public inbox for libc-alpha@sourceware.org
 help / color / mirror / Atom feed
From: Florian Weimer <fweimer@redhat.com>
To: Rich Felker <dalias@libc.org>, Carlos O'Donell <carlos@redhat.com>
Cc: Szabolcs Nagy <szabolcs.nagy@arm.com>,
	GNU C Library <libc-alpha@sourceware.org>,
	nd@arm.com, Jeff Law <law@redhat.com>,
	Richard Earnshaw <Richard.Earnshaw@arm.com>,
	Wilco Dijkstra <Wilco.Dijkstra@arm.com>,
	James Greenhalgh <James.Greenhalgh@arm.com>
Subject: Re: [RFC] nptl: change default stack guard size of threads
Date: Wed, 29 Nov 2017 20:33:00 -0000	[thread overview]
Message-ID: <e68674a4-9c02-b91e-356e-55e23273ebf7@redhat.com> (raw)
In-Reply-To: <20171129182909.GE1627@brightrain.aerifal.cx>

On 11/29/2017 07:29 PM, Rich Felker wrote:
> On Wed, Nov 29, 2017 at 10:16:54AM -0800, Carlos O'Donell wrote:
>> On 11/29/2017 07:18 AM, Florian Weimer wrote:
>>> On 11/29/2017 03:59 PM, Szabolcs Nagy wrote:
>>>> The change can be made for aarch64 only
>>>
>>> That doesn't seem to be the case, looking at the patch.
>>>
>>> So what you intended to do, exactly?
>>>
>>> A 64 KiB probe interval on legacy 32-bit architectures is really a
>>> no-go.  It means we have to increase the guard region size to 64 KiB.
>>> But we cannot do that: The guard allocation comes out of the overall
>>> thread stack size, and existing applications do not expect that 60K
>>> of configured stack suddenly becomes unavailable.  Adding the guard
>>> size on top of the allocation will break setups which are carefully
>>> tuned for a maximum number of threads.
>>
>> We cannot be held to account for carefully tuned applications, such
>> applications have to be tuned again for newer glibc.
>>
>> I think we *could* do this for 64-bit and 32-bit AArch64/ARM, but I
>> don't see the value in doing it for 32-bit.
> 
> If 64k guard is mandatory for safety against jumping over the guard
> zone, then I don't think it's possible to "re-tune" 32-bit apps for
> the new requirement. This imposes a relatively small limit on possible
> number of threads the process can create.

With the probing implementations I have seen so far, it is feasible 
technically because a probe will never touch a stack area which could 
not conceivably be touched by a signal handler, too.

But it is still a bad situation when GCC documents that it is only 
providing full protection with guard size X, and you decide to run with 
size X/16 to actually get things going.  This means that your 
configuration is out of scope what your vendor will support 
security-wise, and probably non-compliant with applicable guidelines at 
the user site.

So technically you can run with a smaller guard size, but it's still 
impractical to do so for most organizations.

Thanks,
Florian

  reply	other threads:[~2017-11-29 20:33 UTC|newest]

Thread overview: 42+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-11-29 14:59 Szabolcs Nagy
2017-11-29 15:18 ` Florian Weimer
2017-11-29 18:17   ` Carlos O'Donell
2017-11-29 18:29     ` Rich Felker
2017-11-29 20:33       ` Florian Weimer [this message]
2017-11-29 18:40   ` Szabolcs Nagy
2017-11-29 20:44     ` Florian Weimer
2017-11-29 20:52       ` Rich Felker
2017-11-29 21:02         ` Florian Weimer
2017-11-29 23:13           ` Szabolcs Nagy
2017-12-05 10:55           ` James Greenhalgh
2017-12-06 12:51             ` Florian Weimer
2017-12-11 23:49             ` Jeff Law
2017-12-12 11:43               ` Szabolcs Nagy
2017-12-12 16:36                 ` Rich Felker
2017-12-12 18:07                   ` Szabolcs Nagy
2017-12-12 19:30               ` Florian Weimer
2017-12-13 11:58                 ` Szabolcs Nagy
2017-12-19 12:35             ` James Greenhalgh
2017-12-19 13:06               ` Florian Weimer
2017-12-19 18:21                 ` Szabolcs Nagy
2017-12-19 20:34                   ` Rich Felker
2017-12-20  4:42                     ` Jeff Law
2017-12-20  4:49                       ` Rich Felker
2017-12-27 13:08                         ` Wilco Dijkstra
2017-12-20  4:45                 ` Jeff Law
2017-11-29 22:28       ` Wilco Dijkstra
2017-11-29 22:38         ` Carlos O'Donell
2017-12-06 12:53           ` Florian Weimer
2017-12-06 13:10             ` Wilco Dijkstra
2017-12-06 13:13               ` Florian Weimer
2017-11-29 23:02         ` Rich Felker
2017-12-06 13:16         ` Florian Weimer
2017-12-06 13:40           ` Joseph Myers
2017-12-06 13:51             ` Florian Weimer
2017-12-06 14:44             ` Jeff Law
2017-12-06 14:27           ` Wilco Dijkstra
2017-12-06 20:41             ` Szabolcs Nagy
2017-12-06 21:24               ` Adhemerval Zanella
2017-12-06 22:08               ` Rich Felker
2017-12-08 18:28                 ` Szabolcs Nagy
2017-11-29 22:45       ` Szabolcs Nagy

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=e68674a4-9c02-b91e-356e-55e23273ebf7@redhat.com \
    --to=fweimer@redhat.com \
    --cc=James.Greenhalgh@arm.com \
    --cc=Richard.Earnshaw@arm.com \
    --cc=Wilco.Dijkstra@arm.com \
    --cc=carlos@redhat.com \
    --cc=dalias@libc.org \
    --cc=law@redhat.com \
    --cc=libc-alpha@sourceware.org \
    --cc=nd@arm.com \
    --cc=szabolcs.nagy@arm.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 read-only IMAP folder(s) and NNTP newsgroup(s).