Merge remote-tracking branch 'torvalds/master' into perf/core

To pick up BPF changes we'll need.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 116 insertions, 22 deletions

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 62f65573eb04..fcb7c2f7f001 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -41,6 +41,8 @@
 #include <linux/in.h>
 #include <net/ip.h>
 #include <linux/ip.h>
+#include <linux/icmp.h>
+#include <linux/icmpv6.h>
 #include <linux/tcp.h>
 #include <linux/udp.h>
 #include <linux/slab.h>
@@ -200,6 +202,51 @@ atomic_t netpoll_block_tx = ATOMIC_INIT(0);
 
 unsigned int bond_net_id __read_mostly;
 
+static const struct flow_dissector_key flow_keys_bonding_keys[] = {
+	{
+		.key_id = FLOW_DISSECTOR_KEY_CONTROL,
+		.offset = offsetof(struct flow_keys, control),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_BASIC,
+		.offset = offsetof(struct flow_keys, basic),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_IPV4_ADDRS,
+		.offset = offsetof(struct flow_keys, addrs.v4addrs),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_IPV6_ADDRS,
+		.offset = offsetof(struct flow_keys, addrs.v6addrs),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_TIPC,
+		.offset = offsetof(struct flow_keys, addrs.tipckey),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_PORTS,
+		.offset = offsetof(struct flow_keys, ports),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_ICMP,
+		.offset = offsetof(struct flow_keys, icmp),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_VLAN,
+		.offset = offsetof(struct flow_keys, vlan),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_FLOW_LABEL,
+		.offset = offsetof(struct flow_keys, tags),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_GRE_KEYID,
+		.offset = offsetof(struct flow_keys, keyid),
+	},
+};
+
+static struct flow_dissector flow_keys_bonding __read_mostly;
+
 /*-------------------------- Forward declarations ---------------------------*/
 
 static int bond_init(struct net_device *bond_dev);
@@ -3252,39 +3299,78 @@ static inline u32 bond_eth_hash(struct sk_buff *skb)
 	return 0;
 }
 
-/* Extract the appropriate headers based on bond's xmit policy */
-static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb,
-			      struct flow_keys *fk)
+static bool bond_flow_ip(struct sk_buff *skb, struct flow_keys *fk,
+			 int *noff, int *proto, bool l34)
 {
 	const struct ipv6hdr *iph6;
 	const struct iphdr *iph;
-	int noff, proto = -1;
-
-	if (bond->params.xmit_policy > BOND_XMIT_POLICY_LAYER23)
-		return skb_flow_dissect_flow_keys(skb, fk, 0);
 
-	fk->ports.ports = 0;
-	noff = skb_network_offset(skb);
 	if (skb->protocol == htons(ETH_P_IP)) {
-		if (unlikely(!pskb_may_pull(skb, noff + sizeof(*iph))))
+		if (unlikely(!pskb_may_pull(skb, *noff + sizeof(*iph))))
 			return false;
-		iph = ip_hdr(skb);
+		iph = (const struct iphdr *)(skb->data + *noff);
 		iph_to_flow_copy_v4addrs(fk, iph);
-		noff += iph->ihl << 2;
+		*noff += iph->ihl << 2;
 		if (!ip_is_fragment(iph))
-			proto = iph->protocol;
+			*proto = iph->protocol;
 	} else if (skb->protocol == htons(ETH_P_IPV6)) {
-		if (unlikely(!pskb_may_pull(skb, noff + sizeof(*iph6))))
+		if (unlikely(!pskb_may_pull(skb, *noff + sizeof(*iph6))))
 			return false;
-		iph6 = ipv6_hdr(skb);
+		iph6 = (const struct ipv6hdr *)(skb->data + *noff);
 		iph_to_flow_copy_v6addrs(fk, iph6);
-		noff += sizeof(*iph6);
-		proto = iph6->nexthdr;
+		*noff += sizeof(*iph6);
+		*proto = iph6->nexthdr;
 	} else {
 		return false;
 	}
-	if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER34 && proto >= 0)
-		fk->ports.ports = skb_flow_get_ports(skb, noff, proto);
+
+	if (l34 && *proto >= 0)
+		fk->ports.ports = skb_flow_get_ports(skb, *noff, *proto);
+
+	return true;
+}
+
+/* Extract the appropriate headers based on bond's xmit policy */
+static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb,
+			      struct flow_keys *fk)
+{
+	bool l34 = bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER34;
+	int noff, proto = -1;
+
+	if (bond->params.xmit_policy > BOND_XMIT_POLICY_LAYER23) {
+		memset(fk, 0, sizeof(*fk));
+		return __skb_flow_dissect(NULL, skb, &flow_keys_bonding,
+					  fk, NULL, 0, 0, 0, 0);
+	}
+
+	fk->ports.ports = 0;
+	memset(&fk->icmp, 0, sizeof(fk->icmp));
+	noff = skb_network_offset(skb);
+	if (!bond_flow_ip(skb, fk, &noff, &proto, l34))
+		return false;
+
+	/* ICMP error packets contains at least 8 bytes of the header
+	 * of the packet which generated the error. Use this information
+	 * to correlate ICMP error packets within the same flow which
+	 * generated the error.
+	 */
+	if (proto == IPPROTO_ICMP || proto == IPPROTO_ICMPV6) {
+		skb_flow_get_icmp_tci(skb, &fk->icmp, skb->data,
+				      skb_transport_offset(skb),
+				      skb_headlen(skb));
+		if (proto == IPPROTO_ICMP) {
+			if (!icmp_is_err(fk->icmp.type))
+				return true;
+
+			noff += sizeof(struct icmphdr);
+		} else if (proto == IPPROTO_ICMPV6) {
+			if (!icmpv6_is_err(fk->icmp.type))
+				return true;
+
+			noff += sizeof(struct icmp6hdr);
+		}
+		return bond_flow_ip(skb, fk, &noff, &proto, l34);
+	}
 
 	return true;
 }
@@ -3311,10 +3397,14 @@ u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb)
 		return bond_eth_hash(skb);
 
 	if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER23 ||
-	    bond->params.xmit_policy == BOND_XMIT_POLICY_ENCAP23)
+	    bond->params.xmit_policy == BOND_XMIT_POLICY_ENCAP23) {
 		hash = bond_eth_hash(skb);
-	else
-		hash = (__force u32)flow.ports.ports;
+	} else {
+		if (flow.icmp.id)
+			memcpy(&hash, &flow.icmp, sizeof(hash));
+		else
+			memcpy(&hash, &flow.ports.ports, sizeof(hash));
+	}
 	hash ^= (__force u32)flow_get_u32_dst(&flow) ^
 		(__force u32)flow_get_u32_src(&flow);
 	hash ^= (hash >> 16);
@@ -4891,6 +4981,10 @@ static int __init bonding_init(void)
 			goto err;
 	}
 
+	skb_flow_dissector_init(&flow_keys_bonding,
+				flow_keys_bonding_keys,
+				ARRAY_SIZE(flow_keys_bonding_keys));
+
 	register_netdevice_notifier(&bond_netdev_notifier);
 out:
 	return res;