linux-kernel - Re: [PATCH 3/6] 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: <167021743246.8267.14900064704332224542@noble.neil.brown.name>
Date:   Mon, 05 Dec 2022 16:17:12 +1100
From:   "NeilBrown" <neilb@...e.de>
To:     "Mel Gorman" <mgorman@...hsingularity.net>
Cc:     "Linux-MM" <linux-mm@...ck.org>,
        "Andrew Morton" <akpm@...ux-foundation.org>,
        "Michal Hocko" <mhocko@...e.com>,
        "Thierry Reding" <thierry.reding@...il.com>,
        "Matthew Wilcox" <willy@...radead.org>,
        "Vlastimil Babka" <vbabka@...e.cz>,
        "LKML" <linux-kernel@...r.kernel.org>,
        "Mel Gorman" <mgorman@...hsingularity.net>
Subject: Re: [PATCH 3/6] mm/page_alloc: Explicitly record high-order atomic
 allocations in alloc_flags


Hi Mel,
 thanks a lot for doing this!
 I tried reviewing it but "HIGHATOMIC" is new to me and I quickly got
 lost :-(
 Maybe one day I'll work it out - now that several names are more
 meaningful, it will likely be easier.

Thanks,
NeilBrown

On Wed, 30 Nov 2022, 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().
> 
> Signed-off-by: Mel Gorman <mgorman@...hsingularity.net>
> ---
>  mm/internal.h   |  1 +
>  mm/page_alloc.c | 19 +++++++++++++------
>  2 files changed, 14 insertions(+), 6 deletions(-)
> 
> diff --git a/mm/internal.h b/mm/internal.h
> index d503e57a57a1..9a9d9b5ee87f 100644
> --- a/mm/internal.h
> +++ b/mm/internal.h
> @@ -754,6 +754,7 @@ 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 da746e9eb2cf..e2b65767dda0 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -3710,7 +3710,7 @@ 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);
> @@ -4028,8 +4028,10 @@ 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) &&
> +		    !free_area_empty(area, MIGRATE_HIGHATOMIC)) {
>  			return true;
> +		}
>  	}
>  	return false;
>  }
> @@ -4291,7 +4293,7 @@ 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;
> @@ -4818,7 +4820,7 @@ 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;
>  
> @@ -4844,8 +4846,13 @@ 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().
> @@ -5053,7 +5060,7 @@ __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
> 
>