diff options
Diffstat (limited to 'fs')
129 files changed, 922 insertions, 492 deletions
diff --git a/fs/9p/acl.c b/fs/9p/acl.c index 31c010372660..de59b4892bfb 100644 --- a/fs/9p/acl.c +++ b/fs/9p/acl.c @@ -320,32 +320,26 @@ static int v9fs_xattr_set_acl(struct dentry *dentry, const char *name, case ACL_TYPE_ACCESS: name = POSIX_ACL_XATTR_ACCESS; if (acl) { - umode_t mode = inode->i_mode; - retval = posix_acl_equiv_mode(acl, &mode); - if (retval < 0) + struct iattr iattr; + + retval = posix_acl_update_mode(inode, &iattr.ia_mode, &acl); + if (retval) goto err_out; - else { - struct iattr iattr; - if (retval == 0) { - /* - * ACL can be represented - * by the mode bits. So don't - * update ACL. - */ - acl = NULL; - value = NULL; - size = 0; - } - /* Updte the mode bits */ - iattr.ia_mode = ((mode & S_IALLUGO) | - (inode->i_mode & ~S_IALLUGO)); - iattr.ia_valid = ATTR_MODE; - /* FIXME should we update ctime ? - * What is the following setxattr update the - * mode ? + if (!acl) { + /* + * ACL can be represented + * by the mode bits. So don't + * update ACL. */ - v9fs_vfs_setattr_dotl(dentry, &iattr); + value = NULL; + size = 0; } + iattr.ia_valid = ATTR_MODE; + /* FIXME should we update ctime ? + * What is the following setxattr update the + * mode ? + */ + v9fs_vfs_setattr_dotl(dentry, &iattr); } break; case ACL_TYPE_DEFAULT: diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 53f1e8a21707..99c3c4ffe1d9 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -1094,7 +1094,7 @@ static int v9fs_vfs_setattr(struct dentry *dentry, struct iattr *iattr) struct p9_wstat wstat; p9_debug(P9_DEBUG_VFS, "\n"); - retval = inode_change_ok(d_inode(dentry), iattr); + retval = setattr_prepare(dentry, iattr); if (retval) return retval; diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index 4d3ecfb55fcf..ce7ab92f7e84 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -560,7 +560,7 @@ int v9fs_vfs_setattr_dotl(struct dentry *dentry, struct iattr *iattr) p9_debug(P9_DEBUG_VFS, "\n"); - retval = inode_change_ok(inode, iattr); + retval = setattr_prepare(dentry, iattr); if (retval) return retval; diff --git a/fs/adfs/inode.c b/fs/adfs/inode.c index 335055d828e4..f57baaa511aa 100644 --- a/fs/adfs/inode.c +++ b/fs/adfs/inode.c @@ -303,7 +303,7 @@ adfs_notify_change(struct dentry *dentry, struct iattr *attr) unsigned int ia_valid = attr->ia_valid; int error; - error = inode_change_ok(inode, attr); + error = setattr_prepare(dentry, attr); /* * we can't change the UID or GID of any file - diff --git a/fs/affs/inode.c b/fs/affs/inode.c index a022f4accd76..87953b94a5ae 100644 --- a/fs/affs/inode.c +++ b/fs/affs/inode.c @@ -218,7 +218,7 @@ affs_notify_change(struct dentry *dentry, struct iattr *attr) pr_debug("notify_change(%lu,0x%x)\n", inode->i_ino, attr->ia_valid); - error = inode_change_ok(inode,attr); + error = setattr_prepare(dentry, attr); if (error) goto out; diff --git a/fs/attr.c b/fs/attr.c index 6530ced19697..ee697ddc6c2e 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -17,19 +17,22 @@ #include <linux/ima.h> /** - * inode_change_ok - check if attribute changes to an inode are allowed - * @inode: inode to check + * setattr_prepare - check if attribute changes to a dentry are allowed + * @dentry: dentry to check * @attr: attributes to change * * Check if we are allowed to change the attributes contained in @attr - * in the given inode. This includes the normal unix access permission - * checks, as well as checks for rlimits and others. + * in the given dentry. This includes the normal unix access permission + * checks, as well as checks for rlimits and others. The function also clears + * SGID bit from mode if user is not allowed to set it. Also file capabilities + * and IMA extended attributes are cleared if ATTR_KILL_PRIV is set. * * Should be called as the first thing in ->setattr implementations, * possibly after taking additional locks. */ -int inode_change_ok(const struct inode *inode, struct iattr *attr) +int setattr_prepare(struct dentry *dentry, struct iattr *attr) { + struct inode *inode = d_inode(dentry); unsigned int ia_valid = attr->ia_valid; /* @@ -44,7 +47,7 @@ int inode_change_ok(const struct inode *inode, struct iattr *attr) /* If force is set do it anyway. */ if (ia_valid & ATTR_FORCE) - return 0; + goto kill_priv; /* Make sure a caller can chown. */ if ((ia_valid & ATTR_UID) && @@ -77,9 +80,19 @@ int inode_change_ok(const struct inode *inode, struct iattr *attr) return -EPERM; } +kill_priv: + /* User has permission for the change */ + if (ia_valid & ATTR_KILL_PRIV) { + int error; + + error = security_inode_killpriv(dentry); + if (error) + return error; + } + return 0; } -EXPORT_SYMBOL(inode_change_ok); +EXPORT_SYMBOL(setattr_prepare); /** * inode_newsize_ok - may this inode be truncated to a given size @@ -217,13 +230,11 @@ int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **de if (!(ia_valid & ATTR_MTIME_SET)) attr->ia_mtime = now; if (ia_valid & ATTR_KILL_PRIV) { - attr->ia_valid &= ~ATTR_KILL_PRIV; - ia_valid &= ~ATTR_KILL_PRIV; error = security_inode_need_killpriv(dentry); - if (error > 0) - error = security_inode_killpriv(dentry); - if (error) + if (error < 0) return error; + if (error == 0) + ia_valid = attr->ia_valid &= ~ATTR_KILL_PRIV; } /* diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h index 5b700ef1e59d..6196b5eaf9a5 100644 --- a/fs/autofs4/autofs_i.h +++ b/fs/autofs4/autofs_i.h @@ -79,9 +79,13 @@ struct autofs_info { }; #define AUTOFS_INF_EXPIRING (1<<0) /* dentry is in the process of expiring */ -#define AUTOFS_INF_NO_RCU (1<<1) /* the dentry is being considered +#define AUTOFS_INF_WANT_EXPIRE (1<<1) /* the dentry is being considered * for expiry, so RCU_walk is - * not permitted + * not permitted. If it progresses to + * actual expiry attempt, the flag is + * not cleared when EXPIRING is set - + * in that case it gets cleared only + * when it comes to clearing EXPIRING. */ #define AUTOFS_INF_PENDING (1<<2) /* dentry pending mount */ diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c index 1cebc3c52fa5..7a5a598a2d94 100644 --- a/fs/autofs4/expire.c +++ b/fs/autofs4/expire.c @@ -315,19 +315,17 @@ struct dentry *autofs4_expire_direct(struct super_block *sb, if (ino->flags & AUTOFS_INF_PENDING) goto out; if (!autofs4_direct_busy(mnt, root, timeout, do_now)) { - ino->flags |= AUTOFS_INF_NO_RCU; + ino->flags |= AUTOFS_INF_WANT_EXPIRE; spin_unlock(&sbi->fs_lock); synchronize_rcu(); spin_lock(&sbi->fs_lock); if (!autofs4_direct_busy(mnt, root, timeout, do_now)) { ino->flags |= AUTOFS_INF_EXPIRING; - smp_mb(); - ino->flags &= ~AUTOFS_INF_NO_RCU; init_completion(&ino->expire_complete); spin_unlock(&sbi->fs_lock); return root; } - ino->flags &= ~AUTOFS_INF_NO_RCU; + ino->flags &= ~AUTOFS_INF_WANT_EXPIRE; } out: spin_unlock(&sbi->fs_lock); @@ -417,6 +415,7 @@ static struct dentry *should_expire(struct dentry *dentry, } return NULL; } + /* * Find an eligible tree to time-out * A tree is eligible if :- @@ -432,6 +431,7 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb, struct dentry *root = sb->s_root; struct dentry *dentry; struct dentry *expired; + struct dentry *found; struct autofs_info *ino; if (!root) @@ -442,48 +442,54 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb, dentry = NULL; while ((dentry = get_next_positive_subdir(dentry, root))) { + int flags = how; + spin_lock(&sbi->fs_lock); ino = autofs4_dentry_ino(dentry); - if (ino->flags & AUTOFS_INF_NO_RCU) - expired = NULL; - else - expired = should_expire(dentry, mnt, timeout, how); - if (!expired) { + if (ino->flags & AUTOFS_INF_WANT_EXPIRE) { spin_unlock(&sbi->fs_lock); continue; } + spin_unlock(&sbi->fs_lock); + + expired = should_expire(dentry, mnt, timeout, flags); + if (!expired) + continue; + + spin_lock(&sbi->fs_lock); ino = autofs4_dentry_ino(expired); - ino->flags |= AUTOFS_INF_NO_RCU; + ino->flags |= AUTOFS_INF_WANT_EXPIRE; spin_unlock(&sbi->fs_lock); synchronize_rcu(); - spin_lock(&sbi->fs_lock); - if (should_expire(expired, mnt, timeout, how)) { - if (expired != dentry) - dput(dentry); - goto found; - } - ino->flags &= ~AUTOFS_INF_NO_RCU; + /* Make sure a reference is not taken on found if + * things have changed. + */ + flags &= ~AUTOFS_EXP_LEAVES; + found = should_expire(expired, mnt, timeout, how); + if (!found || found != expired) + /* Something has changed, continue */ + goto next; + if (expired != dentry) - dput(expired); + dput(dentry); + + spin_lock(&sbi->fs_lock); + goto found; +next: + spin_lock(&sbi->fs_lock); + ino->flags &= ~AUTOFS_INF_WANT_EXPIRE; spin_unlock(&sbi->fs_lock); + if (expired != dentry) + dput(expired); } return NULL; found: DPRINTK("returning %p %pd", expired, expired); ino->flags |= AUTOFS_INF_EXPIRING; - smp_mb(); - ino->flags &= ~AUTOFS_INF_NO_RCU; init_completion(&ino->expire_complete); spin_unlock(&sbi->fs_lock); - spin_lock(&sbi->lookup_lock); - spin_lock(&expired->d_parent->d_lock); - spin_lock_nested(&expired->d_lock, DENTRY_D_LOCK_NESTED); - list_move(&expired->d_parent->d_subdirs, &expired->d_child); - spin_unlock(&expired->d_lock); - spin_unlock(&expired->d_parent->d_lock); - spin_unlock(&sbi->lookup_lock); return expired; } @@ -492,15 +498,27 @@ int autofs4_expire_wait(struct dentry *dentry, int rcu_walk) struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb); struct autofs_info *ino = autofs4_dentry_ino(dentry); int status; + int state; /* Block on any pending expire */ - if (!(ino->flags & (AUTOFS_INF_EXPIRING | AUTOFS_INF_NO_RCU))) + if (!(ino->flags & AUTOFS_INF_WANT_EXPIRE)) return 0; if (rcu_walk) return -ECHILD; +retry: spin_lock(&sbi->fs_lock); - if (ino->flags & AUTOFS_INF_EXPIRING) { + state = ino->flags & (AUTOFS_INF_WANT_EXPIRE | AUTOFS_INF_EXPIRING); + if (state == AUTOFS_INF_WANT_EXPIRE) { + spin_unlock(&sbi->fs_lock); + /* + * Possibly being selected for expire, wait until + * it's selected or not. + */ + schedule_timeout_uninterruptible(HZ/10); + goto retry; + } + if (state & AUTOFS_INF_EXPIRING) { spin_unlock(&sbi->fs_lock); DPRINTK("waiting for expire %p name=%pd", dentry, dentry); @@ -551,7 +569,7 @@ int autofs4_expire_run(struct super_block *sb, ino = autofs4_dentry_ino(dentry); /* avoid rapid-fire expire attempts if expiry fails */ ino->last_used = now; - ino->flags &= ~AUTOFS_INF_EXPIRING; + ino->flags &= ~(AUTOFS_INF_EXPIRING|AUTOFS_INF_WANT_EXPIRE); complete_all(&ino->expire_complete); spin_unlock(&sbi->fs_lock); @@ -579,7 +597,7 @@ int autofs4_do_expire_multi(struct super_block *sb, struct vfsmount *mnt, spin_lock(&sbi->fs_lock); /* avoid rapid-fire expire attempts if expiry fails */ ino->last_used = now; - ino->flags &= ~AUTOFS_INF_EXPIRING; + ino->flags &= ~(AUTOFS_INF_EXPIRING|AUTOFS_INF_WANT_EXPIRE); complete_all(&ino->expire_complete); spin_unlock(&sbi->fs_lock); dput(dentry); diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c index c6d7d3dbd52a..7a54c6a867c8 100644 --- a/fs/autofs4/root.c +++ b/fs/autofs4/root.c @@ -455,7 +455,7 @@ static int autofs4_d_manage(struct dentry *dentry, bool rcu_walk) * a mount-trap. */ struct inode *inode; - if (ino->flags & (AUTOFS_INF_EXPIRING | AUTOFS_INF_NO_RCU)) + if (ino->flags & AUTOFS_INF_WANT_EXPIRE) return 0; if (d_mountpoint(dentry)) return 0; diff --git a/fs/block_dev.c b/fs/block_dev.c index ccfd31f1df3a..300566ea9b74 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -729,7 +729,7 @@ static bool bd_may_claim(struct block_device *bdev, struct block_device *whole, return true; /* already a holder */ else if (bdev->bd_holder != NULL) return false; /* held by someone else */ - else if (bdev->bd_contains == bdev) + else if (whole == bdev) return true; /* is a whole device which isn't held */ else if (whole->bd_holder == bd_may_claim) @@ -1772,6 +1772,7 @@ void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg) spin_lock(&inode_sb_list_lock); list_for_each_entry(inode, &blockdev_superblock->s_inodes, i_sb_list) { struct address_space *mapping = inode->i_mapping; + struct block_device *bdev; spin_lock(&inode->i_lock); if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW) || @@ -1792,8 +1793,12 @@ void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg) */ iput(old_inode); old_inode = inode; + bdev = I_BDEV(inode); - func(I_BDEV(inode), arg); + mutex_lock(&bdev->bd_mutex); + if (bdev->bd_openers) + func(bdev, arg); + mutex_unlock(&bdev->bd_mutex); spin_lock(&inode_sb_list_lock); } diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c index 9a0124a95851..fb3e64d37cb4 100644 --- a/fs/btrfs/acl.c +++ b/fs/btrfs/acl.c @@ -83,11 +83,9 @@ static int __btrfs_set_acl(struct btrfs_trans_handle *trans, case ACL_TYPE_ACCESS: name = POSIX_ACL_XATTR_ACCESS; if (acl) { - ret = posix_acl_equiv_mode(acl, &inode->i_mode); - if (ret < 0) + ret = posix_acl_update_mode(inode, &inode->i_mode, &acl); + if (ret) return ret; - if (ret == 0) - acl = NULL; } ret = 0; break; diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c index 1848705506ff..0ce4de6430ef 100644 --- a/fs/btrfs/async-thread.c +++ b/fs/btrfs/async-thread.c @@ -64,6 +64,20 @@ void btrfs_##name(struct work_struct *arg) \ normal_work_helper(work); \ } +bool btrfs_workqueue_normal_congested(struct btrfs_workqueue *wq) +{ + /* + * We could compare wq->normal->pending with num_online_cpus() + * to support "thresh == NO_THRESHOLD" case, but it requires + * moving up atomic_inc/dec in thresh_queue/exec_hook. Let's + * postpone it until someone needs the support of that case. + */ + if (wq->normal->thresh == NO_THRESHOLD) + return false; + + return atomic_read(&wq->normal->pending) > wq->normal->thresh * 2; +} + BTRFS_WORK_HELPER(worker_helper); BTRFS_WORK_HELPER(delalloc_helper); BTRFS_WORK_HELPER(flush_delalloc_helper); diff --git a/fs/btrfs/async-thread.h b/fs/btrfs/async-thread.h index ec2ee477f8ba..8c4564204f25 100644 --- a/fs/btrfs/async-thread.h +++ b/fs/btrfs/async-thread.h @@ -78,4 +78,5 @@ void btrfs_queue_work(struct btrfs_workqueue *wq, void btrfs_destroy_workqueue(struct btrfs_workqueue *wq); void btrfs_workqueue_set_max(struct btrfs_workqueue *wq, int max); void btrfs_set_work_high_priority(struct btrfs_work *work); +bool btrfs_workqueue_normal_congested(struct btrfs_workqueue *wq); #endif diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index bc2d048a9eb9..8265b0754dca 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1371,7 +1371,8 @@ release_path: total_done++; btrfs_release_prepared_delayed_node(delayed_node); - if (async_work->nr == 0 || total_done < async_work->nr) + if ((async_work->nr == 0 && total_done < BTRFS_DELAYED_WRITEBACK) || + total_done < async_work->nr) goto again; free_path: @@ -1387,7 +1388,8 @@ static int btrfs_wq_run_delayed_node(struct btrfs_delayed_root *delayed_root, { struct btrfs_async_delayed_work *async_work; - if (atomic_read(&delayed_root->items) < BTRFS_DELAYED_BACKGROUND) + if (atomic_read(&delayed_root->items) < BTRFS_DELAYED_BACKGROUND || + btrfs_workqueue_normal_congested(fs_info->delayed_workers)) return 0; async_work = kmalloc(sizeof(*async_work), GFP_NOFS); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index c4771af7fd6f..757a34bdd2b9 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4975,7 +4975,7 @@ static int btrfs_setattr(struct dentry *dentry, struct iattr *attr) if (btrfs_root_readonly(root)) return -EROFS; - err = inode_change_ok(inode, attr); + err = setattr_prepare(dentry, attr); if (err) return err; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 2eca30adb3e3..f1feb3123c9c 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1610,6 +1610,9 @@ static noinline int btrfs_ioctl_snap_create_transid(struct file *file, int namelen; int ret = 0; + if (!S_ISDIR(file_inode(file)->i_mode)) + return -ENOTDIR; + ret = mnt_want_write_file(file); if (ret) goto out; @@ -1667,6 +1670,9 @@ static noinline int btrfs_ioctl_snap_create(struct file *file, struct btrfs_ioctl_vol_args *vol_args; int ret; + if (!S_ISDIR(file_inode(file)->i_mode)) + return -ENOTDIR; + vol_args = memdup_user(arg, sizeof(*vol_args)); if (IS_ERR(vol_args)) return PTR_ERR(vol_args); @@ -1690,6 +1696,9 @@ static noinline int btrfs_ioctl_snap_create_v2(struct file *file, bool readonly = false; struct btrfs_qgroup_inherit *inherit = NULL; + if (!S_ISDIR(file_inode(file)->i_mode)) + return -ENOTDIR; + vol_args = memdup_user(arg, sizeof(*vol_args)); if (IS_ERR(vol_args)) return PTR_ERR(vol_args); @@ -2318,6 +2327,9 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, int ret; int err = 0; + if (!S_ISDIR(dir->i_mode)) + return -ENOTDIR; + vol_args = memdup_user(arg, sizeof(*vol_args)); if (IS_ERR(vol_args)) return PTR_ERR(vol_args); @@ -5496,6 +5508,10 @@ long btrfs_ioctl(struct file *file, unsigned int #ifdef CONFIG_COMPAT long btrfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { + /* + * These all access 32-bit values anyway so no further + * handling is necessary. + */ switch (cmd) { case FS_IOC32_GETFLAGS: cmd = FS_IOC_GETFLAGS; @@ -5506,8 +5522,6 @@ long btrfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case FS_IOC32_GETVERSION: cmd = FS_IOC_GETVERSION; break; - default: - return -ENOIOCTLCMD; } return btrfs_ioctl(file, cmd, (unsigned long) compat_ptr(arg)); diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 5c222f3c4841..6ee954c62fe6 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -1821,12 +1821,11 @@ static noinline int find_dir_range(struct btrfs_root *root, next: /* check the next slot in the tree to see if it is a valid item */ nritems = btrfs_header_nritems(path->nodes[0]); + path->slots[0]++; if (path->slots[0] >= nritems) { ret = btrfs_next_leaf(root, path); if (ret) goto out; - } else { - path->slots[0]++; } btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); @@ -2596,14 +2595,12 @@ static inline void btrfs_remove_all_log_ctxs(struct btrfs_root *root, int index, int error) { struct btrfs_log_ctx *ctx; + struct btrfs_log_ctx *safe; - if (!error) { - INIT_LIST_HEAD(&root->log_ctxs[index]); - return; - } - - list_for_each_entry(ctx, &root->log_ctxs[index], list) + list_for_each_entry_safe(ctx, safe, &root->log_ctxs[index], list) { + list_del_init(&ctx->list); ctx->log_ret = error; + } INIT_LIST_HEAD(&root->log_ctxs[index]); } @@ -2748,6 +2745,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, if (log_root_tree->log_transid_committed >= root_log_ctx.log_transid) { blk_finish_plug(&plug); + list_del_init(&root_log_ctx.list); mutex_unlock(&log_root_tree->log_mutex); ret = root_log_ctx.log_ret; goto out; @@ -2841,13 +2839,9 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, mutex_unlock(&root->log_mutex); out_wake_log_root: - /* - * We needn't get log_mutex here because we are sure all - * the other tasks are blocked. - */ + mutex_lock(&log_root_tree->log_mutex); btrfs_remove_all_log_ctxs(log_root_tree, index2, ret); - mutex_lock(&log_root_tree->log_mutex); log_root_tree->log_transid_committed++; atomic_set(&log_root_tree->log_commit[index2], 0); mutex_unlock(&log_root_tree->log_mutex); @@ -2855,10 +2849,8 @@ out_wake_log_root: if (waitqueue_active(&log_root_tree->log_commit_wait[index2])) wake_up(&log_root_tree->log_commit_wait[index2]); out: - /* See above. */ - btrfs_remove_all_log_ctxs(root, index1, ret); - mutex_lock(&root->log_mutex); + btrfs_remove_all_log_ctxs(root, index1, ret); root->log_transid_committed++; atomic_set(&root->log_commit[index1], 0); mutex_unlock(&root->log_mutex); @@ -4991,6 +4983,7 @@ process_leaf: if (di_key.type == BTRFS_ROOT_ITEM_KEY) continue; + btrfs_release_path(path); di_inode = btrfs_iget(root->fs_info->sb, &di_key, root, NULL); if (IS_ERR(di_inode)) { @@ -5000,13 +4993,12 @@ process_leaf: if (btrfs_inode_in_log(di_inode, trans->transid)) { iput(di_inode); - continue; + break; } ctx->log_new_dentries = false; if (type == BTRFS_FT_DIR) log_mode = LOG_INODE_ALL; - btrfs_release_path(path); ret = btrfs_log_inode(trans, root, di_inode, log_mode, 0, LLONG_MAX, ctx); iput(di_inode); diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c index 64fa248343f6..d7496e3dbfc4 100644 --- a/fs/ceph/acl.c +++ b/fs/ceph/acl.c @@ -94,11 +94,9 @@ int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type) case ACL_TYPE_ACCESS: name = POSIX_ACL_XATTR_ACCESS; if (acl) { - ret = posix_acl_equiv_mode(acl, &new_mode); - if (ret < 0) + ret = posix_acl_update_mode(inode, &new_mode, &acl); + if (ret) goto out; - if (ret == 0) - acl = NULL; } break; case ACL_TYPE_DEFAULT: diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 3b6b522b4b31..5ae447cbd2b5 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -868,7 +868,8 @@ again: statret = __ceph_do_getattr(inode, page, CEPH_STAT_CAP_INLINE_DATA, !!page); if (statret < 0) { - __free_page(page); + if (page) + __free_page(page); if (statret == -ENODATA) { BUG_ON(retry_op != READ_INLINE); goto again; diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index e876e1944519..4484aaf5c478 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -1728,7 +1728,7 @@ int ceph_setattr(struct dentry *dentry, struct iattr *attr) if (ceph_snap(inode) != CEPH_NOSNAP) return -EROFS; - err = inode_change_ok(inode, attr); + err = setattr_prepare(dentry, attr); if (err != 0) return err; diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 1e99b29650a9..4f3bf0f527f6 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -273,12 +273,13 @@ static int parse_reply_info_extra(void **p, void *end, struct ceph_mds_reply_info_parsed *info, u64 features) { - if (info->head->op == CEPH_MDS_OP_GETFILELOCK) + u32 op = le32_to_cpu(info->head->op); + + if (op == CEPH_MDS_OP_GETFILELOCK) return parse_reply_info_filelock(p, end, info, features); - else if (info->head->op == CEPH_MDS_OP_READDIR || - info->head->op == CEPH_MDS_OP_LSSNAP) + else if (op == CEPH_MDS_OP_READDIR || op == CEPH_MDS_OP_LSSNAP) return parse_reply_info_dir(p, end, info, features); - else if (info->head->op == CEPH_MDS_OP_CREATE) + else if (op == CEPH_MDS_OP_CREATE) return parse_reply_info_create(p, end, info, features); else return -EIO; diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 22b289a3b1c4..9d0e4fef8ee1 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -615,6 +615,8 @@ struct TCP_Server_Info { #ifdef CONFIG_CIFS_SMB2 unsigned int max_read; unsigned int max_write; + struct delayed_work reconnect; /* reconnect workqueue job */ + struct mutex reconnect_mutex; /* prevent simultaneous reconnects */ #endif /* CONFIG_CIFS_SMB2 */ }; @@ -814,6 +816,7 @@ cap_unix(struct cifs_ses *ses) struct cifs_tcon { struct list_head tcon_list; int tc_count; + struct list_head rlist; /* reconnect list */ struct list_head openFileList; struct cifs_ses *ses; /* pointer to session associated with */ char treeName[MAX_TREE_SIZE + 1]; /* UNC name of resource in ASCII */ diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index f730c065df34..5ee60b50d8eb 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -207,6 +207,9 @@ extern void cifs_add_pending_open_locked(struct cifs_fid *fid, struct tcon_link *tlink, struct cifs_pending_open *open); extern void cifs_del_pending_open(struct cifs_pending_open *open); +extern void cifs_put_tcp_session(struct TCP_Server_Info *server, + int from_reconnect); +extern void cifs_put_tcon(struct cifs_tcon *tcon); #if IS_ENABLED(CONFIG_CIFS_DFS_UPCALL) extern void cifs_dfs_release_automount_timer(void); diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index cd9d50e4f5f4..7d7bd466520b 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -52,6 +52,9 @@ #include "nterr.h" #include "rfc1002pdu.h" #include "fscache.h" +#ifdef CONFIG_CIFS_SMB2 +#include "smb2proto.h" +#endif #define CIFS_PORT 445 #define RFC1001_PORT 139 @@ -2069,8 +2072,8 @@ cifs_find_tcp_session(struct smb_vol *vol) return NULL; } -static void -cifs_put_tcp_session(struct TCP_Server_Info *server) +void +cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect) { struct task_struct *task; @@ -2087,6 +2090,19 @@ cifs_put_tcp_session(struct TCP_Server_Info *server) cancel_delayed_work_sync(&server->echo); +#ifdef CONFIG_CIFS_SMB2 + if (from_reconnect) + /* + * Avoid deadlock here: reconnect work calls + * cifs_put_tcp_session() at its end. Need to be sure + * that reconnect work does nothing with server pointer after + * that step. + */ + cancel_delayed_work(&server->reconnect); + else + cancel_delayed_work_sync(&server->reconnect); +#endif + spin_lock(&GlobalMid_Lock); server->tcpStatus = CifsExiting; spin_unlock(&GlobalMid_Lock); @@ -2151,6 +2167,10 @@ cifs_get_tcp_session(struct smb_vol *volume_info) INIT_LIST_HEAD(&tcp_ses->tcp_ses_list); INIT_LIST_HEAD(&tcp_ses->smb_ses_list); INIT_DELAYED_WORK(&tcp_ses->echo, cifs_echo_request); +#ifdef CONFIG_CIFS_SMB2 + INIT_DELAYED_WORK(&tcp_ses->reconnect, smb2_reconnect_server); + mutex_init(&tcp_ses->reconnect_mutex); +#endif memcpy(&tcp_ses->srcaddr, &volume_info->srcaddr, sizeof(tcp_ses->srcaddr)); memcpy(&tcp_ses->dstaddr, &volume_info->dstaddr, @@ -2303,7 +2323,7 @@ cifs_put_smb_ses(struct cifs_ses *ses) spin_unlock(&cifs_tcp_ses_lock); sesInfoFree(ses); - cifs_put_tcp_session(server); + cifs_put_tcp_session(server, 0); } #ifdef CONFIG_KEYS @@ -2476,7 +2496,7 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb_vol *volume_info) mutex_unlock(&ses->session_mutex); /* existing SMB ses has a server reference already */ - cifs_put_tcp_session(server); + cifs_put_tcp_session(server, 0); free_xid(xid); return ses; } @@ -2566,7 +2586,7 @@ cifs_find_tcon(struct cifs_ses *ses, const char *unc) return NULL; } -static void +void cifs_put_tcon(struct cifs_tcon *tcon) { unsigned int xid; @@ -3673,7 +3693,7 @@ mount_fail_check: else if (ses) cifs_put_smb_ses(ses); else - cifs_put_tcp_session(server); + cifs_put_tcp_session(server, 0); bdi_destroy(&cifs_sb->bdi); } @@ -3984,7 +4004,7 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid) ses = cifs_get_smb_ses(master_tcon->ses->server, vol_info); if (IS_ERR(ses)) { tcon = (struct cifs_tcon *)ses; - cifs_put_tcp_session(master_tcon->ses->server); + cifs_put_tcp_session(master_tcon->ses->server, 0); goto out; } diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 9fb3bc26a2ab..f82dfe7ae3e8 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -2134,7 +2134,7 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs) if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM) attrs->ia_valid |= ATTR_FORCE; - rc = inode_change_ok(inode, attrs); + rc = setattr_prepare(direntry, attrs); if (rc < 0) goto out; @@ -2274,7 +2274,7 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs) if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM) attrs->ia_valid |= ATTR_FORCE; - rc = inode_change_ok(inode, attrs); + rc = setattr_prepare(direntry, attrs); if (rc < 0) { free_xid(xid); return rc; diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c index 2ab297dae5a7..1bdfd7c5309c 100644 --- a/fs/cifs/smb2file.c +++ b/fs/cifs/smb2file.c @@ -241,7 +241,7 @@ smb2_push_mandatory_locks(struct cifsFileInfo *cfile) * and check it for zero before using. */ max_buf = tlink_tcon(cfile->tlink)->ses->server->maxBuf; - if (!max_buf) { + if (max_buf < sizeof(struct smb2_lock_element)) { free_xid(xid); return -EINVAL; } diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 8f527c867f78..e3cf4a5fb35a 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -264,7 +264,7 @@ out: case SMB2_CHANGE_NOTIFY: case SMB2_QUERY_INFO: case SMB2_SET_INFO: - return -EAGAIN; + rc = -EAGAIN; } unload_nls(nls_codepage); return rc; @@ -1615,6 +1615,54 @@ smb2_echo_callback(struct mid_q_entry *mid) add_credits(server, credits_received, CIFS_ECHO_OP); } +void smb2_reconnect_server(struct work_struct *work) +{ + struct TCP_Server_Info *server = container_of(work, + struct TCP_Server_Info, reconnect.work); + struct cifs_ses *ses; + struct cifs_tcon *tcon, *tcon2; + struct list_head tmp_list; + int tcon_exist = false; + + /* Prevent simultaneous reconnects that can corrupt tcon->rlist list */ + mutex_lock(&server->reconnect_mutex); + + INIT_LIST_HEAD(&tmp_list); + cifs_dbg(FYI, "Need negotiate, reconnecting tcons\n"); + + spin_lock(&cifs_tcp_ses_lock); + list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { + list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { + if (tcon->need_reconnect) { + tcon->tc_count++; + list_add_tail(&tcon->rlist, &tmp_list); + tcon_exist = true; + } + } + } + /* + * Get the reference to server struct to be sure that the last call of + * cifs_put_tcon() in the loop below won't release the server pointer. + */ + if (tcon_exist) + server->srv_count++; + + spin_unlock(&cifs_tcp_ses_lock); + + list_for_each_entry_safe(tcon, tcon2, &tmp_list, rlist) { + smb2_reconnect(SMB2_ECHO, tcon); + list_del_init(&tcon->rlist); + cifs_put_tcon(tcon); + } + + cifs_dbg(FYI, "Reconnecting tcons finished\n"); + mutex_unlock(&server->reconnect_mutex); + + /* now we can safely release srv struct */ + if (tcon_exist) + cifs_put_tcp_session(server, 1); +} + int SMB2_echo(struct