2.6.19-rc1-git5: consolidation of file backed fault handlers

Index: linux-2.6/mm/filemap.c
===================================================================
@@ -120,6 +120,8 @@ void __remove_from_page_cache(struct pag
 	page->mapping = NULL;
 	mapping->nrpages--;
 	__dec_zone_page_state(page, NR_FILE_PAGES);
+
+	BUG_ON(page_mapped(page));
 }
 
 void remove_from_page_cache(struct page *page)

Index: linux-2.6/include/linux/mm.h
===================================================================
@@ -166,6 +166,11 @@ extern unsigned int kobjsize(const void 
 #define VM_NONLINEAR	0x00800000	/* Is non-linear (remap_file_pages) */
 #define VM_MAPPED_COPY	0x01000000	/* T if mapped copy of data (nommu mmap) */
 #define VM_INSERTPAGE	0x02000000	/* The vma has had "vm_insert_page()" done on it */
+#define VM_CAN_INVALIDATE	0x04000000	/* The mapping may be invalidated,
+					 * eg. truncate or invalidate_inode_*.
+					 * In this case, do_no_page must
+					 * return with the page locked.
+					 */
 
 #ifndef VM_STACK_DEFAULT_FLAGS		/* arch can override this */
 #define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS

133 lines not on this page · raw message

224 lines not on this page · raw message

Index: linux-2.6/mm/shmem.c
===================================================================
@@ -81,6 +81,7 @@ 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 */
 };
 
 static int shmem_getpage(struct inode *inode, unsigned long idx,

@@ -1209,8 +1210,10 @@ repeat:
 	}
 done:
 	if (*pagep != filepage) {
-		unlock_page(filepage);
 		*pagep = filepage;
+		if (sgp != SGP_NOPAGE)
+			unlock_page(filepage);
+
 	}
 	return 0;
 

@@ -1229,13 +1232,15 @@ struct page *shmem_nopage(struct vm_area
 	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;
 
-	error = shmem_getpage(inode, idx, &page, SGP_CACHE, type);
+	error = shmem_getpage(inode, idx, &page, SGP_NOPAGE, type);
 	if (error)
 		return (error == -ENOMEM)? NOPAGE_OOM: NOPAGE_SIGBUS;
 

@@ -1333,6 +1338,7 @@ int shmem_mmap(struct file *file, struct
 {
 	file_accessed(file);
 	vma->vm_ops = &shmem_vm_ops;
+	vma->vm_flags |= VM_CAN_INVALIDATE;
 	return 0;
 }
 

@@ -2523,5 +2529,6 @@ int shmem_zero_setup(struct vm_area_stru
 		fput(vma->vm_file);
 	vma->vm_file = file;
 	vma->vm_ops = &shmem_vm_ops;
+	vma->vm_flags |= VM_CAN_INVALIDATE;
 	return 0;
 }

Index: linux-2.6/fs/ncpfs/mmap.c
===================================================================
@@ -123,6 +123,7 @@ int ncp_mmap(struct file *file, struct v
 		return -EFBIG;
 
 	vma->vm_ops = &ncp_file_mmap;
+	vma->vm_flags |= VM_CAN_INVALIDATE;
 	file_accessed(file);
 	return 0;
 }

Index: linux-2.6/fs/ocfs2/mmap.c
===================================================================
@@ -155,6 +155,7 @@ int ocfs2_mmap(struct file *file, struct
 {
 	file_accessed(file);
 	vma->vm_ops = &ocfs2_file_vm_ops;
+	vma->vm_flags |= VM_CAN_INVALIDATE;
 	return 0;
 }
 

Index: linux-2.6/fs/xfs/linux-2.6/xfs_file.c
===================================================================
@@ -343,6 +343,7 @@ xfs_file_mmap(
 	struct vm_area_struct *vma)
 {
 	vma->vm_ops = &xfs_file_vm_ops;
+	vma->vm_flags |= VM_CAN_INVALIDATE;
 
 #ifdef CONFIG_XFS_DMAPI
 	if (vn_from_inode(filp->f_dentry->d_inode)->v_vfsp->vfs_flag & VFS_DMI)

