[PATCH v4 1/1] kasan: fix object remain in offline per-cpu quarantine

Kuan-Ying Lee Kuan-Ying.Lee at mediatek.com
Mon Dec 7 03:42:58 EST 2020


We hit this issue in our internal test.
When enabling generic kasan, a kfree()'d object is put into per-cpu
quarantine first. If the cpu goes offline, object still remains in
the per-cpu quarantine. If we call kmem_cache_destroy() now, slub
will report "Objects remaining" error.

[   74.982625] =============================================================================
[   74.983380] BUG test_module_slab (Not tainted): Objects remaining in test_module_slab on __kmem_cache_shutdown()
[   74.984145] -----------------------------------------------------------------------------
[   74.984145]
[   74.984883] Disabling lock debugging due to kernel taint
[   74.985561] INFO: Slab 0x(____ptrval____) objects=34 used=1 fp=0x(____ptrval____) flags=0x2ffff00000010200
[   74.986638] CPU: 3 PID: 176 Comm: cat Tainted: G    B             5.10.0-rc1-00007-g4525c8781ec0-dirty #10
[   74.987262] Hardware name: linux,dummy-virt (DT)
[   74.987606] Call trace:
[   74.987924]  dump_backtrace+0x0/0x2b0
[   74.988296]  show_stack+0x18/0x68
[   74.988698]  dump_stack+0xfc/0x168
[   74.989030]  slab_err+0xac/0xd4
[   74.989346]  __kmem_cache_shutdown+0x1e4/0x3c8
[   74.989779]  kmem_cache_destroy+0x68/0x130
[   74.990176]  test_version_show+0x84/0xf0
[   74.990679]  module_attr_show+0x40/0x60
[   74.991218]  sysfs_kf_seq_show+0x128/0x1c0
[   74.991656]  kernfs_seq_show+0xa0/0xb8
[   74.992059]  seq_read+0x1f0/0x7e8
[   74.992415]  kernfs_fop_read+0x70/0x338
[   74.993051]  vfs_read+0xe4/0x250
[   74.993498]  ksys_read+0xc8/0x180
[   74.993825]  __arm64_sys_read+0x44/0x58
[   74.994203]  el0_svc_common.constprop.0+0xac/0x228
[   74.994708]  do_el0_svc+0x38/0xa0
[   74.995088]  el0_sync_handler+0x170/0x178
[   74.995497]  el0_sync+0x174/0x180
[   74.996050] INFO: Object 0x(____ptrval____) @offset=15848
[   74.996752] INFO: Allocated in test_version_show+0x98/0xf0 age=8188 cpu=6 pid=172
[   75.000802]  stack_trace_save+0x9c/0xd0
[   75.002420]  set_track+0x64/0xf0
[   75.002770]  alloc_debug_processing+0x104/0x1a0
[   75.003171]  ___slab_alloc+0x628/0x648
[   75.004213]  __slab_alloc.isra.0+0x2c/0x58
[   75.004757]  kmem_cache_alloc+0x560/0x588
[   75.005376]  test_version_show+0x98/0xf0
[   75.005756]  module_attr_show+0x40/0x60
[   75.007035]  sysfs_kf_seq_show+0x128/0x1c0
[   75.007433]  kernfs_seq_show+0xa0/0xb8
[   75.007800]  seq_read+0x1f0/0x7e8
[   75.008128]  kernfs_fop_read+0x70/0x338
[   75.008507]  vfs_read+0xe4/0x250
[   75.008990]  ksys_read+0xc8/0x180
[   75.009462]  __arm64_sys_read+0x44/0x58
[   75.010085]  el0_svc_common.constprop.0+0xac/0x228
[   75.011006] kmem_cache_destroy test_module_slab: Slab cache still has objects

Register a cpu hotplug function to remove all objects in the offline
per-cpu quarantine when cpu is going offline. Set a per-cpu variable
to indicate this cpu is offline.

Signed-off-by: Kuan-Ying Lee <Kuan-Ying.Lee at mediatek.com>
Signed-off-by: Zqiang <qiang.zhang at windriver.com>
Suggested-by: Dmitry Vyukov <dvyukov at google.com>
Reported-by: Guangye Yang <guangye.yang at mediatek.com>
Reviewed-by: Dmitry Vyukov <dvyukov at google.com>
Cc: Andrey Ryabinin <aryabinin at virtuozzo.com>
Cc: Alexander Potapenko <glider at google.com>
Cc: Andrew Morton <akpm at linux-foundation.org>
Cc: Matthias Brugger <matthias.bgg at gmail.com>
Cc: Andrey Konovalov <andreyknvl at google.com>
Cc: Nicholas Tang <nicholas.tang at mediatek.com>
Cc: Miles Chen <miles.chen at mediatek.com>
Cc: Qian Cai <qcai at redhat.com>
Cc: Stephen Rothwell <sfr at canb.auug.org.au>
---
 mm/kasan/quarantine.c | 39 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 39 insertions(+)

diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c
index a598c3514e1a..55783125a767 100644
--- a/mm/kasan/quarantine.c
+++ b/mm/kasan/quarantine.c
@@ -19,6 +19,7 @@
 #include <linux/srcu.h>
 #include <linux/string.h>
 #include <linux/types.h>
+#include <linux/cpuhotplug.h>
 
 #include "../slab.h"
 #include "kasan.h"
@@ -33,6 +34,7 @@ struct qlist_head {
 	struct qlist_node *head;
 	struct qlist_node *tail;
 	size_t bytes;
+	bool offline;
 };
 
 #define QLIST_INIT { NULL, NULL, 0 }
@@ -191,6 +193,10 @@ bool quarantine_put(struct kmem_cache *cache, void *object)
 	local_irq_save(flags);
 
 	q = this_cpu_ptr(&cpu_quarantine);
+	if (q->offline) {
+		local_irq_restore(flags);
+		return false;
+	}
 	qlist_put(q, &meta->quarantine_link, cache->size);
 	if (unlikely(q->bytes > QUARANTINE_PERCPU_SIZE)) {
 		qlist_move_all(q, &temp);
@@ -333,3 +339,36 @@ void quarantine_remove_cache(struct kmem_cache *cache)
 
 	synchronize_srcu(&remove_cache_srcu);
 }
+
+static int kasan_cpu_online(unsigned int cpu)
+{
+	this_cpu_ptr(&cpu_quarantine)->offline = false;
+	return 0;
+}
+
+static int kasan_cpu_offline(unsigned int cpu)
+{
+	struct qlist_head *q;
+
+	q = this_cpu_ptr(&cpu_quarantine);
+	/* Ensure the ordering between the writing to q->offline and
+	 * qlist_free_all. Otherwise, cpu_quarantine may be corrupted
+	 * by interrupt.
+	 */
+	WRITE_ONCE(q->offline, true);
+	barrier();
+	qlist_free_all(q, NULL);
+	return 0;
+}
+
+static int __init kasan_cpu_quarantine_init(void)
+{
+	int ret = 0;
+
+	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "mm/kasan:online",
+				kasan_cpu_online, kasan_cpu_offline);
+	if (ret < 0)
+		pr_err("kasan cpu quarantine register failed [%d]\n", ret);
+	return ret;
+}
+late_initcall(kasan_cpu_quarantine_init);
-- 
2.18.0


More information about the Linux-mediatek mailing list