Merge branch 'master' into gfs2

28 files changed, 2180 insertions, 942 deletions

diff --git a/mm/Makefile b/mm/Makefile
index 9dd824c11ee..60c56c0b5e1 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -23,4 +23,4 @@ obj-$(CONFIG_SLAB) += slab.o
 obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o
 obj-$(CONFIG_FS_XIP) += filemap_xip.o
 obj-$(CONFIG_MIGRATION) += migrate.o
-
+obj-$(CONFIG_SMP) += allocpercpu.o
diff --git a/mm/allocpercpu.c b/mm/allocpercpu.c
new file mode 100644
index 00000000000..eaa9abeea53
--- /dev/null
+++ b/mm/allocpercpu.c
@@ -0,0 +1,129 @@
+/*
+ * linux/mm/allocpercpu.c
+ *
+ * Separated from slab.c August 11, 2006 Christoph Lameter <clameter@sgi.com>
+ */
+#include <linux/mm.h>
+#include <linux/module.h>
+
+/**
+ * percpu_depopulate - depopulate per-cpu data for given cpu
+ * @__pdata: per-cpu data to depopulate
+ * @cpu: depopulate per-cpu data for this cpu
+ *
+ * Depopulating per-cpu data for a cpu going offline would be a typical
+ * use case. You need to register a cpu hotplug handler for that purpose.
+ */
+void percpu_depopulate(void *__pdata, int cpu)
+{
+	struct percpu_data *pdata = __percpu_disguise(__pdata);
+	if (pdata->ptrs[cpu]) {
+		kfree(pdata->ptrs[cpu]);
+		pdata->ptrs[cpu] = NULL;
+	}
+}
+EXPORT_SYMBOL_GPL(percpu_depopulate);
+
+/**
+ * percpu_depopulate_mask - depopulate per-cpu data for some cpu's
+ * @__pdata: per-cpu data to depopulate
+ * @mask: depopulate per-cpu data for cpu's selected through mask bits
+ */
+void __percpu_depopulate_mask(void *__pdata, cpumask_t *mask)
+{
+	int cpu;
+	for_each_cpu_mask(cpu, *mask)
+		percpu_depopulate(__pdata, cpu);
+}
+EXPORT_SYMBOL_GPL(__percpu_depopulate_mask);
+
+/**
+ * percpu_populate - populate per-cpu data for given cpu
+ * @__pdata: per-cpu data to populate further
+ * @size: size of per-cpu object
+ * @gfp: may sleep or not etc.
+ * @cpu: populate per-data for this cpu
+ *
+ * Populating per-cpu data for a cpu coming online would be a typical
+ * use case. You need to register a cpu hotplug handler for that purpose.
+ * Per-cpu object is populated with zeroed buffer.
+ */
+void *percpu_populate(void *__pdata, size_t size, gfp_t gfp, int cpu)
+{
+	struct percpu_data *pdata = __percpu_disguise(__pdata);
+	int node = cpu_to_node(cpu);
+
+	BUG_ON(pdata->ptrs[cpu]);
+	if (node_online(node)) {
+		/* FIXME: kzalloc_node(size, gfp, node) */
+		pdata->ptrs[cpu] = kmalloc_node(size, gfp, node);
+		if (pdata->ptrs[cpu])
+			memset(pdata->ptrs[cpu], 0, size);
+	} else
+		pdata->ptrs[cpu] = kzalloc(size, gfp);
+	return pdata->ptrs[cpu];
+}
+EXPORT_SYMBOL_GPL(percpu_populate);
+
+/**
+ * percpu_populate_mask - populate per-cpu data for more cpu's
+ * @__pdata: per-cpu data to populate further
+ * @size: size of per-cpu object
+ * @gfp: may sleep or not etc.
+ * @mask: populate per-cpu data for cpu's selected through mask bits
+ *
+ * Per-cpu objects are populated with zeroed buffers.
+ */
+int __percpu_populate_mask(void *__pdata, size_t size, gfp_t gfp,
+			   cpumask_t *mask)
+{
+	cpumask_t populated = CPU_MASK_NONE;
+	int cpu;
+
+	for_each_cpu_mask(cpu, *mask)
+		if (unlikely(!percpu_populate(__pdata, size, gfp, cpu))) {
+			__percpu_depopulate_mask(__pdata, &populated);
+			return -ENOMEM;
+		} else
+			cpu_set(cpu, populated);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(__percpu_populate_mask);
+
+/**
+ * percpu_alloc_mask - initial setup of per-cpu data
+ * @size: size of per-cpu object
+ * @gfp: may sleep or not etc.
+ * @mask: populate per-data for cpu's selected through mask bits
+ *
+ * Populating per-cpu data for all online cpu's would be a typical use case,
+ * which is simplified by the percpu_alloc() wrapper.
+ * Per-cpu objects are populated with zeroed buffers.
+ */
+void *__percpu_alloc_mask(size_t size, gfp_t gfp, cpumask_t *mask)
+{
+	void *pdata = kzalloc(sizeof(struct percpu_data), gfp);
+	void *__pdata = __percpu_disguise(pdata);
+
+	if (unlikely(!pdata))
+		return NULL;
+	if (likely(!__percpu_populate_mask(__pdata, size, gfp, mask)))
+		return __pdata;
+	kfree(pdata);
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(__percpu_alloc_mask);
+
+/**
+ * percpu_free - final cleanup of per-cpu data
+ * @__pdata: object to clean up
+ *
+ * We simply clean up any per-cpu object left. No need for the client to
+ * track and specify through a bis mask which per-cpu objects are to free.
+ */
+void percpu_free(void *__pdata)
+{
+	__percpu_depopulate_mask(__pdata, &cpu_possible_map);
+	kfree(__percpu_disguise(__pdata));
+}
+EXPORT_SYMBOL_GPL(percpu_free);
diff --git a/mm/bootmem.c b/mm/bootmem.c
index 50353e0dac1..d53112fcb40 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -8,17 +8,15 @@
  *  free memory collector. It's used to deal with reserved
  *  system memory and memory holes as well.
  */
-
-#include <linux/mm.h>
-#include <linux/kernel_stat.h>
-#include <linux/swap.h>
-#include <linux/interrupt.h>
 #include <linux/init.h>
+#include <linux/pfn.h>
 #include <linux/bootmem.h>
-#include <linux/mmzone.h>
 #include <linux/module.h>
-#include <asm/dma.h>
+
+#include <asm/bug.h>
 #include <asm/io.h>
+#include <asm/processor.h>
+
 #include "internal.h"
 
 /*
@@ -41,7 +39,7 @@ unsigned long saved_max_pfn;
 #endif
 
 /* return the number of _pages_ that will be allocated for the boot bitmap */
-unsigned long __init bootmem_bootmap_pages (unsigned long pages)
+unsigned long __init bootmem_bootmap_pages(unsigned long pages)
 {
 	unsigned long mapsize;
 
@@ -51,12 +49,14 @@ unsigned long __init bootmem_bootmap_pages (unsigned long pages)
 
 	return mapsize;
 }
+
 /*
  * link bdata in order
  */
-static void link_bootmem(bootmem_data_t *bdata)
+static void __init link_bootmem(bootmem_data_t *bdata)
 {
 	bootmem_data_t *ent;
+
 	if (list_empty(&bdata_list)) {
 		list_add(&bdata->list, &bdata_list);
 		return;
@@ -69,22 +69,32 @@ static void link_bootmem(bootmem_data_t *bdata)
 		}
 	}
 	list_add_tail(&bdata->list, &bdata_list);
-	return;
 }
 
+/*
+ * Given an initialised bdata, it returns the size of the boot bitmap
+ */
+static unsigned long __init get_mapsize(bootmem_data_t *bdata)
+{
+	unsigned long mapsize;
+	unsigned long start = PFN_DOWN(bdata->node_boot_start);
+	unsigned long end = bdata->node_low_pfn;
+
+	mapsize = ((end - start) + 7) / 8;
+	return ALIGN(mapsize, sizeof(long));
+}
 
 /*
  * Called once to set up the allocator itself.
  */
-static unsigned long __init init_bootmem_core (pg_data_t *pgdat,
+static unsigned long __init init_bootmem_core(pg_data_t *pgdat,
 	unsigned long mapstart, unsigned long start, unsigned long end)
 {
 	bootmem_data_t *bdata = pgdat->bdata;
-	unsigned long mapsize = ((end - start)+7)/8;
+	unsigned long mapsize;
 
-	mapsize = ALIGN(mapsize, sizeof(long));
-	bdata->node_bootmem_map = phys_to_virt(mapstart << PAGE_SHIFT);
-	bdata->node_boot_start = (start << PAGE_SHIFT);
+	bdata->node_bootmem_map = phys_to_virt(PFN_PHYS(mapstart));
+	bdata->node_boot_start = PFN_PHYS(start);
 	bdata->node_low_pfn = end;
 	link_bootmem(bdata);
 
