summaryrefslogtreecommitdiff
path: root/include/linux
diff options
context:
space:
mode:
authorJakub Sitnicki <jakub@cloudflare.com>2020-07-17 12:35:23 +0200
committerAlexei Starovoitov <ast@kernel.org>2020-07-17 20:18:16 -0700
commite9ddbb7707ff5891616240026062b8c1e29864ca (patch)
treee8d481f2542beb53c3da92433757a8dbea363827 /include/linux
parentce3aa9cc5109363099b7c4ac82e2c9768afcaf31 (diff)
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
Diffstat (limited to 'include/linux')
-rw-r--r--include/linux/bpf-netns.h3
-rw-r--r--include/linux/bpf.h1
-rw-r--r--include/linux/bpf_types.h2
-rw-r--r--include/linux/filter.h17
4 files changed, 23 insertions, 0 deletions
diff --git a/include/linux/bpf-netns.h b/include/linux/bpf-netns.h
index 47d5b0c708c9..722f799c1a2e 100644
--- a/include/linux/bpf-netns.h
+++ b/include/linux/bpf-netns.h
@@ -8,6 +8,7 @@
enum netns_bpf_attach_type {
NETNS_BPF_INVALID = -1,
NETNS_BPF_FLOW_DISSECTOR = 0,
+ NETNS_BPF_SK_LOOKUP,
MAX_NETNS_BPF_ATTACH_TYPE
};
@@ -17,6 +18,8 @@ to_netns_bpf_attach_type(enum bpf_attach_type attach_type)
switch (attach_type) {
case BPF_FLOW_DISSECTOR:
return NETNS_BPF_FLOW_DISSECTOR;
+ case BPF_SK_LOOKUP:
+ return NETNS_BPF_SK_LOOKUP;
default:
return NETNS_BPF_INVALID;
}
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index c8c9eabcd106..adb16bdc5f0a 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -249,6 +249,7 @@ enum bpf_arg_type {
ARG_PTR_TO_INT, /* pointer to int */
ARG_PTR_TO_LONG, /* pointer to long */
ARG_PTR_TO_SOCKET, /* pointer to bpf_sock (fullsock) */
+ ARG_PTR_TO_SOCKET_OR_NULL, /* pointer to bpf_sock (fullsock) or NULL */
ARG_PTR_TO_BTF_ID, /* pointer to in-kernel struct */
ARG_PTR_TO_ALLOC_MEM, /* pointer to dynamically allocated memory */
ARG_PTR_TO_ALLOC_MEM_OR_NULL, /* pointer to dynamically allocated memory or NULL */
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index a18ae82a298a..a52a5688418e 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -64,6 +64,8 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2,
#ifdef CONFIG_INET
BPF_PROG_TYPE(BPF_PROG_TYPE_SK_REUSEPORT, sk_reuseport,
struct sk_reuseport_md, struct sk_reuseport_kern)
+BPF_PROG_TYPE(BPF_PROG_TYPE_SK_LOOKUP, sk_lookup,
+ struct bpf_sk_lookup, struct bpf_sk_lookup_kern)
#endif
#if defined(CONFIG_BPF_JIT)
BPF_PROG_TYPE(BPF_PROG_TYPE_STRUCT_OPS, bpf_struct_ops,
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 0b0144752d78..fa1ea12ad2cd 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1278,4 +1278,21 @@ struct bpf_sockopt_kern {
s32 retval;
};
+struct bpf_sk_lookup_kern {
+ u16 family;
+ u16 protocol;
+ struct {
+ __be32 saddr;
+ __be32 daddr;
+ } v4;
+ struct {
+ const struct in6_addr *saddr;
+ const struct in6_addr *daddr;
+ } v6;
+ __be16 sport;
+ u16 dport;
+ struct sock *selected_sk;
+ bool no_reuseport;
+};
+
#endif /* __LINUX_FILTER_H__ */