Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
The following pull-request contains BPF updates for your *net-next* tree.

There is a small merge conflict in libbpf (Cc Andrii so he's in the loop
as well):

        for (i = 1; i <= btf__get_nr_types(btf); i++) {
                t = (struct btf_type *)btf__type_by_id(btf, i);

                if (!has_datasec && btf_is_var(t)) {
                        /* replace VAR with INT */
                        t->info = BTF_INFO_ENC(BTF_KIND_INT, 0, 0);
  <<<<<<< HEAD
                        /*
                         * using size = 1 is the safest choice, 4 will be too
                         * big and cause kernel BTF validation failure if
                         * original variable took less than 4 bytes
                         */
                        t->size = 1;
                        *(int *)(t+1) = BTF_INT_ENC(0, 0, 8);
                } else if (!has_datasec && kind == BTF_KIND_DATASEC) {
  =======
                        t->size = sizeof(int);
                        *(int *)(t + 1) = BTF_INT_ENC(0, 0, 32);
                } else if (!has_datasec && btf_is_datasec(t)) {
  >>>>>>> 72ef80b5ee131e96172f19e74b4f98fa3404efe8
                        /* replace DATASEC with STRUCT */

Conflict is between the two commits 1d4126c4e119 ("libbpf: sanitize VAR to
conservative 1-byte INT") and b03bc6853c0e ("libbpf: convert libbpf code to
use new btf helpers"), so we need to pick the sanitation fixup as well as
use the new btf_is_datasec() helper and the whitespace cleanup. Looks like
the following:

  [...]
                if (!has_datasec && btf_is_var(t)) {
                        /* replace VAR with INT */
                        t->info = BTF_INFO_ENC(BTF_KIND_INT, 0, 0);
                        /*
                         * using size = 1 is the safest choice, 4 will be too
                         * big and cause kernel BTF validation failure if
                         * original variable took less than 4 bytes
                         */
                        t->size = 1;
                        *(int *)(t + 1) = BTF_INT_ENC(0, 0, 8);
                } else if (!has_datasec && btf_is_datasec(t)) {
                        /* replace DATASEC with STRUCT */
  [...]

The main changes are:

1) Addition of core parts of compile once - run everywhere (co-re) effort,
   that is, relocation of fields offsets in libbpf as well as exposure of
   kernel's own BTF via sysfs and loading through libbpf, from Andrii.

   More info on co-re: http://vger.kernel.org/bpfconf2019.html#session-2
   and http://vger.kernel.org/lpc-bpf2018.html#session-2

2) Enable passing input flags to the BPF flow dissector to customize parsing
   and allowing it to stop early similar to the C based one, from Stanislav.

3) Add a BPF helper function that allows generating SYN cookies from XDP and
   tc BPF, from Petar.

4) Add devmap hash-based map type for more flexibility in device lookup for
   redirects, from Toke.

5) Improvements to XDP forwarding sample code now utilizing recently enabled
   devmap lookups, from Jesper.

6) Add support for reporting the effective cgroup progs in bpftool, from Jakub
   and Takshak.

7) Fix reading kernel config from bpftool via /proc/config.gz, from Peter.

8) Fix AF_XDP umem pages mapping for 32 bit architectures, from Ivan.

9) Follow-up to add two more BPF loop tests for the selftest suite, from Alexei.

10) Add perf event output helper also for other skb-based program types, from Allan.

11) Fix a co-re related compilation error in selftests, from Yonghong.
====================

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>

2 files changed, 105 insertions, 4 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index 7878f918b8c0..0c1059cdad3d 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3517,7 +3517,8 @@ static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd,
 	int err;
 
 	switch (map->map_type) {
-	case BPF_MAP_TYPE_DEVMAP: {
+	case BPF_MAP_TYPE_DEVMAP:
+	case BPF_MAP_TYPE_DEVMAP_HASH: {
 		struct bpf_dtab_netdev *dst = fwd;
 
