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, 76 insertions, 0 deletions

diff --git a/security/keys/sysctl.c b/security/keys/sysctl.c
new file mode 100644
index 000000000..cde08c478
--- /dev/null
+++ b/security/keys/sysctl.c
@@ -0,0 +1,76 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Key management controls
+ *
+ * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/key.h>
+#include <linux/sysctl.h>
+#include "internal.h"
+
+static const struct ctl_table key_sysctls[] = {
+	{
+		.procname = "maxkeys",
+		.data = &key_quota_maxkeys,
+		.maxlen = sizeof(unsigned),
+		.mode = 0644,
+		.proc_handler = proc_dointvec_minmax,
+		.extra1 = (void *) SYSCTL_ONE,
+		.extra2 = (void *) SYSCTL_INT_MAX,
+	},
+	{
+		.procname = "maxbytes",
+		.data = &key_quota_maxbytes,
+		.maxlen = sizeof(unsigned),
+		.mode = 0644,
+		.proc_handler = proc_dointvec_minmax,
+		.extra1 = (void *) SYSCTL_ONE,
+		.extra2 = (void *) SYSCTL_INT_MAX,
+	},
+	{
+		.procname = "root_maxkeys",
+		.data = &key_quota_root_maxkeys,
+		.maxlen = sizeof(unsigned),
+		.mode = 0644,
+		.proc_handler = proc_dointvec_minmax,
+		.extra1 = (void *) SYSCTL_ONE,
+		.extra2 = (void *) SYSCTL_INT_MAX,
+	},
+	{
+		.procname = "root_maxbytes",
+		.data = &key_quota_root_maxbytes,
+		.maxlen = sizeof(unsigned),
+		.mode = 0644,
+		.proc_handler = proc_dointvec_minmax,
+		.extra1 = (void *) SYSCTL_ONE,
+		.extra2 = (void *) SYSCTL_INT_MAX,
+	},
+	{
+		.procname = "gc_delay",
+		.data = &key_gc_delay,
+		.maxlen = sizeof(unsigned),
+		.mode = 0644,
+		.proc_handler = proc_dointvec_minmax,
+		.extra1 = (void *) SYSCTL_ZERO,
+		.extra2 = (void *) SYSCTL_INT_MAX,
+	},
+#ifdef CONFIG_PERSISTENT_KEYRINGS
+	{
+		.procname = "persistent_keyring_expiry",
+		.data = &persistent_keyring_expiry,
+		.maxlen = sizeof(unsigned),
+		.mode = 0644,
+		.proc_handler = proc_dointvec_minmax,
+		.extra1 = (void *) SYSCTL_ZERO,
+		.extra2 = (void *) SYSCTL_INT_MAX,
+	},
+#endif
+};
+
+static int __init init_security_keys_sysctls(void)
+{
+	register_sysctl_init("kernel/keys", key_sysctls);
+	return 0;
+}
+early_initcall(init_security_keys_sysctls);