Skip to contentSkip to conversation

bpf: Add helper to do FIB lookups

RFC Superseded David Ahern 3 participants 14 messages Apr 25, 2018 – Apr 27, 2018

Subsystems (9)

v1 of 3 Superseded Latest is v3 →

lore
Share & tools
lore
#0 lore raw

cover bpf: Add helper to do FIB lookups

Provide a helper for doing a FIB and neighbor lookups in the kernel tables from an XDP program. The helper provides a fastpath for forwarding packets. If the packet is a local delivery or for any reason is not a simple lookup and forward, the packet is expected to continue up the stack for full processing.

Patches 1-6 do some more refactoring to IPv6 with the end goal of extracting a FIB lookup function that aligns with fib_lookup for IPv4, basically returning a fib6_info without creating a dst based entry.

Patch 7 adds lookup functions to the ipv6 stub. These are needed since bpf is built into the kernel and ipv6 may not be built or loaded.

Patch 8 adds the bpf helper and 9 is a sample program.

David Ahern (9):
net/ipv6: Rename fib6_lookup to fib6_node_lookup net/ipv6: Rename rt6_multipath_select
net/ipv6: Extract table lookup from ip6_pol_route net/ipv6: Refactor fib6_rule_action
net/ipv6: Add fib6_lookup
net/ipv6: Update fib6 tracepoint to take fib6_info net/ipv6: Add fib lookup stubs for use in bpf helper
bpf: Provide helper to do lookups in kernel FIB table samples/bpf: Add examples of ipv4 and ipv6 forwarding in XDP

 include/net/addrconf.h                    |  14 ++
 include/net/ip6_fib.h                     |  21 ++-
 include/trace/events/fib6.h               |  14 +-
 include/uapi/linux/bpf.h                  |  68 ++++++++-
 net/core/filter.c                         | 233 ++++++++++++++++++++++++++++++
 net/ipv6/addrconf_core.c                  |  33 ++++-
 net/ipv6/af_inet6.c                       |   6 +-
 net/ipv6/fib6_rules.c                     | 135 ++++++++++++++---
 net/ipv6/ip6_fib.c                        |  12 +-
 net/ipv6/route.c                          |  76 +++++-----
 samples/bpf/Makefile                      |   4 +
 samples/bpf/xdp_fwd_kern.c                | 110 ++++++++++++++
 samples/bpf/xdp_fwd_user.c                | 136 +++++++++++++++++
 tools/testing/selftests/bpf/bpf_helpers.h |   3 +
 14 files changed, 794 insertions(+), 71 deletions(-)
 create mode 100644 samples/bpf/xdp_fwd_kern.c
 create mode 100644 samples/bpf/xdp_fwd_user.c
Signature · 1 line
2.11.0
#1 lore raw

RFC 1/9 net/ipv6: Rename fib6_lookup to fib6_node_lookup

Rename fib6_lookup to fib6_node_lookup to better reflect what it returns. The fib6_lookup name will be used in a later patch for an IPv6 equivalent to IPv4's fib_lookup.

---
 include/net/ip6_fib.h | 6 +++---
 net/ipv6/ip6_fib.c    | 5 +++--
 net/ipv6/route.c      | 8 ++++----
 3 files changed, 10 insertions(+), 9 deletions(-)
include/net/ip6_fib.h +3 -3
index 1af450d4e923..5a16630179cb 100644
@@ -376,9 +376,9 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
 				   const struct sk_buff *skb,
 				   int flags, pol_lookup_t lookup);
 
-struct fib6_node *fib6_lookup(struct fib6_node *root,
-			      const struct in6_addr *daddr,
-			      const struct in6_addr *saddr);
+struct fib6_node *fib6_node_lookup(struct fib6_node *root,
+				   const struct in6_addr *daddr,
+				   const struct in6_addr *saddr);
 
 struct fib6_node *fib6_locate(struct fib6_node *root,
 			      const struct in6_addr *daddr, int dst_len,
net/ipv6/ip6_fib.c +3 -2
index 6421c893466e..f6442d6c5603 100644
@@ -1422,8 +1422,9 @@ static struct fib6_node *fib6_lookup_1(struct fib6_node *root,
 
 /* called with rcu_read_lock() held
  */
-struct fib6_node *fib6_lookup(struct fib6_node *root, const struct in6_addr *daddr,
-			      const struct in6_addr *saddr)
+struct fib6_node *fib6_node_lookup(struct fib6_node *root,
+				   const struct in6_addr *daddr,
+				   const struct in6_addr *saddr)
 {
 	struct fib6_node *fn;
 	struct lookup_args args[] = {
net/ipv6/route.c +4 -4
index 0407bbc5a028..e4082c612fcc 100644
@@ -1006,7 +1006,7 @@ static struct fib6_node* fib6_backtrack(struct fib6_node *fn,
 		pn = rcu_dereference(fn->parent);
 		sn = FIB6_SUBTREE(pn);
 		if (sn && sn != fn)
-			fn = fib6_lookup(sn, NULL, saddr);
+			fn = fib6_node_lookup(sn, NULL, saddr);
 		else
 			fn = pn;
 		if (fn->fn_flags & RTN_RTINFO)
@@ -1059,7 +1059,7 @@ static struct rt6_info *ip6_pol_route_lookup(struct net *net,
 		flags &= ~RT6_LOOKUP_F_IFACE;
 
 	rcu_read_lock();
-	fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
+	fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
 restart:
 	f6i = rcu_dereference(fn->leaf);
 	if (!f6i) {
@@ -1814,7 +1814,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
 
 	rcu_read_lock();
 
-	fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
+	fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
 	saved_fn = fn;
 
 	if (fl6->flowi6_flags & FLOWI_FLAG_SKIP_NH_OIF)
@@ -2417,7 +2417,7 @@ static struct rt6_info *__ip6_route_redirect(struct net *net,
 	 */
 
 	rcu_read_lock();
-	fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
+	fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
 restart:
 	for_each_fib6_node_rt_rcu(fn) {
 		if (rt->fib6_nh.nh_flags & RTNH_F_DEAD)
Signature · 1 line
2.11.0
#2 lore raw

RFC 2/9 net/ipv6: Rename rt6_multipath_select

In reply to David Ahern

Rename rt6_multipath_select to fib6_multipath_select and export it. A later patch wants access to it similar to IPv4's fib_select_path.

---
 include/net/ip6_fib.h |  5 +++++
 net/ipv6/route.c      | 17 +++++++++--------
 2 files changed, 14 insertions(+), 8 deletions(-)
include/net/ip6_fib.h +5 -0
index 5a16630179cb..80d76d8dc683 100644
@@ -376,6 +376,11 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
 				   const struct sk_buff *skb,
 				   int flags, pol_lookup_t lookup);
 
+struct fib6_info *fib6_multipath_select(const struct net *net,
+					struct fib6_info *match,
+					struct flowi6 *fl6, int oif,
+					const struct sk_buff *skb, int strict);
+
 struct fib6_node *fib6_node_lookup(struct fib6_node *root,
 				   const struct in6_addr *daddr,
 				   const struct in6_addr *saddr);
net/ipv6/route.c +9 -8
index e4082c612fcc..72c784add7a1 100644
@@ -419,11 +419,11 @@ static bool rt6_check_expired(const struct rt6_info *rt)
 	return false;
 }
 
-static struct fib6_info *rt6_multipath_select(const struct net *net,
-					      struct fib6_info *match,
-					     struct flowi6 *fl6, int oif,
-					     const struct sk_buff *skb,
-					     int strict)
+struct fib6_info *fib6_multipath_select(const struct net *net,
+					struct fib6_info *match,
+					struct flowi6 *fl6, int oif,
+					const struct sk_buff *skb,
+					int strict)
 {
 	struct fib6_info *sibling, *next_sibling;
 
@@ -1068,8 +1068,9 @@ static struct rt6_info *ip6_pol_route_lookup(struct net *net,
 		f6i = rt6_device_match(net, f6i, &fl6->saddr,
 				      fl6->flowi6_oif, flags);
 		if (f6i->fib6_nsiblings && fl6->flowi6_oif == 0)
-			f6i = rt6_multipath_select(net, f6i, fl6,
-						   fl6->flowi6_oif, skb, flags);
+			f6i = fib6_multipath_select(net, f6i, fl6,
+						    fl6->flowi6_oif, skb,
+						    flags);
 	}
 	if (f6i == net->ipv6.fib6_null_entry) {
 		fn = fib6_backtrack(fn, &fl6->saddr);
@@ -1823,7 +1824,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
 redo_rt6_select:
 	f6i = rt6_select(net, fn, oif, strict);
 	if (f6i->fib6_nsiblings)
-		f6i = rt6_multipath_select(net, f6i, fl6, oif, skb, strict);
+		f6i = fib6_multipath_select(net, f6i, fl6, oif, skb, strict);
 	if (f6i == net->ipv6.fib6_null_entry) {
 		fn = fib6_backtrack(fn, &fl6->saddr);
 		if (fn)
Signature · 1 line
2.11.0
#3 lore raw

RFC 3/9 net/ipv6: Extract table lookup from ip6_pol_route

In reply to David Ahern

ip6_pol_route is used for ingress and egress FIB lookups. Refactor it moving the table lookup into a separate fib6_table_lookup that can be invoked separately and export the new function.

ip6_pol_route now calls fib6_table_lookup and uses the result to generate a dst based rt6_info.