 		err = dev_map_enqueue(dst, xdp, dev_rx);
@@ -3554,6 +3555,7 @@ void xdp_do_flush_map(void)
 	if (map) {
 		switch (map->map_type) {
 		case BPF_MAP_TYPE_DEVMAP:
+		case BPF_MAP_TYPE_DEVMAP_HASH:
 			__dev_map_flush(map);
 			break;
 		case BPF_MAP_TYPE_CPUMAP:
@@ -3574,6 +3576,8 @@ static inline void *__xdp_map_lookup_elem(struct bpf_map *map, u32 index)
 	switch (map->map_type) {
 	case BPF_MAP_TYPE_DEVMAP:
 		return __dev_map_lookup_elem(map, index);
+	case BPF_MAP_TYPE_DEVMAP_HASH:
+		return __dev_map_hash_lookup_elem(map, index);
 	case BPF_MAP_TYPE_CPUMAP:
 		return __cpu_map_lookup_elem(map, index);
 	case BPF_MAP_TYPE_XSKMAP:
@@ -3655,7 +3659,8 @@ static int xdp_do_generic_redirect_map(struct net_device *dev,
 	ri->tgt_value = NULL;
 	WRITE_ONCE(ri->map, NULL);
 
-	if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
+	if (map->map_type == BPF_MAP_TYPE_DEVMAP ||
+	    map->map_type == BPF_MAP_TYPE_DEVMAP_HASH) {
 		struct bpf_dtab_netdev *dst = fwd;
 
 		err = dev_map_generic_redirect(dst, skb, xdp_prog);
@@ -5850,6 +5855,75 @@ static const struct bpf_func_proto bpf_tcp_check_syncookie_proto = {
 	.arg5_type	= ARG_CONST_SIZE,
 };
 
+BPF_CALL_5(bpf_tcp_gen_syncookie, struct sock *, sk, void *, iph, u32, iph_len,
+	   struct tcphdr *, th, u32, th_len)
+{
+#ifdef CONFIG_SYN_COOKIES
+	u32 cookie;
+	u16 mss;
+
+	if (unlikely(th_len < sizeof(*th) || th_len != th->doff * 4))
+		return -EINVAL;
+
+	if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN)
+		return -EINVAL;
+
+	if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies)
+		return -ENOENT;
+
+	if (!th->syn || th->ack || th->fin || th->rst)
+		return -EINVAL;
+
+	if (unlikely(iph_len < sizeof(struct iphdr)))
+		return -EINVAL;
+
+	/* Both struct iphdr and struct ipv6hdr have the version field at the
+	 * same offset so we can cast to the shorter header (struct iphdr).
+	 */
+	switch (((struct iphdr *)iph)->version) {
+	case 4:
+		if (sk->sk_family == AF_INET6 && sk->sk_ipv6only)
+			return -EINVAL;
+
+		mss = tcp_v4_get_syncookie(sk, iph, th, &cookie);
+		break;
+
+#if IS_BUILTIN(CONFIG_IPV6)
+	case 6:
+		if (unlikely(iph_len < sizeof(struct ipv6hdr)))
+			return -EINVAL;
+
+		if (sk->sk_family != AF_INET6)
+			return -EINVAL;
+
+		mss = tcp_v6_get_syncookie(sk, iph, th, &cookie);
+		break;
+#endif /* CONFIG_IPV6 */
+
+	default:
+		return -EPROTONOSUPPORT;
+	}
+	if (mss <= 0)
+		return -ENOENT;
+
+	return cookie | ((u64)mss << 32);
+#else
+	return -EOPNOTSUPP;
+#endif /* CONFIG_SYN_COOKIES */
+}
+
+static const struct bpf_func_proto bpf_tcp_gen_syncookie_proto = {
+	.func		= bpf_tcp_gen_syncookie,
+	.gpl_only	= true, /* __cookie_v*_init_sequence() is GPL */
+	.pkt_access	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_SOCK_COMMON,
+	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_CONST_SIZE,
+	.arg4_type	= ARG_PTR_TO_MEM,
+	.arg5_type	= ARG_CONST_SIZE,
+};
+
 #endif /* CONFIG_INET */
 
