Merge ../linus

Conflicts:

	drivers/cpufreq/cpufreq.c

35 files changed, 1325 insertions, 618 deletions

diff --git a/mm/Makefile b/mm/Makefile
index 12b3a4eee88..f3c077eb0b8 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -10,7 +10,8 @@ mmu-$(CONFIG_MMU)	:= fremap.o highmem.o madvise.o memory.o mincore.o \
 obj-y			:= bootmem.o filemap.o mempool.o oom_kill.o fadvise.o \
 			   page_alloc.o page-writeback.o pdflush.o \
 			   readahead.o swap.o truncate.o vmscan.o \
-			   prio_tree.o util.o mmzone.o vmstat.o $(mmu-y)
+			   prio_tree.o util.o mmzone.o vmstat.o backing-dev.o \
+			   $(mmu-y)
 
 ifeq ($(CONFIG_MMU)$(CONFIG_BLOCK),yy)
 obj-y			+= bounce.o
diff --git a/mm/allocpercpu.c b/mm/allocpercpu.c
index eaa9abeea53..b2486cf887a 100644
--- a/mm/allocpercpu.c
+++ b/mm/allocpercpu.c
@@ -17,10 +17,9 @@
 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;
-	}
+
+	kfree(pdata->ptrs[cpu]);
+	pdata->ptrs[cpu] = NULL;
 }
 EXPORT_SYMBOL_GPL(percpu_depopulate);
 
@@ -123,6 +122,8 @@ EXPORT_SYMBOL_GPL(__percpu_alloc_mask);
  */
 void percpu_free(void *__pdata)
 {
+	if (unlikely(!__pdata))
+		return;
 	__percpu_depopulate_mask(__pdata, &cpu_possible_map);
 	kfree(__percpu_disguise(__pdata));
 }
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
new file mode 100644
index 00000000000..f50a2811f9d
--- /dev/null
+++ b/mm/backing-dev.c
@@ -0,0 +1,69 @@
+
+#include <linux/wait.h>
+#include <linux/backing-dev.h>
+#include <linux/fs.h>
+#include <linux/sched.h>
+#include <linux/module.h>
+
+static wait_queue_head_t congestion_wqh[2] = {
+		__WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[0]),
+		__WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1])
+	};
+
+
+void clear_bdi_congested(struct backing_dev_info *bdi, int rw)
+{
+	enum bdi_state bit;
+	wait_queue_head_t *wqh = &congestion_wqh[rw];
+
+	bit = (rw == WRITE) ? BDI_write_congested : BDI_read_congested;
+	clear_bit(bit, &bdi->state);
+	smp_mb__after_clear_bit();
+	if (waitqueue_active(wqh))
+		wake_up(wqh);
+}
+EXPORT_SYMBOL(clear_bdi_congested);
+
+void set_bdi_congested(struct backing_dev_info *bdi, int rw)
+{
+	enum bdi_state bit;
+
+	bit = (rw == WRITE) ? BDI_write_congested : BDI_read_congested;
+	set_bit(bit, &bdi->state);
+}
+EXPORT_SYMBOL(set_bdi_congested);
+
+/**
+ * congestion_wait - wait for a backing_dev to become uncongested
+ * @rw: READ or WRITE
+ * @timeout: timeout in jiffies
+ *
+ * Waits for up to @timeout jiffies for a backing_dev (any backing_dev) to exit
+ * write congestion.  If no backing_devs are congested then just wait for the
+ * next write to be completed.
+ */
+long congestion_wait(int rw, long timeout)
+{
+	long ret;
+	DEFINE_WAIT(wait);
+	wait_queue_head_t *wqh = &congestion_wqh[rw];
+
+	prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
+	ret = io_schedule_timeout(timeout);
+	finish_wait(wqh, &wait);
+	return ret;
+}
+EXPORT_SYMBOL(congestion_wait);
+
+/**
+ * congestion_end - wake up sleepers on a congested backing_dev_info
+ * @rw: READ or WRITE
+ */
+void congestion_end(int rw)
+{
+	wait_queue_head_t *wqh = &congestion_wqh[rw];
+
+	if (waitqueue_active(wqh))
+		wake_up(wqh);
+}
+EXPORT_SYMBOL(congestion_end);
diff --git a/mm/bootmem.c b/mm/bootmem.c
index d53112fcb40..00a96970b23 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -27,8 +27,6 @@ unsigned long max_low_pfn;
 unsigned long min_low_pfn;
 unsigned long max_pfn;
 
-EXPORT_UNUSED_SYMBOL(max_pfn);  /*  June 2006  */
-
 static LIST_HEAD(bdata_list);
 #ifdef CONFIG_CRASH_DUMP
 /*
@@ -196,6 +194,10 @@ __alloc_bootmem_core(struct bootmem_data *bdata, unsigned long size,
 	if (limit && bdata->node_boot_start >= limit)
 		return NULL;
 
+	/* on nodes without memory - bootmem_map is NULL */
+	if (!bdata->node_bootmem_map)
+		return NULL;
+
 	end_pfn = bdata->node_low_pfn;
 	limit = PFN_DOWN(limit);
 	if (limit && end_pfn > limit)
diff --git a/mm/fadvise.c b/mm/fadvise.c
index 168c78a121b..0df4c899e97 100644
--- a/mm/fadvise.c
+++ b/mm/fadvise.c
@@ -38,7 +38,7 @@ asmlinkage long sys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice)
 	if (!file)
 		return -EBADF;
 
-	if (S_ISFIFO(file->f_dentry->d_inode->i_mode)) {
+	if (S_ISFIFO(file->f_path.dentry->d_inode->i_mode)) {
 		ret = -ESPIPE;
 		goto out;
 	}
diff --git a/mm/filemap.c b/mm/filemap.c
index 3464b681f84..8332c77b1bd 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -75,8 +75,8 @@ generic_file_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
  *  ->mmap_sem
  *    ->lock_page		(access_process_vm)
  *
- *  ->mmap_sem
- *    ->i_mutex			(msync)
+ *  ->i_mutex			(generic_file_buffered_write)
+ *    ->mmap_sem		(fault_in_pages_readable->do_page_fault)
  *
  *  ->i_mutex
  *    ->i_alloc_sem             (various)
@@ -467,25 +467,15 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
 }
 
 #ifdef CONFIG_NUMA
-struct page *page_cache_alloc(struct address_space *x)
+struct page *__page_cache_alloc(gfp_t gfp)
 {
 	if (cpuset_do_page_mem_spread()) {
 		int n = cpuset_mem_spread_node();
-		return alloc_pages_node(n, mapping_gfp_mask(x), 0);
+		return alloc_pages_node(n, gfp, 0);
 	}
-	return alloc_pages(mapping_gfp_mask(x), 0);
+	return alloc_pages(gfp, 0);
 }
-EXPORT_SYMBOL(page_cache_alloc);
-
-struct page *page_cache_alloc_cold(struct address_space *x)
-{
-	if (cpuset_do_page_mem_spread()) {
-		int n = cpuset_mem_spread_node();
-		return alloc_pages_node(n, mapping_gfp_mask(x)|__GFP_COLD, 0);
-	}
-	return alloc_pages(mapping_gfp_mask(x)|__GFP_COLD, 0);
-}
-EXPORT_SYMBOL(page_cache_alloc_cold);
+EXPORT_SYMBOL(__page_cache_alloc);
 #endif
 
 static int __sleep_on_page_lock(void *word)
@@ -826,7 +816,6 @@ struct page *
 grab_cache_page_nowait(struct address_space *mapping, unsigned long index)
 {
 	struct page *page = find_get_page(mapping, index);
-	gfp_t gfp_mask;
 
 	if (page) {
 		if (!TestSetPageLocked(page))
@@ -834,9 +823,8 @@ grab_cache_page_nowait(struct address_space *mapping, unsigned long index)
 		page_cache_release(page);
 		return NULL;
 	}
-	gfp_mask = mapping_gfp_mask(mapping) & ~__GFP_FS;
-	page = alloc_pages(gfp_mask, 0);
-	if (page && add_to_page_cache_lru(page, mapping, index, gfp_mask)) {
+	page = __page_cache_alloc(mapping_gfp_mask(mapping) & ~__GFP_FS);
+	if (page && add_to_page_cache_lru(page, mapping, index, GFP_KERNEL)) {
 		page_cache_release(page);
 		page = NULL;
 	}
@@ -1193,8 +1181,6 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
 		if (pos < size) {
 			retval = generic_file_direct_IO(READ, iocb,
 						iov, pos, nr_segs);
-			if (retval > 0 && !is_sync_kiocb(iocb))
-				retval = -EIOCBQUEUED;
 			if (retval > 0)
 				*ppos = pos + retval;
 		}
@@ -1457,7 +1443,6 @@ no_cached_page:
 	 * effect.
 	 */
 	error = page_cache_read(file, pgoff);
-	grab_swap_token();
 
 	/*
 	 * The page we want has now been added to the page cache.
@@ -1884,11 +1869,10 @@ repeat:
  *	if suid or (sgid and xgrp)
  *		remove privs
  */
-int remove_suid(struct dentry *dentry)
+int should_remove_suid(struct dentry *dentry)
 {
 	mode_t mode = dentry->d_inode->i_mode;
 	int kill = 0;
-	int result = 0;
 
 	/* suid always must be killed */
 	if (unlikely(mode & S_ISUID))
@@ -1901,13 +1885,29 @@ int remove_suid(struct dentry *dentry)
 	if (unlikely((mode & S_ISGID) && (mode & S_IXGRP)))
 		kill |= ATTR_KILL_SGID;
 
-	if (unlikely(kill && !capable(CAP_FSETID))) {
-		struct iattr newattrs;
+	if (unlikely(kill && !capable(CAP_FSETID)))
+		return kill;
 
-		newattrs.ia_valid = ATTR_FORCE | kill;
-		result = notify_change(dentry, &newattrs);
-	}
-	return result;
+	return 0;
+}
+EXPORT_SYMBOL(should_remove_suid);
+
+int __remove_suid(struct dentry *dentry, int kill)
+{
+	struct iattr newattrs;
+
+	newattrs.ia_valid = ATTR_FORCE | kill;
+	return notify_change(dentry, &newattrs);
+}
+
+int remove_suid(struct dentry *dentry)
+{
+	int kill = should_remove_suid(dentry);
+
+	if (unlikely(kill))
+		return __remove_suid(dentry, kill);
+
+	return 0;
 }
 EXPORT_SYMBOL(remove_suid);
 
@@ -2045,15 +2045,14 @@ generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
 	 * Sync the fs metadata but not the minor inode changes and
 	 * of course not the data as we did direct DMA for the IO.
 	 * i_mutex is held, which protects generic_osync_inode() from
-	 * livelocking.
+	 * livelocking.  AIO O_DIRECT ops attempt to sync metadata here.
 	 */
-	if (written >= 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
+	if ((written >= 0 || written == -EIOCBQUEUED) &&
+	    ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
 		int err = generic_osync_inode(inode, mapping, OSYNC_METADATA);
 		if (err < 0)
 			written = err;
 	}
-	if (written == count && !is_sync_kiocb(iocb))
-		written = -EIOCBQUEUED;
 	return written;
 }
 EXPORT_SYMBOL(generic_file_direct_write);
@@ -2222,7 +2221,7 @@ __generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov,
 				unsigned long nr_segs, loff_t *ppos)
 {
 	struct file *file = iocb->ki_filp;
-	const struct address_space * mapping = file->f_mapping;
+	struct address_space * mapping = file->f_mapping;
 	size_t ocount;		/* original count */
 	size_t count;		/* after file limit checks */
 	struct inode 	*inode = mapping->host;
@@ -2267,7 +2266,7 @@ __generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov,
 	if (count == 0)
 		goto out;
 
-	err = remove_suid(file->f_dentry);
+	err = remove_suid(file->f_path.dentry);
 	if (err)
 		goto out;
 
@@ -2275,8 +2274,11 @@ __generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov,
 
 	/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
 	if (unlikely(file->f_flags & O_DIRECT)) {
-		written = generic_file_direct_write(iocb, iov,
-				&nr_segs, pos, ppos, count, ocount);
+		loff_t endbyte;
+		ssize_t written_buffered;
+
+		written = generic_file_direct_write(iocb, iov, &nr_segs, pos,
+							ppos, count, ocount);
 		if (written < 0 || written == count)
 			goto out;
 		/*
@@ -2285,10 +2287,46 @@ __generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov,
 		 */
 		pos += written;
 		count -= written;
-	}
+		written_buffered = generic_file_buffered_write(iocb, iov,
+						nr_segs, pos, ppos, count,
+						written);
+		/*
+		 * If generic_file_buffered_write() retuned a synchronous error
+		 * then we want to return the number of bytes which were
+		 * direct-written, or the error code if that was zero.  Note
+		 * that this differs from normal direct-io semantics, which
+		 * will return -EFOO even if some bytes were written.
+		 */
+		if (written_buffered < 0) {
+			err = written_buffered;
+			goto out;
+		}
 
-	written = generic_file_buffered_write(iocb, iov, nr_segs,
-			pos, ppos, count, written);
+		/*
+		 * We need to ensure that the page cache pages are written to
+		 * disk and invalidated to preserve the expected O_DIRECT
+		 * semantics.
+		 */
+		endbyte = pos + written_buffered - written - 1;
+		err = do_sync_file_range(file, pos, endbyte,
+					 SYNC_FILE_RANGE_WAIT_BEFORE|
+					 SYNC_FILE_RANGE_WRITE|
+					 SYNC_FILE_RANGE_WAIT_AFTER);
+		if (err == 0) {
+			written = written_buffered;
+			invalidate_mapping_pages(mapping,
+						 pos >> PAGE_CACHE_SHIFT,
+						 endbyte >> PAGE_CACHE_SHIFT);
+		} else {
+			/*
+			 * We don't know how much we wrote, so just return
+			 * the number of bytes which were direct-written
+			 */
+		}
+	} else {
+		written = generic_file_buffered_write(iocb, iov, nr_segs,
+				pos, ppos, count, written);
+	}
 out:
 	current->backing_dev_info = NULL;
 	return written ? written : err;
diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c
index b4fd0d7c9bf..8d667617f55 100644
--- a/mm/filemap_xip.c
+++ b/mm/filemap_xip.c
@@ -379,7 +379,7 @@ xip_file_write(struct file *filp, const char __user *buf, size_t len,
 	if (count == 0)
 		goto out_backing;
 
-	ret = remove_suid(filp->f_dentry);
+	ret = remove_suid(filp->f_path.dentry);
 	if (ret)
 		goto out_backing;
 
diff --git a/mm/fremap.c b/mm/fremap.c
index 7a9d0f5d246..b77a002c335 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -101,7 +101,6 @@ int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma,
 {
 	int err = -ENOMEM;
 	pte_t *pte;
-	pte_t pte_val;
 	spinlock_t *ptl;
 
 	pte = get_locked_pte(mm, addr, &ptl);
@@ -114,7 +113,6 @@ int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma,
 	}
 
 	set_pte_at(mm, addr, pte, pgoff_to_pte(pgoff));
-	pte_val = *pte;
 	/*
 	 * We don't need to run update_mmu_cache() here because the "file pte"
 	 * being installed by install_file_pte() is not a real pte - it's a
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 2dbec90dc3b..0ccc7f23025 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -109,7 +109,7 @@ static int alloc_fresh_huge_page(void)
 	if (nid == MAX_NUMNODES)
 		nid = first_node(node_online_map);
 	if (page) {
-		page[1].lru.next = (void *)free_huge_page;	/* dtor */
+		set_compound_page_dtor(page, free_huge_page);
 		spin_lock(&hugetlb_lock);
 		nr_huge_pages++;
 		nr_huge_pages_node[page_to_nid(page)]++;
@@ -344,7 +344,6 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 			entry = *src_pte;
 			ptepage = pte_page(entry);
 			get_page(ptepage);
-			add_mm_counter(dst, file_rss, HPAGE_SIZE / PAGE_SIZE);
 			set_huge_pte_at(dst, addr, dst_pte, entry);
 		}
 		spin_unlock(&src->page_table_lock);
@@ -365,6 +364,11 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 	pte_t pte;
 	struct page *page;
 	struct page *tmp;
+	/*
+	 * A page gathering list, protected by per file i_mmap_lock. The
+	 * lock is used to avoid list corruption from multiple unmapping
+	 * of the same page since we are using page->lru.
+	 */
 	LIST_HEAD(page_list);
 
 	WARN_ON(!is_vm_hugetlb_page(vma));
@@ -372,24 +376,21 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 	BUG_ON(end & ~HPAGE_MASK);
 
 	spin_lock(&mm->page_table_lock);
-
-	/* Update high watermark before we lower rss */
-	update_hiwater_rss(mm);
-
 	for (address = start; address < end; address += HPAGE_SIZE) {
 		ptep = huge_pte_offset(mm, address);
 		if (!ptep)
 			continue;
 
+		if (huge_pmd_unshare(mm, &address, ptep))
+			continue;
+
 		pte = huge_ptep_get_and_clear(mm, address, ptep);
 		if (pte_none(pte))
 			continue;
 
 		page = pte_page(pte);
 		list_add(&page->lru, &page_list);
-		add_mm_counter(mm, file_rss, (int) -(HPAGE_SIZE / PAGE_SIZE));
 	}
-
 	spin_unlock(&mm->page_table_lock);
 	flush_tlb_range(vma, start, end);
 	list_for_each_entry_safe(page, tmp, &page_list, lru) {
@@ -478,6 +479,9 @@ int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
 retry:
 	page = find_lock_page(mapping, idx);
 	if (!page) {
+		size = i_size_read(mapping->host) >> HPAGE_SHIFT;
+		if (idx >= size)
+			goto out;
 		if (hugetlb_get_quota(mapping))
 			goto out;
 		page = alloc_huge_page(vma, address);
@@ -512,7 +516,6 @@ retry:
 	if (!pte_none(*ptep))
 		goto backout;
 
-	add_mm_counter(mm, file_rss, HPAGE_SIZE / PAGE_SIZE);
 	new_pte = make_huge_pte(vma, page, ((vma->vm_flags & VM_WRITE)
 				&& (vma->vm_flags & VM_SHARED)));
 	set_huge_pte_at(mm, address, ptep, new_pte);
@@ -650,11 +653,14 @@ void hugetlb_change_protection(struct vm_area_struct *vma,
 	BUG_ON(address >= end);
 	flush_cache_range(vma, address, end);
 