---
 include/net/ip6_fib.h |  4 ++++
 net/ipv6/route.c      | 39 +++++++++++++++++++++++++--------------
 2 files changed, 29 insertions(+), 14 deletions(-)
include/net/ip6_fib.h +4 -0
index 80d76d8dc683..4f7b8f59ea6d 100644
@@ -376,6 +376,10 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
 				   const struct sk_buff *skb,
 				   int flags, pol_lookup_t lookup);
 
+/* called with rcu lock held; caller needs to select path */
+struct fib6_info *fib6_table_lookup(struct net *net, struct fib6_table *table,
+				    int oif, struct flowi6 *fl6, int strict);
+
 struct fib6_info *fib6_multipath_select(const struct net *net,
 					struct fib6_info *match,
 					struct flowi6 *fl6, int oif,
net/ipv6/route.c +25 -14
index 72c784add7a1..353645ed3d2c 100644
@@ -1799,21 +1799,12 @@ void rt6_age_exceptions(struct fib6_info *rt,
 	rcu_read_unlock_bh();
 }
 
-struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
-			       int oif, struct flowi6 *fl6,
-			       const struct sk_buff *skb, int flags)
+/* must be called with rcu lock held */
+struct fib6_info *fib6_table_lookup(struct net *net, struct fib6_table *table,
+				    int oif, struct flowi6 *fl6, int strict)
 {
 	struct fib6_node *fn, *saved_fn;
 	struct fib6_info *f6i;
-	struct rt6_info *rt;
-	int strict = 0;
-
-	strict |= flags & RT6_LOOKUP_F_IFACE;
-	strict |= flags & RT6_LOOKUP_F_IGNORE_LINKSTATE;
-	if (net->ipv6.devconf_all->forwarding == 0)
-		strict |= RT6_LOOKUP_F_REACHABLE;
-
-	rcu_read_lock();
 
 	fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
 	saved_fn = fn;
@@ -1823,8 +1814,6 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
 
 redo_rt6_select:
 	f6i = rt6_select(net, fn, oif, strict);
-	if (f6i->fib6_nsiblings)
-		f6i = fib6_multipath_select(net, f6i, fl6, oif, skb, strict);
 	if (f6i == net->ipv6.fib6_null_entry) {
 		fn = fib6_backtrack(fn, &fl6->saddr);
 		if (fn)
@@ -1837,6 +1826,28 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
 		}
 	}
 
+	return f6i;
+}
+
+struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
+			       int oif, struct flowi6 *fl6,
+			       const struct sk_buff *skb, int flags)
+{
+	struct fib6_info *f6i;
+	struct rt6_info *rt;
+	int strict = 0;
+
+	strict |= flags & RT6_LOOKUP_F_IFACE;
+	strict |= flags & RT6_LOOKUP_F_IGNORE_LINKSTATE;
+	if (net->ipv6.devconf_all->forwarding == 0)
+		strict |= RT6_LOOKUP_F_REACHABLE;
+
+	rcu_read_lock();
+
+	f6i = fib6_table_lookup(net, table, oif, fl6, strict);
+	if (f6i->fib6_nsiblings)
+		f6i = fib6_multipath_select(net, f6i, fl6, oif, skb, strict);
+
 	if (f6i == net->ipv6.fib6_null_entry) {
 		rt = net->ipv6.ip6_null_entry;
 		rcu_read_unlock();
Signature · 1 line
2.11.0
#4 lore raw

RFC 4/9 net/ipv6: Refactor fib6_rule_action

In reply to David Ahern

Move source address lookup from fib6_rule_action to a helper. It will be used in a later patch by a second variant for fib6_rule_action.

---
 net/ipv6/fib6_rules.c | 52 ++++++++++++++++++++++++++++++---------------------
 1 file changed, 31 insertions(+), 21 deletions(-)
net/ipv6/fib6_rules.c +31 -21
index df113c7b5fc8..d9c0bfd304f0 100644
@@ -96,6 +96,31 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
 	return &net->ipv6.ip6_null_entry->dst;
 }
 
+static int fib6_rule_saddr(struct net *net, struct fib_rule *rule, int flags,
+			   struct flowi6 *flp6, const struct net_device *dev)
+{
+	struct fib6_rule *r = (struct fib6_rule *)rule;
+
+	/* If we need to find a source address for this traffic,
+	 * we check the result if it meets requirement of the rule.
+	 */
+	if ((rule->flags & FIB_RULE_FIND_SADDR) &&
+	    r->src.plen && !(flags & RT6_LOOKUP_F_HAS_SADDR)) {
+		struct in6_addr saddr;
+
+		if (ipv6_dev_get_saddr(net, dev, &flp6->daddr,
+				       rt6_flags2srcprefs(flags), &saddr))
+			return -EAGAIN;
+
+		if (!ipv6_prefix_equal(&saddr, &r->src.addr, r->src.plen))
+			return -EAGAIN;
+
+		flp6->saddr = saddr;
+	}
+
+	return 0;
+}
+
 static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
 			    int flags, struct fib_lookup_arg *arg)
 {
@@ -134,27 +159,12 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
 
 	rt = lookup(net, table, flp6, arg->lookup_data, flags);
 	if (rt != net->ipv6.ip6_null_entry) {
-		struct fib6_rule *r = (struct fib6_rule *)rule;
-
-		/*
-		 * If we need to find a source address for this traffic,
-		 * we check the result if it meets requirement of the rule.
-		 */
-		if ((rule->flags & FIB_RULE_FIND_SADDR) &&
-		    r->src.plen && !(flags & RT6_LOOKUP_F_HAS_SADDR)) {
-			struct in6_addr saddr;
-
-			if (ipv6_dev_get_saddr(net,
-					       ip6_dst_idev(&rt->dst)->dev,
-					       &flp6->daddr,
-					       rt6_flags2srcprefs(flags),
-					       &saddr))
-				goto again;
-			if (!ipv6_prefix_equal(&saddr, &r->src.addr,
-					       r->src.plen))
-				goto again;
-			flp6->saddr = saddr;
-		}
+		err = fib6_rule_saddr(net, rule, flags, flp6,
+				      ip6_dst_idev(&rt->dst)->dev);
+
+		if (err == -EAGAIN)
+			goto again;
+
 		err = rt->dst.error;
 		if (err != -EAGAIN)
 			goto out;
Signature · 1 line
2.11.0
#5 lore raw

RFC 5/9 net/ipv6: Add fib6_lookup

In reply to David Ahern

Add IPv6 equivalent to fib_lookup. Does a fib lookup, including rules, but returns a FIB entry, fib6_info, rather than a dst based rt6_info. fib6_lookup is on the order of 40% faster than any of the dst based lookup methods without custom rules and 25% faster with custom rules.

Since the lookup function has a completely different signature, fib6_rule_action is split into 2 paths: the existing one is renamed __fib6_rule_action and a new one for the fib6_info path is added. fib6_rule_action decides which to call based on the lookup_ptr. If it is fib6_table_lookup then the new path is taken.

Caller must hold rcu lock as no reference is taken on the returned fib entry.

---
 include/net/ip6_fib.h |  6 ++++
 net/ipv6/fib6_rules.c | 83 +++++++++++++++++++++++++++++++++++++++++++++++++--
 net/ipv6/ip6_fib.c    |  7 +++++
 3 files changed, 94 insertions(+), 2 deletions(-)
include/net/ip6_fib.h +6 -0
index 4f7b8f59ea6d..d920dd00139b 100644
@@ -376,6 +376,12 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
 				   const struct sk_buff *skb,
 				   int flags, pol_lookup_t lookup);
 
+/* called with rcu lock held; can return error pointer
+ * caller needs to select path
+ */
+struct fib6_info *fib6_lookup(struct net *net, int oif, struct flowi6 *fl6,
+			      int flags);
+
 /* called with rcu lock held; caller needs to select path */
 struct fib6_info *fib6_table_lookup(struct net *net, struct fib6_table *table,
 				    int oif, struct flowi6 *fl6, int strict);
net/ipv6/fib6_rules.c +81 -2

101 lines not on this page · raw message

net/ipv6/ip6_fib.c +7 -0
index f6442d6c5603..422ce5ca7b33 100644
@@ -354,6 +354,13 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
 	return &rt->dst;
 }
 
+/* called with rcu lock held; no reference taken on fib6_info */
+struct fib6_info *fib6_lookup(struct net *net, int oif, struct flowi6 *fl6,
+			      int flags)
+{
+	return fib6_table_lookup(net, net->ipv6.fib6_main_tbl, oif, fl6, flags);
+}
+
 static void __net_init fib6_tables_init(struct net *net)
 {
 	fib6_link_table(net, net->ipv6.fib6_main_tbl);
Signature · 1 line
2.11.0
#6 lore raw

RFC 6/9 net/ipv6: Update fib6 tracepoint to take fib6_info

In reply to David Ahern

Similar to IPv4, IPv6 should use the FIB lookup result in the tracepoint.

