[PATCH v4 net-next 0/8] flow_dissector: Protocol specific flow dissector offload

@@ -7344,7 +7344,7 @@ static bool bnxt_fltr_match(struct bnxt_ntuple_filter *f1,
 	return false;
 }
 
-static int bnxt_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
+static int bnxt_rx_flow_steer(struct net_device *dev, struct sk_buff *skb,
 			      u16 rxq_index, u32 flow_id)
 {
 	struct bnxt *bp = netdev_priv(dev);

@@ -167,7 +167,7 @@ static struct enic_rfs_fltr_node *htbl_key_search(struct hlist_head *h,
 	return NULL;
 }
 
-int enic_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
+int enic_rx_flow_steer(struct net_device *dev, struct sk_buff *skb,
 		       u16 rxq_index, u32 flow_id)
 {
 	struct flow_keys keys;

@@ -13,7 +13,7 @@ void enic_rfs_flw_tbl_free(struct enic *enic);
 struct enic_rfs_fltr_node *htbl_fltr_search(struct enic *enic, u16 fltr_id);
 
 #ifdef CONFIG_RFS_ACCEL
-int enic_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
+int enic_rx_flow_steer(struct net_device *dev, struct sk_buff *skb,
 		       u16 rxq_index, u32 flow_id);
 void enic_flow_may_expire(unsigned long data);
 

@@ -348,7 +348,7 @@ mlx4_en_filter_find(struct mlx4_en_priv *priv, __be32 src_ip, __be32 dst_ip,
 }
 
 static int
-mlx4_en_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb,
+mlx4_en_filter_rfs(struct net_device *net_dev, struct sk_buff *skb,
 		   u16 rxq_index, u32 flow_id)
 {
 	struct mlx4_en_priv *priv = netdev_priv(net_dev);

@@ -1017,7 +1017,7 @@ int mlx5e_arfs_create_tables(struct mlx5e_priv *priv);
 void mlx5e_arfs_destroy_tables(struct mlx5e_priv *priv);
 int mlx5e_arfs_enable(struct mlx5e_priv *priv);
 int mlx5e_arfs_disable(struct mlx5e_priv *priv);
-int mlx5e_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
+int mlx5e_rx_flow_steer(struct net_device *dev, struct sk_buff *skb,
 			u16 rxq_index, u32 flow_id);
 #endif
 

@@ -699,7 +699,7 @@ static struct arfs_rule *arfs_find_rule(struct arfs_table *arfs_t,
 	return NULL;
 }
 
-int mlx5e_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
+int mlx5e_rx_flow_steer(struct net_device *dev, struct sk_buff *skb,
 			u16 rxq_index, u32 flow_id)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);

@@ -445,7 +445,7 @@ struct qede_fastpath {
 #define QEDE_SP_RX_MODE			1
 
 #ifdef CONFIG_RFS_ACCEL
-int qede_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
+int qede_rx_flow_steer(struct net_device *dev, struct sk_buff *skb,
 		       u16 rxq_index, u32 flow_id);
 #define QEDE_SP_ARFS_CONFIG	4
 #define QEDE_SP_TASK_POLL_DELAY	(5 * HZ)

@@ -411,7 +411,7 @@ qede_alloc_filter(struct qede_dev *edev, int min_hlen)
 	return n;
 }
 
-int qede_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
+int qede_rx_flow_steer(struct net_device *dev, struct sk_buff *skb,
 		       u16 rxq_index, u32 flow_id)
 {
 	struct qede_dev *edev = netdev_priv(dev);

@@ -171,7 +171,7 @@ static inline s32 efx_filter_get_rx_ids(struct efx_nic *efx,
 	return efx->type->filter_get_rx_ids(efx, priority, buf, size);
 }
 #ifdef CONFIG_RFS_ACCEL
-int efx_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb,
+int efx_filter_rfs(struct net_device *net_dev, struct sk_buff *skb,
 		   u16 rxq_index, u32 flow_id);
 bool __efx_filter_rfs_expire(struct efx_nic *efx, unsigned quota);
 static inline void efx_filter_rfs_expire(struct efx_channel *channel)

@@ -164,7 +164,7 @@ static inline s32 ef4_filter_get_rx_ids(struct ef4_nic *efx,
 	return efx->type->filter_get_rx_ids(efx, priority, buf, size);
 }
 #ifdef CONFIG_RFS_ACCEL
-int ef4_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb,
+int ef4_filter_rfs(struct net_device *net_dev, struct sk_buff *skb,
 		   u16 rxq_index, u32 flow_id);
 bool __ef4_filter_rfs_expire(struct ef4_nic *efx, unsigned quota);
 static inline void ef4_filter_rfs_expire(struct ef4_channel *channel)

