Merge branch 'fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull misc vfs fixes from Al Viro:
 "Assorted fixes all over the place; some of that is -stable fodder,
  some regressions from the last window"

* 'fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  ecryptfs_lookup_interpose(): lower_dentry->d_parent is not stable either
  ecryptfs_lookup_interpose(): lower_dentry->d_inode is not stable
  ecryptfs: fix unlink and rmdir in face of underlying fs modifications
  audit_get_nd(): don't unlock parent too early
  exportfs_decode_fh(): negative pinned may become positive without the parent locked
  cgroup: don't put ERR_PTR() into fc->root
  autofs: fix a leak in autofs_expire_indirect()
  aio: Fix io_pgetevents() struct __compat_aio_sigset layout
  fs/namespace.c: fix use-after-free of mount in mnt_warn_timestamp_expiry()

Author: torvalds

fs/aio.c

@@ -2179,7 +2179,7 @@ SYSCALL_DEFINE5(io_getevents_time32, __u32, ctx_id,
 #ifdef CONFIG_COMPAT
 
 struct __compat_aio_sigset {
-	compat_sigset_t __user	*sigmask;
+	compat_uptr_t		sigmask;
 	compat_size_t		sigsetsize;
 };
 
@@ -2193,7 +2193,7 @@ COMPAT_SYSCALL_DEFINE6(io_pgetevents,
 		struct old_timespec32 __user *, timeout,
 		const struct __compat_aio_sigset __user *, usig)
 {
-	struct __compat_aio_sigset ksig = { NULL, };
+	struct __compat_aio_sigset ksig = { 0, };
 	struct timespec64 t;
 	bool interrupted;
 	int ret;
@@ -2204,7 +2204,7 @@ COMPAT_SYSCALL_DEFINE6(io_pgetevents,
 	if (usig && copy_from_user(&ksig, usig, sizeof(ksig)))
 		return -EFAULT;
 
-	ret = set_compat_user_sigmask(ksig.sigmask, ksig.sigsetsize);
+	ret = set_compat_user_sigmask(compat_ptr(ksig.sigmask), ksig.sigsetsize);
 	if (ret)
 		return ret;
 
@@ -2228,7 +2228,7 @@ COMPAT_SYSCALL_DEFINE6(io_pgetevents_time64,
 		struct __kernel_timespec __user *, timeout,
 		const struct __compat_aio_sigset __user *, usig)
 {
-	struct __compat_aio_sigset ksig = { NULL, };
+	struct __compat_aio_sigset ksig = { 0, };
 	struct timespec64 t;
 	bool interrupted;
 	int ret;
@@ -2239,7 +2239,7 @@ COMPAT_SYSCALL_DEFINE6(io_pgetevents_time64,
 	if (usig && copy_from_user(&ksig, usig, sizeof(ksig)))
 		return -EFAULT;
 
-	ret = set_compat_user_sigmask(ksig.sigmask, ksig.sigsetsize);
+	ret = set_compat_user_sigmask(compat_ptr(ksig.sigmask), ksig.sigsetsize);
 	if (ret)
 		return ret;
 

fs/autofs/expire.c

@@ -459,9 +459,10 @@ static struct dentry *autofs_expire_indirect(struct super_block *sb,
 		 */
 		how &= ~AUTOFS_EXP_LEAVES;
 		found = should_expire(expired, mnt, timeout, how);
-		if (!found || found != expired)
-			/* Something has changed, continue */
+		if (found != expired) { // something has changed, continue
+			dput(found);
 			goto next;
+		}
 
 		if (expired != dentry)
 			dput(dentry);

fs/ecryptfs/inode.c

@@ -128,24 +128,32 @@ static int ecryptfs_do_unlink(struct inode *dir, struct dentry *dentry,
 			      struct inode *inode)
 {
 	struct dentry *lower_dentry = ecryptfs_dentry_to_lower(dentry);
-	struct inode *lower_dir_inode = ecryptfs_inode_to_lower(dir);
 	struct dentry *lower_dir_dentry;
+	struct inode *lower_dir_inode;
 	int rc;
 
