1 files changed, 186 insertions, 126 deletions

diff --git a/mm/bootmem.c b/mm/bootmem.c
index 7d1486875e1..90bd3507b41 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -10,9 +10,12 @@
  */
 #include <linux/init.h>
 #include <linux/pfn.h>
+#include <linux/slab.h>
 #include <linux/bootmem.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/kmemleak.h>
+#include <linux/range.h>
+#include <linux/memblock.h>
 
 #include <asm/bug.h>
 #include <asm/io.h>
@@ -20,18 +23,17 @@
 
 #include "internal.h"
 
+#ifndef CONFIG_NEED_MULTIPLE_NODES
+struct pglist_data __refdata contig_page_data = {
+	.bdata = &bootmem_node_data[0]
+};
+EXPORT_SYMBOL(contig_page_data);
+#endif
+
 unsigned long max_low_pfn;
 unsigned long min_low_pfn;
 unsigned long max_pfn;
 
-#ifdef CONFIG_CRASH_DUMP
-/*
- * If we have booted due to a crash, max_pfn will be a very low value. We need
- * to know the amount of memory that the previous kernel used.
- */
-unsigned long saved_max_pfn;
-#endif
-
 bootmem_data_t bootmem_node_data[MAX_NUMNODES] __initdata;
 
 static struct list_head bdata_list __initdata = LIST_HEAD_INIT(bdata_list);
@@ -54,7 +56,7 @@ early_param("bootmem_debug", bootmem_debug_setup);
 
 static unsigned long __init bootmap_bytes(unsigned long pages)
 {
-	unsigned long bytes = (pages + 7) / 8;
+	unsigned long bytes = DIV_ROUND_UP(pages, 8);
 
 	return ALIGN(bytes, sizeof(long));
 }
@@ -75,16 +77,16 @@ unsigned long __init bootmem_bootmap_pages(unsigned long pages)
  */
 static void __init link_bootmem(bootmem_data_t *bdata)
 {
-	struct list_head *iter;
+	bootmem_data_t *ent;
 
-	list_for_each(iter, &bdata_list) {
-		bootmem_data_t *ent;
-
-		ent = list_entry(iter, bootmem_data_t, list);
-		if (bdata->node_min_pfn < ent->node_min_pfn)
-			break;
+	list_for_each_entry(ent, &bdata_list, list) {
+		if (bdata->node_min_pfn < ent->node_min_pfn) {
+			list_add_tail(&bdata->list, &ent->list);
+			return;
+		}
 	}
-	list_add_tail(&bdata->list, iter);
+
+	list_add_tail(&bdata->list, &bdata_list);
 }
 
 /*
@@ -145,21 +147,21 @@ unsigned long __init init_bootmem(unsigned long start, unsigned long pages)
 
 /*
  * free_bootmem_late - free bootmem pages directly to page allocator
- * @addr: starting address of the range
+ * @addr: starting physical address of the range
  * @size: size of the range in bytes
  *
  * This is only useful when the bootmem allocator has already been torn
  * down, but we are still initializing the system.  Pages are given directly
  * to the page allocator, no bootmem metadata is updated because it is gone.
  */
-void __init free_bootmem_late(unsigned long addr, unsigned long size)
+void __init free_bootmem_late(unsigned long physaddr, unsigned long size)
 {
 	unsigned long cursor, end;
 
-	kmemleak_free_part(__va(addr), size);
+	kmemleak_free_part(__va(physaddr), size);
 
-	cursor = PFN_UP(addr);
-	end = PFN_DOWN(addr + size);
+	cursor = PFN_UP(physaddr);
+	end = PFN_DOWN(physaddr + size);
 
 	for (; cursor < end; cursor++) {
 		__free_pages_bootmem(pfn_to_page(cursor), 0);
@@ -169,51 +171,62 @@ void __init free_bootmem_late(unsigned long addr, unsigned long size)
 
 static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
 {
-	int aligned;
 	struct page *page;
-	unsigned long start, end, pages, count = 0;
+	unsigned long *map, start, end, pages, count = 0;
 
 	if (!bdata->node_bootmem_map)
 		return 0;
 
+	map = bdata->node_bootmem_map;
 	start = bdata->node_min_pfn;
 	end = bdata->node_low_pfn;
 
-	/*
-	 * If the start is aligned to the machines wordsize, we might
-	 * be able to free pages in bulks of that order.
-	 */
-	aligned = !(start & (BITS_PER_LONG - 1));
-
-	bdebug("nid=%td start=%lx end=%lx aligned=%d\n",
-		bdata - bootmem_node_data, start, end, aligned);
+	bdebug("nid=%td start=%lx end=%lx\n",
+		bdata - bootmem_node_data, start, end);
 
 	while (start < end) {
-		unsigned long *map, idx, vec;
+		unsigned long idx, vec;
+		unsigned shift;
 
-		map = bdata->node_bootmem_map;
 		idx = start - bdata->node_min_pfn;
+		shift = idx & (BITS_PER_LONG - 1);
+		/*
+		 * vec holds at most BITS_PER_LONG map bits,
+		 * bit 0 corresponds to start.
+		 */
 		vec = ~map[idx / BITS_PER_LONG];
 
-		if (aligned && vec == ~0UL && start + BITS_PER_LONG < end) {
+		if (shift) {
+			vec >>= shift;
+			if (end - start >= BITS_PER_LONG)
+				vec |= ~map[idx / BITS_PER_LONG + 1] <<
+					(BITS_PER_LONG - shift);
+		}
+		/*
+		 * If we have a properly aligned and fully unreserved
+		 * BITS_PER_LONG block of pages in front of us, free
+		 * it in one go.
+		 */
+		if (IS_ALIGNED(start, BITS_PER_LONG) && vec == ~0UL) {
 			int order = ilog2(BITS_PER_LONG);
 
 			__free_pages_bootmem(pfn_to_page(start), order);
 			count += BITS_PER_LONG;
+			start += BITS_PER_LONG;
 		} else {
-			unsigned long off = 0;
+			unsigned long cur = start;
 
-			while (vec && off < BITS_PER_LONG) {
+			start = ALIGN(start + 1, BITS_PER_LONG);
+			while (vec && cur != start) {
 				if (vec & 1) {
-					page = pfn_to_page(start + off);
+					page = pfn_to_page(cur);
 					__free_pages_bootmem(page, 0);
 					count++;
 				}
 				vec >>= 1;
-				off++;
+				++cur;
 			}
 		}
-		start += BITS_PER_LONG;
 	}
 
 	page = virt_to_page(bdata->node_bootmem_map);
@@ -228,16 +241,26 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
 	return count;
 }
 
-/**
- * free_all_bootmem_node - release a node's free pages to the buddy allocator
- * @pgdat: node to be released
- *
- * Returns the number of pages actually released.
- */
-unsigned long __init free_all_bootmem_node(pg_data_t *pgdat)
+static int reset_managed_pages_done __initdata;
+
+static inline void __init reset_node_managed_pages(pg_data_t *pgdat)
+{
+	struct zone *z;
+
+	if (reset_managed_pages_done)
+		return;
+
+	for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++)
+		z->managed_pages = 0;
+}
+
+void __init reset_all_zones_managed_pages(void)
 {
-	register_page_bootmem_info_node(pgdat);
-	return free_all_bootmem_core(pgdat->bdata);
+	struct pglist_data *pgdat;
+
+	for_each_online_pgdat(pgdat)
+		reset_node_managed_pages(pgdat);
+	reset_managed_pages_done = 1;
 }
 
 /**
@@ -247,7 +270,17 @@ unsigned long __init free_all_bootmem_node(pg_data_t *pgdat)
  */
 unsigned long __init free_all_bootmem(void)
 {
-	return free_all_bootmem_core(NODE_DATA(0)->bdata);
+	unsigned long total_pages = 0;
+	bootmem_data_t *bdata;
+
+	reset_all_zones_managed_pages();
+
+	list_for_each_entry(bdata, &bdata_list, list)
+		total_pages += free_all_bootmem_core(bdata);
+
+	totalram_pages += total_pages;
+
+	return total_pages;
 }
 
 static void __init __free(bootmem_data_t *bdata,
@@ -370,21 +403,21 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
 
 /**
  * free_bootmem - mark a page range as usable
- * @addr: starting address of the range
+ * @addr: starting physical address of the range
  * @size: size of the range in bytes
  *
  * Partial pages will be considered reserved and left as they are.
  *
  * The range must be contiguous but may span node boundaries.
  */
-void __init free_bootmem(unsigned long addr, unsigned long size)
+void __init free_bootmem(unsigned long physaddr, unsigned long size)
 {
 	unsigned long start, end;
 
-	kmemleak_free_part(__va(addr), size);
+	kmemleak_free_part(__va(physaddr), size);
 
-	start = PFN_UP(addr);
-	end = PFN_DOWN(addr + size);
+	start = PFN_UP(physaddr);
+	end = PFN_DOWN(physaddr + size);
 
 	mark_bootmem(start, end, 0, 0);
 }
@@ -412,7 +445,7 @@ int __init reserve_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
 }
 
