diff options
Diffstat (limited to 'fs')
37 files changed, 386 insertions, 142 deletions
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 78556447e1d5..ef66db38cedb 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -1454,8 +1454,8 @@ int btrfs_find_all_roots(struct btrfs_trans_handle *trans, * callers (such as fiemap) which want to know whether the extent is * shared but do not need a ref count. * - * This attempts to allocate a transaction in order to account for - * delayed refs, but continues on even when the alloc fails. + * This attempts to attach to the running transaction in order to account for + * delayed refs, but continues on even when no running transaction exists. * * Return: 0 if extent is not shared, 1 if it is shared, < 0 on error. */ @@ -1478,13 +1478,16 @@ int btrfs_check_shared(struct btrfs_root *root, u64 inum, u64 bytenr) tmp = ulist_alloc(GFP_NOFS); roots = ulist_alloc(GFP_NOFS); if (!tmp || !roots) { - ulist_free(tmp); - ulist_free(roots); - return -ENOMEM; + ret = -ENOMEM; + goto out; } - trans = btrfs_join_transaction(root); + trans = btrfs_attach_transaction(root); if (IS_ERR(trans)) { + if (PTR_ERR(trans) != -ENOENT && PTR_ERR(trans) != -EROFS) { + ret = PTR_ERR(trans); + goto out; + } trans = NULL; down_read(&fs_info->commit_root_sem); } else { @@ -1517,6 +1520,7 @@ int btrfs_check_shared(struct btrfs_root *root, u64 inum, u64 bytenr) } else { up_read(&fs_info->commit_root_sem); } +out: ulist_free(tmp); ulist_free(roots); return ret; @@ -1906,13 +1910,19 @@ int iterate_extent_inodes(struct btrfs_fs_info *fs_info, extent_item_objectid); if (!search_commit_root) { - trans = btrfs_join_transaction(fs_info->extent_root); - if (IS_ERR(trans)) - return PTR_ERR(trans); + trans = btrfs_attach_transaction(fs_info->extent_root); + if (IS_ERR(trans)) { + if (PTR_ERR(trans) != -ENOENT && + PTR_ERR(trans) != -EROFS) + return PTR_ERR(trans); + trans = NULL; + } + } + + if (trans) btrfs_get_tree_mod_seq(fs_info, &tree_mod_seq_elem); - } else { + else down_read(&fs_info->commit_root_sem); - } ret = btrfs_find_all_leafs(trans, fs_info, extent_item_objectid, tree_mod_seq_elem.seq, &refs, @@ -1945,7 +1955,7 @@ int iterate_extent_inodes(struct btrfs_fs_info *fs_info, free_leaf_list(refs); out: - if (!search_commit_root) { + if (trans) { btrfs_put_tree_mod_seq(fs_info, &tree_mod_seq_elem); btrfs_end_transaction(trans); } else { diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 5a6c39b44c84..7672932aa5b4 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -2401,6 +2401,16 @@ read_block_for_search(struct btrfs_root *root, struct btrfs_path *p, if (tmp) { /* first we do an atomic uptodate check */ if (btrfs_buffer_uptodate(tmp, gen, 1) > 0) { + /* + * Do extra check for first_key, eb can be stale due to + * being cached, read from scrub, or have multiple + * parents (shared tree blocks). + */ + if (btrfs_verify_level_key(fs_info, tmp, + parent_level - 1, &first_key, gen)) { + free_extent_buffer(tmp); + return -EUCLEAN; + } *eb_ret = tmp; return 0; } diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 7a2a2621f0d9..9019265a2bf9 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1316,6 +1316,12 @@ struct btrfs_root { * manipulation with the read-only status via SUBVOL_SETFLAGS */ int send_in_progress; + /* + * Number of currently running deduplication operations that have a + * destination inode belonging to this root. Protected by the lock + * root_item_lock. + */ + int dedupe_in_progress; struct btrfs_subvolume_writers *subv_writers; atomic_t will_be_snapshotted; atomic_t snapshot_force_cow; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 888d72dda794..90a3c50d751b 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -414,9 +414,9 @@ static int btrfs_check_super_csum(struct btrfs_fs_info *fs_info, return ret; } -static int verify_level_key(struct btrfs_fs_info *fs_info, - struct extent_buffer *eb, int level, - struct btrfs_key *first_key, u64 parent_transid) +int btrfs_verify_level_key(struct btrfs_fs_info *fs_info, + struct extent_buffer *eb, int level, + struct btrfs_key *first_key, u64 parent_transid) { int found_level; struct btrfs_key found_key; @@ -493,8 +493,8 @@ static int btree_read_extent_buffer_pages(struct btrfs_fs_info *fs_info, if (verify_parent_transid(io_tree, eb, parent_transid, 0)) ret = -EIO; - else if (verify_level_key(fs_info, eb, level, - first_key, parent_transid)) + else if (btrfs_verify_level_key(fs_info, eb, level, + first_key, parent_transid)) ret = -EUCLEAN; else break; @@ -1017,13 +1017,18 @@ void readahead_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr) { struct extent_buffer *buf = NULL; struct inode *btree_inode = fs_info->btree_inode; + int ret; buf = btrfs_find_create_tree_block(fs_info, bytenr); if (IS_ERR(buf)) return; - read_extent_buffer_pages(&BTRFS_I(btree_inode)->io_tree, - buf, WAIT_NONE, 0); - free_extent_buffer(buf); + + ret = read_extent_buffer_pages(&BTRFS_I(btree_inode)->io_tree, buf, + WAIT_NONE, 0); + if (ret < 0) + free_extent_buffer_stale(buf); + else + free_extent_buffer(buf); } int reada_tree_block_flagged(struct btrfs_fs_info *fs_info, u64 bytenr, @@ -1043,12 +1048,12 @@ int reada_tree_block_flagged(struct btrfs_fs_info *fs_info, u64 bytenr, ret = read_extent_buffer_pages(io_tree, buf, WAIT_PAGE_LOCK, mirror_num); if (ret) { - free_extent_buffer(buf); + free_extent_buffer_stale(buf); return ret; } if (test_bit(EXTENT_BUFFER_CORRUPT, &buf->bflags)) { - free_extent_buffer(buf); + free_extent_buffer_stale(buf); return -EIO; } else if (extent_buffer_uptodate(buf)) { *eb = buf; @@ -1102,7 +1107,7 @@ struct extent_buffer *read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr, ret = btree_read_extent_buffer_pages(fs_info, buf, parent_transid, level, first_key); if (ret) { - free_extent_buffer(buf); + free_extent_buffer_stale(buf); return ERR_PTR(ret); } return buf; diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index 987a64bc0c66..67a9fe2d29c7 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -39,6 +39,9 @@ static inline u64 btrfs_sb_offset(int mirror) struct btrfs_device; struct btrfs_fs_devices; +int btrfs_verify_level_key(struct btrfs_fs_info *fs_info, + struct extent_buffer *eb, int level, + struct btrfs_key *first_key, u64 parent_transid); struct extent_buffer *read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr, u64 parent_transid, int level, struct btrfs_key *first_key); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 1b68700bc1c5..a19bbfce449e 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -11192,9 +11192,9 @@ int btrfs_error_unpin_extent_range(struct btrfs_fs_info *fs_info, * held back allocations. */ static int btrfs_trim_free_extents(struct btrfs_device *device, - u64 minlen, u64 *trimmed) + struct fstrim_range *range, u64 *trimmed) { - u64 start = 0, len = 0; + u64 start = range->start, len = 0; int ret; *trimmed = 0; @@ -11237,8 +11237,8 @@ static int btrfs_trim_free_extents(struct btrfs_device *device, if (!trans) up_read(&fs_info->commit_root_sem); - ret = find_free_dev_extent_start(trans, device, minlen, start, - &start, &len); + ret = find_free_dev_extent_start(trans, device, range->minlen, + start, &start, &len); if (trans) { up_read(&fs_info->commit_root_sem); btrfs_put_transaction(trans); @@ -11251,6 +11251,16 @@ static int btrfs_trim_free_extents(struct btrfs_device *device, break; } + /* If we are out of the passed range break */ + if (start > range->start + range->len - 1) { + mutex_unlock(&fs_info->chunk_mutex); + ret = 0; + break; + } + + start = max(range->start, start); + len = min(range->len, len); + ret = btrfs_issue_discard(device->bdev, start, len, &bytes); mutex_unlock(&fs_info->chunk_mutex); @@ -11260,6 +11270,10 @@ static int btrfs_trim_free_extents(struct btrfs_device *device, start += len; *trimmed += bytes; + /* We've trimmed enough */ + if (*trimmed >= range->len) + break; + if (fatal_signal_pending(current)) { ret = -ERESTARTSYS; break; @@ -11343,8 +11357,7 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range) mutex_lock(&fs_info->fs_devices->device_list_mutex); devices = &fs_info->fs_devices->devices; list_for_each_entry(device, devices, dev_list) { - ret = btrfs_trim_free_extents(device, range->minlen, - &group_trimmed); + ret = btrfs_trim_free_extents(device, range, &group_trimmed); if (ret) { dev_failed++; dev_ret = ret; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 1d64a6b8e413..679303bf8e74 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3275,6 +3275,19 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen, int ret; int num_pages = PAGE_ALIGN(BTRFS_MAX_DEDUPE_LEN) >> PAGE_SHIFT; u64 i, tail_len, chunk_count; + struct btrfs_root *root_dst = BTRFS_I(dst)->root; + + spin_lock(&root_dst->root_item_lock); + if (root_dst->send_in_progress) { + btrfs_warn_rl(root_dst->fs_info, +"cannot deduplicate to root %llu while send operations are using it (%d in progress)", + root_dst->root_key.objectid, + root_dst->send_in_progress); + spin_unlock(&root_dst->root_item_lock); + return -EAGAIN; + } + root_dst->dedupe_in_progress++; + spin_unlock(&root_dst->root_item_lock); /* don't make the dst file partly checksummed */ if ((BTRFS_I(src)->flags & BTRFS_INODE_NODATASUM) != @@ -3293,7 +3306,7 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen, ret = btrfs_extent_same_range(src, loff, BTRFS_MAX_DEDUPE_LEN, dst, dst_loff); if (ret) - return ret; + goto out; loff += BTRFS_MAX_DEDUPE_LEN; dst_loff += BTRFS_MAX_DEDUPE_LEN; @@ -3302,6 +3315,10 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen, if (tail_len > 0) ret = btrfs_extent_same_range(src, loff, tail_len, dst, dst_loff); +out: + spin_lock(&root_dst->root_item_lock); + root_dst->dedupe_in_progress--; + spin_unlock(&root_dst->root_item_lock); return ret; } diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 7ea2d6b1f170..19b00b1668ed 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -6579,6 +6579,38 @@ commit_trans: return btrfs_commit_transaction(trans); } +/* + * Make sure any existing dellaloc is flushed for any root used by a send + * operation so that we do not miss any data and we do not race with writeback + * finishing and changing a tree while send is using the tree. This could + * happen if a subvolume is in RW mode, has delalloc, is turned to RO mode and + * a send operation then uses the subvolume. + * After flushing delalloc ensure_commit_roots_uptodate() must be called. + */ +static int flush_delalloc_roots(struct send_ctx *sctx) +{ + struct btrfs_root *root = sctx->parent_root; + int ret; + int i; + + if (root) { + ret = btrfs_start_delalloc_snapshot(root); + if (ret) + return ret; + btrfs_wait_ordered_extents(root, U64_MAX, 0, U64_MAX); + } + + for (i = 0; i < sctx->clone_roots_cnt; i++) { + root = sctx->clone_roots[i].root; + ret = btrfs_start_delalloc_snapshot(root); + if (ret) + return ret; + btrfs_wait_ordered_extents(root, U64_MAX, 0, U64_MAX); + } + + return 0; +} + static void btrfs_root_dec_send_in_progress(struct btrfs_root* root) { spin_lock(&root->root_item_lock); @@ -6594,6 +6626,13 @@ static void btrfs_root_dec_send_in_progress(struct btrfs_root* root) spin_unlock(&root->root_item_lock); } +static void dedupe_in_progress_warn(const struct btrfs_root *root) +{ + btrfs_warn_rl(root->fs_info, +"cannot use root %llu for send while deduplications on it are in progress (%d in progress)", + root->root_key.objectid, root->dedupe_in_progress); +} + long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg) { int ret = 0; @@ -6617,6 +6656,11 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg) * making it RW. This also protects against deletion. */ spin_lock(&send_root->root_item_lock); + if (btrfs_root_readonly(send_root) && send_root->dedupe_in_progress) { + dedupe_in_progress_warn(send_root); + spin_unlock(&send_root->root_item_lock); + return -EAGAIN; + } send_root->send_in_progress++; spin_unlock(&send_root->root_item_lock); @@ -6751,6 +6795,13 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg) ret = -EPERM; goto out; } + if (clone_root->dedupe_in_progress) { + dedupe_in_progress_warn(clone_root); + spin_unlock(&clone_root->root_item_lock); + srcu_read_unlock(&fs_info->subvol_srcu, index); + ret = -EAGAIN; + goto out; + } clone_root->send_in_progress++; spin_unlock(&clone_root->root_item_lock); srcu_read_unlock(&fs_info->subvol_srcu, index); @@ -6785,6 +6836,13 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg) ret = -EPERM; goto out; } + if (sctx->parent_root->dedupe_in_progress) { + dedupe_in_progress_warn(sctx->parent_root); + spin_unlock(&sctx->parent_root->root_item_lock); + srcu_read_unlock(&fs_info->subvol_srcu, index); + ret = -EAGAIN; + goto out; + } spin_unlock(&sctx->parent_root->root_item_lock); srcu_read_unlock(&fs_info->subvol_srcu, index); @@ -6803,6 +6861,10 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg) NULL); sort_clone_roots = 1; + ret = flush_delalloc_roots(sctx); + if (ret) + goto out; + ret = ensure_commit_roots_uptodate(sctx); if (ret) goto out; diff --git a/fs/ceph/super.c b/fs/ceph/super.c index da2cd8e89062..950919411460 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -832,6 +832,12 @@ static void ceph_umount_begin(struct super_block *sb) return; } +static int ceph_remount(struct super_block *sb, int *flags, char *data) +{ + sync_filesystem(sb); + return 0; +} + static const struct super_operations ceph_super_ops = { .alloc_inode = ceph_alloc_inode, .destroy_inode = ceph_destroy_inode, @@ -839,6 +845,7 @@ static const struct super_operations ceph_super_ops = { .drop_inode = ceph_drop_inode, .sync_fs = ceph_sync_fs, .put_super = ceph_put_super, + .remount_fs = ceph_remount, .show_options = ceph_show_options, .statfs = ceph_statfs, .umount_begin = ceph_umount_begin, diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index d5434ac0571b..105ddbad00e5 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -2652,26 +2652,28 @@ smb21_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock, unsigned int epoch, bool *purge_cache) { char message[5] = {0}; + unsigned int new_oplock = 0; oplock &= 0xFF; if (oplock == SMB2_OPLOCK_LEVEL_NOCHANGE) return; - cinode->oplock = 0; if (oplock & SMB2_LEASE_READ_CACHING_HE) { - cinode->oplock |= CIFS_CACHE_READ_FLG; + new_oplock |= CIFS_CACHE_READ_FLG; strcat(message, "R"); } if (oplock & SMB2_LEASE_HANDLE_CACHING_HE) { - cinode->oplock |= CIFS_CACHE_HANDLE_FLG; + new_oplock |= CIFS_CACHE_HANDLE_FLG; strcat(message, "H"); } if (oplock & SMB2_LEASE_WRITE_CACHING_HE) { - cinode->oplock |= CIFS_CACHE_WRITE_FLG; + new_oplock |= CIFS_CACHE_WRITE_FLG; strcat(message, "W"); } - if (!cinode->oplock) - strcat(message, "None"); + if (!new_oplock) + strncpy(message, "None", sizeof(message)); + + cinode->oplock = new_oplock; cifs_dbg(FYI, "%s Lease granted on inode %p\n", message, &cinode->vfs_inode); } @@ -1577,8 +1577,7 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp, } trace_dax_pmd_insert_mapping(inode, vmf, PMD_SIZE, pfn, entry); - result = vmf_insert_pfn_pmd(vma, vmf->address, vmf->pmd, pfn, - write); + result = vmf_insert_pfn_pmd(vmf, pfn, write); break; case IOMAP_UNWRITTEN: case IOMAP_HOLE: @@ -1688,8 +1687,7 @@ dax_insert_pfn_mkwrite(struct vm_fault *vmf, pfn_t pfn, unsigned int order) ret = vmf_insert_mixed_mkwrite(vmf->vma, vmf->address, pfn); #ifdef CONFIG_FS_DAX_PMD else if (order == PMD_ORDER) - ret = vmf_insert_pfn_pmd(vmf->vma, vmf->address, vmf->pmd, - pfn, true); + ret = vmf_insert_pfn_pmd(vmf, pfn, FAULT_FLAG_WRITE); #endif else ret = VM_FAULT_FALLBACK; diff --git a/fs/dcache.c b/fs/dcache.c index aac41adf4743..c663c602f9ef 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -344,7 +344,7 @@ static void dentry_free(struct dentry *dentry) } } /* if dentry was never visible to RCU, immediate free is OK */ - if (!