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, 77 insertions, 0 deletions

diff --git a/samples/seccomp/dropper.c b/samples/seccomp/dropper.c
new file mode 100644
index 000000000..4bca4b70f
--- /dev/null
+++ b/samples/seccomp/dropper.c
@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Naive system call dropper built on seccomp_filter.
+ *
+ * Copyright (c) 2012 The Chromium OS Authors <chromium-os-dev@chromium.org>
+ * Author: Will Drewry <wad@chromium.org>
+ *
+ * The code may be used by anyone for any purpose,
+ * and can serve as a starting point for developing
+ * applications using prctl(PR_SET_SECCOMP, 2, ...).
+ *
+ * When run, returns the specified errno for the specified
+ * system call number against the given architecture.
+ *
+ */
+
+#include <errno.h>
+#include <linux/audit.h>
+#include <linux/filter.h>
+#include <linux/seccomp.h>
+#include <linux/unistd.h>
+#include <stdio.h>
+#include <stddef.h>
+#include <stdlib.h>
+#include <sys/prctl.h>
+#include <unistd.h>
+
+static int install_filter(int arch, int nr, int error)
+{
+	struct sock_filter filter[] = {
+		BPF_STMT(BPF_LD+BPF_W+BPF_ABS,
+			 (offsetof(struct seccomp_data, arch))),
+		BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, arch, 0, 3),
+		BPF_STMT(BPF_LD+BPF_W+BPF_ABS,
+			 (offsetof(struct seccomp_data, nr))),
+		BPF_JUMP(BPF_JMP+BPF_JEQ+BPF_K, nr, 0, 1),
+		BPF_STMT(BPF_RET+BPF_K,
+			 SECCOMP_RET_ERRNO|(error & SECCOMP_RET_DATA)),
+		BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_ALLOW),
+	};
+	struct sock_fprog prog = {
+		.len = (unsigned short)(sizeof(filter)/sizeof(filter[0])),
+		.filter = filter,
+	};
+	if (error == -1) {
+		struct sock_filter kill = BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_KILL);
+		filter[4] = kill;
+	}
+	if (prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0)) {
+		perror("prctl(NO_NEW_PRIVS)");
+		return 1;
+	}
+	if (prctl(PR_SET_SECCOMP, 2, &prog)) {
+		perror("prctl(PR_SET_SECCOMP)");
+		return 1;
+	}
+	return 0;
+}
+
+int main(int argc, char **argv)
+{
+	if (argc < 5) {
+		fprintf(stderr, "Usage:\n"
+			"dropper <arch> <syscall_nr> <errno> <prog> [<args>]\n"
+			"Hint:	AUDIT_ARCH_I386: 0x%X\n"
+			"	AUDIT_ARCH_X86_64: 0x%X\n"
+			"	errno == -1 means SECCOMP_RET_KILL\n"
+			"\n", AUDIT_ARCH_I386, AUDIT_ARCH_X86_64);
+		return 1;
+	}
+	if (install_filter(strtol(argv[1], NULL, 0), strtol(argv[2], NULL, 0),
+			   strtol(argv[3], NULL, 0)))
+		return 1;
+	execv(argv[4], &argv[4]);
+	printf("Failed to execv\n");
+	return 255;
+}