Re: [PATCH net-next 4/5] ipv4: route: dissect flow in input path if fib rules need it
From: David Ahern <hidden>
Date: 2018-02-26 03:17:51
On 2/24/18 10:44 PM, Roopa Prabhu wrote:
quoted hunk ↗ jump to hunk
diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 26eefa2..72dd6c6 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c@@ -1783,7 +1783,7 @@ static void ip_multipath_l3_keys(const struct sk_buff *skb, /* if skb is set it will be used and fl4 can be NULL */
update that comment for flow_keys.
quoted hunk ↗ jump to hunk
int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4, - const struct sk_buff *skb) + const struct sk_buff *skb, struct flow_keys *flkeys) { struct net *net = fi->fib_net; struct flow_keys hash_keys;@@ -1810,14 +1810,23 @@ int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4, if (skb->l4_hash) return skb_get_hash_raw(skb) >> 1; memset(&hash_keys, 0, sizeof(hash_keys)); - skb_flow_dissect_flow_keys(skb, &keys, flag); - hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; - hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src; - hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst; - hash_keys.ports.src = keys.ports.src; - hash_keys.ports.dst = keys.ports.dst; - hash_keys.basic.ip_proto = keys.basic.ip_proto; + if (flkeys) { + hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; + hash_keys.addrs.v4addrs.src = flkeys->addrs.v4addrs.src; + hash_keys.addrs.v4addrs.dst = flkeys->addrs.v4addrs.dst; + hash_keys.ports.src = flkeys->ports.src; + hash_keys.ports.dst = flkeys->ports.dst; + hash_keys.basic.ip_proto = flkeys->basic.ip_proto; + } else { + skb_flow_dissect_flow_keys(skb, &keys, flag); + hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; + hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src; + hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst; + hash_keys.ports.src = keys.ports.src; + hash_keys.ports.dst = keys.ports.dst; + hash_keys.basic.ip_proto = keys.basic.ip_proto; + } } else { memset(&hash_keys, 0, sizeof(hash_keys)); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;@@ -1838,11 +1847,12 @@ int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4, static int ip_mkroute_input(struct sk_buff *skb, struct fib_result *res, struct in_device *in_dev, - __be32 daddr, __be32 saddr, u32 tos) + __be32 daddr, __be32 saddr, u32 tos, + struct flow_keys *hkeys) { #ifdef CONFIG_IP_ROUTE_MULTIPATH if (res->fi && res->fi->fib_nhs > 1) { - int h = fib_multipath_hash(res->fi, NULL, skb); + int h = fib_multipath_hash(res->fi, NULL, skb, hkeys); fib_select_multipath(res, h); }@@ -1868,13 +1878,14 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, struct fib_result *res) { struct in_device *in_dev = __in_dev_get_rcu(dev); + struct flow_keys *flkeys = NULL, _flkeys; + struct net *net = dev_net(dev); struct ip_tunnel_info *tun_info; - struct flowi4 fl4; + int err = -EINVAL; unsigned int flags = 0; u32 itag = 0; struct rtable *rth; - int err = -EINVAL; - struct net *net = dev_net(dev); + struct flowi4 fl4; bool do_cache; /* IP on this device is disabled. */@@ -1933,6 +1944,19 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, fl4.daddr = daddr; fl4.saddr = saddr; fl4.flowi4_uid = sock_net_uid(net, NULL); + +#ifdef CONFIG_IP_MULTIPLE_TABLES + if (net->ipv4.fib_rules_require_fldissect) { + unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP; + + memset(&_flkeys, 0, sizeof(_flkeys)); + skb_flow_dissect_flow_keys(skb, &_flkeys, flag); + fl4.fl4_sport = _flkeys.ports.src; + fl4.fl4_dport = _flkeys.ports.dst; + fl4.flowi4_proto = _flkeys.basic.ip_proto; + flkeys = &_flkeys; + } +#endif
I think a helper that compiles out if the config is disabled would be better; this function is already long enough.
quoted hunk ↗ jump to hunk
err = fib_lookup(net, &fl4, res, 0); if (err != 0) { if (!IN_DEV_FORWARD(in_dev))@@ -1958,7 +1982,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (res->type != RTN_UNICAST) goto martian_destination; - err = ip_mkroute_input(skb, res, in_dev, daddr, saddr, tos); + err = ip_mkroute_input(skb, res, in_dev, daddr, saddr, tos, flkeys); out: return err; brd_input: