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 <davem@davemloft.net>

7 files changed, 192 insertions, 27 deletions

diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index a6aea805a0a2..f6f04fc0f629 100644
--- a/net/core/fib_rules.c
+++ b/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) {
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index 35d646a62ad4..737d11bc8838 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -182,6 +182,17 @@ static int fib4_rule_match(struct fib_rule *rule, struct flowi *fl, int flags)
 	if (r->tos && (r->tos != fl4->flowi4_tos))
 		return 0;
 
+	if (rule->ip_proto && (rule->ip_proto != fl4->flowi4_proto))
+		return 0;
+
+	if (fib_rule_port_range_set(&rule->sport_range) &&
+	    !fib_rule_port_inrange(&rule->sport_range, fl4->fl4_sport))
+		return 0;
+
+	if (fib_rule_port_range_set(&rule->dport_range) &&
+	    !fib_rule_port_inrange(&rule->dport_range, fl4->fl4_dport))
+		return 0;
+
 	return 1;
 }
 
@@ -244,6 +255,9 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
 	}
 #endif
 
+	if (fib_rule_requires_fldissect(rule))
+		net->ipv4.fib_rules_require_fldissect++;
+
 	rule4->src_len = frh->src_len;
 	rule4->srcmask = inet_make_mask(rule4->src_len);
 	rule4->dst_len = frh->dst_len;
@@ -272,6 +286,10 @@ static int fib4_rule_delete(struct fib_rule *rule)
 		net->ipv4.fib_num_tclassid_users--;
 #endif
 	net->ipv4.fib_has_custom_rules = true;
+
+	if (net->ipv4.fib_rules_require_fldissect &&
+	    fib_rule_requires_fldissect(rule))
+		net->ipv4.fib_rules_require_fldissect--;
 errout:
 	return err;
 }
@@ -389,6 +407,7 @@ int __net_init fib4_rules_init(struct net *net)
 		goto fail;
 	net->ipv4.rules_ops = ops;
 	net->ipv4.fib_has_custom_rules = false;
+	net->ipv4.fib_rules_require_fldissect = 0;
 	return 0;
 
 fail:
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index f31e6575ab91..181b0d8d589c 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1770,7 +1770,7 @@ void fib_select_path(struct net *net, struct fib_result *res,
 
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	if (res->fi->fib_nhs > 1) {
-		int h = fib_multipath_hash(res->fi, fl4, skb);
+		int h = fib_multipath_hash(res->fi, fl4, skb, NULL);
 
 		fib_select_multipath(res, h);
 	}
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 26eefa2eaa44..3bb686dac273 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1783,7 +1783,7 @@ 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)
+		       const struct sk_buff *skb, struct flow_keys *flkeys)
 {
 	struct net *net = fi->fib_net;
 	struct flow_keys hash_keys;
@@ -1810,14 +1810,23 @@ int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4,
 			if (skb->l4_hash)
 				return skb_get_hash_raw(skb) >> 1;
 			memset(&hash_keys, 0, sizeof(hash_keys));
-			skb_flow_dissect_flow_keys(skb, &keys, flag);
 
-			hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
-			hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src;
-			hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst;
-			hash_keys.ports.src = keys.ports.src;
-			hash_keys.ports.dst = keys.ports.dst;
-			hash_keys.basic.ip_proto = keys.basic.ip_proto;
+			if (flkeys) {
+				hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
+				hash_keys.addrs.v4addrs.src = flkeys->addrs.v4addrs.src;
+				hash_keys.addrs.v4addrs.dst = flkeys->addrs.v4addrs.dst;
+				hash_keys.ports.src = flkeys->ports.src;
+				hash_keys.ports.dst = flkeys->ports.dst;
+				hash_keys.basic.ip_proto = flkeys->basic.ip_proto;
+			} else {
+				skb_flow_dissect_flow_keys(skb, &keys, flag);
+				hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
+				hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src;
+				hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst;
+				hash_keys.ports.src = keys.ports.src;
+				hash_keys.ports.dst = keys.ports.dst;
+				hash_keys.basic.ip_proto = keys.basic.ip_proto;
+			}
 		} else {
 			memset(&hash_keys, 0, sizeof(hash_keys));
 			hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
@@ -1838,11 +1847,12 @@ int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4,
 static int ip_mkroute_input(struct sk_buff *skb,
 			    struct fib_result *res,
 			    struct in_device *in_dev,
-			    __be32 daddr, __be32 saddr, u32 tos)
+			    __be32 daddr, __be32 saddr, u32 tos,
+			    struct flow_keys *hkeys)
 {
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	if (res->fi && res->fi->fib_nhs > 1) {
-		int h = fib_multipath_hash(res->fi, NULL, skb);
+		int h = fib_multipath_hash(res->fi, NULL, skb, hkeys);
 
