto out; - start = (e4b.bd_info->bb_first_free > start) ? - e4b.bd_info->bb_first_free : start; - - while (start <= max) { - start = mb_find_next_zero_bit(bitmap, max + 1, start); - if (start > max) - break; - next = mb_find_next_bit(bitmap, max + 1, start); - - if ((next - start) >= minblocks) { - ret = ext4_trim_extent(sb, start, - next - start, group, &e4b); - if (ret && ret != -EOPNOTSUPP) - break; - ret = 0; - count += next - start; - } - free_count += next - start; - start = next + 1; - - if (fatal_signal_pending(current)) { - count = -ERESTARTSYS; - break; - } - - if (need_resched()) { - ext4_unlock_group(sb, group); - cond_resched(); - ext4_lock_group(sb, group); - } - - if ((e4b.bd_info->bb_free - free_count) < minblocks) - break; - } + if (!EXT4_MB_GRP_WAS_TRIMMED(e4b.bd_info) || + minblocks < EXT4_SB(sb)->s_last_trim_minblks) + ret = ext4_try_to_trim_range(sb, &e4b, start, max, minblocks); + else + ret = 0; - if (!ret) { - ret = count; - EXT4_MB_GRP_SET_TRIMMED(e4b.bd_info); - } -out: ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); ext4_debug("trimmed %d blocks in the group %d\n", - count, group); + ret, group); return ret; } @@ -5295,7 +5346,7 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) if (minlen > EXT4_CLUSTERS_PER_GROUP(sb)) goto out; } - if (end >= max_blks) + if (end >= max_blks - 1) end = max_blks - 1; if (end <= first_data_blk) goto out; @@ -5312,6 +5363,8 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) end = EXT4_CLUSTERS_PER_GROUP(sb) - 1; for (group = first_group; group <= last_group; group++) { + if (ext4_trim_interrupted()) + break; grp = ext4_get_group_info(sb, group); /* We only do this if the grp has never been initialized */ if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) { @@ -5328,10 +5381,9 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) */ if (group == last_group) end = last_cluster; - if (grp->bb_free >= minlen) { cnt = ext4_trim_all_free(sb, group, first_cluster, - end, minlen); + end, minlen); if (cnt < 0) { ret = cnt; break; @@ -5347,7 +5399,7 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) } if (!ret) - atomic_set(&EXT4_SB(sb)->s_last_trim_minblks, minlen); + EXT4_SB(sb)->s_last_trim_minblks = minlen; out: range->len = EXT4_C2B(EXT4_SB(sb), trimmed) << sb->s_blocksize_bits; @@ -5376,8 +5428,7 @@ ext4_mballoc_query_range( ext4_lock_group(sb, group); - start = (e4b.bd_info->bb_first_free > start) ? - e4b.bd_info->bb_first_free : start; + start = max(e4b.bd_info->bb_first_free, start); if (end >= EXT4_CLUSTERS_PER_GROUP(sb)) end = EXT4_CLUSTERS_PER_GROUP(sb) - 1; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index a878b9a8d9ea..93d392576c12 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -322,17 +322,17 @@ static struct ext4_dir_entry_tail *get_dirent_tail(struct inode *inode, struct ext4_dir_entry *de) { struct ext4_dir_entry_tail *t; + int blocksize = EXT4_BLOCK_SIZE(inode->i_sb); #ifdef PARANOID struct ext4_dir_entry *d, *top; d = de; top = (struct ext4_dir_entry *)(((void *)de) + - (EXT4_BLOCK_SIZE(inode->i_sb) - - sizeof(struct ext4_dir_entry_tail))); - while (d < top && d->rec_len) + (blocksize - sizeof(struct ext4_dir_entry_tail))); + while (d < top && ext4_rec_len_from_disk(d->rec_len, blocksize)) d = (struct ext4_dir_entry *)(((void *)d) + - le16_to_cpu(d->rec_len)); + ext4_rec_len_from_disk(d->rec_len, blocksize)); if (d != top) return NULL; @@ -343,7 +343,8 @@ static struct ext4_dir_entry_tail *get_dirent_tail(struct inode *inode, #endif if (t->det_reserved_zero1 || - le16_to_cpu(t->det_rec_len) != sizeof(struct ext4_dir_entry_tail) || + (ext4_rec_len_from_disk(t->det_rec_len, blocksize) != + sizeof(struct ext4_dir_entry_tail)) || t->det_reserved_zero2 || t->det_reserved_ft != EXT4_FT_DIR_CSUM) return NULL; @@ -425,13 +426,14 @@ static struct dx_countlimit *get_dx_countlimit(struct inode *inode, struct ext4_dir_entry *dp; struct dx_root_info *root; int count_offset; + int blocksize = EXT4_BLOCK_SIZE(inode->i_sb); + unsigned int rlen = ext4_rec_len_from_disk(dirent->rec_len, blocksize); - if (le16_to_cpu(dirent->rec_len) == EXT4_BLOCK_SIZE(inode->i_sb)) + if (rlen == blocksize) count_offset = 8; - else if (le16_to_cpu(dirent->rec_len) == 12) { + else if (rlen == 12) { dp = (struct ext4_dir_entry *)(((void *)dirent) + 12); - if (le16_to_cpu(dp->rec_len) != - EXT4_BLOCK_SIZE(inode->i_sb) - 12) + if (ext4_rec_len_from_disk(dp->rec_len, blocksize) != blocksize - 12) return NULL; root = (struct dx_root_info *)(((void *)dp + 12)); if (root->reserved_zero || @@ -1244,6 +1246,7 @@ static int dx_make_map(struct inode *dir, struct buffer_head *bh, unsigned int buflen = bh->b_size; char *base = bh->b_data; struct dx_hash_info h = *hinfo; + int blocksize = EXT4_BLOCK_SIZE(dir->i_sb); if (ext4_has_metadata_csum(dir->i_sb)) buflen -= sizeof(struct ext4_dir_entry_tail); @@ -1257,11 +1260,12 @@ static int dx_make_map(struct inode *dir, struct buffer_head *bh, map_tail--; map_tail->hash = h.hash; map_tail->offs = ((char *) de - base)>>2; - map_tail->size = le16_to_cpu(de->rec_len); + map_tail->size = ext4_rec_len_from_disk(de->rec_len, + blocksize); count++; cond_resched(); } - de = ext4_next_entry(de, dir->i_sb->s_blocksize); + de = ext4_next_entry(de, blocksize); } return count; } @@ -1419,11 +1423,10 @@ static struct buffer_head *__ext4_find_entry(struct inode *dir, int has_inline_data = 1; ret = ext4_find_inline_entry(dir, fname, res_dir, &has_inline_data); - if (has_inline_data) { - if (inlined) - *inlined = 1; + if (inlined) + *inlined = has_inline_data; + if (has_inline_data) goto cleanup_and_exit; - } } if ((namelen <= 2) && (name[0] == '.') && @@ -3515,7 +3518,8 @@ static void ext4_resetent(handle_t *handle, struct ext4_renament *ent, * so the old->de may no longer valid and need to find it again * before reset old inode info. */ - old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de, NULL); + old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de, + &old.inlined); if (IS_ERR(old.bh)) retval = PTR_ERR(old.bh); if (!old.bh) @@ -3677,7 +3681,8 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, return retval; } - old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de, NULL); + old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de, + &old.inlined); if (IS_ERR(old.bh)) return PTR_ERR(old.bh); /* @@ -3870,6 +3875,9 @@ static int ext4_cross_rename(struct inode *old_dir, struct dentry *old_dentry, retval = dquot_initialize(old.dir); if (retval) return retval; + retval = dquot_initialize(old.inode); + if (retval) + return retval; retval = dquot_initialize(new.dir); if (retval) return retval; diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 3de933354a08..bf910f266469 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -388,7 +388,8 @@ static int io_submit_init_bio(struct ext4_io_submit *io, static int io_submit_add_bh(struct ext4_io_submit *io, struct inode *inode, - struct page *page, + struct page *pagecache_page, + struct page *bounce_page, struct buffer_head *bh) { int ret; @@ -403,10 +404,11 @@ submit_and_retry: return ret; io->io_bio->bi_write_hint = inode->i_write_hint; } - ret = bio_add_page(io->io_bio, page, bh->b_size, bh_offset(bh)); + ret = bio_add_page(io->io_bio, bounce_page ?: pagecache_page, + bh->b_size, bh_offset(bh)); if (ret != bh->b_size) goto submit_and_retry; - wbc_account_io(io->io_wbc, page, bh->b_size); + wbc_account_io(io->io_wbc, pagecache_page, bh->b_size); io->io_next_block++; return 0; } @@ -514,8 +516,7 @@ int ext4_bio_write_page(struct ext4_io_submit *io, do { if (!buffer_async_write(bh)) continue; - ret = io_submit_add_bh(io, inode, - data_page ? data_page : page, bh); + ret = io_submit_add_bh(io, inode, page, data_page, bh); if (ret) { /* * We only get here on ENOMEM. Not much else diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 8737d1bcdb6e..f4b3d450dead 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -572,13 +572,8 @@ static int setup_new_flex_group_blocks(struct super_block *sb, if (meta_bg == 0 && !ext4_bg_has_super(sb, group)) goto handle_itb; - if (meta_bg == 1) { - ext4_group_t first_group; - first_group = ext4_meta_bg_first_group(sb, group); - if (first_group != group + 1 && - first_group != group + EXT4_DESC_PER_BLOCK(sb) - 1) - goto handle_itb; - } + if (meta_bg == 1) + goto handle_itb; block = start + ext4_bg_has_super(sb, group); /* Copy all of the GDT blocks into the backup in this group */ @@ -1565,10 +1560,12 @@ exit_journal: int gdb_num_end = ((group + flex_gd->count - 1) / EXT4_DESC_PER_BLOCK(sb)); int meta_bg = ext4_has_feature_meta_bg(sb); + sector_t padding_blocks = meta_bg ? 0 : sbi->s_sbh->b_blocknr - + ext4_group_first_block_no(sb, 0); sector_t old_gdb = 0; - update_backups(sb, sbi->s_sbh->b_blocknr, (char *)es, - sizeof(struct ext4_super_block), 0); + update_backups(sb, ext4_group_first_block_no(sb, 0), + (char *)es, sizeof(struct ext4_super_block), 0); for (; gdb_num <= gdb_num_end; gdb_num++) { struct buffer_head *gdb_bh; @@ -1576,8 +1573,8 @@ exit_journal: gdb_num); if (old_gdb == gdb_bh->b_blocknr) continue; - update_backups(sb, gdb_bh->b_blocknr, gdb_bh->b_data, - gdb_bh->b_size, meta_bg); + update_backups(sb, gdb_bh->b_blocknr - padding_blocks, + gdb_bh->b_data, gdb_bh->b_size, meta_bg); old_gdb = gdb_bh->b_blocknr; } } @@ -1775,7 +1772,7 @@ errout: if (test_opt(sb, DEBUG)) printk(KERN_DEBUG "EXT4-fs: extended group to %llu " "blocks\n", ext4_blocks_count(es)); - update_backups(sb, EXT4_SB(sb)->s_sbh->b_blocknr, + update_backups(sb, ext4_group_first_block_no(sb, 0), (char *)es, sizeof(struct ext4_super_block), 0); } return err; @@ -1940,9 +1937,7 @@ static int ext4_convert_meta_bg(struct super_block *sb, struct inode *inode) errout: ret = ext4_journal_stop(handle); - if (!err) - err = ret; - return ret; + return err ? err : ret; invalid_resize_inode: ext4_error(sb, "corrupted/inconsistent resize inode"); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index f00cc301da36..926063a6d232 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -905,10 +905,16 @@ static void ext4_blkdev_put(struct block_device *bdev) static void ext4_blkdev_remove(struct ext4_sb_info *sbi) { struct block_device *bdev; - bdev = sbi->journal_bdev; + bdev = sbi->s_journal_bdev; if (bdev) { + /* + * Invalidate the journal device's buffers. We don't want them + * floating about in memory - the physical journal device may + * hotswapped, and it breaks the `ro-after' testing code. + */ + invalidate_bdev(bdev); ext4_blkdev_put(bdev); - sbi->journal_bdev = NULL; + sbi->s_journal_bdev = NULL; } } @@ -1032,14 +1038,8 @@ static void ext4_put_super(struct super_block *sb) sync_blockdev(sb->s_bdev); invalidate_bdev(sb->s_bdev); - if (sbi->journal_bdev && sbi->journal_bdev != sb->s_bdev) { - /* - * Invalidate the journal device's buffers. We don't want them - * floating about in memory - the physical journal device may - * hotswapped, and it breaks the `ro-after' testing code. - */ - sync_blockdev(sbi->journal_bdev); - invalidate_bdev(sbi->journal_bdev); + if (sbi->s_journal_bdev && sbi->s_journal_bdev != sb->s_bdev) { + sync_blockdev(sbi->s_journal_bdev); ext4_blkdev_remove(sbi); } if (sbi->s_ea_inode_cache) { @@ -1081,6 +1081,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) return NULL; inode_set_iversion(&ei->vfs_inode, 1); + ei->i_flags = 0; spin_lock_init(&ei->i_raw_lock); INIT_LIST_HEAD(&ei->i_prealloc_list); spin_lock_init(&ei->i_prealloc_lock); @@ -2422,11 +2423,9 @@ static __le16 ext4_group_desc_csum(struct super_block *sb, __u32 block_group, crc = crc16(crc, (__u8 *)gdp, offset); offset += sizeof(gdp->bg_checksum); /* skip checksum */ /* for checksum of struct ext4_group_desc do the rest...*/ - if (ext4_has_feature_64bit(sb) && - offset < le16_to_cpu(sbi->s_es->s_desc_size)) + if (ext4_has_feature_64bit(sb) && offset < sbi->s_desc_size) crc = crc16(crc, (__u8 *)gdp + offset, - le16_to_cpu(sbi->s_es->s_desc_size) - - offset); + sbi->s_desc_size - offset); out: return cpu_to_le16(crc); @@ -3538,7 +3537,7 @@ int ext4_calculate_overhead(struct super_block *sb) * Add the internal journal blocks whether the journal has been * loaded or not */ - if (sbi->s_journal && !sbi->journal_bdev) + if (sbi->s_journal && !sbi->s_journal_bdev) overhead += EXT4_NUM_B2C(sbi, sbi->s_journal->j_maxlen); else if (ext4_has_feature_journal(sb) && !sbi->s_journal && j_inum) { /* j_inum for internal journal is non-zero */ @@ -4302,30 +4301,31 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) ext4_has_feature_journal_needs_recovery(sb)) { ext4_msg(sb, KERN_ERR, "required journal recovery " "suppressed and not mounted read-only"); - goto failed_mount_wq; + goto failed_mount3a; } else { /* Nojournal mode, all journal mount options are illegal */ - if (test_opt2(sb, EXPLICIT_JOURNAL_CHECKSUM)) { - ext4_msg(sb, KERN_ERR, "can't mount with " - "journal_checksum, fs mounted w/o journal"); - goto failed_mount_wq; - } if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) { ext4_msg(sb, KERN_ERR, "can't mount with " "journal_async_commit, fs mounted w/o journal"); - goto failed_mount_wq; + goto failed_mount3a; + } + + if (test_opt2(sb, EXPLICIT_JOURNAL_CHECKSUM)) { + ext4_msg(sb, KERN_ERR, "can't mount with " + "journal_checksum, fs mounted w/o journal"); + goto failed_mount3a; } if (sbi->s_commit_interval != JBD2_DEFAULT_MAX_COMMIT_AGE*HZ) { ext4_msg(sb, KERN_ERR, "can't mount with " "commit=%lu, fs mounted w/o journal", sbi->s_commit_interval / HZ); - goto failed_mount_wq; + goto failed_mount3a; } if (EXT4_MOUNT_DATA_FLAGS & (sbi->s_mount_opt ^ sbi->s_def_mount_opt)) { ext4_msg(sb, KERN_ERR, "can't mount with " "data=, fs mounted w/o journal"); - goto failed_mount_wq; + goto failed_mount3a; } sbi->s_def_mount_opt &= ~EXT4_MOUNT_JOURNAL_CHECKSUM; clear_opt(sb, JOURNAL_CHECKSUM); @@ -4673,6 +4673,7 @@ failed_mount: ext4_blkdev_remove(sbi); brelse(bh); out_fail: + invalidate_bdev(sb->s_bdev); sb->s_fs_info = NULL; kfree(sbi->s_blockgroup_lock); out_free_base: @@ -4731,7 +4732,7 @@ static struct inode *ext4_get_journal_inode(struct super_block *sb, jbd_debug(2, "Journal inode found at %p: %lld bytes\n", journal_inode, journal_inode->i_size); - if (!S_ISREG(journal_inode->i_mode)) { + if (!S_ISREG(journal_inode->i_mode) || IS_ENCRYPTED(journal_inode)) { ext4_msg(sb, KERN_ERR, "invalid journal inode"); iput(journal_inode); return NULL; @@ -4848,7 +4849,7 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb, be32_to_cpu(journal->j_superblock->s_nr_users)); goto out_journal; } - EXT4_SB(sb)->journal_bdev = bdev; + EXT4_SB(sb)->s_journal_bdev = bdev; ext4_init_journal_params(sb, journal); return journal; @@ -5501,9 +5502,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) } #ifdef CONFIG_QUOTA - /* Release old quota file names */ - for (i = 0; i < EXT4_MAXQUOTAS; i++) - kfree(old_opts.s_qf_names[i]); if (enable_quota) { if (sb_any_quota_suspended(sb)) dquot_resume(sb, -1); @@ -5513,6 +5511,9 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) goto restore_opts; } } + /* Release old quota file names */ + for (i = 0; i < EXT4_MAXQUOTAS; i++) + kfree(old_opts.s_qf_names[i]); #endif if (!test_opt(sb, BLOCK_VALIDITY) && sbi->system_blks) ext4_release_system_zone(sb); @@ -5529,6 +5530,13 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) return 0; restore_opts: + /* + * If there was a failing r/w to ro transition, we may need to + * re-enable quota + */ + if ((sb->s_flags & SB_RDONLY) && !(old_sb_flags & SB_RDONLY) && + sb_any_quota_suspended(sb)) + dquot_resume(sb, -1); sb->s_flags = old_sb_flags; sbi->s_mount_opt = old_opts.s_mount_opt; sbi->s_mount_opt2 = old_opts.s_mount_opt2; @@ -5839,6 +5847,20 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id, return err; } +static inline bool ext4_check_quota_inum(int type, unsigned long qf_inum) +{ + switch (type) { + case USRQUOTA: + return qf_inum == EXT4_USR_QUOTA_INO; + case GRPQUOTA: + return qf_inum == EXT4_GRP_QUOTA_INO; + case PRJQUOTA: + return qf_inum >= EXT4_GOOD_OLD_FIRST_INO; + default: + BUG(); + } +} + static int ext4_quota_enable(struct super_block *sb, int type, int format_id, unsigned int flags) { @@ -5855,9 +5877,16 @@ static int ext4_quota_enable(struct super_block *sb, int type, int format_id, if (!qf_inums[type]) return -EPERM; + if (!ext4_check_quota_inum(type, qf_inums[type])) { + ext4_error(sb, "Bad quota inum: %lu, type: %d", + qf_inums[type], type); + return -EUCLEAN; + } + qf_inode = ext4_iget(sb, qf_inums[type], EXT4_IGET_SPECIAL); if (IS_ERR(qf_inode)) { - ext4_error(sb, "Bad quota inode # %lu", qf_inums[type]); + ext4_error(sb, "Bad quota inode: %lu, type: %d", + qf_inums[type], type); return PTR_ERR(qf_inode); } @@ -5896,8 +5925,9 @@ static int ext4_enable_quotas(struct super_block *sb) if (err) { ext4_warning(sb, "Failed to enable quota tracking " - "(type=%d, err=%d). Please run " - "e2fsck to fix.", type, err); + "(type=%d, err=%d, ino=%lu). " + "Please run e2fsck to fix.", type, + err, qf_inums[type]); for (type--; type >= 0; type--) { struct inode *inode; diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c index 9212a026a1f1..74722ce7206c 100644 --- a/fs/ext4/sysfs.c +++ b/fs/ext4/sysfs.c @@ -349,6 +349,11 @@ static void ext4_sb_release(struct kobject *kobj) complete(&sbi->s_kobj_unregister); } +static void ext4_feat_release(struct kobject *kobj) +{ + kfree(kobj); +} + static const struct sysfs_ops ext4_attr_ops = { .show = ext4_attr_show, .store = ext4_attr_store, @@ -363,7 +368,7 @@ static struct kobj_type ext4_sb_ktype = { static struct kobj_type ext4_feat_ktype = { .default_attrs = ext4_feat_attrs, .sysfs_ops = &ext4_attr_ops, - .release = (void (*)(struct kobject *))kfree, + .release = ext4_feat_release, }; static struct kobject *ext4_root; diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 497649c69bba..88bdb2714e51 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -121,7 +121,11 @@ ext4_expand_inode_array(struct ext4_xattr_inode_array **ea_inode_array, #ifdef CONFIG_LOCKDEP void ext4_xattr_inode_set_class(struct inode *ea_inode) { + struct ext4_inode_info *ei = EXT4_I(ea_inode); + lockdep_set_subclass(&ea_inode->i_rwsem, 1); + (void) ei; /* shut up clang warning if !CONFIG_LOCKDEP */ + lockdep_set_subclass(&ei->i_data_sem, I_DATA_SEM_EA); } #endif @@ -384,6 +388,17 @@ static int ext4_xattr_inode_iget(struct inode *parent, unsigned long ea_ino, struct inode *inode; int err; + /* + * We have to check for this corruption early as otherwise + * iget_locked() could wait indefinitely for the state of our + * parent inode. + */ + if (parent->i_ino == ea_ino) { + ext4_error(parent->i_sb, + "Parent and EA inode have the same ino %lu", ea_ino); + return -EFSCORRUPTED; + } + inode = ext4_iget(parent->i_sb, ea_ino, EXT4_IGET_NORMAL); if (IS_ERR(inode)) { err = PTR_ERR(inode); @@ -434,6 +449,21 @@ error: return err; } +/* Remove entry from mbcache when EA inode is getting evicted */ +void ext4_evict_ea_inode(struct inode *inode) +{ + struct mb_cache_entry *oe; + + if (!EA_INODE_CACHE(inode)) + return; + /* Wait for entry to get unused so that we can remove it */ + while ((oe = mb_cache_entry_delete_or_get(EA_INODE_CACHE(inode), + ext4_xattr_inode_get_hash(inode), inode->i_ino))) { + mb_cache_entry_wait_unused(oe); + mb_cache_entry_put(EA_INODE_CACHE(inode), oe); + } +} + static int ext4_xattr_inode_verify_hashes(struct inode *ea_inode, struct ext4_xattr_entry *entry, void *buffer, @@ -1019,10 +1049,8 @@ static int ext4_xattr_ensure_credits(handle_t *handle, struct inode *inode, static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode, int ref_change) { - struct mb_cache *ea_inode_cache = EA_INODE_CACHE(ea_inode); struct ext4_iloc iloc; s64 ref_count; - u32 hash; int ret; inode_lock(ea_inode); @@ -1047,14 +1075,6 @@ static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode, set_nlink(ea_inode, 1); ext4_orphan_del(handle, ea_inode); - - if (ea_inode_cache) { - hash = ext4_xattr_inode_get_hash(ea_inode); - mb_cache_entry_create(ea_inode_cache, - GFP_NOFS, hash, - ea_inode->i_ino, - true /* reusable */); - } } } else { WARN_ONCE(ref_count < 0, "EA inode %lu ref_count=%lld", @@ -1067,12 +1087,6 @@ static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode, clear_nlink(ea_inode); ext4_orphan_add(handle, ea_inode); - - if (ea_inode_cache) { - hash = ext4_xattr_inode_get_hash(ea_inode); - mb_cache_entry_delete(ea_inode_cache, hash, - ea_inode->i_ino); - } } } @@ -1253,6 +1267,7 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode, if (error) goto out; +retry_ref: lock_buffer(bh); hash = le32_to_cpu(BHDR(bh)->h_hash); ref = le32_to_cpu(BHDR(bh)->h_refcount); @@ -1262,9 +1277,18 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode, * This must happen under buffer lock for * ext4_xattr_block_set() to reliably detect freed block */ - if (ea_block_cache) - mb_cache_entry_delete(ea_block_cache, hash, - bh->b_blocknr); + if (ea_block_cache) { + struct mb_cache_entry *oe; + + oe = mb_cache_entry_delete_or_get(ea_block_cache, hash, + bh->b_blocknr); + if (oe) { + unlock_buffer(bh); + mb_cache_entry_wait_unused(oe); + mb_cache_entry_put(ea_block_cache, oe); + goto retry_ref; + } + } get_bh(bh); unlock_buffer(bh); @@ -1288,7 +1312,7 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode, ce = mb_cache_entry_get(ea_block_cache, hash, bh->b_blocknr); if (ce) { - ce->e_reusable = 1; + set_bit(MBE_REUSABLE_B, &ce->e_flags); mb_cache_entry_put(ea_block_cache, ce); } } @@ -1427,6 +1451,13 @@ static struct inode *ext4_xattr_inode_create(handle_t *handle, uid_t owner[2] = { i_uid_read(inode), i_gid_read(inode) }; int err; + if (inode->i_sb->s_root == NULL) { + ext4_warning(inode->i_sb, + "refuse to create EA inode when umounting"); + WARN_ON(1); + return ERR_PTR(-EINVAL); + } + /* * Let the next inode be the goal, so we try and allocate the EA inode * in the same group, or nearby one. @@ -1446,6 +1477,9 @@ static struct inode *ext4_xattr_inode_create(handle_t *handle, if (!err) err = ext4_inode_attach_jinode(ea_inode); if (err) { + if (ext4_xattr_inode_dec_ref(handle, ea_inode)) + ext4_warning_inode(ea_inode, + "cleanup dec ref error %d", err); iput(ea_inode); return ERR_PTR(err); } @@ -1733,6 +1767,20 @@ static int ext4_xattr_set_entry(struct ext4_xattr_info *i, memmove(here, (void *)here + size, (void *)last - (void *)here + sizeof(__u32)); memset(last, 0, size); + + /* + * Update i_inline_off - moved ibody region might contain + * system.data attribute. Handling a failure here won't + * cause other complications for setting an xattr. + */ + if (!is_block && ext4_has_inline_data(inode)) { + ret = ext4_find_inline_data_nolock(inode); + if (ret) { + ext4_warning_inode(inode, + "unable to update i_inline_off"); + goto out; + } + } } else if (s->not_found) { /* Insert new name. */ size_t size = EXT4_XATTR_LEN(name_len); @@ -1872,6 +1920,8 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, #define header(x) ((struct ext4_xattr_header *)(x)) if (s->base) { + int offset = (char *)s->here - bs->bh->b_data; + BUFFER_TRACE(bs->bh, "get_write_access"); error = ext4_journal_get_write_access(handle, bs->bh); if (error) @@ -1886,9 +1936,20 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, * ext4_xattr_block_set() to reliably detect modified * block */ - if (ea_block_cache) - mb_cache_entry_delete(ea_block_cache, hash, - bs->bh->b_blocknr); + if (ea_block_cache) { + struct mb_cache_entry *oe; + + oe = mb_cache_entry_delete_or_get(ea_block_cache, + hash, bs->bh->b_blocknr); + if (oe) { + /* + * Xattr block is getting reused. Leave + * it alone. + */ + mb_cache_entry_put(ea_block_cache, oe); + goto clone_block; + } + } ea_bdebug(bs->bh, "modifying in-place"); error = ext4_xattr_set_entry(i, s, handle, inode, true /* is_block */); @@ -1903,50 +1964,47 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, if (error) goto cleanup; goto inserted; - } else { - int offset = (char *)s->here - bs->bh->b_data; + } +clone_block: + unlock_buffer(bs->bh); + ea_bdebug(bs->bh, "cloning"); + s->base = kmemdup(BHDR(bs->bh), bs->bh->b_size, GFP_NOFS); + error = -ENOMEM; + if (s->base == NULL) + goto cleanup; + s->first = ENTRY(header(s->base)+1); + header(s->base)->h_refcount = cpu_to_le32(1); + s->here = ENTRY(s->base + offset); + s->end = s->base + bs->bh->b_size; - unlock_buffer(bs->bh); - ea_bdebug(bs->bh, "cloning"); - s->base = kmalloc(bs->bh->b_size, GFP_NOFS); - error = -ENOMEM; - if (s->base == NULL) + /* + * If existing entry points to an xattr inode, we need + * to prevent ext4_xattr_set_entry() from decrementing + * ref count on it because the reference belongs to the + * original block. In this case, make the entry look + * like it has an empty value. + */ + if (!s->not_found && s->here->e_value_inum) { + ea_ino = le32_to_cpu(s->here->e_value_inum); + error = ext4_xattr_inode_iget(inode, ea_ino, + le32_to_cpu(s->here->e_hash), + &tmp_inode); + if (error) goto cleanup; - memcpy(s->base, BHDR(bs->bh), bs->bh->b_size); - s->first = ENTRY(header(s->base)+1); - header(s->base)->h_refcount = cpu_to_le32(1); - s->here = ENTRY(s->base + offset); - s->end = s->base + bs->bh->b_size; - - /* - * If existing entry points to an xattr inode, we need - * to prevent ext4_xattr_set_entry() from decrementing - * ref count on it because the reference belongs to the - * original block. In this case, make the entry look - * like it has an empty value. - */ - if (!s->not_found && s->here->e_value_inum) { - ea_ino = le32_to_cpu(s->here->e_value_inum); - error = ext4_xattr_inode_iget(inode, ea_ino, - le32_to_cpu(s->here->e_hash), - &tmp_inode); - if (error) - goto cleanup; - - if (!ext4_test_inode_state(tmp_inode, - EXT4_STATE_LUSTRE_EA_INODE)) { - /* - * Defer quota free call for previous - * inode until success is guaranteed. - */ - old_ea_inode_quota = le32_to_cpu( - s->here->e_value_size); - } - iput(tmp_inode); - s->here->e_value_inum = 0; - s->here->e_value_size = 0; + if (!ext4_test_inode_state(tmp_inode, + EXT4_STATE_LUSTRE_EA_INODE)) { + /* + * Defer quota free call for previous + * inode until success is guaranteed. + */ + old_ea_inode_quota = le32_to_cpu( + s->here->e_value_size); } + iput(tmp_inode); + + s->here->e_value_inum = 0; + s->here->e_value_size = 0; } } else { /* Allocate a buffer where we construct the new block. */ @@ -1997,8 +2055,9 @@ inserted: else { u32 ref; +#ifdef EXT4_XATTR_DEBUG WARN_ON_ONCE(dquot_initialize_needed(inode)); - +#endif /* The old block is released after updating the inode. */ error = dquot_alloc_block(inode, @@ -2013,18 +2072,13 @@ inserted: lock_buffer(new_bh); /* * We have to be careful about races with - * freeing, rehashing or adding references to - * xattr block. Once we hold buffer lock xattr - * block's state is stable so we can check - * whether the block got freed / rehashed or - * not. Since we unhash mbcache entry under - * buffer lock when freeing / rehashing xattr - * block, checking whether entry is still - * hashed is reliable. Same rules hold for - * e_reusable handling. + * adding references to xattr block. Once we + * hold buffer lock xattr block's state is + * stable so we can check the additional + * reference fits. */ - if (hlist_bl_unhashed(&ce->e_hash_list) || - !ce->e_reusable) { + ref = le32_to_cpu(BHDR(new_bh)->h_refcount) + 1; + if (ref > EXT4_XATTR_REFCOUNT_MAX) { /* * Undo everything and check mbcache * again. @@ -2039,10 +2093,9 @@ inserted: new_bh = NULL; goto inserted; } - ref = le32_to_cpu(BHDR(new_bh)->h_refcount) + 1; BHDR(new_bh)->h_refcount = cpu_to_le32(ref); - if (ref >= EXT4_XATTR_REFCOUNT_MAX) - ce->e_reusable = 0; + if (ref == EXT4_XATTR_REFCOUNT_MAX) + clear_bit(MBE_REUSABLE_B, &ce->e_flags); ea_bdebug(new_bh, "reusing; refcount now=%d", ref); ext4_xattr_block_csum_set(inode, new_bh); @@ -2066,23 +2119,16 @@ inserted: /* We need to allocate a new block */ ext4_fsblk_t goal, block; +#ifdef EXT4_XATTR_DEBUG WARN_ON_ONCE(dquot_initialize_needed(inode)); - +#endif goal = ext4_group_first_block_no(sb, EXT4_I(inode)->i_block_group); - - /* non-extent files can't have physical blocks past 2^32 */ - if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) - goal = goal & EXT4_MAX_BLOCK_FILE_PHYS; - block = ext4_new_meta_blocks(handle, inode, goal, 0, NULL, &error); if (error) goto cleanup; - if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) - BUG_ON(block > EXT4_MAX_BLOCK_FILE_PHYS); - ea_idebug(inode, "creating block %llu", (unsigned long long)block); @@ -2210,7 +2256,7 @@ int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i, return 0; } -int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode, +int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode, struct ext4_xattr_info *i, struct ext4_xattr_ibody_find *is) { @@ -2235,30 +2281,6 @@ int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode, return 0; } -static int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode, - struct ext4_xattr_info *i, - struct ext4_xattr_ibody_find *is) -{ - struct ext4_xattr_ibody_header *header; - struct ext4_xattr_search *s = &is->s; - int error; - - if (EXT4_I(inode)->i_extra_isize == 0) - return -ENOSPC; - error = ext4_xattr_set_entry(i, s, handle, inode, false /* is_block */); - if (error) - return error; - header = IHDR(inode, ext4_raw_inode(&is->iloc)); - if (!IS_LAST_ENTRY(s->first)) { - header->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC); - ext4_set_inode_state(inode, EXT4_STATE_XATTR); - } else { - header->h_magic = cpu_to_le32(0); - ext4_clear_inode_state(inode, EXT4_STATE_XATTR); - } - return 0; -} - static int ext4_xattr_value_same(struct ext4_xattr_search *s, struct ext4_xattr_info *i) { @@ -2571,13 +2593,13 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode, .in_inode = !!entry->e_value_inum, }; struct ext4_xattr_ibody_header *header = IHDR(inode, raw_inode); + int needs_kvfree = 0; int error; is = kzalloc(sizeof(struct ext4_xattr_ibody_find), GFP_NOFS); bs = kzalloc(sizeof(struct ext4_xattr_block_find), GFP_NOFS); - buffer = kmalloc(value_size, GFP_NOFS); b_entry_name = kmalloc(entry->e_name_len + 1, GFP_NOFS); - if (!is || !bs || !buffer || !b_entry_name) { + if (!is || !bs || !b_entry_name) { error = -ENOMEM; goto out; } @@ -2589,12 +2611,18 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode, /* Save the entry name and the entry value */ if (entry->e_value_inum) { + buffer = kvmalloc(value_size, GFP_NOFS); + if (!buffer) { + error = -ENOMEM; + goto out; + } + needs_kvfree = 1; error = ext4_xattr_inode_get(inode, entry, buffer, value_size); if (error) goto out; } else { size_t value_offs = le16_to_cpu(entry->e_value_offs); - memcpy(buffer, (void *)IFIRST(header) + value_offs, value_size); + buffer = (void *)IFIRST(header) + value_offs; } memcpy(b_entry_name, entry->e_name, entry->e_name_len); @@ -2609,25 +2637,26 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode, if (error) goto out; - /* Remove the chosen entry from the inode */ - error = ext4_xattr_ibody_set(handle, inode, &i, is); - if (error) - goto out; - i.value = buffer; i.value_len = value_size; error = ext4_xattr_block_find(inode, &i, bs); if (error) goto out; - /* Add entry which was removed from the inode into the block */ + /* Move ea entry from the inode into the block */ error = ext4_xattr_block_set(handle, inode, &i, bs); if (error) goto out; - error = 0; + + /* Remove the chosen entry from the inode */ + i.value = NULL; + i.value_len = 0; + error = ext4_xattr_ibody_set(handle, inode, &i, is); + out: kfree(b_entry_name); - kfree(buffer); + if (needs_kvfree && buffer) + kvfree(buffer); if (is) brelse(is->iloc.bh); if (bs) @@ -2802,6 +2831,9 @@ shift: (void *)header, total_ino); EXT4_I(inode)->i_extra_isize = new_extra_isize; + if (ext4_has_inline_data(inode)) + error = ext4_find_inline_data_nolock(inode); + cleanup: if (error && (mnt_count != le16_to_cpu(sbi->s_es->s_mnt_count))) { ext4_warning(inode->i_sb, "Unable to expand inode %lu. Delete some EAs or run e2fsck.", diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h index 990084e00374..66911f8a11f8 100644 --- a/fs/ext4/xattr.h +++ b/fs/ext4/xattr.h @@ -190,6 +190,7 @@ extern void ext4_xattr_inode_array_free(struct ext4_xattr_inode_array *array); extern int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize, struct ext4_inode *raw_inode, handle_t *handle); +extern void ext4_evict_ea_inode(struct inode *inode); extern const struct xattr_handler *ext4_xattr_handlers[]; @@ -198,9 +199,9 @@ extern int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i, extern int ext4_xattr_ibody_get(struct inode *inode, int name_index, const char *name, void *buffer, size_t buffer_size); -extern int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode, - struct ext4_xattr_info *i, - struct ext4_xattr_ibody_find *is); +extern int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode, + struct ext4_xattr_info *i, + struct ext4_xattr_ibody_find *is); extern struct mb_cache *ext4_xattr_create_cache(void); extern void ext4_xattr_destroy_cache(struct mb_cache *); diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index a563de5ccd21..621e0d4f1fbf 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -273,8 +273,15 @@ static int __f2fs_write_meta_page(struct page *page, trace_f2fs_writepage(page, META); - if (unlikely(f2fs_cp_error(sbi))) + if (unlikely(f2fs_cp_error(sbi))) { + if (is_sbi_flag_set(sbi, SBI_IS_CLOSE)) { + ClearPageUptodate(page); + dec_page_count(sbi, F2FS_DIRTY_META); + unlock_page(page); + return 0; + } goto redirty_out; + } if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) goto redirty_out; if (wbc->for_reclaim && page->index < GET_SUM_BLOCK(sbi, 0)) @@ -1185,7 +1192,8 @@ void f2fs_wait_on_all_pages_writeback(struct f2fs_sb_info *sbi) if (!get_pages(sbi, F2FS_WB_CP_DATA)) break; - if (unlikely(f2fs_cp_error(sbi))) + if (unlikely(f2fs_cp_error(sbi) && + !is_sbi_flag_set(sbi, SBI_IS_CLOSE))) break; io_schedule_timeout(5*HZ); diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index c63f5e32630e..419586809cef 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -464,7 +464,7 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio) } if (fio->io_wbc && !is_read_io(fio->op)) - wbc_account_io(fio->io_wbc, page, PAGE_SIZE); + wbc_account_io(fio->io_wbc, fio->page, PAGE_SIZE); bio_set_op_attrs(bio, fio->op, fio->op_flags); @@ -533,7 +533,7 @@ alloc_new: } if (fio->io_wbc) - wbc_account_io(fio->io_wbc, bio_page, PAGE_SIZE); + wbc_account_io(fio->io_wbc, fio->page, PAGE_SIZE); io->last_block_in_bio = fio->new_blkaddr; f2fs_trace_ios(fio, 0); @@ -1885,7 +1885,8 @@ static int __write_data_page(struct page *page, bool *submitted, * don't drop any dirty dentry pages for keeping lastest * directory structure. */ - if (S_ISDIR(inode->i_mode)) + if (S_ISDIR(inode->i_mode) && + !is_sbi_flag_set(sbi, SBI_IS_CLOSE)) goto redirty_out; goto out; } diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c index 36d6b561b524..e85ed4aa9d46 100644 --- a/fs/f2fs/extent_cache.c +++ b/fs/f2fs/extent_cache.c @@ -375,7 +375,8 @@ static bool f2fs_lookup_extent_tree(struct inode *inode, pgoff_t pgofs, struct extent_node *en; bool ret = false; - f2fs_bug_on(sbi, !et); + if (!et) + return false; trace_f2fs_lookup_extent_tree_start(inode, pgofs); diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 2a7249496c57..043ce96ac127 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -2892,6 +2892,7 @@ int f2fs_precache_extents(struct inode *inode) return -EOPNOTSUPP; map.m_lblk = 0; + map.m_pblk = 0; map.m_next_pgofs = NULL; map.m_next_extent = &m_next_extent; map.m_seg_type = NO_CHECK_TYPE; diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index ff447bbb5248..fb4494c54484 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -958,7 +958,8 @@ next_step: if (phase == 3) { inode = f2fs_iget(sb, dni.ino); - if (IS_ERR(inode) || is_bad_inode(inode)) + if (IS_ERR(inode) || is_bad_inode(inode) || + special_file(inode->i_mode)) continue; if (!down_write_trylock( diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index 6bf78cf63ea2..7ad78aa9c7b8 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -408,18 +408,17 @@ static int f2fs_move_inline_dirents(struct inode *dir, struct page *ipage, dentry_blk = page_address(page); + /* + * Start by zeroing the full block, to ensure that all unused space is + * zeroed and no uninitialized memory is leaked to disk. + */ + memset(dentry_blk, 0, F2FS_BLKSIZE); + make_dentry_ptr_inline(dir, &src, inline_dentry); make_dentry_ptr_block(dir, &dst, dentry_blk); /* copy data from inline dentry block to new dentry block */ memcpy(dst.bitmap, src.bitmap, src.nr_bitmap); - memset(dst.bitmap + src.nr_bitmap, 0, dst.nr_bitmap - src.nr_bitmap); - /* - * we do not need to zero out remainder part of dentry and filename - * field, since we have used bitmap for marking the usage status of - * them, besides, we can also ignore copying/zeroing reserved space - * of dentry block, because them haven't been used so far. - */ memcpy(dst.dentry, src.dentry, SIZE_OF_DIR_ENTRY * src.max); memcpy(dst.filename, src.filename, src.max * F2FS_SLOT_LEN); diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index 9e4c38481830..2eb7b0e2b34a 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -979,7 +979,7 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, } if (old_dir_entry) { - if (old_dir != new_dir && !whiteout) + if (old_dir != new_dir) f2fs_set_link(old_inode, old_dir_entry, old_dir_page, new_dir); else diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 2c28f488ac2f..9911f780e013 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -879,8 +879,10 @@ static int truncate_dnode(struct dnode_of_data *dn) dn->ofs_in_node = 0; f2fs_truncate_data_blocks(dn); err = truncate_node(dn); - if (err) + if (err) { + f2fs_put_page(page, 1); return err; + } return 1; } diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 6fbf0471323e..7596fce92bef 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -1382,7 +1382,7 @@ static int __issue_discard_cmd(struct f2fs_sb_info *sbi, if (i + 1 < dpolicy->granularity) break; - if (i < DEFAULT_DISCARD_GRANULARITY && dpolicy->ordered) + if (i + 1 < DEFAULT_DISCARD_GRANULARITY && dpolicy->ordered) return __issue_discard_cmd_orderly(sbi, dpolicy); pend_list = &dcc->pend_list[i]; diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index 64352d2833e2..db3e76b35607 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -717,6 +717,12 @@ static int __f2fs_setxattr(struct inode *inode, int index, memcpy(pval, value, size); last->e_value_size = cpu_to_le16(size); new_hsize += newsize; + /* + * Explicitly add the null terminator. The unused xattr space + * is supposed to always be zeroed, which would make this + * unnecessary, but don't depend on that. + */ + *(u32 *)((u8 *)last + newsize) = 0; } error = write_all_xattrs(inode, new_hsize, base_addr, ipage); diff --git a/fs/fat/dir.c b/fs/fat/dir.c index 397f95b65881..947fbeb59db1 100644 --- a/fs/fat/dir.c +++ b/fs/fat/dir.c @@ -1302,7 +1302,7 @@ int fat_add_entries(struct inode *dir, void *slots, int nr_slots, struct super_block *sb = dir->i_sb; struct msdos_sb_info *sbi = MSDOS_SB(sb); struct buffer_head *bh, *prev, *bhs[3]; /* 32*slots (672bytes) */ - struct msdos_dir_entry *uninitialized_var(de); + struct msdos_dir_entry *de; int err, free_slots, i, nr_bhs; loff_t pos, i_pos; diff --git a/fs/file.c b/fs/file.c index d6ca500a1053..928ba7b8df1e 100644 --- a/fs/file.c +++ b/fs/file.c @@ -627,6 +627,7 @@ int __close_fd(struct files_struct *files, unsigned fd) fdt = files_fdtable(files); if (fd >= fdt->max_fds) goto out_unlock; + fd = array_index_nospec(fd, fdt->max_fds); file = fdt->fd[fd]; if (!file) goto out_unlock; diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 4d687e2e2373..61dc0dc139f8 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -702,7 +702,7 @@ void wbc_detach_inode(struct writeback_control *wbc) * is okay. The main goal is avoiding keeping an inode on * the wrong wb for an extended period of time. */ - if (hweight32(history) > WB_FRN_HIST_THR_SLOTS) + if (hweight16(history) > WB_FRN_HIST_THR_SLOTS) inode_switch_wbs(inode, max_id); } diff --git a/fs/fuse/control.c b/fs/fuse/control.c index acc35819aae6..af253127b309 100644 --- a/fs/fuse/control.c +++ b/fs/fuse/control.c @@ -117,7 +117,7 @@ static ssize_t fuse_conn_max_background_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { - unsigned uninitialized_var(val); + unsigned val; ssize_t ret; ret = fuse_conn_limit_write(file, buf, count, ppos, &val, diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c index e10e2b62ccf4..acd985aa2cba 100644 --- a/fs/fuse/cuse.c +++ b/fs/fuse/cuse.c @@ -269,7 +269,7 @@ static int cuse_parse_one(char **pp, char *end, char **keyp, char **valp) static int cuse_parse_devinfo(char *p, size_t len, struct cuse_devinfo *devinfo) { char *end = p + len; - char *uninitialized_var(key), *uninitialized_var(val); + char *key, *val; int rc; while (true) { diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 6098e0c7f87b..16252727ec2e 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -232,7 +232,7 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags) spin_unlock(&fc->lock); } kfree(forget); - if (ret == -ENOMEM) + if (ret == -ENOMEM || ret == -EINTR) goto out; if (ret || fuse_invalid_attr(&outarg.attr) || (outarg.attr.mode ^ inode->i_mode) & S_IFMT) @@ -1314,8 +1314,16 @@ retry: dput(dentry); dentry = alias; } - if (IS_ERR(dentry)) + if (IS_ERR(dentry)) { + if (!IS_ERR(inode)) { + struct fuse_inode *fi = get_fuse_inode(inode); + + spin_lock(&fc->lock); + fi->nlookup--; + spin_unlock(&fc->lock); + } return PTR_ERR(dentry); + } } if (fc->readdirplus_auto) set_bit(FUSE_I_INIT_RDPLUS, &get_fuse_inode(inode)->state); diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 599a6eeed02e..c629ccafb2b0 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -2774,7 +2774,7 @@ static void fuse_register_polled_file(struct fuse_conn *fc, { spin_lock(&fc->lock); if (RB_EMPTY_NODE(&ff->polled_node)) { - struct rb_node **link, *uninitialized_var(parent); + struct rb_node **link, *parent; link = fuse_find_polled_node(fc, ff->kh, &parent); BUG_ON(*link); diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 31e8270d0b26..910bfc39dc4b 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -179,7 +179,6 @@ static int __gfs2_jdata_writepage(struct page *page, struct writeback_control *w { struct inode *inode = page->mapping->host; struct gfs2_inode *ip = GFS2_I(inode); - struct gfs2_sbd *sdp = GFS2_SB(inode); if (PageChecked(page)) { ClearPageChecked(page); @@ -187,7 +186,7 @@ static int __gfs2_jdata_writepage(struct page *page, struct writeback_control *w create_empty_buffers(page, inode->i_sb->s_blocksize, BIT(BH_Dirty)|BIT(BH_Uptodate)); } - gfs2_page_add_databufs(ip, page, 0, sdp->sd_vfs->s_blocksize); + gfs2_page_add_databufs(ip, page, 0, PAGE_SIZE); } return gfs2_write_full_page(page, gfs2_get_block_noalloc, wbc); } @@ -360,7 +359,7 @@ static int gfs2_write_cache_jdata(struct address_space *mapping, int done = 0; struct pagevec pvec; int nr_pages; - pgoff_t uninitialized_var(writeback_index); + pgoff_t writeback_index; pgoff_t index; pgoff_t end; pgoff_t done_index; @@ -481,8 +480,6 @@ int stuffed_readpage(struct gfs2_inode *ip, struct page *page) return error; kaddr = kmap_atomic(page); - if (dsize > gfs2_max_stuffed_size(ip)) - dsize = gfs2_max_stuffed_size(ip); memcpy(kaddr, dibh->b_data + sizeof(struct gfs2_dinode), dsize); memset(kaddr + dsize, 0, PAGE_SIZE - dsize); kunmap_atomic(kaddr); diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 150cec85c416..729f36fdced1 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -72,9 +72,6 @@ static int gfs2_unstuffer_page(struct gfs2_inode *ip, struct buffer_head *dibh, void *kaddr = kmap(page); u64 dsize = i_size_read(inode); - if (dsize > gfs2_max_stuffed_size(ip)) - dsize = gfs2_max_stuffed_size(ip); - memcpy(kaddr, dibh->b_data + sizeof(struct gfs2_dinode), dsize); memset(kaddr + dsize, 0, PAGE_SIZE - dsize); kunmap(page); @@ -1757,7 +1754,7 @@ static int punch_hole(struct gfs2_inode *ip, u64 offset, u64 length) u64 lblock = (offset + (1 << bsize_shift) - 1) >> bsize_shift; __u16 start_list[GFS2_MAX_META_HEIGHT]; __u16 __end_list[GFS2_MAX_META_HEIGHT], *end_list = NULL; - unsigned int start_aligned, uninitialized_var(end_aligned); + unsigned int start_aligned, end_aligned; unsigned int strip_h = ip->i_height - 1; u32 btotal = 0; int ret, state; diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index 20f08f4391c9..ff35cc365930 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -339,6 +339,7 @@ static int inode_go_demote_ok(const struct gfs2_glock *gl) static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf) { + struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); const struct gfs2_dinode *str = buf; struct timespec64 atime; u16 height, depth; @@ -378,7 +379,7 @@ static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf) /* i_diskflags and i_eattr must be set before gfs2_set_inode_flags() */ gfs2_set_inode_flags(&ip->i_inode); height = be16_to_cpu(str->di_height); - if (unlikely(height > GFS2_MAX_META_HEIGHT)) + if (unlikely(height > sdp->sd_max_height)) goto corrupt; ip->i_height = (u8)height; @@ -388,6 +389,9 @@ static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf) ip->i_depth = (u8)depth; ip->i_entries = be32_to_cpu(str->di_entries); + if (gfs2_is_stuffed(ip) && ip->i_inode.i_size > gfs2_max_stuffed_size(ip)) + goto corrupt; + if (S_ISREG(ip->i_inode.i_mode)) gfs2_set_aops(&ip->i_inode); diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index dd0f9bc13164..9f753595d90e 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -434,6 +434,17 @@ static int qd_check_sync(struct gfs2_sbd *sdp, struct gfs2_quota_data *qd, (sync_gen && (qd->qd_sync_gen >= *sync_gen))) return 0; + /* + * If qd_change is 0 it means a pending quota change was negated. + * We should not sync it, but we still have a qd reference and slot + * reference taken by gfs2_quota_change -> do_qc that need to be put. + */ + if (!qd->qd_change && test_and_clear_bit(QDF_CHANGE, &qd->qd_flags)) { + slot_put(qd); + qd_put(qd); + return 0; + } + if (!lockref_get_not_dead(&qd->qd_lockref)) return 0; diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 3cc2237e5896..29157f7d9663 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -1374,7 +1374,14 @@ static int gfs2_show_options(struct seq_file *s, struct dentry *root) { struct gfs2_sbd *sdp = root->d_sb->s_fs_info; struct gfs2_args *args = &sdp->sd_args; - int val; + unsigned int logd_secs, statfs_slow, statfs_quantum, quota_quantum; + + spin_lock(&sdp->sd_tune.gt_spin); + logd_secs = sdp->sd_tune.gt_logd_secs; + quota_quantum = sdp->sd_tune.gt_quota_quantum; + statfs_quantum = sdp->sd_tune.gt_statfs_quantum; + statfs_slow = sdp->sd_tune.gt_statfs_slow; + spin_unlock(&sdp->sd_tune.gt_spin); if (is_ancestor(root, sdp->sd_master_dir)) seq_puts(s, ",meta"); @@ -1429,17 +1436,14 @@ static int gfs2_show_options(struct seq_file *s, struct dentry *root) } if (args->ar_discard) seq_puts(s, ",discard"); - val = sdp->sd_tune.gt_logd_secs; - if (val != 30) - seq_printf(s, ",commit=%d", val); - val = sdp->sd_tune.gt_statfs_quantum; - if (val != 30) - seq_printf(s, ",statfs_quantum=%d", val); - else if (sdp->sd_tune.gt_statfs_slow) + if (logd_secs != 30) + seq_printf(s, ",commit=%d", logd_secs); + if (statfs_quantum != 30) + seq_printf(s, ",statfs_quantum=%d", statfs_quantum); + else if (statfs_slow) seq_puts(s, ",statfs_quantum=0"); - val = sdp->sd_tune.gt_quota_quantum; - if (val != 60) - seq_printf(s, ",quota_quantum=%d", val); + if (quota_quantum != 60) + seq_printf(s, ",quota_quantum=%d", quota_quantum); if (args->ar_statfs_percent) seq_printf(s, ",statfs_percent=%d", args->ar_statfs_percent); if (args->ar_errors != GFS2_ERRORS_DEFAULT) { @@ -1586,6 +1590,14 @@ static void gfs2_evict_inode(struct inode *inode) if (inode->i_nlink || sb_rdonly(sb)) goto out; + /* + * In case of an incomplete mount, gfs2_evict_inode() may be called for + * system files without having an active journal to write to. In that + * case, skip the filesystem evict. + */ + if (!sdp->sd_jdesc) + goto out; + if (test_bit(GIF_ALLOC_FAILED, &ip->i_flags)) { BUG_ON(!gfs2_glock_is_locked_by_me(ip->i_gl)); gfs2_holder_mark_uninitialized(&gh); diff --git a/fs/hfs/bnode.c b/fs/hfs/bnode.c index c0a73a6ffb28..397e02a56697 100644 --- a/fs/hfs/bnode.c +++ b/fs/hfs/bnode.c @@ -281,6 +281,7 @@ static struct hfs_bnode *__hfs_bnode_create(struct hfs_btree *tree, u32 cnid) tree->node_hash[hash] = node; tree->node_hash_cnt++; } else { + hfs_bnode_get(node2); spin_unlock(&tree->hash_lock); kfree(node); wait_event(node2->lock_wq, !test_bit(HFS_BNODE_NEW, &node2->flags)); diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index da243c84e93b..ee2ea5532e69 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -453,14 +453,16 @@ int hfs_write_inode(struct inode *inode, struct writeback_control *wbc) /* panic? */ return -EIO; + res = -EIO; + if (HFS_I(main_inode)->cat_key.CName.len > HFS_NAMELEN) + goto out; fd.search_key->cat = HFS_I(main_inode)->cat_key; if (hfs_brec_find(&fd)) - /* panic? */ goto out; if (S_ISDIR(main_inode->i_mode)) { if (fd.entrylength < sizeof(struct hfs_cat_dir)) - /* panic? */; + goto out; hfs_bnode_read(fd.bnode, &rec, fd.entryoffset, sizeof(struct hfs_cat_dir)); if (rec.type != HFS_CDR_DIR || @@ -473,6 +475,8 @@ int hfs_write_inode(struct inode *inode, struct writeback_control *wbc) hfs_bnode_write(fd.bnode, &rec, fd.entryoffset, sizeof(struct hfs_cat_dir)); } else if (HFS_IS_RSRC(inode)) { + if (fd.entrylength < sizeof(struct hfs_cat_file)) + goto out; hfs_bnode_read(fd.bnode, &rec, fd.entryoffset, sizeof(struct hfs_cat_file)); hfs_inode_write_fork(inode, rec.file.RExtRec, @@ -481,7 +485,7 @@ int hfs_write_inode(struct inode *inode, struct writeback_control *wbc) sizeof(struct hfs_cat_file)); } else { if (fd.entrylength < sizeof(struct hfs_cat_file)) - /* panic? */; + goto out; hfs_bnode_read(fd.bnode, &rec, fd.entryoffset, sizeof(struct hfs_cat_file)); if (rec.type != HFS_CDR_FIL || @@ -498,9 +502,10 @@ int hfs_write_inode(struct inode *inode, struct writeback_control *wbc) hfs_bnode_write(fd.bnode, &rec, fd.entryoffset, sizeof(struct hfs_cat_file)); } + res = 0; out: hfs_find_exit(&fd); - return 0; + return res; } static struct dentry *hfs_file_lookup(struct inode *dir, struct dentry *dentry, diff --git a/fs/hfs/trans.c b/fs/hfs/trans.c index 39f5e343bf4d..fdb0edb8a607 100644 --- a/fs/hfs/trans.c +++ b/fs/hfs/trans.c @@ -109,7 +109,7 @@ void hfs_asc2mac(struct super_block *sb, struct hfs_name *out, const struct qstr if (nls_io) { wchar_t ch; - while (srclen > 0) { + while (srclen > 0 && dstlen > 0) { size = nls_io->char2uni(src, srclen, &ch); if (size < 0) { ch = '?'; diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h index dd7ad9f13e3a..db2e1c750199 100644 --- a/fs/hfsplus/hfsplus_fs.h +++ b/fs/hfsplus/hfsplus_fs.h @@ -198,6 +198,8 @@ struct hfsplus_sb_info { #define HFSPLUS_SB_HFSX 3 #define HFSPLUS_SB_CASEFOLD 4 #define HFSPLUS_SB_NOBARRIER 5 +#define HFSPLUS_SB_UID 6 +#define HFSPLUS_SB_GID 7 static inline struct hfsplus_sb_info *HFSPLUS_SB(struct super_block *sb) { diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index d7ab9d8c4b67..a1d4ad584b10 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -187,11 +187,11 @@ static void hfsplus_get_perms(struct inode *inode, mode = be16_to_cpu(perms->mode); i_uid_write(inode, be32_to_cpu(perms->owner)); - if (!i_uid_read(inode) && !mode) + if ((test_bit(HFSPLUS_SB_UID, &sbi->flags)) || (!i_uid_read(inode) && !mode)) inode->i_uid = sbi->uid; i_gid_write(inode, be32_to_cpu(perms->group)); - if (!i_gid_read(inode) && !mode) + if ((test_bit(HFSPLUS_SB_GID, &sbi->flags)) || (!i_gid_read(inode) && !mode)) inode->i_gid = sbi->gid; if (dir) { @@ -476,8 +476,11 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd) if (type == HFSPLUS_FOLDER) { struct hfsplus_cat_folder *folder = &entry.folder; - if (fd->entrylength < sizeof(struct hfsplus_cat_folder)) - /* panic? */; + if (fd->entrylength < sizeof(struct hfsplus_cat_folder)) { + pr_err("bad catalog folder entry\n"); + res = -EIO; + goto out; + } hfs_bnode_read(fd->bnode, &entry, fd->entryoffset, sizeof(struct hfsplus_cat_folder)); hfsplus_get_perms(inode, &folder->permissions, 1); @@ -497,8 +500,11 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd) } else if (type == HFSPLUS_FILE) { struct hfsplus_cat_file *file = &entry.file; - if (fd->entrylength < sizeof(struct hfsplus_cat_file)) - /* panic? */; + if (fd->entrylength < sizeof(struct hfsplus_cat_file)) { + pr_err("bad catalog file entry\n"); + res = -EIO; + goto out; + } hfs_bnode_read(fd->bnode, &entry, fd->entryoffset, sizeof(struct hfsplus_cat_file)); @@ -529,6 +535,7 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd) pr_err("bad catalog entry used to create inode\n"); res = -EIO; } +out: return res; } @@ -537,6 +544,7 @@ int hfsplus_cat_write_inode(struct inode *inode) struct inode *main_inode = inode; struct hfs_find_data fd; hfsplus_cat_entry entry; + int res = 0; if (HFSPLUS_IS_RSRC(inode)) main_inode = HFSPLUS_I(inode)->rsrc_inode; @@ -555,8 +563,11 @@ int hfsplus_cat_write_inode(struct inode *inode) if (S_ISDIR(main_inode->i_mode)) { struct hfsplus_cat_folder *folder = &entry.folder; - if (fd.entrylength < sizeof(struct hfsplus_cat_folder)) - /* panic? */; + if (fd.entrylength < sizeof(struct hfsplus_cat_folder)) { + pr_err("bad catalog folder entry\n"); + res = -EIO; + goto out; + } hfs_bnode_read(fd.bnode, &entry, fd.entryoffset, sizeof(struct hfsplus_cat_folder)); /* simple node checks? */ @@ -581,8 +592,11 @@ int hfsplus_cat_write_inode(struct inode *inode) } else { struct hfsplus_cat_file *file = &entry.file; - if (fd.entrylength < sizeof(struct hfsplus_cat_file)) - /* panic? */; + if (fd.entrylength < sizeof(struct hfsplus_cat_file)) { + pr_err("bad catalog file entry\n"); + res = -EIO; + goto out; + } hfs_bnode_read(fd.bnode, &entry, fd.entryoffset, sizeof(struct hfsplus_cat_file)); hfsplus_inode_write_fork(inode, &file->data_fork); @@ -603,5 +617,5 @@ int hfsplus_cat_write_inode(struct inode *inode) set_bit(HFSPLUS_I_CAT_DIRTY, &HFSPLUS_I(inode)->flags); out: hfs_find_exit(&fd); - return 0; + return res; } diff --git a/fs/hfsplus/options.c b/fs/hfsplus/options.c index 047e05c57560..c94a58762ad6 100644 --- a/fs/hfsplus/options.c +++ b/fs/hfsplus/options.c @@ -140,6 +140,8 @@ int hfsplus_parse_options(char *input, struct hfsplus_sb_info *sbi) if (!uid_valid(sbi->uid)) { pr_err("invalid uid specified\n"); return 0; + } else { + set_bit(HFSPLUS_SB_UID, &sbi->flags); } break; case opt_gid: @@ -151,6 +153,8 @@ int hfsplus_parse_options(char *input, struct hfsplus_sb_info *sbi) if (!gid_valid(sbi->gid)) { pr_err("invalid gid specified\n"); return 0; + } else { + set_bit(HFSPLUS_SB_GID, &sbi->flags); } break; case opt_part: diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c index eb4535eba95d..3b1356b10a47 100644 --- a/fs/hfsplus/super.c +++ b/fs/hfsplus/super.c @@ -294,11 +294,11 @@ static void hfsplus_put_super(struct super_block *sb) hfsplus_sync_fs(sb, 1); } + iput(sbi->alloc_file); + iput(sbi->hidden_dir); hfs_btree_close(sbi->attr_tree); hfs_btree_close(sbi->cat_tree); hfs_btree_close(sbi->ext_tree); - iput(sbi->alloc_file); - iput(sbi->hidden_dir); kfree(sbi->s_vhdr_buf); kfree(sbi->s_backup_vhdr_buf); unload_nls(sbi->nls); diff --git a/fs/hfsplus/unicode.c b/fs/hfsplus/unicode.c index c8d1b2be7854..73342c925a4b 100644 --- a/fs/hfsplus/unicode.c +++ b/fs/hfsplus/unicode.c @@ -398,7 +398,7 @@ int hfsplus_hash_dentry(const struct dentry *dentry, struct qstr *str) astr = str->name; len = str->len; while (len > 0) { - int uninitialized_var(dsize); + int dsize; size = asc2unichar(sb, astr, len, &c); astr += size; len -= size; diff --git a/fs/iomap.c b/fs/iomap.c index ac7b2152c3ad..04e82b6bd9bf 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -109,6 +109,7 @@ static struct iomap_page * iomap_page_create(struct inode *inode, struct page *page) { struct iomap_page *iop = to_iomap_page(page); + unsigned int nr_blocks = PAGE_SIZE / i_blocksize(inode); if (iop || i_blocksize(inode) == PAGE_SIZE) return iop; @@ -118,6 +119,8 @@ iomap_page_create(struct inode *inode, struct page *page) atomic_set(&iop->write_count, 0); spin_lock_init(&iop->uptodate_lock); bitmap_zero(iop->uptodate, PAGE_SIZE / SECTOR_SIZE); + if (PageUptodate(page)) + bitmap_fill(iop->uptodate, nr_blocks); /* * migrate_page_move_mapping() assumes that pages with private data have diff --git a/fs/isofs/namei.c b/fs/isofs/namei.c index 558e7c51ce0d..58f80e1b3ac0 100644 --- a/fs/isofs/namei.c +++ b/fs/isofs/namei.c @@ -153,8 +153,8 @@ isofs_find_entry(struct inode *dir, struct dentry *dentry, struct dentry *isofs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { int found; - unsigned long uninitialized_var(block); - unsigned long uninitialized_var(offset); + unsigned long block; + unsigned long offset; struct inode *inode; struct page *page; diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 8a50722bca29..629928b19e48 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1375,9 +1375,11 @@ static int jbd2_write_superblock(journal_t *journal, int write_flags) return -EIO; } - trace_jbd2_write_superblock(journal, write_flags); if (!(journal->j_flags & JBD2_BARRIER)) write_flags &= ~(REQ_FUA | REQ_PREFLUSH); + + trace_jbd2_write_superblock(journal, write_flags); + if (buffer_write_io_error(bh)) { /* * Oh, dear. A previous attempt to write the journal diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c index a4967b27ffb6..ed923a9765c2 100644 --- a/fs/jbd2/recovery.c +++ b/fs/jbd2/recovery.c @@ -247,6 +247,8 @@ int jbd2_journal_recover(journal_t *journal) journal_superblock_t * sb; struct recovery_info info; + errseq_t wb_err; + struct address_space *mapping; memset(&info, 0, sizeof(info)); sb = journal->j_superblock; @@ -264,6 +266,9 @@ int jbd2_journal_recover(journal_t *journal) return 0; } + wb_err = 0; + mapping = journal->j_fs_dev->bd_inode->i_mapping; + errseq_check_and_advance(&mapping->wb_err, &wb_err); err = do_one_pass(journal, &info, PASS_SCAN); if (!err) err = do_one_pass(journal, &info, PASS_REVOKE); @@ -284,6 +289,9 @@ int jbd2_journal_recover(journal_t *journal) err2 = sync_blockdev(journal->j_fs_dev); if (!err) err = err2; + err2 = errseq_check_and_advance(&mapping->wb_err, &wb_err); + if (!err) + err = err2; /* Make sure all replayed data is on permanent storage */ if (journal->j_flags & JBD2_BARRIER) { err2 = blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL); diff --git a/fs/jffs2/build.c b/fs/jffs2/build.c index 837cd55fd4c5..6ae9d6fefb86 100644 --- a/fs/jffs2/build.c +++ b/fs/jffs2/build.c @@ -211,7 +211,10 @@ static int jffs2_build_filesystem(struct jffs2_sb_info *c) ic->scan_dents = NULL; cond_resched(); } - jffs2_build_xattr_subsystem(c); + ret = jffs2_build_xattr_subsystem(c); + if (ret) + goto exit; + c->flags &= ~JFFS2_SB_FLAG_BUILDING; dbg_fsbuild("FS build complete\n"); diff --git a/fs/jffs2/erase.c b/fs/jffs2/erase.c index 83b8f06b4a64..7e9abdb89712 100644 --- a/fs/jffs2/erase.c +++ b/fs/jffs2/erase.c @@ -401,7 +401,7 @@ static void jffs2_mark_erased_block(struct jffs2_sb_info *c, struct jffs2_eraseb { size_t retlen; int ret; - uint32_t uninitialized_var(bad_offset); + uint32_t bad_offset; switch (jffs2_block_check_erase(c, jeb, &bad_offset)) { case -EAGAIN: goto refile; diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c index 3047872fdac9..bf3d8a4516a5 100644 --- a/fs/jffs2/file.c +++ b/fs/jffs2/file.c @@ -137,19 +137,18 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode); struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb); pgoff_t index = pos >> PAGE_SHIFT; - uint32_t pageofs = index << PAGE_SHIFT; int ret = 0; jffs2_dbg(1, "%s()\n", __func__); - if (pageofs > inode->i_size) { - /* Make new hole frag from old EOF to new page */ + if (pos > inode->i_size) { + /* Make new hole frag from old EOF to new position */ struct jffs2_raw_inode ri; struct jffs2_full_dnode *fn; uint32_t alloc_len; - jffs2_dbg(1, "Writing new hole frag 0x%x-0x%x between current EOF and new page\n", - (unsigned int)inode->i_size, pageofs); + jffs2_dbg(1, "Writing new hole frag 0x%x-0x%x between current EOF and new position\n", + (unsigned int)inode->i_size, (uint32_t)pos); ret = jffs2_reserve_space(c, sizeof(ri), &alloc_len, ALLOC_NORMAL, JFFS2_SUMMARY_INODE_SIZE); @@ -169,10 +168,10 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, ri.mode = cpu_to_jemode(inode->i_mode); ri.uid = cpu_to_je16(i_uid_read(inode)); ri.gid = cpu_to_je16(i_gid_read(inode)); - ri.isize = cpu_to_je32(max((uint32_t)inode->i_size, pageofs)); + ri.isize = cpu_to_je32((uint32_t)pos); ri.atime = ri.ctime = ri.mtime = cpu_to_je32(JFFS2_NOW()); ri.offset = cpu_to_je32(inode->i_size); - ri.dsize = cpu_to_je32(pageofs - inode->i_size); + ri.dsize = cpu_to_je32((uint32_t)pos - inode->i_size); ri.csize = cpu_to_je32(0); ri.compr = JFFS2_COMPR_ZERO; ri.node_crc = cpu_to_je32(crc32(0, &ri, sizeof(ri)-8)); @@ -202,7 +201,7 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, goto out_err; } jffs2_complete_reservation(c); - inode->i_size = pageofs; + inode->i_size = pos; mutex_unlock(&f->sem); } diff --git a/fs/jffs2/xattr.c b/fs/jffs2/xattr.c index da3e18503c65..acb4492f5970 100644 --- a/fs/jffs2/xattr.c +++ b/fs/jffs2/xattr.c @@ -772,10 +772,10 @@ void jffs2_clear_xattr_subsystem(struct jffs2_sb_info *c) } #define XREF_TMPHASH_SIZE (128) -void jffs2_build_xattr_subsystem(struct jffs2_sb_info *c) +int jffs2_build_xattr_subsystem(struct jffs2_sb_info *c) { struct jffs2_xattr_ref *ref, *_ref; - struct jffs2_xattr_ref *xref_tmphash[XREF_TMPHASH_SIZE]; + struct jffs2_xattr_ref **xref_tmphash; struct jffs2_xattr_datum *xd, *_xd; struct jffs2_inode_cache *ic; struct jffs2_raw_node_ref *raw; @@ -784,9 +784,12 @@ void jffs2_build_xattr_subsystem(struct jffs2_sb_info *c) BUG_ON(!(c->flags & JFFS2_SB_FLAG_BUILDING)); + xref_tmphash = kcalloc(XREF_TMPHASH_SIZE, + sizeof(struct jffs2_xattr_ref *), GFP_KERNEL); + if (!xref_tmphash) + return -ENOMEM; + /* Phase.1 : Merge same xref */ - for (i=0; i < XREF_TMPHASH_SIZE; i++) - xref_tmphash[i] = NULL; for (ref=c->xref_temp; ref; ref=_ref) { struct jffs2_xattr_ref *tmp; @@ -884,6 +887,8 @@ void jffs2_build_xattr_subsystem(struct jffs2_sb_info *c) "%u of xref (%u dead, %u orphan) found.\n", xdatum_count, xdatum_unchecked_count, xdatum_orphan_count, xref_count, xref_dead_count, xref_orphan_count); + kfree(xref_tmphash); + return 0; } struct jffs2_xattr_datum *jffs2_setup_xattr_datum(struct jffs2_sb_info *c, diff --git a/fs/jffs2/xattr.h b/fs/jffs2/xattr.h index 720007b2fd65..1b5030a3349d 100644 --- a/fs/jffs2/xattr.h +++ b/fs/jffs2/xattr.h @@ -71,7 +71,7 @@ static inline int is_xattr_ref_dead(struct jffs2_xattr_ref *ref) #ifdef CONFIG_JFFS2_FS_XATTR extern void jffs2_init_xattr_subsystem(struct jffs2_sb_info *c); -extern void jffs2_build_xattr_subsystem(struct jffs2_sb_info *c); +extern int jffs2_build_xattr_subsystem(struct jffs2_sb_info *c); extern void jffs2_clear_xattr_subsystem(struct jffs2_sb_info *c); extern struct jffs2_xattr_datum *jffs2_setup_xattr_datum(struct jffs2_sb_info *c, @@ -103,7 +103,7 @@ extern ssize_t jffs2_listxattr(struct dentry *, char *, size_t); #else #define jffs2_init_xattr_subsystem(c) -#define jffs2_build_xattr_subsystem(c) +#define jffs2_build_xattr_subsystem(c) (0) #define jffs2_clear_xattr_subsystem(c) #define jffs2_xattr_do_crccheck_inode(c, ic) diff --git a/fs/jfs/jfs_dmap.c b/fs/jfs/jfs_dmap.c index 1014f2a24697..2f452b5ee731 100644 --- a/fs/jfs/jfs_dmap.c +++ b/fs/jfs/jfs_dmap.c @@ -100,7 +100,7 @@ static int dbAllocCtl(struct bmap * bmp, s64 nblocks, int l2nb, s64 blkno, static int dbExtend(struct inode *ip, s64 blkno, s64 nblocks, s64 addnblocks); static int dbFindBits(u32 word, int l2nb); static int dbFindCtl(struct bmap * bmp, int l2nb, int level, s64 * blkno); -static int dbFindLeaf(dmtree_t * tp, int l2nb, int *leafidx); +static int dbFindLeaf(dmtree_t *tp, int l2nb, int *leafidx, bool is_ctl); static int dbFreeBits(struct bmap * bmp, struct dmap * dp, s64 blkno, int nblocks); static int dbFreeDmap(struct bmap * bmp, struct dmap * dp, s64 blkno, @@ -168,7 +168,7 @@ int dbMount(struct inode *ipbmap) struct bmap *bmp; struct dbmap_disk *dbmp_le; struct metapage *mp; - int i; + int i, err; /* * allocate/initialize the in-memory bmap descriptor @@ -183,30 +183,53 @@ int dbMount(struct inode *ipbmap) BMAPBLKNO << JFS_SBI(ipbmap->i_sb)->l2nbperpage, PSIZE, 0); if (mp == NULL) { - kfree(bmp); - return -EIO; + err = -EIO; + goto err_kfree_bmp; } /* copy the on-disk bmap descriptor to its in-memory version. */ dbmp_le = (struct dbmap_disk *) mp->data; bmp->db_mapsize = le64_to_cpu(dbmp_le->dn_mapsize); bmp->db_nfree = le64_to_cpu(dbmp_le->dn_nfree); + bmp->db_l2nbperpage = le32_to_cpu(dbmp_le->dn_l2nbperpage); + if (bmp->db_l2nbperpage > L2PSIZE - L2MINBLOCKSIZE || + bmp->db_l2nbperpage < 0) { + err = -EINVAL; + goto err_release_metapage; + } + bmp->db_numag = le32_to_cpu(dbmp_le->dn_numag); if (!bmp->db_numag) { - release_metapage(mp); - kfree(bmp); - return -EINVAL; + err = -EINVAL; + goto err_release_metapage; } bmp->db_maxlevel = le32_to_cpu(dbmp_le->dn_maxlevel); bmp->db_maxag = le32_to_cpu(dbmp_le->dn_maxag); bmp->db_agpref = le32_to_cpu(dbmp_le->dn_agpref); + if (bmp->db_maxag >= MAXAG || bmp->db_maxag < 0 || + bmp->db_agpref >= MAXAG || bmp->db_agpref < 0) { + err = -EINVAL; + goto err_release_metapage; + } + bmp->db_aglevel = le32_to_cpu(dbmp_le->dn_aglevel); bmp->db_agheight = le32_to_cpu(dbmp_le->dn_agheight); bmp->db_agwidth = le32_to_cpu(dbmp_le->dn_agwidth); bmp->db_agstart = le32_to_cpu(dbmp_le->dn_agstart); bmp->db_agl2size = le32_to_cpu(dbmp_le->dn_agl2size); + if (bmp->db_agl2size > L2MAXL2SIZE - L2MAXAG || + bmp->db_agl2size < 0) { + err = -EINVAL; + goto err_release_metapage; + } + + if (((bmp->db_mapsize - 1) >> bmp->db_agl2size) > MAXAG) { + err = -EINVAL; + goto err_release_metapage; + } + for (i = 0; i < MAXAG; i++) bmp->db_agfree[i] = le64_to_cpu(dbmp_le->dn_agfree[i]); bmp->db_agsize = le64_to_cpu(dbmp_le->dn_agsize); @@ -227,6 +250,12 @@ int dbMount(struct inode *ipbmap) BMAP_LOCK_INIT(bmp); return (0); + +err_release_metapage: + release_metapage(mp); +err_kfree_bmp: + kfree(bmp); + return err; } @@ -260,6 +289,7 @@ int dbUnmount(struct inode *ipbmap, int mounterror) /* free the memory for the in-memory bmap. */ kfree(bmp); + JFS_SBI(ipbmap->i_sb)->bmap = NULL; return (0); } @@ -1768,7 +1798,7 @@ static int dbFindCtl(struct bmap * bmp, int l2nb, int level, s64 * blkno) * dbFindLeaf() returns the index of the leaf at which * free space was found. */ - rc = dbFindLeaf((dmtree_t *) dcp, l2nb, &leafidx); + rc = dbFindLeaf((dmtree_t *) dcp, l2nb, &leafidx, true); /* release the buffer. */ @@ -2015,9 +2045,12 @@ dbAllocDmapLev(struct bmap * bmp, * free space. if sufficient free space is found, dbFindLeaf() * returns the index of the leaf at which free space was found. */ - if (dbFindLeaf((dmtree_t *) & dp->tree, l2nb, &leafidx)) + if (dbFindLeaf((dmtree_t *) &dp->tree, l2nb, &leafidx, false)) return -ENOSPC; + if (leafidx < 0) + return -EIO; + /* determine the block number within the file system corresponding * to the leaf at which free space was found. */ @@ -2972,14 +3005,18 @@ static void dbAdjTree(dmtree_t * tp, int leafno, int newval) * leafidx - return pointer to be set to the index of the leaf * describing at least l2nb free blocks if sufficient * free blocks are found. + * is_ctl - determines if the tree is of type ctl * * RETURN VALUES: * 0 - success * -ENOSPC - insufficient free blocks. */ -static int dbFindLeaf(dmtree_t * tp, int l2nb, int *leafidx) +static int dbFindLeaf(dmtree_t *tp, int l2nb, int *leafidx, bool is_ctl) { int ti, n = 0, k, x = 0; + int max_size; + + max_size = is_ctl ? CTLTREESIZE : TREESIZE; /* first check the root of the tree to see if there is * sufficient free space. @@ -3000,6 +3037,8 @@ static int dbFindLeaf(dmtree_t * tp, int l2nb, int *leafidx) /* sufficient free space found. move to the next * level (or quit if this is the last level). */ + if (x + n > max_size) + return -ENOSPC; if (l2nb <= tp->dmt_stree[x + n]) break; } diff --git a/fs/jfs/jfs_extent.c b/fs/jfs/jfs_extent.c index 2ae7d59ab10a..c971e8a6525d 100644 --- a/fs/jfs/jfs_extent.c +++ b/fs/jfs/jfs_extent.c @@ -521,6 +521,11 @@ extBalloc(struct inode *ip, s64 hint, s64 * nblocks, s64 * blkno) * blocks in the map. in that case, we'll start off with the * maximum free. */ + + /* give up if no space left */ + if (bmp->db_maxfreebud == -1) + return -ENOSPC; + max = (s64) 1 << bmp->db_maxfreebud; if (*nblocks >= max && *nblocks > nbperpage) nb = nblks = (max > nbperpage) ? max : nbperpage; diff --git a/fs/jfs/jfs_filsys.h b/fs/jfs/jfs_filsys.h index 415bfa90607a..0c36ce6318d5 100644 --- a/fs/jfs/jfs_filsys.h +++ b/fs/jfs/jfs_filsys.h @@ -135,7 +135,9 @@ #define NUM_INODE_PER_IAG INOSPERIAG #define MINBLOCKSIZE 512 +#define L2MINBLOCKSIZE 9 #define MAXBLOCKSIZE 4096 +#define L2MAXBLOCKSIZE 12 #define MAXFILESIZE ((s64)1 << 52) #define JFS_LINK_MAX 0xffffffff diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c index 93e8c590ff5c..b45cc109e506 100644 --- a/fs/jfs/jfs_imap.c +++ b/fs/jfs/jfs_imap.c @@ -208,6 +208,7 @@ int diUnmount(struct inode *ipimap, int mounterror) * free in-memory control structure */ kfree(imap); + JFS_IP(ipimap)->i_imap = NULL; return (0); } @@ -1334,7 +1335,7 @@ diInitInode(struct inode *ip, int iagno, int ino, int extno, struct iag * iagp) int diAlloc(struct inode *pip, bool dir, struct inode *ip) { int rc, ino, iagno, addext, extno, bitno, sword; - int nwords, rem, i, agno; + int nwords, rem, i, agno, dn_numag; u32 mask, inosmap, extsmap; struct inode *ipimap; struct metapage *mp; @@ -1370,6 +1371,9 @@ int diAlloc(struct inode *pip, bool dir, struct inode *ip) /* get the ag number of this iag */ agno = BLKTOAG(JFS_IP(pip)->agstart, JFS_SBI(pip->i_sb)); + dn_numag = JFS_SBI(pip->i_sb)->bmap->db_numag; + if (agno < 0 || agno > dn_numag) + return -EIO; if (atomic_read(&JFS_SBI(pip->i_sb)->bmap->db_active[agno])) { /* diff --git a/fs/jfs/jfs_txnmgr.c b/fs/jfs/jfs_txnmgr.c index 78789c5ed36b..e10db01f253b 100644 --- a/fs/jfs/jfs_txnmgr.c +++ b/fs/jfs/jfs_txnmgr.c @@ -367,6 +367,11 @@ tid_t txBegin(struct super_block *sb, int flag) jfs_info("txBegin: flag = 0x%x", flag); log = JFS_SBI(sb)->log; + if (!log) { + jfs_error(sb, "read-only filesystem\n"); + return 0; + } + TXN_LOCK(); INCREMENT(TxStat.txBegin); diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c index 14528c0ffe63..c2c439acbb78 100644 --- a/fs/jfs/namei.c +++ b/fs/jfs/namei.c @@ -811,6 +811,11 @@ static int jfs_link(struct dentry *old_dentry, if (rc) goto out; + if (isReadOnly(ip)) { + jfs_error(ip->i_sb, "read-only filesystem\n"); + return -EROFS; + } + tid = txBegin(ip->i_sb, 0); mutex_lock_nested(&JFS_IP(dir)->commit_mutex, COMMIT_MUTEX_PARENT); diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c index 0b22c39dad47..b2a126a947e3 100644 --- a/fs/kernfs/mount.c +++ b/fs/kernfs/mount.c @@ -212,7 +212,7 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn, dput(dentry); return ERR_PTR(-EINVAL); } - dtmp = lookup_one_len_unlocked(kntmp->name, dentry, + dtmp = lookup_positive_unlocked(kntmp->name, dentry, strlen(kntmp->name)); dput(dentry); if (IS_ERR(dtmp)) diff --git a/fs/libfs.c b/fs/libfs.c index be57e64834e5..fd5f6c106059 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -864,8 +864,8 @@ out: EXPORT_SYMBOL_GPL(simple_attr_read); /* interpret the buffer as a number to call the set function with */ -ssize_t simple_attr_write(struct file *file, const char __user *buf, - size_t len, loff_t *ppos) +static ssize_t simple_attr_write_xsigned(struct file *file, const char __user *buf, + size_t len, loff_t *ppos, bool is_signed) { struct simple_attr *attr; unsigned long long val; @@ -886,7 +886,10 @@ ssize_t simple_attr_write(struct file *file, const char __user *buf, goto out; attr->set_buf[size] = '\0'; - ret = kstrtoull(attr->set_buf, 0, &val); + if (is_signed) + ret = kstrtoll(attr->set_buf, 0, &val); + else + ret = kstrtoull(attr->set_buf, 0, &val); if (ret) goto out; ret = attr->set(attr->data, val); @@ -896,8 +899,21 @@ out: mutex_unlock(&attr->mutex); return ret; } + +ssize_t simple_attr_write(struct file *file, const char __user *buf, + size_t len, loff_t *ppos) +{ + return simple_attr_write_xsigned(file, buf, len, ppos, false); +} EXPORT_SYMBOL_GPL(simple_attr_write); +ssize_t simple_attr_write_signed(struct file *file, const char __user *buf, + size_t len, loff_t *ppos) +{ + return simple_attr_write_xsigned(file, buf, len, ppos, true); +} +EXPORT_SYMBOL_GPL(simple_attr_write_signed); + /** * generic_fh_to_dentry - generic helper for the fh_to_dentry export operation * @sb: filesystem to do the file handle conversion on diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c index 654594ef4f94..68a2eac548c3 100644 --- a/fs/lockd/mon.c +++ b/fs/lockd/mon.c @@ -275,6 +275,9 @@ static struct nsm_handle *nsm_create_handle(const struct sockaddr *sap, { struct nsm_handle *new; + if (!hostname) + return NULL; + new = kzalloc(sizeof(*new) + hostname_len + 1, GFP_KERNEL); if (unlikely(new == NULL)) return NULL; diff --git a/fs/mbcache.c b/fs/mbcache.c index 081ccf0caee3..2e2d4de4cf87 100644 --- a/fs/mbcache.c +++ b/fs/mbcache.c @@ -10,7 +10,7 @@ /* * Mbcache is a simple key-value store. Keys need not be unique, however * key-value pairs are expected to be unique (we use this fact in - * mb_cache_entry_delete()). + * mb_cache_entry_delete_or_get()). * * Ext2 and ext4 use this cache for deduplication of extended attribute blocks. * Ext4 also uses it for deduplication of xattr values stored in inodes. @@ -89,12 +89,19 @@ int mb_cache_entry_create(struct mb_cache *cache, gfp_t mask, u32 key, return -ENOMEM; INIT_LIST_HEAD(&entry->e_list); - /* One ref for hash, one ref returned */ - atomic_set(&entry->e_refcnt, 1); + /* + * We create entry with two references. One reference is kept by the + * hash table, the other reference is used to protect us from + * mb_cache_entry_delete_or_get() until the entry is fully setup. This + * avoids nesting of cache->c_list_lock into hash table bit locks which + * is problematic for RT. + */ + atomic_set(&entry->e_refcnt, 2); entry->e_key = key; entry->e_value = value; - entry->e_reusable = reusable; - entry->e_referenced = 0; + entry->e_flags = 0; + if (reusable) + set_bit(MBE_REUSABLE_B, &entry->e_flags); head = mb_cache_entry_head(cache, key); hlist_bl_lock(head); hlist_bl_for_each_entry(dup, dup_node, head, e_hash_list) { @@ -106,24 +113,41 @@ int mb_cache_entry_create(struct mb_cache *cache, gfp_t mask, u32 key, } hlist_bl_add_head(&entry->e_hash_list, head); hlist_bl_unlock(head); - spin_lock(&cache->c_list_lock); list_add_tail(&entry->e_list, &cache->c_list); - /* Grab ref for LRU list */ - atomic_inc(&entry->e_refcnt); cache->c_entry_count++; spin_unlock(&cache->c_list_lock); + mb_cache_entry_put(cache, entry); return 0; } EXPORT_SYMBOL(mb_cache_entry_create); -void __mb_cache_entry_free(struct mb_cache_entry *entry) +void __mb_cache_entry_free(struct mb_cache *cache, struct mb_cache_entry *entry) { + struct hlist_bl_head *head; + + head = mb_cache_entry_head(cache, entry->e_key); + hlist_bl_lock(head); + hlist_bl_del(&entry->e_hash_list); + hlist_bl_unlock(head); kmem_cache_free(mb_entry_cache, entry); } EXPORT_SYMBOL(__mb_cache_entry_free); +/* + * mb_cache_entry_wait_unused - wait to be the last user of the entry + * + * @entry - entry to work on + * + * Wait to be the last user of the entry. + */ +void mb_cache_entry_wait_unused(struct mb_cache_entry *entry) +{ + wait_var_event(&entry->e_refcnt, atomic_read(&entry->e_refcnt) <= 2); +} +EXPORT_SYMBOL(mb_cache_entry_wait_unused); + static struct mb_cache_entry *__entry_find(struct mb_cache *cache, struct mb_cache_entry *entry, u32 key) @@ -141,10 +165,10 @@ static struct mb_cache_entry *__entry_find(struct mb_cache *cache, while (node) { entry = hlist_bl_entry(node, struct mb_cache_entry, e_hash_list); - if (entry->e_key == key && entry->e_reusable) { - atomic_inc(&entry->e_refcnt); + if (entry->e_key == key && + test_bit(MBE_REUSABLE_B, &entry->e_flags) && + atomic_inc_not_zero(&entry->e_refcnt)) goto out; - } node = node->next; } entry = NULL; @@ -204,10 +228,9 @@ struct mb_cache_entry *mb_cache_entry_get(struct mb_cache *cache, u32 key, head = mb_cache_entry_head(cache, key); hlist_bl_lock(head); hlist_bl_for_each_entry(entry, node, head, e_hash_list) { - if (entry->e_key == key && entry->e_value == value) { - atomic_inc(&entry->e_refcnt); + if (entry->e_key == key && entry->e_value == value && + atomic_inc_not_zero(&entry->e_refcnt)) goto out; - } } entry = NULL; out: @@ -216,7 +239,7 @@ out: } EXPORT_SYMBOL(mb_cache_entry_get); -/* mb_cache_entry_delete - remove a cache entry +/* mb_cache_entry_delete - try to remove a cache entry * @cache - cache we work with * @key - key * @value - value @@ -253,6 +276,43 @@ void mb_cache_entry_delete(struct mb_cache *cache, u32 key, u64 value) } EXPORT_SYMBOL(mb_cache_entry_delete); +/* mb_cache_entry_delete_or_get - remove a cache entry if it has no users + * @cache - cache we work with + * @key - key + * @value - value + * + * Remove entry from cache @cache with key @key and value @value. The removal + * happens only if the entry is unused. The function returns NULL in case the + * entry was successfully removed or there's no entry in cache. Otherwise the + * function grabs reference of the entry that we failed to delete because it + * still has users and return it. + */ +struct mb_cache_entry *mb_cache_entry_delete_or_get(struct mb_cache *cache, + u32 key, u64 value) +{ + struct mb_cache_entry *entry; + + entry = mb_cache_entry_get(cache, key, value); + if (!entry) + return NULL; + + /* + * Drop the ref we got from mb_cache_entry_get() and the initial hash + * ref if we are the last user + */ + if (atomic_cmpxchg(&entry->e_refcnt, 2, 0) != 2) + return entry; + + spin_lock(&cache->c_list_lock); + if (!list_empty(&entry->e_list)) + list_del_init(&entry->e_list); + cache->c_entry_count--; + spin_unlock(&cache->c_list_lock); + __mb_cache_entry_free(cache, entry); + return NULL; +} +EXPORT_SYMBOL(mb_cache_entry_delete_or_get); + /* mb_cache_entry_touch - cache entry got used * @cache - cache the entry belongs to * @entry - entry that got used @@ -262,7 +322,7 @@ EXPORT_SYMBOL(mb_cache_entry_delete); void mb_cache_entry_touch(struct mb_cache *cache, struct mb_cache_entry *entry) { - entry->e_referenced = 1; + set_bit(MBE_REFERENCED_B, &entry->e_flags); } EXPORT_SYMBOL(mb_cache_entry_touch); @@ -280,34 +340,24 @@ static unsigned long mb_cache_shrink(struct mb_cache *cache, unsigned long nr_to_scan) { struct mb_cache_entry *entry; - struct hlist_bl_head *head; unsigned long shrunk = 0; spin_lock(&cache->c_list_lock); while (nr_to_scan-- && !list_empty(&cache->c_list)) { entry = list_first_entry(&cache->c_list, struct mb_cache_entry, e_list); - if (entry->e_referenced) { - entry->e_referenced = 0; + /* Drop initial hash reference if there is no user */ + if (test_bit(MBE_REFERENCED_B, &entry->e_flags) || + atomic_cmpxchg(&entry->e_refcnt, 1, 0) != 1) { + clear_bit(MBE_REFERENCED_B, &entry->e_flags); list_move_tail(&entry->e_list, &cache->c_list); continue; } list_del_init(&entry->e_list); cache->c_entry_count--; - /* - * We keep LRU list reference so that entry doesn't go away - * from under us. - */ spin_unlock(&cache->c_list_lock); - head = mb_cache_entry_head(cache, entry->e_key); - hlist_bl_lock(head); - if (!hlist_bl_unhashed(&entry->e_hash_list)) { - hlist_bl_del_init(&entry->e_hash_list); - atomic_dec(&entry->e_refcnt); - } - hlist_bl_unlock(head); - if (mb_cache_entry_put(cache, entry)) - shrunk++; + __mb_cache_entry_free(cache, entry); + shrunk++; cond_resched(); spin_lock(&cache->c_list_lock); } @@ -399,11 +449,6 @@ void mb_cache_destroy(struct mb_cache *cache) * point. */ list_for_each_entry_safe(entry, next, &cache->c_list, e_list) { - if (!hlist_bl_unhashed(&entry->e_hash_list)) { - hlist_bl_del_init(&entry->e_hash_list); - atomic_dec(&entry->e_refcnt); - } else - WARN_ON(1); list_del(&entry->e_list); WARN_ON(atomic_read(&entry->e_refcnt) != 1); mb_cache_entry_put(cache, entry); diff --git a/fs/namei.c b/fs/namei.c index 9e8fca598acc..60b57e0bc174 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2575,6 +2575,26 @@ struct dentry *lookup_one_len_unlocked(const char *name, } EXPORT_SYMBOL(lookup_one_len_unlocked); +/* + * Like lookup_one_len_unlocked(), except that it yields ERR_PTR(-ENOENT) + * on negatives. Returns known positive or ERR_PTR(); that's what + * most of the users want. Note that pinned negative with unlocked parent + * _can_ become positive at any time, so callers of lookup_one_len_unlocked() + * need to be very careful; pinned positives have ->d_inode stable, so + * this one avoids such problems. + */ +struct dentry *lookup_positive_unlocked(const char *name, + struct dentry *base, int len) +{ + struct dentry *ret = lookup_one_len_unlocked(name, base, len); + if (!IS_ERR(ret) && d_is_negative(ret)) { + dput(ret); + ret = ERR_PTR(-ENOENT); + } + return ret; +} +EXPORT_SYMBOL(lookup_positive_unlocked); + #ifdef CONFIG_UNIX98_PTYS int path_pts(struct path *path) { @@ -2593,7 +2613,7 @@ int path_pts(struct path *path) this.name = "pts"; this.len = 3; child = d_hash_and_lookup(parent, &this); - if (!child) + if (IS_ERR_OR_NULL(child)) return -ENOENT; path->dentry = child; diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index 06cb0c1d9aee..a2bca78b80ab 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -604,6 +604,8 @@ retry: nfs4_delete_deviceid(node->ld, node->nfs_client, id); goto retry; } + + nfs4_put_deviceid_node(node); return ERR_PTR(-ENODEV); } diff --git a/fs/nfs/blocklayout/dev.c b/fs/nfs/blocklayout/dev.c index dec5880ac6de..6e3a14fdff9c 100644 --- a/fs/nfs/blocklayout/dev.c +++ b/fs/nfs/blocklayout/dev.c @@ -422,7 +422,7 @@ bl_parse_concat(struct nfs_server *server, struct pnfs_block_dev *d, int ret, i; d->children = kcalloc(v->concat.volumes_count, - sizeof(struct pnfs_block_dev), GFP_KERNEL); + sizeof(struct pnfs_block_dev), gfp_mask); if (!d->children) return -ENOMEM; @@ -451,7 +451,7 @@ bl_parse_stripe(struct nfs_server *server, struct pnfs_block_dev *d, int ret, i; d->children = kcalloc(v->stripe.volumes_count, - sizeof(struct pnfs_block_dev), GFP_KERNEL); + sizeof(struct pnfs_block_dev), gfp_mask); if (!d->children) return -ENOMEM; diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index e8e825497cbd..015d39ac2c8f 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -837,6 +837,12 @@ filelayout_alloc_lseg(struct pnfs_layout_hdr *layoutid, return &fl->generic_hdr; } +static bool +filelayout_lseg_is_striped(const struct nfs4_filelayout_segment *flseg) +{ + return flseg->num_fh > 1; +} + /* * filelayout_pg_test(). Called by nfs_can_coalesce_requests() * @@ -857,6 +863,8 @@ filelayout_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, size = pnfs_generic_pg_test(pgio, prev, req); if (!size) return 0; + else if (!filelayout_lseg_is_striped(FILELAYOUT_LSEG(pgio->pg_lseg))) + return size; /* see if req and prev are in the same stripe */ if (prev) { diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index fee421da2197..bb10f2b21cc1 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -1189,6 +1189,7 @@ static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg, case -EPFNOSUPPORT: case -EPROTONOSUPPORT: case -EOPNOTSUPP: + case -EINVAL: case -ECONNREFUSED: case -ECONNRESET: case -EHOSTDOWN: diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 5ac7bf24c507..2d438318681a 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -190,7 +190,7 @@ struct nfs4_state { unsigned int n_wronly; /* Number of write-only references */ unsigned int n_rdwr; /* Number of read/write references */ fmode_t state; /* State on the server (R,W, or RW) */ - atomic_t count; + refcount_t count; wait_queue_head_t waitq; }; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 9a0f48f7f2b8..c9db9a0fc733 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -163,6 +163,7 @@ static int nfs4_map_errors(int err) case -NFS4ERR_RESOURCE: case -NFS4ERR_LAYOUTTRYLATER: case -NFS4ERR_RECALLCONFLICT: + case -NFS4ERR_RETURNCONFLICT: return -EREMOTEIO; case -NFS4ERR_WRONGSEC: case -NFS4ERR_WRONG_CRED: @@ -509,6 +510,7 @@ static int nfs4_do_handle_exception(struct nfs_server *server, case -NFS4ERR_GRACE: case -NFS4ERR_LAYOUTTRYLATER: case -NFS4ERR_RECALLCONFLICT: + case -NFS4ERR_RETURNCONFLICT: exception->delay = 1; return 0; @@ -1792,7 +1794,7 @@ static struct nfs4_state *nfs4_try_open_cached(struct nfs4_opendata *opendata) out: return ERR_PTR(ret); out_return_state: - atomic_inc(&state->count); + refcount_inc(&state->count); return state; } @@ -1851,8 +1853,7 @@ _nfs4_opendata_reclaim_to_nfs4_state(struct nfs4_opendata *data) if (!data->rpc_done) { if (data->rpc_status) return ERR_PTR(data->rpc_status); - /* cached opens have already been processed */ - goto update; + return nfs4_try_open_cached(data); } ret = nfs_refresh_inode(inode, &data->f_attr); @@ -1861,10 +1862,11 @@ _nfs4_opendata_reclaim_to_nfs4_state(struct nfs4_opendata *data) if (data->o_res.delegation_type != 0) nfs4_opendata_check_deleg(data, state); -update: - update_open_stateid(state, &data->o_res.stateid, NULL, - data->o_arg.fmode); - atomic_inc(&state->count); + + if (!update_open_stateid(state, &data->o_res.stateid, + NULL, data->o_arg.fmode)) + return ERR_PTR(-EAGAIN); + refcount_inc(&state->count); return state; } @@ -1902,7 +1904,7 @@ nfs4_opendata_find_nfs4_state(struct nfs4_opendata *data) return ERR_CAST(inode); if (data->state != NULL && data->state->inode == inode) { state = data->state; - atomic_inc(&state->count); + refcount_inc(&state->count); } else state = nfs4_get_open_state(inode, data->owner); iput(inode); @@ -1928,8 +1930,11 @@ _nfs4_opendata_to_nfs4_state(struct nfs4_opendata *data) if (data->o_res.delegation_type != 0) nfs4_opendata_check_deleg(data, state); - update_open_stateid(state, &data->o_res.stateid, NULL, - data->o_arg.fmode); + if (!update_open_stateid(state, &data->o_res.stateid, + NULL, data->o_arg.fmode)) { + nfs4_put_open_state(state); + state = ERR_PTR(-EAGAIN); + } out: nfs_release_seqid(data->o_arg.seqid); return state; @@ -1975,23 +1980,23 @@ static struct nfs4_opendata *nfs4_open_recoverdata_alloc(struct nfs_open_context if (opendata == NULL) return ERR_PTR(-ENOMEM); opendata->state = state; - atomic_inc(&state->count); + refcount_inc(&state->count); return opendata; } static int nfs4_open_recover_helper(struct nfs4_opendata *opendata, - fmode_t fmode) + fmode_t fmode) { struct nfs4_state *newstate; + struct nfs_server *server = NFS_SB(opendata->dentry->d_sb); + int openflags = opendata->o_arg.open_flags; int ret; if (!nfs4_mode_match_open_stateid(opendata->state, fmode)) return 0; - opendata->o_arg.open_flags = 0; opendata->o_arg.fmode = fmode; - opendata->o_arg.share_access = nfs4_map_atomic_open_share( - NFS_SB(opendata->dentry->d_sb), - fmode, 0); + opendata->o_arg.share_access = + nfs4_map_atomic_open_share(server, fmode, openflags); memset(&opendata->o_res, 0, sizeof(opendata->o_res)); memset(&opendata->c_res, 0, sizeof(opendata->c_res)); nfs4_init_opendata_res(opendata); @@ -2569,10 +2574,15 @@ static int _nfs4_open_expired(struct nfs_open_context *ctx, struct nfs4_state *s struct nfs4_opendata *opendata; int ret; - opendata = nfs4_open_recoverdata_alloc(ctx, state, - NFS4_OPEN_CLAIM_FH); + opendata = nfs4_open_recoverdata_alloc(ctx, state, NFS4_OPEN_CLAIM_FH); if (IS_ERR(opendata)) return PTR_ERR(opendata); + /* + * We're not recovering a delegation, so ask for no delegation. + * Otherwise the recovery thread could deadlock with an outstanding + * delegation return. + */ + opendata->o_arg.open_flags = O_DIRECT; ret = nfs4_open_recover(opendata, state); if (ret == -ESTALE) d_drop(ctx->dentry); @@ -5135,7 +5145,7 @@ static void nfs4_proc_write_setup(struct nfs_pgio_header *hdr, msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_WRITE]; nfs4_init_sequence(&hdr->args.seq_args, &hdr->res.seq_res, 0, 0); - nfs4_state_protect_write(server->nfs_client, clnt, msg, hdr); + nfs4_state_protect_write(hdr->ds_clp ? hdr->ds_clp : server->nfs_client, clnt, msg, hdr); } static void nfs4_proc_commit_rpc_prepare(struct rpc_task *task, struct nfs_commit_data *data) @@ -5176,7 +5186,8 @@ static void nfs4_proc_commit_setup(struct nfs_commit_data *data, struct rpc_mess data->res.server = server; msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_COMMIT]; nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1, 0); - nfs4_state_protect(server->nfs_client, NFS_SP4_MACH_CRED_COMMIT, clnt, msg); + nfs4_state_protect(data->ds_clp ? data->ds_clp : server->nfs_client, + NFS_SP4_MACH_CRED_COMMIT, clnt, msg); } static int _nfs4_proc_commit(struct file *dst, struct nfs_commitargs *args, @@ -8867,6 +8878,7 @@ nfs4_layoutget_handle_exception(struct rpc_task *task, status = -EBUSY; break; case -NFS4ERR_RECALLCONFLICT: + case -NFS4ERR_RETURNCONFLICT: status = -ERECALLCONFLICT; break; case -NFS4ERR_DELEG_REVOKED: diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 5ab021f87ecf..f0f0fb7499e3 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -66,6 +66,8 @@ #define OPENOWNER_POOL_SIZE 8 +static void nfs4_state_start_reclaim_reboot(struct nfs_client *clp); + const nfs4_stateid zero_stateid = { { .data = { 0 } }, .type = NFS4_SPECIAL_STATEID_TYPE, @@ -338,6 +340,8 @@ do_confirm: status = nfs4_proc_create_session(clp, cred); if (status != 0) goto out; + if (!(clp->cl_exchange_flags & EXCHGID4_FLAG_CONFIRMED_R)) + nfs4_state_start_reclaim_reboot(clp); nfs41_finish_session_reset(clp); nfs_mark_client_ready(clp, NFS_CS_READY); out: @@ -675,7 +679,7 @@ nfs4_alloc_open_state(void) state = kzalloc(sizeof(*state), GFP_NOFS); if (!state) return NULL; - atomic_set(&state->count, 1); + refcount_set(&state->count, 1); INIT_LIST_HEAD(&state->lock_states); spin_lock_init(&state->state_lock); seqlock_init(&state->seqlock); @@ -709,7 +713,7 @@ __nfs4_find_state_byowner(struct inode *inode, struct nfs4_state_owner *owner) continue; if (!nfs4_valid_open_stateid(state)) continue; - if (atomic_inc_not_zero(&state->count)) + if (refcount_inc_not_zero(&state->count)) return state; } return NULL; @@ -763,7 +767,7 @@ void nfs4_put_open_state(struct nfs4_state *state) struct inode *inode = state->inode; struct nfs4_state_owner *owner = state->owner; - if (!atomic_dec_and_lock(&state->count, &owner->so_lock)) + if (!refcount_dec_and_lock(&state->count, &owner->so_lock)) return; spin_lock(&inode->i_lock); list_del(&state->inode_states); @@ -1247,6 +1251,8 @@ void nfs4_schedule_state_manager(struct nfs_client *clp) if (IS_ERR(task)) { printk(KERN_ERR "%s: kthread_run: %ld\n", __func__, PTR_ERR(task)); + if (!nfs_client_init_is_complete(clp)) + nfs_mark_client_ready(clp, PTR_ERR(task)); nfs4_clear_state_manager_bit(clp); nfs_put_client(clp); module_put(THIS_MODULE); @@ -1594,7 +1600,7 @@ restart: continue; if (state->state == 0) continue; - atomic_inc(&state->count); + refcount_inc(&state->count); spin_unlock(&sp->so_lock); status = ops->recover_open(sp, state); if (status >= 0) { diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 56e48642c43e..f0021e3b8efd 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -4277,12 +4277,10 @@ static int decode_attr_security_label(struct xdr_stream *xdr, uint32_t *bitmap, if (unlikely(!p)) goto out_overflow; if (len < NFS4_MAXLABELLEN) { - if (label) { - if (label->len) { - if (label->len < len) - return -ERANGE; - memcpy(label->label, p, len); - } + if (label && label->len) { + if (label->len < len) + return -ERANGE; + memcpy(label->label, p, len); label->len = len; label->pi = pi; label->lfs = lfs; diff --git a/fs/nfs/pnfs_dev.c b/fs/nfs/pnfs_dev.c index e8a07b3f9aaa..ba67906d6b2c 100644 --- a/fs/nfs/pnfs_dev.c +++ b/fs/nfs/pnfs_dev.c @@ -152,7 +152,7 @@ nfs4_get_device_info(struct nfs_server *server, set_bit(NFS_DEVICEID_NOCACHE, &d->flags); out_free_pages: - for (i = 0; i < max_pages; i++) + while (--i >= 0) __free_page(pages[i]); kfree(pages); out_free_pdev: diff --git a/fs/nfs/write.c b/fs/nfs/write.c index ec0fd6b3d185..65aaa6eaad2c 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -598,9 +598,8 @@ release_request: static void nfs_write_error_remove_page(struct nfs_page *req) { + SetPageError(req->wb_page); nfs_end_page_writeback(req); - generic_error_remove_page(page_file_mapping(req->wb_page), - req->wb_page); nfs_release_request(req); } diff --git a/fs/nfsd/blocklayoutxdr.c b/fs/nfsd/blocklayoutxdr.c index 442543304930..2455dc8be18a 100644 --- a/fs/nfsd/blocklayoutxdr.c +++ b/fs/nfsd/blocklayoutxdr.c @@ -82,6 +82,15 @@ nfsd4_block_encode_getdeviceinfo(struct xdr_stream *xdr, int len = sizeof(__be32), ret, i; __be32 *p; + /* + * See paragraph 5 of RFC 8881 S18.40.3. + */ + if (!gdp->gd_maxcount) { + if (xdr_stream_encode_u32(xdr, 0) != XDR_UNIT) + return nfserr_resource; + return nfs_ok; + } + p = xdr_reserve_space(xdr, len + sizeof(__be32)); if (!p) return nfserr_resource; diff --git a/fs/nfsd/flexfilelayoutxdr.c b/fs/nfsd/flexfilelayoutxdr.c index e81d2a5cf381..bb205328e043 100644 --- a/fs/nfsd/flexfilelayoutxdr.c +++ b/fs/nfsd/flexfilelayoutxdr.c @@ -85,6 +85,15 @@ nfsd4_ff_encode_getdeviceinfo(struct xdr_stream *xdr, int addr_len; __be32 *p; + /* + * See paragraph 5 of RFC 8881 S18.40.3. + */ + if (!gdp->gd_maxcount) { + if (xdr_stream_encode_u32(xdr, 0) != XDR_UNIT) + return nfserr_resource; + return nfs_ok; + } + /* len + padding for two strings */ addr_len = 16 + da->netaddr.netid_len + da->netaddr.addr_len; ver_len = 20; diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index b90bea1c434e..9f537decdd9c 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -855,13 +855,11 @@ compose_entry_fh(struct nfsd3_readdirres *cd, struct svc_fh *fhp, } else dchild = dget(dparent); } else - dchild = lookup_one_len_unlocked(name, dparent, namlen); + dchild = lookup_positive_unlocked(name, dparent, namlen); if (IS_ERR(dchild)) return rv; if (d_mountpoint(dchild)) goto out; - if (d_really_is_negative(dchild)) - goto out; if (dchild->d_inode->i_ino != ino) goto out; rv = fh_compose(fhp, exp, dchild, &cd->fh); diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 7ee417b685e9..519d994c0c4c 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -800,7 +800,6 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c } else { if (!conn->cb_xprt) return -EINVAL; - clp->cl_cb_conn.cb_xprt = conn->cb_xprt; clp->cl_cb_session = ses; args.bc_xprt = conn->cb_xprt; args.prognumber = clp->cl_cb_session->se_cb_prog; @@ -820,6 +819,9 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c rpc_shutdown_client(client); return PTR_ERR(cred); } + + if (clp->cl_minorversion != 0) + clp->cl_cb_conn.cb_xprt = conn->cb_xprt; clp->cl_cb_client = client; clp->cl_cb_cred = cred; return 0; diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index f4cf1c0793c6..cf81b5bc3e15 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -322,11 +322,11 @@ nfsd4_recall_file_layout(struct nfs4_layout_stateid *ls) if (ls->ls_recalled) goto out_unlock; - ls->ls_recalled = true; - atomic_inc(&ls->ls_stid.sc_file->fi_lo_recalls); if (list_empty(&ls->ls_layouts)) goto out_unlock; + ls->ls_recalled = true; + atomic_inc(&ls->ls_stid.sc_file->fi_lo_recalls); trace_nfsd_layout_recall(&ls->ls_stid.sc_stateid); refcount_inc(&ls->ls_stid.sc_count); diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index a696a9b90786..5ec90b252b6a 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -870,8 +870,8 @@ nfsd4_rename(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, rename->rn_tname, rename->rn_tnamelen); if (status) return status; - set_change_info(&rename->rn_sinfo, &cstate->current_fh); - set_change_info(&rename->rn_tinfo, &cstate->save_fh); + set_change_info(&rename->rn_sinfo, &cstate->save_fh); + set_change_info(&rename->rn_tinfo, &cstate->current_fh); return nfs_ok; } diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 78191320f8e2..5c241e510888 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1019,9 +1019,9 @@ static void revoke_delegation(struct nfs4_delegation *dp) WARN_ON(!list_empty(&dp->dl_recall_lru)); if (clp->cl_minorversion) { + spin_lock(&clp->cl_lock); dp->dl_stid.sc_type = NFS4_REVOKED_DELEG_STID; refcount_inc(&dp->dl_stid.sc_count); - spin_lock(&clp->cl_lock); list_add(&dp->dl_recall_lru, &clp->cl_revoked); spin_unlock(&clp->cl_lock); } @@ -4998,15 +4998,6 @@ static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid) if (ZERO_STATEID(stateid) || ONE_STATEID(stateid) || CLOSE_STATEID(stateid)) return status; - /* Client debugging aid. */ - if (!same_clid(&stateid->si_opaque.so_clid, &cl->cl_clientid)) { - char addr_str[INET6_ADDRSTRLEN]; - rpc_ntop((struct sockaddr *)&cl->cl_addr, addr_str, - sizeof(addr_str)); - pr_warn_ratelimited("NFSD: client %s testing state ID " - "with incorrect client ID\n", addr_str); - return status; - } spin_lock(&cl->cl_lock); s = find_stateid_locked(cl, stateid); if (!s) @@ -6401,12 +6392,16 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp, if (sop->so_is_open_owner || !same_owner_str(sop, owner)) continue; - if (atomic_read(&sop->so_count) != 1) { - spin_unlock(&clp->cl_lock); - return nfserr_locks_held; + /* see if there are still any locks associated with it */ + lo = lockowner(sop); + list_for_each_entry(stp, &sop->so_stateids, st_perstateowner) { + if (check_for_locks(stp->st_stid.sc_file, lo)) { + status = nfserr_locks_held; + spin_unlock(&clp->cl_lock); + return status; + } } - lo = lockowner(sop); nfs4_get_stateowner(sop); break; } diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 96b79bd90631..33827cdd8066 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -2984,18 +2984,9 @@ nfsd4_encode_dirent_fattr(struct xdr_stream *xdr, struct nfsd4_readdir *cd, __be32 nfserr; int ignore_crossmnt = 0; - dentry = lookup_one_len_unlocked(name, cd->rd_fhp->fh_dentry, namlen); + dentry = lookup_positive_unlocked(name, cd->rd_fhp->fh_dentry, namlen); if (IS_ERR(dentry)) return nfserrno(PTR_ERR(dentry)); - if (d_really_is_negative(dentry)) { - /* - * we're not holding the i_mutex here, so there's - * a window where this directory entry could have gone - * away. - */ - dput(dentry); - return nfserr_noent; - } exp_get(exp); /* @@ -3102,6 +3093,17 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen, case nfserr_noent: xdr_truncate_encode(xdr, start_offset); goto skip_entry; + case nfserr_jukebox: + /* + * The pseudoroot should only display dentries that lead to + * exports. If we get EJUKEBOX here, then we can't tell whether + * this entry should be included. Just fail the whole READDIR + * with NFS4ERR_DELAY in that case, and hope that the situation + * will resolve itself by the client's next attempt. + */ + if (cd->rd_fhp->fh_export->ex_flags & NFSEXP_V4ROOT) + goto fail; + /* fallthrough */ default: /* * If the client requested the RDATTR_ERROR attribute, @@ -3392,7 +3394,7 @@ nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_op p = xdr_reserve_space(xdr, 32); if (!p) return nfserr_resource; - *p++ = cpu_to_be32(0); + *p++ = cpu_to_be32(open->op_recall); /* * TODO: space_limit's in delegations @@ -4124,20 +4126,17 @@ nfsd4_encode_getdeviceinfo(struct nfsd4_compoundres *resp, __be32 nfserr, *p++ = cpu_to_be32(gdev->gd_layout_type); - /* If maxcount is 0 then just update notifications */ - if (gdev->gd_maxcount != 0) { - ops = nfsd4_layout_ops[gdev->gd_layout_type]; - nfserr = ops->encode_getdeviceinfo(xdr, gdev); - if (nfserr) { - /* - * We don't bother to burden the layout drivers with - * enforcing gd_maxcount, just tell the client to - * come back with a bigger buffer if it's not enough. - */ - if (xdr->buf->len + 4 > gdev->gd_maxcount) - goto toosmall; - return nfserr; - } + ops = nfsd4_layout_ops[gdev->gd_layout_type]; + nfserr = ops->encode_getdeviceinfo(xdr, gdev); + if (nfserr) { + /* + * We don't bother to burden the layout drivers with + * enforcing gd_maxcount, just tell the client to + * come back with a bigger buffer if it's not enough. + */ + if (xdr->buf->len + 4 > gdev->gd_maxcount) + goto toosmall; + return nfserr; } if (gdev->gd_notify_types) { diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index ff9899cc9913..7af48d306f20 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -347,7 +347,7 @@ static ssize_t write_unlock_fs(struct file *file, char *buf, size_t size) static ssize_t write_filehandle(struct file *file, char *buf, size_t size) { char *dname, *path; - int uninitialized_var(maxsize); + int maxsize; char *mesg = buf; int len; struct auth_domain *dom; diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 28e7f86c8c94..a7231d17e359 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -1691,6 +1691,12 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen, if (!flen || isdotent(fname, flen) || !tlen || isdotent(tname, tlen)) goto out; + err = (rqstp->rq_vers == 2) ? nfserr_acces : nfserr_xdev; + if (ffhp->fh_export->ex_path.mnt != tfhp->fh_export->ex_path.mnt) + goto out; + if (ffhp->fh_export->ex_path.dentry != tfhp->fh_export->ex_path.dentry) + goto out; + host_err = fh_want_write(ffhp); if (host_err) { err = nfserrno(host_err); @@ -1724,12 +1730,6 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen, if (ndentry == trap) goto out_dput_new; - host_err = -EXDEV; - if (ffhp->fh_export->ex_path.mnt != tfhp->fh_export->ex_path.mnt) - goto out_dput_new; - if (ffhp->fh_export->ex_path.dentry != tfhp->fh_export->ex_path.dentry) - goto out_dput_new; - host_err = vfs_rename(fdir, odentry, tdir, ndentry, NULL, 0); if (!host_err) { host_err = commit_metadata(tfhp); diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c index 235b959fc2b3..bbd82f650e93 100644 --- a/fs/nilfs2/alloc.c +++ b/fs/nilfs2/alloc.c @@ -205,7 +205,8 @@ static int nilfs_palloc_get_block(struct inode *inode, unsigned long blkoff, int ret; spin_lock(lock); - if (prev->bh && blkoff == prev->blkoff) { + if (prev->bh && blkoff == prev->blkoff && + likely(buffer_uptodate(prev->bh))) { get_bh(prev->bh); *bhp = prev->bh; spin_unlock(lock); diff --git a/fs/nilfs2/bmap.c b/fs/nilfs2/bmap.c index fb5a9a8a13cf..2ba57e4b4f0a 100644 --- a/fs/nilfs2/bmap.c +++ b/fs/nilfs2/bmap.c @@ -67,20 +67,28 @@ int nilfs_bmap_lookup_at_level(struct nilfs_bmap *bmap, __u64 key, int level, down_read(&bmap->b_sem); ret = bmap->b_ops->bop_lookup(bmap, key, level, ptrp); - if (ret < 0) { - ret = nilfs_bmap_convert_error(bmap, __func__, ret); + if (ret < 0) goto out; - } + if (NILFS_BMAP_USE_VBN(bmap)) { ret = nilfs_dat_translate(nilfs_bmap_get_dat(bmap), *ptrp, &blocknr); if (!ret) *ptrp = blocknr; + else if (ret == -ENOENT) { + /* + * If there was no valid entry in DAT for the block + * address obtained by b_ops->bop_lookup, then pass + * internal code -EINVAL to nilfs_bmap_convert_error + * to treat it as metadata corruption. + */ + ret = -EINVAL; + } } out: up_read(&bmap->b_sem); - return ret; + return nilfs_bmap_convert_error(bmap, __func__, ret); } int nilfs_bmap_lookup_contig(struct nilfs_bmap *bmap, __u64 key, __u64 *ptrp, diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c index 138ebbb7a1ee..677ff78d54fb 100644 --- a/fs/nilfs2/btnode.c +++ b/fs/nilfs2/btnode.c @@ -295,6 +295,14 @@ void nilfs_btnode_abort_change_key(struct address_space *btnc, radix_tree_delete(&btnc->i_pages, newkey); xa_unlock_irq(&btnc->i_pages); unlock_page(ctxt->bh->b_page); - } else - brelse(nbh); + } else { + /* + * When canceling a buffer that a prepare operation has + * allocated to copy a node block to another location, use + * nilfs_btnode_delete() to initialize and release the buffer + * so that the buffer flags will not be in an inconsistent + * state when it is reallocated. + */ + nilfs_btnode_delete(nbh); + } } diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index 919d1238ce45..a0e37530dcf3 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -480,9 +480,18 @@ static int __nilfs_btree_get_block(const struct nilfs_bmap *btree, __u64 ptr, ret = nilfs_btnode_submit_block(btnc, ptr, 0, REQ_OP_READ, 0, &bh, &submit_ptr); if (ret) { - if (ret != -EEXIST) - return ret; - goto out_check; + if (likely(ret == -EEXIST)) + goto out_check; + if (ret == -ENOENT) { + /* + * Block address translation failed due to invalid + * value of 'ptr'. In this case, return internal code + * -EINVAL (broken bmap) to notify bmap layer of fatal + * metadata corruption. + */ + ret = -EINVAL; + } + return ret; } if (ra) { diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c index 114774ac2185..cef46650102e 100644 --- a/fs/nilfs2/gcinode.c +++ b/fs/nilfs2/gcinode.c @@ -73,10 +73,8 @@ int nilfs_gccache_submit_read_data(struct inode *inode, sector_t blkoff, struct the_nilfs *nilfs = inode->i_sb->s_fs_info; err = nilfs_dat_translate(nilfs->ns_dat, vbn, &pbn); - if (unlikely(err)) { /* -EIO, -ENOMEM, -ENOENT */ - brelse(bh); + if (unlikely(err)) /* -EIO, -ENOMEM, -ENOENT */ goto failed; - } } lock_buffer(bh); @@ -102,6 +100,8 @@ int nilfs_gccache_submit_read_data(struct inode *inode, sector_t blkoff, failed: unlock_page(bh->b_page); put_page(bh->b_page); + if (unlikely(err)) + brelse(bh); return err; } diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index cf01aa55dd44..ea94dc21af0c 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -930,6 +930,7 @@ void nilfs_evict_inode(struct inode *inode) struct nilfs_transaction_info ti; struct super_block *sb = inode->i_sb; struct nilfs_inode_info *ii = NILFS_I(inode); + struct the_nilfs *nilfs; int ret; if (inode->i_nlink || !ii->i_root || unlikely(is_bad_inode(inode))) { @@ -942,6 +943,23 @@ void nilfs_evict_inode(struct inode *inode) truncate_inode_pages_final(&inode->i_data); + nilfs = sb->s_fs_info; + if (unlikely(sb_rdonly(sb) || !nilfs->ns_writer)) { + /* + * If this inode is about to be disposed after the file system + * has been degraded to read-only due to file system corruption + * or after the writer has been detached, do not make any + * changes that cause writes, just clear it. + * Do this check after read-locking ns_segctor_sem by + * nilfs_transaction_begin() in order to avoid a race with + * the writer detach operation. + */ + clear_inode(inode); + nilfs_clear_inode(inode); + nilfs_transaction_abort(sb); + return; + } + /* TODO: some of the following operations may fail. */ nilfs_truncate_bmap(ii, 0); nilfs_mark_inode_dirty(inode); @@ -1018,7 +1036,7 @@ int nilfs_load_inode_block(struct inode *inode, struct buffer_head **pbh) int err; spin_lock(&nilfs->ns_inode_lock); - if (ii->i_bh == NULL) { + if (ii->i_bh == NULL || unlikely(!buffer_uptodate(ii->i_bh))) { spin_unlock(&nilfs->ns_inode_lock); err = nilfs_ifile_get_inode_block(ii->i_root->ifile, inode->i_ino, pbh); @@ -1027,7 +1045,10 @@ int nilfs_load_inode_block(struct inode *inode, struct buffer_head **pbh) spin_lock(&nilfs->ns_inode_lock); if (ii->i_bh == NULL) ii->i_bh = *pbh; - else { + else if (unlikely(!buffer_uptodate(ii->i_bh))) { + __brelse(ii->i_bh); + ii->i_bh = *pbh; + } else { brelse(*pbh); *pbh = ii->i_bh; } @@ -1094,9 +1115,17 @@ int nilfs_set_file_dirty(struct inode *inode, unsigned int nr_dirty) int __nilfs_mark_inode_dirty(struct inode *inode, int flags) { + struct the_nilfs *nilfs = inode->i_sb->s_fs_info; struct buffer_head *ibh; int err; + /* + * Do not dirty inodes after the log writer has been detached + * and its nilfs_root struct has been freed. + */ + if (unlikely(nilfs_purging(nilfs))) + return 0; + err = nilfs_load_inode_block(inode, &ibh); if (unlikely(err)) { nilfs_msg(inode->i_sb, KERN_WARNING, diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c index 9b96d79eea6c..dfb2083b8ce1 100644 --- a/fs/nilfs2/ioctl.c +++ b/fs/nilfs2/ioctl.c @@ -70,7 +70,7 @@ static int nilfs_ioctl_wrap_copy(struct the_nilfs *nilfs, if (argv->v_index > ~(__u64)0 - argv->v_nmembs) return -EINVAL; - buf = (void *)__get_free_pages(GFP_NOFS, 0); + buf = (void *)get_zeroed_page(GFP_NOFS); if (unlikely(!buf)) return -ENOMEM; maxmembs = PAGE_SIZE / argv->v_size; @@ -1135,7 +1135,14 @@ static int nilfs_ioctl_set_alloc_range(struct inode *inode, void __user *argp) minseg = range[0] + segbytes - 1; do_div(minseg, segbytes); + + if (range[1] < 4096) + goto out; + maxseg = NILFS_SB2_OFFSET_BYTES(range[1]); + if (maxseg < segbytes) + goto out; + do_div(maxseg, segbytes); maxseg--; diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c index c726b42ca92d..e5fee7fac915 100644 --- a/fs/nilfs2/page.c +++ b/fs/nilfs2/page.c @@ -372,7 +372,15 @@ void nilfs_clear_dirty_pages(struct address_space *mapping, bool silent) struct page *page = pvec.pages[i]; lock_page(page); - nilfs_clear_dirty_page(page, silent); + + /* + * This page may have been removed from the address + * space by truncation or invalidation when the lock + * was acquired. Skip processing in that case. + */ + if (likely(page->mapping == mapping)) + nilfs_clear_dirty_page(page, silent); + unlock_page(page); } pagevec_release(&pvec); diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c index 20c479b5e41b..e72466fc8ca9 100644 --- a/fs/nilfs2/segbuf.c +++ b/fs/nilfs2/segbuf.c @@ -101,6 +101,12 @@ int nilfs_segbuf_extend_segsum(struct nilfs_segment_buffer *segbuf) if (unlikely(!bh)) return -ENOMEM; + lock_buffer(bh); + if (!buffer_uptodate(bh)) { + memset(bh->b_data, 0, bh->b_size); + set_buffer_uptodate(bh); + } + unlock_buffer(bh); nilfs_segbuf_add_segsum_buffer(segbuf, bh); return 0; } diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 11914b3585b3..fdcbed6ee832 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -435,6 +435,23 @@ static int nilfs_segctor_reset_segment_buffer(struct nilfs_sc_info *sci) return 0; } +/** + * nilfs_segctor_zeropad_segsum - zero pad the rest of the segment summary area + * @sci: segment constructor object + * + * nilfs_segctor_zeropad_segsum() zero-fills unallocated space at the end of + * the current segment summary block. + */ +static void nilfs_segctor_zeropad_segsum(struct nilfs_sc_info *sci) +{ + struct nilfs_segsum_pointer *ssp; + + ssp = sci->sc_blk_cnt > 0 ? &sci->sc_binfo_ptr : &sci->sc_finfo_ptr; + if (ssp->offset < ssp->bh->b_size) + memset(ssp->bh->b_data + ssp->offset, 0, + ssp->bh->b_size - ssp->offset); +} + static int nilfs_segctor_feed_segment(struct nilfs_sc_info *sci) { sci->sc_nblk_this_inc += sci->sc_curseg->sb_sum.nblocks; @@ -443,6 +460,7 @@ static int nilfs_segctor_feed_segment(struct nilfs_sc_info *sci) * The current segment is filled up * (internal code) */ + nilfs_segctor_zeropad_segsum(sci); sci->sc_curseg = NILFS_NEXT_SEGBUF(sci->sc_curseg); return nilfs_segctor_reset_segment_buffer(sci); } @@ -547,6 +565,7 @@ static int nilfs_segctor_add_file_block(struct nilfs_sc_info *sci, goto retry; } if (unlikely(required)) { + nilfs_segctor_zeropad_segsum(sci); err = nilfs_segbuf_extend_segsum(segbuf); if (unlikely(err)) goto failed; @@ -711,6 +730,11 @@ static size_t nilfs_lookup_dirty_data_buffers(struct inode *inode, struct page *page = pvec.pages[i]; lock_page(page); + if (unlikely(page->mapping != mapping)) { + /* Exclude pages removed from the address space */ + unlock_page(page); + continue; + } if (!page_has_buffers(page)) create_empty_buffers(page, i_blocksize(inode), 0); unlock_page(page); @@ -965,10 +989,13 @@ static void nilfs_segctor_fill_in_super_root(struct nilfs_sc_info *sci, unsigned int isz, srsz; bh_sr = NILFS_LAST_SEGBUF(&sci->sc_segbufs)->sb_super_root; + + lock_buffer(bh_sr); raw_sr = (struct nilfs_super_root *)bh_sr->b_data; isz = nilfs->ns_inode_size; srsz = NILFS_SR_BYTES(isz); + raw_sr->sr_sum = 0; /* Ensure initialization within this update */ raw_sr->sr_bytes = cpu_to_le16(srsz); raw_sr->sr_nongc_ctime = cpu_to_le64(nilfs_doing_gc() ? @@ -982,6 +1009,8 @@ static void nilfs_segctor_fill_in_super_root(struct nilfs_sc_info *sci, nilfs_write_inode_common(nilfs->ns_sufile, (void *)raw_sr + NILFS_SR_SUFILE_OFFSET(isz), 1); memset((void *)raw_sr + srsz, 0, nilfs->ns_blocksize - srsz); + set_buffer_uptodate(bh_sr); + unlock_buffer(bh_sr); } static void nilfs_redirty_inodes(struct list_head *head) @@ -1531,6 +1560,7 @@ static int