Merge branch 'master' into upstream

11 files changed, 1136 insertions, 200 deletions

diff --git a/mm/memory.c b/mm/memory.c
index 92a3ebd8d79..601159a46ab 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2256,6 +2256,54 @@ oom:
 }
 
 /*
+ * do_no_pfn() tries to create a new page mapping for a page without
+ * a struct_page backing it
+ *
+ * As this is called only for pages that do not currently exist, we
+ * do not need to flush old virtual caches or the TLB.
+ *
+ * We enter with non-exclusive mmap_sem (to exclude vma changes,
+ * but allow concurrent faults), and pte mapped but not yet locked.
+ * We return with mmap_sem still held, but pte unmapped and unlocked.
+ *
+ * It is expected that the ->nopfn handler always returns the same pfn
+ * for a given virtual mapping.
+ *
+ * Mark this `noinline' to prevent it from bloating the main pagefault code.
+ */
+static noinline int do_no_pfn(struct mm_struct *mm, struct vm_area_struct *vma,
+		     unsigned long address, pte_t *page_table, pmd_t *pmd,
+		     int write_access)
+{
+	spinlock_t *ptl;
+	pte_t entry;
+	unsigned long pfn;
+	int ret = VM_FAULT_MINOR;
+
+	pte_unmap(page_table);
+	BUG_ON(!(vma->vm_flags & VM_PFNMAP));
+	BUG_ON(is_cow_mapping(vma->vm_flags));
+
+	pfn = vma->vm_ops->nopfn(vma, address & PAGE_MASK);
+	if (pfn == NOPFN_OOM)
+		return VM_FAULT_OOM;
+	if (pfn == NOPFN_SIGBUS)
+		return VM_FAULT_SIGBUS;
+
+	page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
+
+	/* Only go through if we didn't race with anybody else... */
+	if (pte_none(*page_table)) {
+		entry = pfn_pte(pfn, vma->vm_page_prot);
+		if (write_access)
+			entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+		set_pte_at(mm, address, page_table, entry);
+	}
+	pte_unmap_unlock(page_table, ptl);
+	return ret;
+}
+
+/*
  * Fault of a previously existing named mapping. Repopulate the pte
  * from the encoded file_pte if possible. This enables swappable
  * nonlinear vmas.
@@ -2317,11 +2365,17 @@ static inline int handle_pte_fault(struct mm_struct *mm,
 	old_entry = entry = *pte;
 	if (!pte_present(entry)) {
 		if (pte_none(entry)) {
-			if (!vma->vm_ops || !vma->vm_ops->nopage)
-				return do_anonymous_page(mm, vma, address,
-					pte, pmd, write_access);
-			return do_no_page(mm, vma, address,
-					pte, pmd, write_access);
+			if (vma->vm_ops) {
+				if (vma->vm_ops->nopage)
+					return do_no_page(mm, vma, address,
+							  pte, pmd,
+							  write_access);
+				if (unlikely(vma->vm_ops->nopfn))
+					return do_no_pfn(mm, vma, address, pte,
+							 pmd, write_access);
+			}
+			return do_anonymous_page(mm, vma, address,
+						 pte, pmd, write_access);
 		}
 		if (pte_file(entry))
 			return do_file_page(mm, vma, address,
@@ -2550,3 +2604,56 @@ int in_gate_area_no_task(unsigned long addr)
 }
 
 #endif	/* __HAVE_ARCH_GATE_AREA */
+
+/*
+ * Access another process' address space.
+ * Source/target buffer must be kernel space,
+ * Do not walk the page table directly, use get_user_pages
+ */
+int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write)
+{
+	struct mm_struct *mm;
+	struct vm_area_struct *vma;
+	struct page *page;
+	void *old_buf = buf;
+
+	mm = get_task_mm(tsk);
+	if (!mm)
+		return 0;
+
+	down_read(&mm->mmap_sem);
+	/* ignore errors, just check how much was sucessfully transfered */
+	while (len) {
+		int bytes, ret, offset;
+		void *maddr;
+
+		ret = get_user_pages(tsk, mm, addr, 1,
+				write, 1, &page, &vma);
+		if (ret <= 0)
+			break;
+
+		bytes = len;
+		offset = addr & (PAGE_SIZE-1);
+		if (bytes > PAGE_SIZE-offset)
+			bytes = PAGE_SIZE-offset;
+
+		maddr = kmap(page);
+		if (write) {
+			copy_to_user_page(vma, page, addr,
+					  maddr + offset, buf, bytes);
+			set_page_dirty_lock(page);
+		} else {
+			copy_from_user_page(vma, page, addr,
+					    buf, maddr + offset, bytes);
+		}
+		kunmap(page);
+		page_cache_release(page);
+		len -= bytes;
+		buf += bytes;
+		addr += bytes;
+	}
+	up_read(&mm->mmap_sem);
+	mmput(mm);
+
+	return buf - old_buf;
+}
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 38f89650bc8..cf18f094255 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1136,7 +1136,9 @@ static unsigned interleave_nodes(struct mempolicy *policy)
  */
 unsigned slab_node(struct mempolicy *policy)
 {
-	switch (policy->policy) {
+	int pol = policy ? policy->policy : MPOL_DEFAULT;
+
+	switch (pol) {
 	case MPOL_INTERLEAVE:
 		return interleave_nodes(policy);
 
diff --git a/mm/nommu.c b/mm/nommu.c
index d99dea31e44..56454066219 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -122,26 +122,50 @@ unsigned int kobjsize(const void *objp)
 }
 
 /*
- * The nommu dodgy version :-)
+ * get a list of pages in an address range belonging to the specified process
+ * and indicate the VMA that covers each page
+ * - this is potentially dodgy as we may end incrementing the page count of a
+ *   slab page or a secondary page from a compound page
+ * - don't permit access to VMAs that don't support it, such as I/O mappings
  */
 int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 	unsigned long start, int len, int write, int force,
 	struct page **pages, struct vm_area_struct **vmas)
 {
+	struct vm_area_struct *vma;
+	unsigned long vm_flags;
 	int i;
-	static struct vm_area_struct dummy_vma;
+
+	/* calculate required read or write permissions.
+	 * - if 'force' is set, we only require the "MAY" flags.
+	 */
+	vm_flags  = write ? (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD);
+	vm_flags &= force ? (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE);
 
 	for (i = 0; i < len; i++) {
+		vma = find_vma(mm, start);
+		if (!vma)
+			goto finish_or_fault;
+
+		/* protect what we can, including chardevs */
+		if (vma->vm_flags & (VM_IO | VM_PFNMAP) ||
+		    !(vm_flags & vma->vm_flags))
+			goto finish_or_fault;
+
 		if (pages) {
 			pages[i] = virt_to_page(start);
 			if (pages[i])
 				page_cache_get(pages[i]);
 		}
 		if (vmas)
-			vmas[i] = &dummy_vma;
+			vmas[i] = vma;
 		start += PAGE_SIZE;
 	}
-	return(i);
+
+	return i;
+
+finish_or_fault:
+	return i ? : -EFAULT;
 }
 
 EXPORT_SYMBOL(get_user_pages);
@@ -286,6 +310,77 @@ static void show_process_blocks(void)
 }
 #endif /* DEBUG */
 
+/*
+ * add a VMA into a process's mm_struct in the appropriate place in the list
+ * - should be called with mm->mmap_sem held writelocked
+ */
+static void add_vma_to_mm(struct mm_struct *mm, struct vm_list_struct *vml)
+{
+	struct vm_list_struct **ppv;
+
+	for (ppv = &current->mm->context.vmlist; *ppv; ppv = &(*ppv)->next)
+		if ((*ppv)->vma->vm_start > vml->vma->vm_start)
+			break;
+
+	vml->next = *ppv;
+	*ppv = vml;
+}
+
+/*
+ * look up the first VMA in which addr resides, NULL if none
+ * - should be called with mm->mmap_sem at least held readlocked
+ */
+struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
+{
+	struct vm_list_struct *loop, *vml;
+
+	/* search the vm_start ordered list */
+	vml = NULL;
+	for (loop = mm->context.vmlist; loop; loop = loop->next) {
+		if (loop->vma->vm_start > addr)
+			break;
+		vml = loop;
+	}
+
+	if (vml && vml->vma->vm_end > addr)
+		return vml->vma;
+
+	return NULL;
+}
+EXPORT_SYMBOL(find_vma);
+
+/*
+ * find a VMA
+ * - we don't extend stack VMAs under NOMMU conditions
+ */
+struct vm_area_struct *find_extend_vma(struct mm_struct *mm, unsigned long addr)
+{
+	return find_vma(mm, addr);
+}
+
+/*
+ * look up the first VMA exactly that exactly matches addr
+ * - should be called with mm->mmap_sem at least held readlocked
+ */
+static inline struct vm_area_struct *find_vma_exact(struct mm_struct *mm,
+						    unsigned long addr)
+{
+	struct vm_list_struct *vml;
+
+	/* search the vm_start ordered list */
+	for (vml = mm->context.vmlist; vml; vml = vml->next) {
+		if (vml->vma->vm_start == addr)
+			return vml->vma;
+		if (vml->vma->vm_start > addr)
+			break;
+	}
+
+	return NULL;
+}
+
+/*
+ * find a VMA in the global tree
+ */
 static inline struct vm_area_struct *find_nommu_vma(unsigned long start)
 {
 	struct vm_area_struct *vma;
@@ -305,6 +400,9 @@ static inline struct vm_area_struct *find_nommu_vma(unsigned long start)
 	return NULL;
 }
 