@@ -92,6 +102,7 @@ static unsigned long __init init_bootmem_core (pg_data_t *pgdat,
 	 * Initially all pages are reserved - setup_arch() has to
 	 * register free RAM areas explicitly.
 	 */
+	mapsize = get_mapsize(bdata);
 	memset(bdata->node_bootmem_map, 0xff, mapsize);
 
 	return mapsize;
@@ -102,22 +113,22 @@ static unsigned long __init init_bootmem_core (pg_data_t *pgdat,
  * might be used for boot-time allocations - or it might get added
  * to the free page pool later on.
  */
-static void __init reserve_bootmem_core(bootmem_data_t *bdata, unsigned long addr, unsigned long size)
+static void __init reserve_bootmem_core(bootmem_data_t *bdata, unsigned long addr,
+					unsigned long size)
 {
+	unsigned long sidx, eidx;
 	unsigned long i;
+
 	/*
 	 * round up, partially reserved pages are considered
 	 * fully reserved.
 	 */
-	unsigned long sidx = (addr - bdata->node_boot_start)/PAGE_SIZE;
-	unsigned long eidx = (addr + size - bdata->node_boot_start + 
-							PAGE_SIZE-1)/PAGE_SIZE;
-	unsigned long end = (addr + size + PAGE_SIZE-1)/PAGE_SIZE;
-
 	BUG_ON(!size);
-	BUG_ON(sidx >= eidx);
-	BUG_ON((addr >> PAGE_SHIFT) >= bdata->node_low_pfn);
-	BUG_ON(end > bdata->node_low_pfn);
+	BUG_ON(PFN_DOWN(addr) >= bdata->node_low_pfn);
+	BUG_ON(PFN_UP(addr + size) > bdata->node_low_pfn);
+
+	sidx = PFN_DOWN(addr - bdata->node_boot_start);
+	eidx = PFN_UP(addr + size - bdata->node_boot_start);
 
 	for (i = sidx; i < eidx; i++)
 		if (test_and_set_bit(i, bdata->node_bootmem_map)) {
@@ -127,20 +138,18 @@ static void __init reserve_bootmem_core(bootmem_data_t *bdata, unsigned long add
 		}
 }
 
-static void __init free_bootmem_core(bootmem_data_t *bdata, unsigned long addr, unsigned long size)
+static void __init free_bootmem_core(bootmem_data_t *bdata, unsigned long addr,
+				     unsigned long size)
 {
+	unsigned long sidx, eidx;
 	unsigned long i;
-	unsigned long start;
+
 	/*
 	 * round down end of usable mem, partially free pages are
 	 * considered reserved.
 	 */
-	unsigned long sidx;
-	unsigned long eidx = (addr + size - bdata->node_boot_start)/PAGE_SIZE;
-	unsigned long end = (addr + size)/PAGE_SIZE;
-
 	BUG_ON(!size);
-	BUG_ON(end > bdata->node_low_pfn);
+	BUG_ON(PFN_DOWN(addr + size) > bdata->node_low_pfn);
 
 	if (addr < bdata->last_success)
 		bdata->last_success = addr;
@@ -148,8 +157,8 @@ static void __init free_bootmem_core(bootmem_data_t *bdata, unsigned long addr,
 	/*
 	 * Round up the beginning of the address.
 	 */
-	start = (addr + PAGE_SIZE-1) / PAGE_SIZE;
-	sidx = start - (bdata->node_boot_start/PAGE_SIZE);
+	sidx = PFN_UP(addr) - PFN_DOWN(bdata->node_boot_start);
+	eidx = PFN_DOWN(addr + size - bdata->node_boot_start);
 
 	for (i = sidx; i < eidx; i++) {
 		if (unlikely(!test_and_clear_bit(i, bdata->node_bootmem_map)))
@@ -175,10 +184,10 @@ __alloc_bootmem_core(struct bootmem_data *bdata, unsigned long size,
 	      unsigned long align, unsigned long goal, unsigned long limit)
 {
 	unsigned long offset, remaining_size, areasize, preferred;
-	unsigned long i, start = 0, incr, eidx, end_pfn = bdata->node_low_pfn;
+	unsigned long i, start = 0, incr, eidx, end_pfn;
 	void *ret;
 
