All of lore.kernel.org
 help / color / mirror / Atom feed
From: Dave Hansen <dave.hansen@intel.com>
To: Juerg Haefliger <juerg.haefliger@hpe.com>,
	linux-kernel@vger.kernel.org, linux-mm@kvack.org,
	kernel-hardening@lists.openwall.com,
	linux-x86_64@vger.kernel.org
Cc: vpk@cs.columbia.edu
Subject: Re: [RFC PATCH v2 2/3] xpfo: Only put previous userspace pages into the hot cache
Date: Fri, 2 Sep 2016 13:39:22 -0700	[thread overview]
Message-ID: <57C9E37A.9070805@intel.com> (raw)
In-Reply-To: <20160902113909.32631-3-juerg.haefliger@hpe.com>

On 09/02/2016 04:39 AM, Juerg Haefliger wrote:
> Allocating a page to userspace that was previously allocated to the
> kernel requires an expensive TLB shootdown. To minimize this, we only
> put non-kernel pages into the hot cache to favor their allocation.

But kernel allocations do allocate from these pools, right?  Does this
just mean that kernel allocations usually have to pay the penalty to
convert a page?

So, what's the logic here?  You're assuming that order-0 kernel
allocations are more rare than allocations for userspace?

WARNING: multiple messages have this Message-ID (diff)
From: Dave Hansen <dave.hansen@intel.com>
To: Juerg Haefliger <juerg.haefliger@hpe.com>,
	linux-kernel@vger.kernel.org, linux-mm@kvack.org,
	kernel-hardening@lists.openwall.com,
	linux-x86_64@vger.kernel.org
Cc: vpk@cs.columbia.edu
Subject: Re: [RFC PATCH v2 2/3] xpfo: Only put previous userspace pages into the hot cache
Date: Fri, 2 Sep 2016 13:39:22 -0700	[thread overview]
Message-ID: <57C9E37A.9070805@intel.com> (raw)
In-Reply-To: <20160902113909.32631-3-juerg.haefliger@hpe.com>

On 09/02/2016 04:39 AM, Juerg Haefliger wrote:
> Allocating a page to userspace that was previously allocated to the
> kernel requires an expensive TLB shootdown. To minimize this, we only
> put non-kernel pages into the hot cache to favor their allocation.

But kernel allocations do allocate from these pools, right?  Does this
just mean that kernel allocations usually have to pay the penalty to
convert a page?

So, what's the logic here?  You're assuming that order-0 kernel
allocations are more rare than allocations for userspace?

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

WARNING: multiple messages have this Message-ID (diff)
From: Dave Hansen <dave.hansen@intel.com>
To: Juerg Haefliger <juerg.haefliger@hpe.com>,
	linux-kernel@vger.kernel.org, linux-mm@kvack.org,
	kernel-hardening@lists.openwall.com,
	linux-x86_64@vger.kernel.org
Cc: vpk@cs.columbia.edu
Subject: [kernel-hardening] Re: [RFC PATCH v2 2/3] xpfo: Only put previous userspace pages into the hot cache
Date: Fri, 2 Sep 2016 13:39:22 -0700	[thread overview]
Message-ID: <57C9E37A.9070805@intel.com> (raw)
In-Reply-To: <20160902113909.32631-3-juerg.haefliger@hpe.com>

On 09/02/2016 04:39 AM, Juerg Haefliger wrote:
> Allocating a page to userspace that was previously allocated to the
> kernel requires an expensive TLB shootdown. To minimize this, we only
> put non-kernel pages into the hot cache to favor their allocation.

But kernel allocations do allocate from these pools, right?  Does this
just mean that kernel allocations usually have to pay the penalty to
convert a page?

So, what's the logic here?  You're assuming that order-0 kernel
allocations are more rare than allocations for userspace?

  reply	other threads:[~2016-09-02 20:39 UTC|newest]

