mm/page_alloc: don't reserve ZONE_HIGHMEM for ZONE_MOVABLE request

Freepage on ZONE_HIGHMEM doesn't work for kernel memory so it's not that
important to reserve.  When ZONE_MOVABLE is used, this problem would
theorectically cause to decrease usable memory for GFP_HIGHUSER_MOVABLE
allocation request which is mainly used for page cache and anon page
allocation.  So, fix it by setting 0 to
sysctl_lowmem_reserve_ratio[ZONE_HIGHMEM].

And, defining sysctl_lowmem_reserve_ratio array by MAX_NR_ZONES - 1 size
makes code complex.  For example, if there is highmem system, following
reserve ratio is activated for *NORMAL ZONE* which would be easyily
misleading people.

 #ifdef CONFIG_HIGHMEM
 32
 #endif

This patch also fixes this situation by defining
sysctl_lowmem_reserve_ratio array by MAX_NR_ZONES and place "#ifdef" to
right place.

Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Joonsoo Kim <[email protected]>
Reviewed-by: Aneesh Kumar K.V <[email protected]>
Acked-by: Vlastimil Babka <[email protected]>
Tested-by: Tony Lindgren <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Vlastimil Babka <[email protected]>
Cc: Mel Gorman <[email protected]>
Cc: Johannes Weiner <[email protected]>
Cc: "Aneesh Kumar K . V" <[email protected]>
Cc: Minchan Kim <[email protected]>
Cc: Rik van Riel <[email protected]>
Cc: Laura Abbott <[email protected]>
Cc: Marek Szyprowski <[email protected]>
Cc: Michal Nazarewicz <[email protected]>
Cc: Russell King <[email protected]>
Cc: Will Deacon <[email protected]>
Cc: <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

Documentation/sysctl/vm.txt

@@ -312,8 +312,6 @@ The lowmem_reserve_ratio is an array. You can see them by reading this file.
 % cat /proc/sys/vm/lowmem_reserve_ratio
 256     256     32
 -
-Note: # of this elements is one fewer than number of zones. Because the highest
-      zone's value is not necessary for following calculation.
 
 But, these values are not used directly. The kernel calculates # of protection
 pages for each zones from them. These are shown as array of protection pages
@@ -364,7 +362,8 @@ As above expression, they are reciprocal number of ratio.
 pages of higher zones on the node.
 
 If you would like to protect more pages, smaller values are effective.
-The minimum value is 1 (1/1 -> 100%).
+The minimum value is 1 (1/1 -> 100%). The value less than 1 completely
+disables protection of the pages.
 
 ==============================================================
 

include/linux/mmzone.h

@@ -885,7 +885,7 @@ int min_free_kbytes_sysctl_handler(struct ctl_table *, int,
 					void __user *, size_t *, loff_t *);
 int watermark_scale_factor_sysctl_handler(struct ctl_table *, int,
 					void __user *, size_t *, loff_t *);
-extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1];
+extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES];
 int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int,
 					void __user *, size_t *, loff_t *);
 int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *, int,

mm/page_alloc.c

@@ -205,17 +205,18 @@ static void __free_pages_ok(struct page *page, unsigned int order);
  * TBD: should special case ZONE_DMA32 machines here - in those we normally
  * don't need any ZONE_NORMAL reservation
  */
-int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1] = {
+int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES] = {
 #ifdef CONFIG_ZONE_DMA
-	 256,
+	[ZONE_DMA] = 256,
 #endif
 #ifdef CONFIG_ZONE_DMA32
-	 256,
+	[ZONE_DMA32] = 256,
 #endif
+	[ZONE_NORMAL] = 32,
 #ifdef CONFIG_HIGHMEM
-	 32,
+	[ZONE_HIGHMEM] = 0,
 #endif
-	 32,
+	[ZONE_MOVABLE] = 0,
 };
 
 EXPORT_SYMBOL(totalram_pages);
@@ -7132,13 +7133,15 @@ static void setup_per_zone_lowmem_reserve(void)
 				struct zone *lower_zone;
 
 				idx--;
-
-				if (sysctl_lowmem_reserve_ratio[idx] < 1)
-					sysctl_lowmem_reserve_ratio[idx] = 1;
-
 				lower_zone = pgdat->node_zones + idx;
-				lower_zone->lowmem_reserve[j] = managed_pages /
-					sysctl_lowmem_reserve_ratio[idx];
+
+				if (sysctl_lowmem_reserve_ratio[idx] < 1) {
+					sysctl_lowmem_reserve_ratio[idx] = 0;
+					lower_zone->lowmem_reserve[j] = 0;
+				} else {
+					lower_zone->lowmem_reserve[j] =
+						managed_pages / sysctl_lowmem_reserve_ratio[idx];
+				}
 				managed_pages += lower_zone->managed_pages;
 			}
 		}