From: Wenjun Wu <wenjun1.wu@intel.com>
To: dev@dpdk.org, qiming.yang@intel.com, qi.z.zhang@intel.com
Cc: Wenjun Wu <wenjun1.wu@intel.com>, stable@dpdk.org
Subject: [dpdk-dev] [PATCH v2 1/2] net/ice: fix RSS configuration failure
Date: Thu, 16 Sep 2021 10:34:57 +0800 [thread overview]
Message-ID: <20210916023457.441901-1-wenjun1.wu@intel.com> (raw)
In-Reply-To: <20210914083513.341438-3-wenjun1.wu@intel.com>
According to patch [1], IPv4 and IPv6 fragment ptypes should be
separated from IP other ptypes. That is to say, when RSS for IP
packets is enabled, it should not affect IP fragment packets.
Previously, we try to enable RSS for both IP packets and IP fragment
packets with hash field of src and dst address. However, due to
share code limitation, when RSS for IP packets and IP fragment packets
coexists, they cannot share the same hash field.
As a result, independent configuration of default RSS for IP fragment
packets need to be removed.
This patch revert the original patch to fix this failure.
[1]
commit 08c16b212d03 ("net/ice/base: fix ptype bitmap for IP fragment")
Fixes: 91f59358dc05 ("net/ice: fix default RSS hash for IP fragment packets")
Fixes: 4027fffe86f4 ("net/ice: support default RSS for IP fragment packet")
Cc: stable@dpdk.org
Signed-off-by: Wenjun Wu <wenjun1.wu@intel.com>
---
drivers/net/ice/ice_ethdev.c | 22 +---------------------
1 file changed, 1 insertion(+), 21 deletions(-)
diff --git a/drivers/net/ice/ice_ethdev.c b/drivers/net/ice/ice_ethdev.c
index 8d62b84805..0fcaf24fb1 100644
--- a/drivers/net/ice/ice_ethdev.c
+++ b/drivers/net/ice/ice_ethdev.c
@@ -2822,9 +2822,7 @@ ice_rss_hash_set(struct ice_pf *pf, uint64_t rss_hf)
ETH_RSS_NONFRAG_IPV4_TCP | \
ETH_RSS_NONFRAG_IPV6_TCP | \
ETH_RSS_NONFRAG_IPV4_SCTP | \
- ETH_RSS_NONFRAG_IPV6_SCTP | \
- ETH_RSS_FRAG_IPV4 | \
- ETH_RSS_FRAG_IPV6)
+ ETH_RSS_NONFRAG_IPV6_SCTP)
ret = ice_rem_vsi_rss_cfg(hw, vsi->idx);
if (ret)
@@ -2979,24 +2977,6 @@ ice_rss_hash_set(struct ice_pf *pf, uint64_t rss_hf)
__func__, ret);
}
- if (rss_hf & ETH_RSS_FRAG_IPV4) {
- cfg.addl_hdrs = ICE_FLOW_SEG_HDR_IPV4 | ICE_FLOW_SEG_HDR_IPV_FRAG;
- cfg.hash_flds = ICE_FLOW_HASH_IPV4;
- ret = ice_add_rss_cfg_wrap(pf, vsi->idx, &cfg);
- if (ret)
- PMD_DRV_LOG(ERR, "%s IPV4_FRAG rss flow fail %d",
- __func__, ret);
- }
-
- if (rss_hf & ETH_RSS_FRAG_IPV6) {
- cfg.addl_hdrs = ICE_FLOW_SEG_HDR_IPV6 | ICE_FLOW_SEG_HDR_IPV_FRAG;
- cfg.hash_flds = ICE_FLOW_HASH_IPV6;
- ret = ice_add_rss_cfg_wrap(pf, vsi->idx, &cfg);
- if (ret)
- PMD_DRV_LOG(ERR, "%s IPV6_FRAG rss flow fail %d",
- __func__, ret);
- }
-
pf->rss_hf = rss_hf & ICE_RSS_HF_ALL;
}
--
2.25.1
next prev parent reply other threads:[~2021-09-16 2:53 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-09-14 8:35 [dpdk-dev] [PATCH v1 0/2] " Wenjun Wu
2021-09-14 8:35 ` [dpdk-dev] [PATCH v1 1/2] net/ice: " Wenjun Wu
2021-09-14 8:35 ` [dpdk-dev] [PATCH v1 2/2] net/iavf: " Wenjun Wu
2021-09-16 2:34 ` Wenjun Wu [this message]
2021-09-16 2:35 ` [dpdk-dev] [PATCH v2 " Wenjun Wu
2021-09-16 2:34 ` [dpdk-dev] [PATCH v2 0/2] " Wenjun Wu
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=20210916023457.441901-1-wenjun1.wu@intel.com \
--to=wenjun1.wu@intel.com \
--cc=dev@dpdk.org \
--cc=qi.z.zhang@intel.com \
--cc=qiming.yang@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).