1 files changed, 151 insertions, 27 deletions

diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 44db1808cdb5..f906a250da6a 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -29,6 +29,7 @@
 #include <linux/mpage.h>
 #include <linux/quotaops.h>
 #include <linux/blkdev.h>
+#include <linux/uio.h>
 
 #include <cluster/masklog.h>
 
@@ -663,6 +664,117 @@ static int ocfs2_is_overwrite(struct ocfs2_super *osb,
 	return 0;
 }
 
+static int ocfs2_direct_IO_zero_extend(struct ocfs2_super *osb,
+		struct inode *inode, loff_t offset,
+		u64 zero_len, int cluster_align)
+{
+	u32 p_cpos = 0;
+	u32 v_cpos = ocfs2_bytes_to_clusters(osb->sb, i_size_read(inode));
+	unsigned int num_clusters = 0;
+	unsigned int ext_flags = 0;
+	int ret = 0;
+
+	if (offset <= i_size_read(inode) || cluster_align)
+		return 0;
+
+	ret = ocfs2_get_clusters(inode, v_cpos, &p_cpos, &num_clusters,
+			&ext_flags);
+	if (ret < 0) {
+		mlog_errno(ret);
+		return ret;
+	}
+
+	if (p_cpos && !(ext_flags & OCFS2_EXT_UNWRITTEN)) {
+		u64 s = i_size_read(inode);
+		sector_t sector = (p_cpos << (osb->s_clustersize_bits - 9)) +
+			(do_div(s, osb->s_clustersize) >> 9);
+
+		ret = blkdev_issue_zeroout(osb->sb->s_bdev, sector,
+				zero_len >> 9, GFP_NOFS, false);
+		if (ret < 0)
+			mlog_errno(ret);
+	}
+
+	return ret;
+}
+
+static int ocfs2_direct_IO_extend_no_holes(struct ocfs2_super *osb,
+		struct inode *inode, loff_t offset)
+{
+	u64 zero_start, zero_len, total_zero_len;
+	u32 p_cpos = 0, clusters_to_add;
+	u32 v_cpos = ocfs2_bytes_to_clusters(osb->sb, i_size_read(inode));
+	unsigned int num_clusters = 0;
+	unsigned int ext_flags = 0;
+	u32 size_div, offset_div;
+	int ret = 0;
+
+	{
+		u64 o = offset;
+		u64 s = i_size_read(inode);
+
+		offset_div = do_div(o, osb->s_clustersize);
+		size_div = do_div(s, osb->s_clustersize);
+	}
+
+	if (offset <= i_size_read(inode))
+		return 0;
+
+	clusters_to_add = ocfs2_bytes_to_clusters(inode->i_sb, offset) -
+		ocfs2_bytes_to_clusters(inode->i_sb, i_size_read(inode));
+	total_zero_len = offset - i_size_read(inode);
+	if (clusters_to_add)
+		total_zero_len -= offset_div;
+
+	/* Allocate clusters to fill out holes, and this is only needed
+	 * when we add more than one clusters. Otherwise the cluster will
+	 * be allocated during direct IO */
+	if (clusters_to_add > 1) {
+		ret = ocfs2_extend_allocation(inode,
+				OCFS2_I(inode)->ip_clusters,
+				clusters_to_add - 1, 0);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+	}
+
+	while (total_zero_len) {
+		ret = ocfs2_get_clusters(inode, v_cpos, &p_cpos, &num_clusters,
+				&ext_flags);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto out;
+		}
+
+		zero_start = ocfs2_clusters_to_bytes(osb->sb, p_cpos) +
+			size_div;
+		zero_len = ocfs2_clusters_to_bytes(osb->sb, num_clusters) -
+			size_div;
+		zero_len = min(total_zero_len, zero_len);
+
+		if (p_cpos && !(ext_flags & OCFS2_EXT_UNWRITTEN)) {
+			ret = blkdev_issue_zeroout(osb->sb->s_bdev,
+					zero_start >> 9, zero_len >> 9,
+					GFP_NOFS, false);
+			if (ret < 0) {
+				mlog_errno(ret);
+				goto out;
+			}
+		}
+
+		total_zero_len -= zero_len;
+		v_cpos += ocfs2_bytes_to_clusters(osb->sb, zero_len + size_div);
+
+		/* Only at first iteration can be cluster not aligned.
+		 * So set size_div to 0 for the rest */
+		size_div = 0;
+	}
+
+out:
+	return ret;
+}
+
 static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb,
 		struct iov_iter *iter,
 		loff_t offset)
@@ -677,8 +789,8 @@ static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb,
 	struct buffer_head *di_bh = NULL;
 	size_t count = iter->count;
 	journal_t *journal = osb->journal->j_journal;
-	u32 zero_len;
-	int cluster_align;
+	u64 zero_len_head, zero_len_tail;
+	int cluster_align_head, cluster_align_tail;
 	loff_t final_size = offset + count;
 	int append_write = offset >= i_size_read(inode) ? 1 : 0;
 	unsigned int num_clusters = 0;
@@ -686,9 +798,16 @@ static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb,
 
