Received-SPF: pass (google.com: domain of linux-kernel+bounces-15012-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.80.249 as permitted sender) client-ip=147.75.80.249;
Message-ID: <c628c362-b2e8-4ad6-a34f-50c2822bccd6@linux.dev>
Date: Tue, 2 Jan 2024 16:52:08 -0800
Precedence: bulk
MIME-Version: 1.0
Subject: Re: [PATCH bpf-next 0/2] bpf: add csum/ip_summed fields to __sk_buff
Content-Language: en-US
To: Menglong Dong <menglong8.dong@gmail.com>
Cc: Stanislav Fomichev <sdf@google.com>, andrii@kernel.org, ast@kernel.org,
 daniel@iogearbox.net, song@kernel.org, yonghong.song@linux.dev,
 john.fastabend@gmail.com, kpsingh@kernel.org, haoluo@google.com,
 jolsa@kernel.org, davem@davemloft.net, edumazet@google.com, kuba@kernel.org,
 pabeni@redhat.com, mykolal@fb.com, shuah@kernel.org, horms@kernel.org,
 dhowells@redhat.com, linyunsheng@huawei.com, aleksander.lobakin@intel.com,
 joannelkoong@gmail.com, laoar.shao@gmail.com, kuifeng@meta.com,
 bjorn@rivosinc.com, linux-kernel@vger.kernel.org, bpf@vger.kernel.org,
 netdev@vger.kernel.org, linux-kselftest@vger.kernel.org
References: <20231229081409.1276386-1-menglong8.dong@gmail.com>
 <ZZRR1q1JrJMD1lAy@google.com>
From: Martin KaFai Lau <martin.lau@linux.dev>
In-Reply-To: <ZZRR1q1JrJMD1lAy@google.com>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit

On 1/2/24 10:11 AM, Stanislav Fomichev wrote:
> On 12/29, Menglong Dong wrote:
>> For now, we have to call some helpers when we need to update the csum,
>> such as bpf_l4_csum_replace, bpf_l3_csum_replace, etc. These helpers are
>> not inlined, which causes poor performance.
>>
>> In fact, we can define our own csum update functions in BPF program
>> instead of bpf_l3_csum_replace, which is totally inlined and efficient.
>> However, we can't do this for bpf_l4_csum_replace for now, as we can't
>> update skb->csum, which can cause skb->csum invalid in the rx path with
>> CHECKSUM_COMPLETE mode.
>>
>> What's more, we can't use the direct data access and have to use
>> skb_store_bytes() with the BPF_F_RECOMPUTE_CSUM flag in some case, such
>> as modifing the vni in the vxlan header and the underlay udp header has
>> no checksum.

There is bpf_csum_update(), does it work?
A helper call should be acceptable comparing with the csum calculation itself.

>>
>> In the first patch, we make skb->csum readable and writable, and we make
>> skb->ip_summed readable. For now, for tc only. With these 2 fields, we
>> don't need to call bpf helpers for csum update any more.
>>
>> In the second patch, we add some testcases for the read/write testing for
>> skb->csum and skb->ip_summed.
>>
>> If this series is acceptable, we can define the inlined functions for csum
>> update in libbpf in the next step.
> 
> One downside of exposing those as __sk_buff fields is that all this
> skb internal csum stuff now becomes a UAPI. And I'm not sure we want

+1. Please no new __sk_buff extension and no new conversion in 
bpf_convert_ctx_access().

> that :-) Should we add a lightweight kfunc to reset the fields instead?
> Or will it still have an unacceptable overhead?