 /**
- * reserve_bootmem - mark a page range as usable
+ * reserve_bootmem - mark a page range as reserved
  * @addr: starting address of the range
  * @size: size of the range in bytes
  * @flags: reservation flags (see linux/bootmem.h)
@@ -455,7 +488,7 @@ static unsigned long __init align_off(struct bootmem_data *bdata,
 	return ALIGN(base + off, align) - base;
 }
 
-static void * __init alloc_bootmem_core(struct bootmem_data *bdata,
+static void * __init alloc_bootmem_bdata(struct bootmem_data *bdata,
 					unsigned long size, unsigned long align,
 					unsigned long goal, unsigned long limit)
 {
@@ -562,28 +595,7 @@ find_block:
 	return NULL;
 }
 
-static void * __init alloc_arch_preferred_bootmem(bootmem_data_t *bdata,
-					unsigned long size, unsigned long align,
-					unsigned long goal, unsigned long limit)
-{
-	if (WARN_ON_ONCE(slab_is_available()))
-		return kzalloc(size, GFP_NOWAIT);
-
-#ifdef CONFIG_HAVE_ARCH_BOOTMEM
-	{
-		bootmem_data_t *p_bdata;
-
-		p_bdata = bootmem_arch_preferred_node(bdata, size, align,
-							goal, limit);
-		if (p_bdata)
-			return alloc_bootmem_core(p_bdata, size, align,
-							goal, limit);
-	}
-#endif
-	return NULL;
-}
-
-static void * __init ___alloc_bootmem_nopanic(unsigned long size,
+static void * __init alloc_bootmem_core(unsigned long size,
 					unsigned long align,
 					unsigned long goal,
 					unsigned long limit)
@@ -591,10 +603,8 @@ static void * __init ___alloc_bootmem_nopanic(unsigned long size,
 	bootmem_data_t *bdata;
 	void *region;
 
-restart:
-	region = alloc_arch_preferred_bootmem(NULL, size, align, goal, limit);
-	if (region)
-		return region;
+	if (WARN_ON_ONCE(slab_is_available()))
+		return kzalloc(size, GFP_NOWAIT);
 
 	list_for_each_entry(bdata, &bdata_list, list) {
 		if (goal && bdata->node_low_pfn <= PFN_DOWN(goal))
@@ -602,11 +612,25 @@ restart:
 		if (limit && bdata->node_min_pfn >= PFN_DOWN(limit))
 			break;
 
-		region = alloc_bootmem_core(bdata, size, align, goal, limit);
+		region = alloc_bootmem_bdata(bdata, size, align, goal, limit);
 		if (region)
 			return region;
 	}
 
+	return NULL;
+}
+
+static void * __init ___alloc_bootmem_nopanic(unsigned long size,
+					      unsigned long align,
+					      unsigned long goal,
+					      unsigned long limit)
+{
+	void *ptr;
+
+restart:
+	ptr = alloc_bootmem_core(size, align, goal, limit);
+	if (ptr)
+		return ptr;
 	if (goal) {
 		goal = 0;
 		goto restart;
@@ -631,7 +655,9 @@ restart:
 void * __init __alloc_bootmem_nopanic(unsigned long size, unsigned long align,
 					unsigned long goal)
 {
-	return ___alloc_bootmem_nopanic(size, align, goal, 0);
+	unsigned long limit = 0;
+
+	return ___alloc_bootmem_nopanic(size, align, goal, limit);
 }
 
 static void * __init ___alloc_bootmem(unsigned long size, unsigned long align,
@@ -665,24 +691,63 @@ static void * __init ___alloc_bootmem(unsigned long size, unsigned long align,
 void * __init __alloc_bootmem(unsigned long size, unsigned long align,
 			      unsigned long goal)
 {
-	return ___alloc_bootmem(size, align, goal, 0);
+	unsigned long limit = 0;
+
+	return ___alloc_bootmem(size, align, goal, limit);
 }
 
-static void * __init ___alloc_bootmem_node(bootmem_data_t *bdata,
+void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat,
 				unsigned long size, unsigned long align,
 				unsigned long goal, unsigned long limit)
 {
 	void *ptr;
 
-	ptr = alloc_arch_preferred_bootmem(bdata, size, align, goal, limit);
+	if (WARN_ON_ONCE(slab_is_available()))
+		return kzalloc(size, GFP_NOWAIT);
+again:
+
+	/* do not panic in alloc_bootmem_bdata() */
+	if (limit && goal + size > limit)
+		limit = 0;
+
+	ptr = alloc_bootmem_bdata(pgdat->bdata, size, align, goal, limit);
 	if (ptr)
 		return ptr;
 
-	ptr = alloc_bootmem_core(bdata, size, align, goal, limit);
+	ptr = alloc_bootmem_core(size, align, goal, limit);
 	if (ptr)
 		return ptr;
 