 		fib_select_multipath(res, h);
 	}
@@ -1868,13 +1878,14 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 			       struct fib_result *res)
 {
 	struct in_device *in_dev = __in_dev_get_rcu(dev);
+	struct flow_keys *flkeys = NULL, _flkeys;
+	struct net    *net = dev_net(dev);
 	struct ip_tunnel_info *tun_info;
-	struct flowi4	fl4;
+	int		err = -EINVAL;
 	unsigned int	flags = 0;
 	u32		itag = 0;
 	struct rtable	*rth;
-	int		err = -EINVAL;
-	struct net    *net = dev_net(dev);
+	struct flowi4	fl4;
 	bool do_cache;
 
 	/* IP on this device is disabled. */
@@ -1933,6 +1944,10 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	fl4.daddr = daddr;
 	fl4.saddr = saddr;
 	fl4.flowi4_uid = sock_net_uid(net, NULL);
+
+	if (fib4_rules_early_flow_dissect(net, skb, &fl4, &_flkeys))
+		flkeys = &_flkeys;
+
 	err = fib_lookup(net, &fl4, res, 0);
 	if (err != 0) {
 		if (!IN_DEV_FORWARD(in_dev))
@@ -1958,7 +1973,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	if (res->type != RTN_UNICAST)
 		goto martian_destination;
 
-	err = ip_mkroute_input(skb, res, in_dev, daddr, saddr, tos);
+	err = ip_mkroute_input(skb, res, in_dev, daddr, saddr, tos, flkeys);
 out:	return err;
 
 brd_input:
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index 95a2c9e8699a..04e5f523e50f 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -223,6 +223,17 @@ static int fib6_rule_match(struct fib_rule *rule, struct flowi *fl, int flags)
 	if (r->tclass && r->tclass != ip6_tclass(fl6->flowlabel))
 		return 0;
 
+	if (rule->ip_proto && (rule->ip_proto != fl6->flowi6_proto))
+		return 0;
+
+	if (fib_rule_port_range_set(&rule->sport_range) &&
+	    !fib_rule_port_inrange(&rule->sport_range, fl6->fl6_sport))
+		return 0;
+
+	if (fib_rule_port_range_set(&rule->dport_range) &&
+	    !fib_rule_port_inrange(&rule->dport_range, fl6->fl6_dport))
+		return 0;
+
 	return 1;
 }
 
@@ -258,12 +269,26 @@ static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
 	rule6->dst.plen = frh->dst_len;
 	rule6->tclass = frh->tos;
 
+	if (fib_rule_requires_fldissect(rule))
+		net->ipv6.fib6_rules_require_fldissect++;
+
 	net->ipv6.fib6_has_custom_rules = true;
 	err = 0;
 errout:
 	return err;
 }
 
+static int fib6_rule_delete(struct fib_rule *rule)
+{
+	struct net *net = rule->fr_net;
+
+	if (net->ipv6.fib6_rules_require_fldissect &&
+	    fib_rule_requires_fldissect(rule))
+		net->ipv6.fib6_rules_require_fldissect--;
+
+	return 0;
+}
+
 static int fib6_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh,
 			     struct nlattr **tb)
 {
@@ -323,6 +348,7 @@ static const struct fib_rules_ops __net_initconst fib6_rules_ops_template = {
 	.match			= fib6_rule_match,
 	.suppress		= fib6_rule_suppress,
 	.configure		= fib6_rule_configure,
+	.delete			= fib6_rule_delete,
 	.compare		= fib6_rule_compare,
 	.fill			= fib6_rule_fill,
 	.nlmsg_payload		= fib6_rule_nlmsg_payload,
@@ -350,6 +376,7 @@ static int __net_init fib6_rules_net_init(struct net *net)
 		goto out_fib6_rules_ops;
 
 	net->ipv6.fib6_rules_ops = ops;
+	net->ipv6.fib6_rules_require_fldissect = 0;
 out:
 	return err;
 