-	dget(lower_dentry);
-	lower_dir_dentry = lock_parent(lower_dentry);
-	rc = vfs_unlink(lower_dir_inode, lower_dentry, NULL);
+	lower_dir_dentry = ecryptfs_dentry_to_lower(dentry->d_parent);
+	lower_dir_inode = d_inode(lower_dir_dentry);
+	inode_lock_nested(lower_dir_inode, I_MUTEX_PARENT);
+	dget(lower_dentry);	// don't even try to make the lower negative
+	if (lower_dentry->d_parent != lower_dir_dentry)
+		rc = -EINVAL;
+	else if (d_unhashed(lower_dentry))
+		rc = -EINVAL;
+	else
+		rc = vfs_unlink(lower_dir_inode, lower_dentry, NULL);
 	if (rc) {
 		printk(KERN_ERR "Error in vfs_unlink; rc = [%d]\n", rc);
 		goto out_unlock;
 	}
 	fsstack_copy_attr_times(dir, lower_dir_inode);
 	set_nlink(inode, ecryptfs_inode_to_lower(inode)->i_nlink);
 	inode->i_ctime = dir->i_ctime;
-	d_drop(dentry);
 out_unlock:
-	unlock_dir(lower_dir_dentry);
 	dput(lower_dentry);
+	inode_unlock(lower_dir_inode);
+	if (!rc)
+		d_drop(dentry);
 	return rc;
 }
 
@@ -311,9 +319,9 @@ static int ecryptfs_i_size_read(struct dentry *dentry, struct inode *inode)
 static struct dentry *ecryptfs_lookup_interpose(struct dentry *dentry,
 				     struct dentry *lower_dentry)
 {
-	struct inode *inode, *lower_inode = d_inode(lower_dentry);
+	struct path *path = ecryptfs_dentry_to_lower_path(dentry->d_parent);
+	struct inode *inode, *lower_inode;
 	struct ecryptfs_dentry_info *dentry_info;
-	struct vfsmount *lower_mnt;
 	int rc = 0;
 
 	dentry_info = kmem_cache_alloc(ecryptfs_dentry_info_cache, GFP_KERNEL);
@@ -322,16 +330,23 @@ static struct dentry *ecryptfs_lookup_interpose(struct dentry *dentry,
 		return ERR_PTR(-ENOMEM);
 	}
 
-	lower_mnt = mntget(ecryptfs_dentry_to_lower_mnt(dentry->d_parent));
 	fsstack_copy_attr_atime(d_inode(dentry->d_parent),
-				d_inode(lower_dentry->d_parent));
+				d_inode(path->dentry));
 	BUG_ON(!d_count(lower_dentry));
 
 	ecryptfs_set_dentry_private(dentry, dentry_info);
-	dentry_info->lower_path.mnt = lower_mnt;
+	dentry_info->lower_path.mnt = mntget(path->mnt);
 	dentry_info->lower_path.dentry = lower_dentry;
 
-	if (d_really_is_negative(lower_dentry)) {
+	/*
+	 * negative dentry can go positive under us here - its parent is not
+	 * locked.  That's OK and that could happen just as we return from
+	 * ecryptfs_lookup() anyway.  Just need to be careful and fetch
+	 * ->d_inode only once - it's not stable here.
+	 */
+	lower_inode = READ_ONCE(lower_dentry->d_inode);
+
+	if (!lower_inode) {
 		/* We want to add because we couldn't find in lower */
 		d_add(dentry, NULL);
 		return NULL;
@@ -512,22 +527,30 @@ static int ecryptfs_rmdir(struct inode *dir, struct dentry *dentry)
 {
 	struct dentry *lower_dentry;
 	struct dentry *lower_dir_dentry;
+	struct inode *lower_dir_inode;
 	int rc;
 
