diff options
Diffstat (limited to 'fs')
56 files changed, 470 insertions, 261 deletions
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 0531cb9a3ba9..d826fbaf7d50 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -718,7 +718,7 @@ out: * read tree blocks and add keys where required. */ static int add_missing_keys(struct btrfs_fs_info *fs_info, - struct preftrees *preftrees) + struct preftrees *preftrees, bool lock) { struct prelim_ref *ref; struct extent_buffer *eb; @@ -742,12 +742,14 @@ static int add_missing_keys(struct btrfs_fs_info *fs_info, free_extent_buffer(eb); return -EIO; } - btrfs_tree_read_lock(eb); + if (lock) + btrfs_tree_read_lock(eb); if (btrfs_header_level(eb) == 0) btrfs_item_key_to_cpu(eb, &ref->key_for_search, 0); else btrfs_node_key_to_cpu(eb, &ref->key_for_search, 0); - btrfs_tree_read_unlock(eb); + if (lock) + btrfs_tree_read_unlock(eb); free_extent_buffer(eb); prelim_ref_insert(fs_info, &preftrees->indirect, ref, NULL); cond_resched(); @@ -1228,7 +1230,7 @@ again: btrfs_release_path(path); - ret = add_missing_keys(fs_info, &preftrees); + ret = add_missing_keys(fs_info, &preftrees, path->skip_locking == 0); if (ret) goto out; @@ -1290,9 +1292,14 @@ again: } btrfs_tree_read_lock(eb); btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK); + if (!path->skip_locking) { + btrfs_tree_read_lock(eb); + btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK); + } ret = find_extent_in_eb(eb, bytenr, *extent_item_pos, &eie); - btrfs_tree_read_unlock_blocking(eb); + if (!path->skip_locking) + btrfs_tree_read_unlock_blocking(eb); free_extent_buffer(eb); if (ret < 0) goto out; @@ -1452,8 +1459,8 @@ 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. */ @@ -1476,13 +1483,16 @@ 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 { @@ -1515,6 +1525,7 @@ 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; @@ -1903,13 +1914,19 @@ 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, @@ -1941,7 +1958,7 @@ 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/disk-io.c b/fs/btrfs/disk-io.c index e0bdc0c902e4..813834552aa1 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1688,9 +1688,8 @@ static int cleaner_kthread(void *arg) struct btrfs_root *root = arg; struct btrfs_fs_info *fs_info = root->fs_info; int again; - struct btrfs_trans_handle *trans; - do { + while (1) { again = 0; /* Make the cleaner go to sleep early. */ @@ -1739,42 +1738,16 @@ static int cleaner_kthread(void *arg) */ btrfs_delete_unused_bgs(fs_info); sleep: + if (kthread_should_park()) + kthread_parkme(); + if (kthread_should_stop()) + return 0; if (!again) { set_current_state(TASK_INTERRUPTIBLE); - if (!kthread_should_stop()) - schedule(); + schedule(); __set_current_state(TASK_RUNNING); } - } while (!kthread_should_stop()); - - /* - * Transaction kthread is stopped before us and wakes us up. - * However we might have started a new transaction and COWed some - * tree blocks when deleting unused block groups for example. So - * make sure we commit the transaction we started to have a clean - * shutdown when evicting the btree inode - if it has dirty pages - * when we do the final iput() on it, eviction will trigger a - * writeback for it which will fail with null pointer dereferences - * since work queues and other resources were already released and - * destroyed by the time the iput/eviction/writeback is made. - */ - trans = btrfs_attach_transaction(root); - if (IS_ERR(trans)) { - if (PTR_ERR(trans) != -ENOENT) - btrfs_err(fs_info, - "cleaner transaction attach returned %ld", - PTR_ERR(trans)); - } else { - int ret; - - ret = btrfs_commit_transaction(trans); - if (ret) - btrfs_err(fs_info, - "cleaner open transaction commit returned %d", - ret); } - - return 0; } static int transaction_kthread(void *arg) @@ -3713,6 +3686,13 @@ void close_ctree(struct btrfs_fs_info *fs_info) int ret; set_bit(BTRFS_FS_CLOSING_START, &fs_info->flags); + /* + * We don't want the cleaner to start new transactions, add more delayed + * iputs, etc. while we're closing. We can't use kthread_stop() yet + * because that frees the task_struct, and the transaction kthread might + * still try to wake up the cleaner. + */ + kthread_park(fs_info->cleaner_kthread); /* wait for the qgroup rescan worker to stop */ btrfs_qgroup_wait_for_completion(fs_info, false); @@ -3740,9 +3720,8 @@ void close_ctree(struct btrfs_fs_info *fs_info) if (!sb_rdonly(fs_info->sb)) { /* - * If the cleaner thread is stopped and there are - * block groups queued for removal, the deletion will be - * skipped when we quit the cleaner thread. + * The cleaner kthread is stopped, so do one final pass over + * unused block groups. */ btrfs_delete_unused_bgs(fs_info); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 83791d13c204..49766721b2b1 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4087,8 +4087,7 @@ static int create_space_info(struct btrfs_fs_info *info, u64 flags, info->space_info_kobj, "%s", alloc_name(space_info->flags)); if (ret) { - percpu_counter_destroy(&space_info->total_bytes_pinned); - kfree(space_info); + kobject_put(&space_info->kobj); return ret; } diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 57e25e83b81a..97958ecaeed9 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2059,6 +2059,18 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) u64 len; /* + * If the inode needs a full sync, make sure we use a full range to + * avoid log tree corruption, due to hole detection racing with ordered + * extent completion for adjacent ranges, and assertion failures during + * hole detection. + */ + if (test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, + &BTRFS_I(inode)->runtime_flags)) { + start = 0; + end = LLONG_MAX; + } + + /* * The range length can be represented by u64, we have to do the typecasts * to avoid signed overflow if it's [0, LLONG_MAX] eg. from fsync() */ @@ -2964,6 +2976,7 @@ static long btrfs_fallocate(struct file *file, int mode, ret = btrfs_qgroup_reserve_data(inode, &data_reserved, cur_offset, last_byte - cur_offset); if (ret < 0) { + cur_offset = last_byte; free_extent_map(em); break; } @@ -3034,7 +3047,7 @@ out: /* Let go of our reservation. */ if (ret != 0) btrfs_free_reserved_data_space(inode, data_reserved, - alloc_start, alloc_end - cur_offset); + cur_offset, alloc_end - cur_offset); extent_changeset_free(data_reserved); return ret; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 7e288510fd2c..ea7b65c025c2 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -6580,8 +6580,18 @@ int btrfs_add_link(struct btrfs_trans_handle *trans, btrfs_i_size_write(parent_inode, parent_inode->vfs_inode.i_size + name_len * 2); inode_inc_iversion(&parent_inode->vfs_inode); - parent_inode->vfs_inode.i_mtime = parent_inode->vfs_inode.i_ctime = - current_time(&parent_inode->vfs_inode); + /* + * If we are replaying a log tree, we do not want to update the mtime + * and ctime of the parent directory with the current time, since the + * log replay procedure is responsible for setting them to their correct + * values (the ones it had when the fsync was done). + */ + if (!test_bit(BTRFS_FS_LOG_RECOVERING, &root->fs_info->flags)) { + struct timespec now = current_time(&parent_inode->vfs_inode); + + parent_inode->vfs_inode.i_mtime = now; + parent_inode->vfs_inode.i_ctime = now; + } ret = btrfs_update_inode(trans, root, &parent_inode->vfs_inode); if (ret) btrfs_abort_transaction(trans, ret); diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 5feb8b03ffe8..9fa6db6a6f7d 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -4403,27 +4403,36 @@ int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start) mutex_lock(&fs_info->cleaner_mutex); ret = relocate_block_group(rc); mutex_unlock(&fs_info->cleaner_mutex); - if (ret < 0) { + if (ret < 0) err = ret; - goto out; - } - - if (rc->extents_found == 0) - break; - - btrfs_info(fs_info, "found %llu extents", rc->extents_found); + /* + * We may have gotten ENOSPC after we already dirtied some + * extents. If writeout happens while we're relocating a + * different block group we could end up hitting the + * BUG_ON(rc->stage == UPDATE_DATA_PTRS) in + * btrfs_reloc_cow_block. Make sure we write everything out + * properly so we don't trip over this problem, and then break + * out of the loop if we hit an error. + */ if (rc->stage == MOVE_DATA_EXTENTS && rc->found_file_extent) { ret = btrfs_wait_ordered_range(rc->data_inode, 0, (u64)-1); - if (ret) { + if (ret) err = ret; - goto out; - } invalidate_mapping_pages(rc->data_inode->i_mapping, 0, -1); rc->stage = UPDATE_DATA_PTRS; } + + if (err < 0) + goto out; + + if (rc->extents_found == 0) + break; + + btrfs_info(fs_info, "found %llu extents", rc->extents_found); + } WARN_ON(rc->block_group->pinned > 0); diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index 95bcc3cce78f..7bae7cff150e 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -145,16 +145,17 @@ int btrfs_update_root(struct btrfs_trans_handle *trans, struct btrfs_root return -ENOMEM; ret = btrfs_search_slot(trans, root, key, path, 0, 1); - if (ret < 0) { - btrfs_abort_transaction(trans, ret); + if (ret < 0) goto out; - } - if (ret != 0) { - btrfs_print_leaf(path->nodes[0]); - btrfs_crit(fs_info, "unable to update root key %llu %u %llu", - key->objectid, key->type, key->offset); - BUG_ON(1); + if (ret > 0) { + btrfs_crit(fs_info, + "unable to find root key (%llu %u %llu) in tree %llu", + key->objectid, key->type, key->offset, + root->root_key.objectid); + ret = -EUCLEAN; + btrfs_abort_transaction(trans, ret); + goto out; } l = path->nodes[0]; diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 3f22af96d63b..14c4062a6e58 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -5013,6 +5013,12 @@ static int send_hole(struct send_ctx *sctx, u64 end) u64 len; int ret = 0; + /* + * Don't go beyond the inode's i_size due to prealloc extents that start + * after the i_size. + */ + end = min_t(u64, end, sctx->cur_inode_size); + if (sctx->flags & BTRFS_SEND_FLAG_NO_FILE_DATA) return send_update_extent(sctx, offset, end - offset); diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index 883881b16c86..f05341bda1d1 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -794,7 +794,12 @@ int btrfs_sysfs_add_fsid(struct btrfs_fs_devices *fs_devs, fs_devs->fsid_kobj.kset = btrfs_kset; error = kobject_init_and_add(&fs_devs->fsid_kobj, &btrfs_ktype, parent, "%pU", fs_devs->fsid); - return error; + if (error) { + kobject_put(&fs_devs->fsid_kobj); + return error; + } + + return 0; } int btrfs_sysfs_add_mounted(struct btrfs_fs_info *fs_info) diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 9d72882b0f72..8ac6a64d0422 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -2907,6 +2907,12 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, log->log_transid = root->log_transid; root->log_start_pid = 0; /* + * Update or create log root item under the root's log_mutex to prevent + * races with concurrent log syncs that can lead to failure to update + * log root item because it was not created yet. + */ + ret = update_log_root(trans, log); + /* * IO has been started, blocks of the log tree have WRITTEN flag set * in their headers. new modifications of the log will be written to * new positions. so it's safe to allow log writers to go in. @@ -2925,8 +2931,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, mutex_unlock(&log_root_tree->log_mutex); - ret = update_log_root(trans, log); - mutex_lock(&log_root_tree->log_mutex); if (atomic_dec_and_test(&log_root_tree->log_writers)) { /* @@ -4012,6 +4016,7 @@ fill_holes: *last_extent, 0, 0, len, 0, len, 0, 0, 0); + *last_extent += len; } } } @@ -5327,7 +5332,6 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans, { int ret = 0; struct dentry *old_parent = NULL; - struct btrfs_inode *orig_inode = inode; /* * for regular files, if its inode is already on disk, we don't @@ -5347,16 +5351,6 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans, } while (1) { - /* - * If we are logging a directory then we start with our inode, - * not our parent's inode, so we need to skip setting the - * logged_trans so that further down in the log code we don't - * think this inode has already been logged. - */ - if (inode != orig_inode) - inode->logged_trans = trans->transid; - smp_mb(); - if (btrfs_must_commit_transaction(trans, inode)) { ret = 1; break; @@ -6086,7 +6080,6 @@ void btrfs_record_unlink_dir(struct btrfs_trans_handle *trans, * if this directory was already logged any new * names for this file/dir will get recorded */ - smp_mb(); if (dir->logged_trans == trans->transid) return; diff --git a/fs/ceph/super.c b/fs/ceph/super.c index b79b1211a2b5..f0694293b31a 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -768,6 +768,12 @@ 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, @@ -775,6 +781,7 @@ 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/char_dev.c b/fs/char_dev.c index a65e4a56318c..20ce45c7c57c 100644 --- a/fs/char_dev.c +++ b/fs/char_dev.c @@ -159,6 +159,12 @@ __register_chrdev_region(unsigned int major, unsigned int baseminor, ret = -EBUSY; goto out; } + + if (new_min < old_min && new_max > old_max) { + ret = -EBUSY; + goto out; + } + } cd->next = *cp; diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 48ea9dfd5f02..6ee8f9270892 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -2984,7 +2984,9 @@ cifs_read_allocate_pages(struct cifs_readdata *rdata, unsigned int nr_pages) } if (rc) { - for (i = 0; i < nr_pages; i++) { + unsigned int nr_page_failed = i; + + for (i = 0; i < nr_page_failed; i++) { put_page(rdata->pages[i]); rdata->pages[i] = NULL; } diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 418062c7f040..23326b0cd562 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -1969,26 +1969,28 @@ 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); } diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index d2a1a79fa324..d7955dc56737 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -1755,12 +1755,19 @@ int configfs_register_group(struct config_group *parent_group, inode_lock_nested(d_inode(parent), I_MUTEX_PARENT); ret = create_default_group(parent_group, group); - if (!ret) { - spin_lock(&configfs_dirent_lock); - configfs_dir_set_ready(group->cg_item.ci_dentry->d_fsdata); - spin_unlock(&configfs_dirent_lock); - } + if (ret) + goto err_out; + + spin_lock(&configfs_dirent_lock); + configfs_dir_set_ready(group->cg_item.ci_dentry->d_fsdata); + spin_unlock(&configfs_dirent_lock); + inode_unlock(d_inode(parent)); + return 0; +err_out: inode_unlock(d_inode(parent)); + mutex_lock(&subsys->su_mutex); + unlink_group(group); + mutex_unlock(&subsys->su_mutex); return ret; } EXPORT_SYMBOL(configfs_register_group); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 5592b7726241..01f44364c547 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -1047,6 +1047,7 @@ 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 */ @@ -1138,6 +1139,10 @@ 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); @@ -1217,6 +1222,11 @@ 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); @@ -1282,6 +1292,7 @@ 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)) @@ -1307,9 +1318,11 @@ 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 1913c69498c1..44966b272216 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -262,6 +262,13 @@ 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 5eb28dcaa0f0..862766a1b080 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5450,7 +5450,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) up_write(&EXT4_I(inode)->i_data_sem); ext4_journal_stop(handle); if (error) { - if (orphan) + if (orphan && inode->i_nlink) ext4_orphan_del(NULL, inode); goto err_out; } @@ -5818,7 +5818,7 @@ 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 3dbf4e414706..d2efc0cb8f31 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -918,7 +918,7 @@ group_add_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 1792999eec91..3ba9a4ae4eac 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -1555,7 +1555,7 @@ 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 4e301b0cdfb5..070660cb5b91 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -870,12 +870,15 @@ 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 333fba05e1a5..4f7cd78d0364 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -849,6 +849,7 @@ 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 d0049064f62f..61d07608577e 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -3454,6 +3454,37 @@ 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; @@ -4178,7 +4209,7 @@ 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; @@ -4320,30 +4351,7 @@ no_journal: if (ext4_setup_super(sb, es, sb_rdonly(sb))) sb->s_flags |= MS_RDONLY; - /* 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); @@ -5128,6 +5136,8 @@ 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 6761e905cab0..f2fde3ac8698 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1698,7 +1698,7 @@ 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/f2fs/data.c b/fs/f2fs/data.c index 3d37124eb63e..113d1cd55119 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -133,12 +133,14 @@ struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi, struct block_device *bdev = sbi->sb->s_bdev; int i; - for (i = 0; i < sbi->s_ndevs; i++) { - if (FDEV(i).start_blk <= blk_addr && - FDEV(i).end_blk >= blk_addr) { - blk_addr -= FDEV(i).start_blk; - bdev = FDEV(i).bdev; - break; + if (f2fs_is_multi_device(sbi)) { + for (i = 0; i < sbi->s_ndevs; i++) { + if (FDEV(i).start_blk <= blk_addr && + FDEV(i).end_blk >= blk_addr) { + blk_addr -= FDEV(i).start_blk; + bdev = FDEV(i).bdev; + break; + } } } if (bio) { @@ -152,6 +154,9 @@ int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr) { int i; + if (!f2fs_is_multi_device(sbi)) + return 0; + for (i = 0; i < sbi->s_ndevs; i++) if (FDEV(i).start_blk <= blkaddr && FDEV(i).end_blk >= blkaddr) return i; diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 634165fb64f1..6caae471c1a4 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1167,6 +1167,17 @@ static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type) } #endif +/* + * Test if the mounted volume is a multi-device volume. + * - For a single regular disk volume, sbi->s_ndevs is 0. + * - For a single zoned disk volume, sbi->s_ndevs is 1. + * - For a multi-device volume, sbi->s_ndevs is always 2 or more. + */ +static inline bool f2fs_is_multi_device(struct f2fs_sb_info *sbi) +{ + return sbi->s_ndevs > 1; +} + /* For write statistics. Suppose sector size is 512 bytes, * and the return value is in kbytes. s is of struct f2fs_sb_info. */ @@ -1539,6 +1550,7 @@ enospc: return -ENOSPC; } +void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...); static inline void dec_valid_block_count(struct f2fs_sb_info *sbi, struct inode *inode, block_t count) @@ -1547,9 +1559,17 @@ static inline void dec_valid_block_count(struct f2fs_sb_info *sbi, spin_lock(&sbi->stat_lock); f2fs_bug_on(sbi, sbi->total_valid_block_count < (block_t) count); - f2fs_bug_on(sbi, inode->i_blocks < sectors); sbi->total_valid_block_count -= (block_t)count; spin_unlock(&sbi->stat_lock); + if (unlikely(inode->i_blocks < sectors)) { + f2fs_msg(sbi->sb, KERN_WARNING, + "Inconsistent i_blocks, ino:%lu, iblocks:%llu, sectors:%llu", + inode->i_ino, + (unsigned long long)inode->i_blocks, + (unsigned long long)sectors); + set_sbi_flag(sbi, SBI_NEED_FSCK); + return; + } f2fs_i_blocks_write(inode, count, false, true); } @@ -2371,7 +2391,6 @@ static inline void f2fs_update_iostat(struct f2fs_sb_info *sbi, bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type); -void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...); static inline void verify_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type) { diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 5f549bc4e097..1b1792199445 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -2407,7 +2407,7 @@ static int f2fs_ioc_flush_device(struct file *filp, unsigned long arg) sizeof(range))) return -EFAULT; - if (sbi->s_ndevs <= 1 || sbi->s_ndevs - 1 <= range.dev_num || + if (!f2fs_is_multi_device(sbi) || sbi->s_ndevs - 1 <= range.dev_num || sbi->segs_per_sec != 1) { f2fs_msg(sbi->sb, KERN_WARNING, "Can't flush %u in %d for segs_per_sec %u != 1\n", diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index f22884418e92..ceb6023786bd 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -1111,7 +1111,7 @@ void build_gc_manager(struct f2fs_sb_info *sbi) BLKS_PER_SEC(sbi), (main_count - resv_count)); /* give warm/cold data area from slower device */ - if (sbi->s_ndevs && sbi->segs_per_sec == 1) + if (f2fs_is_multi_device(sbi) && sbi->segs_per_sec == 1) SIT_I(sbi)->last_victim[ALLOC_NEXT] = GET_SEGNO(sbi, FDEV(0).end_blk) + 1; } diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 50818b519df8..e02ed16bc35c 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -397,6 +397,7 @@ make_now: return inode; bad_inode: + f2fs_inode_synced(inode); iget_failed(inode); trace_f2fs_iget_exit(inode, ret); return ERR_PTR(ret); diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index 6ea445377767..65a82c5bafcb 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -445,7 +445,15 @@ retry_dn: get_node_info(sbi, dn.nid, &ni); f2fs_bug_on(sbi, ni.ino != ino_of_node(page)); - f2fs_bug_on(sbi, ofs_of_node(dn.node_page) != ofs_of_node(page)); + + if (ofs_of_node(dn.node_page) != ofs_of_node(page)) { + f2fs_msg(sbi->sb, KERN_WARNING, + "Inconsistent ofs_of_node, ino:%lu, ofs:%u, %u", + inode->i_ino, ofs_of_node(dn.node_page), + ofs_of_node(page)); + err = -EFAULT; + goto err; + } for (; start < end; start++, dn.ofs_in_node++) { block_t src, dest; diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 5c698757e116..70bd15cadb44 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -495,7 +495,7 @@ static int submit_flush_wait(struct f2fs_sb_info *sbi) int ret = __submit_flush_wait(sbi, sbi->sb->s_bdev); int i; - if (!sbi->s_ndevs || ret) + if (!f2fs_is_multi_device(sbi) || ret) return ret; for (i = 1; i < sbi->s_ndevs; i++) { @@ -1050,7 +1050,7 @@ static int __queue_discard_cmd(struct f2fs_sb_info *sbi, trace_f2fs_queue_discard(bdev, blkstart, blklen); - if (sbi->s_ndevs) { + if (f2fs_is_multi_device(sbi)) { int devi = f2fs_target_device_index(sbi, blkstart); blkstart -= FDEV(devi).start_blk; @@ -1283,7 +1283,7 @@ static int __f2fs_issue_discard_zone(struct f2fs_sb_info *sbi, block_t lblkstart = blkstart; int devi = 0; - if (sbi->s_ndevs) { + if (f2fs_is_multi_device(sbi)) { devi = f2fs_target_device_index(sbi, blkstart); blkstart -= FDEV(devi).start_blk; } diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index 47348d98165b..e3d8826c5113 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -641,7 +641,6 @@ static inline void verify_block_addr(struct f2fs_io_info *fio, block_t blk_addr) static inline int check_block_count(struct f2fs_sb_info *sbi, int segno, struct f2fs_sit_entry *raw_sit) { -#ifdef CONFIG_F2FS_CHECK_FS bool is_valid = test_bit_le(0, raw_sit->valid_map) ? true : false; int valid_blocks = 0; int cur_pos = 0, next_pos; @@ -668,7 +667,7 @@ static inline int check_block_count(struct f2fs_sb_info *sbi, set_sbi_flag(sbi, SBI_NEED_FSCK); return -EINVAL; } -#endif + /* check segment usage, and check boundary of a given segment number */ if (unlikely(GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg || segno > TOTAL_SEGS(sbi) - 1)) { diff --git a/fs/fat/file.c b/fs/fat/file.c index 4724cc9ad650..62581de09bf1 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -160,12 +160,17 @@ static int fat_file_release(struct inode *inode, struct file *filp) int fat_file_fsync(struct file *filp, loff_t start, loff_t end, int datasync) { struct inode *inode = filp->f_mapping->host; - int res, err; + int err; + + err = __generic_file_fsync(filp, start, end, datasync); + if (err) + return err; - res = generic_file_fsync(filp, start, end, datasync); err = sync_mapping_buffers(MSDOS_SB(inode->i_sb)->fat_inode->i_mapping); + if (err) + return err; - return res ? res : err; + return blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL); } diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 6a76616c9401..4d561ee08d05 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -530,8 +530,6 @@ 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 mapping's @@ -539,6 +537,9 @@ 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: @@ -908,7 +909,11 @@ 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/dev.c b/fs/fuse/dev.c index 770733106d6d..f580695b7bb9 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -133,9 +133,13 @@ static bool fuse_block_alloc(struct fuse_conn *fc, bool for_background) static void fuse_drop_waiting(struct fuse_conn *fc) { - if (fc->connected) { - atomic_dec(&fc->num_waiting); - } else if (atomic_dec_and_test(&fc->num_waiting)) { + /* + * lockess check of fc->connected is okay, because atomic_dec_and_test() + * provides a memory barrier mached with the one in fuse_wait_aborted() + * to ensure no wake-up is missed. + */ + if (atomic_dec_and_test(&fc->num_waiting) && + !READ_ONCE(fc->connected)) { /* wake up aborters */ wake_up_all(&fc->blocked_waitq); } @@ -1674,7 +1678,7 @@ static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode, offset = outarg->offset & ~PAGE_MASK; file_size = i_size_read(inode); - num = outarg->size; + num = min(outarg->size, fc->max_write); if (outarg->offset > file_size) num = 0; else if (outarg->offset + num > file_size) @@ -2170,6 +2174,8 @@ EXPORT_SYMBOL_GPL(fuse_abort_conn); void fuse_wait_aborted(struct fuse_conn *fc) { + /* matches implicit memory barrier in fuse_drop_waiting() */ + smp_mb(); wait_event(fc->blocked_waitq, atomic_read(&fc->num_waiting) == 0); } diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 19ea122a7d03..e340449ca862 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -178,7 +178,9 @@ 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); @@ -1525,7 +1527,7 @@ __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)) { @@ -2974,6 +2976,13 @@ 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) + goto out; + } + if (!(mode & FALLOC_FL_KEEP_SIZE)) set_bit(FUSE_I_SIZE_UNSTABLE, &fi->state); diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index d5284d0dbdb5..aea1ed0aebd0 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -140,6 +140,7 @@ void gfs2_glock_free(struct gfs2_glock *gl) { struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; + BUG_ON(atomic_read(&gl->gl_revokes)); rhashtable_remove_fast(&gl_hash_table, &gl->gl_node, ht_parms); smp_mb(); wake_up_glock(gl); @@ -183,15 +184,19 @@ static int demote_ok(const struct gfs2_glock *gl) void gfs2_glock_add_to_lru(struct gfs2_glock *gl) { + if (!