1 files changed, 97 insertions, 38 deletions

diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index db2cfb067d0b..0479c32c5eb1 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -632,38 +632,46 @@ xfs_map_at_offset(
 }
 
 /*
- * Test if a given page is suitable for writing as part of an unwritten
- * or delayed allocate extent.
+ * Test if a given page contains at least one buffer of a given @type.
+ * If @check_all_buffers is true, then we walk all the buffers in the page to
+ * try to find one of the type passed in. If it is not set, then the caller only
+ * needs to check the first buffer on the page for a match.
  */
-STATIC int
+STATIC bool
 xfs_check_page_type(
 	struct page		*page,
-	unsigned int		type)
+	unsigned int		type,
+	bool			check_all_buffers)
 {
-	if (PageWriteback(page))
-		return 0;
+	struct buffer_head	*bh;
+	struct buffer_head	*head;
 
-	if (page->mapping && page_has_buffers(page)) {
-		struct buffer_head	*bh, *head;
-		int			acceptable = 0;
+	if (PageWriteback(page))
+		return false;
+	if (!page->mapping)
+		return false;
+	if (!page_has_buffers(page))
+		return false;
 
-		bh = head = page_buffers(page);
-		do {
-			if (buffer_unwritten(bh))
-				acceptable += (type == XFS_IO_UNWRITTEN);
-			else if (buffer_delay(bh))
-				acceptable += (type == XFS_IO_DELALLOC);
-			else if (buffer_dirty(bh) && buffer_mapped(bh))
-				acceptable += (type == XFS_IO_OVERWRITE);
-			else
-				break;
-		} while ((bh = bh->b_this_page) != head);
+	bh = head = page_buffers(page);
+	do {
+		if (buffer_unwritten(bh)) {
+			if (type == XFS_IO_UNWRITTEN)
+				return true;
+		} else if (buffer_delay(bh)) {
+			if (type == XFS_IO_DELALLOC)
+				return true;
+		} else if (buffer_dirty(bh) && buffer_mapped(bh)) {
+			if (type == XFS_IO_OVERWRITE)
+				return true;
+		}
 
-		if (acceptable)
-			return 1;
-	}
+		/* If we are only checking the first buffer, we are done now. */
+		if (!check_all_buffers)
+			break;
+	} while ((bh = bh->b_this_page) != head);
 
-	return 0;
+	return false;
 }
 
 /*
@@ -697,7 +705,7 @@ xfs_convert_page(
 		goto fail_unlock_page;
 	if (page->mapping != inode->i_mapping)
 		goto fail_unlock_page;
-	if (!xfs_check_page_type(page, (*ioendp)->io_type))
+	if (!xfs_check_page_type(page, (*ioendp)->io_type, false))
 		goto fail_unlock_page;
 
 	/*
@@ -742,6 +750,15 @@ xfs_convert_page(
 	p_offset = p_offset ? roundup(p_offset, len) : PAGE_CACHE_SIZE;
 	page_dirty = p_offset / len;
 
+	/*
+	 * The moment we find a buffer that doesn't match our current type
+	 * specification or can't be written, abort the loop and start
+	 * writeback. As per the above xfs_imap_valid() check, only
+	 * xfs_vm_writepage() can handle partial page writeback fully - we are
+	 * limited here to the buffers that are contiguous with the current
+	 * ioend, and hence a buffer we can't write breaks that contiguity and
+	 * we have to defer the rest of the IO to xfs_vm_writepage().
+	 */
 	bh = head = page_buffers(page);
 	do {
 		if (offset >= end_offset)
@@ -750,7 +767,7 @@ xfs_convert_page(
 			uptodate = 0;
 		if (!(PageUptodate(page) || buffer_uptodate(bh))) {
 			done = 1;
-			continue;
+			break;
 		}
 
 		if (buffer_unwritten(bh) || buffer_delay(bh) ||
@@ -762,10 +779,11 @@ xfs_convert_page(
 			else
 				type = XFS_IO_OVERWRITE;
 
-			if (!xfs_imap_valid(inode, imap, offset)) {
-				done = 1;
-				continue;
-			}
+			/*
+			 * imap should always be valid because of the above
+			 * partial page end_offset check on the imap.
+			 */
+			ASSERT(xfs_imap_valid(inode, imap, offset));
 
 			lock_buffer(bh);
 			if (type != XFS_IO_OVERWRITE)
@@ -777,6 +795,7 @@ xfs_convert_page(
 			count++;
 		} else {
 			done = 1;
+			break;
 		}
 	} while (offset += len, (bh = bh->b_this_page) != head);
 
@@ -868,7 +887,7 @@ xfs_aops_discard_page(
 	struct buffer_head	*bh, *head;
 	loff_t			offset = page_offset(page);
 