+/*
+ * add a VMA in the global tree
+ */
 static void add_nommu_vma(struct vm_area_struct *vma)
 {
 	struct vm_area_struct *pvma;
@@ -351,6 +449,9 @@ static void add_nommu_vma(struct vm_area_struct *vma)
 	rb_insert_color(&vma->vm_rb, &nommu_vma_tree);
 }
 
+/*
+ * delete a VMA from the global list
+ */
 static void delete_nommu_vma(struct vm_area_struct *vma)
 {
 	struct address_space *mapping;
@@ -828,8 +929,7 @@ unsigned long do_mmap_pgoff(struct file *file,
 	realalloc += kobjsize(vml);
 	askedalloc += sizeof(*vml);
 
-	vml->next = current->mm->context.vmlist;
-	current->mm->context.vmlist = vml;
+	add_vma_to_mm(current->mm, vml);
 
 	up_write(&nommu_vma_sem);
 
@@ -908,6 +1008,11 @@ static void put_vma(struct vm_area_struct *vma)
 	}
 }
 
+/*
+ * release a mapping
+ * - under NOMMU conditions the parameters must match exactly to the mapping to
+ *   be removed
+ */
 int do_munmap(struct mm_struct *mm, unsigned long addr, size_t len)
 {
 	struct vm_list_struct *vml, **parent;
@@ -917,10 +1022,13 @@ int do_munmap(struct mm_struct *mm, unsigned long addr, size_t len)
 	printk("do_munmap:\n");
 #endif
 
-	for (parent = &mm->context.vmlist; *parent; parent = &(*parent)->next)
+	for (parent = &mm->context.vmlist; *parent; parent = &(*parent)->next) {
+		if ((*parent)->vma->vm_start > addr)
+			break;
 		if ((*parent)->vma->vm_start == addr &&
 		    ((len == 0) || ((*parent)->vma->vm_end == end)))
 			goto found;
+	}
 
 	printk("munmap of non-mmaped memory by process %d (%s): %p\n",
 	       current->pid, current->comm, (void *) addr);
@@ -946,7 +1054,20 @@ int do_munmap(struct mm_struct *mm, unsigned long addr, size_t len)
 	return 0;
 }
 
-/* Release all mmaps. */
+asmlinkage long sys_munmap(unsigned long addr, size_t len)
+{
+	int ret;
+	struct mm_struct *mm = current->mm;
+
+	down_write(&mm->mmap_sem);
+	ret = do_munmap(mm, addr, len);
+	up_write(&mm->mmap_sem);
+	return ret;
+}
+
+/*
+ * Release all mappings
+ */
 void exit_mmap(struct mm_struct * mm)
 {
 	struct vm_list_struct *tmp;
@@ -973,37 +1094,26 @@ void exit_mmap(struct mm_struct * mm)
 	}
 }
 
-asmlinkage long sys_munmap(unsigned long addr, size_t len)
-{
-	int ret;
-	struct mm_struct *mm = current->mm;
-
-	down_write(&mm->mmap_sem);
-	ret = do_munmap(mm, addr, len);
-	up_write(&mm->mmap_sem);
-	return ret;
-}
-
 unsigned long do_brk(unsigned long addr, unsigned long len)
 {
 	return -ENOMEM;
 }
 
 /*
- * Expand (or shrink) an existing mapping, potentially moving it at the
- * same time (controlled by the MREMAP_MAYMOVE flag and available VM space)
+ * expand (or shrink) an existing mapping, potentially moving it at the same
+ * time (controlled by the MREMAP_MAYMOVE flag and available VM space)
  *
- * MREMAP_FIXED option added 5-Dec-1999 by Benjamin LaHaise
- * This option implies MREMAP_MAYMOVE.
+ * under NOMMU conditions, we only permit changing a mapping's size, and only
+ * as long as it stays within the hole allocated by the kmalloc() call in
+ * do_mmap_pgoff() and the block is not shareable
  *
- * on uClinux, we only permit changing a mapping's size, and only as long as it stays within the
- * hole allocated by the kmalloc() call in do_mmap_pgoff() and the block is not shareable
+ * MREMAP_FIXED is not supported under NOMMU conditions
  */
 unsigned long do_mremap(unsigned long addr,
 			unsigned long old_len, unsigned long new_len,
 			unsigned long flags, unsigned long new_addr)
 {
-	struct vm_list_struct *vml = NULL;
+	struct vm_area_struct *vma;
 
 	/* insanity checks first */
 	if (new_len == 0)
@@ -1012,58 +1122,46 @@ unsigned long do_mremap(unsigned long addr,
 	if (flags & MREMAP_FIXED && new_addr != addr)
 		return (unsigned long) -EINVAL;
 
-	for (vml = current->mm->context.vmlist; vml; vml = vml->next)
-		if (vml->vma->vm_start == addr)
-			goto found;
-
-	return (unsigned long) -EINVAL;
+	vma = find_vma_exact(current->mm, addr);
+	if (!vma)
+		return (unsigned long) -EINVAL;
 
- found:
-	if (vml->vma->vm_end != vml->vma->vm_start + old_len)
+	if (vma->vm_end != vma->vm_start + old_len)
 		return (unsigned long) -EFAULT;
 
-	if (vml->vma->vm_flags & VM_MAYSHARE)
+	if (vma->vm_flags & VM_MAYSHARE)
 		return (unsigned long) -EPERM;
 
 	if (new_len > kobjsize((void *) addr))
 		return (unsigned long) -ENOMEM;
 
 	/* all checks complete - do it */
-	vml->vma->vm_end = vml->vma->vm_start + new_len;
+	vma->vm_end = vma->vm_start + new_len;
 
 	askedalloc -= old_len;
 	askedalloc += new_len;
 
-	return vml->vma->vm_start;
+	return vma->vm_start;
 }
 
-/*
- * Look up the first VMA which satisfies  addr < vm_end,  NULL if none
- */
-struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
+asmlinkage unsigned long sys_mremap(unsigned long addr,
+	unsigned long old_len, unsigned long new_len,
+	unsigned long flags, unsigned long new_addr)
 {
-	struct vm_list_struct *vml;
-
-	for (vml = mm->context.vmlist; vml; vml = vml->next)
-		if (addr >= vml->vma->vm_start && addr < vml->vma->vm_end)
-			return vml->vma;
+	unsigned long ret;
 
-	return NULL;
+	down_write(&current->mm->mmap_sem);
+	ret = do_mremap(addr, old_len, new_len, flags, new_addr);
+	up_write(&current->mm->mmap_sem);
+	return ret;
 }
 
-EXPORT_SYMBOL(find_vma);
-
 struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
 			unsigned int foll_flags)
 {
 	return NULL;
 }
 
-struct vm_area_struct *find_extend_vma(struct mm_struct *mm, unsigned long addr)
-{
-	return NULL;
-}
-
 int remap_pfn_range(struct vm_area_struct *vma, unsigned long from,
 		unsigned long to, unsigned long size, pgprot_t prot)
 {
@@ -1206,3 +1304,44 @@ struct page *filemap_nopage(struct vm_area_struct *area,
 	BUG();
 	return NULL;
 }
+
+/*
+ * Access another process' address space.
+ * - source/target buffer must be kernel space
+ */
+int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write)
+{
+	struct vm_area_struct *vma;
+	struct mm_struct *mm;
+
+	if (addr + len < addr)
+		return 0;
+
+	mm = get_task_mm(tsk);
+	if (!mm)
+		return 0;
+
+	down_read(&mm->mmap_sem);
+
+	/* the access must start within one of the target process's mappings */
+	vma = find_vma(mm, addr);
+	if (vma) {
+		/* don't overrun this mapping */
+		if (addr + len >= vma->vm_end)
+			len = vma->vm_end - addr;
+
+		/* only read or write mappings where it is permitted */
+		if (write && vma->vm_flags & VM_MAYWRITE)
+			len -= copy_to_user((void *) addr, buf, len);
+		else if (!write && vma->vm_flags & VM_MAYREAD)
+			len -= copy_from_user(buf, (void *) addr, len);
+		else
+			len = 0;
+	} else {
+		len = 0;
+	}
+
+	up_read(&mm->mmap_sem);
+	mmput(mm);
+	return len;
+}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 9810f0a60db..4f59d90b81e 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -37,6 +37,8 @@
 #include <linux/vmalloc.h>
 #include <linux/mempolicy.h>
 #include <linux/stop_machine.h>
+#include <linux/sort.h>
+#include <linux/pfn.h>
 