-	if(!size) {
+	if (!size) {
 		printk("__alloc_bootmem_core(): zero-sized request\n");
 		BUG();
 	}
@@ -187,23 +196,22 @@ __alloc_bootmem_core(struct bootmem_data *bdata, unsigned long size,
 	if (limit && bdata->node_boot_start >= limit)
 		return NULL;
 
-        limit >>=PAGE_SHIFT;
+	end_pfn = bdata->node_low_pfn;
+	limit = PFN_DOWN(limit);
 	if (limit && end_pfn > limit)
 		end_pfn = limit;
 
-	eidx = end_pfn - (bdata->node_boot_start >> PAGE_SHIFT);
+	eidx = end_pfn - PFN_DOWN(bdata->node_boot_start);
 	offset = 0;
-	if (align &&
-	    (bdata->node_boot_start & (align - 1UL)) != 0)
-		offset = (align - (bdata->node_boot_start & (align - 1UL)));
-	offset >>= PAGE_SHIFT;
+	if (align && (bdata->node_boot_start & (align - 1UL)) != 0)
+		offset = align - (bdata->node_boot_start & (align - 1UL));
+	offset = PFN_DOWN(offset);
 
 	/*
 	 * We try to allocate bootmem pages above 'goal'
 	 * first, then we try to allocate lower pages.
 	 */
-	if (goal && (goal >= bdata->node_boot_start) && 
-	    ((goal >> PAGE_SHIFT) < end_pfn)) {
+	if (goal && goal >= bdata->node_boot_start && PFN_DOWN(goal) < end_pfn) {
 		preferred = goal - bdata->node_boot_start;
 
 		if (bdata->last_success >= preferred)
@@ -212,9 +220,8 @@ __alloc_bootmem_core(struct bootmem_data *bdata, unsigned long size,
 	} else
 		preferred = 0;
 
-	preferred = ALIGN(preferred, align) >> PAGE_SHIFT;
-	preferred += offset;
-	areasize = (size+PAGE_SIZE-1)/PAGE_SIZE;
+	preferred = PFN_DOWN(ALIGN(preferred, align)) + offset;
+	areasize = (size + PAGE_SIZE-1) / PAGE_SIZE;
 	incr = align >> PAGE_SHIFT ? : 1;
 
 restart_scan:
@@ -229,7 +236,7 @@ restart_scan:
 		for (j = i + 1; j < i + areasize; ++j) {
 			if (j >= eidx)
 				goto fail_block;
-			if (test_bit (j, bdata->node_bootmem_map))
+			if (test_bit(j, bdata->node_bootmem_map))
 				goto fail_block;
 		}
 		start = i;
@@ -245,7 +252,7 @@ restart_scan:
 	return NULL;
 
 found:
-	bdata->last_success = start << PAGE_SHIFT;
+	bdata->last_success = PFN_PHYS(start);
 	BUG_ON(start >= eidx);
 
 	/*
@@ -257,19 +264,21 @@ found:
 	    bdata->last_offset && bdata->last_pos+1 == start) {
 		offset = ALIGN(bdata->last_offset, align);
 		BUG_ON(offset > PAGE_SIZE);
-		remaining_size = PAGE_SIZE-offset;
+		remaining_size = PAGE_SIZE - offset;
 		if (size < remaining_size) {
 			areasize = 0;
 			/* last_pos unchanged */
-			bdata->last_offset = offset+size;
-			ret = phys_to_virt(bdata->last_pos*PAGE_SIZE + offset +
-						bdata->node_boot_start);
+			bdata->last_offset = offset + size;
+			ret = phys_to_virt(bdata->last_pos * PAGE_SIZE +
+					   offset +
+					   bdata->node_boot_start);
 		} else {
 			remaining_size = size - remaining_size;
-			areasize = (remaining_size+PAGE_SIZE-1)/PAGE_SIZE;
-			ret = phys_to_virt(bdata->last_pos*PAGE_SIZE + offset +
-						bdata->node_boot_start);
-			bdata->last_pos = start+areasize-1;
+			areasize = (remaining_size + PAGE_SIZE-1) / PAGE_SIZE;
+			ret = phys_to_virt(bdata->last_pos * PAGE_SIZE +
+					   offset +
+					   bdata->node_boot_start);
+			bdata->last_pos = start + areasize - 1;
 			bdata->last_offset = remaining_size;
 		}
 		bdata->last_offset &= ~PAGE_MASK;
@@ -282,7 +291,7 @@ found:
 	/*
 	 * Reserve the area now:
 	 */
-	for (i = start; i < start+areasize; i++)
+	for (i = start; i < start + areasize; i++)
 		if (unlikely(test_and_set_bit(i, bdata->node_bootmem_map)))
 			BUG();
 	memset(ret, 0, size);
@@ -303,8 +312,8 @@ static unsigned long __init free_all_bootmem_core(pg_data_t *pgdat)
 
