bpf: sockmap sample program

This program binds a program to a cgroup and then matches hard
coded IP addresses and adds these to a sockmap.

This will receive messages from the backend and send them to
the client.

     client:X <---> frontend:10000 client:X <---> backend:10001

To keep things simple this is only designed for 1:1 connections
using hard coded values. A more complete example would allow many
backends and clients.

To run,

 # sockmap <cgroup2_dir>

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

4 files changed, 67 insertions, 4 deletions

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index bf3b2e230455..2d97dd27c8f6 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -110,6 +110,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_ARRAY_OF_MAPS,
 	BPF_MAP_TYPE_HASH_OF_MAPS,
 	BPF_MAP_TYPE_DEVMAP,
+	BPF_MAP_TYPE_SOCKMAP,
 };
 
 enum bpf_prog_type {
@@ -127,6 +128,7 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_LWT_OUT,
 	BPF_PROG_TYPE_LWT_XMIT,
 	BPF_PROG_TYPE_SOCK_OPS,
+	BPF_PROG_TYPE_SK_SKB,
 };
 
 enum bpf_attach_type {
@@ -134,11 +136,18 @@ enum bpf_attach_type {
 	BPF_CGROUP_INET_EGRESS,
 	BPF_CGROUP_INET_SOCK_CREATE,
 	BPF_CGROUP_SOCK_OPS,
+	BPF_CGROUP_SMAP_INGRESS,
 	__MAX_BPF_ATTACH_TYPE
 };
 
 #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
 
+enum bpf_sockmap_flags {
+	BPF_SOCKMAP_UNSPEC,
+	BPF_SOCKMAP_STRPARSER,
+	__MAX_BPF_SOCKMAP_FLAG
+};
+
 /* If BPF_F_ALLOW_OVERRIDE flag is used in BPF_PROG_ATTACH command
  * to the given target_fd cgroup the descendent cgroup will be able to
  * override effective bpf program that was inherited from this cgroup
@@ -210,6 +219,7 @@ union bpf_attr {
 		__u32		attach_bpf_fd;	/* eBPF program to attach */
 		__u32		attach_type;
 		__u32		attach_flags;
+		__u32		attach_bpf_fd2;
 	};
 
 	struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */
@@ -545,6 +555,23 @@ union bpf_attr {
  *     @mode: operation mode (enum bpf_adj_room_mode)
  *     @flags: reserved for future use
  *     Return: 0 on success or negative error code
+ *
+ * int bpf_sk_redirect_map(map, key, flags)
+ *     Redirect skb to a sock in map using key as a lookup key for the
+ *     sock in map.
+ *     @map: pointer to sockmap
+ *     @key: key to lookup sock in map
+ *     @flags: reserved for future use
+ *     Return: SK_REDIRECT
+ *
+ * int bpf_sock_map_update(skops, map, key, flags, map_flags)
+ *	@skops: pointer to bpf_sock_ops
+ *	@map: pointer to sockmap to update
+ *	@key: key to insert/update sock in map
+ *	@flags: same flags as map update elem
+ *	@map_flags: sock map specific flags
+ *	   bit 1: Enable strparser
+ *	   other bits: reserved
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -598,7 +625,9 @@ union bpf_attr {
 	FN(set_hash),			\
 	FN(setsockopt),			\
 	FN(skb_adjust_room),		\
-	FN(redirect_map),
+	FN(redirect_map),		\
+	FN(sk_redirect_map),		\
+	FN(sock_map_update),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -675,6 +704,15 @@ struct __sk_buff {
 	__u32 data;
 	__u32 data_end;
 	__u32 napi_id;
+
+	/* accessed by BPF_PROG_TYPE_sk_skb types */
+	__u32 family;
+	__u32 remote_ip4;	/* Stored in network byte order */
+	__u32 local_ip4;	/* Stored in network byte order */
+	__u32 remote_ip6[4];	/* Stored in network byte order */
+	__u32 local_ip6[4];	/* Stored in network byte order */
+	__u32 remote_port;	/* Stored in network byte order */
+	__u32 local_port;	/* stored in host byte order */
 };
 
 struct bpf_tunnel_key {
@@ -734,6 +772,12 @@ struct xdp_md {
 	__u32 data_end;
 };
 
+enum sk_action {
+	SK_ABORTED = 0,
+	SK_DROP,
+	SK_REDIRECT,
+};
+
 #define BPF_TAG_SIZE	8
 
 struct bpf_prog_info {
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index e5bbb090bf88..77660157a684 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -211,20 +211,28 @@ int bpf_obj_get(const char *pathname)
 	return sys_bpf(BPF_OBJ_GET, &attr, sizeof(attr));
 }
 
-int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type,
-		    unsigned int flags)
+int __bpf_prog_attach(int prog_fd1, int prog_fd2, int target_fd,
+		      enum bpf_attach_type type,
+		      unsigned int flags)
 {
 	union bpf_attr attr;
 
 	bzero(&attr, sizeof(attr));
 	attr.target_fd	   = target_fd;
-	attr.attach_bpf_fd = prog_fd;
+	attr.attach_bpf_fd = prog_fd1;
+	attr.attach_bpf_fd2 = prog_fd2;
 	attr.attach_type   = type;
 	attr.attach_flags  = flags;
 
 	return sys_bpf(BPF_PROG_ATTACH, &attr, sizeof(attr));
 }
 
+int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type,
+		    unsigned int flags)
+{
+	return __bpf_prog_attach(prog_fd, 0, target_fd, type, flags);
+}
+
 int bpf_prog_detach(int target_fd, enum bpf_attach_type type)
 {
 	union bpf_attr attr;
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 418c86e69bcb..eaee585c1cea 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -50,6 +50,10 @@ int bpf_obj_pin(int fd, const char *pathname);
 int bpf_obj_get(const char *pathname);
 int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type,
 		    unsigned int flags);
+int __bpf_prog_attach(int prog1, int prog2,
+		      int attachable_fd,
+		      enum bpf_attach_type type,
+		      unsigned int flags);
 int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type);
 int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size,
 		      void *data_out, __u32 *size_out, __u32 *retval,
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index acbd60519467..73092d4a898e 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -65,6 +65,13 @@ static int (*bpf_xdp_adjust_head)(void *ctx, int offset) =
 static int (*bpf_setsockopt)(void *ctx, int level, int optname, void *optval,
 			     int optlen) =
 	(void *) BPF_FUNC_setsockopt;
+static int (*bpf_sk_redirect_map)(void *map, int key, int flags) =
+	(void *) BPF_FUNC_sk_redirect_map;
+static int (*bpf_sock_map_update)(void *map, void *key, void *value,
+				  unsigned long long flags,
+				  unsigned long long map_lags) =
+	(void *) BPF_FUNC_sock_map_update;
+
 
 /* llvm builtin functions that eBPF C program may use to
  * emit BPF_LD_ABS and BPF_LD_IND instructions