Merge branch 'master' of /home/trondmy/kernel/linux-2.6/

Conflicts:

	fs/nfs/inode.c
	fs/super.c

Fix conflicts between patch 'NFS: Split fs/nfs/inode.c' and patch
'VFS: Permit filesystem to override root dentry on mount'

25 files changed, 1816 insertions, 1030 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index 332f5c29b53..66e65ab3942 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -138,8 +138,8 @@ config SPLIT_PTLOCK_CPUS
 #
 config MIGRATION
 	bool "Page migration"
-	def_bool y if NUMA
-	depends on SWAP && NUMA
+	def_bool y
+	depends on NUMA
 	help
 	  Allows the migration of the physical location of pages of processes
 	  while the virtual addresses are not changed. This is useful for
diff --git a/mm/filemap.c b/mm/filemap.c
index fd57442186c..807a463fd5e 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -14,6 +14,7 @@
 #include <linux/slab.h>
 #include <linux/compiler.h>
 #include <linux/fs.h>
+#include <linux/uaccess.h>
 #include <linux/aio.h>
 #include <linux/capability.h>
 #include <linux/kernel_stat.h>
@@ -38,7 +39,6 @@
  */
 #include <linux/buffer_head.h> /* for generic_osync_inode */
 
-#include <asm/uaccess.h>
 #include <asm/mman.h>
 
 static ssize_t
@@ -171,15 +171,17 @@ static int sync_page(void *word)
 }
 
 /**
- * filemap_fdatawrite_range - start writeback against all of a mapping's
- * dirty pages that lie within the byte offsets <start, end>
+ * __filemap_fdatawrite_range - start writeback on mapping dirty pages in range
  * @mapping:	address space structure to write
  * @start:	offset in bytes where the range starts
  * @end:	offset in bytes where the range ends (inclusive)
  * @sync_mode:	enable synchronous operation
  *
+ * Start writeback against all of a mapping's dirty pages that lie
+ * within the byte offsets <start, end> inclusive.
+ *
  * If sync_mode is WB_SYNC_ALL then this is a "data integrity" operation, as
- * opposed to a regular memory * cleansing writeback.  The difference between
+ * opposed to a regular memory cleansing writeback.  The difference between
  * these two operations is that if a dirty page/buffer is encountered, it must
  * be waited upon, and not just skipped over.
  */
@@ -190,8 +192,8 @@ int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
 	struct writeback_control wbc = {
 		.sync_mode = sync_mode,
 		.nr_to_write = mapping->nrpages * 2,
-		.start = start,
-		.end = end,
+		.range_start = start,
+		.range_end = end,
 	};
 
 	if (!mapping_cap_writeback_dirty(mapping))
@@ -204,7 +206,7 @@ int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
 static inline int __filemap_fdatawrite(struct address_space *mapping,
 	int sync_mode)
 {
-	return __filemap_fdatawrite_range(mapping, 0, 0, sync_mode);
+	return __filemap_fdatawrite_range(mapping, 0, LLONG_MAX, sync_mode);
 }
 
 int filemap_fdatawrite(struct address_space *mapping)
@@ -219,7 +221,10 @@ static int filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
 	return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_ALL);
 }
 
-/*
+/**
+ * filemap_flush - mostly a non-blocking flush
+ * @mapping:	target address_space
+ *
  * This is a mostly non-blocking flush.  Not suitable for data-integrity
  * purposes - I/O may not be started against all dirty pages.
  */
@@ -229,7 +234,12 @@ int filemap_flush(struct address_space *mapping)
 }
 EXPORT_SYMBOL(filemap_flush);
 
-/*
+/**
+ * wait_on_page_writeback_range - wait for writeback to complete
+ * @mapping:	target address_space
+ * @start:	beginning page index
+ * @end:	ending page index
+ *
  * Wait for writeback to complete against pages indexed by start->end
  * inclusive
  */
@@ -276,7 +286,13 @@ int wait_on_page_writeback_range(struct address_space *mapping,
 	return ret;
 }
 
