[PATCH mptcp-next v10 0/8] BPF packet scheduler

Geliang Tang posted 8 patches 2 years ago
Patches applied successfully (tree, apply log)
git fetch https://github.com/multipath-tcp/mptcp_net-next tags/patchew/cover.1649303876.git.geliang.tang@suse.com
Maintainers: Mat Martineau <mathew.j.martineau@linux.intel.com>, Song Liu <songliubraving@fb.com>, Shuah Khan <shuah@kernel.org>, John Fastabend <john.fastabend@gmail.com>, Daniel Borkmann <daniel@iogearbox.net>, Paolo Abeni <pabeni@redhat.com>, Jonathan Corbet <corbet@lwn.net>, Matthieu Baerts <matthieu.baerts@tessares.net>, Jakub Kicinski <kuba@kernel.org>, KP Singh <kpsingh@kernel.org>, Martin KaFai Lau <kafai@fb.com>, Andrii Nakryiko <andrii@kernel.org>, "David S. Miller" <davem@davemloft.net>, Alexei Starovoitov <ast@kernel.org>, Yonghong Song <yhs@fb.com>
There is a newer version of this series
Documentation/networking/mptcp-sysctl.rst     |   8 ++
include/net/mptcp.h                           |  13 ++
kernel/bpf/bpf_struct_ops_types.h             |   4 +
net/mptcp/Makefile                            |   2 +-
net/mptcp/bpf.c                               | 129 ++++++++++++++++++
net/mptcp/ctrl.c                              |  14 ++
net/mptcp/protocol.c                          |  16 ++-
net/mptcp/protocol.h                          |  16 +++
net/mptcp/sched.c                             | 104 ++++++++++++++
.../testing/selftests/bpf/bpf_mptcp_helpers.h |  12 ++
.../testing/selftests/bpf/prog_tests/mptcp.c  | 113 +++++++++++++++
.../selftests/bpf/progs/mptcp_bpf_first.c     |  30 ++++
12 files changed, 456 insertions(+), 5 deletions(-)
create mode 100644 net/mptcp/sched.c
create mode 100644 tools/testing/selftests/bpf/progs/mptcp_bpf_first.c
[PATCH mptcp-next v10 0/8] BPF packet scheduler
Posted by Geliang Tang 2 years ago
v10:
 - patch 5: keep msk->last_snd setting in get_subflow().
 - patch 6: add bpf_mptcp_sched_btf_struct_access().
 - patch 8: use MIN() in sys/param.h, instead of defining a new one.
 - update commit logs.

base-commit: export/20220406T054706

v9:
 - patch 2: add the missing mptcp_sched_init() invoking in
   mptcp_proto_init().
 - patch 5: set last_snd after invoking get_subflow().
 - patch 7: merge the squash-to patch.

v8:
 - use global sched_list instead of pernet sched_list.
 - drop synchronize_rcu() in mptcp_unregister_scheduler().
 - update mptcp_init_sched and mptcp_release_sched as Mat and Florian
   suggested.
 - fix the build break in patch 8.
 - depends on: "add skc_to_mptcp_sock" v14.
 - export/20220325T055307

v7:
 - add bpf_try_module_get in mptcp_init_sched.
 - add bpf_module_put in mptcp_release_sched.
 - rename bpf_first to mptcp_bpf_first.
 - update commit logs.

v6:
 - still use pernet sched_list, use current->nsproxy->net_ns in BPF
   context instead of using init_net.
 - patch 1:
   - use rcu_read_lock instead of spin_lock in mptcp_sched_find as Florian suggested.
   - drop synchronize_rcu in sched_exit_net as Florian suggested.
   - keep synchronize_rcu in mptcp_unregister_scheduler, otherwise, got
     a workqueue lockup in my test.
   - update Makefile as Mat suggested.
 - patch 2:
   - add mptcp_sched_data_init to register default sched, instead of
     registering it in init_net.
 - patch 5:
   - move mptcp_sched_get_subflow to protocol.h as Mat suggested.
 - patch 6:
   - use current->nsproxy->net_ns instead of init_net.
 - patch 8:
   - add send_data to send more data, instead of send_byte.

