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, 77 insertions, 0 deletions

diff --git a/include/trace/events/napi.h b/include/trace/events/napi.h
new file mode 100644
index 000000000..b567b9ffe
--- /dev/null
+++ b/include/trace/events/napi.h
@@ -0,0 +1,77 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM napi
+
+#if !defined(_TRACE_NAPI_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_NAPI_H
+
+#include <linux/netdevice.h>
+#include <linux/tracepoint.h>
+#include <linux/ftrace.h>
+
+#define NO_DEV "(no_device)"
+
+TRACE_EVENT(napi_poll,
+
+	TP_PROTO(struct napi_struct *napi, int work, int budget),
+
+	TP_ARGS(napi, work, budget),
+
+	TP_STRUCT__entry(
+		__field(	struct napi_struct *,	napi)
+		__string(	dev_name, napi->dev ? napi->dev->name : NO_DEV)
+		__field(	int,			work)
+		__field(	int,			budget)
+	),
+
+	TP_fast_assign(
+		__entry->napi = napi;
+		__assign_str(dev_name);
+		__entry->work = work;
+		__entry->budget = budget;
+	),
+
+	TP_printk("napi poll on napi struct %p for device %s work %d budget %d",
+		  __entry->napi, __get_str(dev_name),
+		  __entry->work, __entry->budget)
+);
+
+TRACE_EVENT(dql_stall_detected,
+
+	TP_PROTO(unsigned short thrs, unsigned int len,
+		 unsigned long last_reap, unsigned long hist_head,
+		 unsigned long now, unsigned long *hist),
+
+	TP_ARGS(thrs, len, last_reap, hist_head, now, hist),
+
+	TP_STRUCT__entry(
+		__field(	unsigned short,		thrs)
+		__field(	unsigned int,		len)
+		__field(	unsigned long,		last_reap)
+		__field(	unsigned long,		hist_head)
+		__field(	unsigned long,		now)
+		__array(	unsigned long,		hist, 4)
+	),
+
+	TP_fast_assign(
+		__entry->thrs = thrs;
+		__entry->len = len;
+		__entry->last_reap = last_reap;
+		__entry->hist_head = hist_head * BITS_PER_LONG;
+		__entry->now = now;
+		memcpy(__entry->hist, hist, sizeof(entry->hist));
+	),
+
+	TP_printk("thrs %u  len %u  last_reap %lu  hist_head %lu  now %lu  hist %016lx %016lx %016lx %016lx",
+		  __entry->thrs, __entry->len,
+		  __entry->last_reap, __entry->hist_head, __entry->now,
+		  __entry->hist[0], __entry->hist[1],
+		  __entry->hist[2], __entry->hist[3])
+);
+
+#undef NO_DEV
+
+#endif /* _TRACE_NAPI_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>