1 files changed, 144 insertions, 69 deletions

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index f2fa5e8a582..3e5191f9f39 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -639,8 +639,8 @@ static int ext4_alloc_blocks(handle_t *handle, struct inode *inode,
 	while (target > 0) {
 		count = target;
 		/* allocating blocks for indirect blocks and direct blocks */
-		current_block = ext4_new_meta_blocks(handle, inode,
-							goal, &count, err);
+		current_block = ext4_new_meta_blocks(handle, inode, goal,
+						     0, &count, err);
 		if (*err)
 			goto failed_out;
 
@@ -1930,7 +1930,7 @@ repeat:
 	 * We do still charge estimated metadata to the sb though;
 	 * we cannot afford to run out of free blocks.
 	 */
-	if (ext4_claim_free_blocks(sbi, md_needed + 1)) {
+	if (ext4_claim_free_blocks(sbi, md_needed + 1, 0)) {
 		dquot_release_reservation_block(inode, 1);
 		if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
 			yield();
@@ -2634,7 +2634,7 @@ static int ext4_writepage(struct page *page,
 	struct buffer_head *page_bufs = NULL;
 	struct inode *inode = page->mapping->host;
 
-	trace_ext4_writepage(inode, page);
+	trace_ext4_writepage(page);
 	size = i_size_read(inode);
 	if (page->index == size >> PAGE_CACHE_SHIFT)
 		len = size & ~PAGE_CACHE_MASK;
@@ -2741,7 +2741,7 @@ static int write_cache_pages_da(struct address_space *mapping,
 	index = wbc->range_start >> PAGE_CACHE_SHIFT;
 	end = wbc->range_end >> PAGE_CACHE_SHIFT;
 
-	if (wbc->sync_mode == WB_SYNC_ALL)
+	if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
 		tag = PAGECACHE_TAG_TOWRITE;
 	else
 		tag = PAGECACHE_TAG_DIRTY;
@@ -2796,9 +2796,7 @@ static int write_cache_pages_da(struct address_space *mapping,
 				continue;
 			}
 
-			if (PageWriteback(page))
-				wait_on_page_writeback(page);
-
+			wait_on_page_writeback(page);
 			BUG_ON(PageWriteback(page));
 
 			if (mpd->next_page != page->index)
@@ -2975,7 +2973,7 @@ static int ext4_da_writepages(struct address_space *mapping,
 	}
 
 retry:
-	if (wbc->sync_mode == WB_SYNC_ALL)
+	if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
 		tag_pages_for_writeback(mapping, index, end);
 
 	while (!ret && wbc->nr_to_write > 0) {
@@ -3503,17 +3501,15 @@ retry:
 				 offset, nr_segs,
 				 ext4_get_block, NULL, NULL, 0);
 	else {
-		ret = blockdev_direct_IO(rw, iocb, inode,
-				 inode->i_sb->s_bdev, iov,
-				 offset, nr_segs,
-				 ext4_get_block, NULL);
+		ret = blockdev_direct_IO(rw, iocb, inode, iov,
+				 offset, nr_segs, ext4_get_block);
 
 		if (unlikely((rw & WRITE) && ret < 0)) {
 			loff_t isize = i_size_read(inode);
 			loff_t end = offset + iov_length(iov, nr_segs);
 
 			if (end > isize)
-				vmtruncate(inode, isize);
+				ext4_truncate_failed_write(inode);
 		}
 	}
 	if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
@@ -3577,6 +3573,7 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
 			    ssize_t size, void *private, int ret,
 			    bool is_async)
 {
+	struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode;
         ext4_io_end_t *io_end = iocb->private;
 	struct workqueue_struct *wq;
 	unsigned long flags;
@@ -3598,6 +3595,7 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
 out:
 		if (is_async)
 			aio_complete(iocb, ret, 0);
+		inode_dio_done(inode);
 		return;
 	}
 
@@ -3618,6 +3616,9 @@ out:
 	/* queue the work to convert unwritten extents to written */
 	queue_work(wq, &io_end->work);
 	iocb->private = NULL;
+
+	/* XXX: probably should move into the real I/O completion handler */
+	inode_dio_done(inode);
 }
 
 static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate)
@@ -3750,11 +3751,13 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
 			EXT4_I(inode)->cur_aio_dio = iocb->private;
 		}
 
