leandrof/linux
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

tcp-zerocopy: Return inq along with tcp receive zerocopy.

Browse Source 
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 <arjunroy@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
Arjun Roy 2020-02-14 15:30:49 -08:00 committed by David S. Miller
parent 8c8da5b8ea
commit c8856c0514
2 changed files with 15 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
include/uapi/linux/tcp.h
View File

@ -345,5 +345,6 @@ struct tcp_zerocopy_receive {
__u64 address; /* in: address of mapping */ __u64 address; /* in: address of mapping */
__u32 length; /* in/out: number of bytes to map/mapped */ __u32 length; /* in/out: number of bytes to map/mapped */
__u32 recv_skip_hint; /* out: amount of bytes to skip */ __u32 recv_skip_hint; /* out: amount of bytes to skip */
__u32 inq; /* out: amount of bytes in read queue */
}; };
#endif /* _UAPI_LINUX_TCP_H */ #endif /* _UAPI_LINUX_TCP_H */

15
net/ipv4/tcp.c
View File

@ -3667,13 +3667,26 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
if (get_user(len, optlen)) if (get_user(len, optlen))
return -EFAULT; return -EFAULT;
if (len != sizeof(zc)) if (len < offsetofend(struct tcp_zerocopy_receive, length))
return -EINVAL; return -EINVAL;
if (len > sizeof(zc))
len = sizeof(zc);
if (copy_from_user(&zc, optval, len)) if (copy_from_user(&zc, optval, len))
return -EFAULT; return -EFAULT;
lock_sock(sk); lock_sock(sk);
err = tcp_zerocopy_receive(sk, &zc); err = tcp_zerocopy_receive(sk, &zc);
release_sock(sk); 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)) if (!err && copy_to_user(optval, &zc, len))
err = -EFAULT; err = -EFAULT;
return err; return err;