---
 include/trace/events/fib6.h | 14 +++++++-------
 net/ipv6/route.c            | 14 ++++++--------
 2 files changed, 13 insertions(+), 15 deletions(-)
include/trace/events/fib6.h +7 -7
index 7e8d48a81b91..1b8d951e3c12 100644
@@ -12,10 +12,10 @@
 
 TRACE_EVENT(fib6_table_lookup,
 
-	TP_PROTO(const struct net *net, const struct rt6_info *rt,
+	TP_PROTO(const struct net *net, const struct fib6_info *f6i,
 		 struct fib6_table *table, const struct flowi6 *flp),
 
-	TP_ARGS(net, rt, table, flp),
+	TP_ARGS(net, f6i, table, flp),
 
 	TP_STRUCT__entry(
 		__field(	u32,	tb_id		)
@@ -48,20 +48,20 @@ TRACE_EVENT(fib6_table_lookup,
 		in6 = (struct in6_addr *)__entry->dst;
 		*in6 = flp->daddr;
 
-		if (rt->rt6i_idev) {
-			__assign_str(name, rt->rt6i_idev->dev->name);
+		if (f6i->fib6_nh.nh_dev) {
+			__assign_str(name, f6i->fib6_nh.nh_dev);
 		} else {
 			__assign_str(name, "");
 		}
-		if (rt == net->ipv6.ip6_null_entry) {
+		if (f6i == net->ipv6.fib6_null_entry) {
 			struct in6_addr in6_zero = {};
 
 			in6 = (struct in6_addr *)__entry->gw;
 			*in6 = in6_zero;
 
-		} else if (rt) {
+		} else if (f6i) {
 			in6 = (struct in6_addr *)__entry->gw;
-			*in6 = rt->rt6i_gateway;
+			*in6 = f6i->fib6_nh.nh_gw;
 		}
 	),
 
net/ipv6/route.c +6 -8
index 353645ed3d2c..e4163d19d905 100644
@@ -1078,6 +1078,8 @@ static struct rt6_info *ip6_pol_route_lookup(struct net *net,
 			goto restart;
 	}
 
+	trace_fib6_table_lookup(net, f6i, table, fl6);
+
 	/* Search through exception table */
 	rt = rt6_find_cached_rt(f6i, &fl6->daddr, &fl6->saddr);
 	if (rt) {
@@ -1096,8 +1098,6 @@ static struct rt6_info *ip6_pol_route_lookup(struct net *net,
 
 	rcu_read_unlock();
 
-	trace_fib6_table_lookup(net, rt, table, fl6);
-
 	return rt;
 }
 
@@ -1826,6 +1826,8 @@ struct fib6_info *fib6_table_lookup(struct net *net, struct fib6_table *table,
 		}
 	}
 
+	trace_fib6_table_lookup(net, f6i, table, fl6);
+
 	return f6i;
 }
 
@@ -1852,7 +1854,6 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
 		rt = net->ipv6.ip6_null_entry;
 		rcu_read_unlock();
 		dst_hold(&rt->dst);
-		trace_fib6_table_lookup(net, rt, table, fl6);
 		return rt;
 	}
 
@@ -1863,7 +1864,6 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
 			dst_use_noref(&rt->dst, jiffies);
 
 		rcu_read_unlock();
-		trace_fib6_table_lookup(net, rt, table, fl6);
 		return rt;
 	} else if (unlikely((fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH) &&
 			    !(f6i->fib6_flags & RTF_GATEWAY))) {
@@ -1889,9 +1889,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
 			dst_hold(&uncached_rt->dst);
 		}
 
-		trace_fib6_table_lookup(net, uncached_rt, table, fl6);
 		return uncached_rt;
-
 	} else {
 		/* Get a percpu copy */
 
@@ -1905,7 +1903,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
 
 		local_bh_enable();
 		rcu_read_unlock();
-		trace_fib6_table_lookup(net, pcpu_rt, table, fl6);
+
 		return pcpu_rt;
 	}
 }
@@ -2483,7 +2481,7 @@ static struct rt6_info *__ip6_route_redirect(struct net *net,
 
 	rcu_read_unlock();
 
-	trace_fib6_table_lookup(net, ret, table, fl6);
+	trace_fib6_table_lookup(net, rt, table, fl6);
 	return ret;
 };
 
Signature · 1 line
2.11.0
#7 lore raw

RFC 7/9 net/ipv6: Add fib lookup stubs for use in bpf helper

In reply to David Ahern

Add stubs to retrieve a handle to an IPv6 FIB table, fib6_get_table, a stub to do a lookup in a specific table, fib6_table_lookup, and a stub for a full route lookup.

The stubs are needed for core bpf code to handle the case when the IPv6 module is not builtin.

---
 include/net/addrconf.h   | 14 ++++++++++++++
 net/ipv6/addrconf_core.c | 33 ++++++++++++++++++++++++++++++++-
 net/ipv6/af_inet6.c      |  6 +++++-
 3 files changed, 51 insertions(+), 2 deletions(-)
include/net/addrconf.h +14 -0
index 8312cc25a3af..ff766ab207e0 100644
@@ -223,6 +223,20 @@ struct ipv6_stub {
 				 const struct in6_addr *addr);
 	int (*ipv6_dst_lookup)(struct net *net, struct sock *sk,
 			       struct dst_entry **dst, struct flowi6 *fl6);
+
+	struct fib6_table *(*fib6_get_table)(struct net *net, u32 id);
+	struct fib6_info *(*fib6_lookup)(struct net *net, int oif,
+					 struct flowi6 *fl6, int flags);
+	struct fib6_info *(*fib6_table_lookup)(struct net *net,
+					      struct fib6_table *table,
+					      int oif, struct flowi6 *fl6,
+					      int flags);
+	struct fib6_info *(*fib6_multipath_select)(const struct net *net,
+						   struct fib6_info *f6i,
+						   struct flowi6 *fl6, int oif,
+						   const struct sk_buff *skb,
+						   int strict);
+
 	void (*udpv6_encap_enable)(void);
 	void (*ndisc_send_na)(struct net_device *dev, const struct in6_addr *daddr,
 			      const struct in6_addr *solicited_addr,
net/ipv6/addrconf_core.c +32 -1
index 32b564dfd02a..2fe754fd4f5e 100644
@@ -134,8 +134,39 @@ static int eafnosupport_ipv6_dst_lookup(struct net *net, struct sock *u1,
 	return -EAFNOSUPPORT;
 }
 
+static struct fib6_table *eafnosupport_fib6_get_table(struct net *net, u32 id)
+{
+	return NULL;
+}
+
+static struct fib6_info *
+eafnosupport_fib6_table_lookup(struct net *net, struct fib6_table *table,
+			       int oif, struct flowi6 *fl6, int flags)
+{
+	return NULL;
+}
+
+static struct fib6_info *
+eafnosupport_fib6_lookup(struct net *net, int oif, struct flowi6 *fl6,
+			 int flags)
+{
+	return NULL;
+}
+
+static struct fib6_info *
+eafnosupport_fib6_multipath_select(const struct net *net, struct fib6_info *f6i,
+				   struct flowi6 *fl6, int oif,
+				   const struct sk_buff *skb, int strict)
+{
+	return f6i;
+}
+
 const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) {
-	.ipv6_dst_lookup = eafnosupport_ipv6_dst_lookup,
+	.ipv6_dst_lookup   = eafnosupport_ipv6_dst_lookup,
+	.fib6_get_table    = eafnosupport_fib6_get_table,
+	.fib6_table_lookup = eafnosupport_fib6_table_lookup,
+	.fib6_lookup       = eafnosupport_fib6_lookup,
+	.fib6_multipath_select = eafnosupport_fib6_multipath_select,
 };
 EXPORT_SYMBOL_GPL(ipv6_stub);
 
net/ipv6/af_inet6.c +5 -1
index 36d622c477b1..c0e8255d50bb 100644
@@ -887,7 +887,11 @@ static struct pernet_operations inet6_net_ops = {
 static const struct ipv6_stub ipv6_stub_impl = {
 	.ipv6_sock_mc_join = ipv6_sock_mc_join,
 	.ipv6_sock_mc_drop = ipv6_sock_mc_drop,
-	.ipv6_dst_lookup = ip6_dst_lookup,
+	.ipv6_dst_lookup   = ip6_dst_lookup,
+	.fib6_get_table	   = fib6_get_table,
+	.fib6_table_lookup = fib6_table_lookup,
+	.fib6_lookup       = fib6_lookup,
+	.fib6_multipath_select = fib6_multipath_select,
 	.udpv6_encap_enable = udpv6_encap_enable,
 	.ndisc_send_na = ndisc_send_na,
 	.nd_tbl	= &nd_tbl,
Signature · 1 line
2.11.0
#8 lore raw

RFC 8/9 bpf: Provide helper to do lookups in kernel FIB table

In reply to David Ahern

Provide a helper for doing a FIB and neighbor lookup in the kernel tables from an XDP program. The helper provides a fastpath for forwarding packets. If the packet is a local delivery or for any reason is not a simple lookup and forward, the packet continues up the stack.