 	count = 0;
 	/* first extant page of the node */
-	pfn = bdata->node_boot_start >> PAGE_SHIFT;
-	idx = bdata->node_low_pfn - (bdata->node_boot_start >> PAGE_SHIFT);
+	pfn = PFN_DOWN(bdata->node_boot_start);
+	idx = bdata->node_low_pfn - pfn;
 	map = bdata->node_bootmem_map;
 	/* Check physaddr is O(LOG2(BITS_PER_LONG)) page aligned */
 	if (bdata->node_boot_start == 0 ||
@@ -333,7 +342,7 @@ static unsigned long __init free_all_bootmem_core(pg_data_t *pgdat)
 				}
 			}
 		} else {
-			i+=BITS_PER_LONG;
+			i += BITS_PER_LONG;
 		}
 		pfn += BITS_PER_LONG;
 	}
@@ -345,9 +354,10 @@ static unsigned long __init free_all_bootmem_core(pg_data_t *pgdat)
 	 */
 	page = virt_to_page(bdata->node_bootmem_map);
 	count = 0;
-	for (i = 0; i < ((bdata->node_low_pfn-(bdata->node_boot_start >> PAGE_SHIFT))/8 + PAGE_SIZE-1)/PAGE_SIZE; i++,page++) {
-		count++;
+	idx = (get_mapsize(bdata) + PAGE_SIZE-1) >> PAGE_SHIFT;
+	for (i = 0; i < idx; i++, page++) {
 		__free_pages_bootmem(page, 0);
+		count++;
 	}
 	total += count;
 	bdata->node_bootmem_map = NULL;
@@ -355,64 +365,72 @@ static unsigned long __init free_all_bootmem_core(pg_data_t *pgdat)
 	return total;
 }
 
-unsigned long __init init_bootmem_node (pg_data_t *pgdat, unsigned long freepfn, unsigned long startpfn, unsigned long endpfn)
+unsigned long __init init_bootmem_node(pg_data_t *pgdat, unsigned long freepfn,
+				unsigned long startpfn, unsigned long endpfn)
 {
-	return(init_bootmem_core(pgdat, freepfn, startpfn, endpfn));
+	return init_bootmem_core(pgdat, freepfn, startpfn, endpfn);
 }
 
-void __init reserve_bootmem_node (pg_data_t *pgdat, unsigned long physaddr, unsigned long size)
+void __init reserve_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
+				 unsigned long size)
 {
 	reserve_bootmem_core(pgdat->bdata, physaddr, size);
 }
 
-void __init free_bootmem_node (pg_data_t *pgdat, unsigned long physaddr, unsigned long size)
+void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
+			      unsigned long size)
 {
 	free_bootmem_core(pgdat->bdata, physaddr, size);
 }
 
-unsigned long __init free_all_bootmem_node (pg_data_t *pgdat)
+unsigned long __init free_all_bootmem_node(pg_data_t *pgdat)
 {
-	return(free_all_bootmem_core(pgdat));
+	return free_all_bootmem_core(pgdat);
 }
 
-unsigned long __init init_bootmem (unsigned long start, unsigned long pages)
+unsigned long __init init_bootmem(unsigned long start, unsigned long pages)
 {
 	max_low_pfn = pages;
 	min_low_pfn = start;
-	return(init_bootmem_core(NODE_DATA(0), start, 0, pages));
+	return init_bootmem_core(NODE_DATA(0), start, 0, pages);
 }
 
 #ifndef CONFIG_HAVE_ARCH_BOOTMEM_NODE
-void __init reserve_bootmem (unsigned long addr, unsigned long size)
+void __init reserve_bootmem(unsigned long addr, unsigned long size)
 {
 	reserve_bootmem_core(NODE_DATA(0)->bdata, addr, size);
 }
 #endif /* !CONFIG_HAVE_ARCH_BOOTMEM_NODE */
 