 	lower_dentry = ecryptfs_dentry_to_lower(dentry);
-	dget(dentry);
-	lower_dir_dentry = lock_parent(lower_dentry);
-	dget(lower_dentry);
-	rc = vfs_rmdir(d_inode(lower_dir_dentry), lower_dentry);
-	dput(lower_dentry);
-	if (!rc && d_really_is_positive(dentry))
+	lower_dir_dentry = ecryptfs_dentry_to_lower(dentry->d_parent);
+	lower_dir_inode = d_inode(lower_dir_dentry);
+
+	inode_lock_nested(lower_dir_inode, I_MUTEX_PARENT);
+	dget(lower_dentry);	// don't even try to make the lower negative
+	if (lower_dentry->d_parent != lower_dir_dentry)
+		rc = -EINVAL;
+	else if (d_unhashed(lower_dentry))
+		rc = -EINVAL;
+	else
+		rc = vfs_rmdir(lower_dir_inode, lower_dentry);
+	if (!rc) {
 		clear_nlink(d_inode(dentry));
-	fsstack_copy_attr_times(dir, d_inode(lower_dir_dentry));
-	set_nlink(dir, d_inode(lower_dir_dentry)->i_nlink);
-	unlock_dir(lower_dir_dentry);
+		fsstack_copy_attr_times(dir, lower_dir_inode);
+		set_nlink(dir, lower_dir_inode->i_nlink);
+	}
+	dput(lower_dentry);
+	inode_unlock(lower_dir_inode);
 	if (!rc)
 		d_drop(dentry);
-	dput(dentry);
 	return rc;
 }
 
@@ -565,20 +588,22 @@ ecryptfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	struct dentry *lower_new_dentry;
 	struct dentry *lower_old_dir_dentry;
 	struct dentry *lower_new_dir_dentry;
-	struct dentry *trap = NULL;
+	struct dentry *trap;
 	struct inode *target_inode;
 
 	if (flags)
 		return -EINVAL;
 
+	lower_old_dir_dentry = ecryptfs_dentry_to_lower(old_dentry->d_parent);
+	lower_new_dir_dentry = ecryptfs_dentry_to_lower(new_dentry->d_parent);
+
 	lower_old_dentry = ecryptfs_dentry_to_lower(old_dentry);
 	lower_new_dentry = ecryptfs_dentry_to_lower(new_dentry);
-	dget(lower_old_dentry);
-	dget(lower_new_dentry);
-	lower_old_dir_dentry = dget_parent(lower_old_dentry);
-	lower_new_dir_dentry = dget_parent(lower_new_dentry);
+
 	target_inode = d_inode(new_dentry);
+
 	trap = lock_rename(lower_old_dir_dentry, lower_new_dir_dentry);
+	dget(lower_new_dentry);
 	rc = -EINVAL;
 	if (lower_old_dentry->d_parent != lower_old_dir_dentry)
 		goto out_lock;
@@ -606,11 +631,8 @@ ecryptfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	if (new_dir != old_dir)
 		fsstack_copy_attr_all(old_dir, d_inode(lower_old_dir_dentry));
 out_lock:
-	unlock_rename(lower_old_dir_dentry, lower_new_dir_dentry);
-	dput(lower_new_dir_dentry);
-	dput(lower_old_dir_dentry);
 	dput(lower_new_dentry);
-	dput(lower_old_dentry);
+	unlock_rename(lower_old_dir_dentry, lower_new_dir_dentry);
 	return rc;
 }
 

fs/exportfs/expfs.c

@@ -519,26 +519,33 @@ struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid,
 		 * inode is actually connected to the parent.
 		 */
 		err = exportfs_get_name(mnt, target_dir, nbuf, result);
-		if (!err) {
-			inode_lock(target_dir->d_inode);
-			nresult = lookup_one_len(nbuf, target_dir,
-						 strlen(nbuf));
-			inode_unlock(target_dir->d_inode);
-			if (!IS_ERR(nresult)) {
-				if (nresult->d_inode) {
-					dput(result);
-					result = nresult;
-				} else
-					dput(nresult);
-			}
+		if (err) {
+			dput(target_dir);
+			goto err_result;
 		}
 
