mm: merge populate and nopage into fault (fixes nonlinear)

Nonlinear mappings are (AFAIKS) simply a virtual memory concept that encodes
the virtual address -> file offset differently from linear mappings.

->populate is a layering violation because the filesystem/pagecache code
should need to know anything about the virtual memory mapping.  The hitch here
is that the ->nopage handler didn't pass down enough information (ie.  pgoff).
 But it is more logical to pass pgoff rather than have the ->nopage function
calculate it itself anyway (because that's a similar layering violation).

Having the populate handler install the pte itself is likewise a nasty thing
to be doing.

This patch introduces a new fault handler that replaces ->nopage and
->populate and (later) ->nopfn.  Most of the old mechanism is still in place
so there is a lot of duplication and nice cleanups that can be removed if
everyone switches over.

The rationale for doing this in the first place is that nonlinear mappings are
subject to the pagefault vs invalidate/truncate race too, and it seemed stupid
to duplicate the synchronisation logic rather than just consolidate the two.

After this patch, MAP_NONBLOCK no longer sets up ptes for pages present in
pagecache.  Seems like a fringe functionality anyway.

NOPAGE_REFAULT is removed.  This should be implemented with ->fault, and no
users have hit mainline yet.

[akpm@linux-foundation.org: cleanup]
[randy.dunlap@oracle.com: doc. fixes for readahead]
[akpm@linux-foundation.org: build fix]
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Cc: Mark Fasheh <mark.fasheh@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

9 files changed, 273 insertions, 209 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 462cda58a18..26b992d169e 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1301,40 +1301,38 @@ 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_fault - read in file data for page fault handling
+ * @vma:	user vma (not used)
+ * @fdata:	the applicable fault_data
  *
- * filemap_nopage() is invoked via the vma operations vector for a
+ * filemap_fault() is invoked via the vma operations vector for a
  * mapped memory region to read in file data during a page fault.
  *
  * The goto's are kind of ugly, but this streamlines the normal case of having
  * it in the page cache, and handles the special cases reasonably without
  * having a lot of duplicated code.
  */
-struct page *filemap_nopage(struct vm_area_struct *area,
-				unsigned long address, int *type)
+struct page *filemap_fault(struct vm_area_struct *vma, struct fault_data *fdata)
 {
 	int error;
-	struct file *file = area->vm_file;
+	struct file *file = vma->vm_file;
 	struct address_space *mapping = file->f_mapping;
 	struct file_ra_state *ra = &file->f_ra;
 	struct inode *inode = mapping->host;
 	struct page *page;
-	unsigned long size, pgoff;
-	int did_readaround = 0, majmin = VM_FAULT_MINOR;
+	unsigned long size;
+	int did_readaround = 0;
 
-	BUG_ON(!(area->vm_flags & VM_CAN_INVALIDATE));
+	fdata->type = VM_FAULT_MINOR;
 
-	pgoff = ((address-area->vm_start) >> PAGE_CACHE_SHIFT) + area->vm_pgoff;
+	BUG_ON(!(vma->vm_flags & VM_CAN_INVALIDATE));
 
 	size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
-	if (pgoff >= size)
+	if (fdata->pgoff >= size)
 		goto outside_data_content;
 
 	/* If we don't want any read-ahead, don't bother */
-	if (VM_RandomReadHint(area))
+	if (VM_RandomReadHint(vma))
 		goto no_cached_page;
 
 	/*
@@ -1343,19 +1341,19 @@ struct page *filemap_nopage(struct vm_area_struct *area,
 	 *
 	 * For sequential accesses, we use the generic readahead logic.
 	 */
-	if (VM_SequentialReadHint(area))
-		page_cache_readahead(mapping, ra, file, pgoff, 1);
+	if (VM_SequentialReadHint(vma))
+		page_cache_readahead(mapping, ra, file, fdata->pgoff, 1);
 
 	/*
 	 * Do we have something in the page cache already?
 	 */
 retry_find:
-	page = find_lock_page(mapping, pgoff);
+	page = find_lock_page(mapping, fdata->pgoff);
 	if (!page) {
 		unsigned long ra_pages;
 
-		if (VM_SequentialReadHint(area)) {
-			handle_ra_miss(mapping, ra, pgoff);
+		if (VM_SequentialReadHint(vma)) {
+			handle_ra_miss(mapping, ra, fdata->pgoff);
 			goto no_cached_page;
 		}
 		ra->mmap_miss++;
@@ -1372,7 +1370,7 @@ retry_find:
 		 * check did_readaround, as this is an inner loop.
 		 */
 		if (!did_readaround) {
-			majmin = VM_FAULT_MAJOR;
+			fdata->type = VM_FAULT_MAJOR;
 			count_vm_event(PGMAJFAULT);
 		}
 		did_readaround = 1;
@@ -1380,11 +1378,11 @@ retry_find:
 		if (ra_pages) {
 			pgoff_t start = 0;
 
-			if (pgoff > ra_pages / 2)
-				start = pgoff - ra_pages / 2;
+			if (fdata->pgoff > ra_pages / 2)
+				start = fdata->pgoff - ra_pages / 2;
 			do_page_cache_readahead(mapping, file, start, ra_pages);
 		}
-		page = find_lock_page(mapping, pgoff);
+		page = find_lock_page(mapping, fdata->pgoff);
 		if (!page)
 			goto no_cached_page;
 	}
@@ -1401,7 +1399,7 @@ retry_find:
 
 	/* Must recheck i_size under page lock */
 	size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
-	if (unlikely(pgoff >= size)) {
+	if (unlikely(fdata->pgoff >= size)) {
 		unlock_page(page);
 		goto outside_data_content;
 	}
@@ -1410,8 +1408,6 @@ retry_find:
 	 * Found the page and have a reference on it.
 	 */
 	mark_page_accessed(page);
-	if (type)
-		*type = majmin;
 	return page;
 
 outside_data_content:
@@ -1419,15 +1415,17 @@ outside_data_content:
 	 * An external ptracer can access pages that normally aren't
 	 * accessible..
 	 */
-	if (area->vm_mm == current->mm)
-		return NOPAGE_SIGBUS;
+	if (vma->vm_mm == current->mm) {
+		fdata->type = VM_FAULT_SIGBUS;
+		return NULL;
+	}
 	/* Fall through to the non-read-ahead case */
 no_cached_page:
 	/*
 	 * We're only likely to ever get here if MADV_RANDOM is in
 	 * effect.
 	 */
-	error = page_cache_read(file, pgoff);
+	error = page_cache_read(file, fdata->pgoff);
 
 	/*
 	 * The page we want has now been added to the page cache.
@@ -1443,13 +1441,15 @@ no_cached_page:
 	 * to schedule I/O.
 	 */
 	if (error == -ENOMEM)
-		return NOPAGE_OOM;
-	return NOPAGE_SIGBUS;
+		fdata->type = VM_FAULT_OOM;
+	else
+		fdata->type = VM_FAULT_SIGBUS;
+	return NULL;
 
 page_not_uptodate:
 	/* IO error path */
 	if (!did_readaround) {
-		majmin = VM_FAULT_MAJOR;
+		fdata->type = VM_FAULT_MAJOR;
 		count_vm_event(PGMAJFAULT);
 	}
 
@@ -1468,7 +1468,30 @@ page_not_uptodate:
 
 	/* Things didn't work out. Return zero to tell the mm layer so. */
 	shrink_readahead_size_eio(file, ra);
-	return NOPAGE_SIGBUS;
+	fdata->type = VM_FAULT_SIGBUS;
+	return NULL;
+}
+EXPORT_SYMBOL(filemap_fault);
+
+/*
+ * filemap_nopage and filemap_populate are legacy exports that are not used
+ * in tree. Scheduled for removal.
+ */
+struct page *filemap_nopage(struct vm_area_struct *area,
+				unsigned long address, int *type)
+{
+	struct page *page;
+	struct fault_data fdata;
+	fdata.address = address;
+	fdata.pgoff = ((address - area->vm_start) >> PAGE_CACHE_SHIFT)
+			+ area->vm_pgoff;
+	fdata.flags = 0;
+
+	page = filemap_fault(area, &fdata);
+	if (type)
+		*type = fdata.type;
+
+	return page;
 }
 EXPORT_SYMBOL(filemap_nopage);
 
@@ -1646,8 +1669,7 @@ repeat:
 EXPORT_SYMBOL(filemap_populate);
 
 struct vm_operations_struct generic_file_vm_ops = {
-	.nopage		= filemap_nopage,
-	.populate	= filemap_populate,
+	.fault		= filemap_fault,
 };
 