-/*
+/**
+ * sync_page_range - write and wait on all pages in the passed range
+ * @inode:	target inode
+ * @mapping:	target address_space
+ * @pos:	beginning offset in pages to write
+ * @count:	number of bytes to write
+ *
  * Write and wait upon all the pages in the passed range.  This is a "data
  * integrity" operation.  It waits upon in-flight writeout before starting and
  * waiting upon new writeout.  If there was an IO error, return it.
@@ -305,7 +321,13 @@ int sync_page_range(struct inode *inode, struct address_space *mapping,
 }
 EXPORT_SYMBOL(sync_page_range);
 
-/*
+/**
+ * sync_page_range_nolock
+ * @inode:	target inode
+ * @mapping:	target address_space
+ * @pos:	beginning offset in pages to write
+ * @count:	number of bytes to write
+ *
  * Note: Holding i_mutex across sync_page_range_nolock is not a good idea
  * as it forces O_SYNC writers to different parts of the same file
  * to be serialised right until io completion.
@@ -329,10 +351,11 @@ int sync_page_range_nolock(struct inode *inode, struct address_space *mapping,
 EXPORT_SYMBOL(sync_page_range_nolock);
 
 /**
- * filemap_fdatawait - walk the list of under-writeback pages of the given
- *     address space and wait for all of them.
- *
+ * filemap_fdatawait - wait for all under-writeback pages to complete
  * @mapping: address space structure to wait for
+ *
+ * Walk the list of under-writeback pages of the given address space
+ * and wait for all of them.
  */
 int filemap_fdatawait(struct address_space *mapping)
 {
@@ -368,7 +391,12 @@ int filemap_write_and_wait(struct address_space *mapping)
 }
 EXPORT_SYMBOL(filemap_write_and_wait);
 
-/*
+/**
+ * filemap_write_and_wait_range - write out & wait on a file range
+ * @mapping:	the address_space for the pages
+ * @lstart:	offset in bytes where the range starts
+ * @lend:	offset in bytes where the range ends (inclusive)
+ *
  * Write out and wait upon file offsets lstart->lend, inclusive.
  *
  * Note that `lend' is inclusive (describes the last byte to be written) so
@@ -394,8 +422,14 @@ int filemap_write_and_wait_range(struct address_space *mapping,
 	return err;
 }
 
-/*
- * This function is used to add newly allocated pagecache pages:
+/**
+ * add_to_page_cache - add newly allocated pagecache pages
+ * @page:	page to add
+ * @mapping:	the page's address_space
+ * @offset:	page index
+ * @gfp_mask:	page allocation mode
+ *
+ * This function is used to add newly allocated pagecache pages;
  * the page is new, so we can just run SetPageLocked() against it.
  * The other page state flags were set by rmqueue().
  *
@@ -422,7 +456,6 @@ int add_to_page_cache(struct page *page, struct address_space *mapping,
 	}
 	return error;
 }
-
 EXPORT_SYMBOL(add_to_page_cache);
 
 int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
@@ -489,8 +522,7 @@ void fastcall wait_on_page_bit(struct page *page, int bit_nr)
 EXPORT_SYMBOL(wait_on_page_bit);
 
 /**
- * unlock_page() - unlock a locked page
- *
+ * unlock_page - unlock a locked page
  * @page: the page
  *
  * Unlocks the page and wakes up sleepers in ___wait_on_page_locked().
@@ -513,8 +545,9 @@ void fastcall unlock_page(struct page *page)
 }
 EXPORT_SYMBOL(unlock_page);
 
-/*
- * End writeback against a page.
+/**
+ * end_page_writeback - end writeback against a page
+ * @page: the page
  */
 void end_page_writeback(struct page *page)
 {
@@ -527,10 +560,11 @@ void end_page_writeback(struct page *page)
 }
 EXPORT_SYMBOL(end_page_writeback);
 
