1 files changed, 386 insertions, 259 deletions

diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 90383ed6100..4a231a166cf 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -27,8 +27,8 @@
 #include <linux/swap.h>
 #include <linux/pipe_fs_i.h>
 #include <linux/mpage.h>
+#include <linux/quotaops.h>
 
-#define MLOG_MASK_PREFIX ML_FILE_IO
 #include <cluster/masklog.h>
 
 #include "ocfs2.h"
@@ -43,6 +43,8 @@
 #include "suballoc.h"
 #include "super.h"
 #include "symlink.h"
+#include "refcounttree.h"
+#include "ocfs2_trace.h"
 
 #include "buffer_head_io.h"
 
@@ -57,8 +59,9 @@ static int ocfs2_symlink_get_block(struct inode *inode, sector_t iblock,
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 	void *kaddr;
 
-	mlog_entry("(0x%p, %llu, 0x%p, %d)\n", inode,
-		   (unsigned long long)iblock, bh_result, create);
+	trace_ocfs2_symlink_get_block(
+			(unsigned long long)OCFS2_I(inode)->ip_blkno,
+			(unsigned long long)iblock, bh_result, create);
 
 	BUG_ON(ocfs2_inode_is_fast_symlink(inode));
 
@@ -68,24 +71,16 @@ static int ocfs2_symlink_get_block(struct inode *inode, sector_t iblock,
 		goto bail;
 	}
 
-	status = ocfs2_read_block(OCFS2_SB(inode->i_sb),
-				  OCFS2_I(inode)->ip_blkno,
-				  &bh, OCFS2_BH_CACHED, inode);
+	status = ocfs2_read_inode_block(inode, &bh);
 	if (status < 0) {
 		mlog_errno(status);
 		goto bail;
 	}
 	fe = (struct ocfs2_dinode *) bh->b_data;
 
-	if (!OCFS2_IS_VALID_DINODE(fe)) {
-		mlog(ML_ERROR, "Invalid dinode #%llu: signature = %.*s\n",
-		     (unsigned long long)le64_to_cpu(fe->i_blkno), 7,
-		     fe->i_signature);
-		goto bail;
-	}
-
 	if ((u64)iblock >= ocfs2_clusters_to_blocks(inode->i_sb,
 						    le32_to_cpu(fe->i_clusters))) {
+		err = -ENOMEM;
 		mlog(ML_ERROR, "block offset is outside the allocated size: "
 		     "%llu\n", (unsigned long long)iblock);
 		goto bail;
@@ -98,6 +93,7 @@ static int ocfs2_symlink_get_block(struct inode *inode, sector_t iblock,
 			    iblock;
 		buffer_cache_bh = sb_getblk(osb->sb, blkno);
 		if (!buffer_cache_bh) {
+			err = -ENOMEM;
 			mlog(ML_ERROR, "couldn't getblock for symlink!\n");
 			goto bail;
 		}
@@ -108,7 +104,7 @@ static int ocfs2_symlink_get_block(struct inode *inode, sector_t iblock,
 		 * copy, the data is still good. */
 		if (buffer_jbd(buffer_cache_bh)
 		    && ocfs2_inode_is_new(inode)) {
-			kaddr = kmap_atomic(bh_result->b_page, KM_USER0);
+			kaddr = kmap_atomic(bh_result->b_page);
 			if (!kaddr) {
 				mlog(ML_ERROR, "couldn't kmap!\n");
 				goto bail;
@@ -116,7 +112,7 @@ static int ocfs2_symlink_get_block(struct inode *inode, sector_t iblock,
 			memcpy(kaddr + (bh_result->b_size * iblock),
 			       buffer_cache_bh->b_data,
 			       bh_result->b_size);
-			kunmap_atomic(kaddr, KM_USER0);
+			kunmap_atomic(kaddr);
 			set_buffer_uptodate(bh_result);
 		}
 		brelse(buffer_cache_bh);
@@ -128,15 +124,13 @@ static int ocfs2_symlink_get_block(struct inode *inode, sector_t iblock,
 	err = 0;
 
 bail:
-	if (bh)
-		brelse(bh);
+	brelse(bh);
 
-	mlog_exit(err);
 	return err;
 }
 
-static int ocfs2_get_block(struct inode *inode, sector_t iblock,
-			   struct buffer_head *bh_result, int create)
+int ocfs2_get_block(struct inode *inode, sector_t iblock,
+		    struct buffer_head *bh_result, int create)
 {
 	int err = 0;
 	unsigned int ext_flags;
@@ -144,8 +138,8 @@ static int ocfs2_get_block(struct inode *inode, sector_t iblock,
 	u64 p_blkno, count, past_eof;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 
-	mlog_entry("(0x%p, %llu, 0x%p, %d)\n", inode,
-		   (unsigned long long)iblock, bh_result, create);
+	trace_ocfs2_get_block((unsigned long long)OCFS2_I(inode)->ip_blkno,
+			      (unsigned long long)iblock, bh_result, create);
 
 	if (OCFS2_I(inode)->ip_flags & OCFS2_INODE_SYSTEM_FILE)
 		mlog(ML_NOTICE, "get_block on system inode 0x%p (%lu)\n",
@@ -173,11 +167,18 @@ static int ocfs2_get_block(struct inode *inode, sector_t iblock,
 	 * ocfs2 never allocates in this function - the only time we
 	 * need to use BH_New is when we're extending i_size on a file
 	 * system which doesn't support holes, in which case BH_New
-	 * allows block_prepare_write() to zero.
+	 * allows __block_write_begin() to zero.
+	 *
+	 * If we see this on a sparse file system, then a truncate has
+	 * raced us and removed the cluster. In this case, we clear
+	 * the buffers dirty and uptodate bits and let the buffer code
+	 * ignore it as a hole.
 	 */
-	mlog_bug_on_msg(create && p_blkno == 0 && ocfs2_sparse_alloc(osb),
-			"ino %lu, iblock %llu\n", inode->i_ino,
-			(unsigned long long)iblock);
+	if (create && p_blkno == 0 && ocfs2_sparse_alloc(osb)) {
+		clear_buffer_dirty(bh_result);
+		clear_buffer_uptodate(bh_result);
+		goto bail;
+	}
 
 	/* Treat the unwritten extent as a hole for zeroing purposes. */
 	if (p_blkno && !(ext_flags & OCFS2_EXT_UNWRITTEN))
@@ -195,21 +196,21 @@ static int ocfs2_get_block(struct inode *inode, sector_t iblock,
 			     (unsigned long long)OCFS2_I(inode)->ip_blkno);
 			mlog(ML_ERROR, "Size %llu, clusters %u\n", (unsigned long long)i_size_read(inode), OCFS2_I(inode)->ip_clusters);
 			dump_stack();
+			goto bail;
 		}
+	}
 
-		past_eof = ocfs2_blocks_for_bytes(inode->i_sb, i_size_read(inode));
-		mlog(0, "Inode %lu, past_eof = %llu\n", inode->i_ino,
-		     (unsigned long long)past_eof);
+	past_eof = ocfs2_blocks_for_bytes(inode->i_sb, i_size_read(inode));
 
-		if (create && (iblock >= past_eof))
-			set_buffer_new(bh_result);
-	}
+	trace_ocfs2_get_block_end((unsigned long long)OCFS2_I(inode)->ip_blkno,
+				  (unsigned long long)past_eof);
+	if (create && (iblock >= past_eof))
+		set_buffer_new(bh_result);
 
 bail:
 	if (err < 0)
 		err = -EIO;
 
-	mlog_exit(err);
 	return err;
 }
 
@@ -229,7 +230,7 @@ int ocfs2_read_inline_data(struct inode *inode, struct page *page,
 	size = i_size_read(inode);
 
 	if (size > PAGE_CACHE_SIZE ||
-	    size > ocfs2_max_inline_data(inode->i_sb)) {
+	    size > ocfs2_max_inline_data_with_xattr(inode->i_sb, di)) {
 		ocfs2_error(inode->i_sb,
 			    "Inode %llu has with inline data has bad size: %Lu",
 			    (unsigned long long)OCFS2_I(inode)->ip_blkno,
@@ -237,13 +238,13 @@ int ocfs2_read_inline_data(struct inode *inode, struct page *page,
 		return -EROFS;
 	}
 
-	kaddr = kmap_atomic(page, KM_USER0);
+	kaddr = kmap_atomic(page);
 	if (size)
 		memcpy(kaddr, di->id2.i_data.id_data, size);
 	/* Clear the remaining part of the page */
 	memset(kaddr + size, 0, PAGE_CACHE_SIZE - size);
 	flush_dcache_page(page);
-	kunmap_atomic(kaddr, KM_USER0);
+	kunmap_atomic(kaddr);
 
 	SetPageUptodate(page);
 
@@ -254,13 +255,11 @@ static int ocfs2_readpage_inline(struct inode *inode, struct page *page)
 {
 	int ret;
 	struct buffer_head *di_bh = NULL;
-	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 
 	BUG_ON(!PageLocked(page));
 	BUG_ON(!(OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL));
 
-	ret = ocfs2_read_block(osb, OCFS2_I(inode)->ip_blkno, &di_bh,
-			       OCFS2_BH_CACHED, inode);
+	ret = ocfs2_read_inode_block(inode, &di_bh);
 	if (ret) {
 		mlog_errno(ret);
 		goto out;
@@ -281,7 +280,8 @@ static int ocfs2_readpage(struct file *file, struct page *page)
 	loff_t start = (loff_t)page->index << PAGE_CACHE_SHIFT;
 	int ret, unlock = 1;
 
-	mlog_entry("(0x%p, %lu)\n", file, (page ? page->index : 0));
+	trace_ocfs2_readpage((unsigned long long)oi->ip_blkno,
+			     (page ? page->index : 0));
 
 	ret = ocfs2_inode_lock_with_page(inode, NULL, 0, page);
 	if (ret != 0) {
@@ -292,7 +292,15 @@ static int ocfs2_readpage(struct file *file, struct page *page)
 	}
 
 	if (down_read_trylock(&oi->ip_alloc_sem) == 0) {
+		/*
+		 * Unlock the page and cycle ip_alloc_sem so that we don't
+		 * busyloop waiting for ip_alloc_sem to unlock
+		 */
 		ret = AOP_TRUNCATED_PAGE;
+		unlock_page(page);
+		unlock = 0;
+		down_read(&oi->ip_alloc_sem);
+		up_read(&oi->ip_alloc_sem);
 		goto out_inode_unlock;
 	}
 
@@ -326,7 +334,6 @@ out_inode_unlock:
 out:
 	if (unlock)
 		unlock_page(page);
-	mlog_exit(ret);
 	return ret;
 }
 
@@ -399,30 +406,11 @@ out_unlock:
  */
 static int ocfs2_writepage(struct page *page, struct writeback_control *wbc)
 {
-	int ret;
-
-	mlog_entry("(0x%p)\n", page);
-
-	ret = block_write_full_page(page, ocfs2_get_block, wbc);
-
-	mlog_exit(ret);
-
-	return ret;
-}
-
-/*
- * This is called from ocfs2_write_zero_page() which has handled it's
- * own cluster locking and has ensured allocation exists for those
- * blocks to be written.
- */
-int ocfs2_prepare_write_nolock(struct inode *inode, struct page *page,
-			       unsigned from, unsigned to)
-{
-	int ret;
-
-	ret = block_prepare_write(page, from, to, ocfs2_get_block);
+	trace_ocfs2_writepage(
+		(unsigned long long)OCFS2_I(page->mapping->host)->ip_blkno,
+		page->index);
 
-	return ret;
+	return block_write_full_page(page, ocfs2_get_block, wbc);
 }
 
 /* Taken from ext3. We don't necessarily need the full blown
@@ -461,39 +449,6 @@ int walk_page_buffers(	handle_t *handle,
 	return ret;
 }
 
