Re: [PATCH v4 bpf-next 6/7] bpf: introduce bpf_prog_pack allocator

[Alexei Starovoitov]

On Wed, Jan 19, 2022 at 8:48 PM Song Liu <songliubraving@xxxxxx> wrote:
>
>
>
> > On Jan 19, 2022, at 8:14 PM, Alexei Starovoitov <alexei.starovoitov@xxxxxxxxx> wrote:
> >
> > On Wed, Jan 19, 2022 at 03:06:19PM -0800, Song Liu wrote:
> >>
> >> +/*
> >> + * BPF program pack allocator.
> >> + *
> >> + * Most BPF programs are pretty small. Allocating a hole page for each
> >> + * program is sometime a waste. Many small bpf program also adds pressure
> >> + * to instruction TLB. To solve this issue, we introduce a BPF program pack
> >> + * allocator. The prog_pack allocator uses HPAGE_PMD_SIZE page (2MB on x86)
> >> + * to host BPF programs.
> >> + */
> >> +#define BPF_PROG_PACK_SIZE  HPAGE_PMD_SIZE
> >> +#define BPF_PROG_MAX_PACK_PROG_SIZE HPAGE_PMD_SIZE
> >
> > We have a synthetic test with 1M bpf instructions. How did it JIT?
> > Are you saying we were lucky that every BPF insn was JITed to <2 bytes x86?
> > Did I misread the 2MB limit?
>
> The logic is, if the program is bigger than 2MB, we fall back to use
> module_alloc(). This limitation simplifies the bpf_prog_pack allocator.

Ahh. Missed this part of the diff. Makes sense.