Received-SPF: pass (google.com: domain of linux-kernel+bounces-39542-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.48.161 as permitted sender) client-ip=147.75.48.161;
Message-ID: <aefe1d8c-c3fa-43cf-a4df-6ee4bf69b501@linux.alibaba.com>
Date: Fri, 26 Jan 2024 10:29:28 +0800
Precedence: bulk
MIME-Version: 1.0
User-Agent: Mozilla Thunderbird
Subject: Re: [PATCH v2 1/3] mm/compaction: enable compacting >0 order folios.
To: Zi Yan <ziy@nvidia.com>, linux-mm@kvack.org, linux-kernel@vger.kernel.org
Cc: "Huang, Ying" <ying.huang@intel.com>, Ryan Roberts
 <ryan.roberts@arm.com>, Andrew Morton <akpm@linux-foundation.org>,
 "Matthew Wilcox (Oracle)" <willy@infradead.org>,
 David Hildenbrand <david@redhat.com>, "Yin, Fengwei"
 <fengwei.yin@intel.com>, Yu Zhao <yuzhao@google.com>,
 Vlastimil Babka <vbabka@suse.cz>,
 "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>,
 Johannes Weiner <hannes@cmpxchg.org>, Kemeng Shi
 <shikemeng@huaweicloud.com>, Mel Gorman <mgorman@techsingularity.net>,
 Rohan Puri <rohan.puri15@gmail.com>, Mcgrof Chamberlain <mcgrof@kernel.org>,
 Adam Manzanares <a.manzanares@samsung.com>,
 "Vishal Moola (Oracle)" <vishal.moola@gmail.com>
References: <20240123034636.1095672-1-zi.yan@sent.com>
 <20240123034636.1095672-2-zi.yan@sent.com>
From: Baolin Wang <baolin.wang@linux.alibaba.com>
In-Reply-To: <20240123034636.1095672-2-zi.yan@sent.com>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit


On 1/23/2024 11:46 AM, Zi Yan wrote:
> From: Zi Yan <ziy@nvidia.com>
> 
> migrate_pages() supports >0 order folio migration and during compaction,
> even if compaction_alloc() cannot provide >0 order free pages,
> migrate_pages() can split the source page and try to migrate the base pages
> from the split. It can be a baseline and start point for adding support for
> compacting >0 order folios.
> 
> Suggested-by: Huang Ying <ying.huang@intel.com>
> Signed-off-by: Zi Yan <ziy@nvidia.com>

LGTM.
Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>

> ---
>   mm/compaction.c | 43 +++++++++++++++++++++++++++++++++++--------
>   1 file changed, 35 insertions(+), 8 deletions(-)
> 
> diff --git a/mm/compaction.c b/mm/compaction.c
> index 27ada42924d5..61389540e1f1 100644
> --- a/mm/compaction.c
> +++ b/mm/compaction.c
> @@ -816,6 +816,21 @@ static bool too_many_isolated(struct compact_control *cc)
>   	return too_many;
>   }
>   
> +/*
> + * 1. if the page order is larger than or equal to target_order (i.e.,
> + * cc->order and when it is not -1 for global compaction), skip it since
> + * target_order already indicates no free page with larger than target_order
> + * exists and later migrating it will most likely fail;
> + *
> + * 2. compacting > pageblock_order pages does not improve memory fragmentation,
> + * skip them;
> + */
> +static bool skip_isolation_on_order(int order, int target_order)
> +{
> +	return (target_order != -1 && order >= target_order) ||
> +		order >= pageblock_order;
> +}
> +
>   /**
>    * isolate_migratepages_block() - isolate all migrate-able pages within
>    *				  a single pageblock
> @@ -1009,7 +1024,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
>   		/*
>   		 * Regardless of being on LRU, compound pages such as THP and
>   		 * hugetlbfs are not to be compacted unless we are attempting
> -		 * an allocation much larger than the huge page size (eg CMA).
> +		 * an allocation larger than the compound page size.
>   		 * We can potentially save a lot of iterations if we skip them
>   		 * at once. The check is racy, but we can consider only valid
>   		 * values and the only danger is skipping too much.
> @@ -1017,11 +1032,18 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
>   		if (PageCompound(page) && !cc->alloc_contig) {
>   			const unsigned int order = compound_order(page);
>   
> -			if (likely(order <= MAX_PAGE_ORDER)) {
> -				low_pfn += (1UL << order) - 1;
> -				nr_scanned += (1UL << order) - 1;
> +			/*
> +			 * Skip based on page order and compaction target order
> +			 * and skip hugetlbfs pages.
> +			 */
> +			if (skip_isolation_on_order(order, cc->order) ||
> +			    PageHuge(page)) {
> +				if (order <= MAX_PAGE_ORDER) {
> +					low_pfn += (1UL << order) - 1;
> +					nr_scanned += (1UL << order) - 1;
> +				}
> +				goto isolate_fail;
>   			}
> -			goto isolate_fail;
>   		}
>   
>   		/*
> @@ -1146,10 +1168,11 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
>   			}
>   
>   			/*
> -			 * folio become large since the non-locked check,
> -			 * and it's on LRU.
> +			 * Check LRU folio order under the lock
>   			 */
> -			if (unlikely(folio_test_large(folio) && !cc->alloc_contig)) {
> +			if (unlikely(skip_isolation_on_order(folio_order(folio),
> +							     cc->order) &&
> +				     !cc->alloc_contig)) {
>   				low_pfn += folio_nr_pages(folio) - 1;
>   				nr_scanned += folio_nr_pages(folio) - 1;
>   				folio_set_lru(folio);
> @@ -1767,6 +1790,10 @@ static struct folio *compaction_alloc(struct folio *src, unsigned long data)
>   	struct compact_control *cc = (struct compact_control *)data;
>   	struct folio *dst;
>   
> +	/* this makes migrate_pages() split the source page and retry */
> +	if (folio_test_large(src) > 0)
> +		return NULL;
> +
>   	if (list_empty(&cc->freepages)) {
>   		isolate_freepages(cc);
>