v5:
 - patch 1: define per-namespace sched_list (but only used init_net
   namespace. It is difficult to get 'net' in bpf_mptcp_sched_reg and
   bpf_mptcp_sched_unreg. I need some suggestions here.)
 - patch 2: skip mptcp_sched_default in mptcp_unregister_scheduler.
 - patch 8: add tests into mptcp.c, instead of bpf_tcp_ca.c.

v4:
 - set msk->sched to &mptcp_sched_default when the sched argument is NULL
in mptcp_init_sched().

v3:
 - add mptcp_release_sched helper in patch 4.
 - rename mptcp_set_sched to mptcp_init_sched in patch 4.
 - add mptcp_sched_first_release in patch 7.
 - do some cleanups.

v2:
 - split into more small patches.
 - change all parameters of mptcp_sched_ops from sk to msk:
       void (*init)(struct mptcp_sock *msk);
       void (*release)(struct mptcp_sock *msk);
       struct sock *   (*get_subflow)(struct mptcp_sock *msk);
 - add tests in bpf_tcp_ca.c, instead of adding a new one.

v1:
 - Addressed to the commends in the RFC version.

Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/75

Geliang Tang (8):
  mptcp: add struct mptcp_sched_ops
  mptcp: register default scheduler
  mptcp: add a new sysctl scheduler
  mptcp: add sched in mptcp_sock
  mptcp: add get_subflow wrapper
  mptcp: add bpf_mptcp_sched_ops
  selftests: bpf: add bpf_first scheduler
  selftests: bpf: add bpf_first test

 Documentation/networking/mptcp-sysctl.rst     |   8 ++
 include/net/mptcp.h                           |  13 ++
 kernel/bpf/bpf_struct_ops_types.h             |   4 +
 net/mptcp/Makefile                            |   2 +-
 net/mptcp/bpf.c                               | 129 ++++++++++++++++++
 net/mptcp/ctrl.c                              |  14 ++
 net/mptcp/protocol.c                          |  16 ++-
 net/mptcp/protocol.h                          |  16 +++
 net/mptcp/sched.c                             | 104 ++++++++++++++
 .../testing/selftests/bpf/bpf_mptcp_helpers.h |  12 ++
 .../testing/selftests/bpf/prog_tests/mptcp.c  | 113 +++++++++++++++
 .../selftests/bpf/progs/mptcp_bpf_first.c     |  30 ++++
 12 files changed, 456 insertions(+), 5 deletions(-)
 create mode 100644 net/mptcp/sched.c
 create mode 100644 tools/testing/selftests/bpf/progs/mptcp_bpf_first.c

-- 
2.34.1


Re: [PATCH mptcp-next v10 0/8] BPF packet scheduler
Posted by Mat Martineau 2 years ago
On Thu, 7 Apr 2022, Geliang Tang wrote:

> v10:
> - patch 5: keep msk->last_snd setting in get_subflow().
> - patch 6: add bpf_mptcp_sched_btf_struct_access().
> - patch 8: use MIN() in sys/param.h, instead of defining a new one.
> - update commit logs.
>
> base-commit: export/20220406T054706
>

Hi Geliang -

Thanks for updating for v10.

One thing we talked about in the meeting today morning was that the 
in-kernel scheduler doesn't use mptcp_subflow_get_send(), it uses 
mptcp_subflow_get_retrans(). The BPF scheduler needs to handle resends 
too. I think only one BPF hook is still needed, but with an arg that says 
whether it's a resend or not.

Also, the out-of-tree MPTCP kernel scheduler allows for sending 
simulataneously on multiple subflows. This would require a way for the BPF 
hook to return more than one ssk (or maybe some other representation of 
the subflows), and then a way for the MPTCP tx/rtx code to send on 
multiple ssks. Mattheiu, do you know anything about how often the 
'redundant' scheduler is used?

