[PATCH 2/6] net/hns3: fix inconsistent enabled RSS behavior

[lihuisong (C)]

在 2022/3/24 3:50, Ajit Khaparde 写道:
> On Wed, Mar 23, 2022 at 12:04 PM Thomas Monjalon <thomas at monjalon.net> wrote:
>> 23/03/2022 12:04, lihuisong (C):
>>> 在 2022/3/23 17:14, Thomas Monjalon 写道:
>>>> 23/03/2022 04:05, lihuisong (C):
>>>>> 在 2022/3/23 1:13, Thomas Monjalon 写道:
>>>>>> 21/03/2022 08:14, lihuisong (C):
>>>>>>> 2022/3/10 16:08, lihuisong (C):
>>>>>>>> 2022/3/9 17:55, Ori Kam:
>>>>>>>>> From: lihuisong (C) <lihuisong at huawei.com>
>>>>>>>>>> 2022/3/3 10:47, lihuisong (C):
>>>>>>>>>>> 2022/3/2 22:07, Ori Kam:
>>>>>>>>>>>> From: lihuisong (C) <lihuisong at huawei.com>
>>>>>>>>>>>>> 2022/3/1 0:42, Ferruh Yigit:
>>>>>>>>>>>>>> On 2/28/2022 3:21 AM, Min Hu (Connor) wrote:
>>>>>>>>>>>>>>> From: Huisong Li <lihuisong at huawei.com>
>>>>>>>>>>>>>>>
>>>>>>>>>>>>>>> RSS will not be enabled if the RTE_ETH_MQ_RX_RSS_FLAG isn't be
>>>>>>>>>>>>>>> set in
>>>>>>>>>>>>>>> dev_configure phase. However, if this flag isn't set, RSS can be
>>>>>>>>>>>>>>> enabled
>>>>>>>>>>>>>>> through the ethdev ops and rte_flow API. This behavior is
>>>>>>>>>>>>>>> contrary to
>>>>>>>>>>>>>>> each
>>>>>>>>>>>>>>> other.
>>>>>>>>>>>>>>>
>>>>>>>>>>>>>>> Fixes: c37ca66f2b27 ("net/hns3: support RSS")
>>>>>>>>>>>>>>> Cc: stable at dpdk.org
>>>>>>>>>>>>>>>
>>>>>>>>>>>>>>> Signed-off-by: Huisong Li <lihuisong at huawei.com>
>>>>>>>>>>>>>> Hi Huisong, Connor,
>>>>>>>>>>>>>>
>>>>>>>>>>>>>> Let's get a little more feedback for this patch, cc'ed more people.
>>>>>>>>>>>>>>
>>>>>>>>>>>>>> To enable RSS, multi queue mode should be set to
>>>>>>>>>>>>>> 'RTE_ETH_MQ_RX_RSS_FLAG'.
>>>>>>>>>>>>>>
>>>>>>>>>>>>>> But I wonder if it is required to configure RSS via flow API,
>>>>>>>>>>>>> I do not know the original purpose of adding the RSS
>>>>>>>>>>>>> configuration in
>>>>>>>>>>>>> flow API.
>>>>>>>>>>>>>
>>>>>>>>>>>> The purpose is simple, this allow to create RSS per rule and not a
>>>>>>>>>>>> global one.
>>>>>>>>>>>> For example create RSS that sends TCP to some queues while othe RSS
>>>>>>>>>>>> will send
>>>>>>>>>>>> UDP traffic to different queues.
>>>>>>>>>>> I'm a little confused now. The "per rule" also seems to be a global
>>>>>>>>>>> configuration.
>>>>>>>>>>> Example:
>>>>>>>>>>>      - start PMD with 0,1,2,3
>>>>>>>>>>>      - create TCP packets to 2,3 queues. At this moment, only 2,3 queues
>>>>>>>>>>> can be received for other types of packets.
>>>>>>>>>>> Because this rule is implemented by modifying the entry of the
>>>>>>>>>>> redirection table which is global for this device.
>>>>>>>>>> Hi, Ori and Stephen.
>>>>>>>>>> Can you help me clear up the confusion above? If some NICs behave like
>>>>>>>>>> this, what should we do about it?
>>>>>>>>> I'm not sure I understand the issue, maybe it is releated to some
>>>>>>>>> HW/PMD limitation.
>>>>>>>>> In your example non TCP traffic will be routed to one of the 4 queues
>>>>>>>>> (0,1,2,3),
>>>>>>>>> While TCP traffic will only be routed to queues 2,3.
>>>>>>>>>
>>>>>>>>> Now I can add new rule that matches on UDP packet and RSS to queue 0
>>>>>>>>> and 3 in this case:
>>>>>>>>> TCP packets will be routed to queues 0,3.
>>>>>>>>> UDP packets will be routed to queues 2,3.
>>>>>>>>> All the rest of the traffic will be routed to queues 0,1,2,3
>>>>>>>>>
>>>>>>>>> And just to be clear if now I add a rule to match all packets in
>>>>>>>>> higher priority,
>>>>>>>>> with RSS to queues 1,2. Then all traffic will be routed to queues 1,2.
>>>>>>>>>
>>>>>>>>> At least this is what is expected, from API point of view.
>>>>>>>>>
>>>>>>>>> Best,
>>>>>>>>> Ori
>>>>>>>> Thank you for your answer. I understand it.
>>>>>>>> hns3 PMD cannot implement the above functions due to hardware limitation.
>>>>>>>> we may need add a check that specified RSS queues cannot be supported
>>>>>>>> when specified packets types.
>>>>>>>> And only the packet type is specified, which meets the requirements of
>>>>>>>> rte_flow API.
>>>>>>>> The check for the RTE_ETH_MQ_RX_RSS_FLAG flag in rte_flow is not correct.
>>>>>>>> Thanks, Ori and Stephen😁
>>>>>>>>
>>>>>>>> But, I think, it is necessary for the '.rss_hash_update' and
>>>>>>>> '.reta_update' APIs
>>>>>>>> in eth_dev_ops to verify this flag. What do you think? @Thomas,
>>>>>>>> @Ferruh, @Ori and @Stephen.
>>>>>>> What's your take on it? I am looking forward to your reply. Thanks!
>>>>>> I am not sure why you want to check this flag.
>>>>> I want to make sure that the behavior that PMD configured RSS is
>>>>> consistent across different interfaces. The RTE_ETH_MQ_RX_RSS_FLAG
>>>>> flag is a switch to enable RSS hash. If the switch isn't open, some
>>>>> PMD do not configure RSS function. I think the consistency is necessary.
>>>>> If not set RSS muti-queue mode, it is unnecessary to configure RSS.
>>>>>
>>>>>> I can imagine we configure the hash and the table before enabling RSS
>>>>>> with the RTE_ETH_MQ_RX_RSS_FLAG flag.
>>>>> The flag is derived from dev_configure() which also configures
>>>>> hash and key. I don't think it makes sense to configure hash and
>>>>> reta before calling dev_configure. Because they'll be updated.
>>>>> This is similar to configuring mtu.
>>>> OK I see your point.
>>>> So you would like to return an error in RSS functions
>>>> if the flag RTE_ETH_MQ_RX_RSS_FLAG is not set?
>>> Yes
>>>> Should it be checked in ethdev library or PMDs?
>>> I think it's better to put it in the ethdev layer if we do it.
>>> Should we add this check in 'rss_hash_update' and 'reta_update' APIs?
>> I'm OK with adding the check in ethdev.
> +1
>
> Apologies for getting late to this thread.
Thanks. I'll fix it.