DPDK patches and discussions
 help / color / mirror / Atom feed
From: "Hu, Jiayu" <jiayu.hu@intel.com>
To: Maxime Coquelin <maxime.coquelin@redhat.com>,
	"dev@dpdk.org" <dev@dpdk.org>,
	"Xia, Chenbo" <chenbo.xia@intel.com>,
	"Wang, YuanX" <yuanx.wang@intel.com>,
	"Ma, WenwuX" <wenwux.ma@intel.com>,
	"Richardson, Bruce" <bruce.richardson@intel.com>,
	"Mcnamara, John" <john.mcnamara@intel.com>
Subject: Re: [dpdk-dev] [RFC 08/14] vhost: improve IO vector logic
Date: Tue, 12 Oct 2021 06:05:42 +0000
Message-ID: <e1e7b0ccdbad48188e8f5daf38323492@intel.com> (raw)
In-Reply-To: <20211007220013.355530-9-maxime.coquelin@redhat.com>

Hi,

> -----Original Message-----
> From: Maxime Coquelin <maxime.coquelin@redhat.com>
> Sent: Friday, October 8, 2021 6:00 AM
> To: dev@dpdk.org; Xia, Chenbo <chenbo.xia@intel.com>; Hu, Jiayu
> <jiayu.hu@intel.com>; Wang, YuanX <yuanx.wang@intel.com>; Ma,
> WenwuX <wenwux.ma@intel.com>; Richardson, Bruce
> <bruce.richardson@intel.com>; Mcnamara, John
> <john.mcnamara@intel.com>
> Cc: Maxime Coquelin <maxime.coquelin@redhat.com>
> Subject: [RFC 08/14] vhost: improve IO vector logic
> 
> IO vectors and their iterators arrays were part of the async metadata but not
> their indexes.
> 
> In order to makes this more consistent, the patch adds the indexes to the
> async metadata. Doing that, we can avoid triggering DMA transfer within the
> loop as it IO vector index overflow is now prevented in the
> async_mbuf_to_desc() function.
> 
> Note that previous detection mechanism was broken since the overflow
> already happened when detected, so OOB memory access would already
> have happened.
> 
> With this changes done, virtio_dev_rx_async_submit_split()
> and virtio_dev_rx_async_submit_packed() can be further simplified.
> 
> Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
> ---
>  lib/vhost/vhost.h      |   2 +
>  lib/vhost/virtio_net.c | 296 +++++++++++++++++++----------------------
>  2 files changed, 136 insertions(+), 162 deletions(-)
> 
> diff --git a/lib/vhost/vhost.h b/lib/vhost/vhost.h index
> dae9a1ac2d..812d4c55a5 100644
> --- a/lib/vhost/vhost.h
> +++ b/lib/vhost/vhost.h
> @@ -134,6 +134,8 @@ struct vhost_async {
> 
>  	struct rte_vhost_iov_iter iov_iter[VHOST_MAX_ASYNC_IT];
>  	struct rte_vhost_iovec iovec[VHOST_MAX_ASYNC_VEC];
> +	uint16_t iter_idx;
> +	uint16_t iovec_idx;
> 
>  	/* data transfer status */
>  	struct async_inflight_info *pkts_info; diff --git a/lib/vhost/virtio_net.c
> b/lib/vhost/virtio_net.c index ae7dded979..5ce4c14a73 100644
> --- a/lib/vhost/virtio_net.c
> +++ b/lib/vhost/virtio_net.c
> @@ -924,33 +924,91 @@ copy_mbuf_to_desc(struct virtio_net *dev, struct
> vhost_virtqueue *vq,
>  	return error;
>  }
> 
> +static __rte_always_inline int
> +async_iter_initialize(struct vhost_async *async) {
> +	struct rte_vhost_iov_iter *iter;
> +
> +	if (unlikely(async->iter_idx >= VHOST_MAX_ASYNC_IT)) {
> +		VHOST_LOG_DATA(ERR, "no more async iterators
> available\n");
> +		return -1;
> +	}

async->iter_idx will not exceed VHOST_MAX_ASYNC_IT, as virtio_dev_rx
makes sure the number of packets to enqueue is less than or equal to
MAX_PKT_BURST and it is the same as VHOST_MAX_ASYNC_IT.