-handle_t *ocfs2_start_walk_page_trans(struct inode *inode,
-							 struct page *page,
-							 unsigned from,
-							 unsigned to)
-{
-	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
-	handle_t *handle = NULL;
-	int ret = 0;
-
-	handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
-	if (!handle) {
-		ret = -ENOMEM;
-		mlog_errno(ret);
-		goto out;
-	}
-
-	if (ocfs2_should_order_data(inode)) {
-		ret = walk_page_buffers(handle,
-					page_buffers(page),
-					from, to, NULL,
-					ocfs2_journal_dirty_data);
-		if (ret < 0) 
-			mlog_errno(ret);
-	}
-out:
-	if (ret) {
-		if (handle)
-			ocfs2_commit_trans(osb, handle);
-		handle = ERR_PTR(ret);
-	}
-	return handle;
-}
-
 static sector_t ocfs2_bmap(struct address_space *mapping, sector_t block)
 {
 	sector_t status;
@@ -501,7 +456,8 @@ static sector_t ocfs2_bmap(struct address_space *mapping, sector_t block)
 	int err = 0;
 	struct inode *inode = mapping->host;
 
-	mlog_entry("(block = %llu)\n", (unsigned long long)block);
+	trace_ocfs2_bmap((unsigned long long)OCFS2_I(inode)->ip_blkno,
+			 (unsigned long long)block);
 
 	/* We don't need to lock journal system files, since they aren't
 	 * accessed concurrently from multiple nodes.
@@ -535,8 +491,6 @@ static sector_t ocfs2_bmap(struct address_space *mapping, sector_t block)
 bail:
 	status = err ? 0 : p_blkno;
 
-	mlog_exit((int)status);
-
 	return status;
 }
 
@@ -552,6 +506,9 @@ bail:
  *
  * called like this: dio->get_blocks(dio->inode, fs_startblk,
  * 					fs_count, map_bh, dio->rw == WRITE);
+ *
+ * Note that we never bother to allocate blocks here, and thus ignore the
+ * create argument.
  */
 static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
 				     struct buffer_head *bh_result, int create)
@@ -568,14 +525,6 @@ static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
 
 	inode_blocks = ocfs2_blocks_for_bytes(inode->i_sb, i_size_read(inode));
 
-	/*
-	 * Any write past EOF is not allowed because we'd be extending.
-	 */
-	if (create && (iblock + max_blocks) > inode_blocks) {
-		ret = -EIO;
-		goto bail;
-	}
-
 	/* This figures out the size of the next contiguous block, and
 	 * our logical offset */
 	ret = ocfs2_extent_map_get_blocks(inode, iblock, &p_blkno,
@@ -587,14 +536,8 @@ static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
 		goto bail;
 	}
 
-	if (!ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb)) && !p_blkno) {
-		ocfs2_error(inode->i_sb,
-			    "Inode %llu has a hole at block %llu\n",
-			    (unsigned long long)OCFS2_I(inode)->ip_blkno,
-			    (unsigned long long)iblock);
-		ret = -EROFS;
-		goto bail;
-	}
+	/* We should already CoW the refcounted extent in case of create. */
+	BUG_ON(create && (ext_flags & OCFS2_EXT_REFCOUNTED));
 
 	/*
 	 * get_more_blocks() expects us to describe a hole by clearing
@@ -604,20 +547,8 @@ static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
 	 */
 	if (p_blkno && !(ext_flags & OCFS2_EXT_UNWRITTEN))
 		map_bh(bh_result, inode->i_sb, p_blkno);
-	else {
-		/*
-		 * ocfs2_prepare_inode_for_write() should have caught
-		 * the case where we'd be filling a hole and triggered
-		 * a buffered write instead.
-		 */
-		if (create) {
-			ret = -EIO;
-			mlog_errno(ret);
-			goto bail;
-		}
-
+	else
 		clear_buffer_mapped(bh_result);
-	}
 
 	/* make sure we don't map more than max_blocks blocks here as
 	   that's all the kernel will handle at this point. */
@@ -628,63 +559,51 @@ bail:
 	return ret;
 }
 
-/* 
+/*
  * ocfs2_dio_end_io is called by the dio core when a dio is finished.  We're
- * particularly interested in the aio/dio case.  Like the core uses
- * i_alloc_sem, we use the rw_lock DLM lock to protect io on one node from
- * truncation on another.
+ * particularly interested in the aio/dio case.  We use the rw_lock DLM lock
+ * to protect io on one node from truncation on another.
  */
 static void ocfs2_dio_end_io(struct kiocb *iocb,
 			     loff_t offset,
 			     ssize_t bytes,
 			     void *private)
 {
-	struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode;
+	struct inode *inode = file_inode(iocb->ki_filp);
 	int level;
 
 	/* this io's submitter should not have unlocked this before we could */
 	BUG_ON(!ocfs2_iocb_is_rw_locked(iocb));
 
+	if (ocfs2_iocb_is_sem_locked(iocb))
+		ocfs2_iocb_clear_sem_locked(iocb);
+
+	if (ocfs2_iocb_is_unaligned_aio(iocb)) {
+		ocfs2_iocb_clear_unaligned_aio(iocb);
+
+		mutex_unlock(&OCFS2_I(inode)->ip_unaligned_aio);
+	}
+
 	ocfs2_iocb_clear_rw_locked(iocb);
 
 	level = ocfs2_iocb_rw_locked_level(iocb);
-	if (!level)
-		up_read(&inode->i_alloc_sem);
 	ocfs2_rw_unlock(inode, level);
 }
 
-/*
- * ocfs2_invalidatepage() and ocfs2_releasepage() are shamelessly stolen
- * from ext3.  PageChecked() bits have been removed as OCFS2 does not
- * do journalled data.
- */
-static void ocfs2_invalidatepage(struct page *page, unsigned long offset)
-{
-	journal_t *journal = OCFS2_SB(page->mapping->host->i_sb)->journal->j_journal;
-
-	journal_invalidatepage(journal, page, offset);
-}
-
 static int ocfs2_releasepage(struct page *page, gfp_t wait)
 {
-	journal_t *journal = OCFS2_SB(page->mapping->host->i_sb)->journal->j_journal;
-
 	if (!page_has_buffers(page))
 		return 0;
-	return journal_try_to_free_buffers(journal, page, wait);
+	return try_to_free_buffers(page);
 }
 
 static ssize_t ocfs2_direct_IO(int rw,
 			       struct kiocb *iocb,
-			       const struct iovec *iov,
-			       loff_t offset,
-			       unsigned long nr_segs)
+			       struct iov_iter *iter,
+			       loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
-	struct inode *inode = file->f_path.dentry->d_inode->i_mapping->host;
-	int ret;
-
-	mlog_entry_void();
+	struct inode *inode = file_inode(file)->i_mapping->host;
 
