Merge branch 'bpf-fib-lookup-helper'

David Ahern says:

====================
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 is expected to continue up the stack
for full processing.

The response from a FIB and neighbor lookup is either the egress index
with the bpf_fib_lookup struct filled in with dmac and gateway or
0 meaning the packet should continue up the stack. In time we can
revisit this to return the FIB lookup result errno if it is one of the
special RTN_'s such as RTN_BLACKHOLE (-EINVAL) so that the XDP
programs can do an early drop if desired.

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 adds a sample program.

v3
- remove ETH_ALEN and in6_addr from uapi header

v2
- removed pkt_access from bpf_func_proto as noticed by Daniel
- added check in that IPv6 forwarding is enabled
- added DaveM's ack on patches 1-7 and 9 based on v1 response and
  fact that no changes were made to them in v2

v1
- updated commit messages and cover letter
- added comment to sample program noting lack of verification on
  egress device supporting XDP

RFC v2
- fixed use of foward helper from cls_act as noted by Daniel
- in patch 1 rename fib6_lookup_1 as well for consistency
====================

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

4 files changed, 119 insertions, 11 deletions

diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 8312cc25a3af..ff766ab207e0 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -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,
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index a3ec08d05756..cc70f6da8462 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -376,9 +376,24 @@ 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);
+/* 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);
+
+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);
 
 struct fib6_node *fib6_locate(struct fib6_node *root,
 			      const struct in6_addr *daddr, int dst_len,
diff --git a/include/trace/events/fib6.h b/include/trace/events/fib6.h
index 7e8d48a81b91..1b8d951e3c12 100644
--- a/include/trace/events/fib6.h
+++ b/include/trace/events/fib6.h
@@ -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;
 		}
 	),
 
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index d615c777b573..02e4112510f8 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1828,6 +1828,33 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
+ *
+ * int bpf_fib_lookup(void *ctx, struct bpf_fib_lookup *params, int plen, u32 flags)
+ *	Description
+ *		Do FIB lookup in kernel tables using parameters in *params*.
+ *		If lookup is successful and result shows packet is to be
+ *		forwarded, the neighbor tables are searched for the nexthop.
+ *		If successful (ie., FIB lookup shows forwarding and nexthop
+ *		is resolved), the nexthop address is returned in ipv4_dst,
+ *		ipv6_dst or mpls_out based on family, smac is set to mac
+ *		address of egress device, dmac is set to nexthop mac address,
+ *		rt_metric is set to metric from route.
+ *
+ *             *plen* argument is the size of the passed in struct.
+ *             *flags* argument can be one or more BPF_FIB_LOOKUP_ flags:
+ *
+ *             **BPF_FIB_LOOKUP_DIRECT** means do a direct table lookup vs
+ *             full lookup using FIB rules
+ *             **BPF_FIB_LOOKUP_OUTPUT** means do lookup from an egress
+ *             perspective (default is ingress)
+ *
+ *             *ctx* is either **struct xdp_md** for XDP programs or
+ *             **struct sk_buff** tc cls_act programs.
+ *
+ *     Return
+ *             Egress device index on success, 0 if packet needs to continue
+ *             up the stack for further processing or a negative error in case
+ *             of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -1898,7 +1925,8 @@ union bpf_attr {
 	FN(xdp_adjust_tail),		\
 	FN(skb_get_xfrm_state),		\
 	FN(get_stack),			\
-	FN(skb_load_bytes_relative),
+	FN(skb_load_bytes_relative),	\
+	FN(fib_lookup),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -2321,4 +2349,55 @@ 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;
+		__u32		ipv6_src[4];  /* in6_addr; network order */
+	};
+
+	/* 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;
+		__u32		ipv6_dst[4];  /* in6_addr; network order */
+	};
+
+	/* output */
+	__be16	h_vlan_proto;
+	__be16	h_vlan_TCI;
+	__u8	smac[6];     /* ETH_ALEN */
+	__u8	dmac[6];     /* ETH_ALEN */
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */