Re: RFC: Getting rid of LTR in VMX

From: Andy Lutomirski
Date: Mon Feb 20 2017 - 11:46:41 EST

On Mon, Feb 20, 2017 at 3:05 AM, Paolo Bonzini <pbonzini@xxxxxxxxxx> wrote:
> On 18/02/2017 04:29, Andy Lutomirski wrote:
>> There's no code here because the patch is trivial, but I want to run
>> the idea by you all first to see if there are any issues.
>> VMX is silly and forces the TSS limit to the minimum on VM exits. KVM
>> wastes lots of cycles bumping it back up to accomodate the io bitmap.
> Actually looked at the code now...
> reload_tss is only invoked for userspace exits, so it is a nice-to-have
> but it wouldn't show on most workloads. Still it does save 150-200
> clock cycles to remove it (I just commented out reload_tss() from
> __vmx_load_host_state to test).

That's for anything involving userspace or preemption, right?

> Another 100-150 could be saved if we could just use rdgsbase/wrgsbase,
> instead of rdmsr/wrmsr, to read and write the kernel GS. Super hacky
> patch after sig.

I have a Real Patch Series (tm) to do that, but it has a couple of
unresolved corner cases so far.

That being said, vmx_save_host_state() is, um, poorly optimized. I'll
try to find some time to fix the obvious things. Meanwhile, I'll send
real patches for TR.

> + cr4_set_bits(X86_CR4_FSGSBASE);

Nice root hole :-p