Merge branch 'fib_rules-support-sport-dport-and-proto-match'

Roopa Prabhu says:

====================
fib_rules: support sport, dport and proto match

This series extends fib rule match support to include sport, dport
and ip proto match (to complete the 5-tuple match support).
Common use-cases of Policy based routing in the data center require
5-tuple match. The last 2 patches in the series add a call to flow dissect
in the fwd path if required by the installed fib rules (controlled by a flag).

v1:
  - Fix errors reported by kbuild and feedback on RFC
  - extend port match uapi to accomodate port ranges

v2:
  - address comments from Nikolay, David Ahern and Paolo (Thanks!)

Pending things I will submit separate patches for:
  - extack for fib rules
  - fib rules test (as requested by david ahern)
====================

Signed-off-by: David S. Miller <[email protected]>

Author: davem330

include/net/fib_rules.h

@@ -27,7 +27,7 @@ struct fib_rule {
 	u8			action;
 	u8			l3mdev;
 	u8                      proto;
-	/* 1 byte hole, try to use */
+	u8			ip_proto;
 	u32			target;
 	__be64			tun_id;
 	struct fib_rule __rcu	*ctarget;
@@ -40,6 +40,8 @@ struct fib_rule {
 	char			iifname[IFNAMSIZ];
 	char			oifname[IFNAMSIZ];
 	struct fib_kuid_range	uid_range;
+	struct fib_rule_port_range	sport_range;
+	struct fib_rule_port_range	dport_range;
 	struct rcu_head		rcu;
 };
 
@@ -144,6 +146,38 @@ static inline u32 frh_get_table(struct fib_rule_hdr *frh, struct nlattr **nla)
 	return frh->table;
 }
 
+static inline bool fib_rule_port_range_set(const struct fib_rule_port_range *range)
+{
+	return range->start != 0 && range->end != 0;
+}
+
+static inline bool fib_rule_port_inrange(const struct fib_rule_port_range *a,
+					 __be16 port)
+{
+	return ntohs(port) >= a->start &&
+		ntohs(port) <= a->end;
+}
+
+static inline bool fib_rule_port_range_valid(const struct fib_rule_port_range *a)
+{
+	return a->start != 0 && a->end != 0 && a->end < 0xffff &&
+		a->start <= a->end;
+}
+
+static inline bool fib_rule_port_range_compare(struct fib_rule_port_range *a,
+					       struct fib_rule_port_range *b)
+{
+	return a->start == b->start &&
+		a->end == b->end;
+}
+
+static inline bool fib_rule_requires_fldissect(struct fib_rule *rule)
+{
+	return rule->ip_proto ||
+		fib_rule_port_range_set(&rule->sport_range) ||
+		fib_rule_port_range_set(&rule->dport_range);
+}
+
 struct fib_rules_ops *fib_rules_register(const struct fib_rules_ops *,
 					 struct net *);
 void fib_rules_unregister(struct fib_rules_ops *);

include/net/ip6_fib.h

@@ -415,6 +415,24 @@ void fib6_rules_cleanup(void);
 bool fib6_rule_default(const struct fib_rule *rule);
 int fib6_rules_dump(struct net *net, struct notifier_block *nb);
 unsigned int fib6_rules_seq_read(struct net *net);
+
+static inline bool fib6_rules_early_flow_dissect(struct net *net,
+						 struct sk_buff *skb,
+						 struct flowi6 *fl6,
+						 struct flow_keys *flkeys)
+{
+	unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP;
+
+	if (!net->ipv6.fib6_rules_require_fldissect)
+		return false;
+
+	skb_flow_dissect_flow_keys(skb, flkeys, flag);
+	fl6->fl6_sport = flkeys->ports.src;
+	fl6->fl6_dport = flkeys->ports.dst;
+	fl6->flowi6_proto = flkeys->basic.ip_proto;
+
+	return true;
+}
 #else
 static inline int               fib6_rules_init(void)
 {
@@ -436,5 +454,12 @@ static inline unsigned int fib6_rules_seq_read(struct net *net)
 {
 	return 0;
 }
+static inline bool fib6_rules_early_flow_dissect(struct net *net,
+						 struct sk_buff *skb,
+						 struct flowi6 *fl6,
+						 struct flow_keys *flkeys)
+{
+	return false;
+}
 #endif
 #endif

