24 files changed, 358 insertions, 417 deletions

diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index f2e574dbc30..801c08b046e 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -176,6 +176,9 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent,
 	int ret = 0;
 	struct device *dev;
 
+	if (bdi->dev)	/* The driver needs to use separate queues per device */
+		goto exit;
+
 	va_start(args, fmt);
 	dev = device_create_vargs(bdi_class, parent, MKDEV(0, 0), bdi, fmt, args);
 	va_end(args);
diff --git a/mm/filemap.c b/mm/filemap.c
index ab8553658af..f3e5f8944d1 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2029,48 +2029,8 @@ int pagecache_write_begin(struct file *file, struct address_space *mapping,
 {
 	const struct address_space_operations *aops = mapping->a_ops;
 
-	if (aops->write_begin) {
-		return aops->write_begin(file, mapping, pos, len, flags,
+	return aops->write_begin(file, mapping, pos, len, flags,
 							pagep, fsdata);
-	} else {
-		int ret;
-		pgoff_t index = pos >> PAGE_CACHE_SHIFT;
-		unsigned offset = pos & (PAGE_CACHE_SIZE - 1);
-		struct inode *inode = mapping->host;
-		struct page *page;
-again:
-		page = __grab_cache_page(mapping, index);
-		*pagep = page;
-		if (!page)
-			return -ENOMEM;
-
-		if (flags & AOP_FLAG_UNINTERRUPTIBLE && !PageUptodate(page)) {
-			/*
-			 * There is no way to resolve a short write situation
-			 * for a !Uptodate page (except by double copying in
-			 * the caller done by generic_perform_write_2copy).
-			 *
-			 * Instead, we have to bring it uptodate here.
-			 */
-			ret = aops->readpage(file, page);
-			page_cache_release(page);
-			if (ret) {
-				if (ret == AOP_TRUNCATED_PAGE)
-					goto again;
-				return ret;
-			}
-			goto again;
-		}
-
-		ret = aops->prepare_write(file, page, offset, offset+len);
-		if (ret) {
-			unlock_page(page);
-			page_cache_release(page);
-			if (pos + len > inode->i_size)
-				vmtruncate(inode, inode->i_size);
-		}
-		return ret;
-	}
 }
 EXPORT_SYMBOL(pagecache_write_begin);
 
@@ -2079,32 +2039,9 @@ int pagecache_write_end(struct file *file, struct address_space *mapping,
 				struct page *page, void *fsdata)
 {
 	const struct address_space_operations *aops = mapping->a_ops;
-	int ret;
-
-	if (aops->write_end) {
-		mark_page_accessed(page);
-		ret = aops->write_end(file, mapping, pos, len, copied,
-							page, fsdata);
-	} else {
-		unsigned offset = pos & (PAGE_CACHE_SIZE - 1);
-		struct inode *inode = mapping->host;
-
-		flush_dcache_page(page);
-		ret = aops->commit_write(file, page, offset, offset+len);
-		unlock_page(page);
-		mark_page_accessed(page);
-		page_cache_release(page);
-
-		if (ret < 0) {
-			if (pos + len > inode->i_size)
-				vmtruncate(inode, inode->i_size);
-		} else if (ret > 0)
-			ret = min_t(size_t, copied, ret);
-		else
-			ret = copied;
-	}
 
-	return ret;
+	mark_page_accessed(page);
+	return aops->write_end(file, mapping, pos, len, copied, page, fsdata);
 }
 EXPORT_SYMBOL(pagecache_write_end);
 
@@ -2226,174 +2163,6 @@ repeat:
 }
 EXPORT_SYMBOL(__grab_cache_page);
 
