linux-kernel - Re: [PATCH v2] mm, compaction: Skip all non-migratable pages during scan

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <871qji7zhm.fsf@yhuang6-desk2.ccr.corp.intel.com>
Date:   Mon, 15 May 2023 16:47:17 +0800
From:   "Huang, Ying" <ying.huang@...el.com>
To:     Khalid Aziz <khalid.aziz@...cle.com>
Cc:     akpm@...ux-foundation.org, willy@...radead.org, linux-mm@...ck.org,
        linux-kernel@...r.kernel.org,
        Steve Sistare <steven.sistare@...cle.com>,
        Khalid Aziz <khalid@...nel.org>,
        Mel Gorman <mgorman@...hsingularity.net>
Subject: Re: [PATCH v2] mm, compaction: Skip all non-migratable pages during
 scan

Hi, Khalid,

Cced Mel.

Khalid Aziz <khalid.aziz@...cle.com> writes:

> Pages pinned in memory through extra refcounts can not be migrated.
> Currently as isolate_migratepages_block() scans pages for
> compaction, it skips any pinned anonymous pages. All non-migratable
> pages should be skipped and not just the anonymous pinned pages.
> This patch adds a check for extra refcounts on a page to determine
> if the page can be migrated.  This was seen as a real issue on a
> customer workload where a large number of pages were pinned by vfio
> on the host and any attempts to allocate hugepages resulted in
> significant amount of cpu time spent in either direct compaction or
> in kcompatd scanning vfio pinned pages over and over again that can

s/kcompatd/kcompactd/

> not be migrated.

With the patch below, the cycles for kcompactd disappeared?

> Signed-off-by: Khalid Aziz <khalid.aziz@...cle.com>
> Suggested-by: Steve Sistare <steven.sistare@...cle.com>
> Cc: Khalid Aziz <khalid@...nel.org>
> ---
> v2:
> 	- Update comments in the code (Suggested by Andrew)
> 	- Use PagePrivate() instead of page_has_private() (Suggested
> 	  by Matthew)
> 	- Pass mapping to page_has_extrarefs() (Suggested by Matthew)
> 	- Use page_ref_count() (Suggested by Matthew)
> 	- Rename is_pinned_page() to reflect its function more
> 	  accurately (Suggested by Matthew)
>
>  mm/compaction.c | 36 ++++++++++++++++++++++++++++++++----
>  1 file changed, 32 insertions(+), 4 deletions(-)
>
> diff --git a/mm/compaction.c b/mm/compaction.c
> index 5a9501e0ae01..837f20df2bbb 100644
> --- a/mm/compaction.c
> +++ b/mm/compaction.c
> @@ -764,6 +764,34 @@ static bool too_many_isolated(pg_data_t *pgdat)
>  	return too_many;
>  }
>  
> +/*
> + * Check if this base page should be skipped from isolation because
> + * it has extra refcounts that will prevent it from being migrated.
> + * This function is called for regular pages only, and not
> + * for THP or hugetlbfs pages. This code is inspired by similar code
> + * in migrate_vma_check_page(), can_split_folio() and
> + * folio_migrate_mapping()
> + */
> +static inline bool page_has_extrarefs(struct page *page,

Better to be named as page_has_extra_refs()?

> +					struct address_space *mapping)
> +{
> +	unsigned long extra_refs;
> +
> +	/* anonymous page can have extra ref from swap cache */
> +	if (mapping)
> +		extra_refs = 1 + PagePrivate(page);
> +	else
> +		extra_refs = PageSwapCache(page) ? 1 : 0;

IIUC, mapping != NULL if PageSwapCache(page) is true.  Please check the
implementation of page_mapping().

And even if mapping == NULL, the extra_refs should be 1, because we have
elevated the page refcount in isolate_migratepages_block() before
checking whether the page is pinned.  IIUC, this is the original
behavior.  Or, we can add "- 1" in the following checking.

> +
> +	/*
> +	 * This is an admittedly racy check but good enough to determine
> +	 * if a page is pinned and can not be migrated
> +	 */
> +	if ((page_ref_count(page) - extra_refs) > page_mapcount(page))
> +		return true;
> +	return false;
> +}
> +
>  /**
>   * isolate_migratepages_block() - isolate all migrate-able pages within
>   *				  a single pageblock
> @@ -992,12 +1020,12 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
>  			goto isolate_fail;
>  
>  		/*
> -		 * Migration will fail if an anonymous page is pinned in memory,
> -		 * so avoid taking lru_lock and isolating it unnecessarily in an
> -		 * admittedly racy check.
> +		 * Migration will fail if a page has extra refcounts
> +		 * preventing it from migrating, so avoid taking
> +		 * lru_lock and isolating it unnecessarily
>  		 */
>  		mapping = page_mapping(page);
> -		if (!mapping && (page_count(page) - 1) > total_mapcount(page))
> +		if (page_has_extrarefs(page, mapping))
>  			goto isolate_fail_put;
>  
>  		/*

Best Regards,
Huang, Ying