Re: [patch 4/9] x86/io: Speedup schedule out of I/O bitmap user

[Thomas Gleixner]

On Fri, 8 Nov 2019, Andy Lutomirski wrote:
> > On Nov 8, 2019, at 3:45 PM, Thomas Gleixner <tglx@xxxxxxxxxxxxx> wrote:
> > ïOn Fri, 8 Nov 2019, Andy Lutomirski wrote:
> >> SDM vol 3 27.5.2 says the BUILD_BUG_ON is right.  Or am I
> >> misunderstanding you?
> >> 
> >> I'm reasonably confident that the TSS limit is indeed 0x67 after VM
> >> exit, and I wrote the existing code that tries to optimize this to avoid
> >> LTR when not needed.
> > 
> > The BUILD_BUG_ON(IO_BITMAP_OFFSET - 1 == 0x67) in the VMX code is bogus in
> > two aspects:
> > 
> > 1) This wants to be in generic x86 code
> 
> I think disagree. The only thing special about 0x67 is that VMX hard
> codes it. Itâs specifically a VMX-ism. So I think the VMX code should
> indeed assert that 0x67 is a safe value.

Yes, it is a VMX specific issue, but I really prefer the build to fail in
the common code without having to enable VMX if something changes the
TSS layout in incompatible ways.

Thanks,

	tglx