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>

Documentation/feature-removal-schedule.txt

@@ -135,6 +135,33 @@ Who:	Greg Kroah-Hartman <gregkh@suse.de>
 
 ---------------------------
 
+What:	filemap_nopage, filemap_populate
+When:	April 2007
+Why:	These legacy interfaces no longer have any callers in the kernel and
+	any functionality provided can be provided with filemap_fault. The
+	removal schedule is short because they are a big maintainence burden
+	and have some bugs.
+Who:	Nick Piggin <npiggin@suse.de>
+
+---------------------------
+
+What:	vm_ops.populate, install_page
+When:	April 2007
+Why:	These legacy interfaces no longer have any callers in the kernel and
+	any functionality provided can be provided with vm_ops.fault.
+Who:	Nick Piggin <npiggin@suse.de>
+
+---------------------------
+
+What:	vm_ops.nopage
+When:	February 2008, provided in-kernel callers have been converted
+Why:	This interface is replaced by vm_ops.fault, but it has been around
+	forever, is used by a lot of drivers, and doesn't cost much to
+	maintain.
+Who:	Nick Piggin <npiggin@suse.de>
+
+---------------------------
+
 What:	Interrupt only SA_* flags
 When:	September 2007
 Why:	The interrupt related SA_* flags are replaced by IRQF_* to move them

Documentation/filesystems/Locking

@@ -510,12 +510,14 @@ More details about quota locking can be found in fs/dquot.c.
 prototypes:
 	void (*open)(struct vm_area_struct*);
 	void (*close)(struct vm_area_struct*);
+	struct page *(*fault)(struct vm_area_struct*, struct fault_data *);
 	struct page *(*nopage)(struct vm_area_struct*, unsigned long, int *);
 
 locking rules:
 		BKL	mmap_sem
 open:		no	yes
 close:		no	yes
+fault:		no	yes
 nopage:		no	yes
 
 ================================================================================

fs/gfs2/ops_address.c

@@ -251,7 +251,7 @@ static int gfs2_readpage(struct file *file, struct page *page)
 		if (file) {
 			gf = file->private_data;
 			if (test_bit(GFF_EXLOCK, &gf->f_flags))
-				/* gfs2_sharewrite_nopage has grabbed the ip->i_gl already */
+				/* gfs2_sharewrite_fault has grabbed the ip->i_gl already */
 				goto skip_lock;
 		}
 		gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME|LM_FLAG_TRY_1CB, &gh);

fs/gfs2/ops_file.c

@@ -364,7 +364,7 @@ static int gfs2_mmap(struct file *file, struct vm_area_struct *vma)
 	else
 		vma->vm_ops = &gfs2_vm_ops_private;
 
-	vma->vm_flags |= VM_CAN_INVALIDATE;
+	vma->vm_flags |= VM_CAN_INVALIDATE|VM_CAN_NONLINEAR;
 
 	gfs2_glock_dq_uninit(&i_gh);
 

fs/gfs2/ops_vm.c

@@ -27,13 +27,13 @@
 #include "trans.h"
 #include "util.h"
 
-static struct page *gfs2_private_nopage(struct vm_area_struct *area,
-					unsigned long address, int *type)
+static struct page *gfs2_private_fault(struct vm_area_struct *vma,
+					struct fault_data *fdata)
 {
-	struct gfs2_inode *ip = GFS2_I(area->vm_file->f_mapping->host);
+	struct gfs2_inode *ip = GFS2_I(vma->vm_file->f_mapping->host);
 
 	set_bit(GIF_PAGED, &ip->i_flags);
-	return filemap_nopage(area, address, type);
+	return filemap_fault(vma, fdata);
 }
 
 static int alloc_page_backing(struct gfs2_inode *ip, struct page *page)
@@ -104,16 +104,14 @@ static int alloc_page_backing(struct gfs2_inode *ip, struct page *page)
 	return error;
 }
 
-static struct page *gfs2_sharewrite_nopage(struct vm_area_struct *area,
-					   unsigned long address, int *type)
+static struct page *gfs2_sharewrite_fault(struct vm_area_struct *vma,
+						struct fault_data *fdata)
 {
-	struct file *file = area->vm_file;
+	struct file *file = vma->vm_file;
 	struct gfs2_file *gf = file->private_data;
 	struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
 	struct gfs2_holder i_gh;
 	struct page *result = NULL;
-	unsigned long index = ((address - area->vm_start) >> PAGE_CACHE_SHIFT) +
-			      area->vm_pgoff;
 	int alloc_required;
 	int error;
 