 #include <asm/tlbflush.h>
 #include <asm/div64.h>
@@ -102,6 +104,38 @@ int min_free_kbytes = 1024;
 
 unsigned long __meminitdata nr_kernel_pages;
 unsigned long __meminitdata nr_all_pages;
+static unsigned long __initdata dma_reserve;
+
+#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
+  /*
+   * MAX_ACTIVE_REGIONS determines the maxmimum number of distinct
+   * ranges of memory (RAM) that may be registered with add_active_range().
+   * Ranges passed to add_active_range() will be merged if possible
+   * so the number of times add_active_range() can be called is
+   * related to the number of nodes and the number of holes
+   */
+  #ifdef CONFIG_MAX_ACTIVE_REGIONS
+    /* Allow an architecture to set MAX_ACTIVE_REGIONS to save memory */
+    #define MAX_ACTIVE_REGIONS CONFIG_MAX_ACTIVE_REGIONS
+  #else
+    #if MAX_NUMNODES >= 32
+      /* If there can be many nodes, allow up to 50 holes per node */
+      #define MAX_ACTIVE_REGIONS (MAX_NUMNODES*50)
+    #else
+      /* By default, allow up to 256 distinct regions */
+      #define MAX_ACTIVE_REGIONS 256
+    #endif
+  #endif
+
+  struct node_active_region __initdata early_node_map[MAX_ACTIVE_REGIONS];
+  int __initdata nr_nodemap_entries;
+  unsigned long __initdata arch_zone_lowest_possible_pfn[MAX_NR_ZONES];
+  unsigned long __initdata arch_zone_highest_possible_pfn[MAX_NR_ZONES];
+#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE
+  unsigned long __initdata node_boundary_start_pfn[MAX_NUMNODES];
+  unsigned long __initdata node_boundary_end_pfn[MAX_NUMNODES];
+#endif /* CONFIG_MEMORY_HOTPLUG_RESERVE */
+#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */
 
 #ifdef CONFIG_DEBUG_VM
 static int page_outside_zone_boundaries(struct zone *zone, struct page *page)
@@ -908,7 +942,7 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order,
 	 */
 	do {
 		zone = *z;
-		if (unlikely((gfp_mask & __GFP_THISNODE) &&
+		if (unlikely(NUMA_BUILD && (gfp_mask & __GFP_THISNODE) &&
 			zone->zone_pgdat != zonelist->zones[0]->zone_pgdat))
 				break;
 		if ((alloc_flags & ALLOC_CPUSET) &&
@@ -1222,14 +1256,12 @@ unsigned int nr_free_pagecache_pages(void)
 {
 	return nr_free_zone_pages(gfp_zone(GFP_HIGHUSER));
 }
-#ifdef CONFIG_NUMA
-static void show_node(struct zone *zone)
+
+static inline void show_node(struct zone *zone)
 {
-	printk("Node %ld ", zone_to_nid(zone));
+	if (NUMA_BUILD)
+		printk("Node %ld ", zone_to_nid(zone));
 }
-#else
-#define show_node(zone)	do { } while (0)
-#endif
 
 void si_meminfo(struct sysinfo *val)
 {
@@ -1271,34 +1303,30 @@ void si_meminfo_node(struct sysinfo *val, int nid)
  */
 void show_free_areas(void)
 {
-	int cpu, temperature;
+	int cpu;
 	unsigned long active;
 	unsigned long inactive;
 	unsigned long free;
 	struct zone *zone;
 
 	for_each_zone(zone) {
-		show_node(zone);
-		printk("%s per-cpu:", zone->name);
-
-		if (!populated_zone(zone)) {
-			printk(" empty\n");
+		if (!populated_zone(zone))
 			continue;
-		} else
-			printk("\n");
+
+		show_node(zone);
+		printk("%s per-cpu:\n", zone->name);
 
 		for_each_online_cpu(cpu) {
 			struct per_cpu_pageset *pageset;
 
 			pageset = zone_pcp(zone, cpu);
 
-			for (temperature = 0; temperature < 2; temperature++)
-				printk("cpu %d %s: high %d, batch %d used:%d\n",
-					cpu,
-					temperature ? "cold" : "hot",
-					pageset->pcp[temperature].high,
-					pageset->pcp[temperature].batch,
-					pageset->pcp[temperature].count);
+			printk("CPU %4d: Hot: hi:%5d, btch:%4d usd:%4d   "
+			       "Cold: hi:%5d, btch:%4d usd:%4d\n",
+			       cpu, pageset->pcp[0].high,
+			       pageset->pcp[0].batch, pageset->pcp[0].count,
+			       pageset->pcp[1].high, pageset->pcp[1].batch,
+			       pageset->pcp[1].count);
 		}
 	}
 
@@ -1320,6 +1348,9 @@ void show_free_areas(void)
 	for_each_zone(zone) {
 		int i;
 
+		if (!populated_zone(zone))
+			continue;
+
 		show_node(zone);
 		printk("%s"
 			" free:%lukB"
@@ -1352,12 +1383,11 @@ void show_free_areas(void)
 	for_each_zone(zone) {
  		unsigned long nr[MAX_ORDER], flags, order, total = 0;
 
+		if (!populated_zone(zone))
+			continue;
+
 		show_node(zone);
 		printk("%s: ", zone->name);
-		if (!populated_zone(zone)) {
-			printk("empty\n");
-			continue;
-		}
 
 		spin_lock_irqsave(&zone->lock, flags);
 		for (order = 0; order < MAX_ORDER; order++) {
@@ -1561,7 +1591,7 @@ static int __meminit __build_all_zonelists(void *dummy)
 void __meminit build_all_zonelists(void)
 {
 	if (system_state == SYSTEM_BOOTING) {
-		__build_all_zonelists(0);
+		__build_all_zonelists(NULL);
 		cpuset_init_current_mems_allowed();
 	} else {
 		/* we have to stop all cpus to guaranntee there is no user
@@ -1642,25 +1672,6 @@ static inline unsigned long wait_table_bits(unsigned long size)
 
 #define LONG_ALIGN(x) (((x)+(sizeof(long))-1)&~((sizeof(long))-1))
 
-static void __init calculate_zone_totalpages(struct pglist_data *pgdat,
-		unsigned long *zones_size, unsigned long *zholes_size)
-{
-	unsigned long realtotalpages, totalpages = 0;
-	enum zone_type i;
-
-	for (i = 0; i < MAX_NR_ZONES; i++)
-		totalpages += zones_size[i];
-	pgdat->node_spanned_pages = totalpages;
-
-	realtotalpages = totalpages;
-	if (zholes_size)
-		for (i = 0; i < MAX_NR_ZONES; i++)
-			realtotalpages -= zholes_size[i];
-	pgdat->node_present_pages = realtotalpages;
-	printk(KERN_DEBUG "On node %d totalpages: %lu\n", pgdat->node_id, realtotalpages);
-}
-
-
 /*
  * Initially all pages are reserved - free ones are freed
  * up by free_all_bootmem() once the early boot process is
@@ -1818,6 +1829,9 @@ static int __cpuinit process_zones(int cpu)
 
 	for_each_zone(zone) {
 
+		if (!populated_zone(zone))
+			continue;
+
 		zone_pcp(zone, cpu) = kmalloc_node(sizeof(struct per_cpu_pageset),
 					 GFP_KERNEL, cpu_to_node(cpu));
 		if (!zone_pcp(zone, cpu))
@@ -1977,6 +1991,366 @@ __meminit int init_currently_empty_zone(struct zone *zone,
 	return 0;
 }
 
