bpf: Introduce SK_LOOKUP program type with a dedicated attach point

Add a new program type BPF_PROG_TYPE_SK_LOOKUP with a dedicated attach type
BPF_SK_LOOKUP. The new program kind is to be invoked by the transport layer
when looking up a listening socket for a new connection request for
connection oriented protocols, or when looking up an unconnected socket for
a packet for connection-less protocols.

When called, SK_LOOKUP BPF program can select a socket that will receive
the packet. This serves as a mechanism to overcome the limits of what
bind() API allows to express. Two use-cases driving this work are:

 (1) steer packets destined to an IP range, on fixed port to a socket

     192.0.2.0/24, port 80 -> NGINX socket

 (2) steer packets destined to an IP address, on any port to a socket

     198.51.100.1, any port -> L7 proxy socket

In its run-time context program receives information about the packet that
triggered the socket lookup. Namely IP version, L4 protocol identifier, and
address 4-tuple. Context can be further extended to include ingress
interface identifier.

To select a socket BPF program fetches it from a map holding socket
references, like SOCKMAP or SOCKHASH, and calls bpf_sk_assign(ctx, sk, ...)
helper to record the selection. Transport layer then uses the selected
socket as a result of socket lookup.

In its basic form, SK_LOOKUP acts as a filter and hence must return either
SK_PASS or SK_DROP. If the program returns with SK_PASS, transport should
look for a socket to receive the packet, or use the one selected by the
program if available, while SK_DROP informs the transport layer that the
lookup should fail.

This patch only enables the user to attach an SK_LOOKUP program to a
network namespace. Subsequent patches hook it up to run on local delivery
path in ipv4 and ipv6 stacks.

Suggested-by: Marek Majkowski <marek@cloudflare.com>
Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200717103536.397595-3-jakub@cloudflare.com

3 files changed, 24 insertions, 3 deletions

diff --git a/kernel/bpf/net_namespace.c b/kernel/bpf/net_namespace.c
index e9c8e26ac8f2..38b368bccda2 100644
--- a/kernel/bpf/net_namespace.c
+++ b/kernel/bpf/net_namespace.c
@@ -373,6 +373,8 @@ static int netns_bpf_max_progs(enum netns_bpf_attach_type type)
 	switch (type) {
 	case NETNS_BPF_FLOW_DISSECTOR:
 		return 1;
+	case NETNS_BPF_SK_LOOKUP:
+		return 64;
 	default:
 		return 0;
 	}
@@ -403,6 +405,9 @@ static int netns_bpf_link_attach(struct net *net, struct bpf_link *link,
 	case NETNS_BPF_FLOW_DISSECTOR:
 		err = flow_dissector_bpf_prog_attach_check(net, link->prog);
 		break;
+	case NETNS_BPF_SK_LOOKUP:
+		err = 0; /* nothing to check */
+		break;
 	default:
 		err = -EINVAL;
 		break;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 7ea9dfbebd8c..d07417d17712 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2022,6 +2022,10 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
 		default:
 			return -EINVAL;
 		}
+	case BPF_PROG_TYPE_SK_LOOKUP:
+		if (expected_attach_type == BPF_SK_LOOKUP)
+			return 0;
+		return -EINVAL;
 	case BPF_PROG_TYPE_EXT:
 		if (expected_attach_type)
 			return -EINVAL;
@@ -2756,6 +2760,7 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
 	case BPF_PROG_TYPE_CGROUP_SOCK:
 	case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
 	case BPF_PROG_TYPE_CGROUP_SOCKOPT:
+	case BPF_PROG_TYPE_SK_LOOKUP:
 		return attach_type == prog->expected_attach_type ? 0 : -EINVAL;
 	case BPF_PROG_TYPE_CGROUP_SKB:
 		if (!capable(CAP_NET_ADMIN))
@@ -2817,6 +2822,8 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type)
 		return BPF_PROG_TYPE_CGROUP_SOCKOPT;
 	case BPF_TRACE_ITER:
 		return BPF_PROG_TYPE_TRACING;
+	case BPF_SK_LOOKUP:
+		return BPF_PROG_TYPE_SK_LOOKUP;
 	default:
 		return BPF_PROG_TYPE_UNSPEC;
 	}
@@ -2953,6 +2960,7 @@ static int bpf_prog_query(const union bpf_attr *attr,
 	case BPF_LIRC_MODE2:
 		return lirc_prog_query(attr, uattr);
 	case BPF_FLOW_DISSECTOR:
+	case BPF_SK_LOOKUP:
 		return netns_bpf_prog_query(attr, uattr);
 	default:
 		return -EINVAL;
@@ -3891,6 +3899,7 @@ static int link_create(union bpf_attr *attr)
 		ret = tracing_bpf_link_attach(attr, prog);
 		break;
 	case BPF_PROG_TYPE_FLOW_DISSECTOR:
+	case BPF_PROG_TYPE_SK_LOOKUP:
 		ret = netns_bpf_link_create(attr, prog);
 		break;
 	default:
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 3c1efc9d08fd..9a6703bc3f36 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -3878,10 +3878,14 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 			}
 			meta->ref_obj_id = reg->ref_obj_id;
 		}
-	} else if (arg_type == ARG_PTR_TO_SOCKET) {
+	} else if (arg_type == ARG_PTR_TO_SOCKET ||
+		   arg_type == ARG_PTR_TO_SOCKET_OR_NULL) {
 		expected_type = PTR_TO_SOCKET;
-		if (type != expected_type)
-			goto err_type;
+		if (!(register_is_null(reg) &&
+		      arg_type == ARG_PTR_TO_SOCKET_OR_NULL)) {
+			if (type != expected_type)
+				goto err_type;
+		}
 	} else if (arg_type == ARG_PTR_TO_BTF_ID) {
 		expected_type = PTR_TO_BTF_ID;
 		if (type != expected_type)
@@ -7354,6 +7358,9 @@ static int check_return_code(struct bpf_verifier_env *env)
 			return -ENOTSUPP;
 		}
 		break;
+	case BPF_PROG_TYPE_SK_LOOKUP:
+		range = tnum_range(SK_DROP, SK_PASS);
+		break;
 	case BPF_PROG_TYPE_EXT:
 		/* freplace program can return anything as its return value
 		 * depends on the to-be-replaced kernel func or bpf program.