From c8856c051454909e5059df4e81c77b9c366c5515 Mon Sep 17 00:00:00 2001 From: Arjun Roy Date: Fri, 14 Feb 2020 15:30:49 -0800 Subject: [PATCH] tcp-zerocopy: Return inq along with tcp receive zerocopy. This patchset is intended to reduce the number of extra system calls imposed by TCP receive zerocopy. For ping-pong RPC style workloads, this patchset has demonstrated a system call reduction of about 30% when coupled with userspace changes. For applications using edge-triggered epoll, returning inq along with the result of tcp receive zerocopy could remove the need to call recvmsg()=-EAGAIN after a successful zerocopy. Generally speaking, since normally we would need to perform a recvmsg() call for every successful small RPC read via TCP receive zerocopy, returning inq can reduce the number of system calls performed by approximately half. Signed-off-by: Arjun Roy Signed-off-by: Eric Dumazet Signed-off-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- include/uapi/linux/tcp.h | 1 + net/ipv4/tcp.c | 15 ++++++++++++++- 2 files changed, 15 insertions(+), 1 deletion(-) diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index fd9eb8f6bcae..548f480b9c66 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -345,5 +345,6 @@ struct tcp_zerocopy_receive { __u64 address; /* in: address of mapping */ __u32 length; /* in/out: number of bytes to map/mapped */ __u32 recv_skip_hint; /* out: amount of bytes to skip */ + __u32 inq; /* out: amount of bytes in read queue */ }; #endif /* _UAPI_LINUX_TCP_H */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index eb2d80519f8e..a697f1455f8d 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3667,13 +3667,26 @@ static int do_tcp_getsockopt(struct sock *sk, int level, if (get_user(len, optlen)) return -EFAULT; - if (len != sizeof(zc)) + if (len < offsetofend(struct tcp_zerocopy_receive, length)) return -EINVAL; + if (len > sizeof(zc)) + len = sizeof(zc); if (copy_from_user(&zc, optval, len)) return -EFAULT; lock_sock(sk); err = tcp_zerocopy_receive(sk, &zc); release_sock(sk); + switch (len) { + case sizeof(zc): + case offsetofend(struct tcp_zerocopy_receive, inq): + goto zerocopy_rcv_inq; + case offsetofend(struct tcp_zerocopy_receive, length): + default: + goto zerocopy_rcv_out; + } +zerocopy_rcv_inq: + zc.inq = tcp_inq_hint(sk); +zerocopy_rcv_out: if (!err && copy_to_user(optval, &zc, len)) err = -EFAULT; return err;