+	spin_lock(&vma->vm_file->f_mapping->i_mmap_lock);
 	spin_lock(&mm->page_table_lock);
 	for (; address < end; address += HPAGE_SIZE) {
 		ptep = huge_pte_offset(mm, address);
 		if (!ptep)
 			continue;
+		if (huge_pmd_unshare(mm, &address, ptep))
+			continue;
 		if (!pte_none(*ptep)) {
 			pte = huge_ptep_get_and_clear(mm, address, ptep);
 			pte = pte_mkhuge(pte_modify(pte, newprot));
@@ -663,6 +669,7 @@ void hugetlb_change_protection(struct vm_area_struct *vma,
 		}
 	}
 	spin_unlock(&mm->page_table_lock);
+	spin_unlock(&vma->vm_file->f_mapping->i_mmap_lock);
 
 	flush_tlb_range(vma, start, end);
 }
diff --git a/mm/memory.c b/mm/memory.c
index b5a4aadd961..bf6100236e6 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1110,23 +1110,29 @@ static int zeromap_pte_range(struct mm_struct *mm, pmd_t *pmd,
 {
 	pte_t *pte;
 	spinlock_t *ptl;
+	int err = 0;
 
 	pte = pte_alloc_map_lock(mm, pmd, addr, &ptl);
 	if (!pte)
-		return -ENOMEM;
+		return -EAGAIN;
 	arch_enter_lazy_mmu_mode();
 	do {
 		struct page *page = ZERO_PAGE(addr);
 		pte_t zero_pte = pte_wrprotect(mk_pte(page, prot));
+
+		if (unlikely(!pte_none(*pte))) {
+			err = -EEXIST;
+			pte++;
+			break;
+		}
 		page_cache_get(page);
 		page_add_file_rmap(page);
 		inc_mm_counter(mm, file_rss);
-		BUG_ON(!pte_none(*pte));
 		set_pte_at(mm, addr, pte, zero_pte);
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 	arch_leave_lazy_mmu_mode();
 	pte_unmap_unlock(pte - 1, ptl);
-	return 0;
+	return err;
 }
 
 static inline int zeromap_pmd_range(struct mm_struct *mm, pud_t *pud,
@@ -1134,16 +1140,18 @@ static inline int zeromap_pmd_range(struct mm_struct *mm, pud_t *pud,
 {
 	pmd_t *pmd;
 	unsigned long next;
+	int err;
 
 	pmd = pmd_alloc(mm, pud, addr);
 	if (!pmd)
-		return -ENOMEM;
+		return -EAGAIN;
 	do {
 		next = pmd_addr_end(addr, end);
-		if (zeromap_pte_range(mm, pmd, addr, next, prot))
-			return -ENOMEM;
+		err = zeromap_pte_range(mm, pmd, addr, next, prot);
+		if (err)
+			break;
 	} while (pmd++, addr = next, addr != end);
-	return 0;
+	return err;
 }
 
 static inline int zeromap_pud_range(struct mm_struct *mm, pgd_t *pgd,
@@ -1151,16 +1159,18 @@ static inline int zeromap_pud_range(struct mm_struct *mm, pgd_t *pgd,
 {
 	pud_t *pud;
 	unsigned long next;
+	int err;
 
 	pud = pud_alloc(mm, pgd, addr);
 	if (!pud)
-		return -ENOMEM;
+		return -EAGAIN;
 	do {
 		next = pud_addr_end(addr, end);
-		if (zeromap_pmd_range(mm, pud, addr, next, prot))
-			return -ENOMEM;
+		err = zeromap_pmd_range(mm, pud, addr, next, prot);
+		if (err)
+			break;
 	} while (pud++, addr = next, addr != end);
-	return 0;
+	return err;
 }
 
 int zeromap_page_range(struct vm_area_struct *vma,
@@ -1452,6 +1462,7 @@ static inline void cow_user_page(struct page *dst, struct page *src, unsigned lo
 		if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE))
 			memset(kaddr, 0, PAGE_SIZE);
 		kunmap_atomic(kaddr, KM_USER0);
+		flush_dcache_page(dst);
 		return;
 		
 	}
@@ -1901,7 +1912,6 @@ int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end)
 
 	return 0;
 }
-EXPORT_UNUSED_SYMBOL(vmtruncate_range);  /*  June 2006  */
 
 /**
  * swapin_readahead - swap in pages in hope we need them soon
@@ -1990,6 +2000,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	delayacct_set_flag(DELAYACCT_PF_SWAPIN);
 	page = lookup_swap_cache(entry);
 	if (!page) {
+		grab_swap_token(); /* Contend for token _before_ read-in */
  		swapin_readahead(entry, address, vma);
  		page = read_swap_cache_async(entry, vma, address);
 		if (!page) {
@@ -2007,7 +2018,6 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		/* Had to read the page from swap area: Major fault */
 		ret = VM_FAULT_MAJOR;
 		count_vm_event(PGMAJFAULT);
-		grab_swap_token();
 	}
 
 	delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index fd678a662ea..0c055a090f4 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -72,7 +72,6 @@ static int __add_zone(struct zone *zone, unsigned long phys_start_pfn)
 			return ret;
 	}
 	memmap_init_zone(nr_pages, nid, zone_type, phys_start_pfn);
-	zonetable_add(zone, nid, zone_type, phys_start_pfn, nr_pages);
 	return 0;
 }
 
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 617fb31086e..da946394655 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -141,9 +141,11 @@ static struct zonelist *bind_zonelist(nodemask_t *nodes)
 	enum zone_type k;
 
 	max = 1 + MAX_NR_ZONES * nodes_weight(*nodes);
+	max++;			/* space for zlcache_ptr (see mmzone.h) */
 	zl = kmalloc(sizeof(struct zone *) * max, GFP_KERNEL);
 	if (!zl)
 		return NULL;
+	zl->zlcache_ptr = NULL;
 	num = 0;
 	/* First put in the highest zones from all nodes, then all the next 
 	   lower zones etc. Avoid empty zones because the memory allocator
@@ -219,7 +221,7 @@ static int check_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 	orig_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	do {
 		struct page *page;
-		unsigned int nid;
+		int nid;
 
 		if (!pte_present(*pte))
 			continue;
@@ -1324,7 +1326,7 @@ struct mempolicy *__mpol_copy(struct mempolicy *old)
 	atomic_set(&new->refcnt, 1);
 	if (new->policy == MPOL_BIND) {
 		int sz = ksize(old->v.zonelist);
-		new->v.zonelist = kmemdup(old->v.zonelist, sz, SLAB_KERNEL);
+		new->v.zonelist = kmemdup(old->v.zonelist, sz, GFP_KERNEL);
 		if (!new->v.zonelist) {
 			kmem_cache_free(policy_cache, new);
 			return ERR_PTR(-ENOMEM);
@@ -1705,8 +1707,8 @@ void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new)
  * Display pages allocated per node and memory policy via /proc.
  */
 
-static const char *policy_types[] = { "default", "prefer", "bind",
-				      "interleave" };
+static const char * const policy_types[] =
+	{ "default", "prefer", "bind", "interleave" };
 
 /*
  * Convert a mempolicy into a string.
@@ -1855,7 +1857,7 @@ int show_numa_map(struct seq_file *m, void *v)
 
 	if (file) {
 		seq_printf(m, " file=");
-		seq_path(m, file->f_vfsmnt, file->f_dentry, "\n\t= ");
+		seq_path(m, file->f_path.mnt, file->f_path.dentry, "\n\t= ");
 	} else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) {
 		seq_printf(m, " heap");
 	} else if (vma->vm_start <= mm->start_stack &&
diff --git a/mm/migrate.c b/mm/migrate.c
index ba2453f9483..e9b161bde95 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -294,7 +294,7 @@ out:
 static int migrate_page_move_mapping(struct address_space *mapping,
 		struct page *newpage, struct page *page)
 {
-	struct page **radix_pointer;
+	void **pslot;
 
 	if (!mapping) {
 		/* Anonymous page */
@@ -305,12 +305,11 @@ static int migrate_page_move_mapping(struct address_space *mapping,
 
 	write_lock_irq(&mapping->tree_lock);
 
-	radix_pointer = (struct page **)radix_tree_lookup_slot(
-						&mapping->page_tree,
-						page_index(page));
+	pslot = radix_tree_lookup_slot(&mapping->page_tree,
+ 					page_index(page));
 
 	if (page_count(page) != 2 + !!PagePrivate(page) ||
-			*radix_pointer != page) {
+			(struct page *)radix_tree_deref_slot(pslot) != page) {
 		write_unlock_irq(&mapping->tree_lock);
 		return -EAGAIN;
 	}
@@ -318,7 +317,7 @@ static int migrate_page_move_mapping(struct address_space *mapping,
 	/*
 	 * Now we know that no one else is looking at the page.
 	 */
-	get_page(newpage);
+	get_page(newpage);	/* add cache reference */
 #ifdef CONFIG_SWAP
 	if (PageSwapCache(page)) {
 		SetPageSwapCache(newpage);
@@ -326,8 +325,14 @@ static int migrate_page_move_mapping(struct address_space *mapping,
 	}
 #endif
 
-	*radix_pointer = newpage;
+	radix_tree_replace_slot(pslot, newpage);
+
+	/*
+	 * Drop cache reference from old page.
+	 * We know this isn't the last reference.
+	 */
 	__put_page(page);
+
 	write_unlock_irq(&mapping->tree_lock);
 
 	return 0;
@@ -952,7 +957,8 @@ asmlinkage long sys_move_pages(pid_t pid, unsigned long nr_pages,
 				goto out;
 
 			pm[i].node = node;
-		}
+		} else
+			pm[i].node = 0;	/* anything to not match MAX_NUMNODES */
 	}
 	/* End marker */
 	pm[nr_pages].node = MAX_NUMNODES;
diff --git a/mm/mlock.c b/mm/mlock.c
index b90c59573ab..3446b7ef731 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -65,7 +65,7 @@ success:
 			ret = make_pages_present(start, end);
 	}
 
-	vma->vm_mm->locked_vm -= pages;
+	mm->locked_vm -= pages;
 out:
 	if (ret == -ENOMEM)
 		ret = -EAGAIN;
diff --git a/mm/mmap.c b/mm/mmap.c
index 497e502dfd6..9717337293c 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -188,7 +188,7 @@ static void __remove_shared_vm_struct(struct vm_area_struct *vma,
 		struct file *file, struct address_space *mapping)
 {
 	if (vma->vm_flags & VM_DENYWRITE)
-		atomic_inc(&file->f_dentry->d_inode->i_writecount);
+		atomic_inc(&file->f_path.dentry->d_inode->i_writecount);
 	if (vma->vm_flags & VM_SHARED)
 		mapping->i_mmap_writable--;
 
@@ -399,7 +399,7 @@ static inline void __vma_link_file(struct vm_area_struct *vma)
 		struct address_space *mapping = file->f_mapping;
 
 		if (vma->vm_flags & VM_DENYWRITE)
-			atomic_dec(&file->f_dentry->d_inode->i_writecount);
+			atomic_dec(&file->f_path.dentry->d_inode->i_writecount);
 		if (vma->vm_flags & VM_SHARED)
 			mapping->i_mmap_writable++;
 
@@ -907,7 +907,7 @@ unsigned long do_mmap_pgoff(struct file * file, unsigned long addr,
 	 *  mounted, in which case we dont add PROT_EXEC.)
 	 */
 	if ((prot & PROT_READ) && (current->personality & READ_IMPLIES_EXEC))
-		if (!(file && (file->f_vfsmnt->mnt_flags & MNT_NOEXEC)))
+		if (!(file && (file->f_path.mnt->mnt_flags & MNT_NOEXEC)))
 			prot |= PROT_EXEC;
 
 	if (!len)
@@ -960,7 +960,7 @@ unsigned long do_mmap_pgoff(struct file * file, unsigned long addr,
 			return -EAGAIN;
 	}
 
-	inode = file ? file->f_dentry->d_inode : NULL;
+	inode = file ? file->f_path.dentry->d_inode : NULL;
 
 	if (file) {
 		switch (flags & MAP_TYPE) {
@@ -989,7 +989,7 @@ unsigned long do_mmap_pgoff(struct file * file, unsigned long addr,
 		case MAP_PRIVATE:
 			if (!(file->f_mode & FMODE_READ))
 				return -EACCES;
-			if (file->f_vfsmnt->mnt_flags & MNT_NOEXEC) {
+			if (file->f_path.mnt->mnt_flags & MNT_NOEXEC) {
 				if (vm_flags & VM_EXEC)
 					return -EPERM;
 				vm_flags &= ~VM_MAYEXEC;
@@ -1379,7 +1379,7 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
 		 * Check if the given range is hugepage aligned, and
 		 * can be made suitable for hugepages.
 		 */
-		ret = prepare_hugepage_range(addr, len);
+		ret = prepare_hugepage_range(addr, len, pgoff);
 	} else {
 		/*
 		 * Ensure that a normal request is not falling in a
@@ -1736,7 +1736,7 @@ int split_vma(struct mm_struct * mm, struct vm_area_struct * vma,
 	if (mm->map_count >= sysctl_max_map_count)
 		return -ENOMEM;
 
-	new = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
+	new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
 	if (!new)
 		return -ENOMEM;
 
@@ -1880,6 +1880,9 @@ unsigned long do_brk(unsigned long addr, unsigned long len)
 	if ((addr + len) > TASK_SIZE || (addr + len) < addr)
 		return -EINVAL;
 
+	if (is_hugepage_only_range(mm, addr, len))
+		return -EINVAL;
+
 	flags = VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags;
 
 	error = arch_mmap_check(addr, len, flags);
@@ -2054,7 +2057,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
 		    vma_start < new_vma->vm_end)
 			*vmap = new_vma;
 	} else {
-		new_vma = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
+		new_vma = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
 		if (new_vma) {
 			*new_vma = *vma;
 			pol = mpol_copy(vma_policy(vma));
diff --git a/mm/mmzone.c b/mm/mmzone.c
index febea1c9816..eb5838634f1 100644
--- a/mm/mmzone.c
+++ b/mm/mmzone.c
@@ -14,8 +14,6 @@ struct pglist_data *first_online_pgdat(void)
 	return NODE_DATA(first_online_node);
 }
 
-EXPORT_UNUSED_SYMBOL(first_online_pgdat);  /*  June 2006  */
-
 struct pglist_data *next_online_pgdat(struct pglist_data *pgdat)
 {
 	int nid = next_online_node(pgdat->node_id);
@@ -24,8 +22,6 @@ struct pglist_data *next_online_pgdat(struct pglist_data *pgdat)
 		return NULL;
 	return NODE_DATA(nid);
 }
-EXPORT_UNUSED_SYMBOL(next_online_pgdat);  /*  June 2006  */
-
 
 /*
  * next_zone - helper magic for for_each_zone()
@@ -45,5 +41,4 @@ struct zone *next_zone(struct zone *zone)
 	}
 	return zone;
 }
-EXPORT_UNUSED_SYMBOL(next_zone);  /*  June 2006  */
 
diff --git a/mm/nommu.c b/mm/nommu.c
index 8bdde9508f3..23fb033e596 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -497,15 +497,17 @@ static int validate_mmap_request(struct file *file,
 	    (flags & MAP_TYPE) != MAP_SHARED)
 		return -EINVAL;
 
-	if (PAGE_ALIGN(len) == 0)
-		return addr;
-
-	if (len > TASK_SIZE)
+	if (!len)
 		return -EINVAL;
 
+	/* Careful about overflows.. */
+	len = PAGE_ALIGN(len);
+	if (!len || len > TASK_SIZE)
+		return -ENOMEM;
+
 	/* offset overflow? */
 	if ((pgoff + (len >> PAGE_SHIFT)) < pgoff)
-		return -EINVAL;
+		return -EOVERFLOW;
 
 	if (file) {
 		/* validate file mapping requests */
@@ -521,7 +523,7 @@ static int validate_mmap_request(struct file *file,
 		 */
 		mapping = file->f_mapping;
 		if (!mapping)
-			mapping = file->f_dentry->d_inode->i_mapping;
+			mapping = file->f_path.dentry->d_inode->i_mapping;
 
 		capabilities = 0;
 		if (mapping && mapping->backing_dev_info)
@@ -530,7 +532,7 @@ static int validate_mmap_request(struct file *file,
 		if (!capabilities) {
 			/* no explicit capabilities set, so assume some
 			 * defaults */
-			switch (file->f_dentry->d_inode->i_mode & S_IFMT) {
+			switch (file->f_path.dentry->d_inode->i_mode & S_IFMT) {
 			case S_IFREG:
 			case S_IFBLK:
 				capabilities = BDI_CAP_MAP_COPY;
@@ -561,11 +563,11 @@ static int validate_mmap_request(struct file *file,
 			    !(file->f_mode & FMODE_WRITE))
 				return -EACCES;
 
-			if (IS_APPEND(file->f_dentry->d_inode) &&
+			if (IS_APPEND(file->f_path.dentry->d_inode) &&
 			    (file->f_mode & FMODE_WRITE))
 				return -EACCES;
 
-			if (locks_verify_locked(file->f_dentry->d_inode))
+			if (locks_verify_locked(file->f_path.dentry->d_inode))
 				return -EAGAIN;
 
 			if (!(capabilities & BDI_CAP_MAP_DIRECT))
@@ -596,7 +598,7 @@ static int validate_mmap_request(struct file *file,
 
 		/* handle executable mappings and implied executable
 		 * mappings */
-		if (file->f_vfsmnt->mnt_flags & MNT_NOEXEC) {
+		if (file->f_path.mnt->mnt_flags & MNT_NOEXEC) {
 			if (prot & PROT_EXEC)
 				return -EPERM;
 		}
@@ -806,10 +808,9 @@ unsigned long do_mmap_pgoff(struct file *file,
 	vm_flags = determine_vm_flags(file, prot, flags, capabilities);
 
 	/* we're going to need to record the mapping if it works */
-	vml = kmalloc(sizeof(struct vm_list_struct), GFP_KERNEL);
+	vml = kzalloc(sizeof(struct vm_list_struct), GFP_KERNEL);
 	if (!vml)
 		goto error_getting_vml;
-	memset(vml, 0, sizeof(*vml));
 
 	down_write(&nommu_vma_sem);
 
@@ -832,7 +833,7 @@ unsigned long do_mmap_pgoff(struct file *file,
 				continue;
 
 			/* search for overlapping mappings on the same file */
-			if (vma->vm_file->f_dentry->d_inode != file->f_dentry->d_inode)
+			if (vma->vm_file->f_path.dentry->d_inode != file->f_path.dentry->d_inode)
 				continue;
 
 			if (vma->vm_pgoff >= pgoff + pglen)
@@ -885,11 +886,10 @@ unsigned long do_mmap_pgoff(struct file *file,
 	}
 
 	/* we're going to need a VMA struct as well */
-	vma = kmalloc(sizeof(struct vm_area_struct), GFP_KERNEL);
+	vma = kzalloc(sizeof(struct vm_area_struct), GFP_KERNEL);
 	if (!vma)
 		goto error_getting_vma;
 
-	memset(vma, 0, sizeof(*vma));
 	INIT_LIST_HEAD(&vma->anon_vma_node);
 	atomic_set(&vma->vm_usage, 1);
 	if (file)
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 20f41b082e1..223d9ccb7d6 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -15,6 +15,7 @@
  *  kernel subsystems and hints as to where to find out what things do.
  */
 