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 4fa4f1b150a4..b0778d323b6e 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -522,7 +522,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
 	fl6.fl6_icmp_type = type;
 	fl6.fl6_icmp_code = code;
 	fl6.flowi6_uid = sock_net_uid(net, NULL);
-	fl6.mp_hash = rt6_multipath_hash(&fl6, skb);
+	fl6.mp_hash = rt6_multipath_hash(&fl6, skb, NULL);
 	security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
 
 	sk = icmpv6_xmit_lock(net);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index aa709b644945..e2bb40824c85 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -460,7 +460,7 @@ static struct rt6_info *rt6_multipath_select(struct rt6_info *match,
 	 * case it will always be non-zero. Otherwise now is the time to do it.
 	 */
 	if (!fl6->mp_hash)
-		fl6->mp_hash = rt6_multipath_hash(fl6, NULL);
+		fl6->mp_hash = rt6_multipath_hash(fl6, NULL, NULL);
 
 	if (fl6->mp_hash <= atomic_read(&match->rt6i_nh_upper_bound))
 		return match;
@@ -1786,10 +1786,12 @@ struct dst_entry *ip6_route_input_lookup(struct net *net,
 EXPORT_SYMBOL_GPL(ip6_route_input_lookup);
 
 static void ip6_multipath_l3_keys(const struct sk_buff *skb,
-				  struct flow_keys *keys)
+				  struct flow_keys *keys,
+				  struct flow_keys *flkeys)
 {
 	const struct ipv6hdr *outer_iph = ipv6_hdr(skb);
 	const struct ipv6hdr *key_iph = outer_iph;
+	struct flow_keys *_flkeys = flkeys;
 	const struct ipv6hdr *inner_iph;
 	const struct icmp6hdr *icmph;
 	struct ipv6hdr _inner_iph;
@@ -1811,22 +1813,31 @@ static void ip6_multipath_l3_keys(const struct sk_buff *skb,
 		goto out;
 
 	key_iph = inner_iph;
+	_flkeys = NULL;
 out:
 	memset(keys, 0, sizeof(*keys));
 	keys->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
-	keys->addrs.v6addrs.src = key_iph->saddr;
-	keys->addrs.v6addrs.dst = key_iph->daddr;
-	keys->tags.flow_label = ip6_flowinfo(key_iph);
-	keys->basic.ip_proto = key_iph->nexthdr;
+	if (_flkeys) {
+		keys->addrs.v6addrs.src = _flkeys->addrs.v6addrs.src;
+		keys->addrs.v6addrs.dst = _flkeys->addrs.v6addrs.dst;
+		keys->tags.flow_label = _flkeys->tags.flow_label;
+		keys->basic.ip_proto = _flkeys->basic.ip_proto;
+	} else {
+		keys->addrs.v6addrs.src = key_iph->saddr;
+		keys->addrs.v6addrs.dst = key_iph->daddr;
+		keys->tags.flow_label = ip6_flowinfo(key_iph);
+		keys->basic.ip_proto = key_iph->nexthdr;
+	}
 }
 
 /* if skb is set it will be used and fl6 can be NULL */
-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 *flkeys)
 {
 	struct flow_keys hash_keys;
 
 	if (skb) {
-		ip6_multipath_l3_keys(skb, &hash_keys);
+		ip6_multipath_l3_keys(skb, &hash_keys, flkeys);
 		return flow_hash_from_keys(&hash_keys) >> 1;
 	}
 
@@ -1847,12 +1858,17 @@ void ip6_route_input(struct sk_buff *skb)
 		.flowi6_mark = skb->mark,
 		.flowi6_proto = iph->nexthdr,
 	};
+	struct flow_keys *flkeys = NULL, _flkeys;
 
 	tun_info = skb_tunnel_info(skb);
 	if (tun_info && !(tun_info->mode & IP_TUNNEL_INFO_TX))
 		fl6.flowi6_tun_key.tun_id = tun_info->key.tun_id;
+
+	if (fib6_rules_early_flow_dissect(net, skb, &fl6, &_flkeys))
+		flkeys = &_flkeys;
+
 	if (unlikely(fl6.flowi6_proto == IPPROTO_ICMPV6))
-		fl6.mp_hash = rt6_multipath_hash(&fl6, skb);
+		fl6.mp_hash = rt6_multipath_hash(&fl6, skb, flkeys);
 	skb_dst_drop(skb);
 	skb_dst_set(skb, ip6_route_input_lookup(net, skb->dev, &fl6, flags));
 }