flow_dissect: use programable dissector in skb_flow_dissect and friends

Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 153 insertions, 76 deletions

diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 6883e22..6a49aca 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -13,6 +13,7 @@
 #include <linux/if_tunnel.h>
 #include <linux/if_pppox.h>
 #include <linux/ppp_defs.h>
+#include <linux/stddef.h>
 #include <net/flow_dissector.h>
 #include <scsi/fc/fc_fcoe.h>
 
@@ -63,17 +64,6 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector,
 }
 EXPORT_SYMBOL(skb_flow_dissector_init);
 
-/* copy saddr & daddr, possibly using 64bit load/store
- * Equivalent to :	flow->src = iph->saddr;
- *			flow->dst = iph->daddr;
- */
-static void iph_to_flow_copy_addrs(struct flow_keys *flow, const struct iphdr *iph)
-{
-	BUILD_BUG_ON(offsetof(typeof(*flow), dst) !=
-		     offsetof(typeof(*flow), src) + sizeof(flow->src));
-	memcpy(&flow->src, &iph->saddr, sizeof(flow->src) + sizeof(flow->dst));
-}
-
 /**
  * __skb_flow_get_ports - extract the upper layer ports and return them
  * @skb: sk_buff to extract the ports from
@@ -111,17 +101,27 @@ EXPORT_SYMBOL(__skb_flow_get_ports);
 /**
  * __skb_flow_dissect - extract the flow_keys struct and return it
  * @skb: sk_buff to extract the flow from, can be NULL if the rest are specified
+ * @flow_dissector: list of keys to dissect
+ * @target_container: target structure to put dissected values into
  * @data: raw buffer pointer to the packet, if NULL use skb->data
  * @proto: protocol for which to get the flow, if @data is NULL use skb->protocol
  * @nhoff: network header offset, if @data is NULL use skb_network_offset(skb)
  * @hlen: packet header length, if @data is NULL use skb_headlen(skb)
  *
- * The function will try to retrieve the struct flow_keys from either the skbuff
- * or a raw buffer specified by the rest parameters
+ * The function will try to retrieve individual keys into target specified
+ * by flow_dissector from either the skbuff or a raw buffer specified by the
+ * rest parameters.
+ *
+ * Caller must take care of zeroing target container memory.
  */
-bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow,
+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)
 {
+	struct flow_dissector_key_basic *key_basic;
+	struct flow_dissector_key_addrs *key_addrs;
+	struct flow_dissector_key_ports *key_ports;
 	u8 ip_proto;
 
 	if (!data) {
@@ -131,7 +131,12 @@ bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow,
 		hlen = skb_headlen(skb);
 	}
 
-	memset(flow, 0, sizeof(*flow));
+	/* It is ensured by skb_flow_dissector_init() that basic key will
+	 * be always present.
+	 */
+	key_basic = skb_flow_dissector_target(flow_dissector,
+					      FLOW_DISSECTOR_KEY_BASIC,
+					      target_container);
 
 again:
 	switch (proto) {
@@ -148,14 +153,13 @@ ip:
 		if (ip_is_fragment(iph))
 			ip_proto = 0;
 
-		/* skip the address processing if skb is NULL.  The assumption
-		 * here is that if there is no skb we are not looking for flow
-		 * info but lengths and protocols.
-		 */
-		if (!skb)
+		if (!skb_flow_dissector_uses_key(flow_dissector,
+						 FLOW_DISSECTOR_KEY_IPV4_ADDRS))
 			break;
-
-		iph_to_flow_copy_addrs(flow, iph);
+		key_addrs = skb_flow_dissector_target(flow_dissector,
+						      FLOW_DISSECTOR_KEY_IPV4_ADDRS,
+						      target_container);
+		memcpy(key_addrs, &iph->saddr, sizeof(*key_addrs));
 		break;
 	}
 	case htons(ETH_P_IPV6): {
@@ -171,12 +175,15 @@ ipv6:
 		ip_proto = iph->nexthdr;
 		nhoff += sizeof(struct ipv6hdr);
 
-		/* see comment above in IPv4 section */
-		if (!skb)
+		if (!skb_flow_dissector_uses_key(flow_dissector,
+						 FLOW_DISSECTOR_KEY_IPV6_HASH_ADDRS))
 			break;
+		key_addrs = skb_flow_dissector_target(flow_dissector,
+						      FLOW_DISSECTOR_KEY_IPV6_HASH_ADDRS,
+						      target_container);
 