TCP_Server_Info *server) { @@ -1627,32 +1675,11 @@ SMB2_echo(struct TCP_Server_Info *server) cifs_dbg(FYI, "In echo request\n"); if (server->tcpStatus == CifsNeedNegotiate) { - struct list_head *tmp, *tmp2; - struct cifs_ses *ses; - struct cifs_tcon *tcon; - - cifs_dbg(FYI, "Need negotiate, reconnecting tcons\n"); - spin_lock(&cifs_tcp_ses_lock); - list_for_each(tmp, &server->smb_ses_list) { - ses = list_entry(tmp, struct cifs_ses, smb_ses_list); - list_for_each(tmp2, &ses->tcon_list) { - tcon = list_entry(tmp2, struct cifs_tcon, - tcon_list); - /* add check for persistent handle reconnect */ - if (tcon && tcon->need_reconnect) { - spin_unlock(&cifs_tcp_ses_lock); - rc = smb2_reconnect(SMB2_ECHO, tcon); - spin_lock(&cifs_tcp_ses_lock); - } - } - } - spin_unlock(&cifs_tcp_ses_lock); + /* No need to send echo on newly established connections */ + queue_delayed_work(cifsiod_wq, &server->reconnect, 0); + return rc; } - /* if no session, renegotiate failed above */ - if (server->tcpStatus == CifsNeedNegotiate) - return -EIO; - rc = small_smb2_init(SMB2_ECHO, NULL, (void **)&req); if (rc) return rc; diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index 9bc59f9c12fb..0a406ae78129 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -95,6 +95,7 @@ extern int smb2_open_file(const unsigned int xid, extern int smb2_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock, const unsigned int xid); extern int smb2_push_mandatory_locks(struct cifsFileInfo *cfile); +extern void smb2_reconnect_server(struct work_struct *work); /* * SMB2 Worker functions - most of protocol specific implementation details diff --git a/fs/dcache.c b/fs/dcache.c index 660857431b1c..11d466bbfb0b 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -1322,8 +1322,11 @@ int d_set_mounted(struct dentry *dentry) } spin_lock(&dentry->d_lock); if (!d_unlinked(dentry)) { - dentry->d_flags |= DCACHE_MOUNTED; - ret = 0; + ret = -EBUSY; + if (!d_mountpoint(dentry)) { + dentry->d_flags |= DCACHE_MOUNTED; + ret = 0; + } } spin_unlock(&dentry->d_lock); out: diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index fc850b55db67..661dd53f0040 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -942,7 +942,7 @@ static int ecryptfs_setattr(struct dentry *dentry, struct iattr *ia) } mutex_unlock(&crypt_stat->cs_mutex); - rc = inode_change_ok(inode, ia); + rc = setattr_prepare(dentry, ia); if (rc) goto out; if (ia->ia_valid & ATTR_SIZE) { diff --git a/fs/exec.c b/fs/exec.c index 1977c2a553ac..04c9cab4d4d3 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -19,7 +19,7 @@ * current->executable is only used by the procfs. This allows a dispatch * table to check for several different types of binary formats. We keep * trying until we recognize the file or we run out of supported binary - * formats. + * formats. */ #include <linux/slab.h> @@ -1108,6 +1108,13 @@ int flush_old_exec(struct linux_binprm * bprm) flush_thread(); current->personality &= ~bprm->per_clear; + /* + * We have to apply CLOEXEC before we change whether the process is + * dumpable (in setup_new_exec) to avoid a race with a process in userspace + * trying to access the should-be-closed file descriptors of a process + * undergoing exec(2). + */ + do_close_on_exec(current->files); return 0; out: @@ -1157,7 +1164,6 @@ void setup_new_exec(struct linux_binprm * bprm) group */ current->self_exec_id++; flush_signal_handlers(current, 0); - do_close_on_exec(current->files); } EXPORT_SYMBOL(setup_new_exec); @@ -1248,7 +1254,7 @@ static void check_unsafe_exec(struct linux_binprm *bprm) unsigned n_fs; if (p->ptrace) { - if (p->ptrace & PT_PTRACE_CAP) + if (ptracer_capable(p, current_user_ns())) bprm->unsafe |= LSM_UNSAFE_PTRACE_CAP; else bprm->unsafe |= LSM_UNSAFE_PTRACE; diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c index 786e4cc8c889..159c30c18395 100644 --- a/fs/exofs/inode.c +++ b/fs/exofs/inode.c @@ -1038,7 +1038,7 @@ int exofs_setattr(struct dentry *dentry, struct iattr *iattr) if (unlikely(error)) return error; - error = inode_change_ok(inode, iattr); + error = setattr_prepare(dentry, iattr); if (unlikely(error)) return error; diff --git a/fs/ext2/acl.c b/fs/ext2/acl.c index 27695e6f4e46..d6aeb84e90b6 100644 --- a/fs/ext2/acl.c +++ b/fs/ext2/acl.c @@ -193,15 +193,11 @@ ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type) case ACL_TYPE_ACCESS: name_index = EXT2_XATTR_INDEX_POSIX_ACL_ACCESS; if (acl) { - error = posix_acl_equiv_mode(acl, &inode->i_mode); - if (error < 0) + error = posix_acl_update_mode(inode, &inode->i_mode, &acl); + if (error) return error; - else { - inode->i_ctime = CURRENT_TIME_SEC; - mark_inode_dirty(inode); - if (error == 0) - acl = NULL; - } + inode->i_ctime = CURRENT_TIME_SEC; + mark_inode_dirty(inode); } break; diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index f460ae36d5b7..f08604366cb5 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -1547,7 +1547,7 @@ int ext2_setattr(struct dentry *dentry, struct iattr *iattr) struct inode *inode = d_inode(dentry); int error; - error = inode_change_ok(inode, iattr); + error = setattr_prepare(dentry, iattr); if (error) return error; diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index 2ee2dc4351d1..3613e87c688f 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -3244,7 +3244,7 @@ int ext3_setattr(struct dentry *dentry, struct iattr *attr) int error, rc = 0; const unsigned int ia_valid = attr->ia_valid; - error = inode_change_ok(inode, attr); + error = setattr_prepare(dentry, attr); if (error) return error; diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c index 69b1e73026a5..c3fe1e323951 100644 --- a/fs/ext4/acl.c +++ b/fs/ext4/acl.c @@ -196,15 +196,11 @@ __ext4_set_acl(handle_t *handle, struct inode *inode, int type, case ACL_TYPE_ACCESS: name_index = EXT4_XATTR_INDEX_POSIX_ACL_ACCESS; if (acl) { - error = posix_acl_equiv_mode(acl, &inode->i_mode); - if (error < 0) + error = posix_acl_update_mode(inode, &inode->i_mode, &acl); + if (error) return error; - else { - inode->i_ctime = ext4_current_time(inode); - ext4_mark_inode_dirty(handle, inode); - if (error == 0) - acl = NULL; - } + inode->i_ctime = ext4_current_time(inode); + ext4_mark_inode_dirty(handle, inode); } break; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 15213a567301..df67a6f8582a 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -224,6 +224,7 @@ struct ext4_io_submit { #define EXT4_MAX_BLOCK_SIZE 65536 #define EXT4_MIN_BLOCK_LOG_SIZE 10 #define EXT4_MAX_BLOCK_LOG_SIZE 16 +#define EXT4_MAX_CLUSTER_LOG_SIZE 30 #ifdef __KERNEL__ # define EXT4_BLOCK_SIZE(s) ((s)->s_blocksize) #else @@ -1008,6 +1009,7 @@ struct ext4_inode_info { /* * Mount flags set via mount options or defaults */ +#define EXT4_MOUNT_NO_MBCACHE 0x00001 /* Disable mbcache */ #define EXT4_MOUNT_GRPID 0x00004 /* Create files with directory's group */ #define EXT4_MOUNT_DEBUG 0x00008 /* Some debugging messages */ #define EXT4_MOUNT_ERRORS_CONT 0x00010 /* Continue on errors */ diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 095c7a258d97..d77d542c2ed5 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -336,8 +336,10 @@ static int ext4_update_inline_data(handle_t *handle, struct inode *inode, len -= EXT4_MIN_INLINE_DATA_SIZE; value = kzalloc(len, GFP_NOFS); - if (!value) + if (!value) { + error = -ENOMEM; goto out; + } error = ext4_xattr_ibody_get(inode, i.name_index, i.name, value, len); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 9b55c6f71bf2..5beca5c5413e 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4751,7 +4751,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) int orphan = 0; const unsigned int ia_valid = attr->ia_valid; - error = inode_change_ok(inode, attr); + error = setattr_prepare(dentry, attr); if (error) return error; diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 2cb9e178d1c5..4196aa567784 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -637,7 +637,13 @@ resizefs_out: goto encryption_policy_out; } + err = mnt_want_write_file(filp); + if (err) + goto encryption_policy_out; + err = ext4_process_policy(&policy, inode); + + mnt_drop_write_file(filp); encryption_policy_out: return err; #else diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 5b58e266892b..e6798ca34928 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -668,7 +668,7 @@ static void ext4_mb_mark_free_simple(struct super_block *sb, ext4_grpblk_t min; ext4_grpblk_t max; ext4_grpblk_t chunk; - unsigned short border; + unsigned int border; BUG_ON(len > EXT4_CLUSTERS_PER_GROUP(sb)); @@ -2254,7 +2254,7 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v) struct ext4_group_info *grinfo; struct sg { struct ext4_group_info info; - ext4_grpblk_t counters[16]; + ext4_grpblk_t counters[EXT4_MAX_BLOCK_LOG_SIZE + 2]; } sg; group--; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index f01dd19adb7b..97aa8be40175 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1144,6 +1144,7 @@ enum { Opt_nomblk_io_submit, Opt_block_validity, Opt_noblock_validity, Opt_inode_readahead_blks, Opt_journal_ioprio, Opt_dioread_nolock, Opt_dioread_lock, + Opt_no_mbcache, Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable, Opt_max_dir_size_kb, Opt_nojournal_checksum, }; @@ -1222,6 +1223,7 @@ static const match_table_t tokens = { {Opt_discard, "discard"}, {Opt_nodiscard, "nodiscard"}, {Opt_init_itable, "init_itable=%u"}, + {Opt_no_mbcache, "no_mbcache"}, {Opt_init_itable, "init_itable"}, {Opt_noinit_itable, "noinit_itable"}, {Opt_max_dir_size_kb, "max_dir_size_kb=%u"}, @@ -1385,6 +1387,7 @@ static const struct mount_opts { {Opt_noauto_da_alloc, EXT4_MOUNT_NO_AUTO_DA_ALLOC, MOPT_SET}, {Opt_auto_da_alloc, EXT4_MOUNT_NO_AUTO_DA_ALLOC, MOPT_CLEAR}, {Opt_noinit_itable, EXT4_MOUNT_INIT_INODE_TABLE, MOPT_CLEAR}, + {Opt_no_mbcache, EXT4_MOUNT_NO_MBCACHE, MOPT_SET}, {Opt_commit, 0, MOPT_GTE0}, {Opt_max_batch_time, 0, MOPT_GTE0}, {Opt_min_batch_time, 0, MOPT_GTE0}, @@ -2082,6 +2085,7 @@ void ext4_group_desc_csum_set(struct super_block *sb, __u32 block_group, /* Called at mount-time, super-block is locked */ static int ext4_check_descriptors(struct super_block *sb, + ext4_fsblk_t sb_block, ext4_group_t *first_not_zeroed) { struct ext4_sb_info *sbi = EXT4_SB(sb); @@ -2112,6 +2116,11 @@ static int ext4_check_descriptors(struct super_block *sb, grp = i; block_bitmap = ext4_block_bitmap(sb, gdp); + if (block_bitmap == sb_block) { + ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " + "Block bitmap for group %u overlaps " + "superblock", i); + } if (block_bitmap < first_block || block_bitmap > last_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Block bitmap for group %u not in group " @@ -2119,6 +2128,11 @@ static int ext4_check_descriptors(struct super_block *sb, return 0; } inode_bitmap = ext4_inode_bitmap(sb, gdp); + if (inode_bitmap == sb_block) { + ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " + "Inode bitmap for group %u overlaps " + "superblock", i); + } if (inode_bitmap < first_block || inode_bitmap > last_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Inode bitmap for group %u not in group " @@ -2126,6 +2140,11 @@ static int ext4_check_descriptors(struct super_block *sb, return 0; } inode_table = ext4_inode_table(sb, gdp); + if (inode_table == sb_block) { + ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " + "Inode table for group %u overlaps " + "superblock", i); + } if (inode_table < first_block || inode_table + sbi->s_itb_per_group - 1 > last_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " @@ -3342,10 +3361,15 @@ static int count_overhead(struct super_block *sb, ext4_group_t grp, ext4_set_bit(s++, buf); count++; } - for (j = ext4_bg_num_gdb(sb, grp); j > 0; j--) { - ext4_set_bit(EXT4_B2C(sbi, s++), buf); - count++; + j = ext4_bg_num_gdb(sb, grp); + if (s + j > EXT4_BLOCKS_PER_GROUP(sb)) { + ext4_error(sb, "Invalid number of block group " + "descriptor blocks: %d", j); + j = EXT4_BLOCKS_PER_GROUP(sb) - s; } + count += j; + for (; j > 0; j--) + ext4_set_bit(EXT4_B2C(sbi, s++), buf); } if (!count) return 0; @@ -3717,7 +3741,15 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if (blocksize < EXT4_MIN_BLOCK_SIZE || blocksize > EXT4_MAX_BLOCK_SIZE) { ext4_msg(sb, KERN_ERR, - "Unsupported filesystem blocksize %d", blocksize); + "Unsupported filesystem blocksize %d (%d log_block_size)", + blocksize, le32_to_cpu(es->s_log_block_size)); + goto failed_mount; + } + if (le32_to_cpu(es->s_log_block_size) > + (EXT4_MAX_BLOCK_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) { + ext4_msg(sb, KERN_ERR, + "Invalid log block size: %u", + le32_to_cpu(es->s_log_block_size)); goto failed_mount; } @@ -3813,12 +3845,16 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_blocks_per_group = le32_to_cpu(es->s_blocks_per_group); sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group); - if (EXT4_INODE_SIZE(sb) == 0 || EXT4_INODES_PER_GROUP(sb) == 0) - goto cantfind_ext4; sbi->s_inodes_per_block = blocksize / EXT4_INODE_SIZE(sb); if (sbi->s_inodes_per_block == 0) goto cantfind_ext4; + if (sbi->s_inodes_per_group < sbi->s_inodes_per_block || + sbi->s_inodes_per_group > blocksize * 8) { + ext4_msg(sb, KERN_ERR, "invalid inodes per group: %lu\n", + sbi->s_blocks_per_group); + goto failed_mount; + } sbi->s_itb_per_group = sbi->s_inodes_per_group / sbi->s_inodes_per_block; sbi->s_desc_per_block = blocksize / EXT4_DESC_SIZE(sb); @@ -3859,6 +3895,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) "block size (%d)", clustersize, blocksize); goto failed_mount; } + if (le32_to_cpu(es->s_log_cluster_size) > + (EXT4_MAX_CLUSTER_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) { + ext4_msg(sb, KERN_ERR, + "Invalid log cluster size: %u", + le32_to_cpu(es->s_log_cluster_size)); + goto failed_mount; + } sbi->s_cluster_bits = le32_to_cpu(es->s_log_cluster_size) - le32_to_cpu(es->s_log_block_size); sbi->s_clusters_per_group = @@ -3895,13 +3938,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } sbi->s_cluster_ratio = clustersize / blocksize; - if (sbi->s_inodes_per_group > blocksize * 8) { - ext4_msg(sb, KERN_ERR, - "#inodes per group too big: %lu", - sbi->s_inodes_per_group); - goto failed_mount; - } - /* Do we have standard group size of clustersize * 8 blocks ? */ if (sbi->s_blocks_per_group == clustersize << 3) set_opt2(sb, STD_GROUP_SIZE); @@ -3989,7 +4025,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount2; } } - if (!ext4_check_descriptors(sb, &first_not_zeroed)) { + if (!ext4_check_descriptors(sb, logical_sb_block, &first_not_zeroed)) { ext4_msg(sb, KERN_ERR, "group descriptors corrupted!"); goto failed_mount2; } diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 16e28c08d1e8..cdc26e54400f 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -80,7 +80,7 @@ # define ea_bdebug(bh, fmt, ...) no_printk(fmt, ##__VA_ARGS__) #endif -static void ext4_xattr_cache_insert(struct mb_cache *, struct buffer_head *); +static void ext4_xattr_cache_insert(struct inode *, struct buffer_head *); static struct buffer_head *ext4_xattr_cache_find(struct inode *, struct ext4_xattr_header *, struct mb_cache_entry **); @@ -278,7 +278,6 @@ ext4_xattr_block_get(struct inode *inode, int name_index, const char *name, struct ext4_xattr_entry *entry; size_t size; int error; - struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode); ea_idebug(inode, "name=%d.