bpf: Bpf_{g,s}etsockopt for struct bpf_sock_addr

Currently, bpf_getsockopt and bpf_setsockopt helpers operate on the
'struct bpf_sock_ops' context in BPF_PROG_TYPE_SOCK_OPS program.
Let's generalize them and make them available for 'struct bpf_sock_addr'.
That way, in the future, we can allow those helpers in more places.

As an example, let's expose those 'struct bpf_sock_addr' based helpers to
BPF_CGROUP_INET{4,6}_CONNECT hooks. That way we can override CC before the
connection is made.

v3:
* Expose custom helpers for bpf_sock_addr context instead of doing
  generic bpf_sock argument (as suggested by Daniel). Even with
  try_socket_lock that doesn't sleep we have a problem where context sk
  is already locked and socket lock is non-nestable.

v2:
* s/BPF_PROG_TYPE_CGROUP_SOCKOPT/BPF_PROG_TYPE_SOCK_OPS/

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20200430233152.199403-1-sdf@google.com

3 files changed, 59 insertions, 2 deletions

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 705e4822f997..b3643e27e264 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1587,7 +1587,7 @@ union bpf_attr {
  * 	Return
  * 		0
  *
- * int bpf_setsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, void *optval, int optlen)
+ * int bpf_setsockopt(void *bpf_socket, int level, int optname, void *optval, int optlen)
  * 	Description
  * 		Emulate a call to **setsockopt()** on the socket associated to
  * 		*bpf_socket*, which must be a full socket. The *level* at
@@ -1595,6 +1595,11 @@ union bpf_attr {
  * 		must be specified, see **setsockopt(2)** for more information.
  * 		The option value of length *optlen* is pointed by *optval*.
  *
+ * 		*bpf_socket* should be one of the following:
+ * 		* **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**.
+ * 		* **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**
+ * 		  and **BPF_CGROUP_INET6_CONNECT**.
+ *
  * 		This helper actually implements a subset of **setsockopt()**.
  * 		It supports the following *level*\ s:
  *
@@ -1789,7 +1794,7 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
- * int bpf_getsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, void *optval, int optlen)
+ * int bpf_getsockopt(void *bpf_socket, int level, int optname, void *optval, int optlen)
  * 	Description
  * 		Emulate a call to **getsockopt()** on the socket associated to
  * 		*bpf_socket*, which must be a full socket. The *level* at
@@ -1798,6 +1803,11 @@ union bpf_attr {
  * 		The retrieved value is stored in the structure pointed by
  * 		*opval* and of length *optlen*.
  *
+ * 		*bpf_socket* should be one of the following:
+ * 		* **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**.
+ * 		* **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**
+ * 		  and **BPF_CGROUP_INET6_CONNECT**.
+ *
  * 		This helper actually implements a subset of **getsockopt()**.
  * 		It supports the following *level*\ s:
  *
diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index 60e3ae5d4e48..6e5b94c036ca 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -37,3 +37,4 @@ CONFIG_IPV6_SIT=m
 CONFIG_BPF_JIT=y
 CONFIG_BPF_LSM=y
 CONFIG_SECURITY=y
+CONFIG_TCP_CONG_DCTCP=y
diff --git a/tools/testing/selftests/bpf/progs/connect4_prog.c b/tools/testing/selftests/bpf/progs/connect4_prog.c
index ad3c498a8150..972918cd2d7f 100644
--- a/tools/testing/selftests/bpf/progs/connect4_prog.c
+++ b/tools/testing/selftests/bpf/progs/connect4_prog.c
@@ -8,6 +8,7 @@
 #include <linux/in.h>
 #include <linux/in6.h>
 #include <sys/socket.h>
+#include <netinet/tcp.h>
 
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
@@ -16,6 +17,10 @@
 #define DST_REWRITE_IP4		0x7f000001U
 #define DST_REWRITE_PORT4	4444
 
+#ifndef TCP_CA_NAME_MAX
+#define TCP_CA_NAME_MAX 16
+#endif
+
 int _version SEC("version") = 1;
 
 __attribute__ ((noinline))
@@ -33,6 +38,43 @@ int do_bind(struct bpf_sock_addr *ctx)
 	return 1;
 }
 
+static __inline int verify_cc(struct bpf_sock_addr *ctx,
+			      char expected[TCP_CA_NAME_MAX])
+{
+	char buf[TCP_CA_NAME_MAX];
+	int i;
+
+	if (bpf_getsockopt(ctx, SOL_TCP, TCP_CONGESTION, &buf, sizeof(buf)))
+		return 1;
+
+	for (i = 0; i < TCP_CA_NAME_MAX; i++) {
+		if (buf[i] != expected[i])
+			return 1;
+		if (buf[i] == 0)
+			break;
+	}
+
+	return 0;
+}
+
+static __inline int set_cc(struct bpf_sock_addr *ctx)
+{
+	char dctcp[TCP_CA_NAME_MAX] = "dctcp";
+	char cubic[TCP_CA_NAME_MAX] = "cubic";
+
+	if (bpf_setsockopt(ctx, SOL_TCP, TCP_CONGESTION, &dctcp, sizeof(dctcp)))
+		return 1;
+	if (verify_cc(ctx, dctcp))
+		return 1;
+
+	if (bpf_setsockopt(ctx, SOL_TCP, TCP_CONGESTION, &cubic, sizeof(cubic)))
+		return 1;
+	if (verify_cc(ctx, cubic))
+		return 1;
+
+	return 0;
+}
+
 SEC("cgroup/connect4")
 int connect_v4_prog(struct bpf_sock_addr *ctx)
 {
@@ -66,6 +108,10 @@ int connect_v4_prog(struct bpf_sock_addr *ctx)
 
 	bpf_sk_release(sk);
 
+	/* Rewrite congestion control. */
+	if (ctx->type == SOCK_STREAM && set_cc(ctx))
+		return 0;
+
 	/* Rewrite destination. */
 	ctx->user_ip4 = bpf_htonl(DST_REWRITE_IP4);
 	ctx->user_port = bpf_htons(DST_REWRITE_PORT4);