[PATCH net-next 0/2] IP listification follow-ups

[PATCH net-next 0/2] IP listification follow-ups

[Edward Cree]

While working on IPv6 list processing, I found another bug in the IPv4
 version.  So this patch series has that fix, and the IPv6 version with
 both fixes incorporated.

Edward Cree (2):
  net: ipv4: fix list processing on L3 slave devices
  net: ipv6: listify ipv6_rcv() and ip6_rcv_finish()

 include/net/ipv6.h   |   2 +
 net/ipv4/ip_input.c  |  23 +++++----
 net/ipv6/af_inet6.c  |   1 +
 net/ipv6/ip6_input.c | 131 ++++++++++++++++++++++++++++++++++++++++++++-------
 4 files changed, 133 insertions(+), 24 deletions(-)

[PATCH net-next 1/2] net: ipv4: fix list processing on L3 slave devices

[Edward Cree]

If we have an L3 master device, l3mdev_ip_rcv() will steal the skb, but
 we were returning NET_RX_SUCCESS from ip_rcv_finish_core() which meant
 that ip_list_rcv_finish() would keep it on the list.  Instead let's
 move the l3mdev_ip_rcv() call into the caller, so that our response to
 a steal can be different in the single packet path (return
 NET_RX_SUCCESS) and the list path (forget this packet and continue).

Fixes: 5fa12739a53d net: ipv4: listify ip_rcv_finish
Signed-off-by: Edward Cree <ecree@solarflare.com>
---
 net/ipv4/ip_input.c | 23 +++++++++++++++--------
 1 file changed, 15 insertions(+), 8 deletions(-)

diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 14ba628b2761..1a3b6f32b1c9 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -316,13 +316,6 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk,
 	struct rtable *rt;
 	int err;
 
-	/* if ingress device is enslaved to an L3 master device pass the
-	 * skb to its handler for processing
-	 */
-	skb = l3mdev_ip_rcv(skb);
-	if (!skb)
-		return NET_RX_SUCCESS;
-
 	if (net->ipv4.sysctl_ip_early_demux &&
 	    !skb_dst(skb) &&
 	    !skb->sk &&
@@ -408,8 +401,16 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk,
 
 static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
-	int ret = ip_rcv_finish_core(net, sk, skb);
+	int ret;
+
+	/* if ingress device is enslaved to an L3 master device pass the
+	 * skb to its handler for processing
+	 */
+	skb = l3mdev_ip_rcv(skb);
+	if (!skb)
+		return NET_RX_SUCCESS;
 
+	ret = ip_rcv_finish_core(net, sk, skb);
 	if (ret != NET_RX_DROP)
 		ret = dst_input(skb);
 	return ret;
@@ -545,6 +546,12 @@ static void ip_list_rcv_finish(struct net *net, struct sock *sk,
 		struct dst_entry *dst;
 
 		list_del(&skb->list);
+		/* if ingress device is enslaved to an L3 master device pass the
+		 * skb to its handler for processing
+		 */
+		skb = l3mdev_ip_rcv(skb);
+		if (!skb)
+			continue;
 		if (ip_rcv_finish_core(net, sk, skb) == NET_RX_DROP)
 			continue;
 

[PATCH net-next 2/2] net: ipv6: listify ipv6_rcv() and ip6_rcv_finish()

[Edward Cree]

Essentially the same as the ipv4 equivalents.

Signed-off-by: Edward Cree <ecree@solarflare.com>
---
 include/net/ipv6.h   |   2 +
 net/ipv6/af_inet6.c  |   1 +
 net/ipv6/ip6_input.c | 131 ++++++++++++++++++++++++++++++++++++++++++++-------
 3 files changed, 118 insertions(+), 16 deletions(-)

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 16475c269749..b7843e0b16ee 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -922,6 +922,8 @@ static inline __be32 flowi6_get_flowlabel(const struct flowi6 *fl6)
 
 int ipv6_rcv(struct sk_buff *skb, struct net_device *dev,
 	     struct packet_type *pt, struct net_device *orig_dev);
+void ipv6_list_rcv(struct list_head *head, struct packet_type *pt,
+		   struct net_device *orig_dev);
 
 int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb);
 
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 9ed0eae91758..c9535354149f 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -764,6 +764,7 @@ EXPORT_SYMBOL_GPL(ipv6_opt_accepted);
 static struct packet_type ipv6_packet_type __read_mostly = {
 	.type = cpu_to_be16(ETH_P_IPV6),
 	.func = ipv6_rcv,
+	.list_func = ipv6_list_rcv,
 };
 
 static int __init ipv6_packet_init(void)
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index f08d34491ece..6242682be876 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -47,17 +47,11 @@
 #include <net/inet_ecn.h>
 #include <net/dst_metadata.h>
 
-int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
+static void ip6_rcv_finish_core(struct net *net, struct sock *sk,
+				struct sk_buff *skb)
 {
 	void (*edemux)(struct sk_buff *skb);
 
-	/* if ingress device is enslaved to an L3 master device pass the
-	 * skb to its handler for processing
-	 */
-	skb = l3mdev_ip6_rcv(skb);
-	if (!skb)
-		return NET_RX_SUCCESS;
-
 	if (net->ipv4.sysctl_ip_early_demux && !skb_dst(skb) && skb->sk == NULL) {
 		const struct inet6_protocol *ipprot;
 
