1 files changed, 292 insertions, 175 deletions

diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index a1670dff0629..25cd35f5922e 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -5,6 +5,7 @@
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <linux/if_vlan.h>
+#include <linux/filter.h>
 #include <net/dsa.h>
 #include <net/dst_metadata.h>
 #include <net/ip.h>
@@ -21,8 +22,10 @@
 #include <linux/ppp_defs.h>
 #include <linux/stddef.h>
 #include <linux/if_ether.h>
+#include <linux/if_hsr.h>
 #include <linux/mpls.h>
 #include <linux/tcp.h>
+#include <linux/ptp_classify.h>
 #include <net/flow_dissector.h>
 #include <scsi/fc/fc_fcoe.h>
 #include <uapi/linux/batadv_packet.h>
@@ -31,8 +34,7 @@
 #include <net/netfilter/nf_conntrack_core.h>
 #include <net/netfilter/nf_conntrack_labels.h>
 #endif
-
-static DEFINE_MUTEX(flow_dissector_mutex);
+#include <linux/bpf-netns.h>
 
 static void dissector_set_key(struct flow_dissector *flow_dissector,
 			      enum flow_dissector_key_id key_id)
@@ -49,7 +51,7 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector,
 	memset(flow_dissector, 0, sizeof(*flow_dissector));
 
 	for (i = 0; i < key_count; i++, key++) {
-		/* User should make sure that every key target offset is withing
+		/* User should make sure that every key target offset is within
 		 * boundaries of unsigned short.
 		 */
 		BUG_ON(key->offset > USHRT_MAX);
@@ -70,54 +72,11 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector,
 }
 EXPORT_SYMBOL(skb_flow_dissector_init);
 
-int skb_flow_dissector_prog_query(const union bpf_attr *attr,
-				  union bpf_attr __user *uattr)
+#ifdef CONFIG_BPF_SYSCALL
+int flow_dissector_bpf_prog_attach_check(struct net *net,
+					 struct bpf_prog *prog)
 {
-	__u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids);
-	u32 prog_id, prog_cnt = 0, flags = 0;
-	struct bpf_prog *attached;
-	struct net *net;
-
-	if (attr->query.query_flags)
-		return -EINVAL;
-
-	net = get_net_ns_by_fd(attr->query.target_fd);
-	if (IS_ERR(net))
-		return PTR_ERR(net);
-
-	rcu_read_lock();
-	attached = rcu_dereference(net->flow_dissector_prog);
-	if (attached) {
-		prog_cnt = 1;
-		prog_id = attached->aux->id;
-	}
-	rcu_read_unlock();
-
-	put_net(net);
-
-	if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags)))
-		return -EFAULT;
-	if (copy_to_user(&uattr->query.prog_cnt, &prog_cnt, sizeof(prog_cnt)))
-		return -EFAULT;
-
-	if (!attr->query.prog_cnt || !prog_ids || !prog_cnt)
-		return 0;
-
-	if (copy_to_user(prog_ids, &prog_id, sizeof(u32)))
-		return -EFAULT;
-
-	return 0;
-}
-
-int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr,
-				       struct bpf_prog *prog)
-{
-	struct bpf_prog *attached;
-	struct net *net;
-	int ret = 0;
-
-	net = current->nsproxy->net_ns;
-	mutex_lock(&flow_dissector_mutex);
+	enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR;
 
 	if (net == &init_net) {
 		/* BPF flow dissector in the root namespace overrides
@@ -130,54 +89,20 @@ int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr,
 		for_each_net(ns) {
 			if (ns == &init_net)
 				continue;
-			if (rcu_access_pointer(ns->flow_dissector_prog)) {
-				ret = -EEXIST;
-				goto out;
-			}
+			if (rcu_access_pointer(ns->bpf.run_array[type]))
+				return -EEXIST;
 		}
 	} else {
 		/* Make sure root flow dissector is not attached
 		 * when attaching to the non-root namespace.
 		 */
-		if (rcu_access_pointer(init_net.flow_dissector_prog)) {
-			ret = -EEXIST;
-			goto out;
-		}
-	}
-
-	attached = rcu_dereference_protected(net->flow_dissector_prog,
-					     lockdep_is_held(&flow_dissector_mutex));
-	if (attached == prog) {
-		/* The same program cannot be attached twice */
-		ret = -EINVAL;
-		goto out;
+		if (rcu_access_pointer(init_net.bpf.run_array[type]))
+			return -EEXIST;
 	}
-	rcu_assign_pointer(net->flow_dissector_prog, prog);
-	if (attached)
-		bpf_prog_put(attached);
-out:
-	mutex_unlock(&flow_dissector_mutex);
-	return ret;
-}
 
