linux-kernel - Re: [RFC 2/2] cma: support MIGRATE

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]

Date:	Tue, 14 Aug 2012 16:19:55 +0200
From:	Michal Nazarewicz <mina86@...a86.com>
To:	Minchan Kim <minchan@...nel.org>,
	Marek Szyprowski <m.szyprowski@...sung.com>
Cc:	Mel Gorman <mgorman@...e.de>, Rik van Riel <riel@...hat.com>,
	Kamezawa Hiroyuki <kamezawa.hiroyu@...fujitsu.com>,
	Andrew Morton <akpm@...ux-foundation.org>,
	linux-kernel@...r.kernel.org, linux-mm@...ck.org,
	Minchan Kim <minchan@...nel.org>
Subject: Re: [RFC 2/2] cma: support MIGRATE_DISCARD

Minchan Kim <minchan@...nel.org> writes:
> This patch introudes MIGRATE_DISCARD mode in migration.
> It drop clean cache pages instead of migration so that
> migration latency could be reduced. Of course, it could
> evict code pages but latency of big contiguous memory
> is more important than some background application's slow down
> in mobile embedded enviroment.
>
> Signed-off-by: Minchan Kim <minchan@...nel.org>

This looks good to me.

> ---
>  include/linux/migrate_mode.h |   11 +++++++---
>  mm/migrate.c                 |   50 +++++++++++++++++++++++++++++++++---------
>  mm/page_alloc.c              |    2 +-
>  3 files changed, 49 insertions(+), 14 deletions(-)
>
> diff --git a/include/linux/migrate_mode.h b/include/linux/migrate_mode.h
> index ebf3d89..04ca19c 100644
> --- a/include/linux/migrate_mode.h
> +++ b/include/linux/migrate_mode.h
> @@ -6,11 +6,16 @@
>   *	on most operations but not ->writepage as the potential stall time
>   *	is too significant
>   * MIGRATE_SYNC will block when migrating pages
> + * MIGRTATE_DISCARD will discard clean cache page instead of migration
> + *
> + * MIGRATE_ASYNC, MIGRATE_SYNC_LIGHT, MIGRATE_SYNC shouldn't be used
> + * together as OR flag.
>   */
>  enum migrate_mode {
> -	MIGRATE_ASYNC,
> -	MIGRATE_SYNC_LIGHT,
> -	MIGRATE_SYNC,
> +	MIGRATE_ASYNC = 1 << 0,
> +	MIGRATE_SYNC_LIGHT = 1 << 1,
> +	MIGRATE_SYNC = 1 << 2,
> +	MIGRATE_DISCARD = 1 << 3,
>  };

Since CMA is the only user of MIGRATE_DISCARD it may be worth it to
guard it inside an #ifdef, eg:

#ifdef CONFIG_CMA
	MIGRATE_DISCARD = 1 << 3,
#define is_migrate_discard(mode) (((mode) & MIGRATE_DISCARD) == MIGRATE_DISCARD)
#endif

  
>  #endif		/* MIGRATE_MODE_H_INCLUDED */
> diff --git a/mm/migrate.c b/mm/migrate.c
> index 77ed2d7..8119a59 100644
> --- a/mm/migrate.c
> +++ b/mm/migrate.c
> @@ -685,9 +685,12 @@ static int __unmap_and_move(struct page *page, struct page *newpage,
>  	int remap_swapcache = 1;
>  	struct mem_cgroup *mem;
>  	struct anon_vma *anon_vma = NULL;
> +	enum ttu_flags ttu_flags;
> +	bool discard_mode = false;
> +	bool file = false;
>  
>  	if (!trylock_page(page)) {
> -		if (!force || mode == MIGRATE_ASYNC)
> +		if (!force || mode & MIGRATE_ASYNC)

+		if (!force || (mode & MIGRATE_ASYNC))

>  			goto out;
>  
>  		/*


-- 
Best regards,                                         _     _
.o. | Liege of Serenely Enlightened Majesty of      o' \,=./ `o
..o | Computer Science,  Michał “mina86” Nazarewicz    (o o)
ooo +----<email/xmpp: mpn@...gle.com>--------------ooO--(_)--Ooo--

Content of type "application/pgp-signature" skipped