From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from dpdk.org (dpdk.org [92.243.14.124]) by inbox.dpdk.org (Postfix) with ESMTP id 860A2A04DB; Fri, 16 Oct 2020 12:57:31 +0200 (CEST) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id 0099D1EC0E; Fri, 16 Oct 2020 12:57:30 +0200 (CEST) Received: from mga07.intel.com (mga07.intel.com [134.134.136.100]) by dpdk.org (Postfix) with ESMTP id CAE441EC05 for ; Fri, 16 Oct 2020 12:57:27 +0200 (CEST) IronPort-SDR: RKkP9cjcY7fkaFLr+stLNYP7MAa+SvXhaCnteiFG2yNSiA6nGQuoOMMhoz1TLRfLeMQjiSIxbW zXhwfBsye5CQ== X-IronPort-AV: E=McAfee;i="6000,8403,9775"; a="230779256" X-IronPort-AV: E=Sophos;i="5.77,382,1596524400"; d="scan'208";a="230779256" X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from orsmga005.jf.intel.com ([10.7.209.41]) by orsmga105.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 16 Oct 2020 03:57:25 -0700 IronPort-SDR: KEzUUaY+JThB3Wkpy8Qc7xcFdTYODIDaNqeI0+yAe8kh3xVBkp9jR+DNy8T8/DPBDx0bdAsfqh rlm4w1lsCShQ== X-IronPort-AV: E=Sophos;i="5.77,382,1596524400"; d="scan'208";a="531674981" Received: from fyigit-mobl1.ger.corp.intel.com (HELO [10.252.19.66]) ([10.252.19.66]) by orsmga005-auth.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 16 Oct 2020 03:57:23 -0700 To: oulijun , Ophir Munk , "wenzhuo.lu@intel.com" , "beilei.xing@intel.com" , NBU-Contact-Adrien Mazarguil Cc: "dev@dpdk.org" , "linuxarm@huawei.com" , Ori Kam References: <1600955105-53176-2-git-send-email-oulijun@huawei.com> <1602765662-43299-1-git-send-email-oulijun@huawei.com> <1b2b0e11-1458-e2d9-5fde-91db35b8bc73@intel.com> <51676746-ec95-aff2-dc00-b76480ab6cba@huawei.com> <8c543941-e881-aa88-b52a-a70bfe8f6fcf@intel.com> From: Ferruh Yigit Message-ID: <8d592d3e-bace-eb50-a3af-4a0bb87ddae8@intel.com> Date: Fri, 16 Oct 2020 11:57:20 +0100 MIME-Version: 1.0 In-Reply-To: Content-Type: text/plain; charset=utf-8; format=flowed Content-Language: en-US Content-Transfer-Encoding: 8bit Subject: Re: [dpdk-dev] [PATCH v5] app/testpmd: fix the default RSS key configuration X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" On 10/16/2020 11:04 AM, oulijun wrote: > > > 在 2020/10/16 7:53, Ferruh Yigit 写道: >> On 10/16/2020 12:21 AM, Ophir Munk wrote: >>>> From: Ferruh Yigit >>>>>>> On 10/15/2020 1:41 PM, Lijun Ou wrote: >>>>>>>> When start the testpmd, the pmd driver initializes the RSS >>>>>>>> configuration. Generally, the recommended RSS hash key is used as >>>>>>>> the default key in the driver. In addition, the default key is >>>>>>>> different from the default RSS flow in testpmd without specifying >>>>>>>> RSS hash key. So. if you do not specify the RSS key when creating >>>>>>>> an RSS rule, the testpmd uses the default key as the default RSS >>>>>>>> key of the RSS rule. As a result, you may mistakenly consider that >>>>>>>> the RSS key in use is the valid default key of the NIC, actually, >>>>>>>> the key and the valid default key of the NIC are two values. >>>>>>>> >>>>>>>> Consider the follow usage with testpmd: >>>>>>>> 1. first, startup testpmd: >>>>>>>> testpmd> show port 0 rss-hash key >>>>>>>> RSS functions: >>>>>>>>     all ipv4-frag ipv4-other ipv6-frag ipv6-other ip RSS key: >>>>>>>> - >>>> 6D5A56DA255B0EC24167253D43A38FB0D0CA2BCBAE7B30B477CB2DA3803 >>>> 0F >>>>>>>> -20C6A42B73BBEAC01FA >>>>>>>> 2. create a rss rule >>>>>>>> testpmd> flow create 0 ingress pattern eth / ipv4 / udp / end >>>>>>>> testpmd> actions rss \ >>>>>>>> types ipv4-udp end queues end / end >>>>>>>> >>>>>>>> 3. show rss-hash key >>>>>>>> testpmd> show port 0 rss-hash key >>>>>>>> RSS functions: >>>>>>>>     all ipv4-udp udp >>>>>>>> RSS key: >>>>>>>> - >>>> 74657374706D6427732064656661756C74205253532068617368206B65792C >>>> 206F >>>>>>>> -76657272696465 >>>>>>>> >>>>>>>> In order to solve the above problems, it use the NIC valid default >>>>>>>> RSS key instead of the testpmd dummy RSS key in the flow >>>>>>>> configuration when the RSS key is not specified in the flow rule. >>>>>>>> If the NIC RSS key is invalid, it will use testpmd dummy RSS key as the >>>> default key. >>>>>>>> >>>>>>>> Fixes: ac8d22de2394 ("ethdev: flatten RSS configuration in flow >>>>>>>> API") >>>>>>>> Cc: stable@dpdk.org >>>>>>>> >>>>>>>> Signed-off-by: Lijun Ou >>>>>>>> Reviewed-by: Phil Yang >>>>>>>> --- >>>>>>>> V4->V5: >>>>>>>> -rewrite the commit log >>>>>>>> -add reviewed-by >>>>>>> >>>>>>> Hi Lijun, >>>>>>> >>>>>>> There were multiple other comments, it seems they are not addressed >>>>>>> but only updated the commit log, can you please check comments to >>>> prev versions. >>>>>>> >>>>>>> Before going into the details, my question was what happens if >>>>>>> default key not provided at