If it is to be forwarded, the forwarding can be done directly if the neighbor is already known. If the neighbor does not exist, the first few packets go up the stack for neighbor resolution. Once resolved, the xdp program provides the fast path.

On successful lookup the nexthop dmac, current device smac and egress device index are returned.

The API supports IPv4, IPv6 and MPLS protocols, but only IPv4 and IPv6 are implemented in this patch. The API includes layer 4 parameters if the XDP program chooses to do deep packet inspection to allow compare against ACLs implemented as FIB rules.

Header rewrite is left to the XDP program.

The lookup takes 2 flags:
- BPF_FIB_LOOKUP_DIRECT to do a lookup that bypasses FIB rules and goes straight to the table associated with the device (expert setting for those looking to maximize throughput)

- BPF_FIB_LOOKUP_OUTPUT to do a lookup from the egress perspective. Default is an ingress lookup.

Initial performance numbers collected by Jesper, forwarded packets/sec:

Full stack XDP FIB lookup XDP Direct lookup

IPv4   1,947,969       7,074,156          7,415,333
IPv6   1,728,000       6,165,504          7,262,720
---
 include/uapi/linux/bpf.h |  68 +++++++++++++-
 net/core/filter.c        | 233 +++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 300 insertions(+), 1 deletion(-)
include/uapi/linux/bpf.h +67 -1
index e6679393b687..82601c132b9f 100644
@@ -10,6 +10,8 @@
 
 #include <linux/types.h>
 #include <linux/bpf_common.h>
+#include <linux/if_ether.h>
+#include <linux/in6.h>
 
 /* Extended instruction set based on top of classic BPF */
 
@@ -783,6 +785,17 @@ union bpf_attr {
  *     @size: size of 'struct bpf_xfrm_state'
  *     @flags: room for future extensions
  *     Return: 0 on success or negative error
+ *
+ * int bpf_fib_lookup(ctx, params, plen, flags)
+ *     Do a FIB lookup based on given parameters
+ *     @ctx:     pointer to context of type xdp_md
+ *     @params:  pointer to bpf_fib_lookup
+ *     @plen:    size of params argument
+ *     @flags:   u32 bitmask of BPF_FIB_LOOKUP_* flags
+ *     Return: egress device index if packet is to be forwarded,
+ *             0 for local delivery (anything that needs to be handled
+ *             by the full stack), or negative on error.
+ *             If index is > 0, output data in bpf_fib_lookup is set
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -851,7 +864,9 @@ union bpf_attr {
 	FN(msg_pull_data),		\
 	FN(bind),			\
 	FN(xdp_adjust_tail),		\
-	FN(skb_get_xfrm_state),
+	FN(skb_get_xfrm_state),		\
+	FN(fib_lookup),			\
+
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -1255,4 +1270,55 @@ struct bpf_raw_tracepoint_args {
 	__u64 args[0];
 };
 
+/* DIRECT:  Skip the FIB rules and go to FIB table associated with device
+ * OUTPUT:  Do lookup from egress perspective; default is ingress
+ */
+#define BPF_FIB_LOOKUP_DIRECT  BIT(0)
+#define BPF_FIB_LOOKUP_OUTPUT  BIT(1)
+
+struct bpf_fib_lookup {
+	/* input */
+	__u8	family;   /* network family, AF_INET, AF_INET6, AF_MPLS */
+
+	/* set if lookup is to consider L4 data - e.g., FIB rules */
+	__u8	l4_protocol;
+	__be16	sport;
+	__be16	dport;
+
+	/* total length of packet from network header - used for MTU check */
+	__u16	tot_len;
+	__u32	ifindex;  /* L3 device index for lookup */
+
+	union {
+		/* inputs to lookup */
+		__u8	tos;		/* AF_INET  */
+		__be32	flowlabel;	/* AF_INET6 */
+
+		/* output: metric of fib result */
+		__u32 rt_metric;
+	};
+
+	union {
+		__be32		mpls_in;
+		__be32		ipv4_src;
+		struct in6_addr	ipv6_src;
+	};
+
+	/* input to bpf_fib_lookup, *dst is destination address.
+	 * output: bpf_fib_lookup sets to gateway address
+	 */
+	union {
+		/* return for MPLS lookups */
+		__be32		mpls_out[4];  /* support up to 4 labels */
+		__be32		ipv4_dst;
+		struct in6_addr	ipv6_dst;
+	};
+
+	/* output */
+	__be16	h_vlan_proto;
+	__be16	h_vlan_TCI;
+	__u8	smac[ETH_ALEN];
+	__u8	dmac[ETH_ALEN];
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */
net/core/filter.c +233 -0

257 lines not on this page · raw message

Signature · 1 line
2.11.0
maintainer
#9 lore raw

Re: [RFC bpf-next 8/9] bpf: Provide helper to do lookups in kernel FIB table

Quoted 55 lines · David Ahern

Provide a helper for doing a FIB and neighbor lookup in the kernel tables from an XDP program. The helper provides a fastpath for forwarding packets. If the packet is a local delivery or for any reason is not a simple lookup and forward, the packet continues up the stack.

If it is to be forwarded, the forwarding can be done directly if the neighbor is already known. If the neighbor does not exist, the first few packets go up the stack for neighbor resolution. Once resolved, the xdp program provides the fast path.

On successful lookup the nexthop dmac, current device smac and egress device index are returned.

The API supports IPv4, IPv6 and MPLS protocols, but only IPv4 and IPv6 are implemented in this patch. The API includes layer 4 parameters if the XDP program chooses to do deep packet inspection to allow compare against ACLs implemented as FIB rules.

Header rewrite is left to the XDP program.

The lookup takes 2 flags:
- BPF_FIB_LOOKUP_DIRECT to do a lookup that bypasses FIB rules and goes straight to the table associated with the device (expert setting for those looking to maximize throughput)

- BPF_FIB_LOOKUP_OUTPUT to do a lookup from the egress perspective. Default is an ingress lookup.

Initial performance numbers collected by Jesper, forwarded packets/sec:

Full stack XDP FIB lookup XDP Direct lookup

IPv4   1,947,969       7,074,156          7,415,333
IPv6   1,728,000       6,165,504          7,262,720
---
 include/uapi/linux/bpf.h |  68 +++++++++++++-
 net/core/filter.c        | 233 +++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 300 insertions(+), 1 deletion(-)
include/uapi/linux/bpf.h +2 -0
index e6679393b687..82601c132b9f 100644
@@ -10,6 +10,8 @@
 
 #include <linux/types.h>
 #include <linux/bpf_common.h>
+#include <linux/if_ether.h>
+#include <linux/in6.h>
 
 /* Extended instruction set based on top of classic BPF */
 

include/uapi/linux/bpf.h union bpf_attr { · line 791

Quoted 7 lines
include/uapi/linux/bpf.h +4 -0
@@ -783,6 +785,17 @@ union bpf_attr {
  *     @size: size of 'struct bpf_xfrm_state'
  *     @flags: room for future extensions
  *     Return: 0 on success or negative error
+ *
+ * int bpf_fib_lookup(ctx, params, plen, flags)
+ *     Do a FIB lookup based on given parameters
+ *     @ctx:     pointer to context of type xdp_md

Nit: would just say pointer to context here since used with xdp/skb

Quoted 11 lines
include/uapi/linux/bpf.h +7 -0
+ *     @params:  pointer to bpf_fib_lookup
+ *     @plen:    size of params argument
+ *     @flags:   u32 bitmask of BPF_FIB_LOOKUP_* flags
+ *     Return: egress device index if packet is to be forwarded,
+ *             0 for local delivery (anything that needs to be handled
+ *             by the full stack), or negative on error.
+ *             If index is > 0, output data in bpf_fib_lookup is set
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\

include/uapi/linux/bpf.h union bpf_attr { · line 870

Quoted 8 lines
include/uapi/linux/bpf.h +3 -1
@@ -851,7 +864,9 @@ union bpf_attr {
 	FN(msg_pull_data),		\
 	FN(bind),			\
 	FN(xdp_adjust_tail),		\
-	FN(skb_get_xfrm_state),
+	FN(skb_get_xfrm_state),		\
+	FN(fib_lookup),			\
+
 

Nit: trailing '\' resp. double newline

Quoted 2 lines
include/uapi/linux/bpf.h +0 -0
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call

[...]