nilfs_segctor_collect(struct nilfs_sc_info *sci, nadd = min_t(int, nadd << 1, SC_MAX_SEGDELTA); sci->sc_stage = prev_stage; } + nilfs_segctor_zeropad_segsum(sci); nilfs_segctor_truncate_segments(sci, sci->sc_curseg, nilfs->ns_sufile); return 0; @@ -1758,6 +1788,7 @@ static void nilfs_abort_logs(struct list_head *logs, int err) list_for_each_entry(segbuf, logs, sb_list) { list_for_each_entry(bh, &segbuf->sb_segsum_buffers, b_assoc_buffers) { + clear_buffer_uptodate(bh); if (bh->b_page != bd_page) { if (bd_page) end_page_writeback(bd_page); @@ -1769,6 +1800,7 @@ static void nilfs_abort_logs(struct list_head *logs, int err) b_assoc_buffers) { clear_buffer_async_write(bh); if (bh == segbuf->sb_super_root) { + clear_buffer_uptodate(bh); if (bh->b_page != bd_page) { end_page_writeback(bd_page); bd_page = bh->b_page; @@ -2019,6 +2051,9 @@ static int nilfs_segctor_do_construct(struct nilfs_sc_info *sci, int mode) struct the_nilfs *nilfs = sci->sc_super->s_fs_info; int err; + if (sb_rdonly(sci->sc_super)) + return -EROFS; + nilfs_sc_cstage_set(sci, NILFS_ST_INIT); sci->sc_cno = nilfs->ns_cno; @@ -2609,11 +2644,10 @@ static int nilfs_segctor_thread(void *arg) goto loop; end_thread: - spin_unlock(&sci->sc_state_lock); - /* end sync. */ sci->sc_task = NULL; wake_up(&sci->sc_wait_task); /* for nilfs_segctor_kill_thread() */ + spin_unlock(&sci->sc_state_lock); return 0; } @@ -2705,7 +2739,7 @@ static void nilfs_segctor_write_out(struct nilfs_sc_info *sci) flush_work(&sci->sc_iput_work); - } while (ret && retrycount-- > 0); + } while (ret && ret != -EROFS && retrycount-- > 0); } /** @@ -2816,6 +2850,7 @@ void nilfs_detach_log_writer(struct super_block *sb) nilfs_segctor_destroy(nilfs->ns_writer); nilfs->ns_writer = NULL; } + set_nilfs_purging(nilfs); /* Force to free the list of dirty files */ spin_lock(&nilfs->ns_inode_lock); @@ -2828,4 +2863,5 @@ void nilfs_detach_log_writer(struct super_block *sb) up_write(&nilfs->ns_segctor_sem); nilfs_dispose_list(nilfs, &garbage_list, 1); + clear_nilfs_purging(nilfs); } diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c index 150845a43225..4626540008c1 100644 --- a/fs/nilfs2/sufile.c +++ b/fs/nilfs2/sufile.c @@ -504,15 +504,38 @@ int nilfs_sufile_mark_dirty(struct inode *sufile, __u64 segnum) down_write(&NILFS_MDT(sufile)->mi_sem); ret = nilfs_sufile_get_segment_usage_block(sufile, segnum, 0, &bh); - if (!ret) { - mark_buffer_dirty(bh); - nilfs_mdt_mark_dirty(sufile); - kaddr = kmap_atomic(bh->b_page); - su = nilfs_sufile_block_get_segment_usage(sufile, segnum, bh, kaddr); + if (ret) + goto out_sem; + + kaddr = kmap_atomic(bh->b_page); + su = nilfs_sufile_block_get_segment_usage(sufile, segnum, bh, kaddr); + if (unlikely(nilfs_segment_usage_error(su))) { + struct the_nilfs *nilfs = sufile->i_sb->s_fs_info; + + kunmap_atomic(kaddr); + brelse(bh); + if (nilfs_segment_is_active(nilfs, segnum)) { + nilfs_error(sufile->i_sb, + "active segment %llu is erroneous", + (unsigned long long)segnum); + } else { + /* + * Segments marked erroneous are never allocated by + * nilfs_sufile_alloc(); only active segments, ie, + * the segments indexed by ns_segnum or ns_nextnum, + * can be erroneous here. + */ + WARN_ON_ONCE(1); + } + ret = -EIO; + } else { nilfs_segment_usage_set_dirty(su); kunmap_atomic(kaddr); + mark_buffer_dirty(bh); + nilfs_mdt_mark_dirty(sufile); brelse(bh); } +out_sem: up_write(&NILFS_MDT(sufile)->mi_sem); return ret; } @@ -539,9 +562,14 @@ int nilfs_sufile_set_segment_usage(struct inode *sufile, __u64 segnum, kaddr = kmap_atomic(bh->b_page); su = nilfs_sufile_block_get_segment_usage(sufile, segnum, bh, kaddr); - WARN_ON(nilfs_segment_usage_error(su)); - if (modtime) + if (modtime) { + /* + * Check segusage error and set su_lastmod only when updating + * this entry with a valid timestamp, not for cancellation. + */ + WARN_ON_ONCE(nilfs_segment_usage_error(su)); su->su_lastmod = cpu_to_le64(modtime); + } su->su_nblocks = cpu_to_le32(nblocks); kunmap_atomic(kaddr); @@ -782,6 +810,15 @@ int nilfs_sufile_resize(struct inode *sufile, __u64 newnsegs) goto out_header; sui->ncleansegs -= nsegs - newnsegs; + + /* + * If the sufile is successfully truncated, immediately adjust + * the segment allocation space while locking the semaphore + * "mi_sem" so that nilfs_sufile_alloc() never allocates + * segments in the truncated space. + */ + sui->allocmax = newnsegs - 1; + sui->allocmin = 0; } kaddr = kmap_atomic(header_bh->b_page); diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 5e4d7d19102c..99bcb4ab47a6 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -374,10 +374,31 @@ static int nilfs_move_2nd_super(struct super_block *sb, loff_t sb2off) goto out; } nsbp = (void *)nsbh->b_data + offset; - memset(nsbp, 0, nilfs->ns_blocksize); + lock_buffer(nsbh); if (sb2i >= 0) { + /* + * The position of the second superblock only changes by 4KiB, + * which is larger than the maximum superblock data size + * (= 1KiB), so there is no need to use memmove() to allow + * overlap between source and destination. + */ memcpy(nsbp, nilfs->ns_sbp[sb2i], nilfs->ns_sbsize); + + /* + * Zero fill after copy to avoid overwriting in case of move + * within the same block. + */ + memset(nsbh->b_data, 0, offset); + memset((void *)nsbp + nilfs->ns_sbsize, 0, + nsbh->b_size - offset - nilfs->ns_sbsize); + } else { + memset(nsbh->b_data, 0, nsbh->b_size); + } + set_buffer_uptodate(nsbh); + unlock_buffer(nsbh); + + if (sb2i >= 0) { brelse(nilfs->ns_sbh[sb2i]); nilfs->ns_sbh[sb2i] = nsbh; nilfs->ns_sbp[sb2i] = nsbp; @@ -411,6 +432,15 @@ int nilfs_resize_fs(struct super_block *sb, __u64 newsize) goto out; /* + * Prevent underflow in second superblock position calculation. + * The exact minimum size check is done in nilfs_sufile_resize(). + */ + if (newsize < 4096) { + ret = -ENOSPC; + goto out; + } + + /* * Write lock is required to protect some functions depending * on the number of segments, the number of reserved segments, * and so forth. @@ -475,6 +505,7 @@ static void nilfs_put_super(struct super_block *sb) up_write(&nilfs->ns_sem); } + nilfs_sysfs_delete_device_group(nilfs); iput(nilfs->ns_sufile); iput(nilfs->ns_cpfile); iput(nilfs->ns_dat); @@ -1101,6 +1132,7 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent) nilfs_put_root(fsroot); failed_unload: + nilfs_sysfs_delete_device_group(nilfs); iput(nilfs->ns_sufile); iput(nilfs->ns_cpfile); iput(nilfs->ns_dat); diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index fb61c33c6004..c8d869bc25b0 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -13,6 +13,7 @@ #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/random.h> +#include <linux/log2.h> #include <linux/crc32.h> #include "nilfs.h" #include "segment.h" @@ -86,7 +87,6 @@ void destroy_nilfs(struct the_nilfs *nilfs) { might_sleep(); if (nilfs_init(nilfs)) { - nilfs_sysfs_delete_device_group(nilfs); brelse(nilfs->ns_sbh[0]); brelse(nilfs->ns_sbh[1]); } @@ -274,6 +274,10 @@ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb) goto failed; } + err = nilfs_sysfs_create_device_group(sb); + if (unlikely(err)) + goto sysfs_error; + if (valid_fs) goto skip_recovery; @@ -335,6 +339,9 @@ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb) goto failed; failed_unload: + nilfs_sysfs_delete_device_group(nilfs); + + sysfs_error: iput(nilfs->ns_cpfile); iput(nilfs->ns_sufile); iput(nilfs->ns_dat); @@ -368,6 +375,18 @@ unsigned long nilfs_nrsvsegs(struct the_nilfs *nilfs, unsigned long nsegs) 100)); } +/** + * nilfs_max_segment_count - calculate the maximum number of segments + * @nilfs: nilfs object + */ +static u64 nilfs_max_segment_count(struct the_nilfs *nilfs) +{ + u64 max_count = U64_MAX; + + do_div(max_count, nilfs->ns_blocks_per_segment); + return min_t(u64, max_count, ULONG_MAX); +} + void nilfs_set_nsegments(struct the_nilfs *nilfs, unsigned long nsegs) { nilfs->ns_nsegments = nsegs; @@ -377,6 +396,8 @@ void nilfs_set_nsegments(struct the_nilfs *nilfs, unsigned long nsegs) static int nilfs_store_disk_layout(struct the_nilfs *nilfs, struct nilfs_super_block *sbp) { + u64 nsegments, nblocks; + if (le32_to_cpu(sbp->s_rev_level) < NILFS_MIN_SUPP_REV) { nilfs_msg(nilfs->ns_sb, KERN_ERR, "unsupported revision (superblock rev.=%d.%d, current rev.=%d.%d). Please check the version of mkfs.nilfs(2).", @@ -423,7 +444,35 @@ static int nilfs_store_disk_layout(struct the_nilfs *nilfs, return -EINVAL; } - nilfs_set_nsegments(nilfs, le64_to_cpu(sbp->s_nsegments)); + nsegments = le64_to_cpu(sbp->s_nsegments); + if (nsegments > nilfs_max_segment_count(nilfs)) { + nilfs_msg(nilfs->ns_sb, KERN_ERR, + "segment count %llu exceeds upper limit (%llu segments)", + (unsigned long long)nsegments, + (unsigned long long)nilfs_max_segment_count(nilfs)); + return -EINVAL; + } + + nblocks = (u64)i_size_read(nilfs->ns_sb->s_bdev->bd_inode) >> + nilfs->ns_sb->s_blocksize_bits; + if (nblocks) { + u64 min_block_count = nsegments * nilfs->ns_blocks_per_segment; + /* + * To avoid failing to mount early device images without a + * second superblock, exclude that block count from the + * "min_block_count" calculation. + */ + + if (nblocks < min_block_count) { + nilfs_msg(nilfs->ns_sb, KERN_ERR, + "total number of segment blocks %llu exceeds device size (%llu blocks)", + (unsigned long long)min_block_count, + (unsigned long long)nblocks); + return -EINVAL; + } + } + + nilfs_set_nsegments(nilfs, nsegments); nilfs->ns_crc_seed = le32_to_cpu(sbp->s_crc_seed); return 0; } @@ -448,11 +497,33 @@ static int nilfs_valid_sb(struct nilfs_super_block *sbp) return crc == le32_to_cpu(sbp->s_sum); } -static int nilfs_sb2_bad_offset(struct nilfs_super_block *sbp, u64 offset) +/** + * nilfs_sb2_bad_offset - check the location of the second superblock + * @sbp: superblock raw data buffer + * @offset: byte offset of second superblock calculated from device size + * + * nilfs_sb2_bad_offset() checks if the position on the second + * superblock is valid or not based on the filesystem parameters + * stored in @sbp. If @offset points to a location within the segment + * area, or if the parameters themselves are not normal, it is + * determined to be invalid. + * + * Return Value: true if invalid, false if valid. + */ +static bool nilfs_sb2_bad_offset(struct nilfs_super_block *sbp, u64 offset) { - return offset < ((le64_to_cpu(sbp->s_nsegments) * - le32_to_cpu(sbp->s_blocks_per_segment)) << - (le32_to_cpu(sbp->s_log_block_size) + 10)); + unsigned int shift_bits = le32_to_cpu(sbp->s_log_block_size); + u32 blocks_per_segment = le32_to_cpu(sbp->s_blocks_per_segment); + u64 nsegments = le64_to_cpu(sbp->s_nsegments); + u64 index; + + if (blocks_per_segment < NILFS_SEG_MIN_BLOCKS || + shift_bits > ilog2(NILFS_MAX_BLOCK_SIZE) - BLOCK_SIZE_BITS) + return true; + + index = offset >> (shift_bits + BLOCK_SIZE_BITS); + do_div(index, blocks_per_segment); + return index < nsegments; } static void nilfs_release_super_block(struct the_nilfs *nilfs) @@ -494,9 +565,15 @@ static int nilfs_load_super_block(struct the_nilfs *nilfs, { struct nilfs_super_block **sbp = nilfs->ns_sbp; struct buffer_head **sbh = nilfs->ns_sbh; - u64 sb2off = NILFS_SB2_OFFSET_BYTES(nilfs->ns_bdev->bd_inode->i_size); + u64 sb2off, devsize = nilfs->ns_bdev->bd_inode->i_size; int valid[2], swp = 0; + if (devsize < NILFS_SEG_MIN_BLOCKS * NILFS_MIN_BLOCK_SIZE + 4096) { + nilfs_msg(sb, KERN_ERR, "device size too small"); + return -EINVAL; + } + sb2off = NILFS_SB2_OFFSET_BYTES(devsize); + sbp[0] = nilfs_read_super_block(sb, NILFS_SB_OFFSET_BYTES, blocksize, &sbh[0]); sbp[1] = nilfs_read_super_block(sb, sb2off, blocksize, &sbh[1]); @@ -611,7 +688,11 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb, char *data) goto failed_sbh; } nilfs_release_super_block(nilfs); - sb_set_blocksize(sb, blocksize); + if (!sb_set_blocksize(sb, blocksize)) { + nilfs_msg(sb, KERN_ERR, "bad blocksize %d", blocksize); + err = -EINVAL; + goto out; + } err = nilfs_load_super_block(nilfs, sb, blocksize, &sbp); if (err) @@ -639,10 +720,6 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb, char *data) if (err) goto failed_sbh; - err = nilfs_sysfs_create_device_group(sb); - if (err) - goto failed_sbh; - set_nilfs_init(nilfs); err = 0; out: diff --git a/fs/nilfs2/the_nilfs.h b/fs/nilfs2/the_nilfs.h index 380a543c5b19..de6e24d80eb6 100644 --- a/fs/nilfs2/the_nilfs.h +++ b/fs/nilfs2/the_nilfs.h @@ -29,6 +29,7 @@ enum { THE_NILFS_DISCONTINUED, /* 'next' pointer chain has broken */ THE_NILFS_GC_RUNNING, /* gc process is running */ THE_NILFS_SB_DIRTY, /* super block is dirty */ + THE_NILFS_PURGING, /* disposing dirty files for cleanup */ }; /** @@ -208,6 +209,7 @@ THE_NILFS_FNS(INIT, init) THE_NILFS_FNS(DISCONTINUED, discontinued) THE_NILFS_FNS(GC_RUNNING, gc_running) THE_NILFS_FNS(SB_DIRTY, sb_dirty) +THE_NILFS_FNS(PURGING, purging) /* * Mount option operations diff --git a/fs/nls/nls_base.c b/fs/nls/nls_base.c index 52ccd34b1e79..a026dbd3593f 100644 --- a/fs/nls/nls_base.c +++ b/fs/nls/nls_base.c @@ -272,7 +272,7 @@ int unregister_nls(struct nls_table * nls) return -EINVAL; } -static struct nls_table *find_nls(char *charset) +static struct nls_table *find_nls(const char *charset) { struct nls_table *nls; spin_lock(&nls_lock); @@ -288,7 +288,7 @@ static struct nls_table *find_nls(char *charset) return nls; } -struct nls_table *load_nls(char *charset) +struct nls_table *load_nls(const char *charset) { return try_then_request_module(find_nls(charset), "nls_%s", charset); } diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index 046f5e3c9622..c7cf0913229c 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -4722,7 +4722,7 @@ int ocfs2_insert_extent(handle_t *handle, struct ocfs2_alloc_context *meta_ac) { int status; - int uninitialized_var(free_records); + int free_records; struct buffer_head *last_eb_bh = NULL; struct ocfs2_insert_type insert = {0, }; struct ocfs2_extent_rec rec; @@ -7052,7 +7052,7 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode, int need_free = 0; u32 bit_off, num; handle_t *handle; - u64 uninitialized_var(block); + u64 block; struct ocfs2_inode_info *oi = OCFS2_I(inode); struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index b6948813eb06..1353db3f7f48 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -2003,11 +2003,25 @@ int ocfs2_write_end_nolock(struct address_space *mapping, } if (unlikely(copied < len) && wc->w_target_page) { + loff_t new_isize; + if (!PageUptodate(wc->w_target_page)) copied = 0; - ocfs2_zero_new_buffers(wc->w_target_page, start+copied, - start+len); + new_isize = max_t(loff_t, i_size_read(inode), pos + copied); + if (new_isize > page_offset(wc->w_target_page)) + ocfs2_zero_new_buffers(wc->w_target_page, start+copied, + start+len); + else { + /* + * When page is fully beyond new isize (data copy + * failed), do not bother zeroing the page. Invalidate + * it instead so that writeback does not get confused + * put page & buffer dirty bits into inconsistent + * state. + */ + block_invalidatepage(wc->w_target_page, 0, PAGE_SIZE); + } } if (wc->w_target_page) flush_dcache_page(wc->w_target_page); diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index c121abbdfc7d..13f4bb4e174c 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -866,9 +866,9 @@ static int ocfs2_dx_dir_lookup(struct inode *inode, u64 *ret_phys_blkno) { int ret = 0; - unsigned int cend, uninitialized_var(clen); - u32 uninitialized_var(cpos); - u64 uninitialized_var(blkno); + unsigned int cend, clen; + u32 cpos; + u64 blkno; u32 name_hash = hinfo->major_hash; ret = ocfs2_dx_dir_lookup_rec(inode, el, name_hash, &cpos, &blkno, @@ -912,7 +912,7 @@ static int ocfs2_dx_dir_search(const char *name, int namelen, struct ocfs2_dir_lookup_result *res) { int ret, i, found; - u64 uninitialized_var(phys); + u64 phys; struct buffer_head *dx_leaf_bh = NULL; struct ocfs2_dx_leaf *dx_leaf; struct ocfs2_dx_entry *dx_entry = NULL; @@ -4420,9 +4420,9 @@ out: int ocfs2_dx_dir_truncate(struct inode *dir, struct buffer_head *di_bh) { int ret; - unsigned int uninitialized_var(clen); - u32 major_hash = UINT_MAX, p_cpos, uninitialized_var(cpos); - u64 uninitialized_var(blkno); + unsigned int clen; + u32 major_hash = UINT_MAX, p_cpos, cpos; + u64 blkno; struct ocfs2_super *osb = OCFS2_SB(dir->i_sb); struct buffer_head *dx_root_bh = NULL; struct ocfs2_dx_root_block *dx_root; diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h index d06e27ec4be4..fb181f6d6c06 100644 --- a/fs/ocfs2/dlm/dlmcommon.h +++ b/fs/ocfs2/dlm/dlmcommon.h @@ -704,10 +704,6 @@ struct dlm_begin_reco __be32 pad2; }; - -#define BITS_PER_BYTE 8 -#define BITS_TO_BYTES(bits) (((bits)+BITS_PER_BYTE-1)/BITS_PER_BYTE) - struct dlm_query_join_request { u8 node_idx; diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c index 06cb96462bf9..1f41171c1468 100644 --- a/fs/ocfs2/extent_map.c +++ b/fs/ocfs2/extent_map.c @@ -416,7 +416,7 @@ static int ocfs2_get_clusters_nocache(struct inode *inode, { int i, ret, tree_height, len; struct ocfs2_dinode *di; - struct ocfs2_extent_block *uninitialized_var(eb); + struct ocfs2_extent_block *eb; struct ocfs2_extent_list *el; struct ocfs2_extent_rec *rec; struct buffer_head *eb_bh = NULL; @@ -613,7 +613,7 @@ int ocfs2_get_clusters(struct inode *inode, u32 v_cluster, unsigned int *extent_flags) { int ret; - unsigned int uninitialized_var(hole_len), flags = 0; + unsigned int hole_len, flags = 0; struct buffer_head *di_bh = NULL; struct ocfs2_extent_rec rec; diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 0141298bb2e5..c1780b14d23d 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -2111,14 +2111,20 @@ static long ocfs2_fallocate(struct file *file, int mode, loff_t offset, struct ocfs2_space_resv sr; int change_size = 1; int cmd = OCFS2_IOC_RESVSP64; + int ret = 0; if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE)) return -EOPNOTSUPP; if (!ocfs2_writes_unwritten_extents(osb)) return -EOPNOTSUPP; - if (mode & FALLOC_FL_KEEP_SIZE) + if (mode & FALLOC_FL_KEEP_SIZE) { change_size = 0; + } else { + ret = inode_newsize_ok(inode, offset + len); + if (ret) + return ret; + } if (mode & FALLOC_FL_PUNCH_HOLE) cmd = OCFS2_IOC_UNRESVSP64; diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c index 1565dd8e8856..fbbc30f20173 100644 --- a/fs/ocfs2/move_extents.c +++ b/fs/ocfs2/move_extents.c @@ -115,14 +115,6 @@ static int __ocfs2_move_extent(handle_t *handle, */ replace_rec.e_flags = ext_flags & ~OCFS2_EXT_REFCOUNTED; - ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), - context->et.et_root_bh, - OCFS2_JOURNAL_ACCESS_WRITE); - if (ret) { - mlog_errno(ret); - goto out; - } - ret = ocfs2_split_extent(handle, &context->et, path, index, &replace_rec, context->meta_ac, &context->dealloc); @@ -131,8 +123,6 @@ static int __ocfs2_move_extent(handle_t *handle, goto out; } - ocfs2_journal_dirty(handle, context->et.et_root_bh); - context->new_phys_cpos = new_p_cpos; /* @@ -454,7 +444,7 @@ static int ocfs2_find_victim_alloc_group(struct inode *inode, bg = (struct ocfs2_group_desc *)gd_bh->b_data; if (vict_blkno < (le64_to_cpu(bg->bg_blkno) + - le16_to_cpu(bg->bg_bits))) { + (le16_to_cpu(bg->bg_bits) << bits_per_unit))) { *ret_bh = gd_bh; *vict_bit = (vict_blkno - blkno) >> @@ -569,6 +559,7 @@ static void ocfs2_probe_alloc_group(struct inode *inode, struct buffer_head *bh, last_free_bits++; if (last_free_bits == move_len) { + i -= move_len; *goal_bit = i; *phys_cpos = base_cpos + i; break; @@ -1040,18 +1031,19 @@ int ocfs2_ioctl_move_extents(struct file *filp, void __user *argp) context->range = ⦥ + /* + * ok, the default theshold for the defragmentation + * is 1M, since our maximum clustersize was 1M also. + * any thought? + */ + if (!range.me_threshold) + range.me_threshold = 1024 * 1024; + + if (range.me_threshold > i_size_read(inode)) + range.me_threshold = i_size_read(inode); + if (range.me_flags & OCFS2_MOVE_EXT_FL_AUTO_DEFRAG) { context->auto_defrag = 1; - /* - * ok, the default theshold for the defragmentation - * is 1M, since our maximum clustersize was 1M also. - * any thought? - */ - if (!range.me_threshold) - range.me_threshold = 1024 * 1024; - - if (range.me_threshold > i_size_read(inode)) - range.me_threshold = i_size_read(inode); if (range.me_flags & OCFS2_MOVE_EXT_FL_PART_DEFRAG) context->partial = 1; diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index d437b2192522..bb8483510327 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -1538,6 +1538,10 @@ static int ocfs2_rename(struct inode *old_dir, status = ocfs2_add_entry(handle, new_dentry, old_inode, OCFS2_I(old_inode)->ip_blkno, new_dir_bh, &target_insert); + if (status < 0) { + mlog_errno(status); + goto bail; + } } old_inode->i_ctime = current_time(old_inode); @@ -2506,7 +2510,7 @@ int ocfs2_create_inode_in_orphan(struct inode *dir, struct buffer_head *new_di_bh = NULL; struct ocfs2_alloc_context *inode_ac = NULL; struct ocfs2_dir_lookup_result orphan_insert = { NULL, }; - u64 uninitialized_var(di_blkno), suballoc_loc; + u64 di_blkno, suballoc_loc; u16 suballoc_bit; status = ocfs2_inode_lock(dir, &parent_di_bh, 1); diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index fc197e599e8c..e184b36f8dd3 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -1069,7 +1069,7 @@ static int ocfs2_get_refcount_rec(struct ocfs2_caching_info *ci, struct buffer_head **ret_bh) { int ret = 0, i, found; - u32 low_cpos, uninitialized_var(cpos_end); + u32 low_cpos, cpos_end; struct ocfs2_extent_list *el; struct ocfs2_extent_rec *rec = NULL; struct ocfs2_extent_block *eb = NULL; diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c index e7eb08ac4215..10d691530d83 100644 --- a/fs/ocfs2/stackglue.c +++ b/fs/ocfs2/stackglue.c @@ -715,6 +715,8 @@ static struct ctl_table_header *ocfs2_table_header; static int __init ocfs2_stack_glue_init(void) { + int ret; + strcpy(cluster_stack_name, OCFS2_STACK_PLUGIN_O2CB); ocfs2_table_header = register_sysctl_table(ocfs2_root_table); @@ -724,7 +726,11 @@ static int __init ocfs2_stack_glue_init(void) return -ENOMEM; /* or something. */ } - return ocfs2_sysfs_init(); + ret = ocfs2_sysfs_init(); + if (ret) + unregister_sysctl_table(ocfs2_table_header); + + return ret; } static void __exit ocfs2_stack_glue_exit(void) diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 7a08053d95c2..4fd99ef7f334 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -985,8 +985,10 @@ static void ocfs2_disable_quotas(struct ocfs2_super *osb) for (type = 0; type < OCFS2_MAXQUOTAS; type++) { if (!sb_has_quota_loaded(sb, type)) continue; - oinfo = sb_dqinfo(sb, type)->dqi_priv; - cancel_delayed_work_sync(&oinfo->dqi_sync_work); + if (!sb_has_quota_suspended(sb, type)) { + oinfo = sb_dqinfo(sb, type)->dqi_priv; + cancel_delayed_work_sync(&oinfo->dqi_sync_work); + } inode = igrab(sb->s_dquot.files[type]); /* Turn off quotas. This will remove all dquot structures from * memory and so they will be automatically synced to global diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index c146e12a8601..54d881c9ac81 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -1219,7 +1219,7 @@ static int ocfs2_xattr_block_get(struct inode *inode, struct ocfs2_xattr_value_root *xv; size_t size; int ret = -ENODATA, name_offset, name_len, i; - int uninitialized_var(block_off); + int block_off; xs->bucket = ocfs2_xattr_bucket_new(inode); if (!xs->bucket) { diff --git a/fs/omfs/file.c b/fs/omfs/file.c index bf83e6644333..ce59b2fb50c7 100644 --- a/fs/omfs/file.c +++ b/fs/omfs/file.c @@ -220,7 +220,7 @@ static int omfs_get_block(struct inode *inode, sector_t block, struct buffer_head *bh; sector_t next, offset; int ret; - u64 uninitialized_var(new_block); + u64 new_block; u32 max_extents; int extent_count; struct omfs_extent *oe; diff --git a/fs/orangefs/orangefs-debugfs.c b/fs/orangefs/orangefs-debugfs.c index e24738c691f6..f79c015fa7cb 100644 --- a/fs/orangefs/orangefs-debugfs.c +++ b/fs/orangefs/orangefs-debugfs.c @@ -254,6 +254,8 @@ out: void orangefs_debugfs_cleanup(void) { debugfs_remove_recursive(debug_dir); + kfree(debug_help_string); + debug_help_string = NULL; } /* open ORANGEFS_KMOD_DEBUG_HELP_FILE */ @@ -709,6 +711,7 @@ int orangefs_prepare_debugfs_help_string(int at_boot) memset(debug_help_string, 0, DEBUG_HELP_STRING_SIZE); strlcat(debug_help_string, new, string_size); mutex_unlock(&orangefs_help_file_lock); + kfree(new); } rc = 0; diff --git a/fs/orangefs/orangefs-mod.c b/fs/orangefs/orangefs-mod.c index 85ef87245a87..c8818163e392 100644 --- a/fs/orangefs/orangefs-mod.c +++ b/fs/orangefs/orangefs-mod.c @@ -141,7 +141,7 @@ static int __init orangefs_init(void) gossip_err("%s: could not initialize device subsystem %d!