ARM: 9485/1: mm: acquire mmap write lock around show_pte() for user faultsgrafted

When CONFIG_DEBUG_USER=y, and cmdline "user_debug=31" is set,
a user fault may trigger show_pte() without any lock.
If another thread in the same process concurrently calls munmap(),
the page table pages may be freed while show_pte() is still traversing
them, causing a use-after-free in show_pte().

If CONFIG_ARM_LPAE=y, this may cause a kernel panic if the pages table
of PMD are freed when show_pte() is running.

Acquire mmap_write_lock() around show_pte() for user faults to fix the
contention.

For user faults, additionally restrict that show_pte() is called only
when the addr is a user-space address (addr < TASK_SIZE). This is because
the lock of tsk->mm only protects the virtual memory of user address space,
furthermore, dumping the page tables of a kernel-space address for user
faults is unnecessary and may have security implications.

Keep everything unchanged for kernel faults, because the kernel is
already in the "oops" state, acquiring a lock may risk a deadlock.

Co-developed-by: Qi Xi <xiqi2@huawei.com>

Fixes: 6d021b724481 ("ARM: dump pgd, pmd and pte states on unhandled data abort faults")
Link: https://lore.kernel.org/20260716014022.2823-1-xieyuanbin1@huawei.com
Acked-by: Lorenzo Stoakes (ARM) <ljs@kernel.org>
Reviewed-by: Linus Walleij <linusw@kernel.org>
Signed-off-by: Qi Xi <xiqi2@huawei.com>
Signed-off-by: Xie Yuanbin <xieyuanbin1@huawei.com>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>

1 files changed, 103 insertions, 0 deletions

diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c
new file mode 100644
index 000000000..88c10823f
--- /dev/null
+++ b/fs/sysfs/mount.c
@@ -0,0 +1,103 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * fs/sysfs/symlink.c - operations for initializing and mounting sysfs
+ *
+ * Copyright (c) 2001-3 Patrick Mochel
+ * Copyright (c) 2007 SUSE Linux Products GmbH
+ * Copyright (c) 2007 Tejun Heo <teheo@suse.de>
+ *
+ * Please see Documentation/filesystems/sysfs.rst for more information.
+ */
+
+#include <linux/fs.h>
+#include <linux/magic.h>
+#include <linux/mount.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/user_namespace.h>
+#include <linux/fs_context.h>
+#include <net/net_namespace.h>
+
+#include "sysfs.h"
+
+static struct kernfs_root *sysfs_root;
+struct kernfs_node *sysfs_root_kn;
+
+static void sysfs_fs_context_free(struct fs_context *fc)
+{
+	struct kernfs_fs_context *kfc = fc->fs_private;
+
+	if (kfc->ns_tag)
+		kobj_ns_drop(KOBJ_NS_TYPE_NET, kfc->ns_tag);
+	kernfs_free_fs_context(fc);
+	kfree(kfc);
+}
+
+static const struct fs_context_operations sysfs_fs_context_ops = {
+	.free		= sysfs_fs_context_free,
+	.get_tree	= kernfs_get_tree,
+};
+
+static int sysfs_init_fs_context(struct fs_context *fc)
+{
+	struct kernfs_fs_context *kfc;
+	struct ns_common *ns;
+
+	if (!(fc->sb_flags & SB_KERNMOUNT)) {
+		if (!kobj_ns_current_may_mount(KOBJ_NS_TYPE_NET))
+			return -EPERM;
+	}
+
+	kfc = kzalloc_obj(struct kernfs_fs_context);
+	if (!kfc)
+		return -ENOMEM;
+
+	kfc->ns_tag = ns = kobj_ns_grab_current(KOBJ_NS_TYPE_NET);
+	kfc->root = sysfs_root;
+	kfc->magic = SYSFS_MAGIC;
+	fc->fs_private = kfc;
+	fc->ops = &sysfs_fs_context_ops;
+	if (ns) {
+		struct net *netns = to_net_ns(ns);
+
+		put_user_ns(fc->user_ns);
+		fc->user_ns = get_user_ns(netns->user_ns);
+	}
+	fc->global = true;
+	return 0;
+}
+
+static void sysfs_kill_sb(struct super_block *sb)
+{
+	struct ns_common *ns = (struct ns_common *)kernfs_super_ns(sb);
+
+	kernfs_kill_sb(sb);
+	kobj_ns_drop(KOBJ_NS_TYPE_NET, ns);
+}
+
+static struct file_system_type sysfs_fs_type = {
+	.name			= "sysfs",
+	.init_fs_context	= sysfs_init_fs_context,
+	.kill_sb		= sysfs_kill_sb,
+	.fs_flags		= FS_USERNS_MOUNT | FS_USERNS_MOUNT_RESTRICTED,
+};
+
+int __init sysfs_init(void)
+{
+	int err;
+
+	sysfs_root = kernfs_create_root(NULL, KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK,
+					NULL);
+	if (IS_ERR(sysfs_root))
+		return PTR_ERR(sysfs_root);
+
+	sysfs_root_kn = kernfs_root_to_node(sysfs_root);
+
+	err = register_filesystem(&sysfs_fs_type);
+	if (err) {
+		kernfs_destroy_root(sysfs_root);
+		return err;
+	}
+
+	return 0;
+}