%s, buffer=%p, buffer_size=%ld", name_index, name, buffer, (long)buffer_size); @@ -300,7 +299,7 @@ bad_block: error = -EIO; goto cleanup; } - ext4_xattr_cache_insert(ext4_mb_cache, bh); + ext4_xattr_cache_insert(inode, bh); entry = BFIRST(bh); error = ext4_xattr_find_entry(&entry, name_index, name, bh->b_size, 1); if (error == -EIO) @@ -426,7 +425,6 @@ ext4_xattr_block_list(struct dentry *dentry, char *buffer, size_t buffer_size) struct inode *inode = d_inode(dentry); struct buffer_head *bh = NULL; int error; - struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode); ea_idebug(inode, "buffer=%p, buffer_size=%ld", buffer, (long)buffer_size); @@ -448,7 +446,7 @@ ext4_xattr_block_list(struct dentry *dentry, char *buffer, size_t buffer_size) error = -EIO; goto cleanup; } - ext4_xattr_cache_insert(ext4_mb_cache, bh); + ext4_xattr_cache_insert(inode, bh); error = ext4_xattr_list_entries(dentry, BFIRST(bh), buffer, buffer_size); cleanup: @@ -547,7 +545,8 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode, int error = 0; struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode); - ce = mb_cache_entry_get(ext4_mb_cache, bh->b_bdev, bh->b_blocknr); + if (!test_opt(inode->i_sb, NO_MBCACHE)) + ce = mb_cache_entry_get(ext4_mb_cache, bh->b_bdev, bh->b_blocknr); BUFFER_TRACE(bh, "get_write_access"); error = ext4_journal_get_write_access(handle, bh); if (error) @@ -788,8 +787,9 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, if (i->value && i->value_len > sb->s_blocksize) return -ENOSPC; if (s->base) { - ce = mb_cache_entry_get(ext4_mb_cache, bs->bh->b_bdev, - bs->bh->b_blocknr); + if (!test_opt(inode->i_sb, NO_MBCACHE)) + ce = mb_cache_entry_get(ext4_mb_cache, bs->bh->b_bdev, + bs->bh->b_blocknr); BUFFER_TRACE(bs->bh, "get_write_access"); error = ext4_journal_get_write_access(handle, bs->bh); if (error) @@ -807,7 +807,7 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, if (!IS_LAST_ENTRY(s->first)) ext4_xattr_rehash(header(s->base), s->here); - ext4_xattr_cache_insert(ext4_mb_cache, + ext4_xattr_cache_insert(inode, bs->bh); } unlock_buffer(bs->bh); @@ -892,7 +892,8 @@ inserted: if (error) goto cleanup_dquot; } - mb_cache_entry_release(ce); + if (ce) + mb_cache_entry_release(ce); ce = NULL; } else if (bs->bh && s->base == bs->bh->b_data) { /* We were modifying this block in-place. */ @@ -939,7 +940,7 @@ getblk_failed: memcpy(new_bh->b_data, s->base, new_bh->b_size); set_buffer_uptodate(new_bh); unlock_buffer(new_bh); - ext4_xattr_cache_insert(ext4_mb_cache, new_bh); + ext4_xattr_cache_insert(inode, new_bh); error = ext4_handle_dirty_xattr_block(handle, inode, new_bh); if (error) @@ -1529,12 +1530,17 @@ ext4_xattr_put_super(struct super_block *sb) * Returns 0, or a negative error number on failure. */ static void -ext4_xattr_cache_insert(struct mb_cache *ext4_mb_cache, struct buffer_head *bh) +ext4_xattr_cache_insert(struct inode *inode, struct buffer_head *bh) { + struct super_block *sb = inode->i_sb; + struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode); __u32 hash = le32_to_cpu(BHDR(bh)->h_hash); struct mb_cache_entry *ce; int error; + if (test_opt(sb, NO_MBCACHE)) + return; + ce = mb_cache_entry_alloc(ext4_mb_cache, GFP_NOFS); if (!ce) { ea_bdebug(bh, "out of memory"); @@ -1609,6 +1615,8 @@ ext4_xattr_cache_find(struct inode *inode, struct ext4_xattr_header *header, struct mb_cache_entry *ce; struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode); + if (test_opt(inode->i_sb, NO_MBCACHE)) + return NULL; if (!header->h_hash) return NULL; /* never share */ ea_idebug(inode, "looking for cached blocks [%x]", (int)hash); diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c index 4320ffab3495..c5e4a1856a0f 100644 --- a/fs/f2fs/acl.c +++ b/fs/f2fs/acl.c @@ -214,12 +214,10 @@ static int __f2fs_set_acl(struct inode *inode, int type, case ACL_TYPE_ACCESS: name_index = F2FS_XATTR_INDEX_POSIX_ACL_ACCESS; if (acl) { - error = posix_acl_equiv_mode(acl, &inode->i_mode); - if (error < 0) + error = posix_acl_update_mode(inode, &inode->i_mode, &acl); + if (error) return error; set_acl_inode(fi, inode->i_mode); - if (error == 0) - acl = NULL; } break; diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c index f5388f37217e..bb73d0a0f387 100644 --- a/fs/f2fs/debug.c +++ b/fs/f2fs/debug.c @@ -339,6 +339,7 @@ static int stat_open(struct inode *inode, struct file *file) } static const struct file_operations stat_fops = { + .owner = THIS_MODULE, .open = stat_open, .read = seq_read, .llseek = seq_lseek, diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 2b52e48d7482..85e40c0fdcc4 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -617,7 +617,7 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) struct f2fs_inode_info *fi = F2FS_I(inode); int err; - err = inode_change_ok(inode, attr); + err = setattr_prepare(dentry, attr); if (err) return err; diff --git a/fs/fat/file.c b/fs/fat/file.c index 442d50a0e33e..5d37650483c6 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -388,7 +388,7 @@ int fat_setattr(struct dentry *dentry, struct iattr *attr) attr->ia_valid &= ~TIMES_SET_FLAGS; } - error = inode_change_ok(inode, attr); + error = setattr_prepare(dentry, attr); attr->ia_valid = ia_valid; if (error) { if (sbi->options.quiet) diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 0572bca49f15..88b09a33d117 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1602,9 +1602,10 @@ int fuse_flush_times(struct inode *inode, struct fuse_file *ff) * vmtruncate() doesn't allow for this case, so do the rlimit checking * and the actual truncation by hand. */ -int fuse_do_setattr(struct inode *inode, struct iattr *attr, +int fuse_do_setattr(struct dentry *dentry, struct iattr *attr, struct file *file) { + struct inode *inode = d_inode(dentry); struct fuse_conn *fc = get_fuse_conn(inode); struct fuse_inode *fi = get_fuse_inode(inode); FUSE_ARGS(args); @@ -1619,7 +1620,7 @@ int fuse_do_setattr(struct inode *inode, struct iattr *attr, if (!(fc->flags & FUSE_DEFAULT_PERMISSIONS)) attr->ia_valid |= ATTR_FORCE; - err = inode_change_ok(inode, attr); + err = setattr_prepare(dentry, attr); if (err) return err; @@ -1718,9 +1719,9 @@ static int fuse_setattr(struct dentry *entry, struct iattr *attr) return -EACCES; if (attr->ia_valid & ATTR_FILE) - return fuse_do_setattr(inode, attr, attr->ia_file); + return fuse_do_setattr(entry, attr, attr->ia_file); else - return fuse_do_setattr(inode, attr, NULL); + return fuse_do_setattr(entry, attr, NULL); } static int fuse_getattr(struct vfsmount *mnt, struct dentry *entry, diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 5cae35490b37..1f03f0a36e35 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -540,13 +540,13 @@ void fuse_read_fill(struct fuse_req *req, struct file *file, loff_t pos, req->out.args[0].size = count; } -static void fuse_release_user_pages(struct fuse_req *req, int write) +static void fuse_release_user_pages(struct fuse_req *req, bool should_dirty) { unsigned i; for (i = 0; i < req->num_pages; i++) { struct page *page = req->pages[i]; - if (write) + if (should_dirty) set_page_dirty_lock(page); put_page(page); } @@ -1331,6 +1331,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter, loff_t *ppos, int flags) { int write = flags & FUSE_DIO_WRITE; + bool should_dirty = !write && iter_is_iovec(iter); int cuse = flags & FUSE_DIO_CUSE; struct file *file = io->file; struct inode *inode = file->f_mapping->host; @@ -1375,7 +1376,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter, nres = fuse_send_read(req, io, pos, nbytes, owner); if (!io->async) - fuse_release_user_pages(req, !write); + fuse_release_user_pages(req, should_dirty); if (req->out.h.error) { if (!res) res = req->out.h.error; @@ -2796,7 +2797,7 @@ static void fuse_do_truncate(struct file *file) attr.ia_file = file; attr.ia_valid |= ATTR_FILE; - fuse_do_setattr(inode, &attr, file); + fuse_do_setattr(file->f_path.dentry, &attr, file); } static inline loff_t fuse_round_up(loff_t off) diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 85f9d8273455..30d2bde45f68 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -913,7 +913,7 @@ bool fuse_write_update_size(struct inode *inode, loff_t pos); int fuse_flush_times(struct inode *inode, struct fuse_file *ff); int fuse_write_inode(struct inode *inode, struct writeback_control *wbc); -int fuse_do_setattr(struct inode *inode, struct iattr *attr, +int fuse_do_setattr(struct dentry *dentry, struct iattr *attr, struct file *file); void fuse_set_initialized(struct fuse_conn *fc); diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c index 1be3b061c05c..ff0ac96a8e7b 100644 --- a/fs/gfs2/acl.c +++ b/fs/gfs2/acl.c @@ -79,17 +79,11 @@ int gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type) if (type == ACL_TYPE_ACCESS) { umode_t mode = inode->i_mode; - error = posix_acl_equiv_mode(acl, &mode); - if (error < 0) + error = posix_acl_update_mode(inode, &inode->i_mode, &acl); + if (error) return error; - - if (error == 0) - acl = NULL; - - if (mode != inode->i_mode) { - inode->i_mode = mode; + if (mode != inode->i_mode) mark_inode_dirty(inode); - } } if (acl) { diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 1b3ca7a2e3fc..6f7f848a3c4e 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -1759,7 +1759,7 @@ static int gfs2_setattr(struct dentry *dentry, struct iattr *attr) if (IS_IMMUTABLE(inode) || IS_APPEND(inode)) goto out; - error = inode_change_ok(inode, attr); + error = setattr_prepare(dentry, attr); if (error) goto out; diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index b99ebddb10cb..6409b8b4afd4 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -604,7 +604,7 @@ int hfs_inode_setattr(struct dentry *dentry, struct iattr * attr) struct hfs_sb_info *hsb = HFS_SB(inode->i_sb); int error; - error = inode_change_ok(inode, attr); /* basic permission checks */ + error = setattr_prepare(dentry, attr); /* basic permission checks */ if (error) return error; diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index 6dd107d7421e..d87c8a27e063 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -246,7 +246,7 @@ static int hfsplus_setattr(struct dentry *dentry, struct iattr *attr) struct inode *inode = d_inode(dentry); int error; - error = inode_change_ok(inode, attr); + error = setattr_prepare(dentry, attr); if (error) return error; diff --git a/fs/hfsplus/posix_acl.c b/fs/hfsplus/posix_acl.c index df0c9af68d05..71b3087b7e32 100644 --- a/fs/hfsplus/posix_acl.c +++ b/fs/hfsplus/posix_acl.c @@ -68,8 +68,8 @@ int hfsplus_set_posix_acl(struct inode *inode, struct posix_acl *acl, case ACL_TYPE_ACCESS: xattr_name = POSIX_ACL_XATTR_ACCESS; if (acl) { - err = posix_acl_equiv_mode(acl, &inode->i_mode); - if (err < 0) + err = posix_acl_update_mode(inode, &inode->i_mode, &acl); + if (err) return err; } err = 0; diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index f895a85d9304..81ce4e4ad0f9 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -812,7 +812,7 @@ static int hostfs_setattr(struct dentry *dentry, struct iattr *attr) int fd = HOSTFS_I(inode)->fd; - err = inode_change_ok(inode, attr); + err = setattr_prepare(dentry, attr); if (err) return err; diff --git a/fs/hpfs/inode.c b/fs/hpfs/inode.c index 933c73780813..efbed9520fdc 100644 --- a/fs/hpfs/inode.c +++ b/fs/hpfs/inode.c @@ -272,7 +272,7 @@ int hpfs_setattr(struct dentry *dentry, struct iattr *attr) if ((attr->ia_valid & ATTR_SIZE) && attr->ia_size > inode->i_size) goto out_unlock; - error = inode_change_ok(inode, attr); + error = setattr_prepare(dentry, attr); if (error) goto out_unlock; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 87724c1d7be6..a533d8c66489 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -400,7 +400,7 @@ static int hugetlbfs_setattr(struct dentry *dentry, struct iattr *attr) BUG_ON(!inode); - error = inode_change_ok(inode, attr); + error = setattr_prepare(dentry, attr); if (error) return error; diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index d67a16f2a45d..350f67fb5b9c 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -690,6 +690,11 @@ static int isofs_fill_super(struct super_block *s, void *data, int silent) pri_bh = NULL; root_found: + /* We don't support read-write mounts */ + if (!(s->s_flags & MS_RDONLY)) { + error = -EACCES; + goto out_freebh; + } if (joliet_level && (pri == NULL || !opt.rock)) { /* This is the case of Joliet with the norock mount flag. @@ -1503,9 +1508,6 @@ struct inode *__isofs_iget(struct super_block *sb, static struct dentry *isofs_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data) { - /* We don't support read-write mounts */ - if (!