 bool bpf_helper_changes_pkt_data(void *func)
@@ -5999,6 +6073,8 @@ 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_perf_event_output:
+		return &bpf_skb_event_output_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -6019,6 +6095,8 @@ cg_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sk_storage_get_proto;
 	case BPF_FUNC_sk_storage_delete:
 		return &bpf_sk_storage_delete_proto;
+	case BPF_FUNC_perf_event_output:
+		return &bpf_skb_event_output_proto;
 #ifdef CONFIG_SOCK_CGROUP_DATA
 	case BPF_FUNC_skb_cgroup_id:
 		return &bpf_skb_cgroup_id_proto;
@@ -6135,6 +6213,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_tcp_check_syncookie_proto;
 	case BPF_FUNC_skb_ecn_set_ce:
 		return &bpf_skb_ecn_set_ce_proto;
+	case BPF_FUNC_tcp_gen_syncookie:
+		return &bpf_tcp_gen_syncookie_proto;
 #endif
 	default:
 		return bpf_base_func_proto(func_id);
@@ -6174,6 +6254,8 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_xdp_skc_lookup_tcp_proto;
 	case BPF_FUNC_tcp_check_syncookie:
 		return &bpf_tcp_check_syncookie_proto;
+	case BPF_FUNC_tcp_gen_syncookie:
+		return &bpf_tcp_gen_syncookie_proto;
 #endif
 	default:
 		return bpf_base_func_proto(func_id);
@@ -6267,6 +6349,8 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sk_redirect_map_proto;
 	case BPF_FUNC_sk_redirect_hash:
 		return &bpf_sk_redirect_hash_proto;
+	case BPF_FUNC_perf_event_output:
+		return &bpf_skb_event_output_proto;
 #ifdef CONFIG_INET
 	case BPF_FUNC_sk_lookup_tcp:
 		return &bpf_sk_lookup_tcp_proto;
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 3e6fedb57bc1..9741b593ea53 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -737,6 +737,7 @@ static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys,
 	struct flow_dissector_key_basic *key_basic;
 	struct flow_dissector_key_addrs *key_addrs;
 	struct flow_dissector_key_ports *key_ports;
+	struct flow_dissector_key_tags *key_tags;
 
 	key_control = skb_flow_dissector_target(flow_dissector,
 						FLOW_DISSECTOR_KEY_CONTROL,
@@ -781,10 +782,18 @@ static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys,
 		key_ports->src = flow_keys->sport;
 		key_ports->dst = flow_keys->dport;
 	}
+
+	if (dissector_uses_key(flow_dissector,
+			       FLOW_DISSECTOR_KEY_FLOW_LABEL)) {
+		key_tags = skb_flow_dissector_target(flow_dissector,
+						     FLOW_DISSECTOR_KEY_FLOW_LABEL,
+						     target_container);
+		key_tags->flow_label = ntohl(flow_keys->flow_label);
+	}
 }
 
 bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx,
-		      __be16 proto, int nhoff, int hlen)
+		      __be16 proto, int nhoff, int hlen, unsigned int flags)
 {
 	struct bpf_flow_keys *flow_keys = ctx->flow_keys;
 	u32 result;
@@ -795,6 +804,14 @@ bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx,
 	flow_keys->nhoff = nhoff;
 	flow_keys->thoff = flow_keys->nhoff;
 
+	BUILD_BUG_ON((int)BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG !=
+		     (int)FLOW_DISSECTOR_F_PARSE_1ST_FRAG);
+	BUILD_BUG_ON((int)BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL !=
+		     (int)FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL);
+	BUILD_BUG_ON((int)BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP !=
+		     (int)FLOW_DISSECTOR_F_STOP_AT_ENCAP);
+	flow_keys->flags = flags;
+
 	preempt_disable();
 	result = BPF_PROG_RUN(prog, ctx);
 	preempt_enable();
@@ -914,7 +931,7 @@ bool __skb_flow_dissect(const struct net *net,
 			}
 
 			ret = bpf_flow_dissect(attached, &ctx, n_proto, nhoff,
-					       hlen);
+					       hlen, flags);
 			__skb_flow_bpf_to_target(&flow_keys, flow_dissector,
 						 target_container);
 			rcu_read_unlock();