-/*
- * Get a lock on the page, assuming we need to sleep to get it.
+/**
+ * __lock_page - get a lock on the page, assuming we need to sleep to get it
+ * @page: the page to lock
  *
- * Ugly: running sync_page() in state TASK_UNINTERRUPTIBLE is scary.  If some
+ * Ugly. Running sync_page() in state TASK_UNINTERRUPTIBLE is scary.  If some
  * random driver's requestfn sets TASK_RUNNING, we could busywait.  However
  * chances are that on the second loop, the block layer's plug list is empty,
  * so sync_page() will then return in state TASK_UNINTERRUPTIBLE.
@@ -544,8 +578,12 @@ void fastcall __lock_page(struct page *page)
 }
 EXPORT_SYMBOL(__lock_page);
 
-/*
- * a rather lightweight function, finding and getting a reference to a
+/**
+ * find_get_page - find and get a page reference
+ * @mapping: the address_space to search
+ * @offset: the page index
+ *
+ * A rather lightweight function, finding and getting a reference to a
  * hashed page atomically.
  */
 struct page * find_get_page(struct address_space *mapping, unsigned long offset)
@@ -559,11 +597,14 @@ struct page * find_get_page(struct address_space *mapping, unsigned long offset)
 	read_unlock_irq(&mapping->tree_lock);
 	return page;
 }
-
 EXPORT_SYMBOL(find_get_page);
 
-/*
- * Same as above, but trylock it instead of incrementing the count.
+/**
+ * find_trylock_page - find and lock a page
+ * @mapping: the address_space to search
+ * @offset: the page index
+ *
+ * Same as find_get_page(), but trylock it instead of incrementing the count.
  */
 struct page *find_trylock_page(struct address_space *mapping, unsigned long offset)
 {
@@ -576,12 +617,10 @@ struct page *find_trylock_page(struct address_space *mapping, unsigned long offs
 	read_unlock_irq(&mapping->tree_lock);
 	return page;
 }
-
 EXPORT_SYMBOL(find_trylock_page);
 
 /**
  * find_lock_page - locate, pin and lock a pagecache page
- *
  * @mapping: the address_space to search
  * @offset: the page index
  *
@@ -617,12 +656,10 @@ repeat:
 	read_unlock_irq(&mapping->tree_lock);
 	return page;
 }
-
 EXPORT_SYMBOL(find_lock_page);
 
 /**
  * find_or_create_page - locate or add a pagecache page
- *
  * @mapping: the page's address_space
  * @index: the page's index into the mapping
  * @gfp_mask: page allocation mode
@@ -663,7 +700,6 @@ repeat:
 		page_cache_release(cached_page);
 	return page;
 }
-
 EXPORT_SYMBOL(find_or_create_page);
 
 /**
@@ -729,9 +765,16 @@ unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index,
 	return i;
 }
 
-/*
+/**
+ * find_get_pages_tag - find and return pages that match @tag
+ * @mapping:	the address_space to search
+ * @index:	the starting page index
+ * @tag:	the tag index
+ * @nr_pages:	the maximum number of pages
+ * @pages:	where the resulting pages are placed
+ *
  * Like find_get_pages, except we only return pages which are tagged with
- * `tag'.   We update *index to index the next page for the traversal.
+ * @tag.   We update @index to index the next page for the traversal.
  */
 unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index,
 			int tag, unsigned int nr_pages, struct page **pages)
@@ -750,7 +793,11 @@ unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index,
 	return ret;
 }
 
-/*
+/**
+ * grab_cache_page_nowait - returns locked page at given index in given cache
+ * @mapping: target address_space
+ * @index: the page index
+ *
  * Same as grab_cache_page, but do not wait if the page is unavailable.
  * This is intended for speculative data generators, where the data can
  * be regenerated if the page couldn't be grabbed.  This routine should
@@ -779,19 +826,25 @@ grab_cache_page_nowait(struct address_space *mapping, unsigned long index)
 	}
 	return page;
 }
-
 EXPORT_SYMBOL(grab_cache_page_nowait);
 
