Re: [PATCH net-next 3/3] net/smc: Cork when sendpage with MSG_SENDPAGE_NOTLAST flag

[Stefan Raspl <raspl@linux.ibm.com>]

On 1/30/22 19:02, Tony Lu wrote:
> This introduces a new corked flag, MSG_SENDPAGE_NOTLAST, which is
> involved in syscall sendfile() [1], it indicates this is not the last
> page. So we can cork the data until the page is not specify this flag.
> It has the same effect as MSG_MORE, but existed in sendfile() only.
> 
> This patch adds a option MSG_SENDPAGE_NOTLAST for corking data, try to
> cork more data before sending when using sendfile(), which acts like
> TCP's behaviour. Also, this reimplements the default sendpage to inform
> that it is supported to some extent.
> 
> [1] https://man7.org/linux/man-pages/man2/sendfile.2.html
> 
> Signed-off-by: Tony Lu <tonylu@linux.alibaba.com>
> ---
>   net/smc/af_smc.c |  4 +++-
>   net/smc/smc_tx.c | 19 ++++++++++++++++++-
>   net/smc/smc_tx.h |  2 ++
>   3 files changed, 23 insertions(+), 2 deletions(-)
> 
> diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
> index ef021ec6b361..8b78010afe01 100644
> --- a/net/smc/af_smc.c
> +++ b/net/smc/af_smc.c
> @@ -2729,8 +2729,10 @@ static ssize_t smc_sendpage(struct socket *sock, struct page *page,
>   		rc = kernel_sendpage(smc->clcsock, page, offset,
>   				     size, flags);
>   	} else {
> +		lock_sock(sk);
> +		rc = smc_tx_sendpage(smc, page, offset, size, flags);
> +		release_sock(sk);
>   		SMC_STAT_INC(smc, sendpage_cnt);
> -		rc = sock_no_sendpage(sock, page, offset, size, flags);
>   	}
>   
>   out:
> diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c
> index 9cec62cae7cb..a96ce162825e 100644
> --- a/net/smc/smc_tx.c
> +++ b/net/smc/smc_tx.c
> @@ -235,7 +235,8 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len)
>   		 */
>   		if ((msg->msg_flags & MSG_OOB) && !send_remaining)
>   			conn->urg_tx_pend = true;
> -		if ((msg->msg_flags & MSG_MORE || smc_tx_is_corked(smc)) &&
> +		if ((msg->msg_flags & MSG_MORE || smc_tx_is_corked(smc) ||
> +		     msg->msg_flags & MSG_SENDPAGE_NOTLAST) &&
>   		    (atomic_read(&conn->sndbuf_space)))
>   			/* for a corked socket defer the RDMA writes if
>   			 * sndbuf_space is still available. The applications
> @@ -257,6 +258,22 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len)
>   	return rc;
>   }
>   
> +int smc_tx_sendpage(struct smc_sock *smc, struct page *page, int offset,
> +		    size_t size, int flags)
> +{
> +	struct msghdr msg = {.msg_flags = flags};
> +	char *kaddr = kmap(page);
> +	struct kvec iov;
> +	int rc;
> +
> +	iov.iov_base = kaddr + offset;
> +	iov.iov_len = size;
> +	iov_iter_kvec(&msg.msg_iter, WRITE, &iov, 1, size);
> +	rc = smc_tx_sendmsg(smc, &msg, size);
> +	kunmap(page);
> +	return rc;
> +}
> +
>   /***************************** sndbuf consumer *******************************/
>   
>   /* sndbuf consumer: actual data transfer of one target chunk with ISM write */
> diff --git a/net/smc/smc_tx.h b/net/smc/smc_tx.h
> index a59f370b8b43..34b578498b1f 100644
> --- a/net/smc/smc_tx.h
> +++ b/net/smc/smc_tx.h
> @@ -31,6 +31,8 @@ void smc_tx_pending(struct smc_connection *conn);
>   void smc_tx_work(struct work_struct *work);
>   void smc_tx_init(struct smc_sock *smc);
>   int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len);
> +int smc_tx_sendpage(struct smc_sock *smc, struct page *page, int offset,
> +		    size_t size, int flags);
>   int smc_tx_sndbuf_nonempty(struct smc_connection *conn);
>   void smc_tx_sndbuf_nonfull(struct smc_sock *smc);
>   void smc_tx_consumer_update(struct smc_connection *conn, bool force);
> 

Reviewed-by: Stefan Raspl <raspl@linux.ibm.com>