DPDK patches and discussions
 help / color / mirror / Atom feed
From: "Zhang, Qi Z" <qi.z.zhang@intel.com>
To: "Yan, Zhirun" <zhirun.yan@intel.com>, "dev@dpdk.org" <dev@dpdk.org>
Cc: "Wang, Haiyue" <haiyue.wang@intel.com>
Subject: Re: [dpdk-dev] [PATCH v4 1/2] net/i40e: support VF request more queues
Date: Fri, 14 Dec 2018 11:59:55 +0000	[thread overview]
Message-ID: <039ED4275CED7440929022BC67E70611532FEF79@SHSMSX103.ccr.corp.intel.com> (raw)
In-Reply-To: <20181214143720.34163-2-zhirun.yan@intel.com>



> -----Original Message-----
> From: Yan, Zhirun
> Sent: Friday, December 14, 2018 10:37 PM
> To: dev@dpdk.org; Zhang, Qi Z <qi.z.zhang@intel.com>
> Cc: Yan, Zhirun <zhirun.yan@intel.com>; Wang, Haiyue <haiyue.wang@intel.com>
> Subject: [PATCH v4 1/2] net/i40e: support VF request more queues
> 
> Before this patch, VF gets a default number of queues from the PF.
> This patch enables VF to request a different number. When VF configures more
> queues, it will send VIRTCHNL_OP_REQUEST_QUEUES to PF to request more
> queues, if success, PF will reset the VF.
> 
> User can run "port stop all", "port config port_id rxq/txq queue_num"
> and "port start all" to reconfigure queue number.
> 
> Signed-off-by: Zhirun Yan <zhirun.yan@intel.com>
> Signed-off-by: Haiyue Wang <haiyue.wang@intel.com>
> ---
>  drivers/net/i40e/i40e_ethdev_vf.c | 62 ++++++++++++++++++++++++++++++-
>  1 file changed, 60 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/net/i40e/i40e_ethdev_vf.c
> b/drivers/net/i40e/i40e_ethdev_vf.c
> index 05dc6596b..a568fb528 100644
> --- a/drivers/net/i40e/i40e_ethdev_vf.c
> +++ b/drivers/net/i40e/i40e_ethdev_vf.c
> @@ -359,6 +359,25 @@ i40evf_execute_vf_cmd(struct rte_eth_dev *dev, struct
> vf_cmd_info *args)
>  		} while (i++ < MAX_TRY_TIMES);
>  		_clear_cmd(vf);
>  		break;
> +	case VIRTCHNL_OP_REQUEST_QUEUES:
> +		 /*ignore async reply, only wait for system message,*/
> +		 /*vf_reset = true if get VIRTCHNL_EVENT_RESET_IMPENDING,*/
> +		 /*if not, means request queues failed */
> +		err = -1;
> +		do {
> +			ret = i40evf_read_pfmsg(dev, &info);
> +			vf->cmd_retval = info.result;
> +			if (ret == I40EVF_MSG_SYS && vf->vf_reset) {
> +				err = 0;
> +				break;
> +			} else if (ret == I40EVF_MSG_ERR) {