-/*
+/**
+ * do_generic_mapping_read - generic file read routine
+ * @mapping:	address_space to be read
+ * @_ra:	file's readahead state
+ * @filp:	the file to read
+ * @ppos:	current file position
+ * @desc:	read_descriptor
+ * @actor:	read method
+ *
  * This is a generic file read routine, and uses the
- * mapping->a_ops->readpage() function for the actual low-level
- * stuff.
+ * mapping->a_ops->readpage() function for the actual low-level stuff.
  *
  * This is really ugly. But the goto's actually try to clarify some
  * of the logic when it comes to error handling etc.
  *
- * Note the struct file* is only passed for the use of readpage.  It may be
- * NULL.
+ * Note the struct file* is only passed for the use of readpage.
+ * It may be NULL.
  */
 void do_generic_mapping_read(struct address_space *mapping,
 			     struct file_ra_state *_ra,
@@ -1004,7 +1057,6 @@ out:
 	if (filp)
 		file_accessed(filp);
 }
-
 EXPORT_SYMBOL(do_generic_mapping_read);
 
 int file_read_actor(read_descriptor_t *desc, struct page *page,
@@ -1045,7 +1097,13 @@ success:
 	return size;
 }
 
-/*
+/**
+ * __generic_file_aio_read - generic filesystem read routine
+ * @iocb:	kernel I/O control block
+ * @iov:	io vector request
+ * @nr_segs:	number of segments in the iovec
+ * @ppos:	current file position
+ *
  * This is the "read()" routine for all filesystems
  * that can use the page cache directly.
  */
@@ -1124,7 +1182,6 @@ __generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
 out:
 	return retval;
 }
-
 EXPORT_SYMBOL(__generic_file_aio_read);
 
 ssize_t
@@ -1135,7 +1192,6 @@ generic_file_aio_read(struct kiocb *iocb, char __user *buf, size_t count, loff_t
 	BUG_ON(iocb->ki_pos != pos);
 	return __generic_file_aio_read(iocb, &local_iov, 1, &iocb->ki_pos);
 }
-
 EXPORT_SYMBOL(generic_file_aio_read);
 
 ssize_t
@@ -1151,7 +1207,6 @@ generic_file_read(struct file *filp, char __user *buf, size_t count, loff_t *ppo
 		ret = wait_on_sync_kiocb(&kiocb);
 	return ret;
 }
-
 EXPORT_SYMBOL(generic_file_read);
 
 int file_send_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size)
@@ -1192,7 +1247,6 @@ ssize_t generic_file_sendfile(struct file *in_file, loff_t *ppos,
 		return desc.written;
 	return desc.error;
 }
-
 EXPORT_SYMBOL(generic_file_sendfile);
 
 static ssize_t
@@ -1228,11 +1282,15 @@ asmlinkage ssize_t sys_readahead(int fd, loff_t offset, size_t count)
 }
 
 #ifdef CONFIG_MMU
-/*
+static int FASTCALL(page_cache_read(struct file * file, unsigned long offset));
+/**
+ * page_cache_read - adds requested page to the page cache if not already there
+ * @file:	file to read
+ * @offset:	page index
+ *
  * This adds the requested page to the page cache if it isn't already there,
  * and schedules an I/O to read in its contents from disk.
  */
-static int FASTCALL(page_cache_read(struct file * file, unsigned long offset));
 static int fastcall page_cache_read(struct file * file, unsigned long offset)
 {
 	struct address_space *mapping = file->f_mapping;
@@ -1259,7 +1317,12 @@ static int fastcall page_cache_read(struct file * file, unsigned long offset)
 
 #define MMAP_LOTSAMISS  (100)
 
-/*
+/**
+ * filemap_nopage - read in file data for page fault handling
+ * @area:	the applicable vm_area
+ * @address:	target address to read in
+ * @type:	returned with VM_FAULT_{MINOR,MAJOR} if not %NULL
+ *
  * filemap_nopage() is invoked via the vma operations vector for a
  * mapped memory region to read in file data during a page fault.
  *
@@ -1462,7 +1525,6 @@ page_not_uptodate:
 	page_cache_release(page);
 	return NULL;
 }
-
 EXPORT_SYMBOL(filemap_nopage);
 
 static struct page * filemap_getpage(struct file *file, unsigned long pgoff,
@@ -1716,7 +1778,13 @@ repeat:
 	return page;
 }
 
