Re: [RFC PATCH v7 04/22] af_vsock: implement SEQPACKET receive loop

[Arseny Krasnov <arseny.krasnov@kaspersky.com>]

On 25.03.2021 12:34, Stefano Garzarella wrote:
> On Tue, Mar 23, 2021 at 04:10:03PM +0300, Arseny Krasnov wrote:
>> This adds receive loop for SEQPACKET. It looks like receive loop for
>> STREAM, but there is a little bit difference:
>> 1) It doesn't call notify callbacks.
>> 2) It doesn't care about 'SO_SNDLOWAT' and 'SO_RCVLOWAT' values, because
>>   there is no sense for these values in SEQPACKET case.
>> 3) It waits until whole record is received or error is found during
>>   receiving.
>> 4) It processes and sets 'MSG_TRUNC' flag.
>>
>> So to avoid extra conditions for two types of socket inside one loop, two
>> independent functions were created.
>>
>> Signed-off-by: Arseny Krasnov <arseny.krasnov@kaspersky.com>
>> ---
>> v6 -> v7:
>> 'seqpacket_get_len' callback now removed, length of message is returned
>>  by 'seqpacket_dequeue' callback.
>>
>> include/net/af_vsock.h   |  4 ++
>> net/vmw_vsock/af_vsock.c | 88 +++++++++++++++++++++++++++++++++++++++-
>> 2 files changed, 91 insertions(+), 1 deletion(-)
>>
>> diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
>> index b1c717286993..74ac8a4c4168 100644
>> --- a/include/net/af_vsock.h
>> +++ b/include/net/af_vsock.h
>> @@ -135,6 +135,10 @@ struct vsock_transport {
>> 	bool (*stream_is_active)(struct vsock_sock *);
>> 	bool (*stream_allow)(u32 cid, u32 port);
>>
>> +	/* SEQ_PACKET. */
>> +	int (*seqpacket_dequeue)(struct vsock_sock *vsk, struct msghdr *msg,
>> +				 int flags, bool *msg_ready, size_t *record_len);
>> +
> Why not using ssize_t as return value and return the length or a 
> negative value in case of error?
>
> In this way we can remove the 'record_len' parameter.
Ok, i think it is possible
>
>> 	/* Notification. */
>> 	int (*notify_poll_in)(struct vsock_sock *, size_t, bool *);
>> 	int (*notify_poll_out)(struct vsock_sock *, size_t, bool *);
>> diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
>> index 0bc661e54262..fa0c37f97330 100644
>> --- a/net/vmw_vsock/af_vsock.c
>> +++ b/net/vmw_vsock/af_vsock.c
>> @@ -1973,6 +1973,89 @@ static int __vsock_stream_recvmsg(struct sock 
>> *sk, struct msghdr *msg,
>> 	return err;
>> }
>>
>> +static int __vsock_seqpacket_recvmsg(struct sock *sk, struct msghdr 
>> *msg,
>> +				     size_t len, int flags)
>> +{
>> +	const struct vsock_transport *transport;
>> +	const struct iovec *orig_iov;
>> +	unsigned long orig_nr_segs;
>> +	bool msg_ready;
>> +	struct vsock_sock *vsk;
>> +	size_t record_len;
>> +	long timeout;
>> +	int err = 0;
>> +	DEFINE_WAIT(wait);
>> +
>> +	vsk = vsock_sk(sk);
>> +	transport = vsk->transport;
>> +
>> +	timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
>> +	orig_nr_segs = msg->msg_iter.nr_segs;
>> +	orig_iov = msg->msg_iter.iov;
>> +	msg_ready = false;
>> +	record_len = 0;
>> +
>> +	while (1) {
>> +		err = vsock_wait_data(sk, &wait, timeout, NULL, 0);
>> +
>> +		if (err <= 0) {
>> +			/* In case of any loop break(timeout, signal
>> +			 * interrupt or shutdown), we report user that
>> +			 * nothing was copied.
>> +			 */
>> +			err = 0;
>> +			break;
>> +		}
>> +
>> +		err = transport->seqpacket_dequeue(vsk, msg, flags, &msg_ready, &record_len);
>> +
>> +		if (err < 0) {
>> +			if (err == -EAGAIN) {
>> +				iov_iter_init(&msg->msg_iter, READ,
>> +					      orig_iov, orig_nr_segs,
>> +					      len);
>> +				/* Clear 'MSG_EOR' here, because dequeue
>> +				 * callback above set it again if it was
>> +				 * set by sender. This 'MSG_EOR' is from
>> +				 * dropped record.
>> +				 */
>> +				msg->msg_flags &= ~MSG_EOR;
>> +				record_len = 0;
>> +				continue;
>> +			}
>> +
>> +			err = -ENOMEM;
>> +			break;
>> +		}
>> +
>> +		if (msg_ready)
>> +			break;
>> +	}
>> +
>> +	if (sk->sk_err)
>> +		err = -sk->sk_err;
>> +	else if (sk->sk_shutdown & RCV_SHUTDOWN)
>> +		err = 0;
>> +
>> +	if (msg_ready) {
> If 'err' is not 0, should we skip this branch?
Ack
>
>> +		/* User sets MSG_TRUNC, so return real length of
>> +		 * packet.
>> +		 */
>> +		if (flags & MSG_TRUNC)
>> +			err = record_len;
>> +		else
>> +			err = len - msg->msg_iter.count;
>> +
>> +		/* Always set MSG_TRUNC if real length of packet is
>> +		 * bigger than user's buffer.
>> +		 */
>> +		if (record_len > len)
>> +			msg->msg_flags |= MSG_TRUNC;
>> +	}
>> +
>> +	return err;
>> +}
>> +
>> static int
>> vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
>> 			  int flags)
>> @@ -2028,7 +2111,10 @@ vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
>> 		goto out;
>> 	}
>>
>> -	err = __vsock_stream_recvmsg(sk, msg, len, flags);
>> +	if (sk->sk_type == SOCK_STREAM)
>> +		err = __vsock_stream_recvmsg(sk, msg, len, flags);
>> +	else
>> +		err = __vsock_seqpacket_recvmsg(sk, msg, len, flags);
>>
>> out:
>> 	release_sock(sk);
>> -- 
>> 2.25.1
>>
>