+#include <linux/oom.h>
 #include <linux/mm.h>
 #include <linux/sched.h>
 #include <linux/swap.h>
@@ -263,7 +264,7 @@ static struct task_struct *select_bad_process(unsigned long *ppoints)
  * flag though it's unlikely that  we select a process with CAP_SYS_RAW_IO
  * set.
  */
-static void __oom_kill_task(struct task_struct *p, const char *message)
+static void __oom_kill_task(struct task_struct *p, int verbose)
 {
 	if (is_init(p)) {
 		WARN_ON(1);
@@ -277,10 +278,8 @@ static void __oom_kill_task(struct task_struct *p, const char *message)
 		return;
 	}
 
-	if (message) {
-		printk(KERN_ERR "%s: Killed process %d (%s).\n",
-				message, p->pid, p->comm);
-	}
+	if (verbose)
+		printk(KERN_ERR "Killed process %d (%s)\n", p->pid, p->comm);
 
 	/*
 	 * We give our sacrificial lamb high priority and access to
@@ -293,7 +292,7 @@ static void __oom_kill_task(struct task_struct *p, const char *message)
 	force_sig(SIGKILL, p);
 }
 
-static int oom_kill_task(struct task_struct *p, const char *message)
+static int oom_kill_task(struct task_struct *p)
 {
 	struct mm_struct *mm;
 	struct task_struct *g, *q;
@@ -312,15 +311,25 @@ static int oom_kill_task(struct task_struct *p, const char *message)
 	if (mm == NULL)
 		return 1;
 
-	__oom_kill_task(p, message);
+	/*
+	 * Don't kill the process if any threads are set to OOM_DISABLE
+	 */
+	do_each_thread(g, q) {
+		if (q->mm == mm && p->oomkilladj == OOM_DISABLE)
+			return 1;
+	} while_each_thread(g, q);
+
+	__oom_kill_task(p, 1);
+
 	/*
 	 * kill all processes that share the ->mm (i.e. all threads),
-	 * but are in a different thread group
+	 * but are in a different thread group. Don't let them have access
+	 * to memory reserves though, otherwise we might deplete all memory.
 	 */
-	do_each_thread(g, q)
+	do_each_thread(g, q) {
 		if (q->mm == mm && q->tgid != p->tgid)
-			__oom_kill_task(q, message);
-	while_each_thread(g, q);
+			force_sig(SIGKILL, p);
+	} while_each_thread(g, q);
 
 	return 0;
 }
@@ -336,21 +345,22 @@ static int oom_kill_process(struct task_struct *p, unsigned long points,
 	 * its children or threads, just set TIF_MEMDIE so it can die quickly
 	 */
 	if (p->flags & PF_EXITING) {
-		__oom_kill_task(p, NULL);
+		__oom_kill_task(p, 0);
 		return 0;
 	}
 
-	printk(KERN_ERR "Out of Memory: Kill process %d (%s) score %li"
-			" and children.\n", p->pid, p->comm, points);
+	printk(KERN_ERR "%s: kill process %d (%s) score %li or a child\n",
+					message, p->pid, p->comm, points);
+
 	/* Try to kill a child first */
 	list_for_each(tsk, &p->children) {
 		c = list_entry(tsk, struct task_struct, sibling);
 		if (c->mm == p->mm)
 			continue;
-		if (!oom_kill_task(c, message))
+		if (!oom_kill_task(c))
 			return 0;
 	}
-	return oom_kill_task(p, message);
+	return oom_kill_task(p);
 }
 
 static BLOCKING_NOTIFIER_HEAD(oom_notify_list);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index a0f33905744..237107c1b08 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -21,6 +21,7 @@
 #include <linux/writeback.h>
 #include <linux/init.h>
 #include <linux/backing-dev.h>
+#include <linux/task_io_accounting_ops.h>
 #include <linux/blkdev.h>
 #include <linux/mpage.h>
 #include <linux/rmap.h>
@@ -222,7 +223,7 @@ static void balance_dirty_pages(struct address_space *mapping)
 			if (pages_written >= write_chunk)
 				break;		/* We've done our duty */
 		}
-		blk_congestion_wait(WRITE, HZ/10);
+		congestion_wait(WRITE, HZ/10);
 	}
 
 	if (nr_reclaimable + global_page_state(NR_WRITEBACK)
@@ -314,7 +315,7 @@ void throttle_vm_writeout(void)
                 if (global_page_state(NR_UNSTABLE_NFS) +
 			global_page_state(NR_WRITEBACK) <= dirty_thresh)
                         	break;
-                blk_congestion_wait(WRITE, HZ/10);
+                congestion_wait(WRITE, HZ/10);
         }
 }
 
@@ -351,7 +352,7 @@ static void background_writeout(unsigned long _min_pages)
 		min_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
 		if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) {
 			/* Wrote less than expected */
-			blk_congestion_wait(WRITE, HZ/10);
+			congestion_wait(WRITE, HZ/10);
 			if (!wbc.encountered_congestion)
 				break;
 		}
@@ -422,7 +423,7 @@ static void wb_kupdate(unsigned long arg)
 		writeback_inodes(&wbc);
 		if (wbc.nr_to_write > 0) {
 			if (wbc.encountered_congestion)
-				blk_congestion_wait(WRITE, HZ/10);
+				congestion_wait(WRITE, HZ/10);
 			else
 				break;	/* All the old data is written */
 		}
@@ -761,23 +762,24 @@ int __set_page_dirty_nobuffers(struct page *page)
 		struct address_space *mapping = page_mapping(page);
 		struct address_space *mapping2;
 
-		if (mapping) {
-			write_lock_irq(&mapping->tree_lock);
-			mapping2 = page_mapping(page);
-			if (mapping2) { /* Race with truncate? */
-				BUG_ON(mapping2 != mapping);
-				if (mapping_cap_account_dirty(mapping))
-					__inc_zone_page_state(page,
-								NR_FILE_DIRTY);
-				radix_tree_tag_set(&mapping->page_tree,
-					page_index(page), PAGECACHE_TAG_DIRTY);
-			}
-			write_unlock_irq(&mapping->tree_lock);
-			if (mapping->host) {
-				/* !PageAnon && !swapper_space */
-				__mark_inode_dirty(mapping->host,
-							I_DIRTY_PAGES);
+		if (!mapping)
+			return 1;
+
+		write_lock_irq(&mapping->tree_lock);
+		mapping2 = page_mapping(page);
+		if (mapping2) { /* Race with truncate? */
+			BUG_ON(mapping2 != mapping);
+			if (mapping_cap_account_dirty(mapping)) {
+				__inc_zone_page_state(page, NR_FILE_DIRTY);
+				task_io_account_write(PAGE_CACHE_SIZE);
 			}
+			radix_tree_tag_set(&mapping->page_tree,
+				page_index(page), PAGECACHE_TAG_DIRTY);
+		}
+		write_unlock_irq(&mapping->tree_lock);
+		if (mapping->host) {
+			/* !PageAnon && !swapper_space */
+			__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
 		}
 		return 1;
 	}
@@ -851,27 +853,26 @@ int test_clear_page_dirty(struct page *page)
 	struct address_space *mapping = page_mapping(page);
 	unsigned long flags;
 
-	if (mapping) {
-		write_lock_irqsave(&mapping->tree_lock, flags);
-		if (TestClearPageDirty(page)) {
-			radix_tree_tag_clear(&mapping->page_tree,
-						page_index(page),
-						PAGECACHE_TAG_DIRTY);
-			write_unlock_irqrestore(&mapping->tree_lock, flags);
-			/*
-			 * We can continue to use `mapping' here because the
-			 * page is locked, which pins the address_space
-			 */
-			if (mapping_cap_account_dirty(mapping)) {
-				page_mkclean(page);
-				dec_zone_page_state(page, NR_FILE_DIRTY);
-			}
-			return 1;
-		}
+	if (!mapping)
+		return TestClearPageDirty(page);
+
+	write_lock_irqsave(&mapping->tree_lock, flags);
+	if (TestClearPageDirty(page)) {
+		radix_tree_tag_clear(&mapping->page_tree,
+				page_index(page), PAGECACHE_TAG_DIRTY);
 		write_unlock_irqrestore(&mapping->tree_lock, flags);
-		return 0;
+		/*
+		 * We can continue to use `mapping' here because the
+		 * page is locked, which pins the address_space
+		 */
+		if (mapping_cap_account_dirty(mapping)) {
+			page_mkclean(page);
+			dec_zone_page_state(page, NR_FILE_DIRTY);
+		}
+		return 1;
 	}
-	return TestClearPageDirty(page);
+	write_unlock_irqrestore(&mapping->tree_lock, flags);
+	return 0;
 }
 EXPORT_SYMBOL(test_clear_page_dirty);
 
@@ -893,17 +894,17 @@ int clear_page_dirty_for_io(struct page *page)
 {
 	struct address_space *mapping = page_mapping(page);
 
-	if (mapping) {
-		if (TestClearPageDirty(page)) {
-			if (mapping_cap_account_dirty(mapping)) {
-				page_mkclean(page);
-				dec_zone_page_state(page, NR_FILE_DIRTY);
-			}
-			return 1;
+	if (!mapping)
+		return TestClearPageDirty(page);
+
+	if (TestClearPageDirty(page)) {
+		if (mapping_cap_account_dirty(mapping)) {
+			page_mkclean(page);
+			dec_zone_page_state(page, NR_FILE_DIRTY);
 		}
-		return 0;
+		return 1;
 	}
-	return TestClearPageDirty(page);
+	return 0;
 }
 EXPORT_SYMBOL(clear_page_dirty_for_io);
 
@@ -956,15 +957,6 @@ int test_set_page_writeback(struct page *page)
 EXPORT_SYMBOL(test_set_page_writeback);
 
 /*
- * Wakes up tasks that are being throttled due to writeback congestion
- */
-void writeback_congestion_end(void)
-{
-	blk_congestion_end(WRITE);
-}
-EXPORT_SYMBOL(writeback_congestion_end);
-
-/*
  * Return true if any of the pages in the mapping are marged with the
  * passed tag.
  */
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 40db96a655d..e6b17b2989e 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -39,6 +39,8 @@
 #include <linux/stop_machine.h>
 #include <linux/sort.h>
 #include <linux/pfn.h>
+#include <linux/backing-dev.h>
+#include <linux/fault-inject.h>
 
 #include <asm/tlbflush.h>
 #include <asm/div64.h>
@@ -82,14 +84,7 @@ int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1] = {
 
 EXPORT_SYMBOL(totalram_pages);
 
-/*
- * Used by page_zone() to look up the address of the struct zone whose
- * id is encoded in the upper bits of page->flags
- */
-struct zone *zone_table[1 << ZONETABLE_SHIFT] __read_mostly;
-EXPORT_SYMBOL(zone_table);
-
-static char *zone_names[MAX_NR_ZONES] = {
+static char * const zone_names[MAX_NR_ZONES] = {
 	 "DMA",
 #ifdef CONFIG_ZONE_DMA32
 	 "DMA32",
@@ -236,7 +231,7 @@ static void prep_compound_page(struct page *page, unsigned long order)
 	int i;
 	int nr_pages = 1 << order;
 
-	page[1].lru.next = (void *)free_compound_page;	/* set dtor */
+	set_compound_page_dtor(page, free_compound_page);
 	page[1].lru.prev = (void *)order;
 	for (i = 0; i < nr_pages; i++) {
 		struct page *p = page + i;
@@ -485,7 +480,7 @@ static void free_one_page(struct zone *zone, struct page *page, int order)
 	spin_lock(&zone->lock);
 	zone->all_unreclaimable = 0;
 	zone->pages_scanned = 0;
-	__free_one_page(page, zone ,order);
+	__free_one_page(page, zone, order);
 	spin_unlock(&zone->lock);
 }
 
@@ -604,6 +599,8 @@ static int prep_new_page(struct page *page, int order, gfp_t gfp_flags)
 			1 << PG_checked | 1 << PG_mappedtodisk);
 	set_page_private(page, 0);
 	set_page_refcounted(page);
+
+	arch_alloc_page(page, order);
 	kernel_map_pages(page, 1 << order, 1);
 
 	if (gfp_flags & __GFP_ZERO)
@@ -689,9 +686,15 @@ void drain_node_pages(int nodeid)
 
 			pcp = &pset->pcp[i];
 			if (pcp->count) {
+				int to_drain;
+
 				local_irq_save(flags);
-				free_pages_bulk(zone, pcp->count, &pcp->list, 0);
-				pcp->count = 0;
+				if (pcp->count >= pcp->batch)
+					to_drain = pcp->batch;
+				else
+					to_drain = pcp->count;
+				free_pages_bulk(zone, to_drain, &pcp->list, 0);
+				pcp->count -= to_drain;
 				local_irq_restore(flags);
 			}
 		}
@@ -699,7 +702,6 @@ void drain_node_pages(int nodeid)
 }
 #endif
 
-#if defined(CONFIG_PM) || defined(CONFIG_HOTPLUG_CPU)
 static void __drain_pages(unsigned int cpu)
 {
 	unsigned long flags;
@@ -721,7 +723,6 @@ static void __drain_pages(unsigned int cpu)
 		}
 	}
 }
-#endif /* CONFIG_PM || CONFIG_HOTPLUG_CPU */
 
 #ifdef CONFIG_PM
 
@@ -852,7 +853,7 @@ again:
 		pcp = &zone_pcp(zone, cpu)->pcp[cold];
 		local_irq_save(flags);
 		if (!pcp->count) {
-			pcp->count += rmqueue_bulk(zone, 0,
+			pcp->count = rmqueue_bulk(zone, 0,
 						pcp->batch, &pcp->list);
 			if (unlikely(!pcp->count))
 				goto failed;
@@ -892,6 +893,91 @@ failed:
 #define ALLOC_HIGH		0x20 /* __GFP_HIGH set */
 #define ALLOC_CPUSET		0x40 /* check for correct cpuset */
 
+#ifdef CONFIG_FAIL_PAGE_ALLOC
+
+static struct fail_page_alloc_attr {
+	struct fault_attr attr;
+
+	u32 ignore_gfp_highmem;
+	u32 ignore_gfp_wait;
+
+#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
+
+	struct dentry *ignore_gfp_highmem_file;
+	struct dentry *ignore_gfp_wait_file;
+
+#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */
+
+} fail_page_alloc = {
+	.attr = FAULT_ATTR_INITIALIZER,
+	.ignore_gfp_wait = 1,
+	.ignore_gfp_highmem = 1,
+};
+
+static int __init setup_fail_page_alloc(char *str)
+{
+	return setup_fault_attr(&fail_page_alloc.attr, str);
+}
+__setup("fail_page_alloc=", setup_fail_page_alloc);
+
+static int should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
+{
+	if (gfp_mask & __GFP_NOFAIL)
+		return 0;
+	if (fail_page_alloc.ignore_gfp_highmem && (gfp_mask & __GFP_HIGHMEM))
+		return 0;
+	if (fail_page_alloc.ignore_gfp_wait && (gfp_mask & __GFP_WAIT))
+		return 0;
+
+	return should_fail(&fail_page_alloc.attr, 1 << order);
+}
+
+#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
+
+static int __init fail_page_alloc_debugfs(void)
+{
+	mode_t mode = S_IFREG | S_IRUSR | S_IWUSR;
+	struct dentry *dir;
+	int err;
+
+	err = init_fault_attr_dentries(&fail_page_alloc.attr,
+				       "fail_page_alloc");
+	if (err)
+		return err;
+	dir = fail_page_alloc.attr.dentries.dir;
+
+	fail_page_alloc.ignore_gfp_wait_file =
+		debugfs_create_bool("ignore-gfp-wait", mode, dir,
+				      &fail_page_alloc.ignore_gfp_wait);
+
+	fail_page_alloc.ignore_gfp_highmem_file =
+		debugfs_create_bool("ignore-gfp-highmem", mode, dir,
+				      &fail_page_alloc.ignore_gfp_highmem);
+
+	if (!fail_page_alloc.ignore_gfp_wait_file ||
+			!fail_page_alloc.ignore_gfp_highmem_file) {
+		err = -ENOMEM;
+		debugfs_remove(fail_page_alloc.ignore_gfp_wait_file);
+		debugfs_remove(fail_page_alloc.ignore_gfp_highmem_file);
+		cleanup_fault_attr_dentries(&fail_page_alloc.attr);
+	}
+
+	return err;
+}
+
+late_initcall(fail_page_alloc_debugfs);
+
+#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */
+
+#else /* CONFIG_FAIL_PAGE_ALLOC */
+
+static inline int should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
+{
+	return 0;
+}
+
+#endif /* CONFIG_FAIL_PAGE_ALLOC */
+
 /*
  * Return 1 if free pages are above 'mark'. This takes into account the order
  * of the allocation.
@@ -924,31 +1010,160 @@ int zone_watermark_ok(struct zone *z, int order, unsigned long mark,
 	return 1;
 }
 