-		flow->src = (__force __be32)ipv6_addr_hash(&iph->saddr);
-		flow->dst = (__force __be32)ipv6_addr_hash(&iph->daddr);
+		key_addrs->src = (__force __be32)ipv6_addr_hash(&iph->saddr);
+		key_addrs->dst = (__force __be32)ipv6_addr_hash(&iph->daddr);
 
 		flow_label = ip6_flowlabel(iph);
 		if (flow_label) {
@@ -184,10 +191,18 @@ ipv6:
 			 * use that to represent the ports without any
 			 * further dissection.
 			 */
-			flow->n_proto = proto;
-			flow->ip_proto = ip_proto;
-			flow->ports = flow_label;
-			flow->thoff = (u16)nhoff;
+
+			key_basic->n_proto = proto;
+			key_basic->ip_proto = ip_proto;
+			key_basic->thoff = (u16)nhoff;
+
+			if (!skb_flow_dissector_uses_key(flow_dissector,
+							 FLOW_DISSECTOR_KEY_PORTS))
+				break;
+			key_ports = skb_flow_dissector_target(flow_dissector,
+							      FLOW_DISSECTOR_KEY_PORTS,
+							      target_container);
+			key_ports->ports = flow_label;
 
 			return true;
 		}
@@ -234,14 +249,22 @@ ipv6:
 		hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr);
 		if (!hdr)
 			return false;
-		flow->src = hdr->srcnode;
-		flow->dst = 0;
-		flow->n_proto = proto;
-		flow->thoff = (u16)nhoff;
+		key_basic->n_proto = proto;
+		key_basic->thoff = (u16)nhoff;
+
+		if (skb_flow_dissector_uses_key(flow_dissector,
+						FLOW_DISSECTOR_KEY_IPV6_HASH_ADDRS)) {
+			return true;
+			key_addrs = skb_flow_dissector_target(flow_dissector,
+							      FLOW_DISSECTOR_KEY_IPV6_HASH_ADDRS,
+							      target_container);
+			key_addrs->src = hdr->srcnode;
+			key_addrs->dst = 0;
+		}
 		return true;
 	}
 	case htons(ETH_P_FCOE):
-		flow->thoff = (u16)(nhoff + FCOE_HEADER_LEN);
+		key_basic->thoff = (u16)(nhoff + FCOE_HEADER_LEN);
 		/* fall through */
 	default:
 		return false;
@@ -296,14 +319,24 @@ ipv6:
 		break;
 	}
 
-	flow->n_proto = proto;
-	flow->ip_proto = ip_proto;
-	flow->thoff = (u16) nhoff;
-
-	/* unless skb is set we don't need to record port info */
-	if (skb)
-		flow->ports = __skb_flow_get_ports(skb, nhoff, ip_proto,
-						   data, hlen);
+	/* It is ensured by skb_flow_dissector_init() that basic key will
+	 * be always present.
+	 */
+	key_basic = skb_flow_dissector_target(flow_dissector,
+					      FLOW_DISSECTOR_KEY_BASIC,
+					      target_container);
+	key_basic->n_proto = proto;
+	key_basic->ip_proto = ip_proto;
+	key_basic->thoff = (u16) nhoff;
+
+	if (skb_flow_dissector_uses_key(flow_dissector,
+					FLOW_DISSECTOR_KEY_PORTS)) {
+		key_ports = skb_flow_dissector_target(flow_dissector,
+						      FLOW_DISSECTOR_KEY_PORTS,
+						      target_container);
+		key_ports->ports = __skb_flow_get_ports(skb, nhoff, ip_proto,
+							data, hlen);
+	}
 
 	return true;
 }
@@ -325,16 +358,16 @@ static inline u32 __flow_hash_from_keys(struct flow_keys *keys, u32 keyval)
 	u32 hash;
 