(flags & MS_RDONLY)) - return ERR_PTR(-EACCES); return mount_bdev(fs_type, flags, dev_name, data, isofs_fill_super); } diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index ff2f2e6ad311..2abbb2babcae 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -1087,6 +1087,7 @@ int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh) JBUFFER_TRACE(jh, "file as BJ_Reserved"); spin_lock(&journal->j_list_lock); __jbd2_journal_file_buffer(jh, transaction, BJ_Reserved); + spin_unlock(&journal->j_list_lock); } else if (jh->b_transaction == journal->j_committing_transaction) { /* first access by this transaction */ jh->b_modified = 0; @@ -1094,8 +1095,8 @@ int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh) JBUFFER_TRACE(jh, "set next transaction"); spin_lock(&journal->j_list_lock); jh->b_next_transaction = transaction; + spin_unlock(&journal->j_list_lock); } - spin_unlock(&journal->j_list_lock); jbd_unlock_bh_state(bh); /* diff --git a/fs/jffs2/acl.c b/fs/jffs2/acl.c index 2f7a3c090489..f9f86f87d32b 100644 --- a/fs/jffs2/acl.c +++ b/fs/jffs2/acl.c @@ -235,9 +235,10 @@ int jffs2_set_acl(struct inode *inode, struct posix_acl *acl, int type) case ACL_TYPE_ACCESS: xprefix = JFFS2_XPREFIX_ACL_ACCESS; if (acl) { - umode_t mode = inode->i_mode; - rc = posix_acl_equiv_mode(acl, &mode); - if (rc < 0) + umode_t mode; + + rc = posix_acl_update_mode(inode, &mode, &acl); + if (rc) return rc; if (inode->i_mode != mode) { struct iattr attr; @@ -249,8 +250,6 @@ int jffs2_set_acl(struct inode *inode, struct posix_acl *acl, int type) if (rc < 0) return rc; } - if (rc == 0) - acl = NULL; } break; case ACL_TYPE_DEFAULT: diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c index fe5ea080b4ec..6273abad377f 100644 --- a/fs/jffs2/fs.c +++ b/fs/jffs2/fs.c @@ -193,7 +193,7 @@ int jffs2_setattr(struct dentry *dentry, struct iattr *iattr) struct inode *inode = d_inode(dentry); int rc; - rc = inode_change_ok(inode, iattr); + rc = setattr_prepare(dentry, iattr); if (rc) return rc; diff --git a/fs/jfs/acl.c b/fs/jfs/acl.c index 0c8ca830b113..9fad9f4fe883 100644 --- a/fs/jfs/acl.c +++ b/fs/jfs/acl.c @@ -84,13 +84,11 @@ static int __jfs_set_acl(tid_t tid, struct inode *inode, int type, case ACL_TYPE_ACCESS: ea_name = POSIX_ACL_XATTR_ACCESS; if (acl) { - rc = posix_acl_equiv_mode(acl, &inode->i_mode); - if (rc < 0) + rc = posix_acl_update_mode(inode, &inode->i_mode, &acl); + if (rc) return rc; inode->i_ctime = CURRENT_TIME; mark_inode_dirty(inode); - if (rc == 0) - acl = NULL; } break; case ACL_TYPE_DEFAULT: diff --git a/fs/jfs/file.c b/fs/jfs/file.c index e98d39d75cf4..66d6362a9007 100644 --- a/fs/jfs/file.c +++ b/fs/jfs/file.c @@ -103,7 +103,7 @@ int jfs_setattr(struct dentry *dentry, struct iattr *iattr) struct inode *inode = d_inode(dentry); int rc; - rc = inode_change_ok(inode, iattr); + rc = setattr_prepare(dentry, iattr); if (rc) return rc; diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index 2bacb9988566..9ff28bc294c0 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -834,21 +834,35 @@ repeat: mutex_lock(&kernfs_mutex); list_for_each_entry(info, &kernfs_root(kn)->supers, node) { + struct kernfs_node *parent; struct inode *inode; - struct dentry *dentry; + /* + * We want fsnotify_modify() on @kn but as the + * modifications aren't originating from userland don't + * have the matching @file available. Look up the inodes + * and generate the events manually. + */ inode = ilookup(info->sb, kn->ino); if (!inode) continue; - dentry = d_find_any_alias(inode); - if (dentry) { - fsnotify_parent(NULL, dentry, FS_MODIFY); - fsnotify(inode, FS_MODIFY, inode, FSNOTIFY_EVENT_INODE, - NULL, 0); - dput(dentry); + parent = kernfs_get_parent(kn); + if (parent) { + struct inode *p_inode; + + p_inode = ilookup(info->sb, parent->ino); + if (p_inode) { + fsnotify(p_inode, FS_MODIFY | FS_EVENT_ON_CHILD, + inode, FSNOTIFY_EVENT_INODE, kn->name, 0); + iput(p_inode); + } + + kernfs_put(parent); } + fsnotify(inode, FS_MODIFY, inode, FSNOTIFY_EVENT_INODE, + kn->name, 0); iput(inode); } diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index 756dd56aaf60..a17c850a4958 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -119,7 +119,7 @@ int kernfs_iop_setattr(struct dentry *dentry, struct iattr *iattr) return -EINVAL; mutex_lock(&kernfs_mutex); - error = inode_change_ok(inode, iattr); + error = setattr_prepare(dentry, iattr); if (error) goto out; diff --git a/fs/libfs.c b/fs/libfs.c index f4641fd27bda..50edbdc23cef 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -371,7 +371,7 @@ int simple_setattr(struct dentry *dentry, struct iattr *iattr) struct inode *inode = d_inode(dentry); int error; - error = inode_change_ok(inode, iattr); + error = setattr_prepare(dentry, iattr); if (error) return error; diff --git a/fs/logfs/file.c b/fs/logfs/file.c index 1a6f0167b16a..3abe1414c3f4 100644 --- a/fs/logfs/file.c +++ b/fs/logfs/file.c @@ -244,7 +244,7 @@ static int logfs_setattr(struct dentry *dentry, struct iattr *attr) struct inode *inode = d_inode(dentry); int err = 0; - err = inode_change_ok(inode, attr); + err = setattr_prepare(dentry, attr); if (err) return err; diff --git a/fs/minix/file.c b/fs/minix/file.c index 94f0eb9a6e2c..a6a4797aa0d4 100644 --- a/fs/minix/file.c +++ b/fs/minix/file.c @@ -26,7 +26,7 @@ static int minix_setattr(struct dentry *dentry, struct iattr *attr) struct inode *inode = d_inode(dentry); int error; - error = inode_change_ok(inode, attr); + error = setattr_prepare(dentry, attr); if (error) return error; diff --git a/fs/mount.h b/fs/mount.h index 6a61c2b3e385..2152c16ddf74 100644 --- a/fs/mount.h +++ b/fs/mount.h @@ -13,6 +13,8 @@ struct mnt_namespace { u64 seq; /* Sequence number to prevent loops */ wait_queue_head_t poll; u64 event; + unsigned int mounts; /* # of mounts in the namespace */ + unsigned int pending_mounts; }; struct mnt_pcp { diff --git a/fs/namespace.c b/fs/namespace.c index 556721fb0cf6..c46921daca22 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -27,6 +27,9 @@ #include "pnode.h" #include "internal.h" +/* Maximum number of mounts in a mount namespace */ +unsigned int sysctl_mount_max __read_mostly = 100000; + static unsigned int m_hash_mask __read_mostly; static unsigned int m_hash_shift __read_mostly; static unsigned int mp_hash_mask __read_mostly; @@ -732,26 +735,50 @@ static struct mountpoint *lookup_mountpoint(struct dentry *dentry) return NULL; } -static struct mountpoint *new_mountpoint(struct dentry *dentry) +static struct mountpoint *get_mountpoint(struct dentry *dentry) { - struct hlist_head *chain = mp_hash(dentry); - struct mountpoint *mp; + struct mountpoint *mp, *new = NULL; int ret; - mp = kmalloc(sizeof(struct mountpoint), GFP_KERNEL); - if (!mp) + if (d_mountpoint(dentry)) { +mountpoint: + read_seqlock_excl(&mount_lock); + mp = lookup_mountpoint(dentry); + read_sequnlock_excl(&mount_lock); + if (mp) + goto done; + } + + if (!new) + new = kmalloc(sizeof(struct mountpoint), GFP_KERNEL); + if (!new) return ERR_PTR(-ENOMEM); + + /* Exactly one processes may set d_mounted */ ret = d_set_mounted(dentry); - if (ret) { - kfree(mp); - return ERR_PTR(ret); - } - mp->m_dentry = dentry; - mp->m_count = 1; - hlist_add_head(&mp->m_hash, chain); - INIT_HLIST_HEAD(&mp->m_list); + /* Someone else set d_mounted? */ + if (ret == -EBUSY) + goto mountpoint; + + /* The dentry is not available as a mountpoint? */ + mp = ERR_PTR(ret); + if (ret) + goto done; + + /* Add the new mountpoint to the hash table */ + read_seqlock_excl(&mount_lock); + new->m_dentry = dentry; + new->m_count = 1; + hlist_add_head(&new->m_hash, mp_hash(dentry)); + INIT_HLIST_HEAD(&new->m_list); + read_sequnlock_excl(&mount_lock); + + mp = new; + new = NULL; +done: + kfree(new); return mp; } @@ -888,6 +915,9 @@ static void commit_tree(struct mount *mnt, struct mount *shadows) list_splice(&head, n->list.prev); + n->mounts += n->pending_mounts; + n->pending_mounts = 0; + attach_shadowed(mnt, parent, shadows); touch_mnt_namespace(n); } @@ -1408,11 +1438,16 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how) propagate_umount(&tmp_list); while (!list_empty(&tmp_list)) { + struct mnt_namespace *ns; bool disconnect; p = list_first_entry(&tmp_list, struct mount, mnt_list); list_del_init(&p->mnt_expire); list_del_init(&p->mnt_list); - __touch_mnt_namespace(p->mnt_ns); + ns = p->mnt_ns; + if (ns) { + ns->mounts--; + __touch_mnt_namespace(ns); + } p->mnt_ns = NULL; if (how & UMOUNT_SYNC) p->mnt.mnt_flags |= MNT_SYNC_UMOUNT; @@ -1546,11 +1581,11 @@ void __detach_mounts(struct dentry *dentry) struct mount *mnt; namespace_lock(); + lock_mount_hash(); mp = lookup_mountpoint(dentry); if (IS_ERR_OR_NULL(mp)) goto out_unlock; - lock_mount_hash(); event++; while (!hlist_empty(&mp->m_list)) { mnt = hlist_entry(mp->m_list.first, struct mount, mnt_mp_list); @@ -1560,9 +1595,9 @@ void __detach_mounts(struct dentry *dentry) } else umount_tree(mnt, UMOUNT_CONNECTED); } - unlock_mount_hash(); put_mountpoint(mp); out_unlock: + unlock_mount_hash(); namespace_unlock(); } @@ -1821,6 +1856,28 @@ static int invent_group_ids(struct mount *mnt, bool recurse) return 0; } +int count_mounts(struct mnt_namespace *ns, struct mount *mnt) +{ + unsigned int max = READ_ONCE(sysctl_mount_max); + unsigned int mounts = 0, old, pending, sum; + struct mount *p; + + for (p = mnt; p; p = next_mnt(p, mnt)) + mounts++; + + old = ns->mounts; + pending = ns->pending_mounts; + sum = old + pending; + if ((old > sum) || + (pending > sum) || + (max < sum) || + (mounts > (max - sum))) + return -ENOSPC; + + ns->pending_mounts = pending + mounts; + return 0; +} + /* * @source_mnt : mount tree to be attached * @nd : place the mount tree @source_mnt is attached @@ -1890,10 +1947,18 @@ static int attach_recursive_mnt(struct mount *source_mnt, struct path *parent_path) { HLIST_HEAD(tree_list); + struct mnt_namespace *ns = dest_mnt->mnt_ns; struct mount *child, *p; struct hlist_node *n; int err; + /* Is there space to add these mounts to the mount namespace? */ + if (!parent_path) { + err = count_mounts(ns, source_mnt); + if (err) + goto out; + } + if (IS_MNT_SHARED(dest_mnt)) { err = invent_group_ids(source_mnt, true); if (err) @@ -1930,11 +1995,13 @@ static int attach_recursive_mnt(struct mount *source_mnt, out_cleanup_ids: while (!hlist_empty(&tree_list)) { child = hlist_entry(tree_list.first, struct mount, mnt_hash); + child->mnt_parent->mnt_ns->pending_mounts = 0; umount_tree(child, UMOUNT_SYNC); } unlock_mount_hash(); cleanup_group_ids(source_mnt, NULL); out: + ns->pending_mounts = 0; return err; } @@ -1951,9 +2018,7 @@ retry: namespace_lock(); mnt = lookup_mnt(path); if (likely(!mnt)) { - struct mountpoint *mp = lookup_mountpoint(dentry); - if (!mp) - mp = new_mountpoint(dentry); + struct mountpoint *mp = get_mountpoint(dentry); if (IS_ERR(mp)) { namespace_unlock(); mutex_unlock(&dentry->d_inode->i_mutex); @@ -1972,7 +2037,11 @@ retry: static void unlock_mount(struct mountpoint *where) { struct dentry *dentry = where->m_dentry; + + read_seqlock_excl(&mount_lock); put_mountpoint(where); + read_sequnlock_excl(&mount_lock); + namespace_unlock(); mutex_unlock(&dentry->d_inode->i_mutex); } @@ -2758,6 +2827,8 @@ static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns) init_waitqueue_head(&new_ns->poll); new_ns->event = 0; new_ns->user_ns = get_user_ns(user_ns); + new_ns->mounts = 0; + new_ns->pending_mounts = 0; return new_ns; } @@ -2807,6 +2878,7 @@ struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns, q = new; while (p) { q->mnt_ns = new_ns; + new_ns->mounts++; if (new_fs) { if (&p->mnt == new_fs->root.mnt) { new_fs->root.mnt = mntget(&q->mnt); @@ -2845,6 +2917,7 @@ static struct mnt_namespace *create_mnt_ns(struct vfsmount *m) struct mount *mnt = real_mount(m); mnt->mnt_ns = new_ns; new_ns->root = mnt; + new_ns->mounts++; list_add(&mnt->mnt_list, &new_ns->list); } else { mntput(m); @@ -3044,9 +3117,9 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root, touch_mnt_namespace(current->nsproxy->mnt_ns); /* A moved mount should not expire automatically */ list_del_init(&new_mnt->mnt_expire); + put_mountpoint(root_mp); unlock_mount_hash(); chroot_fs_refs(&root, &new); - put_mountpoint(root_mp); error = 0; out4: unlock_mount(old_mp); diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c index 9605a2f63549..7b1261bc2dee 100644 --- a/fs/ncpfs/inode.c +++ b/fs/ncpfs/inode.c @@ -884,7 +884,7 @@ int ncp_notify_change(struct dentry *dentry, struct iattr *attr) /* ageing the dentry to force validation */ ncp_age_dentry(server, dentry); - result = inode_change_ok(inode, attr); + result = setattr_prepare(dentry, attr); if (result < 0) goto out; diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index 8d129bb7355a..a78558a25035 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -303,6 +303,7 @@ static int nfs_callback_up_net(int minorversion, struct svc_serv *serv, struct n err_socks: svc_rpcb_cleanup(serv, net); err_bind: + nn->cb_users[minorversion]--; dprintk("NFS: Couldn't create callback socket: err = %d; " "net = %p\n", ret, net); return ret; diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 8b8d83a526ce..ddf5f9fd719f 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -414,7 +414,7 @@ static int nfs_write_end(struct file *file, struct address_space *mapping, */ if (!PageUptodate(page)) { unsigned pglen = nfs_page_length(page); - unsigned end = offset + len; + unsigned end = offset + copied; if (pglen == 0) { zero_user_segments(page, 0, offset, diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index eef16ec0638a..319ba6814899 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -7281,12 +7281,20 @@ static int _nfs4_proc_create_session(struct nfs_client *clp, status = rpc_call_sync(session->clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT); trace_nfs4_create_session(clp, status); + switch (status) { + case -NFS4ERR_STALE_CLIENTID: + case -NFS4ERR_DELAY: + case -ETIMEDOUT: + case -EACCES: + case -EAGAIN: + goto out; + }; + + clp->cl_seqid++; if (!status) { /* Verify the session's negotiated channel_attrs values */ status = nfs4_verify_channel_attrs(&args, &res); /* Increment the clientid slot sequence id */ - if (clp->cl_seqid == res.seqid) - clp->cl_seqid++; if (status) goto out; nfs4_update_session(session, &res); diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index ddef1dc80cf7..2a9ab265aa32 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1073,6 +1073,7 @@ static void nfs_increment_seqid(int status, struct nfs_seqid *seqid) case -NFS4ERR_BADXDR: case -NFS4ERR_RESOURCE: case -NFS4ERR_NOFILEHANDLE: + case -NFS4ERR_MOVED: /* Non-seqid mutating errors */ return; }; diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index d47c188682b1..ea4fe630cdac 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1472,6 +1472,7 @@ pnfs_update_layout(struct inode *ino, goto out; lookup_again: + nfs4_client_recover_expired_lease(clp); first = false; spin_lock(&ino->i_lock); lo = pnfs_find_alloc_layout(ino, ctx, gfp_flags); diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index 6904213a4363..8b6ec3eab627 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -189,10 +189,11 @@ nfsd4_alloc_layout_stateid(struct nfsd4_compound_state *cstate, struct nfs4_layout_stateid *ls; struct nfs4_stid *stp; - stp = nfs4_alloc_stid(cstate->clp, nfs4_layout_stateid_cache); + stp = nfs4_alloc_stid(cstate->clp, nfs4_layout_stateid_cache, + nfsd4_free_layout_stateid); if (!stp) return NULL; - stp->sc_free = nfsd4_free_layout_stateid; + get_nfs4_file(fp); stp->sc_file = fp; diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index bb6c324f1f3d..22e9799323ad 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -553,8 +553,8 @@ out: return co; } -struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, - struct kmem_cache *slab) +struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *slab, + void (*sc_free)(struct nfs4_stid *)) { struct nfs4_stid *stid; int new_id; @@ -570,6 +570,8 @@ struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, idr_preload_end(); if (new_id < 0) goto out_free; + + stid->sc_free = sc_free; stid->sc_client = cl; stid->sc_stateid.si_opaque.so_id = new_id; stid->sc_stateid.si_opaque.so_clid = cl->cl_clientid; @@ -594,15 +596,12 @@ out_free: static struct nfs4_ol_stateid * nfs4_alloc_open_stateid(struct nfs4_client *clp) { struct nfs4_stid *stid; - struct nfs4_ol_stateid *stp; - stid = nfs4_alloc_stid(clp, stateid_slab); + stid = nfs4_alloc_stid(clp, stateid_slab, nfs4_free_ol_stateid); if (!stid) return NULL; - stp = openlockstateid(stid); - stp->st_stid.sc_free = nfs4_free_ol_stateid; - return stp; + return openlockstateid(stid); } static void nfs4_free_deleg(struct nfs4_stid *stid) @@ -700,11 +699,10 @@ alloc_init_deleg(struct nfs4_client *clp, struct svc_fh *current_fh, goto out_dec; if (delegation_blocked(¤t_fh->fh_handle)) goto out_dec; - dp = delegstateid(nfs4_alloc_stid(clp, deleg_slab)); + dp = delegstateid(nfs4_alloc_stid(clp, deleg_slab, nfs4_free_deleg)); if (dp == NULL) goto out_dec; - dp->dl_stid.sc_free = nfs4_free_deleg; /* * delegation seqid's are never incremented. The 4.1 special * meaning of seqid 0 isn't meaningful, really, but let's avoid @@ -5309,7 +5307,6 @@ init_lock_stateid(struct nfs4_ol_stateid *stp, struct nfs4_lockowner *lo, stp->st_stateowner = nfs4_get_stateowner(&lo->lo_owner); get_nfs4_file(fp); stp->st_stid.sc_file = fp; - stp->st_stid.sc_free = nfs4_free_lock_stateid; stp->st_access_bmap = 0; stp->st_deny_bmap = open_stp->st_deny_bmap; stp->st_openstp = open_stp; @@ -5352,7 +5349,7 @@ find_or_create_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fi, lst = find_lock_stateid(lo, fi); if (lst == NULL) { spin_unlock(&clp->cl_lock); - ns = nfs4_alloc_stid(clp, stateid_slab); + ns = nfs4_alloc_stid(clp, stateid_slab, nfs4_free_lock_stateid); if (ns == NULL) return NULL; diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index aecbcd34d336..44f6f4f5eee0 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -59,13 +59,59 @@ static __be32 nfsd_proc_setattr(struct svc_rqst *rqstp, struct nfsd_sattrargs *argp, struct nfsd_attrstat *resp) { + struct iattr *iap = &argp->attrs; + struct svc_fh *fhp; __be32 nfserr; + dprintk("nfsd: SETATTR %s, valid=%x, size=%ld\n", SVCFH_fmt(&argp->fh), argp->attrs.ia_valid, (long) argp->attrs.ia_size); - fh_copy(&resp->fh, &argp->fh); - nfserr = nfsd_setattr(rqstp, &resp->fh, &argp->attrs,0, (time_t)0); + fhp = fh_copy(&resp->fh, &argp->fh); + + /* + * NFSv2 does not differentiate between "set-[ac]time-to-now" + * which only requires access, and "set-[ac]time-to-X" which + * requires ownership. + * So if it looks like it might be "set both to the same time which + * is close to now", and if setattr_prepare fails, then we + * convert to "set to now" instead of "set to explicit time" + * + * We only call setattr_prepare as the last test as technically + * it is not an interface that we should be using. + */ +#define BOTH_TIME_SET (ATTR_ATIME_SET | ATTR_MTIME_SET) +#define MAX_TOUCH_TIME_ERROR (30*60) + if ((iap->ia_valid & BOTH_TIME_SET) == BOTH_TIME_SET && + iap->ia_mtime.tv_sec == iap->ia_atime.tv_sec) { + /* + * Looks probable. + * + * Now just make sure time is in the right ballpark. + * Solaris, at least, doesn't seem to care what the time + * request is. We require it be within 30 minutes of now. + */ + time_t delta = iap->ia_atime.tv_sec - get_seconds(); + + nfserr = fh_verify(rqstp, fhp, 0, NFSD_MAY_NOP); + if (nfserr) + goto done; + + if (delta < 0) + delta = -delta; + if (delta < MAX_TOUCH_TIME_ERROR && + setattr_prepare(fhp->fh_dentry, iap) != 0) { + /* + * Turn off ATTR_[AM]TIME_SET but leave ATTR_[AM]TIME. + * This will cause notify_change to set these times + * to "now" + */ + iap->ia_valid &= ~BOTH_TIME_SET; + } + } + + nfserr = nfsd_setattr(rqstp, fhp, iap, 0, (time_t)0); +done: return nfsd_return_attrs(nfserr, resp); } diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 67685b6cfef3..fa2430e3d6a8 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -589,8 +589,8 @@ extern __be32 nfs4_preprocess_stateid_op(struct net *net, __be32 nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate, stateid_t *stateid, unsigned char typemask, struct nfs4_stid **s, struct nfsd_net *nn); -struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, - struct kmem_cache *slab); +struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *slab, + void (*sc_free)(struct nfs4_stid *)); void nfs4_unhash_stid(struct nfs4_stid *s); void nfs4_put_stid(struct nfs4_stid *s); void nfs4_remove_reclaim_record(struct nfs4_client_reclaim *, struct nfsd_net *); diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 84d770be056e..92de3747ea8b 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -302,42 +302,6 @@ commit_metadata(struct svc_fh *fhp) static void nfsd_sanitize_attrs(struct inode *inode, struct iattr *iap) { - /* - * NFSv2 does not differentiate between "set-[ac]time-to-now" - * which only requires access, and "set-[ac]time-to-X" which - * requires ownership. - * So if it looks like it might be "set both to the same time which - * is close to now", and if inode_change_ok fails, then we - * convert to "set to now" instead of "set to explicit time" - * - * We only call inode_change_ok as the last test as technically - * it is not an interface that we should be using. - */ -#define BOTH_TIME_SET (ATTR_ATIME_SET | ATTR_MTIME_SET) -#define MAX_TOUCH_TIME_ERROR (30*60) - if ((iap->ia_valid & BOTH_TIME_SET) == BOTH_TIME_SET && - iap->ia_mtime.tv_sec == iap->ia_atime.tv_sec) { - /* - * Looks probable. - * - * Now just make sure time is in the right ballpark. - * Solaris, at least, doesn't seem to care what the time - * request is. We require it be within 30 minutes of now. - */ - time_t delta = iap->ia_atime.tv_sec - get_seconds(); - if (delta < 0) - delta = -delta; - if (delta < MAX_TOUCH_TIME_ERROR && - inode_change_ok(inode, iap) != 0) { - /* - * Turn off ATTR_[AM]TIME_SET but leave ATTR_[AM]TIME. - * This will cause notify_change to set these times - * to "now" - */ - iap->ia_valid &= ~BOTH_TIME_SET; - } - } - /* sanitize the mode change */ if (iap->ia_valid & ATTR_MODE) { iap->ia_mode &= S_IALLUGO; diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 258d9fe2521a..b40df2bb5ee4 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -839,7 +839,7 @@ int nilfs_setattr(struct dentry *dentry, struct iattr *iattr) struct super_block *sb = inode->i_sb; int err; - err = inode_change_ok(inode, iattr); + err = setattr_prepare(dentry, iattr); if (err) return err; diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index d2f97ecca6a5..e0e5f7c3c99f 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -67,18 +67,7 @@ static int fanotify_get_response(struct fsnotify_group *group, pr_debug("%s: group=%p event=%p\n", __func__, group, event); - wait_event(group->fanotify_data.access_waitq, event->response || - atomic_read(&group->fanotify_data.bypass_perm)); - - if (!event->response) { /* bypass_perm set */ - /* - * Event was canceled because group is being destroyed. Remove - * it from group's event list because we are responsible for - * freeing the permission event. - */ - fsnotify_remove_event(group, &event->fae.fse); - return 0; - } + wait_event(group->fanotify_data.access_waitq, event->response); /* userspace responded, convert to something usable */ switch (event->response) { diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index cf275500a665..45ca844d1323 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -358,16 +358,20 @@ static int fanotify_release(struct inode *ignored, struct file *file) #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS struct fanotify_perm_event_info *event, *next; + struct fsnotify_event *fsn_event; /* - * There may be still new events arriving in the notification queue - * but since userspace cannot use fanotify fd anymore, no event can - * enter or leave access_list by now. + * Stop new events from arriving in the notification queue. since + * userspace cannot use fanotify fd anymore, no event can enter or + * leave access_list by now either. */ - spin_lock(&group->fanotify_data.access_lock); - - atomic_inc(&group->fanotify_data.bypass_perm); + fsnotify_group_stop_queueing(group); + /* + * Process all permission events on access_list and notification queue + * and simulate reply from userspace. + */ + spin_lock(&group->fanotify_data.access_lock); list_for_each_entry_safe(event, next, &group->fanotify_data.access_list, fae.fse.list) { pr_debug("%s: found group=%p event=%p\n", __func__, group, @@ -379,12 +383,21 @@ static int fanotify_release(struct inode *ignored, struct file *file) spin_unlock(&group->fanotify_data.access_lock); /* - * Since bypass_perm is set, newly queued events will not wait for - * access response. Wake up the already sleeping ones now. - * synchronize_srcu() in fsnotify_destroy_group() will wait for all - * processes sleeping in fanotify_handle_event() waiting for access - * response and thus also for all permission events to be freed. + * Destroy all non-permission events. For permission events just + * dequeue them and set the response. They will be freed once the + * response is consumed and fanotify_get_response() returns. */ + mutex_lock(&group->notification_mutex); + while (!fsnotify_notify_queue_is_empty(group)) { + fsn_event = fsnotify_remove_first_event(group); + if (!(fsn_event->mask & FAN_ALL_PERM_EVENTS)) + fsnotify_destroy_event(group, fsn_event); + else + FANOTIFY_PE(fsn_event)->response = FAN_ALLOW; + } + mutex_unlock(&group->notification_mutex); + + /* Response for all permission events it set, wakeup waiters */ wake_up(&group->fanotify_data.access_waitq); #endif @@ -751,7 +764,6 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) spin_lock_init(&group->fanotify_data.access_lock); init_waitqueue_head(&group->fanotify_data.access_waitq); INIT_LIST_HEAD(&group->fanotify_data.access_list); - atomic_set(&group->fanotify_data.bypass_perm, 0); #endif switch (flags & FAN_ALL_CLASS_BITS) { case FAN_CLASS_NOTIF: diff --git a/fs/notify/group.c b/fs/notify/group.c index d16b62cb2854..18eb30c6bd8f 100644 --- a/fs/notify/group.c +++ b/fs/notify/group.c @@ -40,6 +40,17 @@ static void fsnotify_final_destroy_group(struct fsnotify_group *group) } /* + * Stop queueing new events for this group. Once this function returns + * fsnotify_add_event() will not add any new events to the group's queue. + */ +void fsnotify_group_stop_queueing(struct fsnotify_group *group) +{ + mutex_lock(&group->notification_mutex); + group->shutdown = true; + mutex_unlock(&group->notification_mutex); +} + +/* * Trying to get rid of a group. Remove all marks, flush all events and release * the group reference. * Note that another thread calling fsnotify_clear_marks_by_group() may still @@ -47,6 +58,14 @@ static void fsnotify_final_destroy_group(struct fsnotify_group *group) */ void fsnotify_destroy_group(struct fsnotify_group *group) { + /* + * Stop queueing new events. The code below is careful enough to not + * require this but fanotify needs to stop queuing events even before + * fsnotify_destroy_group() is called and this makes the other callers + * of fsnotify_destroy_group() to see the same behavior. + */ + fsnotify_group_stop_queueing(group); + /* clear all inode marks for this group */ fsnotify_clear_marks_by_group(group); diff --git a/fs/notify/notification.c b/fs/notify/notification.c index a95d8e037aeb..e455e83ceeeb 100644 --- a/fs/notify/notification.c +++ b/fs/notify/notification.c @@ -82,7 +82,8 @@ void fsnotify_destroy_event(struct fsnotify_group *group, * Add an event to the group notification queue. The group can later pull this * event off the queue to deal with. The function returns 0 if the event was * added to the queue, 1 if the event was merged with some other queued event, - * 2 if the queue of events has overflown. + * 2 if the event was not queued - either the queue of events has overflown + * or the group is shutting down. */ int fsnotify_add_event(struct fsnotify_group *group, struct fsnotify_event *event, @@ -96,6 +97,11 @@ int fsnotify_add_event(struct fsnotify_group *group, mutex_lock(&group->notification_mutex); + if (group->shutdown) { + mutex_unlock(&group->notification_mutex); + return 2; + } + if (group->q_len >= group->max_events) { ret = 2; /* Queue overflow event only if it isn't already queued */ @@ -126,21 +132,6 @@ queue: } /* - * Remove @event from group's notification queue. It is the responsibility of - * the caller to destroy the event. - */ -void fsnotify_remove_event(struct fsnotify_group *group, - struct fsnotify_event *event) -{ - mutex_lock(&group->notification_mutex); - if (!list_empty(&event->list)) { - list_del_init(&event->list); - group->q_len--; - } - mutex_unlock(&group->notification_mutex); -} - -/* * Remove and return the first event from the notification list. It is the * responsibility of the caller to destroy the obtained event */ diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c index d284f07eda77..c178763893f3 100644 --- a/fs/ntfs/inode.c +++ b/fs/ntfs/inode.c @@ -2893,7 +2893,7 @@ int ntfs_setattr(struct dentry *dentry, struct iattr *attr) int err; unsigned int ia_valid = attr->ia_valid; - err = inode_change_ok(vi, attr); + err = setattr_prepare(dentry, attr); if (err) goto out; /* We do not support NTFS ACLs yet. */ diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c index 762e5a3aecd3..c7641f656494 100644 --- a/fs/ocfs2/acl.c +++ b/fs/ocfs2/acl.c @@ -241,13 +241,11 @@ int ocfs2_set_acl(handle_t *handle, case ACL_TYPE_ACCESS: name_index = OCFS2_XATTR_INDEX_POSIX_ACL_ACCESS; if (acl) { - umode_t mode = inode->i_mode; - ret = posix_acl_equiv_mode(acl, &mode); - if (ret < 0) - return ret; + umode_t mode; - if (ret == 0) - acl = NULL; + ret = posix_acl_update_mode(inode, &mode, &acl); + if (ret) + return ret; ret = ocfs2_acl_set_mode(inode, di_bh, handle, mode); diff --git a/fs/ocfs2/dlm/dlmconvert.c b/fs/ocfs2/dlm/dlmconvert.c index f90931335c6b..2e11658676eb 100644 --- a/fs/ocfs2/dlm/dlmconvert.c +++ b/fs/ocfs2/dlm/dlmconvert.c @@ -262,7 +262,6 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm, struct dlm_lock *lock, int flags, int type) { enum dlm_status status; - u8 old_owner = res->owner; mlog(0, "type=%d, convert_type=%d, busy=%d\n", lock->ml.type, lock->ml.convert_type, res->state & DLM_LOCK_RES_IN_PROGRESS); @@ -329,7 +328,6 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm, spin_lock(&res->spinlock); res->state &= ~DLM_LOCK_RES_IN_PROGRESS; - lock->convert_pending = 0; /* if it failed, move it back to granted queue. * if master returns DLM_NORMAL and then down before sending ast, * it may have already been moved to granted queue, reset to @@ -338,12 +336,14 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm, if (status != DLM_NOTQUEUED) dlm_error(status); dlm_revert_pending_convert(res, lock); - } else if ((res->state & DLM_LOCK_RES_RECOVERING) || - (old_owner != res->owner)) { - mlog(0, "res %.