(gl->gl_ops->go_flags & GLOF_LRU)) + return; + spin_lock(&lru_lock); - if (!list_empty(&gl->gl_lru)) - list_del_init(&gl->gl_lru); - else + list_del(&gl->gl_lru); + list_add_tail(&gl->gl_lru, &lru_list); + + if (!test_bit(GLF_LRU, &gl->gl_flags)) { + set_bit(GLF_LRU, &gl->gl_flags); atomic_inc(&lru_count); + } - list_add_tail(&gl->gl_lru, &lru_list); - set_bit(GLF_LRU, &gl->gl_flags); spin_unlock(&lru_lock); } @@ -201,7 +206,7 @@ static void gfs2_glock_remove_from_lru(struct gfs2_glock *gl) return; spin_lock(&lru_lock); - if (!list_empty(&gl->gl_lru)) { + if (test_bit(GLF_LRU, &gl->gl_flags)) { list_del_init(&gl->gl_lru); atomic_dec(&lru_count); clear_bit(GLF_LRU, &gl->gl_flags); @@ -1158,8 +1163,7 @@ void gfs2_glock_dq(struct gfs2_holder *gh) !test_bit(GLF_DEMOTE, &gl->gl_flags)) fast_path = 1; } - if (!test_bit(GLF_LFLUSH, &gl->gl_flags) && demote_ok(gl) && - (glops->go_flags & GLOF_LRU)) + if (!test_bit(GLF_LFLUSH, &gl->gl_flags) && demote_ok(gl)) gfs2_glock_add_to_lru(gl); trace_gfs2_glock_queue(gh, 0); @@ -1454,6 +1458,7 @@ __acquires(&lru_lock) if (!spin_trylock(&gl->gl_lockref.lock)) { add_back_to_lru: list_add(&gl->gl_lru, &lru_list); + set_bit(GLF_LRU, &gl->gl_flags); atomic_inc(&lru_count); continue; } @@ -1461,7 +1466,6 @@ add_back_to_lru: spin_unlock(&gl->gl_lockref.lock); goto add_back_to_lru; } - clear_bit(GLF_LRU, &gl->gl_flags); gl->gl_lockref.count++; if (demote_ok(gl)) handle_callback(gl, LM_ST_UNLOCKED, 0, false); @@ -1496,6 +1500,7 @@ static long gfs2_scan_glock_lru(int nr) if (!test_bit(GLF_LOCK, &gl->gl_flags)) { list_move(&gl->gl_lru, &dispose); atomic_dec(&lru_count); + clear_bit(GLF_LRU, &gl->gl_flags); freed++; continue; } diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c index 65f33a0ac190..6f5c033fe4b5 100644 --- a/fs/gfs2/lock_dlm.c +++ b/fs/gfs2/lock_dlm.c @@ -31,9 +31,10 @@ * @delta is the difference between the current rtt sample and the * running average srtt. We add 1/8 of that to the srtt in order to * update the current srtt estimate. The variance estimate is a bit - * more complicated. We subtract the abs value of the @delta from - * the current variance estimate and add 1/4 of that to the running - * total. + * more complicated. We subtract the current variance estimate from + * the abs value of the @delta and add 1/4 of that to the running + * total. That's equivalent to 3/4 of the current variance + * estimate plus 1/4 of the abs of @delta. * * Note that the index points at the array entry containing the smoothed * mean value, and the variance is always in the following entry @@ -49,7 +50,7 @@ static inline void gfs2_update_stats(struct gfs2_lkstats *s, unsigned index, s64 delta = sample - s->stats[index]; s->stats[index] += (delta >> 3); index++; - s->stats[index] += ((abs(delta) - s->stats[index]) >> 2); + s->stats[index] += (s64)(abs(delta) - s->stats[index]) >> 2; } /** diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index f72c44231406..483b82e2be92 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -588,7 +588,8 @@ void gfs2_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd) bd->bd_bh = NULL; bd->bd_ops = &gfs2_revoke_lops; sdp->sd_log_num_revoke++; - atomic_inc(&gl->gl_revokes); + if (atomic_inc_return(&gl->gl_revokes) == 1) + gfs2_glock_hold(gl); set_bit(GLF_LFLUSH, &gl->gl_flags); list_add(&bd->bd_list, &sdp->sd_log_le_revoke); } diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index c8ff7b7954f0..049f8c6721b4 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -660,8 +660,10 @@ static void revoke_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr) bd = list_entry(head->next, struct gfs2_bufdata, bd_list); list_del_init(&bd->bd_list); gl = bd->bd_gl; - atomic_dec(&gl->gl_revokes); - clear_bit(GLF_LFLUSH, &gl->gl_flags); + if (atomic_dec_return(&gl->gl_revokes) == 0) { + clear_bit(GLF_LFLUSH, &gl->gl_flags); + gfs2_glock_queue_put(gl); + } kmem_cache_free(gfs2_bufdata_cachep, bd); } } diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index dd28a9b287da..ba54a0e12bbd 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -436,9 +436,7 @@ 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]); /* @@ -557,7 +555,6 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, struct address_space *mapping = inode->i_mapping; struct hstate *h = hstate_inode(inode); struct vm_area_struct pseudo_vma; - struct mm_struct *mm = current->mm; loff_t hpage_size = huge_page_size(h); unsigned long hpage_shift = huge_page_shift(h); pgoff_t start, index, end; @@ -621,8 +618,7 @@ 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 0c8f77db60e2..593f3e31fb21 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1353,6 +1353,10 @@ 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); diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 89d1dc19340b..9e9117533fd7 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -649,11 +649,10 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root, kn->id.generation = gen; /* - * set ino first. This barrier is paired with atomic_inc_not_zero in + * set ino first. This RELEASE is paired with atomic_inc_not_zero in * kernfs_find_and_get_node_by_ino */ - smp_mb__before_atomic(); - atomic_set(&kn->count, 1); + atomic_set_release(&kn->count, 1); atomic_set(&kn->active, KN_DEACTIVATED_BIAS); RB_CLEAR_NODE(&kn->rb); diff --git a/fs/lockd/xdr.c b/fs/lockd/xdr.c index 9846f7e95282..7147e4aebecc 100644 --- a/fs/lockd/xdr.c +++ b/fs/lockd/xdr.c @@ -127,7 +127,7 @@ nlm_decode_lock(__be32 *p, struct nlm_lock *lock) locks_init_lock(fl); fl->fl_owner = current->files; - fl->fl_pid = current->tgid; + fl->fl_pid = (pid_t)lock->svid; fl->fl_flags = FL_POSIX; fl->fl_type = F_RDLCK; /* as good as anything else */ start = ntohl(*p++); @@ -269,7 +269,7 @@ nlmsvc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p) memset(lock, 0, sizeof(*lock)); locks_init_lock(&lock->fl); lock->svid = ~(u32) 0; - lock->fl.fl_pid = current->tgid; + lock->fl.fl_pid = (pid_t)lock->svid; if (!