Index: linux-2.6/ipc/shm.c
===================================================================
@@ -230,6 +230,7 @@ static int shm_mmap(struct file * file, 
 	ret = shmem_mmap(file, vma);
 	if (ret == 0) {
 		vma->vm_ops = &shm_vm_ops;
+		vma->vm_flags |= VM_CAN_INVALIDATE;
 		if (!(vma->vm_flags & VM_WRITE))
 			vma->vm_flags &= ~VM_MAYWRITE;
 		shm_inc(shm_file_ns(file), file->f_dentry->d_inode->i_ino);

Index: linux-2.6/mm/truncate.c
===================================================================
@@ -163,6 +163,11 @@ void truncate_inode_pages_range(struct a
 				unlock_page(page);
 				continue;
 			}
+			while (page_mapped(page)) {
+				unmap_mapping_range(mapping,
+				  (loff_t)page_index<<PAGE_CACHE_SHIFT,
+				  PAGE_CACHE_SIZE, 0);
+			}
 			truncate_complete_page(mapping, page);
 			unlock_page(page);
 		}

@@ -200,6 +205,11 @@ void truncate_inode_pages_range(struct a
 				break;
 			lock_page(page);
 			wait_on_page_writeback(page);
+			while (page_mapped(page)) {
+				unmap_mapping_range(mapping,
+				  (loff_t)page_index<<PAGE_CACHE_SHIFT,
+				  PAGE_CACHE_SIZE, 0);
+			}
 			if (page->index > next)
 				next = page->index;
 			next++;

Index: linux-2.6/fs/gfs2/ops_file.c
===================================================================
@@ -396,6 +396,8 @@ static int gfs2_mmap(struct file *file, 
 	else
 		vma->vm_ops = &gfs2_vm_ops_private;
 
+	vma->vm_flags |= VM_CAN_INVALIDATE;
+
 	gfs2_glock_dq_uninit(&i_gh);
 
 	return error;

Index: linux-2.6/fs/nfs/fscache.h
===================================================================
@@ -198,8 +198,10 @@ static inline void nfs_fscache_disable_f
 static inline void nfs_fscache_install_vm_ops(struct inode *inode,
 					      struct vm_area_struct *vma)
 {
-	if (NFS_I(inode)->fscache)
+	if (NFS_I(inode)->fscache) {
 		vma->vm_ops = &nfs_fs_vm_operations;
+		vma->vm_flags |= VM_CAN_INVALIDATE;
+	}
 }
 
 /*

Index: linux-2.6/fs/afs/file.c
===================================================================
@@ -82,6 +82,7 @@ static int afs_file_mmap(struct file *fi
 
 	file_accessed(file);
 	vma->vm_ops = &afs_fs_vm_operations;
+	vma->vm_flags |= VM_CAN_INVALIDATE;
 	return 0;
 }
 

index 3464b68..e5ecf42 100644
@@ -1496,6 +1496,8 @@ page_not_uptodate:
 		goto success;
 	}
 
+	/* Clear any potential old errors, and try to read.. */
+	ClearPageError(page);
 	error = mapping->a_ops->readpage(file, page);
 	if (!error) {
 		wait_on_page_locked(page);

@@ -1526,21 +1528,12 @@ page_not_uptodate:
 		unlock_page(page);
 		goto success;
 	}
-	ClearPageError(page);
-	error = mapping->a_ops->readpage(file, page);
-	if (!error) {
-		wait_on_page_locked(page);
-		if (PageUptodate(page))
-			goto success;
-	} else if (error == AOP_TRUNCATED_PAGE) {
-		page_cache_release(page);
-		goto retry_find;
-	}
 
 	/*
 	 * Things didn't work out. Return zero to tell the
 	 * mm layer so, possibly freeing the page cache page first.
 	 */
+	unlock_page(page);
 	shrink_readahead_size_eio(file, ra);
 	page_cache_release(page);
 	return NOPAGE_SIGBUS;

diff -puN mm/filemap.c~revert-generic_file_buffered_write-handle-zero-length-iovec-segments mm/filemap.c
@@ -2121,12 +2121,6 @@ generic_file_buffered_write(struct kiocb
 			break;
 		}
 
-		if (unlikely(bytes == 0)) {
-			status = 0;
-			copied = 0;
-			goto zero_length_segment;
-		}
-
 		status = a_ops->prepare_write(file, page, offset, offset+bytes);
 		if (unlikely(status)) {
 			loff_t isize = i_size_read(inode);

@@ -2156,8 +2150,7 @@ generic_file_buffered_write(struct kiocb
 			page_cache_release(page);
 			continue;
 		}
-zero_length_segment:
-		if (likely(copied >= 0)) {
+		if (likely(copied > 0)) {
 			if (!status)
 				status = copied;
 

diff -puN mm/filemap.h~revert-generic_file_buffered_write-handle-zero-length-iovec-segments mm/filemap.h
@@ -87,7 +87,7 @@ filemap_set_next_iovec(const struct iove
 	const struct iovec *iov = *iovp;
 	size_t base = *basep;
 
-	do {
+	while (bytes) {
 		int copy = min(bytes, iov->iov_len - base);
 
 		bytes -= copy;

@@ -96,7 +96,7 @@ filemap_set_next_iovec(const struct iove
 			iov++;
 			base = 0;
 		}
-	} while (bytes);
+	}
 	*iovp = iov;
 	*basep = base;
 }

diff -puN mm/filemap.c~revert-generic_file_buffered_write-deadlock-on-vectored-write mm/filemap.c
@@ -2091,21 +2091,14 @@ generic_file_buffered_write(struct kiocb
 	do {
 		unsigned long index;
 		unsigned long offset;
+		unsigned long maxlen;
 		size_t copied;
 
 		offset = (pos & (PAGE_CACHE_SIZE -1)); /* Within page */
 		index = pos >> PAGE_CACHE_SHIFT;
 		bytes = PAGE_CACHE_SIZE - offset;
-
-		/* Limit the size of the copy to the caller's write size */
-		bytes = min(bytes, count);
-
-		/*
-		 * Limit the size of the copy to that of the current segment,
-		 * because fault_in_pages_readable() doesn't know how to walk
-		 * segments.
-		 */
-		bytes = min(bytes, cur_iov->iov_len - iov_base);
+		if (bytes > count)
+			bytes = count;
 
 		/*
 		 * Bring in the user page that we will copy from _first_.

@@ -2113,7 +2106,10 @@ generic_file_buffered_write(struct kiocb
 		 * same page as we're writing to, without it being marked
 		 * up-to-date.
 		 */
-		fault_in_pages_readable(buf, bytes);
+		maxlen = cur_iov->iov_len - iov_base;
+		if (maxlen > bytes)
+			maxlen = bytes;
+		fault_in_pages_readable(buf, maxlen);
 
 		page = __grab_cache_page(mapping,index,&cached_page,&lru_pvec);
 		if (!page) {

diff -puN mm/filemap.c~generic_file_buffered_write-cleanup mm/filemap.c
@@ -2064,16 +2064,15 @@ generic_file_buffered_write(struct kiocb
 		size_t count, ssize_t written)
 {
 	struct file *file = iocb->ki_filp;
-	struct address_space * mapping = file->f_mapping;
+	struct address_space *mapping = file->f_mapping;
 	const struct address_space_operations *a_ops = mapping->a_ops;
 	struct inode 	*inode = mapping->host;
 	long		status = 0;
 	struct page	*page;
 	struct page	*cached_page = NULL;
-	size_t		bytes;
 	struct pagevec	lru_pvec;
 	const struct iovec *cur_iov = iov; /* current iovec */
-	size_t		iov_base = 0;	   /* offset in the current iovec */
+	size_t		iov_offset = 0;	   /* offset in the current iovec */
 	char __user	*buf;
 
 	pagevec_init(&lru_pvec, 0);

