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, 65 insertions, 0 deletions

diff --git a/fs/proc/thread_self.c b/fs/proc/thread_self.c
new file mode 100644
index 000000000..61ac62c3f
--- /dev/null
+++ b/fs/proc/thread_self.c
@@ -0,0 +1,65 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/cache.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/pid_namespace.h>
+#include "internal.h"
+
+/*
+ * /proc/thread_self:
+ */
+static const char *proc_thread_self_get_link(struct dentry *dentry,
+					     struct inode *inode,
+					     struct delayed_call *done)
+{
+	struct pid_namespace *ns = proc_pid_ns(inode->i_sb);
+	pid_t tgid = task_tgid_nr_ns(current, ns);
+	pid_t pid = task_pid_nr_ns(current, ns);
+	char *name;
+
+	if (!pid)
+		return ERR_PTR(-ENOENT);
+	name = kmalloc(10 + 6 + 10 + 1, dentry ? GFP_KERNEL : GFP_ATOMIC);
+	if (unlikely(!name))
+		return dentry ? ERR_PTR(-ENOMEM) : ERR_PTR(-ECHILD);
+	sprintf(name, "%u/task/%u", tgid, pid);
+	set_delayed_call(done, kfree_link, name);
+	return name;
+}
+
+static const struct inode_operations proc_thread_self_inode_operations = {
+	.get_link	= proc_thread_self_get_link,
+};
+
+unsigned thread_self_inum __ro_after_init;
+
+int proc_setup_thread_self(struct super_block *s)
+{
+	struct dentry *thread_self;
+	int ret = -ENOMEM;
+
+	thread_self = d_alloc_name(s->s_root, "thread-self");
+	if (thread_self) {
+		struct inode *inode = new_inode(s);
+		if (inode) {
+			inode->i_ino = thread_self_inum;
+			simple_inode_init_ts(inode);
+			inode->i_mode = S_IFLNK | S_IRWXUGO;
+			inode->i_uid = GLOBAL_ROOT_UID;
+			inode->i_gid = GLOBAL_ROOT_GID;
+			inode->i_op = &proc_thread_self_inode_operations;
+			d_make_persistent(thread_self, inode);
+			ret = 0;
+		}
+		dput(thread_self);
+	}
+
+	if (ret)
+		pr_err("proc_fill_super: can't allocate /proc/thread-self\n");
+	return ret;
+}
+
+void __init proc_thread_self_init(void)
+{
+	proc_alloc_inum(&thread_self_inum);
+}