linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Sean Christopherson <sean.j.christopherson@intel.com>
To: Andrea Arcangeli <aarcange@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>,
	Vitaly Kuznetsov <vkuznets@redhat.com>,
	"Dr. David Alan Gilbert" <dgilbert@redhat.com>,
	Marcelo Tosatti <mtosatti@redhat.com>,
	Peter Xu <peterx@redhat.com>,
	kvm@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH 15/17] KVM: retpolines: x86: eliminate retpoline from vmx.c exit handlers
Date: Mon, 23 Sep 2019 11:15:58 -0700	[thread overview]
Message-ID: <20190923181558.GI18195@linux.intel.com> (raw)
In-Reply-To: <20190923174244.GA19996@redhat.com>

On Mon, Sep 23, 2019 at 01:42:44PM -0400, Andrea Arcangeli wrote:
> On Mon, Sep 23, 2019 at 06:53:10PM +0200, Paolo Bonzini wrote:
> > On 23/09/19 18:37, Sean Christopherson wrote:
> > >> Would it be too much if we get rid of
> > >> kvm_vmx_exit_handlers completely replacing this code with one switch()?
> > > Hmm, that'd require redirects for nVMX functions since they are set at
> > > runtime.  That isn't necessarily a bad thing.  The approach could also be
> > > used if Paolo's idea of making kvm_vmx_max_exit_handlers const allows the
> > > compiler to avoid retpoline.
> > 
> > But aren't switch statements also retpolin-ized if they use a jump table?
> 
> See commit a9d57ef15cbe327fe54416dd194ee0ea66ae53a4.
> 
> We disabled that feature or the kernel would potentially suffer the
> downsides of the exit handlers through pointer to functions for every
> switch statement in the kernel.
> 
> In turn you can't make it run any faster by converting my "if" to a
> "switch" at least the "if" can deterministic control the order of what
> is more likely that we should also re-review, but the order of secondary
> effect, the important thing is to reduce the retpolines to zero during
> normal hrtimer guest runtime.

On the flip side, using a switch for the fast-path handlers gives the
compiler more flexibility to rearrange and combine checks.  Of course that
doesn't mean the compiler will actually generate faster code for our
purposes :-)

Anyways, getting rid of the retpolines is much more important.

  reply	other threads:[~2019-09-23 18:16 UTC|newest]

