netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Simon Horman <simon.horman@corigine.com>
To: Arseniy Krasnov <AVKrasnov@sberdevices.ru>
Cc: Stefan Hajnoczi <stefanha@redhat.com>,
	Stefano Garzarella <sgarzare@redhat.com>,
	"David S. Miller" <davem@davemloft.net>,
	Eric Dumazet <edumazet@google.com>,
	Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
	"Michael S. Tsirkin" <mst@redhat.com>,
	Jason Wang <jasowang@redhat.com>,
	Bobby Eshleman <bobby.eshleman@bytedance.com>,
	kvm@vger.kernel.org, virtualization@lists.linux-foundation.org,
	netdev@vger.kernel.org, linux-kernel@vger.kernel.org,
	kernel@sberdevices.ru, oxffffaa@gmail.com
Subject: Re: [RFC PATCH v3 05/17] vsock/virtio: MSG_ZEROCOPY flag support
Date: Mon, 22 May 2023 15:11:46 +0200	[thread overview]
Message-ID: <ZGtqEghjjiBnvEBW@corigine.com> (raw)
In-Reply-To: <20230522073950.3574171-6-AVKrasnov@sberdevices.ru>

On Mon, May 22, 2023 at 10:39:38AM +0300, Arseniy Krasnov wrote:
> This adds handling of MSG_ZEROCOPY flag on transmission path: if this
> flag is set and zerocopy transmission is possible, then non-linear skb
> will be created and filled with the pages of user's buffer. Pages of
> user's buffer are locked in memory by 'get_user_pages()'.
> 
> Signed-off-by: Arseniy Krasnov <AVKrasnov@sberdevices.ru>
> ---
>  net/vmw_vsock/virtio_transport_common.c | 305 +++++++++++++++++++-----
>  1 file changed, 243 insertions(+), 62 deletions(-)
> 
> diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
> index 9854f48a0544..5acf824afe41 100644
> --- a/net/vmw_vsock/virtio_transport_common.c
> +++ b/net/vmw_vsock/virtio_transport_common.c
> @@ -37,73 +37,161 @@ virtio_transport_get_ops(struct vsock_sock *vsk)
>  	return container_of(t, struct virtio_transport, transport);
>  }
>  
> -/* Returns a new packet on success, otherwise returns NULL.
> - *
> - * If NULL is returned, errp is set to a negative errno.
> - */
> -static struct sk_buff *
> -virtio_transport_alloc_skb(struct virtio_vsock_pkt_info *info,
> -			   size_t len,
> -			   u32 src_cid,
> -			   u32 src_port,
> -			   u32 dst_cid,
> -			   u32 dst_port)
> -{
> -	const size_t skb_len = VIRTIO_VSOCK_SKB_HEADROOM + len;
> -	struct virtio_vsock_hdr *hdr;
> -	struct sk_buff *skb;
> -	void *payload;
> -	int err;
> +static bool virtio_transport_can_zcopy(struct virtio_vsock_pkt_info *info,
> +				       size_t max_to_send)
> +{
> +	struct iov_iter *iov_iter;
> +	size_t max_skb_cap;
> +	size_t bytes;
> +	int i;
>  
> -	skb = virtio_vsock_alloc_skb(skb_len, GFP_KERNEL);
> -	if (!skb)
> -		return NULL;
> +	if (!info->msg)
> +		return false;
>  
> -	hdr = virtio_vsock_hdr(skb);
> -	hdr->type	= cpu_to_le16(info->type);
> -	hdr->op		= cpu_to_le16(info->op);
> -	hdr->src_cid	= cpu_to_le64(src_cid);
> -	hdr->dst_cid	= cpu_to_le64(dst_cid);
> -	hdr->src_port	= cpu_to_le32(src_port);
> -	hdr->dst_port	= cpu_to_le32(dst_port);
> -	hdr->flags	= cpu_to_le32(info->flags);
> -	hdr->len	= cpu_to_le32(len);
> +	if (!(info->flags & MSG_ZEROCOPY) && !info->msg->msg_ubuf)
> +		return false;
>  
> -	if (info->msg && len > 0) {
> -		payload = skb_put(skb, len);
> -		err = memcpy_from_msg(payload, info->msg, len);
> -		if (err)
> -			goto out;
> +	iov_iter = &info->msg->msg_iter;
> +
> +	if (iter_is_ubuf(iov_iter)) {
> +		if (offset_in_page(iov_iter->ubuf))
> +			return false;
> +
> +		return true;
> +	}
> +
> +	if (!iter_is_iovec(iov_iter))
> +		return false;
> +
> +	if (iov_iter->iov_offset)
> +		return false;
> +
> +	/* We can't send whole iov. */
> +	if (iov_iter->count > max_to_send)
> +		return false;
> +
> +	for (bytes = 0, i = 0; i < iov_iter->nr_segs; i++) {
> +		const struct iovec *iovec;
> +		int pages_in_elem;
> +
> +		iovec = &iov_iter->__iov[i];
> +
> +		/* Base must be page aligned. */
> +		if (offset_in_page(iovec->iov_base))
> +			return false;
>  
> -		if (msg_data_left(info->msg) == 0 &&
> -		    info->type == VIRTIO_VSOCK_TYPE_SEQPACKET) {
> -			hdr->flags |= cpu_to_le32(VIRTIO_VSOCK_SEQ_EOM);
> +		/* Only last element could have non page aligned size. */
> +		if (i != (iov_iter->nr_segs - 1)) {
> +			if (offset_in_page(iovec->iov_len))
> +				return false;
>  
> -			if (info->msg->msg_flags & MSG_EOR)
> -				hdr->flags |= cpu_to_le32(VIRTIO_VSOCK_SEQ_EOR);
> +			pages_in_elem = iovec->iov_len >> PAGE_SHIFT;
> +		} else {
> +			pages_in_elem = round_up(iovec->iov_len, PAGE_SIZE);
> +			pages_in_elem >>= PAGE_SHIFT;
>  		}
> +
> +		bytes += (pages_in_elem * PAGE_SIZE);
>  	}

Hi Arseniy,

bytes is set but the loop above, but seems otherwise unused in this function.