\n", __func__, ret); - goto cleanup_device; + goto cleanup_sysfs; } ret = register_filesystem(&orangefs_fs_type); @@ -153,11 +153,11 @@ static int __init orangefs_init(void) goto out; } - orangefs_sysfs_exit(); - -cleanup_device: orangefs_dev_cleanup(); +cleanup_sysfs: + orangefs_sysfs_exit(); + sysfs_init_failed: debugfs_init_failed: diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 30abafcd4ecc..debcac35a51d 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -195,7 +195,7 @@ static int ovl_set_timestamps(struct dentry *upperdentry, struct kstat *stat) { struct iattr attr = { .ia_valid = - ATTR_ATIME | ATTR_MTIME | ATTR_ATIME_SET | ATTR_MTIME_SET, + ATTR_ATIME | ATTR_MTIME | ATTR_ATIME_SET | ATTR_MTIME_SET | ATTR_CTIME, .ia_atime = stat->atime, .ia_mtime = stat->mtime, }; @@ -713,7 +713,7 @@ static int ovl_copy_up_meta_inode_data(struct ovl_copy_up_ctx *c) struct path upperpath, datapath; int err; char *capability = NULL; - ssize_t uninitialized_var(cap_size); + ssize_t cap_size; ovl_path_upper(c->dentry, &upperpath); if (WARN_ON(upperpath.dentry == NULL)) diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 06dc649629c7..9fa64dbde97a 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -561,28 +561,42 @@ static int ovl_create_or_link(struct dentry *dentry, struct inode *inode, goto out_revert_creds; } - err = -ENOMEM; - override_cred = prepare_creds(); - if (override_cred) { + if (!attr->hardlink) { + err = -ENOMEM; + override_cred = prepare_creds(); + if (!override_cred) + goto out_revert_creds; + /* + * In the creation cases(create, mkdir, mknod, symlink), + * ovl should transfer current's fs{u,g}id to underlying + * fs. Because underlying fs want to initialize its new + * inode owner using current's fs{u,g}id. And in this + * case, the @inode is a new inode that is initialized + * in inode_init_owner() to current's fs{u,g}id. So use + * the inode's i_{u,g}id to override the cred's fs{u,g}id. + * + * But in the other hardlink case, ovl_link() does not + * create a new inode, so just use the ovl mounter's + * fs{u,g}id. + */ override_cred->fsuid = inode->i_uid; override_cred->fsgid = inode->i_gid; - if (!attr->hardlink) { - err = security_dentry_create_files_as(dentry, - attr->mode, &dentry->d_name, old_cred, - override_cred); - if (err) { - put_cred(override_cred); - goto out_revert_creds; - } + err = security_dentry_create_files_as(dentry, + attr->mode, &dentry->d_name, old_cred, + override_cred); + if (err) { + put_cred(override_cred); + goto out_revert_creds; } put_cred(override_creds(override_cred)); put_cred(override_cred); - - if (!ovl_dentry_is_whiteout(dentry)) - err = ovl_create_upper(dentry, inode, attr); - else - err = ovl_create_over_whiteout(dentry, inode, attr); } + + if (!ovl_dentry_is_whiteout(dentry)) + err = ovl_create_upper(dentry, inode, attr); + else + err = ovl_create_over_whiteout(dentry, inode, attr); + out_revert_creds: revert_creds(old_cred); return err; diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c index badf039267a2..e51dc7f16596 100644 --- a/fs/overlayfs/namei.c +++ b/fs/overlayfs/namei.c @@ -203,7 +203,7 @@ static int ovl_lookup_single(struct dentry *base, struct ovl_lookup_data *d, int err; bool last_element = !post[0]; - this = lookup_one_len_unlocked(name, base, namelen); + this = lookup_positive_unlocked(name, base, namelen); if (IS_ERR(this)) { err = PTR_ERR(this); this = NULL; @@ -211,8 +211,6 @@ static int ovl_lookup_single(struct dentry *base, struct ovl_lookup_data *d, goto out; goto out_err; } - if (!this->d_inode) - goto put_and_out; if (ovl_dentry_weird(this)) { /* Don't support traversing automounts and other weirdness */ @@ -654,7 +652,7 @@ struct dentry *ovl_get_index_fh(struct ovl_fs *ofs, struct ovl_fh *fh) if (err) return ERR_PTR(err); - index = lookup_one_len_unlocked(name.name, ofs->indexdir, name.len); + index = lookup_positive_unlocked(name.name, ofs->indexdir, name.len); kfree(name.name); if (IS_ERR(index)) { if (PTR_ERR(index) == -ENOENT) @@ -662,9 +660,7 @@ struct dentry *ovl_get_index_fh(struct ovl_fs *ofs, struct ovl_fh *fh) return index; } - if (d_is_negative(index)) - err = 0; - else if (ovl_is_whiteout(index)) + if (ovl_is_whiteout(index)) err = -ESTALE; else if (ovl_dentry_weird(index)) err = -EIO; @@ -688,7 +684,7 @@ struct dentry *ovl_lookup_index(struct ovl_fs *ofs, struct dentry *upper, if (err) return ERR_PTR(err); - index = lookup_one_len_unlocked(name.name, ofs->indexdir, name.len); + index = lookup_positive_unlocked(name.name, ofs->indexdir, name.len); if (IS_ERR(index)) { err = PTR_ERR(index); if (err == -ENOENT) { @@ -703,9 +699,7 @@ struct dentry *ovl_lookup_index(struct ovl_fs *ofs, struct dentry *upper, } inode = d_inode(index); - if (d_is_negative(index)) { - goto out_dput; - } else if (ovl_is_whiteout(index) && !verify) { + if (ovl_is_whiteout(index) && !verify) { /* * When index lookup is called with !verify for decoding an * overlay file handle, a whiteout index implies that decode @@ -1134,7 +1128,7 @@ bool ovl_lower_positive(struct dentry *dentry) struct dentry *this; struct dentry *lowerdir = poe->lowerstack[i].dentry; - this = lookup_one_len_unlocked(name->name, lowerdir, + this = lookup_positive_unlocked(name->name, lowerdir, name->len); if (IS_ERR(this)) { switch (PTR_ERR(this)) { @@ -1151,10 +1145,8 @@ bool ovl_lower_positive(struct dentry *dentry) break; } } else { - if (this->d_inode) { - positive = !ovl_is_whiteout(this); - done = true; - } + positive = !ovl_is_whiteout(this); + done = true; dput(this); } } diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 1a7a1e298885..1c1eb873e6ec 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -268,8 +268,8 @@ static int ovl_sync_fs(struct super_block *sb, int wait) return 0; /* - * If this is a sync(2) call or an emergency sync, all the super blocks - * will be iterated, including upper_sb, so no need to do anything. + * Not called for sync(2) call or an emergency sync (SB_I_SKIP_SYNC). + * All the super blocks will be iterated, including upper_sb. * * If this is a syncfs(2) call, then we do need to call * sync_filesystem() on upper_sb, but enough if we do it when being @@ -1664,6 +1664,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) sb->s_xattr = ovl_xattr_handlers; sb->s_fs_info = ofs; sb->s_flags |= SB_POSIXACL; + sb->s_iflags |= SB_I_SKIP_SYNC; err = -ENOMEM; root_dentry = d_make_root(ovl_new_inode(sb, S_IFDIR, 0)); diff --git a/fs/pnode.c b/fs/pnode.c index 7910ae91f17e..d27b7b97c4c1 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -245,7 +245,7 @@ static int propagate_one(struct mount *m) } do { struct mount *parent = last_source->mnt_parent; - if (last_source == first_source) + if (peers(last_source, first_source)) break; done = parent->mnt_master == p; if (done && peers(n, parent)) diff --git a/fs/proc/base.c b/fs/proc/base.c index e3f10c110b74..69f48794b550 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -3338,7 +3338,8 @@ static int proc_tid_comm_permission(struct inode *inode, int mask) } static const struct inode_operations proc_tid_comm_inode_operations = { - .permission = proc_tid_comm_permission, + .setattr = proc_setattr, + .permission = proc_tid_comm_permission, }; /* diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index c95f32b83a94..7c62a526506c 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -13,6 +13,7 @@ #include <linux/namei.h> #include <linux/mm.h> #include <linux/module.h> +#include <linux/kmemleak.h> #include "internal.h" static const struct dentry_operations proc_sys_dentry_operations; @@ -1376,6 +1377,38 @@ struct ctl_table_header *register_sysctl(const char *path, struct ctl_table *tab } EXPORT_SYMBOL(register_sysctl); +/** + * __register_sysctl_init() - register sysctl table to path + * @path: path name for sysctl base + * @table: This is the sysctl table that needs to be registered to the path + * @table_name: The name of sysctl table, only used for log printing when + * registration fails + * + * The sysctl interface is used by userspace to query or modify at runtime + * a predefined value set on a variable. These variables however have default + * values pre-set. Code which depends on these variables will always work even + * if register_sysctl() fails. If register_sysctl() fails you'd just loose the + * ability to query or modify the sysctls dynamically at run time. Chances of + * register_sysctl() failing on init are extremely low, and so for both reasons + * this function does not return any error as it is used by initialization code. + * + * Context: Can only be called after your respective sysctl base path has been + * registered. So for instance, most base directories are registered early on + * init before init levels are processed through proc_sys_init() and + * sysctl_init(). + */ +void __init __register_sysctl_init(const char *path, struct ctl_table *table, + const char *table_name) +{ + struct ctl_table_header *hdr = register_sysctl(path, table); + + if (unlikely(!hdr)) { + pr_err("failed when register_sysctl %s to %s\n", table_name, path); + return; + } + kmemleak_not_leak(hdr); +} + static char *append_path(const char *path, char *pos, const char *name) { int namelen; diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index dc63d4c6029e..2f2afc3c6fc6 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -701,9 +701,7 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask, page = device_private_entry_to_page(swpent); } if (page) { - int mapcount = page_mapcount(page); - - if (mapcount >= 2) + if (page_mapcount(page) >= 2 || hugetlb_pmd_shared(pte)) mss->shared_hugetlb += huge_page_size(hstate_vma(vma)); else mss->private_hugetlb += huge_page_size(hstate_vma(vma)); diff --git a/fs/pstore/Kconfig b/fs/pstore/Kconfig index 503086f7f7c1..d5fb6d95d4d4 100644 --- a/fs/pstore/Kconfig +++ b/fs/pstore/Kconfig @@ -117,6 +117,7 @@ config PSTORE_CONSOLE config PSTORE_PMSG bool "Log user space messages" depends on PSTORE + select RT_MUTEXES help When the option is enabled, pstore will export a character interface /dev/pmsg0 to log user space messages. On reboot diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index bafbab2dd039..33294dee7d7f 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -753,6 +753,7 @@ static int ramoops_probe(struct platform_device *pdev) /* Make sure we didn't get bogus platform data pointer. */ if (!pdata) { pr_err("NULL platform data\n"); + err = -EINVAL; goto fail_out; } @@ -760,6 +761,7 @@ static int ramoops_probe(struct platform_device *pdev) !pdata->ftrace_size && !pdata->pmsg_size)) { pr_err("The memory size and the record/console size must be " "non-zero\n"); + err = -EINVAL; goto fail_out; } diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c index 3c777ec80d47..a6e5022469ab 100644 --- a/fs/pstore/ram_core.c +++ b/fs/pstore/ram_core.c @@ -189,7 +189,7 @@ static int persistent_ram_init_ecc(struct persistent_ram_zone *prz, { int numerr; struct persistent_ram_buffer *buffer = prz->buffer; - int ecc_blocks; + size_t ecc_blocks; size_t ecc_total; if (!ecc_info || !ecc_info->ecc_size) @@ -426,7 +426,11 @@ static void *persistent_ram_vmap(phys_addr_t start, size_t size, phys_addr_t addr = page_start + i * PAGE_SIZE; pages[i] = pfn_to_page(addr >> PAGE_SHIFT); } - vaddr = vmap(pages, page_count, VM_MAP, prot); + /* + * VM_IOREMAP used here to bypass this region during vread() + * and kmap_atomic() (i.e. kcore) to avoid __va() failures. + */ + vaddr = vmap(pages, page_count, VM_MAP | VM_IOREMAP, prot); kfree(pages); /* @@ -496,7 +500,7 @@ static int persistent_ram_post_init(struct persistent_ram_zone *prz, u32 sig, sig ^= PERSISTENT_RAM_SIG; if (prz->buffer->sig == sig) { - if (buffer_size(prz) == 0) { + if (buffer_size(prz) == 0 && buffer_start(prz) == 0) { pr_debug("found existing empty buffer\n"); return 0; } diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index ddb379abd919..868936076f41 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -223,18 +223,31 @@ static void put_quota_format(struct quota_format_type *fmt) /* * Dquot List Management: - * The quota code uses three lists for dquot management: the inuse_list, - * free_dquots, and dquot_hash[] array. A single dquot structure may be - * on all three lists, depending on its current state. + * The quota code uses five lists for dquot management: the inuse_list, + * releasing_dquots, free_dquots, dqi_dirty_list, and dquot_hash[] array. + * A single dquot structure may be on some of those lists, depending on + * its current state. * * All dquots are placed to the end of inuse_list when first created, and this * list is used for invalidate operation, which must look at every dquot. * - * Unused dquots (dq_count == 0) are added to the free_dquots list when freed, - * and this list is searched whenever we need an available dquot. Dquots are - * removed from the list as soon as they are used again, and - * dqstats.free_dquots gives the number of dquots on the list. When - * dquot is invalidated it's completely released from memory. + * When the last reference of a dquot is dropped, the dquot is added to + * releasing_dquots. We'll then queue work item which will call + * synchronize_srcu() and after that perform the final cleanup of all the + * dquots on the list. Each cleaned up dquot is moved to free_dquots list. + * Both releasing_dquots and free_dquots use the dq_free list_head in the dquot + * struct. + * + * Unused and cleaned up dquots are in the free_dquots list and this list is + * searched whenever we need an available dquot. Dquots are removed from the + * list as soon as they are used again and dqstats.free_dquots gives the number + * of dquots on the list. When dquot is invalidated it's completely released + * from memory. + * + * Dirty dquots are added to the dqi_dirty_list of quota_info when mark + * dirtied, and this list is searched when writing dirty dquots back to + * quota file. Note that some filesystems do dirty dquot tracking on their + * own (e.g. in a journal) and thus don't use dqi_dirty_list. * * Dquots with a specific identity (device, type and id) are placed on * one of the dquot_hash[] hash chains. The provides an efficient search @@ -243,6 +256,7 @@ static void put_quota_format(struct quota_format_type *fmt) static LIST_HEAD(inuse_list); static LIST_HEAD(free_dquots); +static LIST_HEAD(releasing_dquots); static unsigned int dq_hash_bits, dq_hash_mask; static struct hlist_head *dquot_hash; @@ -253,6 +267,9 @@ static qsize_t inode_get_rsv_space(struct inode *inode); static qsize_t __inode_get_rsv_space(struct inode *inode); static int __dquot_initialize(struct inode *inode, int type); +static void quota_release_workfn(struct work_struct *work); +static DECLARE_DELAYED_WORK(quota_release_work, quota_release_workfn); + static inline unsigned int hashfn(const struct super_block *sb, struct kqid qid) { @@ -300,12 +317,21 @@ static inline void put_dquot_last(struct dquot *dquot) dqstats_inc(DQST_FREE_DQUOTS); } +static inline void put_releasing_dquots(struct dquot *dquot) +{ + list_add_tail(&dquot->dq_free, &releasing_dquots); + set_bit(DQ_RELEASING_B, &dquot->dq_flags); +} + static inline void remove_free_dquot(struct dquot *dquot) { if (list_empty(&dquot->dq_free)) return; list_del_init(&dquot->dq_free); - dqstats_dec(DQST_FREE_DQUOTS); + if (!test_bit(DQ_RELEASING_B, &dquot->dq_flags)) + dqstats_dec(DQST_FREE_DQUOTS); + else + clear_bit(DQ_RELEASING_B, &dquot->dq_flags); } static inline void put_inuse(struct dquot *dquot) @@ -331,6 +357,11 @@ static void wait_on_dquot(struct dquot *dquot) mutex_unlock(&dquot->dq_lock); } +static inline int dquot_active(struct dquot *dquot) +{ + return test_bit(DQ_ACTIVE_B, &dquot->dq_flags); +} + static inline int dquot_dirty(struct dquot *dquot) { return test_bit(DQ_MOD_B, &dquot->dq_flags); @@ -346,14 +377,14 @@ int dquot_mark_dquot_dirty(struct dquot *dquot) { int ret = 1; - if (!test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) + if (!dquot_active(dquot)) return 0; if (sb_dqopt(dquot->dq_sb)->flags & DQUOT_NOLIST_DIRTY) return test_and_set_bit(DQ_MOD_B, &dquot->dq_flags); /* If quota is dirty already, we don't have to acquire dq_list_lock */ - if (test_bit(DQ_MOD_B, &dquot->dq_flags)) + if (dquot_dirty(dquot)) return 1; spin_lock(&dq_list_lock); @@ -432,7 +463,7 @@ int dquot_acquire(struct dquot *dquot) smp_mb__before_atomic(); set_bit(DQ_READ_B, &dquot->dq_flags); /* Instantiate dquot if needed */ - if (!test_bit(DQ_ACTIVE_B, &dquot->dq_flags) && !dquot->dq_off) { + if (!dquot_active(dquot) && !dquot->dq_off) { ret = dqopt->ops[dquot->dq_id.type]->commit_dqblk(dquot); /* Write the info if needed */ if (info_dirty(&dqopt->info[dquot->dq_id.type])) { @@ -471,7 +502,7 @@ int dquot_commit(struct dquot *dquot) goto out_lock; /* Inactive dquot can be only if there was error during read/init * => we have better not writing it */ - if (test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) + if (dquot_active(dquot)) ret = dqopt->ops[dquot->dq_id.type]->commit_dqblk(dquot); else ret = -EIO; @@ -532,6 +563,8 @@ static void invalidate_dquots(struct super_block *sb, int type) struct dquot *dquot, *tmp; restart: + flush_delayed_work("a_release_work); + spin_lock(&dq_list_lock); list_for_each_entry_safe(dquot, tmp, &inuse_list, dq_inuse) { if (dquot->dq_sb != sb) @@ -540,7 +573,7 @@ restart: continue; /* Wait for dquot users */ if (atomic_read(&dquot->dq_count)) { - dqgrab(dquot); + atomic_inc(&dquot->dq_count); spin_unlock(&dq_list_lock); /* * Once dqput() wakes us up, we know it's time to free @@ -559,6 +592,15 @@ restart: goto restart; } /* + * The last user already dropped its reference but dquot didn't + * get fully cleaned up yet. Restart the scan which flushes the + * work cleaning up released dquots. + */ + if (test_bit(DQ_RELEASING_B, &dquot->dq_flags)) { + spin_unlock(&dq_list_lock); + goto restart; + } + /* * Quota now has no users and it has been written on last * dqput() */ @@ -582,14 +624,13 @@ int dquot_scan_active(struct super_block *sb, spin_lock(&dq_list_lock); list_for_each_entry(dquot, &inuse_list, dq_inuse) { - if (!test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) + if (!dquot_active(dquot)) continue; if (dquot->dq_sb != sb) continue; /* Now we have active dquot so we can just increase use count */ atomic_inc(&dquot->dq_count); spin_unlock(&dq_list_lock); - dqstats_inc(DQST_LOOKUPS); dqput(old_dquot); old_dquot = dquot; /* @@ -598,7 +639,7 @@ int dquot_scan_active(struct super_block *sb, * outstanding call and recheck the DQ_ACTIVE_B after that. */ wait_on_dquot(dquot); - if (test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) { + if (dquot_active(dquot)) { ret = fn(dquot, priv); if (ret < 0) goto out; @@ -614,6 +655,18 @@ out: } EXPORT_SYMBOL(dquot_scan_active); +static inline int dquot_write_dquot(struct dquot *dquot) +{ + int ret = dquot->dq_sb->dq_op->write_dquot(dquot); + if (ret < 0) { + quota_error(dquot->dq_sb, "Can't write quota structure " + "(error %d). Quota may get out of sync!", ret); + /* Clear dirty bit anyway to avoid infinite loop. */ + clear_dquot_dirty(dquot); + } + return ret; +} + /* Write all dquot structures to quota files */ int dquot_writeback_dquots(struct super_block *sb, int type) { @@ -637,24 +690,23 @@ int dquot_writeback_dquots(struct super_block *sb, int type) dquot = list_first_entry(&dirty, struct dquot, dq_dirty); - WARN_ON(!test_bit(DQ_ACTIVE_B, &dquot->dq_flags)); + WARN_ON(!dquot_active(dquot)); + /* If the dquot is releasing we should not touch it */ + if (test_bit(DQ_RELEASING_B, &dquot->dq_flags)) { + spin_unlock(&dq_list_lock); + flush_delayed_work("a_release_work); + spin_lock(&dq_list_lock); + continue; + } /* Now we have active dquot from which someone is * holding reference so we can safely just increase * use count */ dqgrab(dquot); spin_unlock(&dq_list_lock); - dqstats_inc(DQST_LOOKUPS); - err = sb->dq_op->write_dquot(dquot); - if (err) { - /* - * Clear dirty bit anyway to avoid infinite - * loop here. - */ - clear_dquot_dirty(dquot); - if (!ret) - ret = err; - } + err = dquot_write_dquot(dquot); + if (err && !ret) + ret = err; dqput(dquot); spin_lock(&dq_list_lock); } @@ -748,12 +800,52 @@ static struct shrinker dqcache_shrinker = { }; /* + * Safely release dquot and put reference to dquot. + */ +static void quota_release_workfn(struct work_struct *work) +{ + struct dquot *dquot; + struct list_head rls_head; + + spin_lock(&dq_list_lock); + /* Exchange the list head to avoid livelock. */ + list_replace_init(&releasing_dquots, &rls_head); + spin_unlock(&dq_list_lock); + synchronize_srcu(&dquot_srcu); + +restart: + spin_lock(&dq_list_lock); + while (!list_empty(&rls_head)) { + dquot = list_first_entry(&rls_head, struct dquot, dq_free); + WARN_ON_ONCE(atomic_read(&dquot->dq_count)); + /* + * Note that DQ_RELEASING_B protects us from racing with + * invalidate_dquots() calls so we are safe to work with the + * dquot even after we drop dq_list_lock. + */ + if (dquot_dirty(dquot)) { + spin_unlock(&dq_list_lock); + /* Commit dquot before releasing */ + dquot_write_dquot(dquot); + goto restart; + } + if (dquot_active(dquot)) { + spin_unlock(&dq_list_lock); + dquot->dq_sb->dq_op->release_dquot(dquot); + goto restart; + } + /* Dquot is inactive and clean, now move it to free list */ + remove_free_dquot(dquot); + put_dquot_last(dquot); + } + spin_unlock(&dq_list_lock); +} + +/* * Put reference to dquot */ void dqput(struct dquot *dquot) { - int ret; - if (!dquot) return; #ifdef CONFIG_QUOTA_DEBUG @@ -765,7 +857,7 @@ void dqput(struct dquot *dquot) } #endif dqstats_inc(DQST_DROPS); -we_slept: + spin_lock(&dq_list_lock); if (atomic_read(&dquot->dq_count) > 1) { /* We have more than one user... nothing to do */ @@ -777,35 +869,16 @@ we_slept: spin_unlock(&dq_list_lock); return; } + /* Need to release dquot? */ - if (dquot_dirty(dquot)) { - spin_unlock(&dq_list_lock); - /* Commit dquot before releasing */ - ret = dquot->dq_sb->dq_op->write_dquot(dquot); - if (ret < 0) { - quota_error(dquot->dq_sb, "Can't write quota structure" - " (error %d). Quota may get out of sync!", - ret); - /* - * We clear dirty bit anyway, so that we avoid - * infinite loop here - */ - clear_dquot_dirty(dquot); - } - goto we_slept; - } - if (test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) { - spin_unlock(&dq_list_lock); - dquot->dq_sb->dq_op->release_dquot(dquot); - goto we_slept; - } - atomic_dec(&dquot->dq_count); #ifdef CONFIG_QUOTA_DEBUG /* sanity check */ BUG_ON(!list_empty(&dquot->dq_free)); #endif - put_dquot_last(dquot); + put_releasing_dquots(dquot); + atomic_dec(&dquot->dq_count); spin_unlock(&dq_list_lock); + queue_delayed_work(system_unbound_wq, "a_release_work, 1); } EXPORT_SYMBOL(dqput); @@ -892,10 +965,10 @@ we_slept: dqstats_inc(DQST_LOOKUPS); } /* Wait for dq_lock - after this we know that either dquot_release() is - * already finished or it will be canceled due to dq_count > 1 test */ + * already finished or it will be canceled due to dq_count > 0 test */ wait_on_dquot(dquot); /* Read the dquot / allocate space in quota file */ - if (!test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) { + if (!dquot_active(dquot)) { int err; err = sb->dq_op->acquire_dquot(dquot); @@ -1408,7 +1481,7 @@ static int info_bdq_free(struct dquot *dquot, qsize_t space) return QUOTA_NL_NOWARN; } -static int dquot_active(const struct inode *inode) +static int inode_quota_active(const struct inode *inode) { struct super_block *sb = inode->i_sb; @@ -1431,7 +1504,7 @@ static int __dquot_initialize(struct inode *inode, int type) qsize_t rsv; int ret = 0; - if (!dquot_active(inode)) + if (!inode_quota_active(inode)) return 0; dquots = i_dquot(inode); @@ -1539,7 +1612,7 @@ bool dquot_initialize_needed(struct inode *inode) struct dquot **dquots; int i; - if (!dquot_active(inode)) + if (!inode_quota_active(inode)) return false; dquots = i_dquot(inode); @@ -1650,7 +1723,7 @@ int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags) int reserve = flags & DQUOT_SPACE_RESERVE; struct dquot **dquots; - if (!dquot_active(inode)) { + if (!inode_quota_active(inode)) { if (reserve) { spin_lock(&inode->i_lock); *inode_reserved_space(inode) += number; @@ -1722,7 +1795,7 @@ int dquot_alloc_inode(struct inode *inode) struct dquot_warn warn[MAXQUOTAS]; struct dquot * const *dquots; - if (!dquot_active(inode)) + if (!inode_quota_active(inode)) return 0; for (cnt = 0; cnt < MAXQUOTAS; cnt++) warn[cnt].w_type = QUOTA_NL_NOWARN; @@ -1765,7 +1838,7 @@ int dquot_claim_space_nodirty(struct inode *inode, qsize_t number) struct dquot **dquots; int cnt, index; - if (!dquot_active(inode)) { + if (!inode_quota_active(inode)) { spin_lock(&inode->i_lock); *inode_reserved_space(inode) -= number; __inode_add_bytes(inode, number); @@ -1807,7 +1880,7 @@ void dquot_reclaim_space_nodirty(struct inode *inode, qsize_t number) struct dquot **dquots; int cnt, index; - if (!dquot_active(inode)) { + if (!inode_quota_active(inode)) { spin_lock(&inode->i_lock); *inode_reserved_space(inode) += number; __inode_sub_bytes(inode, number); @@ -1851,7 +1924,7 @@ void __dquot_free_space(struct inode *inode, qsize_t number, int flags) struct dquot **dquots; int reserve = flags & DQUOT_SPACE_RESERVE, index; - if (!dquot_active(inode)) { + if (!inode_quota_active(inode)) { if (reserve) { spin_lock(&inode->i_lock); *inode_reserved_space(inode) -= number; @@ -1906,7 +1979,7 @@ void dquot_free_inode(struct inode *inode) struct dquot * const *dquots; int index; - if (!dquot_active(inode)) + if (!inode_quota_active(inode)) return; dquots = i_dquot(inode); @@ -2077,7 +2150,7 @@ int dquot_transfer(struct inode *inode, struct iattr *iattr) struct super_block *sb = inode->i_sb; int ret; - if (!dquot_active(inode)) + if (!inode_quota_active(inode)) return 0; if (iattr->ia_valid & ATTR_UID && !uid_eq(iattr->ia_uid, inode->i_uid)){ @@ -2298,28 +2371,76 @@ EXPORT_SYMBOL(dquot_quota_off); * Turn quotas on on a device */ -/* - * Helper function to turn quotas on when we already have the inode of - * quota file and no quota information is loaded. - */ -static int vfs_load_quota_inode(struct inode *inode, int type, int format_id, +static int vfs_setup_quota_inode(struct inode *inode, int type) +{ + struct super_block *sb = inode->i_sb; + struct quota_info *dqopt = sb_dqopt(sb); + + if (is_bad_inode(inode)) + return -EUCLEAN; + if (!S_ISREG(inode->i_mode)) + return -EACCES; + if (IS_RDONLY(inode)) + return -EROFS; + if (sb_has_quota_loaded(sb, type)) + return -EBUSY; + + /* + * Quota files should never be encrypted. They should be thought of as + * filesystem metadata, not user data. New-style internal quota files + * cannot be encrypted by users anyway, but old-style external quota + * files could potentially be incorrectly created in an encrypted + * directory, hence this explicit check. Some reasons why encrypted + * quota files don't work include: (1) some filesystems that support + * encryption don't handle it in their quota_read and quota_write, and + * (2) cleaning up encrypted quota files at unmount would need special + * consideration, as quota files are cleaned up later than user files. + */ + if (IS_ENCRYPTED(inode)) + return -EINVAL; + + dqopt->files[type] = igrab(inode); + if (!dqopt->files[type]) + return -EIO; + if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE)) { + /* We don't want quota and atime on quota files (deadlocks + * possible) Also nobody should write to the file - we use + * special IO operations which ignore the immutable bit. */ + inode_lock(inode); + inode->i_flags |= S_NOQUOTA; + inode_unlock(inode); + /* + * When S_NOQUOTA is set, remove dquot references as no more + * references can be added + */ + __dquot_drop(inode); + } + return 0; +} + +static void vfs_cleanup_quota_inode(struct super_block *sb, int type) +{ + struct quota_info *dqopt = sb_dqopt(sb); + struct inode *inode = dqopt->files[type]; + + if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE)) { + inode_lock(inode); + inode->i_flags &= ~S_NOQUOTA; + inode_unlock(inode); + } + dqopt->files[type] = NULL; + iput(inode); +} + +int dquot_load_quota_sb(struct super_block *sb, int type, int format_id, unsigned int flags) { struct quota_format_type *fmt = find_quota_format(format_id); - struct super_block *sb = inode->i_sb; struct quota_info *dqopt = sb_dqopt(sb); int error; if (!fmt) return -ESRCH; - if (!S_ISREG(inode->i_mode)) { - error = -EACCES; - goto out_fmt; - } - if (IS_RDONLY(inode)) { - error = -EROFS; - goto out_fmt; - } if (!sb->s_op->quota_write || !sb->s_op->quota_read || (type == PRJQUOTA && sb->dq_op->get_projid == NULL)) { error = -EINVAL; @@ -2351,27 +2472,9 @@ static int vfs_load_quota_inode(struct inode *inode, int type, int format_id, invalidate_bdev(sb->s_bdev); } - if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE)) { - /* We don't want quota and atime on quota files (deadlocks - * possible) Also nobody should write to the file - we use - * special IO operations which ignore the immutable bit. */ - inode_lock(inode); - inode->i_flags |= S_NOQUOTA; - inode_unlock(inode); - /* - * When S_NOQUOTA is set, remove dquot references as no more - * references can be added - */ - __dquot_drop(inode); - } - - error = -EIO; - dqopt->files[type] = igrab(inode); - if (!dqopt->files[type]) - goto out_file_flags; error = -EINVAL; if (!fmt->qf_ops->check_quota_file(sb, type)) - goto out_file_init; + goto out_fmt; dqopt->ops[type] = fmt->qf_ops; dqopt->info[type].dqi_format = fmt; @@ -2379,7 +2482,7 @@ static int vfs_load_quota_inode(struct inode *inode, int type, int format_id, INIT_LIST_HEAD(&dqopt->info[type].dqi_dirty_list); error = dqopt->ops[type]->read_file_info(sb, type); if (error < 0) - goto out_file_init; + goto out_fmt; if (dqopt->flags & DQUOT_QUOTA_SYS_FILE) { spin_lock(&dq_data_lock); dqopt->info[type].dqi_flags |= DQF_SYS_FILE; @@ -2391,21 +2494,34 @@ static int vfs_load_quota_inode(struct inode *inode, int type, int format_id, error = add_dquot_ref(sb, type); if (error) - dquot_disable(sb, type, flags); + dquot_disable(sb, type, + DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED); return error; -out_file_init: - dqopt->files[type] = NULL; - iput(inode); -out_file_flags: - inode_lock(inode); - inode->i_flags &= ~S_NOQUOTA; - inode_unlock(inode); out_fmt: put_quota_format(fmt); return error; } +EXPORT_SYMBOL(dquot_load_quota_sb); + +/* + * Helper function to turn quotas on when we already have the inode of + * quota file and no quota information is loaded. + */ +static int vfs_load_quota_inode(struct inode *inode, int type, int format_id, + unsigned int flags) +{ + int err; + + err = vfs_setup_quota_inode(inode, type); + if (err < 0) + return err; + err = dquot_load_quota_sb(inode->i_sb, type, format_id, flags); + if (err < 0) + vfs_cleanup_quota_inode(inode->i_sb, type); + return err; +} /* Reenable quotas on remount RW */ int dquot_resume(struct super_block *sb, int type) @@ -2506,21 +2622,15 @@ int dquot_quota_on_mount(struct super_block *sb, char *qf_name, struct dentry *dentry; int error; - dentry = lookup_one_len_unlocked(qf_name, sb->s_root, strlen(qf_name)); + dentry = lookup_positive_unlocked(qf_name, sb->s_root, strlen(qf_name)); if (IS_ERR(dentry)) return PTR_ERR(dentry); - if (d_really_is_negative(dentry)) { - error = -ENOENT; - goto out; - } - error = security_quota_on(dentry); if (!error) error = vfs_load_quota_inode(d_inode(dentry), type, format_id, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED); -out: dput(dentry); return error; } diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c index 78be6dbcd762..3425a04bc8a0 100644 --- a/fs/reiserfs/journal.c +++ b/fs/reiserfs/journal.c @@ -2336,7 +2336,7 @@ static struct buffer_head *reiserfs_breada(struct block_device *dev, int i, j; bh = __getblk(dev, block, bufsize); - if (buffer_uptodate(bh)) + if (!bh || buffer_uptodate(bh)) return (bh); if (block + BUFNR > max_block) { @@ -2346,6 +2346,8 @@ static struct buffer_head *reiserfs_breada(struct block_device *dev, j = 1; for (i = 1; i < blocks; i++) { bh = __getblk(dev, block + i, bufsize); + if (!bh) + break; if (buffer_uptodate(bh)) { brelse(bh); break; diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c index 959a066b7bb0..2843b7cf4d7a 100644 --- a/fs/reiserfs/namei.c +++ b/fs/reiserfs/namei.c @@ -695,6 +695,7 @@ static int reiserfs_create(struct inode *dir, struct dentry *dentry, umode_t mod out_failed: reiserfs_write_unlock(dir->i_sb); + reiserfs_security_free(&security); return retval; } @@ -778,6 +779,7 @@ static int reiserfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode out_failed: reiserfs_write_unlock(dir->i_sb); + reiserfs_security_free(&security); return retval; } @@ -876,6 +878,7 @@ static int reiserfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode retval = journal_end(&th); out_failed: reiserfs_write_unlock(dir->i_sb); + reiserfs_security_free(&security); return retval; } @@ -1191,6 +1194,7 @@ static int reiserfs_symlink(struct inode *parent_dir, retval = journal_end(&th); out_failed: reiserfs_write_unlock(parent_dir->i_sb); + reiserfs_security_free(&security); return retval; } diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index 831a542c22c6..e5be1d747c03 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -1443,7 +1443,6 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) unsigned long safe_mask = 0; unsigned int commit_max_age = (unsigned int)-1; struct reiserfs_journal *journal = SB_JOURNAL(s); - char *new_opts; int err; char *qf_names[REISERFS_MAXQUOTAS]; unsigned int qfmt = 0; @@ -1451,10 +1450,6 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) int i; #endif - new_opts = kstrdup(arg, GFP_KERNEL); - if (arg && !new_opts) - return -ENOMEM; - sync_filesystem(s); reiserfs_write_lock(s); @@ -1605,7 +1600,6 @@ out_ok_unlocked: out_err_unlock: reiserfs_write_unlock(s); out_err: - kfree(new_opts); return err; } diff --git a/fs/reiserfs/xattr_security.c b/fs/reiserfs/xattr_security.c index 20be9a0e5870..159af6c26f4b 100644 --- a/fs/reiserfs/xattr_security.c +++ b/fs/reiserfs/xattr_security.c @@ -49,6 +49,7 @@ int reiserfs_security_init(struct inode *dir, struct inode *inode, int error; sec->name = NULL; + sec->value = NULL; /* Don't add selinux attributes on xattrs - they'll never get used */ if (IS_PRIVATE(dir)) @@ -80,11 +81,15 @@ int reiserfs_security_write(struct reiserfs_transaction_handle *th, struct inode *inode, struct reiserfs_security_handle *sec) { + char xattr_name[XATTR_NAME_MAX + 1] = XATTR_SECURITY_PREFIX; int error; - if (strlen(sec->name) < sizeof(XATTR_SECURITY_PREFIX)) + + if (XATTR_SECURITY_PREFIX_LEN + strlen(sec->name) > XATTR_NAME_MAX) return -EINVAL; - error = reiserfs_xattr_set_handle(th, inode, sec->name, sec->value, + strlcat(xattr_name, sec->name, sizeof(xattr_name)); + + error = reiserfs_xattr_set_handle(th, inode, xattr_name, sec->value, sec->length, XATTR_CREATE); if (error == -ENODATA || error == -EOPNOTSUPP) error = 0; @@ -94,7 +99,6 @@ int reiserfs_security_write(struct reiserfs_transaction_handle *th, void reiserfs_security_free(struct reiserfs_security_handle *sec) { - kfree(sec->name); kfree(sec->value); sec->name = NULL; sec->value = NULL; diff --git a/fs/squashfs/squashfs_fs.h b/fs/squashfs/squashfs_fs.h index 10e93345b615..75886e6d9c97 100644 --- a/fs/squashfs/squashfs_fs.h +++ b/fs/squashfs/squashfs_fs.h @@ -196,7 +196,7 @@ static inline int squashfs_block_size(__le32 raw) #define SQUASHFS_ID_BLOCK_BYTES(A) (SQUASHFS_ID_BLOCKS(A) *\ sizeof(u64)) /* xattr id lookup table defines */ -#define SQUASHFS_XATTR_BYTES(A) ((A) * sizeof(struct squashfs_xattr_id)) +#define SQUASHFS_XATTR_BYTES(A) (((u64) (A)) * sizeof(struct squashfs_xattr_id)) #define SQUASHFS_XATTR_BLOCK(A) (SQUASHFS_XATTR_BYTES(A) / \ SQUASHFS_METADATA_SIZE) diff --git a/fs/squashfs/squashfs_fs_sb.h b/fs/squashfs/squashfs_fs_sb.h index 5234c19a0eab..7ec30a11273e 100644 --- a/fs/squashfs/squashfs_fs_sb.h +++ b/fs/squashfs/squashfs_fs_sb.h @@ -76,7 +76,7 @@ struct squashfs_sb_info { long long bytes_used; unsigned int inodes; unsigned int fragments; - int xattr_ids; + unsigned int xattr_ids; unsigned int ids; }; #endif diff --git a/fs/squashfs/xattr.h b/fs/squashfs/xattr.h index 86b0a0073e51..f360f27e38f3 100644 --- a/fs/squashfs/xattr.h +++ b/fs/squashfs/xattr.h @@ -23,12 +23,12 @@ #ifdef CONFIG_SQUASHFS_XATTR extern __le64 *squashfs_read_xattr_id_table(struct super_block *, u64, - u64 *, int *); + u64 *, unsigned int *); extern int squashfs_xattr_lookup(struct super_block *, unsigned int, int *, unsigned int *, unsigned long long *); #else static inline __le64 *squashfs_read_xattr_id_table(struct super_block *sb, - u64 start, u64 *xattr_table_start, int *xattr_ids) + u64 start, u64 *xattr_table_start, unsigned int *xattr_ids) { struct squashfs_xattr_id_table *id_table; diff --git a/fs/squashfs/xattr_id.c b/fs/squashfs/xattr_id.c index 7f718d2bf357..fe266b3e95f8 100644 --- a/fs/squashfs/xattr_id.c +++ b/fs/squashfs/xattr_id.c @@ -69,7 +69,7 @@ int squashfs_xattr_lookup(struct super_block *sb, unsigned int index, * Read uncompressed xattr id lookup table indexes from disk into memory */ __le64 *squashfs_read_xattr_id_table(struct super_block *sb, u64 table_start, - u64 *xattr_table_start, int *xattr_ids) + u64 *xattr_table_start, unsigned int *xattr_ids) { struct squashfs_sb_info *msblk = sb->s_fs_info; unsigned int len, indexes; diff --git a/fs/statfs.c b/fs/statfs.c index 56f655f757ff..29786598c2b5 100644 --- a/fs/statfs.c +++ b/fs/statfs.c @@ -114,6 +114,7 @@ static int do_statfs_native(struct kstatfs *st, struct statfs __user *p) if (sizeof(buf) == sizeof(*st)) memcpy(&buf, st, sizeof(*st)); else { + memset(&buf, 0, sizeof(buf)); if (sizeof buf.f_blocks == 4) { if ((st->f_blocks | st->f_bfree | st->f_bavail | st->f_bsize | st->f_frsize) & @@ -142,7 +143,6 @@ static int do_statfs_native(struct kstatfs *st, struct statfs __user *p) buf.f_namelen = st->f_namelen; buf.f_frsize = st->f_frsize; buf.f_flags = st->f_flags; - memset(buf.f_spare, 0, sizeof(buf.f_spare)); } if (copy_to_user(p, &buf, sizeof(buf))) return -EFAULT; @@ -155,6 +155,7 @@ static int do_statfs64(struct kstatfs *st, struct statfs64 __user *p) if (sizeof(buf) == sizeof(*st)) memcpy(&buf, st, sizeof(*st)); else { + memset(&buf, 0, sizeof(buf)); buf.f_type = st->f_type; buf.f_bsize = st->f_bsize; buf.f_blocks = st->f_blocks; @@ -166,7 +167,6 @@ static int do_statfs64(struct kstatfs *st, struct statfs64 __user *p) buf.f_namelen = st->f_namelen; buf.f_frsize = st->f_frsize; buf.f_flags = st->f_flags; - memset(buf.f_spare, 0, sizeof(buf.f_spare)); } if (copy_to_user(p, &buf, sizeof(buf))) return -EFAULT; diff --git a/fs/sync.c b/fs/sync.c index b54e0541ad89..917ebd12c251 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -76,7 +76,8 @@ static void sync_inodes_one_sb(struct super_block *sb, void *arg) static void sync_fs_one_sb(struct super_block *sb, void *arg) { - if (!sb_rdonly(sb) && sb->s_op->sync_fs) + if (!sb_rdonly(sb) && !(sb->s_iflags & SB_I_SKIP_SYNC) && + sb->s_op->sync_fs) sb->s_op->sync_fs(sb, *(int *)arg); } diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 011e391497f4..cd70dbeeab22 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -599,7 +599,7 @@ int sysfs_emit_at(char *buf, int at, const char *fmt, ...) va_list args; int len; - if (WARN(!buf || offset_in_page(buf) || at < 0 || at >= PAGE_SIZE, + if (WARN(!buf || at < 0 || at >= PAGE_SIZE, "invalid sysfs_emit_at: buf:%p at:%d\n", buf, at)) return 0; diff --git a/fs/sysv/itree.c b/fs/sysv/itree.c index bcb67b0cabe7..e3d1673b8ec9 100644 --- a/fs/sysv/itree.c +++ b/fs/sysv/itree.c @@ -145,6 +145,10 @@ static int alloc_branch(struct inode *inode, */ parent = block_to_cpu(SYSV_SB(inode->i_sb), branch[n-1].key); bh = sb_getblk(inode->i_sb, parent); + if (!bh) { + sysv_free_block(inode->i_sb, branch[n].key); + break; + } lock_buffer(bh); memset(bh->b_data, 0, blocksize); branch[n].bh = bh; @@ -438,7 +442,7 @@ static unsigned sysv_nblocks(struct super_block *s, loff_t size) res += blocks; direct = 1; } - return blocks; + return res; } int sysv_getattr(const struct path *path, struct kstat *stat, diff --git a/fs/ubifs/budget.c b/fs/ubifs/budget.c index 7ef22baf9d15..30c7bd63c2ad 100644 --- a/fs/ubifs/budget.c +++ b/fs/ubifs/budget.c @@ -224,11 +224,10 @@ long long ubifs_calc_available(const struct ubifs_info *c, int min_idx_lebs) subtract_lebs += 1; /* - * The GC journal head LEB is not really accessible. And since - * different write types go to different heads, we may count only on - * one head's space. + * Since different write types go to different heads, we should + * reserve one leb for each head. */ - subtract_lebs += c->jhead_cnt - 1; + subtract_lebs += c->jhead_cnt; /* We also reserve one LEB for deletions, which bypass budgeting */ subtract_lebs += 1; @@ -415,7 +414,7 @@ static int calc_dd_growth(const struct ubifs_info *c, dd_growth = req->dirtied_page ? c->bi.page_budget : 0; if (req->dirtied_ino) - dd_growth += c->bi.inode_budget << (req->dirtied_ino - 1); + dd_growth += c->bi.inode_budget * req->dirtied_ino; if (req->mod_dent) dd_growth += c->bi.dent_budget; dd_growth += req->dirtied_ino_d; diff --git a/fs/ubifs/commit.c b/fs/ubifs/commit.c index 591f2c7a48f0..583e20787689 100644 --- a/fs/ubifs/commit.c +++ b/fs/ubifs/commit.c @@ -564,11 +564,11 @@ out: */ int dbg_check_old_index(struct ubifs_info *c, struct ubifs_zbranch *zroot) { - int lnum, offs, len, err = 0, uninitialized_var(last_level), child_cnt; + int lnum, offs, len, err = 0, last_level, child_cnt; int first = 1, iip; struct ubifs_debug_info *d = c->dbg; - union ubifs_key uninitialized_var(lower_key), upper_key, l_key, u_key; - unsigned long long uninitialized_var(last_sqnum); + union ubifs_key lower_key, upper_key, l_key, u_key; + unsigned long long last_sqnum; struct ubifs_idx_node *idx; struct list_head list; struct idx_node *i; diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index 111905ddbfc2..39296e801242 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -445,6 +445,7 @@ static int do_tmpfile(struct inode *dir, struct dentry *dentry, mutex_unlock(&dir_ui->ui_mutex); ubifs_release_budget(c, &req); + fscrypt_free_filename(&nm); return 0; @@ -1141,7 +1142,6 @@ static int ubifs_symlink(struct inode *dir, struct dentry *dentry, int err, sz_change, len = strlen(symname); struct fscrypt_str disk_link; struct ubifs_budget_req req = { .new_ino = 1, .new_dent = 1, - .new_ino_d = ALIGN(len, 8), .dirtied_ino = 1 }; struct fscrypt_name nm; @@ -1157,6 +1157,7 @@ static int ubifs_symlink(struct inode *dir, struct dentry *dentry, * Budget request settings: new inode, new direntry and changing parent * directory inode. */ + req.new_ino_d = ALIGN(disk_link.len - 1, 8); err = ubifs_budget_space(c, &req); if (err) return err; @@ -1293,7 +1294,7 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry, struct ubifs_budget_req ino_req = { .dirtied_ino = 1, .dirtied_ino_d = ALIGN(old_inode_ui->data_len, 8) }; struct timespec64 time; - unsigned int uninitialized_var(saved_nlink); + unsigned int saved_nlink; struct fscrypt_name old_nm, new_nm; /* @@ -1309,9 +1310,13 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry, old_dentry, old_inode->i_ino, old_dir->i_ino, new_dentry, new_dir->i_ino, flags); - if (unlink) + if (unlink) { ubifs_assert(c, inode_is_locked(new_inode)); + /* Budget for old inode's data when its nlink > 1. */ + req.dirtied_ino_d = ALIGN(ubifs_inode(new_inode)->data_len, 8); + } + if (unlink && is_dir) { err = ubifs_check_dir_empty(new_inode); if (err) @@ -1549,6 +1554,10 @@ static int ubifs_xrename(struct inode *old_dir, struct dentry *old_dentry, return err; } + err = ubifs_budget_space(c, &req); + if (err) + goto out; + lock_4_inodes(old_dir, new_dir, NULL, NULL); time = current_time(old_dir); @@ -1574,6 +1583,7 @@ static int ubifs_xrename(struct inode *old_dir, struct dentry *old_dentry, unlock_4_inodes(old_dir, new_dir, NULL, NULL); ubifs_release_budget(c, &req); +out: fscrypt_free_filename(&fst_nm); fscrypt_free_filename(&snd_nm); return err; diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 3dbb5ac630e4..fca3b7f483c7 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -234,7 +234,7 @@ static int write_begin_slow(struct address_space *mapping, struct ubifs_info *c = inode->i_sb->s_fs_info; pgoff_t index = pos >> PAGE_SHIFT; struct ubifs_budget_req req = { .new_page = 1 }; - int uninitialized_var(err), appending = !!(pos + len > inode->i_size); + int err, appending = !!(pos + len > inode->i_size); struct page *page; dbg_gen("ino %lu, pos %llu, len %u, i_size %lld", @@ -438,7 +438,7 @@ static int ubifs_write_begin(struct file *file, struct address_space *mapping, struct ubifs_info *c = inode->i_sb->s_fs_info; struct ubifs_inode *ui = ubifs_inode(inode); pgoff_t index = pos >> PAGE_SHIFT; - int uninitialized_var(err), appending = !!(pos + len > inode->i_size); + int err, appending = !!(pos + len > inode->i_size); int skipped_read = 0; struct page *page; @@ -1043,7 +1043,7 @@ static int ubifs_writepage(struct page *page, struct writeback_control *wbc) if (page->index >= synced_i_size >> PAGE_SHIFT) { err = inode->i_sb->s_op->write_inode(inode, NULL); if (err) - goto out_unlock; + goto out_redirty; /* * The inode has been written, but the write-buffer has * not been synchronized, so in case of an unclean @@ -1071,11 +1071,17 @@ static int ubifs_writepage(struct page *page, struct writeback_control *wbc) if (i_size > synced_i_size) { err = inode->i_sb->s_op->write_inode(inode, NULL); if (err) - goto out_unlock; + goto out_redirty; } return do_writepage(page, len); - +out_redirty: + /* + * redirty_page_for_writepage() won't call ubifs_dirty_inode() because + * it passes I_DIRTY_PAGES flag while calling __mark_inode_dirty(), so + * there is no need to do space budget for dirty inode. + */ + redirty_page_for_writepage(wbc, page); out_unlock: unlock_page(page); return err; diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c index 802565a17733..0a60a065c7e8 100644 --- a/fs/ubifs/journal.c +++ b/fs/ubifs/journal.c @@ -1355,7 +1355,7 @@ int ubifs_jnl_truncate(struct ubifs_info *c, const struct inode *inode, union ubifs_key key, to_key; struct ubifs_ino_node *ino; struct ubifs_trun_node *trun; - struct ubifs_data_node *uninitialized_var(dn); + struct ubifs_data_node *dn; int err, dlen, len, lnum, offs, bit, sz, sync = IS_SYNC(inode); struct ubifs_inode *ui = ubifs_inode(inode); ino_t inum = inode->i_ino; diff --git a/fs/ubifs/lpt.c b/fs/ubifs/lpt.c index 31393370e334..433bfcddc497 100644 --- a/fs/ubifs/lpt.c +++ b/fs/ubifs/lpt.c @@ -287,7 +287,7 @@ uint32_t ubifs_unpack_bits(const struct ubifs_info *c, uint8_t **addr, int *pos, const int k = 32 - nrbits; uint8_t *p = *addr; int b = *pos; - uint32_t uninitialized_var(val); + uint32_t val; const int bytes = (nrbits + b + 7) >> 3; ubifs_assert(c, nrbits > 0); diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c index f15ac37956e7..330ccf72745b 100644 --- a/fs/ubifs/tnc.c +++ b/fs/ubifs/tnc.c @@ -56,6 +56,33 @@ enum { NOT_ON_MEDIA = 3, }; +static void do_insert_old_idx(struct ubifs_info *c, + struct ubifs_old_idx *old_idx) +{ + struct ubifs_old_idx *o; + struct rb_node **p, *parent = NULL; + + p = &c->old_idx.rb_node; + while (*p) { + parent = *p; + o = rb_entry(parent, struct ubifs_old_idx, rb); + if (old_idx->lnum < o->lnum) + p = &(*p)->rb_left; + else if (old_idx->lnum > o->lnum) + p = &(*p)->rb_right; + else if (old_idx->offs < o->offs) + p = &(*p)->rb_left; + else if (old_idx->offs > o->offs) + p = &(*p)->rb_right; + else { + ubifs_err(c, "old idx added twice!"); + kfree(old_idx); + } + } + rb_link_node(&old_idx->rb, parent, p); + rb_insert_color(&old_idx->rb, &c->old_idx); +} + /** * insert_old_idx - record an index node obsoleted since the last commit start. * @c: UBIFS file-system description object @@ -81,35 +108,15 @@ enum { */ static int insert_old_idx(struct ubifs_info *c, int lnum, int offs) { - struct ubifs_old_idx *old_idx, *o; - struct rb_node **p, *parent = NULL; + struct ubifs_old_idx *old_idx; old_idx = kmalloc(sizeof(struct ubifs_old_idx), GFP_NOFS); if (unlikely(!old_idx)) return -ENOMEM; old_idx->lnum = lnum; old_idx->offs = offs; + do_insert_old_idx(c, old_idx); - p = &c->old_idx.rb_node; - while (*p) { - parent = *p; - o = rb_entry(parent, struct ubifs_old_idx, rb); - if (lnum < o->lnum) - p = &(*p)->rb_left; - else if (lnum > o->lnum) - p = &(*p)->rb_right; - else if (offs < o->offs) - p = &(*p)->rb_left; - else if (offs > o->offs) - p = &(*p)->rb_right; - else { - ubifs_err(c, "old idx added twice!"); - kfree(old_idx); - return 0; - } - } - rb_link_node(&old_idx->rb, parent, p); - rb_insert_color(&old_idx->rb, &c->old_idx); return 0; } @@ -211,23 +218,6 @@ static struct ubifs_znode *copy_znode(struct ubifs_info *c, __set_bit(DIRTY_ZNODE, &zn->flags); __clear_bit(COW_ZNODE, &zn->flags); - ubifs_assert(c, !ubifs_zn_obsolete(znode)); - __set_bit(OBSOLETE_ZNODE, &znode->flags); - - if (znode->level != 0) { - int i; - const int n = zn->child_cnt; - - /* The children now have new parent */ - for (i = 0; i < n; i++) { - struct ubifs_zbranch *zbr = &zn->zbranch[i]; - - if (zbr->znode) - zbr->znode->parent = zn; - } - } - - atomic_long_inc(&c->dirty_zn_cnt); return zn; } @@ -246,6 +236,42 @@ static int add_idx_dirt(struct ubifs_info *c, int lnum, int dirt) } /** + * replace_znode - replace old znode with new znode. + * @c: UBIFS file-system description object + * @new_zn: new znode + * @old_zn: old znode + * @zbr: the branch of parent znode + * + * Replace old znode with new znode in TNC. + */ +static void replace_znode(struct ubifs_info *c, struct ubifs_znode *new_zn, + struct ubifs_znode *old_zn, struct ubifs_zbranch *zbr) +{ + ubifs_assert(c, !ubifs_zn_obsolete(old_zn)); + __set_bit(OBSOLETE_ZNODE, &old_zn->flags); + + if (old_zn->level != 0) { + int i; + const int n = new_zn->child_cnt; + + /* The children now have new parent */ + for (i = 0; i < n; i++) { + struct ubifs_zbranch *child = &new_zn->zbranch[i]; + + if (child->znode) + child->znode->parent = new_zn; + } + } + + zbr->znode = new_zn; + zbr->lnum = 0; + zbr->offs = 0; + zbr->len = 0; + + atomic_long_inc(&c->dirty_zn_cnt); +} + +/** * dirty_cow_znode - ensure a znode is not being committed. * @c: UBIFS file-system description object * @zbr: branch of znode to check @@ -277,21 +303,32 @@ static struct ubifs_znode *dirty_cow_znode(struct ubifs_info *c, return zn; if (zbr->len) { - err = insert_old_idx(c, zbr->lnum, zbr->offs); - if (unlikely(err)) - return ERR_PTR(err); + struct ubifs_old_idx *old_idx; + + old_idx = kmalloc(sizeof(struct ubifs_old_idx), GFP_NOFS); + if (unlikely(!old_idx)) { + err = -ENOMEM; + goto out; + } + old_idx->lnum = zbr->lnum; + old_idx->offs = zbr->offs; + err = add_idx_dirt(c, zbr->lnum, zbr->len); - } else - err = 0; + if (err) { + kfree(old_idx); + goto out; + } - zbr->znode = zn; - zbr->lnum = 0; - zbr->offs = 0; - zbr->len = 0; + do_insert_old_idx(c, old_idx); + } + + replace_znode(c, zn, znode, zbr); - if (unlikely(err)) - return ERR_PTR(err); return zn; + +out: + kfree(zn); + return ERR_PTR(err); } /** @@ -899,7 +936,7 @@ static int fallible_resolve_collision(struct ubifs_info *c, int adding) { struct ubifs_znode *o_znode = NULL, *znode = *zn; - int uninitialized_var(o_n), err, cmp, unsure = 0, nn = *n; + int o_n, err, cmp, unsure = 0, nn = *n; cmp = fallible_matches_name(c, &znode->zbranch[nn], nm); if (unlikely(cmp < 0)) @@ -1521,8 +1558,8 @@ out: */ int ubifs_tnc_get_bu_keys(struct ubifs_info *c, struct bu_info *bu) { - int n, err = 0, lnum = -1, uninitialized_var(offs); - int uninitialized_var(len); + int n, err = 0, lnum = -1, offs; + int len; unsigned int block = key_block(c, &bu->key); struct ubifs_znode *znode; @@ -3046,6 +3083,21 @@ static void tnc_destroy_cnext(struct ubifs_info *c) cnext = cnext->cnext; if (ubifs_zn_obsolete(znode)) kfree(znode); + else if (!ubifs_zn_cow(znode)) { + /* + * Don't forget to update clean znode count after + * committing failed, because ubifs will check this + * count while closing tnc. Non-obsolete znode could + * be re-dirtied during committing process, so dirty + * flag is untrustable. The flag 'COW_ZNODE' is set + * for each dirty znode before committing, and it is + * cleared as long as the znode become clean, so we + * can statistic clean znode count according to this + * flag. + */ + atomic_long_inc(&c->clean_zn_cnt); + atomic_long_inc(&ubifs_clean_zn_cnt); + } } while (cnext && cnext != c->cnext); } diff --git a/fs/ubifs/tnc_misc.c b/fs/ubifs/tnc_misc.c index d90ee01076a9..fe3b52d2749b 100644 --- a/fs/ubifs/tnc_misc.c +++ b/fs/ubifs/tnc_misc.c @@ -138,8 +138,8 @@ int ubifs_search_zbranch(const struct ubifs_info *c, const struct ubifs_znode *znode, const union ubifs_key *key, int *n) { - int beg = 0, end = znode->child_cnt, uninitialized_var(mid); - int uninitialized_var(cmp); + int beg = 0, end = znode->child_cnt, mid; + int cmp; const struct ubifs_zbranch *zbr = &znode->zbranch[0]; ubifs_assert(c, end > beg); diff --git a/fs/udf/balloc.c b/fs/udf/balloc.c index fcda0fc97b90..0dc98bbad9c4 100644 --- a/fs/udf/balloc.c +++ b/fs/udf/balloc.c @@ -36,18 +36,41 @@ static int read_block_bitmap(struct super_block *sb, unsigned long bitmap_nr) { struct buffer_head *bh = NULL; - int retval = 0; + int i; + int max_bits, off, count; struct kernel_lb_addr loc; loc.logicalBlockNum = bitmap->s_extPosition; loc.partitionReferenceNum = UDF_SB(sb)->s_partition; bh = udf_tread(sb, udf_get_lb_pblock(sb, &loc, block)); + bitmap->s_block_bitmap[bitmap_nr] = bh; if (!bh) - retval = -EIO; + return -EIO; - bitmap->s_block_bitmap[bitmap_nr] = bh; - return retval; + /* Check consistency of Space Bitmap buffer. */ + max_bits = sb->s_blocksize * 8; + if (!bitmap_nr) { + off = sizeof(struct spaceBitmapDesc) << 3; + count = min(max_bits - off, bitmap->s_nr_groups); + } else { + /* + * Rough check if bitmap number is too big to have any bitmap + * blocks reserved. + */ + if (bitmap_nr > + (bitmap->s_nr_groups >> (sb->s_blocksize_bits + 3)) + 2) + return 0; + off = 0; + count = bitmap->s_nr_groups - bitmap_nr * max_bits + + (sizeof(struct spaceBitmapDesc) << 3); + count = min(count, max_bits); + } + + for (i = 0; i < count; i++) + if (udf_test_bit(i + off, bh->b_data)) + return -EFSCORRUPTED; + return 0; } static int __load_block_bitmap(struct super_block *sb, @@ -555,7 +578,7 @@ static udf_pblk_t udf_table_new_block(struct super_block *sb, udf_pblk_t newblock = 0; uint32_t adsize; uint32_t elen, goal_elen = 0; - struct kernel_lb_addr eloc, uninitialized_var(goal_eloc); + struct kernel_lb_addr eloc, goal_eloc; struct extent_position epos, goal_epos; int8_t etype; struct udf_inode_info *iinfo = UDF_I(table); diff --git a/fs/udf/directory.c b/fs/udf/directory.c index d9523013096f..73720320f0ab 100644 --- a/fs/udf/directory.c +++ b/fs/udf/directory.c @@ -34,7 +34,7 @@ struct fileIdentDesc *udf_fileident_read(struct inode *dir, loff_t *nf_pos, fibh->soffset = fibh->eoffset; if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { - fi = udf_get_fileident(iinfo->i_ext.i_data - + fi = udf_get_fileident(iinfo->i_data - (iinfo->i_efe ? sizeof(struct extendedFileEntry) : sizeof(struct fileEntry)), diff --git a/fs/udf/file.c b/fs/udf/file.c index cd31e4f6d6da..8fff7ffc33a8 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -50,7 +50,7 @@ static void __udf_adinicb_readpage(struct page *page) * So just sample it once and use the same value everywhere. */ kaddr = kmap_atomic(page); - memcpy(kaddr, iinfo->i_ext.i_data + iinfo->i_lenEAttr, isize); + memcpy(kaddr, iinfo->i_data + iinfo->i_lenEAttr, isize); memset(kaddr + isize, 0, PAGE_SIZE - isize); flush_dcache_page(page); SetPageUptodate(page); @@ -76,8 +76,7 @@ static int udf_adinicb_writepage(struct page *page, BUG_ON(!PageLocked(page)); kaddr = kmap_atomic(page); - memcpy(iinfo->i_ext.i_data + iinfo->i_lenEAttr, kaddr, - i_size_read(inode)); + memcpy(iinfo->i_data + iinfo->i_lenEAttr, kaddr, i_size_read(inode)); SetPageUptodate(page); kunmap_atomic(kaddr); mark_inode_dirty(inode); @@ -148,26 +147,24 @@ static ssize_t udf_file_write_iter(struct kiocb *iocb, struct iov_iter *from) goto out; down_write(&iinfo->i_data_sem); - if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { - loff_t end = iocb->ki_pos + iov_iter_count(from); - - if (inode->i_sb->s_blocksize < - (udf_file_entry_alloc_offset(inode) + end)) { - err = udf_expand_file_adinicb(inode); - if (err) { - inode_unlock(inode); - udf_debug("udf_expand_adinicb: err=%d\n", err); - return err; - } - } else { - iinfo->i_lenAlloc = max(end, inode->i_size); - up_write(&iinfo->i_data_sem); + if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB && + inode->i_sb->s_blocksize < (udf_file_entry_alloc_offset(inode) + + iocb->ki_pos + iov_iter_count(from))) { + err = udf_expand_file_adinicb(inode); + if (err) { + inode_unlock(inode); + udf_debug("udf_expand_adinicb: err=%d\n", err); + return err; } } else up_write(&iinfo->i_data_sem); retval = __generic_file_write_iter(iocb, from); out: + down_write(&iinfo->i_data_sem); + if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB && retval > 0) + iinfo->i_lenAlloc = inode->i_size; + up_write(&iinfo->i_data_sem); inode_unlock(inode); if (retval > 0) { @@ -215,7 +212,7 @@ long udf_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return put_user(UDF_I(inode)->i_lenEAttr, (int __user *)arg); case UDF_GETEABLOCK: return copy_to_user((char __user *)arg, - UDF_I(inode)->i_ext.i_data, + UDF_I(inode)->i_data, UDF_I(inode)->i_lenEAttr) ? -EFAULT : 0; default: return -ENOIOCTLCMD; diff --git a/fs/udf/ialloc.c b/fs/udf/ialloc.c index f8e5872f7cc2..cdaa86e077b2 100644 --- a/fs/udf/ialloc.c +++ b/fs/udf/ialloc.c @@ -67,16 +67,16 @@ struct inode *udf_new_inode(struct inode *dir, umode_t mode) iinfo->i_efe = 1; if (UDF_VERS_USE_EXTENDED_FE > sbi->s_udfrev) sbi->s_udfrev = UDF_VERS_USE_EXTENDED_FE; - iinfo->i_ext.i_data = kzalloc(inode->i_sb->s_blocksize - - sizeof(struct extendedFileEntry), - GFP_KERNEL); + iinfo->i_data = kzalloc(inode->i_sb->s_blocksize - + sizeof(struct extendedFileEntry), + GFP_KERNEL); } else { iinfo->i_efe = 0; - iinfo->i_ext.i_data = kzalloc(inode->i_sb->s_blocksize - - sizeof(struct fileEntry), - GFP_KERNEL); + iinfo->i_data = kzalloc(inode->i_sb->s_blocksize - + sizeof(struct fileEntry), + GFP_KERNEL); } - if (!iinfo->i_ext.i_data) { + if (!iinfo->i_data) { iput(inode); return ERR_PTR(-ENOMEM); } diff --git a/fs/udf/inode.c b/fs/udf/inode.c index ec8089a31390..08d7208eb7b7 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -50,15 +50,15 @@ static int udf_update_inode(struct inode *, int); static int udf_sync_inode(struct inode *inode); static int udf_alloc_i_data(struct inode *inode, size_t size); static sector_t inode_getblk(struct inode *, sector_t, int *, int *); -static int8_t udf_insert_aext(struct inode *, struct extent_position, - struct kernel_lb_addr, uint32_t); +static int udf_insert_aext(struct inode *, struct extent_position, + struct kernel_lb_addr, uint32_t); static void udf_split_extents(struct inode *, int *, int, udf_pblk_t, struct kernel_long_ad *, int *); static void udf_prealloc_extents(struct inode *, int, int, struct kernel_long_ad *, int *); static void udf_merge_extents(struct inode *, struct kernel_long_ad *, int *); -static void udf_update_extents(struct inode *, struct kernel_long_ad *, int, - int, struct extent_position *); +static int udf_update_extents(struct inode *, struct kernel_long_ad *, int, + int, struct extent_position *); static int udf_get_block(struct inode *, sector_t, struct buffer_head *, int); static void __udf_clear_extent_cache(struct inode *inode) @@ -150,8 +150,8 @@ void udf_evict_inode(struct inode *inode) truncate_inode_pages_final(&inode->i_data); invalidate_inode_buffers(inode); clear_inode(inode); - kfree(iinfo->i_ext.i_data); - iinfo->i_ext.i_data = NULL; + kfree(iinfo->i_data); + iinfo->i_data = NULL; udf_clear_extent_cache(inode); if (want_delete) { udf_free_inode(inode); @@ -278,14 +278,14 @@ int udf_expand_file_adinicb(struct inode *inode) kaddr = kmap_atomic(page); memset(kaddr + iinfo->i_lenAlloc, 0x00, PAGE_SIZE - iinfo->i_lenAlloc); - memcpy(kaddr, iinfo->i_ext.i_data + iinfo->i_lenEAttr, + memcpy(kaddr, iinfo->i_data + iinfo->i_lenEAttr, iinfo->i_lenAlloc); flush_dcache_page(page); SetPageUptodate(page); kunmap_atomic(kaddr); } down_write(&iinfo->i_data_sem); - memset(iinfo->i_ext.i_data + iinfo->i_lenEAttr, 0x00, + memset(iinfo->i_data + iinfo->i_lenEAttr, 0x00, iinfo->i_lenAlloc); iinfo->i_lenAlloc = 0; if (UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_USE_SHORT_AD)) @@ -303,8 +303,7 @@ int udf_expand_file_adinicb(struct inode *inode) lock_page(page); down_write(&iinfo->i_data_sem); kaddr = kmap_atomic(page); - memcpy(iinfo->i_ext.i_data + iinfo->i_lenEAttr, kaddr, - inode->i_size); + memcpy(iinfo->i_data + iinfo->i_lenEAttr, kaddr, inode->i_size); kunmap_atomic(kaddr); unlock_page(page); iinfo->i_alloc_type = ICBTAG_FLAG_AD_IN_ICB; @@ -392,8 +391,7 @@ struct buffer_head *udf_expand_dir_adinicb(struct inode *inode, } mark_buffer_dirty_inode(dbh, inode); - memset(iinfo->i_ext.i_data + iinfo->i_lenEAttr, 0, - iinfo->i_lenAlloc); + memset(iinfo->i_data + iinfo->i_lenEAttr, 0, iinfo->i_lenAlloc); iinfo->i_lenAlloc = 0; eloc.logicalBlockNum = *block; eloc.partitionReferenceNum = @@ -434,6 +432,12 @@ static int udf_get_block(struct inode *inode, sector_t block, iinfo->i_next_alloc_goal++; } + /* + * Block beyond EOF and prealloc extents? Just discard preallocation + * as it is not useful and complicates things. + */ + if (((loff_t)block) << inode->i_blkbits > iinfo->i_lenExtents) + udf_discard_prealloc(inode); udf_clear_extent_cache(inode); phys = inode_getblk(inode, block, &err, &new); if (!phys) @@ -483,8 +487,6 @@ static int udf_do_extend_file(struct inode *inode, uint32_t add; int count = 0, fake = !