From: huangshaobo <huangshaobo6@huawei.com>
Subject: kfence: enable check kfence canary on panic via boot param

Out-of-bounds accesses that aren't caught by a guard page will result in
corruption of canary memory.  In pathological cases, where an object has
certain alignment requirements, an out-of-bounds access might never be
caught by the guard page.  Such corruptions, however, are only detected on
kfree() normally.  If the bug causes the kernel to panic before kfree(),
KFENCE has no opportunity to report the issue.  Such corruptions may also
indicate failing memory or other faults.

To provide some more information in such cases, add the option to check
canary bytes on panic.  This might help narrow the search for the panic
cause; but, due to only having the allocation stack trace, such reports
are difficult to use to diagnose an issue alone.  In most cases, such
reports are inactionable, and is therefore an opt-in feature (disabled by
default).

Link: https://lkml.kernel.org/r/20220425022456.44300-1-huangshaobo6@huawei.com
Signed-off-by: huangshaobo <huangshaobo6@huawei.com>
Suggested-by: chenzefeng <chenzefeng2@huawei.com>
Reviewed-by: Marco Elver <elver@google.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Xiaoming Ni <nixiaoming@huawei.com>
Cc: Wangbing <wangbing6@huawei.com>
Cc: Jubin Zhong <zhongjubin@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/kfence/core.c |   34 ++++++++++++++++++++++++++++++++++
 1 file changed, 34 insertions(+)

--- a/mm/kfence/core.c~kfence-enable-check-kfence-canary-on-panic-via-boot-param
+++ a/mm/kfence/core.c
@@ -21,6 +21,8 @@
 #include <linux/log2.h>
 #include <linux/memblock.h>
 #include <linux/moduleparam.h>
+#include <linux/notifier.h>
+#include <linux/panic_notifier.h>
 #include <linux/random.h>
 #include <linux/rcupdate.h>
 #include <linux/sched/clock.h>
@@ -99,6 +101,10 @@ module_param_named(skip_covered_thresh,
 static bool kfence_deferrable __read_mostly = IS_ENABLED(CONFIG_KFENCE_DEFERRABLE);
 module_param_named(deferrable, kfence_deferrable, bool, 0444);
 
+/* If true, check all canary bytes on panic. */
+static bool kfence_check_on_panic;
+module_param_named(check_on_panic, kfence_check_on_panic, bool, 0444);
+
 /* The pool of pages used for guard pages and objects. */
 char *__kfence_pool __read_mostly;
 EXPORT_SYMBOL(__kfence_pool); /* Export for test modules. */
@@ -727,6 +733,31 @@ static int __init kfence_debugfs_init(vo
 
 late_initcall(kfence_debugfs_init);
 
+/* === Panic Notifier ====================================================== */
+
+static void kfence_check_all_canary(void)
+{
+	int i;
+
+	for (i = 0; i < CONFIG_KFENCE_NUM_OBJECTS; i++) {
+		struct kfence_metadata *meta = &kfence_metadata[i];
+
+		if (meta->state == KFENCE_OBJECT_ALLOCATED)
+			for_each_canary(meta, check_canary_byte);
+	}
+}
+
+static int kfence_check_canary_callback(struct notifier_block *nb,
+					unsigned long reason, void *arg)
+{
+	kfence_check_all_canary();
+	return NOTIFY_OK;
+}
+
+static struct notifier_block kfence_check_canary_notifier = {
+	.notifier_call = kfence_check_canary_callback,
+};
+
 /* === Allocation Gate Timer ================================================ */
 
 static struct delayed_work kfence_timer;
@@ -804,6 +835,9 @@ static void kfence_init_enable(void)
 	else
 		INIT_DELAYED_WORK(&kfence_timer, toggle_allocation_gate);
 
+	if (kfence_check_on_panic)
+		atomic_notifier_chain_register(&panic_notifier_list, &kfence_check_canary_notifier);
+
 	WRITE_ONCE(kfence_enabled, true);
 	queue_delayed_work(system_unbound_wq, &kfence_timer, 0);
 
_