 /* This is used for a general mmap of a disk file */
@@ -1660,7 +1682,7 @@ int generic_file_mmap(struct file * file, struct vm_area_struct * vma)
 		return -ENOEXEC;
 	file_accessed(file);
 	vma->vm_ops = &generic_file_vm_ops;
-	vma->vm_flags |= VM_CAN_INVALIDATE;
+	vma->vm_flags |= VM_CAN_INVALIDATE | VM_CAN_NONLINEAR;
 	return 0;
 }
 
diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c
index 65ffc321f0c..82f4b8e9834 100644
--- a/mm/filemap_xip.c
+++ b/mm/filemap_xip.c
@@ -205,62 +205,67 @@ __xip_unmap (struct address_space * mapping,
 }
 
 /*
- * xip_nopage() is invoked via the vma operations vector for a
+ * xip_fault() is invoked via the vma operations vector for a
  * mapped memory region to read in file data during a page fault.
  *
- * This function is derived from filemap_nopage, but used for execute in place
+ * This function is derived from filemap_fault, but used for execute in place
  */
-static struct page *
-xip_file_nopage(struct vm_area_struct * area,
-		   unsigned long address,
-		   int *type)
+static struct page *xip_file_fault(struct vm_area_struct *area,
+					struct fault_data *fdata)
 {
 	struct file *file = area->vm_file;
 	struct address_space *mapping = file->f_mapping;
 	struct inode *inode = mapping->host;
 	struct page *page;
-	unsigned long size, pgoff, endoff;
+	pgoff_t size;
 
-	pgoff = ((address - area->vm_start) >> PAGE_CACHE_SHIFT)
-		+ area->vm_pgoff;
-	endoff = ((area->vm_end - area->vm_start) >> PAGE_CACHE_SHIFT)
-		+ area->vm_pgoff;
+	/* XXX: are VM_FAULT_ codes OK? */
 
 	size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
-	if (pgoff >= size)
-		return NOPAGE_SIGBUS;
+	if (fdata->pgoff >= size) {
+		fdata->type = VM_FAULT_SIGBUS;
+		return NULL;
+	}
 
-	page = mapping->a_ops->get_xip_page(mapping, pgoff*(PAGE_SIZE/512), 0);
+	page = mapping->a_ops->get_xip_page(mapping,
+					fdata->pgoff*(PAGE_SIZE/512), 0);
 	if (!IS_ERR(page))
 		goto out;
-	if (PTR_ERR(page) != -ENODATA)
-		return NOPAGE_SIGBUS;
+	if (PTR_ERR(page) != -ENODATA) {
+		fdata->type = VM_FAULT_OOM;
+		return NULL;
+	}
 
 	/* sparse block */
 	if ((area->vm_flags & (VM_WRITE | VM_MAYWRITE)) &&
 	    (area->vm_flags & (VM_SHARED| VM_MAYSHARE)) &&
 	    (!(mapping->host->i_sb->s_flags & MS_RDONLY))) {
 		/* maybe shared writable, allocate new block */
-		page = mapping->a_ops->get_xip_page (mapping,
-			pgoff*(PAGE_SIZE/512), 1);
-		if (IS_ERR(page))
-			return NOPAGE_SIGBUS;
+		page = mapping->a_ops->get_xip_page(mapping,
+					fdata->pgoff*(PAGE_SIZE/512), 1);
+		if (IS_ERR(page)) {
+			fdata->type = VM_FAULT_SIGBUS;
+			return NULL;
+		}
 		/* unmap page at pgoff from all other vmas */
-		__xip_unmap(mapping, pgoff);
+		__xip_unmap(mapping, fdata->pgoff);
 	} else {
 		/* not shared and writable, use xip_sparse_page() */
 		page = xip_sparse_page();
-		if (!page)
-			return NOPAGE_OOM;
+		if (!page) {
+			fdata->type = VM_FAULT_OOM;
+			return NULL;
+		}
 	}
 
 out:
+	fdata->type = VM_FAULT_MINOR;
 	page_cache_get(page);
 	return page;
 }
 
 static struct vm_operations_struct xip_file_vm_ops = {
-	.nopage         = xip_file_nopage,
+	.fault	= xip_file_fault,
 };
 
 int xip_file_mmap(struct file * file, struct vm_area_struct * vma)
@@ -269,6 +274,7 @@ int xip_file_mmap(struct file * file, struct vm_area_struct * vma)
 
 	file_accessed(file);
 	vma->vm_ops = &xip_file_vm_ops;
+	vma->vm_flags |= VM_CAN_NONLINEAR;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(xip_file_mmap);
diff --git a/mm/fremap.c b/mm/fremap.c
index 4e3f53dd5fd..01e51f01b84 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -126,6 +126,25 @@ out:
 	return err;
 }
 