(dentry->d_flags & DCACHE_RCUACCESS)) + if (dentry->d_flags & DCACHE_NORCU) __d_free(&dentry->d_u.d_rcu); else call_rcu(&dentry->d_u.d_rcu, __d_free); @@ -1701,7 +1701,6 @@ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name) struct dentry *dentry = __d_alloc(parent->d_sb, name); if (!dentry) return NULL; - dentry->d_flags |= DCACHE_RCUACCESS; spin_lock(&parent->d_lock); /* * don't need child lock because it is not subject @@ -1726,7 +1725,7 @@ struct dentry *d_alloc_cursor(struct dentry * parent) { struct dentry *dentry = d_alloc_anon(parent->d_sb); if (dentry) { - dentry->d_flags |= DCACHE_RCUACCESS | DCACHE_DENTRY_CURSOR; + dentry->d_flags |= DCACHE_DENTRY_CURSOR; dentry->d_parent = dget(parent); } return dentry; @@ -1739,10 +1738,17 @@ struct dentry *d_alloc_cursor(struct dentry * parent) * * For a filesystem that just pins its dentries in memory and never * performs lookups at all, return an unhashed IS_ROOT dentry. + * This is used for pipes, sockets et.al. - the stuff that should + * never be anyone's children or parents. Unlike all other + * dentries, these will not have RCU delay between dropping the + * last reference and freeing them. */ struct dentry *d_alloc_pseudo(struct super_block *sb, const struct qstr *name) { - return __d_alloc(sb, name); + struct dentry *dentry = __d_alloc(sb, name); + if (likely(dentry)) + dentry->d_flags |= DCACHE_NORCU; + return dentry; } EXPORT_SYMBOL(d_alloc_pseudo); @@ -1911,12 +1917,10 @@ struct dentry *d_make_root(struct inode *root_inode) if (root_inode) { res = d_alloc_anon(root_inode->i_sb); - if (res) { - res->d_flags |= DCACHE_RCUACCESS; + if (res) d_instantiate(res, root_inode); - } else { + else iput(root_inode); - } } return res; } @@ -2781,9 +2785,7 @@ static void __d_move(struct dentry *dentry, struct dentry *target, copy_name(dentry, target); target->d_hash.pprev = NULL; dentry->d_parent->d_lockref.count++; - if (dentry == old_parent) - dentry->d_flags |= DCACHE_RCUACCESS; - else + if (dentry != old_parent) /* wasn't IS_ROOT */ WARN_ON(!--old_parent->d_lockref.count); } else { target->d_parent = old_parent; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 508a37ec9271..b8fde74ff76d 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1665,6 +1665,8 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei) #define EXT4_FEATURE_INCOMPAT_INLINE_DATA 0x8000 /* data in inode */ #define EXT4_FEATURE_INCOMPAT_ENCRYPT 0x10000 +extern void ext4_update_dynamic_rev(struct super_block *sb); + #define EXT4_FEATURE_COMPAT_FUNCS(name, flagname) \ static inline bool ext4_has_feature_##name(struct super_block *sb) \ { \ @@ -1673,6 +1675,7 @@ static inline bool ext4_has_feature_##name(struct super_block *sb) \ } \ static inline void ext4_set_feature_##name(struct super_block *sb) \ { \ + ext4_update_dynamic_rev(sb); \ EXT4_SB(sb)->s_es->s_feature_compat |= \ cpu_to_le32(EXT4_FEATURE_COMPAT_##flagname); \ } \ @@ -1690,6 +1693,7 @@ static inline bool ext4_has_feature_##name(struct super_block *sb) \ } \ static inline void ext4_set_feature_##name(struct super_block *sb) \ { \ + ext4_update_dynamic_rev(sb); \ EXT4_SB(sb)->s_es->s_feature_ro_compat |= \ cpu_to_le32(EXT4_FEATURE_RO_COMPAT_##flagname); \ } \ @@ -1707,6 +1711,7 @@ static inline bool ext4_has_feature_##name(struct super_block *sb) \ } \ static inline void ext4_set_feature_##name(struct super_block *sb) \ { \ + ext4_update_dynamic_rev(sb); \ EXT4_SB(sb)->s_es->s_feature_incompat |= \ cpu_to_le32(EXT4_FEATURE_INCOMPAT_##flagname); \ } \ @@ -2675,7 +2680,6 @@ do { \ #endif -extern void ext4_update_dynamic_rev(struct super_block *sb); extern int ext4_update_compat_feature(handle_t *handle, struct super_block *sb, __u32 compat); extern int ext4_update_rocompat_feature(handle_t *handle, diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 252bbbb5a2f4..cd00b19746bd 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -1035,6 +1035,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, __le32 border; ext4_fsblk_t *ablocks = NULL; /* array of allocated blocks */ int err = 0; + size_t ext_size = 0; /* make decision: where to split? */ /* FIXME: now decision is simplest: at current extent */ @@ -1126,6 +1127,10 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, le16_add_cpu(&neh->eh_entries, m); } + /* zero out unused area in the extent block */ + ext_size = sizeof(struct ext4_extent_header) + + sizeof(struct ext4_extent) * le16_to_cpu(neh->eh_entries); + memset(bh->b_data + ext_size, 0, inode->i_sb->s_blocksize - ext_size); ext4_extent_block_csum_set(inode, neh); set_buffer_uptodate(bh); unlock_buffer(bh); @@ -1205,6 +1210,11 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, sizeof(struct ext4_extent_idx) * m); le16_add_cpu(&neh->eh_entries, m); } + /* zero out unused area in the extent block */ + ext_size = sizeof(struct ext4_extent_header) + + (sizeof(struct ext4_extent) * le16_to_cpu(neh->eh_entries)); + memset(bh->b_data + ext_size, 0, + inode->i_sb->s_blocksize - ext_size); ext4_extent_block_csum_set(inode, neh); set_buffer_uptodate(bh); unlock_buffer(bh); @@ -1270,6 +1280,7 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode, ext4_fsblk_t newblock, goal = 0; struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es; int err = 0; + size_t ext_size = 0; /* Try to prepend new index to old one */ if (ext_depth(inode)) @@ -1295,9 +1306,11 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode, goto out; } + ext_size = sizeof(EXT4_I(inode)->i_data); /* move top-level index/leaf into new block */ - memmove(bh->b_data, EXT4_I(inode)->i_data, - sizeof(EXT4_I(inode)->i_data)); + memmove(bh->b_data, EXT4_I(inode)->i_data, ext_size); + /* zero out unused area in the extent block */ + memset(bh->b_data + ext_size, 0, inode->i_sb->s_blocksize - ext_size); /* set size of new block */ neh = ext_block_hdr(bh); diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 