+#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
+/*
+ * Basic iterator support. Return the first range of PFNs for a node
+ * Note: nid == MAX_NUMNODES returns first region regardless of node
+ */
+static int __init first_active_region_index_in_nid(int nid)
+{
+	int i;
+
+	for (i = 0; i < nr_nodemap_entries; i++)
+		if (nid == MAX_NUMNODES || early_node_map[i].nid == nid)
+			return i;
+
+	return -1;
+}
+
+/*
+ * Basic iterator support. Return the next active range of PFNs for a node
+ * Note: nid == MAX_NUMNODES returns next region regardles of node
+ */
+static int __init next_active_region_index_in_nid(int index, int nid)
+{
+	for (index = index + 1; index < nr_nodemap_entries; index++)
+		if (nid == MAX_NUMNODES || early_node_map[index].nid == nid)
+			return index;
+
+	return -1;
+}
+
+#ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID
+/*
+ * Required by SPARSEMEM. Given a PFN, return what node the PFN is on.
+ * Architectures may implement their own version but if add_active_range()
+ * was used and there are no special requirements, this is a convenient
+ * alternative
+ */
+int __init early_pfn_to_nid(unsigned long pfn)
+{
+	int i;
+
+	for (i = 0; i < nr_nodemap_entries; i++) {
+		unsigned long start_pfn = early_node_map[i].start_pfn;
+		unsigned long end_pfn = early_node_map[i].end_pfn;
+
+		if (start_pfn <= pfn && pfn < end_pfn)
+			return early_node_map[i].nid;
+	}
+
+	return 0;
+}
+#endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */
+
+/* Basic iterator support to walk early_node_map[] */
+#define for_each_active_range_index_in_nid(i, nid) \
+	for (i = first_active_region_index_in_nid(nid); i != -1; \
+				i = next_active_region_index_in_nid(i, nid))
+
+/**
+ * free_bootmem_with_active_regions - Call free_bootmem_node for each active range
+ * @nid: The node to free memory on. If MAX_NUMNODES, all nodes are freed
+ * @max_low_pfn: The highest PFN that till be passed to free_bootmem_node
+ *
+ * If an architecture guarantees that all ranges registered with
+ * add_active_ranges() contain no holes and may be freed, this
+ * this function may be used instead of calling free_bootmem() manually.
+ */
+void __init free_bootmem_with_active_regions(int nid,
+						unsigned long max_low_pfn)
+{
+	int i;
+
+	for_each_active_range_index_in_nid(i, nid) {
+		unsigned long size_pages = 0;
+		unsigned long end_pfn = early_node_map[i].end_pfn;
+
+		if (early_node_map[i].start_pfn >= max_low_pfn)
+			continue;
+
+		if (end_pfn > max_low_pfn)
+			end_pfn = max_low_pfn;
+
+		size_pages = end_pfn - early_node_map[i].start_pfn;
+		free_bootmem_node(NODE_DATA(early_node_map[i].nid),
+				PFN_PHYS(early_node_map[i].start_pfn),
+				size_pages << PAGE_SHIFT);
+	}
+}
+
+/**
+ * sparse_memory_present_with_active_regions - Call memory_present for each active range
+ * @nid: The node to call memory_present for. If MAX_NUMNODES, all nodes will be used
+ *
+ * If an architecture guarantees that all ranges registered with
+ * add_active_ranges() contain no holes and may be freed, this
+ * this function may be used instead of calling memory_present() manually.
+ */
+void __init sparse_memory_present_with_active_regions(int nid)
+{
+	int i;
+
+	for_each_active_range_index_in_nid(i, nid)
+		memory_present(early_node_map[i].nid,
+				early_node_map[i].start_pfn,
+				early_node_map[i].end_pfn);
+}
+
+/**
+ * push_node_boundaries - Push node boundaries to at least the requested boundary
+ * @nid: The nid of the node to push the boundary for
+ * @start_pfn: The start pfn of the node
+ * @end_pfn: The end pfn of the node
+ *
+ * In reserve-based hot-add, mem_map is allocated that is unused until hotadd
+ * time. Specifically, on x86_64, SRAT will report ranges that can potentially
+ * be hotplugged even though no physical memory exists. This function allows
+ * an arch to push out the node boundaries so mem_map is allocated that can
+ * be used later.
+ */
+#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE
+void __init push_node_boundaries(unsigned int nid,
+		unsigned long start_pfn, unsigned long end_pfn)
+{
+	printk(KERN_DEBUG "Entering push_node_boundaries(%u, %lu, %lu)\n",
+			nid, start_pfn, end_pfn);
+
+	/* Initialise the boundary for this node if necessary */
+	if (node_boundary_end_pfn[nid] == 0)
+		node_boundary_start_pfn[nid] = -1UL;
+
+	/* Update the boundaries */
+	if (node_boundary_start_pfn[nid] > start_pfn)
+		node_boundary_start_pfn[nid] = start_pfn;
+	if (node_boundary_end_pfn[nid] < end_pfn)
+		node_boundary_end_pfn[nid] = end_pfn;
+}
+
+/* If necessary, push the node boundary out for reserve hotadd */
+static void __init account_node_boundary(unsigned int nid,
+		unsigned long *start_pfn, unsigned long *end_pfn)
+{
+	printk(KERN_DEBUG "Entering account_node_boundary(%u, %lu, %lu)\n",
+			nid, *start_pfn, *end_pfn);
+
+	/* Return if boundary information has not been provided */
+	if (node_boundary_end_pfn[nid] == 0)
+		return;
+
+	/* Check the boundaries and update if necessary */
+	if (node_boundary_start_pfn[nid] < *start_pfn)
+		*start_pfn = node_boundary_start_pfn[nid];
+	if (node_boundary_end_pfn[nid] > *end_pfn)
+		*end_pfn = node_boundary_end_pfn[nid];
+}
+#else
+void __init push_node_boundaries(unsigned int nid,
+		unsigned long start_pfn, unsigned long end_pfn) {}
+
+static void __init account_node_boundary(unsigned int nid,
+		unsigned long *start_pfn, unsigned long *end_pfn) {}
+#endif
+
+
+/**
+ * get_pfn_range_for_nid - Return the start and end page frames for a node
+ * @nid: The nid to return the range for. If MAX_NUMNODES, the min and max PFN are returned
+ * @start_pfn: Passed by reference. On return, it will have the node start_pfn
+ * @end_pfn: Passed by reference. On return, it will have the node end_pfn
+ *
+ * It returns the start and end page frame of a node based on information
+ * provided by an arch calling add_active_range(). If called for a node
+ * with no available memory, a warning is printed and the start and end
+ * PFNs will be 0
+ */
+void __init get_pfn_range_for_nid(unsigned int nid,
+			unsigned long *start_pfn, unsigned long *end_pfn)
+{
+	int i;
+	*start_pfn = -1UL;
+	*end_pfn = 0;
+
+	for_each_active_range_index_in_nid(i, nid) {
+		*start_pfn = min(*start_pfn, early_node_map[i].start_pfn);
+		*end_pfn = max(*end_pfn, early_node_map[i].end_pfn);
+	}
+
+	if (*start_pfn == -1UL) {
+		printk(KERN_WARNING "Node %u active with no memory\n", nid);
+		*start_pfn = 0;
+	}
+
+	/* Push the node boundaries out if requested */
+	account_node_boundary(nid, start_pfn, end_pfn);
+}
+
+/*
+ * Return the number of pages a zone spans in a node, including holes
+ * present_pages = zone_spanned_pages_in_node() - zone_absent_pages_in_node()
+ */
+unsigned long __init zone_spanned_pages_in_node(int nid,
+					unsigned long zone_type,
+					unsigned long *ignored)
+{
+	unsigned long node_start_pfn, node_end_pfn;
+	unsigned long zone_start_pfn, zone_end_pfn;
+
+	/* Get the start and end of the node and zone */
+	get_pfn_range_for_nid(nid, &node_start_pfn, &node_end_pfn);
+	zone_start_pfn = arch_zone_lowest_possible_pfn[zone_type];
+	zone_end_pfn = arch_zone_highest_possible_pfn[zone_type];
+
+	/* Check that this node has pages within the zone's required range */
+	if (zone_end_pfn < node_start_pfn || zone_start_pfn > node_end_pfn)
+		return 0;
+
+	/* Move the zone boundaries inside the node if necessary */
+	zone_end_pfn = min(zone_end_pfn, node_end_pfn);
+	zone_start_pfn = max(zone_start_pfn, node_start_pfn);
+
+	/* Return the spanned pages */
+	return zone_end_pfn - zone_start_pfn;
+}
+
+/*
+ * Return the number of holes in a range on a node. If nid is MAX_NUMNODES,
+ * then all holes in the requested range will be accounted for
+ */
+unsigned long __init __absent_pages_in_range(int nid,
+				unsigned long range_start_pfn,
+				unsigned long range_end_pfn)
+{
+	int i = 0;
+	unsigned long prev_end_pfn = 0, hole_pages = 0;
+	unsigned long start_pfn;
+
+	/* Find the end_pfn of the first active range of pfns in the node */
+	i = first_active_region_index_in_nid(nid);
+	if (i == -1)
+		return 0;
+
+	/* Account for ranges before physical memory on this node */
+	if (early_node_map[i].start_pfn > range_start_pfn)
+		hole_pages = early_node_map[i].start_pfn - range_start_pfn;
+
+	prev_end_pfn = early_node_map[i].start_pfn;
+
+	/* Find all holes for the zone within the node */
+	for (; i != -1; i = next_active_region_index_in_nid(i, nid)) {
+
+		/* No need to continue if prev_end_pfn is outside the zone */
+		if (prev_end_pfn >= range_end_pfn)
+			break;
+
+		/* Make sure the end of the zone is not within the hole */
+		start_pfn = min(early_node_map[i].start_pfn, range_end_pfn);
+		prev_end_pfn = max(prev_end_pfn, range_start_pfn);
+
+		/* Update the hole size cound and move on */
+		if (start_pfn > range_start_pfn) {
+			BUG_ON(prev_end_pfn > start_pfn);
+			hole_pages += start_pfn - prev_end_pfn;
+		}
+		prev_end_pfn = early_node_map[i].end_pfn;
+	}
+
+	/* Account for ranges past physical memory on this node */
+	if (range_end_pfn > prev_end_pfn)
+		hole_pages = range_end_pfn -
+				max(range_start_pfn, prev_end_pfn);
+
+	return hole_pages;
+}
+
+/**
+ * absent_pages_in_range - Return number of page frames in holes within a range
+ * @start_pfn: The start PFN to start searching for holes
+ * @end_pfn: The end PFN to stop searching for holes
+ *
+ * It returns the number of pages frames in memory holes within a range
+ */
+unsigned long __init absent_pages_in_range(unsigned long start_pfn,
+							unsigned long end_pfn)
+{
+	return __absent_pages_in_range(MAX_NUMNODES, start_pfn, end_pfn);
+}
+
+/* Return the number of page frames in holes in a zone on a node */
+unsigned long __init zone_absent_pages_in_node(int nid,
+					unsigned long zone_type,
+					unsigned long *ignored)
+{
+	unsigned long node_start_pfn, node_end_pfn;
+	unsigned long zone_start_pfn, zone_end_pfn;
+
+	get_pfn_range_for_nid(nid, &node_start_pfn, &node_end_pfn);
+	zone_start_pfn = max(arch_zone_lowest_possible_pfn[zone_type],
+							node_start_pfn);
+	zone_end_pfn = min(arch_zone_highest_possible_pfn[zone_type],
+							node_end_pfn);
+
+	return __absent_pages_in_range(nid, zone_start_pfn, zone_end_pfn);
+}
+
+/* Return the zone index a PFN is in */
+int memmap_zone_idx(struct page *lmem_map)
+{
+	int i;
+	unsigned long phys_addr = virt_to_phys(lmem_map);
+	unsigned long pfn = phys_addr >> PAGE_SHIFT;
+
+	for (i = 0; i < MAX_NR_ZONES; i++)
+		if (pfn < arch_zone_highest_possible_pfn[i])
+			break;
+
+	return i;
+}
+#else
+static inline unsigned long zone_spanned_pages_in_node(int nid,
+					unsigned long zone_type,
+					unsigned long *zones_size)
+{
+	return zones_size[zone_type];
+}
+
+static inline unsigned long zone_absent_pages_in_node(int nid,
+						unsigned long zone_type,
+						unsigned long *zholes_size)
+{
+	if (!zholes_size)
+		return 0;
+
+	return zholes_size[zone_type];
+}
+
+static inline int memmap_zone_idx(struct page *lmem_map)
+{
+	return MAX_NR_ZONES;
+}
+#endif
+
+static void __init calculate_node_totalpages(struct pglist_data *pgdat,
+		unsigned long *zones_size, unsigned long *zholes_size)
+{
+	unsigned long realtotalpages, totalpages = 0;
+	enum zone_type i;
+
+	for (i = 0; i < MAX_NR_ZONES; i++)
+		totalpages += zone_spanned_pages_in_node(pgdat->node_id, i,
+								zones_size);
+	pgdat->node_spanned_pages = totalpages;
+
+	realtotalpages = totalpages;
+	for (i = 0; i < MAX_NR_ZONES; i++)
+		realtotalpages -=
+			zone_absent_pages_in_node(pgdat->node_id, i,
+								zholes_size);
+	pgdat->node_present_pages = realtotalpages;
+	printk(KERN_DEBUG "On node %d totalpages: %lu\n", pgdat->node_id,
+							realtotalpages);
+}
+
 /*
  * Set up the zone data structures:
  *   - mark all pages reserved
@@ -1998,11 +2372,34 @@ static void __meminit free_area_init_core(struct pglist_data *pgdat,
 	