-static ssize_t generic_perform_write_2copy(struct file *file,
-				struct iov_iter *i, loff_t pos)
-{
-	struct address_space *mapping = file->f_mapping;
-	const struct address_space_operations *a_ops = mapping->a_ops;
-	struct inode *inode = mapping->host;
-	long status = 0;
-	ssize_t written = 0;
-
-	do {
-		struct page *src_page;
-		struct page *page;
-		pgoff_t index;		/* Pagecache index for current page */
-		unsigned long offset;	/* Offset into pagecache page */
-		unsigned long bytes;	/* Bytes to write to page */
-		size_t copied;		/* Bytes copied from user */
-
-		offset = (pos & (PAGE_CACHE_SIZE - 1));
-		index = pos >> PAGE_CACHE_SHIFT;
-		bytes = min_t(unsigned long, PAGE_CACHE_SIZE - offset,
-						iov_iter_count(i));
-
-		/*
-		 * a non-NULL src_page indicates that we're doing the
-		 * copy via get_user_pages and kmap.
-		 */
-		src_page = NULL;
-
-		/*
-		 * Bring in the user page that we will copy from _first_.
-		 * Otherwise there's a nasty deadlock on copying from the
-		 * same page as we're writing to, without it being marked
-		 * up-to-date.
-		 *
-		 * Not only is this an optimisation, but it is also required
-		 * to check that the address is actually valid, when atomic
-		 * usercopies are used, below.
-		 */
-		if (unlikely(iov_iter_fault_in_readable(i, bytes))) {
-			status = -EFAULT;
-			break;
-		}
-
-		page = __grab_cache_page(mapping, index);
-		if (!page) {
-			status = -ENOMEM;
-			break;
-		}
-
-		/*
-		 * non-uptodate pages cannot cope with short copies, and we
-		 * cannot take a pagefault with the destination page locked.
-		 * So pin the source page to copy it.
-		 */
-		if (!PageUptodate(page) && !segment_eq(get_fs(), KERNEL_DS)) {
-			unlock_page(page);
-
-			src_page = alloc_page(GFP_KERNEL);
-			if (!src_page) {
-				page_cache_release(page);
-				status = -ENOMEM;
-				break;
-			}
-
-			/*
-			 * Cannot get_user_pages with a page locked for the
-			 * same reason as we can't take a page fault with a
-			 * page locked (as explained below).
-			 */
-			copied = iov_iter_copy_from_user(src_page, i,
-								offset, bytes);
-			if (unlikely(copied == 0)) {
-				status = -EFAULT;
-				page_cache_release(page);
-				page_cache_release(src_page);
-				break;
-			}
-			bytes = copied;
-
-			lock_page(page);
-			/*
-			 * Can't handle the page going uptodate here, because
-			 * that means we would use non-atomic usercopies, which
-			 * zero out the tail of the page, which can cause
-			 * zeroes to become transiently visible. We could just
-			 * use a non-zeroing copy, but the APIs aren't too
-			 * consistent.
-			 */
-			if (unlikely(!page->mapping || PageUptodate(page))) {
-				unlock_page(page);
-				page_cache_release(page);
-				page_cache_release(src_page);
-				continue;
-			}
-		}
-
-		status = a_ops->prepare_write(file, page, offset, offset+bytes);
-		if (unlikely(status))
-			goto fs_write_aop_error;
-
-		if (!src_page) {
-			/*
-			 * Must not enter the pagefault handler here, because
-			 * we hold the page lock, so we might recursively
-			 * deadlock on the same lock, or get an ABBA deadlock
-			 * against a different lock, or against the mmap_sem
-			 * (which nests outside the page lock).  So increment
-			 * preempt count, and use _atomic usercopies.
-			 *
-			 * The page is uptodate so we are OK to encounter a
-			 * short copy: if unmodified parts of the page are
-			 * marked dirty and written out to disk, it doesn't
-			 * really matter.
-			 */
-			pagefault_disable();
-			copied = iov_iter_copy_from_user_atomic(page, i,
-								offset, bytes);
-			pagefault_enable();
-		} else {
-			void *src, *dst;
-			src = kmap_atomic(src_page, KM_USER0);
-			dst = kmap_atomic(page, KM_USER1);
-			memcpy(dst + offset, src + offset, bytes);
-			kunmap_atomic(dst, KM_USER1);
-			kunmap_atomic(src, KM_USER0);
-			copied = bytes;
-		}
-		flush_dcache_page(page);
-
-		status = a_ops->commit_write(file, page, offset, offset+bytes);
-		if (unlikely(status < 0))
-			goto fs_write_aop_error;
-		if (unlikely(status > 0)) /* filesystem did partial write */
-			copied = min_t(size_t, copied, status);
-
-		unlock_page(page);
-		mark_page_accessed(page);
-		page_cache_release(page);
-		if (src_page)
-			page_cache_release(src_page);
-
-		iov_iter_advance(i, copied);
-		pos += copied;
-		written += copied;
-
-		balance_dirty_pages_ratelimited(mapping);
-		cond_resched();
-		continue;
-
-fs_write_aop_error:
-		unlock_page(page);
-		page_cache_release(page);
-		if (src_page)
-			page_cache_release(src_page);
-
-		/*
-		 * prepare_write() may have instantiated a few blocks
-		 * outside i_size.  Trim these off again. Don't need
-		 * i_size_read because we hold i_mutex.
-		 */
-		if (pos + bytes > inode->i_size)
-			vmtruncate(inode, inode->i_size);
-		break;
-	} while (iov_iter_count(i));
-
-	return written ? written : status;
-}
-
 static ssize_t generic_perform_write(struct file *file,
 				struct iov_iter *i, loff_t pos)
 {
@@ -2494,10 +2263,7 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
 	struct iov_iter i;
 