-int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr)
-{
-	struct bpf_prog *attached;
-	struct net *net;
-
-	net = current->nsproxy->net_ns;
-	mutex_lock(&flow_dissector_mutex);
-	attached = rcu_dereference_protected(net->flow_dissector_prog,
-					     lockdep_is_held(&flow_dissector_mutex));
-	if (!attached) {
-		mutex_unlock(&flow_dissector_mutex);
-		return -ENOENT;
-	}
-	RCU_INIT_POINTER(net->flow_dissector_prog, NULL);
-	bpf_prog_put(attached);
-	mutex_unlock(&flow_dissector_mutex);
 	return 0;
 }
+#endif /* CONFIG_BPF_SYSCALL */
 
 /**
  * __skb_flow_get_ports - extract the upper layer ports and return them
@@ -191,7 +116,7 @@ int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr)
  * is the protocol port offset returned from proto_ports_offset
  */
 __be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto,
-			    void *data, int hlen)
+			    const void *data, int hlen)
 {
 	int poff = proto_ports_offset(ip_proto);
 
@@ -238,7 +163,7 @@ static bool icmp_has_id(u8 type)
  */
 void skb_flow_get_icmp_tci(const struct sk_buff *skb,
 			   struct flow_dissector_key_icmp *key_icmp,
-			   void *data, int thoff, int hlen)
+			   const void *data, int thoff, int hlen)
 {
 	struct icmphdr *ih, _ih;
 
@@ -253,7 +178,7 @@ void skb_flow_get_icmp_tci(const struct sk_buff *skb,
 	 * avoid confusion with packets without such field
 	 */
 	if (icmp_has_id(ih->type))
-		key_icmp->id = ih->un.echo.id ? : 1;
+		key_icmp->id = ih->un.echo.id ? ntohs(ih->un.echo.id) : 1;
 	else
 		key_icmp->id = 0;
 }
@@ -264,8 +189,8 @@ EXPORT_SYMBOL(skb_flow_get_icmp_tci);
  */
 static void __skb_flow_dissect_icmp(const struct sk_buff *skb,
 				    struct flow_dissector *flow_dissector,
-				    void *target_container,
-				    void *data, int thoff, int hlen)
+				    void *target_container, const void *data,
+				    int thoff, int hlen)
 {
 	struct flow_dissector_key_icmp *key_icmp;
 
@@ -279,6 +204,30 @@ static void __skb_flow_dissect_icmp(const struct sk_buff *skb,
 	skb_flow_get_icmp_tci(skb, key_icmp, data, thoff, hlen);
 }
 
+static void __skb_flow_dissect_l2tpv3(const struct sk_buff *skb,
+				      struct flow_dissector *flow_dissector,
+				      void *target_container, const void *data,
+				      int nhoff, int hlen)
+{
+	struct flow_dissector_key_l2tpv3 *key_l2tpv3;
+	struct {
+		__be32 session_id;
+	} *hdr, _hdr;
+
+	if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_L2TPV3))
+		return;
+
+	hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr);
+	if (!hdr)
+		return;
+
+	key_l2tpv3 = skb_flow_dissector_target(flow_dissector,
+					       FLOW_DISSECTOR_KEY_L2TPV3,
+					       target_container);
+
+	key_l2tpv3->session_id = hdr->session_id;
+}
+
 void skb_flow_dissect_meta(const struct sk_buff *skb,
 			   struct flow_dissector *flow_dissector,
 			   void *target_container)
@@ -314,9 +263,8 @@ skb_flow_dissect_set_enc_addr_type(enum flow_dissector_key_id type,
 void
 skb_flow_dissect_ct(const struct sk_buff *skb,
 		    struct flow_dissector *flow_dissector,
-		    void *target_container,
-		    u16 *ctinfo_map,
-		    size_t mapsize)
+		    void *target_container, u16 *ctinfo_map,
+		    size_t mapsize, bool post_ct, u16 zone)
 {
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
 	struct flow_dissector_key_ct *key;
@@ -328,13 +276,20 @@ skb_flow_dissect_ct(const struct sk_buff *skb,
 		return;
 
 	ct = nf_ct_get(skb, &ctinfo);
-	if (!ct)
+	if (!ct && !post_ct)
 		return;
 
 	key = skb_flow_dissector_target(flow_dissector,
 					FLOW_DISSECTOR_KEY_CT,
 					target_container);
 
