Merge branch 'flow-dissector-features'

Tom Herbert says:

====================
flow_dissector: Paramterize dissection and other features

This patch set adds some new capabilities to flow_dissector:

- Add flags to flow dissector functions to control dissection
  - Flag to stop dissection when L3 header is seen (don't
    dissect L4)
  - Flag to stop dissection when encapsulation is detected
  - Flag to parse first fragment of fragmented packet. This
    may provide L4 ports
- Added new reporting in key_control
  - Packet is a fragment
  - Packet is a first fragment
  - Packet has encapsulation

Also:
  - Make __skb_set_sw_hash a general function
  - Create functions to get a flow hash based on flowi4 or flowi6
    structures without an reference to an skbuff
  - Ignore flow dissector return value from ___skb_get_hash. Just
    use whatever key fields are found to make a hash

Tested:

Ran 200 netperf TCP_RR instances for IPv6 and IPv4. Did not see any
regression. Ran UDP_RR with 10000 byte request and response size
for IPv4 and IPv6, no regression observed however I did see better
performance with IPv6 flow labels due to use of flow labels for L4
hash.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 126 insertions, 71 deletions

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 989307f991db..9e62687c70f3 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -937,14 +937,90 @@ enum pkt_hash_types {
 	PKT_HASH_TYPE_L4,	/* Input: src_IP, dst_IP, src_port, dst_port */
 };
 
-static inline void
-skb_set_hash(struct sk_buff *skb, __u32 hash, enum pkt_hash_types type)
+static inline void skb_clear_hash(struct sk_buff *skb)
 {
-	skb->l4_hash = (type == PKT_HASH_TYPE_L4);
+	skb->hash = 0;
 	skb->sw_hash = 0;
+	skb->l4_hash = 0;
+}
+
+static inline void skb_clear_hash_if_not_l4(struct sk_buff *skb)
+{
+	if (!skb->l4_hash)
+		skb_clear_hash(skb);
+}
+
+static inline void
+__skb_set_hash(struct sk_buff *skb, __u32 hash, bool is_sw, bool is_l4)
+{
+	skb->l4_hash = is_l4;
+	skb->sw_hash = is_sw;
 	skb->hash = hash;
 }
 
+static inline void
+skb_set_hash(struct sk_buff *skb, __u32 hash, enum pkt_hash_types type)
+{
+	/* Used by drivers to set hash from HW */
+	__skb_set_hash(skb, hash, false, type == PKT_HASH_TYPE_L4);
+}
+
+static inline void
+__skb_set_sw_hash(struct sk_buff *skb, __u32 hash, bool is_l4)
+{
+	__skb_set_hash(skb, hash, true, is_l4);
+}
+
+void __skb_get_hash(struct sk_buff *skb);
+u32 skb_get_poff(const 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,
+			    void *data, int hlen_proto);
+
+static inline __be32 skb_flow_get_ports(const struct sk_buff *skb,
+					int thoff, u8 ip_proto)
+{
+	return __skb_flow_get_ports(skb, thoff, ip_proto, NULL, 0);
+}
+
+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,
+			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,
+				    struct flow_dissector *flow_dissector,
+				    void *target_container, unsigned int flags)
+{
+	return __skb_flow_dissect(skb, flow_dissector, target_container,
+				  NULL, 0, 0, 0, flags);
+}
+
+static inline bool skb_flow_dissect_flow_keys(const struct sk_buff *skb,
+					      struct flow_keys *flow,
+					      unsigned int flags)
+{
+	memset(flow, 0, sizeof(*flow));
+	return __skb_flow_dissect(skb, &flow_keys_dissector, flow,
+				  NULL, 0, 0, 0, flags);
+}
+
+static inline bool skb_flow_dissect_flow_keys_buf(struct flow_keys *flow,
+						  void *data, __be16 proto,
+						  int nhoff, int hlen,
+						  unsigned int flags)
+{
+	memset(flow, 0, sizeof(*flow));
+	return __skb_flow_dissect(NULL, &flow_keys_buf_dissector, flow,
+				  data, proto, nhoff, hlen, flags);
+}
+
 static inline __u32 skb_get_hash(struct sk_buff *skb)
 {
 	if (!skb->l4_hash && !skb->sw_hash)
@@ -957,8 +1033,12 @@ __u32 __skb_get_hash_flowi6(struct sk_buff *skb, struct flowi6 *fl6);
 