-	if (!xfs_check_page_type(page, XFS_IO_DELALLOC))
+	if (!xfs_check_page_type(page, XFS_IO_DELALLOC, true))
 		goto out_invalidate;
 
 	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
@@ -1325,6 +1344,14 @@ __xfs_get_blocks(
 	/*
 	 * If this is O_DIRECT or the mpage code calling tell them how large
 	 * the mapping is, so that we can avoid repeated get_blocks calls.
+	 *
+	 * If the mapping spans EOF, then we have to break the mapping up as the
+	 * mapping for blocks beyond EOF must be marked new so that sub block
+	 * regions can be correctly zeroed. We can't do this for mappings within
+	 * EOF unless the mapping was just allocated or is unwritten, otherwise
+	 * the callers would overwrite existing data with zeros. Hence we have
+	 * to split the mapping into a range up to and including EOF, and a
+	 * second mapping for beyond EOF.
 	 */
 	if (direct || size > (1 << inode->i_blkbits)) {
 		xfs_off_t		mapping_size;
@@ -1335,6 +1362,12 @@ __xfs_get_blocks(
 		ASSERT(mapping_size > 0);
 		if (mapping_size > size)
 			mapping_size = size;
+		if (offset < i_size_read(inode) &&
+		    offset + mapping_size >= i_size_read(inode)) {
+			/* limit mapping to block that spans EOF */
+			mapping_size = roundup_64(i_size_read(inode) - offset,
+						  1 << inode->i_blkbits);
+		}
 		if (mapping_size > LONG_MAX)
 			mapping_size = LONG_MAX;
 
@@ -1441,7 +1474,8 @@ xfs_vm_direct_IO(
 		ret = __blockdev_direct_IO(rw, iocb, inode, bdev, iov,
 					    offset, nr_segs,
 					    xfs_get_blocks_direct,
-					    xfs_end_io_direct_write, NULL, 0);
+					    xfs_end_io_direct_write, NULL,
+					    DIO_ASYNC_EXTEND);
 		if (ret != -EIOCBQUEUED && iocb->private)
 			goto out_destroy_ioend;
 	} else {
@@ -1546,6 +1580,16 @@ xfs_vm_write_failed(
 
 		xfs_vm_kill_delalloc_range(inode, block_offset,
 					   block_offset + bh->b_size);
+
+		/*
+		 * This buffer does not contain data anymore. make sure anyone
+		 * who finds it knows that for certain.
+		 */
+		clear_buffer_delay(bh);
+		clear_buffer_uptodate(bh);
+		clear_buffer_mapped(bh);
+		clear_buffer_new(bh);
+		clear_buffer_dirty(bh);
 	}
 
 }
@@ -1579,12 +1623,21 @@ xfs_vm_write_begin(
 	status = __block_write_begin(page, pos, len, xfs_get_blocks);
 	if (unlikely(status)) {
 		struct inode	*inode = mapping->host;
+		size_t		isize = i_size_read(inode);
 
 		xfs_vm_write_failed(inode, page, pos, len);
 		unlock_page(page);
 
-		if (pos + len > i_size_read(inode))
-			truncate_pagecache(inode, i_size_read(inode));
+		/*
+		 * If the write is beyond EOF, we only want to kill blocks
+		 * allocated in this write, not blocks that were previously
+		 * written successfully.
+		 */
+		if (pos + len > isize) {
+			ssize_t start = max_t(ssize_t, pos, isize);
+
+			truncate_pagecache_range(inode, start, pos + len);
+		}
 
 		page_cache_release(page);
 		page = NULL;
@@ -1595,9 +1648,12 @@ xfs_vm_write_begin(
 }
 
 /*
- * On failure, we only need to kill delalloc blocks beyond EOF because they
- * will never be written. For blocks within EOF, generic_write_end() zeros them
- * so they are safe to leave alone and be written with all the other valid data.
+ * On failure, we only need to kill delalloc blocks beyond EOF in the range of
+ * this specific write because they will never be written. Previous writes
+ * beyond EOF where block allocation succeeded do not need to be trashed, so
+ * only new blocks from this write should be trashed. For blocks within
+ * EOF, generic_write_end() zeros them so they are safe to leave alone and be
+ * written with all the other valid data.
  */
 STATIC int
 xfs_vm_write_end(
@@ -1620,8 +1676,11 @@ xfs_vm_write_end(
 		loff_t		to = pos + len;
 
 		if (to > isize) {
-			truncate_pagecache(inode, isize);
+			/* only kill blocks in this write beyond EOF */
+			if (pos > isize)
+				isize = pos;
 			xfs_vm_kill_delalloc_range(inode, isize, to);
+			truncate_pagecache_range(inode, isize, to);
 		}
 	}
 	return ret;