vfs-7.1-rc7.fixes

Please consider pulling these changes from the signed vfs-7.1-rc7.fixes tag.
 
 Thanks!
 Christian
 -----BEGIN PGP SIGNATURE-----
 
 iHUEABYKAB0WIQRAhzRXHqcMeLMyaSiRxhvAZXjcogUCaiQb2wAKCRCRxhvAZXjc
 ol4fAP46Ta2gcT8uzJRHaXo3HMWJYY02dK1pXQ4zZDdiQMMSTgEAuaj/mOvx0VeX
 prloV/t7TBri6GAiWeE7Wu54d9rJZQ4=
 =clMX
 -----END PGP SIGNATURE-----

Merge tag 'vfs-7.1-rc7.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull vfs fixes from Christian Brauner:

 - Fix error handling in ovl_cache_get()

 - Tighten access checks for exited tasks in pidfd_getfd()

 - Fix selftests leak in __wait_for_test()

 - Limit FUSE_NOTIFY_RETRIEVE to uptodate folios

 - Reject fuse_notify() pagecache ops on directories

 - Clear JOBCTL_PENDING_MASK for caller in zap_other_threads()

 - Fix failure to unlock in nfsd4_create_file()

 - Fix pointer arithmetic in qnx6 directory iteration

 - Fix UAF due to unlocked ->mnt_ns read in may_decode_fh()

 - Avoid potential null folio->mapping deref during iomap error
   reporting

* tag 'vfs-7.1-rc7.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
  iomap: avoid potential null folio->mapping deref during error reporting
  fhandle: fix UAF due to unlocked ->mnt_ns read in may_decode_fh()
  fs/qnx6: fix pointer arithmetic in directory iteration
  VFS: fix possible failure to unlock in nfsd4_create_file()
  signal: clear JOBCTL_PENDING_MASK for caller in zap_other_threads()
  fuse: reject fuse_notify() pagecache ops on directories
  fuse: limit FUSE_NOTIFY_RETRIEVE to uptodate folios
  selftests: harness: fix pidfd leak in __wait_for_test
  pidfd: refuse access to tasks that have started exiting harder
  ovl: keep err zero after successful ovl_cache_get()

fs/fhandle.c

@@ -285,6 +285,19 @@ static int do_handle_to_path(struct file_handle *handle, struct path *path,
 	return 0;
 }
 
+static bool capable_wrt_mount(struct mount *mount)
+{
+	struct mnt_namespace *mnt_ns;
+
+	/*
+	 * For ->mnt_ns access.
+	 * The following READ_ONCE() is semantically rcu_dereference().
+	 */
+	guard(rcu)();
+	mnt_ns = READ_ONCE(mount->mnt_ns);
+	return ns_capable(mnt_ns->user_ns, CAP_SYS_ADMIN);
+}
+
 static inline int may_decode_fh(struct handle_to_path_ctx *ctx,
 				unsigned int o_flags)
 {
@@ -320,8 +333,7 @@ static inline int may_decode_fh(struct handle_to_path_ctx *ctx,
 	if (ns_capable(root->mnt->mnt_sb->s_user_ns, CAP_SYS_ADMIN))
 		ctx->flags = HANDLE_CHECK_PERMS;
 	else if (is_mounted(root->mnt) &&
-		 ns_capable(real_mount(root->mnt)->mnt_ns->user_ns,
-			    CAP_SYS_ADMIN) &&
+		 capable_wrt_mount(real_mount(root->mnt)) &&
 		 !has_locked_children(real_mount(root->mnt), root->dentry))
 		ctx->flags = HANDLE_CHECK_PERMS | HANDLE_CHECK_SUBTREE;
 	else

fs/fuse/dev.c

@@ -1793,6 +1793,10 @@ static int fuse_notify_store(struct fuse_conn *fc, unsigned int size,
 	inode = fuse_ilookup(fc, nodeid,  NULL);
 	if (!inode)
 		goto out_up_killsb;
+	if (!S_ISREG(inode->i_mode)) {
+		err = -EINVAL;
+		goto out_iput;
+	}
 
 	mapping = inode->i_mapping;
 	file_size = i_size_read(inode);
@@ -1912,6 +1916,10 @@ static int fuse_retrieve(struct fuse_mount *fm, struct inode *inode,
 		folio = filemap_get_folio(mapping, index);
 		if (IS_ERR(folio))
 			break;
+		if (!folio_test_uptodate(folio)) {
+			folio_put(folio);
+			break;
+		}
 