 static inline __u32 skb_get_hash_flowi6(struct sk_buff *skb, struct flowi6 *fl6)
 {
-	if (!skb->l4_hash && !skb->sw_hash)
-		__skb_get_hash_flowi6(skb, fl6);
+	if (!skb->l4_hash && !skb->sw_hash) {
+		struct flow_keys keys;
+
+		__skb_set_sw_hash(skb, __get_hash_from_flowi6(fl6, &keys),
+				  flow_keys_have_l4(&keys));
+	}
 
 	return skb->hash;
 }
@@ -967,8 +1047,12 @@ __u32 __skb_get_hash_flowi4(struct sk_buff *skb, struct flowi4 *fl);
 
 static inline __u32 skb_get_hash_flowi4(struct sk_buff *skb, struct flowi4 *fl4)
 {
-	if (!skb->l4_hash && !skb->sw_hash)
-		__skb_get_hash_flowi4(skb, fl4);
+	if (!skb->l4_hash && !skb->sw_hash) {
+		struct flow_keys keys;
+
+		__skb_set_sw_hash(skb, __get_hash_from_flowi4(fl4, &keys),
+				  flow_keys_have_l4(&keys));
+	}
 
 	return skb->hash;
 }
@@ -980,19 +1064,6 @@ static inline __u32 skb_get_hash_raw(const struct sk_buff *skb)
 	return skb->hash;
 }
 
-static inline void skb_clear_hash(struct sk_buff *skb)
-{
-	skb->hash = 0;
-	skb->sw_hash = 0;
-	skb->l4_hash = 0;
-}
-
-static inline void skb_clear_hash_if_not_l4(struct sk_buff *skb)
-{
-	if (!skb->l4_hash)
-		skb_clear_hash(skb);
-}
-
 static inline void skb_copy_hash(struct sk_buff *to, const struct sk_buff *from)
 {
 	to->hash = from->hash;
@@ -1978,7 +2049,7 @@ static inline void skb_probe_transport_header(struct sk_buff *skb,
 
 	if (skb_transport_header_was_set(skb))
 		return;
-	else if (skb_flow_dissect_flow_keys(skb, &keys))
+	else if (skb_flow_dissect_flow_keys(skb, &keys, 0))
 		skb_set_transport_header(skb, keys.control.thoff);
 	else
 		skb_set_transport_header(skb, offset_hint);
diff --git a/include/net/flow.h b/include/net/flow.h
index 9e0297c4c11d..dafe97c3c048 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -10,6 +10,7 @@
 #include <linux/socket.h>
 #include <linux/in6.h>
 #include <linux/atomic.h>
+#include <net/flow_dissector.h>
 
 /*
  * ifindex generation is per-net namespace, and loopback is
@@ -243,4 +244,22 @@ void flow_cache_flush(struct net *net);
 void flow_cache_flush_deferred(struct net *net);
 extern atomic_t flow_cache_genid;
 
+__u32 __get_hash_from_flowi6(struct flowi6 *fl6, struct flow_keys *keys);
+
+static inline __u32 get_hash_from_flowi6(struct flowi6 *fl6)
+{
+	struct flow_keys keys;
+
+	return __get_hash_from_flowi6(fl6, &keys);
+}
+
+__u32 __get_hash_from_flowi4(struct flowi4 *fl4, struct flow_keys *keys);
+
+static inline __u32 get_hash_from_flowi4(struct flowi4 *fl4)
+{
+	struct flow_keys keys;
+
+	return __get_hash_from_flowi4(fl4, &keys);
+}
+
 #endif
diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
index 1a8c22419936..bddd1089dbce 100644
--- a/include/net/flow_dissector.h
+++ b/include/net/flow_dissector.h
@@ -2,7 +2,6 @@
 #define _NET_FLOW_DISSECTOR_H
 