all? >>>>>>> It seems this has been already tried by Ophir [1], later reverted >>>>>>> back [2] bringing the initial issue back. >>>>>>> >>>>>>> According commit, the reason of revert is to support following >>>> command: >>>>>>> "flow create 0 actions rss queues 0 1 end key_len 40 / end" >>>>>>> >>>>>>> @Ophir, @Lijun, >>>>>>> Can we ignore the 'key_len' if the 'key' is not supported and solve >>>>>>> current issue as initially intended ([1])? >>>>>>> >>>>>> Hi, Ferruh >>>>>>     I have discussed with Phil Yang about the problem in [1]. I think >>>>>> there may be other problems with the idea and there is no better >>>>>> solution. and we need to remove key_len definition from rte_rss_conf >>>>>> structure. They don't have a plan. And [1] was eventually reverted. >>>>>> >>>>> >>>>> Why ignoring 'key_len' (set it to zero) when there is no 'key' >>>>> provided doesn't work? >>>>> >>>> >>>> What do you think [1] + following update, will it work? >>>> >>>>    diff --git a/lib/librte_ethdev/rte_flow.c b/lib/librte_ethdev/rte_flow.c >>>>    index ee4f3464fe..e7789c87b3 100644 >>>>    --- a/lib/librte_ethdev/rte_flow.c >>>>    +++ b/lib/librte_ethdev/rte_flow.c >>>>    @@ -535,7 +535,7 @@ rte_flow_conv_action_conf(void *buf, const size_t >>>> size, >>>>                               }), >>>>                               size > sizeof(*dst.rss) ? sizeof(*dst.rss) : >>>> size); >>>>                    off = sizeof(*dst.rss); >>>>    -               if (src.rss->key_len) { >>>>    +               if (src.rss->key_len && src.rss->key) { >>>>                            off = RTE_ALIGN_CEIL(off, sizeof(*dst.rss->key)); >>>>                            tmp = sizeof(*src.rss->key) * src.rss->key_len; >>>>                            if (size >= off + tmp) >>>> >>> >>> Ferruh, your suggestion ([1] + update) looks correct. I also verified it on >>> mlx5 PMD. >>> Advantage: it's a generic fix for all dpdk applications using rte_flows (not >>> just testpmd). >>> It reduces code. >>> With this fix the responsibility of handling key==NULL and/or len==0 is moved >>> to the PMDs (which is good). >>> With regard to Lijun patch - I liked the approach of overriding the default >>> testpmd key with the default PMD key. >>> But it only addresses testpmd. More code was added. >>> It seems OK to call rte_eth_dev_rss_hash_conf_get() as part of parsing RSS, >>> but it would feel more confident if we could confirm it for all the PMDs (by >>> testing) or at least review the PMDs rss_hash_conf_get() implementations. >>> >> >> Lijun's idea can work. There was a problem in implementation related to the >> key size assumption, which can be fixed. >> >> Even it is fixed, when user gives a rss rule without a key, we are getting key >> from device and feeding same key back to device, this is unnecessary I think. >> When user didn't provide a key, rss rule shouldn't touch the key at all. >> > Do you mean that the driver should not configure the key to the hardware when > the RSS key is not specified? We are talking about 'key' in RSS rte flow rule, not generally configuring the device for RSS. If a specific rss rte flow rule, lets say to filter some defined packets to some specific queues, don't have 'key' as a part of rule, I am suggesting not touch 'key' configuration of the device. > If so, we cannot identify when the user does not specify the RSS key to > determine whether to configure the key. I think we can. If the rule has 'key' attribute, driver can use that key to program the device, if 'key' attribute is missing, don't do anything related to the rss key. > In hardware design, most vendors do not configure keys for hardware > independently, which may be associated with other RSS config parameters. > I think it would be reasonable for us to reconfigure the RSS key with the > default value configured and valid in the hardware as the default value if the > user does not specify the RSS key. There are already APIs to update the RSS configuration, like RSS key, hash functions etc.. They are independent from the rte flow RSS rule. Application should configure RSS according needs using those APIs. The question here is about each RSS rte flow rule that can update the key. Am I missing something? >> Complication was when user provides key_len without a key, I think both >> ignoring or returning error in this case is OK. > I agree. However, I think it is meaningless to expose the RSS key length to > users. Do you consider deleting the RSS key length directly? Isn't both 'key' and 'key_len' needed to program the RSS key? Can the driver know the size of the 'key' without 'key_len'? And driver should verify these provided values.