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, 160 insertions, 0 deletions

diff --git a/include/trace/events/lock.h b/include/trace/events/lock.h
new file mode 100644
index 000000000..1ded869cd
--- /dev/null
+++ b/include/trace/events/lock.h
@@ -0,0 +1,160 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM lock
+
+#if !defined(_TRACE_LOCK_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_LOCK_H
+
+#include <linux/tracepoint.h>
+
+/* flags for lock:contention_begin */
+#define LCB_F_SPIN	(1U << 0)
+#define LCB_F_READ	(1U << 1)
+#define LCB_F_WRITE	(1U << 2)
+#define LCB_F_RT	(1U << 3)
+#define LCB_F_PERCPU	(1U << 4)
+#define LCB_F_MUTEX	(1U << 5)
+
+
+#ifdef CONFIG_LOCKDEP
+
+#include <linux/lockdep.h>
+
+TRACE_EVENT(lock_acquire,
+
+	TP_PROTO(struct lockdep_map *lock, unsigned int subclass,
+		int trylock, int read, int check,
+		struct lockdep_map *next_lock, unsigned long ip),
+
+	TP_ARGS(lock, subclass, trylock, read, check, next_lock, ip),
+
+	TP_STRUCT__entry(
+		__field(unsigned int, flags)
+		__string(name, lock->name)
+		__field(void *, lockdep_addr)
+	),
+
+	TP_fast_assign(
+		__entry->flags = (trylock ? 1 : 0) | (read ? 2 : 0);
+		__assign_str(name);
+		__entry->lockdep_addr = lock;
+	),
+
+	TP_printk("%p %s%s%s", __entry->lockdep_addr,
+		  (__entry->flags & 1) ? "try " : "",
+		  (__entry->flags & 2) ? "read " : "",
+		  __get_str(name))
+);
+
+DECLARE_EVENT_CLASS(lock,
+
+	TP_PROTO(struct lockdep_map *lock, unsigned long ip),
+
+	TP_ARGS(lock, ip),
+
+	TP_STRUCT__entry(
+		__string(	name, 	lock->name	)
+		__field(	void *, lockdep_addr	)
+	),
+
+	TP_fast_assign(
+		__assign_str(name);
+		__entry->lockdep_addr = lock;
+	),
+
+	TP_printk("%p %s",  __entry->lockdep_addr, __get_str(name))
+);
+
+DEFINE_EVENT(lock, lock_release,
+
+	TP_PROTO(struct lockdep_map *lock, unsigned long ip),
+
+	TP_ARGS(lock, ip)
+);
+
+#ifdef CONFIG_LOCK_STAT
+
+DEFINE_EVENT(lock, lock_contended,
+
+	TP_PROTO(struct lockdep_map *lock, unsigned long ip),
+
+	TP_ARGS(lock, ip)
+);
+
+DEFINE_EVENT(lock, lock_acquired,
+
+	TP_PROTO(struct lockdep_map *lock, unsigned long ip),
+
+	TP_ARGS(lock, ip)
+);
+
+#endif /* CONFIG_LOCK_STAT */
+#endif /* CONFIG_LOCKDEP */
+
+TRACE_EVENT(contention_begin,
+
+	TP_PROTO(void *lock, unsigned int flags),
+
+	TP_ARGS(lock, flags),
+
+	TP_STRUCT__entry(
+		__field(void *, lock_addr)
+		__field(unsigned int, flags)
+	),
+
+	TP_fast_assign(
+		__entry->lock_addr = lock;
+		__entry->flags = flags;
+	),
+
+	TP_printk("%p (flags=%s)", __entry->lock_addr,
+		  __print_flags(__entry->flags, "|",
+				{ LCB_F_SPIN,		"SPIN" },
+				{ LCB_F_READ,		"READ" },
+				{ LCB_F_WRITE,		"WRITE" },
+				{ LCB_F_RT,		"RT" },
+				{ LCB_F_PERCPU,		"PERCPU" },
+				{ LCB_F_MUTEX,		"MUTEX" }
+			  ))
+);
+
+TRACE_EVENT(contention_end,
+
+	TP_PROTO(void *lock, int ret),
+
+	TP_ARGS(lock, ret),
+
+	TP_STRUCT__entry(
+		__field(void *, lock_addr)
+		__field(int, ret)
+	),
+
+	TP_fast_assign(
+		__entry->lock_addr = lock;
+		__entry->ret = ret;
+	),
+
+	TP_printk("%p (ret=%d)", __entry->lock_addr, __entry->ret)
+);
+
+TRACE_EVENT(contended_release,
+
+	TP_PROTO(void *lock),
+
+	TP_ARGS(lock),
+
+	TP_STRUCT__entry(
+		__field(void *, lock_addr)
+	),
+
+	TP_fast_assign(
+		__entry->lock_addr = lock;
+	),
+
+	TP_printk("%p", __entry->lock_addr)
+);
+
+#endif /* _TRACE_LOCK_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>