+static int populate_range(struct mm_struct *mm, struct vm_area_struct *vma,
+			unsigned long addr, unsigned long size, pgoff_t pgoff)
+{
+	int err;
+
+	do {
+		err = install_file_pte(mm, vma, addr, pgoff, vma->vm_page_prot);
+		if (err)
+			return err;
+
+		size -= PAGE_SIZE;
+		addr += PAGE_SIZE;
+		pgoff++;
+	} while (size);
+
+        return 0;
+
+}
+
 /***
  * sys_remap_file_pages - remap arbitrary pages of a shared backing store
  *                        file within an existing vma.
@@ -183,41 +202,63 @@ asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size,
 	 * the single existing vma.  vm_private_data is used as a
 	 * swapout cursor in a VM_NONLINEAR vma.
 	 */
-	if (vma && (vma->vm_flags & VM_SHARED) &&
-		(!vma->vm_private_data || (vma->vm_flags & VM_NONLINEAR)) &&
-		vma->vm_ops && vma->vm_ops->populate &&
-			end > start && start >= vma->vm_start &&
-				end <= vma->vm_end) {
-
-		/* Must set VM_NONLINEAR before any pages are populated. */
-		if (pgoff != linear_page_index(vma, start) &&
-		    !(vma->vm_flags & VM_NONLINEAR)) {
-			if (!has_write_lock) {
-				up_read(&mm->mmap_sem);
-				down_write(&mm->mmap_sem);
-				has_write_lock = 1;
-				goto retry;
+	if (!vma || !(vma->vm_flags & VM_SHARED))
+		goto out;
+
+	if (vma->vm_private_data && !(vma->vm_flags & VM_NONLINEAR))
+		goto out;
+
+	if ((!vma->vm_ops || !vma->vm_ops->populate) &&
+					!(vma->vm_flags & VM_CAN_NONLINEAR))
+		goto out;
+
+	if (end <= start || start < vma->vm_start || end > vma->vm_end)
+		goto out;
+
+	/* Must set VM_NONLINEAR before any pages are populated. */
+	if (!(vma->vm_flags & VM_NONLINEAR)) {
+		/* Don't need a nonlinear mapping, exit success */
+		if (pgoff == linear_page_index(vma, start)) {
+			err = 0;
+			goto out;
+		}
+
+		if (!has_write_lock) {
+			up_read(&mm->mmap_sem);
+			down_write(&mm->mmap_sem);
+			has_write_lock = 1;
+			goto retry;
+		}
+		mapping = vma->vm_file->f_mapping;
+		spin_lock(&mapping->i_mmap_lock);
+		flush_dcache_mmap_lock(mapping);
+		vma->vm_flags |= VM_NONLINEAR;
+		vma_prio_tree_remove(vma, &mapping->i_mmap);
+		vma_nonlinear_insert(vma, &mapping->i_mmap_nonlinear);
+		flush_dcache_mmap_unlock(mapping);
+		spin_unlock(&mapping->i_mmap_lock);
+	}
+
+	if (vma->vm_flags & VM_CAN_NONLINEAR) {
+		err = populate_range(mm, vma, start, size, pgoff);
+		if (!err && !(flags & MAP_NONBLOCK)) {
+			if (unlikely(has_write_lock)) {
+				downgrade_write(&mm->mmap_sem);
+				has_write_lock = 0;
 			}
-			mapping = vma->vm_file->f_mapping;
-			spin_lock(&mapping->i_mmap_lock);
-			flush_dcache_mmap_lock(mapping);
-			vma->vm_flags |= VM_NONLINEAR;
-			vma_prio_tree_remove(vma, &mapping->i_mmap);
-			vma_nonlinear_insert(vma, &mapping->i_mmap_nonlinear);
-			flush_dcache_mmap_unlock(mapping);
-			spin_unlock(&mapping->i_mmap_lock);
+			make_pages_present(start, start+size);
 		}
+	} else
+		err = vma->vm_ops->populate(vma, start, size, vma->vm_page_prot,
+					    	pgoff, flags & MAP_NONBLOCK);
 
-		err = vma->vm_ops->populate(vma, start, size,
-					    vma->vm_page_prot,
-					    pgoff, flags & MAP_NONBLOCK);
+	/*
+	 * We can't clear VM_NONLINEAR because we'd have to do
+	 * it after ->populate completes, and that would prevent
+	 * downgrading the lock.  (Locks can't be upgraded).
+	 */
 
