kfence: enable check kfence canary on panic via boot param

[ Upstream commit 3c81b3bb0a33e2b555edb8d7eb99a7ae4f17d8bb ]

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).

[akpm@linux-foundation.org: add __read_mostly, per Marco]
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>
Stable-dep-of: e64f81946adf ("kfence: skip __GFP_THISNODE allocations on NUMA systems")
Signed-off-by: Sasha Levin <sashal@kernel.org>

diff --git a/mm/kfence/core.c b/mm/kfence/core.c
index 1a2dc187a72f9c2ecd8654fc54cda0380b9c05f0..0d1a66811c32b71acd1b8727e84a7b66af110502 100644 (file)
--- a/mm/kfence/core.c
+++ b/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>
@@ -93,6 +95,10 @@ module_param_named(skip_covered_thresh, kfence_skip_covered_thresh, ulong, 0644)
 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 __read_mostly;
+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 __ro_after_init;
 EXPORT_SYMBOL(__kfence_pool); /* Export for test modules. */
@@ -697,6 +703,31 @@ static int kfence_debugfs_init(void)
 
 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;
@@ -784,6 +815,9 @@ void __init kfence_init(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);