> +
> +	if (unlikely(async->iovec_idx >= VHOST_MAX_ASYNC_VEC)) {
> +		VHOST_LOG_DATA(ERR, "no more async iovec available\n");
> +		return -1;
> +	}
> +
> +
> +	iter = async->iov_iter + async->iter_idx;
> +	iter->iov = async->iovec + async->iovec_idx;
> +	iter->nr_segs = 0;
> +
> +	return 0;
> +}
> +
> +static __rte_always_inline int
> +async_iter_add_iovec(struct vhost_async *async, void *src, void *dst,
> +size_t len) {
> +	struct rte_vhost_iov_iter *iter;
> +	struct rte_vhost_iovec *iovec;
> +
> +	if (unlikely(async->iovec_idx >= VHOST_MAX_ASYNC_VEC)) {
> +		VHOST_LOG_DATA(ERR, "no more async iovec available\n");
> +		return -1;
> +	}
> +
> +	iter = async->iov_iter + async->iter_idx;
> +	iovec = async->iovec + async->iovec_idx;

async->iovec_idx is never gotten increased.

Thanks,
Jiayu

  reply	other threads:[~2021-10-12  6:05 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-10-07 21:59 [dpdk-dev] [RFC 00/14] vhost: clean-up and simplify async implementation Maxime Coquelin
2021-10-07 22:00 ` [dpdk-dev] [RFC 01/14] vhost: move async data in a dedicated structure Maxime Coquelin
2021-10-14  3:24   ` Hu, Jiayu
2021-10-14  8:54     ` Maxime Coquelin
2021-10-07 22:00 ` [dpdk-dev] [RFC 02/14] vhost: hide inflight async structure Maxime Coquelin
2021-10-07 22:00 ` [dpdk-dev] [RFC 03/14] vhost: simplify async IO vectors Maxime Coquelin
2021-10-07 22:00 ` [dpdk-dev] [RFC 04/14] vhost: simplify async IO vectors iterators Maxime Coquelin
2021-10-07 22:00 ` [dpdk-dev] [RFC 05/14] vhost: remove async batch threshold Maxime Coquelin
2021-10-07 22:00 ` [dpdk-dev] [RFC 06/14] vhost: introduce specific iovec structure Maxime Coquelin
2021-10-07 22:00 ` [dpdk-dev] [RFC 07/14] vhost: remove useless fields in async iterator struct Maxime Coquelin
2021-10-07 22:00 ` [dpdk-dev] [RFC 08/14] vhost: improve IO vector logic Maxime Coquelin
2021-10-12  6:05   ` Hu, Jiayu [this message]
2021-10-12  8:34     ` Maxime Coquelin
2021-10-07 22:00 ` [dpdk-dev] [RFC 09/14] vhost: remove notion of async descriptor Maxime Coquelin
2021-10-07 22:00 ` [dpdk-dev] [RFC 10/14] vhost: simplify async enqueue completion Maxime Coquelin
2021-10-07 22:00 ` [dpdk-dev] [RFC 11/14] vhost: simplify getting the first in-flight index Maxime Coquelin
2021-10-07 22:00 ` [dpdk-dev] [RFC 12/14] vhost: prepare async for mbuf to desc refactoring Maxime Coquelin
2021-10-07 22:00 ` [dpdk-dev] [RFC 13/14] vhost: prepare sync " Maxime Coquelin
2021-10-07 22:00 ` [dpdk-dev] [RFC 14/14] vhost: merge sync and async mbuf to desc filling Maxime Coquelin
2021-10-08 12:36 ` [dpdk-dev] [RFC 00/14] vhost: clean-up and simplify async implementation David Marchand
2021-10-12  6:24 ` Hu, Jiayu

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=e1e7b0ccdbad48188e8f5daf38323492@intel.com \
    --to=jiayu.hu@intel.com \
    --cc=bruce.richardson@intel.com \
    --cc=chenbo.xia@intel.com \
    --cc=dev@dpdk.org \
    --cc=john.mcnamara@intel.com \
    --cc=maxime.coquelin@redhat.com \
    --cc=wenwux.ma@intel.com \
    --cc=yuanx.wang@intel.com \
    /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

DPDK patches and discussions

This inbox may be cloned and mirrored by anyone:

	git clone --mirror http://inbox.dpdk.org/dev/0 dev/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 dev dev/ http://inbox.dpdk.org/dev \
		dev@dpdk.org
	public-inbox-index dev

Example config snippet for mirrors.
Newsgroup available over NNTP:
	nntp://inbox.dpdk.org/inbox.dpdk.dev


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git