+#ifdef CONFIG_NUMA
+/*
+ * zlc_setup - Setup for "zonelist cache".  Uses cached zone data to
+ * skip over zones that are not allowed by the cpuset, or that have
+ * been recently (in last second) found to be nearly full.  See further
+ * comments in mmzone.h.  Reduces cache footprint of zonelist scans
+ * that have to skip over alot of full or unallowed zones.
+ *
+ * If the zonelist cache is present in the passed in zonelist, then
+ * returns a pointer to the allowed node mask (either the current
+ * tasks mems_allowed, or node_online_map.)
+ *
+ * If the zonelist cache is not available for this zonelist, does
+ * nothing and returns NULL.
+ *
+ * If the fullzones BITMAP in the zonelist cache is stale (more than
+ * a second since last zap'd) then we zap it out (clear its bits.)
+ *
+ * We hold off even calling zlc_setup, until after we've checked the
+ * first zone in the zonelist, on the theory that most allocations will
+ * be satisfied from that first zone, so best to examine that zone as
+ * quickly as we can.
+ */
+static nodemask_t *zlc_setup(struct zonelist *zonelist, int alloc_flags)
+{
+	struct zonelist_cache *zlc;	/* cached zonelist speedup info */
+	nodemask_t *allowednodes;	/* zonelist_cache approximation */
+
+	zlc = zonelist->zlcache_ptr;
+	if (!zlc)
+		return NULL;
+
+	if (jiffies - zlc->last_full_zap > 1 * HZ) {
+		bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST);
+		zlc->last_full_zap = jiffies;
+	}
+
+	allowednodes = !in_interrupt() && (alloc_flags & ALLOC_CPUSET) ?
+					&cpuset_current_mems_allowed :
+					&node_online_map;
+	return allowednodes;
+}
+
+/*
+ * Given 'z' scanning a zonelist, run a couple of quick checks to see
+ * if it is worth looking at further for free memory:
+ *  1) Check that the zone isn't thought to be full (doesn't have its
+ *     bit set in the zonelist_cache fullzones BITMAP).
+ *  2) Check that the zones node (obtained from the zonelist_cache
+ *     z_to_n[] mapping) is allowed in the passed in allowednodes mask.
+ * Return true (non-zero) if zone is worth looking at further, or
+ * else return false (zero) if it is not.
+ *
+ * This check -ignores- the distinction between various watermarks,
+ * such as GFP_HIGH, GFP_ATOMIC, PF_MEMALLOC, ...  If a zone is
+ * found to be full for any variation of these watermarks, it will
+ * be considered full for up to one second by all requests, unless
+ * we are so low on memory on all allowed nodes that we are forced
+ * into the second scan of the zonelist.
+ *
+ * In the second scan we ignore this zonelist cache and exactly
+ * apply the watermarks to all zones, even it is slower to do so.
+ * We are low on memory in the second scan, and should leave no stone
+ * unturned looking for a free page.
+ */
+static int zlc_zone_worth_trying(struct zonelist *zonelist, struct zone **z,
+						nodemask_t *allowednodes)
+{
+	struct zonelist_cache *zlc;	/* cached zonelist speedup info */
+	int i;				/* index of *z in zonelist zones */
+	int n;				/* node that zone *z is on */
+
+	zlc = zonelist->zlcache_ptr;
+	if (!zlc)
+		return 1;
+
+	i = z - zonelist->zones;
+	n = zlc->z_to_n[i];
+
+	/* This zone is worth trying if it is allowed but not full */
+	return node_isset(n, *allowednodes) && !test_bit(i, zlc->fullzones);
+}
+
 /*
- * get_page_from_freeliest goes through the zonelist trying to allocate
+ * Given 'z' scanning a zonelist, set the corresponding bit in
+ * zlc->fullzones, so that subsequent attempts to allocate a page
+ * from that zone don't waste time re-examining it.
+ */
+static void zlc_mark_zone_full(struct zonelist *zonelist, struct zone **z)
+{
+	struct zonelist_cache *zlc;	/* cached zonelist speedup info */
+	int i;				/* index of *z in zonelist zones */
+
+	zlc = zonelist->zlcache_ptr;
+	if (!zlc)
+		return;
+
+	i = z - zonelist->zones;
+
+	set_bit(i, zlc->fullzones);
+}
+
+#else	/* CONFIG_NUMA */
+
+static nodemask_t *zlc_setup(struct zonelist *zonelist, int alloc_flags)
+{
+	return NULL;
+}
+
+static int zlc_zone_worth_trying(struct zonelist *zonelist, struct zone **z,
+				nodemask_t *allowednodes)
+{
+	return 1;
+}
+
+static void zlc_mark_zone_full(struct zonelist *zonelist, struct zone **z)
+{
+}
+#endif	/* CONFIG_NUMA */
+
+/*
+ * get_page_from_freelist goes through the zonelist trying to allocate
  * a page.
  */
 static struct page *
 get_page_from_freelist(gfp_t gfp_mask, unsigned int order,
 		struct zonelist *zonelist, int alloc_flags)
 {
-	struct zone **z = zonelist->zones;
+	struct zone **z;
 	struct page *page = NULL;
-	int classzone_idx = zone_idx(*z);
+	int classzone_idx = zone_idx(zonelist->zones[0]);
 	struct zone *zone;
+	nodemask_t *allowednodes = NULL;/* zonelist_cache approximation */
+	int zlc_active = 0;		/* set if using zonelist_cache */
+	int did_zlc_setup = 0;		/* just call zlc_setup() one time */
 
+zonelist_scan:
 	/*
-	 * Go through the zonelist once, looking for a zone with enough free.
+	 * Scan zonelist, looking for a zone with enough free.
 	 * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
 	 */
+	z = zonelist->zones;
+
 	do {
+		if (NUMA_BUILD && zlc_active &&
+			!zlc_zone_worth_trying(zonelist, z, allowednodes))
+				continue;
 		zone = *z;
 		if (unlikely(NUMA_BUILD && (gfp_mask & __GFP_THISNODE) &&
 			zone->zone_pgdat != zonelist->zones[0]->zone_pgdat))
 				break;
 		if ((alloc_flags & ALLOC_CPUSET) &&
-				!cpuset_zone_allowed(zone, gfp_mask))
-			continue;
+			!cpuset_zone_allowed(zone, gfp_mask))
+				goto try_next_zone;
 
 		if (!(alloc_flags & ALLOC_NO_WATERMARKS)) {
 			unsigned long mark;
@@ -958,18 +1173,34 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order,
 				mark = zone->pages_low;
 			else
 				mark = zone->pages_high;
-			if (!zone_watermark_ok(zone , order, mark,
-				    classzone_idx, alloc_flags))
+			if (!zone_watermark_ok(zone, order, mark,
+				    classzone_idx, alloc_flags)) {
 				if (!zone_reclaim_mode ||
 				    !zone_reclaim(zone, gfp_mask, order))
-					continue;
+					goto this_zone_full;
+			}
 		}
 
 		page = buffered_rmqueue(zonelist, zone, order, gfp_mask);
-		if (page) {
+		if (page)
 			break;
+this_zone_full:
+		if (NUMA_BUILD)
+			zlc_mark_zone_full(zonelist, z);
+try_next_zone:
+		if (NUMA_BUILD && !did_zlc_setup) {
+			/* we do zlc_setup after the first zone is tried */
+			allowednodes = zlc_setup(zonelist, alloc_flags);
+			zlc_active = 1;
+			did_zlc_setup = 1;
 		}
 	} while (*(++z) != NULL);
+
+	if (unlikely(NUMA_BUILD && page == NULL && zlc_active)) {
+		/* Disable zlc cache for second zonelist scan */
+		zlc_active = 0;
+		goto zonelist_scan;
+	}
 	return page;
 }
 
@@ -991,6 +1222,9 @@ __alloc_pages(gfp_t gfp_mask, unsigned int order,
 
 	might_sleep_if(wait);
 
+	if (should_fail_alloc_page(gfp_mask, order))
+		return NULL;
+
 restart:
 	z = zonelist->zones;  /* the list of zones suitable for gfp_mask */
 
@@ -1004,9 +1238,19 @@ restart:
 	if (page)
 		goto got_pg;
 
-	do {
+	/*
+	 * GFP_THISNODE (meaning __GFP_THISNODE, __GFP_NORETRY and
+	 * __GFP_NOWARN set) should not cause reclaim since the subsystem
+	 * (f.e. slab) using GFP_THISNODE may choose to trigger reclaim
+	 * using a larger set of nodes after it has established that the
+	 * allowed per node queues are empty and that nodes are
+	 * over allocated.
+	 */
+	if (NUMA_BUILD && (gfp_mask & GFP_THISNODE) == GFP_THISNODE)
+		goto nopage;
+
+	for (z = zonelist->zones; *z; z++)
 		wakeup_kswapd(*z, order);
-	} while (*(++z));
 
 	/*
 	 * OK, we're below the kswapd watermark and have kicked background
@@ -1040,6 +1284,7 @@ restart:
 
 	/* This allocation should allow future memory freeing. */
 
+rebalance:
 	if (((p->flags & PF_MEMALLOC) || unlikely(test_thread_flag(TIF_MEMDIE)))
 			&& !in_interrupt()) {
 		if (!(gfp_mask & __GFP_NOMEMALLOC)) {
@@ -1050,7 +1295,7 @@ nofail_alloc:
 			if (page)
 				goto got_pg;
 			if (gfp_mask & __GFP_NOFAIL) {
-				blk_congestion_wait(WRITE, HZ/50);
+				congestion_wait(WRITE, HZ/50);
 				goto nofail_alloc;
 			}
 		}
@@ -1061,7 +1306,6 @@ nofail_alloc:
 	if (!wait)
 		goto nopage;
 
-rebalance:
 	cond_resched();
 
 	/* We now go into synchronous reclaim */
@@ -1113,7 +1357,7 @@ rebalance:
 			do_retry = 1;
 	}
 	if (do_retry) {
-		blk_congestion_wait(WRITE, HZ/50);
+		congestion_wait(WRITE, HZ/50);
 		goto rebalance;
 	}
 
@@ -1261,7 +1505,7 @@ unsigned int nr_free_pagecache_pages(void)
 static inline void show_node(struct zone *zone)
 {
 	if (NUMA_BUILD)
-		printk("Node %ld ", zone_to_nid(zone));
+		printk("Node %d ", zone_to_nid(zone));
 }
 
 void si_meminfo(struct sysinfo *val)
@@ -1541,6 +1785,24 @@ static void __meminit build_zonelists(pg_data_t *pgdat)
 	}
 }
 
+/* Construct the zonelist performance cache - see further mmzone.h */
+static void __meminit build_zonelist_cache(pg_data_t *pgdat)
+{
+	int i;
+
+	for (i = 0; i < MAX_NR_ZONES; i++) {
+		struct zonelist *zonelist;
+		struct zonelist_cache *zlc;
+		struct zone **z;
+
+		zonelist = pgdat->node_zonelists + i;
+		zonelist->zlcache_ptr = zlc = &zonelist->zlcache;
+		bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST);
+		for (z = zonelist->zones; *z; z++)
+			zlc->z_to_n[z - zonelist->zones] = zone_to_nid(*z);
+	}
+}
+
 #else	/* CONFIG_NUMA */
 
 static void __meminit build_zonelists(pg_data_t *pgdat)
@@ -1578,14 +1840,26 @@ static void __meminit build_zonelists(pg_data_t *pgdat)
 	}
 }
 
+/* non-NUMA variant of zonelist performance cache - just NULL zlcache_ptr */
+static void __meminit build_zonelist_cache(pg_data_t *pgdat)
+{
+	int i;
+
+	for (i = 0; i < MAX_NR_ZONES; i++)
+		pgdat->node_zonelists[i].zlcache_ptr = NULL;
+}
+
 #endif	/* CONFIG_NUMA */
 
 /* return values int ....just for stop_machine_run() */
 static int __meminit __build_all_zonelists(void *dummy)
 {
 	int nid;
-	for_each_online_node(nid)
+
+	for_each_online_node(nid) {
 		build_zonelists(NODE_DATA(nid));
+		build_zonelist_cache(NODE_DATA(nid));
+	}
 	return 0;
 }
 
@@ -1688,6 +1962,8 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 	for (pfn = start_pfn; pfn < end_pfn; pfn++) {
 		if (!early_pfn_valid(pfn))
 			continue;
+		if (!early_pfn_in_nid(pfn, nid))
+			continue;
 		page = pfn_to_page(pfn);
 		set_page_links(page, zone, nid, pfn);
 		init_page_count(page);
@@ -1712,20 +1988,6 @@ void zone_init_free_lists(struct pglist_data *pgdat, struct zone *zone,
 	}
 }
 
-#define ZONETABLE_INDEX(x, zone_nr)	((x << ZONES_SHIFT) | zone_nr)
-void zonetable_add(struct zone *zone, int nid, enum zone_type zid,
-		unsigned long pfn, unsigned long size)
-{
-	unsigned long snum = pfn_to_section_nr(pfn);
-	unsigned long end = pfn_to_section_nr(pfn + size);
-
-	if (FLAGS_HAS_NODE)
-		zone_table[ZONETABLE_INDEX(nid, zid)] = zone;
-	else
-		for (; snum <= end; snum++)
-			zone_table[ZONETABLE_INDEX(snum, zid)] = zone;
-}
-
 #ifndef __HAVE_ARCH_MEMMAP_INIT
 #define memmap_init(size, nid, zone, start_pfn) \
 	memmap_init_zone((size), (nid), (zone), (start_pfn))
@@ -1878,16 +2140,16 @@ static int __cpuinit pageset_cpuup_callback(struct notifier_block *nfb,
 	int ret = NOTIFY_OK;
 
 	switch (action) {
-		case CPU_UP_PREPARE:
-			if (process_zones(cpu))
-				ret = NOTIFY_BAD;
-			break;
-		case CPU_UP_CANCELED:
-		case CPU_DEAD:
-			free_zone_pagesets(cpu);
-			break;
-		default:
-			break;
+	case CPU_UP_PREPARE:
+		if (process_zones(cpu))
+			ret = NOTIFY_BAD;
+		break;
+	case CPU_UP_CANCELED:
+	case CPU_DEAD:
+		free_zone_pagesets(cpu);
+		break;
+	default:
+		break;
 	}
 	return ret;
 }
@@ -2258,7 +2520,7 @@ unsigned long __init __absent_pages_in_range(int nid,
 
 	/* Account for ranges past physical memory on this node */
 	if (range_end_pfn > prev_end_pfn)
-		hole_pages = range_end_pfn -
+		hole_pages += range_end_pfn -
 				max(range_start_pfn, prev_end_pfn);
 
 	return hole_pages;
@@ -2404,7 +2666,7 @@ static void __meminit free_area_init_core(struct pglist_data *pgdat,
 		zone->zone_pgdat = pgdat;
 		zone->free_pages = 0;
 
-		zone->temp_priority = zone->prev_priority = DEF_PRIORITY;
+		zone->prev_priority = DEF_PRIORITY;
 
 		zone_pcp_init(zone);
 		INIT_LIST_HEAD(&zone->active_list);
@@ -2418,7 +2680,6 @@ static void __meminit free_area_init_core(struct pglist_data *pgdat,
 		if (!size)
 			continue;
 
-		zonetable_add(zone, nid, j, zone_start_pfn, size);
 		ret = init_currently_empty_zone(zone, zone_start_pfn, size);
 		BUG_ON(ret);
 		zone_start_pfn += size;
@@ -2609,6 +2870,9 @@ unsigned long __init find_min_pfn_for_node(unsigned long nid)
 {
 	int i;
 
+	/* Regions in the early_node_map can be in any order */
+	sort_node_map();
+
 	/* 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;
@@ -2677,9 +2941,6 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn)
 			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++)
@@ -2733,7 +2994,6 @@ void __init free_area_init(unsigned long *zones_size)
 			__pa(PAGE_OFFSET) >> PAGE_SHIFT, NULL);
 }
 
-#ifdef CONFIG_HOTPLUG_CPU
 static int page_alloc_cpu_notify(struct notifier_block *self,
 				 unsigned long action, void *hcpu)
 {
@@ -2748,7 +3008,6 @@ static int page_alloc_cpu_notify(struct notifier_block *self,
 	}
 	return NOTIFY_OK;
 }
-#endif /* CONFIG_HOTPLUG_CPU */
 
 void __init page_alloc_init(void)
 {
@@ -3052,7 +3311,7 @@ void *__init alloc_large_system_hash(const char *tablename,
 	/* allow the kernel cmdline to have a say */
 	if (!numentries) {
 		/* round applicable memory size up to nearest megabyte */
-		numentries = (flags & HASH_HIGHMEM) ? nr_all_pages : nr_kernel_pages;
+		numentries = nr_kernel_pages;
 		numentries += (1UL << (20 - PAGE_SHIFT)) - 1;
 		numentries >>= 20 - PAGE_SHIFT;
 		numentries <<= 20 - PAGE_SHIFT;
@@ -3074,7 +3333,7 @@ void *__init alloc_large_system_hash(const char *tablename,
 	if (numentries > max)
 		numentries = max;
 
-	log2qty = long_log2(numentries);
+	log2qty = ilog2(numentries);
 
 	do {
 		size = bucketsize << log2qty;
@@ -3096,7 +3355,7 @@ void *__init alloc_large_system_hash(const char *tablename,
 	printk("%s hash table entries: %d (order: %d, %lu bytes)\n",
 	       tablename,
 	       (1U << log2qty),
-	       long_log2(size) - PAGE_SHIFT,
+	       ilog2(size) - PAGE_SHIFT,
 	       size);
 
 	if (_hash_shift)
@@ -3119,3 +3378,19 @@ unsigned long page_to_pfn(struct page *page)
 EXPORT_SYMBOL(pfn_to_page);
 EXPORT_SYMBOL(page_to_pfn);
 #endif /* CONFIG_OUT_OF_LINE_PFN_TO_PAGE */
+
+#if MAX_NUMNODES > 1
+/*
+ * Find the highest possible node id.
+ */
+int highest_possible_node_id(void)
+{
+	unsigned int node;
+	unsigned int highest = 0;
+
+	for_each_node_mask(node, node_possible_map)
+		highest = node;
+	return highest;
+}
+EXPORT_SYMBOL(highest_possible_node_id);
+#endif
diff --git a/mm/page_io.c b/mm/page_io.c
index d4840ecbf8f..dbffec0d78c 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -147,48 +147,3 @@ int swap_readpage(struct file *file, struct page *page)
 out:
 	return ret;
 }
-
-#ifdef CONFIG_SOFTWARE_SUSPEND
-/*
- * A scruffy utility function to read or write an arbitrary swap page
- * and wait on the I/O.  The caller must have a ref on the page.
- *
- * We use end_swap_bio_read() even for writes, because it happens to do what
- * we want.
- */
-int rw_swap_page_sync(int rw, swp_entry_t entry, struct page *page,
-			struct bio **bio_chain)
-{
-	struct bio *bio;
-	int ret = 0;
-	int bio_rw;
-
-	lock_page(page);
-
-	bio = get_swap_bio(GFP_KERNEL, entry.val, page, end_swap_bio_read);
-	if (bio == NULL) {
-		unlock_page(page);
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	bio_rw = rw;
-	if (!bio_chain)
-		bio_rw |= (1 << BIO_RW_SYNC);
-	if (bio_chain)
-		bio_get(bio);
-	submit_bio(bio_rw, bio);
-	if (bio_chain == NULL) {
-		wait_on_page_locked(page);
-
-		if (!PageUptodate(page) || PageError(page))
-			ret = -EIO;
-	}
-	if (bio_chain) {
-		bio->bi_private = *bio_chain;
-		*bio_chain = bio;
-	}
-out:
-	return ret;
-}
-#endif
diff --git a/mm/pdflush.c b/mm/pdflush.c
index b02102feeb4..8ce0900dc95 100644
--- a/mm/pdflush.c
+++ b/mm/pdflush.c
@@ -21,6 +21,7 @@
 #include <linux/writeback.h>	// Prototypes pdflush_operation()
 #include <linux/kthread.h>
 #include <linux/cpuset.h>
+#include <linux/freezer.h>
 
 
 /*
diff --git a/mm/readahead.c b/mm/readahead.c
index 1ba736ac036..0f539e8e827 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -13,6 +13,7 @@
 #include <linux/module.h>
 #include <linux/blkdev.h>
 #include <linux/backing-dev.h>
+#include <linux/task_io_accounting_ops.h>
 #include <linux/pagevec.h>
 
 void default_unplug_io_fn(struct backing_dev_info *bdi, struct page *page)
@@ -148,15 +149,10 @@ int read_cache_pages(struct address_space *mapping, struct list_head *pages,
 		if (!pagevec_add(&lru_pvec, page))
 			__pagevec_lru_add(&lru_pvec);
 		if (ret) {
-			while (!list_empty(pages)) {
-				struct page *victim;
-
-				victim = list_to_page(pages);
-				list_del(&victim->lru);
-				page_cache_release(victim);
-			}
+			put_pages_list(pages);
 			break;
 		}
+		task_io_account_read(PAGE_CACHE_SIZE);
 	}
 	pagevec_lru_add(&lru_pvec);
 	return ret;
@@ -173,6 +169,8 @@ static int read_pages(struct address_space *mapping, struct file *filp,
 
 	if (mapping->a_ops->readpages) {
 		ret = mapping->a_ops->readpages(filp, mapping, pages, nr_pages);
+		/* Clean up the remaining pages */
+		put_pages_list(pages);
 		goto out;
 	}
 
