ipv4: use dst hint for ipv4 list receive

This is alike the previous change, with some additional ipv4 specific
quirk. Even when using the route hint we still have to do perform
additional per packet checks about source address validity: a new
helper is added to wrap them.

Hints are explicitly disabled if the destination is a local broadcast,
that keeps the code simple and local broadcast are a slower path anyway.

UDP flood performances vs recvmmsg() receiver:

vanilla		patched		delta
Kpps		Kpps		%
1683		1871		+11

In the worst case scenario - each packet has a different
destination address - the performance delta is within noise
range.

v3 -> v4:
 - re-enable hints for forward

v2 -> v3:
 - really fix build (sic) and hint usage check
 - use fib4_has_custom_rules() helpers (David A.)
 - add ip_extract_route_hint() helper (Edward C.)
 - use prev skb as hint instead of copying data (Willem)

v1 -> v2:
 - fix build issue with !CONFIG_IP_MULTIPLE_TABLES

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/net/route.h b/include/net/route.h
index 6c516840380db2babc82ef05e2f2e3c49aaeafa3..a9c60fc68e3699d4b9dcc1918b815708365aadad 100644 (file)
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -185,6 +185,10 @@ int ip_route_input_rcu(struct sk_buff *skb, __be32 dst, __be32 src,
                       u8 tos, struct net_device *devin,
                       struct fib_result *res);
 
+int ip_route_use_hint(struct sk_buff *skb, __be32 dst, __be32 src,
+                     u8 tos, struct net_device *devin,
+                     const struct sk_buff *hint);
+
 static inline int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src,
                                 u8 tos, struct net_device *devin)
 {

diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 24a95126e6981efe2bdbc8cef2f26bfc0072167d..aa438c6758a7f9fadbf3dddce56ea7821e290cf2 100644 (file)
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -302,16 +302,31 @@ drop:
        return true;
 }
 
+static bool ip_can_use_hint(const struct sk_buff *skb, const struct iphdr *iph,
+                           const struct sk_buff *hint)
+{
+       return hint && !skb_dst(skb) && ip_hdr(hint)->daddr == iph->daddr &&
+              ip_hdr(hint)->tos == iph->tos;
+}
+
 INDIRECT_CALLABLE_DECLARE(int udp_v4_early_demux(struct sk_buff *));
 INDIRECT_CALLABLE_DECLARE(int tcp_v4_early_demux(struct sk_buff *));
 static int ip_rcv_finish_core(struct net *net, struct sock *sk,
-                             struct sk_buff *skb, struct net_device *dev)
+                             struct sk_buff *skb, struct net_device *dev,
+                             const struct sk_buff *hint)
 {
        const struct iphdr *iph = ip_hdr(skb);
        int (*edemux)(struct sk_buff *skb);
        struct rtable *rt;
        int err;
 
+       if (ip_can_use_hint(skb, iph, hint)) {
+               err = ip_route_use_hint(skb, iph->daddr, iph->saddr, iph->tos,
+                                       dev, hint);
+               if (unlikely(err))
+                       goto drop_error;
+       }
+
        if (net->ipv4.sysctl_ip_early_demux &&
            !skb_dst(skb) &&
            !skb->sk &&
@@ -408,7 +423,7 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
        if (!skb)
                return NET_RX_SUCCESS;
 
-       ret = ip_rcv_finish_core(net, sk, skb, dev);
+       ret = ip_rcv_finish_core(net, sk, skb, dev, NULL);
        if (ret != NET_RX_DROP)
                ret = dst_input(skb);
        return ret;
@@ -535,11 +550,20 @@ static void ip_sublist_rcv_finish(struct list_head *head)
        }
 }
 
+static struct sk_buff *ip_extract_route_hint(const struct net *net,
+                                            struct sk_buff *skb, int rt_type)
+{
+       if (fib4_has_custom_rules(net) || rt_type == RTN_BROADCAST)
+               return NULL;
+
+       return skb;
+}
+
 static void ip_list_rcv_finish(struct net *net, struct sock *sk,
                               struct list_head *head)
 {
+       struct sk_buff *skb, *next, *hint = NULL;
        struct dst_entry *curr_dst = NULL;
-       struct sk_buff *skb, *next;
        struct list_head sublist;
 
        INIT_LIST_HEAD(&sublist);
@@ -554,11 +578,14 @@ static void ip_list_rcv_finish(struct net *net, struct sock *sk,
                skb = l3mdev_ip_rcv(skb);
                if (!skb)
                        continue;
-               if (ip_rcv_finish_core(net, sk, skb, dev) == NET_RX_DROP)
+               if (ip_rcv_finish_core(net, sk, skb, dev, hint) == NET_RX_DROP)
                        continue;
 
                dst = skb_dst(skb);
                if (curr_dst != dst) {
+                       hint = ip_extract_route_hint(net, skb,
+                                              ((struct rtable *)dst)->rt_type);
+
                        /* dispatch old sublist */
                        if (!list_empty(&sublist))
                                ip_sublist_rcv_finish(&sublist);

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index dcc4fa10138d499c366428a0fc8d00c6624cca1e..f88c93c38f1173614363b10cab7362771dd9ed8c 100644 (file)
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2019,10 +2019,52 @@ static int ip_mkroute_input(struct sk_buff *skb,
        return __mkroute_input(skb, res, in_dev, daddr, saddr, tos);
 }
 
+/* Implements all the saddr-related checks as ip_route_input_slow(),
+ * assuming daddr is valid and the destination is not a local broadcast one.
+ * Uses the provided hint instead of performing a route lookup.
+ */
+int ip_route_use_hint(struct sk_buff *skb, __be32 daddr, __be32 saddr,
+                     u8 tos, struct net_device *dev,
+                     const struct sk_buff *hint)
+{
+       struct in_device *in_dev = __in_dev_get_rcu(dev);
+       struct rtable *rt = (struct rtable *)hint;
+       struct net *net = dev_net(dev);
+       int err = -EINVAL;
+       u32 tag = 0;
+
+       if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr))
+               goto martian_source;
+
+       if (ipv4_is_zeronet(saddr))
+               goto martian_source;
+
+       if (ipv4_is_loopback(saddr) && !IN_DEV_NET_ROUTE_LOCALNET(in_dev, net))
+               goto martian_source;
+
+       if (rt->rt_type != RTN_LOCAL)
+               goto skip_validate_source;
+
+       tos &= IPTOS_RT_MASK;
+       err = fib_validate_source(skb, saddr, daddr, tos, 0, dev, in_dev, &tag);
+       if (err < 0)
+               goto martian_source;
+
+skip_validate_source:
+       skb_dst_copy(skb, hint);
+       return 0;
+
+martian_source:
+       ip_handle_martian_source(dev, in_dev, skb, daddr, saddr);
+       return err;
+}
+
 /*
  *     NOTE. We drop all the packets that has local source
  *     addresses, because every properly looped back packet
  *     must have correct destination already attached by output routine.
+ *     Changes in the enforced policies must be applied also to
+ *     ip_route_use_hint().
  *
  *     Such approach solves two big problems:
  *     1. Not simplex devices are handled properly.