 	for (j = 0; j < MAX_NR_ZONES; j++) {
 		struct zone *zone = pgdat->node_zones + j;
-		unsigned long size, realsize;
+		unsigned long size, realsize, memmap_pages;
 
-		realsize = size = zones_size[j];
-		if (zholes_size)
-			realsize -= zholes_size[j];
+		size = zone_spanned_pages_in_node(nid, j, zones_size);
+		realsize = size - zone_absent_pages_in_node(nid, j,
+								zholes_size);
+
+		/*
+		 * Adjust realsize so that it accounts for how much memory
+		 * is used by this zone for memmap. This affects the watermark
+		 * and per-cpu initialisations
+		 */
+		memmap_pages = (size * sizeof(struct page)) >> PAGE_SHIFT;
+		if (realsize >= memmap_pages) {
+			realsize -= memmap_pages;
+			printk(KERN_DEBUG
+				"  %s zone: %lu pages used for memmap\n",
+				zone_names[j], memmap_pages);
+		} else
+			printk(KERN_WARNING
+				"  %s zone: %lu pages exceeds realsize %lu\n",
+				zone_names[j], memmap_pages, realsize);
+
+		/* Account for reserved DMA pages */
+		if (j == ZONE_DMA && realsize > dma_reserve) {
+			realsize -= dma_reserve;
+			printk(KERN_DEBUG "  DMA zone: %lu pages reserved\n",
+								dma_reserve);
+		}
 
 		if (!is_highmem_idx(j))
 			nr_kernel_pages += realsize;
@@ -2011,6 +2408,7 @@ static void __meminit free_area_init_core(struct pglist_data *pgdat,
 		zone->spanned_pages = size;
 		zone->present_pages = realsize;
 #ifdef CONFIG_NUMA
+		zone->node = nid;
 		zone->min_unmapped_pages = (realsize*sysctl_min_unmapped_ratio)
 						/ 100;
 		zone->min_slab_pages = (realsize * sysctl_min_slab_ratio) / 100;
@@ -2073,8 +2471,13 @@ static void __init alloc_node_mem_map(struct pglist_data *pgdat)
 	/*
 	 * With no DISCONTIG, the global mem_map is just set as node 0's
 	 */
-	if (pgdat == NODE_DATA(0))
+	if (pgdat == NODE_DATA(0)) {
 		mem_map = NODE_DATA(0)->node_mem_map;
+#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
+		if (page_to_pfn(mem_map) != pgdat->node_start_pfn)
+			mem_map -= pgdat->node_start_pfn;
+#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */
+	}
 #endif
 #endif /* CONFIG_FLAT_NODE_MEM_MAP */
 }
@@ -2085,13 +2488,255 @@ void __meminit free_area_init_node(int nid, struct pglist_data *pgdat,
 {
 	pgdat->node_id = nid;
 	pgdat->node_start_pfn = node_start_pfn;
-	calculate_zone_totalpages(pgdat, zones_size, zholes_size);
+	calculate_node_totalpages(pgdat, zones_size, zholes_size);
 
 	alloc_node_mem_map(pgdat);
 