 	/*
 	 * Fallback to buffered I/O if we see an inode without
@@ -693,14 +612,14 @@ static ssize_t ocfs2_direct_IO(int rw,
 	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
 		return 0;
 
-	ret = blockdev_direct_IO_no_locking(rw, iocb, inode,
-					    inode->i_sb->s_bdev, iov, offset,
-					    nr_segs, 
-					    ocfs2_direct_IO_get_blocks,
-					    ocfs2_dio_end_io);
+	/* Fallback to buffered I/O if we are appending. */
+	if (i_size_read(inode) <= offset)
+		return 0;
 
-	mlog_exit(ret);
-	return ret;
+	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);
 }
 
 static void ocfs2_figure_cluster_boundaries(struct ocfs2_super *osb,
@@ -747,7 +666,7 @@ static void ocfs2_clear_page_regions(struct page *page,
 
 	ocfs2_figure_cluster_boundaries(osb, cpos, &cluster_start, &cluster_end);
 
-	kaddr = kmap_atomic(page, KM_USER0);
+	kaddr = kmap_atomic(page);
 
 	if (from || to) {
 		if (from > cluster_start)
@@ -758,7 +677,7 @@ static void ocfs2_clear_page_regions(struct page *page,
 		memset(kaddr + cluster_start, 0, cluster_end - cluster_start);
 	}
 
-	kunmap_atomic(kaddr, KM_USER0);
+	kunmap_atomic(kaddr);
 }
 
 /*
@@ -783,7 +702,7 @@ static int ocfs2_should_read_blk(struct inode *inode, struct page *page,
 }
 
 /*
- * Some of this taken from block_prepare_write(). We already have our
+ * Some of this taken from __block_write_begin(). We already have our
  * mapping by now though, and the entire write will be allocating or
  * it won't, so not much need to use BH_New.
  *
@@ -901,18 +820,17 @@ struct ocfs2_write_cluster_desc {
 	 */
 	unsigned	c_new;
 	unsigned	c_unwritten;
+	unsigned	c_needs_zero;
 };
 
-static inline int ocfs2_should_zero_cluster(struct ocfs2_write_cluster_desc *d)
-{
-	return d->c_new || d->c_unwritten;
-}
-
 struct ocfs2_write_ctxt {
 	/* Logical cluster position / len of write */
 	u32				w_cpos;
 	u32				w_clen;
 
+	/* First cluster allocated in a nonsparse extend */
+	u32				w_first_new_cpos;
+
 	struct ocfs2_write_cluster_desc	w_desc[OCFS2_MAX_CLUSTERS_PER_PAGE];
 
 	/*
@@ -935,11 +853,17 @@ struct ocfs2_write_ctxt {
 	 * out in so that future reads from that region will get
 	 * zero's.
 	 */
-	struct page			*w_pages[OCFS2_MAX_CTXT_PAGES];
 	unsigned int			w_num_pages;
+	struct page			*w_pages[OCFS2_MAX_CTXT_PAGES];
 	struct page			*w_target_page;
 
 	/*
+	 * w_target_locked is used for page_mkwrite path indicating no unlocking
+	 * against w_target_page in ocfs2_write_end_nolock.
+	 */
+	unsigned int			w_target_locked:1;
+
+	/*
 	 * ocfs2_write_end() uses this to know what the real range to
 	 * write in the target should be.
 	 */
@@ -972,6 +896,24 @@ void ocfs2_unlock_and_free_pages(struct page **pages, int num_pages)
 
 static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc)
 {
+	int i;
+
+	/*
+	 * w_target_locked is only set to true in the page_mkwrite() case.
+	 * The intent is to allow us to lock the target page from write_begin()
+	 * to write_end(). The caller must hold a ref on w_target_page.
+	 */
+	if (wc->w_target_locked) {
+		BUG_ON(!wc->w_target_page);
+		for (i = 0; i < wc->w_num_pages; i++) {
+			if (wc->w_target_page == wc->w_pages[i]) {
+				wc->w_pages[i] = NULL;
+				break;
+			}
+		}
+		mark_page_accessed(wc->w_target_page);
+		page_cache_release(wc->w_target_page);
+	}
 	ocfs2_unlock_and_free_pages(wc->w_pages, wc->w_num_pages);
 
 	brelse(wc->w_di_bh);
@@ -990,6 +932,7 @@ static int ocfs2_alloc_write_ctxt(struct ocfs2_write_ctxt **wcp,
 		return -ENOMEM;
 
 	wc->w_cpos = pos >> osb->s_clustersize_bits;
+	wc->w_first_new_cpos = UINT_MAX;
 	cend = (pos + len - 1) >> osb->s_clustersize_bits;
 	wc->w_clen = cend - wc->w_cpos + 1;
 	get_bh(di_bh);
@@ -1066,12 +1009,12 @@ static void ocfs2_write_failure(struct inode *inode,
 	for(i = 0; i < wc->w_num_pages; i++) {
 		tmppage = wc->w_pages[i];
 
-		if (ocfs2_should_order_data(inode))
-			walk_page_buffers(wc->w_handle, page_buffers(tmppage),
-					  from, to, NULL,
-					  ocfs2_journal_dirty_data);
+		if (page_has_buffers(tmppage)) {
+			if (ocfs2_should_order_data(inode))
+				ocfs2_jbd2_file_inode(wc->w_handle, inode);
 
-		block_commit_write(tmppage, from, to);
+			block_commit_write(tmppage, from, to);
+		}
 	}
 }
 
@@ -1089,6 +1032,12 @@ static int ocfs2_prepare_page_for_write(struct inode *inode, u64 *p_blkno,
 	ocfs2_figure_cluster_boundaries(OCFS2_SB(inode->i_sb), cpos,
 					&cluster_start, &cluster_end);
 