 #include <linux/types.h>
-#include <linux/skbuff.h>
 #include <linux/in6.h>
 #include <uapi/linux/if_ether.h>
 
@@ -13,6 +12,9 @@
 struct flow_dissector_key_control {
 	u16	thoff;
 	u16	addr_type;
+	u32	is_fragment:1;
+	u32	first_frag:1;
+	u32	encapsulation:1;
 };
 
 /**
@@ -123,6 +125,11 @@ enum flow_dissector_key_id {
 	FLOW_DISSECTOR_KEY_MAX,
 };
 
+#define FLOW_DISSECTOR_F_PARSE_1ST_FRAG		BIT(0)
+#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)
+
 struct flow_dissector_key {
 	enum flow_dissector_key_id key_id;
 	size_t offset; /* offset of struct flow_dissector_key_*
@@ -134,23 +141,6 @@ struct flow_dissector {
 	unsigned short int offset[FLOW_DISSECTOR_KEY_MAX];
 };
 
-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,
-			struct flow_dissector *flow_dissector,
-			void *target_container,
-			void *data, __be16 proto, int nhoff, int hlen);
-
-static inline bool skb_flow_dissect(const struct sk_buff *skb,
-				    struct flow_dissector *flow_dissector,
-				    void *target_container)
-{
-	return __skb_flow_dissect(skb, flow_dissector, target_container,
-				  NULL, 0, 0, 0);
-}
-
 struct flow_keys {
 	struct flow_dissector_key_control control;
 #define FLOW_KEYS_HASH_START_FIELD basic
@@ -170,38 +160,6 @@ __be32 flow_get_u32_dst(const struct flow_keys *flow);
 extern struct flow_dissector flow_keys_dissector;
 extern struct flow_dissector flow_keys_buf_dissector;
 
-static inline bool skb_flow_dissect_flow_keys(const struct sk_buff *skb,
-					      struct flow_keys *flow)
-{
-	memset(flow, 0, sizeof(*flow));
-	return __skb_flow_dissect(skb, &flow_keys_dissector, flow,
-				  NULL, 0, 0, 0);
-}
-
-static inline bool skb_flow_dissect_flow_keys_buf(struct flow_keys *flow,
-						  void *data, __be16 proto,
-						  int nhoff, int hlen)
-{
-	memset(flow, 0, sizeof(*flow));
-	return __skb_flow_dissect(NULL, &flow_keys_buf_dissector, flow,
-				  data, proto, nhoff, hlen);
-}
-
-__be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto,
-			    void *data, int hlen_proto);
-
-static inline __be32 skb_flow_get_ports(const struct sk_buff *skb,
-					int thoff, u8 ip_proto)
-{
-	return __skb_flow_get_ports(skb, thoff, ip_proto, NULL, 0);
-}
-
-u32 flow_hash_from_keys(struct flow_keys *keys);
-void __skb_get_hash(struct sk_buff *skb);
-u32 skb_get_poff(const struct sk_buff *skb);
-u32 __skb_get_poff(const struct sk_buff *skb, void *data,
-		   const struct flow_keys *keys, int hlen);
-
 /* struct flow_keys_digest:
  *
  * This structure is used to hold a digest of the full flow keys. This is a
@@ -217,4 +175,11 @@ struct flow_keys_digest {
 void make_flow_keys_digest(struct flow_keys_digest *digest,
 			   const struct flow_keys *flow);
 
+static inline bool flow_keys_have_l4(struct flow_keys *keys)
+{
+	return (keys->ports.ports || keys->tags.flow_label);
+}
+
+u32 flow_hash_from_keys(struct flow_keys *keys);
+
 #endif