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, 68 insertions, 0 deletions

diff --git a/include/trace/events/devfreq.h b/include/trace/events/devfreq.h
new file mode 100644
index 000000000..6cbc4d59f
--- /dev/null
+++ b/include/trace/events/devfreq.h
@@ -0,0 +1,68 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM devfreq
+
+#if !defined(_TRACE_DEVFREQ_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_DEVFREQ_H
+
+#include <linux/devfreq.h>
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(devfreq_frequency,
+	TP_PROTO(struct devfreq *devfreq, unsigned long freq,
+		 unsigned long prev_freq),
+
+	TP_ARGS(devfreq, freq, prev_freq),
+
+	TP_STRUCT__entry(
+		__string(dev_name, dev_name(&devfreq->dev))
+		__field(unsigned long, freq)
+		__field(unsigned long, prev_freq)
+		__field(unsigned long, busy_time)
+		__field(unsigned long, total_time)
+	),
+
+	TP_fast_assign(
+		__assign_str(dev_name);
+		__entry->freq = freq;
+		__entry->prev_freq = prev_freq;
+		__entry->busy_time = devfreq->last_status.busy_time;
+		__entry->total_time = devfreq->last_status.total_time;
+	),
+
+	TP_printk("dev_name=%-30s freq=%-12lu prev_freq=%-12lu load=%-2lu",
+		__get_str(dev_name), __entry->freq, __entry->prev_freq,
+		__entry->total_time == 0 ? 0 :
+			(100 * __entry->busy_time) / __entry->total_time)
+);
+
+TRACE_EVENT(devfreq_monitor,
+	TP_PROTO(struct devfreq *devfreq),
+
+	TP_ARGS(devfreq),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, freq)
+		__field(unsigned long, busy_time)
+		__field(unsigned long, total_time)
+		__field(unsigned int, polling_ms)
+		__string(dev_name, dev_name(&devfreq->dev))
+	),
+
+	TP_fast_assign(
+		__entry->freq = devfreq->previous_freq;
+		__entry->busy_time = devfreq->last_status.busy_time;
+		__entry->total_time = devfreq->last_status.total_time;
+		__entry->polling_ms = devfreq->profile->polling_ms;
+		__assign_str(dev_name);
+	),
+
+	TP_printk("dev_name=%-30s freq=%-12lu polling_ms=%-3u load=%-2lu",
+		__get_str(dev_name), __entry->freq, __entry->polling_ms,
+		__entry->total_time == 0 ? 0 :
+			(100 * __entry->busy_time) / __entry->total_time)
+);
+#endif /* _TRACE_DEVFREQ_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>