Re: [PATCH][GIT PULL][v2.6.32] tracing/x86: Add check to detect GCC messing with mcount prologue

From: Andrew Haley <aph@redhat.com>
To: "H.J. Lu" <hjl.tools@gmail.com>
Cc: rostedt@goodmis.org, Thomas Gleixner <tglx@linutronix.de>,
	Ingo Molnar <mingo@elte.hu>, "H. Peter Anvin" <hpa@zytor.com>,
	LKML <linux-kernel@vger.kernel.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	Heiko Carstens <heiko.carstens@de.ibm.com>,
	feng.tang@intel.com, Peter Zijlstra <peterz@infradead.org>,
	Frederic Weisbecker <fweisbec@gmail.com>,
	David Daney <ddaney@caviumnetworks.com>,
	Richard Guenther <richard.guenther@gmail.com>,
	jakub@redhat.com, gcc <gcc@gcc.gnu.org>,
	Linus Torvalds <torvalds@linux-foundation.org>
Subject: Re: [PATCH][GIT PULL][v2.6.32] tracing/x86: Add check to detect GCC messing with mcount prologue
Date: Tue, 24 Nov 2009 14:43:37 +0000	[thread overview]
Message-ID: <4B0BF119.4070704@redhat.com> (raw)
In-Reply-To: <6dc9ffc80911221530t38d83cf6je739743c8d756667@mail.gmail.com>

H.J. Lu wrote:
> On Sun, Nov 22, 2009 at 9:20 AM, Andrew Haley <aph@redhat.com> wrote:
>> H.J. Lu wrote:
>>> On Fri, Nov 20, 2009 at 11:35 AM, Andrew Haley <aph@redhat.com> wrote:
>>>> Steven Rostedt wrote:
>>>>> Ingo, Thomas and Linus,
>>>>>
>>>>> I know Thomas did a patch to force the -mtune=generic, but just in case
>>>>> gcc decides to do something crazy again, this patch will catch it.
>>>>>
>>>>> Should we try to get this in now?
>>>> I'm sure this makes sense, but a gcc test case would be even better.
>>>> If this can be detected in the gcc test suite it'll be found and
>>>> fixed long before y'all in kernel land get to see it.  That's the
>>>> only way to guarantee this never bothers you again.
>>>>
>>>> H.J., who wrote the code in question, is hopefully looking at why
>>>> this odd code is being generated.  Once he's done I can put a
>>>> suitable test case in the gcc test suite.
>>>>
>>> See:
>>>
>>> http://gcc.gnu.org/bugzilla/show_bug.cgi?id=42109#c7
>> I saw that, but does it mean you're going to investigate?  There is
>> no obvious reason why -mtune=generic should affect code generation
>> in this way, but it does.
> 
> Why not, there is
> 
> static const unsigned int x86_accumulate_outgoing_args
>   = m_AMD_MULTIPLE | m_ATOM | m_PENT4 | m_NOCONA | m_PPRO | m_CORE2
>     | m_GENERIC;
> 
> -mtune=generic turns on -maccumulate-outgoing-args.

Alright, so let's at least try to give the kernel people the information
that they need.

What you're saying is, to avoid this:

  000005f0 <timer_stats_update_stats>:
 5f0:   57                      push   %edi
 5f1:   8d 7c 24 08             lea    0x8(%esp),%edi
 5f5:   83 e4 f0                and    $0xfffffff0,%esp
 5f8:   ff 77 fc                pushl  -0x4(%edi)
 5fb:   55                      push   %ebp
 5fc:   89 e5                   mov    %esp,%ebp

you should compile your code with -maccumulate-outgoing-args, and there's
no need to use -mtune=generic.  Is that right?

Andrew.