@@ -833,7 +833,7 @@ MODULE_PARM_DESC(rx_refill_threshold,
 
 #ifdef CONFIG_RFS_ACCEL
 
-int ef4_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb,
+int ef4_filter_rfs(struct net_device *net_dev, struct sk_buff *skb,
 		   u16 rxq_index, u32 flow_id)
 {
 	struct ef4_nic *efx = netdev_priv(net_dev);

@@ -827,7 +827,7 @@ MODULE_PARM_DESC(rx_refill_threshold,
 
 #ifdef CONFIG_RFS_ACCEL
 
-int efx_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb,
+int efx_filter_rfs(struct net_device *net_dev, struct sk_buff *skb,
 		   u16 rxq_index, u32 flow_id)
 {
 	struct efx_nic *efx = netdev_priv(net_dev);

@@ -1010,7 +1010,7 @@ struct xfrmdev_ops {
  *	protocol stack to use.
  *
  *	RFS acceleration.
- * int (*ndo_rx_flow_steer)(struct net_device *dev, const struct sk_buff *skb,
+ * int (*ndo_rx_flow_steer)(struct net_device *dev, struct sk_buff *skb,
  *			    u16 rxq_index, u32 flow_id);
  *	Set hardware filter for RFS.  rxq_index is the target queue index;
  *	flow_id is a flow ID to be passed to rps_may_expire_flow() later.

@@ -1236,7 +1236,7 @@ struct net_device_ops {
 
 #ifdef CONFIG_RFS_ACCEL
 	int			(*ndo_rx_flow_steer)(struct net_device *dev,
-						     const struct sk_buff *skb,
+						     struct sk_buff *skb,
 						     u16 rxq_index,
 						     u32 flow_id);
 #endif

@@ -1155,8 +1155,8 @@ __skb_set_sw_hash(struct sk_buff *skb, __u32 hash, bool is_l4)
 }
 
 void __skb_get_hash(struct sk_buff *skb);
-u32 __skb_get_hash_symmetric(const struct sk_buff *skb);
-u32 skb_get_poff(const struct sk_buff *skb);
+u32 __skb_get_hash_symmetric(struct sk_buff *skb);
+u32 skb_get_poff(struct sk_buff *skb);
 u32 __skb_get_poff(const struct sk_buff *skb, void *data,
 		   const struct flow_keys *keys, int hlen);
 __be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto,

@@ -1172,13 +1172,13 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector,
 			     const struct flow_dissector_key *key,
 			     unsigned int key_count);
 
-bool __skb_flow_dissect(const struct sk_buff *skb,
+bool __skb_flow_dissect(struct sk_buff *skb,
 			struct flow_dissector *flow_dissector,
 			void *target_container,
 			void *data, __be16 proto, int nhoff, int hlen,
 			unsigned int flags);
 
-static inline bool skb_flow_dissect(const struct sk_buff *skb,
+static inline bool skb_flow_dissect(struct sk_buff *skb,
 				    struct flow_dissector *flow_dissector,
 				    void *target_container, unsigned int flags)
 {

@@ -1186,7 +1186,7 @@ static inline bool skb_flow_dissect(const struct sk_buff *skb,
 				  NULL, 0, 0, 0, flags);
 }
 
-static inline bool skb_flow_dissect_flow_keys(const struct sk_buff *skb,
+static inline bool skb_flow_dissect_flow_keys(struct sk_buff *skb,
 					      struct flow_keys *flow,
 					      unsigned int flags)
 {

@@ -1225,7 +1225,7 @@ static inline __u32 skb_get_hash_flowi6(struct sk_buff *skb, const struct flowi6
 	return skb->hash;
 }
 
-__u32 skb_get_hash_perturb(const struct sk_buff *skb, u32 perturb);
+__u32 skb_get_hash_perturb(struct sk_buff *skb, u32 perturb);
 
 static inline __u32 skb_get_hash_raw(const struct sk_buff *skb)
 {

@@ -374,11 +374,11 @@ int fib_sync_up(struct net_device *dev, unsigned int nh_flags);
 
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4,
-		       const struct sk_buff *skb);
+		       struct sk_buff *skb);
 #endif
 void fib_select_multipath(struct fib_result *res, int hash);
 void fib_select_path(struct net *net, struct fib_result *res,
-		     struct flowi4 *fl4, const struct sk_buff *skb);
+		     struct flowi4 *fl4, struct sk_buff *skb);
 
 /* Exported by fib_trie.c */
 void fib_trie_init(void);

@@ -114,10 +114,10 @@ int ip_rt_init(void);
 void rt_cache_flush(struct net *net);
 void rt_flush_dev(struct net_device *dev);
 struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *flp,
-					const struct sk_buff *skb);
+					struct sk_buff *skb);
 struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *flp,
 					    struct fib_result *res,
-					    const struct sk_buff *skb);
+					    struct sk_buff *skb);
 
 static inline struct rtable *__ip_route_output_key(struct net *net,
 						   struct flowi4 *flp)

