linux-kernel - Re: [PATCH 3/7] mm/page_alloc: Explicitly record high-order atomic allocations in alloc

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: Windows password security audit tool. GUI, reports in PDF.

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

Message-ID: <Y77XYW/81sfSXCj9@dhcp22.suse.cz>
Date:   Wed, 11 Jan 2023 16:36:01 +0100
From:   Michal Hocko <mhocko@...e.com>
To:     Mel Gorman <mgorman@...hsingularity.net>
Cc:     Linux-MM <linux-mm@...ck.org>,
        Andrew Morton <akpm@...ux-foundation.org>,
        NeilBrown <neilb@...e.de>,
        Thierry Reding <thierry.reding@...il.com>,
        Matthew Wilcox <willy@...radead.org>,
        Vlastimil Babka <vbabka@...e.cz>,
        LKML <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH 3/7] mm/page_alloc: Explicitly record high-order atomic
 allocations in alloc_flags

On Mon 09-01-23 15:16:27, Mel Gorman wrote:
> A high-order ALLOC_HARDER allocation is assumed to be atomic. While that
> is accurate, it changes later in the series. In preparation, explicitly
> record high-order atomic allocations in gfp_to_alloc_flags(). There is
> a slight functional change in that OOM handling avoids using high-order
> reserve until it has to.

I do not follow the oom handling part. IIRC we are dropping highatomic
reserves before triggering oom. Something might have changed down the
path but I can still see unreserve_highatomic_pageblock in
should_reclaim_retry.

I do not have any objection to ALLOC_HIGHATOMIC itself, though.

> Signed-off-by: Mel Gorman <mgorman@...hsingularity.net>
> ---
>  mm/internal.h   |  1 +
>  mm/page_alloc.c | 29 +++++++++++++++++++++++------
>  2 files changed, 24 insertions(+), 6 deletions(-)
> 
> diff --git a/mm/internal.h b/mm/internal.h
> index 403e4386626d..178484d9fd94 100644
> --- a/mm/internal.h
> +++ b/mm/internal.h
> @@ -746,6 +746,7 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone,
>  #else
>  #define ALLOC_NOFRAGMENT	  0x0
>  #endif
> +#define ALLOC_HIGHATOMIC	0x200 /* Allows access to MIGRATE_HIGHATOMIC */
>  #define ALLOC_KSWAPD		0x800 /* allow waking of kswapd, __GFP_KSWAPD_RECLAIM set */
>  
>  enum ttu_flags;
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index 0040b4e00913..0ef4f3236a5a 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -3706,10 +3706,20 @@ struct page *rmqueue_buddy(struct zone *preferred_zone, struct zone *zone,
>  		 * reserved for high-order atomic allocation, so order-0
>  		 * request should skip it.
>  		 */
> -		if (order > 0 && alloc_flags & ALLOC_HARDER)
> +		if (alloc_flags & ALLOC_HIGHATOMIC)
>  			page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC);
>  		if (!page) {
>  			page = __rmqueue(zone, order, migratetype, alloc_flags);
> +
> +			/*
> +			 * If the allocation fails, allow OOM handling access
> +			 * to HIGHATOMIC reserves as failing now is worse than
> +			 * failing a high-order atomic allocation in the
> +			 * future.
> +			 */
> +			if (!page && (alloc_flags & ALLOC_OOM))
> +				page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC);
> +
>  			if (!page) {
>  				spin_unlock_irqrestore(&zone->lock, flags);
>  				return NULL;
> @@ -4023,8 +4033,10 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
>  			return true;
>  		}
>  #endif
> -		if (alloc_harder && !free_area_empty(area, MIGRATE_HIGHATOMIC))
> +		if ((alloc_flags & (ALLOC_HIGHATOMIC|ALLOC_OOM)) &&
> +		    !free_area_empty(area, MIGRATE_HIGHATOMIC)) {
>  			return true;
> +		}
>  	}
>  	return false;
>  }
> @@ -4286,7 +4298,7 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
>  			 * If this is a high-order atomic allocation then check
>  			 * if the pageblock should be reserved for the future
>  			 */
> -			if (unlikely(order && (alloc_flags & ALLOC_HARDER)))
> +			if (unlikely(alloc_flags & ALLOC_HIGHATOMIC))
>  				reserve_highatomic_pageblock(page, zone, order);
>  
>  			return page;
> @@ -4813,7 +4825,7 @@ static void wake_all_kswapds(unsigned int order, gfp_t gfp_mask,
>  }
>  
>  static inline unsigned int
> -gfp_to_alloc_flags(gfp_t gfp_mask)
> +gfp_to_alloc_flags(gfp_t gfp_mask, unsigned int order)
>  {
>  	unsigned int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET;
>  
> @@ -4839,8 +4851,13 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
>  		 * Not worth trying to allocate harder for __GFP_NOMEMALLOC even
>  		 * if it can't schedule.
>  		 */
> -		if (!(gfp_mask & __GFP_NOMEMALLOC))
> +		if (!(gfp_mask & __GFP_NOMEMALLOC)) {
>  			alloc_flags |= ALLOC_HARDER;
> +
> +			if (order > 0)
> +				alloc_flags |= ALLOC_HIGHATOMIC;
> +		}
> +
>  		/*
>  		 * Ignore cpuset mems for GFP_ATOMIC rather than fail, see the
>  		 * comment for __cpuset_node_allowed().
> @@ -5048,7 +5065,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
>  	 * kswapd needs to be woken up, and to avoid the cost of setting up
>  	 * alloc_flags precisely. So we do that now.
>  	 */
> -	alloc_flags = gfp_to_alloc_flags(gfp_mask);
> +	alloc_flags = gfp_to_alloc_flags(gfp_mask, order);
>  
>  	/*
>  	 * We need to recalculate the starting point for the zonelist iterator
> -- 
> 2.35.3

-- 
Michal Hocko
SUSE Labs