bpf: Add tcp_notsent_lowat bpf setsockopt

Adding support for TCP_NOTSENT_LOWAT sockoption (https://lwn.net/Articles/560082/)
in tcp bpf programs.

Signed-off-by: Nikita V. Shirokov <tehnerd@tehnerd.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20201009070325.226855-1-tehnerd@tehnerd.com

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index d83561e..42d2df7 100644 (file)
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1698,7 +1698,7 @@ union bpf_attr {
  *               **TCP_CONGESTION**, **TCP_BPF_IW**,
  *               **TCP_BPF_SNDCWND_CLAMP**, **TCP_SAVE_SYN**,
  *               **TCP_KEEPIDLE**, **TCP_KEEPINTVL**, **TCP_KEEPCNT**,
- *               **TCP_SYNCNT**, **TCP_USER_TIMEOUT**.
+ *               **TCP_SYNCNT**, **TCP_USER_TIMEOUT**, **TCP_NOTSENT_LOWAT**.
  *             * **IPPROTO_IP**, which supports *optname* **IP_TOS**.
  *             * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**.
  *     Return

diff --git a/net/core/filter.c b/net/core/filter.c
index 05df737..5da44b1 100644 (file)
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4827,6 +4827,10 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname,
                                else
                                        icsk->icsk_user_timeout = val;
                                break;
+                       case TCP_NOTSENT_LOWAT:
+                               tp->notsent_lowat = val;
+                               sk->sk_write_space(sk);
+                               break;
                        default:
                                ret = -EINVAL;
                        }

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index d83561e..42d2df7 100644 (file)
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1698,7 +1698,7 @@ union bpf_attr {
  *               **TCP_CONGESTION**, **TCP_BPF_IW**,
  *               **TCP_BPF_SNDCWND_CLAMP**, **TCP_SAVE_SYN**,
  *               **TCP_KEEPIDLE**, **TCP_KEEPINTVL**, **TCP_KEEPCNT**,
- *               **TCP_SYNCNT**, **TCP_USER_TIMEOUT**.
+ *               **TCP_SYNCNT**, **TCP_USER_TIMEOUT**, **TCP_NOTSENT_LOWAT**.
  *             * **IPPROTO_IP**, which supports *optname* **IP_TOS**.
  *             * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**.
  *     Return

diff --git a/tools/testing/selftests/bpf/progs/connect4_prog.c b/tools/testing/selftests/bpf/progs/connect4_prog.c
index b1b2773..a943d39 100644 (file)
--- a/tools/testing/selftests/bpf/progs/connect4_prog.c
+++ b/tools/testing/selftests/bpf/progs/connect4_prog.c
@@ -23,6 +23,10 @@
 #define TCP_CA_NAME_MAX 16
 #endif
 
+#ifndef TCP_NOTSENT_LOWAT
+#define TCP_NOTSENT_LOWAT 25
+#endif
+
 #ifndef IFNAMSIZ
 #define IFNAMSIZ 16
 #endif
@@ -128,6 +132,18 @@ static __inline int set_keepalive(struct bpf_sock_addr *ctx)
        return 0;
 }
 
+static __inline int set_notsent_lowat(struct bpf_sock_addr *ctx)
+{
+       int lowat = 65535;
+
+       if (ctx->type == SOCK_STREAM) {
+               if (bpf_setsockopt(ctx, SOL_TCP, TCP_NOTSENT_LOWAT, &lowat, sizeof(lowat)))
+                       return 1;
+       }
+
+       return 0;
+}
+
 SEC("cgroup/connect4")
 int connect_v4_prog(struct bpf_sock_addr *ctx)
 {
@@ -148,6 +164,9 @@ int connect_v4_prog(struct bpf_sock_addr *ctx)
        if (set_keepalive(ctx))
                return 0;
 
+       if (set_notsent_lowat(ctx))
+               return 0;
+
        if (ctx->type != SOCK_STREAM && ctx->type != SOCK_DGRAM)
                return 0;
        else if (ctx->type == SOCK_STREAM)