 	/* get a consistent hash (same value on both flow directions) */
-	if (((__force u32)keys->dst < (__force u32)keys->src) ||
-	    (((__force u32)keys->dst == (__force u32)keys->src) &&
-	     ((__force u16)keys->port16[1] < (__force u16)keys->port16[0]))) {
-		swap(keys->dst, keys->src);
-		swap(keys->port16[0], keys->port16[1]);
+	if (((__force u32)keys->addrs.dst < (__force u32)keys->addrs.src) ||
+	    (((__force u32)keys->addrs.dst == (__force u32)keys->addrs.src) &&
+	     ((__force u16)keys->ports.port16[1] < (__force u16)keys->ports.port16[0]))) {
+		swap(keys->addrs.dst, keys->addrs.src);
+		swap(keys->ports.port16[0], keys->ports.port16[1]);
 	}
 
-	hash = __flow_hash_3words((__force u32)keys->dst,
-				  (__force u32)keys->src,
-				  (__force u32)keys->ports,
+	hash = __flow_hash_3words((__force u32)keys->addrs.dst,
+				  (__force u32)keys->addrs.src,
+				  (__force u32)keys->ports.ports,
 				  keyval);
 	if (!hash)
 		hash = 1;
@@ -352,7 +385,7 @@ EXPORT_SYMBOL(flow_hash_from_keys);
 static inline u32 ___skb_get_hash(const struct sk_buff *skb,
 				  struct flow_keys *keys, u32 keyval)
 {
-	if (!skb_flow_dissect(skb, keys))
+	if (!skb_flow_dissect_flow_keys(skb, keys))
 		return 0;
 
 	return __flow_hash_from_keys(keys, keyval);
@@ -377,11 +410,11 @@ void make_flow_keys_digest(struct flow_keys_digest *digest,
 
 	memset(digest, 0, sizeof(*digest));
 
-	data->n_proto = flow->n_proto;
-	data->ip_proto = flow->ip_proto;
-	data->ports = flow->ports;
-	data->src = flow->src;
-	data->dst = flow->dst;
+	data->n_proto = flow->basic.n_proto;
+	data->ip_proto = flow->basic.ip_proto;
+	data->ports = flow->ports.ports;
+	data->src = flow->addrs.src;
+	data->dst = flow->addrs.dst;
 }
 EXPORT_SYMBOL(make_flow_keys_digest);
 
@@ -404,7 +437,7 @@ void __skb_get_hash(struct sk_buff *skb)
 	hash = ___skb_get_hash(skb, &keys, hashrnd);
 	if (!hash)
 		return;
-	if (keys.ports)
+	if (keys.ports.ports)
 		skb->l4_hash = 1;
 	skb->sw_hash = 1;
 	skb->hash = hash;
@@ -422,9 +455,9 @@ EXPORT_SYMBOL(skb_get_hash_perturb);
 u32 __skb_get_poff(const struct sk_buff *skb, void *data,
 		   const struct flow_keys *keys, int hlen)
 {
-	u32 poff = keys->thoff;
+	u32 poff = keys->basic.thoff;
 
-	switch (keys->ip_proto) {
+	switch (keys->basic.ip_proto) {
 	case IPPROTO_TCP: {
 		/* access doff as u8 to avoid unaligned access */
 		const u8 *doff;
@@ -478,8 +511,52 @@ u32 skb_get_poff(const struct sk_buff *skb)
 {
 	struct flow_keys keys;
 
-	if (!skb_flow_dissect(skb, &keys))
+	if (!skb_flow_dissect_flow_keys(skb, &keys))
 		return 0;
 
 	return __skb_get_poff(skb, skb->data, &keys, skb_headlen(skb));
 }
+
+static const struct flow_dissector_key flow_keys_dissector_keys[] = {
+	{
+		.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),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_IPV6_HASH_ADDRS,
+		.offset = offsetof(struct flow_keys, addrs),
+	},
+	{
+		.key_id = FLOW_DISSECTOR_KEY_PORTS,
+		.offset = offsetof(struct flow_keys, ports),
+	},
+};
+
+static const struct flow_dissector_key flow_keys_buf_dissector_keys[] = {
+	{
+		.key_id = FLOW_DISSECTOR_KEY_BASIC,
+		.offset = offsetof(struct flow_keys, basic),
+	},
+};
+
+struct flow_dissector flow_keys_dissector __read_mostly;
+EXPORT_SYMBOL(flow_keys_dissector);
+
+struct flow_dissector flow_keys_buf_dissector __read_mostly;
+
+static int __init init_default_flow_dissectors(void)
+{
+	skb_flow_dissector_init(&flow_keys_dissector,
+				flow_keys_dissector_keys,
+				ARRAY_SIZE(flow_keys_dissector_keys));
+	skb_flow_dissector_init(&flow_keys_buf_dissector,
+				flow_keys_buf_dissector_keys,
+				ARRAY_SIZE(flow_keys_buf_dissector_keys));
+	return 0;
+}
+
+late_initcall_sync(init_default_flow_dissectors);
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index 9332a0a..c3325bd 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -131,9 +131,9 @@ u32 eth_get_headlen(void *data, unsigned int len)
 		return len;
 