include/net/ip6_route.h

@@ -127,7 +127,8 @@ static inline int ip6_route_get_saddr(struct net *net, struct rt6_info *rt,
 
 struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr,
 			    const struct in6_addr *saddr, int oif, int flags);
-u32 rt6_multipath_hash(const struct flowi6 *fl6, const struct sk_buff *skb);
+u32 rt6_multipath_hash(const struct flowi6 *fl6, const struct sk_buff *skb,
+		       struct flow_keys *hkeys);
 
 struct dst_entry *icmp6_dst_alloc(struct net_device *dev, struct flowi6 *fl6);
 
@@ -266,4 +267,5 @@ static inline bool rt6_duplicate_nexthop(struct rt6_info *a, struct rt6_info *b)
 	       ipv6_addr_equal(&a->rt6i_gateway, &b->rt6i_gateway) &&
 	       !lwtunnel_cmp_encap(a->dst.lwtstate, b->dst.lwtstate);
 }
+
 #endif

include/net/ip_fib.h

@@ -293,6 +293,13 @@ static inline unsigned int fib4_rules_seq_read(struct net *net)
 	return 0;
 }
 
+static inline bool fib4_rules_early_flow_dissect(struct net *net,
+						 struct sk_buff *skb,
+						 struct flowi4 *fl4,
+						 struct flow_keys *flkeys)
+{
+	return false;
+}
 #else /* CONFIG_IP_MULTIPLE_TABLES */
 int __net_init fib4_rules_init(struct net *net);
 void __net_exit fib4_rules_exit(struct net *net);
@@ -341,6 +348,24 @@ bool fib4_rule_default(const struct fib_rule *rule);
 int fib4_rules_dump(struct net *net, struct notifier_block *nb);
 unsigned int fib4_rules_seq_read(struct net *net);
 
+static inline bool fib4_rules_early_flow_dissect(struct net *net,
+						 struct sk_buff *skb,
+						 struct flowi4 *fl4,
+						 struct flow_keys *flkeys)
+{
+	unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP;
+
+	if (!net->ipv4.fib_rules_require_fldissect)
+		return false;
+
+	skb_flow_dissect_flow_keys(skb, flkeys, flag);
+	fl4->fl4_sport = flkeys->ports.src;
+	fl4->fl4_dport = flkeys->ports.dst;
+	fl4->flowi4_proto = flkeys->basic.ip_proto;
+
+	return true;
+}
+
 #endif /* CONFIG_IP_MULTIPLE_TABLES */
 
 /* Exported by fib_frontend.c */
@@ -371,7 +396,7 @@ 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);
+		       const struct sk_buff *skb, struct flow_keys *flkeys);
 #endif
 void fib_select_multipath(struct fib_result *res, int hash);
 void fib_select_path(struct net *net, struct fib_result *res,

include/net/netns/ipv4.h

@@ -52,6 +52,7 @@ struct netns_ipv4 {
 #ifdef CONFIG_IP_MULTIPLE_TABLES
 	struct fib_rules_ops	*rules_ops;
 	bool			fib_has_custom_rules;
+	unsigned int		fib_rules_require_fldissect;
 	struct fib_table __rcu	*fib_main;
 	struct fib_table __rcu	*fib_default;
 #endif

include/net/netns/ipv6.h

@@ -71,7 +71,8 @@ struct netns_ipv6 {
 	unsigned int		 ip6_rt_gc_expire;
 	unsigned long		 ip6_rt_last_gc;
 #ifdef CONFIG_IPV6_MULTIPLE_TABLES
-	bool			 fib6_has_custom_rules;
+	unsigned int		fib6_rules_require_fldissect;
+	bool			fib6_has_custom_rules;
 	struct rt6_info         *ip6_prohibit_entry;
 	struct rt6_info         *ip6_blk_hole_entry;
 	struct fib6_table       *fib6_local_tbl;

include/uapi/linux/fib_rules.h

@@ -35,6 +35,11 @@ struct fib_rule_uid_range {
 	__u32		end;
 };
 