@@ -2084,31 +2083,33 @@ generic_file_buffered_write(struct kiocb
 	if (likely(nr_segs == 1))
 		buf = iov->iov_base + written;
 	else {
-		filemap_set_next_iovec(&cur_iov, &iov_base, written);
-		buf = cur_iov->iov_base + iov_base;
+		filemap_set_next_iovec(&cur_iov, &iov_offset, written);
+		buf = cur_iov->iov_base + iov_offset;
 	}
 
 	do {
-		unsigned long index;
-		unsigned long offset;
-		unsigned long maxlen;
-		size_t copied;
+		pgoff_t index;		/* Pagecache index for current page */
+		unsigned long offset;	/* Offset into pagecache page */
+		unsigned long maxlen;	/* Bytes remaining in current iovec */
+		size_t bytes;		/* Bytes to write to page */
+		size_t copied;		/* Bytes copied from user */
 
-		offset = (pos & (PAGE_CACHE_SIZE -1)); /* Within page */
+		offset = (pos & (PAGE_CACHE_SIZE - 1));
 		index = pos >> PAGE_CACHE_SHIFT;
 		bytes = PAGE_CACHE_SIZE - offset;
 		if (bytes > count)
 			bytes = count;
 
+		maxlen = cur_iov->iov_len - iov_offset;
+		if (maxlen > bytes)
+			maxlen = bytes;
+
 		/*
 		 * Bring in the user page that we will copy from _first_.
 		 * Otherwise there's a nasty deadlock on copying from the
 		 * same page as we're writing to, without it being marked
 		 * up-to-date.
 		 */
-		maxlen = cur_iov->iov_len - iov_base;
-		if (maxlen > bytes)
-			maxlen = bytes;
 		fault_in_pages_readable(buf, maxlen);
 
 		page = __grab_cache_page(mapping,index,&cached_page,&lru_pvec);

@@ -2139,7 +2140,7 @@ generic_file_buffered_write(struct kiocb
 							buf, bytes);
 		else
 			copied = filemap_copy_from_user_iovec(page, offset,
-						cur_iov, iov_base, bytes);
+						cur_iov, iov_offset, bytes);
 		flush_dcache_page(page);
 		status = a_ops->commit_write(file, page, offset, offset+bytes);
 		if (status == AOP_TRUNCATED_PAGE) {

@@ -2157,12 +2158,12 @@ generic_file_buffered_write(struct kiocb
 				buf += status;
 				if (unlikely(nr_segs > 1)) {
 					filemap_set_next_iovec(&cur_iov,
-							&iov_base, status);
+							&iov_offset, status);
 					if (count)
 						buf = cur_iov->iov_base +
-							iov_base;
+							iov_offset;
 				} else {
-					iov_base += status;
+					iov_offset += status;
 				}
 			}
 		}

diff -puN mm/filemap.c~generic_file_buffered_write-fix-page-prefaulting mm/filemap.c
@@ -2110,7 +2110,7 @@ generic_file_buffered_write(struct kiocb
 		 * same page as we're writing to, without it being marked
 		 * up-to-date.
 		 */
-		fault_in_pages_readable(buf, maxlen);
+		fault_in_pages_readable(buf, bytes);
 
 		page = __grab_cache_page(mapping,index,&cached_page,&lru_pvec);
 		if (!page) {

diff -puN mm/filemap.c~generic_file_buffered_write-max_len-cleanup mm/filemap.c
@@ -2090,7 +2090,6 @@ generic_file_buffered_write(struct kiocb
 	do {
 		pgoff_t index;		/* Pagecache index for current page */
 		unsigned long offset;	/* Offset into pagecache page */
-		unsigned long maxlen;	/* Bytes remaining in current iovec */
 		size_t bytes;		/* Bytes to write to page */
 		size_t copied;		/* Bytes copied from user */
 

@@ -2100,9 +2099,7 @@ generic_file_buffered_write(struct kiocb
 		if (bytes > count)
 			bytes = count;
 
-		maxlen = cur_iov->iov_len - iov_offset;
-		if (maxlen > bytes)
-			maxlen = bytes;
+		bytes = min(cur_iov->iov_len - iov_offset, bytes);
 
 		/*
 		 * Bring in the user page that we will copy from _first_.