-void __init free_bootmem (unsigned long addr, unsigned long size)
+void __init free_bootmem(unsigned long addr, unsigned long size)
 {
 	free_bootmem_core(NODE_DATA(0)->bdata, addr, size);
 }
 
-unsigned long __init free_all_bootmem (void)
+unsigned long __init free_all_bootmem(void)
 {
-	return(free_all_bootmem_core(NODE_DATA(0)));
+	return free_all_bootmem_core(NODE_DATA(0));
 }
 
-void * __init __alloc_bootmem_nopanic(unsigned long size, unsigned long align, unsigned long goal)
+void * __init __alloc_bootmem_nopanic(unsigned long size, unsigned long align,
+				      unsigned long goal)
 {
 	bootmem_data_t *bdata;
 	void *ptr;
 
-	list_for_each_entry(bdata, &bdata_list, list)
-		if ((ptr = __alloc_bootmem_core(bdata, size, align, goal, 0)))
-			return(ptr);
+	list_for_each_entry(bdata, &bdata_list, list) {
+		ptr = __alloc_bootmem_core(bdata, size, align, goal, 0);
+		if (ptr)
+			return ptr;
+	}
 	return NULL;
 }
 
-void * __init __alloc_bootmem(unsigned long size, unsigned long align, unsigned long goal)
+void * __init __alloc_bootmem(unsigned long size, unsigned long align,
+			      unsigned long goal)
 {
 	void *mem = __alloc_bootmem_nopanic(size,align,goal);
+
 	if (mem)
 		return mem;
 	/*
@@ -424,29 +442,34 @@ void * __init __alloc_bootmem(unsigned long size, unsigned long align, unsigned
 }
 
 
-void * __init __alloc_bootmem_node(pg_data_t *pgdat, unsigned long size, unsigned long align,
-				   unsigned long goal)
+void * __init __alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
+				   unsigned long align, unsigned long goal)
 {
 	void *ptr;
 
 	ptr = __alloc_bootmem_core(pgdat->bdata, size, align, goal, 0);
 	if (ptr)
-		return (ptr);
+		return ptr;
 
 	return __alloc_bootmem(size, align, goal);
 }
 
-#define LOW32LIMIT 0xffffffff
+#ifndef ARCH_LOW_ADDRESS_LIMIT
+#define ARCH_LOW_ADDRESS_LIMIT	0xffffffffUL
+#endif
 
-void * __init __alloc_bootmem_low(unsigned long size, unsigned long align, unsigned long goal)
+void * __init __alloc_bootmem_low(unsigned long size, unsigned long align,
+				  unsigned long goal)
 {
 	bootmem_data_t *bdata;
 	void *ptr;
 
-	list_for_each_entry(bdata, &bdata_list, list)
-		if ((ptr = __alloc_bootmem_core(bdata, size,
-						 align, goal, LOW32LIMIT)))
-			return(ptr);
+	list_for_each_entry(bdata, &bdata_list, list) {
+		ptr = __alloc_bootmem_core(bdata, size, align, goal,
+						ARCH_LOW_ADDRESS_LIMIT);
+		if (ptr)
+			return ptr;
+	}
 
 	/*
 	 * Whoops, we cannot satisfy the allocation request.
@@ -459,5 +482,6 @@ void * __init __alloc_bootmem_low(unsigned long size, unsigned long align, unsig
 void * __init __alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long size,
 				       unsigned long align, unsigned long goal)
 {
-	return __alloc_bootmem_core(pgdat->bdata, size, align, goal, LOW32LIMIT);
+	return __alloc_bootmem_core(pgdat->bdata, size, align, goal,
+				    ARCH_LOW_ADDRESS_LIMIT);
 }
diff --git a/mm/filemap.c b/mm/filemap.c
index 3195806d78e..87d4a398cd1 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -488,6 +488,12 @@ struct page *page_cache_alloc_cold(struct address_space *x)
 EXPORT_SYMBOL(page_cache_alloc_cold);
 #endif
 
+static int __sleep_on_page_lock(void *word)
+{
+	io_schedule();
+	return 0;
+}
+
 /*
  * In order to wait for pages to become available there must be
  * waitqueues associated with pages. By using a hash table of
@@ -577,13 +583,24 @@ void fastcall __lock_page(struct page *page)
 }
 EXPORT_SYMBOL(__lock_page);
 
