ocfs2: teach ocfs2_file_aio_write() about sparse files

Unfortunately, ocfs2 can no longer make use of generic_file_aio_write_nlock()
because allocating writes will require zeroing of pages adjacent to the I/O
for cluster sizes greater than page size.

Implement a custom file write here, which can order page locks for zeroing.
This also has the advantage that cluster locks can easily be ordered outside
of the page locks.
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>

fs/ocfs2/aops.h

@@ -30,6 +30,44 @@ handle_t *ocfs2_start_walk_page_trans(struct inode *inode,
 							 unsigned from,
 							 unsigned to);
 
+struct ocfs2_write_ctxt;
+typedef int (ocfs2_page_writer)(struct inode *, struct ocfs2_write_ctxt *,
+				u64 *, unsigned int *, unsigned int *);
+
+ssize_t ocfs2_buffered_write_cluster(struct file *file, loff_t pos,
+				     size_t count, ocfs2_page_writer *actor,
+				     void *priv);
+
+struct ocfs2_write_ctxt {
+	size_t				w_count;
+	loff_t				w_pos;
+	u32				w_cpos;
+	unsigned int			w_finished_copy;
+
+	/* This is true if page_size > cluster_size */
+	unsigned int			w_large_pages;
+
+	/* Filler callback and private data */
+	ocfs2_page_writer		*w_write_data_page;
+	void				*w_private;
+
+	/* Only valid for the filler callback */
+	struct page			*w_this_page;
+	unsigned int			w_this_page_new;
+};
+
+struct ocfs2_buffered_write_priv {
+	char				*b_src_buf;
+	const struct iovec		*b_cur_iov; /* Current iovec */
+	size_t				b_cur_off; /* Offset in the
+						    * current iovec */
+};
+int ocfs2_map_and_write_user_data(struct inode *inode,
+				  struct ocfs2_write_ctxt *wc,
+				  u64 *p_blkno,
+				  unsigned int *ret_from,
+				  unsigned int *ret_to);
+
 /* all ocfs2_dio_end_io()'s fault */
 #define ocfs2_iocb_is_rw_locked(iocb) \
 	test_bit(0, (unsigned long *)&iocb->private)

fs/ocfs2/extent_map.c

@@ -67,8 +67,8 @@ static int ocfs2_search_extent_list(struct ocfs2_extent_list *el,
 	return ret;
 }
 
-static int ocfs2_get_clusters(struct inode *inode, u32 v_cluster,
-			      u32 *p_cluster, u32 *num_clusters)
+int ocfs2_get_clusters(struct inode *inode, u32 v_cluster,
+		       u32 *p_cluster, u32 *num_clusters)
 {
 	int ret, i;
 	struct buffer_head *di_bh = NULL;

fs/ocfs2/extent_map.h

@@ -25,6 +25,8 @@
 #ifndef _EXTENT_MAP_H
 #define _EXTENT_MAP_H
 
+int ocfs2_get_clusters(struct inode *inode, u32 v_cluster, u32 *p_cluster,
+		       u32 *num_clusters);
 int ocfs2_extent_map_get_blocks(struct inode *inode, u64 v_blkno, u64 *p_blkno,
 				int *ret_count);
 

fs/ocfs2/file.h

@@ -46,6 +46,10 @@ int ocfs2_do_extend_allocation(struct ocfs2_super *osb,
 			       struct ocfs2_alloc_context *data_ac,
 			       struct ocfs2_alloc_context *meta_ac,
 			       enum ocfs2_alloc_restarted *reason);
+int ocfs2_lock_allocators(struct inode *inode, struct ocfs2_dinode *di,
+			  u32 clusters_to_add,
+			  struct ocfs2_alloc_context **data_ac,
+			  struct ocfs2_alloc_context **meta_ac);
 int ocfs2_setattr(struct dentry *dentry, struct iattr *attr);
 int ocfs2_getattr(struct vfsmount *mnt, struct dentry *dentry,
 		  struct kstat *stat);

fs/ocfs2/ocfs2.h

@@ -463,6 +463,38 @@ static inline unsigned long ocfs2_align_bytes_to_sectors(u64 bytes)
 	return (unsigned long)((bytes + 511) >> 9);
 }
 
+static inline unsigned int ocfs2_page_index_to_clusters(struct super_block *sb,
+							unsigned long pg_index)
+{
+	u32 clusters = pg_index;
+	unsigned int cbits = OCFS2_SB(sb)->s_clustersize_bits;
+
+	if (unlikely(PAGE_CACHE_SHIFT > cbits))
+		clusters = pg_index << (PAGE_CACHE_SHIFT - cbits);
+	else if (PAGE_CACHE_SHIFT < cbits)
+		clusters = pg_index >> (cbits - PAGE_CACHE_SHIFT);
+
+	return clusters;
+}
+
+/*
+ * Find the 1st page index which covers the given clusters.
+ */
+static inline unsigned long ocfs2_align_clusters_to_page_index(struct super_block *sb,
+							u32 clusters)
+{
+	unsigned int cbits = OCFS2_SB(sb)->s_clustersize_bits;
+	unsigned long index = clusters;
+
+	if (PAGE_CACHE_SHIFT > cbits) {
+		index = clusters >> (PAGE_CACHE_SHIFT - cbits);
+	} else if (PAGE_CACHE_SHIFT < cbits) {
+		index = clusters << (cbits - PAGE_CACHE_SHIFT);
+	}
+
+	return index;
+}
+
 #define ocfs2_set_bit ext2_set_bit
 #define ocfs2_clear_bit ext2_clear_bit
 #define ocfs2_test_bit ext2_test_bit