net: ipv4: use a dedicated counter for icmp_v4 redirect packets

According to the algorithm described in the comment block at the
beginning of ip_rt_send_redirect, the host should try to send
'ip_rt_redirect_number' ICMP redirect packets with an exponential
backoff and then stop sending them at all assuming that the destination
ignores redirects.
If the device has previously sent some ICMP error packets that are
rate-limited (e.g TTL expired) and continues to receive traffic,
the redirect packets will never be transmitted. This happens since
peer->rate_tokens will be typically greater than 'ip_rt_redirect_number'
and so it will never be reset even if the redirect silence timeout
(ip_rt_redirect_silence) has elapsed without receiving any packet
requiring redirects.

Fix it by using a dedicated counter for the number of ICMP redirect
packets that has been sent by the host

I have not been able to identify a given commit that introduced the
issue since ip_rt_send_redirect implements the same rate-limiting
algorithm from commit 1da177e4c3f4 ("Linux-2.6.12-rc2")

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h
index 00b5e7825508aab5c72156f7fba889dd166899c2..74ff688568a0c6559946a9ae763d5c9822f1d112 100644 (file)
--- a/include/net/inetpeer.h
+++ b/include/net/inetpeer.h
@@ -39,6 +39,7 @@ struct inet_peer {
 
        u32                     metrics[RTAX_MAX];
        u32                     rate_tokens;    /* rate limiting for ICMP */
+       u32                     n_redirects;
        unsigned long           rate_last;
        /*
         * Once inet_peer is queued for deletion (refcnt == 0), following field

diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index d757b9642d0d1c418bffad5bcd50e8e7bf336c66..be778599bfedf73be139f67e814d46092a88dc40 100644 (file)
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -216,6 +216,7 @@ struct inet_peer *inet_getpeer(struct inet_peer_base *base,
                        atomic_set(&p->rid, 0);
                        p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW;
                        p->rate_tokens = 0;
+                       p->n_redirects = 0;
                        /* 60*HZ is arbitrary, but chosen enough high so that the first
                         * calculation of tokens is at its maximum.
                         */

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index ce92f73cf1042613cf29c95b59e10b31b1cd649b..5163b64f8fb3e31a8ebb3a0f3d49aad0191d2197 100644 (file)
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -887,13 +887,15 @@ void ip_rt_send_redirect(struct sk_buff *skb)
        /* No redirected packets during ip_rt_redirect_silence;
         * reset the algorithm.
         */
-       if (time_after(jiffies, peer->rate_last + ip_rt_redirect_silence))
+       if (time_after(jiffies, peer->rate_last + ip_rt_redirect_silence)) {
                peer->rate_tokens = 0;
+               peer->n_redirects = 0;
+       }
 
        /* Too many ignored redirects; do not send anything
         * set dst.rate_last to the last seen redirected packet.
         */
-       if (peer->rate_tokens >= ip_rt_redirect_number) {
+       if (peer->n_redirects >= ip_rt_redirect_number) {
                peer->rate_last = jiffies;
                goto out_put_peer;
        }
@@ -910,6 +912,7 @@ void ip_rt_send_redirect(struct sk_buff *skb)
                icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw);
                peer->rate_last = jiffies;
                ++peer->rate_tokens;
+               ++peer->n_redirects;
 #ifdef CONFIG_IP_ROUTE_VERBOSE
                if (log_martians &&
                    peer->rate_tokens == ip_rt_redirect_number)