98ec11f69cd4..2c5baa5e8291 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -264,6 +264,13 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from) } ret = __generic_file_write_iter(iocb, from); + /* + * Unaligned direct AIO must be the only IO in flight. Otherwise + * overlapping aligned IO after unaligned might result in data + * corruption. + */ + if (ret == -EIOCBQUEUED && unaligned_aio) + ext4_unwritten_wait(inode); inode_unlock(inode); if (ret > 0) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 34d7e0703cc6..878f8b5dd39f 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5351,7 +5351,6 @@ static int ext4_do_update_inode(handle_t *handle, err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh); if (err) goto out_brelse; - ext4_update_dynamic_rev(sb); ext4_set_feature_large_file(sb); ext4_handle_sync(handle); err = ext4_handle_dirty_super(handle, sb); @@ -6002,7 +6001,7 @@ int ext4_expand_extra_isize(struct inode *inode, ext4_write_lock_xattr(inode, &no_expand); - BUFFER_TRACE(iloc.bh, "get_write_access"); + BUFFER_TRACE(iloc->bh, "get_write_access"); error = ext4_journal_get_write_access(handle, iloc->bh); if (error) { brelse(iloc->bh); diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 5f24fdc140ad..53d57cdf3c4d 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -977,7 +977,7 @@ mext_out: if (err == 0) err = err2; mnt_drop_write_file(filp); - if (!err && (o_group > EXT4_SB(sb)->s_groups_count) && + if (!err && (o_group < EXT4_SB(sb)->s_groups_count) && ext4_has_group_desc_csum(sb) && test_opt(sb, INIT_INODE_TABLE)) err = ext4_register_li_request(sb, o_group); diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index e2248083cdca..459450e59a88 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -1539,7 +1539,7 @@ static int mb_find_extent(struct ext4_buddy *e4b, int block, ex->fe_len += 1 << order; } - if (ex->fe_start + ex->fe_len > (1 << (e4b->bd_blkbits + 3))) { + if (ex->fe_start + ex->fe_len > EXT4_CLUSTERS_PER_GROUP(e4b->bd_sb)) { /* Should never happen! (but apparently sometimes does?!?) */ WARN_ON(1); ext4_error(e4b->bd_sb, "corruption or bug in mb_find_extent " diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 2b928eb07fa2..03c623407648 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -871,12 +871,15 @@ static void dx_release(struct dx_frame *frames) { struct dx_root_info *info; int i; + unsigned int indirect_levels; if (frames[0].bh == NULL) return; info = &((struct dx_root *)frames[0].bh->b_data)->info; - for (i = 0; i <= info->indirect_levels; i++) { + /* save local copy, "info" may be freed after brelse() */ + indirect_levels = info->indirect_levels; + for (i = 0; i <= indirect_levels; i++) { if (frames[i].bh == NULL) break; brelse(frames[i].bh); diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index e7ae26e36c9c..4d5c0fc9d23a 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -874,6 +874,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode, err = ext4_handle_dirty_metadata(handle, NULL, gdb_bh); if (unlikely(err)) { ext4_std_error(sb, err); + iloc.bh = NULL; goto errout; } brelse(dind); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index b9bca7298f96..7b22c01b1cdb 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -698,7 +698,7 @@ void __ext4_abort(struct super_block *sb, const char *function, jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO); save_error_info(sb, function, line); } - if (test_opt(sb, ERRORS_PANIC)) { + if (test_opt(sb, ERRORS_PANIC) && !system_going_down()) { if (EXT4_SB(sb)->s_journal && !(EXT4_SB(sb)->s_journal->j_flags & JBD2_REC_ERR)) return; @@ -2259,7 +2259,6 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es, es->s_max_mnt_count = cpu_to_le16(EXT4_DFL_MAX_MNT_COUNT); le16_add_cpu(&es->s_mnt_count, 1); ext4_update_tstamp(es, s_mtime); - ext4_update_dynamic_rev(sb); if (sbi->s_journal) ext4_set_feature_journal_needs_recovery(sb); @@ -3514,6 +3513,37 @@ int ext4_calculate_overhead(struct super_block *sb) return 0; } +static void ext4_clamp_want_extra_isize(struct super_block *sb) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_super_block *es = sbi->s_es; + + /* determine the minimum size of new large inodes, if present */ + if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE && + sbi->s_want_extra_isize == 0) { + sbi->s_want_extra_isize = sizeof(struct ext4_inode) - + EXT4_GOOD_OLD_INODE_SIZE; + if (ext4_has_feature_extra_isize(sb)) { + if (sbi->s_want_extra_isize < + le16_to_cpu(es->s_want_extra_isize)) + sbi->s_want_extra_isize = + le16_to_cpu(es->s_want_extra_isize); + if (sbi->s_want_extra_isize < + le16_to_cpu(es->s_min_extra_isize)) + sbi->s_want_extra_isize = + le16_to_cpu(es->s_min_extra_isize); + } + } + /* Check if enough inode space is available */ + if (EXT4_GOOD_OLD_INODE_SIZE + sbi->s_want_extra_isize > + sbi->s_inode_size) { + sbi->s_want_extra_isize = sizeof(struct ext4_inode) - + EXT4_GOOD_OLD_INODE_SIZE; + ext4_msg(sb, KERN_INFO, + "required extra inode space not available"); + } +} + static void ext4_set_resv_clusters(struct super_block *sb) { ext4_fsblk_t resv_clusters; @@ -4239,7 +4269,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) "data=, fs mounted w/o journal"); goto failed_mount_wq; } - sbi->s_def_mount_opt &= EXT4_MOUNT_JOURNAL_CHECKSUM; + sbi->s_def_mount_opt &= ~EXT4_MOUNT_JOURNAL_CHECKSUM; clear_opt(sb, JOURNAL_CHECKSUM); clear_opt(sb, DATA_FLAGS); sbi->s_journal = NULL; @@ -4388,30 +4418,7 @@ no_journal: } else if (ret) goto failed_mount4a; - /* determine the minimum size of new large inodes, if present */ - if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE && - sbi->s_want_extra_isize == 0) { - sbi->s_want_extra_isize = sizeof(struct ext4_inode) - - EXT4_GOOD_OLD_INODE_SIZE; - if (ext4_has_feature_extra_isize(sb)) { - if (sbi->s_want_extra_isize < - le16_to_cpu(es->s_want_extra_isize)) - sbi->s_want_extra_isize = - le16_to_cpu(es->s_want_extra_isize); - if (sbi->s_want_extra_isize < - le16_to_cpu(es->s_min_extra_isize)) - sbi->s_want_extra_isize = - le16_to_cpu(es->s_min_extra_isize); - } - } - /* Check if enough inode space is available */ - if (EXT4_GOOD_OLD_INODE_SIZE + sbi->s_want_extra_isize > - sbi->s_inode_size) { - sbi->s_want_extra_isize = sizeof(struct ext4_inode) - - EXT4_GOOD_OLD_INODE_SIZE; - ext4_msg(sb, KERN_INFO, "required extra inode space not" - "available"); - } + ext4_clamp_want_extra_isize(sb); ext4_set_resv_clusters(sb); @@ -5195,6 +5202,8 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) goto restore_opts; } + ext4_clamp_want_extra_isize(sb); + if ((old_opts.s_mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) ^ test_opt(sb, JOURNAL_CHECKSUM)) { ext4_msg(sb, KERN_ERR, "changing journal_checksum " diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index dc82e7757f67..491f9ee4040e 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1696,7 +1696,7 @@ static int ext4_xattr_set_entry(struct ext4_xattr_info *i, /* No failures allowed past this point. */ - if (!s->not_found && here->e_value_size && here->e_value_offs) { + if (!s->not_found && here->e_value_size && !here->e_value_inum) { /* Remove the old value. */ void *first_val = s->base + min_offs; size_t offs = le16_to_cpu(here->e_value_offs); diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 36855c1f8daf..b16645b417d9 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -523,8 +523,6 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id) isw->inode = inode; - atomic_inc(&isw_nr_in_flight); - /* * In addition to synchronizing among switchers, I_WB_SWITCH tells * the RCU protected stat update paths to grab the i_page @@ -532,6 +530,9 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id) * Let's continue after I_WB_SWITCH is guaranteed to be visible. */ call_rcu(&isw->rcu_head, inode_switch_wbs_rcu_fn); + + atomic_inc(&isw_nr_in_flight); + goto out_unlock; out_free: @@ -901,7 +902,11 @@ restart: void cgroup_writeback_umount(void) { if (atomic_read(&isw_nr_in_flight)) { - synchronize_rcu(); + /* + * Use rcu_barrier() to wait for all pending callbacks to + * ensure that all in-flight wb switches are in the workqueue. + */ + rcu_barrier(); flush_workqueue(isw_wq); } } diff --git a/fs/fuse/file.c b/fs/fuse/file.c index a59c16bd90ac..d2926ac44f83 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -181,7 +181,9 @@ void fuse_finish_open(struct inode *inode, struct file *file) file->f_op = &fuse_direct_io_file_operations; if (!(ff->open_flags & FOPEN_KEEP_CACHE)) invalidate_inode_pages2(inode->i_mapping); - if (ff->open_flags & FOPEN_NONSEEKABLE) + if (ff->open_flags & FOPEN_STREAM) + stream_open(inode, file); + else if (ff->open_flags & FOPEN_NONSEEKABLE) nonseekable_open(inode, file); if (fc->atomic_o_trunc && (file->f_flags & O_TRUNC)) { struct fuse_inode *fi = get_fuse_inode(inode); @@ -1530,7 +1532,7 @@ __acquires(fc->lock) { struct fuse_conn *fc = get_fuse_conn(inode); struct fuse_inode *fi = get_fuse_inode(inode); - size_t crop = i_size_read(inode); + loff_t crop = i_size_read(inode); struct fuse_req *req; while (fi->writectr >= 0 && !list_empty(&fi->queued_writes)) { @@ -2987,6 +2989,13 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset, } } + if (!(mode & FALLOC_FL_KEEP_SIZE) && + offset + length > i_size_read(inode)) { + err = inode_newsize_ok(inode, offset + length); + if (err) + return err; + } + if (!(mode & FALLOC_FL_KEEP_SIZE)) set_bit(FUSE_I_SIZE_UNSTABLE, &fi->state); diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index a3a3d256fb0e..7a24f91af29e 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -426,9 +426,7 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, u32 hash; index = page->index; - hash = hugetlb_fault_mutex_hash(h, current->mm, - &pseudo_vma, - mapping, index, 0); + hash = hugetlb_fault_mutex_hash(h, mapping, index, 0); mutex_lock(&hugetlb_fault_mutex_table[hash]); /* @@ -625,8 +623,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, addr = index * hpage_size; /* mutex taken here, fault path and hole punch */ - hash = hugetlb_fault_mutex_hash(h, mm, &pseudo_vma, mapping, - index, addr); + hash = hugetlb_fault_mutex_hash(h, mapping, index, addr); mutex_lock(&hugetlb_fault_mutex_table[hash]); /* See if already present in mapping to avoid alloc/free */ diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 88f2a49338a1..e9cf88f0bc29 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1366,6 +1366,10 @@ static int jbd2_write_superblock(journal_t *journal, int write_flags) journal_superblock_t *sb = journal->j_superblock; int ret; + /* Buffer got discarded which means block device got invalidated */ + if (!buffer_mapped(bh)) + return -EIO; + trace_jbd2_write_superblock(journal, write_flags); if (!