@@ -454,7 +452,7 @@ static int make_ahead_window(struct address_space *mapping, struct file *filp,
  *
  * Note that @filp is purely used for passing on to the ->readpage[s]()
  * handler: it may refer to a different file from @mapping (so we may not use
- * @filp->f_mapping or @filp->f_dentry->d_inode here).
+ * @filp->f_mapping or @filp->f_path.dentry->d_inode here).
  * Also, @ra may not be equal to &@filp->f_ra.
  *
  */
diff --git a/mm/rmap.c b/mm/rmap.c
index a9136d8b757..d8a842a586d 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -21,27 +21,21 @@
  * Lock ordering in mm:
  *
  * inode->i_mutex	(while writing or truncating, not reading or faulting)
- *   inode->i_alloc_sem
- *
- * When a page fault occurs in writing from user to file, down_read
- * of mmap_sem nests within i_mutex; in sys_msync, i_mutex nests within
- * down_read of mmap_sem; i_mutex and down_write of mmap_sem are never
- * taken together; in truncation, i_mutex is taken outermost.
- *
- * mm->mmap_sem
- *   page->flags PG_locked (lock_page)
- *     mapping->i_mmap_lock
- *       anon_vma->lock
- *         mm->page_table_lock or pte_lock
- *           zone->lru_lock (in mark_page_accessed, isolate_lru_page)
- *           swap_lock (in swap_duplicate, swap_info_get)
- *             mmlist_lock (in mmput, drain_mmlist and others)
- *             mapping->private_lock (in __set_page_dirty_buffers)
- *             inode_lock (in set_page_dirty's __mark_inode_dirty)
- *               sb_lock (within inode_lock in fs/fs-writeback.c)
- *               mapping->tree_lock (widely used, in set_page_dirty,
- *                         in arch-dependent flush_dcache_mmap_lock,
- *                         within inode_lock in __sync_single_inode)
+ *   inode->i_alloc_sem (vmtruncate_range)
+ *   mm->mmap_sem
+ *     page->flags PG_locked (lock_page)
+ *       mapping->i_mmap_lock
+ *         anon_vma->lock
+ *           mm->page_table_lock or pte_lock
+ *             zone->lru_lock (in mark_page_accessed, isolate_lru_page)
+ *             swap_lock (in swap_duplicate, swap_info_get)
+ *               mmlist_lock (in mmput, drain_mmlist and others)
+ *               mapping->private_lock (in __set_page_dirty_buffers)
+ *               inode_lock (in set_page_dirty's __mark_inode_dirty)
+ *                 sb_lock (within inode_lock in fs/fs-writeback.c)
+ *                 mapping->tree_lock (widely used, in set_page_dirty,
+ *                           in arch-dependent flush_dcache_mmap_lock,
+ *                           within inode_lock in __sync_single_inode)
  */
 
 #include <linux/mm.h>
diff --git a/mm/shmem.c b/mm/shmem.c
index bb8ca7ef709..4bb28d218eb 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -48,6 +48,7 @@
 #include <linux/ctype.h>
 #include <linux/migrate.h>
 #include <linux/highmem.h>
+#include <linux/backing-dev.h>
 
 #include <asm/uaccess.h>
 #include <asm/div64.h>
@@ -176,7 +177,7 @@ static inline void shmem_unacct_blocks(unsigned long flags, long pages)
 
 static struct super_operations shmem_ops;
 static const struct address_space_operations shmem_aops;
-static struct file_operations shmem_file_operations;
+static const struct file_operations shmem_file_operations;
 static struct inode_operations shmem_inode_operations;
 static struct inode_operations shmem_dir_inode_operations;
 static struct inode_operations shmem_special_inode_operations;
@@ -1131,7 +1132,7 @@ repeat:
 			page_cache_release(swappage);
 			if (error == -ENOMEM) {
 				/* let kswapd refresh zone for GFP_ATOMICs */
-				blk_congestion_wait(WRITE, HZ/50);
+				congestion_wait(WRITE, HZ/50);
 			}
 			goto repeat;
 		}
@@ -1224,7 +1225,7 @@ failed:
 
 struct page *shmem_nopage(struct vm_area_struct *vma, unsigned long address, int *type)
 {
-	struct inode *inode = vma->vm_file->f_dentry->d_inode;
+	struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
 	struct page *page = NULL;
 	unsigned long idx;
 	int error;
@@ -1247,7 +1248,7 @@ static int shmem_populate(struct vm_area_struct *vma,
 	unsigned long addr, unsigned long len,
 	pgprot_t prot, unsigned long pgoff, int nonblock)
 {
-	struct inode *inode = vma->vm_file->f_dentry->d_inode;
+	struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
 	struct mm_struct *mm = vma->vm_mm;
 	enum sgp_type sgp = nonblock? SGP_QUICK: SGP_CACHE;
 	unsigned long size;
@@ -1292,14 +1293,14 @@ static int shmem_populate(struct vm_area_struct *vma,
 #ifdef CONFIG_NUMA
 int shmem_set_policy(struct vm_area_struct *vma, struct mempolicy *new)
 {
-	struct inode *i = vma->vm_file->f_dentry->d_inode;
+	struct inode *i = vma->vm_file->f_path.dentry->d_inode;
 	return mpol_set_shared_policy(&SHMEM_I(i)->policy, vma, new);
 }
 
 struct mempolicy *
 shmem_get_policy(struct vm_area_struct *vma, unsigned long addr)
 {
-	struct inode *i = vma->vm_file->f_dentry->d_inode;
+	struct inode *i = vma->vm_file->f_path.dentry->d_inode;
 	unsigned long idx;
 
 	idx = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
@@ -1309,7 +1310,7 @@ shmem_get_policy(struct vm_area_struct *vma, unsigned long addr)
 
 int shmem_lock(struct file *file, int lock, struct user_struct *user)
 {
-	struct inode *inode = file->f_dentry->d_inode;
+	struct inode *inode = file->f_path.dentry->d_inode;
 	struct shmem_inode_info *info = SHMEM_I(inode);
 	int retval = -ENOMEM;
 
@@ -1362,6 +1363,7 @@ shmem_get_inode(struct super_block *sb, int mode, dev_t dev)
 		inode->i_mapping->a_ops = &shmem_aops;
 		inode->i_mapping->backing_dev_info = &shmem_backing_dev_info;
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+		inode->i_generation = get_seconds();
 		info = SHMEM_I(inode);
 		memset(info, 0, (char *)inode - (char *)info);
 		spin_lock_init(&info->lock);
@@ -1420,7 +1422,7 @@ shmem_prepare_write(struct file *file, struct page *page, unsigned offset, unsig
 static ssize_t
 shmem_file_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
 {
-	struct inode	*inode = file->f_dentry->d_inode;
+	struct inode	*inode = file->f_path.dentry->d_inode;
 	loff_t		pos;
 	unsigned long	written;
 	ssize_t		err;
@@ -1440,7 +1442,7 @@ shmem_file_write(struct file *file, const char __user *buf, size_t count, loff_t
 	if (err || !count)
 		goto out;
 
-	err = remove_suid(file->f_dentry);
+	err = remove_suid(file->f_path.dentry);
 	if (err)
 		goto out;
 
@@ -1522,7 +1524,7 @@ out:
 
 static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_t *desc, read_actor_t actor)
 {
-	struct inode *inode = filp->f_dentry->d_inode;
+	struct inode *inode = filp->f_path.dentry->d_inode;
 	struct address_space *mapping = inode->i_mapping;
 	unsigned long index, offset;
 
@@ -1941,7 +1943,7 @@ static int shmem_xattr_security_set(struct inode *inode, const char *name,
 	return security_inode_setsecurity(inode, name, value, size, flags);
 }
 
-struct xattr_handler shmem_xattr_security_handler = {
+static struct xattr_handler shmem_xattr_security_handler = {
 	.prefix = XATTR_SECURITY_PREFIX,
 	.list   = shmem_xattr_security_list,
 	.get    = shmem_xattr_security_get,
@@ -1956,6 +1958,85 @@ static struct xattr_handler *shmem_xattr_handlers[] = {
 };
 #endif
 
+static struct dentry *shmem_get_parent(struct dentry *child)
+{
+	return ERR_PTR(-ESTALE);
+}
+
+static int shmem_match(struct inode *ino, void *vfh)
+{
+	__u32 *fh = vfh;
+	__u64 inum = fh[2];
+	inum = (inum << 32) | fh[1];
+	return ino->i_ino == inum && fh[0] == ino->i_generation;
+}
+
+static struct dentry *shmem_get_dentry(struct super_block *sb, void *vfh)
+{
+	struct dentry *de = NULL;
+	struct inode *inode;
+	__u32 *fh = vfh;
+	__u64 inum = fh[2];
+	inum = (inum << 32) | fh[1];
+
+	inode = ilookup5(sb, (unsigned long)(inum+fh[0]), shmem_match, vfh);
+	if (inode) {
+		de = d_find_alias(inode);
+		iput(inode);
+	}
+
+	return de? de: ERR_PTR(-ESTALE);
+}
+
+static struct dentry *shmem_decode_fh(struct super_block *sb, __u32 *fh,
+		int len, int type,
+		int (*acceptable)(void *context, struct dentry *de),
+		void *context)
+{
+	if (len < 3)
+		return ERR_PTR(-ESTALE);
+
+	return sb->s_export_op->find_exported_dentry(sb, fh, NULL, acceptable,
+							context);
+}
+
+static int shmem_encode_fh(struct dentry *dentry, __u32 *fh, int *len,
+				int connectable)
+{
+	struct inode *inode = dentry->d_inode;
+
+	if (*len < 3)
+		return 255;
+
+	if (hlist_unhashed(&inode->i_hash)) {
+		/* Unfortunately insert_inode_hash is not idempotent,
+		 * so as we hash inodes here rather than at creation
+		 * time, we need a lock to ensure we only try
+		 * to do it once
+		 */
+		static DEFINE_SPINLOCK(lock);
+		spin_lock(&lock);
+		if (hlist_unhashed(&inode->i_hash))
+			__insert_inode_hash(inode,
+					    inode->i_ino + inode->i_generation);
+		spin_unlock(&lock);
+	}
+
+	fh[0] = inode->i_generation;
+	fh[1] = inode->i_ino;
+	fh[2] = ((__u64)inode->i_ino) >> 32;
+
+	*len = 3;
+	return 1;
+}
+
+static struct export_operations shmem_export_ops = {
+	.get_parent     = shmem_get_parent,
+	.get_dentry     = shmem_get_dentry,
+	.encode_fh      = shmem_encode_fh,
+	.decode_fh      = shmem_decode_fh,
+};
+
 static int shmem_parse_options(char *options, int *mode, uid_t *uid,
 	gid_t *gid, unsigned long *blocks, unsigned long *inodes,
 	int *policy, nodemask_t *policy_nodes)
@@ -2128,6 +2209,7 @@ static int shmem_fill_super(struct super_block *sb,
 					&inodes, &policy, &policy_nodes))
 			return -EINVAL;
 	}
+	sb->s_export_op = &shmem_export_ops;
 #else
 	sb->s_flags |= MS_NOUSER;
 #endif
@@ -2181,7 +2263,7 @@ static struct kmem_cache *shmem_inode_cachep;
 static struct inode *shmem_alloc_inode(struct super_block *sb)
 {
 	struct shmem_inode_info *p;
-	p = (struct shmem_inode_info *)kmem_cache_alloc(shmem_inode_cachep, SLAB_KERNEL);
+	p = (struct shmem_inode_info *)kmem_cache_alloc(shmem_inode_cachep, GFP_KERNEL);
 	if (!p)
 		return NULL;
 	return &p->vfs_inode;
@@ -2237,7 +2319,7 @@ static const struct address_space_operations shmem_aops = {
 	.migratepage	= migrate_page,
 };
 
-static struct file_operations shmem_file_operations = {
+static const struct file_operations shmem_file_operations = {
 	.mmap		= shmem_mmap,
 #ifdef CONFIG_TMPFS
 	.llseek		= generic_file_llseek,
@@ -2411,8 +2493,8 @@ struct file *shmem_file_setup(char *name, loff_t size, unsigned long flags)
 	d_instantiate(dentry, inode);
 	inode->i_size = size;
 	inode->i_nlink = 0;	/* It is unlinked */
-	file->f_vfsmnt = mntget(shm_mnt);
-	file->f_dentry = dentry;
+	file->f_path.mnt = mntget(shm_mnt);
+	file->f_path.dentry = dentry;
 	file->f_mapping = inode->i_mapping;
 	file->f_op = &shmem_file_operations;
 	file->f_mode = FMODE_WRITE | FMODE_READ;
diff --git a/mm/slab.c b/mm/slab.c
index 266449d604b..2c655532f5e 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -103,12 +103,13 @@
 #include	<linux/module.h>
 #include	<linux/rcupdate.h>
 #include	<linux/string.h>
+#include	<linux/uaccess.h>
 #include	<linux/nodemask.h>
 #include	<linux/mempolicy.h>
 #include	<linux/mutex.h>
+#include	<linux/fault-inject.h>
 #include	<linux/rtmutex.h>
 
-#include	<asm/uaccess.h>
 #include	<asm/cacheflush.h>
 #include	<asm/tlbflush.h>
 #include	<asm/page.h>
@@ -313,7 +314,7 @@ static int drain_freelist(struct kmem_cache *cache,
 static void free_block(struct kmem_cache *cachep, void **objpp, int len,
 			int node);
 static int enable_cpucache(struct kmem_cache *cachep);
-static void cache_reap(void *unused);
+static void cache_reap(struct work_struct *unused);
 
 /*
  * This function must be completely optimized away if a constant is passed to
@@ -730,7 +731,10 @@ static inline void init_lock_keys(void)
 }
 #endif
 
-/* Guard access to the cache-chain. */
+/*
+ * 1. Guard access to the cache-chain.
+ * 2. Protect sanity of cpu_online_map against cpu hotplug events
+ */
 static DEFINE_MUTEX(cache_chain_mutex);
 static struct list_head cache_chain;
 
@@ -753,7 +757,7 @@ int slab_is_available(void)
 	return g_cpucache_up == FULL;
 }
 
-static DEFINE_PER_CPU(struct work_struct, reap_work);
+static DEFINE_PER_CPU(struct delayed_work, reap_work);
 
 static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep)
 {
@@ -866,6 +870,22 @@ static void __slab_error(const char *function, struct kmem_cache *cachep,
 	dump_stack();
 }
 
+/*
+ * By default on NUMA we use alien caches to stage the freeing of
+ * objects allocated from other nodes. This causes massive memory
+ * inefficiencies when using fake NUMA setup to split memory into a
+ * large number of small nodes, so it can be disabled on the command
+ * line
+  */
+
+static int use_alien_caches __read_mostly = 1;
+static int __init noaliencache_setup(char *s)
+{
+	use_alien_caches = 0;
+	return 1;
+}
+__setup("noaliencache", noaliencache_setup);
+
 #ifdef CONFIG_NUMA
 /*
  * Special reaping functions for NUMA systems called from cache_reap().
@@ -883,7 +903,7 @@ static void init_reap_node(int cpu)
 	if (node == MAX_NUMNODES)
 		node = first_node(node_online_map);
 
-	__get_cpu_var(reap_node) = node;
+	per_cpu(reap_node, cpu) = node;
 }
 
 static void next_reap_node(void)
@@ -916,17 +936,18 @@ static void next_reap_node(void)
  */
 static void __devinit start_cpu_timer(int cpu)
 {
-	struct work_struct *reap_work = &per_cpu(reap_work, cpu);
+	struct delayed_work *reap_work = &per_cpu(reap_work, cpu);
 
 	/*
 	 * When this gets called from do_initcalls via cpucache_init(),
 	 * init_workqueues() has already run, so keventd will be setup
 	 * at that time.
 	 */
-	if (keventd_up() && reap_work->func == NULL) {
+	if (keventd_up() && reap_work->work.func == NULL) {
 		init_reap_node(cpu);
-		INIT_WORK(reap_work, cache_reap, NULL);
-		schedule_delayed_work_on(cpu, reap_work, HZ + 3 * cpu);
+		INIT_DELAYED_WORK(reap_work, cache_reap);
+		schedule_delayed_work_on(cpu, reap_work,
+					__round_jiffies_relative(HZ, cpu));
 	}
 }
 
@@ -996,7 +1017,7 @@ static inline void *alternate_node_alloc(struct kmem_cache *cachep,
 	return NULL;
 }
 
-static inline void *__cache_alloc_node(struct kmem_cache *cachep,
+static inline void *____cache_alloc_node(struct kmem_cache *cachep,
 		 gfp_t flags, int nodeid)
 {
 	return NULL;
@@ -1004,7 +1025,7 @@ static inline void *__cache_alloc_node(struct kmem_cache *cachep,
 
 #else	/* CONFIG_NUMA */
 
-static void *__cache_alloc_node(struct kmem_cache *, gfp_t, int);
+static void *____cache_alloc_node(struct kmem_cache *, gfp_t, int);
 static void *alternate_node_alloc(struct kmem_cache *, gfp_t);
 
 static struct array_cache **alloc_alien_cache(int node, int limit)
@@ -1114,7 +1135,7 @@ static inline int cache_free_alien(struct kmem_cache *cachep, void *objp)
 	 * Make sure we are not freeing a object from another node to the array
 	 * cache on this cpu.
 	 */
-	if (likely(slabp->nodeid == node))
+	if (likely(slabp->nodeid == node) || unlikely(!use_alien_caches))
 		return 0;
 
 	l3 = cachep->nodelists[node];
@@ -1192,7 +1213,7 @@ static int __cpuinit cpuup_callback(struct notifier_block *nfb,
 		list_for_each_entry(cachep, &cache_chain, next) {
 			struct array_cache *nc;
 			struct array_cache *shared;
-			struct array_cache **alien;
+			struct array_cache **alien = NULL;
 
 			nc = alloc_arraycache(node, cachep->limit,
 						cachep->batchcount);
@@ -1204,9 +1225,11 @@ static int __cpuinit cpuup_callback(struct notifier_block *nfb,
 			if (!shared)
 				goto bad;
 