(p = nlm_decode_cookie(p, &argp->cookie)) || !(p = xdr_decode_string_inplace(p, &lock->caller, diff --git a/fs/lockd/xdr4.c b/fs/lockd/xdr4.c index 70154f376695..7ed9edf9aed4 100644 --- a/fs/lockd/xdr4.c +++ b/fs/lockd/xdr4.c @@ -119,7 +119,7 @@ nlm4_decode_lock(__be32 *p, struct nlm_lock *lock) locks_init_lock(fl); fl->fl_owner = current->files; - fl->fl_pid = current->tgid; + fl->fl_pid = (pid_t)lock->svid; fl->fl_flags = FL_POSIX; fl->fl_type = F_RDLCK; /* as good as anything else */ p = xdr_decode_hyper(p, &start); @@ -266,7 +266,7 @@ nlm4svc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p) memset(lock, 0, sizeof(*lock)); locks_init_lock(&lock->fl); lock->svid = ~(u32) 0; - lock->fl.fl_pid = current->tgid; + lock->fl.fl_pid = (pid_t)lock->svid; if (!(p = nlm4_decode_cookie(p, &argp->cookie)) || !(p = xdr_decode_string_inplace(p, &lock->caller, diff --git a/fs/nfs/client.c b/fs/nfs/client.c index a98d64a6eda5..0c7008fb6d5a 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -290,6 +290,7 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat struct nfs_client *clp; const struct sockaddr *sap = data->addr; struct nfs_net *nn = net_generic(data->net, nfs_net_id); + int error; again: list_for_each_entry(clp, &nn->nfs_client_list, cl_share_link) { @@ -302,9 +303,11 @@ again: if (clp->cl_cons_state > NFS_CS_READY) { atomic_inc(&clp->cl_count); spin_unlock(&nn->nfs_client_lock); - nfs_wait_client_init_complete(clp); + error = nfs_wait_client_init_complete(clp); nfs_put_client(clp); spin_lock(&nn->nfs_client_lock); + if (error < 0) + return ERR_PTR(error); goto again; } @@ -413,6 +416,8 @@ struct nfs_client *nfs_get_client(const struct nfs_client_initdata *cl_init) clp = nfs_match_client(cl_init); if (clp) { spin_unlock(&nn->nfs_client_lock); + if (IS_ERR(clp)) + return clp; if (new) new->rpc_ops->free_client(new); return nfs_found_client(cl_init, clp); diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index 3db2b7464748..03da4e0b0098 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 e1d88bca815e..85ec07e4aa91 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -143,6 +143,10 @@ 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/nfsd/vfs.h b/fs/nfsd/vfs.h index be6d8e00453f..85f544007311 100644 --- a/fs/nfsd/vfs.h +++ b/fs/nfsd/vfs.h @@ -117,8 +117,11 @@ void nfsd_put_raparams(struct file *file, struct raparms *ra); static inline int fh_want_write(struct svc_fh *fh) { - int ret = mnt_want_write(fh->fh_export->ex_path.mnt); + int ret; + if (fh->fh_want_write) + return 0; + ret = mnt_want_write(fh->fh_export->ex_path.mnt); if (!ret) fh->fh_want_write = true; return ret; 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/open.c b/fs/open.c index 28a3956c4479..f4ea0dc88823 100644 --- a/fs/open.c +++ b/fs/open.c @@ -1212,3 +1212,21 @@ int nonseekable_open(struct inode *inode, struct file *filp) } EXPORT_SYMBOL(nonseekable_open); + +/* + * stream_open is used by subsystems that want stream-like file descriptors. + * Such file descriptors are not seekable and don't have notion of position + * (file.f_pos is always 0). Contrary to file descriptors of other regular + * files, .read() and .write() can run simultaneously. + * + * stream_open never fails and is marked to return int so that it could be + * directly used as file_operations.open . + */ +int stream_open(struct inode *inode, struct file *filp) +{ + filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE | FMODE_ATOMIC_POS); + filp->f_mode |= FMODE_STREAM; + return 0; +} + +EXPORT_SYMBOL(stream_open); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 309d24118f9a..755149cfcf23 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -758,7 +758,7 @@ static int show_smap(struct seq_file *m, void *v, int is_pid) }; int ret = 0; bool rollup_mode; - bool last_vma; + bool last_vma = true; if (priv->rollup) { rollup_mode = true; diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index 2b21d180157c..8af9efa0ca0a 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -129,26 +129,27 @@ static const char *get_reason_str(enum kmsg_dump_reason reason) } } -bool pstore_cannot_block_path(enum kmsg_dump_reason reason) +/* + * Should pstore_dump() wait for a concurrent pstore_dump()? If + * not, the current pstore_dump() will report a failure to dump + * and return. + */ +static bool pstore_cannot_wait(enum kmsg_dump_reason reason) { - /* - * In case of NMI path, pstore shouldn't be blocked - * regardless of reason. - */ + /* In NMI path, pstore shouldn't block regardless of reason. */ if (in_nmi()) return true; switch (reason) { /* In panic case, other cpus are stopped by smp_send_stop(). */ case KMSG_DUMP_PANIC: - /* Emergency restart shouldn't be blocked by spin lock. */ + /* Emergency restart shouldn't be blocked. */ case KMSG_DUMP_EMERG: return true; default: return false; } } -EXPORT_SYMBOL_GPL(pstore_cannot_block_path); #ifdef CONFIG_PSTORE_ZLIB_COMPRESS /* Derived from logfs_compress() */ @@ -499,23 +500,23 @@ static void pstore_dump(struct kmsg_dumper *dumper, unsigned long total = 0; const char *why; unsigned int part = 1; - unsigned long flags = 0; - int is_locked; int ret; why = get_reason_str(reason); - if (pstore_cannot_block_path(reason)) { - is_locked = spin_trylock_irqsave(&psinfo->buf_lock, flags); - if (!is_locked) { - pr_err("pstore dump routine blocked in %s path, may corrupt error record\n" - , in_nmi() ? "NMI" : why); + if (down_trylock(&psinfo->buf_lock)) { + /* Failed to acquire lock: give up if we cannot wait. */ + if (pstore_cannot_wait(reason)) { + pr_err("dump skipped in %s path: may corrupt error record\n", + in_nmi() ? "NMI" : why); + return; + } + if (down_interruptible(&psinfo->buf_lock)) { + pr_err("could not grab semaphore?!