(journal->j_flags & JBD2_BARRIER)) write_flags &= ~(REQ_FUA | REQ_PREFLUSH); @@ -2385,22 +2389,19 @@ static struct kmem_cache *jbd2_journal_head_cache; static atomic_t nr_journal_heads = ATOMIC_INIT(0); #endif -static int jbd2_journal_init_journal_head_cache(void) +static int __init jbd2_journal_init_journal_head_cache(void) { - int retval; - - J_ASSERT(jbd2_journal_head_cache == NULL); + J_ASSERT(!jbd2_journal_head_cache); jbd2_journal_head_cache = kmem_cache_create("jbd2_journal_head", sizeof(struct journal_head), 0, /* offset */ SLAB_TEMPORARY | SLAB_TYPESAFE_BY_RCU, NULL); /* ctor */ - retval = 0; if (!jbd2_journal_head_cache) { - retval = -ENOMEM; printk(KERN_EMERG "JBD2: no memory for journal_head cache\n"); + return -ENOMEM; } - return retval; + return 0; } static void jbd2_journal_destroy_journal_head_cache(void) @@ -2646,28 +2647,38 @@ static void __exit jbd2_remove_jbd_stats_proc_entry(void) struct kmem_cache *jbd2_handle_cache, *jbd2_inode_cache; +static int __init jbd2_journal_init_inode_cache(void) +{ + J_ASSERT(!jbd2_inode_cache); + jbd2_inode_cache = KMEM_CACHE(jbd2_inode, 0); + if (!jbd2_inode_cache) { + pr_emerg("JBD2: failed to create inode cache\n"); + return -ENOMEM; + } + return 0; +} + static int __init jbd2_journal_init_handle_cache(void) { + J_ASSERT(!jbd2_handle_cache); jbd2_handle_cache = KMEM_CACHE(jbd2_journal_handle, SLAB_TEMPORARY); - if (jbd2_handle_cache == NULL) { + if (!jbd2_handle_cache) { printk(KERN_EMERG "JBD2: failed to create handle cache\n"); return -ENOMEM; } - jbd2_inode_cache = KMEM_CACHE(jbd2_inode, 0); - if (jbd2_inode_cache == NULL) { - printk(KERN_EMERG "JBD2: failed to create inode cache\n"); - kmem_cache_destroy(jbd2_handle_cache); - return -ENOMEM; - } return 0; } +static void jbd2_journal_destroy_inode_cache(void) +{ + kmem_cache_destroy(jbd2_inode_cache); + jbd2_inode_cache = NULL; +} + static void jbd2_journal_destroy_handle_cache(void) { kmem_cache_destroy(jbd2_handle_cache); jbd2_handle_cache = NULL; - kmem_cache_destroy(jbd2_inode_cache); - jbd2_inode_cache = NULL; } /* @@ -2678,21 +2689,27 @@ static int __init journal_init_caches(void) { int ret; - ret = jbd2_journal_init_revoke_caches(); + ret = jbd2_journal_init_revoke_record_cache(); + if (ret == 0) + ret = jbd2_journal_init_revoke_table_cache(); if (ret == 0) ret = jbd2_journal_init_journal_head_cache(); if (ret == 0) ret = jbd2_journal_init_handle_cache(); if (ret == 0) + ret = jbd2_journal_init_inode_cache(); + if (ret == 0) ret = jbd2_journal_init_transaction_cache(); return ret; } static void jbd2_journal_destroy_caches(void) { - jbd2_journal_destroy_revoke_caches(); + jbd2_journal_destroy_revoke_record_cache(); + jbd2_journal_destroy_revoke_table_cache(); jbd2_journal_destroy_journal_head_cache(); jbd2_journal_destroy_handle_cache(); + jbd2_journal_destroy_inode_cache(); jbd2_journal_destroy_transaction_cache(); jbd2_journal_destroy_slabs(); } diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c index a1143e57a718..69b9bc329964 100644 --- a/fs/jbd2/revoke.c +++ b/fs/jbd2/revoke.c @@ -178,33 +178,41 @@ static struct jbd2_revoke_record_s *find_revoke_record(journal_t *journal, return NULL; } -void jbd2_journal_destroy_revoke_caches(void) +void jbd2_journal_destroy_revoke_record_cache(void) { kmem_cache_destroy(jbd2_revoke_record_cache); jbd2_revoke_record_cache = NULL; +} + +void jbd2_journal_destroy_revoke_table_cache(void) +{ kmem_cache_destroy(jbd2_revoke_table_cache); jbd2_revoke_table_cache = NULL; } -int __init jbd2_journal_init_revoke_caches(void) +int __init jbd2_journal_init_revoke_record_cache(void) { J_ASSERT(!jbd2_revoke_record_cache); - J_ASSERT(!jbd2_revoke_table_cache); - jbd2_revoke_record_cache = KMEM_CACHE(jbd2_revoke_record_s, SLAB_HWCACHE_ALIGN|SLAB_TEMPORARY); - if (!jbd2_revoke_record_cache) - goto record_cache_failure; + if (!jbd2_revoke_record_cache) { + pr_emerg("JBD2: failed to create revoke_record cache\n"); + return -ENOMEM; + } + return 0; +} + +int __init jbd2_journal_init_revoke_table_cache(void) +{ + J_ASSERT(!jbd2_revoke_table_cache); jbd2_revoke_table_cache = KMEM_CACHE(jbd2_revoke_table_s, SLAB_TEMPORARY); - if (!jbd2_revoke_table_cache) - goto table_cache_failure; - return 0; -table_cache_failure: - jbd2_journal_destroy_revoke_caches(); -record_cache_failure: + if (!jbd2_revoke_table_cache) { + pr_emerg("JBD2: failed to create revoke_table cache\n"); return -ENOMEM; + } + return 0; } static struct jbd2_revoke_table_s *jbd2_journal_init_revoke_table(int hash_size) diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index f0d8dabe1ff5..e9dded268a9b 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -42,9 +42,11 @@ int __init jbd2_journal_init_transaction_cache(void) 0, SLAB_HWCACHE_ALIGN|SLAB_TEMPORARY, NULL); - if (transaction_cache) - return 0; - return -ENOMEM; + if (!transaction_cache) { + pr_emerg("JBD2: failed to create transaction cache\n"); + return -ENOMEM; + } + return 0; } void jbd2_journal_destroy_transaction_cache(void) diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index 61f46facb39c..b3e8ba3bd654 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -904,7 +904,7 @@ fl_pnfs_update_layout(struct inode *ino, status = filelayout_check_deviceid(lo, fl, gfp_flags); if (status) { pnfs_put_lseg(lseg); - lseg = ERR_PTR(status); + lseg = NULL; } out: return lseg; diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 02488b50534a..6999e870baa9 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -159,6 +159,10 @@ int