bpf: sockmap with sk redirect support

Recently we added a new map type called dev map used to forward XDP
packets between ports (6093ec2dc313). This patches introduces a
similar notion for sockets.

A sockmap allows users to add participating sockets to a map. When
sockets are added to the map enough context is stored with the
map entry to use the entry with a new helper

  bpf_sk_redirect_map(map, key, flags)

This helper (analogous to bpf_redirect_map in XDP) is given the map
and an entry in the map. When called from a sockmap program, discussed
below, the skb will be sent on the socket using skb_send_sock().

With the above we need a bpf program to call the helper from that will
then implement the send logic. The initial site implemented in this
series is the recv_sock hook. For this to work we implemented a map
attach command to add attributes to a map. In sockmap we add two
programs a parse program and a verdict program. The parse program
uses strparser to build messages and pass them to the verdict program.
The parse programs use the normal strparser semantics. The verdict
program is of type SK_SKB.

The verdict program returns a verdict SK_DROP, or  SK_REDIRECT for
now. Additional actions may be added later. When SK_REDIRECT is
returned, expected when bpf program uses bpf_sk_redirect_map(), the
sockmap logic will consult per cpu variables set by the helper routine
and pull the sock entry out of the sock map. This pattern follows the
existing redirect logic in cls and xdp programs.

This gives the flow,

 recv_sock -> str_parser (parse_prog) -> verdict_prog -> skb_send_sock
                                                     \
                                                      -> kfree_skb

As an example use case a message based load balancer may use specific
logic in the verdict program to select the sock to send on.

Sample programs are provided in future patches that hopefully illustrate
the user interfaces. Also selftests are in follow-on patches.

Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 8 insertions, 2 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index d6e1de8ce0fc..a4145e9c74b5 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -16,6 +16,7 @@
 #include <linux/rbtree_latch.h>
 
 struct perf_event;
+struct bpf_prog;
 struct bpf_map;
 
 /* map is generic key/value storage optionally accesible by eBPF programs */
@@ -37,6 +38,8 @@ struct bpf_map_ops {
 	void (*map_fd_put_ptr)(void *ptr);
 	u32 (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf);
 	u32 (*map_fd_sys_lookup_elem)(void *ptr);
+	int (*map_attach)(struct bpf_map *map,
+			  struct bpf_prog *p1, struct bpf_prog *p2);
 };
 
 struct bpf_map {
@@ -138,8 +141,6 @@ enum bpf_reg_type {
 	PTR_TO_PACKET_END,	 /* skb->data + headlen */
 };
 
-struct bpf_prog;
-
 /* The information passed from prog-specific *_is_valid_access
  * back to the verifier.
  */
@@ -312,6 +313,7 @@ int bpf_check(struct bpf_prog **fp, union bpf_attr *attr);
 
 /* Map specifics */
 struct net_device  *__dev_map_lookup_elem(struct bpf_map *map, u32 key);
+struct sock  *__sock_map_lookup_elem(struct bpf_map *map, u32 key);
 void __dev_map_insert_ctx(struct bpf_map *map, u32 index);
 void __dev_map_flush(struct bpf_map *map);
 
@@ -391,6 +393,7 @@ extern const struct bpf_func_proto bpf_get_current_comm_proto;
 extern const struct bpf_func_proto bpf_skb_vlan_push_proto;
 extern const struct bpf_func_proto bpf_skb_vlan_pop_proto;
 extern const struct bpf_func_proto bpf_get_stackid_proto;
+extern const struct bpf_func_proto bpf_sock_map_update_proto;
 
 /* Shared helpers among cBPF and eBPF. */
 void bpf_user_rnd_init_once(void);
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index 4b72db30dacf..fa805074d168 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -38,4 +38,5 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY_OF_MAPS, array_of_maps_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops)
 #ifdef CONFIG_NET
 BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops)
+BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops)
 #endif
diff --git a/include/linux/filter.h b/include/linux/filter.h
index d19ed3c15e1e..7015116331af 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -727,6 +727,8 @@ void xdp_do_flush_map(void);
 void bpf_warn_invalid_xdp_action(u32 act);
 void bpf_warn_invalid_xdp_redirect(u32 ifindex);
 
+struct sock *do_sk_redirect_map(void);
+
 #ifdef CONFIG_BPF_JIT
 extern int bpf_jit_enable;
 extern int bpf_jit_harden;