| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <1432162349-788789-5-git-send-email-kafai@fb.com>
Date: Wed, 20 May 2015 15:52:23 -0700
From: Martin KaFai Lau <kafai@...com>
To: netdev <netdev@...r.kernel.org>
CC: David Miller <davem@...emloft.net>,
Hannes Frederic Sowa <hannes@...essinduktion.org>,
Julian Anastasov <ja@....bg>,
Steffen Klassert <steffen.klassert@...unet.com>,
Kernel Team <Kernel-team@...com>
Subject: [PATCH net-next v4 04/10] ipv6: Only create RTF_CACHE routes after encountering pmtu exception
This patch creates a RTF_CACHE routes only after encountering a pmtu
exception.
After ip6_rt_update_pmtu() has inserted the RTF_CACHE route to the fib6
tree, the rt->rt6i_node->fn_sernum is bumped which will fail the
ip6_dst_check() and trigger a relookup.
Signed-off-by: Martin KaFai Lau <kafai@...com>
Cc: Hannes Frederic Sowa <hannes@...essinduktion.org>
Cc: Steffen Klassert <steffen.klassert@...unet.com>
Cc: Julian Anastasov <ja@....bg>
---
include/net/ip6_route.h | 2 +-
net/ipv6/ip6_fib.c | 1 +
net/ipv6/route.c | 100 ++++++++++++++++++++++++------------------------
3 files changed, 53 insertions(+), 50 deletions(-)
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 4caf7d6..784ee3d 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -202,7 +202,7 @@ static inline struct in6_addr *rt6_nexthop(struct rt6_info *rt,
{
if (rt->rt6i_flags & RTF_GATEWAY)
return &rt->rt6i_gateway;
- else if (rt->rt6i_flags & RTF_CACHE)
+ else if (unlikely(rt->rt6i_flags & RTF_CACHE))
return &rt->rt6i_dst.addr;
else
return daddr;
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 96dbfff..7d66490 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -732,6 +732,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
rt6_clean_expires(iter);
else
rt6_set_expires(iter, rt->dst.expires);
+ iter->rt6i_pmtu = rt->rt6i_pmtu;
return -EEXIST;
}
/* If we have the same destination and the same metric,
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index c820308..52deb9d 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -873,16 +873,13 @@ static struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
struct flowi6 *fl6, int flags)
{
struct fib6_node *fn, *saved_fn;
- struct rt6_info *rt, *nrt;
+ struct rt6_info *rt;
int strict = 0;
- int attempts = 3;
- int err;
strict |= flags & RT6_LOOKUP_F_IFACE;
if (net->ipv6.devconf_all->forwarding == 0)
strict |= RT6_LOOKUP_F_REACHABLE;
-redo_fib6_lookup_lock:
read_lock_bh(&table->tb6_lock);
fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
@@ -901,46 +898,12 @@ redo_rt6_select:
strict &= ~RT6_LOOKUP_F_REACHABLE;
fn = saved_fn;
goto redo_rt6_select;
- } else {
- dst_hold(&rt->dst);
- read_unlock_bh(&table->tb6_lock);
- goto out2;
}
}
dst_hold(&rt->dst);
read_unlock_bh(&table->tb6_lock);
- if (rt->rt6i_flags & RTF_CACHE)
- goto out2;
-
- if (!rt6_is_gw_or_nonexthop(rt) ||
- !(rt->dst.flags & DST_HOST) || !(rt->rt6i_flags & RTF_LOCAL))
- nrt = ip6_rt_cache_alloc(rt, &fl6->daddr, &fl6->saddr);
- else
- goto out2;
-
- ip6_rt_put(rt);
- rt = nrt ? : net->ipv6.ip6_null_entry;
-
- dst_hold(&rt->dst);
- if (nrt) {
- err = ip6_ins_rt(nrt);
- if (!err)
- goto out2;
- }
-
- if (--attempts <= 0)
- goto out2;
-
- /*
- * Race condition! In the gap, when table->tb6_lock was
- * released someone could insert this route. Relookup.
- */
- ip6_rt_put(rt);
- goto redo_fib6_lookup_lock;
-
-out2:
rt6_dst_from_metrics_check(rt);
rt->dst.lastuse = jiffies;
rt->dst.__use++;
@@ -1113,24 +1076,63 @@ static void ip6_link_failure(struct sk_buff *skb)
}
}
-static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
- struct sk_buff *skb, u32 mtu)
+static void rt6_do_update_pmtu(struct rt6_info *rt, u32 mtu)
+{
+ struct net *net = dev_net(rt->dst.dev);
+
+ rt->rt6i_flags |= RTF_MODIFIED;
+ rt->rt6i_pmtu = mtu;
+ rt6_update_expires(rt, net->ipv6.sysctl.ip6_rt_mtu_expires);
+}
+
+static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
+ const struct ipv6hdr *iph, u32 mtu)
{
struct rt6_info *rt6 = (struct rt6_info *)dst;
- dst_confirm(dst);
- if (mtu < dst_mtu(dst) && (rt6->rt6i_flags & RTF_CACHE)) {
- struct net *net = dev_net(dst->dev);
+ if (rt6->rt6i_flags & RTF_LOCAL)
+ return;
- rt6->rt6i_flags |= RTF_MODIFIED;
- if (mtu < IPV6_MIN_MTU)
- mtu = IPV6_MIN_MTU;
+ dst_confirm(dst);
+ mtu = max_t(u32, mtu, IPV6_MIN_MTU);
+ if (mtu >= dst_mtu(dst))
+ return;
- rt6->rt6i_pmtu = mtu;
- rt6_update_expires(rt6, net->ipv6.sysctl.ip6_rt_mtu_expires);
+ if (rt6->rt6i_flags & RTF_CACHE) {
+ rt6_do_update_pmtu(rt6, mtu);
+ } else {
+ const struct in6_addr *daddr, *saddr;
+ struct rt6_info *nrt6;
+
+ if (iph) {
+ daddr = &iph->daddr;
+ saddr = &iph->saddr;
+ } else if (sk) {
+ daddr = &sk->sk_v6_daddr;
+ saddr = &inet6_sk(sk)->saddr;
+ } else {
+ return;
+ }
+ nrt6 = ip6_rt_cache_alloc(rt6, daddr, saddr);
+ if (nrt6) {
+ rt6_do_update_pmtu(nrt6, mtu);
+
+ /* ip6_ins_rt(nrt6) will bump the
+ * rt6->rt6i_node->fn_sernum
+ * which will fail the next rt6_check() and
+ * invalidate the sk->sk_dst_cache.
+ */
+ ip6_ins_rt(nrt6);
+ }
}
}
+static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
+ struct sk_buff *skb, u32 mtu)
+{
+ __ip6_rt_update_pmtu(dst, sk, skb ? ipv6_hdr(skb) : NULL, mtu);
+}
+
void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
int oif, u32 mark)
{
@@ -1147,7 +1149,7 @@ void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
dst = ip6_route_output(net, NULL, &fl6);
if (!dst->error)
- ip6_rt_update_pmtu(dst, NULL, skb, ntohl(mtu));
+ __ip6_rt_update_pmtu(dst, NULL, iph, ntohl(mtu));
dst_release(dst);
}
EXPORT_SYMBOL_GPL(ip6_update_pmtu);
--
1.8.1
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists