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, 85 insertions, 0 deletions

diff --git a/samples/check-exec/set-exec.c b/samples/check-exec/set-exec.c
new file mode 100644
index 000000000..ba86a60a2
--- /dev/null
+++ b/samples/check-exec/set-exec.c
@@ -0,0 +1,85 @@
+// SPDX-License-Identifier: BSD-3-Clause
+/*
+ * Simple tool to set SECBIT_EXEC_RESTRICT_FILE, SECBIT_EXEC_DENY_INTERACTIVE,
+ * before executing a command.
+ *
+ * Copyright © 2024 Microsoft Corporation
+ */
+
+#define _GNU_SOURCE
+#define __SANE_USERSPACE_TYPES__
+#include <errno.h>
+#include <linux/prctl.h>
+#include <linux/securebits.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/prctl.h>
+#include <unistd.h>
+
+static void print_usage(const char *argv0)
+{
+	fprintf(stderr, "usage: %s -f|-i -- <cmd> [args]...\n\n", argv0);
+	fprintf(stderr, "Execute a command with\n");
+	fprintf(stderr, "- SECBIT_EXEC_RESTRICT_FILE set: -f\n");
+	fprintf(stderr, "- SECBIT_EXEC_DENY_INTERACTIVE set: -i\n");
+}
+
+int main(const int argc, char *const argv[], char *const *const envp)
+{
+	const char *cmd_path;
+	char *const *cmd_argv;
+	int opt, secbits_cur, secbits_new;
+	bool has_policy = false;
+
+	secbits_cur = prctl(PR_GET_SECUREBITS);
+	if (secbits_cur == -1) {
+		/*
+		 * This should never happen, except with a buggy seccomp
+		 * filter.
+		 */
+		perror("ERROR: Failed to get securebits");
+		return 1;
+	}
+
+	secbits_new = secbits_cur;
+	while ((opt = getopt(argc, argv, "fi")) != -1) {
+		switch (opt) {
+		case 'f':
+			secbits_new |= SECBIT_EXEC_RESTRICT_FILE |
+				       SECBIT_EXEC_RESTRICT_FILE_LOCKED;
+			has_policy = true;
+			break;
+		case 'i':
+			secbits_new |= SECBIT_EXEC_DENY_INTERACTIVE |
+				       SECBIT_EXEC_DENY_INTERACTIVE_LOCKED;
+			has_policy = true;
+			break;
+		default:
+			print_usage(argv[0]);
+			return 1;
+		}
+	}
+
+	if (!argv[optind] || !has_policy) {
+		print_usage(argv[0]);
+		return 1;
+	}
+
+	if (secbits_cur != secbits_new &&
+	    prctl(PR_SET_SECUREBITS, secbits_new)) {
+		perror("Failed to set secure bit(s).");
+		fprintf(stderr,
+			"Hint: The running kernel may not support this feature.\n");
+		return 1;
+	}
+
+	cmd_path = argv[optind];
+	cmd_argv = argv + optind;
+	fprintf(stderr, "Executing command...\n");
+	execvpe(cmd_path, cmd_argv, envp);
+	fprintf(stderr, "Failed to execute \"%s\": %s\n", cmd_path,
+		strerror(errno));
+	return 1;
+}