Re: [PATCH v3] futex: Fix regression with read only mappings

[Darren Hart <dvhart@linux.intel.com>]

On 06/28/2011 03:54 AM, Peter Zijlstra wrote:
> On Mon, 2011-06-27 at 17:22 -0500, Shawn Bohrer wrote:
>> commit 7485d0d3758e8e6491a5c9468114e74dc050785d (futexes: Remove rw
>> parameter from get_futex_key()) in 2.6.33 introduced a user-mode
>> regression in that it additionally prevented futex operations on a
>> region within a read only memory mapped file.  For example this breaks
>> workloads that have one or more reader processes doing a FUTEX_WAIT on a
>> futex within a read only shared mapping, and a writer processes that has
>> a writable mapping issuing the FUTEX_WAKE.
>>
>> This fixes the regression for futex operations that should be valid on
>> RO mappings by trying a RO get_user_pages_fast() when the RW
>> get_user_pages_fast() fails so as not to slow down the common path of
>> writable anonymous maps and bailing when we used the RO path on
>> anonymous memory.
>>
>> While fixing the regression this patch opens up two possible bad
>> scenarios as identified by KOSAKI Motohiro:
>>
>> 1) This patch also allows FUTEX_WAIT on RO private mappings which have
>> the following corner case.
>>
>>   Thread-A: call futex(FUTEX_WAIT, memory-region-A).
>>             get_futex_key() return inode based key.
>>             sleep on the key
>>   Thread-B: call mprotect(PROT_READ|PROT_WRITE, memory-region-A)
>>   Thread-B: write memory-region-A.
>>             COW happen. This process's memory-region-A become related
>>             to new COWed private (ie PageAnon=1) page.
>>   Thread-B: call futex(FUETX_WAKE, memory-region-A).
>>             get_futex_key() return mm based key.
>>             IOW, we fail to wake up Thread-A.
>>
>> 2) Current futex code doesn't handle zero page properly.
>>
>>   Read mode get_user_pages() can return zero page, but current futex
>>   code doesn't handle it at all. Then, zero page makes infinite loop
>>   internally.
>>
>> This Patch is based on Peter Zijlstra's initial patch with modifications to
>> only allow RO mappings for futex operations that need VERIFY_READ access.
>>
>> Reported-by: David Oliver <david@rgmadvisors.com>
>> Signed-off-by: Shawn Bohrer <sbohrer@rgmadvisors.com>
> 
> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>

I think we need to address #2 above first.

1) Is the loop killable?
2) If not, and we try to catch zero_page scenario, we need to ensure RO
   sparse file mapping work. Peter notes that these are probably fine,
   filemap.c doesn't seem to use the zero page - but we need to test.

It's agreed, I believe, between myself, Peter, and Shawn that we will
document Private RW mappings as unsupported.

-- 
Darren Hart
Intel Open Source Technology Center
Yocto Project - Linux Kernel