Base on patch 2/2, in the case some error happen for example that no more free queue available, I40EVF_MSG_CMD will be returned. 
I think it should be "else if (ret == I40EVF_MSG_ERR || ret == I40EVF_MSG_CMD)" here
So we don't need to wait until end of loop in that case.
> +				break;
> +			}
> +			rte_delay_ms(ASQ_DELAY_MS);
> +			/* If don't read msg or read sys event, continue */
> +		} while (i++ < MAX_TRY_TIMES);
> +		_clear_cmd(vf);
> +		break;
> 
>  	default:
>  		/* for other adminq in running time, waiting the cmd done flag */ @@
> -1012,6 +1031,28 @@ i40evf_add_vlan(struct rte_eth_dev *dev, uint16_t vlanid)
>  	return err;
>  }
> 
> +static int
> +i40evf_request_queues(struct rte_eth_dev *dev, uint16_t num) {
> +	struct i40e_vf *vf =
> I40EVF_DEV_PRIVATE_TO_VF(dev->data->dev_private);
> +	struct virtchnl_vf_res_request vfres;
> +	struct vf_cmd_info args;
> +	int err;
> +
> +	vfres.num_queue_pairs = num;
> +
> +	args.ops = VIRTCHNL_OP_REQUEST_QUEUES;
> +	args.in_args = (u8 *)&vfres;
> +	args.in_args_size = sizeof(vfres);
> +	args.out_buffer = vf->aq_resp;
> +	args.out_size = I40E_AQ_BUF_SZ;
> +	err = i40evf_execute_vf_cmd(dev, &args);
> +	if (err)
> +		PMD_DRV_LOG(ERR, "fail to execute command
> OP_REQUEST_QUEUES");
> +
> +	return err;
> +}
> +
>  static int
>  i40evf_del_vlan(struct rte_eth_dev *dev, uint16_t vlanid)  { @@ -1516,8
> +1557,11 @@ RTE_PMD_REGISTER_KMOD_DEP(net_i40e_vf, "* igb_uio |
> vfio-pci");  static int  i40evf_dev_configure(struct rte_eth_dev *dev)  {
> +	struct i40e_vf *vf =
> I40EVF_DEV_PRIVATE_TO_VF(dev->data->dev_private);
>  	struct i40e_adapter *ad =
>  		I40E_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
> +	uint16_t num_queue_pairs = RTE_MAX(dev->data->nb_rx_queues,
> +				dev->data->nb_tx_queues);
> 
>  	/* Initialize to TRUE. If any of Rx queues doesn't meet the bulk
>  	 * allocation or vector Rx preconditions we will reset it.
> @@ -1527,6 +1571,20 @@ i40evf_dev_configure(struct rte_eth_dev *dev)
>  	ad->tx_simple_allowed = true;
>  	ad->tx_vec_allowed = true;
> 
> +	if (num_queue_pairs > vf->vsi_res->num_queue_pairs) {
> +		int ret = 0;
> +
> +		PMD_DRV_LOG(INFO, "change queue pairs from %u to %u",
> +			    vf->vsi_res->num_queue_pairs, num_queue_pairs);
> +		ret = i40evf_request_queues(dev, num_queue_pairs);
> +		if (ret != 0)
> +			return ret;
> +
> +		ret = i40evf_dev_reset(dev);
> +		if (ret != 0)
> +			return ret;
> +	}
> +
>  	return i40evf_init_vlan(dev);
>  }
> 
> @@ -2145,8 +2203,8 @@ i40evf_dev_info_get(struct rte_eth_dev *dev, struct
> rte_eth_dev_info *dev_info)  {
>  	struct i40e_vf *vf =
> I40EVF_DEV_PRIVATE_TO_VF(dev->data->dev_private);
> 
> -	dev_info->max_rx_queues = vf->vsi_res->num_queue_pairs;
> -	dev_info->max_tx_queues = vf->vsi_res->num_queue_pairs;
> +	dev_info->max_rx_queues = I40E_MAX_QP_NUM_PER_VF;
> +	dev_info->max_tx_queues = I40E_MAX_QP_NUM_PER_VF;
>  	dev_info->min_rx_bufsize = I40E_BUF_SIZE_MIN;
>  	dev_info->max_rx_pktlen = I40E_FRAME_SIZE_MAX;
>  	dev_info->hash_key_size = (I40E_VFQF_HKEY_MAX_INDEX + 1) *
> sizeof(uint32_t);
> --
> 2.17.1

  reply	other threads:[~2018-12-14 11:59 UTC|newest]

