X-Git-Url: http://plrg.eecs.uci.edu/git/?a=blobdiff_plain;f=mm%2Fpage_alloc.c;h=d17ff0504401eb8072bee3fbc3740b4a873cb7e9;hb=b1a14b3056873e639b0a61b379a23cc18438acd5;hp=6a117213feb8727380610b71751b434956a6a9f2;hpb=e21901d7a5eb2d41109847dc0ae08c97bba933d7;p=firefly-linux-kernel-4.4.55.git

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 6a117213feb8..d17ff0504401 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -114,13 +114,6 @@ static DEFINE_SPINLOCK(managed_page_count_lock);
 unsigned long totalram_pages __read_mostly;
 unsigned long totalreserve_pages __read_mostly;
 unsigned long totalcma_pages __read_mostly;
-/*
- * When calculating the number of globally allowed dirty pages, there
- * is a certain number of per-zone reserves that should not be
- * considered dirtyable memory.  This is the sum of those reserves
- * over all existing zones that contribute dirtyable memory.
- */
-unsigned long dirty_balance_reserve __read_mostly;
 
 int percpu_pagelist_fraction;
 gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK;
@@ -238,9 +231,21 @@ compound_page_dtor * const compound_page_dtors[] = {
 #endif
 };
 
+/*
+ * Try to keep at least this much lowmem free.  Do not allow normal
+ * allocations below this point, only high priority ones. Automatically
+ * tuned according to the amount of memory in the system.
+ */
 int min_free_kbytes = 1024;
 int user_min_free_kbytes = -1;
 
+/*
+ * Extra memory for the system to try freeing. Used to temporarily
+ * free memory, to make space for new workloads. Anyone can allocate
+ * down to the min watermarks controlled by min_free_kbytes above.
+ */
+int extra_free_kbytes = 0;
+
 static unsigned long __meminitdata nr_kernel_pages;
 static unsigned long __meminitdata nr_all_pages;
 static unsigned long __meminitdata dma_reserve;
@@ -2467,7 +2472,7 @@ static bool zone_local(struct zone *local_zone, struct zone *zone)
 
 static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
 {
-	return node_distance(zone_to_nid(local_zone), zone_to_nid(zone)) <
+	return node_distance(zone_to_nid(local_zone), zone_to_nid(zone)) <=
 				RECLAIM_DISTANCE;
 }
 #else	/* CONFIG_NUMA */
@@ -5981,20 +5986,12 @@ static void calculate_totalreserve_pages(void)
 
 			if (max > zone->managed_pages)
 				max = zone->managed_pages;
+
+			zone->totalreserve_pages = max;
+
 			reserve_pages += max;
-			/*
-			 * Lowmem reserves are not available to
-			 * GFP_HIGHUSER page cache allocations and
-			 * kswapd tries to balance zones to their high
-			 * watermark.  As a result, neither should be
-			 * regarded as dirtyable memory, to prevent a
-			 * situation where reclaim has to clean pages
-			 * in order to balance the zones.
-			 */
-			zone->dirty_balance_reserve = max;
 		}
 	}
-	dirty_balance_reserve = reserve_pages;
 	totalreserve_pages = reserve_pages;
 }
 
@@ -6040,6 +6037,7 @@ static void setup_per_zone_lowmem_reserve(void)
 static void __setup_per_zone_wmarks(void)
 {
 	unsigned long pages_min = min_free_kbytes >> (PAGE_SHIFT - 10);
+	unsigned long pages_low = extra_free_kbytes >> (PAGE_SHIFT - 10);
 	unsigned long lowmem_pages = 0;
 	struct zone *zone;
 	unsigned long flags;
@@ -6051,11 +6049,14 @@ static void __setup_per_zone_wmarks(void)
 	}
 
 	for_each_zone(zone) {
-		u64 tmp;
+		u64 min, low;
 
 		spin_lock_irqsave(&zone->lock, flags);
-		tmp = (u64)pages_min * zone->managed_pages;
-		do_div(tmp, lowmem_pages);
+		min = (u64)pages_min * zone->managed_pages;
+		do_div(min, lowmem_pages);
+		low = (u64)pages_low * zone->managed_pages;
+		do_div(low, vm_total_pages);
+
 		if (is_highmem(zone)) {
 			/*
 			 * __GFP_HIGH and PF_MEMALLOC allocations usually don't
@@ -6076,11 +6077,13 @@ static void __setup_per_zone_wmarks(void)
 			 * If it's a lowmem zone, reserve a number of pages
 			 * proportionate to the zone's size.
 			 */
-			zone->watermark[WMARK_MIN] = tmp;
+			zone->watermark[WMARK_MIN] = min;
 		}
 
-		zone->watermark[WMARK_LOW]  = min_wmark_pages(zone) + (tmp >> 2);
-		zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + (tmp >> 1);
+		zone->watermark[WMARK_LOW]  = min_wmark_pages(zone) +
+					low + (min >> 2);
+		zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) +
+					low + (min >> 1);
 
 		__mod_zone_page_state(zone, NR_ALLOC_BATCH,
 			high_wmark_pages(zone) - low_wmark_pages(zone) -
@@ -6203,7 +6206,7 @@ core_initcall(init_per_zone_wmark_min)
 /*
  * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so
  *	that we can call two helper functions whenever min_free_kbytes
- *	changes.
+ *	or extra_free_kbytes changes.
  */
 int min_free_kbytes_sysctl_handler(struct ctl_table *table, int write,
 	void __user *buffer, size_t *length, loff_t *ppos)