>  
> -	if (info->reply)
> -		virtio_vsock_skb_set_reply(skb);
> +	/* How many bytes we can pack to single skb. Maximum packet
> +	 * buffer size is needed to allow vhost handle such packets,
> +	 * otherwise they will be dropped.
> +	 */
> +	max_skb_cap = min((unsigned int)(MAX_SKB_FRAGS * PAGE_SIZE),
> +			  (unsigned int)VIRTIO_VSOCK_MAX_PKT_BUF_SIZE);

Likewise, max_skb_cap seems to be set but unused in this function.

>  
> -	trace_virtio_transport_alloc_pkt(src_cid, src_port,
> -					 dst_cid, dst_port,
> -					 len,
> -					 info->type,
> -					 info->op,
> -					 info->flags);
> +	return true;
> +}

...

  reply	other threads:[~2023-05-22 13:12 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-05-22  7:39 [RFC PATCH v3 00/17] vsock: MSG_ZEROCOPY flag support Arseniy Krasnov
2023-05-22  7:39 ` [RFC PATCH v3 01/17] vsock/virtio: read data from non-linear skb Arseniy Krasnov
2023-05-22  7:39 ` [RFC PATCH v3 02/17] vhost/vsock: " Arseniy Krasnov
2023-05-22  7:39 ` [RFC PATCH v3 03/17] vsock/virtio: support to send " Arseniy Krasnov
2023-05-22  7:39 ` [RFC PATCH v3 04/17] vsock/virtio: non-linear skb handling for tap Arseniy Krasnov
2023-05-22 13:13   ` Simon Horman
2023-05-22 13:15     ` Arseniy Krasnov
2023-05-22  7:39 ` [RFC PATCH v3 05/17] vsock/virtio: MSG_ZEROCOPY flag support Arseniy Krasnov
2023-05-22 13:11   ` Simon Horman [this message]
2023-05-22 13:09     ` Arseniy Krasnov
2023-05-23  5:46       ` Arseniy Krasnov
2023-05-22  7:39 ` [RFC PATCH v3 06/17] vsock: check error queue to set EPOLLERR Arseniy Krasnov
2023-05-22  7:39 ` [RFC PATCH v3 07/17] vsock: read from socket's error queue Arseniy Krasnov
2023-05-22  7:39 ` [RFC PATCH v3 08/17] vsock: check for MSG_ZEROCOPY support Arseniy Krasnov
2023-05-22  7:39 ` [RFC PATCH v3 09/17] vsock: enable SOCK_SUPPORT_ZC bit Arseniy Krasnov
2023-05-22  7:39 ` [RFC PATCH v3 10/17] vhost/vsock: support MSG_ZEROCOPY for transport Arseniy Krasnov
2023-05-22  7:39 ` [RFC PATCH v3 11/17] vsock/virtio: " Arseniy Krasnov
2023-05-22  7:39 ` [RFC PATCH v3 12/17] vsock/loopback: " Arseniy Krasnov
2023-05-22  7:39 ` [RFC PATCH v3 13/17] net/sock: enable setting SO_ZEROCOPY for PF_VSOCK Arseniy Krasnov
2023-05-22  7:39 ` [RFC PATCH v3 14/17] docs: net: description of MSG_ZEROCOPY for AF_VSOCK Arseniy Krasnov
2023-05-22  7:39 ` [RFC PATCH v3 15/17] test/vsock: MSG_ZEROCOPY flag tests Arseniy Krasnov
2023-05-22  7:39 ` [RFC PATCH v3 16/17] test/vsock: MSG_ZEROCOPY support for vsock_perf Arseniy Krasnov
2023-05-22  7:39 ` [RFC PATCH v3 17/17] test/vsock: io_uring rx/tx tests Arseniy Krasnov
2023-05-25 15:56 ` [RFC PATCH v3 00/17] vsock: MSG_ZEROCOPY flag support Arseniy Krasnov
2023-05-26 10:30   ` Stefano Garzarella
2023-05-26 11:36     ` Arseniy Krasnov
2023-05-26 12:23       ` Stefano Garzarella
2023-05-26 12:28         ` Arseniy Krasnov

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=ZGtqEghjjiBnvEBW@corigine.com \
    --to=simon.horman@corigine.com \
    --cc=AVKrasnov@sberdevices.ru \
    --cc=bobby.eshleman@bytedance.com \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=jasowang@redhat.com \
    --cc=kernel@sberdevices.ru \
    --cc=kuba@kernel.org \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mst@redhat.com \
    --cc=netdev@vger.kernel.org \
    --cc=oxffffaa@gmail.com \
    --cc=pabeni@redhat.com \
    --cc=sgarzare@redhat.com \
    --cc=stefanha@redhat.com \
    --cc=virtualization@lists.linux-foundation.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).