+	if (!ct) {
+		key->ct_state = TCA_FLOWER_KEY_CT_FLAGS_TRACKED |
+				TCA_FLOWER_KEY_CT_FLAGS_INVALID;
+		key->ct_zone = zone;
+		return;
+	}
+
 	if (ctinfo < mapsize)
 		key->ct_state = ctinfo_map[ctinfo];
 #if IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES)
@@ -461,56 +416,86 @@ skb_flow_dissect_tunnel_info(const struct sk_buff *skb,
 }
 EXPORT_SYMBOL(skb_flow_dissect_tunnel_info);
 
+void skb_flow_dissect_hash(const struct sk_buff *skb,
+			   struct flow_dissector *flow_dissector,
+			   void *target_container)
+{
+	struct flow_dissector_key_hash *key;
+
+	if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_HASH))
+		return;
+
+	key = skb_flow_dissector_target(flow_dissector,
+					FLOW_DISSECTOR_KEY_HASH,
+					target_container);
+
+	key->hash = skb_get_hash_raw(skb);
+}
+EXPORT_SYMBOL(skb_flow_dissect_hash);
+
 static enum flow_dissect_ret
 __skb_flow_dissect_mpls(const struct sk_buff *skb,
 			struct flow_dissector *flow_dissector,
-			void *target_container, void *data, int nhoff, int hlen)
+			void *target_container, const void *data, int nhoff,
+			int hlen, int lse_index, bool *entropy_label)
 {
-	struct flow_dissector_key_keyid *key_keyid;
-	struct mpls_label *hdr, _hdr[2];
-	u32 entry, label;
+	struct mpls_label *hdr, _hdr;
+	u32 entry, label, bos;
 
 	if (!dissector_uses_key(flow_dissector,
 				FLOW_DISSECTOR_KEY_MPLS_ENTROPY) &&
 	    !dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_MPLS))
 		return FLOW_DISSECT_RET_OUT_GOOD;
 
+	if (lse_index >= FLOW_DIS_MPLS_MAX)
+		return FLOW_DISSECT_RET_OUT_GOOD;
+
 	hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data,
 				   hlen, &_hdr);
 	if (!hdr)
 		return FLOW_DISSECT_RET_OUT_BAD;
 
-	entry = ntohl(hdr[0].entry);
+	entry = ntohl(hdr->entry);
 	label = (entry & MPLS_LS_LABEL_MASK) >> MPLS_LS_LABEL_SHIFT;
+	bos = (entry & MPLS_LS_S_MASK) >> MPLS_LS_S_SHIFT;
 
 	if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_MPLS)) {
 		struct flow_dissector_key_mpls *key_mpls;
+		struct flow_dissector_mpls_lse *lse;
 
 		key_mpls = skb_flow_dissector_target(flow_dissector,
 						     FLOW_DISSECTOR_KEY_MPLS,
 						     target_container);
-		key_mpls->mpls_label = label;
-		key_mpls->mpls_ttl = (entry & MPLS_LS_TTL_MASK)
-					>> MPLS_LS_TTL_SHIFT;
-		key_mpls->mpls_tc = (entry & MPLS_LS_TC_MASK)
-					>> MPLS_LS_TC_SHIFT;
-		key_mpls->mpls_bos = (entry & MPLS_LS_S_MASK)
-					>> MPLS_LS_S_SHIFT;
+		lse = &key_mpls->ls[lse_index];
+
+		lse->mpls_ttl = (entry & MPLS_LS_TTL_MASK) >> MPLS_LS_TTL_SHIFT;
+		lse->mpls_bos = bos;
+		lse->mpls_tc = (entry & MPLS_LS_TC_MASK) >> MPLS_LS_TC_SHIFT;
+		lse->mpls_label = label;
+		dissector_set_mpls_lse(key_mpls, lse_index);
 	}
 
-	if (label == MPLS_LABEL_ENTROPY) {
+	if (*entropy_label &&
+	    dissector_uses_key(flow_dissector,
+			       FLOW_DISSECTOR_KEY_MPLS_ENTROPY)) {
+		struct flow_dissector_key_keyid *key_keyid;
+
 		key_keyid = skb_flow_dissector_target(flow_dissector,
 						      FLOW_DISSECTOR_KEY_MPLS_ENTROPY,
 						      target_container);
-		key_keyid->keyid = hdr[1].entry & htonl(MPLS_LS_LABEL_MASK);
+		key_keyid->keyid = cpu_to_be32(label);
 	}
-	return FLOW_DISSECT_RET_OUT_GOOD;
+
+	*entropy_label = label == MPLS_LABEL_ENTROPY;
+
+	return bos ? FLOW_DISSECT_RET_OUT_GOOD : FLOW_DISSECT_RET_PROTO_AGAIN;
 }
 
