DPDK patches and discussions
 help / color / mirror / Atom feed
From: "Ananyev, Konstantin" <konstantin.ananyev@intel.com>
To: "Xing, Beilei" <beilei.xing@intel.com>,
	"Zhang, Qi Z" <qi.z.zhang@intel.com>
Cc: "dev@dpdk.org" <dev@dpdk.org>, "stable@dpdk.org" <stable@dpdk.org>
Subject: Re: [dpdk-dev] [PATCH v4] net/i40e: fix Rx instability with vector mode
Date: Mon, 5 Nov 2018 11:05:01 +0000	[thread overview]
Message-ID: <2601191342CEEE43887BDE71AB9772580103068AF1@irsmsx105.ger.corp.intel.com> (raw)
In-Reply-To: <1541387892-51117-1-git-send-email-beilei.xing@intel.com>


> 
> Previously, there is instability during vector Rx if descriptor
> number is not power of 2, e.g. process hang and some Rx packets
> are unexpectedly empty. That's because vector Rx mode assumes Rx
> descriptor number is power of 2 when doing bit mask.
> This patch allows vector mode only when the number of Rx descriptor
> is power of 2.
> 
> Fixes: 8e109464c022 ("i40e: allow vector Rx and Tx usage")
> Fixes: a3c83a2527e1 ("net/i40e: enable runtime queue setup")
> Cc: stable@dpdk.org
> 
> Signed-off-by: Beilei Xing <beilei.xing@intel.com>
> ---
> v4 changes:
>  - Configure rx_vec_allowed in i40e_rx_vec_dev_conf_condition_check function.
> v3 changes:
>  - Add branch for non-first queue during runtime queue setup.
>  - Use function rte_is_power_of_2().
>  - Configure rx_vec_allowed during setting Rx function.
> v2 changes:
>  - rx_vec_allowed is global configuration, avoid overwrite.
> 
>  doc/guides/nics/i40e.rst                |  7 ++++++
>  drivers/net/i40e/i40e_rxtx.c            |  5 +++++
>  drivers/net/i40e/i40e_rxtx_vec_common.h | 38 +++++++++++++++++++++++++++++++++
>  3 files changed, 50 insertions(+)
> 
> diff --git a/doc/guides/nics/i40e.rst b/doc/guides/nics/i40e.rst
> index ab3928a..bfacbd1 100644
> --- a/doc/guides/nics/i40e.rst
> +++ b/doc/guides/nics/i40e.rst
> @@ -172,6 +172,13 @@ Runtime Config Options
> 
>    -w 84:00.0,use-latest-supported-vec=1
> 
> +Vector RX Pre-conditions
> +~~~~~~~~~~~~~~~~~~~~~~~~
> +For Vector RX it is assumed that the number of descriptor rings will be a power
> +of 2. With this pre-condition, the ring pointer can easily scroll back to the
> +head after hitting the tail without a conditional check. In addition Vector RX
> +can use this assumption to do a bit mask using ``ring_size - 1``.
> +
>  Driver compilation and testing
>  ------------------------------
> 
> diff --git a/drivers/net/i40e/i40e_rxtx.c b/drivers/net/i40e/i40e_rxtx.c
> index a827456..5bb1a3c 100644
> --- a/drivers/net/i40e/i40e_rxtx.c
> +++ b/drivers/net/i40e/i40e_rxtx.c
> @@ -1741,6 +1741,11 @@ i40e_dev_rx_queue_setup_runtime(struct rte_eth_dev *dev,
>  			ad->rx_bulk_alloc_allowed = false;
>  		i40e_set_rx_function(dev);
>  		return 0;
> +	} else if (ad->rx_vec_allowed && !rte_is_power_of_2(rxq->nb_rx_desc)) {
> +		PMD_DRV_LOG(ERR, "Vector mode is allowed, but descriptor"
> +			    " number %d of queue %d isn't power of 2",
> +			    rxq->nb_rx_desc, rxq->queue_id);
> +		return -EINVAL;
>  	}
> 
>  	/* check bulk alloc conflict */
> diff --git a/drivers/net/i40e/i40e_rxtx_vec_common.h b/drivers/net/i40e/i40e_rxtx_vec_common.h
> index f00f6d6..0e6ffa0 100644
> --- a/drivers/net/i40e/i40e_rxtx_vec_common.h
> +++ b/drivers/net/i40e/i40e_rxtx_vec_common.h
> @@ -192,8 +192,13 @@ static inline int
>  i40e_rx_vec_dev_conf_condition_check_default(struct rte_eth_dev *dev)
>  {
>  #ifndef RTE_LIBRTE_IEEE1588
> +	struct i40e_adapter *ad =
> +		I40E_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
>  	struct rte_eth_rxmode *rxmode = &dev->data->dev_conf.rxmode;
>  	struct rte_fdir_conf *fconf = &dev->data->dev_conf.fdir_conf;
> +	struct i40e_rx_queue *rxq;
> +	uint16_t desc, i;
> +	bool first_queue;
> 
>  	/* no fdir support */
>  	if (fconf->mode != RTE_FDIR_MODE_NONE)
> @@ -207,6 +212,39 @@ i40e_rx_vec_dev_conf_condition_check_default(struct rte_eth_dev *dev)
>  	if (rxmode->offloads & DEV_RX_OFFLOAD_VLAN_EXTEND)
>  		return -1;
> 
> +	/**
> +	 * Vector mode is allowed only when number of Rx queue
> +	 * descriptor is power of 2.
> +	 */
> +	if (!dev->data->dev_started) {
> +		first_queue = true;
> +		for (i = 0; i < dev->data->nb_rx_queues; i++) {
> +			rxq = dev->data->rx_queues[i];
> +			if (!rxq)
> +				continue;
> +			desc = rxq->nb_rx_desc;
> +			if (first_queue)
> +				ad->rx_vec_allowed =
> +					rte_is_power_of_2(desc);
> +			else
> +				ad->rx_vec_allowed =
> +					ad->rx_vec_allowed ?
> +					rte_is_power_of_2(desc) :
> +					ad->rx_vec_allowed;
> +			first_queue = false;
> +		}
> +	} else {
> +		/* Only check the first queue's descriptor number */
> +		for (i = 0; i < dev->data->nb_rx_queues; i++) {
> +			rxq = dev->data->rx_queues[i];
> +			if (!rxq)
> +				continue;
> +			desc = rxq->nb_rx_desc;
> +			ad->rx_vec_allowed = rte_is_power_of_2(desc);
> +			break;
> +		}
> +	}
> +
>  	return 0;
>  #else
>  	RTE_SET_USED(dev);
> --

Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>

> 2.5.5

  reply	other threads:[~2018-11-05 11:05 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-10-25  7:40 [dpdk-dev] [PATCH] " Beilei Xing
2018-10-25 16:47 ` Zhang, Qi Z
2018-10-26  6:33 ` [dpdk-dev] [PATCH v2] " Beilei Xing
2018-10-26  8:47   ` Ananyev, Konstantin
2018-10-26 15:41     ` Zhang, Qi Z
2018-10-29  1:48       ` Xing, Beilei
2018-10-26 11:11   ` Bruce Richardson
2018-10-26 15:49     ` Zhang, Qi Z
2018-11-01  5:53   ` [dpdk-dev] [PATCH v3] " Beilei Xing
2018-11-01 11:48     ` Ananyev, Konstantin
2018-11-01 13:13       ` Zhang, Qi Z
2018-11-05  3:18     ` [dpdk-dev] [PATCH v4] " Beilei Xing
2018-11-05 11:05       ` Ananyev, Konstantin [this message]
2018-11-05 15:53         ` Zhang, Qi Z

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=2601191342CEEE43887BDE71AB9772580103068AF1@irsmsx105.ger.corp.intel.com \
    --to=konstantin.ananyev@intel.com \
    --cc=beilei.xing@intel.com \
    --cc=dev@dpdk.org \
    --cc=qi.z.zhang@intel.com \
    --cc=stable@dpdk.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).