@@ -67,20 +61,73 @@ int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 	}
 	if (!skb_valid_dst(skb))
 		ip6_route_input(skb);
+}
+
+int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+	/* if ingress device is enslaved to an L3 master device pass the
+	 * skb to its handler for processing
+	 */
+	skb = l3mdev_ip6_rcv(skb);
+	if (!skb)
+		return NET_RX_SUCCESS;
+	ip6_rcv_finish_core(net, sk, skb);
 
 	return dst_input(skb);
 }
 
-int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)
+static void ip6_sublist_rcv_finish(struct list_head *head)
+{
+	struct sk_buff *skb, *next;
+
+	list_for_each_entry_safe(skb, next, head, list)
+		dst_input(skb);
+}
+
+static void ip6_list_rcv_finish(struct net *net, struct sock *sk,
+				struct list_head *head)
+{
+	struct dst_entry *curr_dst = NULL;
+	struct sk_buff *skb, *next;
+	struct list_head sublist;
+
+	INIT_LIST_HEAD(&sublist);
+	list_for_each_entry_safe(skb, next, head, list) {
+		struct dst_entry *dst;
+
+		list_del(&skb->list);
+		/* if ingress device is enslaved to an L3 master device pass the
+		 * skb to its handler for processing
+		 */
+		skb = l3mdev_ip6_rcv(skb);
+		if (!skb)
+			continue;
+		ip6_rcv_finish_core(net, sk, skb);
+		dst = skb_dst(skb);
+		if (curr_dst != dst) {
+			/* dispatch old sublist */
+			if (!list_empty(&sublist))
+				ip6_sublist_rcv_finish(&sublist);
+			/* start new sublist */
+			INIT_LIST_HEAD(&sublist);
+			curr_dst = dst;
+		}
+		list_add_tail(&skb->list, &sublist);
+	}
+	/* dispatch final sublist */
+	ip6_sublist_rcv_finish(&sublist);
+}
+
+static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev,
+				    struct net *net)
 {
 	const struct ipv6hdr *hdr;
 	u32 pkt_len;
 	struct inet6_dev *idev;
-	struct net *net = dev_net(skb->dev);
 
 	if (skb->pkt_type == PACKET_OTHERHOST) {
 		kfree_skb(skb);
-		return NET_RX_DROP;
+		return NULL;
 	}
 
 	rcu_read_lock();
@@ -196,7 +243,7 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt
 		if (ipv6_parse_hopopts(skb) < 0) {
 			__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
 			rcu_read_unlock();
-			return NET_RX_DROP;
+			return NULL;
 		}
 	}
 
@@ -205,15 +252,67 @@ int ipv6_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_IPV6, NF_INET_PRE_ROUTING,
-		       net, NULL, skb, dev, NULL,
-		       ip6_rcv_finish);
+	return skb;
 err:
 	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
 drop:
 	rcu_read_unlock();
 	kfree_skb(skb);
-	return NET_RX_DROP;
+	return NULL;
+}
+
+int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)
+{
+	struct net *net = dev_net(skb->dev);
+
+	skb = ip6_rcv_core(skb, dev, net);
+	if (skb == NULL)
+		return NET_RX_DROP;
+	return NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING,
+		       net, NULL, skb, dev, NULL,
+		       ip6_rcv_finish);
+}
+
+static void ip6_sublist_rcv(struct list_head *head, struct net_device *dev,
+			    struct net *net)
+{
+	NF_HOOK_LIST(NFPROTO_IPV6, NF_INET_PRE_ROUTING, net, NULL,
+		     head, dev, NULL, ip6_rcv_finish);
+	ip6_list_rcv_finish(net, NULL, head);
+}
+
+/* Receive a list of IPv6 packets */
+void ipv6_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;
+
+	INIT_LIST_HEAD(&sublist);
+	list_for_each_entry_safe(skb, next, head, list) {
+		struct net_device *dev = skb->dev;
+		struct net *net = dev_net(dev);
+
+		list_del(&skb->list);
+		skb = ip6_rcv_core(skb, dev, net);
+		if (skb == NULL)
+			continue;
+
+		if (curr_dev != dev || curr_net != net) {
+			/* dispatch old sublist */
+			if (!list_empty(&sublist))
+				ip6_sublist_rcv(&sublist, curr_dev, curr_net);
+			/* start new sublist */
+			INIT_LIST_HEAD(&sublist);
+			curr_dev = dev;
+			curr_net = net;
+		}
+		list_add_tail(&skb->list, &sublist);
+	}
+	/* dispatch final sublist */
+	ip6_sublist_rcv(&sublist, curr_dev, curr_net);
 }
 
 /*

Re: [PATCH net-next 0/2] IP listification follow-ups

[David Miller]

From: Edward Cree <ecree@solarflare.com>
Date: Thu, 5 Jul 2018 15:45:04 +0100

> While working on IPv6 list processing, I found another bug in the IPv4
>  version.  So this patch series has that fix, and the IPv6 version with
>  both fixes incorporated.

Series applied.

Edward, please put (" ") around the commit header line text in your
Fixes: tags in the future.  I fixed it up for you this time.

Thank you.