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;
> +}
...
next prev parent 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).