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

Pull networking updates from David Miller:

 1) Support ipv6 checksum offload in sunvnet driver, from Shannon
    Nelson.

 2) Move to RB-tree instead of custom AVL code in inetpeer, from Eric
    Dumazet.

 3) Allow generic XDP to work on virtual devices, from John Fastabend.

 4) Add bpf device maps and XDP_REDIRECT, which can be used to build
    arbitrary switching frameworks using XDP. From John Fastabend.

 5) Remove UFO offloads from the tree, gave us little other than bugs.

 6) Remove the IPSEC flow cache, from Florian Westphal.

 7) Support ipv6 route offload in mlxsw driver.

 8) Support VF representors in bnxt_en, from Sathya Perla.

 9) Add support for forward error correction modes to ethtool, from
    Vidya Sagar Ravipati.

10) Add time filter for packet scheduler action dumping, from Jamal Hadi
    Salim.

11) Extend the zerocopy sendmsg() used by virtio and tap to regular
    sockets via MSG_ZEROCOPY. From Willem de Bruijn.

12) Significantly rework value tracking in the BPF verifier, from Edward
    Cree.

13) Add new jump instructions to eBPF, from Daniel Borkmann.

14) Rework rtnetlink plumbing so that operations can be run without
    taking the RTNL semaphore. From Florian Westphal.

15) Support XDP in tap driver, from Jason Wang.

16) Add 32-bit eBPF JIT for ARM, from Shubham Bansal.

17) Add Huawei hinic ethernet driver.

18) Allow to report MD5 keys in TCP inet_diag dumps, from Ivan
    Delalande.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1780 commits)
  i40e: point wb_desc at the nvm_wb_desc during i40e_read_nvm_aq
  i40e: avoid NVM acquire deadlock during NVM update
  drivers: net: xgene: Remove return statement from void function
  drivers: net: xgene: Configure tx/rx delay for ACPI
  drivers: net: xgene: Read tx/rx delay for ACPI
  rocker: fix kcalloc parameter order
  rds: Fix non-atomic operation on shared flag variable
  net: sched: don't use GFP_KERNEL under spin lock
  vhost_net: correctly check tx avail during rx busy polling
  net: mdio-mux: add mdio_mux parameter to mdio_mux_init()
  rxrpc: Make service connection lookup always check for retry
  net: stmmac: Delete dead code for MDIO registration
  gianfar: Fix Tx flow control deactivation
  cxgb4: Ignore MPS_TX_INT_CAUSE[Bubble] for T6
  cxgb4: Fix pause frame count in t4_get_port_stats
  cxgb4: fix memory leak
  tun: rename generic_xdp to skb_xdp
  tun: reserve extra headroom only when XDP is set
  net: dsa: bcm_sf2: Configure IMP port TC2QOS mapping
  net: dsa: bcm_sf2: Advertise number of egress queues
  ...

6 files changed, 19 insertions, 37 deletions

diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 03859e386b47..d558e882ca0c 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -579,8 +579,8 @@ static struct nf_conn *
 ovs_ct_find_existing(struct net *net, const struct nf_conntrack_zone *zone,
 		     u8 l3num, struct sk_buff *skb, bool natted)
 {
-	struct nf_conntrack_l3proto *l3proto;
-	struct nf_conntrack_l4proto *l4proto;
+	const struct nf_conntrack_l3proto *l3proto;
+	const struct nf_conntrack_l4proto *l4proto;
 	struct nf_conntrack_tuple tuple;
 	struct nf_conntrack_tuple_hash *h;
 	struct nf_conn *ct;
@@ -1180,15 +1180,13 @@ static int parse_nat(const struct nlattr *attr,
 		int type = nla_type(a);
 
 		if (type > OVS_NAT_ATTR_MAX) {
-			OVS_NLERR(log,
-				  "Unknown NAT attribute (type=%d, max=%d).\n",
+			OVS_NLERR(log, "Unknown NAT attribute (type=%d, max=%d)",
 				  type, OVS_NAT_ATTR_MAX);
 			return -EINVAL;
 		}
 
