Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from David Miller:
 "Another merge window, another pull full of stuff:

   1) Support alternative names for network devices, from Jiri Pirko.

   2) Introduce per-netns netdev notifiers, also from Jiri Pirko.

   3) Support MSG_PEEK in vsock/virtio, from Matias Ezequiel Vara
      Larsen.

   4) Allow compiling out the TLS TOE code, from Jakub Kicinski.

   5) Add several new tracepoints to the kTLS code, also from Jakub.

   6) Support set channels ethtool callback in ena driver, from Sameeh
      Jubran.

   7) New SCTP events SCTP_ADDR_ADDED, SCTP_ADDR_REMOVED,
      SCTP_ADDR_MADE_PRIM, and SCTP_SEND_FAILED_EVENT. From Xin Long.

   8) Add XDP support to mvneta driver, from Lorenzo Bianconi.

   9) Lots of netfilter hw offload fixes, cleanups and enhancements,
      from Pablo Neira Ayuso.

  10) PTP support for aquantia chips, from Egor Pomozov.

  11) Add UDP segmentation offload support to igb, ixgbe, and i40e. From
      Josh Hunt.

  12) Add smart nagle to tipc, from Jon Maloy.

  13) Support L2 field rewrite by TC offloads in bnxt_en, from Venkat
      Duvvuru.

  14) Add a flow mask cache to OVS, from Tonghao Zhang.

  15) Add XDP support to ice driver, from Maciej Fijalkowski.

  16) Add AF_XDP support to ice driver, from Krzysztof Kazimierczak.

  17) Support UDP GSO offload in atlantic driver, from Igor Russkikh.

  18) Support it in stmmac driver too, from Jose Abreu.

  19) Support TIPC encryption and auth, from Tuong Lien.

  20) Introduce BPF trampolines, from Alexei Starovoitov.

  21) Make page_pool API more numa friendly, from Saeed Mahameed.

  22) Introduce route hints to ipv4 and ipv6, from Paolo Abeni.

  23) Add UDP segmentation offload to cxgb4, Rahul Lakkireddy"

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1857 commits)
  libbpf: Fix usage of u32 in userspace code
  mm: Implement no-MMU variant of vmalloc_user_node_flags
  slip: Fix use-after-free Read in slip_open
  net: dsa: sja1105: fix sja1105_parse_rgmii_delays()
  macvlan: schedule bc_work even if error
  enetc: add support Credit Based Shaper(CBS) for hardware offload
  net: phy: add helpers phy_(un)lock_mdio_bus
  mdio_bus: don't use managed reset-controller
  ax88179_178a: add ethtool_op_get_ts_info()
  mlxsw: spectrum_router: Fix use of uninitialized adjacency index
  mlxsw: spectrum_router: After underlay moves, demote conflicting tunnels
  bpf: Simplify __bpf_arch_text_poke poke type handling
  bpf: Introduce BPF_TRACE_x helper for the tracing tests
  bpf: Add bpf_jit_blinding_enabled for !CONFIG_BPF_JIT
  bpf, testing: Add various tail call test cases
  bpf, x86: Emit patchable direct jump as tail call
  bpf: Constant map key tracking for prog array pokes
  bpf: Add poke dependency tracking for prog array maps
  bpf: Add initial poke descriptor table for jit images
  bpf: Move owner type, jited info into array auxiliary data
  ...

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;