-			alien = alloc_alien_cache(node, cachep->limit);
-			if (!alien)
-				goto bad;
+			if (use_alien_caches) {
+                                alien = alloc_alien_cache(node, cachep->limit);
+                                if (!alien)
+                                        goto bad;
+                        }
 			cachep->array[cpu] = nc;
 			l3 = cachep->nodelists[node];
 			BUG_ON(!l3);
@@ -1230,12 +1253,18 @@ static int __cpuinit cpuup_callback(struct notifier_block *nfb,
 			kfree(shared);
 			free_alien_cache(alien);
 		}
-		mutex_unlock(&cache_chain_mutex);
 		break;
 	case CPU_ONLINE:
+		mutex_unlock(&cache_chain_mutex);
 		start_cpu_timer(cpu);
 		break;
 #ifdef CONFIG_HOTPLUG_CPU
+	case CPU_DOWN_PREPARE:
+		mutex_lock(&cache_chain_mutex);
+		break;
+	case CPU_DOWN_FAILED:
+		mutex_unlock(&cache_chain_mutex);
+		break;
 	case CPU_DEAD:
 		/*
 		 * Even if all the cpus of a node are down, we don't free the
@@ -1246,8 +1275,8 @@ static int __cpuinit cpuup_callback(struct notifier_block *nfb,
 		 * gets destroyed at kmem_cache_destroy().
 		 */
 		/* fall thru */
+#endif
 	case CPU_UP_CANCELED:
-		mutex_lock(&cache_chain_mutex);
 		list_for_each_entry(cachep, &cache_chain, next) {
 			struct array_cache *nc;
 			struct array_cache *shared;
@@ -1308,11 +1337,9 @@ free_array_cache:
 		}
 		mutex_unlock(&cache_chain_mutex);
 		break;
-#endif
 	}
 	return NOTIFY_OK;
 bad:
-	mutex_unlock(&cache_chain_mutex);
 	return NOTIFY_BAD;
 }
 
@@ -1580,12 +1607,7 @@ static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid)
 	flags |= __GFP_COMP;
 #endif
 
-	/*
-	 * 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;
+	flags |= cachep->gfpflags;
 
 	page = alloc_pages_node(nodeid, flags, cachep->gfporder);
 	if (!page)
@@ -2098,15 +2120,12 @@ kmem_cache_create (const char *name, size_t size, size_t align,
 	}
 
 	/*
-	 * Prevent CPUs from coming and going.
-	 * lock_cpu_hotplug() nests outside cache_chain_mutex
+	 * We use cache_chain_mutex to ensure a consistent view of
+	 * cpu_online_map as well.  Please see cpuup_callback
 	 */
-	lock_cpu_hotplug();
-
 	mutex_lock(&cache_chain_mutex);
 
 	list_for_each_entry(pc, &cache_chain, next) {
-		mm_segment_t old_fs = get_fs();
 		char tmp;
 		int res;
 
@@ -2115,9 +2134,7 @@ kmem_cache_create (const char *name, size_t size, size_t align,
 		 * destroy its slab cache and no-one else reuses the vmalloc
 		 * area of the module.  Print a warning.
 		 */
-		set_fs(KERNEL_DS);
-		res = __get_user(tmp, pc->name);
-		set_fs(old_fs);
+		res = probe_kernel_address(pc->name, tmp);
 		if (res) {
 			printk("SLAB: cache with size %d has lost its name\n",
 			       pc->buffer_size);
@@ -2197,25 +2214,24 @@ kmem_cache_create (const char *name, size_t size, size_t align,
 	if (flags & SLAB_RED_ZONE || flags & SLAB_STORE_USER)
 		ralign = BYTES_PER_WORD;
 
-	/* 2) arch mandated alignment: disables debug if necessary */
+	/* 2) arch mandated alignment */
 	if (ralign < ARCH_SLAB_MINALIGN) {
 		ralign = ARCH_SLAB_MINALIGN;
-		if (ralign > BYTES_PER_WORD)
-			flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER);
 	}
-	/* 3) caller mandated alignment: disables debug if necessary */
+	/* 3) caller mandated alignment */
 	if (ralign < align) {
 		ralign = align;
-		if (ralign > BYTES_PER_WORD)
-			flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER);
 	}
+	/* disable debug if necessary */
+	if (ralign > BYTES_PER_WORD)
+		flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER);
 	/*
 	 * 4) Store it.
 	 */
 	align = ralign;
 
 	/* Get cache's description obj. */
-	cachep = kmem_cache_zalloc(&cache_cache, SLAB_KERNEL);
+	cachep = kmem_cache_zalloc(&cache_cache, GFP_KERNEL);
 	if (!cachep)
 		goto oops;
 
@@ -2326,7 +2342,6 @@ oops:
 		panic("kmem_cache_create(): failed to create slab `%s'\n",
 		      name);
 	mutex_unlock(&cache_chain_mutex);
-	unlock_cpu_hotplug();
 	return cachep;
 }
 EXPORT_SYMBOL(kmem_cache_create);
@@ -2444,6 +2459,7 @@ out:
 	return nr_freed;
 }
 
+/* Called with cache_chain_mutex held to protect against cpu hotplug */
 static int __cache_shrink(struct kmem_cache *cachep)
 {
 	int ret = 0, i = 0;
@@ -2474,9 +2490,13 @@ static int __cache_shrink(struct kmem_cache *cachep)
  */
 int kmem_cache_shrink(struct kmem_cache *cachep)
 {
+	int ret;
 	BUG_ON(!cachep || in_interrupt());
 
-	return __cache_shrink(cachep);
+	mutex_lock(&cache_chain_mutex);
+	ret = __cache_shrink(cachep);
+	mutex_unlock(&cache_chain_mutex);
+	return ret;
 }
 EXPORT_SYMBOL(kmem_cache_shrink);
 
@@ -2500,23 +2520,16 @@ void kmem_cache_destroy(struct kmem_cache *cachep)
 {
 	BUG_ON(!cachep || in_interrupt());
 
-	/* Don't let CPUs to come and go */
-	lock_cpu_hotplug();
-
 	/* Find the cache in the chain of caches. */
 	mutex_lock(&cache_chain_mutex);
 	/*
 	 * the chain is never empty, cache_cache is never destroyed
 	 */
 	list_del(&cachep->next);
-	mutex_unlock(&cache_chain_mutex);
-
 	if (__cache_shrink(cachep)) {
 		slab_error(cachep, "Can't free all objects");
-		mutex_lock(&cache_chain_mutex);
 		list_add(&cachep->next, &cache_chain);
 		mutex_unlock(&cache_chain_mutex);
-		unlock_cpu_hotplug();
 		return;
 	}
 
@@ -2524,7 +2537,7 @@ void kmem_cache_destroy(struct kmem_cache *cachep)
 		synchronize_rcu();
 
 	__kmem_cache_destroy(cachep);
-	unlock_cpu_hotplug();
+	mutex_unlock(&cache_chain_mutex);
 }
 EXPORT_SYMBOL(kmem_cache_destroy);
 
@@ -2548,7 +2561,7 @@ static struct slab *alloc_slabmgmt(struct kmem_cache *cachep, void *objp,
 	if (OFF_SLAB(cachep)) {
 		/* Slab management obj is off-slab. */
 		slabp = kmem_cache_alloc_node(cachep->slabp_cache,
-					      local_flags, nodeid);
+					      local_flags & ~GFP_THISNODE, nodeid);
 		if (!slabp)
 			return NULL;
 	} else {
@@ -2618,7 +2631,7 @@ static void cache_init_objs(struct kmem_cache *cachep,
 
 static void kmem_flagcheck(struct kmem_cache *cachep, gfp_t flags)
 {
-	if (flags & SLAB_DMA)
+	if (flags & GFP_DMA)
 		BUG_ON(!(cachep->gfpflags & GFP_DMA));
 	else
 		BUG_ON(cachep->gfpflags & GFP_DMA);
@@ -2689,10 +2702,10 @@ static void slab_map_pages(struct kmem_cache *cache, struct slab *slab,
  * Grow (by 1) the number of slabs within a cache.  This is called by
  * kmem_cache_alloc() when there are no active objs left in a cache.
  */
-static int cache_grow(struct kmem_cache *cachep, gfp_t flags, int nodeid)
+static int cache_grow(struct kmem_cache *cachep,
+		gfp_t flags, int nodeid, void *objp)
 {
 	struct slab *slabp;
-	void *objp;
 	size_t offset;
 	gfp_t local_flags;
 	unsigned long ctor_flags;
@@ -2702,12 +2715,12 @@ static int cache_grow(struct kmem_cache *cachep, gfp_t flags, int nodeid)
 	 * Be lazy and only check for valid flags here,  keeping it out of the
 	 * critical path in kmem_cache_alloc().
 	 */
-	BUG_ON(flags & ~(SLAB_DMA | SLAB_LEVEL_MASK | SLAB_NO_GROW));
-	if (flags & SLAB_NO_GROW)
+	BUG_ON(flags & ~(GFP_DMA | GFP_LEVEL_MASK | __GFP_NO_GROW));
+	if (flags & __GFP_NO_GROW)
 		return 0;
 
 	ctor_flags = SLAB_CTOR_CONSTRUCTOR;
-	local_flags = (flags & SLAB_LEVEL_MASK);
+	local_flags = (flags & GFP_LEVEL_MASK);
 	if (!(local_flags & __GFP_WAIT))
 		/*
 		 * Not allowed to sleep.  Need to tell a constructor about
@@ -2744,12 +2757,14 @@ static int cache_grow(struct kmem_cache *cachep, gfp_t flags, int nodeid)
 	 * Get mem for the objs.  Attempt to allocate a physical page from
 	 * 'nodeid'.
 	 */
-	objp = kmem_getpages(cachep, flags, nodeid);
+	if (!objp)
+		objp = kmem_getpages(cachep, flags, nodeid);
 	if (!objp)
 		goto failed;
 
 	/* Get slab management. */
-	slabp = alloc_slabmgmt(cachep, objp, offset, local_flags, nodeid);
+	slabp = alloc_slabmgmt(cachep, objp, offset,
+			local_flags & ~GFP_THISNODE, nodeid);
 	if (!slabp)
 		goto opps1;
 
@@ -2987,7 +3002,7 @@ alloc_done:
 
 	if (unlikely(!ac->avail)) {
 		int x;
-		x = cache_grow(cachep, flags, node);
+		x = cache_grow(cachep, flags | GFP_THISNODE, node, NULL);
 
 		/* cache_grow can reenable interrupts, then ac could change. */
 		ac = cpu_cache_get(cachep);
@@ -3063,18 +3078,101 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep,
 
 		cachep->ctor(objp, cachep, ctor_flags);
 	}
+#if ARCH_SLAB_MINALIGN
+	if ((u32)objp & (ARCH_SLAB_MINALIGN-1)) {
+		printk(KERN_ERR "0x%p: not aligned to ARCH_SLAB_MINALIGN=%d\n",
+		       objp, ARCH_SLAB_MINALIGN);
+	}
+#endif
 	return objp;
 }
 #else
 #define cache_alloc_debugcheck_after(a,b,objp,d) (objp)
 #endif
 
+#ifdef CONFIG_FAILSLAB
+
+static struct failslab_attr {
+
+	struct fault_attr attr;
+
+	u32 ignore_gfp_wait;
+#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
+	struct dentry *ignore_gfp_wait_file;
+#endif
+
+} failslab = {
+	.attr = FAULT_ATTR_INITIALIZER,
+	.ignore_gfp_wait = 1,
+};
+
+static int __init setup_failslab(char *str)
+{
+	return setup_fault_attr(&failslab.attr, str);
+}
+__setup("failslab=", setup_failslab);
+
+static int should_failslab(struct kmem_cache *cachep, gfp_t flags)
+{
+	if (cachep == &cache_cache)
+		return 0;
+	if (flags & __GFP_NOFAIL)
+		return 0;
+	if (failslab.ignore_gfp_wait && (flags & __GFP_WAIT))
+		return 0;
+
+	return should_fail(&failslab.attr, obj_size(cachep));
+}
+
+#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
+
+static int __init failslab_debugfs(void)
+{
+	mode_t mode = S_IFREG | S_IRUSR | S_IWUSR;
+	struct dentry *dir;
+	int err;
+
+       	err = init_fault_attr_dentries(&failslab.attr, "failslab");
+	if (err)
+		return err;
+	dir = failslab.attr.dentries.dir;
+
+	failslab.ignore_gfp_wait_file =
+		debugfs_create_bool("ignore-gfp-wait", mode, dir,
+				      &failslab.ignore_gfp_wait);
+
+	if (!failslab.ignore_gfp_wait_file) {
+		err = -ENOMEM;
+		debugfs_remove(failslab.ignore_gfp_wait_file);
+		cleanup_fault_attr_dentries(&failslab.attr);
+	}
+
+	return err;
+}
+
+late_initcall(failslab_debugfs);
+
+#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */
+
+#else /* CONFIG_FAILSLAB */
+
+static inline int should_failslab(struct kmem_cache *cachep, gfp_t flags)
+{
+	return 0;
+}
+
+#endif /* CONFIG_FAILSLAB */
+
 static inline void *____cache_alloc(struct kmem_cache *cachep, gfp_t flags)
 {
 	void *objp;
 	struct array_cache *ac;
 
 	check_irq_off();
+
+	if (should_failslab(cachep, flags))
+		return NULL;
+
 	ac = cpu_cache_get(cachep);
 	if (likely(ac->avail)) {
 		STATS_INC_ALLOCHIT(cachep);
@@ -3105,10 +3203,10 @@ static __always_inline void *__cache_alloc(struct kmem_cache *cachep,
 		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
+	 * ____cache_alloc_node() knows how to locate memory on other nodes
 	 */
  	if (NUMA_BUILD && !objp)
- 		objp = __cache_alloc_node(cachep, flags, numa_node_id());
+ 		objp = ____cache_alloc_node(cachep, flags, numa_node_id());
 	local_irq_restore(save_flags);
 	objp = cache_alloc_debugcheck_after(cachep, flags, objp,
 					    caller);
@@ -3135,15 +3233,17 @@ static void *alternate_node_alloc(struct kmem_cache *cachep, gfp_t flags)
 	else if (current->mempolicy)
 		nid_alloc = slab_node(current->mempolicy);
 	if (nid_alloc != nid_here)
-		return __cache_alloc_node(cachep, flags, nid_alloc);
+		return ____cache_alloc_node(cachep, flags, nid_alloc);
 	return NULL;
 }
 
 /*
  * 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.
+ * certain node and fall back is permitted. First we scan all the
+ * available nodelists for available objects. If that fails then we
+ * perform an allocation without specifying a node. This allows the page
+ * allocator to do its reclaim / fallback magic. We then insert the
+ * slab into the proper nodelist and then allocate from it.
  */
 void *fallback_alloc(struct kmem_cache *cache, gfp_t flags)
 {
@@ -3151,20 +3251,59 @@ void *fallback_alloc(struct kmem_cache *cache, gfp_t flags)
 					->node_zonelists[gfp_zone(flags)];
 	struct zone **z;
 	void *obj = NULL;
+	int nid;
 
-	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));
+retry:
+	/*
+	 * Look through allowed nodes for objects available
+	 * from existing per node queues.
+	 */
+	for (z = zonelist->zones; *z && !obj; z++) {
+		nid = zone_to_nid(*z);
+
+		if (cpuset_zone_allowed(*z, flags | __GFP_HARDWALL) &&
+			cache->nodelists[nid] &&
+			cache->nodelists[nid]->free_objects)
+				obj = ____cache_alloc_node(cache,
+					flags | GFP_THISNODE, nid);
+	}
+
+	if (!obj) {
+		/*
+		 * This allocation will be performed within the constraints
+		 * of the current cpuset / memory policy requirements.
+		 * We may trigger various forms of reclaim on the allowed
+		 * set and go into memory reserves if necessary.
+		 */
+		obj = kmem_getpages(cache, flags, -1);
+		if (obj) {
+			/*
+			 * Insert into the appropriate per node queues
+			 */
+			nid = page_to_nid(virt_to_page(obj));
+			if (cache_grow(cache, flags, nid, obj)) {
+				obj = ____cache_alloc_node(cache,
+					flags | GFP_THISNODE, nid);
+				if (!obj)
+					/*
+					 * Another processor may allocate the
+					 * objects in the slab since we are
+					 * not holding any locks.
+					 */
+					goto retry;
+			} else {
+				kmem_freepages(cache, obj);
+				obj = NULL;
+			}
+		}
+	}
 	return obj;
 }
 
 /*
  * A interface to enable slab creation on nodeid
  */
-static void *__cache_alloc_node(struct kmem_cache *cachep, gfp_t flags,
+static void *____cache_alloc_node(struct kmem_cache *cachep, gfp_t flags,
 				int nodeid)
 {
 	struct list_head *entry;
@@ -3213,7 +3352,7 @@ retry:
 
 must_grow:
 	spin_unlock(&l3->list_lock);
-	x = cache_grow(cachep, flags, nodeid);
+	x = cache_grow(cachep, flags | GFP_THISNODE, nodeid, NULL);
 	if (x)
 		goto retry;
 
@@ -3431,35 +3570,59 @@ out:
  * @flags: See kmalloc().
  * @nodeid: node number of the target node.
  *
- * Identical to kmem_cache_alloc, except that this function is slow
- * and can sleep. And it will allocate memory on the given node, which
- * can improve the performance for cpu bound structures.
- * New and improved: it will now make sure that the object gets
- * put on the correct node list so that there is no false sharing.
+ * Identical to kmem_cache_alloc but it will allocate memory on the given
+ * node, which can improve the performance for cpu bound structures.
+ *
+ * Fallback to other node is possible if __GFP_THISNODE is not set.
  */
-void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid)
+static __always_inline void *
+__cache_alloc_node(struct kmem_cache *cachep, gfp_t flags,
+		int nodeid, void *caller)
 {
 	unsigned long save_flags;
-	void *ptr;
+	void *ptr = NULL;
 
 	cache_alloc_debugcheck_before(cachep, flags);
 	local_irq_save(save_flags);
 
-	if (nodeid == -1 || nodeid == numa_node_id() ||
-			!cachep->nodelists[nodeid])
-		ptr = ____cache_alloc(cachep, flags);
-	else
-		ptr = __cache_alloc_node(cachep, flags, nodeid);
-	local_irq_restore(save_flags);
+	if (unlikely(nodeid == -1))
+		nodeid = numa_node_id();
 
-	ptr = cache_alloc_debugcheck_after(cachep, flags, ptr,
-					   __builtin_return_address(0));
+	if (likely(cachep->nodelists[nodeid])) {
+		if (nodeid == numa_node_id()) {
+			/*
+			 * Use the locally cached objects if possible.
+			 * However ____cache_alloc does not allow fallback
+			 * to other nodes. It may fail while we still have
+			 * objects on other nodes available.
+			 */
+			ptr = ____cache_alloc(cachep, flags);
+		}
+		if (!ptr) {
+			/* ___cache_alloc_node can fall back to other nodes */
+			ptr = ____cache_alloc_node(cachep, flags, nodeid);
+		}
+	} else {
+		/* Node not bootstrapped yet */
+		if (!(flags & __GFP_THISNODE))
+			ptr = fallback_alloc(cachep, flags);
+	}
+
+	local_irq_restore(save_flags);
+	ptr = cache_alloc_debugcheck_after(cachep, flags, ptr, caller);
 
 	return ptr;
 }
+
+void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid)
+{
+	return __cache_alloc_node(cachep, flags, nodeid,
+			__builtin_return_address(0));
+}
 EXPORT_SYMBOL(kmem_cache_alloc_node);
 
-void *__kmalloc_node(size_t size, gfp_t flags, int node)
+static __always_inline void *
+__do_kmalloc_node(size_t size, gfp_t flags, int node, void *caller)
 {
 	struct kmem_cache *cachep;
 
@@ -3468,8 +3631,29 @@ void *__kmalloc_node(size_t size, gfp_t flags, int node)
 		return NULL;
 	return kmem_cache_alloc_node(cachep, flags, node);
 }
+
+#ifdef CONFIG_DEBUG_SLAB
+void *__kmalloc_node(size_t size, gfp_t flags, int node)
+{
+	return __do_kmalloc_node(size, flags, node,
+			__builtin_return_address(0));
+}
 EXPORT_SYMBOL(__kmalloc_node);
-#endif
+
+void *__kmalloc_node_track_caller(size_t size, gfp_t flags,
+		int node, void *caller)
+{
+	return __do_kmalloc_node(size, flags, node, caller);
+}
+EXPORT_SYMBOL(__kmalloc_node_track_caller);
+#else
+void *__kmalloc_node(size_t size, gfp_t flags, int node)
+{
+	return __do_kmalloc_node(size, flags, node, NULL);
+}
+EXPORT_SYMBOL(__kmalloc_node);
+#endif /* CONFIG_DEBUG_SLAB */
+#endif /* CONFIG_NUMA */
 
 /**
  * __do_kmalloc - allocate memory
@@ -3580,13 +3764,15 @@ static int alloc_kmemlist(struct kmem_cache *cachep)
 	int node;
 	struct kmem_list3 *l3;
 	struct array_cache *new_shared;
-	struct array_cache **new_alien;
+	struct array_cache **new_alien = NULL;
 
 	for_each_online_node(node) {
 
-		new_alien = alloc_alien_cache(node, cachep->limit);
-		if (!new_alien)
-			goto fail;
+                if (use_alien_caches) {
+                        new_alien = alloc_alien_cache(node, cachep->limit);
+                        if (!new_alien)
+                                goto fail;
+                }
 
 		new_shared = alloc_arraycache(node,
 				cachep->shared*cachep->batchcount,
@@ -3812,7 +3998,7 @@ void drain_array(struct kmem_cache *cachep, struct kmem_list3 *l3,
  * If we cannot acquire the cache chain mutex then just give up - we'll try
  * again on the next iteration.
  */
-static void cache_reap(void *unused)
+static void cache_reap(struct work_struct *unused)
 {
 	struct kmem_cache *searchp;
 	struct kmem_list3 *l3;
@@ -3821,7 +4007,7 @@ static void cache_reap(void *unused)
 	if (!mutex_trylock(&cache_chain_mutex)) {
 		/* Give up. Setup the next iteration. */
 		schedule_delayed_work(&__get_cpu_var(reap_work),
-				      REAPTIMEOUT_CPUC);
+				      round_jiffies_relative(REAPTIMEOUT_CPUC));
 		return;
 	}
 
@@ -3867,7 +4053,8 @@ next:
 	next_reap_node();
 	refresh_cpu_vm_stats(smp_processor_id());
 	/* Set up the next iteration */
-	schedule_delayed_work(&__get_cpu_var(reap_work), REAPTIMEOUT_CPUC);
+	schedule_delayed_work(&__get_cpu_var(reap_work),
+		round_jiffies_relative(REAPTIMEOUT_CPUC));
 }
 
 #ifdef CONFIG_PROC_FS
@@ -4035,7 +4222,7 @@ static int s_show(struct seq_file *m, void *p)
  * + further values on SMP and with statistics enabled
  */
 
-struct seq_operations slabinfo_op = {
+const struct seq_operations slabinfo_op = {
 	.start = s_start,
 	.next = s_next,
 	.stop = s_stop,
@@ -4233,7 +4420,7 @@ static int leaks_show(struct seq_file *m, void *p)
 	return 0;
 }
 
-struct seq_operations slabstats_op = {
+const struct seq_operations slabstats_op = {
 	.start = leaks_start,
 	.next = s_next,
 	.stop = s_stop,
diff --git a/mm/sparse.c b/mm/sparse.c
index 86c52ab8087..ac26eb0d73c 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -24,6 +24,25 @@ struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT]
 #endif
 EXPORT_SYMBOL(mem_section);
 
+#ifdef NODE_NOT_IN_PAGE_FLAGS
+/*
+ * If we did not store the node number in the page then we have to
+ * do a lookup in the section_to_node_table in order to find which
+ * node the page belongs to.
+ */
+#if MAX_NUMNODES <= 256
+static u8 section_to_node_table[NR_MEM_SECTIONS] __cacheline_aligned;
+#else
+static u16 section_to_node_table[NR_MEM_SECTIONS] __cacheline_aligned;
+#endif
+
+int page_to_nid(struct page *page)
+{
+	return section_to_node_table[page_to_section(page)];
+}
+EXPORT_SYMBOL(page_to_nid);
+#endif
+
 #ifdef CONFIG_SPARSEMEM_EXTREME
 static struct mem_section *sparse_index_alloc(int nid)
 {
@@ -49,6 +68,10 @@ static int sparse_index_init(unsigned long section_nr, int nid)
 	struct mem_section *section;
 	int ret = 0;
 
+#ifdef NODE_NOT_IN_PAGE_FLAGS
+	section_to_node_table[section_nr] = nid;
+#endif
+
 	if (mem_section[root])
 		return -EEXIST;
 
@@ -211,7 +234,7 @@ static struct page *__kmalloc_section_memmap(unsigned long nr_pages)
 	struct page *page, *ret;
 	unsigned long memmap_size = sizeof(struct page) * nr_pages;
 
-	page = alloc_pages(GFP_KERNEL, get_order(memmap_size));
+	page = alloc_pages(GFP_KERNEL|__GFP_NOWARN, get_order(memmap_size));
 	if (page)
 		goto got_map_page;
 
diff --git a/mm/swap.c b/mm/swap.c
index 2e0e871f542..2ed7be39795 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -57,9 +57,9 @@ static void put_compound_page(struct page *page)
 {
 	page = (struct page *)page_private(page);
 	if (put_page_testzero(page)) {
-		void (*dtor)(struct page *page);
+		compound_page_dtor *dtor;
 
-		dtor = (void (*)(struct page *))page[1].lru.next;
+		dtor = get_compound_page_dtor(page);
 		(*dtor)(page);
 	}
 }
@@ -216,7 +216,7 @@ void lru_add_drain(void)
 }
 
 #ifdef CONFIG_NUMA
-static void lru_add_drain_per_cpu(void *dummy)
+static void lru_add_drain_per_cpu(struct work_struct *dummy)
 {
 	lru_add_drain();
 }
@@ -226,7 +226,7 @@ static void lru_add_drain_per_cpu(void *dummy)
  */
 int lru_add_drain_all(void)
 {
-	return schedule_on_each_cpu(lru_add_drain_per_cpu, NULL);
+	return schedule_on_each_cpu(lru_add_drain_per_cpu);
 }
 
 #else
@@ -514,5 +514,7 @@ void __init swap_setup(void)
 	 * Right now other parts of the system means that we
 	 * _really_ don't want to cluster much more
 	 */
+#ifdef CONFIG_HOTPLUG_CPU
 	hotcpu_notifier(cpu_swap_callback, 0);
+#endif
 }
diff --git a/mm/swapfile.c b/mm/swapfile.c
index a15def63f28..b9fc0e5de6d 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -427,34 +427,48 @@ void free_swap_and_cache(swp_entry_t entry)
 
 #ifdef CONFIG_SOFTWARE_SUSPEND
 /*
- * Find the swap type that corresponds to given device (if any)
+ * Find the swap type that corresponds to given device (if any).
  *
- * This is needed for software suspend and is done in such a way that inode
- * aliasing is allowed.
+ * @offset - number of the PAGE_SIZE-sized block of the device, starting
+ * from 0, in which the swap header is expected to be located.
+ *
+ * This is needed for the suspend to disk (aka swsusp).
  */
-int swap_type_of(dev_t device)
+int swap_type_of(dev_t device, sector_t offset)
 {
+	struct block_device *bdev = NULL;
 	int i;
 
+	if (device)
+		bdev = bdget(device);
+
 	spin_lock(&swap_lock);
 	for (i = 0; i < nr_swapfiles; i++) {
-		struct inode *inode;
+		struct swap_info_struct *sis = swap_info + i;
 
-		if (!(swap_info[i].flags & SWP_WRITEOK))
+		if (!(sis->flags & SWP_WRITEOK))
 			continue;
 
-		if (!device) {
+		if (!bdev) {
 			spin_unlock(&swap_lock);
 			return i;
 		}
-		inode = swap_info[i].swap_file->f_dentry->d_inode;
-		if (S_ISBLK(inode->i_mode) &&
-		    device == MKDEV(imajor(inode), iminor(inode))) {
-			spin_unlock(&swap_lock);
-			return i;
+		if (bdev == sis->bdev) {
+			struct swap_extent *se;
+
+			se = list_entry(sis->extent_list.next,
+					struct swap_extent, list);
+			if (se->start_block == offset) {
+				spin_unlock(&swap_lock);
+				bdput(bdev);
+				return i;
+			}
 		}
 	}
 	spin_unlock(&swap_lock);
+	if (bdev)
+		bdput(bdev);
+
 	return -ENODEV;
 }
 
@@ -931,6 +945,23 @@ sector_t map_swap_page(struct swap_info_struct *sis, pgoff_t offset)
 	}
 }
 
+#ifdef CONFIG_SOFTWARE_SUSPEND
+/*
+ * Get the (PAGE_SIZE) block corresponding to given offset on the swapdev
+ * corresponding to given index in swap_info (swap type).
+ */
+sector_t swapdev_block(int swap_type, pgoff_t offset)
+{
+	struct swap_info_struct *sis;
+
+	if (swap_type >= nr_swapfiles)
+		return 0;
+
+	sis = swap_info + swap_type;
+	return (sis->flags & SWP_WRITEOK) ? map_swap_page(sis, offset) : 0;
+}
+#endif /* CONFIG_SOFTWARE_SUSPEND */
+
 /*
  * Free all of a swapdev's extent information
  */
@@ -1274,10 +1305,13 @@ static void *swap_start(struct seq_file *swap, loff_t *pos)
 
 	mutex_lock(&swapon_mutex);
 
+	if (!l)
+		return SEQ_START_TOKEN;
+
 	for (i = 0; i < nr_swapfiles; i++, ptr++) {
 		if (!(ptr->flags & SWP_USED) || !ptr->swap_map)
 			continue;
-		if (!l--)
+		if (!--l)
 			return ptr;
 	}
 
@@ -1286,10 +1320,17 @@ static void *swap_start(struct seq_file *swap, loff_t *pos)
 
 static void *swap_next(struct seq_file *swap, void *v, loff_t *pos)
 {
-	struct swap_info_struct *ptr = v;
+	struct swap_info_struct *ptr;
 	struct swap_info_struct *endptr = swap_info + nr_swapfiles;
 
-	for (++ptr; ptr < endptr; ptr++) {
+	if (v == SEQ_START_TOKEN)
+		ptr = swap_info;
+	else {
+		ptr = v;
+		ptr++;
+	}
+
+	for (; ptr < endptr; ptr++) {
 		if (!(ptr->flags & SWP_USED) || !ptr->swap_map)
 			continue;
 		++*pos;
@@ -1310,14 +1351,16 @@ static int swap_show(struct seq_file *swap, void *v)
 	struct file *file;
 	int len;
 
-	if (v == swap_info)
-		seq_puts(swap, "Filename\t\t\t\tType\t\tSize\tUsed\tPriority\n");
+	if (ptr == SEQ_START_TOKEN) {
+		seq_puts(swap,"Filename\t\t\t\tType\t\tSize\tUsed\tPriority\n");
+		return 0;
+	}
 
 	file = ptr->swap_file;
-	len = seq_path(swap, file->f_vfsmnt, file->f_dentry, " \t\n\\");
+	len = seq_path(swap, file->f_path.mnt, file->f_path.dentry, " \t\n\\");
 	seq_printf(swap, "%*s%s\t%u\t%u\t%d\n",
 		       len < 40 ? 40 - len : 1, " ",
-		       S_ISBLK(file->f_dentry->d_inode->i_mode) ?
+		       S_ISBLK(file->f_path.dentry->d_inode->i_mode) ?
 				"partition" : "file\t",
 		       ptr->pages << (PAGE_SHIFT - 10),
 		       ptr->inuse_pages << (PAGE_SHIFT - 10),
@@ -1325,7 +1368,7 @@ static int swap_show(struct seq_file *swap, void *v)
 	return 0;
 }
 
-static struct seq_operations swaps_op = {
+static const struct seq_operations swaps_op = {
 	.start =	swap_start,
 	.next =		swap_next,
 	.stop =		swap_stop,
@@ -1337,7 +1380,7 @@ static int swaps_open(struct inode *inode, struct file *file)
 	return seq_open(file, &swaps_op);
 }
 
-static struct file_operations proc_swaps_operations = {
+static const struct file_operations proc_swaps_operations = {
 	.open		= swaps_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
@@ -1540,6 +1583,11 @@ asmlinkage long sys_swapon(const char __user * specialfile, int swap_flags)
 		error = -EINVAL;
 		if (!maxpages)
 			goto bad_swap;
+		if (swapfilesize && maxpages > swapfilesize) {
+			printk(KERN_WARNING
+			       "Swap area shorter than signature indicates\n");
+			goto bad_swap;
+		}
 		if (swap_header->info.nr_badpages && S_ISREG(inode->i_mode))
 			goto bad_swap;
 		if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES)
@@ -1567,12 +1615,6 @@ asmlinkage long sys_swapon(const char __user * specialfile, int swap_flags)
 			goto bad_swap;
 	}
 
-	if (swapfilesize && maxpages > swapfilesize) {
-		printk(KERN_WARNING
-		       "Swap area shorter than signature indicates\n");
-		error = -EINVAL;
-		goto bad_swap;
-	}
 	if (nr_good_pages) {
 		p->swap_map[0] = SWAP_MAP_BAD;
 		p->max = maxpages;
diff --git a/mm/thrash.c b/mm/thrash.c
index f4c560b4a2b..9ef9071f99b 100644
--- a/mm/thrash.c
+++ b/mm/thrash.c
@@ -7,100 +7,74 @@
  *
  * Simple token based thrashing protection, using the algorithm
  * described in:  http://www.cs.wm.edu/~sjiang/token.pdf
+ *
+ * Sep 2006, Ashwin Chaugule <ashwin.chaugule@celunite.com>
+ * Improved algorithm to pass token:
+ * Each task has a priority which is incremented if it contended
+ * for the token in an interval less than its previous attempt.
+ * If the token is acquired, that task's priority is boosted to prevent
+ * the token from bouncing around too often and to let the task make
+ * some progress in its execution.
  */
+
 #include <linux/jiffies.h>
 #include <linux/mm.h>
 #include <linux/sched.h>
 #include <linux/swap.h>
 
 static DEFINE_SPINLOCK(swap_token_lock);
-static unsigned long swap_token_timeout;
-static unsigned long swap_token_check;
-struct mm_struct * swap_token_mm = &init_mm;
-
-#define SWAP_TOKEN_CHECK_INTERVAL (HZ * 2)
-#define SWAP_TOKEN_TIMEOUT	(300 * HZ)
-/*
- * Currently disabled; Needs further code to work at HZ * 300.
- */
-unsigned long swap_token_default_timeout = SWAP_TOKEN_TIMEOUT;
-
-/*
- * Take the token away if the process had no page faults
- * in the last interval, or if it has held the token for
- * too long.
- */
-#define SWAP_TOKEN_ENOUGH_RSS 1
-#define SWAP_TOKEN_TIMED_OUT 2
-static int should_release_swap_token(struct mm_struct *mm)
-{
-	int ret = 0;
-	if (!mm->recent_pagein)
-		ret = SWAP_TOKEN_ENOUGH_RSS;
-	else if (time_after(jiffies, swap_token_timeout))
-		ret = SWAP_TOKEN_TIMED_OUT;
-	mm->recent_pagein = 0;
-	return ret;
-}
+struct mm_struct *swap_token_mm;
+static unsigned int global_faults;
 
-/*
- * Try to grab the swapout protection token.  We only try to
- * grab it once every TOKEN_CHECK_INTERVAL, both to prevent
- * SMP lock contention and to check that the process that held
- * the token before is no longer thrashing.
- */
 void grab_swap_token(void)
 {
-	struct mm_struct *mm;
-	int reason;
+	int current_interval;
 
-	/* We have the token. Let others know we still need it. */
-	if (has_swap_token(current->mm)) {
-		current->mm->recent_pagein = 1;
-		if (unlikely(!swap_token_default_timeout))
-			disable_swap_token();
-		return;
-	}
-
-	if (time_after(jiffies, swap_token_check)) {
+	global_faults++;
 
-		if (!swap_token_default_timeout) {
-			swap_token_check = jiffies + SWAP_TOKEN_CHECK_INTERVAL;
-			return;
-		}
-
-		/* ... or if we recently held the token. */
-		if (time_before(jiffies, current->mm->swap_token_time))
-			return;
+	current_interval = global_faults - current->mm->faultstamp;
 
-		if (!spin_trylock(&swap_token_lock))
-			return;
+	if (!spin_trylock(&swap_token_lock))
+		return;
 
-		swap_token_check = jiffies + SWAP_TOKEN_CHECK_INTERVAL;
+	/* First come first served */
+	if (swap_token_mm == NULL) {
+		current->mm->token_priority = current->mm->token_priority + 2;
+		swap_token_mm = current->mm;
+		goto out;
+	}
 
-		mm = swap_token_mm;
-		if ((reason = should_release_swap_token(mm))) {
-			unsigned long eligible = jiffies;
-			if (reason == SWAP_TOKEN_TIMED_OUT) {
-				eligible += swap_token_default_timeout;
-			}
-			mm->swap_token_time = eligible;
-			swap_token_timeout = jiffies + swap_token_default_timeout;
+	if (current->mm != swap_token_mm) {
+		if (current_interval < current->mm->last_interval)
+			current->mm->token_priority++;
+		else {
+			current->mm->token_priority--;
+			if (unlikely(current->mm->token_priority < 0))
+				current->mm->token_priority = 0;
+		}
+		/* Check if we deserve the token */
+		if (current->mm->token_priority >
+				swap_token_mm->token_priority) {
+			current->mm->token_priority += 2;
 			swap_token_mm = current->mm;
 		}
-		spin_unlock(&swap_token_lock);
+	} else {
+		/* Token holder came in again! */
+		current->mm->token_priority += 2;
 	}
-	return;
+
+out:
+	current->mm->faultstamp = global_faults;
+	current->mm->last_interval = current_interval;
+	spin_unlock(&swap_token_lock);
+return;
 }
 