Thread overview: 93+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-02-26 14:21 [RFC PATCH] Add support for eXclusive Page Frame Ownership (XPFO) Juerg Haefliger
2016-02-26 14:21 ` Juerg Haefliger
2016-03-01  1:31 ` Laura Abbott
2016-03-01  1:31   ` Laura Abbott
2016-03-21  8:37   ` Juerg Haefliger
2016-03-21  8:37     ` Juerg Haefliger
2016-03-28 19:29     ` Laura Abbott
2016-03-28 19:29       ` Laura Abbott
2016-03-01  2:10 ` Balbir Singh
2016-03-01  2:10   ` Balbir Singh
2016-03-21  8:44   ` Juerg Haefliger
2016-03-21  8:44     ` Juerg Haefliger
2016-04-01  0:21     ` Balbir Singh
2016-04-01  0:21       ` Balbir Singh
2016-09-02 11:39 ` [RFC PATCH v2 0/3] " Juerg Haefliger
2016-09-02 11:39   ` [kernel-hardening] " Juerg Haefliger
2016-09-02 11:39   ` Juerg Haefliger
2016-09-02 11:39   ` [RFC PATCH v2 1/3] " Juerg Haefliger
2016-09-02 11:39     ` [kernel-hardening] " Juerg Haefliger
2016-09-02 11:39     ` Juerg Haefliger
2016-09-02 11:39   ` [RFC PATCH v2 2/3] xpfo: Only put previous userspace pages into the hot cache Juerg Haefliger
2016-09-02 11:39     ` [kernel-hardening] " Juerg Haefliger
2016-09-02 11:39     ` Juerg Haefliger
2016-09-02 20:39     ` Dave Hansen [this message]
2016-09-02 20:39       ` [kernel-hardening] " Dave Hansen
2016-09-02 20:39       ` Dave Hansen
2016-09-05 11:54       ` Juerg Haefliger
2016-09-05 11:54         ` [kernel-hardening] " Juerg Haefliger
2016-09-02 11:39   ` [RFC PATCH v2 3/3] block: Always use a bounce buffer when XPFO is enabled Juerg Haefliger
2016-09-02 11:39     ` [kernel-hardening] " Juerg Haefliger
2016-09-02 11:39     ` Juerg Haefliger
2016-09-14  7:18   ` [RFC PATCH v2 0/3] Add support for eXclusive Page Frame Ownership (XPFO) Juerg Haefliger
2016-09-14  7:18     ` [kernel-hardening] " Juerg Haefliger
2016-09-14  7:18     ` Juerg Haefliger
2016-09-14  7:18     ` [RFC PATCH v2 1/3] " Juerg Haefliger
2016-09-14  7:18       ` [kernel-hardening] " Juerg Haefliger
2016-09-14  7:18       ` Juerg Haefliger
2016-09-14  7:19     ` [RFC PATCH v2 2/3] xpfo: Only put previous userspace pages into the hot cache Juerg Haefliger
2016-09-14  7:19       ` [kernel-hardening] " Juerg Haefliger
2016-09-14  7:19       ` Juerg Haefliger
2016-09-14 14:33       ` [kernel-hardening] " Dave Hansen
2016-09-14 14:33         ` Dave Hansen
2016-09-14 14:40         ` Juerg Haefliger
2016-09-14 14:48           ` Dave Hansen
2016-09-14 14:48             ` Dave Hansen
2016-09-21  5:32             ` Juerg Haefliger
2016-09-14  7:19     ` [RFC PATCH v2 3/3] block: Always use a bounce buffer when XPFO is enabled Juerg Haefliger
2016-09-14  7:19       ` [kernel-hardening] " Juerg Haefliger
2016-09-14  7:19       ` Juerg Haefliger
2016-09-14  7:33       ` Christoph Hellwig
2016-09-14  7:33         ` [kernel-hardening] " Christoph Hellwig
2016-09-14  7:33         ` Christoph Hellwig
2016-09-14  7:23     ` [RFC PATCH v2 0/3] Add support for eXclusive Page Frame Ownership (XPFO) Juerg Haefliger
2016-09-14  7:23       ` [kernel-hardening] " Juerg Haefliger
2016-09-14  9:36     ` [kernel-hardening] " Mark Rutland
2016-09-14  9:36       ` Mark Rutland
2016-09-14  9:49       ` Mark Rutland
2016-09-14  9:49         ` Mark Rutland
2016-11-04 14:45     ` [RFC PATCH v3 0/2] " Juerg Haefliger
2016-11-04 14:45       ` [kernel-hardening] " Juerg Haefliger
2016-11-04 14:45       ` Juerg Haefliger
2016-11-04 14:45       ` [RFC PATCH v3 1/2] " Juerg Haefliger
2016-11-04 14:45         ` [kernel-hardening] " Juerg Haefliger
2016-11-04 14:45         ` Juerg Haefliger
2016-11-04 14:50         ` Christoph Hellwig
2016-11-04 14:50           ` [kernel-hardening] " Christoph Hellwig
2016-11-04 14:50           ` Christoph Hellwig
2016-11-10  5:53         ` [kernel-hardening] " ZhaoJunmin Zhao(Junmin)
2016-11-10  5:53           ` ZhaoJunmin Zhao(Junmin)
2016-11-10  5:53           ` ZhaoJunmin Zhao(Junmin)
2016-11-10 19:11         ` Kees Cook
2016-11-10 19:11           ` [kernel-hardening] " Kees Cook
2016-11-10 19:11           ` Kees Cook
2016-11-15 11:15           ` Juerg Haefliger
2016-11-15 11:15             ` [kernel-hardening] " Juerg Haefliger
2016-11-15 11:15             ` Juerg Haefliger
2016-11-10 19:24         ` Kees Cook
2016-11-10 19:24           ` [kernel-hardening] " Kees Cook
2016-11-10 19:24           ` Kees Cook
2016-11-15 11:18           ` Juerg Haefliger
2016-11-15 11:18             ` [kernel-hardening] " Juerg Haefliger
2016-11-15 11:18             ` Juerg Haefliger
2016-11-24 10:56         ` AKASHI Takahiro
2016-11-24 10:56           ` [kernel-hardening] " AKASHI Takahiro
2016-11-24 10:56           ` AKASHI Takahiro
2016-11-28 11:15           ` Juerg Haefliger
2016-11-28 11:15             ` [kernel-hardening] " Juerg Haefliger
2016-12-09  9:02           ` AKASHI Takahiro
2016-12-09  9:02             ` [kernel-hardening] " AKASHI Takahiro
2016-12-09  9:02             ` AKASHI Takahiro
2016-11-04 14:45       ` [RFC PATCH v3 2/2] xpfo: Only put previous userspace pages into the hot cache Juerg Haefliger
2016-11-04 14:45         ` [kernel-hardening] " Juerg Haefliger
2016-11-04 14:45         ` Juerg Haefliger

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=57C9E37A.9070805@intel.com \
    --to=dave.hansen@intel.com \
    --cc=juerg.haefliger@hpe.com \
    --cc=kernel-hardening@lists.openwall.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-x86_64@vger.kernel.org \
    --cc=vpk@cs.columbia.edu \
    /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.