@@ -424,7 +424,7 @@ static bool skb_flow_dissect_allowed(int *num_hdrs)
  *
  * Caller must take care of zeroing target container memory.
  */
-bool __skb_flow_dissect(const struct sk_buff *skb,
+bool __skb_flow_dissect(struct sk_buff *skb,
 			struct flow_dissector *flow_dissector,
 			void *target_container,
 			void *data, __be16 proto, int nhoff, int hlen,

@@ -1015,7 +1015,7 @@ u32 flow_hash_from_keys(struct flow_keys *keys)
 }
 EXPORT_SYMBOL(flow_hash_from_keys);
 
-static inline u32 ___skb_get_hash(const struct sk_buff *skb,
+static inline u32 ___skb_get_hash(struct sk_buff *skb,
 				  struct flow_keys *keys, u32 keyval)
 {
 	skb_flow_dissect_flow_keys(skb, keys,

@@ -1053,7 +1053,7 @@ EXPORT_SYMBOL(make_flow_keys_digest);
 
 static struct flow_dissector flow_keys_dissector_symmetric __read_mostly;
 
-u32 __skb_get_hash_symmetric(const struct sk_buff *skb)
+u32 __skb_get_hash_symmetric(struct sk_buff *skb)
 {
 	struct flow_keys keys;
 

@@ -1090,7 +1090,7 @@ void __skb_get_hash(struct sk_buff *skb)
 }
 EXPORT_SYMBOL(__skb_get_hash);
 
-__u32 skb_get_hash_perturb(const struct sk_buff *skb, u32 perturb)
+__u32 skb_get_hash_perturb(struct sk_buff *skb, u32 perturb)
 {
 	struct flow_keys keys;
 

@@ -1158,7 +1158,7 @@ u32 __skb_get_poff(const struct sk_buff *skb, void *data,
  * truncate packets without needing to push actual payload to the user
  * space and can analyze headers only, instead.
  */
-u32 skb_get_poff(const struct sk_buff *skb)
+u32 skb_get_poff(struct sk_buff *skb)
 {
 	struct flow_keys keys;
 

@@ -1759,7 +1759,7 @@ void fib_select_multipath(struct fib_result *res, int hash)
 #endif
 
 void fib_select_path(struct net *net, struct fib_result *res,
-		     struct flowi4 *fl4, const struct sk_buff *skb)
+		     struct flowi4 *fl4, struct sk_buff *skb)
 {
 	bool oif_check;
 

@@ -1791,7 +1791,7 @@ static void ip_multipath_l3_keys(const struct sk_buff *skb,
 
 /* if skb is set it will be used and fl4 can be NULL */
 int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4,
-		       const struct sk_buff *skb)
+		       struct sk_buff *skb)
 {
 	struct net *net = fi->fib_net;
 	struct flow_keys hash_keys;

@@ -2270,7 +2270,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
  */
 
 struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *fl4,
-					const struct sk_buff *skb)
+					struct sk_buff *skb)
 {
 	__u8 tos = RT_FL_TOS(fl4);
 	struct fib_result res;

@@ -2295,7 +2295,7 @@ EXPORT_SYMBOL_GPL(ip_route_output_key_hash);
 
 struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4,
 					    struct fib_result *res,
-					    const struct sk_buff *skb)
+					    struct sk_buff *skb)
 {
 	struct net_device *dev_out = NULL;
 	int orig_oif = fl4->flowi4_oif;

@@ -158,7 +158,7 @@ static inline struct sfq_head *sfq_dep_head(struct sfq_sched_data *q, sfq_index
 }
 
 static unsigned int sfq_hash(const struct sfq_sched_data *q,
-			     const struct sk_buff *skb)
+			     struct sk_buff *skb)
 {
 	return skb_get_hash_perturb(skb, q->perturbation) & (q->divisor - 1);
 }

@@ -282,27 +282,8 @@ __skb_flow_dissect_gre(const struct sk_buff *skb,
 	if (hdr->flags & GRE_SEQ)
 		offset += sizeof(((struct pptp_gre_header *) 0)->seq);
 
-	if (gre_ver == 0) {
-		if (*p_proto == htons(ETH_P_TEB)) {
-			const struct ethhdr *eth;
-			struct ethhdr _eth;
-
-			eth = __skb_header_pointer(skb, *p_nhoff + offset,
-						   sizeof(_eth),
-						   data, *p_hlen, &_eth);
-			if (!eth)
-				return FLOW_DISSECT_RET_OUT_BAD;
-			*p_proto = eth->h_proto;
-			offset += sizeof(*eth);
-
-			/* Cap headers that we access via pointers at the
-			 * end of the Ethernet header as our maximum alignment
-			 * at that point is only 2 bytes.
-			 */
-			if (NET_IP_ALIGN)
-				*p_hlen = *p_nhoff + offset;
-		}
-	} else { /* version 1, must be PPTP */
+	/* version 1, must be PPTP */
+	if (gre_ver == 1) {
 		u8 _ppp_hdr[PPP_HDRLEN];
 		u8 *ppp_hdr;
 