 		if (nla_len(a) != ovs_nat_attr_lens[type][ip_vers]) {
-			OVS_NLERR(log,
-				  "NAT attribute type %d has unexpected length (%d != %d).\n",
+			OVS_NLERR(log, "NAT attribute type %d has unexpected length (%d != %d)",
 				  type, nla_len(a),
 				  ovs_nat_attr_lens[type][ip_vers]);
 			return -EINVAL;
@@ -1198,9 +1196,7 @@ static int parse_nat(const struct nlattr *attr,
 		case OVS_NAT_ATTR_SRC:
 		case OVS_NAT_ATTR_DST:
 			if (info->nat) {
-				OVS_NLERR(log,
-					  "Only one type of NAT may be specified.\n"
-					  );
+				OVS_NLERR(log, "Only one type of NAT may be specified");
 				return -ERANGE;
 			}
 			info->nat |= OVS_CT_NAT;
@@ -1245,13 +1241,13 @@ static int parse_nat(const struct nlattr *attr,
 			break;
 
 		default:
-			OVS_NLERR(log, "Unknown nat attribute (%d).\n", type);
+			OVS_NLERR(log, "Unknown nat attribute (%d)", type);
 			return -EINVAL;
 		}
 	}
 
 	if (rem > 0) {
-		OVS_NLERR(log, "NAT attribute has %d unknown bytes.\n", rem);
+		OVS_NLERR(log, "NAT attribute has %d unknown bytes", rem);
 		return -EINVAL;
 	}
 	if (!info->nat) {
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 6b44fe405282..76cf273a56c7 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -335,8 +335,6 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb,
 			     const struct dp_upcall_info *upcall_info,
 				 uint32_t cutlen)
 {
-	unsigned short gso_type = skb_shinfo(skb)->gso_type;
-	struct sw_flow_key later_key;
 	struct sk_buff *segs, *nskb;
 	int err;
 
@@ -347,21 +345,9 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb,
 	if (segs == NULL)
 		return -EINVAL;
 
-	if (gso_type & SKB_GSO_UDP) {
-		/* The initial flow key extracted by ovs_flow_key_extract()
-		 * in this case is for a first fragment, so we need to
-		 * properly mark later fragments.
-		 */
-		later_key = *key;
-		later_key.ip.frag = OVS_FRAG_TYPE_LATER;
-	}
-
 	/* Queue all of the segments. */
 	skb = segs;
 	do {
-		if (gso_type & SKB_GSO_UDP && skb != segs)
-			key = &later_key;
-
 		err = queue_userspace_packet(dp, skb, key, upcall_info, cutlen);
 		if (err)
 			break;
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index 3f76cb765e5b..8c94cef25a72 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -72,8 +72,7 @@ void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags,
 			   const struct sk_buff *skb)
 {
 	struct flow_stats *stats;
-	int node = numa_node_id();
-	int cpu = smp_processor_id();
+	unsigned int cpu = smp_processor_id();
 	int len = skb->len + (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0);
 
 	stats = rcu_dereference(flow->stats[cpu]);
@@ -108,7 +107,7 @@ void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags,
 							      __GFP_THISNODE |
 							      __GFP_NOWARN |
 							      __GFP_NOMEMALLOC,
-							      node);
+							      numa_node_id());
 				if (likely(new_stats)) {
 					new_stats->used = jiffies;
 					new_stats->packet_count = 1;
@@ -118,6 +117,7 @@ void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags,
 
 					rcu_assign_pointer(flow->stats[cpu],
 							   new_stats);
+					cpumask_set_cpu(cpu, &flow->cpu_used_mask);
 					goto unlock;
 				}
 			}
@@ -145,7 +145,7 @@ void ovs_flow_stats_get(const struct sw_flow *flow,
 	memset(ovs_stats, 0, sizeof(*ovs_stats));
 