- Mat


> v9:
> - patch 2: add the missing mptcp_sched_init() invoking in
>   mptcp_proto_init().
> - patch 5: set last_snd after invoking get_subflow().
> - patch 7: merge the squash-to patch.
>
> v8:
> - use global sched_list instead of pernet sched_list.
> - drop synchronize_rcu() in mptcp_unregister_scheduler().
> - update mptcp_init_sched and mptcp_release_sched as Mat and Florian
>   suggested.
> - fix the build break in patch 8.
> - depends on: "add skc_to_mptcp_sock" v14.
> - export/20220325T055307
>
> v7:
> - add bpf_try_module_get in mptcp_init_sched.
> - add bpf_module_put in mptcp_release_sched.
> - rename bpf_first to mptcp_bpf_first.
> - update commit logs.
>
> v6:
> - still use pernet sched_list, use current->nsproxy->net_ns in BPF
>   context instead of using init_net.
> - patch 1:
>   - use rcu_read_lock instead of spin_lock in mptcp_sched_find as Florian suggested.
>   - drop synchronize_rcu in sched_exit_net as Florian suggested.
>   - keep synchronize_rcu in mptcp_unregister_scheduler, otherwise, got
>     a workqueue lockup in my test.
>   - update Makefile as Mat suggested.
> - patch 2:
>   - add mptcp_sched_data_init to register default sched, instead of
>     registering it in init_net.
> - patch 5:
>   - move mptcp_sched_get_subflow to protocol.h as Mat suggested.
> - patch 6:
>   - use current->nsproxy->net_ns instead of init_net.
> - patch 8:
>   - add send_data to send more data, instead of send_byte.
>
> v5:
> - patch 1: define per-namespace sched_list (but only used init_net
>   namespace. It is difficult to get 'net' in bpf_mptcp_sched_reg and
>   bpf_mptcp_sched_unreg. I need some suggestions here.)
> - patch 2: skip mptcp_sched_default in mptcp_unregister_scheduler.
> - patch 8: add tests into mptcp.c, instead of bpf_tcp_ca.c.
>
> v4:
> - set msk->sched to &mptcp_sched_default when the sched argument is NULL
> in mptcp_init_sched().
>
> v3:
> - add mptcp_release_sched helper in patch 4.
> - rename mptcp_set_sched to mptcp_init_sched in patch 4.
> - add mptcp_sched_first_release in patch 7.
> - do some cleanups.
>
> v2:
> - split into more small patches.
> - change all parameters of mptcp_sched_ops from sk to msk:
>       void (*init)(struct mptcp_sock *msk);
>       void (*release)(struct mptcp_sock *msk);
>       struct sock *   (*get_subflow)(struct mptcp_sock *msk);
> - add tests in bpf_tcp_ca.c, instead of adding a new one.
>
> v1:
> - Addressed to the commends in the RFC version.
>
> Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/75
>
> Geliang Tang (8):
>  mptcp: add struct mptcp_sched_ops
>  mptcp: register default scheduler
>  mptcp: add a new sysctl scheduler
>  mptcp: add sched in mptcp_sock
>  mptcp: add get_subflow wrapper
>  mptcp: add bpf_mptcp_sched_ops
>  selftests: bpf: add bpf_first scheduler
>  selftests: bpf: add bpf_first test
>
> Documentation/networking/mptcp-sysctl.rst     |   8 ++
> include/net/mptcp.h                           |  13 ++
> kernel/bpf/bpf_struct_ops_types.h             |   4 +
> net/mptcp/Makefile                            |   2 +-
> net/mptcp/bpf.c                               | 129 ++++++++++++++++++
> net/mptcp/ctrl.c                              |  14 ++
> net/mptcp/protocol.c                          |  16 ++-
> net/mptcp/protocol.h                          |  16 +++
> net/mptcp/sched.c                             | 104 ++++++++++++++
> .../testing/selftests/bpf/bpf_mptcp_helpers.h |  12 ++
> .../testing/selftests/bpf/prog_tests/mptcp.c  | 113 +++++++++++++++
> .../selftests/bpf/progs/mptcp_bpf_first.c     |  30 ++++
> 12 files changed, 456 insertions(+), 5 deletions(-)
> create mode 100644 net/mptcp/sched.c
> create mode 100644 tools/testing/selftests/bpf/progs/mptcp_bpf_first.c
>
> -- 
> 2.34.1
>
>
>

--
Mat Martineau
Intel