+		inode_lock(target_dir->d_inode);
+		nresult = lookup_one_len(nbuf, target_dir, strlen(nbuf));
+		if (!IS_ERR(nresult)) {
+			if (unlikely(nresult->d_inode != result->d_inode)) {
+				dput(nresult);
+				nresult = ERR_PTR(-ESTALE);
+			}
+		}
+		inode_unlock(target_dir->d_inode);
 		/*
 		 * At this point we are done with the parent, but it's pinned
 		 * by the child dentry anyway.
 		 */
 		dput(target_dir);
 
+		if (IS_ERR(nresult)) {
+			err = PTR_ERR(nresult);
+			goto err_result;
+		}
+		dput(result);
+		result = nresult;
+
 		/*
 		 * And finally make sure the dentry is actually acceptable
 		 * to NFSD.

fs/namespace.c

@@ -2478,8 +2478,10 @@ static void mnt_warn_timestamp_expiry(struct path *mountpoint, struct vfsmount *
 
 		time64_to_tm(sb->s_time_max, 0, &tm);
 
-		pr_warn("Mounted %s file system at %s supports timestamps until %04ld (0x%llx)\n",
-			sb->s_type->name, mntpath,
+		pr_warn("%s filesystem being %s at %s supports timestamps until %04ld (0x%llx)\n",
+			sb->s_type->name,
+			is_mounted(mnt) ? "remounted" : "mounted",
+			mntpath,
 			tm.tm_year+1900, (unsigned long long)sb->s_time_max);
 
 		free_page((unsigned long)buf);
@@ -2764,14 +2766,11 @@ static int do_new_mount_fc(struct fs_context *fc, struct path *mountpoint,
 	if (IS_ERR(mnt))
 		return PTR_ERR(mnt);
 
-	error = do_add_mount(real_mount(mnt), mountpoint, mnt_flags);
-	if (error < 0) {
-		mntput(mnt);
-		return error;
-	}
-
 	mnt_warn_timestamp_expiry(mountpoint, mnt);
 
+	error = do_add_mount(real_mount(mnt), mountpoint, mnt_flags);
+	if (error < 0)
+		mntput(mnt);
 	return error;
 }
 

kernel/audit_watch.c

@@ -351,12 +351,12 @@ static int audit_get_nd(struct audit_watch *watch, struct path *parent)
 	struct dentry *d = kern_path_locked(watch->path, parent);
 	if (IS_ERR(d))
 		return PTR_ERR(d);
-	inode_unlock(d_backing_inode(parent->dentry));
 	if (d_is_positive(d)) {
 		/* update watch filter fields */
 		watch->dev = d->d_sb->s_dev;
 		watch->ino = d_backing_inode(d)->i_ino;
 	}
+	inode_unlock(d_backing_inode(parent->dentry));
 	dput(d);
 	return 0;
 }

kernel/cgroup/cgroup.c

@@ -2119,11 +2119,12 @@ int cgroup_do_get_tree(struct fs_context *fc)
 
 		nsdentry = kernfs_node_dentry(cgrp->kn, sb);
 		dput(fc->root);
-		fc->root = nsdentry;
 		if (IS_ERR(nsdentry)) {
-			ret = PTR_ERR(nsdentry);
 			deactivate_locked_super(sb);
+			ret = PTR_ERR(nsdentry);
+			nsdentry = NULL;
 		}
+		fc->root = nsdentry;
 	}
 
 	if (!ctx->kfc.new_sb_created)