On 03/31/2017 12:40 AM, Andrew Morton wrote:
>> > BUG: kernel hang in boot stage
>>
>> Thanks, I was able to reproduce and debug this.
>> Andrew, please apply the following -fix. There will be conflicts on later
>> patches, but with trivial resolution (pages -> free_pages). Thanks!
>>
>> ...
>>
>> --- a/mm/page_alloc.c
>> +++ b/mm/page_alloc.c
>> @@ -1977,6 +1977,9 @@ static void steal_suitable_fallback(struct zone *zone,
>> struct page *page,
>> goto single_page;
>>
>> pages = move_freepages_block(zone, page, start_type);
>> + /* moving whole block can fail due to zone boundary conditions */
>> + if (!pages)
>> + goto single_page;
>>
>> /* Claim the whole block if over half of it is free */
>> if (pages >= (1 << (pageblock_order-1)) ||
>
> The result is a bit odd:
>
> free_pages = move_freepages_block(zone, page, start_type,
> &movable_pages);
> /*
> * Determine how many pages are compatible with our allocation.
> * For movable allocation, it's the number of movable pages which
> * we just obtained. For other types it's a bit more tricky.
> */
> if (start_type == MIGRATE_MOVABLE) {
> alike_pages = movable_pages;
> } else {
> /*
> * If we are falling back a RECLAIMABLE or UNMOVABLE allocation
> * to MOVABLE pageblock, consider all non-movable pages as
> * compatible. If it's UNMOVABLE falling back to RECLAIMABLE or
> * vice versa, be conservative since we can't distinguish the
> * exact migratetype of non-movable pages.
> */
> if (old_block_type == MIGRATE_MOVABLE)
> alike_pages = pageblock_nr_pages
> - (free_pages + movable_pages);
> else
> alike_pages = 0;
> }
>
> /* moving whole block can fail due to zone boundary conditions */
> if (!free_pages)
> goto single_page;
>
> should we do `goto single_page' as soon as the move_freepages_block()
> call fails?
Yeah, that would be more obvious. Thanks!
