Re: ppc elf_map breakage with MAP_FIXED_NOREPLACE

From: Anshuman Khandual <khandual@linux.vnet.ibm.com>
To: Michal Hocko <mhocko@kernel.org>,
	Anshuman Khandual <khandual@linux.vnet.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>,
	akpm@linux-foundation.org, mm-commits@vger.kernel.org,
	linux-kernel@vger.kernel.org, linux-mm@kvack.org,
	linux-fsdevel@vger.kernel.org, linux-next@vger.kernel.org,
	sfr@canb.auug.org.au, broonie@kernel.org
Subject: Re: ppc elf_map breakage with MAP_FIXED_NOREPLACE
Date: Thu, 11 Jan 2018 15:38:37 +0530	[thread overview]
Message-ID: <a495f210-0015-efb2-a6a7-868f30ac4ace@linux.vnet.ibm.com> (raw)
In-Reply-To: <20180109161355.GL1732@dhcp22.suse.cz>

On 01/09/2018 09:43 PM, Michal Hocko wrote:
> On Tue 09-01-18 17:18:38, Anshuman Khandual wrote:
>> On 01/09/2018 03:42 AM, Michael Ellerman wrote:
>>> Anshuman Khandual <khandual@linux.vnet.ibm.com> writes:
>>>
>>>> On 01/07/2018 04:56 PM, Michael Ellerman wrote:
>>>>> Michal Hocko <mhocko@kernel.org> writes:
>>>>>
>>>>>> On Sun 07-01-18 12:19:32, Anshuman Khandual wrote:
>>>>>>> On 01/05/2018 02:16 PM, Michal Hocko wrote:
>>>>>> [...]
>>>>>>>> Could you give us more information about the failure please. Debugging
>>>>>>>> patch from http://lkml.kernel.org/r/20171218091302.GL16951@dhcp22.suse.cz
>>>>>>>> should help to see what is the clashing VMA.
>>>>>>> Seems like its re-requesting the same mapping again.
>>>>>> It always seems to be the same mapping which is a bit strange as we
>>>>>> have multiple binaries here. Are these binaries any special? Does this
>>>>>> happen to all bianries (except for init which has obviously started
>>>>>> successfully)? Could you add an additional debugging (at the do_mmap
>>>>>> layer) to see who is requesting the mapping for the first time?
>>>>>>
>>>>>>> [   23.423642] 9148 (sed): Uhuuh, elf segment at 0000000010030000 requested but the memory is mapped already
>>>>>>> [   23.423706] requested [10030000, 10040000] mapped [10030000, 10040000] 100073 anon
>>>>>> I also find it a bit unexpected that this is an anonymous mapping
>>>>>> because the elf loader should always map a file backed one.
>>>>> Anshuman what machine is this on, and what distro and toolchain is it running?
>>>>>
>>>>> I don't see this on any of my machines, so I wonder if this is
>>>>> toolchain/distro specific.
>>>>
>>>> POWER9, RHEL 7.4, gcc (GCC) 4.8.5 20150623, GNU Make 3.82 etc.
>>>
>>> So what does readelf -a of /bin/sed look like?
>>
>> Please find here.
> 
> Did you manage to catch _who_ is requesting that anonymous mapping? Do
> you need a help with the debugging patch?

Not yet, will get back on this.