diff mbox series

[4/7] mm/page_alloc: Explicitly define what alloc flags deplete min reserves

Message ID 20230109151631.24923-5-mgorman@techsingularity.net (mailing list archive)
State New
Headers show
Series Discard __GFP_ATOMIC | expand

Commit Message

Mel Gorman Jan. 9, 2023, 3:16 p.m. UTC
As there are more ALLOC_ flags that affect reserves, define what flags
affect reserves and clarify the effect of each flag.

Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
---
 mm/internal.h   |  3 +++
 mm/page_alloc.c | 34 ++++++++++++++++++++++------------
 2 files changed, 25 insertions(+), 12 deletions(-)

Comments

Vlastimil Babka Jan. 11, 2023, 2:04 p.m. UTC | #1
On 1/9/23 16:16, Mel Gorman wrote:
> As there are more ALLOC_ flags that affect reserves, define what flags
> affect reserves and clarify the effect of each flag.
> 
> Signed-off-by: Mel Gorman <mgorman@techsingularity.net>

Acked-by: Vlastimil Babka <vbabka@suse.cz>
Michal Hocko Jan. 11, 2023, 3:37 p.m. UTC | #2
On Mon 09-01-23 15:16:28, Mel Gorman wrote:
> As there are more ALLOC_ flags that affect reserves, define what flags
> affect reserves and clarify the effect of each flag.

I like this! It makes the code much easier to follow.

> Signed-off-by: Mel Gorman <mgorman@techsingularity.net>

Acked-by: Michal Hocko <mhocko@suse.com>

Thanks!

> ---
>  mm/internal.h   |  3 +++
>  mm/page_alloc.c | 34 ++++++++++++++++++++++------------
>  2 files changed, 25 insertions(+), 12 deletions(-)
> 
> diff --git a/mm/internal.h b/mm/internal.h
> index 178484d9fd94..8706d46863df 100644
> --- a/mm/internal.h
> +++ b/mm/internal.h
> @@ -749,6 +749,9 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone,
>  #define ALLOC_HIGHATOMIC	0x200 /* Allows access to MIGRATE_HIGHATOMIC */
>  #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)
> +
>  enum ttu_flags;
>  struct tlbflush_unmap_batch;
>  
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index 0ef4f3236a5a..6f41b84a97ac 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -3949,15 +3949,14 @@ ALLOW_ERROR_INJECTION(should_fail_alloc_page, TRUE);
>  static inline long __zone_watermark_unusable_free(struct zone *z,
>  				unsigned int order, unsigned int alloc_flags)
>  {
> -	const bool alloc_harder = (alloc_flags & (ALLOC_HARDER|ALLOC_OOM));
>  	long unusable_free = (1 << order) - 1;
>  
>  	/*
> -	 * If the caller does not have rights to ALLOC_HARDER then subtract
> -	 * the high-atomic reserves. This will over-estimate the size of the
> -	 * atomic reserve but it avoids a search.
> +	 * If the caller does not have rights to reserves below the min
> +	 * watermark then subtract the high-atomic reserves. This will
> +	 * over-estimate the size of the atomic reserve but it avoids a search.
>  	 */
> -	if (likely(!alloc_harder))
> +	if (likely(!(alloc_flags & ALLOC_RESERVES)))
>  		unusable_free += z->nr_reserved_highatomic;
>  
>  #ifdef CONFIG_CMA
> @@ -3981,25 +3980,36 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
>  {
>  	long min = mark;
>  	int o;
> -	const bool alloc_harder = (alloc_flags & (ALLOC_HARDER|ALLOC_OOM));
>  
>  	/* free_pages may go negative - that's OK */
>  	free_pages -= __zone_watermark_unusable_free(z, order, alloc_flags);
>  
> -	if (alloc_flags & ALLOC_MIN_RESERVE)
> -		min -= min / 2;
> +	if (unlikely(alloc_flags & ALLOC_RESERVES)) {
> +		/*
> +		 * __GFP_HIGH allows access to 50% of the min reserve as well
> +		 * as OOM.
> +		 */
> +		if (alloc_flags & ALLOC_MIN_RESERVE)
> +			min -= min / 2;
>  
> -	if (unlikely(alloc_harder)) {
>  		/*
> -		 * OOM victims can try even harder than normal ALLOC_HARDER
> +		 * Non-blocking allocations can access some of the reserve
> +		 * with more access if also __GFP_HIGH. The reasoning is that
> +		 * a non-blocking caller may incur a more severe penalty
> +		 * if it cannot get memory quickly, particularly if it's
> +		 * also __GFP_HIGH.
> +		 */
> +		if (alloc_flags & ALLOC_HARDER)
> +			min -= min / 4;
> +
> +		/*
> +		 * OOM victims can try even harder than the normal reserve
>  		 * users on the grounds that it's definitely going to be in
>  		 * the exit path shortly and free memory. Any allocation it
>  		 * makes during the free path will be small and short-lived.
>  		 */
>  		if (alloc_flags & ALLOC_OOM)
>  			min -= min / 2;
> -		else
> -			min -= min / 4;
>  	}
>  
>  	/*
> -- 
> 2.35.3
diff mbox series

Patch

diff --git a/mm/internal.h b/mm/internal.h
index 178484d9fd94..8706d46863df 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -749,6 +749,9 @@  unsigned int reclaim_clean_pages_from_list(struct zone *zone,
 #define ALLOC_HIGHATOMIC	0x200 /* Allows access to MIGRATE_HIGHATOMIC */
 #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)
+
 enum ttu_flags;
 struct tlbflush_unmap_batch;
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 0ef4f3236a5a..6f41b84a97ac 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3949,15 +3949,14 @@  ALLOW_ERROR_INJECTION(should_fail_alloc_page, TRUE);
 static inline long __zone_watermark_unusable_free(struct zone *z,
 				unsigned int order, unsigned int alloc_flags)
 {
-	const bool alloc_harder = (alloc_flags & (ALLOC_HARDER|ALLOC_OOM));
 	long unusable_free = (1 << order) - 1;
 
 	/*
-	 * If the caller does not have rights to ALLOC_HARDER then subtract
-	 * the high-atomic reserves. This will over-estimate the size of the
-	 * atomic reserve but it avoids a search.
+	 * If the caller does not have rights to reserves below the min
+	 * watermark then subtract the high-atomic reserves. This will
+	 * over-estimate the size of the atomic reserve but it avoids a search.
 	 */
-	if (likely(!alloc_harder))
+	if (likely(!(alloc_flags & ALLOC_RESERVES)))
 		unusable_free += z->nr_reserved_highatomic;
 
 #ifdef CONFIG_CMA
@@ -3981,25 +3980,36 @@  bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
 {
 	long min = mark;
 	int o;
-	const bool alloc_harder = (alloc_flags & (ALLOC_HARDER|ALLOC_OOM));
 
 	/* free_pages may go negative - that's OK */
 	free_pages -= __zone_watermark_unusable_free(z, order, alloc_flags);
 
-	if (alloc_flags & ALLOC_MIN_RESERVE)
-		min -= min / 2;
+	if (unlikely(alloc_flags & ALLOC_RESERVES)) {
+		/*
+		 * __GFP_HIGH allows access to 50% of the min reserve as well
+		 * as OOM.
+		 */
+		if (alloc_flags & ALLOC_MIN_RESERVE)
+			min -= min / 2;
 
-	if (unlikely(alloc_harder)) {
 		/*
-		 * OOM victims can try even harder than normal ALLOC_HARDER
+		 * Non-blocking allocations can access some of the reserve
+		 * with more access if also __GFP_HIGH. The reasoning is that
+		 * a non-blocking caller may incur a more severe penalty
+		 * if it cannot get memory quickly, particularly if it's
+		 * also __GFP_HIGH.
+		 */
+		if (alloc_flags & ALLOC_HARDER)
+			min -= min / 4;
+
+		/*
+		 * OOM victims can try even harder than the normal reserve
 		 * users on the grounds that it's definitely going to be in
 		 * the exit path shortly and free memory. Any allocation it
 		 * makes during the free path will be small and short-lived.
 		 */
 		if (alloc_flags & ALLOC_OOM)
 			min -= min / 2;
-		else
-			min -= min / 4;
 	}
 
 	/*