All of lore.kernel.org
 help / color / mirror / Atom feed
From: Juergen Gross <jgross@suse.com>
To: Wei Liu <wei.liu2@citrix.com>,
	Xen-devel <xen-devel@lists.xenproject.org>
Cc: Andrew Cooper <andrew.cooper3@citrix.com>,
	Jan Beulich <JBeulich@suse.com>
Subject: Re: [PATCH RFC 0/4] Use INVPCID to flush global mappings
Date: Thu, 15 Feb 2018 16:38:42 +0100	[thread overview]
Message-ID: <d0830e46-106d-29cb-aace-bfdfaa4c35d0@suse.com> (raw)
In-Reply-To: <20180215121040.20585-1-wei.liu2@citrix.com>

On 15/02/18 13:10, Wei Liu wrote:
> I wrote these patches sometime ago to explore PCID and INVPCID. I haven't
> thought through whether how to use both in Xen yet. But seeing Juergen laid out
> his thought on PCID and INVPCID I think some of the patches can be useful.
> 
> I had done some benchmark on the speed in one of my older branch by inserting
> some trace points before and after the flush. It showed that twiddling CR4.PGE
> is 3 to 5 times slower than invpcid.
> 
> This series is in incomplete -- obviously we have CR4.PGE twiddling in a few
> other places. But if you think it is beneficial I can try to convert those
> places as well.

I just did a little experiment by replacing the %cr4 based TLB flush in
Jan's XPTI patches by invpcid, on top of my last XPTI speedup patch (no
fancy ALTERNATIVE, just a plain replacement).

Doing a parallel build of the hypervisor in dom0 showed following data:

                real      user      sys
xpti=no         61.2     167.7     71.9
xpti=yes       112.1     170.1    141.8
 + my speedup  103.0     171.2    131.2
  + invpcid     99.0     170.2    122.0

So system time reduction due to invpcid is quite nice.


Juergen

_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel

      parent reply	other threads:[~2018-02-15 15:38 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-02-15 12:10 [PATCH RFC 0/4] Use INVPCID to flush global mappings Wei Liu
2018-02-15 12:10 ` [PATCH RFC 1/4] x86: introduce cpu_has_invpcid Wei Liu
2018-02-15 12:31   ` Jan Beulich
2018-02-15 12:10 ` [PATCH RFC 2/4] x86: report if PCID and INVPCID are supported Wei Liu
2018-02-15 12:10 ` [PATCH RFC 3/4] x86: add invpcid.h Wei Liu
2018-02-15 12:15   ` Andrew Cooper
2018-02-15 12:24     ` Wei Liu
2018-02-15 12:26       ` Andrew Cooper
2018-02-15 12:34   ` Jan Beulich
2018-02-15 12:35     ` Wei Liu
2018-02-15 13:23       ` Jan Beulich
2018-02-15 12:10 ` [PATCH RFC 4/4] x86: use invpcid to do global flush Wei Liu
2018-02-15 15:38 ` Juergen Gross [this message]

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=d0830e46-106d-29cb-aace-bfdfaa4c35d0@suse.com \
    --to=jgross@suse.com \
    --cc=JBeulich@suse.com \
    --cc=andrew.cooper3@citrix.com \
    --cc=wei.liu2@citrix.com \
    --cc=xen-devel@lists.xenproject.org \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.