-		/*
-		 * We can't clear VM_NONLINEAR because we'd have to do
-		 * it after ->populate completes, and that would prevent
-		 * downgrading the lock.  (Locks can't be upgraded).
-		 */
-	}
+out:
 	if (likely(!has_write_lock))
 		up_read(&mm->mmap_sem);
 	else
diff --git a/mm/memory.c b/mm/memory.c
index e6c99f6b564..eee7fec3ab5 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1047,7 +1047,8 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 		if (pages)
 			foll_flags |= FOLL_GET;
 		if (!write && !(vma->vm_flags & VM_LOCKED) &&
-		    (!vma->vm_ops || !vma->vm_ops->nopage))
+		    (!vma->vm_ops || (!vma->vm_ops->nopage &&
+					!vma->vm_ops->fault)))
 			foll_flags |= FOLL_ANON;
 
 		do {
@@ -2288,10 +2289,10 @@ oom:
 }
 
 /*
- * do_no_page() tries to create a new page mapping. It aggressively
+ * __do_fault() tries to create a new page mapping. It aggressively
  * tries to share with existing pages, but makes a separate copy if
- * the "write_access" parameter is true in order to avoid the next
- * page fault.
+ * the FAULT_FLAG_WRITE is set in the flags parameter in order to avoid
+ * the next page fault.
  *
  * As this is called only for pages that do not currently exist, we
  * do not need to flush old virtual caches or the TLB.
@@ -2300,64 +2301,82 @@ oom:
  * but allow concurrent faults), and pte mapped but not yet locked.
  * We return with mmap_sem still held, but pte unmapped and unlocked.
  */
-static int do_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
+static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		unsigned long address, pte_t *page_table, pmd_t *pmd,
-		int write_access)
+		pgoff_t pgoff, unsigned int flags, pte_t orig_pte)
 {
 	spinlock_t *ptl;
-	struct page *page, *nopage_page;
+	struct page *page, *faulted_page;
 	pte_t entry;
-	int ret = VM_FAULT_MINOR;
 	int anon = 0;
 	struct page *dirty_page = NULL;
+	struct fault_data fdata;
+
+	fdata.address = address & PAGE_MASK;
+	fdata.pgoff = pgoff;
+	fdata.flags = flags;
 
 	pte_unmap(page_table);
 	BUG_ON(vma->vm_flags & VM_PFNMAP);
 
-	nopage_page = vma->vm_ops->nopage(vma, address & PAGE_MASK, &ret);
-	/* no page was available -- either SIGBUS, OOM or REFAULT */
-	if (unlikely(nopage_page == NOPAGE_SIGBUS))
-		return VM_FAULT_SIGBUS;
-	else if (unlikely(nopage_page == NOPAGE_OOM))
-		return VM_FAULT_OOM;
-	else if (unlikely(nopage_page == NOPAGE_REFAULT))
-		return VM_FAULT_MINOR;
+	if (likely(vma->vm_ops->fault)) {
+		fdata.type = -1;
+		faulted_page = vma->vm_ops->fault(vma, &fdata);
+		WARN_ON(fdata.type == -1);
+		if (unlikely(!faulted_page))
+			return fdata.type;
+	} else {
+		/* Legacy ->nopage path */
+		fdata.type = VM_FAULT_MINOR;
+		faulted_page = vma->vm_ops->nopage(vma, address & PAGE_MASK,
+								&fdata.type);
+		/* no page was available -- either SIGBUS or OOM */
+		if (unlikely(faulted_page == NOPAGE_SIGBUS))
+			return VM_FAULT_SIGBUS;
+		else if (unlikely(faulted_page == NOPAGE_OOM))
+			return VM_FAULT_OOM;
+	}
 
-	BUG_ON(vma->vm_flags & VM_CAN_INVALIDATE && !PageLocked(nopage_page));
 	/*
-	 * For consistency in subsequent calls, make the nopage_page always
+	 * For consistency in subsequent calls, make the faulted_page always
 	 * locked.
 	 */
 	if (unlikely(!(vma->vm_flags & VM_CAN_INVALIDATE)))
-		lock_page(nopage_page);
+		lock_page(faulted_page);
+	else
+		BUG_ON(!PageLocked(faulted_page));
 
