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>

1 files changed, 20 insertions, 62 deletions

diff --git a/mm/shmem.c b/mm/shmem.c
index 5808fad..6b44440 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,