*s is in recovering or has been recovered.\n", - res->lockname.len, res->lockname.name); + } else if (!lock->convert_pending) { + mlog(0, "%s: res %.*s, owner died and lock has been moved back " + "to granted list, retry convert.\n", + dlm->name, res->lockname.len, res->lockname.name); status = DLM_RECOVERING; } + + lock->convert_pending = 0; bail: spin_unlock(&res->spinlock); diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c index b5cf27dcb18a..43ac2289c613 100644 --- a/fs/ocfs2/dlmfs/dlmfs.c +++ b/fs/ocfs2/dlmfs/dlmfs.c @@ -211,7 +211,7 @@ static int dlmfs_file_setattr(struct dentry *dentry, struct iattr *attr) struct inode *inode = d_inode(dentry); attr->ia_valid &= ~ATTR_SIZE; - error = inode_change_ok(inode, attr); + error = setattr_prepare(dentry, attr); if (error) return error; diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 3623ab6fa97f..4a4ac9386d4d 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -3322,6 +3322,16 @@ static int ocfs2_downconvert_lock(struct ocfs2_super *osb, mlog(ML_BASTS, "lockres %s, level %d => %d\n", lockres->l_name, lockres->l_level, new_level); + /* + * On DLM_LKF_VALBLK, fsdlm behaves differently with o2cb. It always + * expects DLM_LKF_VALBLK being set if the LKB has LVB, so that + * we can recover correctly from node failure. Otherwise, we may get + * invalid LVB in LKB, but without DLM_SBF_VALNOTVALID being set. + */ + if (!ocfs2_is_o2cb_active() && + lockres->l_ops->flags & LOCK_TYPE_USES_LVB) + lvb = 1; + if (lvb) dlm_flags |= DLM_LKF_VALBLK; diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 3f1ee404f40f..bc06b982e9ea 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1150,7 +1150,7 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr) if (!(attr->ia_valid & OCFS2_VALID_ATTRS)) return 0; - status = inode_change_ok(inode, attr); + status = setattr_prepare(dentry, attr); if (status) return status; @@ -1522,7 +1522,8 @@ static int ocfs2_zero_partial_clusters(struct inode *inode, u64 start, u64 len) { int ret = 0; - u64 tmpend, end = start + len; + u64 tmpend = 0; + u64 end = start + len; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); unsigned int csize = osb->s_clustersize; handle_t *handle; @@ -1554,18 +1555,31 @@ static int ocfs2_zero_partial_clusters(struct inode *inode, } /* - * We want to get the byte offset of the end of the 1st cluster. + * If start is on a cluster boundary and end is somewhere in another + * cluster, we have not COWed the cluster starting at start, unless + * end is also within the same cluster. So, in this case, we skip this + * first call to ocfs2_zero_range_for_truncate() truncate and move on + * to the next one. */ - tmpend = (u64)osb->s_clustersize + (start & ~(osb->s_clustersize - 1)); - if (tmpend > end) - tmpend = end; + if ((start & (csize - 1)) != 0) { + /* + * We want to get the byte offset of the end of the 1st + * cluster. + */ + tmpend = (u64)osb->s_clustersize + + (start & ~(osb->s_clustersize - 1)); + if (tmpend > end) + tmpend = end; - trace_ocfs2_zero_partial_clusters_range1((unsigned long long)start, - (unsigned long long)tmpend); + trace_ocfs2_zero_partial_clusters_range1( + (unsigned long long)start, + (unsigned long long)tmpend); - ret = ocfs2_zero_range_for_truncate(inode, handle, start, tmpend); - if (ret) - mlog_errno(ret); + ret = ocfs2_zero_range_for_truncate(inode, handle, start, + tmpend); + if (ret) + mlog_errno(ret); + } if (tmpend < end) { /* diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c index 5d965e83bd43..783bcdce5666 100644 --- a/fs/ocfs2/stackglue.c +++ b/fs/ocfs2/stackglue.c @@ -48,6 +48,12 @@ static char ocfs2_hb_ctl_path[OCFS2_MAX_HB_CTL_PATH] = "/sbin/ocfs2_hb_ctl"; */ static struct ocfs2_stack_plugin *active_stack; +inline int ocfs2_is_o2cb_active(void) +{ + return !strcmp(active_stack->sp_name, OCFS2_STACK_PLUGIN_O2CB); +} +EXPORT_SYMBOL_GPL(ocfs2_is_o2cb_active); + static struct ocfs2_stack_plugin *ocfs2_stack_lookup(const char *name) { struct ocfs2_stack_plugin *p; diff --git a/fs/ocfs2/stackglue.h b/fs/ocfs2/stackglue.h index 66334a30cea8..e1b30931974d 100644 --- a/fs/ocfs2/stackglue.h +++ b/fs/ocfs2/stackglue.h @@ -298,4 +298,7 @@ void ocfs2_stack_glue_set_max_proto_version(struct ocfs2_protocol_version *max_p int ocfs2_stack_glue_register(struct ocfs2_stack_plugin *plugin); void ocfs2_stack_glue_unregister(struct ocfs2_stack_plugin *plugin); +/* In ocfs2_downconvert_lock(), we need to know which stack we are using */ +int ocfs2_is_o2cb_active(void); + #endif /* STACKGLUE_H */ diff --git a/fs/omfs/file.c b/fs/omfs/file.c index d9e26cfbb793..bf83e6644333 100644 --- a/fs/omfs/file.c +++ b/fs/omfs/file.c @@ -349,7 +349,7 @@ static int omfs_setattr(struct dentry *dentry, struct iattr *attr) struct inode *inode = d_inode(dentry); int error; - error = inode_change_ok(inode, attr); + error = setattr_prepare(dentry, attr); if (error) return error; diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 758012bfd5f0..c57cd417802b 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -48,6 +48,8 @@ int ovl_copy_xattr(struct dentry *old, struct dentry *new) } for (name = buf; name < (buf + list_size); name += strlen(name) + 1) { + if (ovl_is_private_xattr(name)) + continue; retry: size = vfs_getxattr(old, name, value, value_size); if (size == -ERANGE) @@ -127,6 +129,8 @@ static int ovl_copy_up_data(struct path *old, struct path *new, loff_t len) len -= bytes; } + if (!error) + error = vfs_fsync(new_file, 0); fput(new_file); out_fput: fput(old_file); diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 97fd65700ae2..d293034ae2cb 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -54,7 +54,7 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr) * inode_newsize_ok() will always check against MAX_LFS_FILESIZE and not * check for a swapfile (which this won't be anyway). */ - err = inode_change_ok(dentry->d_inode, attr); + err = setattr_prepare(dentry, attr); if (err) return err; @@ -221,8 +221,7 @@ static int ovl_readlink(struct dentry *dentry, char __user *buf, int bufsiz) return realinode->i_op->readlink(realpath.dentry, buf, bufsiz); } - -static bool ovl_is_private_xattr(const char *name) +bool ovl_is_private_xattr(const char *name) { return strncmp(name, OVL_XATTR_PRE_NAME, OVL_XATTR_PRE_LEN) == 0; } @@ -280,7 +279,8 @@ ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size) struct path realpath; enum ovl_path_type type = ovl_path_real(dentry, &realpath); ssize_t res; - int off; + size_t len; + char *s; res = vfs_listxattr(realpath.dentry, list, size); if (res <= 0 || size == 0) @@ -290,17 +290,19 @@ ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size) return res; /* filter out private xattrs */ - for (off = 0; off < res;) { - char *s = list + off; - size_t slen = strlen(s) + 1; + for (s = list, len = res; len;) { + size_t slen = strnlen(s, len) + 1; - BUG_ON(off + slen > res); + /* underlying fs providing us with an broken xattr list? */ + if (WARN_ON(slen > len)) + return -EIO; + len -= slen; if (ovl_is_private_xattr(s)) { res -= slen; - memmove(s, s + slen, res - off); + memmove(s, s + slen, len); } else { - off += slen; + s += slen; } } diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index 983540910ba8..32b077b07085 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -174,6 +174,7 @@ ssize_t ovl_getxattr(struct dentry *dentry, const char *name, ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size); int ovl_removexattr(struct dentry *dentry, const char *name); struct inode *ovl_d_select_inode(struct dentry *dentry, unsigned file_flags); +bool ovl_is_private_xattr(const char *name); struct inode *ovl_new_inode(struct super_block *sb, umode_t mode, struct ovl_entry *oe); diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 39266655d2bd..f60b2c745d02 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -658,6 +658,10 @@ retry: struct kstat stat = { .mode = S_IFDIR | 0, }; + struct iattr attr = { + .ia_valid = ATTR_MODE, + .ia_mode = stat.mode, + }; if (work->d_inode) { err = -EEXIST; @@ -673,6 +677,21 @@ retry: err = ovl_create_real(dir, work, &stat, NULL, NULL, true); if (err) goto out_dput; + + err = vfs_removexattr(work, XATTR_NAME_POSIX_ACL_DEFAULT); + if (err && err != -ENODATA && err != -EOPNOTSUPP) + goto out_dput; + + err = vfs_removexattr(work, XATTR_NAME_POSIX_ACL_ACCESS); + if (err && err != -ENODATA && err != -EOPNOTSUPP) + goto out_dput; + + /* Clear any inherited mode bits */ + mutex_lock(&work->d_inode->i_mutex); + err = notify_change(work, &attr, NULL); + mutex_unlock(&work->d_inode->i_mutex); + if (err) + goto out_dput; } out_unlock: mutex_unlock(&dir->i_mutex); diff --git a/fs/pnode.c b/fs/pnode.c index 99899705b105..234a9ac49958 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -259,7 +259,7 @@ static int propagate_one(struct mount *m) read_sequnlock_excl(&mount_lock); } hlist_add_head(&child->mnt_hash, list); - return 0; + return count_mounts(m->mnt_ns, child); } /* diff --git a/fs/pnode.h b/fs/pnode.h index 0fcdbe7ca648..550f5a8b4fcf 100644 --- a/fs/pnode.h +++ b/fs/pnode.h @@ -52,4 +52,5 @@ void mnt_set_mountpoint(struct mount *, struct mountpoint *, struct mount *copy_tree(struct mount *, struct dentry *, int); bool is_path_reachable(struct mount *, struct dentry *, const struct path *root); +int count_mounts(struct mnt_namespace *ns, struct mount *mnt); #endif /* _LINUX_PNODE_H */ diff --git a/fs/posix_acl.c b/fs/posix_acl.c index a9dafa83678c..0ef1c3722504 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -598,6 +598,37 @@ no_mem: } EXPORT_SYMBOL_GPL(posix_acl_create); +/** + * posix_acl_update_mode - update mode in set_acl + * + * Update the file mode when setting an ACL: compute the new file permission + * bits based on the ACL. In addition, if the ACL is equivalent to the new + * file mode, set *acl to NULL to indicate that no ACL should be set. + * + * As with chmod, clear the setgit bit if the caller is not in the owning group + * or capable of CAP_FSETID (see inode_change_ok). + * + * Called from set_acl inode operations. + */ +int posix_acl_update_mode(struct inode *inode, umode_t *mode_p, + struct posix_acl **acl) +{ + umode_t mode = inode->i_mode; + int error; + + error = posix_acl_equiv_mode(*acl, &mode); + if (error < 0) + return error; + if (error == 0) + *acl = NULL; + if (!in_group_p(inode->i_gid) && + !capable_wrt_inode_uidgid(inode, CAP_FSETID)) + mode &= ~S_ISGID; + *mode_p = mode; + return 0; +} +EXPORT_SYMBOL(posix_acl_update_mode); + /* * Fix up the uids and gids in posix acl extended attributes in place. */ diff --git a/fs/proc/base.c b/fs/proc/base.c index 239dca3fb676..fab32ad5d96d 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -517,7 +517,7 @@ int proc_setattr(struct dentry *dentry, struct iattr *attr) if (attr->ia_valid & ATTR_MODE) return -EPERM; - error = inode_change_ok(inode, attr); + error = setattr_prepare(dentry, attr); if (error) return error; diff --git a/fs/proc/generic.c b/fs/proc/generic.c index e5dee5c3188e..d99099fe62d4 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -105,7 +105,7 @@ static int proc_notify_change(struct dentry *dentry, struct iattr *iattr) struct proc_dir_entry *de = PDE(inode); int error; - error = inode_change_ok(inode, iattr); + error = setattr_prepare(dentry, iattr); if (error) return error; diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index fdda62e6115e..d38541256287 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -703,7 +703,7 @@ static int proc_sys_readdir(struct file *file, struct dir_context *ctx) ctl_dir = container_of(head, struct ctl_dir, header); if (!dir_emit_dots(file, ctx)) - return 0; + goto out; pos = 2; @@ -713,6 +713,7 @@ static int proc_sys_readdir(struct file *file, struct dir_context *ctx) break; } } +out: sysctl_head_finish(head); return 0; } @@ -753,7 +754,7 @@ static int proc_sys_setattr(struct dentry *dentry, struct iattr *attr) if (attr->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID)) return -EPERM; - error = inode_change_ok(inode, attr); + error = setattr_prepare(dentry, attr); if (error) return error; diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c index ba1323a94924..aab2593f3179 100644 --- a/fs/ramfs/file-nommu.c +++ b/fs/ramfs/file-nommu.c @@ -168,7 +168,7 @@ static int ramfs_nommu_setattr(struct dentry *dentry, struct iattr *ia) int ret = 0; /* POSIX UID/GID verification for setting inode attributes */ - ret = inode_change_ok(inode, ia); + ret = setattr_prepare(dentry, ia); if (ret) return ret; diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index f6f2fbad9777..7da1232a78e3 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -3312,7 +3312,7 @@ int reiserfs_setattr(struct dentry *dentry, struct iattr *attr) unsigned int ia_valid; int error; - error = inode_change_ok(inode, attr); + error = setattr_prepare(dentry, attr); if (error) return error; diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c index 4b34b9dc03dd..9b1824f35501 100644 --- a/fs/reiserfs/xattr_acl.c +++ b/fs/reiserfs/xattr_acl.c @@ -246,13 +246,9 @@ __reiserfs_set_acl(struct reiserfs_transaction_handle *th, struct inode *inode, case ACL_TYPE_ACCESS: name = POSIX_ACL_XATTR_ACCESS; if (acl) { - error = posix_acl_equiv_mode(acl, &inode->i_mode); - if (error < 0) + error = posix_acl_update_mode(inode, &inode->i_mode, &acl); + if (error) return error; - else { - if (error == 0) - acl = NULL; - } } break; case ACL_TYPE_DEFAULT: diff --git a/fs/splice.c b/fs/splice.c index e7522c486068..6ec6054df138 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -211,6 +211,7 @@ ssize_t splice_to_pipe(struct pipe_inode_info *pipe, buf->len = spd->partial[page_nr].len; buf->private = spd->partial[page_nr].private; buf->ops = spd->ops; + buf->flags = 0; if (spd->flags & SPLICE_F_GIFT) buf->flags |= PIPE_BUF_FLAG_GIFT; diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 7c2867b44141..167f80e8f08d 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -108,14 +108,22 @@ static ssize_t sysfs_kf_read(struct kernfs_open_file *of, char *buf, { const struct sysfs_ops *ops = sysfs_file_ops(of->kn); struct kobject *kobj = of->kn->parent->priv; + size_t len; /* * If buf != of->prealloc_buf, we don't know how * large it is, so cannot safely pass it to ->show */ - if (pos || WARN_ON_ONCE(buf != of->prealloc_buf)) + if (WARN_ON_ONCE(buf != of->prealloc_buf)) return 0; - return ops->show(kobj, of->kn->priv, buf); + len = ops->show(kobj, of->kn->priv, buf); + if (pos) { + if (len <= pos) + return 0; + len -= pos; + memmove(buf, buf + pos, len); + } + return min(count, len); } /* kernfs write callback for regular sysfs files */ diff --git a/fs/sysv/file.c b/fs/sysv/file.c index 82ddc09061e2..7ba997e31aeb 100644 --- a/fs/sysv/file.c +++ b/fs/sysv/file.c @@ -33,7 +33,7 @@ static int sysv_setattr(struct dentry *dentry, struct iattr *attr) struct inode *inode = d_inode(dentry); int error; - error = inode_change_ok(inode, attr); + error = setattr_prepare(dentry, attr); if (error) return error; diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index 27060fc855d4..e0af247f4740 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -350,7 +350,7 @@ static unsigned int vfs_dent_type(uint8_t type) */ static int ubifs_readdir(struct file *file, struct dir_context *ctx) { - int err; + int err = 0; struct qstr nm; union ubifs_key key; struct ubifs_dent_node *dent; @@ -449,16 +449,23 @@ static int ubifs_readdir(struct file *file, struct dir_context *ctx) } out: - if (err != -ENOENT) { - ubifs_err(c, "cannot find next direntry, error %d", err); - return err; - } - kfree(file->private_data); file->private_data = NULL; + + if (err != -ENOENT) + ubifs_err(c, "cannot find next direntry, error %d", err); + else + /* + * -ENOENT is a non-fatal error in this context, the TNC uses + * it to indicate that the cursor moved past the current directory + * and readdir() has to stop. + */ + err = 0; + + /* 2 is a special value indicating that there are no more direntries */ ctx->pos = 2; - return 0; + return err; } /* Free saved readdir() state when the directory is closed */ diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 75e9b2db14ab..2dc8ce485c51 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -1263,7 +1263,7 @@ int ubifs_setattr(struct dentry *dentry, struct iattr *attr) dbg_gen("ino %lu, mode %#x, ia_valid %#x", inode->i_ino, inode->i_mode, attr->ia_valid); - err = inode_change_ok(inode, attr); + err = setattr_prepare(dentry, attr); if (err) return err; diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c index 957f5757f374..a18574237034 100644 --- a/fs/ubifs/tnc.c +++ b/fs/ubifs/tnc.c @@ -34,6 +34,11 @@ #include <linux/slab.h> #include "ubifs.h" +static int try_read_node(const struct ubifs_info *c, void *buf, int type, + int len, int lnum, int offs); +static int fallible_read_node(struct ubifs_info *c, const union ubifs_key *key, + struct ubifs_zbranch *zbr, void *node); + /* * Returned codes of 'matches_name()' and 'fallible_matches_name()' functions. * @NAME_LESS: name corresponding to the first argument is less than second @@ -403,7 +408,19 @@ static int tnc_read_node_nm(struct ubifs_info *c, struct ubifs_zbranch *zbr, return 0; } - err = ubifs_tnc_read_node(c, zbr, node); + if (c->replaying) { + err = fallible_read_node(c, &zbr->key, zbr, node); + /* + * When the node was not found, return -ENOENT, 0 otherwise. + * Negative return codes stay as-is. + */ + if (err == 0) + err = -ENOENT; + else if (err == 1) + err = 0; + } else { + err = ubifs_tnc_read_node(c, zbr, node); + } if (err) return err; @@ -2767,7 +2784,11 @@ struct ubifs_dent_node *ubifs_tnc_next_ent(struct ubifs_info *c, if (nm->name) { if (err) { /* Handle collisions */ - err = resolve_collision(c, key, &znode, &n, nm); + if (c->replaying) + err = fallible_resolve_collision(c, key, &znode, &n, + nm, 0); + else + err = resolve_collision(c, key, &znode, &n, nm); dbg_tnc("rc returned %d, znode %p, n %d", err, znode, n); if (unlikely(err < 0)) diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c index fd65b3f1923c..7270162b72e4 100644 --- a/fs/ubifs/xattr.c +++ b/fs/ubifs/xattr.c @@ -173,6 +173,7 @@ out_cancel: host_ui->xattr_cnt -= 1; host_ui->xattr_size -= CALC_DENT_SIZE(nm->len); host_ui->xattr_size -= CALC_XATTR_BYTES(size); + host_ui->xattr_names -= nm->len; mutex_unlock(&host_ui->ui_mutex); out_free: make_bad_inode(inode); @@ -527,6 +528,7 @@ out_cancel: host_ui->xattr_cnt += 1; host_ui->xattr_size += CALC_DENT_SIZE(nm->len); host_ui->xattr_size += CALC_XATTR_BYTES(ui->data_len); + host_ui->xattr_names += nm->len; mutex_unlock(&host_ui->ui_mutex); ubifs_release_budget(c, &req); make_bad_inode(inode); diff --git a/fs/udf/file.c b/fs/udf/file.c index 7a95b8fed302..889f1e5da507 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -252,7 +252,7 @@ static int udf_setattr(struct dentry *dentry, struct iattr *attr) struct inode *inode = d_inode(dentry); int error; - error = inode_change_ok(inode, attr); + error = setattr_prepare(dentry, attr); if (error) return error; diff --git a/fs/ufs/truncate.c b/fs/ufs/truncate.c index 21154704c168..a958b36f40bb 100644 --- a/fs/ufs/truncate.c +++ b/fs/ufs/truncate.c @@ -496,7 +496,7 @@ int ufs_setattr(struct dentry *dentry, struct iattr *attr) unsigned int ia_valid = attr->ia_valid; int error; - error = inode_change_ok(inode, attr); + error = setattr_prepare(dentry, attr); if (error) return error; diff --git a/fs/utimes.c b/fs/utimes.c index aa138d64560a..61abc3051377 100644 --- a/fs/utimes.c +++ b/fs/utimes.c @@ -81,7 +81,7 @@ static int utimes_common(struct path *path, struct timespec *times) newattrs.ia_valid |= ATTR_MTIME_SET; } /* - * Tell inode_change_ok(), that this is an explicit time + * Tell setattr_prepare(), that this is an explicit time * update, even if neither ATTR_ATIME_SET nor ATTR_MTIME_SET * were used. */ @@ -90,7 +90,7 @@ static int utimes_common(struct path *path, struct timespec *times) /* * If times is NULL (or both times are UTIME_NOW), * then we need to check permissions, because - * inode_change_ok() won't do it. + * setattr_prepare() won't do it. */ error = -EACCES; if (IS_IMMUTABLE(inode)) diff --git a/fs/xfs/libxfs/xfs_dquot_buf.c b/fs/xfs/libxfs/xfs_dquot_buf.c index f48c3040c9ce..6021c322316c 100644 --- a/fs/xfs/libxfs/xfs_dquot_buf.c +++ b/fs/xfs/libxfs/xfs_dquot_buf.c @@ -191,8 +191,7 @@ xfs_dquot_buf_verify_crc( if (mp->m_quotainfo) ndquots = mp->m_quotainfo->qi_dqperchunk; else - ndquots = xfs_calc_dquots_per_chunk( - XFS_BB_TO_FSB(mp, bp->b_length)); + ndquots = xfs_calc_dquots_per_chunk(bp->b_length); for (i = 0; i < ndquots; i++, d++) { if (!xfs_verify_cksum((char *)d, sizeof(struct xfs_dqblk), diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index 535bd843f2f4..901f11b30174 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -539,7 +539,8 @@ xfs_sb_verify( * Only check the in progress field for the primary superblock as * mkfs.xfs doesn't clear it from secondary superblocks. */ - return xfs_mount_validate_sb(mp, &sb, bp->b_bn == XFS_SB_DADDR, + return xfs_mount_validate_sb(mp, &sb, + bp->b_maps[0].bm_bn == XFS_SB_DADDR, check_version); } diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c index 4b641676f258..e80dbfa2a7b9 100644 --- a/fs/xfs/xfs_acl.c +++ b/fs/xfs/xfs_acl.c @@ -284,16 +284,11 @@ xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) return error; if (type == ACL_TYPE_ACCESS) { - umode_t mode = inode->i_mode; - error = posix_acl_equiv_mode(acl, &mode); - - if (error <= 0) { - acl = NULL; - - if (error < 0) - return error; - } + umode_t mode; + error = posix_acl_update_mode(inode, &mode, &acl); + if (error) + return error; error = xfs_set_mode(inode, mode); if (error) return error; diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 7dd64bf98c56..6e2b892b58ee 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -1537,7 +1537,7 @@ xfs_wait_buftarg( * ensure here that all reference counts have been dropped before we * start walking the LRU list. */ - drain_workqueue(btp->bt_mount->m_buf_workqueue); + flush_workqueue(btp->bt_mount->m_buf_workqueue); /* loop until there is nothing left on the lru list. */ while (list_lru_count(&btp->bt_lru)) { diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 3b7591224f4a..550f8c4733ee 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -973,7 +973,7 @@ xfs_file_fallocate( iattr.ia_valid = ATTR_SIZE; iattr.ia_size = new_size; - error = xfs_setattr_size(ip, &iattr); + error = xfs_vn_setattr_size(file->f_path.dentry, &iattr); if (error) goto out_unlock; } diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index c29f34253e2b..6b67d617c092 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1766,7 +1766,7 @@ xfs_inactive_truncate( /* * Log the inode size first to prevent stale data exposure in the event * of a system crash before the truncate completes. See the related - * comment in xfs_setattr_size() for details. + * comment in xfs_vn_setattr_size() for details. */ ip->i_d.di_size = 0; xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 87f67c6b654c..82e49109d0b6 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -720,7 +720,7 @@ xfs_ioc_space( iattr.ia_valid = ATTR_SIZE; iattr.ia_size = bf->l_start; - error = xfs_setattr_size(ip, &iattr); + error = xfs_vn_setattr_size(filp->f_path.dentry, &iattr); break; default: ASSERT(0); diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index f4cd7204e236..4e4d6511185b 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -537,6 +537,30 @@ xfs_setattr_time( } } +static int +xfs_vn_change_ok( + struct dentry *dentry, + struct iattr *iattr) +{ + struct inode *inode = d_inode(dentry); + struct xfs_inode *ip = XFS_I(inode); + struct xfs_mount *mp = ip->i_mount; + + if (mp->m_flags & XFS_MOUNT_RDONLY) + return -EROFS; + + if (XFS_FORCED_SHUTDOWN(mp)) + return -EIO; + + return setattr_prepare(dentry, iattr); +} + +/* + * Set non-size attributes of an inode. + * + * Caution: The caller of this function is responsible for calling + * setattr_prepare() or otherwise verifying the change is fine. + */ int xfs_setattr_nonsize( struct xfs_inode *ip, @@ -553,21 +577,6 @@ xfs_setattr_nonsize( struct xfs_dquot *udqp = NULL, *gdqp = NULL; struct xfs_dquot *olddquot1 = NULL, *olddquot2 = NULL; - trace_xfs_setattr(ip); - - /* If acls are being inherited, we already have this checked */ - if (!(flags & XFS_ATTR_NOACL)) { - if (mp->m_flags & XFS_MOUNT_RDONLY) - return -EROFS; - - if (XFS_FORCED_SHUTDOWN(mp)) - return -EIO; - - error = inode_change_ok(inode, iattr); - if (error) - return error; - } - ASSERT((mask & ATTR_SIZE) == 0); /* @@ -741,8 +750,27 @@ out_dqrele: return error; } +int +xfs_vn_setattr_nonsize( + struct dentry *dentry, + struct iattr *iattr) +{ + struct xfs_inode *ip = XFS_I(d_inode(dentry)); + int error; + + trace_xfs_setattr(ip); + + error = xfs_vn_change_ok(dentry, iattr); + if (error) + return error; + return xfs_setattr_nonsize(ip, iattr, 0); +} + /* * Truncate file. Must have write permission and not be a directory. + * + * Caution: The caller of this function is responsible for calling + * setattr_prepare() or otherwise verifying the change is fine. */ int xfs_setattr_size( @@ -758,18 +786,6 @@ xfs_setattr_size( uint commit_flags = 0; bool did_zeroing = false; - trace_xfs_setattr(ip); - - if (mp->m_flags & XFS_MOUNT_RDONLY) - return -EROFS; - - if (XFS_FORCED_SHUTDOWN(mp)) - return -EIO; - - error = inode_change_ok(inode, iattr); - if (error) - return error; - ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL)); ASSERT(xfs_isilocked(ip, XFS_MMAPLOCK_EXCL)); ASSERT(S_ISREG(ip->i_d.di_mode)); @@ -941,16 +957,32 @@ out_trans_cancel: goto out_unlock; } +int +xfs_vn_setattr_size( + struct dentry *dentry, + struct iattr *iattr) +{ + struct xfs_inode *ip = XFS_I(d_inode(dentry)); + int error; + + trace_xfs_setattr(ip); + + error = xfs_vn_change_ok(dentry, iattr); + if (error) + return error; + return xfs_setattr_size(ip, iattr); +} + STATIC int xfs_vn_setattr( struct dentry *dentry, struct iattr *iattr) { - struct xfs_inode *ip = XFS_I(d_inode(dentry)); int error; if (iattr->ia_valid & ATTR_SIZE) { - uint iolock = XFS_IOLOCK_EXCL; + struct xfs_inode *ip = XFS_I(d_inode(dentry)); + uint iolock = XFS_IOLOCK_EXCL; xfs_ilock(ip, iolock); error = xfs_break_layouts(d_inode(dentry), &iolock, true); @@ -958,11 +990,11 @@ xfs_vn_setattr( xfs_ilock(ip, XFS_MMAPLOCK_EXCL); iolock |= XFS_MMAPLOCK_EXCL; - error = xfs_setattr_size(ip, iattr); + error = xfs_vn_setattr_size(dentry, iattr); } xfs_iunlock(ip, iolock); } else { - error = xfs_setattr_nonsize(ip, iattr, 0); + error = xfs_vn_setattr_nonsize(dentry, iattr); } return error; diff --git a/fs/xfs/xfs_iops.h b/fs/xfs/xfs_iops.h index a0f84abb0d09..0259a383721a 100644 --- a/fs/xfs/xfs_iops.h +++ b/fs/xfs/xfs_iops.h @@ -33,6 +33,7 @@ extern ssize_t xfs_vn_listxattr(struct dentry *, char *data, size_t size); extern void xfs_setattr_time(struct xfs_inode *ip, struct iattr *iattr); extern int xfs_setattr_nonsize(struct xfs_inode *ip, struct iattr *vap, int flags); -extern int xfs_setattr_size(struct xfs_inode *ip, struct iattr *vap); +extern int xfs_vn_setattr_nonsize(struct dentry *dentry, struct iattr *vap); +extern int xfs_vn_setattr_size(struct dentry *dentry, struct iattr *vap); #endif /* __XFS_IOPS_H__ */ diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 1114afdd5a6b..4aefff89949d 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -3864,6 +3864,7 @@ xlog_recover_clear_agi_bucket( agi->agi_unlinked[bucket] = cpu_to_be32(NULLAGINO); offset = offsetof(xfs_agi_t, agi_unlinked) + (sizeof(xfs_agino_t) * bucket); + xfs_trans_buf_set_type(tp, agibp, XFS_BLFT_AGI_BUF); xfs_trans_log_buf(tp, agibp, offset, (offset + sizeof(xfs_agino_t) - 1)); |