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, 95 insertions, 0 deletions

diff --git a/tools/perf/util/trigger.h b/tools/perf/util/trigger.h
new file mode 100644
index 000000000..33e997f9c
--- /dev/null
+++ b/tools/perf/util/trigger.h
@@ -0,0 +1,95 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __TRIGGER_H_
+#define __TRIGGER_H_ 1
+
+#include "asm/bug.h"
+
+/*
+ * Use trigger to model operations which need to be executed when
+ * an event (a signal, for example) is observed.
+ *
+ * States and transits:
+ *
+ *
+ *  OFF--> ON --> READY --(hit)--> HIT
+ *                 ^               |
+ *                 |            (ready)
+ *                 |               |
+ *                  \_____________/
+ *
+ * is_hit and is_ready are two key functions to query the state of
+ * a trigger. is_hit means the event already happen; is_ready means the
+ * trigger is waiting for the event.
+ */
+
+struct trigger {
+	volatile enum {
+		TRIGGER_ERROR		= -2,
+		TRIGGER_OFF		= -1,
+		TRIGGER_ON		= 0,
+		TRIGGER_READY		= 1,
+		TRIGGER_HIT		= 2,
+	} state;
+	const char *name;
+};
+
+#define TRIGGER_WARN_ONCE(t, exp) \
+	WARN_ONCE(t->state != exp, "trigger '%s' state transist error: %d in %s()\n", \
+		  t->name, t->state, __func__)
+
+static inline bool trigger_is_available(struct trigger *t)
+{
+	return t->state >= 0;
+}
+
+static inline bool trigger_is_error(struct trigger *t)
+{
+	return t->state <= TRIGGER_ERROR;
+}
+
+static inline void trigger_on(struct trigger *t)
+{
+	TRIGGER_WARN_ONCE(t, TRIGGER_OFF);
+	t->state = TRIGGER_ON;
+}
+
+static inline void trigger_ready(struct trigger *t)
+{
+	if (!trigger_is_available(t))
+		return;
+	t->state = TRIGGER_READY;
+}
+
+static inline void trigger_hit(struct trigger *t)
+{
+	if (!trigger_is_available(t))
+		return;
+	TRIGGER_WARN_ONCE(t, TRIGGER_READY);
+	t->state = TRIGGER_HIT;
+}
+
+static inline void trigger_off(struct trigger *t)
+{
+	if (!trigger_is_available(t))
+		return;
+	t->state = TRIGGER_OFF;
+}
+
+static inline void trigger_error(struct trigger *t)
+{
+	t->state = TRIGGER_ERROR;
+}
+
+static inline bool trigger_is_ready(struct trigger *t)
+{
+	return t->state == TRIGGER_READY;
+}
+
+static inline bool trigger_is_hit(struct trigger *t)
+{
+	return t->state == TRIGGER_HIT;
+}
+
+#define DEFINE_TRIGGER(n) \
+struct trigger n = {.state = TRIGGER_OFF, .name = #n}
+#endif