linux-kernel - Re: Is: axe read_tscp pvops call. Was: Re: [RFC] ACPI S3 and Xen (suprisingly small\!).

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

Message-ID: <20121017163945.GA28856@phenom.dumpdata.com>
Date:	Wed, 17 Oct 2012 12:39:45 -0400
From:	Konrad Rzeszutek Wilk <konrad.wilk@...cle.com>
To:	"H. Peter Anvin" <hpa@...or.com>
Cc:	linux-kernel@...r.kernel.org, xen-devel@...ts.xensource.com,
	lenb@...nel.org, linux-acpi@...r.kernel.org, x86@...nel.org
Subject: Re: Is: axe read_tscp pvops call. Was: Re: [RFC] ACPI S3 and Xen
 (suprisingly small\!).

On Wed, Oct 17, 2012 at 12:10:36PM -0400, Konrad Rzeszutek Wilk wrote:
> On Wed, Oct 17, 2012 at 09:03:12AM -0700, H. Peter Anvin wrote:
> > On 10/17/2012 06:49 AM, Konrad Rzeszutek Wilk wrote:
> > >
> > >Note: These are the other patches that went in 3.7-rc1:
> > >xen/bootup: allow {read|write}_cr8 pvops call [https://lkml.org/lkml/2012/10/10/339]
> > >xen/bootup: allow read_tscp call for Xen PV guests. [https://lkml.org/lkml/2012/10/10/340]
> > >
> > 
> > So WTF do we have a read_tscp PV call?  Again, if there isn't a user
> > we should just axe it...
> 
> Let me spin off a patch to see if that can be done.

It can be done faily easy. That said  the only user that could
_potentially_ use this (if the read_tscp had some extra logic to
do 'readtsc' operations) would be the __vdso_getcpu.

Meaning in __vdso_getcpu we would modify it from native_read_tscp
to paravirt_read_tscp:

notrace long
__vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *unused)
{
	unsigned int p;

	if (VVAR(vgetcpu_mode) == VGETCPU_RDTSCP) {
		/* Load per CPU data from RDTSCP */
===>		native_read_tscp(&p);
	} else {
		/* Load per CPU data from GDT */
		asm("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG));
	}
	if (cpu)
		*cpu = p & 0xfff;
	if (node)
		*node = p >> 12;
	return 0;
}

but that line was added for a purpose, which was
in git commit 8f12dea6135d0a55b151dcb4c6bbe211f5f8d35d
Author: Glauber de Oliveira Costa <gcosta@...hat.com>
Date:   Wed Jan 30 13:31:06 2008 +0100

    x86: introduce native_read_tscp
    
    Targetting paravirt, this patch introduces native_read_tscp, in
    place of rdtscp() macro. When in a paravirt guest, this will
    involve a function call, and thus, cannot be done in the vdso area.
    These users then have to call the native version directly
    
    Signed-off-by: Glauber de Oliveira Costa <gcosta@...hat.com>
    Signed-off-by: Ingo Molnar <mingo@...e.hu>
    Signed-off-by: Thomas Gleixner <tglx@...utronix.de>

which implies that it since it is a vDSO area it cannot do paravirt
calls anyhow.

In other words, I think I'm OK with axing it. Going to spin a patch
and ask for some other folks to review/double check.
--
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/