 static enum flow_dissect_ret
 __skb_flow_dissect_arp(const struct sk_buff *skb,
 		       struct flow_dissector *flow_dissector,
-		       void *target_container, void *data, int nhoff, int hlen)
+		       void *target_container, const void *data,
+		       int nhoff, int hlen)
 {
 	struct flow_dissector_key_arp *key_arp;
 	struct {
@@ -566,7 +551,7 @@ static enum flow_dissect_ret
 __skb_flow_dissect_gre(const struct sk_buff *skb,
 		       struct flow_dissector_key_control *key_control,
 		       struct flow_dissector *flow_dissector,
-		       void *target_container, void *data,
+		       void *target_container, const void *data,
 		       __be16 *p_proto, int *p_nhoff, int *p_hlen,
 		       unsigned int flags)
 {
@@ -706,8 +691,8 @@ __skb_flow_dissect_gre(const struct sk_buff *skb,
 static enum flow_dissect_ret
 __skb_flow_dissect_batadv(const struct sk_buff *skb,
 			  struct flow_dissector_key_control *key_control,
-			  void *data, __be16 *p_proto, int *p_nhoff, int hlen,
-			  unsigned int flags)
+			  const void *data, __be16 *p_proto, int *p_nhoff,
+			  int hlen, unsigned int flags)
 {
 	struct {
 		struct batadv_unicast_packet batadv_unicast;
@@ -738,7 +723,8 @@ __skb_flow_dissect_batadv(const struct sk_buff *skb,
 static void
 __skb_flow_dissect_tcp(const struct sk_buff *skb,
 		       struct flow_dissector *flow_dissector,
-		       void *target_container, void *data, int thoff, int hlen)
+		       void *target_container, const void *data,
+		       int thoff, int hlen)
 {
 	struct flow_dissector_key_tcp *key_tcp;
 	struct tcphdr *th, _th;
@@ -762,8 +748,8 @@ __skb_flow_dissect_tcp(const struct sk_buff *skb,
 static void
 __skb_flow_dissect_ports(const struct sk_buff *skb,
 			 struct flow_dissector *flow_dissector,
-			 void *target_container, void *data, int nhoff,
-			 u8 ip_proto, int hlen)
+			 void *target_container, const void *data,
+			 int nhoff, u8 ip_proto, int hlen)
 {
 	enum flow_dissector_key_id dissector_ports = FLOW_DISSECTOR_KEY_MAX;
 	struct flow_dissector_key_ports *key_ports;
@@ -787,7 +773,8 @@ __skb_flow_dissect_ports(const struct sk_buff *skb,
 static void
 __skb_flow_dissect_ipv4(const struct sk_buff *skb,
 			struct flow_dissector *flow_dissector,
-			void *target_container, void *data, const struct iphdr *iph)
+			void *target_container, const void *data,
+			const struct iphdr *iph)
 {
 	struct flow_dissector_key_ip *key_ip;
 
@@ -804,7 +791,8 @@ __skb_flow_dissect_ipv4(const struct sk_buff *skb,
 static void
 __skb_flow_dissect_ipv6(const struct sk_buff *skb,
 			struct flow_dissector *flow_dissector,
-			void *target_container, void *data, const struct ipv6hdr *iph)
+			void *target_container, const void *data,
+			const struct ipv6hdr *iph)
 {
 	struct flow_dissector_key_ip *key_ip;
 
@@ -871,8 +859,10 @@ static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys,
 		key_addrs = skb_flow_dissector_target(flow_dissector,
 						      FLOW_DISSECTOR_KEY_IPV6_ADDRS,
 						      target_container);
-		memcpy(&key_addrs->v6addrs, &flow_keys->ipv6_src,
-		       sizeof(key_addrs->v6addrs));
+		memcpy(&key_addrs->v6addrs.src, &flow_keys->ipv6_src,
+		       sizeof(key_addrs->v6addrs.src));
+		memcpy(&key_addrs->v6addrs.dst, &flow_keys->ipv6_dst,
+		       sizeof(key_addrs->v6addrs.dst));
 		key_control->addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
 	}
 
@@ -900,8 +890,8 @@ static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys,
 	}
 }
 
-bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx,
-		      __be16 proto, int nhoff, int hlen, unsigned int flags)
+u32 bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx,
+		     __be16 proto, int nhoff, int hlen, unsigned int flags)
 {
 	struct bpf_flow_keys *flow_keys = ctx->flow_keys;
 	u32 result;
@@ -920,15 +910,18 @@ bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx,
 		     (int)FLOW_DISSECTOR_F_STOP_AT_ENCAP);
 	flow_keys->flags = flags;
 
-	preempt_disable();
-	result = BPF_PROG_RUN(prog, ctx);
-	preempt_enable();
+	result = bpf_prog_run_pin_on_cpu(prog, ctx);
 
 	flow_keys->nhoff = clamp_t(u16, flow_keys->nhoff, nhoff, hlen);
 	flow_keys->thoff = clamp_t(u16, flow_keys->thoff,
 				   flow_keys->nhoff, hlen);
 
-	return result == BPF_OK;
+	return result;
+}
+
+static bool is_pppoe_ses_hdr_valid(const struct pppoe_hdr *hdr)
+{
+	return hdr->ver == 1 && hdr->type == 1 && hdr->code == 0;
 }
 
 /**
@@ -953,18 +946,18 @@ bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx,
 bool __skb_flow_dissect(const struct net *net,
 			const struct sk_buff *skb,
 			struct flow_dissector *flow_dissector,
-			void *target_container,
-			void *data, __be16 proto, int nhoff, int hlen,
-			unsigned int flags)
+			void *target_container, const void *data,
+			__be16 proto, int nhoff, int hlen, unsigned int flags)
 {
 	struct flow_dissector_key_control *key_control;
 	struct flow_dissector_key_basic *key_basic;
 	struct flow_dissector_key_addrs *key_addrs;
 	struct flow_dissector_key_tags *key_tags;
 	struct flow_dissector_key_vlan *key_vlan;
-	struct bpf_prog *attached = NULL;
 	enum flow_dissect_ret fdret;
 	enum flow_dissector_key_id dissector_vlan = FLOW_DISSECTOR_KEY_MAX;
+	bool mpls_el = false;
+	int mpls_lse = 0;
 	int num_hdrs = 0;
 	u8 ip_proto = 0;
 	bool ret;
@@ -982,8 +975,14 @@ bool __skb_flow_dissect(const struct net *net,
 			int offset = 0;
 
 			ops = skb->dev->dsa_ptr->tag_ops;
-			if (ops->flow_dissect &&
-			    !ops->flow_dissect(skb, &proto, &offset)) {
+			/* Only DSA header taggers break flow dissection */
+			if (ops->needed_headroom) {
+				if (ops->flow_dissect)
+					ops->flow_dissect(skb, &proto, &offset);
+				else
+					dsa_tag_generic_flow_dissect(skb,
+								     &proto,
+								     &offset);
 				hlen -= offset;
 				nhoff += offset;
 			}
@@ -1016,13 +1015,15 @@ bool __skb_flow_dissect(const struct net *net,
 
 	WARN_ON_ONCE(!net);
 	if (net) {
-		rcu_read_lock();
-		attached = rcu_dereference(init_net.flow_dissector_prog);
+		enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR;
+		struct bpf_prog_array *run_array;
 
-		if (!attached)
-			attached = rcu_dereference(net->flow_dissector_prog);
+		rcu_read_lock();
+		run_array = rcu_dereference(init_net.bpf.run_array[type]);
+		if (!run_array)
+			run_array = rcu_dereference(net->bpf.run_array[type]);
 
-		if (attached) {
+		if (run_array) {
 			struct bpf_flow_keys flow_keys;
 			struct bpf_flow_dissector ctx = {
 				.flow_keys = &flow_keys,
@@ -1030,6 +1031,8 @@ bool __skb_flow_dissect(const struct net *net,
 				.data_end = data + hlen,
 			};
 			__be16 n_proto = proto;
+			struct bpf_prog *prog;
+			u32 result;
 
 			if (skb) {
 				ctx.skb = skb;
@@ -1040,13 +1043,17 @@ bool __skb_flow_dissect(const struct net *net,
 				n_proto = skb->protocol;
 			}
 
-			ret = bpf_flow_dissect(attached, &ctx, n_proto, nhoff,
-					       hlen, flags);
+			prog = READ_ONCE(run_array->items[0].prog);
+			result = bpf_flow_dissect(prog, &ctx, n_proto, nhoff,
+						  hlen, flags);
+			if (result == BPF_FLOW_DISSECTOR_CONTINUE)
+				goto dissect_continue;
 			__skb_flow_bpf_to_target(&flow_keys, flow_dissector,
 						 target_container);
 			rcu_read_unlock();
-			return ret;
+			return result == BPF_OK;
 		}
+dissect_continue:
 		rcu_read_unlock();
 	}
 
