bpf: Remove extra lock_sock for TCP_ZEROCOPY_RECEIVE

Add custom implementation of getsockopt hook for TCP_ZEROCOPY_RECEIVE.
We skip generic hooks for TCP_ZEROCOPY_RECEIVE and have a custom
call in do_tcp_getsockopt using the on-stack data. This removes
3% overhead for locking/unlocking the socket.

Without this patch:
     3.38%     0.07%  tcp_mmap  [kernel.kallsyms]  [k] __cgroup_bpf_run_filter_getsockopt
            |
             --3.30%--__cgroup_bpf_run_filter_getsockopt
                       |
                        --0.81%--__kmalloc

With the patch applied:
     0.52%     0.12%  tcp_mmap  [kernel.kallsyms]  [k] __cgroup_bpf_run_filter_getsockopt_kern

Note, exporting uapi/tcp.h requires removing netinet/tcp.h
from test_progs.h because those headers have confliciting
definitions.

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20210115163501.805133-2-sdf@google.com

4 files changed, 31 insertions, 0 deletions

diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
index 9a8f47fc0b91..37c5494a0381 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2019 Facebook */
 
 #include <linux/err.h>
+#include <netinet/tcp.h>
 #include <test_progs.h>
 #include "bpf_dctcp.skel.h"
 #include "bpf_cubic.skel.h"
diff --git a/tools/testing/selftests/bpf/prog_tests/cls_redirect.c b/tools/testing/selftests/bpf/prog_tests/cls_redirect.c
index 9781d85cb223..e075d03ab630 100644
--- a/tools/testing/selftests/bpf/prog_tests/cls_redirect.c
+++ b/tools/testing/selftests/bpf/prog_tests/cls_redirect.c
@@ -7,6 +7,7 @@
 #include <string.h>
 
 #include <linux/pkt_cls.h>
+#include <netinet/tcp.h>
 
 #include <test_progs.h>
 
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
index 85f73261fab0..b8b48cac2ac3 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 // Copyright (c) 2020 Cloudflare
 #include <error.h>
+#include <netinet/tcp.h>
 
 #include "test_progs.h"
 #include "test_skmsg_load_helpers.skel.h"
diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c
index b25c9c45c148..d5b44b135c00 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c
@@ -2,6 +2,12 @@
 #include <test_progs.h>
 #include "cgroup_helpers.h"
 
+#include <linux/tcp.h>
+
+#ifndef SOL_TCP
+#define SOL_TCP IPPROTO_TCP
+#endif
+
 #define SOL_CUSTOM			0xdeadbeef
 
 static int getsetsockopt(void)
@@ -11,6 +17,7 @@ static int getsetsockopt(void)
 		char u8[4];
 		__u32 u32;
 		char cc[16]; /* TCP_CA_NAME_MAX */
+		struct tcp_zerocopy_receive zc;
 	} buf = {};
 	socklen_t optlen;
 	char *big_buf = NULL;
@@ -154,6 +161,27 @@ static int getsetsockopt(void)
 		goto err;
 	}
 
+	/* TCP_ZEROCOPY_RECEIVE triggers */
+	memset(&buf, 0, sizeof(buf));
+	optlen = sizeof(buf.zc);
+	err = getsockopt(fd, SOL_TCP, TCP_ZEROCOPY_RECEIVE, &buf, &optlen);
+	if (err) {
+		log_err("Unexpected getsockopt(TCP_ZEROCOPY_RECEIVE) err=%d errno=%d",
+			err, errno);
+		goto err;
+	}
+
+	memset(&buf, 0, sizeof(buf));
+	buf.zc.address = 12345; /* rejected by BPF */
+	optlen = sizeof(buf.zc);
+	errno = 0;
+	err = getsockopt(fd, SOL_TCP, TCP_ZEROCOPY_RECEIVE, &buf, &optlen);
+	if (errno != EPERM) {
+		log_err("Unexpected getsockopt(TCP_ZEROCOPY_RECEIVE) err=%d errno=%d",
+			err, errno);
+		goto err;
+	}
+
 	free(big_buf);
 	close(fd);
 	return 0;