diff -puN mm/filemap.c~fix-pagecache-write-deadlocks mm/filemap.c
@@ -2133,11 +2133,12 @@ generic_file_buffered_write(struct kiocb
 			break;
 		}
 		if (likely(nr_segs == 1))
-			copied = filemap_copy_from_user(page, offset,
+			copied = filemap_copy_from_user_atomic(page, offset,
 							buf, bytes);
 		else
-			copied = filemap_copy_from_user_iovec(page, offset,
-						cur_iov, iov_offset, bytes);
+			copied = filemap_copy_from_user_iovec_atomic(page,
+						offset, cur_iov, iov_offset,
+						bytes);
 		flush_dcache_page(page);
 		status = a_ops->commit_write(file, page, offset, offset+bytes);
 		if (status == AOP_TRUNCATED_PAGE) {

96 lines not on this page · raw message

Index: linux-2.6/include/linux/mm.h
===================================================================
@@ -166,11 +166,12 @@ extern unsigned int kobjsize(const void 
 #define VM_NONLINEAR	0x00800000	/* Is non-linear (remap_file_pages) */
 #define VM_MAPPED_COPY	0x01000000	/* T if mapped copy of data (nommu mmap) */
 #define VM_INSERTPAGE	0x02000000	/* The vma has had "vm_insert_page()" done on it */
-#define VM_CAN_INVALIDATE	0x04000000	/* The mapping may be invalidated,
+#define VM_CAN_INVALIDATE 0x04000000	/* The mapping may be invalidated,
 					 * eg. truncate or invalidate_inode_*.
 					 * In this case, do_no_page must
 					 * return with the page locked.
 					 */
+#define VM_CAN_NONLINEAR 0x08000000	/* Has ->fault & does nonlinear pages */
 
 #ifndef VM_STACK_DEFAULT_FLAGS		/* arch can override this */
 #define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS

@@ -194,6 +195,23 @@ extern unsigned int kobjsize(const void 
  */
 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.
+ */
+struct fault_data {
+	struct vm_area_struct *vma;
+	unsigned long address;
+	pgoff_t pgoff;
+	unsigned int flags;
+
+	int type;
+};
 
 /*
  * These are the virtual MM functions - opening of an area, closing and

@@ -203,6 +221,7 @@ 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 * (*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);

@@ -614,7 +633,6 @@ static inline int page_mapped(struct pag
  */
 #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

@@ -643,14 +661,13 @@ static inline int page_mapped(struct pag
 extern void show_free_areas(void);
 
 #ifdef CONFIG_SHMEM
-struct page *shmem_nopage(struct vm_area_struct *vma,
-			unsigned long address, int *type);
+struct page *shmem_fault(struct vm_area_struct *vma, struct fault_data *fdata);
 int shmem_set_policy(struct vm_area_struct *vma, struct mempolicy *new);
 struct mempolicy *shmem_get_policy(struct vm_area_struct *vma,
 					unsigned long addr);
 int shmem_lock(struct file *file, int lock, struct user_struct *user);
 #else
-#define shmem_nopage filemap_nopage
+#define shmem_fault filemap_fault
 
 static inline int shmem_lock(struct file *file, int lock,
 			     struct user_struct *user)

@@ -1043,7 +1060,8 @@ extern void truncate_inode_pages_range(s
 				       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 struct page * __deprecated filemap_fault(struct vm_area_struct *, struct fault_data *);
+extern struct page * __deprecated 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);
 

220 lines not on this page · raw message

199 lines not on this page · raw message

120 lines not on this page · raw message

Index: linux-2.6/fs/gfs2/ops_file.c
===================================================================
@@ -396,7 +396,7 @@ static int gfs2_mmap(struct file *file, 
 	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);
 

Index: linux-2.6/fs/gfs2/ops_vm.c
===================================================================
@@ -42,17 +42,17 @@ static void pfault_be_greedy(struct gfs2
 		iput(&ip->i_inode);
 }
 
-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);
 	struct page *result;
 
 	set_bit(GIF_PAGED, &ip->i_flags);
 
-	result = filemap_nopage(area, address, type);
+	result = filemap_fault(vma, fdata);
 
-	if (result && result != NOPAGE_OOM)
+	if (result)
 		pfault_be_greedy(ip);
 
 	return result;

@@ -126,16 +126,14 @@ out:
 	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;
 

@@ -146,21 +144,25 @@ static struct page *gfs2_sharewrite_nopa
 	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) {
 			page_cache_release(result);
+			fdata->type = VM_FAULT_OOM;
 			result = NULL;
 			goto out;
 		}