@@ -1058,7 +1065,17 @@ bool __skb_flow_dissect(const struct net *net,
 		key_eth_addrs = skb_flow_dissector_target(flow_dissector,
 							  FLOW_DISSECTOR_KEY_ETH_ADDRS,
 							  target_container);
-		memcpy(key_eth_addrs, &eth->h_dest, sizeof(*key_eth_addrs));
+		memcpy(key_eth_addrs, eth, sizeof(*key_eth_addrs));
+	}
+
+	if (dissector_uses_key(flow_dissector,
+			       FLOW_DISSECTOR_KEY_NUM_OF_VLANS)) {
+		struct flow_dissector_key_num_of_vlans *key_num_of_vlans;
+
+		key_num_of_vlans = skb_flow_dissector_target(flow_dissector,
+							     FLOW_DISSECTOR_KEY_NUM_OF_VLANS,
+							     target_container);
+		key_num_of_vlans->num_of_vlans = 0;
 	}
 
 proto_again:
@@ -1085,11 +1102,16 @@ proto_again:
 							      FLOW_DISSECTOR_KEY_IPV4_ADDRS,
 							      target_container);
 
-			memcpy(&key_addrs->v4addrs, &iph->saddr,
-			       sizeof(key_addrs->v4addrs));
+			memcpy(&key_addrs->v4addrs.src, &iph->saddr,
+			       sizeof(key_addrs->v4addrs.src));
+			memcpy(&key_addrs->v4addrs.dst, &iph->daddr,
+			       sizeof(key_addrs->v4addrs.dst));
 			key_control->addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
 		}
 
+		__skb_flow_dissect_ipv4(skb, flow_dissector,
+					target_container, data, iph);
+
 		if (ip_is_fragment(iph)) {
 			key_control->flags |= FLOW_DIS_IS_FRAGMENT;
 
@@ -1106,9 +1128,6 @@ proto_again:
 			}
 		}
 
-		__skb_flow_dissect_ipv4(skb, flow_dissector,
-					target_container, data, iph);
-
 		break;
 	}
 	case htons(ETH_P_IPV6): {
@@ -1130,8 +1149,10 @@ proto_again:
 							      FLOW_DISSECTOR_KEY_IPV6_ADDRS,
 							      target_container);
 
-			memcpy(&key_addrs->v6addrs, &iph->saddr,
-			       sizeof(key_addrs->v6addrs));
+			memcpy(&key_addrs->v6addrs.src, &iph->saddr,
+			       sizeof(key_addrs->v6addrs.src));
+			memcpy(&key_addrs->v6addrs.dst, &iph->daddr,
+			       sizeof(key_addrs->v6addrs.dst));
 			key_control->addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
 		}
 
@@ -1180,6 +1201,16 @@ proto_again:
 			nhoff += sizeof(*vlan);
 		}
 
+		if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_NUM_OF_VLANS) &&
+		    !(key_control->flags & FLOW_DIS_ENCAPSULATION)) {
+			struct flow_dissector_key_num_of_vlans *key_nvs;
+
+			key_nvs = skb_flow_dissector_target(flow_dissector,
+							    FLOW_DISSECTOR_KEY_NUM_OF_VLANS,
+							    target_container);
+			key_nvs->num_of_vlans++;
+		}
+
 		if (dissector_vlan == FLOW_DISSECTOR_KEY_MAX) {
 			dissector_vlan = FLOW_DISSECTOR_KEY_VLAN;
 		} else if (dissector_vlan == FLOW_DISSECTOR_KEY_VLAN) {
@@ -1205,6 +1236,7 @@ proto_again:
 					 VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
 			}
 			key_vlan->vlan_tpid = saved_vlan_tpid;
+			key_vlan->vlan_eth_type = proto;
 		}
 
 		fdret = FLOW_DISSECT_RET_PROTO_AGAIN;
@@ -1215,27 +1247,60 @@ proto_again:
 			struct pppoe_hdr hdr;
 			__be16 proto;
 		} *hdr, _hdr;
+		u16 ppp_proto;
+
 		hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr);
 		if (!hdr) {
 			fdret = FLOW_DISSECT_RET_OUT_BAD;
 			break;
 		}
 
