Merge branch 'net-fib_rules-add-flow-label-selector-support'

Ido Schimmel says:

====================
net: fib_rules: Add flow label selector support

In some deployments users would like to encode path information into
certain bits of the IPv6 flow label, the UDP source port and the DSCP
and use this information to route packets accordingly.

Redirecting traffic to a routing table based on the flow label is not
currently possible with Linux as FIB rules cannot match on it despite
the flow label being available in the IPv6 flow key.

This patchset extends FIB rules to match on the flow label with a mask.
Future patches will add mask attributes to L4 ports and DSCP matches.

Patches #1-#5 gradually extend FIB rules to match on the flow label.

Patches #6-#7 allow user space to specify a flow label in route get
requests. This is useful for both debugging and testing.

Patch #8 adjusts the fib6_table_lookup tracepoint to print the flow
label to the trace buffer for better observability.

Patch #9 extends the FIB rule selftest with flow label test cases while
utilizing the route get functionality from patch #6.
====================

Link: https://patch.msgid.link/[e-mail]
Signed-off-by: Paolo Abeni <[e-mail]>

Documentation/netlink/specs/rt_route.yaml

···
       -
         name: rta-nh-id
         type: u32
+      -
+        name: rta-flowlabel
+        type: u32
+        byte-order: big-endian
+        display-hint: hex
   -
     name: rta-metrics
     attributes:
···
             - rta-dport
             - rta-mark
             - rta-uid
+            - rta-flowlabel
         reply:
           value: 24
           attributes: &all-route-attrs
···
             - rta-sport
             - rta-dport
             - rta-nh-id
+            - rta-flowlabel
       dump:
         request:
           value: 26

Documentation/netlink/specs/rt_rule.yaml

···
       -
         name: dscp
         type: u8
+      -
+        name: flowlabel
+        type: u32
+        byte-order: big-endian
+        display-hint: hex
+      -
+        name: flowlabel-mask
+        type: u32
+        byte-order: big-endian
+        display-hint: hex
 
 operations:
   enum-model: directional
···
             - sport-range
             - dport-range
             - dscp
+            - flowlabel
+            - flowlabel-mask
     -
       name: newrule-ntf
       doc: Notify a rule creation

include/trace/events/fib6.h

···
 		__field(	int,	err		)
 		__field(	int,	oif		)
 		__field(	int,	iif		)
+		__field(	u32,	flowlabel	)
 		__field(	__u8,	tos		)
 		__field(	__u8,	scope		)
 		__field(	__u8,	flags		)
···
 		__entry->err = ip6_rt_type_to_error(res->fib6_type);
 		__entry->oif = flp->flowi6_oif;
 		__entry->iif = flp->flowi6_iif;
+		__entry->flowlabel = ntohl(flowi6_get_flowlabel(flp));
 		__entry->tos = ip6_tclass(flp->flowlabel);
 		__entry->scope = flp->flowi6_scope;
 		__entry->flags = flp->flowi6_flags;
···
 		}
 	),
 
-	TP_printk("table %3u oif %d iif %d proto %u %pI6c/%u -> %pI6c/%u tos %d scope %d flags %x ==> dev %s gw %pI6c err %d",
+	TP_printk("table %3u oif %d iif %d proto %u %pI6c/%u -> %pI6c/%u flowlabel %#x tos %d scope %d flags %x ==> dev %s gw %pI6c err %d",
 		  __entry->tb_id, __entry->oif, __entry->iif, __entry->proto,
 		  __entry->src, __entry->sport, __entry->dst, __entry->dport,
-		  __entry->tos, __entry->scope, __entry->flags,
-		  __entry->name, __entry->gw, __entry->err)
+		  __entry->flowlabel, __entry->tos, __entry->scope,
+		  __entry->flags, __entry->name, __entry->gw, __entry->err)
 );
 
 #endif /* _TRACE_FIB6_H */

include/uapi/linux/fib_rules.h

···
 	FRA_SPORT_RANGE, /* sport */
 	FRA_DPORT_RANGE, /* dport */
 	FRA_DSCP,	/* dscp */
+	FRA_FLOWLABEL,	/* flowlabel */
+	FRA_FLOWLABEL_MASK,	/* flowlabel mask */
 	__FRA_MAX
 };
 

include/uapi/linux/rtnetlink.h

···
 	RTA_SPORT,
 	RTA_DPORT,
 	RTA_NH_ID,
+	RTA_FLOWLABEL,
 	__RTA_MAX
 };
 

net/core/fib_rules.c

···
 	[FRA_SPORT_RANGE] = { .len = sizeof(struct fib_rule_port_range) },
 	[FRA_DPORT_RANGE] = { .len = sizeof(struct fib_rule_port_range) },
 	[FRA_DSCP]	= NLA_POLICY_MAX(NLA_U8, INET_DSCP_MASK >> 2),
+	[FRA_FLOWLABEL] = { .type = NLA_BE32 },
+	[FRA_FLOWLABEL_MASK] = { .type = NLA_BE32 },
 };
 
 int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh,

net/ipv4/fib_rules.c

···
 	int err = -EINVAL;
 	struct fib4_rule *rule4 = (struct fib4_rule *) rule;
 
