Il 30/07/2013 16:57, Arthur Chunqi Li ha scritto:
> On Tue, Jul 30, 2013 at 10:53 PM, Paolo Bonzini <pbonzini@xxxxxxxxxx> wrote:
>> Il 28/07/2013 16:00, Arthur Chunqi Li ha scritto:
>>> +
>>> + while (1) {
>>> + asm volatile (
>>> + "mov %%rsp, %%rsi\n\t"
>>> + "mov %2, %%rdi\n\t"
>>> + "vmwrite %%rsi, %%rdi\n\t"
>>> +
>>> + LOAD_GPR_C
>>> + "cmpl $0, %1\n\t"
>>> + "jne 1f\n\t"
>>> + LOAD_RFLAGS
>>> + "vmlaunch\n\t"
>>> + "jmp 2f\n\t"
>>> + "1: "
>>> + "vmresume\n\t"
>>> + "2: "
>>> + "setbe %0\n\t"
>>
>> Perhaps here add
>>
>> jbe vmx_return
>> ud2
>>
>> but it can be added in a follow-up.
>>
>>> + "vmx_return:\n\t"
>>> + SAVE_GPR_C
>>> + SAVE_RFLAGS
>>> + : "=m"(fail)
>>> + : "m"(launched), "i"(HOST_RSP)
>>> + : "rdi", "rsi", "memory", "cc"
>>> +
>>> + );
>>
>> Nice! :)
>>
>> I pushed the patch.
> Hi Paolo,
> Slow down pushing it. There's something wrong with host_rflags
> handling. I will commit another version as well as your suggestion,
> you could push that version.
Well, too late...
anyway I prefer follow-up patches because they make the differences
clearer. With a single 1200-line patch it is a bit complicated to follow.
Paolo
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
