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>

2 files changed, 12 insertions, 6 deletions

diff --git a/include/net/dst.h b/include/net/dst.h
index 049af33da3b6..cfc043784166 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -107,10 +107,16 @@ struct dst_entry {
 	};
 };
 
+struct dst_metrics {
+	u32		metrics[RTAX_MAX];
+	atomic_t	refcnt;
+};
+extern const struct dst_metrics dst_default_metrics;
+
 u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old);
-extern const u32 dst_default_metrics[];
 
 #define DST_METRICS_READ_ONLY		0x1UL
+#define DST_METRICS_REFCOUNTED		0x2UL
 #define DST_METRICS_FLAGS		0x3UL
 #define __DST_METRICS_PTR(Y)	\
 	((u32 *)((Y) & ~DST_METRICS_FLAGS))
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 6692c5758b33..f7f6aa789c61 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -114,11 +114,11 @@ struct fib_info {
 	__be32			fib_prefsrc;
 	u32			fib_tb_id;
 	u32			fib_priority;
-	u32			*fib_metrics;
-#define fib_mtu fib_metrics[RTAX_MTU-1]
-#define fib_window fib_metrics[RTAX_WINDOW-1]
-#define fib_rtt fib_metrics[RTAX_RTT-1]
-#define fib_advmss fib_metrics[RTAX_ADVMSS-1]
+	struct dst_metrics	*fib_metrics;
+#define fib_mtu fib_metrics->metrics[RTAX_MTU-1]
+#define fib_window fib_metrics->metrics[RTAX_WINDOW-1]
+#define fib_rtt fib_metrics->metrics[RTAX_RTT-1]
+#define fib_advmss fib_metrics->metrics[RTAX_ADVMSS-1]
 	int			fib_nhs;
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	int			fib_weight;