 	{
 		u64 o = offset;
+		u64 s = i_size_read(inode);
+
+		zero_len_head = do_div(o, 1 << osb->s_clustersize_bits);
+		cluster_align_head = !zero_len_head;
 
-		zero_len = do_div(o, 1 << osb->s_clustersize_bits);
-		cluster_align = !zero_len;
+		zero_len_tail = osb->s_clustersize -
+			do_div(s, osb->s_clustersize);
+		if ((offset - i_size_read(inode)) < zero_len_tail)
+			zero_len_tail = offset - i_size_read(inode);
+		cluster_align_tail = !zero_len_tail;
 	}
 
 	/*
@@ -706,21 +825,23 @@ static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb,
 	}
 
 	if (append_write) {
-		ret = ocfs2_inode_lock(inode, &di_bh, 1);
+		ret = ocfs2_inode_lock(inode, NULL, 1);
 		if (ret < 0) {
 			mlog_errno(ret);
 			goto clean_orphan;
 		}
 
+		/* zeroing out the previously allocated cluster tail
+		 * that but not zeroed */
 		if (ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb)))
-			ret = ocfs2_zero_extend(inode, di_bh, offset);
+			ret = ocfs2_direct_IO_zero_extend(osb, inode, offset,
+					zero_len_tail, cluster_align_tail);
 		else
-			ret = ocfs2_extend_no_holes(inode, di_bh, offset,
+			ret = ocfs2_direct_IO_extend_no_holes(osb, inode,
 					offset);
 		if (ret < 0) {
 			mlog_errno(ret);
 			ocfs2_inode_unlock(inode, 1);
-			brelse(di_bh);
 			goto clean_orphan;
 		}
 
@@ -728,19 +849,15 @@ static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb,
 		if (is_overwrite < 0) {
 			mlog_errno(is_overwrite);
 			ocfs2_inode_unlock(inode, 1);
-			brelse(di_bh);
 			goto clean_orphan;
 		}
 
 		ocfs2_inode_unlock(inode, 1);
-		brelse(di_bh);
-		di_bh = NULL;
 	}
 
-	written = __blockdev_direct_IO(WRITE, iocb, inode, inode->i_sb->s_bdev,
-			iter, offset,
-			ocfs2_direct_IO_get_blocks,
-			ocfs2_dio_end_io, NULL, 0);
+	written = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter,
+				       offset, ocfs2_direct_IO_get_blocks,
+				       ocfs2_dio_end_io, NULL, 0);
 	if (unlikely(written < 0)) {
 		loff_t i_size = i_size_read(inode);
 
@@ -771,15 +888,23 @@ static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb,
 			if (ret < 0)
 				mlog_errno(ret);
 		}
-	} else if (written < 0 && append_write && !is_overwrite &&
-			!cluster_align) {
+	} else if (written > 0 && append_write && !is_overwrite &&
+			!cluster_align_head) {
+		/* zeroing out the allocated cluster head */
 		u32 p_cpos = 0;
 		u32 v_cpos = ocfs2_bytes_to_clusters(osb->sb, offset);
 
+		ret = ocfs2_inode_lock(inode, NULL, 0);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto clean_orphan;
+		}
+
 		ret = ocfs2_get_clusters(inode, v_cpos, &p_cpos,
 				&num_clusters, &ext_flags);
 		if (ret < 0) {
 			mlog_errno(ret);
+			ocfs2_inode_unlock(inode, 0);
 			goto clean_orphan;
 		}
 
@@ -787,9 +912,11 @@ static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb,
 
 		ret = blkdev_issue_zeroout(osb->sb->s_bdev,
 				p_cpos << (osb->s_clustersize_bits - 9),
-				zero_len >> 9, GFP_KERNEL, false);
+				zero_len_head >> 9, GFP_NOFS, false);
 		if (ret < 0)
 			mlog_errno(ret);
+
+		ocfs2_inode_unlock(inode, 0);
 	}
 
 clean_orphan:
@@ -818,9 +945,7 @@ out:
 	return ret;
 }
 
-static ssize_t ocfs2_direct_IO(int rw,
-			       struct kiocb *iocb,
-			       struct iov_iter *iter,
+static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 			       loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
@@ -842,12 +967,11 @@ static ssize_t ocfs2_direct_IO(int rw,
 	if (i_size_read(inode) <= offset && !full_coherency)
 		return 0;
 
-	if (rw == READ)
-		return __blockdev_direct_IO(rw, iocb, inode,
-				    inode->i_sb->s_bdev,
-				    iter, offset,
-				    ocfs2_direct_IO_get_blocks,
-				    ocfs2_dio_end_io, NULL, 0);
+	if (iov_iter_rw(iter) == READ)
+		return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,
+					    iter, offset,
+					    ocfs2_direct_IO_get_blocks,
+					    ocfs2_dio_end_io, NULL, 0);
 	else
 		return ocfs2_direct_IO_write(iocb, iter, offset);
 }