-/*
+/**
+ * read_cache_page - read into page cache, fill it if needed
+ * @mapping:	the page's address_space
+ * @index:	the page index
+ * @filler:	function to perform the read
+ * @data:	destination for read data
+ *
  * Read into the page cache. If a page already exists,
  * and PageUptodate() is not set, try to fill the page.
  */
@@ -1754,7 +1822,6 @@ retry:
  out:
 	return page;
 }
-
 EXPORT_SYMBOL(read_cache_page);
 
 /*
@@ -1835,7 +1902,7 @@ __filemap_copy_from_user_iovec(char *vaddr,
 		int copy = min(bytes, iov->iov_len - base);
 
 		base = 0;
-		left = __copy_from_user_inatomic(vaddr, buf, copy);
+		left = __copy_from_user_inatomic_nocache(vaddr, buf, copy);
 		copied += copy;
 		bytes -= copy;
 		vaddr += copy;
@@ -1854,7 +1921,7 @@ __filemap_copy_from_user_iovec(char *vaddr,
 /*
  * Performs necessary checks before doing a write
  *
- * Can adjust writing position aor amount of bytes to write.
+ * Can adjust writing position or amount of bytes to write.
  * Returns appropriate error code that caller should return or
  * zero in case that write should be allowed.
  */
diff --git a/mm/filemap.h b/mm/filemap.h
index 13793ba0ce1..5683cde2205 100644
--- a/mm/filemap.h
+++ b/mm/filemap.h
@@ -13,7 +13,7 @@
 #include <linux/highmem.h>
 #include <linux/uio.h>
 #include <linux/config.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 size_t
 __filemap_copy_from_user_iovec(char *vaddr,
@@ -34,13 +34,13 @@ filemap_copy_from_user(struct page *page, unsigned long offset,
 	int left;
 
 	kaddr = kmap_atomic(page, KM_USER0);
-	left = __copy_from_user_inatomic(kaddr + offset, buf, bytes);
+	left = __copy_from_user_inatomic_nocache(kaddr + offset, buf, bytes);
 	kunmap_atomic(kaddr, KM_USER0);
 
 	if (left != 0) {
 		/* Do it the slow way */
 		kaddr = kmap(page);
-		left = __copy_from_user(kaddr + offset, buf, bytes);
+		left = __copy_from_user_nocache(kaddr + offset, buf, bytes);
 		kunmap(page);
 	}
 	return bytes - left;
diff --git a/mm/fremap.c b/mm/fremap.c
index 9f381e58bf4..21b7d0cbc98 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -83,6 +83,7 @@ int install_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	page_add_file_rmap(page);
 	pte_val = *pte;
 	update_mmu_cache(vma, addr, pte_val);
+	lazy_mmu_prot_update(pte_val);
 	err = 0;
 unlock:
 	pte_unmap_unlock(pte, ptl);
@@ -114,7 +115,13 @@ 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;
-	update_mmu_cache(vma, addr, pte_val);
+	/*
+	 * 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
+	 * non-present entry (like a swap entry), noting what file offset should
+	 * be mapped there when there's a fault (in a non-linear vma where
+	 * that's not obvious).
+	 */
 	pte_unmap_unlock(pte, ptl);
 	err = 0;
 out:
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 832f676ca03..df499973255 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -22,7 +22,7 @@
 #include "internal.h"
 