 	free_area_init_core(pgdat, zones_size, zholes_size);
 }
 
+#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
+/**
+ * add_active_range - Register a range of PFNs backed by physical memory
+ * @nid: The node ID the range resides on
+ * @start_pfn: The start PFN of the available physical memory
+ * @end_pfn: The end PFN of the available physical memory
+ *
+ * These ranges are stored in an early_node_map[] and later used by
+ * free_area_init_nodes() to calculate zone sizes and holes. If the
+ * range spans a memory hole, it is up to the architecture to ensure
+ * the memory is not freed by the bootmem allocator. If possible
+ * the range being registered will be merged with existing ranges.
+ */
+void __init add_active_range(unsigned int nid, unsigned long start_pfn,
+						unsigned long end_pfn)
+{
+	int i;
+
+	printk(KERN_DEBUG "Entering add_active_range(%d, %lu, %lu) "
+			  "%d entries of %d used\n",
+			  nid, start_pfn, end_pfn,
+			  nr_nodemap_entries, MAX_ACTIVE_REGIONS);
+
+	/* Merge with existing active regions if possible */
+	for (i = 0; i < nr_nodemap_entries; i++) {
+		if (early_node_map[i].nid != nid)
+			continue;
+
+		/* Skip if an existing region covers this new one */
+		if (start_pfn >= early_node_map[i].start_pfn &&
+				end_pfn <= early_node_map[i].end_pfn)
+			return;
+
+		/* Merge forward if suitable */
+		if (start_pfn <= early_node_map[i].end_pfn &&
+				end_pfn > early_node_map[i].end_pfn) {
+			early_node_map[i].end_pfn = end_pfn;
+			return;
+		}
+
+		/* Merge backward if suitable */
+		if (start_pfn < early_node_map[i].end_pfn &&
+				end_pfn >= early_node_map[i].start_pfn) {
+			early_node_map[i].start_pfn = start_pfn;
+			return;
+		}
+	}
+
+	/* Check that early_node_map is large enough */
+	if (i >= MAX_ACTIVE_REGIONS) {
+		printk(KERN_CRIT "More than %d memory regions, truncating\n",
+							MAX_ACTIVE_REGIONS);
+		return;
+	}
+
+	early_node_map[i].nid = nid;
+	early_node_map[i].start_pfn = start_pfn;
+	early_node_map[i].end_pfn = end_pfn;
+	nr_nodemap_entries = i + 1;
+}
+
+/**
+ * shrink_active_range - Shrink an existing registered range of PFNs
+ * @nid: The node id the range is on that should be shrunk
+ * @old_end_pfn: The old end PFN of the range
+ * @new_end_pfn: The new PFN of the range
+ *
+ * i386 with NUMA use alloc_remap() to store a node_mem_map on a local node.
+ * The map is kept at the end physical page range that has already been
+ * registered with add_active_range(). This function allows an arch to shrink
+ * an existing registered range.
+ */
+void __init shrink_active_range(unsigned int nid, unsigned long old_end_pfn,
+						unsigned long new_end_pfn)
+{
+	int i;
+
+	/* Find the old active region end and shrink */
+	for_each_active_range_index_in_nid(i, nid)
+		if (early_node_map[i].end_pfn == old_end_pfn) {
+			early_node_map[i].end_pfn = new_end_pfn;
+			break;
+		}
+}
+
+/**
+ * remove_all_active_ranges - Remove all currently registered regions
+ * During discovery, it may be found that a table like SRAT is invalid
+ * and an alternative discovery method must be used. This function removes
+ * all currently registered regions.
+ */
+void __init remove_all_active_ranges()
+{
+	memset(early_node_map, 0, sizeof(early_node_map));
+	nr_nodemap_entries = 0;
+#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE
+	memset(node_boundary_start_pfn, 0, sizeof(node_boundary_start_pfn));
+	memset(node_boundary_end_pfn, 0, sizeof(node_boundary_end_pfn));
+#endif /* CONFIG_MEMORY_HOTPLUG_RESERVE */
+}
+
+/* Compare two active node_active_regions */
+static int __init cmp_node_active_region(const void *a, const void *b)
+{
+	struct node_active_region *arange = (struct node_active_region *)a;
+	struct node_active_region *brange = (struct node_active_region *)b;
+
+	/* Done this way to avoid overflows */
+	if (arange->start_pfn > brange->start_pfn)
+		return 1;
+	if (arange->start_pfn < brange->start_pfn)
+		return -1;
+
+	return 0;
+}
+
+/* sort the node_map by start_pfn */
+static void __init sort_node_map(void)
+{
+	sort(early_node_map, (size_t)nr_nodemap_entries,
+			sizeof(struct node_active_region),
+			cmp_node_active_region, NULL);
+}
+
+/* Find the lowest pfn for a node. This depends on a sorted early_node_map */
+unsigned long __init find_min_pfn_for_node(unsigned long nid)
+{
+	int i;
+
+	/* Assuming a sorted map, the first range found has the starting pfn */
+	for_each_active_range_index_in_nid(i, nid)
+		return early_node_map[i].start_pfn;
+
+	printk(KERN_WARNING "Could not find start_pfn for node %lu\n", nid);
+	return 0;
+}
+
+/**
+ * find_min_pfn_with_active_regions - Find the minimum PFN registered
+ *
+ * It returns the minimum PFN based on information provided via
+ * add_active_range()
+ */
+unsigned long __init find_min_pfn_with_active_regions(void)
+{
+	return find_min_pfn_for_node(MAX_NUMNODES);
+}
+
+/**
+ * find_max_pfn_with_active_regions - Find the maximum PFN registered
+ *
+ * It returns the maximum PFN based on information provided via
+ * add_active_range()
+ */
+unsigned long __init find_max_pfn_with_active_regions(void)
+{
+	int i;
+	unsigned long max_pfn = 0;
+
+	for (i = 0; i < nr_nodemap_entries; i++)
+		max_pfn = max(max_pfn, early_node_map[i].end_pfn);
+
+	return max_pfn;
+}
+
+/**
+ * free_area_init_nodes - Initialise all pg_data_t and zone data
+ * @arch_max_dma_pfn: The maximum PFN usable for ZONE_DMA
+ * @arch_max_dma32_pfn: The maximum PFN usable for ZONE_DMA32
+ * @arch_max_low_pfn: The maximum PFN usable for ZONE_NORMAL
+ * @arch_max_high_pfn: The maximum PFN usable for ZONE_HIGHMEM
+ *
+ * This will call free_area_init_node() for each active node in the system.
+ * Using the page ranges provided by add_active_range(), the size of each
+ * zone in each node and their holes is calculated. If the maximum PFN
+ * between two adjacent zones match, it is assumed that the zone is empty.
+ * For example, if arch_max_dma_pfn == arch_max_dma32_pfn, it is assumed
+ * that arch_max_dma32_pfn has no pages. It is also assumed that a zone
+ * starts where the previous one ended. For example, ZONE_DMA32 starts
+ * at arch_max_dma_pfn.
+ */
+void __init free_area_init_nodes(unsigned long *max_zone_pfn)
+{
+	unsigned long nid;
+	enum zone_type i;
+
+	/* Record where the zone boundaries are */
+	memset(arch_zone_lowest_possible_pfn, 0,
+				sizeof(arch_zone_lowest_possible_pfn));
+	memset(arch_zone_highest_possible_pfn, 0,
+				sizeof(arch_zone_highest_possible_pfn));
+	arch_zone_lowest_possible_pfn[0] = find_min_pfn_with_active_regions();
+	arch_zone_highest_possible_pfn[0] = max_zone_pfn[0];
+	for (i = 1; i < MAX_NR_ZONES; i++) {
+		arch_zone_lowest_possible_pfn[i] =
+			arch_zone_highest_possible_pfn[i-1];
+		arch_zone_highest_possible_pfn[i] =
+			max(max_zone_pfn[i], arch_zone_lowest_possible_pfn[i]);
+	}
+
+	/* Regions in the early_node_map can be in any order */
+	sort_node_map();
+
+	/* Print out the zone ranges */
+	printk("Zone PFN ranges:\n");
+	for (i = 0; i < MAX_NR_ZONES; i++)
+		printk("  %-8s %8lu -> %8lu\n",
+				zone_names[i],
+				arch_zone_lowest_possible_pfn[i],
+				arch_zone_highest_possible_pfn[i]);
+
+	/* Print out the early_node_map[] */
+	printk("early_node_map[%d] active PFN ranges\n", nr_nodemap_entries);
+	for (i = 0; i < nr_nodemap_entries; i++)
+		printk("  %3d: %8lu -> %8lu\n", early_node_map[i].nid,
+						early_node_map[i].start_pfn,
+						early_node_map[i].end_pfn);
+
+	/* Initialise every node */
+	for_each_online_node(nid) {
+		pg_data_t *pgdat = NODE_DATA(nid);
+		free_area_init_node(nid, pgdat, NULL,
+				find_min_pfn_for_node(nid), NULL);
+	}
+}
+#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */
+
+/**
+ * set_dma_reserve - Account the specified number of pages reserved in ZONE_DMA
+ * @new_dma_reserve - The number of pages to mark reserved
+ *
+ * The per-cpu batchsize and zone watermarks are determined by present_pages.
+ * In the DMA zone, a significant percentage may be consumed by kernel image
+ * and other unfreeable allocations which can skew the watermarks badly. This
+ * function may optionally be used to account for unfreeable pages in
+ * ZONE_DMA. The effect will be lower watermarks and smaller per-cpu batchsize
+ */
+void __init set_dma_reserve(unsigned long new_dma_reserve)
+{
+	dma_reserve = new_dma_reserve;
+}
+
 #ifndef CONFIG_NEED_MULTIPLE_NODES
 static bootmem_data_t contig_bootmem_data;
 struct pglist_data contig_page_data = { .bdata = &contig_bootmem_data };
diff --git a/mm/shmem.c b/mm/shmem.c
index 8631be45b40..eda907c3a86 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1351,7 +1351,6 @@ shmem_get_inode(struct super_block *sb, int mode, dev_t dev)
 		inode->i_mode = mode;
 		inode->i_uid = current->fsuid;
 		inode->i_gid = current->fsgid;
-		inode->i_blksize = PAGE_CACHE_SIZE;
 		inode->i_blocks = 0;
 		inode->i_mapping->a_ops = &shmem_aops;
 		inode->i_mapping->backing_dev_info = &shmem_backing_dev_info;
@@ -2157,8 +2156,7 @@ static int init_inodecache(void)
 
 static void destroy_inodecache(void)
 {
-	if (kmem_cache_destroy(shmem_inode_cachep))
-		printk(KERN_INFO "shmem_inode_cache: not all structures were freed\n");
+	kmem_cache_destroy(shmem_inode_cachep);
 }
 
 static const struct address_space_operations shmem_aops = {
diff --git a/mm/slab.c b/mm/slab.c
index 7a48eb1a60c..792bfe320a8 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -972,7 +972,39 @@ static int transfer_objects(struct array_cache *to,
 	return nr;
 }
 
