Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   "Huang, Ying" <ying.huang@intel.com>
To:     Baolin Wang <baolin.wang@linux.alibaba.com>
Cc:     <linux-mm@kvack.org>, <linux-kernel@vger.kernel.org>,
        Andrew Morton <akpm@linux-foundation.org>,
        Zi Yan <ziy@nvidia.com>, Yang Shi <shy828301@gmail.com>,
        Oscar Salvador <osalvador@suse.de>,
        Matthew Wilcox <willy@infradead.org>
Subject: Re: [RFC 1/6] mm/migrate_pages: separate huge page and normal pages
 migration
References: <20220921060616.73086-1-ying.huang@intel.com>
        <20220921060616.73086-2-ying.huang@intel.com>
        <0a41c051-7d7e-cb1b-8273-192252e74b94@linux.alibaba.com>
Date:   Thu, 22 Sep 2022 14:22:49 +0800
In-Reply-To: <0a41c051-7d7e-cb1b-8273-192252e74b94@linux.alibaba.com> (Baolin
        Wang's message of "Thu, 22 Sep 2022 14:03:55 +0800")
Message-ID: <87pmfoj5c6.fsf@yhuang6-desk2.ccr.corp.intel.com>
User-Agent: Gnus/5.13 (Gnus v5.13) Emacs/27.1 (gnu/linux)
MIME-Version: 1.0
Content-Type: text/plain; charset=ascii
Precedence: bulk

Baolin Wang <baolin.wang@linux.alibaba.com> writes:

> On 9/21/2022 2:06 PM, Huang Ying wrote:
>> This is a preparation patch to batch the page unmapping and moving for
>> the normal pages and THPs.  Based on that we can batch the TLB
>> shootdown during the page migration and make it possible to use some
>> hardware accelerator for the page copying.
>> In this patch the huge page (PageHuge()) and normal page and THP
>> migration is separated in migrate_pages() to make it easy to change
>> the normal page and THP migration implementation.
>> Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
>> Cc: Zi Yan <ziy@nvidia.com>
>> Cc: Yang Shi <shy828301@gmail.com>
>> Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
>> Cc: Oscar Salvador <osalvador@suse.de>
>> Cc: Matthew Wilcox <willy@infradead.org>
>> ---
>>   mm/migrate.c | 73 +++++++++++++++++++++++++++++++++++++++++++++-------
>>   1 file changed, 64 insertions(+), 9 deletions(-)
>> diff --git a/mm/migrate.c b/mm/migrate.c
>> index 571d8c9fd5bc..117134f1c6dc 100644
>> --- a/mm/migrate.c
>> +++ b/mm/migrate.c
>> @@ -1414,6 +1414,66 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
>>     	trace_mm_migrate_pages_start(mode, reason);
>>   +	for (pass = 0; pass < 10 && retry; pass++) {
>> +		retry = 0;
>> +
>> +		list_for_each_entry_safe(page, page2, from, lru) {
>> +			nr_subpages = compound_nr(page);
>> +			cond_resched();
>> +
>> +			if (!PageHuge(page))
>> +				continue;
>> +
>> +			rc = unmap_and_move_huge_page(get_new_page,
>> +						put_new_page, private, page,
>> +						pass > 2, mode, reason,
>> +						&ret_pages);
>> +			/*
>> +			 * The rules are:
>> +			 *	Success: hugetlb page will be put back
>> +			 *	-EAGAIN: stay on the from list
>> +			 *	-ENOMEM: stay on the from list
>> +			 *	-ENOSYS: stay on the from list
>> +			 *	Other errno: put on ret_pages list then splice to
>> +			 *		     from list
>> +			 */
>> +			switch(rc) {
>> +			case -ENOSYS:
>> +				/* Hugetlb migration is unsupported */
>> +				nr_failed++;
>> +				nr_failed_pages += nr_subpages;
>> +				list_move_tail(&page->lru, &ret_pages);
>> +				break;
>> +			case -ENOMEM:
>> +				/*
>> +				 * When memory is low, don't bother to try to migrate
>> +				 * other pages, just exit.
>> +				 */
>> +				nr_failed++;
>> +				nr_failed_pages += nr_subpages + nr_retry_pages;
>> +				goto out;
>> +			case -EAGAIN:
>> +				retry++;
>> +				nr_retry_pages += nr_subpages;
>> +				break;
>> +			case MIGRATEPAGE_SUCCESS:
>> +				nr_succeeded += nr_subpages;
>> +				break;
>> +			default:
>> +				/*
>> +				 * Permanent failure (-EBUSY, etc.):
>> +				 * unlike -EAGAIN case, the failed page is
>> +				 * removed from migration page list and not
>> +				 * retried in the next outer loop.
>> +				 */
>> +				nr_failed++;
>> +				nr_failed_pages += nr_subpages;
>> +				break;
>> +			}
>> +		}
>> +	}
>> +	nr_failed += retry;
>
> Seems we should also record the nr_retry_pages? since the second loop
> will reset the nr_retry_pages.
>
> nr_failed_pages += nr_retry_pages;

Good catch!  Will do that in the next version.

> Besides, I also agree with Zi Yan's comment to simplify this larger
> function.

Yes.  I think so too.

Best Regards,
Huang, Ying