Quoted 25 lines
net/core/filter.c +10 -0
index 8e45c6c7ab08..37602b2fb94a 100644
@@ -59,6 +59,10 @@
 #include <net/tcp.h>
 #include <net/xfrm.h>
 #include <linux/bpf_trace.h>
+#include <linux/inetdevice.h>
+#include <net/ip_fib.h>
+#include <net/flow.h>
+#include <net/arp.h>
 
 /**
  *	sk_filter_trim_cap - run a packet through a socket filter
@@ -3787,6 +3791,231 @@ static const struct bpf_func_proto bpf_skb_get_xfrm_state_proto = {
 };
 #endif
 
+#if IS_ENABLED(CONFIG_INET) || IS_ENABLED(CONFIG_IPV6)
+static int bpf_fib_set_fwd_params(struct bpf_fib_lookup *params,
+				  const struct neighbour *neigh,
+				  const struct net_device *dev)
+{
+	memcpy(params->dmac, neigh->ha, ETH_ALEN);

net/core/filter.c static const struct bpf_func_proto bpf_skb_get_xfrm_state_proto = { · line 3809

Quoted 10 lines
net/core/filter.c +10 -0
+	memcpy(params->smac, dev->dev_addr, ETH_ALEN);
+	params->h_vlan_TCI = 0;
+	params->h_vlan_proto = 0;
+
+	return dev->ifindex;
+}
+#endif
+
+#if IS_ENABLED(CONFIG_INET)
+static int bpf_ipv4_fib_lookup(struct xdp_buff *ctx,

Instead of passing xdp_buff here, just pass the netdev pointer. More below why it's needed.

Quoted 79 lines
net/core/filter.c +79 -0
+			       struct bpf_fib_lookup *params, u32 flags)
+{
+	struct net *net = dev_net(ctx->rxq->dev);
+	struct in_device *in_dev;
+	struct neighbour *neigh;
+	struct net_device *dev;
+	struct fib_result res;
+	struct fib_nh *nh;
+	struct flowi4 fl4;
+	int err;
+
+	dev = dev_get_by_index_rcu(net, params->ifindex);
+	if (unlikely(!dev))
+		return -ENODEV;
+
+	/* verify forwarding is enabled on this interface */
+	in_dev = __in_dev_get_rcu(dev);
+	if (unlikely(!in_dev || !IN_DEV_FORWARD(in_dev)))
+		return 0;
+
+	if (flags & BPF_FIB_LOOKUP_OUTPUT) {
+		fl4.flowi4_iif = 1;
+		fl4.flowi4_oif = params->ifindex;
+	} else {
+		fl4.flowi4_iif = params->ifindex;
+		fl4.flowi4_oif = 0;
+	}
+	fl4.flowi4_tos = params->tos & IPTOS_RT_MASK;
+	fl4.flowi4_scope = RT_SCOPE_UNIVERSE;
+	fl4.flowi4_flags = 0;
+
+	fl4.flowi4_proto = params->l4_protocol;
+	fl4.daddr = params->ipv4_dst;
+	fl4.saddr = params->ipv4_src;
+	fl4.fl4_sport = params->sport;
+	fl4.fl4_dport = params->dport;
+
+	if (flags & BPF_FIB_LOOKUP_DIRECT) {
+		u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN;
+		struct fib_table *tb;
+
+		tb = fib_get_table(net, tbid);
+		if (unlikely(!tb))
+			return 0;
+
+		err = fib_table_lookup(tb, &fl4, &res, FIB_LOOKUP_NOREF);
+	} else {
+		fl4.flowi4_mark = 0;
+		fl4.flowi4_secid = 0;
+		fl4.flowi4_tun_key.tun_id = 0;
+		fl4.flowi4_uid = sock_net_uid(net, NULL);
+
+		err = fib_lookup(net, &fl4, &res, FIB_LOOKUP_NOREF);
+	}
+
+	if (err || res.type != RTN_UNICAST)
+		return 0;
+
+	if (res.fi->fib_nhs > 1)
+		fib_select_path(net, &res, &fl4, NULL);
+
+	nh = &res.fi->fib_nh[res.nh_sel];
+
+	/* do not handle lwt encaps right now */
+	if (nh->nh_lwtstate)
+		return 0;
+
+	dev = nh->nh_dev;
+	if (unlikely(!dev))
+		return 0;
+
+	if (nh->nh_gw)
+		params->ipv4_dst = nh->nh_gw;
+
+	params->rt_metric = res.fi->fib_priority;
+
+	/* xdp and cls_bpf programs are run in RCU-bh so
+	 * rcu_read_lock_bh is not needed here
+	 */

net/core/filter.c static const struct bpf_func_proto bpf_skb_get_xfrm_state_proto = { · line 3898

Quoted 10 lines
net/core/filter.c +10 -0
+	neigh = __ipv4_neigh_lookup_noref(dev, (__force u32)params->ipv4_dst);
+	if (neigh)
+		return bpf_fib_set_fwd_params(params, neigh, dev);
+
+	return 0;
+}
+#endif
+
+#if IS_ENABLED(CONFIG_IPV6)
+static int bpf_ipv6_fib_lookup(struct xdp_buff *ctx,

Same here.

Quoted 124 lines
net/core/filter.c +120 -0
+			       struct bpf_fib_lookup *params, u32 flags)
+{
+	struct net *net = dev_net(ctx->rxq->dev);
+	struct neighbour *neigh;
+	struct net_device *dev;
+	struct fib6_info *f6i;
+	struct flowi6 fl6;
+	int strict = 0;
+	int oif;
+
+	/* link local addresses are never forwarded */
+	if (rt6_need_strict(&params->ipv6_dst) ||
+	    rt6_need_strict(&params->ipv6_src))
+		return 0;
+
+	dev = dev_get_by_index_rcu(net, params->ifindex);
+	if (unlikely(!dev))
+		return -ENODEV;
+
+	if (flags & BPF_FIB_LOOKUP_OUTPUT) {
+		fl6.flowi6_iif = 1;
+		oif = fl6.flowi6_oif = params->ifindex;
+	} else {
+		oif = fl6.flowi6_iif = params->ifindex;
+		fl6.flowi6_oif = 0;
+		strict = RT6_LOOKUP_F_HAS_SADDR;
+	}
+	fl6.flowlabel = params->flowlabel;
+	fl6.flowi6_scope = 0;
+	fl6.flowi6_flags = 0;
+	fl6.mp_hash = 0;
+
+	fl6.flowi6_proto = params->l4_protocol;
+	fl6.daddr = params->ipv6_dst;
+	fl6.saddr = params->ipv6_src;
+	fl6.fl6_sport = params->sport;
+	fl6.fl6_dport = params->dport;
+
+	if (flags & BPF_FIB_LOOKUP_DIRECT) {
+		u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN;
+		struct fib6_table *tb;
+
+		tb = ipv6_stub->fib6_get_table(net, tbid);
+		if (unlikely(!tb))
+			return 0;
+
+		f6i = ipv6_stub->fib6_table_lookup(net, tb, oif, &fl6, strict);
+	} else {
+		fl6.flowi6_mark = 0;
+		fl6.flowi6_secid = 0;
+		fl6.flowi6_tun_key.tun_id = 0;
+		fl6.flowi6_uid = sock_net_uid(net, NULL);
+
+		f6i = ipv6_stub->fib6_lookup(net, oif, &fl6, strict);
+	}
+
+	if (unlikely(IS_ERR_OR_NULL(f6i) || f6i == net->ipv6.fib6_null_entry))
+		return 0;
+
+	if (unlikely(f6i->fib6_flags & RTF_REJECT ||
+	    f6i->fib6_type != RTN_UNICAST))
+		return 0;
+
+	if (f6i->fib6_nsiblings && fl6.flowi6_oif == 0)
+		f6i = ipv6_stub->fib6_multipath_select(net, f6i, &fl6,
+						       fl6.flowi6_oif, NULL,
+						       strict);
+
+	if (f6i->fib6_nh.nh_lwtstate)
+		return 0;
+
+	if (f6i->fib6_flags & RTF_GATEWAY)
+		params->ipv6_dst = f6i->fib6_nh.nh_gw;
+
+	dev = f6i->fib6_nh.nh_dev;
+	params->rt_metric = f6i->fib6_metric;
+
+	/* xdp and cls_bpf programs are run in RCU-bh so rcu_read_lock_bh is
+	 * not needed here. Can not use __ipv6_neigh_lookup_noref here
+	 * because we need to get nd_tbl via the stub
+	 */
+	neigh = ___neigh_lookup_noref(ipv6_stub->nd_tbl, neigh_key_eq128,
+				      ndisc_hashfn, &params->ipv6_dst, dev);
+	if (neigh)
+		return bpf_fib_set_fwd_params(params, neigh, dev);
+
+	return 0;
+}
+#endif
+
+BPF_CALL_4(bpf_fib_lookup, struct xdp_buff *, ctx,
+	   struct bpf_fib_lookup *, params, int, plen, u32, flags)
+{
+	if (plen < sizeof(*params))
+		return -EINVAL;
+
+	switch (params->family) {
+#if IS_ENABLED(CONFIG_INET)
+	case AF_INET:
+		return bpf_ipv4_fib_lookup(ctx, params, flags);
+#endif
+#if IS_ENABLED(CONFIG_IPV6)
+	case AF_INET6:
+		return bpf_ipv6_fib_lookup(ctx, params, flags);
+#endif
+	}
+	return -ENOTSUPP;
+}
+
+static const struct bpf_func_proto bpf_fib_lookup_proto = {
+	.func		= bpf_fib_lookup,
+	.gpl_only	= true,
+	.pkt_access	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type      = ARG_PTR_TO_CTX,
+	.arg2_type      = ARG_PTR_TO_MEM,
+	.arg3_type      = ARG_CONST_SIZE,
+	.arg4_type	= ARG_ANYTHING,
+};
+
 static const struct bpf_func_proto *
 bpf_base_func_proto(enum bpf_func_id func_id)
 {

