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, 70 insertions, 0 deletions

diff --git a/io_uring/alloc_cache.h b/io_uring/alloc_cache.h
new file mode 100644
index 000000000..962b6e2d0
--- /dev/null
+++ b/io_uring/alloc_cache.h
@@ -0,0 +1,70 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef IOU_ALLOC_CACHE_H
+#define IOU_ALLOC_CACHE_H
+
+#include <linux/io_uring_types.h>
+#include <linux/kasan.h>
+
+/*
+ * Don't allow the cache to grow beyond this size.
+ */
+#define IO_ALLOC_CACHE_MAX	128
+
+void io_alloc_cache_free(struct io_alloc_cache *cache,
+			 void (*free)(const void *));
+bool io_alloc_cache_init(struct io_alloc_cache *cache,
+			 unsigned max_nr, unsigned int size,
+			 unsigned int init_bytes);
+
+void *io_cache_alloc_new(struct io_alloc_cache *cache, gfp_t gfp);
+
+static inline bool io_alloc_cache_put(struct io_alloc_cache *cache,
+				      void *entry)
+{
+	if (cache->nr_cached < cache->max_cached) {
+		if (!kasan_mempool_poison_object(entry))
+			return false;
+		cache->entries[cache->nr_cached++] = entry;
+		return true;
+	}
+	return false;
+}
+
+static inline void *io_alloc_cache_get(struct io_alloc_cache *cache)
+{
+	if (cache->nr_cached) {
+		void *entry = cache->entries[--cache->nr_cached];
+
+		/*
+		 * If KASAN is enabled, always clear the initial bytes that
+		 * must be zeroed post alloc, in case any of them overlap
+		 * with KASAN storage.
+		 */
+#if defined(CONFIG_KASAN)
+		kasan_mempool_unpoison_object(entry, cache->elem_size);
+		if (cache->init_clear)
+			memset(entry, 0, cache->init_clear);
+#endif
+		return entry;
+	}
+
+	return NULL;
+}
+
+static inline void *io_cache_alloc(struct io_alloc_cache *cache, gfp_t gfp)
+{
+	void *obj;
+
+	obj = io_alloc_cache_get(cache);
+	if (obj)
+		return obj;
+	return io_cache_alloc_new(cache, gfp);
+}
+
+static inline void io_cache_free(struct io_alloc_cache *cache, void *obj)
+{
+	if (!io_alloc_cache_put(cache, obj))
+		kvfree(obj);
+}
+
+#endif