@@ -175,10 +177,10 @@ out:
 }
 
 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,
 };
 

Index: linux-2.6/fs/ocfs2/mmap.c
===================================================================
@@ -59,24 +59,23 @@ static inline int ocfs2_vm_op_unblock_si
 	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 *vma,
+					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, address=%lu)\n", vma, fdata->address);
 
 	ret = ocfs2_vm_op_block_sigs(&blocked, &oldset);
 	if (ret < 0) {
 		mlog_errno(ret);
+		fdata->type = VM_FAULT_SIGBUS;
 		goto out;
 	}
 
-	page = filemap_nopage(area, address, type);
+	page = filemap_fault(vma, fdata);
 
 	ret = ocfs2_vm_op_unblock_sigs(&oldset);
 	if (ret < 0)

@@ -147,7 +146,7 @@ out:
 }
 
 static struct vm_operations_struct ocfs2_file_vm_ops = {
-	.nopage		= ocfs2_nopage,
+	.fault		= ocfs2_fault,
 	.page_mkwrite	= ocfs2_page_mkwrite,
 };
 

@@ -155,7 +154,7 @@ int ocfs2_mmap(struct file *file, struct
 {
 	file_accessed(file);
 	vma->vm_ops = &ocfs2_file_vm_ops;
-	vma->vm_flags |= VM_CAN_INVALIDATE;
+	vma->vm_flags |= VM_CAN_INVALIDATE | VM_CAN_NONLINEAR;
 	return 0;
 }
 

Index: linux-2.6/fs/xfs/linux-2.6/xfs_file.c
===================================================================
@@ -246,18 +246,19 @@ 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_dentry->d_inode;
+	struct inode	*inode = vma->vm_file->f_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), area, 0)) {
+		fdata->type = VM_FAULT_SIGBUS;
 		return NULL;
-	return filemap_nopage(area, address, type);
+	}
+	return filemap_fault(vma, fdata);
 }
 #endif /* CONFIG_XFS_DMAPI */
 

@@ -343,7 +344,7 @@ 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_dentry->d_inode)->v_vfsp->vfs_flag & VFS_DMI)

@@ -502,14 +503,12 @@ const struct file_operations xfs_dir_fil
 };
 
 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

Index: linux-2.6/mm/mmap.c
===================================================================
@@ -1148,12 +1148,8 @@ 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:

Index: linux-2.6/ipc/shm.c
===================================================================
@@ -260,7 +260,7 @@ static struct file_operations shm_file_o
 static struct vm_operations_struct shm_vm_ops = {
 	.open	= shm_open,	/* callback for a new vm-area open */
 	.close	= shm_close,	/* callback for when the vm-area is released */
-	.nopage	= shmem_nopage,
+	.fault	= shmem_fault,
 #if defined(CONFIG_NUMA) && defined(CONFIG_SHMEM)
 	.set_policy = shmem_set_policy,
 	.get_policy = shmem_get_policy,

92 lines not on this page · raw message

Index: linux-2.6/mm/nommu.c
===================================================================
@@ -1299,8 +1299,7 @@ int in_gate_area_no_task(unsigned long a
 	return 0;
 }
 
-struct page *filemap_nopage(struct vm_area_struct *area,
-			unsigned long address, int *type)
+struct page *filemap_fault(struct fault_data *fdata)
 {
 	BUG();
 	return NULL;

129 lines not on this page · raw message

Index: linux-2.6/mm/truncate.c
===================================================================
@@ -53,7 +53,7 @@ static inline void truncate_partial_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

Index: linux-2.6/fs/afs/file.c
===================================================================
@@ -63,8 +63,7 @@ const struct address_space_operations af
 };
 
 static struct vm_operations_struct afs_fs_vm_operations = {
-	.nopage		= filemap_nopage,
-	.populate	= filemap_populate,
+	.fault		= filemap_fault,
 #ifdef CONFIG_AFS_FSCACHE
 	.page_mkwrite	= afs_file_page_mkwrite,
 #endif