 	/*
 	 * Should we do an early C-O-W break?
 	 */
-	page = nopage_page;
-	if (write_access) {
+	page = faulted_page;
+	if (flags & FAULT_FLAG_WRITE) {
 		if (!(vma->vm_flags & VM_SHARED)) {
+			anon = 1;
 			if (unlikely(anon_vma_prepare(vma))) {
-				ret = VM_FAULT_OOM;
-				goto out_error;
+				fdata.type = VM_FAULT_OOM;
+				goto out;
 			}
 			page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
 			if (!page) {
-				ret = VM_FAULT_OOM;
-				goto out_error;
+				fdata.type = VM_FAULT_OOM;
+				goto out;
 			}
-			copy_user_highpage(page, nopage_page, address, vma);
-			anon = 1;
+			copy_user_highpage(page, faulted_page, address, vma);
 		} else {
-			/* if the page will be shareable, see if the backing
+			/*
+			 * If the page will be shareable, see if the backing
 			 * address space wants to know that the page is about
-			 * to become writable */
+			 * to become writable
+			 */
 			if (vma->vm_ops->page_mkwrite &&
 			    vma->vm_ops->page_mkwrite(vma, page) < 0) {
-				ret = VM_FAULT_SIGBUS;
-				goto out_error;
+				fdata.type = VM_FAULT_SIGBUS;
+				anon = 1; /* no anon but release faulted_page */
+				goto out;
 			}
 		}
+
 	}
 
 	page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
@@ -2373,10 +2392,10 @@ static int do_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * handle that later.
 	 */
 	/* Only go through if we didn't race with anybody else... */
-	if (likely(pte_none(*page_table))) {
+	if (likely(pte_same(*page_table, orig_pte))) {
 		flush_icache_page(vma, page);
 		entry = mk_pte(page, vma->vm_page_prot);
-		if (write_access)
+		if (flags & FAULT_FLAG_WRITE)
 			entry = maybe_mkwrite(pte_mkdirty(entry), vma);
 		set_pte_at(mm, address, page_table, entry);
 		if (anon) {
@@ -2386,7 +2405,7 @@ static int do_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		} else {
 			inc_mm_counter(mm, file_rss);
 			page_add_file_rmap(page);
-			if (write_access) {
+			if (flags & FAULT_FLAG_WRITE) {
 				dirty_page = page;
 				get_page(dirty_page);
 			}
@@ -2399,25 +2418,42 @@ static int do_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		if (anon)
 			page_cache_release(page);
 		else
-			anon = 1; /* not anon, but release nopage_page */
+			anon = 1; /* no anon but release faulted_page */
 	}
 
 	pte_unmap_unlock(page_table, ptl);
 
 out:
-	unlock_page(nopage_page);
+	unlock_page(faulted_page);
 	if (anon)
-		page_cache_release(nopage_page);
+		page_cache_release(faulted_page);
 	else if (dirty_page) {
 		set_page_dirty_balance(dirty_page);
 		put_page(dirty_page);
 	}
 
-	return ret;
+	return fdata.type;
+}
 
-out_error:
-	anon = 1; /* relase nopage_page */
-	goto out;
+static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
+		unsigned long address, pte_t *page_table, pmd_t *pmd,
+		int write_access, pte_t orig_pte)
+{
+	pgoff_t pgoff = (((address & PAGE_MASK)
+			- vma->vm_start) >> PAGE_CACHE_SHIFT) + vma->vm_pgoff;
+	unsigned int flags = (write_access ? FAULT_FLAG_WRITE : 0);
+
+	return __do_fault(mm, vma, address, page_table, pmd, pgoff, flags, orig_pte);
+}
+
+static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
+		unsigned long address, pte_t *page_table, pmd_t *pmd,
+		int write_access, pgoff_t pgoff, pte_t orig_pte)
+{
+	unsigned int flags = FAULT_FLAG_NONLINEAR |
+				(write_access ? FAULT_FLAG_WRITE : 0);
+
+	return __do_fault(mm, vma, address, page_table, pmd, pgoff, flags, orig_pte);
 }
 
 /*
@@ -2496,9 +2532,14 @@ static int do_file_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		print_bad_pte(vma, orig_pte, address);
 		return VM_FAULT_OOM;
 	}
-	/* We can then assume vm->vm_ops && vma->vm_ops->populate */
 