 /* Called on process exit. */
 void __put_swap_token(struct mm_struct *mm)
 {
 	spin_lock(&swap_token_lock);
-	if (likely(mm == swap_token_mm)) {
-		mm->swap_token_time = jiffies + SWAP_TOKEN_CHECK_INTERVAL;
-		swap_token_mm = &init_mm;
-		swap_token_check = jiffies;
-	}
+	if (likely(mm == swap_token_mm))
+		swap_token_mm = NULL;
 	spin_unlock(&swap_token_lock);
 }
diff --git a/mm/tiny-shmem.c b/mm/tiny-shmem.c
index 5f2cbf0f153..c7f6e1914bc 100644
--- a/mm/tiny-shmem.c
+++ b/mm/tiny-shmem.c
@@ -79,8 +79,8 @@ struct file *shmem_file_setup(char *name, loff_t size, unsigned long flags)
 	d_instantiate(dentry, inode);
 	inode->i_nlink = 0;	/* It is unlinked */
 
-	file->f_vfsmnt = mntget(shm_mnt);
-	file->f_dentry = dentry;
+	file->f_path.mnt = mntget(shm_mnt);
+	file->f_path.dentry = dentry;
 	file->f_mapping = inode->i_mapping;
 	file->f_op = &ramfs_file_operations;
 	file->f_mode = FMODE_WRITE | FMODE_READ;
diff --git a/mm/truncate.c b/mm/truncate.c
index 11ca480701d..9bfb8e85386 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -13,6 +13,7 @@
 #include <linux/module.h>
 #include <linux/pagemap.h>
 #include <linux/pagevec.h>
+#include <linux/task_io_accounting_ops.h>
 #include <linux/buffer_head.h>	/* grr. try_to_release_page,
 				   do_invalidatepage */
 
@@ -69,7 +70,8 @@ truncate_complete_page(struct address_space *mapping, struct page *page)
 	if (PagePrivate(page))
 		do_invalidatepage(page, 0);
 
-	clear_page_dirty(page);
+	if (test_clear_page_dirty(page))
+		task_io_account_cancelled_write(PAGE_CACHE_SIZE);
 	ClearPageUptodate(page);
 	ClearPageMappedToDisk(page);
 	remove_from_page_cache(page);
@@ -96,7 +98,6 @@ invalidate_complete_page(struct address_space *mapping, struct page *page)
 		return 0;
 
 	ret = remove_mapping(mapping, page);
-	ClearPageUptodate(page);
 
 	return ret;
 }
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 750ab6ed13f..86897ee792d 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -160,13 +160,15 @@ int map_vm_area(struct vm_struct *area, pgprot_t prot, struct page ***pages)
 	return err;
 }
 
-struct vm_struct *__get_vm_area_node(unsigned long size, unsigned long flags,
-				unsigned long start, unsigned long end, int node)
+static struct vm_struct *__get_vm_area_node(unsigned long size, unsigned long flags,
+					    unsigned long start, unsigned long end,
+					    int node, gfp_t gfp_mask)
 {
 	struct vm_struct **p, *tmp, *area;
 	unsigned long align = 1;
 	unsigned long addr;
 
+	BUG_ON(in_interrupt());
 	if (flags & VM_IOREMAP) {
 		int bit = fls(size);
 
@@ -179,16 +181,13 @@ struct vm_struct *__get_vm_area_node(unsigned long size, unsigned long flags,
 	}
 	addr = ALIGN(start, align);
 	size = PAGE_ALIGN(size);
+	if (unlikely(!size))
+		return NULL;
 
-	area = kmalloc_node(sizeof(*area), GFP_KERNEL, node);
+	area = kmalloc_node(sizeof(*area), gfp_mask & GFP_LEVEL_MASK, node);
 	if (unlikely(!area))
 		return NULL;
 
-	if (unlikely(!size)) {
-		kfree (area);
-		return NULL;
-	}
-
 	/*
 	 * We always allocate a guard page.
 	 */
@@ -236,7 +235,7 @@ out:
 struct vm_struct *__get_vm_area(unsigned long size, unsigned long flags,
 				unsigned long start, unsigned long end)
 {
-	return __get_vm_area_node(size, flags, start, end, -1);
+	return __get_vm_area_node(size, flags, start, end, -1, GFP_KERNEL);
 }
 
 /**
@@ -253,9 +252,11 @@ struct vm_struct *get_vm_area(unsigned long size, unsigned long flags)
 	return __get_vm_area(size, flags, VMALLOC_START, VMALLOC_END);
 }
 
-struct vm_struct *get_vm_area_node(unsigned long size, unsigned long flags, int node)
+struct vm_struct *get_vm_area_node(unsigned long size, unsigned long flags,
+				   int node, gfp_t gfp_mask)
 {
-	return __get_vm_area_node(size, flags, VMALLOC_START, VMALLOC_END, node);
+	return __get_vm_area_node(size, flags, VMALLOC_START, VMALLOC_END, node,
+				  gfp_mask);
 }
 
 /* Caller must hold vmlist_lock */
@@ -428,8 +429,11 @@ void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 	if (array_size > PAGE_SIZE) {
 		pages = __vmalloc_node(array_size, gfp_mask, PAGE_KERNEL, node);
 		area->flags |= VM_VPAGES;
-	} else
-		pages = kmalloc_node(array_size, (gfp_mask & ~__GFP_HIGHMEM), node);
+	} else {
+		pages = kmalloc_node(array_size,
+				(gfp_mask & ~(__GFP_HIGHMEM | __GFP_ZERO)),
+				node);
+	}
 	area->pages = pages;
 	if (!area->pages) {
 		remove_vm_area(area->addr);
@@ -484,7 +488,7 @@ static void *__vmalloc_node(unsigned long size, gfp_t gfp_mask, pgprot_t prot,
 	if (!size || (size >> PAGE_SHIFT) > num_physpages)
 		return NULL;
 
-	area = get_vm_area_node(size, VM_ALLOC, node);
+	area = get_vm_area_node(size, VM_ALLOC, node, gfp_mask);
 	if (!area)
 		return NULL;
 
@@ -525,11 +529,12 @@ void *vmalloc_user(unsigned long size)
 	void *ret;
 
 	ret = __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO, PAGE_KERNEL);
-	write_lock(&vmlist_lock);
-	area = __find_vm_area(ret);
-	area->flags |= VM_USERMAP;
-	write_unlock(&vmlist_lock);
-
+	if (ret) {
+		write_lock(&vmlist_lock);
+		area = __find_vm_area(ret);
+		area->flags |= VM_USERMAP;
+		write_unlock(&vmlist_lock);
+	}
 	return ret;
 }
 EXPORT_SYMBOL(vmalloc_user);
@@ -598,11 +603,12 @@ void *vmalloc_32_user(unsigned long size)
 	void *ret;
 
 	ret = __vmalloc(size, GFP_KERNEL | __GFP_ZERO, PAGE_KERNEL);
-	write_lock(&vmlist_lock);
-	area = __find_vm_area(ret);
-	area->flags |= VM_USERMAP;
-	write_unlock(&vmlist_lock);
-
+	if (ret) {
+		write_lock(&vmlist_lock);
+		area = __find_vm_area(ret);
+		area->flags |= VM_USERMAP;
+		write_unlock(&vmlist_lock);
+	}
 	return ret;
 }
 EXPORT_SYMBOL(vmalloc_32_user);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index eca70310adb..093f5fe6dd7 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -36,6 +36,7 @@
 #include <linux/rwsem.h>
 #include <linux/delay.h>
 #include <linux/kthread.h>
+#include <linux/freezer.h>
 
 #include <asm/tlbflush.h>
 #include <asm/div64.h>
@@ -378,6 +379,12 @@ static pageout_t pageout(struct page *page, struct address_space *mapping)
 	return PAGE_CLEAN;
 }
 
+/*
+ * Attempt to detach a locked page from its ->mapping.  If it is dirty or if
+ * someone else has a ref on the page, abort and return 0.  If it was
+ * successfully detached, return 1.  Assumes the caller has a single ref on
+ * this page.
+ */
 int remove_mapping(struct address_space *mapping, struct page *page)
 {
 	BUG_ON(!PageLocked(page));
@@ -717,6 +724,20 @@ done:
 	return nr_reclaimed;
 }
 
+/*
+ * We are about to scan this zone at a certain priority level.  If that priority
+ * level is smaller (ie: more urgent) than the previous priority, then note
+ * that priority level within the zone.  This is done so that when the next
+ * process comes in to scan this zone, it will immediately start out at this
+ * priority level rather than having to build up its own scanning priority.
+ * Here, this priority affects only the reclaim-mapped threshold.
+ */
+static inline void note_zone_scanning_priority(struct zone *zone, int priority)
+{
+	if (priority < zone->prev_priority)
+		zone->prev_priority = priority;
+}
+
 static inline int zone_is_near_oom(struct zone *zone)
 {
 	return zone->pages_scanned >= (zone->nr_active + zone->nr_inactive)*3;
@@ -740,7 +761,7 @@ static inline int zone_is_near_oom(struct zone *zone)
  * But we had to alter page->flags anyway.
  */
 static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
-				struct scan_control *sc)
+				struct scan_control *sc, int priority)
 {
 	unsigned long pgmoved;
 	int pgdeactivate = 0;
@@ -764,7 +785,7 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 		 * `distress' is a measure of how much trouble we're having
 		 * reclaiming pages.  0 -> no problems.  100 -> great trouble.
 		 */
-		distress = 100 >> zone->prev_priority;
+		distress = 100 >> min(zone->prev_priority, priority);
 
 		/*
 		 * The point of this algorithm is to decide when to start
@@ -916,7 +937,7 @@ static unsigned long shrink_zone(int priority, struct zone *zone,
 			nr_to_scan = min(nr_active,
 					(unsigned long)sc->swap_cluster_max);
 			nr_active -= nr_to_scan;
-			shrink_active_list(nr_to_scan, zone, sc);
+			shrink_active_list(nr_to_scan, zone, sc, priority);
 		}
 
 		if (nr_inactive) {
@@ -966,9 +987,7 @@ static unsigned long shrink_zones(int priority, struct zone **zones,
 		if (!cpuset_zone_allowed(zone, __GFP_HARDWALL))
 			continue;
 
-		zone->temp_priority = priority;
-		if (zone->prev_priority > priority)
-			zone->prev_priority = priority;
+		note_zone_scanning_priority(zone, priority);
 
 		if (zone->all_unreclaimable && priority != DEF_PRIORITY)
 			continue;	/* Let kswapd poll it */
@@ -1018,7 +1037,6 @@ unsigned long try_to_free_pages(struct zone **zones, gfp_t gfp_mask)
 		if (!cpuset_zone_allowed(zone, __GFP_HARDWALL))
 			continue;
 
-		zone->temp_priority = DEF_PRIORITY;
 		lru_pages += zone->nr_active + zone->nr_inactive;
 	}
 
@@ -1053,19 +1071,28 @@ unsigned long try_to_free_pages(struct zone **zones, gfp_t gfp_mask)
 
 		/* Take a nap, wait for some writeback to complete */
 		if (sc.nr_scanned && priority < DEF_PRIORITY - 2)
-			blk_congestion_wait(WRITE, HZ/10);
+			congestion_wait(WRITE, HZ/10);
 	}
 	/* top priority shrink_caches still had more to do? don't OOM, then */
 	if (!sc.all_unreclaimable)
 		ret = 1;
 out:
+	/*
+	 * Now that we've scanned all the zones at this priority level, note
+	 * that level within the zone so that the next thread which performs
+	 * scanning of this zone will immediately start out at this priority
+	 * level.  This affects only the decision whether or not to bring
+	 * mapped pages onto the inactive list.
+	 */
+	if (priority < 0)
+		priority = 0;
 	for (i = 0; zones[i] != 0; i++) {
 		struct zone *zone = zones[i];
 
 		if (!cpuset_zone_allowed(zone, __GFP_HARDWALL))
 			continue;
 
-		zone->prev_priority = zone->temp_priority;
+		zone->prev_priority = priority;
 	}
 	return ret;
 }
@@ -1105,6 +1132,11 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order)
 		.swap_cluster_max = SWAP_CLUSTER_MAX,
 		.swappiness = vm_swappiness,
 	};
+	/*
+	 * temp_priority is used to remember the scanning priority at which
+	 * this zone was successfully refilled to free_pages == pages_high.
+	 */
+	int temp_priority[MAX_NR_ZONES];
 
 loop_again:
 	total_scanned = 0;
@@ -1112,11 +1144,8 @@ loop_again:
 	sc.may_writepage = !laptop_mode;
 	count_vm_event(PAGEOUTRUN);
 
-	for (i = 0; i < pgdat->nr_zones; i++) {
-		struct zone *zone = pgdat->node_zones + i;
-
-		zone->temp_priority = DEF_PRIORITY;
-	}
+	for (i = 0; i < pgdat->nr_zones; i++)
+		temp_priority[i] = DEF_PRIORITY;
 
 	for (priority = DEF_PRIORITY; priority >= 0; priority--) {
 		int end_zone = 0;	/* Inclusive.  0 = ZONE_DMA */
@@ -1144,11 +1173,12 @@ loop_again:
 			if (!zone_watermark_ok(zone, order, zone->pages_high,
 					       0, 0)) {
 				end_zone = i;
-				goto scan;
+				break;
 			}
 		}
-		goto out;
-scan:
+		if (i < 0)
+			goto out;
+
 		for (i = 0; i <= end_zone; i++) {
 			struct zone *zone = pgdat->node_zones + i;
 
@@ -1177,10 +1207,9 @@ scan:
 			if (!zone_watermark_ok(zone, order, zone->pages_high,
 					       end_zone, 0))
 				all_zones_ok = 0;
-			zone->temp_priority = priority;
-			if (zone->prev_priority > priority)
-				zone->prev_priority = priority;
+			temp_priority[i] = priority;
 			sc.nr_scanned = 0;
+			note_zone_scanning_priority(zone, priority);
 			nr_reclaimed += shrink_zone(priority, zone, &sc);
 			reclaim_state->reclaimed_slab = 0;
 			nr_slab = shrink_slab(sc.nr_scanned, GFP_KERNEL,
@@ -1208,7 +1237,7 @@ scan:
 		 * another pass across the zones.
 		 */
 		if (total_scanned && priority < DEF_PRIORITY - 2)
-			blk_congestion_wait(WRITE, HZ/10);
+			congestion_wait(WRITE, HZ/10);
 
 		/*
 		 * We do this so kswapd doesn't build up large priorities for
@@ -1220,13 +1249,21 @@ scan:
 			break;
 	}
 out:
+	/*
+	 * Note within each zone the priority level at which this zone was
+	 * brought into a happy state.  So that the next thread which scans this
+	 * zone will start out at that priority level.
+	 */
 	for (i = 0; i < pgdat->nr_zones; i++) {
 		struct zone *zone = pgdat->node_zones + i;
 
-		zone->prev_priority = zone->temp_priority;
+		zone->prev_priority = temp_priority[i];
 	}
 	if (!all_zones_ok) {
 		cond_resched();
+
+		try_to_freeze();
+
 		goto loop_again;
 	}
 
@@ -1352,7 +1389,7 @@ static unsigned long shrink_all_zones(unsigned long nr_pages, int pass,
 			if (zone->nr_scan_active >= nr_pages || pass > 3) {
 				zone->nr_scan_active = 0;
 				nr_to_scan = min(nr_pages, zone->nr_active);
-				shrink_active_list(nr_to_scan, zone, sc);
+				shrink_active_list(nr_to_scan, zone, sc, prio);
 			}
 		}
 
@@ -1452,7 +1489,7 @@ unsigned long shrink_all_memory(unsigned long nr_pages)
 				goto out;
 
 			if (sc.nr_scanned && prio < DEF_PRIORITY - 2)
-				blk_congestion_wait(WRITE, HZ / 10);
+				congestion_wait(WRITE, HZ / 10);
 		}
 
 		lru_pages = 0;
@@ -1476,7 +1513,6 @@ out:
 }
 #endif
 
-#ifdef CONFIG_HOTPLUG_CPU
 /* It's optimal to keep kswapds on the same CPUs as their memory, but
    not required for correctness.  So if the last cpu in a node goes
    away, we get changed to run anywhere: as the first one comes back,
@@ -1497,7 +1533,6 @@ static int __devinit cpu_callback(struct notifier_block *nfb,
 	}
 	return NOTIFY_OK;
 }
-#endif /* CONFIG_HOTPLUG_CPU */
 
 /*
  * This kswapd start function will be called by init and node-hot-add.
@@ -1608,6 +1643,7 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 		 */
 		priority = ZONE_RECLAIM_PRIORITY;
 		do {
+			note_zone_scanning_priority(zone, priority);
 			nr_reclaimed += shrink_zone(priority, zone, &sc);
 			priority--;
 		} while (priority >= 0 && nr_reclaimed < nr_pages);
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 45b124e012f..dc005a0c96a 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -430,7 +430,7 @@ static int frag_show(struct seq_file *m, void *arg)
 	return 0;
 }
 
-struct seq_operations fragmentation_op = {
+const struct seq_operations fragmentation_op = {
 	.start	= frag_start,
 	.next	= frag_next,
 	.stop	= frag_stop,
@@ -452,7 +452,7 @@ struct seq_operations fragmentation_op = {
 #define TEXTS_FOR_ZONES(xx) xx "_dma", TEXT_FOR_DMA32(xx) xx "_normal", \
 					TEXT_FOR_HIGHMEM(xx)
 
-static char *vmstat_text[] = {
+static const char * const vmstat_text[] = {
 	/* Zoned VM counters */
 	"nr_anon_pages",
 	"nr_mapped",
@@ -587,11 +587,9 @@ static int zoneinfo_show(struct seq_file *m, void *arg)
 		seq_printf(m,
 			   "\n  all_unreclaimable: %u"
 			   "\n  prev_priority:     %i"
-			   "\n  temp_priority:     %i"
 			   "\n  start_pfn:         %lu",
 			   zone->all_unreclaimable,
 			   zone->prev_priority,
-			   zone->temp_priority,
 			   zone->zone_start_pfn);
 		spin_unlock_irqrestore(&zone->lock, flags);
 		seq_putc(m, '\n');
@@ -599,7 +597,7 @@ static int zoneinfo_show(struct seq_file *m, void *arg)
 	return 0;
 }
 
-struct seq_operations zoneinfo_op = {
+const struct seq_operations zoneinfo_op = {
 	.start	= frag_start, /* iterate over all zones. The same as in
 			       * fragmentation. */
 	.next	= frag_next,
@@ -662,7 +660,7 @@ static void vmstat_stop(struct seq_file *m, void *arg)
 	m->private = NULL;
 }
 
-struct seq_operations vmstat_op = {
+const struct seq_operations vmstat_op = {
 	.start	= vmstat_start,
 	.next	= vmstat_next,
 	.stop	= vmstat_stop,
@@ -681,13 +679,13 @@ static int __cpuinit vmstat_cpuup_callback(struct notifier_block *nfb,
 		void *hcpu)
 {
 	switch (action) {
-		case CPU_UP_PREPARE:
-		case CPU_UP_CANCELED:
-		case CPU_DEAD:
-			refresh_zone_stat_thresholds();
-			break;
-		default:
-			break;
+	case CPU_UP_PREPARE:
+	case CPU_UP_CANCELED:
+	case CPU_DEAD:
+		refresh_zone_stat_thresholds();
+		break;
+	default:
+		break;
 	}
 	return NOTIFY_OK;
 }