 const unsigned long hugetlb_zero = 0, hugetlb_infinity = ~0UL;
-static unsigned long nr_huge_pages, free_huge_pages, reserved_huge_pages;
+static unsigned long nr_huge_pages, free_huge_pages, resv_huge_pages;
 unsigned long max_huge_pages;
 static struct list_head hugepage_freelists[MAX_NUMNODES];
 static unsigned int nr_huge_pages_node[MAX_NUMNODES];
@@ -123,39 +123,13 @@ static int alloc_fresh_huge_page(void)
 static struct page *alloc_huge_page(struct vm_area_struct *vma,
 				    unsigned long addr)
 {
-	struct inode *inode = vma->vm_file->f_dentry->d_inode;
 	struct page *page;
-	int use_reserve = 0;
-	unsigned long idx;
 
 	spin_lock(&hugetlb_lock);
-
-	if (vma->vm_flags & VM_MAYSHARE) {
-
-		/* idx = radix tree index, i.e. offset into file in
-		 * HPAGE_SIZE units */
-		idx = ((addr - vma->vm_start) >> HPAGE_SHIFT)
-			+ (vma->vm_pgoff >> (HPAGE_SHIFT - PAGE_SHIFT));
-
-		/* The hugetlbfs specific inode info stores the number
-		 * of "guaranteed available" (huge) pages.  That is,
-		 * the first 'prereserved_hpages' pages of the inode
-		 * are either already instantiated, or have been
-		 * pre-reserved (by hugetlb_reserve_for_inode()). Here
-		 * we're in the process of instantiating the page, so
-		 * we use this to determine whether to draw from the
-		 * pre-reserved pool or the truly free pool. */
-		if (idx < HUGETLBFS_I(inode)->prereserved_hpages)
-			use_reserve = 1;
-	}
-
-	if (!use_reserve) {
-		if (free_huge_pages <= reserved_huge_pages)
-			goto fail;
-	} else {
-		BUG_ON(reserved_huge_pages == 0);
-		reserved_huge_pages--;
-	}
+	if (vma->vm_flags & VM_MAYSHARE)
+		resv_huge_pages--;
+	else if (free_huge_pages <= resv_huge_pages)
+		goto fail;
 
 	page = dequeue_huge_page(vma, addr);
 	if (!page)
@@ -165,96 +139,11 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma,
 	set_page_refcounted(page);
 	return page;
 
- fail:
-	WARN_ON(use_reserve); /* reserved allocations shouldn't fail */
+fail:
 	spin_unlock(&hugetlb_lock);
 	return NULL;
 }
 
-/* hugetlb_extend_reservation()
- *
- * Ensure that at least 'atleast' hugepages are, and will remain,
- * available to instantiate the first 'atleast' pages of the given
- * inode.  If the inode doesn't already have this many pages reserved
- * or instantiated, set aside some hugepages in the reserved pool to
- * satisfy later faults (or fail now if there aren't enough, rather
- * than getting the SIGBUS later).
- */
-int hugetlb_extend_reservation(struct hugetlbfs_inode_info *info,
-			       unsigned long atleast)
-{
-	struct inode *inode = &info->vfs_inode;
-	unsigned long change_in_reserve = 0;
-	int ret = 0;
-
-	spin_lock(&hugetlb_lock);
-	read_lock_irq(&inode->i_mapping->tree_lock);
-
-	if (info->prereserved_hpages >= atleast)
-		goto out;
-
-	/* Because we always call this on shared mappings, none of the
-	 * pages beyond info->prereserved_hpages can have been
-	 * instantiated, so we need to reserve all of them now. */
-	change_in_reserve = atleast - info->prereserved_hpages;
-
-	if ((reserved_huge_pages + change_in_reserve) > free_huge_pages) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	reserved_huge_pages += change_in_reserve;
-	info->prereserved_hpages = atleast;
-
- out:
-	read_unlock_irq(&inode->i_mapping->tree_lock);
-	spin_unlock(&hugetlb_lock);
-
-	return ret;
-}
-
-/* hugetlb_truncate_reservation()
- *
- * This returns pages reserved for the given inode to the general free
- * hugepage pool.  If the inode has any pages prereserved, but not
- * instantiated, beyond offset (atmost << HPAGE_SIZE), then release
- * them.
- */
-void hugetlb_truncate_reservation(struct hugetlbfs_inode_info *info,
-				  unsigned long atmost)
-{
-	struct inode *inode = &info->vfs_inode;
-	struct address_space *mapping = inode->i_mapping;
-	unsigned long idx;
-	unsigned long change_in_reserve = 0;
-	struct page *page;
-
-	spin_lock(&hugetlb_lock);
-	read_lock_irq(&inode->i_mapping->tree_lock);
-
-	if (info->prereserved_hpages <= atmost)
-		goto out;
-
-	/* Count pages which were reserved, but not instantiated, and
-	 * which we can now release. */
-	for (idx = atmost; idx < info->prereserved_hpages; idx++) {
-		page = radix_tree_lookup(&mapping->page_tree, idx);
-		if (!page)
-			/* Pages which are already instantiated can't
-			 * be unreserved (and in fact have already
-			 * been removed from the reserved pool) */
-			change_in_reserve++;
-	}
-
-	BUG_ON(reserved_huge_pages < change_in_reserve);
-	reserved_huge_pages -= change_in_reserve;
-	info->prereserved_hpages = atmost;
-
- out:
-	read_unlock_irq(&inode->i_mapping->tree_lock);
-	spin_unlock(&hugetlb_lock);
-}
-
 static int __init hugetlb_init(void)
 {
 	unsigned long i;
@@ -334,7 +223,7 @@ static unsigned long set_max_huge_pages(unsigned long count)
 		return nr_huge_pages;
 