@@ -595,6 +576,28 @@ bool __skb_flow_dissect(struct sk_buff *skb,
 
 		break;
 	}
+	case htons(ETH_P_TEB): {
+		const struct ethhdr *eth;
+		struct ethhdr _eth;
+
+		eth = __skb_header_pointer(skb, nhoff, sizeof(_eth),
+					   data, hlen, &_eth);
+		if (!eth)
+			goto out_bad;
+
+		proto = eth->h_proto;
+		nhoff += sizeof(*eth);
+
+		/* Cap headers that we access via pointers at the
+		 * end of the Ethernet header as our maximum alignment
+		 * at that point is only 2 bytes.
+		 */
+		if (NET_IP_ALIGN)
+			hlen = nhoff;
+
+		fdret = FLOW_DISSECT_RET_PROTO_AGAIN;
+		break;
+	}
 	case htons(ETH_P_8021AD):
 	case htons(ETH_P_8021Q): {
 		const struct vlan_hdr *vlan;

@@ -97,6 +97,8 @@ static inline struct udp_hslot *udp_hashslot2(struct udp_table *table,
 
 extern struct proto udp_prot;
 
+extern struct static_key udp_encap_needed;
+
 extern atomic_long_t udp_memory_allocated;
 
 /* sysctl variables for udp */

@@ -1813,7 +1813,9 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	return 0;
 }
 
-static struct static_key udp_encap_needed __read_mostly;
+struct static_key udp_encap_needed __read_mostly;
+EXPORT_SYMBOL(udp_encap_needed);
+
 void udp_encap_enable(void)
 {
 	static_key_enable(&udp_encap_needed);

@@ -261,6 +261,13 @@ static struct sk_buff **udp4_gro_receive(struct sk_buff **head,
 {
 	struct udphdr *uh = udp_gro_udphdr(skb);
 
+	if (!static_key_false(&udp_encap_needed)) {
+		/* Currently udp_gro_receive only does something if
+		 * a UDP encapsulation has been set.
+		 */
+		goto flush;
+	}
+
 	if (unlikely(!uh))
 		goto flush;
 

@@ -34,6 +34,13 @@ static struct sk_buff **udp6_gro_receive(struct sk_buff **head,
 {
 	struct udphdr *uh = udp_gro_udphdr(skb);
 
+	if (!static_key_false(&udp_encap_needed)) {
+		/* Currently udp_gro_receive only does something if
+		 * a UDP encapsulation has been set.
+		 */
+		goto flush;
+	}
+
 	if (unlikely(!uh))
 		goto flush;
 

@@ -2207,12 +2207,25 @@ struct offload_callbacks {
 	struct sk_buff		**(*gro_receive)(struct sk_buff **head,
 						 struct sk_buff *skb);
 	int			(*gro_complete)(struct sk_buff *skb, int nhoff);
+	enum flow_dissect_ret (*flow_dissect)(struct sk_buff *skb,
+			struct flow_dissector_key_control *key_control,
+			struct flow_dissector *flow_dissector,
+			void *target_container, void *data,
+			__be16 *p_proto, u8 *p_ip_proto, int *p_nhoff,
+			int *p_hlen, unsigned int flags);
 };
 
 struct packet_offload {
 	__be16			 type;	/* This is really htons(ether_type). */
 	u16			 priority;
 	struct offload_callbacks callbacks;
+	enum flow_dissect_ret (*proto_flow_dissect)(struct sk_buff *skb,
+			u8 proto,
+			struct flow_dissector_key_control *key_control,
+			struct flow_dissector *flow_dissector,
+			void *target_container, void *data,
+			__be16 *p_proto, u8 *p_ip_proto, int *p_nhoff,
+			int *p_hlen, unsigned int flags);
 	struct list_head	 list;
 };
 

@@ -3252,6 +3265,20 @@ struct sk_buff *napi_get_frags(struct napi_struct *napi);
 gro_result_t napi_gro_frags(struct napi_struct *napi);
 struct packet_offload *gro_find_receive_by_type(__be16 type);
 struct packet_offload *gro_find_complete_by_type(__be16 type);
+enum flow_dissect_ret flow_dissect_by_type(struct sk_buff *skb,
+			__be16 type,
+			struct flow_dissector_key_control *key_control,
+			struct flow_dissector *flow_dissector,
+			void *target_container, void *data,
+			__be16 *p_proto, u8 *p_ip_proto, int *p_nhoff,
+			int *p_hlen, unsigned int flags);
+enum flow_dissect_ret flow_dissect_by_type_proto(struct sk_buff *skb,
+			__be16 type, u8 proto,
+			struct flow_dissector_key_control *key_control,
+			struct flow_dissector *flow_dissector,
+			void *target_container, void *data,
+			__be16 *p_proto, u8 *p_ip_proto, int *p_nhoff,
+			int *p_hlen, unsigned int flags);
 
 static inline void napi_free_frags(struct napi_struct *napi)
 {

@@ -213,6 +213,7 @@ enum flow_dissector_key_id {
 #define FLOW_DISSECTOR_F_STOP_AT_L3		BIT(1)
 #define FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL	BIT(2)
 #define FLOW_DISSECTOR_F_STOP_AT_ENCAP		BIT(3)
+#define FLOW_DISSECTOR_F_STOP_AT_L4		BIT(4)
 
 struct flow_dissector_key {
 	enum flow_dissector_key_id key_id;