 	iov_iter_init(&i, iov, nr_segs, count, written);
-	if (a_ops->write_begin)
-		status = generic_perform_write(file, &i, pos);
-	else
-		status = generic_perform_write_2copy(file, &i, pos);
+	status = generic_perform_write(file, &i, pos);
 
 	if (likely(status >= 0)) {
 		written += status;
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 421aee99b84..6058b53dcb8 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -354,11 +354,26 @@ static int vma_has_reserves(struct vm_area_struct *vma)
 	return 0;
 }
 
+static void clear_gigantic_page(struct page *page,
+			unsigned long addr, unsigned long sz)
+{
+	int i;
+	struct page *p = page;
+
+	might_sleep();
+	for (i = 0; i < sz/PAGE_SIZE; i++, p = mem_map_next(p, page, i)) {
+		cond_resched();
+		clear_user_highpage(p, addr + i * PAGE_SIZE);
+	}
+}
 static void clear_huge_page(struct page *page,
 			unsigned long addr, unsigned long sz)
 {
 	int i;
 
+	if (unlikely(sz > MAX_ORDER_NR_PAGES))
+		return clear_gigantic_page(page, addr, sz);
+
 	might_sleep();
 	for (i = 0; i < sz/PAGE_SIZE; i++) {
 		cond_resched();
@@ -366,12 +381,32 @@ static void clear_huge_page(struct page *page,
 	}
 }
 
+static void copy_gigantic_page(struct page *dst, struct page *src,
+			   unsigned long addr, struct vm_area_struct *vma)
+{
+	int i;
+	struct hstate *h = hstate_vma(vma);
+	struct page *dst_base = dst;
+	struct page *src_base = src;
+	might_sleep();
+	for (i = 0; i < pages_per_huge_page(h); ) {
+		cond_resched();
+		copy_user_highpage(dst, src, addr + i*PAGE_SIZE, vma);
+
+		i++;
+		dst = mem_map_next(dst, dst_base, i);
+		src = mem_map_next(src, src_base, i);
+	}
+}
 static void copy_huge_page(struct page *dst, struct page *src,
 			   unsigned long addr, struct vm_area_struct *vma)
 {
 	int i;
 	struct hstate *h = hstate_vma(vma);
 
+	if (unlikely(pages_per_huge_page(h) > MAX_ORDER_NR_PAGES))
+		return copy_gigantic_page(dst, src, addr, vma);
+
 	might_sleep();
 	for (i = 0; i < pages_per_huge_page(h); i++) {
 		cond_resched();
@@ -456,6 +491,8 @@ static void update_and_free_page(struct hstate *h, struct page *page)
 {
 	int i;
 
+	VM_BUG_ON(h->order >= MAX_ORDER);
+
 	h->nr_huge_pages--;
 	h->nr_huge_pages_node[page_to_nid(page)]--;
 	for (i = 0; i < pages_per_huge_page(h); i++) {
@@ -970,6 +1007,14 @@ found:
 	return 1;
 }
 
