KVM Archive on lore.kernel.org
 help / color / Atom feed
From: Sean Christopherson <sean.j.christopherson@intel.com>
To: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>,
	Wanpeng Li <wanpengli@tencent.com>,
	Jim Mattson <jmattson@google.com>, Joerg Roedel <joro@8bytes.org>,
	kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
	David Laight <David.Laight@ACULAB.COM>,
	Arvind Sankar <nivedita@alum.mit.edu>
Subject: Re: [PATCH v2 2/2] KVM: x86/mmu: Micro-optimize nEPT's bad memptype/XWR checks
Date: Fri, 10 Jan 2020 08:04:53 -0800
Message-ID: <20200110160453.GA21485@linux.intel.com> (raw)
In-Reply-To: <878smfr18i.fsf@vitty.brq.redhat.com>

On Fri, Jan 10, 2020 at 12:37:33PM +0100, Vitaly Kuznetsov wrote:
> Sean Christopherson <sean.j.christopherson@intel.com> writes:
> > --- a/arch/x86/kvm/mmu/paging_tmpl.h
> > +++ b/arch/x86/kvm/mmu/paging_tmpl.h
> > @@ -128,6 +128,21 @@ static inline int FNAME(is_present_gpte)(unsigned long pte)
> >  #endif
> >  }
> >  
> > +static bool FNAME(is_bad_mt_xwr)(struct rsvd_bits_validate *rsvd_check, u64 gpte)
> > +{
> > +#if PTTYPE != PTTYPE_EPT
> > +	return false;
> > +#else
> > +	return __is_bad_mt_xwr(rsvd_check, gpte);
> > +#endif
> > +}
> > +
> > +static bool FNAME(is_rsvd_bits_set)(struct kvm_mmu *mmu, u64 gpte, int level)
> > +{
> > +	return __is_rsvd_bits_set(&mmu->guest_rsvd_check, gpte, level) ||
> > +	       FNAME(is_bad_mt_xwr)(&mmu->guest_rsvd_check, gpte);
> > +}
> > +
> 
> Not sure if it would make sense/difference (well, this is famous KVM
> MMU!) but as FNAME(is_bad_mt_xwr)
> 
> has only one call site we could've as well merged it, something like:
> 
> static bool FNAME(is_rsvd_bits_set)(struct kvm_mmu *mmu, u64 gpte, int level)
> {
> #if PTTYPE == PTTYPE_EPT
> 	bool res =  __is_bad_mt_xwr(&mmu->guest_rsvd_check, gpte);
> #else
> 	bool res = false;
> #endif
> 	return __is_rsvd_bits_set(&mmu->guest_rsvd_check, gpte, level) || res;
> }
> 
> but keeping it in-line with __is_rsvd_bits_set()/__is_bad_mt_xwr() in
> mmu.c likely has greater benefits.

Ya, I don't love the code, but it was the least awful of the options I
tried, in that it's the most readable without being too obnoxious.


Similar to your suggestion, but it avoids evaluating __is_bad_mt_xwr() if
reserved bits are set, which is admittedly rare.

	return __is_rsvd_bits_set(&mmu->guest_rsvd_check, gpte, level)
#if PTTYPE == PTTYPE_EPT
	       || __is_bad_mt_xwr(&mmu->guest_rsvd_check, gpte)
#endif
	       ;

Or macrofying the call to keep the call site clean, but IMO this obfuscates
things too much.

	return __is_rsvd_bits_set(&mmu->guest_rsvd_check, gpte, level) ||
	       IS_BAD_MT_XWR(&mmu->guest_rsvd_check, gpte);

  reply index

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-01-09 23:06 [PATCH v2 0/2] KVM: x86/mmu: Optimize rsvd pte checks Sean Christopherson
2020-01-09 23:06 ` [PATCH v2 1/2] KVM: x86/mmu: Reorder the reserved bit check in prefetch_invalid_gpte() Sean Christopherson
2020-01-10 11:37   ` Vitaly Kuznetsov
2020-01-09 23:06 ` [PATCH v2 2/2] KVM: x86/mmu: Micro-optimize nEPT's bad memptype/XWR checks Sean Christopherson
2020-01-10 11:37   ` Vitaly Kuznetsov
2020-01-10 16:04     ` Sean Christopherson [this message]
2020-01-10 16:13       ` David Laight
2020-01-15 18:17       ` Paolo Bonzini

Reply instructions:

You may reply publically to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200110160453.GA21485@linux.intel.com \
    --to=sean.j.christopherson@intel.com \
    --cc=David.Laight@ACULAB.COM \
    --cc=jmattson@google.com \
    --cc=joro@8bytes.org \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=nivedita@alum.mit.edu \
    --cc=pbonzini@redhat.com \
    --cc=vkuznets@redhat.com \
    --cc=wanpengli@tencent.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

KVM Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/kvm/0 kvm/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 kvm kvm/ https://lore.kernel.org/kvm \
		kvm@vger.kernel.org
	public-inbox-index kvm

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.kvm


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git