@@ -124,23 +122,27 @@ static struct page *gfs2_sharewrite_nopage(struct vm_area_struct *area,
 	set_bit(GIF_PAGED, &ip->i_flags);
 	set_bit(GIF_SW_PAGED, &ip->i_flags);
 
-	error = gfs2_write_alloc_required(ip, (u64)index << PAGE_CACHE_SHIFT,
-					  PAGE_CACHE_SIZE, &alloc_required);
-	if (error)
+	error = gfs2_write_alloc_required(ip,
+					(u64)fdata->pgoff << PAGE_CACHE_SHIFT,
+					PAGE_CACHE_SIZE, &alloc_required);
+	if (error) {
+		fdata->type = VM_FAULT_OOM; /* XXX: are these right? */
 		goto out;
+	}
 
 	set_bit(GFF_EXLOCK, &gf->f_flags);
-	result = filemap_nopage(area, address, type);
+	result = filemap_fault(vma, fdata);
 	clear_bit(GFF_EXLOCK, &gf->f_flags);
-	if (!result || result == NOPAGE_OOM)
+	if (!result)
 		goto out;
 
 	if (alloc_required) {
 		error = alloc_page_backing(ip, result);
 		if (error) {
-			if (area->vm_flags & VM_CAN_INVALIDATE)
+			if (vma->vm_flags & VM_CAN_INVALIDATE)
 				unlock_page(result);
 			page_cache_release(result);
+			fdata->type = VM_FAULT_OOM;
 			result = NULL;
 			goto out;
 		}
@@ -154,10 +156,10 @@ static struct page *gfs2_sharewrite_nopage(struct vm_area_struct *area,
 }
 
 struct vm_operations_struct gfs2_vm_ops_private = {
-	.nopage = gfs2_private_nopage,
+	.fault = gfs2_private_fault,
 };
 
 struct vm_operations_struct gfs2_vm_ops_sharewrite = {
-	.nopage = gfs2_sharewrite_nopage,
+	.fault = gfs2_sharewrite_fault,
 };
 

fs/ncpfs/mmap.c

@@ -25,8 +25,8 @@
 /*
  * Fill in the supplied page for mmap
  */
-static struct page* ncp_file_mmap_nopage(struct vm_area_struct *area,
-				     unsigned long address, int *type)
+static struct page* ncp_file_mmap_fault(struct vm_area_struct *area,
+						struct fault_data *fdata)
 {
 	struct file *file = area->vm_file;
 	struct dentry *dentry = file->f_path.dentry;
@@ -40,15 +40,17 @@ static struct page* ncp_file_mmap_nopage(struct vm_area_struct *area,
 
 	page = alloc_page(GFP_HIGHUSER); /* ncpfs has nothing against high pages
 	           as long as recvmsg and memset works on it */
-	if (!page)
-		return page;
+	if (!page) {
+		fdata->type = VM_FAULT_OOM;
+		return NULL;
+	}
 	pg_addr = kmap(page);
-	address &= PAGE_MASK;
-	pos = address - area->vm_start + (area->vm_pgoff << PAGE_SHIFT);
+	pos = fdata->pgoff << PAGE_SHIFT;
 
 	count = PAGE_SIZE;
-	if (address + PAGE_SIZE > area->vm_end) {
-		count = area->vm_end - address;
+	if (fdata->address + PAGE_SIZE > area->vm_end) {
+		WARN_ON(1); /* shouldn't happen? */
+		count = area->vm_end - fdata->address;
 	}
 	/* what we can read in one go */
 	bufsize = NCP_SERVER(inode)->buffer_size;
@@ -91,15 +93,14 @@ static struct page* ncp_file_mmap_nopage(struct vm_area_struct *area,
 	 * fetches from the network, here the analogue of disk.
 	 * -- wli
 	 */
-	if (type)
-		*type = VM_FAULT_MAJOR;
+	fdata->type = VM_FAULT_MAJOR;
 	count_vm_event(PGMAJFAULT);
 	return page;
 }
 
 static struct vm_operations_struct ncp_file_mmap =
 {
-	.nopage	= ncp_file_mmap_nopage,
+	.fault = ncp_file_mmap_fault,
 };
 
