DPDK patches and discussions
 help / color / mirror / Atom feed
From: Ferruh Yigit <ferruh.yigit@intel.com>
To: Joyce Kong <joyce.kong@arm.com>,
	maxime.coquelin@redhat.com, stephen@networkplumber.org,
	xiaolong.ye@intel.com, zhihong.wang@intel.com,
	thomas@monjalon.net, jerinj@marvell.com, yinan.wang@intel.com,
	honnappa.nagarahalli@arm.com, gavin.hu@arm.com
Cc: nd@arm.com, dev@dpdk.org
Subject: Re: [dpdk-dev] [PATCH v5 1/2] virtio: one way barrier for split vring used idx
Date: Thu, 30 Apr 2020 23:58:27 +0100	[thread overview]
Message-ID: <4d360c36-7426-469f-7910-864516f39aeb@intel.com> (raw)
In-Reply-To: <20200430091437.34958-2-joyce.kong@arm.com>

On 4/30/2020 10:14 AM, Joyce Kong wrote:
> In case VIRTIO_F_ORDER_PLATFORM(36) is not negotiated, then the frontend
> and backend are assumed to be implemented in software, that is they can
> run on identical CPUs in an SMP configuration.
> Thus a weak form of memory barriers like rte_smp_r/wmb, other than
> rte_cio_r/wmb, is sufficient for this case(vq->hw->weak_barriers == 1)
> and yields better performance.
> For the above case, this patch helps yielding even better performance
> by replacing the two-way barriers with C11 one-way barriers for used
> index in split ring.
> 
> Signed-off-by: Joyce Kong <joyce.kong@arm.com>
> Reviewed-by: Gavin Hu <gavin.hu@arm.com>
> Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>

<...>

> @@ -464,8 +464,33 @@ virtio_get_queue_type(struct virtio_hw *hw, uint16_t vtpci_queue_idx)
>  		return VTNET_TQ;
>  }
>  
> -#define VIRTQUEUE_NUSED(vq) ((uint16_t)((vq)->vq_split.ring.used->idx - \
> -					(vq)->vq_used_cons_idx))
> +/* virtqueue_nused has load-acquire or rte_cio_rmb insed */
> +static inline uint16_t
> +virtqueue_nused(const struct virtqueue *vq)
> +{
> +	uint16_t idx;
> +
> +	if (vq->hw->weak_barriers) {
> +	/**
> +	 * x86 prefers to using rte_smp_rmb over __atomic_load_n as it
> +	 * reports a slightly better perf, which comes from the saved
> +	 * branch by the compiler.
> +	 * The if and else branches are identical with the smp and cio
> +	 * barriers both defined as compiler barriers on x86.
> +	 */
> +#ifdef RTE_ARCH_X86_64
> +		idx = vq->vq_split.ring.used->idx;
> +		rte_smp_rmb();
> +#else
> +		idx = __atomic_load_n(&(vq)->vq_split.ring.used->idx,
> +				__ATOMIC_ACQUIRE);
> +#endif
> +	} else {
> +		idx = vq->vq_split.ring.used->idx;
> +		rte_cio_rmb();
> +	}
> +	return idx - vq->vq_used_cons_idx;
> +}

AltiVec implementation (virtio_rxtx_simple_altivec.c) is also using
'VIRTQUEUE_NUSED' macro, it also needs to be updated with this change.

  reply	other threads:[~2020-04-30 22:58 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-02-12  9:24 [dpdk-dev] [PATCH v1 0/2] one way barrier for split vring idx Joyce Kong
2020-02-12  9:24 ` [dpdk-dev] [PATCH v1 1/2] virtio: one way barrier for split vring used idx Joyce Kong
2020-02-12  9:24 ` [dpdk-dev] [PATCH v1 2/2] virtio: one way barrier for split vring avail idx Joyce Kong
2020-04-02  2:57 ` [dpdk-dev] [PATCH v2 0/2] one way barrier for split vring idx Joyce Kong
2020-04-02  2:57 ` [dpdk-dev] [PATCH v2 1/2] virtio: one way barrier for split vring used idx Joyce Kong
2020-04-02 15:47   ` Stephen Hemminger
2020-04-03  8:55     ` Gavin Hu
2020-04-16  4:40       ` Honnappa Nagarahalli
2020-04-16  6:46         ` Joyce Kong
2020-04-02  2:57 ` [dpdk-dev] [PATCH v2 2/2] virtio: one way barrier for split vring avail idx Joyce Kong
2020-04-06 15:26 ` [dpdk-dev] [PATCH v3 0/2] one way barrier for split vring idx Joyce Kong
2020-04-16  9:08   ` Ye Xiaolong
2020-04-06 15:26 ` [dpdk-dev] [PATCH v3 1/2] virtio: one way barrier for split vring used idx Joyce Kong
2020-04-17  6:51   ` Ye Xiaolong
2020-04-17  8:14     ` Joyce Kong
2020-04-06 15:26 ` [dpdk-dev] [PATCH v3 2/2] virtio: one way barrier for split vring avail idx Joyce Kong
2020-04-24  3:39 ` [dpdk-dev] [PATCH v4 0/2] one way barrier for split vring idx Joyce Kong
2020-04-28 16:06   ` Maxime Coquelin
2020-04-29 17:45   ` Ferruh Yigit
2020-04-30  9:09     ` Maxime Coquelin
2020-04-30  9:16       ` Joyce Kong
2020-04-30  9:24         ` Maxime Coquelin
2020-04-24  3:39 ` [dpdk-dev] [PATCH v4 1/2] virtio: one way barrier for split vring used idx Joyce Kong
2020-04-27  9:03   ` Maxime Coquelin
2020-04-24  3:39 ` [dpdk-dev] [PATCH v4 2/2] virtio: one way barrier for split vring avail idx Joyce Kong
2020-04-27  9:03   ` Maxime Coquelin
2020-04-30  9:14 ` [dpdk-dev] [PATCH v5 0/2] one way barrier for split vring idx Joyce Kong
2020-04-30 20:54   ` Maxime Coquelin
2020-04-30  9:14 ` [dpdk-dev] [PATCH v5 1/2] virtio: one way barrier for split vring used idx Joyce Kong
2020-04-30 22:58   ` Ferruh Yigit [this message]
2020-05-04 10:04     ` Maxime Coquelin
2020-04-30  9:14 ` [dpdk-dev] [PATCH v5 2/2] virtio: one way barrier for split vring avail idx Joyce Kong

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=4d360c36-7426-469f-7910-864516f39aeb@intel.com \
    --to=ferruh.yigit@intel.com \
    --cc=dev@dpdk.org \
    --cc=gavin.hu@arm.com \
    --cc=honnappa.nagarahalli@arm.com \
    --cc=jerinj@marvell.com \
    --cc=joyce.kong@arm.com \
    --cc=maxime.coquelin@redhat.com \
    --cc=nd@arm.com \
    --cc=stephen@networkplumber.org \
    --cc=thomas@monjalon.net \
    --cc=xiaolong.ye@intel.com \
    --cc=yinan.wang@intel.com \
    --cc=zhihong.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
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).