+struct fib_rule_port_range {
+	__u16		start;
+	__u16		end;
+};
+
 enum {
 	FRA_UNSPEC,
 	FRA_DST,	/* destination address */
@@ -59,6 +64,9 @@ enum {
 	FRA_L3MDEV,	/* iif or oif is l3mdev goto its table */
 	FRA_UID_RANGE,	/* UID range */
 	FRA_PROTOCOL,   /* Originator of the rule */
+	FRA_IP_PROTO,	/* ip proto */
+	FRA_SPORT_RANGE, /* sport */
+	FRA_DPORT_RANGE, /* dport */
 	__FRA_MAX
 };
 

net/core/fib_rules.c

@@ -33,6 +33,10 @@ bool fib_rule_matchall(const struct fib_rule *rule)
 	if (!uid_eq(rule->uid_range.start, fib_kuid_range_unset.start) ||
 	    !uid_eq(rule->uid_range.end, fib_kuid_range_unset.end))
 		return false;
+	if (fib_rule_port_range_set(&rule->sport_range))
+		return false;
+	if (fib_rule_port_range_set(&rule->dport_range))
+		return false;
 	return true;
 }
 EXPORT_SYMBOL_GPL(fib_rule_matchall);
@@ -221,6 +225,26 @@ static int nla_put_uid_range(struct sk_buff *skb, struct fib_kuid_range *range)
 	return nla_put(skb, FRA_UID_RANGE, sizeof(out), &out);
 }
 
+static int nla_get_port_range(struct nlattr *pattr,
+			      struct fib_rule_port_range *port_range)
+{
+	const struct fib_rule_port_range *pr = nla_data(pattr);
+
+	if (!fib_rule_port_range_valid(pr))
+		return -EINVAL;
+
+	port_range->start = pr->start;
+	port_range->end = pr->end;
+
+	return 0;
+}
+
+static int nla_put_port_range(struct sk_buff *skb, int attrtype,
+			      struct fib_rule_port_range *range)
+{
+	return nla_put(skb, attrtype, sizeof(*range), range);
+}
+
 static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops,
 			  struct flowi *fl, int flags,
 			  struct fib_lookup_arg *arg)
@@ -425,6 +449,17 @@ static int rule_exists(struct fib_rules_ops *ops, struct fib_rule_hdr *frh,
 		    !uid_eq(r->uid_range.end, rule->uid_range.end))
 			continue;
 
+		if (r->ip_proto != rule->ip_proto)
+			continue;
+
+		if (!fib_rule_port_range_compare(&r->sport_range,
+						 &rule->sport_range))
+			continue;
+
+		if (!fib_rule_port_range_compare(&r->dport_range,
+						 &rule->dport_range))
+			continue;
+
 		if (!ops->compare(r, frh, tb))
 			continue;
 		return 1;
@@ -569,6 +604,23 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh,
 		rule->uid_range = fib_kuid_range_unset;
 	}
 