-#ifdef CONFIG_NUMA
+#ifndef CONFIG_NUMA
+
+#define drain_alien_cache(cachep, alien) do { } while (0)
+#define reap_alien(cachep, l3) do { } while (0)
+
+static inline struct array_cache **alloc_alien_cache(int node, int limit)
+{
+	return (struct array_cache **)BAD_ALIEN_MAGIC;
+}
+
+static inline void free_alien_cache(struct array_cache **ac_ptr)
+{
+}
+
+static inline int cache_free_alien(struct kmem_cache *cachep, void *objp)
+{
+	return 0;
+}
+
+static inline void *alternate_node_alloc(struct kmem_cache *cachep,
+		gfp_t flags)
+{
+	return NULL;
+}
+
+static inline void *__cache_alloc_node(struct kmem_cache *cachep,
+		 gfp_t flags, int nodeid)
+{
+	return NULL;
+}
+
+#else	/* CONFIG_NUMA */
+
 static void *__cache_alloc_node(struct kmem_cache *, gfp_t, int);
 static void *alternate_node_alloc(struct kmem_cache *, gfp_t);
 
@@ -1101,26 +1133,6 @@ static inline int cache_free_alien(struct kmem_cache *cachep, void *objp)
 	}
 	return 1;
 }
-
-#else
-
-#define drain_alien_cache(cachep, alien) do { } while (0)
-#define reap_alien(cachep, l3) do { } while (0)
-
-static inline struct array_cache **alloc_alien_cache(int node, int limit)
-{
-	return (struct array_cache **)BAD_ALIEN_MAGIC;
-}
-
-static inline void free_alien_cache(struct array_cache **ac_ptr)
-{
-}
-
-static inline int cache_free_alien(struct kmem_cache *cachep, void *objp)
-{
-	return 0;
-}
-
 #endif
 
 static int __cpuinit cpuup_callback(struct notifier_block *nfb,
@@ -1564,7 +1576,13 @@ static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid)
 	 */
 	flags |= __GFP_COMP;
 #endif
-	flags |= cachep->gfpflags;
+
+	/*
+	 * Under NUMA we want memory on the indicated node. We will handle
+	 * the needed fallback ourselves since we want to serve from our
+	 * per node object lists first for other nodes.
+	 */
+	flags |= cachep->gfpflags | GFP_THISNODE;
 
 	page = alloc_pages_node(nodeid, flags, cachep->gfporder);
 	if (!page)
@@ -2442,7 +2460,6 @@ EXPORT_SYMBOL(kmem_cache_shrink);
  * @cachep: the cache to destroy
  *
  * Remove a struct kmem_cache object from the slab cache.
- * Returns 0 on success.
  *
  * It is expected this function will be called by a module when it is
  * unloaded.  This will remove the cache completely, and avoid a duplicate
@@ -2454,7 +2471,7 @@ EXPORT_SYMBOL(kmem_cache_shrink);
  * The caller must guarantee that noone will allocate memory from the cache
  * during the kmem_cache_destroy().
  */
-int kmem_cache_destroy(struct kmem_cache *cachep)
+void kmem_cache_destroy(struct kmem_cache *cachep)
 {
 	BUG_ON(!cachep || in_interrupt());
 
@@ -2475,7 +2492,7 @@ int kmem_cache_destroy(struct kmem_cache *cachep)
 		list_add(&cachep->next, &cache_chain);
 		mutex_unlock(&cache_chain_mutex);
 		unlock_cpu_hotplug();
-		return 1;
+		return;
 	}
 
 	if (unlikely(cachep->flags & SLAB_DESTROY_BY_RCU))
@@ -2483,7 +2500,6 @@ int kmem_cache_destroy(struct kmem_cache *cachep)
 
 	__kmem_cache_destroy(cachep);
 	unlock_cpu_hotplug();
-	return 0;
 }
 EXPORT_SYMBOL(kmem_cache_destroy);
 
@@ -3030,14 +3046,6 @@ static inline void *____cache_alloc(struct kmem_cache *cachep, gfp_t flags)
 	void *objp;
 	struct array_cache *ac;
 
-#ifdef CONFIG_NUMA
-	if (unlikely(current->flags & (PF_SPREAD_SLAB | PF_MEMPOLICY))) {
-		objp = alternate_node_alloc(cachep, flags);
-		if (objp != NULL)
-			return objp;
-	}
-#endif
-
 	check_irq_off();
 	ac = cpu_cache_get(cachep);
 	if (likely(ac->avail)) {
@@ -3055,12 +3063,24 @@ static __always_inline void *__cache_alloc(struct kmem_cache *cachep,
 						gfp_t flags, void *caller)
 {
 	unsigned long save_flags;
-	void *objp;
+	void *objp = NULL;
 
 	cache_alloc_debugcheck_before(cachep, flags);
 
 	local_irq_save(save_flags);
-	objp = ____cache_alloc(cachep, flags);
+
+	if (unlikely(NUMA_BUILD &&
+			current->flags & (PF_SPREAD_SLAB | PF_MEMPOLICY)))
+		objp = alternate_node_alloc(cachep, flags);
+
+	if (!objp)
+		objp = ____cache_alloc(cachep, flags);
+	/*
+	 * We may just have run out of memory on the local node.
+	 * __cache_alloc_node() knows how to locate memory on other nodes
+	 */
+ 	if (NUMA_BUILD && !objp)
+ 		objp = __cache_alloc_node(cachep, flags, numa_node_id());
 	local_irq_restore(save_flags);
 	objp = cache_alloc_debugcheck_after(cachep, flags, objp,
 					    caller);
@@ -3079,7 +3099,7 @@ static void *alternate_node_alloc(struct kmem_cache *cachep, gfp_t flags)
 {
 	int nid_alloc, nid_here;
 
-	if (in_interrupt())
+	if (in_interrupt() || (flags & __GFP_THISNODE))
 		return NULL;
 	nid_alloc = nid_here = numa_node_id();
 	if (cpuset_do_slab_mem_spread() && (cachep->flags & SLAB_MEM_SPREAD))
@@ -3092,6 +3112,28 @@ static void *alternate_node_alloc(struct kmem_cache *cachep, gfp_t flags)
 }
 
 /*
+ * Fallback function if there was no memory available and no objects on a
+ * certain node and we are allowed to fall back. We mimick the behavior of
+ * the page allocator. We fall back according to a zonelist determined by
+ * the policy layer while obeying cpuset constraints.
+ */
+void *fallback_alloc(struct kmem_cache *cache, gfp_t flags)
+{
+	struct zonelist *zonelist = &NODE_DATA(slab_node(current->mempolicy))
+					->node_zonelists[gfp_zone(flags)];
+	struct zone **z;
+	void *obj = NULL;
+
+	for (z = zonelist->zones; *z && !obj; z++)
+		if (zone_idx(*z) <= ZONE_NORMAL &&
+				cpuset_zone_allowed(*z, flags))
+			obj = __cache_alloc_node(cache,
+					flags | __GFP_THISNODE,
+					zone_to_nid(*z));
+	return obj;
+}
+
+/*
  * A interface to enable slab creation on nodeid
  */
 static void *__cache_alloc_node(struct kmem_cache *cachep, gfp_t flags,
@@ -3144,11 +3186,15 @@ retry:
 must_grow:
 	spin_unlock(&l3->list_lock);
 	x = cache_grow(cachep, flags, nodeid);
+	if (x)
+		goto retry;
 
-	if (!x)
-		return NULL;
+	if (!(flags & __GFP_THISNODE))
+		/* Unable to grow the cache. Fall back to other nodes. */
+		return fallback_alloc(cachep, flags);
+
+	return NULL;
 
-	goto retry;
 done:
 	return obj;
 }
diff --git a/mm/slob.c b/mm/slob.c
index 20188627347..542394184a5 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -270,10 +270,9 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size,
 }
 EXPORT_SYMBOL(kmem_cache_create);
 
-int kmem_cache_destroy(struct kmem_cache *c)
+void kmem_cache_destroy(struct kmem_cache *c)
 {
 	slob_free(c, sizeof(struct kmem_cache));
-	return 0;
 }
 EXPORT_SYMBOL(kmem_cache_destroy);
 
diff --git a/mm/truncate.c b/mm/truncate.c
index c6ab55ec688..a654928323d 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -9,6 +9,7 @@
 