 	/* parse any remaining L2/L3 headers, check for L4 */
-	if (!__skb_flow_dissect(NULL, &keys, data,
-				eth->h_proto, sizeof(*eth), len))
-		return max_t(u32, keys.thoff, sizeof(*eth));
+	if (!skb_flow_dissect_flow_keys_buf(&keys, data, eth->h_proto,
+					    sizeof(*eth), len))
+		return max_t(u32, keys.basic.thoff, sizeof(*eth));
 
 	/* parse for any L4 headers */
 	return min_t(u32, __skb_get_poff(NULL, data, &keys, len), len);
diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index 4c5a922..4b3e3e3 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -68,35 +68,35 @@ static inline u32 addr_fold(void *addr)
 
 static u32 flow_get_src(const struct sk_buff *skb, const struct flow_keys *flow)
 {
-	if (flow->src)
-		return ntohl(flow->src);
+	if (flow->addrs.src)
+		return ntohl(flow->addrs.src);
 	return addr_fold(skb->sk);
 }
 
 static u32 flow_get_dst(const struct sk_buff *skb, const struct flow_keys *flow)
 {
-	if (flow->dst)
-		return ntohl(flow->dst);
+	if (flow->addrs.dst)
+		return ntohl(flow->addrs.dst);
 	return addr_fold(skb_dst(skb)) ^ (__force u16) tc_skb_protocol(skb);
 }
 
 static u32 flow_get_proto(const struct sk_buff *skb, const struct flow_keys *flow)
 {
-	return flow->ip_proto;
+	return flow->basic.ip_proto;
 }
 
 static u32 flow_get_proto_src(const struct sk_buff *skb, const struct flow_keys *flow)
 {
-	if (flow->ports)
-		return ntohs(flow->port16[0]);
+	if (flow->ports.ports)
+		return ntohs(flow->ports.port16[0]);
 
 	return addr_fold(skb->sk);
 }
 
 static u32 flow_get_proto_dst(const struct sk_buff *skb, const struct flow_keys *flow)
 {
-	if (flow->ports)
-		return ntohs(flow->port16[1]);
+	if (flow->ports.ports)
+		return ntohs(flow->ports.port16[1]);
 
 	return addr_fold(skb_dst(skb)) ^ (__force u16) tc_skb_protocol(skb);
 }
@@ -295,7 +295,7 @@ static int flow_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 
 		keymask = f->keymask;
 		if (keymask & FLOW_KEYS_NEEDED)
-			skb_flow_dissect(skb, &flow_keys);
+			skb_flow_dissect_flow_keys(skb, &flow_keys);
 
 		for (n = 0; n < f->nkeys; n++) {
 			key = ffs(keymask) - 1;
diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c
index 2624e99..93d5742 100644
--- a/net/sched/sch_choke.c
+++ b/net/sched/sch_choke.c
@@ -170,13 +170,13 @@ static bool choke_match_flow(struct sk_buff *skb1,
 
 	if (!choke_skb_cb(skb1)->keys_valid) {
 		choke_skb_cb(skb1)->keys_valid = 1;
-		skb_flow_dissect(skb1, &temp);
+		skb_flow_dissect_flow_keys(skb1, &temp);
 		make_flow_keys_digest(&choke_skb_cb(skb1)->keys, &temp);
 	}
 
 	if (!choke_skb_cb(skb2)->keys_valid) {
 		choke_skb_cb(skb2)->keys_valid = 1;
-		skb_flow_dissect(skb2, &temp);
+		skb_flow_dissect_flow_keys(skb2, &temp);
 		make_flow_keys_digest(&choke_skb_cb(skb2)->keys, &temp);
 	}