@@ -104,6 +104,7 @@
 #include <linux/stat.h>
 #include <net/dst.h>
 #include <net/dst_metadata.h>
+#include <net/flow_dissector.h>
 #include <net/pkt_sched.h>
 #include <net/pkt_cls.h>
 #include <net/checksum.h>

@@ -4907,6 +4908,70 @@ struct packet_offload *gro_find_complete_by_type(__be16 type)
 }
 EXPORT_SYMBOL(gro_find_complete_by_type);
 
+enum flow_dissect_ret flow_dissect_by_type(struct sk_buff *skb,
+			__be16 type,
+			struct flow_dissector_key_control *key_control,
+			struct flow_dissector *flow_dissector,
+			void *target_container, void *data,
+			__be16 *p_proto, u8 *p_ip_proto, int *p_nhoff,
+			int *p_hlen, unsigned int flags)
+{
+	enum flow_dissect_ret ret = FLOW_DISSECT_RET_CONTINUE;
+	struct list_head *offload_head = &offload_base;
+	struct packet_offload *ptype;
+
+	rcu_read_lock();
+
+	list_for_each_entry_rcu(ptype, offload_head, list) {
+		if (ptype->type != type || !ptype->callbacks.flow_dissect)
+			continue;
+		ret = ptype->callbacks.flow_dissect(skb, key_control,
+						    flow_dissector,
+						    target_container,
+						    data, p_proto,
+						    p_ip_proto, p_nhoff,
+						    p_hlen, flags);
+		break;
+	}
+
+	rcu_read_unlock();
+
+	return ret;
+}
+EXPORT_SYMBOL(flow_dissect_by_type);
+
+enum flow_dissect_ret flow_dissect_by_type_proto(struct sk_buff *skb,
+			__be16 type, u8 proto,
+			struct flow_dissector_key_control *key_control,
+			struct flow_dissector *flow_dissector,
+			void *target_container, void *data,
+			__be16 *p_proto, u8 *p_ip_proto, int *p_nhoff,
+			int *p_hlen, unsigned int flags)
+{
+	enum flow_dissect_ret ret = FLOW_DISSECT_RET_CONTINUE;
+	struct list_head *offload_head = &offload_base;
+	struct packet_offload *ptype;
+
+	rcu_read_lock();
+
+	list_for_each_entry_rcu(ptype, offload_head, list) {
+		if (ptype->type != type || !ptype->proto_flow_dissect)
+			continue;
+		ret = ptype->proto_flow_dissect(skb, proto, key_control,
+						    flow_dissector,
+						    target_container,
+						    data, p_proto,
+						    p_ip_proto, p_nhoff,
+						    p_hlen, flags);
+		break;
+	}
+
+	rcu_read_unlock();
+
+	return ret;
+}
+EXPORT_SYMBOL(flow_dissect_by_type_proto);
+
 static void napi_skb_free_stolen_head(struct sk_buff *skb)
 {
 	skb_dst_drop(skb);

@@ -9,6 +9,7 @@
 #include <net/ipv6.h>
 #include <net/gre.h>
 #include <net/pptp.h>
+#include <net/protocol.h>
 #include <linux/igmp.h>
 #include <linux/icmp.h>
 #include <linux/sctp.h>

@@ -721,7 +722,11 @@ bool __skb_flow_dissect(struct sk_buff *skb,
 		break;
 
 	default:
-		fdret = FLOW_DISSECT_RET_OUT_BAD;
+		fdret = flow_dissect_by_type(skb, proto, key_control,
+					     flow_dissector,
+					     target_container,
+					     data, &proto, &ip_proto, &nhoff,
+					     &hlen, flags);
 		break;
 	}
 

@@ -838,6 +843,12 @@ bool __skb_flow_dissect(struct sk_buff *skb,
 		break;
 
 	default:
+		fdret = flow_dissect_by_type_proto(skb, proto,
+						ip_proto, key_control,
+						flow_dissector,
+						target_container,
+						data, &proto, &ip_proto, &nhoff,
+						&hlen, flags);
 		break;
 	}
 

