| Message ID | 20230603204939.1598818-14-AVKrasnov@sberdevices.ru (mailing list archive) |
|---|---|
| State | RFC |
| Delegated to: | Netdev Maintainers |
| Headers | show |
| Series | vsock: MSG_ZEROCOPY flag support | expand |
diff --git a/net/core/sock.c b/net/core/sock.c index 5440e67bcfe3..d558e541e6d7 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1452,9 +1452,11 @@ int sk_setsockopt(struct sock *sk, int level, int optname, (sk->sk_type == SOCK_DGRAM && sk->sk_protocol == IPPROTO_UDP))) ret = -EOPNOTSUPP; - } else if (sk->sk_family != PF_RDS) { + } else if (sk->sk_family != PF_RDS && + sk->sk_family != PF_VSOCK) { ret = -EOPNOTSUPP; } + if (!ret) { if (val < 0 || val > 1) ret = -EINVAL;
PF_VSOCK supports MSG_ZEROCOPY transmission, so SO_ZEROCOPY could be enabled. PF_VSOCK implementation is a little bit special comparing to PF_INET - MSG_ZEROCOPY support depends on transport layer of PF_VSOCK, but here we can't "ask" its transport, so setting of this option is always allowed, but if some transport doesn't support zerocopy tx, send callback of PF_VSOCK will return -EOPNOTSUPP. Signed-off-by: Arseniy Krasnov <AVKrasnov@sberdevices.ru> --- net/core/sock.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)