ipv4: add reference counting to metrics

Andrey Konovalov reported crashes in ipv4_mtu()

I could reproduce the issue with KASAN kernels, between
10.246.7.151 and 10.246.7.152 :

1) 20 concurrent netperf -t TCP_RR -H 10.246.7.152 -l 1000 &

2) At the same time run following loop :
while :
do
 ip ro add 10.246.7.152 dev eth0 src 10.246.7.151 mtu 1500
 ip ro del 10.246.7.152 dev eth0 src 10.246.7.151 mtu 1500
done

Cong Wang attempted to add back rt->fi in commit
82486aa6f1b9 ("ipv4: restore rt->fi for reference counting")
but this proved to add some issues that were complex to solve.

Instead, I suggested to add a refcount to the metrics themselves,
being a standalone object (in particular, no reference to other objects)

I tried to make this patch as small as possible to ease its backport,
instead of being super clean. Note that we believe that only ipv4 dst
need to take care of the metric refcount. But if this is wrong,
this patch adds the basic infrastructure to extend this to other
families.

Many thanks to Julian Anastasov for reviewing this patch, and Cong Wang
for his efforts on this problem.

Fixes: 2860583fe840 ("ipv4: Kill rt->fi")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Reviewed-by: Julian Anastasov <ja@ssi.bg>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 14 insertions, 9 deletions

diff --git a/net/core/dst.c b/net/core/dst.c
index 960e503b5a52..6192f11beec9 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -151,13 +151,13 @@ int dst_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb)
 }
 EXPORT_SYMBOL(dst_discard_out);
 
-const u32 dst_default_metrics[RTAX_MAX + 1] = {
+const struct dst_metrics dst_default_metrics = {
 	/* This initializer is needed to force linker to place this variable
 	 * into const section. Otherwise it might end into bss section.
 	 * We really want to avoid false sharing on this variable, and catch
 	 * any writes on it.
 	 */
-	[RTAX_MAX] = 0xdeadbeef,
+	.refcnt = ATOMIC_INIT(1),
 };
 
 void dst_init(struct dst_entry *dst, struct dst_ops *ops,
@@ -169,7 +169,7 @@ void dst_init(struct dst_entry *dst, struct dst_ops *ops,
 	if (dev)
 		dev_hold(dev);
 	dst->ops = ops;
-	dst_init_metrics(dst, dst_default_metrics, true);
+	dst_init_metrics(dst, dst_default_metrics.metrics, true);
 	dst->expires = 0UL;
 	dst->path = dst;
 	dst->from = NULL;
@@ -314,25 +314,30 @@ EXPORT_SYMBOL(dst_release);
 
 u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old)
 {
-	u32 *p = kmalloc(sizeof(u32) * RTAX_MAX, GFP_ATOMIC);
+	struct dst_metrics *p = kmalloc(sizeof(*p), GFP_ATOMIC);
 
 	if (p) {
-		u32 *old_p = __DST_METRICS_PTR(old);
+		struct dst_metrics *old_p = (struct dst_metrics *)__DST_METRICS_PTR(old);
 		unsigned long prev, new;
 
-		memcpy(p, old_p, sizeof(u32) * RTAX_MAX);
+		atomic_set(&p->refcnt, 1);
+		memcpy(p->metrics, old_p->metrics, sizeof(p->metrics));
 
 		new = (unsigned long) p;
 		prev = cmpxchg(&dst->_metrics, old, new);
 
 		if (prev != old) {
 			kfree(p);
-			p = __DST_METRICS_PTR(prev);
+			p = (struct dst_metrics *)__DST_METRICS_PTR(prev);
 			if (prev & DST_METRICS_READ_ONLY)
 				p = NULL;
+		} else if (prev & DST_METRICS_REFCOUNTED) {
+			if (atomic_dec_and_test(&old_p->refcnt))
+				kfree(old_p);
 		}
 	}
-	return p;
+	BUILD_BUG_ON(offsetof(struct dst_metrics, metrics) != 0);
+	return (u32 *)p;
 }
 EXPORT_SYMBOL(dst_cow_metrics_generic);
 
@@ -341,7 +346,7 @@ void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old)
 {
 	unsigned long prev, new;
 
-	new = ((unsigned long) dst_default_metrics) | DST_METRICS_READ_ONLY;
+	new = ((unsigned long) &dst_default_metrics) | DST_METRICS_READ_ONLY;
 	prev = cmpxchg(&dst->_metrics, old, new);
 	if (prev == old)
 		kfree(__DST_METRICS_PTR(old));