 	/* We open code this to make sure cpu 0 is always considered */
-	for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, cpu_possible_mask)) {
+	for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, &flow->cpu_used_mask)) {
 		struct flow_stats *stats = rcu_dereference_ovsl(flow->stats[cpu]);
 
 		if (stats) {
@@ -169,7 +169,7 @@ void ovs_flow_stats_clear(struct sw_flow *flow)
 	int cpu;
 
 	/* We open code this to make sure cpu 0 is always considered */
-	for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, cpu_possible_mask)) {
+	for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, &flow->cpu_used_mask)) {
 		struct flow_stats *stats = ovsl_dereference(flow->stats[cpu]);
 
 		if (stats) {
@@ -584,8 +584,7 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
 			key->ip.frag = OVS_FRAG_TYPE_LATER;
 			return 0;
 		}
-		if (nh->frag_off & htons(IP_MF) ||
-			skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
+		if (nh->frag_off & htons(IP_MF))
 			key->ip.frag = OVS_FRAG_TYPE_FIRST;
 		else
 			key->ip.frag = OVS_FRAG_TYPE_NONE;
@@ -701,9 +700,6 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
 
 		if (key->ip.frag == OVS_FRAG_TYPE_LATER)
 			return 0;
-		if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
-			key->ip.frag = OVS_FRAG_TYPE_FIRST;
-
 		/* Transport layer. */
 		if (key->ip.proto == NEXTHDR_TCP) {
 			if (tcphdr_ok(skb)) {
diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h
index a9bc1c875965..1875bba4f865 100644
--- a/net/openvswitch/flow.h
+++ b/net/openvswitch/flow.h
@@ -31,6 +31,7 @@
 #include <linux/jiffies.h>
 #include <linux/time.h>
 #include <linux/flex_array.h>
+#include <linux/cpumask.h>
 #include <net/inet_ecn.h>
 #include <net/ip_tunnels.h>
 #include <net/dst_metadata.h>
@@ -219,6 +220,7 @@ struct sw_flow {
 					 */
 	struct sw_flow_key key;
 	struct sw_flow_id id;
+	struct cpumask cpu_used_mask;
 	struct sw_flow_mask *mask;
 	struct sw_flow_actions __rcu *sf_acts;
 	struct flow_stats __rcu *stats[]; /* One for each CPU.  First one
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index f07d10ac35d8..e8eb427ce6d1 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -1255,7 +1255,7 @@ static int ovs_key_from_nlattrs(struct net *net, struct sw_flow_match *match,
 		}
 
 		if (!is_mask && ipv6_key->ipv6_label & htonl(0xFFF00000)) {
-			OVS_NLERR(log, "IPv6 flow label %x is out of range (max=%x).\n",
+			OVS_NLERR(log, "IPv6 flow label %x is out of range (max=%x)",
 				  ntohl(ipv6_key->ipv6_label), (1 << 20) - 1);
 			return -EINVAL;
 		}
diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c
index ea7a8073fa02..80ea2a71852e 100644
--- a/net/openvswitch/flow_table.c
+++ b/net/openvswitch/flow_table.c
@@ -98,6 +98,8 @@ struct sw_flow *ovs_flow_alloc(void)
 
 	RCU_INIT_POINTER(flow->stats[0], stats);
 
+	cpumask_set_cpu(0, &flow->cpu_used_mask);
+
 	return flow;
 err:
 	kmem_cache_free(flow_cache, flow);
@@ -141,7 +143,7 @@ static void flow_free(struct sw_flow *flow)
 	if (flow->sf_acts)
 		ovs_nla_free_flow_actions((struct sw_flow_actions __force *)flow->sf_acts);
 	/* We open code this to make sure cpu 0 is always considered */
-	for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, cpu_possible_mask))
+	for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, &flow->cpu_used_mask))
 		if (flow->stats[cpu])
 			kmem_cache_free(flow_stats_cache,
 					(struct flow_stats __force *)flow->stats[cpu]);