+	/* treat the write as new if the a hole/lseek spanned across
+	 * the page boundary.
+	 */
+	new = new | ((i_size_read(inode) <= page_offset(page)) &&
+			(page_offset(page) <= user_pos));
+
 	if (page == wc->w_target_page) {
 		map_from = user_pos & (PAGE_CACHE_SIZE - 1);
 		map_to = map_from + user_len;
@@ -1155,23 +1104,37 @@ out:
  */
 static int ocfs2_grab_pages_for_write(struct address_space *mapping,
 				      struct ocfs2_write_ctxt *wc,
-				      u32 cpos, loff_t user_pos, int new,
+				      u32 cpos, loff_t user_pos,
+				      unsigned user_len, int new,
 				      struct page *mmap_page)
 {
 	int ret = 0, i;
-	unsigned long start, target_index, index;
+	unsigned long start, target_index, end_index, index;
 	struct inode *inode = mapping->host;
+	loff_t last_byte;
 
 	target_index = user_pos >> PAGE_CACHE_SHIFT;
 
 	/*
 	 * Figure out how many pages we'll be manipulating here. For
 	 * non allocating write, we just change the one
-	 * page. Otherwise, we'll need a whole clusters worth.
+	 * page. Otherwise, we'll need a whole clusters worth.  If we're
+	 * writing past i_size, we only need enough pages to cover the
+	 * last page of the write.
 	 */
 	if (new) {
 		wc->w_num_pages = ocfs2_pages_per_cluster(inode->i_sb);
 		start = ocfs2_align_clusters_to_page_index(inode->i_sb, cpos);
+		/*
+		 * We need the index *past* the last page we could possibly
+		 * touch.  This is the page past the end of the write or
+		 * i_size, whichever is greater.
+		 */
+		last_byte = max(user_pos + user_len, i_size_read(inode));
+		BUG_ON(last_byte < 1);
+		end_index = ((last_byte - 1) >> PAGE_CACHE_SHIFT) + 1;
+		if ((start + wc->w_num_pages) > end_index)
+			wc->w_num_pages = end_index - start;
 	} else {
 		wc->w_num_pages = 1;
 		start = target_index;
@@ -1188,20 +1151,17 @@ static int ocfs2_grab_pages_for_write(struct address_space *mapping,
 			 */
 			lock_page(mmap_page);
 
+			/* Exit and let the caller retry */
 			if (mmap_page->mapping != mapping) {
+				WARN_ON(mmap_page->mapping);
 				unlock_page(mmap_page);
-				/*
-				 * Sanity check - the locking in
-				 * ocfs2_pagemkwrite() should ensure
-				 * that this code doesn't trigger.
-				 */
-				ret = -EINVAL;
-				mlog_errno(ret);
+				ret = -EAGAIN;
 				goto out;
 			}
 
 			page_cache_get(mmap_page);
 			wc->w_pages[i] = mmap_page;
+			wc->w_target_locked = true;
 		} else {
 			wc->w_pages[i] = find_or_create_page(mapping, index,
 							     GFP_NOFS);
@@ -1211,11 +1171,14 @@ static int ocfs2_grab_pages_for_write(struct address_space *mapping,
 				goto out;
 			}
 		}
+		wait_for_stable_page(wc->w_pages[i]);
 
 		if (index == target_index)
 			wc->w_target_page = wc->w_pages[i];
 	}
 out:
+	if (ret)
+		wc->w_target_locked = false;
 	return ret;
 }
 
@@ -1224,19 +1187,18 @@ out:
  */
 static int ocfs2_write_cluster(struct address_space *mapping,
 			       u32 phys, unsigned int unwritten,
+			       unsigned int should_zero,
 			       struct ocfs2_alloc_context *data_ac,
 			       struct ocfs2_alloc_context *meta_ac,
 			       struct ocfs2_write_ctxt *wc, u32 cpos,
 			       loff_t user_pos, unsigned user_len)
 {
-	int ret, i, new, should_zero = 0;
+	int ret, i, new;
 	u64 v_blkno, p_blkno;
 	struct inode *inode = mapping->host;
+	struct ocfs2_extent_tree et;
 
 	new = phys == 0 ? 1 : 0;
-	if (new || unwritten)
-		should_zero = 1;
-
 	if (new) {
 		u32 tmp_pos;
 
@@ -1245,10 +1207,10 @@ static int ocfs2_write_cluster(struct address_space *mapping,
 		 * any additional semaphores or cluster locks.
 		 */
 		tmp_pos = cpos;
-		ret = ocfs2_do_extend_allocation(OCFS2_SB(inode->i_sb), inode,
-						 &tmp_pos, 1, 0, wc->w_di_bh,
-						 wc->w_handle, data_ac,
-						 meta_ac, NULL);
+		ret = ocfs2_add_inode_data(OCFS2_SB(inode->i_sb), inode,
+					   &tmp_pos, 1, 0, wc->w_di_bh,
+					   wc->w_handle, data_ac,
+					   meta_ac, NULL);
 		/*
 		 * This shouldn't happen because we must have already
 		 * calculated the correct meta data allocation required. The
@@ -1266,7 +1228,9 @@ static int ocfs2_write_cluster(struct address_space *mapping,
 			goto out;
 		}
 	} else if (unwritten) {
-		ret = ocfs2_mark_extent_written(inode, wc->w_di_bh,
+		ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(inode),
+					      wc->w_di_bh);
+		ret = ocfs2_mark_extent_written(inode, &et,
 						wc->w_handle, cpos, 1, phys,
 						meta_ac, &wc->w_dealloc);
 		if (ret < 0) {
@@ -1306,7 +1270,7 @@ static int ocfs2_write_cluster(struct address_space *mapping,
 		if (tmpret) {
 			mlog_errno(tmpret);
 			if (ret == 0)
-				tmpret = ret;
+				ret = tmpret;
 		}
 	}
 
@@ -1346,7 +1310,9 @@ static int ocfs2_write_cluster_by_desc(struct address_space *mapping,
 			local_len = osb->s_clustersize - cluster_off;
 
 		ret = ocfs2_write_cluster(mapping, desc->c_phys,
-					  desc->c_unwritten, data_ac, meta_ac,
+					  desc->c_unwritten,
+					  desc->c_needs_zero,
+					  data_ac, meta_ac,
 					  wc, desc->c_cpos, pos, local_len);
 		if (ret) {
 			mlog_errno(ret);
@@ -1396,14 +1362,14 @@ static void ocfs2_set_target_boundaries(struct ocfs2_super *osb,
 		 * newly allocated cluster.
 		 */
 		desc = &wc->w_desc[0];
-		if (ocfs2_should_zero_cluster(desc))
+		if (desc->c_needs_zero)
 			ocfs2_figure_cluster_boundaries(osb,
 							desc->c_cpos,
 							&wc->w_target_from,
 							NULL);
 
 		desc = &wc->w_desc[wc->w_clen - 1];
-		if (ocfs2_should_zero_cluster(desc))
+		if (desc->c_needs_zero)
 			ocfs2_figure_cluster_boundaries(osb,
 							desc->c_cpos,
 							NULL,
@@ -1452,6 +1418,9 @@ static int ocfs2_populate_write_desc(struct inode *inode,
 				goto out;
 			}
 