(last_ext->extLength & UDF_EXTENT_LENGTH_MASK); struct super_block *sb = inode->i_sb; - struct kernel_lb_addr prealloc_loc = {}; - uint32_t prealloc_len = 0; struct udf_inode_info *iinfo; int err; @@ -505,19 +507,6 @@ static int udf_do_extend_file(struct inode *inode, ~(sb->s_blocksize - 1); } - /* Last extent are just preallocated blocks? */ - if ((last_ext->extLength & UDF_EXTENT_FLAG_MASK) == - EXT_NOT_RECORDED_ALLOCATED) { - /* Save the extent so that we can reattach it to the end */ - prealloc_loc = last_ext->extLocation; - prealloc_len = last_ext->extLength; - /* Mark the extent as a hole */ - last_ext->extLength = EXT_NOT_RECORDED_NOT_ALLOCATED | - (last_ext->extLength & UDF_EXTENT_LENGTH_MASK); - last_ext->extLocation.logicalBlockNum = 0; - last_ext->extLocation.partitionReferenceNum = 0; - } - /* Can we merge with the previous extent? */ if ((last_ext->extLength & UDF_EXTENT_FLAG_MASK) == EXT_NOT_RECORDED_NOT_ALLOCATED) { @@ -530,8 +519,10 @@ static int udf_do_extend_file(struct inode *inode, } if (fake) { - udf_add_aext(inode, last_pos, &last_ext->extLocation, - last_ext->extLength, 1); + err = udf_add_aext(inode, last_pos, &last_ext->extLocation, + last_ext->extLength, 1); + if (err < 0) + goto out_err; count++; } else { struct kernel_lb_addr tmploc; @@ -545,7 +536,7 @@ static int udf_do_extend_file(struct inode *inode, * more extents, we may need to enter possible following * empty indirect extent. */ - if (new_block_bytes || prealloc_len) + if (new_block_bytes) udf_next_aext(inode, last_pos, &tmploc, &tmplen, 0); } @@ -565,7 +556,7 @@ static int udf_do_extend_file(struct inode *inode, err = udf_add_aext(inode, last_pos, &last_ext->extLocation, last_ext->extLength, 1); if (err) - return err; + goto out_err; count++; } if (new_block_bytes) { @@ -574,22 +565,11 @@ static int udf_do_extend_file(struct inode *inode, err = udf_add_aext(inode, last_pos, &last_ext->extLocation, last_ext->extLength, 1); if (err) - return err; + goto out_err; count++; } out: - /* Do we have some preallocated blocks saved? */ - if (prealloc_len) { - err = udf_add_aext(inode, last_pos, &prealloc_loc, - prealloc_len, 1); - if (err) - return err; - last_ext->extLocation = prealloc_loc; - last_ext->extLength = prealloc_len; - count++; - } - /* last_pos should point to the last written extent... */ if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT) last_pos->offset -= sizeof(struct short_ad); @@ -599,19 +579,28 @@ out: return -EIO; return count; +out_err: + /* Remove extents we've created so far */ + udf_clear_extent_cache(inode); + udf_truncate_extents(inode); + return err; } /* Extend the final block of the file to final_block_len bytes */ static void udf_do_extend_final_block(struct inode *inode, struct extent_position *last_pos, struct kernel_long_ad *last_ext, - uint32_t final_block_len) + uint32_t new_elen) { - struct super_block *sb = inode->i_sb; uint32_t added_bytes; - added_bytes = final_block_len - - (last_ext->extLength & (sb->s_blocksize - 1)); + /* + * Extent already large enough? It may be already rounded up to block + * size... + */ + if (new_elen <= (last_ext->extLength & UDF_EXTENT_LENGTH_MASK)) + return; + added_bytes = new_elen - (last_ext->extLength & UDF_EXTENT_LENGTH_MASK); last_ext->extLength += added_bytes; UDF_I(inode)->i_lenExtents += added_bytes; @@ -628,12 +617,12 @@ static int udf_extend_file(struct inode *inode, loff_t newsize) int8_t etype; struct super_block *sb = inode->i_sb; sector_t first_block = newsize >> sb->s_blocksize_bits, offset; - unsigned long partial_final_block; + loff_t new_elen; int adsize; struct udf_inode_info *iinfo = UDF_I(inode); struct kernel_long_ad extent; int err = 0; - int within_final_block; + bool within_last_ext; if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT) adsize = sizeof(struct short_ad); @@ -642,8 +631,17 @@ static int udf_extend_file(struct inode *inode, loff_t newsize) else BUG(); + /* + * When creating hole in file, just don't bother with preserving + * preallocation. It likely won't be very useful anyway. + */ + udf_discard_prealloc(inode); + etype = inode_bmap(inode, first_block, &epos, &eloc, &elen, &offset); - within_final_block = (etype != -1); + within_last_ext = (etype != -1); + /* We don't expect extents past EOF... */ + WARN_ON_ONCE(within_last_ext && + elen > ((loff_t)offset + 1) << inode->i_blkbits); if ((!epos.bh && epos.offset == udf_file_entry_alloc_offset(inode)) || (epos.bh && epos.offset == sizeof(struct allocExtDesc))) { @@ -659,19 +657,17 @@ static int udf_extend_file(struct inode *inode, loff_t newsize) extent.extLength |= etype << 30; } - partial_final_block = newsize & (sb->s_blocksize - 1); + new_elen = ((loff_t)offset << inode->i_blkbits) | + (newsize & (sb->s_blocksize - 1)); /* File has extent covering the new size (could happen when extending * inside a block)? */ - if (within_final_block) { + if (within_last_ext) { /* Extending file within the last file block */ - udf_do_extend_final_block(inode, &epos, &extent, - partial_final_block); + udf_do_extend_final_block(inode, &epos, &extent, new_elen); } else { - loff_t add = ((loff_t)offset << sb->s_blocksize_bits) | - partial_final_block; - err = udf_do_extend_file(inode, &epos, &extent, add); + err = udf_do_extend_file(inode, &epos, &extent, new_elen); } if (err < 0) @@ -693,7 +689,7 @@ static sector_t inode_getblk(struct inode *inode, sector_t block, struct kernel_lb_addr eloc, tmpeloc; int c = 1; loff_t lbcount = 0, b_off = 0; - udf_pblk_t newblocknum, newblock; + udf_pblk_t newblocknum, newblock = 0; sector_t offset = 0; int8_t etype; struct udf_inode_info *iinfo = UDF_I(inode); @@ -772,10 +768,11 @@ static sector_t inode_getblk(struct inode *inode, sector_t block, goto out_free; } - /* Are we beyond EOF? */ + /* Are we beyond EOF and preallocated extent? */ if (etype == -1) { int ret; loff_t hole_len; + isBeyondEOF = true; if (count) { if (c) @@ -795,25 +792,22 @@ static sector_t inode_getblk(struct inode *inode, sector_t block, ret = udf_do_extend_file(inode, &prev_epos, laarr, hole_len); if (ret < 0) { *err = ret; - newblock = 0; goto out_free; } c = 0; offset = 0; count += ret; - /* We are not covered by a preallocated extent? */ - if ((laarr[0].extLength & UDF_EXTENT_FLAG_MASK) != - EXT_NOT_RECORDED_ALLOCATED) { - /* Is there any real extent? - otherwise we overwrite - * the fake one... */ - if (count) - c = !c; - laarr[c].extLength = EXT_NOT_RECORDED_NOT_ALLOCATED | - inode->i_sb->s_blocksize; - memset(&laarr[c].extLocation, 0x00, - sizeof(struct kernel_lb_addr)); - count++; - } + /* + * Is there any real extent? - otherwise we overwrite the fake + * one... + */ + if (count) + c = !c; + laarr[c].extLength = EXT_NOT_RECORDED_NOT_ALLOCATED | + inode->i_sb->s_blocksize; + memset(&laarr[c].extLocation, 0x00, + sizeof(struct kernel_lb_addr)); + count++; endnum = c + 1; lastblock = 1; } else { @@ -860,7 +854,6 @@ static sector_t inode_getblk(struct inode *inode, sector_t block, goal, err); if (!newblocknum) { *err = -ENOSPC; - newblock = 0; goto out_free; } if (isBeyondEOF) @@ -886,7 +879,9 @@ static sector_t inode_getblk(struct inode *inode, sector_t block, /* write back the new extents, inserting new extents if the new number * of extents is greater than the old number, and deleting extents if * the new number of extents is less than the old number */ - udf_update_extents(inode, laarr, startnum, endnum, &prev_epos); + *err = udf_update_extents(inode, laarr, startnum, endnum, &prev_epos); + if (*err < 0) + goto out_free; newblock = udf_get_pblock(inode->i_sb, newblocknum, iinfo->i_location.partitionReferenceNum, 0); @@ -1090,23 +1085,8 @@ static void udf_merge_extents(struct inode *inode, struct kernel_long_ad *laarr, blocksize - 1) >> blocksize_bits)))) { if (((li->extLength & UDF_EXTENT_LENGTH_MASK) + - (lip1->extLength & UDF_EXTENT_LENGTH_MASK) + - blocksize - 1) & ~UDF_EXTENT_LENGTH_MASK) { - lip1->extLength = (lip1->extLength - - (li->extLength & - UDF_EXTENT_LENGTH_MASK) + - UDF_EXTENT_LENGTH_MASK) & - ~(blocksize - 1); - li->extLength = (li->extLength & - UDF_EXTENT_FLAG_MASK) + - (UDF_EXTENT_LENGTH_MASK + 1) - - blocksize; - lip1->extLocation.logicalBlockNum = - li->extLocation.logicalBlockNum + - ((li->extLength & - UDF_EXTENT_LENGTH_MASK) >> - blocksize_bits); - } else { + (lip1->extLength & UDF_EXTENT_LENGTH_MASK) + + blocksize - 1) <= UDF_EXTENT_LENGTH_MASK) { li->extLength = lip1->extLength + (((li->extLength & UDF_EXTENT_LENGTH_MASK) + @@ -1169,21 +1149,30 @@ static void udf_merge_extents(struct inode *inode, struct kernel_long_ad *laarr, } } -static void udf_update_extents(struct inode *inode, struct kernel_long_ad *laarr, - int startnum, int endnum, - struct extent_position *epos) +static int udf_update_extents(struct inode *inode, struct kernel_long_ad *laarr, + int startnum, int endnum, + struct extent_position *epos) { int start = 0, i; struct kernel_lb_addr tmploc; uint32_t tmplen; + int err; if (startnum > endnum) { for (i = 0; i < (startnum - endnum); i++) udf_delete_aext(inode, *epos); } else if (startnum < endnum) { for (i = 0; i < (endnum - startnum); i++) { - udf_insert_aext(inode, *epos, laarr[i].extLocation, - laarr[i].extLength); + err = udf_insert_aext(inode, *epos, + laarr[i].extLocation, + laarr[i].extLength); + /* + * If we fail here, we are likely corrupting the extent + * list and leaking blocks. At least stop early to + * limit the damage. + */ + if (err < 0) + return err; udf_next_aext(inode, epos, &laarr[i].extLocation, &laarr[i].extLength, 1); start++; @@ -1195,6 +1184,7 @@ static void udf_update_extents(struct inode *inode, struct kernel_long_ad *laarr udf_write_aext(inode, epos, &laarr[i].extLocation, laarr[i].extLength, 1); } + return 0; } struct buffer_head *udf_bread(struct inode *inode, udf_pblk_t block, @@ -1259,7 +1249,7 @@ set_size: if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { down_write(&iinfo->i_data_sem); udf_clear_extent_cache(inode); - memset(iinfo->i_ext.i_data + iinfo->i_lenEAttr + newsize, + memset(iinfo->i_data + iinfo->i_lenEAttr + newsize, 0x00, bsize - newsize - udf_file_entry_alloc_offset(inode)); iinfo->i_lenAlloc = newsize; @@ -1395,6 +1385,7 @@ reread: ret = -EIO; goto out; } + iinfo->i_hidden = hidden_inode; iinfo->i_unique = 0; iinfo->i_lenEAttr = 0; iinfo->i_lenExtents = 0; @@ -1408,7 +1399,7 @@ reread: sizeof(struct extendedFileEntry)); if (ret) goto out; - memcpy(iinfo->i_ext.i_data, + memcpy(iinfo->i_data, bh->b_data + sizeof(struct extendedFileEntry), bs - sizeof(struct extendedFileEntry)); } else if (fe->descTag.tagIdent == cpu_to_le16(TAG_IDENT_FE)) { @@ -1417,7 +1408,7 @@ reread: ret = udf_alloc_i_data(inode, bs - sizeof(struct fileEntry)); if (ret) goto out; - memcpy(iinfo->i_ext.i_data, + memcpy(iinfo->i_data, bh->b_data + sizeof(struct fileEntry), bs - sizeof(struct fileEntry)); } else if (fe->descTag.tagIdent == cpu_to_le16(TAG_IDENT_USE)) { @@ -1430,7 +1421,7 @@ reread: sizeof(struct unallocSpaceEntry)); if (ret) goto out; - memcpy(iinfo->i_ext.i_data, + memcpy(iinfo->i_data, bh->b_data + sizeof(struct unallocSpaceEntry), bs - sizeof(struct unallocSpaceEntry)); return 0; @@ -1488,6 +1479,8 @@ reread: iinfo->i_lenEAttr = le32_to_cpu(fe->lengthExtendedAttr); iinfo->i_lenAlloc = le32_to_cpu(fe->lengthAllocDescs); iinfo->i_checkpoint = le32_to_cpu(fe->checkpoint); + iinfo->i_streamdir = 0; + iinfo->i_lenStreams = 0; } else { inode->i_blocks = le64_to_cpu(efe->logicalBlocksRecorded) << (inode->i_sb->s_blocksize_bits - 9); @@ -1501,6 +1494,16 @@ reread: iinfo->i_lenEAttr = le32_to_cpu(efe->lengthExtendedAttr); iinfo->i_lenAlloc = le32_to_cpu(efe->lengthAllocDescs); iinfo->i_checkpoint = le32_to_cpu(efe->checkpoint); + + /* Named streams */ + iinfo->i_streamdir = (efe->streamDirectoryICB.extLength != 0); + iinfo->i_locStreamdir = + lelb_to_cpu(efe->streamDirectoryICB.extLocation); + iinfo->i_lenStreams = le64_to_cpu(efe->objectSize); + if (iinfo->i_lenStreams >= inode->i_size) + iinfo->i_lenStreams -= inode->i_size; + else + iinfo->i_lenStreams = 0; } inode->i_generation = iinfo->i_unique; @@ -1597,8 +1600,8 @@ out: static int udf_alloc_i_data(struct inode *inode, size_t size) { struct udf_inode_info *iinfo = UDF_I(inode); - iinfo->i_ext.i_data = kmalloc(size, GFP_KERNEL); - if (!iinfo->i_ext.i_data) + iinfo->i_data = kmalloc(size, GFP_KERNEL); + if (!iinfo->i_data) return -ENOMEM; return 0; } @@ -1672,7 +1675,7 @@ static int udf_update_inode(struct inode *inode, int do_sync) use->lengthAllocDescs = cpu_to_le32(iinfo->i_lenAlloc); memcpy(bh->b_data + sizeof(struct unallocSpaceEntry), - iinfo->i_ext.i_data, inode->i_sb->s_blocksize - + iinfo->i_data, inode->i_sb->s_blocksize - sizeof(struct unallocSpaceEntry)); use->descTag.tagIdent = cpu_to_le16(TAG_IDENT_USE); crclen = sizeof(struct unallocSpaceEntry); @@ -1702,8 +1705,12 @@ static int udf_update_inode(struct inode *inode, int do_sync) if (S_ISDIR(inode->i_mode) && inode->i_nlink > 0) fe->fileLinkCount = cpu_to_le16(inode->i_nlink - 1); - else - fe->fileLinkCount = cpu_to_le16(inode->i_nlink); + else { + if (iinfo->i_hidden) + fe->fileLinkCount = cpu_to_le16(0); + else + fe->fileLinkCount = cpu_to_le16(inode->i_nlink); + } fe->informationLength = cpu_to_le64(inode->i_size); @@ -1741,7 +1748,7 @@ static int udf_update_inode(struct inode *inode, int do_sync) if (iinfo->i_efe == 0) { memcpy(bh->b_data + sizeof(struct fileEntry), - iinfo->i_ext.i_data, + iinfo->i_data, inode->i_sb->s_blocksize - sizeof(struct fileEntry)); fe->logicalBlocksRecorded = cpu_to_le64(lb_recorded); @@ -1760,12 +1767,22 @@ static int udf_update_inode(struct inode *inode, int do_sync) crclen = sizeof(struct fileEntry); } else { memcpy(bh->b_data + sizeof(struct extendedFileEntry), - iinfo->i_ext.i_data, + iinfo->i_data, inode->i_sb->s_blocksize - sizeof(struct extendedFileEntry)); - efe->objectSize = cpu_to_le64(inode->i_size); + efe->objectSize = + cpu_to_le64(inode->i_size + iinfo->i_lenStreams); efe->logicalBlocksRecorded = cpu_to_le64(lb_recorded); + if (iinfo->i_streamdir) { + struct long_ad *icb_lad = &efe->streamDirectoryICB; + + icb_lad->extLocation = + cpu_to_lelb(iinfo->i_locStreamdir); + icb_lad->extLength = + cpu_to_le32(inode->i_sb->s_blocksize); + } + udf_adjust_time(iinfo, inode->i_atime); udf_adjust_time(iinfo, inode->i_mtime); udf_adjust_time(iinfo, inode->i_ctime); @@ -1864,8 +1881,13 @@ struct inode *__udf_iget(struct super_block *sb, struct kernel_lb_addr *ino, if (!inode) return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) + if (!(inode->i_state & I_NEW)) { + if (UDF_I(inode)->i_hidden != hidden_inode) { + iput(inode); + return ERR_PTR(-EFSCORRUPTED); + } return inode; + } memcpy(&UDF_I(inode)->i_location, ino, sizeof(struct kernel_lb_addr)); err = udf_read_inode(inode, hidden_inode); @@ -2046,7 +2068,7 @@ void udf_write_aext(struct inode *inode, struct extent_position *epos, struct udf_inode_info *iinfo = UDF_I(inode); if (!epos->bh) - ptr = iinfo->i_ext.i_data + epos->offset - + ptr = iinfo->i_data + epos->offset - udf_file_entry_alloc_offset(inode) + iinfo->i_lenEAttr; else @@ -2138,7 +2160,7 @@ int8_t udf_current_aext(struct inode *inode, struct extent_position *epos, if (!epos->bh) { if (!epos->offset) epos->offset = udf_file_entry_alloc_offset(inode); - ptr = iinfo->i_ext.i_data + epos->offset - + ptr = iinfo->i_data + epos->offset - udf_file_entry_alloc_offset(inode) + iinfo->i_lenEAttr; alen = udf_file_entry_alloc_offset(inode) + @@ -2179,12 +2201,13 @@ int8_t udf_current_aext(struct inode *inode, struct extent_position *epos, return etype; } -static int8_t udf_insert_aext(struct inode *inode, struct extent_position epos, - struct kernel_lb_addr neloc, uint32_t nelen) +static int udf_insert_aext(struct inode *inode, struct extent_position epos, + struct kernel_lb_addr neloc, uint32_t nelen) { struct kernel_lb_addr oeloc; uint32_t oelen; int8_t etype; + int err; if (epos.bh) get_bh(epos.bh); @@ -2194,10 +2217,10 @@ static int8_t udf_insert_aext(struct inode *inode, struct extent_position epos, neloc = oeloc; nelen = (etype << 30) | oelen; } - udf_add_aext(inode, &epos, &neloc, nelen, 1); + err = udf_add_aext(inode, &epos, &neloc, nelen, 1); brelse(epos.bh); - return (nelen >> 30); + return err; } int8_t udf_delete_aext(struct inode *inode, struct extent_position epos) diff --git a/fs/udf/misc.c b/fs/udf/misc.c index 853bcff51043..1614d308d0f0 100644 --- a/fs/udf/misc.c +++ b/fs/udf/misc.c @@ -52,9 +52,9 @@ struct genericFormat *udf_add_extendedattr(struct inode *inode, uint32_t size, uint16_t crclen; struct udf_inode_info *iinfo = UDF_I(inode); - ea = iinfo->i_ext.i_data; + ea = iinfo->i_data; if (iinfo->i_lenEAttr) { - ad = iinfo->i_ext.i_data + iinfo->i_lenEAttr; + ad = iinfo->i_data + iinfo->i_lenEAttr; } else { ad = ea; size += sizeof(struct extendedAttrHeaderDesc); @@ -153,7 +153,7 @@ struct genericFormat *udf_get_extendedattr(struct inode *inode, uint32_t type, uint32_t offset; struct udf_inode_info *iinfo = UDF_I(inode); - ea = iinfo->i_ext.i_data; + ea = iinfo->i_data; if (iinfo->i_lenEAttr) { struct extendedAttrHeaderDesc *eahd; diff --git a/fs/udf/namei.c b/fs/udf/namei.c index d13ded8e2c30..05dd1f45ba90 100644 --- a/fs/udf/namei.c +++ b/fs/udf/namei.c @@ -478,8 +478,7 @@ add: if (dinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { block = dinfo->i_location.logicalBlockNum; fi = (struct fileIdentDesc *) - (dinfo->i_ext.i_data + - fibh->soffset - + (dinfo->i_data + fibh->soffset - udf_ext0_offset(dir) + dinfo->i_lenEAttr); } else { @@ -962,7 +961,7 @@ static int udf_symlink(struct inode *dir, struct dentry *dentry, mark_buffer_dirty_inode(epos.bh, inode); ea = epos.bh->b_data + udf_ext0_offset(inode); } else - ea = iinfo->i_ext.i_data + iinfo->i_lenEAttr; + ea = iinfo->i_data + iinfo->i_lenEAttr; eoffset = sb->s_blocksize - udf_ext0_offset(inode); pc = (struct pathComponent *)ea; @@ -1106,8 +1105,9 @@ static int udf_rename(struct inode *old_dir, struct dentry *old_dentry, return -EINVAL; ofi = udf_find_entry(old_dir, &old_dentry->d_name, &ofibh, &ocfi); - if (IS_ERR(ofi)) { - retval = PTR_ERR(ofi); + if (!ofi || IS_ERR(ofi)) { + if (IS_ERR(ofi)) + retval = PTR_ERR(ofi); goto end_rename; } @@ -1116,8 +1116,7 @@ static int udf_rename(struct inode *old_dir, struct dentry *old_dentry, brelse(ofibh.sbh); tloc = lelb_to_cpu(ocfi.icb.extLocation); - if (!ofi || udf_get_lb_pblock(old_dir->i_sb, &tloc, 0) - != old_inode->i_ino) + if (udf_get_lb_pblock(old_dir->i_sb, &tloc, 0) != old_inode->i_ino) goto end_rename; nfi = udf_find_entry(new_dir, &new_dentry->d_name, &nfibh, &ncfi); @@ -1142,7 +1141,7 @@ static int udf_rename(struct inode *old_dir, struct dentry *old_dentry, retval = -EIO; if (old_iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { dir_fi = udf_get_fileident( - old_iinfo->i_ext.i_data - + old_iinfo->i_data - (old_iinfo->i_efe ? sizeof(struct extendedFileEntry) : sizeof(struct fileEntry)), diff --git a/fs/udf/partition.c b/fs/udf/partition.c index 090baff83990..4cbf40575965 100644 --- a/fs/udf/partition.c +++ b/fs/udf/partition.c @@ -65,7 +65,7 @@ uint32_t udf_get_pblock_virt15(struct super_block *sb, uint32_t block, } if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { - loc = le32_to_cpu(((__le32 *)(iinfo->i_ext.i_data + + loc = le32_to_cpu(((__le32 *)(iinfo->i_data + vdata->s_start_offset))[block]); goto translate; } diff --git a/fs/udf/super.c b/fs/udf/super.c index b7fb7cd35d89..bce48a07790c 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -146,9 +146,12 @@ static struct inode *udf_alloc_inode(struct super_block *sb) ei->i_unique = 0; ei->i_lenExtents = 0; + ei->i_lenStreams = 0; ei->i_next_alloc_block = 0; ei->i_next_alloc_goal = 0; ei->i_strat4096 = 0; + ei->i_streamdir = 0; + ei->i_hidden = 0; init_rwsem(&ei->i_data_sem); ei->cached_extent.lstart = -1; spin_lock_init(&ei->i_extent_cache_lock); @@ -172,7 +175,7 @@ static void init_once(void *foo) { struct udf_inode_info *ei = (struct udf_inode_info *)foo; - ei->i_ext.i_data = NULL; + ei->i_data = NULL; inode_init_once(&ei->vfs_inode); } @@ -572,6 +575,11 @@ static int udf_parse_options(char *options, struct udf_options *uopt, if (!remount) { if (uopt->nls_map) unload_nls(uopt->nls_map); + /* + * load_nls() failure is handled later in + * udf_fill_super() after all options are + * parsed. + */ uopt->nls_map = load_nls(args[0].from); uopt->flags |= (1 << UDF_FLAG_NLS_MAP); } @@ -1200,7 +1208,7 @@ static int udf_load_vat(struct super_block *sb, int p_index, int type1_index) vat20 = (struct virtualAllocationTable20 *)bh->b_data; } else { vat20 = (struct virtualAllocationTable20 *) - vati->i_ext.i_data; + vati->i_data; } map->s_type_specific.s_virtual.s_start_offset = diff --git a/fs/udf/symlink.c b/fs/udf/symlink.c index 6023c97c6da2..aef3e4d9014d 100644 --- a/fs/udf/symlink.c +++ b/fs/udf/symlink.c @@ -122,7 +122,7 @@ static int udf_symlink_filler(struct file *file, struct page *page) down_read(&iinfo->i_data_sem); if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { - symlink = iinfo->i_ext.i_data + iinfo->i_lenEAttr; + symlink = iinfo->i_data + iinfo->i_lenEAttr; } else { bh = sb_bread(inode->i_sb, pos); diff --git a/fs/udf/truncate.c b/fs/udf/truncate.c index 94220ba85628..b0c71edc83f7 100644 --- a/fs/udf/truncate.c +++ b/fs/udf/truncate.c @@ -120,60 +120,42 @@ void udf_truncate_tail_extent(struct inode *inode) void udf_discard_prealloc(struct inode *inode) { - struct extent_position epos = { NULL, 0, {0, 0} }; + struct extent_position epos = {}; + struct extent_position prev_epos = {}; struct kernel_lb_addr eloc; uint32_t elen; uint64_t lbcount = 0; int8_t etype = -1, netype; - int adsize; struct udf_inode_info *iinfo = UDF_I(inode); + int bsize = 1 << inode->i_blkbits; if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB || - inode->i_size == iinfo->i_lenExtents) + ALIGN(inode->i_size, bsize) == ALIGN(iinfo->i_lenExtents, bsize)) return; - if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT) - adsize = sizeof(struct short_ad); - else if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_LONG) - adsize = sizeof(struct long_ad); - else - adsize = 0; - epos.block = iinfo->i_location; /* Find the last extent in the file */ - while ((netype = udf_next_aext(inode, &epos, &eloc, &elen, 1)) != -1) { - etype = netype; + while ((netype = udf_next_aext(inode, &epos, &eloc, &elen, 0)) != -1) { + brelse(prev_epos.bh); + prev_epos = epos; + if (prev_epos.bh) + get_bh(prev_epos.bh); + + etype = udf_next_aext(inode, &epos, &eloc, &elen, 1); lbcount += elen; } if (etype == (EXT_NOT_RECORDED_ALLOCATED >> 30)) { - epos.offset -= adsize; lbcount -= elen; - extent_trunc(inode, &epos, &eloc, etype, elen, 0); - if (!epos.bh) { - iinfo->i_lenAlloc = - epos.offset - - udf_file_entry_alloc_offset(inode); - mark_inode_dirty(inode); - } else { - struct allocExtDesc *aed = - (struct allocExtDesc *)(epos.bh->b_data); - aed->lengthAllocDescs = - cpu_to_le32(epos.offset - - sizeof(struct allocExtDesc)); - if (!UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_STRICT) || - UDF_SB(inode->i_sb)->s_udfrev >= 0x0201) - udf_update_tag(epos.bh->b_data, epos.offset); - else - udf_update_tag(epos.bh->b_data, - sizeof(struct allocExtDesc)); - mark_buffer_dirty_inode(epos.bh, inode); - } + udf_delete_aext(inode, prev_epos); + udf_free_blocks(inode->i_sb, inode, &eloc, 0, + DIV_ROUND_UP(elen, 1 << inode->i_blkbits)); } /* This inode entry is in-memory only and thus we don't have to mark * the inode dirty */ iinfo->i_lenExtents = lbcount; brelse(epos.bh); + brelse(prev_epos.bh); } static void udf_update_alloc_ext_desc(struct inode *inode, diff --git a/fs/udf/udf_i.h b/fs/udf/udf_i.h index 2ef0e212f08a..b77bf713a1b6 100644 --- a/fs/udf/udf_i.h +++ b/fs/udf/udf_i.h @@ -42,12 +42,12 @@ struct udf_inode_info { unsigned i_efe : 1; /* extendedFileEntry */ unsigned i_use : 1; /* unallocSpaceEntry */ unsigned i_strat4096 : 1; - unsigned reserved : 26; - union { - struct short_ad *i_sad; - struct long_ad *i_lad; - __u8 *i_data; - } i_ext; + unsigned i_streamdir : 1; + unsigned i_hidden : 1; /* hidden system inode */ + unsigned reserved : 24; + __u8 *i_data; + struct kernel_lb_addr i_locStreamdir; + __u64 i_lenStreams; struct rw_semaphore i_data_sem; struct udf_ext_cache cached_extent; /* Spinlock for protecting extent cache */ diff --git a/fs/udf/udf_sb.h b/fs/udf/udf_sb.h index d12e507e9eb2..aa58173b468f 100644 --- a/fs/udf/udf_sb.h +++ b/fs/udf/udf_sb.h @@ -57,6 +57,8 @@ #define MF_DUPLICATE_MD 0x01 #define MF_MIRROR_FE_LOADED 0x02 +#define EFSCORRUPTED EUCLEAN + struct udf_meta_data { __u32 s_meta_file_loc; __u32 s_mirror_file_loc; diff --git a/fs/udf/unicode.c b/fs/udf/unicode.c index 5fcfa96463eb..85521d6b0237 100644 --- a/fs/udf/unicode.c +++ b/fs/udf/unicode.c @@ -247,7 +247,7 @@ static int udf_name_from_CS0(struct super_block *sb, } if (translate) { - if (str_o_len <= 2 && str_o[0] == '.' && + if (str_o_len > 0 && str_o_len <= 2 && str_o[0] == '.' && (str_o_len == 1 || str_o[1] == '.')) needsCRC = 1; if (needsCRC) { diff --git a/fs/xattr.c b/fs/xattr.c index 470ee0af3200..5c3407e18e15 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -1012,7 +1012,7 @@ static int xattr_list_one(char **buffer, ssize_t *remaining_size, ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs, char *buffer, size_t size) { - bool trusted = capable(CAP_SYS_ADMIN); + bool trusted = ns_capable_noaudit(&init_user_ns, CAP_SYS_ADMIN); struct simple_xattr *xattr; ssize_t remaining_size = size; int err = 0; diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 3e1dd66bd676..734b80a4220c 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -130,7 +130,7 @@ xfs_bmap_rtalloc( * pick an extent that will space things out in the rt area. */ if (ap->eof && ap->offset == 0) { - xfs_rtblock_t uninitialized_var(rtx); /* realtime extent no */ + xfs_rtblock_t rtx; /* realtime extent no */ error = xfs_rtpick_extent(mp, ap->tp, ralen, &rtx); if (error) |