 

fs/ocfs2/aops.c

@@ -232,7 +232,7 @@ static int ocfs2_readpage(struct file *file, struct page *page)
 	 * might now be discovering a truncate that hit on another node.
 	 * block_read_full_page->get_block freaks out if it is asked to read
 	 * beyond the end of a file, so we check here.  Callers
-	 * (generic_file_read, fault->nopage) are clever enough to check i_size
+	 * (generic_file_read, vm_ops->fault) are clever enough to check i_size
 	 * and notice that the page they just read isn't needed.
 	 *
 	 * XXX sys_readahead() seems to get that wrong?

fs/ocfs2/mmap.c

@@ -60,24 +60,23 @@ static inline int ocfs2_vm_op_unblock_sigs(sigset_t *oldset)
 	return sigprocmask(SIG_SETMASK, oldset, NULL);
 }
 
-static struct page *ocfs2_nopage(struct vm_area_struct * area,
-				 unsigned long address,
-				 int *type)
+static struct page *ocfs2_fault(struct vm_area_struct *area,
+						struct fault_data *fdata)
 {
-	struct page *page = NOPAGE_SIGBUS;
+	struct page *page = NULL;
 	sigset_t blocked, oldset;
 	int ret;
 
-	mlog_entry("(area=%p, address=%lu, type=%p)\n", area, address,
-		   type);
+	mlog_entry("(area=%p, page offset=%lu)\n", area, fdata->pgoff);
 
 	ret = ocfs2_vm_op_block_sigs(&blocked, &oldset);
 	if (ret < 0) {
+		fdata->type = VM_FAULT_SIGBUS;
 		mlog_errno(ret);
 		goto out;
 	}
 
-	page = filemap_nopage(area, address, type);
+	page = filemap_fault(area, fdata);
 
 	ret = ocfs2_vm_op_unblock_sigs(&oldset);
 	if (ret < 0)
@@ -209,7 +208,7 @@ static int ocfs2_page_mkwrite(struct vm_area_struct *vma, struct page *page)
 }
 
 static struct vm_operations_struct ocfs2_file_vm_ops = {
-	.nopage		= ocfs2_nopage,
+	.fault		= ocfs2_fault,
 	.page_mkwrite	= ocfs2_page_mkwrite,
 };
 
@@ -226,7 +225,7 @@ int ocfs2_mmap(struct file *file, struct vm_area_struct *vma)
 	ocfs2_meta_unlock(file->f_dentry->d_inode, lock_level);
 out:
 	vma->vm_ops = &ocfs2_file_vm_ops;
-	vma->vm_flags |= VM_CAN_INVALIDATE;
+	vma->vm_flags |= VM_CAN_INVALIDATE | VM_CAN_NONLINEAR;
 	return 0;
 }
 

fs/xfs/linux-2.6/xfs_file.c

@@ -213,18 +213,19 @@ xfs_file_fsync(
 
 #ifdef CONFIG_XFS_DMAPI
 STATIC struct page *
-xfs_vm_nopage(
-	struct vm_area_struct	*area,
-	unsigned long		address,
-	int			*type)
+xfs_vm_fault(
+	struct vm_area_struct	*vma,
+	struct fault_data	*fdata)
 {
-	struct inode	*inode = area->vm_file->f_path.dentry->d_inode;
+	struct inode	*inode = vma->vm_file->f_path.dentry->d_inode;
 	bhv_vnode_t	*vp = vn_from_inode(inode);
 
 	ASSERT_ALWAYS(vp->v_vfsp->vfs_flag & VFS_DMI);
-	if (XFS_SEND_MMAP(XFS_VFSTOM(vp->v_vfsp), area, 0))
+	if (XFS_SEND_MMAP(XFS_VFSTOM(vp->v_vfsp), vma, 0)) {
+		fdata->type = VM_FAULT_SIGBUS;
 		return NULL;
-	return filemap_nopage(area, address, type);
+	}
+	return filemap_fault(vma, fdata);
 }
 #endif /* CONFIG_XFS_DMAPI */
 
@@ -310,7 +311,7 @@ xfs_file_mmap(
 	struct vm_area_struct *vma)
 {
 	vma->vm_ops = &xfs_file_vm_ops;
-	vma->vm_flags |= VM_CAN_INVALIDATE;
+	vma->vm_flags |= VM_CAN_INVALIDATE | VM_CAN_NONLINEAR;
 