+			/* We should already CoW the refcountd extent. */
+			BUG_ON(ext_flags & OCFS2_EXT_REFCOUNTED);
+
 			/*
 			 * Assume worst case - that we're writing in
 			 * the middle of the extent.
@@ -1471,13 +1440,28 @@ static int ocfs2_populate_write_desc(struct inode *inode,
 			phys++;
 		}
 
+		/*
+		 * If w_first_new_cpos is < UINT_MAX, we have a non-sparse
+		 * file that got extended.  w_first_new_cpos tells us
+		 * where the newly allocated clusters are so we can
+		 * zero them.
+		 */
+		if (desc->c_cpos >= wc->w_first_new_cpos) {
+			BUG_ON(phys == 0);
+			desc->c_needs_zero = 1;
+		}
+
 		desc->c_phys = phys;
 		if (phys == 0) {
 			desc->c_new = 1;
+			desc->c_needs_zero = 1;
 			*clusters_to_alloc = *clusters_to_alloc + 1;
 		}
-		if (ext_flags & OCFS2_EXT_UNWRITTEN)
+
+		if (ext_flags & OCFS2_EXT_UNWRITTEN) {
 			desc->c_unwritten = 1;
+			desc->c_needs_zero = 1;
+		}
 
 		num_clusters--;
 	}
@@ -1517,8 +1501,8 @@ static int ocfs2_write_begin_inline(struct address_space *mapping,
 		goto out;
 	}
 
-	ret = ocfs2_journal_access(handle, inode, wc->w_di_bh,
-				   OCFS2_JOURNAL_ACCESS_WRITE);
+	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), wc->w_di_bh,
+				      OCFS2_JOURNAL_ACCESS_WRITE);
 	if (ret) {
 		ocfs2_commit_trans(osb, handle);
 
@@ -1560,10 +1544,11 @@ static int ocfs2_try_to_write_inline_data(struct address_space *mapping,
 	int ret, written = 0;
 	loff_t end = pos + len;
 	struct ocfs2_inode_info *oi = OCFS2_I(inode);
+	struct ocfs2_dinode *di = NULL;
 
-	mlog(0, "Inode %llu, write of %u bytes at off %llu. features: 0x%x\n",
-	     (unsigned long long)oi->ip_blkno, len, (unsigned long long)pos,
-	     oi->ip_dyn_features);
+	trace_ocfs2_try_to_write_inline_data((unsigned long long)oi->ip_blkno,
+					     len, (unsigned long long)pos,
+					     oi->ip_dyn_features);
 
 	/*
 	 * Handle inodes which already have inline data 1st.
@@ -1592,7 +1577,9 @@ static int ocfs2_try_to_write_inline_data(struct address_space *mapping,
 	/*
 	 * Check whether the write can fit.
 	 */
-	if (mmap_page || end > ocfs2_max_inline_data(inode->i_sb))
+	di = (struct ocfs2_dinode *)wc->w_di_bh->b_data;
+	if (mmap_page ||
+	    end > ocfs2_max_inline_data_with_xattr(inode->i_sb, di))
 		return 0;
 
 do_inline_write:
@@ -1620,34 +1607,86 @@ out:
  * write path can treat it as an non-allocating write, which has no
  * special case code for sparse/nonsparse files.
  */
-static int ocfs2_expand_nonsparse_inode(struct inode *inode, loff_t pos,
-					unsigned len,
+static int ocfs2_expand_nonsparse_inode(struct inode *inode,
+					struct buffer_head *di_bh,
+					loff_t pos, unsigned len,
 					struct ocfs2_write_ctxt *wc)
 {
 	int ret;
-	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 	loff_t newsize = pos + len;
 
-	if (ocfs2_sparse_alloc(osb))
-		return 0;
+	BUG_ON(ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb)));
 
 	if (newsize <= i_size_read(inode))
 		return 0;
 
-	ret = ocfs2_extend_no_holes(inode, newsize, newsize - len);
+	ret = ocfs2_extend_no_holes(inode, di_bh, newsize, pos);
 	if (ret)
 		mlog_errno(ret);
 
+	wc->w_first_new_cpos =
+		ocfs2_clusters_for_bytes(inode->i_sb, i_size_read(inode));
+
+	return ret;
+}
+
+static int ocfs2_zero_tail(struct inode *inode, struct buffer_head *di_bh,
+			   loff_t pos)
+{
+	int ret = 0;
+
+	BUG_ON(!ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb)));
+	if (pos > i_size_read(inode))
+		ret = ocfs2_zero_extend(inode, di_bh, pos);
+
 	return ret;
 }
 
-int ocfs2_write_begin_nolock(struct address_space *mapping,
+/*
+ * Try to flush truncate logs if we can free enough clusters from it.
+ * As for return value, "< 0" means error, "0" no space and "1" means
+ * we have freed enough spaces and let the caller try to allocate again.
+ */
+static int ocfs2_try_to_free_truncate_log(struct ocfs2_super *osb,
+					  unsigned int needed)
+{
+	tid_t target;
+	int ret = 0;
+	unsigned int truncated_clusters;
+
+	mutex_lock(&osb->osb_tl_inode->i_mutex);
+	truncated_clusters = osb->truncated_clusters;
+	mutex_unlock(&osb->osb_tl_inode->i_mutex);
+
+	/*
+	 * Check whether we can succeed in allocating if we free
+	 * the truncate log.
+	 */
+	if (truncated_clusters < needed)
+		goto out;
+
+	ret = ocfs2_flush_truncate_log(osb);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	if (jbd2_journal_start_commit(osb->journal->j_journal, &target)) {
+		jbd2_log_wait_commit(osb->journal->j_journal, target);
+		ret = 1;
+	}
+out:
+	return ret;
+}
+
+int ocfs2_write_begin_nolock(struct file *filp,
+			     struct address_space *mapping,
 			     loff_t pos, unsigned len, unsigned flags,
 			     struct page **pagep, void **fsdata,
 			     struct buffer_head *di_bh, struct page *mmap_page)
 {
-	int ret, credits = OCFS2_INODE_UPDATE_CREDITS;
-	unsigned int clusters_to_alloc, extents_to_split;
+	int ret, cluster_of_pages, credits = OCFS2_INODE_UPDATE_CREDITS;
+	unsigned int clusters_to_alloc, extents_to_split, clusters_need = 0;
 	struct ocfs2_write_ctxt *wc;
 	struct inode *inode = mapping->host;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
@@ -1655,7 +1694,10 @@ int ocfs2_write_begin_nolock(struct address_space *mapping,
 	struct ocfs2_alloc_context *data_ac = NULL;
 	struct ocfs2_alloc_context *meta_ac = NULL;
 	handle_t *handle;
+	struct ocfs2_extent_tree et;
+	int try_free = 1, ret1;
 
