net: ipv4: listified version of ip_rcv

Also involved adding a way to run a netfilter hook over a list of packets.
 Rather than attempting to make netfilter know about lists (which would be
 a major project in itself) we just let it call the regular okfn (in this
 case ip_rcv_finish()) for any packets it steals, and have it give us back
 a list of packets it's synchronously accepted (which normally NF_HOOK
 would automatically call okfn() on, but we want to be able to potentially
 pass the list to a listified version of okfn().)
The netfilter hooks themselves are indirect calls that still happen per-
 packet (see nf_hook_entry_hookfn()), but again, changing that can be left
 for future work.

There is potential for out-of-order receives if the netfilter hook ends up
 synchronously stealing packets, as they will be processed before any
 accepts earlier in the list.  However, it was already possible for an
 asynchronous accept to cause out-of-order receives, so presumably this is
 considered OK.

Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 62 insertions, 7 deletions

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 9263a2c114e0..c716be13d58c 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1882,6 +1882,7 @@ fs_initcall(ipv4_offload_init);
 static struct packet_type ip_packet_type __read_mostly = {
 	.type = cpu_to_be16(ETH_P_IP),
 	.func = ip_rcv,
+	.list_func = ip_list_rcv,
 };
 
 static int __init inet_init(void)
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 7582713dd18f..914240830bdf 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -408,10 +408,9 @@ drop_error:
 /*
  * 	Main IP Receive routine.
  */
-int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)
+static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net)
 {
 	const struct iphdr *iph;
-	struct net *net;
 	u32 len;
 
 	/* When the interface is in promisc. mode, drop all the crap
@@ -421,7 +420,6 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt,
 		goto drop;
 
 
-	net = dev_net(dev);
 	__IP_UPD_PO_STATS(net, IPSTATS_MIB_IN, skb->len);
 
 	skb = skb_share_check(skb, GFP_ATOMIC);
@@ -489,9 +487,7 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt,
 	/* Must drop socket now because of tproxy. */
 	skb_orphan(skb);
 
-	return NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING,
-		       net, NULL, skb, dev, NULL,
-		       ip_rcv_finish);
+	return skb;
 
 csum_error:
 	__IP_INC_STATS(net, IPSTATS_MIB_CSUMERRORS);
@@ -500,5 +496,63 @@ inhdr_error:
 drop:
 	kfree_skb(skb);
 out:
-	return NET_RX_DROP;
+	return NULL;
+}
+
+/*
+ * IP receive entry point
+ */
+int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt,
+	   struct net_device *orig_dev)
+{
+	struct net *net = dev_net(dev);
+
+	skb = ip_rcv_core(skb, net);
+	if (skb == NULL)
+		return NET_RX_DROP;
+	return NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING,
+		       net, NULL, skb, dev, NULL,
+		       ip_rcv_finish);
+}
+
+static void ip_sublist_rcv(struct list_head *head, struct net_device *dev,
+			   struct net *net)
+{
+	struct sk_buff *skb, *next;
+
+	NF_HOOK_LIST(NFPROTO_IPV4, NF_INET_PRE_ROUTING, net, NULL,
+		     head, dev, NULL, ip_rcv_finish);
+	list_for_each_entry_safe(skb, next, head, list)
+		ip_rcv_finish(net, NULL, skb);
+}
+
+/* Receive a list of IP packets */
+void ip_list_rcv(struct list_head *head, struct packet_type *pt,
+		 struct net_device *orig_dev)
+{
+	struct net_device *curr_dev = NULL;
+	struct net *curr_net = NULL;
+	struct sk_buff *skb, *next;
+	struct list_head sublist;
+
+	list_for_each_entry_safe(skb, next, head, list) {
+		struct net_device *dev = skb->dev;
+		struct net *net = dev_net(dev);
+
+		skb = ip_rcv_core(skb, net);
+		if (skb == NULL)
+			continue;
+
+		if (curr_dev != dev || curr_net != net) {
+			/* dispatch old sublist */
+			list_cut_before(&sublist, head, &skb->list);
+			if (!list_empty(&sublist))
+				ip_sublist_rcv(&sublist, dev, net);
+			/* start new sublist */
+			curr_dev = dev;
+			curr_net = net;
+		}
+	}
+	/* dispatch final sublist */
+	ip_sublist_rcv(head, curr_dev, curr_net);
 }