From: Daniel Xu <dxu@xxxxxxxxx>
Date: Thu, 08 Aug 2024 16:52:51 -0400
> Hi,
>
> On Thu, Aug 8, 2024, at 7:57 AM, Alexander Lobakin wrote:
>> From: Lorenzo Bianconi <lorenzo.bianconi@xxxxxxxxxx>
>> Date: Thu, 8 Aug 2024 06:54:06 +0200
>>
>>>> Hi Alexander,
>>>>
>>>> On Tue, Jun 28, 2022, at 12:47 PM, Alexander Lobakin wrote:
>>>>> cpumap has its own BH context based on kthread. It has a sane batch
>>>>> size of 8 frames per one cycle.
>>>>> GRO can be used on its own, adjust cpumap calls to the
>>>>> upper stack to use GRO API instead of netif_receive_skb_list() which
>>>>> processes skbs by batches, but doesn't involve GRO layer at all.
>>>>> It is most beneficial when a NIC which frame come from is XDP
>>>>> generic metadata-enabled, but in plenty of tests GRO performs better
>>>>> than listed receiving even given that it has to calculate full frame
>>>>> checksums on CPU.
>>>>> As GRO passes the skbs to the upper stack in the batches of
>>>>> @gro_normal_batch, i.e. 8 by default, and @skb->dev point to the
>>>>> device where the frame comes from, it is enough to disable GRO
>>>>> netdev feature on it to completely restore the original behaviour:
>>>>> untouched frames will be being bulked and passed to the upper stack
>>>>> by 8, as it was with netif_receive_skb_list().
>>>>>
>>>>> Signed-off-by: Alexander Lobakin <alexandr.lobakin@xxxxxxxxx>
>>>>> ---
>>>>> kernel/bpf/cpumap.c | 43 ++++++++++++++++++++++++++++++++++++++-----
>>>>> 1 file changed, 38 insertions(+), 5 deletions(-)
>>>>>
>>>>
>>>> AFAICT the cpumap + GRO is a good standalone improvement. I think
>>>> cpumap is still missing this.
>>
>> The only concern for having GRO in cpumap without metadata from the NIC
>> descriptor was that when the checksum status is missing, GRO calculates
>> the checksum on CPU, which is not really fast.
>> But I remember sometimes GRO was faster despite that.
>
> Good to know, thanks. IIUC some kind of XDP hint support landed already?
>
> My use case could also use HW RSS hash to avoid a rehash in XDP prog.
Unfortunately, for now it's impossible to get HW metadata such as RSS
hash and checksum status in cpumap. They're implemented via kfuncs
specific to a particular netdevice and this info is available only when
running XDP prog.
But I think one solution could be:
1. We create some generic structure for cpumap, like
struct cpumap_meta {
u32 magic;
u32 hash;
}
2. We add such check in the cpumap code
if (xdpf->metalen == sizeof(struct cpumap_meta) &&
<here we check magic>)
skb->hash = meta->hash;
3. In XDP prog, you call Rx hints kfuncs when they're available, obtain
RSS hash and then put it in the struct cpumap_meta as XDP frame metadata.
> And HW RX timestamp to not break SO_TIMESTAMPING. These two
> are on one of my TODO lists. But I can’t get to them for at least
> a few weeks. So free to take it if you’d like.
>
>>
>>>>
>>>> I have a production use case for this now. We want to do some intelligent
>>>> RX steering and I think GRO would help over list-ified receive in some cases.
>>>> We would prefer steer in HW (and thus get existing GRO support) but not all
>>>> our NICs support it. So we need a software fallback.
>>>>
>>>> Are you still interested in merging the cpumap + GRO patches?
>>
>> For sure I can revive this part. I was planning to get back to this
>> branch and pick patches which were not related to XDP hints and send
>> them separately.
>>
>>>
>>> Hi Daniel and Alex,
>>>
>>> Recently I worked on a PoC to add GRO support to cpumap codebase:
>>> - https://github.com/LorenzoBianconi/bpf-next/commit/a4b8264d5000ecf016da5a2dd9ac302deaf38b3e
>>> Here I added GRO support to cpumap through gro-cells.
>>> - https://github.com/LorenzoBianconi/bpf-next/commit/da6cb32a4674aa72401c7414c9a8a0775ef41a55
>>> Here I added GRO support to cpumap trough napi-threaded APIs (with a some
>>> changes to them).
>>
>> Hmm, when I was testing it, adding a whole NAPI to cpumap was sorta
>> overkill, that's why I separated GRO structure from &napi_struct.
>>
>> Let me maybe find some free time, I would then test all 3 solutions
>> (mine, gro_cells, threaded NAPI) and pick/send the best?
>
> Sounds good. Would be good to compare results.
>
> […]
>
> Thanks,
> Daniel
Thanks,
Olek