+try_again:
 	ret = ocfs2_alloc_write_ctxt(&wc, osb, pos, len, di_bh);
 	if (ret) {
 		mlog_errno(ret);
@@ -1675,21 +1717,47 @@ int ocfs2_write_begin_nolock(struct address_space *mapping,
 		}
 	}
 
-	ret = ocfs2_expand_nonsparse_inode(inode, pos, len, wc);
+	if (ocfs2_sparse_alloc(osb))
+		ret = ocfs2_zero_tail(inode, di_bh, pos);
+	else
+		ret = ocfs2_expand_nonsparse_inode(inode, di_bh, pos, len,
+						   wc);
 	if (ret) {
 		mlog_errno(ret);
 		goto out;
 	}
 
+	ret = ocfs2_check_range_for_refcount(inode, pos, len);
+	if (ret < 0) {
+		mlog_errno(ret);
+		goto out;
+	} else if (ret == 1) {
+		clusters_need = wc->w_clen;
+		ret = ocfs2_refcount_cow(inode, di_bh,
+					 wc->w_cpos, wc->w_clen, UINT_MAX);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+	}
+
 	ret = ocfs2_populate_write_desc(inode, wc, &clusters_to_alloc,
 					&extents_to_split);
 	if (ret) {
 		mlog_errno(ret);
 		goto out;
 	}
+	clusters_need += clusters_to_alloc;
 
 	di = (struct ocfs2_dinode *)wc->w_di_bh->b_data;
 
+	trace_ocfs2_write_begin_nolock(
+			(unsigned long long)OCFS2_I(inode)->ip_blkno,
+			(long long)i_size_read(inode),
+			le32_to_cpu(di->i_clusters),
+			pos, len, flags, mmap_page,
+			clusters_to_alloc, extents_to_split);
+
 	/*
 	 * We set w_target_from, w_target_to here so that
 	 * ocfs2_write_end() knows which range in the target page to
@@ -1702,20 +1770,37 @@ int ocfs2_write_begin_nolock(struct address_space *mapping,
 		 * ocfs2_lock_allocators(). It greatly over-estimates
 		 * the work to be done.
 		 */
-		ret = ocfs2_lock_allocators(inode, di, clusters_to_alloc,
-					    extents_to_split, &data_ac, &meta_ac);
+		ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(inode),
+					      wc->w_di_bh);
+		ret = ocfs2_lock_allocators(inode, &et,
+					    clusters_to_alloc, extents_to_split,
+					    &data_ac, &meta_ac);
 		if (ret) {
 			mlog_errno(ret);
 			goto out;
 		}
 
-		credits = ocfs2_calc_extend_credits(inode->i_sb, di,
-						    clusters_to_alloc);
+		if (data_ac)
+			data_ac->ac_resv = &OCFS2_I(inode)->ip_la_data_resv;
+
+		credits = ocfs2_calc_extend_credits(inode->i_sb,
+						    &di->id2.i_list);
 
 	}
 
-	ocfs2_set_target_boundaries(osb, wc, pos, len,
-				    clusters_to_alloc + extents_to_split);
+	/*
+	 * We have to zero sparse allocated clusters, unwritten extent clusters,
+	 * and non-sparse clusters we just extended.  For non-sparse writes,
+	 * we know zeros will only be needed in the first and/or last cluster.
+	 */
+	if (clusters_to_alloc || extents_to_split ||
+	    (wc->w_clen && (wc->w_desc[0].c_needs_zero ||
+			    wc->w_desc[wc->w_clen - 1].c_needs_zero)))
+		cluster_of_pages = 1;
+	else
+		cluster_of_pages = 0;
+
+	ocfs2_set_target_boundaries(osb, wc, pos, len, cluster_of_pages);
 
 	handle = ocfs2_start_trans(osb, credits);
 	if (IS_ERR(handle)) {
@@ -1726,15 +1811,21 @@ int ocfs2_write_begin_nolock(struct address_space *mapping,
 
 	wc->w_handle = handle;
 
+	if (clusters_to_alloc) {
+		ret = dquot_alloc_space_nodirty(inode,
+			ocfs2_clusters_to_bytes(osb->sb, clusters_to_alloc));
+		if (ret)
+			goto out_commit;
+	}
 	/*
 	 * We don't want this to fail in ocfs2_write_end(), so do it
 	 * here.
 	 */
-	ret = ocfs2_journal_access(handle, inode, wc->w_di_bh,
-				   OCFS2_JOURNAL_ACCESS_WRITE);
+	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), wc->w_di_bh,
+				      OCFS2_JOURNAL_ACCESS_WRITE);
 	if (ret) {
 		mlog_errno(ret);
-		goto out_commit;
+		goto out_quota;
 	}
 