@@ -82,7 +81,7 @@ static int afs_file_mmap(struct file *fi
 
 	file_accessed(file);
 	vma->vm_ops = &afs_fs_vm_operations;
-	vma->vm_flags |= VM_CAN_INVALIDATE;
+	vma->vm_flags |= VM_CAN_INVALIDATE | VM_CAN_NONLINEAR;
 	return 0;
 }
 

Index: linux-2.6/fs/gfs2/ops_address.c
===================================================================
@@ -227,7 +227,7 @@ static int gfs2_readpage(struct file *fi
 		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|GL_AOP, &gh);

Index: linux-2.6/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_dentry;

@@ -40,15 +40,17 @@ static struct page* ncp_file_mmap_nopage
 
 	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
 	 * 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,
 };
 
 

Index: linux-2.6/fs/nfs/fscache.c
===================================================================
@@ -293,8 +293,7 @@ static int nfs_file_page_mkwrite(struct 
 }
 
 struct vm_operations_struct nfs_fs_vm_operations = {
-	.nopage		= filemap_nopage,
-	.populate	= filemap_populate,
+	.fault		= filemap_fault,
 	.page_mkwrite	= nfs_file_page_mkwrite,
 };
 

Index: linux-2.6/fs/nfs/fscache.h
===================================================================
@@ -200,7 +200,7 @@ static inline void nfs_fscache_install_v
 {
 	if (NFS_I(inode)->fscache) {
 		vma->vm_ops = &nfs_fs_vm_operations;
-		vma->vm_flags |= VM_CAN_INVALIDATE;
+		vma->vm_flags |= VM_CAN_INVALIDATE | VM_CAN_NONLINEAR;
 	}
 }
 

Index: linux-2.6/fs/ocfs2/aops.c
===================================================================
@@ -215,7 +215,7 @@ static int ocfs2_readpage(struct file *f
 	 * 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?

Index: linux-2.6/include/linux/mm.h
===================================================================
@@ -1121,6 +1121,7 @@ unsigned long vmalloc_to_pfn(void *addr)
 int remap_pfn_range(struct vm_area_struct *, unsigned long addr,
 			unsigned long pfn, unsigned long size, pgprot_t);
 int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *);
+int vm_insert_pfn(struct vm_area_struct *, unsigned long addr, unsigned long pfn);
 
 struct page *follow_page(struct vm_area_struct *, unsigned long address,
 			unsigned int foll_flags);

50 lines not on this page · raw message

Index: linux-2.6/drivers/char/mspec.c
===================================================================
@@ -178,24 +178,25 @@ mspec_close(struct vm_area_struct *vma)
 
 
 /*
- * mspec_nopfn
+ * mspec_fault
  *
  * Creates a mspec page and maps it to user space.
  */
-static unsigned long
-mspec_nopfn(struct vm_area_struct *vma, unsigned long address)
+static struct page *
+mspec_fault(struct fault_data *fdata)
 {
 	unsigned long paddr, maddr;
 	unsigned long pfn;
-	int index;
-	struct vma_data *vdata = vma->vm_private_data;
+	int index = fdata->pgoff;
+	struct vma_data *vdata = fdata->vma->vm_private_data;
 
-	index = (address - vma->vm_start) >> PAGE_SHIFT;
 	maddr = (volatile unsigned long) vdata->maddr[index];
 	if (maddr == 0) {
 		maddr = uncached_alloc_page(numa_node_id());
-		if (maddr == 0)
-			return NOPFN_OOM;
+		if (maddr == 0) {
+			fdata->type = VM_FAULT_OOM;
+			return NULL;
+		}
 
 		spin_lock(&vdata->lock);
 		if (vdata->maddr[index] == 0) {

@@ -215,13 +216,21 @@ mspec_nopfn(struct vm_area_struct *vma, 
 
 	pfn = paddr >> PAGE_SHIFT;
 
-	return pfn;
+	fdata->type = VM_FAULT_MINOR;
+	/*
+	 * vm_insert_pfn can fail with -EBUSY, but in that case it will
+	 * be because another thread has installed the pte first, so it
+	 * is no problem.
+	 */
+	vm_insert_pfn(fdata->vma, fdata->address, pfn);
+
+	return NULL;
 }
 
 static struct vm_operations_struct mspec_vm_ops = {
 	.open = mspec_open,
 	.close = mspec_close,
-	.nopfn = mspec_nopfn
+	.fault = mspec_fault,
 };
 