\n"); return; } - } else { - spin_lock_irqsave(&psinfo->buf_lock, flags); - is_locked = 1; } + oopscount++; while (total < kmsg_bytes) { char *dst; @@ -532,7 +533,7 @@ static void pstore_dump(struct kmsg_dumper *dumper, record.part = part; record.buf = psinfo->buf; - if (big_oops_buf && is_locked) { + if (big_oops_buf) { dst = big_oops_buf; dst_size = big_oops_buf_sz; } else { @@ -550,7 +551,7 @@ static void pstore_dump(struct kmsg_dumper *dumper, dst_size, &dump_size)) break; - if (big_oops_buf && is_locked) { + if (big_oops_buf) { zipped_len = pstore_compress(dst, psinfo->buf, header_size + dump_size, psinfo->bufsize); @@ -573,8 +574,8 @@ static void pstore_dump(struct kmsg_dumper *dumper, total += record.size; part++; } - if (is_locked) - spin_unlock_irqrestore(&psinfo->buf_lock, flags); + + up(&psinfo->buf_lock); } static struct kmsg_dumper pstore_dumper = { @@ -597,31 +598,14 @@ static void pstore_unregister_kmsg(void) #ifdef CONFIG_PSTORE_CONSOLE static void pstore_console_write(struct console *con, const char *s, unsigned c) { - const char *e = s + c; + struct pstore_record record; - while (s < e) { - struct pstore_record record; - unsigned long flags; - - pstore_record_init(&record, psinfo); - record.type = PSTORE_TYPE_CONSOLE; - - if (c > psinfo->bufsize) - c = psinfo->bufsize; + pstore_record_init(&record, psinfo); + record.type = PSTORE_TYPE_CONSOLE; - if (oops_in_progress) { - if (!spin_trylock_irqsave(&psinfo->buf_lock, flags)) - break; - } else { - spin_lock_irqsave(&psinfo->buf_lock, flags); - } - record.buf = (char *)s; - record.size = c; - psinfo->write(&record); - spin_unlock_irqrestore(&psinfo->buf_lock, flags); - s += c; - c = e - s; - } + record.buf = (char *)s; + record.size = c; + psinfo->write(&record); } static struct console pstore_console = { @@ -710,6 +694,7 @@ int pstore_register(struct pstore_info *psi) psi->write_user = pstore_write_user_compat; psinfo = psi; mutex_init(&psinfo->read_mutex); + sema_init(&psinfo->buf_lock, 1); spin_unlock(&pstore_lock); if (owner && !try_module_get(owner)) { @@ -717,7 +702,8 @@ int pstore_register(struct pstore_info *psi) return -EINVAL; } - allocate_buf_for_compression(); + if (psi->flags & PSTORE_FLAGS_DMESG) + allocate_buf_for_compression(); if (pstore_is_mounted()) pstore_get_records(0); diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index f371e03cf3bf..40bfc6c58374 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -801,27 +801,36 @@ static int ramoops_probe(struct platform_device *pdev) cxt->pstore.data = cxt; /* - * Since bufsize is only used for dmesg crash dumps, it - * must match the size of the dprz record (after PRZ header - * and ECC bytes have been accounted for). + * Prepare frontend flags based on which areas are initialized. + * For ramoops_init_przs() cases, the "max count" variable tells + * if there are regions present. For ramoops_init_prz() cases, + * the single region size is how to check. */ - cxt->pstore.bufsize = cxt->dprzs[0]->buffer_size; - cxt->pstore.buf = kzalloc(cxt->pstore.bufsize, GFP_KERNEL); - if (!cxt->pstore.buf) { - pr_err("cannot allocate pstore crash dump buffer\n"); - err = -ENOMEM; - goto fail_clear; - } - spin_lock_init(&cxt->pstore.buf_lock); - - cxt->pstore.flags = PSTORE_FLAGS_DMESG; + cxt->pstore.flags = 0; + if (cxt->max_dump_cnt) + cxt->pstore.flags |= PSTORE_FLAGS_DMESG; if (cxt->console_size) cxt->pstore.flags |= PSTORE_FLAGS_CONSOLE; - if (cxt->ftrace_size) + if (cxt->max_ftrace_cnt) cxt->pstore.flags |= PSTORE_FLAGS_FTRACE; if (cxt->pmsg_size) cxt->pstore.flags |= PSTORE_FLAGS_PMSG; + /* + * Since bufsize is only used for dmesg crash dumps, it + * must match the size of the dprz record (after PRZ header + * and ECC bytes have been accounted for). + */ + if (cxt->pstore.flags & PSTORE_FLAGS_DMESG) { + cxt->pstore.bufsize = cxt->dprzs[0]->buffer_size; + cxt->pstore.buf = kzalloc(cxt->pstore.bufsize, GFP_KERNEL); + if (!cxt->pstore.buf) { + pr_err("cannot allocate pstore crash dump buffer\n"); + err = -ENOMEM; + goto fail_clear; + } + } + err = pstore_register(&cxt->pstore); if (err) { pr_err("registering with pstore failed\n"); diff --git a/fs/read_write.c b/fs/read_write.c index 1c3eada2fe25..d6f8bfb0f794 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -555,12 +555,13 @@ ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_ static inline loff_t file_pos_read(struct file *file) { - return file->f_pos; + return file->f_mode & FMODE_STREAM ? 0 : file->f_pos; } static inline void file_pos_write(struct file *file, loff_t pos) { - file->f_pos = pos; + if ((file->f_mode & FMODE_STREAM) == 0) + file->f_pos = pos; } SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count) diff --git a/fs/ufs/util.h b/fs/ufs/util.h index 1907be6d5808..f3092d513551 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: |