 	spin_lock(&hugetlb_lock);
-	count = max(count, reserved_huge_pages);
+	count = max(count, resv_huge_pages);
 	try_to_free_low(count);
 	while (count < nr_huge_pages) {
 		struct page *page = dequeue_huge_page(NULL, 0);
@@ -361,11 +250,11 @@ int hugetlb_report_meminfo(char *buf)
 	return sprintf(buf,
 			"HugePages_Total: %5lu\n"
 			"HugePages_Free:  %5lu\n"
-		        "HugePages_Rsvd:  %5lu\n"
+			"HugePages_Rsvd:  %5lu\n"
 			"Hugepagesize:    %5lu kB\n",
 			nr_huge_pages,
 			free_huge_pages,
-		        reserved_huge_pages,
+			resv_huge_pages,
 			HPAGE_SIZE/1024);
 }
 
@@ -754,3 +643,156 @@ void hugetlb_change_protection(struct vm_area_struct *vma,
 	flush_tlb_range(vma, start, end);
 }
 
+struct file_region {
+	struct list_head link;
+	long from;
+	long to;
+};
+
+static long region_add(struct list_head *head, long f, long t)
+{
+	struct file_region *rg, *nrg, *trg;
+
+	/* Locate the region we are either in or before. */
+	list_for_each_entry(rg, head, link)
+		if (f <= rg->to)
+			break;
+
+	/* Round our left edge to the current segment if it encloses us. */
+	if (f > rg->from)
+		f = rg->from;
+
+	/* Check for and consume any regions we now overlap with. */
+	nrg = rg;
+	list_for_each_entry_safe(rg, trg, rg->link.prev, link) {
+		if (&rg->link == head)
+			break;
+		if (rg->from > t)
+			break;
+
+		/* If this area reaches higher then extend our area to
+		 * include it completely.  If this is not the first area
+		 * which we intend to reuse, free it. */
+		if (rg->to > t)
+			t = rg->to;
+		if (rg != nrg) {
+			list_del(&rg->link);
+			kfree(rg);
+		}
+	}
+	nrg->from = f;
+	nrg->to = t;
+	return 0;
+}
+
+static long region_chg(struct list_head *head, long f, long t)
+{
+	struct file_region *rg, *nrg;
+	long chg = 0;
+
+	/* Locate the region we are before or in. */
+	list_for_each_entry(rg, head, link)
+		if (f <= rg->to)
+			break;
+
+	/* If we are below the current region then a new region is required.
+	 * Subtle, allocate a new region at the position but make it zero
+	 * size such that we can guarentee to record the reservation. */
+	if (&rg->link == head || t < rg->from) {
+		nrg = kmalloc(sizeof(*nrg), GFP_KERNEL);
+		if (nrg == 0)
+			return -ENOMEM;
+		nrg->from = f;
+		nrg->to   = f;
+		INIT_LIST_HEAD(&nrg->link);
+		list_add(&nrg->link, rg->link.prev);
+
+		return t - f;
+	}
+
+	/* Round our left edge to the current segment if it encloses us. */
+	if (f > rg->from)
+		f = rg->from;
+	chg = t - f;
+
+	/* Check for and consume any regions we now overlap with. */
+	list_for_each_entry(rg, rg->link.prev, link) {
+		if (&rg->link == head)
+			break;
+		if (rg->from > t)
+			return chg;
+