-		proto = hdr->proto;
-		nhoff += PPPOE_SES_HLEN;
-		switch (proto) {
-		case htons(PPP_IP):
+		if (!is_pppoe_ses_hdr_valid(&hdr->hdr)) {
+			fdret = FLOW_DISSECT_RET_OUT_BAD;
+			break;
+		}
+
+		/* least significant bit of the most significant octet
+		 * indicates if protocol field was compressed
+		 */
+		ppp_proto = ntohs(hdr->proto);
+		if (ppp_proto & 0x0100) {
+			ppp_proto = ppp_proto >> 8;
+			nhoff += PPPOE_SES_HLEN - 1;
+		} else {
+			nhoff += PPPOE_SES_HLEN;
+		}
+
+		if (ppp_proto == PPP_IP) {
 			proto = htons(ETH_P_IP);
 			fdret = FLOW_DISSECT_RET_PROTO_AGAIN;
-			break;
-		case htons(PPP_IPV6):
+		} else if (ppp_proto == PPP_IPV6) {
 			proto = htons(ETH_P_IPV6);
 			fdret = FLOW_DISSECT_RET_PROTO_AGAIN;
-			break;
-		default:
+		} else if (ppp_proto == PPP_MPLS_UC) {
+			proto = htons(ETH_P_MPLS_UC);
+			fdret = FLOW_DISSECT_RET_PROTO_AGAIN;
+		} else if (ppp_proto == PPP_MPLS_MC) {
+			proto = htons(ETH_P_MPLS_MC);
+			fdret = FLOW_DISSECT_RET_PROTO_AGAIN;
+		} else if (ppp_proto_is_valid(ppp_proto)) {
+			fdret = FLOW_DISSECT_RET_OUT_GOOD;
+		} else {
 			fdret = FLOW_DISSECT_RET_OUT_BAD;
 			break;
 		}
+
+		if (dissector_uses_key(flow_dissector,
+				       FLOW_DISSECTOR_KEY_PPPOE)) {
+			struct flow_dissector_key_pppoe *key_pppoe;
+
+			key_pppoe = skb_flow_dissector_target(flow_dissector,
+							      FLOW_DISSECTOR_KEY_PPPOE,
+							      target_container);
+			key_pppoe->session_id = hdr->hdr.sid;
+			key_pppoe->ppp_proto = htons(ppp_proto);
+			key_pppoe->type = htons(ETH_P_PPP_SES);
+		}
 		break;
 	}
 	case htons(ETH_P_TIPC): {
@@ -1264,7 +1329,10 @@ proto_again:
 	case htons(ETH_P_MPLS_MC):
 		fdret = __skb_flow_dissect_mpls(skb, flow_dissector,
 						target_container, data,
-						nhoff, hlen);
+						nhoff, hlen, mpls_lse,
+						&mpls_el);
+		nhoff += sizeof(struct mpls_label);
+		mpls_lse++;
 		break;
 	case htons(ETH_P_FCOE):
 		if ((hlen - nhoff) < FCOE_HEADER_LEN) {
@@ -1288,6 +1356,38 @@ proto_again:
 						  &proto, &nhoff, hlen, flags);
 		break;
 
+	case htons(ETH_P_1588): {
+		struct ptp_header *hdr, _hdr;
+
+		hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data,
+					   hlen, &_hdr);
+		if (!hdr) {
+			fdret = FLOW_DISSECT_RET_OUT_BAD;
+			break;
+		}
+
+		nhoff += ntohs(hdr->message_length);
+		fdret = FLOW_DISSECT_RET_OUT_GOOD;
+		break;
+	}
+
+	case htons(ETH_P_PRP):
+	case htons(ETH_P_HSR): {
+		struct hsr_tag *hdr, _hdr;
+
+		hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen,
+					   &_hdr);
+		if (!hdr) {
+			fdret = FLOW_DISSECT_RET_OUT_BAD;
+			break;
+		}
+
+		proto = hdr->encap_proto;
+		nhoff += HSR_HLEN;
+		fdret = FLOW_DISSECT_RET_PROTO_AGAIN;
+		break;
+	}
+
 	default:
 		fdret = FLOW_DISSECT_RET_OUT_BAD;
 		break;
@@ -1314,6 +1414,11 @@ ip_proto_again:
 
 	switch (ip_proto) {
 	case IPPROTO_GRE:
+		if (flags & FLOW_DISSECTOR_F_STOP_BEFORE_ENCAP) {
+			fdret = FLOW_DISSECT_RET_OUT_GOOD;
+			break;
+		}
+
 		fdret = __skb_flow_dissect_gre(skb, key_control, flow_dissector,
 					       target_container, data,
 					       &proto, &nhoff, &hlen, flags);
@@ -1371,6 +1476,11 @@ ip_proto_again:
 		break;
 	}
 	case IPPROTO_IPIP:
+		if (flags & FLOW_DISSECTOR_F_STOP_BEFORE_ENCAP) {
+			fdret = FLOW_DISSECT_RET_OUT_GOOD;
+			break;
+		}
+
 		proto = htons(ETH_P_IP);
 
