Re: [PATCH] KVM: x86: optimize check for valid PAT value

[Sean Christopherson]

On Wed, Apr 10, 2019 at 12:55:53PM +0000, David Laight wrote:
> From: Paolo Bonzini
> > Sent: 10 April 2019 10:55
> > 
> > This check will soon be done on every nested vmentry and vmexit,
> > "parallelize" it using bitwise operations.
> > 
> > Signed-off-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>
> > ---
> ...
> > diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
> > index 28406aa1136d..7bc7ac9d2a44 100644
> > --- a/arch/x86/kvm/x86.h
> > +++ b/arch/x86/kvm/x86.h
> > @@ -347,4 +347,12 @@ static inline void kvm_after_interrupt(struct kvm_vcpu *vcpu)
> >  	__this_cpu_write(current_vcpu, NULL);
> >  }
> > 
> > +static inline bool kvm_pat_valid(u64 data)
> > +{
> > +	if (data & 0xF8F8F8F8F8F8F8F8)
> > +		return false;
> > +	/* 0, 1, 4, 5, 6, 7 are valid values.  */
> > +	return (data | ((data & 0x0202020202020202) << 1)) == data;
> > +}
> > +
> 
> How about:
> 	/*
> 	 * Each byte must be 0, 1, 4, 5, 6 or 7.
> 	 * Convert 001x to 011x then 100x so 2 and 3 fail the test.
> 	 */
> 	data |= (data ^ 0x0404040404040404ULL)) + 0x0202020202020202ULL;
> 	if (data & 0xF8F8F8F8F8F8F8F8ULL)
> 		return false;

Woah.  My vote is for Paolo's version as the separate checks allow the
reader to walk through step-by-step.  The generated assembly isn't much
different from a performance perspective since the TEST+JNE will be not
taken in the fast path.

Fancy:
   0x000000000004844f <+255>:   movabs $0xf8f8f8f8f8f8f8f8,%rcx
   0x0000000000048459 <+265>:   xor    %eax,%eax
   0x000000000004845b <+267>:   test   %rcx,%rdx
   0x000000000004845e <+270>:   jne    0x4848b <kvm_mtrr_valid+315>
   0x0000000000048460 <+272>:   movabs $0x202020202020202,%rax
   0x000000000004846a <+282>:   and    %rdx,%rax
   0x000000000004846d <+285>:   add    %rax,%rax
   0x0000000000048470 <+288>:   or     %rdx,%rax
   0x0000000000048473 <+291>:   cmp    %rdx,%rax
   0x0000000000048476 <+294>:   sete   %al
   0x0000000000048479 <+297>:   retq

Really fancy:
   0x0000000000048447 <+247>:   movabs $0x404040404040404,%rcx
   0x0000000000048451 <+257>:   movabs $0x202020202020202,%rax
   0x000000000004845b <+267>:   xor    %rdx,%rcx
   0x000000000004845e <+270>:   add    %rax,%rcx
   0x0000000000048461 <+273>:   movabs $0xf8f8f8f8f8f8f8f8,%rax
   0x000000000004846b <+283>:   or     %rcx,%rdx
   0x000000000004846e <+286>:   test   %rax,%rdx
   0x0000000000048471 <+289>:   sete   %al
   0x0000000000048474 <+292>:   retq