+	if (tb[FRA_IP_PROTO])
+		rule->ip_proto = nla_get_u8(tb[FRA_IP_PROTO]);
+
+	if (tb[FRA_SPORT_RANGE]) {
+		err = nla_get_port_range(tb[FRA_SPORT_RANGE],
+					 &rule->sport_range);
+		if (err)
+			goto errout_free;
+	}
+
+	if (tb[FRA_DPORT_RANGE]) {
+		err = nla_get_port_range(tb[FRA_DPORT_RANGE],
+					 &rule->dport_range);
+		if (err)
+			goto errout_free;
+	}
+
 	if ((nlh->nlmsg_flags & NLM_F_EXCL) &&
 	    rule_exists(ops, frh, tb, rule)) {
 		err = -EEXIST;
@@ -634,6 +686,8 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh,
 {
 	struct net *net = sock_net(skb->sk);
 	struct fib_rule_hdr *frh = nlmsg_data(nlh);
+	struct fib_rule_port_range sprange = {0, 0};
+	struct fib_rule_port_range dprange = {0, 0};
 	struct fib_rules_ops *ops = NULL;
 	struct fib_rule *rule, *r;
 	struct nlattr *tb[FRA_MAX+1];
@@ -667,6 +721,20 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh,
 		range = fib_kuid_range_unset;
 	}
 
+	if (tb[FRA_SPORT_RANGE]) {
+		err = nla_get_port_range(tb[FRA_SPORT_RANGE],
+					 &sprange);
+		if (err)
+			goto errout;
+	}
+
+	if (tb[FRA_DPORT_RANGE]) {
+		err = nla_get_port_range(tb[FRA_DPORT_RANGE],
+					 &dprange);
+		if (err)
+			goto errout;
+	}
+
 	list_for_each_entry(rule, &ops->rules_list, list) {
 		if (tb[FRA_PROTOCOL] &&
 		    (rule->proto != nla_get_u8(tb[FRA_PROTOCOL])))
@@ -712,6 +780,18 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh,
 		     !uid_eq(rule->uid_range.end, range.end)))
 			continue;
 
+		if (tb[FRA_IP_PROTO] &&
+		    (rule->ip_proto != nla_get_u8(tb[FRA_IP_PROTO])))
+			continue;
+
+		if (fib_rule_port_range_set(&sprange) &&
+		    !fib_rule_port_range_compare(&rule->sport_range, &sprange))
+			continue;
+
+		if (fib_rule_port_range_set(&dprange) &&
+		    !fib_rule_port_range_compare(&rule->dport_range, &dprange))
+			continue;
+
 		if (!ops->compare(rule, frh, tb))
 			continue;
 
@@ -790,7 +870,10 @@ static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops,
 			 + nla_total_size(4) /* FRA_FWMASK */
 			 + nla_total_size_64bit(8) /* FRA_TUN_ID */
 			 + nla_total_size(sizeof(struct fib_kuid_range))
-			 + nla_total_size(1); /* FRA_PROTOCOL */
+			 + nla_total_size(1) /* FRA_PROTOCOL */
+			 + nla_total_size(1) /* FRA_IP_PROTO */
+			 + nla_total_size(sizeof(struct fib_rule_port_range)) /* FRA_SPORT_RANGE */
+			 + nla_total_size(sizeof(struct fib_rule_port_range)); /* FRA_DPORT_RANGE */
 
 	if (ops->nlmsg_payload)
 		payload += ops->nlmsg_payload(rule);
@@ -855,7 +938,12 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule,
 	    (rule->l3mdev &&
 	     nla_put_u8(skb, FRA_L3MDEV, rule->l3mdev)) ||
 	    (uid_range_set(&rule->uid_range) &&
-	     nla_put_uid_range(skb, &rule->uid_range)))
+	     nla_put_uid_range(skb, &rule->uid_range)) ||
+	    (fib_rule_port_range_set(&rule->sport_range) &&
+	     nla_put_port_range(skb, FRA_SPORT_RANGE, &rule->sport_range)) ||
+	    (fib_rule_port_range_set(&rule->dport_range) &&
+	     nla_put_port_range(skb, FRA_DPORT_RANGE, &rule->dport_range)) ||
+	    (rule->ip_proto && nla_put_u8(skb, FRA_IP_PROTO, rule->ip_proto)))
 		goto nla_put_failure;
 
 	if (rule->suppress_ifgroup != -1) {