 		key_control->flags |= FLOW_DIS_ENCAPSULATION;
@@ -1383,6 +1493,11 @@ ip_proto_again:
 		break;
 
 	case IPPROTO_IPV6:
+		if (flags & FLOW_DISSECTOR_F_STOP_BEFORE_ENCAP) {
+			fdret = FLOW_DISSECT_RET_OUT_GOOD;
+			break;
+		}
+
 		proto = htons(ETH_P_IPV6);
 
 		key_control->flags |= FLOW_DIS_ENCAPSULATION;
@@ -1410,6 +1525,10 @@ ip_proto_again:
 		__skb_flow_dissect_icmp(skb, flow_dissector, target_container,
 					data, nhoff, hlen);
 		break;
+	case IPPROTO_L2TP:
+		__skb_flow_dissect_l2tpv3(skb, flow_dissector, target_container,
+					  data, nhoff, hlen);
+		break;
 
 	default:
 		break;
@@ -1453,7 +1572,7 @@ out_bad:
 }
 EXPORT_SYMBOL(__skb_flow_dissect);
 
-static siphash_key_t hashrnd __read_mostly;
+static siphash_aligned_key_t hashrnd;
 static __always_inline void __flow_hash_secret_init(void)
 {
 	net_get_random_once(&hashrnd, sizeof(hashrnd));
@@ -1515,7 +1634,7 @@ __be32 flow_get_u32_dst(const struct flow_keys *flow)
 }
 EXPORT_SYMBOL(flow_get_u32_dst);
 
-/* Sort the source and destination IP (and the ports if the IP are the same),
+/* Sort the source and destination IP and the ports,
  * to have consistent hash within the two directions
  */
 static inline void __flow_hash_consistentify(struct flow_keys *keys)
@@ -1524,13 +1643,12 @@ static inline void __flow_hash_consistentify(struct flow_keys *keys)
 
 	switch (keys->control.addr_type) {
 	case FLOW_DISSECTOR_KEY_IPV4_ADDRS:
-		addr_diff = (__force u32)keys->addrs.v4addrs.dst -
-			    (__force u32)keys->addrs.v4addrs.src;
-		if ((addr_diff < 0) ||
-		    (addr_diff == 0 &&
-		     ((__force u16)keys->ports.dst <
-		      (__force u16)keys->ports.src))) {
+		if ((__force u32)keys->addrs.v4addrs.dst <
+		    (__force u32)keys->addrs.v4addrs.src)
 			swap(keys->addrs.v4addrs.src, keys->addrs.v4addrs.dst);
+
+		if ((__force u16)keys->ports.dst <
+		    (__force u16)keys->ports.src) {
 			swap(keys->ports.src, keys->ports.dst);
 		}
 		break;
@@ -1538,13 +1656,13 @@ static inline void __flow_hash_consistentify(struct flow_keys *keys)
 		addr_diff = memcmp(&keys->addrs.v6addrs.dst,
 				   &keys->addrs.v6addrs.src,
 				   sizeof(keys->addrs.v6addrs.dst));
-		if ((addr_diff < 0) ||
-		    (addr_diff == 0 &&
-		     ((__force u16)keys->ports.dst <
-		      (__force u16)keys->ports.src))) {
+		if (addr_diff < 0) {
 			for (i = 0; i < 4; i++)
 				swap(keys->addrs.v6addrs.src.s6_addr32[i],
 				     keys->addrs.v6addrs.dst.s6_addr32[i]);
+		}
+		if ((__force u16)keys->ports.dst <
+		    (__force u16)keys->ports.src) {
 			swap(keys->ports.src, keys->ports.dst);
 		}
 		break;
@@ -1658,7 +1776,7 @@ __u32 skb_get_hash_perturb(const struct sk_buff *skb,
 }
 EXPORT_SYMBOL(skb_get_hash_perturb);
 
-u32 __skb_get_poff(const struct sk_buff *skb, void *data,
+u32 __skb_get_poff(const struct sk_buff *skb, const void *data,
 		   const struct flow_keys_basic *keys, int hlen)
 {
 	u32 poff = keys->control.thoff;
@@ -1840,5 +1958,4 @@ static int __init init_default_flow_dissectors(void)
 				ARRAY_SIZE(flow_keys_basic_dissector_keys));
 	return 0;
 }
-
 core_initcall(init_default_flow_dissectors);