 #ifdef CONFIG_XFS_DMAPI
 	if (vn_from_inode(filp->f_path.dentry->d_inode)->v_vfsp->vfs_flag & VFS_DMI)
@@ -465,14 +466,12 @@ const struct file_operations xfs_dir_file_operations = {
 };
 
 static struct vm_operations_struct xfs_file_vm_ops = {
-	.nopage		= filemap_nopage,
-	.populate	= filemap_populate,
+	.fault		= filemap_fault,
 };
 
 #ifdef CONFIG_XFS_DMAPI
 static struct vm_operations_struct xfs_dmapi_file_vm_ops = {
-	.nopage		= xfs_vm_nopage,
-	.populate	= filemap_populate,
+	.fault		= xfs_vm_fault,
 #ifdef HAVE_VMOP_MPROTECT
 	.mprotect	= xfs_vm_mprotect,
 #endif

include/linux/mm.h

@@ -173,6 +173,7 @@ extern unsigned int kobjsize(const void *objp);
 					 * In this case, do_no_page must
 					 * return with the page locked.
 					 */
+#define VM_CAN_NONLINEAR 0x10000000	/* Has ->fault & does nonlinear pages */
 
 #ifndef VM_STACK_DEFAULT_FLAGS		/* arch can override this */
 #define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS
@@ -196,6 +197,25 @@ extern unsigned int kobjsize(const void *objp);
  */
 extern pgprot_t protection_map[16];
 
+#define FAULT_FLAG_WRITE	0x01
+#define FAULT_FLAG_NONLINEAR	0x02
+
+/*
+ * fault_data is filled in the the pagefault handler and passed to the
+ * vma's ->fault function. That function is responsible for filling in
+ * 'type', which is the type of fault if a page is returned, or the type
+ * of error if NULL is returned.
+ *
+ * pgoff should be used in favour of address, if possible. If pgoff is
+ * used, one may set VM_CAN_NONLINEAR in the vma->vm_flags to get
+ * nonlinear mapping support.
+ */
+struct fault_data {
+	unsigned long address;
+	pgoff_t pgoff;
+	unsigned int flags;
+	int type;
+};
 
 /*
  * These are the virtual MM functions - opening of an area, closing and
@@ -205,9 +225,15 @@ extern pgprot_t protection_map[16];
 struct vm_operations_struct {
 	void (*open)(struct vm_area_struct * area);
 	void (*close)(struct vm_area_struct * area);
-	struct page * (*nopage)(struct vm_area_struct * area, unsigned long address, int *type);
-	unsigned long (*nopfn)(struct vm_area_struct * area, unsigned long address);
-	int (*populate)(struct vm_area_struct * area, unsigned long address, unsigned long len, pgprot_t prot, unsigned long pgoff, int nonblock);
+	struct page *(*fault)(struct vm_area_struct *vma,
+			struct fault_data *fdata);
+	struct page *(*nopage)(struct vm_area_struct *area,
+			unsigned long address, int *type);
+	unsigned long (*nopfn)(struct vm_area_struct *area,
+			unsigned long address);
+	int (*populate)(struct vm_area_struct *area, unsigned long address,
+			unsigned long len, pgprot_t prot, unsigned long pgoff,
+			int nonblock);
 
 	/* notification that a previously read-only page is about to become
 	 * writable, if an error is returned it will cause a SIGBUS */
@@ -661,7 +687,6 @@ static inline int page_mapped(struct page *page)
  */
 #define NOPAGE_SIGBUS	(NULL)
 #define NOPAGE_OOM	((struct page *) (-1))
-#define NOPAGE_REFAULT	((struct page *) (-2))	/* Return to userspace, rerun */
 
 /*
  * Error return values for the *_nopfn functions
@@ -1110,9 +1135,11 @@ extern void truncate_inode_pages_range(struct address_space *,
 				       loff_t lstart, loff_t lend);
 
 /* generic vm_area_ops exported for stackable file systems */
-extern struct page *filemap_nopage(struct vm_area_struct *, unsigned long, int *);
-extern int filemap_populate(struct vm_area_struct *, unsigned long,
-		unsigned long, pgprot_t, unsigned long, int);
+extern struct page *filemap_fault(struct vm_area_struct *, struct fault_data *);
+extern struct page * __deprecated_for_modules
+filemap_nopage(struct vm_area_struct *, unsigned long, int *);
+extern int __deprecated_for_modules filemap_populate(struct vm_area_struct *,
+		unsigned long, unsigned long, pgprot_t, unsigned long, int);
 
 /* mm/page-writeback.c */
 int write_one_page(struct page *page, int wait);