From: Alexei Starovoitov <alexei.starovoitov@gmail.com>
To: Cong Wang <xiyou.wangcong@gmail.com>
Cc: netdev@vger.kernel.org, bpf@vger.kernel.org,
duanxiongchun@bytedance.com, wangdongdong.6@bytedance.com,
jiang.wang@bytedance.com, Cong Wang <cong.wang@bytedance.com>
Subject: Re: [Patch bpf-next v7 00/13] sockmap: introduce BPF_SK_SKB_VERDICT and support UDP
Date: Sun, 28 Mar 2021 16:27:59 -0700 [thread overview]
Message-ID: <20210328232759.2ixde3jvudnl3pi6@ast-mbp> (raw)
In-Reply-To: <20210328202013.29223-1-xiyou.wangcong@gmail.com>
On Sun, Mar 28, 2021 at 01:20:00PM -0700, Cong Wang wrote:
> From: Cong Wang <cong.wang@bytedance.com>
>
> We have thousands of services connected to a daemon on every host
> via AF_UNIX dgram sockets, after they are moved into VM, we have to
> add a proxy to forward these communications from VM to host, because
> rewriting thousands of them is not practical. This proxy uses an
> AF_UNIX socket connected to services and a UDP socket to connect to
> the host. It is inefficient because data is copied between kernel
> space and user space twice, and we can not use splice() which only
> supports TCP. Therefore, we want to use sockmap to do the splicing
> without going to user-space at all (after the initial setup).
>
> Currently sockmap only fully supports TCP, UDP is partially supported
> as it is only allowed to add into sockmap. This patchset, as the second
> part of the original large patchset, extends sockmap with:
> 1) cross-protocol support with BPF_SK_SKB_VERDICT; 2) full UDP support.
>
> On the high level, ->read_sock() is required for each protocol to support
> sockmap redirection, and in order to do sock proto update, a new ops
> ->psock_update_sk_prot() is introduced, which is also required. And the
> BPF ->recvmsg() is also needed to replace the original ->recvmsg() to
> retrieve skmsg. To make life easier, we have to get rid of lock_sock()
> in sk_psock_handle_skb(), otherwise we would have to implement
> ->sendmsg_locked() on top of ->sendmsg(), which is ugly.
>
> Please see each patch for more details.
>
> To see the big picture, the original patchset is available here:
> https://github.com/congwang/linux/tree/sockmap
> this patchset is also available:
> https://github.com/congwang/linux/tree/sockmap2
>
> ---
> v7: use work_mutex to protect psock->work
> return err in udp_read_sock()
> add patch 6/13
> clean up test case
The feature looks great to me.
I think the selftest is a bit light in terms of coverage, but it's acceptable.
I'd like to see the final Acks from John/Daniel and Jakub/Lorenz before merging.
Folks,
please prioritize the review of these patches.
next prev parent reply other threads:[~2021-03-28 23:31 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-03-28 20:20 [Patch bpf-next v7 00/13] sockmap: introduce BPF_SK_SKB_VERDICT and support UDP Cong Wang
2021-03-28 20:20 ` [Patch bpf-next v7 01/13] skmsg: lock ingress_skb when purging Cong Wang
2021-03-28 20:20 ` [Patch bpf-next v7 02/13] skmsg: introduce a spinlock to protect ingress_msg Cong Wang
2021-03-29 19:11 ` John Fastabend
2021-03-28 20:20 ` [Patch bpf-next v7 03/13] net: introduce skb_send_sock() for sock_map Cong Wang
2021-03-28 20:20 ` [Patch bpf-next v7 04/13] skmsg: avoid lock_sock() in sk_psock_backlog() Cong Wang
2021-03-29 19:41 ` John Fastabend
2021-03-28 20:20 ` [Patch bpf-next v7 05/13] skmsg: use rcu work for destroying psock Cong Wang
2021-03-29 19:42 ` John Fastabend
2021-03-28 20:20 ` [Patch bpf-next v7 06/13] skmsg: use GFP_KERNEL in sk_psock_create_ingress_msg() Cong Wang
2021-03-29 19:44 ` John Fastabend
2021-03-28 20:20 ` [Patch bpf-next v7 07/13] sock_map: introduce BPF_SK_SKB_VERDICT Cong Wang
2021-03-29 20:09 ` John Fastabend
2021-03-30 1:27 ` Cong Wang
2021-03-28 20:20 ` [Patch bpf-next v7 08/13] sock: introduce sk->sk_prot->psock_update_sk_prot() Cong Wang
2021-03-28 20:20 ` [Patch bpf-next v7 09/13] udp: implement ->read_sock() for sockmap Cong Wang
2021-03-29 20:54 ` John Fastabend
2021-03-30 5:39 ` Cong Wang
2021-03-30 6:23 ` John Fastabend
2021-03-30 6:36 ` Cong Wang
2021-03-30 6:45 ` John Fastabend
2021-03-28 20:20 ` [Patch bpf-next v7 10/13] skmsg: extract __tcp_bpf_recvmsg() and tcp_bpf_wait_data() Cong Wang
2021-03-28 20:20 ` [Patch bpf-next v7 11/13] udp: implement udp_bpf_recvmsg() for sockmap Cong Wang
2021-03-28 20:20 ` [Patch bpf-next v7 12/13] sock_map: update sock type checks for UDP Cong Wang
2021-03-29 23:10 ` John Fastabend
2021-03-30 5:47 ` Cong Wang
2021-03-28 20:20 ` [Patch bpf-next v7 13/13] selftests/bpf: add a test case for udp sockmap Cong Wang
2021-03-28 23:27 ` Alexei Starovoitov [this message]
2021-03-29 15:03 ` [Patch bpf-next v7 00/13] sockmap: introduce BPF_SK_SKB_VERDICT and support UDP John Fastabend
2021-03-29 16:57 ` Cong Wang
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=20210328232759.2ixde3jvudnl3pi6@ast-mbp \
--to=alexei.starovoitov@gmail.com \
--cc=bpf@vger.kernel.org \
--cc=cong.wang@bytedance.com \
--cc=duanxiongchun@bytedance.com \
--cc=jiang.wang@bytedance.com \
--cc=netdev@vger.kernel.org \
--cc=wangdongdong.6@bytedance.com \
--cc=xiyou.wangcong@gmail.com \
/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