From: Josef Bacik <jbacik@redhat.com>
Date: Tue, 10 Feb 2009 13:49:29 -0500
Subject: [fs] new cont helpers
Message-id: 1234291777-15344-17-git-send-email-jbacik@redhat.com
O-Subject: [PATCH 16/24] [RHEL 5.4] fs: new cont helpers
Bugzilla: 445433

This is a backport of upstream commit

89e107877b65bf6eff1d63a1302dee9a091586f5

and is in reference to bz 445433.  This patch reworks the generic block "cont"
stuff to use the new aops.  This patch also export's all of the iov_iter
functions.

Signed-off-by: Josef Bacik <jbacik@redhat.com>

diff --git a/fs/buffer.c b/fs/buffer.c
index 7b321fa..b3f5428 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -2323,14 +2323,14 @@ int block_read_full_page(struct page *page, get_block_t *get_block)
 }
 
 /* utility function for filesystems that need to do work on expanding
- * truncates.  Uses prepare/commit_write to allow the filesystem to
+ * truncates.  Uses filesystem pagecache writes to allow the filesystem to
  * deal with the hole.  
  */
-static int __generic_cont_expand(struct inode *inode, loff_t size,
-				 pgoff_t index, unsigned int offset)
+int generic_cont_expand_simple(struct inode *inode, loff_t size)
 {
 	struct address_space *mapping = inode->i_mapping;
 	struct page *page;
+	void *fsdata;
 	unsigned long limit;
 	int err;
 
@@ -2343,60 +2343,134 @@ static int __generic_cont_expand(struct inode *inode, loff_t size,
 	if (size > inode->i_sb->s_maxbytes)
 		goto out;
 
-	err = -ENOMEM;
-	page = grab_cache_page(mapping, index);
-	if (!page)
-		goto out;
-	err = mapping->a_ops->prepare_write(NULL, page, offset, offset);
-	if (err) {
-		/*
-		 * ->prepare_write() may have instantiated a few blocks
-		 * outside i_size.  Trim these off again.
-		 */
-		unlock_page(page);
-		page_cache_release(page);
-		vmtruncate(inode, inode->i_size);
+	err = pagecache_write_begin(NULL, mapping, size, 0,
+				AOP_FLAG_UNINTERRUPTIBLE|AOP_FLAG_CONT_EXPAND,
+				&page, &fsdata);
+	if (err)
 		goto out;
-	}
 
-	err = mapping->a_ops->commit_write(NULL, page, offset, offset);
+	err = pagecache_write_end(NULL, mapping, size, 0, 0, page, fsdata);
+	BUG_ON(err > 0);
 
-	unlock_page(page);
-	page_cache_release(page);
-	if (err > 0)
-		err = 0;
 out:
 	return err;
 }
 
 int generic_cont_expand(struct inode *inode, loff_t size)
 {
-	pgoff_t index;
 	unsigned int offset;
 
 	offset = (size & (PAGE_CACHE_SIZE - 1)); /* Within page */
 
 	/* ugh.  in prepare/commit_write, if from==to==start of block, we
-	** skip the prepare.  make sure we never send an offset for the start
-	** of a block
-	*/
+	 * skip the prepare.  make sure we never send an offset for the start
+	 * of a block
+	 * XXX: actually, this should be handled in those filesystems by
+	 * checking for the AOP_FLAG_CONT_EXPAND flag.
+	 */
 	if ((offset & (inode->i_sb->s_blocksize - 1)) == 0) {
 		/* caller must handle this extra byte. */
-		offset++;
+		size++;
+	}
+	return generic_cont_expand_simple(inode, size);
+}
+
+int cont_expand_zero(struct file *file, struct address_space *mapping,
+			loff_t pos, loff_t *bytes)
+{
+	struct inode *inode = mapping->host;
+	unsigned blocksize = 1 << inode->i_blkbits;
+	struct page *page;
+	void *fsdata;
+	pgoff_t index, curidx;
+	loff_t curpos;
+	unsigned zerofrom, offset, len;
+	int err = 0;
+
+	index = pos >> PAGE_CACHE_SHIFT;
+	offset = pos & ~PAGE_CACHE_MASK;
+
+	while (index > (curidx = (curpos = *bytes)>>PAGE_CACHE_SHIFT)) {
+		zerofrom = curpos & ~PAGE_CACHE_MASK;
+		if (zerofrom & (blocksize-1)) {
+			*bytes |= (blocksize-1);
+			(*bytes)++;
+		}
+		len = PAGE_CACHE_SIZE - zerofrom;
+
+		err = pagecache_write_begin(file, mapping, curpos, len,
+						AOP_FLAG_UNINTERRUPTIBLE,
+						&page, &fsdata);
+		if (err)
+			goto out;
+		zero_user(page, zerofrom, len);
+		err = pagecache_write_end(file, mapping, curpos, len, len,
+						page, fsdata);
+		if (err < 0)
+			goto out;
+		BUG_ON(err != len);
+		err = 0;
 	}
-	index = size >> PAGE_CACHE_SHIFT;
 
