linux-kernel - Re: [PATCH 3/3] x86, vdso32: handle 32 bit vDSO larger one page

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [day] [month] [year] [list]

Date:	Thu, 13 Mar 2014 12:13:17 -0700
From:	Andy Lutomirski <luto@...capital.net>
To:	Linus Torvalds <torvalds@...ux-foundation.org>
Cc:	Pavel Emelyanov <xemul@...allels.com>,
	"the arch/x86 maintainers" <x86@...nel.org>,
	Ingo Molnar <mingo@...hat.com>,
	Cyrill Gorcunov <gorcunov@...nvz.org>,
	Stefani Seibold <stefani@...bold.net>,
	"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
	"H. Peter Anvin" <hpa@...or.com>,
	Greg KH <gregkh@...uxfoundation.org>,
	Andrea Arcangeli <aarcange@...hat.com>,
	Andreas Brief <Andreas.Brief@...de-schwarz.com>,
	Andi Kleen <ak@...ux.intel.com>,
	John Stultz <john.stultz@...aro.org>,
	Thomas Gleixner <tglx@...utronix.de>,
	Andy Shevchenko <andriy.shevchenko@...ux.intel.com>,
	Martin Runge <Martin.Runge@...de-schwarz.com>
Subject: Re: [PATCH 3/3] x86, vdso32: handle 32 bit vDSO larger one page

On Thu, Mar 13, 2014 at 12:06 PM, Linus Torvalds
<torvalds@...ux-foundation.org> wrote:
> On my phone, so the lists will reject this, and sorry for top posting.
>
> Maybe we could do something similar to the vsyscall=native thing, where the
> compat vdso just does the system calls, but at least uses syscall rather
> than int80 when appropriate? Make the suse situation not suck horribly...

How?  We either set null in AT_SYSINFO_EHDR, we set something simple
that SuSE is okay with (and compile separate images?) or we set
something fancy and not relocated, and SuSE crashes.

At least for the 64-bit vsyscall case, modern code is polite enough to
completely ignore the vsyscall page.  Unfortunately, modern 32-bit
glibc looks at the exact same AT_SYSINFO_EHDR.

If the syscall overhead is that bad, the dynamic relocation approach
might be better...

On a related note: is it okay to keep the option called
CONFIG_COMPAT_VDSO but change the default to n?  The assumption is
that everyone with OpenSUSE already has a working config, but new
defconfig users will get the better choice?

--Andy
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/