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, 57 insertions, 0 deletions

diff --git a/include/trace/events/capability.h b/include/trace/events/capability.h
new file mode 100644
index 000000000..173402579
--- /dev/null
+++ b/include/trace/events/capability.h
@@ -0,0 +1,57 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM capability
+
+#if !defined(_TRACE_CAPABILITY_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_CAPABILITY_H
+
+#include <linux/cred.h>
+#include <linux/tracepoint.h>
+#include <linux/user_namespace.h>
+
+/**
+ * cap_capable - called after it's determined if a task has a particular
+ * effective capability
+ *
+ * @cred: The credentials used
+ * @target_ns: The user namespace of the resource being accessed
+ * @capable_ns: The user namespace in which the credential provides the
+ *              capability to access the targeted resource.
+ *              This will be NULL if ret is not 0.
+ * @cap: The capability to check for
+ * @ret: The return value of the check: 0 if it does, -ve if it does not
+ *
+ * Allows to trace calls to cap_capable in commoncap.c
+ */
+TRACE_EVENT(cap_capable,
+
+	TP_PROTO(const struct cred *cred, struct user_namespace *target_ns,
+		const struct user_namespace *capable_ns, int cap, int ret),
+
+	TP_ARGS(cred, target_ns, capable_ns, cap, ret),
+
+	TP_STRUCT__entry(
+		__field(const struct cred *, cred)
+		__field(struct user_namespace *, target_ns)
+		__field(const struct user_namespace *, capable_ns)
+		__field(int, cap)
+		__field(int, ret)
+	),
+
+	TP_fast_assign(
+		__entry->cred       = cred;
+		__entry->target_ns    = target_ns;
+		__entry->capable_ns = ret == 0 ? capable_ns : NULL;
+		__entry->cap        = cap;
+		__entry->ret        = ret;
+	),
+
+	TP_printk("cred %p, target_ns %p, capable_ns %p, cap %d, ret %d",
+		__entry->cred, __entry->target_ns, __entry->capable_ns, __entry->cap,
+		__entry->ret)
+);
+
+#endif /* _TRACE_CAPABILITY_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>