net/core/filter.c sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) · line 4094

Quoted 5 lines
net/core/filter.c +2 -0
@@ -3861,6 +4090,8 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_socket_cookie_proto;
 	case BPF_FUNC_get_socket_uid:
 		return &bpf_get_socket_uid_proto;
+	case BPF_FUNC_fib_lookup:
+		return &bpf_fib_lookup_proto;

This part doesn't belong to sk_filter_func_proto(), but to the tc_cls_act_func_proto() instead.

net/core/filter.c xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) · line 4192

Quoted 9 lines
net/core/filter.c +2 -0
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -3957,6 +4188,8 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_xdp_redirect_map_proto;
 	case BPF_FUNC_xdp_adjust_tail:
 		return &bpf_xdp_adjust_tail_proto;
+	case BPF_FUNC_fib_lookup:
+		return &bpf_fib_lookup_proto;

Basically, you're using the very same bpf_fib_lookup_proto for both XDP and skb. In the skb case, you're reusing the two functions bpf_ipv{4,6}_fib_lookup(), so when you get the netdev pointer for retrieving the netns, you'll crash at dev_net(ctx->rxq->dev) since this is XDP only and not skb meta data.

Therefore, as mentioned, pass the netdev to bpf_ipv{4,6}_fib_lookup() to have it generic and have bpf_xdp_fib_lookup_proto and bpf_skb_fib_lookup_proto where both are under the case BPF_FUNC_fib_lookup in the respective *func_proto(), but using the proper prototypes according to their correct context. Meaning, both reuse bpf_ipv{4,6}_fib_lookup() from each of their BPF_CALL_4() helper implementation.

Quoted 4 lines
net/core/filter.c +0 -0
 	default:
 		return bpf_base_func_proto(func_id);
 	}
#10 lore raw

Re: [RFC bpf-next 8/9] bpf: Provide helper to do lookups in kernel FIB table

Quoted 8 lines · Daniel Borkmann

net/core/filter.c sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) · line 4094

Quoted 6 lines
net/core/filter.c +2 -0
@@ -3861,6 +4090,8 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_socket_cookie_proto;
 	case BPF_FUNC_get_socket_uid:
 		return &bpf_get_socket_uid_proto;
+	case BPF_FUNC_fib_lookup:
+		return &bpf_fib_lookup_proto;

This part doesn't belong to sk_filter_func_proto(), but to the tc_cls_act_func_proto() instead.

oops, somewhere in all of the re-basing it got added to the wrong function. Will fix.

Quoted 16 lines

net/core/filter.c xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) · line 4192

Quoted 10 lines
net/core/filter.c +2 -0
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -3957,6 +4188,8 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_xdp_redirect_map_proto;
 	case BPF_FUNC_xdp_adjust_tail:
 		return &bpf_xdp_adjust_tail_proto;
+	case BPF_FUNC_fib_lookup:
+		return &bpf_fib_lookup_proto;

Basically, you're using the very same bpf_fib_lookup_proto for both XDP and skb. In the skb case, you're reusing the two functions bpf_ipv{4,6}_fib_lookup(), so when you get the netdev pointer for retrieving the netns, you'll crash at dev_net(ctx->rxq->dev) since this is XDP only and not skb meta data.

Quoted 6 lines

Therefore, as mentioned, pass the netdev to bpf_ipv{4,6}_fib_lookup() to have it generic and have bpf_xdp_fib_lookup_proto and bpf_skb_fib_lookup_proto where both are under the case BPF_FUNC_fib_lookup in the respective *func_proto(), but using the proper prototypes according to their correct context. Meaning, both reuse bpf_ipv{4,6}_fib_lookup() from each of their BPF_CALL_4() helper implementation.

ok. I have been focused on the xdp program and not the tc path. Will fix.

#11 lore raw

Re: [RFC bpf-next 8/9] bpf: Provide helper to do lookups in kernel FIB table

In reply to David Ahern
Quoted 274 lines · David Ahern

Provide a helper for doing a FIB and neighbor lookup in the kernel tables from an XDP program. The helper provides a fastpath for forwarding packets. If the packet is a local delivery or for any reason is not a simple lookup and forward, the packet continues up the stack.

If it is to be forwarded, the forwarding can be done directly if the neighbor is already known. If the neighbor does not exist, the first few packets go up the stack for neighbor resolution. Once resolved, the xdp program provides the fast path.

On successful lookup the nexthop dmac, current device smac and egress device index are returned.

The API supports IPv4, IPv6 and MPLS protocols, but only IPv4 and IPv6 are implemented in this patch. The API includes layer 4 parameters if the XDP program chooses to do deep packet inspection to allow compare against ACLs implemented as FIB rules.

Header rewrite is left to the XDP program.

The lookup takes 2 flags:
- BPF_FIB_LOOKUP_DIRECT to do a lookup that bypasses FIB rules and goes straight to the table associated with the device (expert setting for those looking to maximize throughput)

- BPF_FIB_LOOKUP_OUTPUT to do a lookup from the egress perspective. Default is an ingress lookup.

Initial performance numbers collected by Jesper, forwarded packets/sec:

Full stack XDP FIB lookup XDP Direct lookup

IPv4   1,947,969       7,074,156          7,415,333
IPv6   1,728,000       6,165,504          7,262,720
---
 include/uapi/linux/bpf.h |  68 +++++++++++++-
 net/core/filter.c        | 233 +++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 300 insertions(+), 1 deletion(-)
include/uapi/linux/bpf.h +67 -1
index e6679393b687..82601c132b9f 100644
@@ -10,6 +10,8 @@
 
 #include <linux/types.h>
 #include <linux/bpf_common.h>
+#include <linux/if_ether.h>
+#include <linux/in6.h>
 
 /* Extended instruction set based on top of classic BPF */
 
@@ -783,6 +785,17 @@ union bpf_attr {
  *     @size: size of 'struct bpf_xfrm_state'
  *     @flags: room for future extensions
  *     Return: 0 on success or negative error
+ *
+ * int bpf_fib_lookup(ctx, params, plen, flags)
+ *     Do a FIB lookup based on given parameters
+ *     @ctx:     pointer to context of type xdp_md
+ *     @params:  pointer to bpf_fib_lookup
+ *     @plen:    size of params argument
+ *     @flags:   u32 bitmask of BPF_FIB_LOOKUP_* flags
+ *     Return: egress device index if packet is to be forwarded,
+ *             0 for local delivery (anything that needs to be handled
+ *             by the full stack), or negative on error.
+ *             If index is > 0, output data in bpf_fib_lookup is set
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -851,7 +864,9 @@ union bpf_attr {
 	FN(msg_pull_data),		\
 	FN(bind),			\
 	FN(xdp_adjust_tail),		\
-	FN(skb_get_xfrm_state),
+	FN(skb_get_xfrm_state),		\
+	FN(fib_lookup),			\
+
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -1255,4 +1270,55 @@ struct bpf_raw_tracepoint_args {
 	__u64 args[0];
 };
 
