Re: [RFC 09/13] x86/mm: Disable interrupts when flushing the TLB using CR3

From: Ingo Molnar
Date: Mon Jan 11 2016 - 05:51:14 EST



* Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx> wrote:

> >> Or is there some reason you wanted the odd flags version? If so, that
> >> should be documented.
> >
> > What do you mean "odd"?
>
> It's odd because it makes no sense for non-pcid (christ, I wish Intel had just
> called it "asid" instead, "pcid" always makes me react to "pci"), and I think it
> would make more sense to pair up the pcid case with the invpcid rather than have
> those preemption rules here.

The naming is really painful, so a trivial suggestion: could we just name all the
Linux side bits 'asid' or 'ctx_id' (even in x86 arch code) and only use 'PCID'
nomenclature in the very lowest level code?

I.e. rename pcid_live_cpus et al and most functions to the asid or ctx_id or asid
naming scheme or so. That would hide most of the naming ugliness.

Thanks,

Ingo