 #include <linux/kernel.h>
 #include <linux/mm.h>
+#include <linux/swap.h>
 #include <linux/module.h>
 #include <linux/pagemap.h>
 #include <linux/pagevec.h>
@@ -52,36 +53,26 @@ truncate_complete_page(struct address_space *mapping, struct page *page)
 /*
  * This is for invalidate_inode_pages().  That function can be called at
  * any time, and is not supposed to throw away dirty pages.  But pages can
- * be marked dirty at any time too.  So we re-check the dirtiness inside
- * ->tree_lock.  That provides exclusion against the __set_page_dirty
- * functions.
+ * be marked dirty at any time too, so use remove_mapping which safely
+ * discards clean, unused pages.
  *
  * Returns non-zero if the page was successfully invalidated.
  */
 static int
 invalidate_complete_page(struct address_space *mapping, struct page *page)
 {
+	int ret;
+
 	if (page->mapping != mapping)
 		return 0;
 
 	if (PagePrivate(page) && !try_to_release_page(page, 0))
 		return 0;
 
-	write_lock_irq(&mapping->tree_lock);
-	if (PageDirty(page))
-		goto failed;
-	if (page_count(page) != 2)	/* caller's ref + pagecache ref */
-		goto failed;
-
-	BUG_ON(PagePrivate(page));
-	__remove_from_page_cache(page);
-	write_unlock_irq(&mapping->tree_lock);
+	ret = remove_mapping(mapping, page);
 	ClearPageUptodate(page);
-	page_cache_release(page);	/* pagecache ref */
-	return 1;
-failed:
-	write_unlock_irq(&mapping->tree_lock);
-	return 0;
+
+	return ret;
 }
 
 /**
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 9aad8b0cc6e..1ac191ce564 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -241,7 +241,6 @@ struct vm_struct *__get_vm_area(unsigned long size, unsigned long flags,
 
 /**
  *	get_vm_area  -  reserve a contingous kernel virtual area
- *
  *	@size:		size of the area
  *	@flags:		%VM_IOREMAP for I/O mappings or VM_ALLOC
  *
@@ -273,7 +272,7 @@ static struct vm_struct *__find_vm_area(void *addr)
 }
 
 /* Caller must hold vmlist_lock */
-struct vm_struct *__remove_vm_area(void *addr)
+static struct vm_struct *__remove_vm_area(void *addr)
 {
 	struct vm_struct **p, *tmp;
 
@@ -296,7 +295,6 @@ found:
 
 /**
  *	remove_vm_area  -  find and remove a contingous kernel virtual area
- *
  *	@addr:		base address
  *
  *	Search for the kernel VM area starting at @addr, and remove it.
@@ -355,7 +353,6 @@ void __vunmap(void *addr, int deallocate_pages)
 
 /**
  *	vfree  -  release memory allocated by vmalloc()
- *
  *	@addr:		memory base address
  *
  *	Free the virtually contiguous memory area starting at @addr, as
@@ -373,7 +370,6 @@ EXPORT_SYMBOL(vfree);
 
 /**
  *	vunmap  -  release virtual mapping obtained by vmap()
- *
  *	@addr:		memory base address
  *
  *	Free the virtually contiguous memory area starting at @addr,
@@ -390,7 +386,6 @@ EXPORT_SYMBOL(vunmap);
 
 /**
  *	vmap  -  map an array of pages into virtually contiguous space
- *
  *	@pages:		array of page pointers
  *	@count:		number of pages to map
  *	@flags:		vm_area->flags
@@ -471,7 +466,6 @@ void *__vmalloc_area(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot)
 
 /**
  *	__vmalloc_node  -  allocate virtually contiguous memory
- *
  *	@size:		allocation size
  *	@gfp_mask:	flags for the page level allocator
  *	@prot:		protection mask for the allocated pages
@@ -505,9 +499,7 @@ EXPORT_SYMBOL(__vmalloc);
 
 /**
  *	vmalloc  -  allocate virtually contiguous memory
- *
  *	@size:		allocation size
- *
  *	Allocate enough pages to cover @size from the page level
  *	allocator and map them into contiguous kernel virtual space.
  *
@@ -521,11 +513,11 @@ void *vmalloc(unsigned long size)
 EXPORT_SYMBOL(vmalloc);
 
 /**
- *	vmalloc_user  -  allocate virtually contiguous memory which has
- *			   been zeroed so it can be mapped to userspace without
- *			   leaking data.
+ * vmalloc_user - allocate zeroed virtually contiguous memory for userspace
+ * @size: allocation size
  *
- *	@size:		allocation size
+ * The resulting memory area is zeroed so it can be mapped to userspace
+ * without leaking data.
  */
 void *vmalloc_user(unsigned long size)
 {
@@ -544,7 +536,6 @@ EXPORT_SYMBOL(vmalloc_user);
 
 /**
  *	vmalloc_node  -  allocate memory on a specific node
- *
  *	@size:		allocation size
  *	@node:		numa node
  *
@@ -566,7 +557,6 @@ EXPORT_SYMBOL(vmalloc_node);
 
 /**
  *	vmalloc_exec  -  allocate virtually contiguous, executable memory
- *
  *	@size:		allocation size
  *
  *	Kernel-internal function to allocate enough pages to cover @size
@@ -584,7 +574,6 @@ void *vmalloc_exec(unsigned long size)
 
 /**
  *	vmalloc_32  -  allocate virtually contiguous memory (32bit addressable)
- *
  *	@size:		allocation size
  *
  *	Allocate enough 32bit PA addressable pages to cover @size from the
@@ -597,11 +586,11 @@ void *vmalloc_32(unsigned long size)
 EXPORT_SYMBOL(vmalloc_32);
 
 /**
- *	vmalloc_32_user  -  allocate virtually contiguous memory (32bit
- *			      addressable) which is zeroed so it can be
- *			      mapped to userspace without leaking data.
- *
+ * vmalloc_32_user - allocate zeroed virtually contiguous 32bit memory
  *	@size:		allocation size
+ *
+ * The resulting memory area is 32bit addressable and zeroed so it can be
+ * mapped to userspace without leaking data.
  */
 void *vmalloc_32_user(unsigned long size)
 {
@@ -695,7 +684,6 @@ finished:
 
 /**
  *	remap_vmalloc_range  -  map vmalloc pages to userspace
- *
  *	@vma:		vma to cover (map full range of vma)
  *	@addr:		vmalloc memory
  *	@pgoff:		number of pages into addr before first page to map
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 87779dda4ec..eca70310adb 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -19,6 +19,7 @@
 #include <linux/pagemap.h>
 #include <linux/init.h>
 #include <linux/highmem.h>
+#include <linux/vmstat.h>
 #include <linux/file.h>
 #include <linux/writeback.h>
 #include <linux/blkdev.h>
@@ -370,7 +371,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping)
 			/* synchronous write or broken a_ops? */
 			ClearPageReclaim(page);
 		}
-
+		inc_zone_page_state(page, NR_VMSCAN_WRITE);
 		return PAGE_SUCCESS;
 	}
 
@@ -383,11 +384,30 @@ int remove_mapping(struct address_space *mapping, struct page *page)
 	BUG_ON(mapping != page_mapping(page));
 
 	write_lock_irq(&mapping->tree_lock);
-
 	/*
-	 * The non-racy check for busy page.  It is critical to check
-	 * PageDirty _after_ making sure that the page is freeable and
-	 * not in use by anybody. 	(pagecache + us == 2)
+	 * The non racy check for a busy page.
+	 *
+	 * Must be careful with the order of the tests. When someone has
+	 * a ref to the page, it may be possible that they dirty it then
+	 * drop the reference. So if PageDirty is tested before page_count
+	 * here, then the following race may occur:
+	 *
+	 * get_user_pages(&page);
+	 * [user mapping goes away]
+	 * write_to(page);
+	 *				!PageDirty(page)    [good]
+	 * SetPageDirty(page);
+	 * put_page(page);
+	 *				!page_count(page)   [good, discard it]
+	 *
+	 * [oops, our write_to data is lost]
+	 *
+	 * Reversing the order of the tests ensures such a situation cannot
+	 * escape unnoticed. The smp_rmb is needed to ensure the page->flags
+	 * load is not satisfied before that of page->_count.
+	 *
+	 * Note that if SetPageDirty is always performed via set_page_dirty,
+	 * and thus under tree_lock, then this ordering is not required.
 	 */
 	if (unlikely(page_count(page) != 2))
 		goto cannot_free;
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 490d8c1a0de..a2b6a9f96e5 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -371,7 +371,7 @@ void zone_statistics(struct zonelist *zonelist, struct zone *z)
 		__inc_zone_state(z, NUMA_MISS);
 		__inc_zone_state(zonelist->zones[0], NUMA_FOREIGN);
 	}
-	if (z->zone_pgdat == NODE_DATA(numa_node_id()))
+	if (z->node == numa_node_id())
 		__inc_zone_state(z, NUMA_LOCAL);
 	else
 		__inc_zone_state(z, NUMA_OTHER);
@@ -465,6 +465,7 @@ static char *vmstat_text[] = {
 	"nr_writeback",
 	"nr_unstable",
 	"nr_bounce",
+	"nr_vmscan_write",
 
 #ifdef CONFIG_NUMA
 	"numa_hit",