X-Git-Url: http://demsky.eecs.uci.edu/git/?a=blobdiff_plain;f=mm%2Fpage_alloc.c;h=755f29fac22f917d56f175efb8ac7021006e9722;hb=fe16f4b53f5a0ce564299f402079ab73c9cb8697;hp=9d666df5ef9502b70cf7ba0aedef5eb805fdd811;hpb=79dbddaf8e9613a529d1b07f181f07894bf6fb8e;p=firefly-linux-kernel-4.4.55.git

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 9d666df5ef95..755f29fac22f 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -238,9 +238,21 @@ 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;
@@ -662,34 +674,28 @@ static inline void __free_one_page(struct page *page,
 	unsigned long combined_idx;
 	unsigned long uninitialized_var(buddy_idx);
 	struct page *buddy;
-	unsigned int max_order = MAX_ORDER;
+	unsigned int max_order;
+
+	max_order = min_t(unsigned int, MAX_ORDER, pageblock_order + 1);
 
 	VM_BUG_ON(!zone_is_initialized(zone));
 	VM_BUG_ON_PAGE(page->flags & PAGE_FLAGS_CHECK_AT_PREP, page);
 
 	VM_BUG_ON(migratetype == -1);
-	if (is_migrate_isolate(migratetype)) {
-		/*
-		 * We restrict max order of merging to prevent merge
-		 * between freepages on isolate pageblock and normal
-		 * pageblock. Without this, pageblock isolation
-		 * could cause incorrect freepage accounting.
-		 */
-		max_order = min_t(unsigned int, MAX_ORDER, pageblock_order + 1);
-	} else {
+	if (likely(!is_migrate_isolate(migratetype)))
 		__mod_zone_freepage_state(zone, 1 << order, migratetype);
-	}
 
-	page_idx = pfn & ((1 << max_order) - 1);
+	page_idx = pfn & ((1 << MAX_ORDER) - 1);
 
 	VM_BUG_ON_PAGE(page_idx & ((1 << order) - 1), page);
 	VM_BUG_ON_PAGE(bad_range(zone, page), page);
 
+continue_merging:
 	while (order < max_order - 1) {
 		buddy_idx = __find_buddy_index(page_idx, order);
 		buddy = page + (buddy_idx - page_idx);
 		if (!page_is_buddy(page, buddy, order))
-			break;
+			goto done_merging;
 		/*
 		 * Our buddy is free or it is CONFIG_DEBUG_PAGEALLOC guard page,
 		 * merge with it and move up one order.
@@ -706,6 +712,32 @@ static inline void __free_one_page(struct page *page,
 		page_idx = combined_idx;
 		order++;
 	}
+	if (max_order < MAX_ORDER) {
+		/* If we are here, it means order is >= pageblock_order.
+		 * We want to prevent merge between freepages on isolate
+		 * pageblock and normal pageblock. Without this, pageblock
+		 * isolation could cause incorrect freepage or CMA accounting.
+		 *
+		 * We don't want to hit this code for the more frequent
+		 * low-order merging.
+		 */
+		if (unlikely(has_isolate_pageblock(zone))) {
+			int buddy_mt;
+
+			buddy_idx = __find_buddy_index(page_idx, order);
+			buddy = page + (buddy_idx - page_idx);
+			buddy_mt = get_pageblock_migratetype(buddy);
+
+			if (migratetype != buddy_mt
+					&& (is_migrate_isolate(migratetype) ||
+						is_migrate_isolate(buddy_mt)))
+				goto done_merging;
+		}
+		max_order++;
+		goto continue_merging;
+	}
+
+done_merging:
 	set_page_order(page, order);
 
 	/*
@@ -6015,6 +6047,7 @@ 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;
@@ -6026,11 +6059,14 @@ 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
@@ -6051,11 +6087,13 @@ 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) -
@@ -6173,12 +6211,12 @@ int __meminit init_per_zone_wmark_min(void)
 	setup_per_zone_inactive_ratio();
 	return 0;
 }
-module_init(init_per_zone_wmark_min)
+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)