From mboxrd@z Thu Jan 1 00:00:00 1970 From: Avi Kivity Subject: Re: [PATCH 4/4] KVM: x86 emulator: fix REPZ/REPNZ termination condition Date: Tue, 17 Aug 2010 12:29:10 +0300 Message-ID: <4C6A5666.10807@redhat.com> References: <1282033603-25938-1-git-send-email-avi@redhat.com> <1282033603-25938-5-git-send-email-avi@redhat.com> <20100817091302.GW10499@redhat.com> <4C6A5462.3090705@redhat.com> <20100817092727.GX10499@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: kvm@vger.kernel.org, Marcelo Tosatti , Mohammed Gamal To: Gleb Natapov Return-path: Received: from mx1.redhat.com ([209.132.183.28]:23343 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1757059Ab0HQJ3M (ORCPT ); Tue, 17 Aug 2010 05:29:12 -0400 In-Reply-To: <20100817092727.GX10499@redhat.com> Sender: kvm-owner@vger.kernel.org List-ID: On 08/17/2010 12:27 PM, Gleb Natapov wrote: > On Tue, Aug 17, 2010 at 12:20:34PM +0300, Avi Kivity wrote: >> On 08/17/2010 12:13 PM, Gleb Natapov wrote: >>> On Tue, Aug 17, 2010 at 11:26:43AM +0300, Avi Kivity wrote: >>>> EFLAGS.ZF needs to be checked after each iteration, not before. >>>> >>>> Signed-off-by: Avi Kivity >>>> --- >>>> arch/x86/kvm/emulate.c | 42 +++++++++++++++++++++++------------------- >>>> 1 files changed, 23 insertions(+), 19 deletions(-) >>>> >>>> diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c >>>> index 0c0ada9..a2edfb1 100644 >>>> --- a/arch/x86/kvm/emulate.c >>>> +++ b/arch/x86/kvm/emulate.c >>>> @@ -2747,6 +2747,7 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt) >>>> int rc = X86EMUL_CONTINUE; >>>> int saved_dst_type = c->dst.type; >>>> int irq; /* Used for int 3, int, and into */ >>>> + ulong old_eip; >>> Is never used. >>> >> Whoops. >> >>>> @@ -3250,13 +3234,33 @@ writeback: >>>> if (c->rep_prefix&& (c->d& String)) { >>>> struct read_cache *rc =&ctxt->decode.io_read; >>>> register_address_increment(c,&c->regs[VCPU_REGS_RCX], -1); >>>> + /* The second termination condition only applies for REPE >>>> + * and REPNE. Test if the repeat string operation prefix is >>>> + * REPE/REPZ or REPNE/REPNZ and if it's the case it tests the >>>> + * corresponding termination condition according to: >>>> + * - if REPE/REPZ and ZF = 0 then done >>>> + * - if REPNE/REPNZ and ZF = 1 then done >>>> + */ >>>> + if ((c->b == 0xa6) || (c->b == 0xa7) || >>>> + (c->b == 0xae) || (c->b == 0xaf)) { >>>> + trace_printk("c->eip %lx ctxt->eip %lx\n", >>>> + c->eip, ctxt->eip); >>>> + if (((c->rep_prefix == REPE_PREFIX)&& >>>> + ((ctxt->eflags& EFLG_ZF) == 0)) >>>> + || ((c->rep_prefix == REPNE_PREFIX)&& >>>> + ((ctxt->eflags& EFLG_ZF) == EFLG_ZF))) { >>>> + ctxt->restart = false; >>> Why not jump to string_done label here? >> It does a 'goto done;' which skips a couple of things. >> > The only thing it skips is: > ctxt->decode.mem_read.end = 0; > as far as I can see. And this is ok if instruction is completed. I'd like to avoid this interdependency (and there are enough gotos in the emulator already). -- error compiling committee.c: too many arguments to function