+/*
+ * Variant of lock_page that does not require the caller to hold a reference
+ * on the page's mapping.
+ */
+void fastcall __lock_page_nosync(struct page *page)
+{
+	DEFINE_WAIT_BIT(wait, &page->flags, PG_locked);
+	__wait_on_bit_lock(page_waitqueue(page), &wait, __sleep_on_page_lock,
+							TASK_UNINTERRUPTIBLE);
+}
+
 /**
  * find_get_page - find and get a page reference
  * @mapping: the address_space to search
  * @offset: the page index
  *
- * A rather lightweight function, finding and getting a reference to a
- * hashed page atomically.
+ * Is there a pagecache struct page at the given (mapping, offset) tuple?
+ * If yes, increment its refcount and return it; if no, return NULL.
  */
 struct page * find_get_page(struct address_space *mapping, unsigned long offset)
 {
@@ -970,7 +987,7 @@ page_not_up_to_date:
 		/* Get exclusive access to the page ... */
 		lock_page(page);
 
-		/* Did it get unhashed before we got the lock? */
+		/* Did it get truncated before we got the lock? */
 		if (!page->mapping) {
 			unlock_page(page);
 			page_cache_release(page);
@@ -1612,7 +1629,7 @@ no_cached_page:
 page_not_uptodate:
 	lock_page(page);
 
-	/* Did it get unhashed while we waited for it? */
+	/* Did it get truncated while we waited for it? */
 	if (!page->mapping) {
 		unlock_page(page);
 		goto err;
diff --git a/mm/fremap.c b/mm/fremap.c
index 21b7d0cbc98..aa30618ec6b 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -79,9 +79,9 @@ int install_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		inc_mm_counter(mm, file_rss);
 
 	flush_icache_page(vma, page);
-	set_pte_at(mm, addr, pte, mk_pte(page, prot));
+	pte_val = mk_pte(page, prot);
+	set_pte_at(mm, addr, pte, pte_val);
 	page_add_file_rmap(page);
-	pte_val = *pte;
 	update_mmu_cache(vma, addr, pte_val);
 	lazy_mmu_prot_update(pte_val);
 	err = 0;
diff --git a/mm/highmem.c b/mm/highmem.c
index 9b2a5403c44..ee5519b176e 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -46,6 +46,19 @@ static void *mempool_alloc_pages_isa(gfp_t gfp_mask, void *data)
  */
 #ifdef CONFIG_HIGHMEM
 
+unsigned long totalhigh_pages __read_mostly;
+
+unsigned int nr_free_highpages (void)
+{
+	pg_data_t *pgdat;
+	unsigned int pages = 0;
+
+	for_each_online_pgdat(pgdat)
+		pages += pgdat->node_zones[ZONE_HIGHMEM].free_pages;
+
+	return pages;
+}
+
 static int pkmap_count[LAST_PKMAP];
 static unsigned int last_pkmap_nr;
 static  __cacheline_aligned_in_smp DEFINE_SPINLOCK(kmap_lock);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index df499973255..7c7d03dbf73 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -72,7 +72,7 @@ static struct page *dequeue_huge_page(struct vm_area_struct *vma,
 	struct zone **z;
 
 	for (z = zonelist->zones; *z; z++) {
-		nid = (*z)->zone_pgdat->node_id;
+		nid = zone_to_nid(*z);
 		if (cpuset_zone_allowed(*z, GFP_HIGHUSER) &&
 		    !list_empty(&hugepage_freelists[nid]))
 			break;
@@ -177,7 +177,7 @@ static void update_and_free_page(struct page *page)
 {
 	int i;
 	nr_huge_pages--;
-	nr_huge_pages_node[page_zone(page)->zone_pgdat->node_id]--;
+	nr_huge_pages_node[page_to_nid(page)]--;
 	for (i = 0; i < (HPAGE_SIZE / PAGE_SIZE); i++) {
 		page[i].flags &= ~(1 << PG_locked | 1 << PG_error | 1 << PG_referenced |
 				1 << PG_dirty | 1 << PG_active | 1 << PG_reserved |
@@ -191,7 +191,8 @@ static void update_and_free_page(struct page *page)
 #ifdef CONFIG_HIGHMEM
 static void try_to_free_low(unsigned long count)
 {
-	int i, nid;
+	int i;
+
 	for (i = 0; i < MAX_NUMNODES; ++i) {
 		struct page *page, *next;
 		list_for_each_entry_safe(page, next, &hugepage_freelists[i], lru) {
@@ -199,9 +200,8 @@ static void try_to_free_low(unsigned long count)
 				continue;
 			list_del(&page->lru);
 			update_and_free_page(page);
-			nid = page_zone(page)->zone_pgdat->node_id;
 			free_huge_pages--;
-			free_huge_pages_node[nid]--;
+			free_huge_pages_node[page_to_nid(page)]--;
 			if (count >= nr_huge_pages)
 				return;
 		}
diff --git a/mm/internal.h b/mm/internal.h
index d20e3cc4aef..d527b80b292 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -24,8 +24,8 @@ static inline void set_page_count(struct page *page, int v)
  */
 static inline void set_page_refcounted(struct page *page)
 {
-	BUG_ON(PageCompound(page) && page_private(page) != (unsigned long)page);
-	BUG_ON(atomic_read(&page->_count));
+	VM_BUG_ON(PageCompound(page) && page_private(page) != (unsigned long)page);
+	VM_BUG_ON(atomic_read(&page->_count));
 	set_page_count(page, 1);
 }
 