+static void prep_compound_huge_page(struct page *page, int order)
+{
+	if (unlikely(order > (MAX_ORDER - 1)))
+		prep_compound_gigantic_page(page, order);
+	else
+		prep_compound_page(page, order);
+}
+
 /* Put bootmem huge pages into the standard lists after mem_map is up */
 static void __init gather_bootmem_prealloc(void)
 {
@@ -980,7 +1025,7 @@ static void __init gather_bootmem_prealloc(void)
 		struct hstate *h = m->hstate;
 		__ClearPageReserved(page);
 		WARN_ON(page_count(page) != 1);
-		prep_compound_page(page, h->order);
+		prep_compound_huge_page(page, h->order);
 		prep_new_huge_page(h, page, page_to_nid(page));
 	}
 }
@@ -1751,6 +1796,7 @@ void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
 				struct page *page, unsigned long address)
 {
+	struct hstate *h = hstate_vma(vma);
 	struct vm_area_struct *iter_vma;
 	struct address_space *mapping;
 	struct prio_tree_iter iter;
@@ -1760,7 +1806,7 @@ static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * vm_pgoff is in PAGE_SIZE units, hence the different calculation
 	 * from page cache lookup which is in HPAGE_SIZE units.
 	 */
-	address = address & huge_page_mask(hstate_vma(vma));
+	address = address & huge_page_mask(h);
 	pgoff = ((address - vma->vm_start) >> PAGE_SHIFT)
 		+ (vma->vm_pgoff >> PAGE_SHIFT);
 	mapping = (struct address_space *)page_private(page);
@@ -1779,7 +1825,7 @@ static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
 		 */
 		if (!is_vma_resv_set(iter_vma, HPAGE_RESV_OWNER))
 			unmap_hugepage_range(iter_vma,
-				address, address + HPAGE_SIZE,
+				address, address + huge_page_size(h),
 				page);
 	}
 
@@ -2130,7 +2176,7 @@ same_page:
 			if (zeropage_ok)
 				pages[i] = ZERO_PAGE(0);
 			else
-				pages[i] = page + pfn_offset;
+				pages[i] = mem_map_offset(page, pfn_offset);
 			get_page(pages[i]);
 		}
 
diff --git a/mm/internal.h b/mm/internal.h
index e4e728bdf32..13333bc2eb6 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -17,6 +17,7 @@ void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
 		unsigned long floor, unsigned long ceiling);
 
 extern void prep_compound_page(struct page *page, unsigned long order);
+extern void prep_compound_gigantic_page(struct page *page, unsigned long order);
 
 static inline void set_page_count(struct page *page, int v)
 {
@@ -176,6 +177,34 @@ static inline void free_page_mlock(struct page *page) { }
 #endif /* CONFIG_UNEVICTABLE_LRU */
 
 /*
+ * Return the mem_map entry representing the 'offset' subpage within
+ * the maximally aligned gigantic page 'base'.  Handle any discontiguity
+ * in the mem_map at MAX_ORDER_NR_PAGES boundaries.
+ */
+static inline struct page *mem_map_offset(struct page *base, int offset)
+{
+	if (unlikely(offset >= MAX_ORDER_NR_PAGES))
+		return pfn_to_page(page_to_pfn(base) + offset);
+	return base + offset;
+}
+
+/*
+ * Iterator over all subpages withing the maximally aligned gigantic
+ * page 'base'.  Handle any discontiguity in the mem_map.
+ */
+static inline struct page *mem_map_next(struct page *iter,
+						struct page *base, int offset)
+{
+	if (unlikely((offset & (MAX_ORDER_NR_PAGES - 1)) == 0)) {
+		unsigned long pfn = page_to_pfn(base) + offset;
+		if (!pfn_valid(pfn))
+			return NULL;
+		return pfn_to_page(pfn);
+	}
+	return iter + 1;
+}
+
+/*
  * FLATMEM and DISCONTIGMEM configurations use alloc_bootmem_node,
  * so all functions starting at paging_init should be marked __init
  * in those cases. SPARSEMEM, however, allows for memory hotplug,
diff --git a/mm/memory.c b/mm/memory.c
index 164951c4730..f01b7eed6e1 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -669,6 +669,16 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	if (is_vm_hugetlb_page(vma))
 		return copy_hugetlb_page_range(dst_mm, src_mm, vma);
 
+	if (unlikely(is_pfn_mapping(vma))) {
+		/*
+		 * We do not free on error cases below as remove_vma
+		 * gets called on error from higher level routine
+		 */
+		ret = track_pfn_vma_copy(vma);
+		if (ret)
+			return ret;
+	}
+
 	/*
 	 * We need to invalidate the secondary MMU mappings only when
 	 * there could be a permission downgrade on the ptes of the
@@ -915,6 +925,9 @@ unsigned long unmap_vmas(struct mmu_gather **tlbp,
 		if (vma->vm_flags & VM_ACCOUNT)
 			*nr_accounted += (end - start) >> PAGE_SHIFT;
 
+		if (unlikely(is_pfn_mapping(vma)))
+			untrack_pfn_vma(vma, 0, 0);
+
 		while (start != end) {
 			if (!tlb_start_valid) {
 				tlb_start = start;
@@ -1430,6 +1443,7 @@ out:
 int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 			unsigned long pfn)
 {
+	int ret;
 	/*
 	 * Technically, architectures with pte_special can avoid all these
 	 * restrictions (same for remap_pfn_range).  However we would like
@@ -1444,7 +1458,15 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 
 	if (addr < vma->vm_start || addr >= vma->vm_end)
 		return -EFAULT;
-	return insert_pfn(vma, addr, pfn, vma->vm_page_prot);
+	if (track_pfn_vma_new(vma, vma->vm_page_prot, pfn, PAGE_SIZE))
+		return -EINVAL;
+
+	ret = insert_pfn(vma, addr, pfn, vma->vm_page_prot);
+
+	if (ret)
+		untrack_pfn_vma(vma, pfn, PAGE_SIZE);
+
+	return ret;
 }
 EXPORT_SYMBOL(vm_insert_pfn);
 
@@ -1575,14 +1597,17 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
 	 * behaviour that some programs depend on. We mark the "original"
 	 * un-COW'ed pages by matching them up with "vma->vm_pgoff".
 	 */
-	if (is_cow_mapping(vma->vm_flags)) {
-		if (addr != vma->vm_start || end != vma->vm_end)
-			return -EINVAL;
+	if (addr == vma->vm_start && end == vma->vm_end)
 		vma->vm_pgoff = pfn;
-	}
+	else if (is_cow_mapping(vma->vm_flags))
+		return -EINVAL;
 
 	vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP;
 
+	err = track_pfn_vma_new(vma, prot, pfn, PAGE_ALIGN(size));
+	if (err)
+		return -EINVAL;
+
 	BUG_ON(addr >= end);
 	pfn -= addr >> PAGE_SHIFT;
 	pgd = pgd_offset(mm, addr);
@@ -1594,6 +1619,10 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
 		if (err)
 			break;
 	} while (pgd++, addr = next, addr != end);
+
+	if (err)
+		untrack_pfn_vma(vma, pfn, PAGE_ALIGN(size));
+
 	return err;
 }
 EXPORT_SYMBOL(remap_pfn_range);
@@ -2865,9 +2894,9 @@ int in_gate_area_no_task(unsigned long addr)
 #endif	/* __HAVE_ARCH_GATE_AREA */
 
 #ifdef CONFIG_HAVE_IOREMAP_PROT
-static resource_size_t follow_phys(struct vm_area_struct *vma,
-			unsigned long address, unsigned int flags,
-			unsigned long *prot)
+int follow_phys(struct vm_area_struct *vma,
+		unsigned long address, unsigned int flags,
+		unsigned long *prot, resource_size_t *phys)
 {
 	pgd_t *pgd;
 	pud_t *pud;
@@ -2876,24 +2905,26 @@ static resource_size_t follow_phys(struct vm_area_struct *vma,
 	spinlock_t *ptl;
 	resource_size_t phys_addr = 0;
 	struct mm_struct *mm = vma->vm_mm;
+	int ret = -EINVAL;
 
-	VM_BUG_ON(!(vma->vm_flags & (VM_IO | VM_PFNMAP)));
+	if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
+		goto out;
 
 	pgd = pgd_offset(mm, address);
 	if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
-		goto no_page_table;
+		goto out;
 
 	pud = pud_offset(pgd, address);
 	if (pud_none(*pud) || unlikely(pud_bad(*pud)))
-		goto no_page_table;
+		goto out;
 
 	pmd = pmd_offset(pud, address);
 	if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
-		goto no_page_table;
+		goto out;
 
 	/* We cannot handle huge page PFN maps. Luckily they don't exist. */
 	if (pmd_huge(*pmd))
-		goto no_page_table;
+		goto out;
 
 	ptep = pte_offset_map_lock(mm, pmd, address, &ptl);
 	if (!ptep)
@@ -2908,13 +2939,13 @@ static resource_size_t follow_phys(struct vm_area_struct *vma,
 	phys_addr <<= PAGE_SHIFT; /* Shift here to avoid overflow on PAE */
 
 	*prot = pgprot_val(pte_pgprot(pte));
+	*phys = phys_addr;
+	ret = 0;
 
 unlock:
 	pte_unmap_unlock(ptep, ptl);
 out:
-	return phys_addr;
-no_page_table:
-	return 0;
+	return ret;
 }
 
 int generic_access_phys(struct vm_area_struct *vma, unsigned long addr,
@@ -2925,12 +2956,7 @@ int generic_access_phys(struct vm_area_struct *vma, unsigned long addr,
 	void *maddr;
 	int offset = addr & (PAGE_SIZE-1);
 
-	if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
-		return -EINVAL;
-
-	phys_addr = follow_phys(vma, addr, write, &prot);
-
-	if (!phys_addr)
+	if (follow_phys(vma, addr, write, &prot, &phys_addr))
 		return -EINVAL;
 
 	maddr = ioremap_prot(phys_addr, PAGE_SIZE, prot);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 6837a101437..b1737118546 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -22,7 +22,6 @@
 #include <linux/highmem.h>
 #include <linux/vmalloc.h>
 #include <linux/ioport.h>
-#include <linux/cpuset.h>
 #include <linux/delay.h>
 #include <linux/migrate.h>
 #include <linux/page-isolation.h>
@@ -190,7 +189,7 @@ static void grow_pgdat_span(struct pglist_data *pgdat, unsigned long start_pfn,
 					pgdat->node_start_pfn;
 }
 
-static int __add_zone(struct zone *zone, unsigned long phys_start_pfn)
+static int __meminit __add_zone(struct zone *zone, unsigned long phys_start_pfn)
 {
 	struct pglist_data *pgdat = zone->zone_pgdat;
 	int nr_pages = PAGES_PER_SECTION;
@@ -217,7 +216,7 @@ static int __add_zone(struct zone *zone, unsigned long phys_start_pfn)
 	return 0;
 }
 
-static int __add_section(struct zone *zone, unsigned long phys_start_pfn)
+static int __meminit __add_section(struct zone *zone, unsigned long phys_start_pfn)
 {
 	int nr_pages = PAGES_PER_SECTION;
 	int ret;
@@ -274,7 +273,7 @@ static int __remove_section(struct zone *zone, struct mem_section *ms)
  * call this function after deciding the zone to which to
  * add the new pages.
  */
-int __add_pages(struct zone *zone, unsigned long phys_start_pfn,
+int __ref __add_pages(struct zone *zone, unsigned long phys_start_pfn,
 		 unsigned long nr_pages)
 {
 	unsigned long i;
@@ -471,7 +470,8 @@ static void rollback_node_hotadd(int nid, pg_data_t *pgdat)
 }
 
 
-int add_memory(int nid, u64 start, u64 size)
+/* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */
+int __ref add_memory(int nid, u64 start, u64 size)
 {
 	pg_data_t *pgdat = NULL;
 	int new_pgdat = 0;
@@ -498,8 +498,6 @@ int add_memory(int nid, u64 start, u64 size)
 	/* we online node here. we can't roll back from here. */
 	node_set_online(nid);
 
-	cpuset_track_online_nodes();
-
 	if (new_pgdat) {
 		ret = register_one_node(nid);
 		/*
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 36f42573a33..e9493b1c111 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -489,12 +489,6 @@ check_range(struct mm_struct *mm, unsigned long start, unsigned long end,
 	int err;
 	struct vm_area_struct *first, *vma, *prev;
 
-	if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
-
-		err = migrate_prep();
-		if (err)
-			return ERR_PTR(err);
-	}
 
 	first = find_vma(mm, start);
 	if (!first)
@@ -809,9 +803,13 @@ int do_migrate_pages(struct mm_struct *mm,
 	const nodemask_t *from_nodes, const nodemask_t *to_nodes, int flags)
 {
 	int busy = 0;
-	int err = 0;
+	int err;
 	nodemask_t tmp;
 
+	err = migrate_prep();
+	if (err)
+		return err;
+
 	down_read(&mm->mmap_sem);
 
 	err = migrate_vmas(mm, from_nodes, to_nodes, flags);
@@ -974,6 +972,12 @@ static long do_mbind(unsigned long start, unsigned long len,
 		 start, start + len, mode, mode_flags,
 		 nmask ? nodes_addr(*nmask)[0] : -1);
 
+	if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
+
+		err = migrate_prep();
+		if (err)
+			return err;
+	}
 	down_write(&mm->mmap_sem);
 	vma = check_range(mm, start, end, nmask,
 			  flags | MPOL_MF_INVERT, &pagelist);
diff --git a/mm/migrate.c b/mm/migrate.c
index 6602941bfab..037b0967c1e 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -522,15 +522,12 @@ static int writeout(struct address_space *mapping, struct page *page)
 	remove_migration_ptes(page, page);
 
 	rc = mapping->a_ops->writepage(page, &wbc);
-	if (rc < 0)
-		/* I/O Error writing */
-		return -EIO;
 
 	if (rc != AOP_WRITEPAGE_ACTIVATE)
 		/* unlocked. Relock */
 		lock_page(page);
 
-	return -EAGAIN;
+	return (rc < 0) ? -EIO : -EAGAIN;
 }
 
 /*
@@ -841,12 +838,12 @@ static int do_move_page_to_node_array(struct mm_struct *mm,
 	struct page_to_node *pp;
 	LIST_HEAD(pagelist);
 
+	migrate_prep();
 	down_read(&mm->mmap_sem);
 
 	/*
 	 * Build a list of pages to migrate
 	 */
-	migrate_prep();
 	for (pp = pm; pp->node != MAX_NUMNODES; pp++) {
 		struct vm_area_struct *vma;
 		struct page *page;
@@ -990,25 +987,18 @@ out:
 /*
  * Determine the nodes of an array of pages and store it in an array of status.
  */
-static int do_pages_stat(struct mm_struct *mm, unsigned long nr_pages,
-			 const void __user * __user *pages,
-			 int __user *status)
+static void do_pages_stat_array(struct mm_struct *mm, unsigned long nr_pages,
+				const void __user **pages, int *status)
 {
 	unsigned long i;
-	int err;
 
 	down_read(&mm->mmap_sem);
 
 	for (i = 0; i < nr_pages; i++) {
-		const void __user *p;
-		unsigned long addr;
+		unsigned long addr = (unsigned long)(*pages);
 		struct vm_area_struct *vma;
 		struct page *page;
-
-		err = -EFAULT;
-		if (get_user(p, pages+i))
-			goto out;
-		addr = (unsigned long) p;
+		int err = -EFAULT;
 
 		vma = find_vma(mm, addr);
 		if (!vma)
@@ -1027,12 +1017,52 @@ static int do_pages_stat(struct mm_struct *mm, unsigned long nr_pages,
 
 		err = page_to_nid(page);
 set_status:
-		put_user(err, status+i);
+		*status = err;
+
+		pages++;
+		status++;
+	}
+
+	up_read(&mm->mmap_sem);
+}
+
+/*
+ * Determine the nodes of a user array of pages and store it in
+ * a user array of status.
+ */
+static int do_pages_stat(struct mm_struct *mm, unsigned long nr_pages,
+			 const void __user * __user *pages,
+			 int __user *status)
+{
+#define DO_PAGES_STAT_CHUNK_NR 16
+	const void __user *chunk_pages[DO_PAGES_STAT_CHUNK_NR];
+	int chunk_status[DO_PAGES_STAT_CHUNK_NR];
+	unsigned long i, chunk_nr = DO_PAGES_STAT_CHUNK_NR;
+	int err;
+
+	for (i = 0; i < nr_pages; i += chunk_nr) {
+		if (chunk_nr + i > nr_pages)
+			chunk_nr = nr_pages - i;
+
+		err = copy_from_user(chunk_pages, &pages[i],
+				     chunk_nr * sizeof(*chunk_pages));
+		if (err) {
+			err = -EFAULT;
+			goto out;
+		}
+
+		do_pages_stat_array(mm, chunk_nr, chunk_pages, chunk_status);
+
+		err = copy_to_user(&status[i], chunk_status,
+				   chunk_nr * sizeof(*chunk_status));
+		if (err) {
+			err = -EFAULT;
+			goto out;
+		}
 	}
 	err = 0;
 
 out:
-	up_read(&mm->mmap_sem);
 	return err;
 }
 
diff --git a/mm/mlock.c b/mm/mlock.c
index 008ea70b7af..1ada366570c 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -66,14 +66,10 @@ void __clear_page_mlock(struct page *page)
 		putback_lru_page(page);
 	} else {
 		/*
-		 * Page not on the LRU yet.  Flush all pagevecs and retry.
+		 * We lost the race. the page already moved to evictable list.
 		 */
-		lru_add_drain_all();
-		if (!isolate_lru_page(page))
-			putback_lru_page(page);
-		else if (PageUnevictable(page))
+		if (PageUnevictable(page))
 			count_vm_event(UNEVICTABLE_PGSTRANDED);
-
 	}
 }
 
@@ -166,7 +162,7 @@ static long __mlock_vma_pages_range(struct vm_area_struct *vma,
 	unsigned long addr = start;
 	struct page *pages[16]; /* 16 gives a reasonable batch */
 	int nr_pages = (end - start) / PAGE_SIZE;
-	int ret;
+	int ret = 0;
 	int gup_flags = 0;
 
 	VM_BUG_ON(start & ~PAGE_MASK);
@@ -187,8 +183,6 @@ static long __mlock_vma_pages_range(struct vm_area_struct *vma,
 	if (vma->vm_flags & VM_WRITE)
 		gup_flags |= GUP_FLAGS_WRITE;
 
-	lru_add_drain_all();	/* push cached pages to LRU */
-
 	while (nr_pages > 0) {
 		int i;
 
@@ -251,8 +245,6 @@ static long __mlock_vma_pages_range(struct vm_area_struct *vma,
 		ret = 0;
 	}
 
-	lru_add_drain_all();	/* to update stats */
-
 	return ret;	/* count entire vma as locked_vm */
 }
 
@@ -546,6 +538,8 @@ asmlinkage long sys_mlock(unsigned long start, size_t len)
 	if (!can_do_mlock())
 		return -EPERM;
 
+	lru_add_drain_all();	/* flush pagevec */
+
 	down_write(&current->mm->mmap_sem);
 	len = PAGE_ALIGN(len + (start & ~PAGE_MASK));
 	start &= PAGE_MASK;
@@ -612,6 +606,8 @@ asmlinkage long sys_mlockall(int flags)
 	if (!can_do_mlock())
 		goto out;
 
+	lru_add_drain_all();	/* flush pagevec */
+
 	down_write(&current->mm->mmap_sem);
 
 	lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur;
diff --git a/mm/mmap.c b/mm/mmap.c
index 74f4d158022..d4855a682ab 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -175,7 +175,8 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
 
 	/* Don't let a single process grow too big:
 	   leave 3% of the size of this process for other processes */
-	allowed -= mm->total_vm / 32;
+	if (mm)
+		allowed -= mm->total_vm / 32;
 
 	/*
 	 * cast `allowed' as a signed long because vm_committed_space
@@ -1703,7 +1704,7 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr)
 	vma = find_vma_prev(mm, addr, &prev);
 	if (vma &&am