+/* DIRECT:  Skip the FIB rules and go to FIB table associated with device
+ * OUTPUT:  Do lookup from egress perspective; default is ingress
+ */
+#define BPF_FIB_LOOKUP_DIRECT  BIT(0)
+#define BPF_FIB_LOOKUP_OUTPUT  BIT(1)
+
+struct bpf_fib_lookup {
+	/* input */
+	__u8	family;   /* network family, AF_INET, AF_INET6, AF_MPLS */
+
+	/* set if lookup is to consider L4 data - e.g., FIB rules */
+	__u8	l4_protocol;
+	__be16	sport;
+	__be16	dport;
+
+	/* total length of packet from network header - used for MTU check */
+	__u16	tot_len;
+	__u32	ifindex;  /* L3 device index for lookup */
+
+	union {
+		/* inputs to lookup */
+		__u8	tos;		/* AF_INET  */
+		__be32	flowlabel;	/* AF_INET6 */
+
+		/* output: metric of fib result */
+		__u32 rt_metric;
+	};
+
+	union {
+		__be32		mpls_in;
+		__be32		ipv4_src;
+		struct in6_addr	ipv6_src;
+	};
+
+	/* input to bpf_fib_lookup, *dst is destination address.
+	 * output: bpf_fib_lookup sets to gateway address
+	 */
+	union {
+		/* return for MPLS lookups */
+		__be32		mpls_out[4];  /* support up to 4 labels */
+		__be32		ipv4_dst;
+		struct in6_addr	ipv6_dst;
+	};
+
+	/* output */
+	__be16	h_vlan_proto;
+	__be16	h_vlan_TCI;
+	__u8	smac[ETH_ALEN];
+	__u8	dmac[ETH_ALEN];
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */
net/core/filter.c +120 -0
index 8e45c6c7ab08..37602b2fb94a 100644
@@ -59,6 +59,10 @@
 #include <net/tcp.h>
 #include <net/xfrm.h>
 #include <linux/bpf_trace.h>
+#include <linux/inetdevice.h>
+#include <net/ip_fib.h>
+#include <net/flow.h>
+#include <net/arp.h>
 
 /**
  *	sk_filter_trim_cap - run a packet through a socket filter
@@ -3787,6 +3791,231 @@ static const struct bpf_func_proto bpf_skb_get_xfrm_state_proto = {
 };
 #endif
 
+#if IS_ENABLED(CONFIG_INET) || IS_ENABLED(CONFIG_IPV6)
+static int bpf_fib_set_fwd_params(struct bpf_fib_lookup *params,
+				  const struct neighbour *neigh,
+				  const struct net_device *dev)
+{
+	memcpy(params->dmac, neigh->ha, ETH_ALEN);
+	memcpy(params->smac, dev->dev_addr, ETH_ALEN);
+	params->h_vlan_TCI = 0;
+	params->h_vlan_proto = 0;
+
+	return dev->ifindex;
+}
+#endif
+
+#if IS_ENABLED(CONFIG_INET)
+static int bpf_ipv4_fib_lookup(struct xdp_buff *ctx,
+			       struct bpf_fib_lookup *params, u32 flags)
+{
+	struct net *net = dev_net(ctx->rxq->dev);
+	struct in_device *in_dev;
+	struct neighbour *neigh;
+	struct net_device *dev;
+	struct fib_result res;
+	struct fib_nh *nh;
+	struct flowi4 fl4;
+	int err;
+
+	dev = dev_get_by_index_rcu(net, params->ifindex);
+	if (unlikely(!dev))
+		return -ENODEV;
+
+	/* verify forwarding is enabled on this interface */
+	in_dev = __in_dev_get_rcu(dev);
+	if (unlikely(!in_dev || !IN_DEV_FORWARD(in_dev)))
+		return 0;
+
+	if (flags & BPF_FIB_LOOKUP_OUTPUT) {
+		fl4.flowi4_iif = 1;
+		fl4.flowi4_oif = params->ifindex;
+	} else {
+		fl4.flowi4_iif = params->ifindex;
+		fl4.flowi4_oif = 0;
+	}
+	fl4.flowi4_tos = params->tos & IPTOS_RT_MASK;
+	fl4.flowi4_scope = RT_SCOPE_UNIVERSE;
+	fl4.flowi4_flags = 0;
+
+	fl4.flowi4_proto = params->l4_protocol;
+	fl4.daddr = params->ipv4_dst;
+	fl4.saddr = params->ipv4_src;
+	fl4.fl4_sport = params->sport;
+	fl4.fl4_dport = params->dport;
+
+	if (flags & BPF_FIB_LOOKUP_DIRECT) {
+		u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN;
+		struct fib_table *tb;
+
+		tb = fib_get_table(net, tbid);
+		if (unlikely(!tb))
+			return 0;
+
+		err = fib_table_lookup(tb, &fl4, &res, FIB_LOOKUP_NOREF);
+	} else {
+		fl4.flowi4_mark = 0;
+		fl4.flowi4_secid = 0;
+		fl4.flowi4_tun_key.tun_id = 0;
+		fl4.flowi4_uid = sock_net_uid(net, NULL);
+
+		err = fib_lookup(net, &fl4, &res, FIB_LOOKUP_NOREF);
+	}
+
+	if (err || res.type != RTN_UNICAST)
+		return 0;
+
+	if (res.fi->fib_nhs > 1)
+		fib_select_path(net, &res, &fl4, NULL);
+
+	nh = &res.fi->fib_nh[res.nh_sel];
+
+	/* do not handle lwt encaps right now */
+	if (nh->nh_lwtstate)
+		return 0;
+
+	dev = nh->nh_dev;
+	if (unlikely(!dev))
+		return 0;
+
+	if (nh->nh_gw)
+		params->ipv4_dst = nh->nh_gw;
+
+	params->rt_metric = res.fi->fib_priority;
+
+	/* xdp and cls_bpf programs are run in RCU-bh so
+	 * rcu_read_lock_bh is not needed here
+	 */
+	neigh = __ipv4_neigh_lookup_noref(dev, (__force u32)params->ipv4_dst);
+	if (neigh)
+		return bpf_fib_set_fwd_params(params, neigh, dev);
+
+	return 0;
+}
+#endif
+
+#if IS_ENABLED(CONFIG_IPV6)
+static int bpf_ipv6_fib_lookup(struct xdp_buff *ctx,
+			       struct bpf_fib_lookup *params, u32 flags)
+{
+	struct net *net = dev_net(ctx->rxq->dev);
+	struct neighbour *neigh;
+	struct net_device *dev;
+	struct fib6_info *f6i;
+	struct flowi6 fl6;
+	int strict = 0;
+	int oif;
+
+	/* link local addresses are never forwarded */

net/core/filter.c static const struct bpf_func_proto bpf_skb_get_xfrm_state_proto = { · line 3919

Quoted 10 lines
net/core/filter.c +10 -0
+	if (rt6_need_strict(&params->ipv6_dst) ||
+	    rt6_need_strict(&params->ipv6_src))
+		return 0;
+
+	dev = dev_get_by_index_rcu(net, params->ifindex);
+	if (unlikely(!dev))
+		return -ENODEV;
+
+	if (flags & BPF_FIB_LOOKUP_OUTPUT) {
+		fl6.flowi6_iif = 1;

1 is for LOOPBACK_IFINDEX?