diff --git a/mm/memory.c b/mm/memory.c
index 109e9866237..601159a46ab 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -49,6 +49,7 @@
 #include <linux/module.h>
 #include <linux/delayacct.h>
 #include <linux/init.h>
+#include <linux/writeback.h>
 
 #include <asm/pgalloc.h>
 #include <asm/uaccess.h>
@@ -1226,7 +1227,12 @@ out:
 	return retval;
 }
 
-/*
+/**
+ * vm_insert_page - insert single page into user vma
+ * @vma: user vma to map to
+ * @addr: target user address of this page
+ * @page: source kernel page
+ *
  * This allows drivers to insert individual pages they've allocated
  * into a user vma.
  *
@@ -1318,7 +1324,16 @@ static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd,
 	return 0;
 }
 
-/*  Note: this is only safe if the mm semaphore is held when called. */
+/**
+ * remap_pfn_range - remap kernel memory to userspace
+ * @vma: user vma to map to
+ * @addr: target user address to start at
+ * @pfn: physical address of kernel memory
+ * @size: size of map area
+ * @prot: page protection flags for this mapping
+ *
+ *  Note: this is only safe if the mm semaphore is held when called.
+ */
 int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
 		    unsigned long pfn, unsigned long size, pgprot_t prot)
 {
@@ -1458,14 +1473,29 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 {
 	struct page *old_page, *new_page;
 	pte_t entry;
-	int reuse, ret = VM_FAULT_MINOR;
+	int reuse = 0, ret = VM_FAULT_MINOR;
+	struct page *dirty_page = NULL;
 
 	old_page = vm_normal_page(vma, address, orig_pte);
 	if (!old_page)
 		goto gotten;
 
-	if (unlikely((vma->vm_flags & (VM_SHARED|VM_WRITE)) ==
-				(VM_SHARED|VM_WRITE))) {
+	/*
+	 * Take out anonymous pages first, anonymous shared vmas are
+	 * not dirty accountable.
+	 */
+	if (PageAnon(old_page)) {
+		if (!TestSetPageLocked(old_page)) {
+			reuse = can_share_swap_page(old_page);
+			unlock_page(old_page);
+		}
+	} else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) ==
+					(VM_WRITE|VM_SHARED))) {
+		/*
+		 * Only catch write-faults on shared writable pages,
+		 * read-only shared pages can get COWed by
+		 * get_user_pages(.write=1, .force=1).
+		 */
 		if (vma->vm_ops && vma->vm_ops->page_mkwrite) {
 			/*
 			 * Notify the address space that the page is about to
@@ -1494,13 +1524,9 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			if (!pte_same(*page_table, orig_pte))
 				goto unlock;
 		}
-
+		dirty_page = old_page;
+		get_page(dirty_page);
 		reuse = 1;
-	} else if (PageAnon(old_page) && !TestSetPageLocked(old_page)) {
-		reuse = can_share_swap_page(old_page);
-		unlock_page(old_page);
-	} else {
-		reuse = 0;
 	}
 
 	if (reuse) {
@@ -1566,6 +1592,10 @@ gotten:
 		page_cache_release(old_page);
 unlock:
 	pte_unmap_unlock(page_table, ptl);
+	if (dirty_page) {
+		set_page_dirty_balance(dirty_page);
+		put_page(dirty_page);
+	}
 	return ret;
 oom: