linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Dave Hansen <dave.hansen@linux.intel.com>
To: Ingo Molnar <mingo@kernel.org>, Thomas Gleixner <tglx@linutronix.de>
Cc: "Linus Torvalds" <torvalds@linux-foundation.org>,
	"Linux Kernel Mailing List" <linux-kernel@vger.kernel.org>,
	linux-mm <linux-mm@kvack.org>,
	"Andrea Arcangeli" <aarcange@redhat.com>,
	"Andrew Lutomirski" <luto@kernel.org>,
	"Kees Cook" <keescook@google.com>,
	"Hugh Dickins" <hughd@google.com>,
	"Jürgen Groß" <jgross@suse.com>,
	"the arch/x86 maintainers" <x86@kernel.org>,
	namit@vmware.com
Subject: Re: [PATCH 00/11] Use global pages with PTI
Date: Tue, 27 Mar 2018 13:19:40 -0700	[thread overview]
Message-ID: <a3837d26-031f-6bce-cb1e-f34e5c0cfd2f@linux.intel.com> (raw)
In-Reply-To: <20180327200719.lvdomez6hszpmo4s@gmail.com>

On 03/27/2018 01:07 PM, Ingo Molnar wrote:
>  - To see at minimum stddev numbers, to make sure we are not looking at some weird
>    statistical artifact. (I also outlined a more robust measurement method.)
> 
>  - If the numbers are right, a CPU engineer should have a look if possible, 
>    because frankly this effect is not expected and is not intuitive. Where global 
>    pages can be used safely they are almost always an unconditional win.
>    Maybe we are missing some limitation or some interaction with PCID.
> 
> Since we'll be using PCID even on Meltdown-fixed hardware, maybe the same negative 
> performance effect already exists on non-PTI kernels as well, we just never 
> noticed?

Yep, totally agree.  I'll do the more robust collection and also explore
on "real" !PCID hardware.  I also know the right CPU folks to go ask
about this, I just want to do the second round of robust data collection
before I bug them.

  reply	other threads:[~2018-03-27 20:19 UTC|newest]

Thread overview: 38+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-03-23 17:44 [PATCH 00/11] Use global pages with PTI Dave Hansen
2018-03-23 17:44 ` [PATCH 01/11] x86/mm: factor out pageattr _PAGE_GLOBAL setting Dave Hansen
2018-03-23 17:44 ` [PATCH 02/11] x86/mm: undo double _PAGE_PSE clearing Dave Hansen
2018-03-23 17:44 ` [PATCH 03/11] x86/mm: introduce "default" kernel PTE mask Dave Hansen
2018-03-23 17:44 ` [PATCH 04/11] x86/espfix: document use of _PAGE_GLOBAL Dave Hansen
2018-03-23 17:44 ` [PATCH 05/11] x86/mm: do not auto-massage page protections Dave Hansen
2018-03-23 19:15   ` Nadav Amit
2018-03-23 19:26     ` Dave Hansen
2018-03-23 19:34       ` Nadav Amit
2018-03-23 19:38         ` Dave Hansen
2018-03-24 15:10   ` kbuild test robot
2018-03-24 15:21   ` kbuild test robot
2018-03-23 17:44 ` [PATCH 06/11] x86/mm: remove extra filtering in pageattr code Dave Hansen
2018-03-23 17:44 ` [PATCH 07/11] x86/mm: comment _PAGE_GLOBAL mystery Dave Hansen
2018-03-23 17:44 ` [PATCH 08/11] x86/mm: do not forbid _PAGE_RW before init for __ro_after_init Dave Hansen
2018-03-23 17:45 ` [PATCH 09/11] x86/pti: enable global pages for shared areas Dave Hansen
2018-03-23 19:12   ` Nadav Amit
2018-03-23 19:36     ` Dave Hansen
2018-03-23 17:45 ` [PATCH 10/11] x86/pti: clear _PAGE_GLOBAL for kernel image Dave Hansen
2018-03-23 17:45 ` [PATCH 11/11] x86/pti: leave kernel text global for !PCID Dave Hansen
2018-03-23 18:26 ` [PATCH 00/11] Use global pages with PTI Linus Torvalds
2018-03-24  0:40   ` Dave Hansen
2018-03-24  0:46     ` Linus Torvalds
2018-03-24  0:54       ` Linus Torvalds
2018-03-24 11:05     ` Ingo Molnar
2018-03-27 13:36     ` Thomas Gleixner
2018-03-27 16:32       ` Dave Hansen
2018-03-27 17:51         ` Thomas Gleixner
2018-03-27 20:07           ` Ingo Molnar
2018-03-27 20:19             ` Dave Hansen [this message]
2018-03-29  0:17             ` Dave Hansen
2018-03-30 12:09               ` Ingo Molnar
2018-03-30 12:17                 ` Ingo Molnar
2018-03-30 20:26                   ` Dave Hansen
2018-03-30 20:32                     ` Thomas Gleixner
2018-03-30 21:40                       ` Dave Hansen
2018-03-31  5:39                         ` Ingo Molnar
2018-03-31 18:19                           ` Dave Hansen

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=a3837d26-031f-6bce-cb1e-f34e5c0cfd2f@linux.intel.com \
    --to=dave.hansen@linux.intel.com \
    --cc=aarcange@redhat.com \
    --cc=hughd@google.com \
    --cc=jgross@suse.com \
    --cc=keescook@google.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=luto@kernel.org \
    --cc=mingo@kernel.org \
    --cc=namit@vmware.com \
    --cc=tglx@linutronix.de \
    --cc=torvalds@linux-foundation.org \
    --cc=x86@kernel.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 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).