Quoted 123 lines
net/core/filter.c +103 -0
+		oif = fl6.flowi6_oif = params->ifindex;
+	} else {
+		oif = fl6.flowi6_iif = params->ifindex;
+		fl6.flowi6_oif = 0;
+		strict = RT6_LOOKUP_F_HAS_SADDR;
+	}
+	fl6.flowlabel = params->flowlabel;
+	fl6.flowi6_scope = 0;
+	fl6.flowi6_flags = 0;
+	fl6.mp_hash = 0;
+
+	fl6.flowi6_proto = params->l4_protocol;
+	fl6.daddr = params->ipv6_dst;
+	fl6.saddr = params->ipv6_src;
+	fl6.fl6_sport = params->sport;
+	fl6.fl6_dport = params->dport;
+
+	if (flags & BPF_FIB_LOOKUP_DIRECT) {
+		u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN;
+		struct fib6_table *tb;
+
+		tb = ipv6_stub->fib6_get_table(net, tbid);
+		if (unlikely(!tb))
+			return 0;
+
+		f6i = ipv6_stub->fib6_table_lookup(net, tb, oif, &fl6, strict);
+	} else {
+		fl6.flowi6_mark = 0;
+		fl6.flowi6_secid = 0;
+		fl6.flowi6_tun_key.tun_id = 0;
+		fl6.flowi6_uid = sock_net_uid(net, NULL);
+
+		f6i = ipv6_stub->fib6_lookup(net, oif, &fl6, strict);
+	}
+
+	if (unlikely(IS_ERR_OR_NULL(f6i) || f6i == net->ipv6.fib6_null_entry))
+		return 0;
+
+	if (unlikely(f6i->fib6_flags & RTF_REJECT ||
+	    f6i->fib6_type != RTN_UNICAST))
+		return 0;
+
+	if (f6i->fib6_nsiblings && fl6.flowi6_oif == 0)
+		f6i = ipv6_stub->fib6_multipath_select(net, f6i, &fl6,
+						       fl6.flowi6_oif, NULL,
+						       strict);
+
+	if (f6i->fib6_nh.nh_lwtstate)
+		return 0;
+
+	if (f6i->fib6_flags & RTF_GATEWAY)
+		params->ipv6_dst = f6i->fib6_nh.nh_gw;
+
+	dev = f6i->fib6_nh.nh_dev;
+	params->rt_metric = f6i->fib6_metric;
+
+	/* xdp and cls_bpf programs are run in RCU-bh so rcu_read_lock_bh is
+	 * not needed here. Can not use __ipv6_neigh_lookup_noref here
+	 * because we need to get nd_tbl via the stub
+	 */
+	neigh = ___neigh_lookup_noref(ipv6_stub->nd_tbl, neigh_key_eq128,
+				      ndisc_hashfn, &params->ipv6_dst, dev);
+	if (neigh)
+		return bpf_fib_set_fwd_params(params, neigh, dev);
+
+	return 0;
+}
+#endif
+
+BPF_CALL_4(bpf_fib_lookup, struct xdp_buff *, ctx,
+	   struct bpf_fib_lookup *, params, int, plen, u32, flags)
+{
+	if (plen < sizeof(*params))
+		return -EINVAL;
+
+	switch (params->family) {
+#if IS_ENABLED(CONFIG_INET)
+	case AF_INET:
+		return bpf_ipv4_fib_lookup(ctx, params, flags);
+#endif
+#if IS_ENABLED(CONFIG_IPV6)
+	case AF_INET6:
+		return bpf_ipv6_fib_lookup(ctx, params, flags);
+#endif
+	}
+	return -ENOTSUPP;
+}
+
+static const struct bpf_func_proto bpf_fib_lookup_proto = {
+	.func		= bpf_fib_lookup,
+	.gpl_only	= true,
+	.pkt_access	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type      = ARG_PTR_TO_CTX,
+	.arg2_type      = ARG_PTR_TO_MEM,
+	.arg3_type      = ARG_CONST_SIZE,
+	.arg4_type	= ARG_ANYTHING,
+};
+
 static const struct bpf_func_proto *
 bpf_base_func_proto(enum bpf_func_id func_id)
 {
@@ -3861,6 +4090,8 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_socket_cookie_proto;
 	case BPF_FUNC_get_socket_uid:
 		return &bpf_get_socket_uid_proto;
+	case BPF_FUNC_fib_lookup:
+		return &bpf_fib_lookup_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -3957,6 +4188,8 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_xdp_redirect_map_proto;
 	case BPF_FUNC_xdp_adjust_tail:
 		return &bpf_xdp_adjust_tail_proto;
+	case BPF_FUNC_fib_lookup:
+		return &bpf_fib_lookup_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
Signature · 1 line
2.11.0
#12 lore raw

Re: [RFC bpf-next 8/9] bpf: Provide helper to do lookups in kernel FIB table

Quoted 16 lines · Martin KaFai Lau
Quoted 16 lines
net/core/filter.c +16 -0
+#if IS_ENABLED(CONFIG_IPV6)
+static int bpf_ipv6_fib_lookup(struct xdp_buff *ctx,
+			       struct bpf_fib_lookup *params, u32 flags)
+{
+	struct net *net = dev_net(ctx->rxq->dev);
+	struct neighbour *neigh;
+	struct net_device *dev;
+	struct fib6_info *f6i;
+	struct flowi6 fl6;
+	int strict = 0;
+	int oif;
+
+	/* link local addresses are never forwarded */
+	if (rt6_need_strict(&params->ipv6_dst) ||
+	    rt6_need_strict(&params->ipv6_src))
+		return 0;
Quoted 8 lines

net/core/filter.c static const struct bpf_func_proto bpf_skb_get_xfrm_state_proto = { · line 3919

Quoted 7 lines
net/core/filter.c +7 -0
+
+	dev = dev_get_by_index_rcu(net, params->ifindex);
+	if (unlikely(!dev))
+		return -ENODEV;
+
+	if (flags & BPF_FIB_LOOKUP_OUTPUT) {
+		fl6.flowi6_iif = 1;

1 is for LOOPBACK_IFINDEX?

yes. The intention is to mirror the flow struct created by full stack so that routing in bpf == routing in IPv6 stack. ip6_route_output_flags sets flowi6_iif to 1, so I repeated it here.

Quoted 7 lines
Quoted 7 lines
net/core/filter.c +6 -0
+		oif = fl6.flowi6_oif = params->ifindex;
+	} else {
+		oif = fl6.flowi6_iif = params->ifindex;
+		fl6.flowi6_oif = 0;
+		strict = RT6_LOOKUP_F_HAS_SADDR;
+	}
#13 lore raw

RFC 9/9 samples/bpf: Add examples of ipv4 and ipv6 forwarding in XDP

In reply to David Ahern
---
 samples/bpf/Makefile                      |   4 +
 samples/bpf/xdp_fwd_kern.c                | 110 ++++++++++++++++++++++++
 samples/bpf/xdp_fwd_user.c                | 136 ++++++++++++++++++++++++++++++
 tools/testing/selftests/bpf/bpf_helpers.h |   3 +
 4 files changed, 253 insertions(+)
 create mode 100644 samples/bpf/xdp_fwd_kern.c
 create mode 100644 samples/bpf/xdp_fwd_user.c
samples/bpf/Makefile +4 -0
index aa8c392e2e52..c90d2ff74873 100644
@@ -45,6 +45,7 @@ hostprogs-y += xdp_rxq_info
 hostprogs-y += syscall_tp
 hostprogs-y += cpustat
 hostprogs-y += xdp_adjust_tail
+hostprogs-y += xdp_fwd
 
 # Libbpf dependencies
 LIBBPF := ../../tools/lib/bpf/bpf.o ../../tools/lib/bpf/nlattr.o
@@ -97,6 +98,7 @@ xdp_rxq_info-objs := bpf_load.o $(LIBBPF) xdp_rxq_info_user.o
 syscall_tp-objs := bpf_load.o $(LIBBPF) syscall_tp_user.o
 cpustat-objs := bpf_load.o $(LIBBPF) cpustat_user.o
 xdp_adjust_tail-objs := bpf_load.o $(LIBBPF) xdp_adjust_tail_user.o
+xdp_fwd-objs := bpf_load.o $(LIBBPF) xdp_fwd_user.o
 
 # Tell kbuild to always build the programs
 always := $(hostprogs-y)
@@ -151,6 +153,7 @@ always += xdp2skb_meta_kern.o
 always += syscall_tp_kern.o
 always += cpustat_kern.o
 always += xdp_adjust_tail_kern.o
+always += xdp_fwd_kern.o
 
 HOSTCFLAGS += -I$(objtree)/usr/include
 HOSTCFLAGS += -I$(srctree)/tools/lib/
@@ -197,6 +200,7 @@ HOSTLOADLIBES_xdp_rxq_info += -lelf
 HOSTLOADLIBES_syscall_tp += -lelf
 HOSTLOADLIBES_cpustat += -lelf
 HOSTLOADLIBES_xdp_adjust_tail += -lelf
+HOSTLOADLIBES_xdp_fwd += -lelf
 
 # Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline:
 #  make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang
samples/bpf/xdp_fwd_kern.c new file +110 -0

110 lines not on this page · raw message

samples/bpf/xdp_fwd_user.c new file +136 -0

136 lines not on this page · raw message

tools/testing/selftests/bpf/bpf_helpers.h +3 -0
index 69d7b918e66a..4407766a5950 100644
@@ -101,6 +101,9 @@ static int (*bpf_xdp_adjust_tail)(void *ctx, int offset) =
 static int (*bpf_skb_get_xfrm_state)(void *ctx, int index, void *state,
 				     int size, int flags) =
 	(void *) BPF_FUNC_skb_get_xfrm_state;
+static int (*bpf_fib_lookup)(void *ctx, struct bpf_fib_lookup *params,
+			     int plen, __u32 flags) =
+	(void *) BPF_FUNC_fib_lookup;
 
 /* llvm builtin functions that eBPF C program may use to
  * emit BPF_LD_ABS and BPF_LD_IND instructions
Signature · 1 line
2.11.0