-	return ___alloc_bootmem(size, align, goal, limit);
+	if (goal) {
+		goal = 0;
+		goto again;
+	}
+
+	return NULL;
+}
+
+void * __init __alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size,
+				   unsigned long align, unsigned long goal)
+{
+	if (WARN_ON_ONCE(slab_is_available()))
+		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
+
+	return ___alloc_bootmem_node_nopanic(pgdat, size, align, goal, 0);
+}
+
+void * __init ___alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
+				    unsigned long align, unsigned long goal,
+				    unsigned long limit)
+{
+	void *ptr;
+
+	ptr = ___alloc_bootmem_node_nopanic(pgdat, size, align, goal, 0);
+	if (ptr)
+		return ptr;
+
+	printk(KERN_ALERT "bootmem alloc of %lu bytes failed!\n", size);
+	panic("Out of memory");
+	return NULL;
 }
 
 /**
@@ -706,49 +771,36 @@ void * __init __alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
 	if (WARN_ON_ONCE(slab_is_available()))
 		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
 
-	return ___alloc_bootmem_node(pgdat->bdata, size, align, goal, 0);
+	return  ___alloc_bootmem_node(pgdat, size, align, goal, 0);
 }
 
-#ifdef CONFIG_SPARSEMEM
-/**
- * alloc_bootmem_section - allocate boot memory from a specific section
- * @size: size of the request in bytes
- * @section_nr: sparse map section to allocate from
- *
- * Return NULL on failure.
- */
-void * __init alloc_bootmem_section(unsigned long size,
-				    unsigned long section_nr)
-{
-	bootmem_data_t *bdata;
-	unsigned long pfn, goal, limit;
-
-	pfn = section_nr_to_pfn(section_nr);
-	goal = pfn << PAGE_SHIFT;
-	limit = section_nr_to_pfn(section_nr + 1) << PAGE_SHIFT;
-	bdata = &bootmem_node_data[early_pfn_to_nid(pfn)];
-
-	return alloc_bootmem_core(bdata, size, SMP_CACHE_BYTES, goal, limit);
-}
-#endif
-
-void * __init __alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size,
+void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size,
 				   unsigned long align, unsigned long goal)
 {
-	void *ptr;
+#ifdef MAX_DMA32_PFN
+	unsigned long end_pfn;
 
 	if (WARN_ON_ONCE(slab_is_available()))
 		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
 
-	ptr = alloc_arch_preferred_bootmem(pgdat->bdata, size, align, goal, 0);
-	if (ptr)
-		return ptr;
+	/* update goal according ...MAX_DMA32_PFN */
+	end_pfn = pgdat_end_pfn(pgdat);
 
-	ptr = alloc_bootmem_core(pgdat->bdata, size, align, goal, 0);
-	if (ptr)
-		return ptr;
+	if (end_pfn > MAX_DMA32_PFN + (128 >> (20 - PAGE_SHIFT)) &&
+	    (goal >> PAGE_SHIFT) < MAX_DMA32_PFN) {
+		void *ptr;
+		unsigned long new_goal;
+
+		new_goal = MAX_DMA32_PFN << PAGE_SHIFT;
+		ptr = alloc_bootmem_bdata(pgdat->bdata, size, align,
+						 new_goal, 0);
+		if (ptr)
+			return ptr;
+	}
+#endif
+
+	return __alloc_bootmem_node(pgdat, size, align, goal);
 
-	return __alloc_bootmem_nopanic(size, align, goal);
 }
 
 #ifndef ARCH_LOW_ADDRESS_LIMIT
@@ -774,6 +826,14 @@ void * __init __alloc_bootmem_low(unsigned long size, unsigned long align,
 	return ___alloc_bootmem(size, align, goal, ARCH_LOW_ADDRESS_LIMIT);
 }
 
+void * __init __alloc_bootmem_low_nopanic(unsigned long size,
+					  unsigned long align,
+					  unsigned long goal)
+{
+	return ___alloc_bootmem_nopanic(size, align, goal,
+					ARCH_LOW_ADDRESS_LIMIT);
+}
+
 /**
  * __alloc_bootmem_low_node - allocate low boot memory from a specific node
  * @pgdat: node to allocate from
@@ -795,6 +855,6 @@ void * __init __alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long size,
 	if (WARN_ON_ONCE(slab_is_available()))
 		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
 
-	return ___alloc_bootmem_node(pgdat->bdata, size, align,
-				goal, ARCH_LOW_ADDRESS_LIMIT);
+	return ___alloc_bootmem_node(pgdat, size, align,
+				     goal, ARCH_LOW_ADDRESS_LIMIT);
 }