Thread overview: 68+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-09-20 21:24 [PATCH 00/17] KVM monolithic v1 Andrea Arcangeli
2019-09-20 21:24 ` [PATCH 01/17] x86: spec_ctrl: fix SPEC_CTRL initialization after kexec Andrea Arcangeli
2019-09-23 10:22   ` Paolo Bonzini
2019-09-23 15:30     ` Sean Christopherson
2019-09-23 17:34       ` Andrea Arcangeli
2019-09-23 22:27         ` Sean Christopherson
2019-09-20 21:24 ` [PATCH 02/17] KVM: monolithic: x86: convert the kvm_x86_ops methods to external functions Andrea Arcangeli
2019-09-23 10:19   ` Paolo Bonzini
2019-09-23 16:13     ` Sean Christopherson
2019-09-23 16:51       ` Paolo Bonzini
2019-09-23 19:21     ` Andrea Arcangeli
2019-09-20 21:24 ` [PATCH 03/17] KVM: monolithic: x86: handle the request_immediate_exit variation Andrea Arcangeli
2019-09-23 22:35   ` Sean Christopherson
2019-09-23 23:06     ` Andrea Arcangeli
2019-09-23 23:45       ` Sean Christopherson
2019-09-24  0:24         ` Andrea Arcangeli
2019-09-20 21:24 ` [PATCH 04/17] KVM: monolithic: x86: convert the kvm_pmu_ops methods to external functions Andrea Arcangeli
2019-09-20 21:24 ` [PATCH 05/17] KVM: monolithic: x86: enable the kvm_x86_ops " Andrea Arcangeli
2019-09-20 21:24 ` [PATCH 06/17] KVM: monolithic: x86: enable the kvm_pmu_ops " Andrea Arcangeli
2019-09-20 21:24 ` [PATCH 07/17] KVM: monolithic: x86: adjust the section prefixes Andrea Arcangeli
2019-09-23 10:15   ` Paolo Bonzini
2019-09-25 12:13     ` Andrea Arcangeli
2019-09-25 12:32       ` Paolo Bonzini
2019-09-20 21:25 ` [PATCH 08/17] KVM: monolithic: adjust the section prefixes in the KVM common code Andrea Arcangeli
2019-09-20 21:25 ` [PATCH 09/17] KVM: monolithic: x86: remove kvm.ko Andrea Arcangeli
2019-09-20 21:25 ` [PATCH 10/17] KVM: monolithic: x86: use the external functions instead of kvm_x86_ops Andrea Arcangeli
2019-09-23 10:02   ` Paolo Bonzini
2019-09-20 21:25 ` [PATCH 11/17] KVM: monolithic: x86: remove exports Andrea Arcangeli
2019-09-20 21:25 ` [PATCH 12/17] KVM: monolithic: remove exports from KVM common code Andrea Arcangeli
2019-09-20 21:25 ` [PATCH 13/17] KVM: monolithic: x86: drop the kvm_pmu_ops structure Andrea Arcangeli
2019-09-23 10:21   ` Paolo Bonzini
2019-09-24  0:51     ` Andrea Arcangeli
2019-09-24  1:24       ` Paolo Bonzini
2019-09-20 21:25 ` [PATCH 14/17] KVM: monolithic: x86: inline more exit handlers in vmx.c Andrea Arcangeli
2019-09-23 10:19   ` Paolo Bonzini
2019-09-24  1:00     ` Andrea Arcangeli
2019-09-24  1:25       ` Paolo Bonzini
2019-09-24  1:55         ` Andrea Arcangeli
2019-09-24  2:56           ` Andrea Arcangeli
2019-09-25  7:52           ` Paolo Bonzini
2019-09-20 21:25 ` [PATCH 15/17] KVM: retpolines: x86: eliminate retpoline from vmx.c exit handlers Andrea Arcangeli
2019-09-23  9:31   ` Vitaly Kuznetsov
2019-09-23  9:57     ` Paolo Bonzini
2019-09-23 19:05       ` Andrea Arcangeli
2019-09-23 20:23         ` Sean Christopherson
2019-09-23 21:08           ` Andrea Arcangeli
2019-09-23 21:24             ` Sean Christopherson
2019-09-23 23:43               ` Andrea Arcangeli
2019-09-23 23:52                 ` Sean Christopherson
2019-09-24  0:16             ` Paolo Bonzini
2019-09-24  0:35               ` Sean Christopherson
2019-09-24  0:37                 ` Paolo Bonzini
2019-09-24  0:15           ` Paolo Bonzini
2019-09-24  0:38             ` Andrea Arcangeli
2019-09-24  0:46             ` Sean Christopherson
2019-09-24 21:46         ` Andrea Arcangeli
2019-09-25  7:50           ` Paolo Bonzini
2019-09-23 16:37     ` Sean Christopherson
2019-09-23 16:53       ` Paolo Bonzini
2019-09-23 17:42         ` Andrea Arcangeli
2019-09-23 18:15           ` Sean Christopherson [this message]
2019-09-23 19:12             ` Andrea Arcangeli
     [not found]     ` <E8FE7592-69C3-455E-8D80-A2D73BB2E14C@dinechin.org>
2019-09-25 20:51       ` Andrea Arcangeli
2019-09-23 16:28   ` Sean Christopherson
2019-09-20 21:25 ` [PATCH 16/17] KVM: retpolines: x86: eliminate retpoline from svm.c " Andrea Arcangeli
2019-09-23 10:01   ` Paolo Bonzini
2019-09-20 21:25 ` [PATCH 17/17] x86: retpolines: eliminate retpoline from msr event handlers Andrea Arcangeli
2019-09-23 15:39 ` [PATCH 00/17] KVM monolithic v1 Sean Christopherson

Reply instructions:

You may reply publicly 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=20190923181558.GI18195@linux.intel.com \
    --to=sean.j.christopherson@intel.com \
    --cc=aarcange@redhat.com \
    --cc=dgilbert@redhat.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mtosatti@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=peterx@redhat.com \
    --cc=vkuznets@redhat.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
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).