+		/* We overlap with this area, if it extends futher than
+		 * us then we must extend ourselves.  Account for its
+		 * existing reservation. */
+		if (rg->to > t) {
+			chg += rg->to - t;
+			t = rg->to;
+		}
+		chg -= rg->to - rg->from;
+	}
+	return chg;
+}
+
+static long region_truncate(struct list_head *head, long end)
+{
+	struct file_region *rg, *trg;
+	long chg = 0;
+
+	/* Locate the region we are either in or before. */
+	list_for_each_entry(rg, head, link)
+		if (end <= rg->to)
+			break;
+	if (&rg->link == head)
+		return 0;
+
+	/* If we are in the middle of a region then adjust it. */
+	if (end > rg->from) {
+		chg = rg->to - end;
+		rg->to = end;
+		rg = list_entry(rg->link.next, typeof(*rg), link);
+	}
+
+	/* Drop any remaining regions. */
+	list_for_each_entry_safe(rg, trg, rg->link.prev, link) {
+		if (&rg->link == head)
+			break;
+		chg += rg->to - rg->from;
+		list_del(&rg->link);
+		kfree(rg);
+	}
+	return chg;
+}
+
+static int hugetlb_acct_memory(long delta)
+{
+	int ret = -ENOMEM;
+
+	spin_lock(&hugetlb_lock);
+	if ((delta + resv_huge_pages) <= free_huge_pages) {
+		resv_huge_pages += delta;
+		ret = 0;
+	}
+	spin_unlock(&hugetlb_lock);
+	return ret;
+}
+
+int hugetlb_reserve_pages(struct inode *inode, long from, long to)
+{
+	long ret, chg;
+
+	chg = region_chg(&inode->i_mapping->private_list, from, to);
+	if (chg < 0)
+		return chg;
+	ret = hugetlb_acct_memory(chg);
+	if (ret < 0)
+		return ret;
+	region_add(&inode->i_mapping->private_list, from, to);
+	return 0;
+}
+
+void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed)
+{
+	long chg = region_truncate(&inode->i_mapping->private_list, offset);
+	hugetlb_acct_memory(freed - chg);
+}
diff --git a/mm/memory.c b/mm/memory.c
index 0ec7bc64427..247b5c312b9 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -434,7 +434,9 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	/* pte contains position in swap or file, so copy. */
 	if (unlikely(!pte_present(pte))) {
 		if (!pte_file(pte)) {
-			swap_duplicate(pte_to_swp_entry(pte));
+			swp_entry_t entry = pte_to_swp_entry(pte);
+
+			swap_duplicate(entry);
 			/* make sure dst_mm is on swapoff's mmlist. */
 			if (unlikely(list_empty(&dst_mm->mmlist))) {
 				spin_lock(&mmlist_lock);
@@ -443,6 +445,16 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 						 &src_mm->mmlist);
 				spin_unlock(&mmlist_lock);
 			}
+			if (is_write_migration_entry(entry) &&
+					is_cow_mapping(vm_flags)) {
+				/*
+				 * COW mappings require pages in both parent
+				 * and child to be set to read.
+				 */
+				make_migration_entry_read(&entry);
+				pte = swp_entry_to_pte(entry);
+				set_pte_at(src_mm, addr, src_pte, pte);