-		ret = blockdev_direct_IO(rw, iocb, inode,
+		ret = __blockdev_direct_IO(rw, iocb, inode,
 					 inode->i_sb->s_bdev, iov,
 					 offset, nr_segs,
 					 ext4_get_block_write,
-					 ext4_end_io_dio);
+					 ext4_end_io_dio,
+					 NULL,
+					 DIO_LOCKING | DIO_SKIP_HOLES);
 		if (iocb->private)
 			EXT4_I(inode)->cur_aio_dio = NULL;
 		/*
@@ -3916,9 +3919,30 @@ void ext4_set_aops(struct inode *inode)
 int ext4_block_truncate_page(handle_t *handle,
 		struct address_space *mapping, loff_t from)
 {
+	unsigned offset = from & (PAGE_CACHE_SIZE-1);
+	unsigned length;
+	unsigned blocksize;
+	struct inode *inode = mapping->host;
+
+	blocksize = inode->i_sb->s_blocksize;
+	length = blocksize - (offset & (blocksize - 1));
+
+	return ext4_block_zero_page_range(handle, mapping, from, length);
+}
+
+/*
+ * ext4_block_zero_page_range() zeros out a mapping of length 'length'
+ * starting from file offset 'from'.  The range to be zero'd must
+ * be contained with in one block.  If the specified range exceeds
+ * the end of the block it will be shortened to end of the block
+ * that cooresponds to 'from'
+ */
+int ext4_block_zero_page_range(handle_t *handle,
+		struct address_space *mapping, loff_t from, loff_t length)
+{
 	ext4_fsblk_t index = from >> PAGE_CACHE_SHIFT;
 	unsigned offset = from & (PAGE_CACHE_SIZE-1);
-	unsigned blocksize, length, pos;
+	unsigned blocksize, max, pos;
 	ext4_lblk_t iblock;
 	struct inode *inode = mapping->host;
 	struct buffer_head *bh;
@@ -3931,7 +3955,15 @@ int ext4_block_truncate_page(handle_t *handle,
 		return -EINVAL;
 
 	blocksize = inode->i_sb->s_blocksize;
-	length = blocksize - (offset & (blocksize - 1));
+	max = blocksize - (offset & (blocksize - 1));
+
+	/*
+	 * correct length if it does not fall between
+	 * 'from' and the end of the block
+	 */
+	if (length > max || length < 0)
+		length = max;
+
 	iblock = index << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits);
 
 	if (!page_has_buffers(page))
@@ -4380,8 +4412,6 @@ static void ext4_free_branches(handle_t *handle, struct inode *inode,
 
 int ext4_can_truncate(struct inode *inode)
 {
-	if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
-		return 0;
 	if (S_ISREG(inode->i_mode))
 		return 1;
 	if (S_ISDIR(inode->i_mode))
@@ -4392,6 +4422,31 @@ int ext4_can_truncate(struct inode *inode)
 }
 
 /*
+ * ext4_punch_hole: punches a hole in a file by releaseing the blocks
+ * associated with the given offset and length
+ *
+ * @inode:  File inode
+ * @offset: The offset where the hole will begin
+ * @len:    The length of the hole
+ *
+ * Returns: 0 on sucess or negative on failure
+ */
+
+int ext4_punch_hole(struct file *file, loff_t offset, loff_t length)
+{
+	struct inode *inode = file->f_path.dentry->d_inode;
+	if (!S_ISREG(inode->i_mode))
+		return -ENOTSUPP;
+
+	if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
+		/* TODO: Add support for non extent hole punching */
+		return -ENOTSUPP;
+	}
+
+	return ext4_ext_punch_hole(file, offset, length);
+}
+
+/*
  * ext4_truncate()
  *
  * We block out ext4_get_block() block instantiations across the entire
@@ -4617,7 +4672,7 @@ static int __ext4_get_inode_loc(struct inode *inode,
 	/*
 	 * Figure out the offset within the block group inode table
 	 */
-	inodes_per_block = (EXT4_BLOCK_SIZE(sb) / EXT4_INODE_SIZE(sb));
+	inodes_per_block = EXT4_SB(sb)->s_inodes_per_block;
 	inode_offset = ((inode->i_ino - 1) %
 			EXT4_INODES_PER_GROUP(sb));
 	block = ext4_inode_table(sb, gdp) + (inode_offset / inodes_per_block);
@@ -5301,6 +5356,8 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 	}
 
 	if (attr->ia_valid & ATTR_SIZE) {
+		inode_dio_wait(inode);
+
 		if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
 			struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 
@@ -5311,8 +5368,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 
 	if (S_ISREG(inode->i_mode) &&
 	    attr->ia_valid & ATTR_SIZE &&
-	    (attr->ia_size < inode->i_size ||
-	     (ext4_test_inode_flag(inode, EXT4_INODE_EOFBLOCKS)))) {
+	    (attr->ia_size < inode->i_size)) {
 		handle_t *handle;
 
 		handle = ext4_journal_start(inode, 3);
@@ -5346,14 +5402,15 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 				goto err_out;
 			}
 		}
-		/* ext4_truncate will clear the flag */
-		if ((ext4_test_inode_flag(inode, EXT4_INODE_EOFBLOCKS)))
-			ext4_truncate(inode);
 	}
 
-	if ((attr->ia_valid & ATTR_SIZE) &&
-	    attr->ia_size != i_size_read(inode))
-		rc = vmtruncate(inode, attr->ia_size);
+	if (attr->ia_valid & ATTR_SIZE) {
+		if (attr->ia_size != i_size_read(inode)) {
+			truncate_setsize(inode, attr->ia_size);
+			ext4_truncate(inode);
+		} else if (ext4_test_inode_flag(inode, EXT4_INODE_EOFBLOCKS))
+			ext4_truncate(inode);
+	}
 
 	if (!rc) {
 		setattr_copy(inode, attr);
@@ -5683,7 +5740,7 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
  * so would cause a commit on atime updates, which we don't bother doing.
  * We handle synchronous inodes at the highest possible level.
  */
-void ext4_dirty_inode(struct inode *inode)
+void ext4_dirty_inode(struct inode *inode, int flags)
 {
 	handle_t *handle;
 
