From: Julian Anastasov <ja@ssi.bg>
To: netdev@vger.kernel.org
Subject: [PATCH net 4/6] ipv4: introduce rt_uses_gateway
Date: Sun, 7 Oct 2012 14:26:06 +0300 [thread overview]
Message-ID: <1349609168-9848-5-git-send-email-ja@ssi.bg> (raw)
In-Reply-To: <1349609168-9848-1-git-send-email-ja@ssi.bg>
Add new flag to remember when route is via gateway.
We will use it to allow rt_gateway to contain address of
directly connected host for the cases when DST_NOCACHE is
used or when the NH exception caches per-destination route
without DST_NOCACHE flag, i.e. when routes are not used for
other destinations. By this way we force the neighbour
resolving to work with the routed destination but we
can use different address in the packet, feature needed
for IPVS-DR where original packet for virtual IP is routed
via route to real IP.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
---
include/net/route.h | 3 +-
net/ipv4/inet_connection_sock.c | 4 +-
net/ipv4/ip_forward.c | 2 +-
net/ipv4/ip_output.c | 4 +-
net/ipv4/route.c | 45 +++++++++++++++++++++-----------------
net/ipv4/xfrm4_policy.c | 1 +
6 files changed, 33 insertions(+), 26 deletions(-)
diff --git a/include/net/route.h b/include/net/route.h
index da22243..bc40b63 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -48,7 +48,8 @@ struct rtable {
int rt_genid;
unsigned int rt_flags;
__u16 rt_type;
- __u16 rt_is_input;
+ __u8 rt_is_input;
+ __u8 rt_uses_gateway;
int rt_iif;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index f0c5b9c..d34ce29 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -406,7 +406,7 @@ struct dst_entry *inet_csk_route_req(struct sock *sk,
rt = ip_route_output_flow(net, fl4, sk);
if (IS_ERR(rt))
goto no_route;
- if (opt && opt->opt.is_strictroute && rt->rt_gateway)
+ if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway)
goto route_err;
return &rt->dst;
@@ -442,7 +442,7 @@ struct dst_entry *inet_csk_route_child_sock(struct sock *sk,
rt = ip_route_output_flow(net, fl4, sk);
if (IS_ERR(rt))
goto no_route;
- if (opt && opt->opt.is_strictroute && rt->rt_gateway)
+ if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway)
goto route_err;
rcu_read_unlock();
return &rt->dst;
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 7f35ac2..694de3b 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -85,7 +85,7 @@ int ip_forward(struct sk_buff *skb)
rt = skb_rtable(skb);
- if (opt->is_strictroute && rt->rt_gateway)
+ if (opt->is_strictroute && rt->rt_uses_gateway)
goto sr_failed;
if (unlikely(skb->len > dst_mtu(&rt->dst) && !skb_is_gso(skb) &&
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 24a29a3..6537a40 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -193,7 +193,7 @@ static inline int ip_finish_output2(struct sk_buff *skb)
}
rcu_read_lock_bh();
- nexthop = rt->rt_gateway ? rt->rt_gateway : ip_hdr(skb)->daddr;
+ nexthop = (__force u32) rt_nexthop(rt, ip_hdr(skb)->daddr);
neigh = __ipv4_neigh_lookup_noref(dev, nexthop);
if (unlikely(!neigh))
neigh = __neigh_create(&arp_tbl, &nexthop, dev, false);
@@ -371,7 +371,7 @@ int ip_queue_xmit(struct sk_buff *skb, struct flowi *fl)
skb_dst_set_noref(skb, &rt->dst);
packet_routed:
- if (inet_opt && inet_opt->opt.is_strictroute && rt->rt_gateway)
+ if (inet_opt && inet_opt->opt.is_strictroute && rt->rt_uses_gateway)
goto no_route;
/* OK, we know where to send it, allocate and build IP header. */
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 0a600cc..eaf9575 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1123,7 +1123,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst)
mtu = dst->dev->mtu;
if (unlikely(dst_metric_locked(dst, RTAX_MTU))) {
- if (rt->rt_gateway && mtu > 576)
+ if (rt->rt_uses_gateway && mtu > 576)
mtu = 576;
}
@@ -1174,7 +1174,9 @@ static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe,
if (fnhe->fnhe_gw) {
rt->rt_flags |= RTCF_REDIRECTED;
rt->rt_gateway = fnhe->fnhe_gw;
- }
+ rt->rt_uses_gateway = 1;
+ } else if (!rt->rt_gateway)
+ rt->rt_gateway = daddr;
orig = rcu_dereference(fnhe->fnhe_rth);
rcu_assign_pointer(fnhe->fnhe_rth, rt);
@@ -1183,13 +1185,6 @@ static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe,
fnhe->fnhe_stamp = jiffies;
ret = true;
- } else {
- /* Routes we intend to cache in nexthop exception have
- * the DST_NOCACHE bit clear. However, if we are
- * unsuccessful at storing this route into the cache
- * we really need to set it.
- */
- rt->dst.flags |= DST_NOCACHE;
}
spin_unlock_bh(&fnhe_lock);
@@ -1215,13 +1210,7 @@ static bool rt_cache_route(struct fib_nh *nh, struct rtable *rt)
if (orig)
rt_free(orig);
} else {
- /* Routes we intend to cache in the FIB nexthop have
- * the DST_NOCACHE bit clear. However, if we are
- * unsuccessful at storing this route into the cache
- * we really need to set it.
- */
nocache:
- rt->dst.flags |= DST_NOCACHE;
ret = false;
}
@@ -1284,8 +1273,10 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
if (fi) {
struct fib_nh *nh = &FIB_RES_NH(*res);
- if (nh->nh_gw && nh->nh_scope == RT_SCOPE_LINK)
+ if (nh->nh_gw && nh->nh_scope == RT_SCOPE_LINK) {
rt->rt_gateway = nh->nh_gw;
+ rt->rt_uses_gateway = 1;
+ }
dst_init_metrics(&rt->dst, fi->fib_metrics, true);
#ifdef CONFIG_IP_ROUTE_CLASSID
rt->dst.tclassid = nh->nh_tclassid;
@@ -1294,8 +1285,18 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
cached = rt_bind_exception(rt, fnhe, daddr);
else if (!(rt->dst.flags & DST_NOCACHE))
cached = rt_cache_route(nh, rt);
- }
- if (unlikely(!cached))
+ if (unlikely(!cached)) {
+ /* Routes we intend to cache in nexthop exception or
+ * FIB nexthop have the DST_NOCACHE bit clear.
+ * However, if we are unsuccessful at storing this
+ * route into the cache we really need to set it.
+ */
+ rt->dst.flags |= DST_NOCACHE;
+ if (!rt->rt_gateway)
+ rt->rt_gateway = daddr;
+ rt_add_uncached_list(rt);
+ }
+ } else
rt_add_uncached_list(rt);
#ifdef CONFIG_IP_ROUTE_CLASSID
@@ -1363,6 +1364,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
rth->rt_iif = 0;
rth->rt_pmtu = 0;
rth->rt_gateway = 0;
+ rth->rt_uses_gateway = 0;
INIT_LIST_HEAD(&rth->rt_uncached);
if (our) {
rth->dst.input= ip_local_deliver;
@@ -1432,7 +1434,6 @@ static int __mkroute_input(struct sk_buff *skb,
return -EINVAL;
}
-
err = fib_validate_source(skb, saddr, daddr, tos, FIB_RES_OIF(*res),
in_dev->dev, in_dev, &itag);
if (err < 0) {
@@ -1488,6 +1489,7 @@ static int __mkroute_input(struct sk_buff *skb,
rth->rt_iif = 0;
rth->rt_pmtu = 0;
rth->rt_gateway = 0;
+ rth->rt_uses_gateway = 0;
INIT_LIST_HEAD(&rth->rt_uncached);
rth->dst.input = ip_forward;
@@ -1658,6 +1660,7 @@ local_input:
rth->rt_iif = 0;
rth->rt_pmtu = 0;
rth->rt_gateway = 0;
+ rth->rt_uses_gateway = 0;
INIT_LIST_HEAD(&rth->rt_uncached);
if (res.type == RTN_UNREACHABLE) {
rth->dst.input= ip_error;
@@ -1832,6 +1835,7 @@ add:
rth->rt_iif = orig_oif ? : 0;
rth->rt_pmtu = 0;
rth->rt_gateway = 0;
+ rth->rt_uses_gateway = 0;
INIT_LIST_HEAD(&rth->rt_uncached);
RT_CACHE_STAT_INC(out_slow_tot);
@@ -2110,6 +2114,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or
rt->rt_flags = ort->rt_flags;
rt->rt_type = ort->rt_type;
rt->rt_gateway = ort->rt_gateway;
+ rt->rt_uses_gateway = ort->rt_uses_gateway;
INIT_LIST_HEAD(&rt->rt_uncached);
@@ -2188,7 +2193,7 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src,
if (nla_put_be32(skb, RTA_PREFSRC, fl4->saddr))
goto nla_put_failure;
}
- if (rt->rt_gateway &&
+ if (rt->rt_uses_gateway &&
nla_put_be32(skb, RTA_GATEWAY, rt->rt_gateway))
goto nla_put_failure;
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 681ea2f..05c5ab8 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -91,6 +91,7 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
RTCF_LOCAL);
xdst->u.rt.rt_type = rt->rt_type;
xdst->u.rt.rt_gateway = rt->rt_gateway;
+ xdst->u.rt.rt_uses_gateway = rt->rt_uses_gateway;
xdst->u.rt.rt_pmtu = rt->rt_pmtu;
INIT_LIST_HEAD(&xdst->u.rt.rt_uncached);
--
1.7.3.4
next prev parent reply other threads:[~2012-10-07 11:20 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-10-07 11:26 [PATCH net 0/6] ipv4: Changes for rt_gateway Julian Anastasov
2012-10-07 11:26 ` [PATCH net 1/6] ipv4: fix sending of redirects Julian Anastasov
2012-10-08 19:16 ` David Miller
2012-10-08 20:43 ` Julian Anastasov
2012-10-08 20:41 ` David Miller
2012-10-07 11:26 ` [PATCH net 2/6] ipv4: fix forwarding for strict source routes Julian Anastasov
2012-10-07 11:26 ` [PATCH net 3/6] ipv4: add check if nh_pcpu_rth_output is allocated Julian Anastasov
2012-10-07 13:34 ` Eric Dumazet
2012-10-07 17:24 ` Julian Anastasov
2012-10-08 19:17 ` David Miller
2012-10-07 11:26 ` Julian Anastasov [this message]
2012-10-07 11:26 ` [PATCH net 5/6] ipv4: Add FLOWI_FLAG_KNOWN_NH Julian Anastasov
2012-10-07 11:26 ` [PATCH net 6/6] ipvs: fix ARP resolving for direct routing mode Julian Anastasov
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1349609168-9848-5-git-send-email-ja@ssi.bg \
--to=ja@ssi.bg \
--cc=netdev@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).