From mboxrd@z Thu Jan 1 00:00:00 1970 From: Will Deacon Subject: Re: [PATCH] arm64: bpf: jit JMP_JSET_{X,K} Date: Fri, 13 May 2016 11:03:07 +0100 Message-ID: <20160513100307.GC13689@arm.com> References: <1463121478-18484-1-git-send-email-zlim.lnx@gmail.com> <20160513095718.GB13689@arm.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Alexei Starovoitov , "David S. Miller" , Catalin Marinas , Daniel Borkmann , Yang Shi , netdev@vger.kernel.org, linux-arm-kernel@lists.infradead.org To: Zi Shen Lim Return-path: Received: from foss.arm.com ([217.140.101.70]:35270 "EHLO foss.arm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751796AbcEMKDB (ORCPT ); Fri, 13 May 2016 06:03:01 -0400 Content-Disposition: inline In-Reply-To: <20160513095718.GB13689@arm.com> Sender: netdev-owner@vger.kernel.org List-ID: On Fri, May 13, 2016 at 10:57:18AM +0100, Will Deacon wrote: > On Thu, May 12, 2016 at 11:37:58PM -0700, Zi Shen Lim wrote: > > Original implementation commit e54bcde3d69d ("arm64: eBPF JIT compiler") > > had the relevant code paths, but due to an oversight always fail jiting. > > > > As a result, we had been falling back to BPF interpreter whenever a BPF > > program has JMP_JSET_{X,K} instructions. > > > > With this fix, we confirm that the corresponding tests in lib/test_bpf > > continue to pass, and also jited. > > > > ... > > [ 2.784553] test_bpf: #30 JSET jited:1 188 192 197 PASS > > [ 2.791373] test_bpf: #31 tcpdump port 22 jited:1 325 677 625 PASS > > [ 2.808800] test_bpf: #32 tcpdump complex jited:1 323 731 991 PASS > > ... > > [ 3.190759] test_bpf: #237 JMP_JSET_K: if (0x3 & 0x2) return 1 jited:1 110 PASS > > [ 3.192524] test_bpf: #238 JMP_JSET_K: if (0x3 & 0xffffffff) return 1 jited:1 98 PASS > > [ 3.211014] test_bpf: #249 JMP_JSET_X: if (0x3 & 0x2) return 1 jited:1 120 PASS > > [ 3.212973] test_bpf: #250 JMP_JSET_X: if (0x3 & 0xffffffff) return 1 jited:1 89 PASS > > ... > > > > Fixes: e54bcde3d69d ("arm64: eBPF JIT compiler") > > Signed-off-by: Zi Shen Lim > > --- > > arch/arm64/net/bpf_jit_comp.c | 1 + > > 1 file changed, 1 insertion(+) > > > > diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c > > index 031ed08..d0d5190 100644 > > --- a/arch/arm64/net/bpf_jit_comp.c > > +++ b/arch/arm64/net/bpf_jit_comp.c > > @@ -478,6 +478,7 @@ emit_cond_jmp: > > case BPF_JGE: > > jmp_cond = A64_COND_CS; > > break; > > + case BPF_JSET: > > case BPF_JNE: > > jmp_cond = A64_COND_NE; > > break; > > Are you sure about this? filter.txt says: > > jne - Jump on K != A > ... > jset - Jump on k & A > > so it looks weird wiring them both to the same thing. I'm not sure you > can express this as a simple CMP + B.. Ah, sorry, I see how this works now. I overlooked the BPF_JMP | BPF_JSET | BPF_X case emitting a TST instruction. In which case: Acked-by: Will Deacon I'm assuming David will queue this? Will