nfs40_discover_server_trunking(struct nfs_client *clp, /* Sustain the lease, even if it's empty. If the clientid4 * goes stale it's of no use for trunking discovery. */ nfs4_schedule_state_renewal(*result); + + /* If the client state need to recover, do it. */ + if (clp->cl_state) + nfs4_schedule_state_manager(clp); } out: return status; diff --git a/fs/nsfs.c b/fs/nsfs.c index 60702d677bd4..30d150a4f0c6 100644 --- a/fs/nsfs.c +++ b/fs/nsfs.c @@ -85,13 +85,12 @@ slow: inode->i_fop = &ns_file_operations; inode->i_private = ns; - dentry = d_alloc_pseudo(mnt->mnt_sb, &empty_name); + dentry = d_alloc_anon(mnt->mnt_sb); if (!dentry) { iput(inode); return ERR_PTR(-ENOMEM); } d_instantiate(dentry, inode); - dentry->d_flags |= DCACHE_RCUACCESS; dentry->d_fsdata = (void *)ns->ops; d = atomic_long_cmpxchg(&ns->stashed, 0, (unsigned long)dentry); if (d) { diff --git a/fs/ocfs2/export.c b/fs/ocfs2/export.c index 4bf8d5854b27..af2888d23de3 100644 --- a/fs/ocfs2/export.c +++ b/fs/ocfs2/export.c @@ -148,16 +148,24 @@ static struct dentry *ocfs2_get_parent(struct dentry *child) u64 blkno; struct dentry *parent; struct inode *dir = d_inode(child); + int set; trace_ocfs2_get_parent(child, child->d_name.len, child->d_name.name, (unsigned long long)OCFS2_I(dir)->ip_blkno); + status = ocfs2_nfs_sync_lock(OCFS2_SB(dir->i_sb), 1); + if (status < 0) { + mlog(ML_ERROR, "getting nfs sync lock(EX) failed %d\n", status); + parent = ERR_PTR(status); + goto bail; + } + status = ocfs2_inode_lock(dir, NULL, 0); if (status < 0) { if (status != -ENOENT) mlog_errno(status); parent = ERR_PTR(status); - goto bail; + goto unlock_nfs_sync; } status = ocfs2_lookup_ino_from_name(dir, "..", 2, &blkno); @@ -166,11 +174,31 @@ static struct dentry *ocfs2_get_parent(struct dentry *child) goto bail_unlock; } + status = ocfs2_test_inode_bit(OCFS2_SB(dir->i_sb), blkno, &set); + if (status < 0) { + if (status == -EINVAL) { + status = -ESTALE; + } else + mlog(ML_ERROR, "test inode bit failed %d\n", status); + parent = ERR_PTR(status); + goto bail_unlock; + } + + trace_ocfs2_get_dentry_test_bit(status, set); + if (!set) { + status = -ESTALE; + parent = ERR_PTR(status); + goto bail_unlock; + } + parent = d_obtain_alias(ocfs2_iget(OCFS2_SB(dir->i_sb), blkno, 0, 0)); bail_unlock: ocfs2_inode_unlock(dir, 0); +unlock_nfs_sync: + ocfs2_nfs_sync_unlock(OCFS2_SB(dir->i_sb), 1); + bail: trace_ocfs2_get_parent_end(parent); diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 68b3303e4b46..56feaa739979 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -909,14 +909,14 @@ static bool ovl_open_need_copy_up(struct dentry *dentry, int flags) return true; } -int ovl_open_maybe_copy_up(struct dentry *dentry, unsigned int file_flags) +int ovl_maybe_copy_up(struct dentry *dentry, int flags) { int err = 0; - if (ovl_open_need_copy_up(dentry, file_flags)) { + if (ovl_open_need_copy_up(dentry, flags)) { err = ovl_want_write(dentry); if (!err) { - err = ovl_copy_up_flags(dentry, file_flags); + err = ovl_copy_up_flags(dentry, flags); ovl_drop_write(dentry); } } diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index 84dd957efa24..50e4407398d8 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -116,11 +116,10 @@ static int ovl_real_fdget(const struct file *file, struct fd *real) static int ovl_open(struct inode *inode, struct file *file) { - struct dentry *dentry = file_dentry(file); struct file *realfile; int err; - err = ovl_open_maybe_copy_up(dentry, file->f_flags); + err = ovl_maybe_copy_up(file_dentry(file), file->f_flags); if (err) return err; @@ -390,7 +389,7 @@ static long ovl_ioctl(struct file *file, unsigned int cmd, unsigned long arg) if (ret) return ret; - ret = ovl_copy_up_with_data(file_dentry(file)); + ret = ovl_maybe_copy_up(file_dentry(file), O_WRONLY); if (!ret) { ret = ovl_real_ioctl(file, cmd, arg); diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index 9c6018287d57..d26efed9f80a 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -421,7 +421,7 @@ extern const struct file_operations ovl_file_operations; int ovl_copy_up(struct dentry *dentry); int ovl_copy_up_with_data(struct dentry *dentry); int ovl_copy_up_flags(struct dentry *dentry, int flags); -int ovl_open_maybe_copy_up(struct dentry *dentry, unsigned int file_flags); +int ovl_maybe_copy_up(struct dentry *dentry, int flags); int ovl_copy_xattr(struct dentry *old, struct dentry *new); int ovl_set_attr(struct dentry *upper, struct kstat *stat); struct ovl_fh *ovl_encode_real_fh(struct dentry *real, bool is_upper); diff --git a/fs/proc/base.c b/fs/proc/base.c index f5ed9512d193..ef11c54ad712 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2550,6 +2550,11 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf, rcu_read_unlock(); return -EACCES; } + /* Prevent changes to overridden credentials. */ + if (current_cred() != current_real_cred()) { + rcu_read_unlock(); + return -EBUSY; + } rcu_read_unlock(); if (count > PAGE_SIZE) diff --git a/fs/ufs/util.h b/fs/ufs/util.h index 1fd3011ea623..7fd4802222b8 100644 --- a/fs/ufs/util.h +++ b/fs/ufs/util.h @@ -229,7 +229,7 @@ ufs_get_inode_gid(struct super_block *sb, struct ufs_inode *inode) case UFS_UID_44BSD: return fs32_to_cpu(sb, inode->ui_u3.ui_44.ui_gid); case UFS_UID_EFT: - if (inode->ui_u1.oldids.ui_suid == 0xFFFF) + if (inode->ui_u1.oldids.ui_sgid == 0xFFFF) return fs32_to_cpu(sb, inode->ui_u3.ui_sun.ui_gid); /* Fall through */ default: |