@@ -1022,7 +1033,8 @@ static inline u32 ___skb_get_hash(struct sk_buff *skb,
 				  struct flow_keys *keys, u32 keyval)
 {
 	skb_flow_dissect_flow_keys(skb, keys,
-				   FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL);
+				   FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL |
+				   FLOW_DISSECTOR_F_STOP_AT_L4);
 
 	return __flow_hash_from_keys(keys, keyval);
 }

@@ -1811,7 +1811,9 @@ int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4,
 	case 1:
 		/* skb is currently provided only when forwarding */
 		if (skb) {
-			unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP;
+			unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP |
+					    FLOW_DISSECTOR_F_STOP_AT_L4;
+;
 			struct flow_keys keys;
 
 			/* short-circuit if we already have L4 hash present */

@@ -1440,6 +1440,32 @@ static struct sk_buff **ipip_gro_receive(struct sk_buff **head,
 	return inet_gro_receive(head, skb);
 }
 
+static enum flow_dissect_ret inet_proto_flow_dissect(struct sk_buff *skb,
+			u8 proto,
+			struct flow_dissector_key_control *key_control,
+			struct flow_dissector *flow_dissector,
+			void *target_container, void *data,
+			__be16 *p_proto, u8 *p_ip_proto, int *p_nhoff,
+			int *p_hlen, unsigned int flags)
+{
+	enum flow_dissect_ret ret = FLOW_DISSECT_RET_CONTINUE;
+	const struct net_offload *ops;
+
+	rcu_read_lock();
+
+	ops = rcu_dereference(inet_offloads[proto]);
+	if (ops && ops->callbacks.flow_dissect)
+		ret =  ops->callbacks.flow_dissect(skb, key_control,
+						   flow_dissector,
+						   target_container,
+						   data, p_proto, p_ip_proto,
+						   p_nhoff, p_hlen, flags);
+
+	rcu_read_unlock();
+
+	return ret;
+}
+
 #define SECONDS_PER_DAY	86400
 
 /* inet_current_timestamp - Return IP network timestamp

@@ -1763,6 +1789,7 @@ static int ipv4_proc_init(void);
 
 static struct packet_offload ip_packet_offload __read_mostly = {
 	.type = cpu_to_be16(ETH_P_IP),
+	.proto_flow_dissect = inet_proto_flow_dissect,
 	.callbacks = {
 		.gso_segment = inet_gso_segment,
 		.gro_receive = inet_gro_receive,

@@ -339,8 +339,35 @@ static int ip4ip6_gro_complete(struct sk_buff *skb, int nhoff)
 	return inet_gro_complete(skb, nhoff);
 }
 
+static enum flow_dissect_ret inet6_proto_flow_dissect(struct sk_buff *skb,
+			u8 proto,
+			struct flow_dissector_key_control *key_control,
+			struct flow_dissector *flow_dissector,
+			void *target_container, void *data,
+			__be16 *p_proto, u8 *p_ip_proto, int *p_nhoff,
+			int *p_hlen, unsigned int flags)
+{
+	enum flow_dissect_ret ret = FLOW_DISSECT_RET_CONTINUE;
+	const struct net_offload *ops;
+
+	rcu_read_lock();
+
+	ops = rcu_dereference(inet6_offloads[proto]);
+	if (ops && ops->callbacks.flow_dissect)
+		ret =  ops->callbacks.flow_dissect(skb, key_control,
+						   flow_dissector,
+						   target_container, data,
+						   p_proto, p_ip_proto, p_nhoff,
+						   p_hlen, flags);
+
+	rcu_read_unlock();
+
+	return ret;
+}
+
 static struct packet_offload ipv6_packet_offload __read_mostly = {
 	.type = cpu_to_be16(ETH_P_IPV6),
+	.proto_flow_dissect = inet6_proto_flow_dissect,
 	.callbacks = {
 		.gso_segment = ipv6_gso_segment,
 		.gro_receive = ipv6_gro_receive,

@@ -79,6 +79,14 @@ struct udp_sock {
 	int			(*gro_complete)(struct sock *sk,
 						struct sk_buff *skb,
 						int nhoff);
+	/* Flow dissector function for a UDP socket */
+	enum flow_dissect_ret (*flow_dissect)(struct sock *sk,
+			const struct sk_buff *skb,
+			struct flow_dissector_key_control *key_control,
+			struct flow_dissector *flow_dissector,
+			void *target_container, void *data,
+			__be16 *p_proto, u8 *p_ip_proto, int *p_nhoff,
+			int *p_hlen, unsigned int flags);
 
 	/* udp_recvmsg try to use this before splicing sk_receive_queue */
 	struct sk_buff_head	reader_queue ____cacheline_aligned_in_smp;

@@ -176,6 +176,14 @@ struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb,
 				 struct udphdr *uh, udp_lookup_t lookup);
 int udp_gro_complete(struct sk_buff *skb, int nhoff, udp_lookup_t lookup);
 