 	/*
@@ -1742,19 +1833,30 @@ int ocfs2_write_begin_nolock(struct address_space *mapping,
 	 * that we can zero and flush if we error after adding the
 	 * extent.
 	 */
-	ret = ocfs2_grab_pages_for_write(mapping, wc, wc->w_cpos, pos,
-					 clusters_to_alloc + extents_to_split,
-					 mmap_page);
-	if (ret) {
+	ret = ocfs2_grab_pages_for_write(mapping, wc, wc->w_cpos, pos, len,
+					 cluster_of_pages, mmap_page);
+	if (ret && ret != -EAGAIN) {
 		mlog_errno(ret);
-		goto out_commit;
+		goto out_quota;
+	}
+
+	/*
+	 * ocfs2_grab_pages_for_write() returns -EAGAIN if it could not lock
+	 * the target page. In this case, we exit with no error and no target
+	 * page. This will trigger the caller, page_mkwrite(), to re-try
+	 * the operation.
+	 */
+	if (ret == -EAGAIN) {
+		BUG_ON(wc->w_target_page);
+		ret = 0;
+		goto out_quota;
 	}
 
 	ret = ocfs2_write_cluster_by_desc(mapping, data_ac, meta_ac, wc, pos,
 					  len);
 	if (ret) {
 		mlog_errno(ret);
-		goto out_commit;
+		goto out_quota;
 	}
 
 	if (data_ac)
@@ -1766,16 +1868,40 @@ success:
 	*pagep = wc->w_target_page;
 	*fsdata = wc;
 	return 0;
+out_quota:
+	if (clusters_to_alloc)
+		dquot_free_space(inode,
+			  ocfs2_clusters_to_bytes(osb->sb, clusters_to_alloc));
 out_commit:
 	ocfs2_commit_trans(osb, handle);
 
 out:
 	ocfs2_free_write_ctxt(wc);
 
-	if (data_ac)
+	if (data_ac) {
 		ocfs2_free_alloc_context(data_ac);
-	if (meta_ac)
+		data_ac = NULL;
+	}
+	if (meta_ac) {
 		ocfs2_free_alloc_context(meta_ac);
+		meta_ac = NULL;
+	}
+
+	if (ret == -ENOSPC && try_free) {
+		/*
+		 * Try to free some truncate log so that we can have enough
+		 * clusters to allocate.
+		 */
+		try_free = 0;
+
+		ret1 = ocfs2_try_to_free_truncate_log(osb, clusters_need);
+		if (ret1 == 1)
+			goto try_again;
+
+		if (ret1 < 0)
+			mlog_errno(ret1);
+	}
+
 	return ret;
 }
 
@@ -1802,7 +1928,7 @@ static int ocfs2_write_begin(struct file *file, struct address_space *mapping,
 	 */
 	down_write(&OCFS2_I(inode)->ip_alloc_sem);
 
-	ret = ocfs2_write_begin_nolock(mapping, pos, len, flags, pagep,
+	ret = ocfs2_write_begin_nolock(file, mapping, pos, len, flags, pagep,
 				       fsdata, di_bh, NULL);
 	if (ret) {
 		mlog_errno(ret);
@@ -1836,12 +1962,12 @@ static void ocfs2_write_end_inline(struct inode *inode, loff_t pos,
 		}
 	}
 
-	kaddr = kmap_atomic(wc->w_target_page, KM_USER0);
+	kaddr = kmap_atomic(wc->w_target_page);
 	memcpy(di->id2.i_data.id_data + pos, kaddr + pos, *copied);
-	kunmap_atomic(kaddr, KM_USER0);
+	kunmap_atomic(kaddr);
 
-	mlog(0, "Data written to inode at offset %llu. "
-	     "id_count = %u, copied = %u, i_dyn_features = 0x%x\n",
+	trace_ocfs2_write_end_inline(
+	     (unsigned long long)OCFS2_I(inode)->ip_blkno,
 	     (unsigned long long)pos, *copied,
 	     le16_to_cpu(di->id2.i_data.id_count),
 	     le16_to_cpu(di->i_dyn_features));
@@ -1894,17 +2020,16 @@ int ocfs2_write_end_nolock(struct address_space *mapping,
 			to = PAGE_CACHE_SIZE;
 		}
 
-		if (ocfs2_should_order_data(inode))
-			walk_page_buffers(wc->w_handle, page_buffers(tmppage),
-					  from, to, NULL,
-					  ocfs2_journal_dirty_data);
-
-		block_commit_write(tmppage, from, to);
+		if (page_has_buffers(tmppage)) {
+			if (ocfs2_should_order_data(inode))
+				ocfs2_jbd2_file_inode(wc->w_handle, inode);
+			block_commit_write(tmppage, from, to);
+		}
 	}
 
 out_write_size:
 	pos += copied;
-	if (pos > inode->i_size) {
+	if (pos > i_size_read(inode)) {
 		i_size_write(inode, pos);
 		mark_inode_dirty(inode);
 	}
@@ -1913,6 +2038,7 @@ out_write_size:
 	inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 	di->i_mtime = di->i_ctime = cpu_to_le64(inode->i_mtime.tv_sec);
 	di->i_mtime_nsec = di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
+	ocfs2_update_inode_fsync_trans(handle, inode, 1);
 	ocfs2_journal_dirty(handle, wc->w_di_bh);
 
 	ocfs2_commit_trans(osb, handle);
@@ -1940,15 +2066,16 @@ static int ocfs2_write_end(struct file *file, struct address_space *mapping,
 }
 
 const struct address_space_operations ocfs2_aops = {
-	.readpage	= ocfs2_readpage,
-	.readpages	= ocfs2_readpages,
-	.writepage	= ocfs2_writepage,
-	.write_begin	= ocfs2_write_begin,
-	.write_end	= ocfs2_write_end,
-	.bmap		= ocfs2_bmap,
-	.sync_page	= block_sync_page,
-	.direct_IO	= ocfs2_direct_IO,
-	.invalidatepage	= ocfs2_invalidatepage,
-	.releasepage	= ocfs2_releasepage,
-	.migratepage	= buffer_migrate_page,
+	.readpage		= ocfs2_readpage,
+	.readpages		= ocfs2_readpages,
+	.writepage		= ocfs2_writepage,
+	.write_begin		= ocfs2_write_begin,
+	.write_end		= ocfs2_write_end,
+	.bmap			= ocfs2_bmap,
+	.direct_IO		= ocfs2_direct_IO,
+	.invalidatepage		= block_invalidatepage,
+	.releasepage		= ocfs2_releasepage,
+	.migratepage		= buffer_migrate_page,
+	.is_partially_uptodate	= block_is_partially_uptodate,
+	.error_remove_page	= generic_error_remove_page,
 };