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-11-28 16:58 [dpdk-dev] [PATCH v2 0/2] Support " Zhirun Yan
2018-11-28 16:58 ` [dpdk-dev] [PATCH v2 1/2] net/i40e: support VF " Zhirun Yan
2018-11-28 16:58 ` [dpdk-dev] [PATCH v2 2/2] net/i40e: support PF respond " Zhirun Yan
2018-12-13 14:05 ` [dpdk-dev] [PATCH v3 0/2] Support " Zhirun Yan
2018-12-13 14:05   ` [dpdk-dev] [PATCH v3 1/2] net/i40e: support VF " Zhirun Yan
2018-12-13  8:26     ` David Marchand
2018-12-14  3:17       ` Yan, Zhirun
2018-12-13 10:49     ` Zhang, Qi Z
2018-12-14  3:22       ` Yan, Zhirun
2018-12-13 14:05   ` [dpdk-dev] [PATCH v3 2/2] net/i40e: support PF respond " Zhirun Yan
2018-12-14 14:37   ` [dpdk-dev] [PATCH v4 0/2] Support " Zhirun Yan
2018-12-14 14:37     ` [dpdk-dev] [PATCH v4 1/2] net/i40e: support VF " Zhirun Yan
2018-12-14 11:59       ` Zhang, Qi Z [this message]
2018-12-17  3:12         ` Yan, Zhirun
2018-12-14 14:37     ` [dpdk-dev] [PATCH v4 2/2] net/i40e: support PF respond " Zhirun Yan
2018-12-17 11:10     ` [dpdk-dev] [PATCH v5 0/2] Support " Zhirun Yan
2018-12-17  5:31       ` Zhang, Qi Z
2018-12-17 11:10       ` [dpdk-dev] [PATCH v5 1/2] net/i40e: support VF " Zhirun Yan
2018-12-17 14:28         ` Ferruh Yigit
2018-12-18  1:44           ` Zhang, Qi Z
2018-12-17 14:31         ` Ferruh Yigit
2018-12-17 11:10       ` [dpdk-dev] [PATCH v5 2/2] net/i40e: support PF respond " Zhirun Yan
2018-12-17 14:26         ` Ferruh Yigit
2018-12-18 16:09       ` [dpdk-dev] [PATCH v6 0/3] Support " Zhirun Yan
2018-12-18 16:09         ` [dpdk-dev] [PATCH v6 1/3] net/i40e: support VF " Zhirun Yan
2018-12-18 12:44           ` Zhang, Qi Z
2018-12-19  1:34             ` Yan, Zhirun
2018-12-18 16:09         ` [dpdk-dev] [PATCH v6 2/3] net/i40e: support PF respond " Zhirun Yan
2018-12-18 16:09         ` [dpdk-dev] [PATCH v6 3/3] doc: update queue number per vf for i40e Zhirun Yan
2018-12-18 12:59           ` Zhang, Qi Z
2018-12-19  1:33             ` Yan, Zhirun
2018-12-19 13:08         ` [dpdk-dev] [PATCH v7 0/3] Support request more queues Zhirun Yan
2018-12-19 13:08           ` [dpdk-dev] [PATCH v7 1/3] net/i40e: support VF " Zhirun Yan
2018-12-19 13:08           ` [dpdk-dev] [PATCH v7 2/3] net/i40e: support PF respond " Zhirun Yan
2018-12-19 13:08           ` [dpdk-dev] [PATCH v7 3/3] doc: update queue number per vf for i40e Zhirun Yan
2018-12-19 13:37             ` [dpdk-dev] [PATCH v8 0/3] Support request more queues Zhirun Yan
2018-12-19 13:37               ` [dpdk-dev] [PATCH v8 1/3] net/i40e: support VF " Zhirun Yan
2018-12-19 13:37               ` [dpdk-dev] [PATCH v8 2/3] net/i40e: support PF respond " Zhirun Yan
2018-12-19 13:37               ` [dpdk-dev] [PATCH v8 3/3] doc: update queue number per vf for i40e Zhirun Yan

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=039ED4275CED7440929022BC67E70611532FEF79@SHSMSX103.ccr.corp.intel.com \
    --to=qi.z.zhang@intel.com \
    --cc=dev@dpdk.org \
    --cc=haiyue.wang@intel.com \
    --cc=zhirun.yan@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).