+	if (tb[FRA_FLOWLABEL] || tb[FRA_FLOWLABEL_MASK]) {
+		NL_SET_ERR_MSG(extack,
+			       "Flow label cannot be specified for IPv4 FIB rules");
+		goto errout;
+	}
+
 	if (!inet_validate_dscp(frh->tos)) {
 		NL_SET_ERR_MSG(extack,
 			       "Invalid dsfield (tos): ECN bits must be 0");

net/ipv6/fib6_rules.c

···
 	struct fib_rule		common;
 	struct rt6key		src;
 	struct rt6key		dst;
+	__be32			flowlabel;
+	__be32			flowlabel_mask;
 	dscp_t			dscp;
 	u8			dscp_full:1;	/* DSCP or TOS selector */
 };
···
 {
 	struct fib6_rule *r = container_of(rule, struct fib6_rule, common);
 
-	if (r->dst.plen || r->src.plen || r->dscp)
+	if (r->dst.plen || r->src.plen || r->dscp || r->flowlabel_mask)
 		return false;
 	return fib_rule_matchall(rule);
 }
···
 	if (r->dscp && r->dscp != ip6_dscp(fl6->flowlabel))
 		return 0;
 
+	if ((r->flowlabel ^ flowi6_get_flowlabel(fl6)) & r->flowlabel_mask)
+		return 0;
+
 	if (rule->ip_proto && (rule->ip_proto != fl6->flowi6_proto))
 		return 0;
 
···
 	return 0;
 }
 
+static int fib6_nl2rule_flowlabel(struct nlattr **tb, struct fib6_rule *rule6,
+				  struct netlink_ext_ack *extack)
+{
+	__be32 flowlabel, flowlabel_mask;
+
+	if (NL_REQ_ATTR_CHECK(extack, NULL, tb, FRA_FLOWLABEL) ||
+	    NL_REQ_ATTR_CHECK(extack, NULL, tb, FRA_FLOWLABEL_MASK))
+		return -EINVAL;
+
+	flowlabel = nla_get_be32(tb[FRA_FLOWLABEL]);
+	flowlabel_mask = nla_get_be32(tb[FRA_FLOWLABEL_MASK]);
+
+	if (flowlabel_mask & ~IPV6_FLOWLABEL_MASK) {
+		NL_SET_ERR_MSG_ATTR(extack, tb[FRA_FLOWLABEL_MASK],
+				    "Invalid flow label mask");
+		return -EINVAL;
+	}
+
+	if (flowlabel & ~flowlabel_mask) {
+		NL_SET_ERR_MSG(extack, "Flow label and mask do not match");
+		return -EINVAL;
+	}
+
+	rule6->flowlabel = flowlabel;
+	rule6->flowlabel_mask = flowlabel_mask;
+
+	return 0;
+}
+
 static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
 			       struct fib_rule_hdr *frh,
 			       struct nlattr **tb,
···
 	rule6->dscp = inet_dsfield_to_dscp(frh->tos);
 
 	if (tb[FRA_DSCP] && fib6_nl2rule_dscp(tb[FRA_DSCP], rule6, extack) < 0)
+		goto errout;
+
+	if ((tb[FRA_FLOWLABEL] || tb[FRA_FLOWLABEL_MASK]) &&
+	    fib6_nl2rule_flowlabel(tb, rule6, extack) < 0)
 		goto errout;
 
 	if (rule->action == FR_ACT_TO_TBL && !rule->l3mdev) {
···
 			return 0;
 	}
 
+	if (tb[FRA_FLOWLABEL] &&
+	    nla_get_be32(tb[FRA_FLOWLABEL]) != rule6->flowlabel)
+		return 0;
+
+	if (tb[FRA_FLOWLABEL_MASK] &&
+	    nla_get_be32(tb[FRA_FLOWLABEL_MASK]) != rule6->flowlabel_mask)
+		return 0;
+
 	if (frh->src_len &&
 	    nla_memcmp(tb[FRA_SRC], &rule6->src.addr, sizeof(struct in6_addr)))
 		return 0;
···
 		frh->tos = inet_dscp_to_dsfield(rule6->dscp);
 	}
 
