All of lore.kernel.org
 help / color / mirror / Atom feed
From: Song Liu <songliubraving@fb.com>
To: Thomas Gleixner <tglx@linutronix.de>
Cc: Dave Hansen <dave.hansen@intel.com>,
	LKML <linux-kernel@vger.kernel.org>,
	"x86@kernel.org" <x86@kernel.org>, Joerg Roedel <jroedel@suse.de>,
	"Andy Lutomirski" <luto@kernel.org>,
	Peter Zijlstra <peterz@infradead.org>,
	"Rik van Riel" <riel@surriel.com>
Subject: Re: [patch 1/2] x86/mm/pti: Handle unaligned address gracefully in pti_clone_pagetable()
Date: Wed, 28 Aug 2019 17:58:20 +0000	[thread overview]
Message-ID: <309E5006-E869-4761-ADE2-ADB7A1A63FF1@fb.com> (raw)
In-Reply-To: <alpine.DEB.2.21.1908281750410.1938@nanos.tec.linutronix.de>



> On Aug 28, 2019, at 8:51 AM, Thomas Gleixner <tglx@linutronix.de> wrote:
> 
> On Wed, 28 Aug 2019, Dave Hansen wrote:
>> On 8/28/19 7:24 AM, Thomas Gleixner wrote:
>>> From: Song Liu <songliubraving@fb.com>
>>> 
>>> pti_clone_pmds() assumes that the supplied address is either:
>>> 
>>> - properly PUD/PMD aligned
>>> or
>>> - the address is actually mapped which means that independent
>>>   of the mapping level (PUD/PMD/PTE) the next higher mapping
>>>   exist.
>>> 
>>> If that's not the case the unaligned address can be incremented by PUD or
>>> PMD size wrongly. All callers supply mapped and/or aligned addresses, but
>>> for robustness sake, it's better to handle that case proper and to emit a
>>> warning.
>> 
>> Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
>> 
>> Song, did you ever root-cause the performance regression?  I thought
>> there were still some mysteries there.
> 
> See Peter's series to rework the ftrace code patching ...

Thanks Thomas. 

Yes, in summary, enabling ftrace or kprobe-on-ftrace causes the kernel
to split PMDs in kernel text mapping. 

Related question: while Peter's patches fix it for 5.3 kernel, they don't 
apply cleanly over 5.2 kernel (which we are using). So I wonder what is
the best solution for 5.2 kernel. May patch also fixes the issue:

https://lore.kernel.org/lkml/20190823052335.572133-1-songliubraving@fb.com/

How about we apply this patch to upstream 5.2 kernel?

Thanks,
Song

  reply	other threads:[~2019-08-28 17:59 UTC|newest]

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-08-28 14:24 [patch 0/2] x86/mm/pti: Robustness updates Thomas Gleixner
2019-08-28 14:24 ` [patch 1/2] x86/mm/pti: Handle unaligned address gracefully in pti_clone_pagetable() Thomas Gleixner
2019-08-28 15:46   ` Dave Hansen
2019-08-28 15:51     ` Thomas Gleixner
2019-08-28 17:58       ` Song Liu [this message]
2019-08-28 20:05         ` Thomas Gleixner
2019-08-28 20:32           ` Song Liu
2019-08-28 22:31             ` [PATCH] x86/mm/cpa: Prevent large page split when ftrace flips RW on kernel text Thomas Gleixner
2019-08-28 23:03               ` Song Liu
2019-08-29 13:01               ` Peter Zijlstra
2019-08-29 18:55               ` [tip: x86/urgent] " tip-bot2 for Thomas Gleixner
2019-08-28 18:58   ` [patch 1/2] x86/mm/pti: Handle unaligned address gracefully in pti_clone_pagetable() Ingo Molnar
2019-08-28 19:45     ` Thomas Gleixner
2019-08-28 20:54   ` [patch V2 " Thomas Gleixner
2019-08-28 21:52     ` Thomas Gleixner
2019-08-28 21:54     ` [patch V3 " Thomas Gleixner
2019-08-28 23:22       ` Ingo Molnar
2019-08-29 19:02       ` [tip: x86/pti] " tip-bot2 for Song Liu
2019-08-30 10:24       ` [patch V3 1/2] " Joerg Roedel
2019-08-28 14:24 ` [patch 2/2] x86/mm/pti: Do not invoke PTI functions when PTI is disabled Thomas Gleixner
2019-08-28 15:47   ` Dave Hansen
2019-08-28 17:49   ` Song Liu
2019-08-28 19:00   ` Ingo Molnar
2019-08-29 19:02   ` [tip: x86/pti] " tip-bot2 for Thomas Gleixner
2019-08-30 10:25   ` [patch 2/2] " Joerg Roedel
2019-08-28 16:03 ` [patch 0/2] x86/mm/pti: Robustness updates Peter Zijlstra

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=309E5006-E869-4761-ADE2-ADB7A1A63FF1@fb.com \
    --to=songliubraving@fb.com \
    --cc=dave.hansen@intel.com \
    --cc=jroedel@suse.de \
    --cc=linux-kernel@vger.kernel.org \
    --cc=luto@kernel.org \
    --cc=peterz@infradead.org \
    --cc=riel@surriel.com \
    --cc=tglx@linutronix.de \
    --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 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.