+enum flow_dissect_ret udp_flow_dissect(struct sk_buff *skb,
+			udp_lookup_t lookup,
+			struct flow_dissector_key_control *key_control,
+			struct flow_dissector *flow_dissector,
+			void *target_container, void *data,
+			__be16 *p_proto, u8 *p_ip_proto, int *p_nhoff,
+			int *p_hlen, unsigned int flags);
+
 static inline struct udphdr *udp_gro_udphdr(struct sk_buff *skb)
 {
 	struct udphdr *uh;

@@ -69,6 +69,13 @@ typedef struct sk_buff **(*udp_tunnel_gro_receive_t)(struct sock *sk,
 						     struct sk_buff *skb);
 typedef int (*udp_tunnel_gro_complete_t)(struct sock *sk, struct sk_buff *skb,
 					 int nhoff);
+typedef enum flow_dissect_ret (*udp_tunnel_flow_dissect_t)(struct sock *sk,
+			const struct sk_buff *skb,
+			struct flow_dissector_key_control *key_control,
+			struct flow_dissector *flow_dissector,
+			void *target_container, void *data,
+			__be16 *p_proto, u8 *p_ip_proto, int *p_nhoff,
+			int *p_hlen, unsigned int flags);
 
 struct udp_tunnel_sock_cfg {
 	void *sk_user_data;     /* user data used by encap_rcv call back */

@@ -78,6 +85,7 @@ struct udp_tunnel_sock_cfg {
 	udp_tunnel_encap_destroy_t encap_destroy;
 	udp_tunnel_gro_receive_t gro_receive;
 	udp_tunnel_gro_complete_t gro_complete;
+	udp_tunnel_flow_dissect_t flow_dissect;
 };
 
 /* Setup the given (UDP) sock to receive UDP encapsulated packets */

@@ -335,11 +335,59 @@ static int udp4_gro_complete(struct sk_buff *skb, int nhoff)
 	return udp_gro_complete(skb, nhoff, udp4_lib_lookup_skb);
 }
 
+enum flow_dissect_ret udp_flow_dissect(struct sk_buff *skb,
+			udp_lookup_t lookup,
+			struct flow_dissector_key_control *key_control,
+			struct flow_dissector *flow_dissector,
+			void *target_container, void *data,
+			__be16 *p_proto, u8 *p_ip_proto, int *p_nhoff,
+			int *p_hlen, unsigned int flags)
+{
+	enum flow_dissect_ret ret = FLOW_DISSECT_RET_CONTINUE;
+	struct udphdr *uh, _uh;
+	struct sock *sk;
+
+	uh = __skb_header_pointer(skb, *p_nhoff, sizeof(_uh), data,
+				  *p_hlen, &_uh);
+	if (!uh)
+		return FLOW_DISSECT_RET_OUT_BAD;
+
+	rcu_read_lock();
+
+	sk = (*lookup)(skb, uh->source, uh->dest);
+
+	if (sk && udp_sk(sk)->flow_dissect)
+		ret = udp_sk(sk)->flow_dissect(sk, skb, key_control,
+					       flow_dissector, target_container,
+					       data, p_proto, p_ip_proto,
+					       p_nhoff, p_hlen, flags);
+	rcu_read_unlock();
+
+	return ret;
+}
+EXPORT_SYMBOL(udp_flow_dissect);
+
+static enum flow_dissect_ret udp4_flow_dissect(struct sk_buff *skb,
+			struct flow_dissector_key_control *key_control,
+			struct flow_dissector *flow_dissector,
+			void *target_container, void *data,
+			__be16 *p_proto, u8 *p_ip_proto, int *p_nhoff,
+			int *p_hlen, unsigned int flags)
+{
+	if (!static_key_false(&udp_encap_needed))
+		return FLOW_DISSECT_RET_CONTINUE;
+
+	return udp_flow_dissect(skb, udp4_lib_lookup_skb, key_control,
+				flow_dissector, target_container, data,
+				p_proto, p_ip_proto, p_nhoff, p_hlen, flags);
+}
+
 static const struct net_offload udpv4_offload = {
 	.callbacks = {
 		.gso_segment = udp4_tunnel_segment,
 		.gro_receive  =	udp4_gro_receive,
 		.gro_complete =	udp4_gro_complete,
+		.flow_dissect = udp4_flow_dissect,
 	},
 };
 

@@ -71,6 +71,7 @@ void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
 	udp_sk(sk)->encap_destroy = cfg->encap_destroy;
 	udp_sk(sk)->gro_receive = cfg->gro_receive;
 	udp_sk(sk)->gro_complete = cfg->gro_complete;
+	udp_sk(sk)->flow_dissect = cfg->flow_dissect;
 
 	udp_tunnel_encap_enable(sock);
 }

@@ -80,11 +80,27 @@ static int udp6_gro_complete(struct sk_buff *skb, int nhoff)
 	return udp_gro_complete(skb, nhoff, udp6_lib_lookup_skb);
 }
 