 /*

Index: linux-2.6/include/linux/mm.h
===================================================================
@@ -223,7 +223,6 @@ struct vm_operations_struct {
 	void (*close)(struct vm_area_struct * area);
 	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

@@ -635,12 +634,6 @@ static inline int page_mapped(struct pag
 #define NOPAGE_OOM	((struct page *) (-1))
 
 /*
- * Error return values for the *_nopfn functions
- */
-#define NOPFN_SIGBUS	((unsigned long) -1)
-#define NOPFN_OOM	((unsigned long) -2)
-
-/*
  * Different kinds of faults, as returned by handle_mm_fault().
  * Used to decide whether a process gets delivered SIGBUS or
  * just gets major/minor fault counters bumped up.

74 lines not on this page · raw message

Index: linux-2.6/include/linux/mm.h
===================================================================
@@ -223,8 +223,6 @@ struct vm_operations_struct {
 	void (*close)(struct vm_area_struct * area);
 	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);
-	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 */
 	int (*page_mkwrite)(struct vm_area_struct *vma, struct page *page);

@@ -742,8 +740,6 @@ static inline void unmap_shared_mapping_
 
 extern int vmtruncate(struct inode * inode, loff_t offset);
 extern int vmtruncate_range(struct inode * inode, loff_t offset, loff_t end);
-extern int install_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, struct page *page, pgprot_t prot);
-extern int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long pgoff, pgprot_t prot);
 
 #ifdef CONFIG_MMU
 extern int __handle_mm_fault(struct mm_struct *mm,struct vm_area_struct *vma,

@@ -1053,10 +1049,7 @@ extern void truncate_inode_pages_range(s
 				       loff_t lstart, loff_t lend);
 
 /* generic vm_area_ops exported for stackable file systems */
-extern struct page * __deprecated filemap_fault(struct vm_area_struct *, struct fault_data *);
-extern struct page * __deprecated 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 *);
 
 /* mm/page-writeback.c */
 int write_one_page(struct page *page, int wait);

201 lines not on this page · raw message

93 lines not on this page · raw message

Index: linux-2.6/mm/memory.c
===================================================================
@@ -2327,18 +2327,10 @@ static int do_linear_fault(struct mm_str
 			- 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);
+	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);
-}
 
 /*
  * Fault of a previously existing named mapping. Repopulate the pte

@@ -2349,17 +2341,19 @@ static int do_nonlinear_fault(struct mm_
  * 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_file_page(struct mm_struct *mm, struct vm_area_struct *vma,
+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, pte_t orig_pte)
 {
+	unsigned int flags = FAULT_FLAG_NONLINEAR |
+				(write_access ? FAULT_FLAG_WRITE : 0);
 	pgoff_t pgoff;
-	int err;
 
 	if (!pte_unmap_same(mm, pmd, page_table, orig_pte))
 		return VM_FAULT_MINOR;
 
-	if (unlikely(!(vma->vm_flags & VM_NONLINEAR))) {
+	if (unlikely(!(vma->vm_flags & VM_NONLINEAR) ||
+			!(vma->vm_flags & VM_CAN_NONLINEAR))) {
 		/*
 		 * Page table corrupted: show pte and kill process.
 		 */

@@ -2369,18 +2363,8 @@ static int do_file_page(struct mm_struct
 
 	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)
-		return VM_FAULT_OOM;
-	if (err)
-		return VM_FAULT_SIGBUS;
-	return VM_FAULT_MAJOR;
+	return __do_fault(mm, vma, address, page_table, pmd, pgoff,
+							flags, orig_pte);
 }
 
 /*

@@ -2416,7 +2400,7 @@ static inline int handle_pte_fault(struc
 						 pte, pmd, write_access);
 		}
 		if (pte_file(entry))
-			return do_file_page(mm, vma, address,
+			return do_nonlinear_fault(mm, vma, address,
 					pte, pmd, write_access, entry);
 		return do_swap_page(mm, vma, address,
 					pte, pmd, write_access, entry);