-	return __generic_cont_expand(inode, size, index, offset);
+	/* page covers the boundary, find the boundary offset */
+	if (index == curidx) {
+		zerofrom = curpos & ~PAGE_CACHE_MASK;
+		/* if we will expand the thing last block will be filled */
+		if (offset <= zerofrom) {
+			goto out;
+		}
+		if (zerofrom & (blocksize-1)) {
+			*bytes |= (blocksize-1);
+			(*bytes)++;
+		}
+		len = offset - zerofrom;
+
+		err = pagecache_write_begin(file, mapping, curpos, len,
+						AOP_FLAG_UNINTERRUPTIBLE,
+						&page, &fsdata);
+		if (err)
+			goto out;
+		zero_user(page, zerofrom, len);
+		err = pagecache_write_end(file, mapping, curpos, len, len,
+						page, fsdata);
+		if (err < 0)
+			goto out;
+		BUG_ON(err != len);
+		err = 0;
+	}
+out:
+	return err;
 }
 
-int generic_cont_expand_simple(struct inode *inode, loff_t size)
+/*
+ * For moronic filesystems that do not allow holes in file.
+ * We may have to extend the file.
+ */
+int cont_write_begin(struct file *file, struct address_space *mapping,
+			loff_t pos, unsigned len, unsigned flags,
+			struct page **pagep, void **fsdata,
+			get_block_t *get_block, loff_t *bytes)
 {
-	loff_t pos = size - 1;
-	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
-	unsigned int offset = (pos & (PAGE_CACHE_SIZE - 1)) + 1;
+	struct inode *inode = mapping->host;
+	unsigned blocksize = 1 << inode->i_blkbits;
+	unsigned zerofrom;
+	int err;
+
+	err = cont_expand_zero(file, mapping, pos, bytes);
+	if (err)
+		goto out;
 
-	/* prepare/commit_write can handle even if from==to==start of block. */
-	return __generic_cont_expand(inode, size, index, offset);
+	zerofrom = *bytes & ~PAGE_CACHE_MASK;
+	if (pos+len > *bytes && zerofrom & (blocksize-1)) {
+		*bytes |= (blocksize-1);
+		(*bytes)++;
+	}
+
+	*pagep = NULL;
+	err = block_write_begin(file, mapping, pos, len,
+				flags, pagep, fsdata, get_block);
+out:
+	return err;
 }
 
 /*
@@ -3386,6 +3460,7 @@ EXPORT_SYMBOL(block_sync_page);
 EXPORT_SYMBOL(block_truncate_page);
 EXPORT_SYMBOL(block_write_full_page);
 EXPORT_SYMBOL(cont_prepare_write);
+EXPORT_SYMBOL(cont_write_begin);
 EXPORT_SYMBOL(end_buffer_read_sync);
 EXPORT_SYMBOL(end_buffer_write_sync);
 EXPORT_SYMBOL(file_fsync);
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 7ffad00..2d15847 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -214,6 +214,9 @@ void page_zero_new_buffers(struct page *page, unsigned from, unsigned to);
 int block_prepare_write(struct page*, unsigned, unsigned, get_block_t*);
 int cont_prepare_write(struct page*, unsigned, unsigned, get_block_t*,
 				loff_t *);
+int cont_write_begin(struct file *, struct address_space *, loff_t,
+			unsigned, unsigned, struct page **, void **,
+			get_block_t *, loff_t *);
 int generic_cont_expand(struct inode *inode, loff_t size);
 int generic_cont_expand_simple(struct inode *inode, loff_t size);
 int block_commit_write(struct page *page, unsigned from, unsigned to);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index d3f6617..e244844 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -398,6 +398,7 @@ enum positive_aop_returns {
 };
 
 #define AOP_FLAG_UNINTERRUPTIBLE	0x0001 /* will not do a short write */
+#define AOP_FLAG_CONT_EXPAND		0x0002 /* called from cont_expand */
 
 /*
  * oh the beauties of C type declarations.
diff --git a/mm/filemap.c b/mm/filemap.c
index 124f7b7..2529e95 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1952,6 +1952,7 @@ size_t iov_iter_copy_from_user_atomic(struct page *page,
 
 	return copied;
 }
+EXPORT_SYMBOL(iov_iter_copy_from_user_atomic);
 
 /*
  * This has the same sideeffects and return value as
@@ -1978,6 +1979,7 @@ size_t iov_iter_copy_from_user(struct page *page,
 	kunmap(page);
 	return copied;
 }
+EXPORT_SYMBOL(iov_iter_copy_from_user);
 
 static void __iov_iter_advance_iov(struct iov_iter *i, size_t bytes)
 {
@@ -2009,6 +2011,7 @@ void iov_iter_advance(struct iov_iter *i, size_t bytes)
 	__iov_iter_advance_iov(i, bytes);
 	i->count -= bytes;
 }
+EXPORT_SYMBOL(iov_iter_advance);
 
 /*
  * Fault in the first iovec of the given iov_iter, to a maximum length
@@ -2025,6 +2028,7 @@ int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes)
 	bytes = min(bytes, i->iov->iov_len - i->iov_offset);
 	return fault_in_pages_readable(buf, bytes);
 }
+EXPORT_SYMBOL(iov_iter_fault_in_readable);
 
 /*
  * Return the count of just the current iov_iter segment.
@@ -2037,6 +2041,7 @@ size_t iov_iter_single_seg_count(struct iov_iter *i)
 	else
 		return min(i->count, iov->iov_len - i->iov_offset);
 }
+EXPORT_SYMBOL(iov_iter_single_seg_count);
 
 /*
  * Performs necessary checks before doing a write