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, 69 insertions, 0 deletions

diff --git a/tools/testing/memblock/internal.h b/tools/testing/memblock/internal.h
new file mode 100644
index 000000000..b6b1d147f
--- /dev/null
+++ b/tools/testing/memblock/internal.h
@@ -0,0 +1,69 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _MM_INTERNAL_H
+#define _MM_INTERNAL_H
+
+/*
+ * Enable memblock_dbg() messages
+ */
+#ifdef MEMBLOCK_DEBUG
+static int memblock_debug = 1;
+#endif
+
+#define pr_warn_ratelimited(fmt, ...)    printf(fmt, ##__VA_ARGS__)
+
+#define K(x) ((x) << (PAGE_SHIFT-10))
+
+bool mirrored_kernelcore = false;
+
+struct page {};
+static inline void *page_address(struct page *page)
+{
+	BUG();
+	return page;
+}
+
+static inline struct page *virt_to_page(void *virt)
+{
+	BUG();
+	return virt;
+}
+
+void memblock_free_pages(unsigned long pfn, unsigned int order)
+{
+}
+
+static inline void accept_memory(phys_addr_t start, unsigned long size)
+{
+}
+
+unsigned long free_reserved_area(void *start, void *end, int poison, const char *s);
+void free_reserved_page(struct page *page);
+
+static inline bool deferred_pages_enabled(void)
+{
+	return false;
+}
+
+#define for_each_valid_pfn(pfn, start_pfn, end_pfn)			 \
+	for ((pfn) = (start_pfn); (pfn) < (end_pfn); (pfn)++)
+
+static inline void *kasan_reset_tag(const void *addr)
+{
+	return (void *)addr;
+}
+
+static inline bool __is_kernel(unsigned long addr)
+{
+	return false;
+}
+
+#define for_each_valid_pfn(pfn, start_pfn, end_pfn)                     \
+       for ((pfn) = (start_pfn); (pfn) < (end_pfn); (pfn)++)
+
+static inline void init_deferred_page(unsigned long pfn, int nid)
+{
+}
+
+#define __SetPageReserved(p)	((void)(p))
+
+#endif