@@ -5793,66 +5850,84 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	struct page *page = vmf->page;
 	loff_t size;
 	unsigned long len;
-	int ret = -EINVAL;
-	void *fsdata;
+	int ret;
 	struct file *file = vma->vm_file;
 	struct inode *inode = file->f_path.dentry->d_inode;
 	struct address_space *mapping = inode->i_mapping;
+	handle_t *handle;
+	get_block_t *get_block;
+	int retries = 0;
 
 	/*
-	 * Get i_alloc_sem to stop truncates messing with the inode. We cannot
-	 * get i_mutex because we are already holding mmap_sem.
+	 * This check is racy but catches the common case. We rely on
+	 * __block_page_mkwrite() to do a reliable check.
 	 */
-	down_read(&inode->i_alloc_sem);
+	vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
+	/* Delalloc case is easy... */
+	if (test_opt(inode->i_sb, DELALLOC) &&
+	    !ext4_should_journal_data(inode) &&
+	    !ext4_nonda_switch(inode->i_sb)) {
+		do {
+			ret = __block_page_mkwrite(vma, vmf,
+						   ext4_da_get_block_prep);
+		} while (ret == -ENOSPC &&
+		       ext4_should_retry_alloc(inode->i_sb, &retries));
+		goto out_ret;
+	}
+
+	lock_page(page);
 	size = i_size_read(inode);
-	if (page->mapping != mapping || size <= page_offset(page)
-	    || !PageUptodate(page)) {
-		/* page got truncated from under us? */
-		goto out_unlock;
+	/* Page got truncated from under us? */
+	if (page->mapping != mapping || page_offset(page) > size) {
+		unlock_page(page);
+		ret = VM_FAULT_NOPAGE;
+		goto out;
 	}
-	ret = 0;
-	if (PageMappedToDisk(page))
-		goto out_unlock;
 
 	if (page->index == size >> PAGE_CACHE_SHIFT)
 		len = size & ~PAGE_CACHE_MASK;
 	else
 		len = PAGE_CACHE_SIZE;
-
-	lock_page(page);
 	/*
-	 * return if we have all the buffers mapped. This avoid
-	 * the need to call write_begin/write_end which does a
-	 * journal_start/journal_stop which can block and take
-	 * long time
+	 * Return if we have all the buffers mapped. This avoids the need to do
+	 * journal_start/journal_stop which can block and take a long time
 	 */
 	if (page_has_buffers(page)) {
 		if (!walk_page_buffers(NULL, page_buffers(page), 0, len, NULL,
 					ext4_bh_unmapped)) {
-			unlock_page(page);
-			goto out_unlock;
+			/* Wait so that we don't change page under IO */
+			wait_on_page_writeback(page);
+			ret = VM_FAULT_LOCKED;
+			goto out;
 		}
 	}
 	unlock_page(page);
-	/*
-	 * OK, we need to fill the hole... Do write_begin write_end
-	 * to do block allocation/reservation.We are not holding
-	 * inode.i__mutex here. That allow * parallel write_begin,
-	 * write_end call. lock_page prevent this from happening
-	 * on the same page though
-	 */
-	ret = mapping->a_ops->write_begin(file, mapping, page_offset(page),
-			len, AOP_FLAG_UNINTERRUPTIBLE, &page, &fsdata);
-	if (ret < 0)
-		goto out_unlock;
-	ret = mapping->a_ops->write_end(file, mapping, page_offset(page),
-			len, len, page, fsdata);
-	if (ret < 0)
-		goto out_unlock;
-	ret = 0;
-out_unlock:
-	if (ret)
+	/* OK, we need to fill the hole... */
+	if (ext4_should_dioread_nolock(inode))
+		get_block = ext4_get_block_write;
+	else
+		get_block = ext4_get_block;
+retry_alloc:
+	handle = ext4_journal_start(inode, ext4_writepage_trans_blocks(inode));
+	if (IS_ERR(handle)) {
 		ret = VM_FAULT_SIGBUS;
-	up_read(&inode->i_alloc_sem);
+		goto out;
+	}
+	ret = __block_page_mkwrite(vma, vmf, get_block);
+	if (!ret && ext4_should_journal_data(inode)) {
+		if (walk_page_buffers(handle, page_buffers(page), 0,
+			  PAGE_CACHE_SIZE, NULL, do_journal_get_write_access)) {
+			unlock_page(page);
+			ret = VM_FAULT_SIGBUS;
+			goto out;
+		}
+		ext4_set_inode_state(inode, EXT4_STATE_JDATA);
+	}
+	ext4_journal_stop(handle);
+	if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
+		goto retry_alloc;
+out_ret:
+	ret = block_page_mkwrite_return(ret);
+out:
 	return ret;
 }