From: "Zhang, Qi Z" <qi.z.zhang@intel.com>
To: "Li, Xiaoyun" <xiaoyun.li@intel.com>
Cc: "dev@dpdk.org" <dev@dpdk.org>
Subject: Re: [dpdk-dev] [PATCH] net/i40e: adjust the RSS table
Date: Mon, 3 Dec 2018 05:29:56 +0000 [thread overview]
Message-ID: <039ED4275CED7440929022BC67E70611532F89A9@SHSMSX103.ccr.corp.intel.com> (raw)
In-Reply-To: <1542936954-39421-1-git-send-email-xiaoyun.li@intel.com>
> -----Original Message-----
> From: Li, Xiaoyun
> Sent: Friday, November 23, 2018 9:36 AM
> To: Zhang, Qi Z <qi.z.zhang@intel.com>
> Cc: dev@dpdk.org; Li, Xiaoyun <xiaoyun.li@intel.com>
> Subject: [PATCH] net/i40e: adjust the RSS table
>
> When starting the device, the RSS table is set. For 8 queues, the RSS hash table
> would be like | 3,2,1,0,7,6,5,4 | 3,2,1,0,7,6,5,4 |... This patch adjusts this table
> to set entries sequentially. Then for 8 queues, the RSS table would be like |
> 0,1,2,3,4,5,6,7 | 0,1,2,3,4,5,6,7 |...
My understanding is this is a byte order issue.
Does below change will fix the same thing?
- I40E_WRITE_REG(hw, I40E_PFQF_HLUT(i >> 2), lut);
- I40E_WRITE_REG(hw, I40E_PFQF_HLUT(i >> 2), rte_bswap32(lut));
>
> Signed-off-by: Xiaoyun Li <xiaoyun.li@intel.com>
> ---
> drivers/net/i40e/i40e_ethdev.c | 15 ++++++++++-----
> 1 file changed, 10 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/net/i40e/i40e_ethdev.c b/drivers/net/i40e/i40e_ethdev.c
> index 790ecc3..031eba0 100644
> --- a/drivers/net/i40e/i40e_ethdev.c
> +++ b/drivers/net/i40e/i40e_ethdev.c
> @@ -8468,6 +8468,7 @@ i40e_pf_config_rss(struct i40e_pf *pf) {
> struct i40e_hw *hw = I40E_PF_TO_HW(pf);
> struct rte_eth_rss_conf rss_conf;
> + uint32_t size = hw->func_caps.rss_table_size;
> uint32_t i, lut = 0;
> uint16_t j, num;
>
> @@ -8489,13 +8490,17 @@ i40e_pf_config_rss(struct i40e_pf *pf)
> return -ENOTSUP;
> }
>
> - for (i = 0, j = 0; i < hw->func_caps.rss_table_size; i++, j++) {
> - if (j == num)
> - j = 0;
> + for (i = size - 1, j = (size - 1) % num;; i--, j--) {
> lut = (lut << 8) | (j & ((0x1 <<
> - hw->func_caps.rss_table_entry_width) - 1));
> - if ((i & 3) == 3)
> + hw->func_caps.rss_table_entry_width) - 1));
> +
> + if (j == 0)
> + j = num;
> +
> + if ((i & 3) == 0)
> I40E_WRITE_REG(hw, I40E_PFQF_HLUT(i >> 2), lut);
> + if (i == 0)
> + break;
> }
>
> rss_conf = pf->dev_data->dev_conf.rx_adv_conf.rss_conf;
> --
> 2.7.4
next prev parent reply other threads:[~2018-12-03 5:30 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-11-23 1:35 Xiaoyun Li
2018-12-03 5:29 ` Zhang, Qi Z [this message]
2018-12-03 6:58 ` [dpdk-dev] [PATCH v2] " Xiaoyun Li
2018-12-03 8:30 ` Zhang, Qi Z
2018-12-03 8:26 ` [dpdk-dev] [PATCH v3] " Xiaoyun Li
2018-12-03 9:25 ` 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=039ED4275CED7440929022BC67E70611532F89A9@SHSMSX103.ccr.corp.intel.com \
--to=qi.z.zhang@intel.com \
--cc=dev@dpdk.org \
--cc=xiaoyun.li@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).