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, 99 insertions, 0 deletions

diff --git a/include/trace/events/alarmtimer.h b/include/trace/events/alarmtimer.h
new file mode 100644
index 000000000..8e9c76a7f
--- /dev/null
+++ b/include/trace/events/alarmtimer.h
@@ -0,0 +1,99 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM alarmtimer
+
+#if !defined(_TRACE_ALARMTIMER_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_ALARMTIMER_H
+
+#include <linux/alarmtimer.h>
+#include <linux/rtc.h>
+#include <linux/tracepoint.h>
+
+TRACE_DEFINE_ENUM(ALARM_REALTIME);
+TRACE_DEFINE_ENUM(ALARM_BOOTTIME);
+TRACE_DEFINE_ENUM(ALARM_REALTIME_FREEZER);
+TRACE_DEFINE_ENUM(ALARM_BOOTTIME_FREEZER);
+
+#define show_alarm_type(type)	__print_flags(type, " | ",	\
+	{ 1 << ALARM_REALTIME, "REALTIME" },			\
+	{ 1 << ALARM_BOOTTIME, "BOOTTIME" },			\
+	{ 1 << ALARM_REALTIME_FREEZER, "REALTIME Freezer" },	\
+	{ 1 << ALARM_BOOTTIME_FREEZER, "BOOTTIME Freezer" })
+
+#ifdef CONFIG_RTC_CLASS
+TRACE_EVENT(alarmtimer_suspend,
+
+	TP_PROTO(ktime_t expires, int flag),
+
+	TP_ARGS(expires, flag),
+
+	TP_STRUCT__entry(
+		__field(s64, expires)
+		__field(unsigned char, alarm_type)
+	),
+
+	TP_fast_assign(
+		__entry->expires = expires;
+		__entry->alarm_type = flag;
+	),
+
+	TP_printk("alarmtimer type:%s expires:%llu",
+		  show_alarm_type((1 << __entry->alarm_type)),
+		  __entry->expires
+	)
+);
+#endif /* CONFIG_RTC_CLASS */
+
+DECLARE_EVENT_CLASS(alarm_class,
+
+	TP_PROTO(struct alarm *alarm, ktime_t now),
+
+	TP_ARGS(alarm, now),
+
+	TP_STRUCT__entry(
+		__field(void *,	alarm)
+		__field(unsigned char, alarm_type)
+		__field(s64, expires)
+		__field(s64, now)
+	),
+
+	TP_fast_assign(
+		__entry->alarm = alarm;
+		__entry->alarm_type = alarm->type;
+		__entry->expires = alarm->node.expires;
+		__entry->now = now;
+	),
+
+	TP_printk("alarmtimer:%p type:%s expires:%llu now:%llu",
+		  __entry->alarm,
+		  show_alarm_type((1 << __entry->alarm_type)),
+		  __entry->expires,
+		  __entry->now
+	)
+);
+
+DEFINE_EVENT(alarm_class, alarmtimer_fired,
+
+	TP_PROTO(struct alarm *alarm, ktime_t now),
+
+	TP_ARGS(alarm, now)
+);
+
+DEFINE_EVENT(alarm_class, alarmtimer_start,
+
+	TP_PROTO(struct alarm *alarm, ktime_t now),
+
+	TP_ARGS(alarm, now)
+);
+
+DEFINE_EVENT(alarm_class, alarmtimer_cancel,
+
+	TP_PROTO(struct alarm *alarm, ktime_t now),
+
+	TP_ARGS(alarm, now)
+);
+
+#endif /* _TRACE_ALARMTIMER_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>