+	if (rule6->flowlabel_mask &&
+	    (nla_put_be32(skb, FRA_FLOWLABEL, rule6->flowlabel) ||
+	     nla_put_be32(skb, FRA_FLOWLABEL_MASK, rule6->flowlabel_mask)))
+		goto nla_put_failure;
+
 	if ((rule6->dst.plen &&
 	     nla_put_in6_addr(skb, FRA_DST, &rule6->dst.addr)) ||
 	    (rule6->src.plen &&
···
 {
 	return nla_total_size(16) /* dst */
 	       + nla_total_size(16) /* src */
-	       + nla_total_size(1); /* dscp */
+	       + nla_total_size(1) /* dscp */
+	       + nla_total_size(4) /* flowlabel */
+	       + nla_total_size(4); /* flowlabel mask */
 }
 
 static void fib6_rule_flush_cache(struct fib_rules_ops *ops)

net/ipv6/route.c

···
 	[RTA_SPORT]		= { .type = NLA_U16 },
 	[RTA_DPORT]		= { .type = NLA_U16 },
 	[RTA_NH_ID]		= { .type = NLA_U32 },
+	[RTA_FLOWLABEL]		= { .type = NLA_BE32 },
 };
 
 static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
···
 	if (rtm->rtm_tos) {
 		NL_SET_ERR_MSG(extack,
 			       "Invalid dsfield (tos): option not available for IPv6");
+		goto errout;
+	}
+
+	if (tb[RTA_FLOWLABEL]) {
+		NL_SET_ERR_MSG_ATTR(extack, tb[RTA_FLOWLABEL],
+				    "Flow label cannot be specified for this operation");
 		goto errout;
 	}
 
···
 		return -EINVAL;
 	}
 
+	if (tb[RTA_FLOWLABEL] &&
+	    (nla_get_be32(tb[RTA_FLOWLABEL]) & ~IPV6_FLOWLABEL_MASK)) {
+		NL_SET_ERR_MSG_ATTR(extack, tb[RTA_FLOWLABEL],
+				    "Invalid flow label");
+		return -EINVAL;
+	}
+
 	for (i = 0; i <= RTA_MAX; i++) {
 		if (!tb[i])
 			continue;
···
 		case RTA_SPORT:
 		case RTA_DPORT:
 		case RTA_IP_PROTO:
+		case RTA_FLOWLABEL:
 			break;
 		default:
 			NL_SET_ERR_MSG_MOD(extack, "Unsupported attribute in get route request");
···
 	struct sk_buff *skb;
 	struct rtmsg *rtm;
 	struct flowi6 fl6 = {};
+	__be32 flowlabel;
 	bool fibmatch;
 
 	err = inet6_rtm_valid_getroute_req(in_skb, nlh, tb, extack);
···
 
 	err = -EINVAL;
 	rtm = nlmsg_data(nlh);
-	fl6.flowlabel = ip6_make_flowinfo(rtm->rtm_tos, 0);
 	fibmatch = !!(rtm->rtm_flags & RTM_F_FIB_MATCH);
 
 	if (tb[RTA_SRC]) {
···
 		if (err)
 			goto errout;
 	}
+
+	flowlabel = nla_get_be32_default(tb[RTA_FLOWLABEL], 0);
+	fl6.flowlabel = ip6_make_flowinfo(rtm->rtm_tos, flowlabel);
 
 	if (iif) {
 		struct net_device *dev;

tools/testing/selftests/net/fib_rule_tests.sh

···
 			"$getnomatch" "iif dscp redirect to table" \
 			"iif dscp no redirect to table"
 	fi
+
+	fib_check_iproute_support "flowlabel" "flowlabel"
+	if [ $? -eq 0 ]; then
+		match="flowlabel 0xfffff"
+		getmatch="flowlabel 0xfffff"
+		getnomatch="flowlabel 0xf"
+		fib_rule6_test_match_n_redirect "$match" "$getmatch" \
+			"$getnomatch" "flowlabel redirect to table" \
+			"flowlabel no redirect to table"
+
+		match="flowlabel 0xfffff"
+		getmatch="from $SRC_IP6 iif $DEV flowlabel 0xfffff"
+		getnomatch="from $SRC_IP6 iif $DEV flowlabel 0xf"
+		fib_rule6_test_match_n_redirect "$match" "$getmatch" \
+			"$getnomatch" "iif flowlabel redirect to table" \
+			"iif flowlabel no redirect to table"
+
+		match="flowlabel 0x08000/0x08000"
+		getmatch="flowlabel 0xfffff"
+		getnomatch="flowlabel 0xf7fff"
+		fib_rule6_test_match_n_redirect "$match" "$getmatch" \
+			"$getnomatch" "flowlabel masked redirect to table" \
+			"flowlabel masked no redirect to table"
+
+		match="flowlabel 0x08000/0x08000"
+		getmatch="from $SRC_IP6 iif $DEV flowlabel 0xfffff"
+		getnomatch="from $SRC_IP6 iif $DEV flowlabel 0xf7fff"
+		fib_rule6_test_match_n_redirect "$match" "$getmatch" \
+			"$getnomatch" "iif flowlabel masked redirect to table" \
+			"iif flowlabel masked no redirect to table"
+	fi
 }
 
 fib_rule6_vrf_test()