+static enum flow_dissect_ret udp6_flow_dissect(struct sk_buff *skb,
+			struct flow_dissector_key_control *key_control,
+			struct flow_dissector *flow_dissector,
+			void *target_container, void *data,
+			__be16 *p_proto, u8 *p_ip_proto, int *p_nhoff,
+			int *p_hlen, unsigned int flags)
+{
+	if (!static_key_false(&udp_encap_needed))
+		return FLOW_DISSECT_RET_CONTINUE;
+
+	return udp_flow_dissect(skb, udp6_lib_lookup_skb, key_control,
+				flow_dissector, target_container, data,
+				p_proto, p_ip_proto, p_nhoff, p_hlen, flags);
+}
+
 static const struct net_offload udpv6_offload = {
 	.callbacks = {
 		.gso_segment	=	udp6_tunnel_segment,
 		.gro_receive	=	udp6_gro_receive,
 		.gro_complete	=	udp6_gro_complete,
+		.flow_dissect	=	udp6_flow_dissect,
 	},
 };
 

@@ -282,6 +282,20 @@ static int fou_gro_complete(struct sock *sk, struct sk_buff *skb,
 	return err;
 }
 
+static enum flow_dissect_ret fou_flow_dissect(struct sock *sk,
+			const struct sk_buff *skb,
+			struct flow_dissector_key_control *key_control,
+			struct flow_dissector *flow_dissector,
+			void *target_container, void *data,
+			__be16 *p_proto, u8 *p_ip_proto, int *p_nhoff,
+			int *p_hlen, unsigned int flags)
+{
+	*p_ip_proto = fou_from_sock(sk)->protocol;
+	*p_nhoff += sizeof(struct udphdr);
+
+	return FLOW_DISSECT_RET_IPPROTO_AGAIN;
+}
+
 static struct guehdr *gue_gro_remcsum(struct sk_buff *skb, unsigned int off,
 				      struct guehdr *guehdr, void *data,
 				      size_t hdrlen, struct gro_remcsum *grc,

@@ -500,6 +514,53 @@ static int gue_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff)
 	return err;
 }
 
+static enum flow_dissect_ret gue_flow_dissect(struct sock *sk,
+			const struct sk_buff *skb,
+			struct flow_dissector_key_control *key_control,
+			struct flow_dissector *flow_dissector,
+			void *target_container, void *data,
+			__be16 *p_proto, u8 *p_ip_proto, int *p_nhoff,
+			int *p_hlen, unsigned int flags)
+{
+	struct guehdr *guehdr, _guehdr;
+
+	guehdr = __skb_header_pointer(skb, *p_nhoff + sizeof(struct udphdr),
+				      sizeof(_guehdr), data, *p_hlen, &_guehdr);
+	if (!guehdr)
+		return FLOW_DISSECT_RET_OUT_BAD;
+
+	switch (guehdr->version) {
+	case 0:
+		if (unlikely(guehdr->control))
+			return FLOW_DISSECT_RET_CONTINUE;
+
+		*p_ip_proto = guehdr->proto_ctype;
+		*p_nhoff += sizeof(struct udphdr) +
+		    sizeof(*guehdr) + (guehdr->hlen << 2);
+
+		break;
+	case 1:
+		switch (((struct iphdr *)guehdr)->version) {
+		case 4:
+			*p_ip_proto = IPPROTO_IPIP;
+			break;
+		case 6:
+			*p_ip_proto = IPPROTO_IPV6;
+			break;
+		default:
+			return FLOW_DISSECT_RET_CONTINUE;
+		}
+
+		*p_nhoff += sizeof(struct udphdr);
+
+		break;
+	default:
+		return FLOW_DISSECT_RET_CONTINUE;
+	}
+
+	return FLOW_DISSECT_RET_IPPROTO_AGAIN;
+}
+
 static int fou_add_to_port_list(struct net *net, struct fou *fou)
 {
 	struct fou_net *fn = net_generic(net, fou_net_id);

@@ -570,12 +631,14 @@ static int fou_create(struct net *net, struct fou_cfg *cfg,
 		tunnel_cfg.encap_rcv = fou_udp_recv;
 		tunnel_cfg.gro_receive = fou_gro_receive;
 		tunnel_cfg.gro_complete = fou_gro_complete;
+		tunnel_cfg.flow_dissect = fou_flow_dissect;
 		fou->protocol = cfg->protocol;
 		break;
 	case FOU_ENCAP_GUE:
 		tunnel_cfg.encap_rcv = gue_udp_recv;
 		tunnel_cfg.gro_receive = gue_gro_receive;
 		tunnel_cfg.gro_complete = gue_gro_complete;
+		tunnel_cfg.flow_dissect = gue_flow_dissect;
 		break;
 	default:
 		err = -EINVAL;