Re: [PATCH v2 2/4] mm: check for proper migrate type during isolation

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On 05/22/2018 01:10 AM, Mike Kravetz wrote:
> On 05/18/2018 03:32 AM, Vlastimil Babka wrote:
>> On 05/04/2018 01:29 AM, Mike Kravetz wrote:
>>> The routine start_isolate_page_range and alloc_contig_range have
>>> comments saying that migratetype must be either MIGRATE_MOVABLE or
>>> MIGRATE_CMA.  However, this is not enforced.
>>
>> Enforced, no. But if the pageblocks really were as such, it used to
>> shortcut has_unmovable_pages(). This was wrong and removed in
>> d7b236e10ced ("mm: drop migrate type checks from has_unmovable_pages")
>> plus 4da2ce250f98 ("mm: distinguish CMA and MOVABLE isolation in
>> has_unmovable_pages()").
>>
>>
>>   What is important is
>>> that that all pageblocks in the range are of type migratetype.
>>                                                the same
>>> This is because blocks will be set to migratetype on error.
>>
>> Strictly speaking this is true only for the CMA case. For other cases,
>> the best thing actually would be to employ the same heuristics as page
>> allocation migratetype fallbacks, and count how many pages are free and
>> how many appear to be movable, see how steal_suitable_fallback() uses
>> the last parameter of move_freepages_block().
>>
>>> Add a boolean argument enforce_migratetype to the routine
>>> start_isolate_page_range.  If set, it will check that all pageblocks
>>> in the range have the passed migratetype.  Return -EINVAL is pageblock
>>                                                             if
>>> is wrong type is found in range.
>>   of
>>>
>>> A boolean is used for enforce_migratetype as there are two primary
>>> users.  Contiguous range allocation which wants to enforce migration
>>> type checking.  Memory offline (hotplug) which is not concerned about
>>> type checking.
>>
>> This is missing some high-level result. The end change is that CMA is
>> now enforcing. So we are making it more robust when it's called on
>> non-CMA pageblocks by mistake? (BTW I still do hope we can remove
>> MIGRATE_CMA soon after Joonsoo's ZONE_MOVABLE CMA conversion. Combined
>> with my suggestion above we could hopefully get rid of the migratetype
>> parameter completely instead of enforcing it?). Is this also a
>> preparation for introducing find_alloc_contig_pages() which will be
>> enforcing? (I guess, and will find out shortly, but it should be stated
>> here)
> 
> Thank you for looking at these patches Vlastimil.
> 
> My primary motivation for this patch was the 'error recovery' in
> start_isolate_page_range.  It takes a range and attempts to set
> all pageblocks to MIGRATE_ISOLATE.  If it encounters an error after
> setting some blocks to isolate, it will 'clean up' by setting the
> migrate type of previously modified blocks to the passed migratetype.

Right.

> So, one possible side effect of an error in start_isolate_page_range
> is that the migrate type of some pageblocks could be modified.  Thinking
> about it more now, that may be OK.

It would be definitely OK if the migratetype was changed similarly as
steal_suitable_fallback() does it, as I've said above.

> It just does not seem like the
> right thing to do, especially with comments saying "migratetype must
> be either MIGRATE_MOVABLE or MIGRATE_CMA".  I'm fine with leaving the
> code as is and just cleaning up the comments if you think that may
> be better.

That's also possible, especially when the code is restructured as I've
suggested in the other reply, which should significantly reduce the
amount of error recoveries.
--
To unsubscribe from this list: send the line "unsubscribe linux-api" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html



[Index of Archives]     [Linux USB Devel]     [Video for Linux]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]

  Powered by Linux