 	pgoff = pte_to_pgoff(orig_pte);
+
+	if (vma->vm_ops && vma->vm_ops->fault)
+		return do_nonlinear_fault(mm, vma, address, page_table, pmd,
+					write_access, pgoff, orig_pte);
+
+	/* We can then assume vm->vm_ops && vma->vm_ops->populate */
 	err = vma->vm_ops->populate(vma, address & PAGE_MASK, PAGE_SIZE,
 					vma->vm_page_prot, pgoff, 0);
 	if (err == -ENOMEM)
@@ -2532,10 +2573,9 @@ static inline int handle_pte_fault(struct mm_struct *mm,
 	if (!pte_present(entry)) {
 		if (pte_none(entry)) {
 			if (vma->vm_ops) {
-				if (vma->vm_ops->nopage)
-					return do_no_page(mm, vma, address,
-							  pte, pmd,
-							  write_access);
+				if (vma->vm_ops->fault || vma->vm_ops->nopage)
+					return do_linear_fault(mm, vma, address,
+						pte, pmd, write_access, entry);
 				if (unlikely(vma->vm_ops->nopfn))
 					return do_no_pfn(mm, vma, address, pte,
 							 pmd, write_access);
diff --git a/mm/mmap.c b/mm/mmap.c
index 144b4a290f2..724f342bcf8 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1165,12 +1165,8 @@ out:
 		mm->locked_vm += len >> PAGE_SHIFT;
 		make_pages_present(addr, addr + len);
 	}
-	if (flags & MAP_POPULATE) {
-		up_write(&mm->mmap_sem);
-		sys_remap_file_pages(addr, len, 0,
-					pgoff, flags & MAP_NONBLOCK);
-		down_write(&mm->mmap_sem);
-	}
+	if ((flags & MAP_POPULATE) && !(flags & MAP_NONBLOCK))
+		make_pages_present(addr, addr + len);
 	return addr;
 
 unmap_and_free_vma:
diff --git a/mm/nommu.c b/mm/nommu.c
index 8bbbf147a79..aee0e1b0ebe 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1341,8 +1341,7 @@ int in_gate_area_no_task(unsigned long addr)
 	return 0;
 }
 
-struct page *filemap_nopage(struct vm_area_struct *area,
-			unsigned long address, int *type)
+struct page *filemap_fault(struct vm_area_struct *vma, struct fault_data *fdata)
 {
 	BUG();
 	return NULL;
diff --git a/mm/rmap.c b/mm/rmap.c
index 61e492597a0..fede5c7910b 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -621,8 +621,10 @@ void page_remove_rmap(struct page *page, struct vm_area_struct *vma)
 			printk (KERN_EMERG "  page->count = %x\n", page_count(page));
 			printk (KERN_EMERG "  page->mapping = %p\n", page->mapping);
 			print_symbol (KERN_EMERG "  vma->vm_ops = %s\n", (unsigned long)vma->vm_ops);
-			if (vma->vm_ops)
+			if (vma->vm_ops) {
 				print_symbol (KERN_EMERG "  vma->vm_ops->nopage = %s\n", (unsigned long)vma->vm_ops->nopage);
+				print_symbol (KERN_EMERG "  vma->vm_ops->fault = %s\n", (unsigned long)vma->vm_ops->fault);
+			}
 			if (vma->vm_file && vma->vm_file->f_op)
 				print_symbol (KERN_EMERG "  vma->vm_file->f_op->mmap = %s\n", (unsigned long)vma->vm_file->f_op->mmap);
 			BUG();
diff --git a/mm/shmem.c b/mm/shmem.c
index 5808fadd394..6b44440f1b2 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -83,7 +83,7 @@ enum sgp_type {
 	SGP_READ,	/* don't exceed i_size, don't allocate page */
 	SGP_CACHE,	/* don't exceed i_size, may allocate page */
 	SGP_WRITE,	/* may exceed i_size, may allocate page */
-	SGP_NOPAGE,	/* same as SGP_CACHE, return with page locked */
+	SGP_FAULT,	/* same as SGP_CACHE, return with page locked */
 };
 
 static int shmem_getpage(struct inode *inode, unsigned long idx,
@@ -1101,6 +1101,10 @@ static int shmem_getpage(struct inode *inode, unsigned long idx,
 
 	if (idx >= SHMEM_MAX_INDEX)
 		return -EFBIG;
+
+	if (type)
+		*type = VM_FAULT_MINOR;
+
 	/*
 	 * Normally, filepage is NULL on entry, and either found
 	 * uptodate immediately, or allocated and zeroed, or read
@@ -1291,7 +1295,7 @@ repeat:
 done:
 	if (*pagep != filepage) {
 		*pagep = filepage;
-		if (sgp != SGP_NOPAGE)
+		if (sgp != SGP_FAULT)
 			unlock_page(filepage);
 