 		folio_offset = offset_in_folio(folio, pos);
 		nr_bytes = min(folio_size(folio) - folio_offset, num);
@@ -1966,6 +1974,9 @@ static int fuse_notify_retrieve(struct fuse_conn *fc, unsigned int size,
 
 	inode = fuse_ilookup(fc, nodeid, &fm);
 	if (inode) {
+		if (!S_ISREG(inode->i_mode))
+			err = -EINVAL;
+		else
 			err = fuse_retrieve(fm, inode, &outarg);
 		iput(inode);
 	}

fs/iomap/buffered-io.c

@@ -400,6 +400,11 @@ void iomap_finish_folio_read(struct folio *folio, size_t off, size_t len,
 	bool uptodate = !error;
 	bool finished = true;
 
+	if (error)
+		fserror_report_io(folio->mapping->host, FSERR_BUFFERED_READ,
+				  folio_pos(folio) + off, len, error,
+				  GFP_ATOMIC);
+
 	if (ifs) {
 		unsigned long flags;
 
@@ -411,11 +416,6 @@ void iomap_finish_folio_read(struct folio *folio, size_t off, size_t len,
 		spin_unlock_irqrestore(&ifs->state_lock, flags);
 	}
 
-	if (error)
-		fserror_report_io(folio->mapping->host, FSERR_BUFFERED_READ,
-				  folio_pos(folio) + off, len, error,
-				  GFP_ATOMIC);
-
 	if (finished)
 		folio_end_read(folio, uptodate);
 }

fs/mount.h

@@ -71,7 +71,15 @@ struct mount {
 	struct hlist_head mnt_slave_list;/* list of slave mounts */
 	struct hlist_node mnt_slave;	/* slave list entry */
 	struct mount *mnt_master;	/* slave is on master->mnt_slave_list */
-	struct mnt_namespace *mnt_ns;	/* containing namespace */
+	/*
+	 * Containing namespace (active or deactivating, non-refcounted).
+	 * Normally protected by namespace_sem.
+	 * Can also be accessed locklessly under RCU. RCU readers can't rely on
+	 * the namespace still being active, but implicitly hold a passive
+	 * reference (because an RCU delay happens between a namespace being
+	 * deactivated and the corresponding passive refcount drop).
+	 */
+	struct mnt_namespace *mnt_ns;
 	struct mountpoint *mnt_mp;	/* where is it mounted */
 	union {
 		struct hlist_node mnt_mp_list;	/* list mounts with the same mountpoint */

fs/namei.c

@@ -5024,6 +5024,7 @@ struct file *dentry_create(struct path *path, int flags, umode_t mode,
 {
 	struct file *file __free(fput) = NULL;
 	struct dentry *dentry = path->dentry;
+	struct dentry *orig_dentry = dentry;
 	struct dentry *dir = dentry->d_parent;
 	struct inode *dir_inode = d_inode(dir);
 	struct mnt_idmap *idmap;
@@ -5043,9 +5044,18 @@ struct file *dentry_create(struct path *path, int flags, umode_t mode,
 		if (create_error)
 			flags &= ~O_CREAT;
 
+		/* atomic_open will dput(dentry) on error */
+		dget(orig_dentry);
 		dentry = atomic_open(path, dentry, file, flags, mode);
 		error = PTR_ERR_OR_ZERO(dentry);
 
+		if (IS_ERR(dentry))
+			/* keep the original */
+			dentry = orig_dentry;
+		else
+			/* Drop the extra reference */
+			dput(orig_dentry);
+
 		if (unlikely(create_error) && error == -ENOENT)
 			error = create_error;
 

fs/namespace.c

@@ -1079,7 +1079,7 @@ static void mnt_add_to_ns(struct mnt_namespace *ns, struct mount *mnt)
 	bool mnt_first_node = true, mnt_last_node = true;
 
