[v5,bpf-next,0/7] bpf_prog_pack allocator

Message

Song Liu Jan. 20, 2022, 7:12 p.m. UTC

Changes v4 => v5:
1. Do not use atomic64 for bpf_jit_current. (Alexei)

Changes v3 => v4:
1. Rename text_poke_jit() => text_poke_copy(). (Peter)
2. Change comment style. (Peter)

Changes v2 => v3:
1. Fix tailcall.

Changes v1 => v2:
1. Use text_poke instead of writing through linear mapping. (Peter)
2. Avoid making changes to non-x86_64 code.

Most BPF programs are small, but they consume a page each. For systems
with busy traffic and many BPF programs, this could also add significant
pressure to instruction TLB.

This set tries to solve this problem with customized allocator that pack
multiple programs into a huge page.

Patches 1-5 prepare the work. Patch 6 contains key logic of the allocator.
Patch 7 uses this allocator in x86_64 jit compiler.

Song Liu (7):
  x86/Kconfig: select HAVE_ARCH_HUGE_VMALLOC with HAVE_ARCH_HUGE_VMAP
  bpf: use bytes instead of pages for bpf_jit_[charge|uncharge]_modmem
  bpf: use size instead of pages in bpf_binary_header
  bpf: add a pointer of bpf_binary_header to bpf_prog
  x86/alternative: introduce text_poke_copy
  bpf: introduce bpf_prog_pack allocator
  bpf, x86_64: use bpf_prog_pack allocator

 arch/x86/Kconfig                     |   1 +
 arch/x86/include/asm/text-patching.h |   1 +
 arch/x86/kernel/alternative.c        |  32 ++++
 arch/x86/net/bpf_jit_comp.c          | 136 +++++++++++++----
 include/linux/bpf.h                  |   4 +-
 include/linux/filter.h               |  23 ++-
 kernel/bpf/core.c                    | 211 ++++++++++++++++++++++++---
 kernel/bpf/trampoline.c              |   6 +-
 8 files changed, 356 insertions(+), 58 deletions(-)

--
2.30.2

Comments

Song Liu Jan. 21, 2022, 1:06 a.m. UTC | #1

Hi Peter,

> On Jan 20, 2022, at 11:12 AM, Song Liu <[e-mail]> wrote:
> 
> Changes v4 => v5:
> 1. Do not use atomic64 for bpf_jit_current. (Alexei)
> 
> Changes v3 => v4:
> 1. Rename text_poke_jit() => text_poke_copy(). (Peter)
> 2. Change comment style. (Peter)
> 
> Changes v2 => v3:
> 1. Fix tailcall.
> 
> Changes v1 => v2:
> 1. Use text_poke instead of writing through linear mapping. (Peter)
> 2. Avoid making changes to non-x86_64 code.
> 
> Most BPF programs are small, but they consume a page each. For systems
> with busy traffic and many BPF programs, this could also add significant
> pressure to instruction TLB.
> 
> This set tries to solve this problem with customized allocator that pack
> multiple programs into a huge page.
> 
> Patches 1-5 prepare the work. Patch 6 contains key logic of the allocator.
> Patch 7 uses this allocator in x86_64 jit compiler.
> 
> Song Liu (7):
>  x86/Kconfig: select HAVE_ARCH_HUGE_VMALLOC with HAVE_ARCH_HUGE_VMAP
>  bpf: use bytes instead of pages for bpf_jit_[charge|uncharge]_modmem
>  bpf: use size instead of pages in bpf_binary_header
>  bpf: add a pointer of bpf_binary_header to bpf_prog
>  x86/alternative: introduce text_poke_copy
>  bpf: introduce bpf_prog_pack allocator
>  bpf, x86_64: use bpf_prog_pack allocator

Could you please share your feedback for and/or ack this set?

Thanks,
Song