Re: [PATCH v2] net: filter: BPF 'JIT' compiler for PPC64

On 19/07/11 16:59, Kumar Gala wrote:

On Jul 18, 2011, at 9:13 PM, Matt Evans wrote:

quoted

An implementation of a code generator for BPF programs to speed up packet
filtering on PPC64, inspired by Eric Dumazet's x86-64 version.

Filter code is generated as an ABI-compliant function in module_alloc()'d mem
with stackframe & prologue/epilogue generated if required (simple filters don't
need anything more than an li/blr).  The filter's local variables, M[], live in
registers.  Supports all BPF opcodes, although "complicated" loads from negative
packet offsets (e.g. SKF_LL_OFF) are not yet supported.

There are a couple of further optimisations left for future work; many-pass
assembly with branch-reach reduction and a register allocator to push M[]
variables into volatile registers would improve the code quality further.

This currently supports big-endian 64-bit PowerPC only (but is fairly simple
to port to PPC32 or LE!).

Enabled in the same way as x86-64:

	echo 1 > /proc/sys/net/core/bpf_jit_enable

Or, enabled with extra debug output:

	echo 2 > /proc/sys/net/core/bpf_jit_enable

Signed-off-by: Matt Evans <redacted>
---

V2: Removed some cut/paste woe in setting SEEN_X even on writes.
   Merci for le review, Eric!

arch/powerpc/Kconfig                  |    1 +
arch/powerpc/Makefile                 |    3 +-
arch/powerpc/include/asm/ppc-opcode.h |   40 ++
arch/powerpc/net/Makefile             |    4 +
arch/powerpc/net/bpf_jit.S            |  138 +++++++

can we rename to bpf_jit_64.S, since this doesn't work on PPC32.

quoted

arch/powerpc/net/bpf_jit.h            |  227 +++++++++++
arch/powerpc/net/bpf_jit_comp.c       |  690 +++++++++++++++++++++++++++++++++

same here, or split between bpf_jit_comp.c (shared between ppc32 & ppc64) and
bpf_jit_comp_64.c

A reasonable suggestion -- bpf_jit_64.S certainly.  I think it may not be worth
splitting bpf_jit_comp.c until we support both tho?  (I'm thinking
bpf_jit_comp_{32,64}.c would just house the stackframe generation code which is
the main difference, plus compile-time switched macros for the odd LD vs LWZ.)

Sorry it's not 32bit-friendly just yet (I knew you'd ask, hehe), I've postponed
that for when I get a mo :-)

Cheers,


Matt