 	WARN_ON(mnt_ns_attached(mnt));
-	mnt->mnt_ns = ns;
+	WRITE_ONCE(mnt->mnt_ns, ns);
 	while (*link) {
 		parent = *link;
 		if (mnt->mnt_id_unique < node_to_mount(parent)->mnt_id_unique) {
@@ -1434,7 +1434,7 @@ EXPORT_SYMBOL(mntget);
 void mnt_make_shortterm(struct vfsmount *mnt)
 {
 	if (mnt)
-		real_mount(mnt)->mnt_ns = NULL;
+		WRITE_ONCE(real_mount(mnt)->mnt_ns, NULL);
 }
 
 /**
@@ -1806,7 +1806,7 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how)
 			ns->nr_mounts--;
 			__touch_mnt_namespace(ns);
 		}
-		p->mnt_ns = NULL;
+		WRITE_ONCE(p->mnt_ns, NULL);
 		if (how & UMOUNT_SYNC)
 			p->mnt.mnt_flags |= MNT_SYNC_UMOUNT;
 

fs/overlayfs/readdir.c

@@ -838,15 +838,14 @@ static int ovl_iterate_merged(struct file *file, struct dir_context *ctx)
 	struct ovl_dir_file *od = file->private_data;
 	struct dentry *dentry = file->f_path.dentry;
 	struct ovl_cache_entry *p;
-	int err = 0;
+	int err;
 
 	if (!od->cache) {
 		struct ovl_dir_cache *cache;
 
 		cache = ovl_cache_get(dentry);
-		err = PTR_ERR(cache);
 		if (IS_ERR(cache))
-			return err;
+			return PTR_ERR(cache);
 
 		od->cache = cache;
 		ovl_seek_cursor(od, ctx->pos);
@@ -869,7 +868,7 @@ static int ovl_iterate_merged(struct file *file, struct dir_context *ctx)
 		od->cursor = p->l_node.next;
 		ctx->pos++;
 	}
-	return err;
+	return 0;
 }
 
 static bool ovl_need_adjust_d_ino(struct file *file)

fs/qnx6/dir.c

@@ -132,16 +132,16 @@ static int qnx6_readdir(struct file *file, struct dir_context *ctx)
 		struct qnx6_dir_entry *de;
 		struct folio *folio;
 		char *kaddr = qnx6_get_folio(inode, n, &folio);
-		char *limit;
+		struct qnx6_dir_entry *limit;
 
 		if (IS_ERR(kaddr)) {
 			pr_err("%s(): read failed\n", __func__);
 			ctx->pos = (n + 1) << PAGE_SHIFT;
 			return PTR_ERR(kaddr);
 		}
-		de = (struct qnx6_dir_entry *)(kaddr + offset);
-		limit = kaddr + last_entry(inode, n);
-		for (; (char *)de < limit; de++, ctx->pos += QNX6_DIR_ENTRY_SIZE) {
+		de = (struct qnx6_dir_entry *)kaddr + offset;
+		limit = (struct qnx6_dir_entry *)kaddr + last_entry(inode, n);
+		for (; de < limit; de++, ctx->pos += QNX6_DIR_ENTRY_SIZE) {
 			int size = de->de_size;
 			u32 no_inode = fs32_to_cpu(sbi, de->de_inode);
 

kernel/pid.c

@@ -885,10 +885,12 @@ static struct file *__pidfd_fget(struct task_struct *task, int fd)
 	if (ret)
 		return ERR_PTR(ret);
 
-	if (ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS))
-		file = fget_task(task, fd);
-	else
+	if (!ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS))
 		file = ERR_PTR(-EPERM);
+	else if (task->flags & PF_EXITING)
+		file = ERR_PTR(-ESRCH);
+	else
+		file = fget_task(task, fd);
 
 	up_read(&task->signal->exec_update_lock);
 

kernel/signal.c

@@ -1338,6 +1338,7 @@ int zap_other_threads(struct task_struct *p)
 	int count = 0;
 
 	p->signal->group_stop_count = 0;
+	task_clear_jobctl_pending(p, JOBCTL_PENDING_MASK);
 
 	for_other_threads(p, t) {
 		task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK);

tools/testing/selftests/kselftest_harness.h

@@ -996,6 +996,7 @@ static void __wait_for_test(struct __test_metadata *t)
 	poll_child.fd = childfd;
 	poll_child.events = POLLIN;
 	ret = poll(&poll_child, 1, t->timeout * 1000);
+	close(childfd);
 	if (ret == -1) {
 		t->exit_code = KSFT_FAIL;
 		fprintf(TH_LOG_STREAM,