Re: [RFC PATCH v2 0/7] Use pageblock_order for cma and alloc_contig_range alignment.

[Zi Yan <ziy@nvidia.com>]

[-- Attachment #1: Type: text/plain, Size: 4035 bytes --]

On 10 Dec 2021, at 2:30, Eric Ren wrote:

> Hi Zi Yan,
>
> On 2021/12/10 07:04, Zi Yan wrote:
>> From: Zi Yan <ziy@nvidia.com>
>>
>> Hi all,
>>
>> This patchset tries to remove the MAX_ORDER - 1 alignment requirement for CMA
>> and alloc_contig_range(). It prepares for my upcoming changes to make MAX_ORDER
>> adjustable at boot time[1].
>>
>> The MAX_ORDER - 1 alignment requirement comes from that alloc_contig_range()
>> isolates pageblocks to remove free memory from buddy allocator but isolating
>> only a subset of pageblocks within a page spanning across multiple pageblocks
>> causes free page accounting issues. Isolated page might not be put into the
>> right free list, since the code assumes the migratetype of the first pageblock
>> as the whole free page migratetype. This is based on the discussion at [2].
>>
>> To remove the requirement, this patchset:
>> 1. still isolates pageblocks at MAX_ORDER - 1 granularity;
> Then, unplug fails if either pageblock of the  MAX_ORDER - 1 page has unmovable page, right?

Right. One of the optimizations mentioned is targeting this by passing the actual
range instead of the MAX_ORDER-1 aligned range, so that has_unmovable_pages()
will not give false positive, minimizing the isolation failure rates.

>
> Thanks,
> Eric
>> 2. but saves the pageblock migratetypes outside the specified range of
>>     alloc_contig_range() and restores them after all pages within the range
>>     become free after __alloc_contig_migrate_range();
>> 3. splits free pages spanning multiple pageblocks at the beginning and the end
>>     of the range and puts the split pages to the right migratetype free lists
>>     based on the pageblock migratetypes;
>> 4. returns pages not in the range as it did before this patch.
>>
>> Isolation needs to happen at MAX_ORDER - 1 granularity, because otherwise
>> 1) extra code is needed to detect pages (free, PageHuge, THP, or PageCompound)
>> to make sure all pageblocks belonging to a single page are isolated together
>> and later pageblocks outside the range need to have their migratetypes restored;
>> or 2) extra logic will need to be added during page free time to split a free
>> page with multi-migratetype pageblocks.
>>
>> Two optimizations might come later:
>> 1. only check unmovable pages within the range instead of MAX_ORDER - 1 aligned
>>     range during isolation to increase successful rate of alloc_contig_range().
^^^^^^^^^^^^^^

>> 2. make MIGRATE_ISOLATE a separate bit to avoid saving and restoring existing
>>     migratetypes before and after isolation respectively.
>>
>> Feel free to give comments and suggestions. Thanks.
>>
>>
>> [1] https://lore.kernel.org/linux-mm/20210805190253.2795604-1-zi.yan@sent.com/
>> [2] https://lore.kernel.org/linux-mm/d19fb078-cb9b-f60f-e310-fdeea1b947d2@redhat.com/
>>
>>
>> Zi Yan (7):
>>    mm: page_alloc: avoid merging non-fallbackable pageblocks with others.
>>    mm: compaction: handle non-lru compound pages properly in
>>      isolate_migratepages_block().
>>    mm: migrate: allocate the right size of non hugetlb or THP compound
>>      pages.
>>    mm: make alloc_contig_range work at pageblock granularity
>>    mm: cma: use pageblock_order as the single alignment
>>    drivers: virtio_mem: use pageblock size as the minimum virtio_mem
>>      size.
>>    arch: powerpc: adjust fadump alignment to be pageblock aligned.
>>
>>   arch/powerpc/include/asm/fadump-internal.h |   4 +-
>>   drivers/virtio/virtio_mem.c                |   6 +-
>>   include/linux/mmzone.h                     |  11 +-
>>   kernel/dma/contiguous.c                    |   2 +-
>>   mm/cma.c                                   |   6 +-
>>   mm/compaction.c                            |  10 +-
>>   mm/migrate.c                               |   8 +-
>>   mm/page_alloc.c                            | 203 +++++++++++++++++----
>>   8 files changed, 196 insertions(+), 54 deletions(-)
>>


--
Best Regards,
Yan, Zi

[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 854 bytes --]