linux-kernel - Re: [PATCH 5/6] mm/page_alloc: Give GFP_ATOMIC and non-blocking allocations access to reserves

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]

Date:   Thu, 8 Dec 2022 19:07:06 +0100
From:   Vlastimil Babka <vbabka@...e.cz>
To:     Mel Gorman <mgorman@...hsingularity.net>,
        Linux-MM <linux-mm@...ck.org>
Cc:     Andrew Morton <akpm@...ux-foundation.org>,
        Michal Hocko <mhocko@...e.com>, NeilBrown <neilb@...e.de>,
        Thierry Reding <thierry.reding@...il.com>,
        Matthew Wilcox <willy@...radead.org>,
        LKML <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH 5/6] mm/page_alloc: Give GFP_ATOMIC and non-blocking
 allocations access to reserves

On 11/29/22 16:17, Mel Gorman wrote:
> Explicit GFP_ATOMIC allocations get flagged ALLOC_HARDER which is a bit
> vague. In preparation for removing __GFP_ATOMIC, give GFP_ATOMIC and
> other non-blocking allocation requests equal access to reserve.  Rename
> ALLOC_HARDER to ALLOC_NON_BLOCK to make it more clear what the flag
> means.
> 
> Signed-off-by: Mel Gorman <mgorman@...hsingularity.net>
> ---
>  mm/internal.h   |  7 +++++--
>  mm/page_alloc.c | 23 +++++++++++++----------
>  2 files changed, 18 insertions(+), 12 deletions(-)
> 
> diff --git a/mm/internal.h b/mm/internal.h
> index 370500718732..98b1e526559d 100644
> --- a/mm/internal.h
> +++ b/mm/internal.h
> @@ -743,7 +743,10 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone,
>  #define ALLOC_OOM		ALLOC_NO_WATERMARKS
>  #endif
>  
> -#define ALLOC_HARDER		 0x10 /* try to alloc harder */
> +#define ALLOC_NON_BLOCK		 0x10 /* Caller cannot block. Allow access
> +				       * to 25% of the min watermark or
> +				       * 62.5% if __GFP_HIGH is set.
> +				       */
>  #define ALLOC_MIN_RESERVE	 0x20 /* __GFP_HIGH set. Allow access to 50%
>  				       * of the min watermark.
>  				       */
> @@ -758,7 +761,7 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone,
>  #define ALLOC_KSWAPD		0x800 /* allow waking of kswapd, __GFP_KSWAPD_RECLAIM set */
>  
>  /* Flags that allow allocations below the min watermark. */
> -#define ALLOC_RESERVES (ALLOC_HARDER|ALLOC_MIN_RESERVE|ALLOC_HIGHATOMIC|ALLOC_OOM)
> +#define ALLOC_RESERVES (ALLOC_NON_BLOCK|ALLOC_MIN_RESERVE|ALLOC_HIGHATOMIC|ALLOC_OOM)
>  
>  enum ttu_flags;
>  struct tlbflush_unmap_batch;
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index 85a87d0ac57a..6bee987ec9a3 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -3994,7 +3994,7 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
>  		 * if it cannot get memory quickly, particularly if it's
>  		 * also __GFP_HIGH.
>  		 */
> -		if (alloc_flags & (ALLOC_HARDER|ALLOC_HIGHATOMIC))
> +		if (alloc_flags & (ALLOC_NON_BLOCK|ALLOC_HIGHATOMIC))
>  			min -= min / 4;
>  
>  		/*
> @@ -4846,28 +4846,30 @@ gfp_to_alloc_flags(gfp_t gfp_mask, unsigned int order)
>  	 * The caller may dip into page reserves a bit more if the caller
>  	 * cannot run direct reclaim, or if the caller has realtime scheduling
>  	 * policy or is asking for __GFP_HIGH memory.  GFP_ATOMIC requests will
> -	 * set both ALLOC_HARDER (__GFP_ATOMIC) and ALLOC_MIN_RESERVE(__GFP_HIGH).
> +	 * set both ALLOC_NON_BLOCK and ALLOC_MIN_RESERVE(__GFP_HIGH).
>  	 */
>  	alloc_flags |= (__force int)
>  		(gfp_mask & (__GFP_HIGH | __GFP_KSWAPD_RECLAIM));
>  
> -	if (gfp_mask & __GFP_ATOMIC) {
> +	if (!(gfp_mask & __GFP_RECLAIM)) {

This is supposed to be __GFP_DIRECT_RECLAIM right? Otherwise that includes
also __GFP_KSWAPD_RECLAIM and GFP_ATOMIC sets that one...

>  		/*
>  		 * Not worth trying to allocate harder for __GFP_NOMEMALLOC even
>  		 * if it can't schedule.
>  		 */
>  		if (!(gfp_mask & __GFP_NOMEMALLOC)) {
> -			alloc_flags |= ALLOC_HARDER;
> +			alloc_flags |= ALLOC_NON_BLOCK;
>  
>  			if (order > 0)
>  				alloc_flags |= ALLOC_HIGHATOMIC;
>  		}
>  
>  		/*
> -		 * Ignore cpuset mems for GFP_ATOMIC rather than fail, see the
> -		 * comment for __cpuset_node_allowed().
> +		 * Ignore cpuset mems for non-blocking __GFP_HIGH (probably
> +		 * GFP_ATOMIC) rather than fail, see the comment for
> +		 * __cpuset_node_allowed().
>  		 */
> -		alloc_flags &= ~ALLOC_CPUSET;
> +		if (alloc_flags & ALLOC_MIN_RESERVE)
> +			alloc_flags &= ~ALLOC_CPUSET;
>  	} else if (unlikely(rt_task(current)) && in_task())
>  		alloc_flags |= ALLOC_MIN_RESERVE;
>  
> @@ -5299,11 +5301,12 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
>  
>  		/*
>  		 * Help non-failing allocations by giving them access to memory
> -		 * reserves but do not use ALLOC_NO_WATERMARKS because this
> +		 * reserves normally used for high priority non-blocking
> +		 * allocations but do not use ALLOC_NO_WATERMARKS because this
>  		 * could deplete whole memory reserves which would just make
> -		 * the situation worse
> +		 * the situation worse.
>  		 */
> -		page = __alloc_pages_cpuset_fallback(gfp_mask, order, ALLOC_MIN_RESERVE|ALLOC_HARDER, ac);
> +		page = __alloc_pages_cpuset_fallback(gfp_mask, order, ALLOC_MIN_RESERVE|ALLOC_NON_BLOCK, ac);
>  		if (page)
>  			goto got_pg;
>