 	}
@@ -1305,76 +1309,31 @@ failed:
 	return error;
 }
 
-static struct page *shmem_nopage(struct vm_area_struct *vma,
-				 unsigned long address, int *type)
+static struct page *shmem_fault(struct vm_area_struct *vma,
+					struct fault_data *fdata)
 {
 	struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
 	struct page *page = NULL;
-	unsigned long idx;
 	int error;
 
 	BUG_ON(!(vma->vm_flags & VM_CAN_INVALIDATE));
 
-	idx = (address - vma->vm_start) >> PAGE_SHIFT;
-	idx += vma->vm_pgoff;
-	idx >>= PAGE_CACHE_SHIFT - PAGE_SHIFT;
-	if (((loff_t) idx << PAGE_CACHE_SHIFT) >= i_size_read(inode))
-		return NOPAGE_SIGBUS;
+	if (((loff_t)fdata->pgoff << PAGE_CACHE_SHIFT) >= i_size_read(inode)) {
+		fdata->type = VM_FAULT_SIGBUS;
+		return NULL;
+	}
 
-	error = shmem_getpage(inode, idx, &page, SGP_NOPAGE, type);
-	if (error)
-		return (error == -ENOMEM)? NOPAGE_OOM: NOPAGE_SIGBUS;
+	error = shmem_getpage(inode, fdata->pgoff, &page,
+						SGP_FAULT, &fdata->type);
+	if (error) {
+		fdata->type = ((error == -ENOMEM)?VM_FAULT_OOM:VM_FAULT_SIGBUS);
+		return NULL;
+	}
 
 	mark_page_accessed(page);
 	return page;
 }
 
-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_path.dentry->d_inode;
-	struct mm_struct *mm = vma->vm_mm;
-	enum sgp_type sgp = nonblock? SGP_QUICK: SGP_CACHE;
-	unsigned long size;
-
-	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	if (pgoff >= size || pgoff + (len >> PAGE_SHIFT) > size)
-		return -EINVAL;
-
-	while ((long) len > 0) {
-		struct page *page = NULL;
-		int err;
-		/*
-		 * Will need changing if PAGE_CACHE_SIZE != PAGE_SIZE
-		 */
-		err = shmem_getpage(inode, pgoff, &page, sgp, NULL);
-		if (err)
-			return err;
-		/* Page may still be null, but only if nonblock was set. */
-		if (page) {
-			mark_page_accessed(page);
-			err = install_page(mm, vma, addr, page, prot);
-			if (err) {
-				page_cache_release(page);
-				return err;
-			}
-		} else if (vma->vm_flags & VM_NONLINEAR) {
-			/* No page was found just because we can't read it in
-			 * now (being here implies nonblock != 0), but the page
-			 * may exist, so set the PTE to fault it in later. */
-    			err = install_file_pte(mm, vma, addr, pgoff, prot);
-			if (err)
-	    			return err;
-		}
-
-		len -= PAGE_SIZE;
-		addr += PAGE_SIZE;
-		pgoff++;
-	}
-	return 0;
-}
-
 #ifdef CONFIG_NUMA
 int shmem_set_policy(struct vm_area_struct *vma, struct mempolicy *new)
 {
@@ -1419,7 +1378,7 @@ static int shmem_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	file_accessed(file);
 	vma->vm_ops = &shmem_vm_ops;
-	vma->vm_flags |= VM_CAN_INVALIDATE;
+	vma->vm_flags |= VM_CAN_INVALIDATE | VM_CAN_NONLINEAR;
 	return 0;
 }
 
@@ -2465,8 +2424,7 @@ static const struct super_operations shmem_ops = {
 };
 
 static struct vm_operations_struct shmem_vm_ops = {
-	.nopage		= shmem_nopage,
-	.populate	= shmem_populate,
+	.fault		= shmem_fault,
 #ifdef CONFIG_NUMA
 	.set_policy     = shmem_set_policy,
 	.get_policy     = shmem_get_policy,
diff --git a/mm/truncate.c b/mm/truncate.c
index aed85f0b707..5cdfbc1a59f 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -82,7 +82,7 @@ EXPORT_SYMBOL(cancel_dirty_page);
 /*
  * If truncate cannot remove the fs-private metadata from the page, the page
  * becomes anonymous.  It will be left on the LRU and may even be mapped into
- * user pagetables if we're racing with filemap_nopage().
+ * user pagetables if we're racing with filemap_fault().
  *
  * We need to bale out if page->mapping is no longer equal to the original
  * mapping.  This happens a) when the VM reclaimed the page while we waited on