diff --git a/block/blk-map.c b/block/blk-map.c
index f5598322954d03f9bb8404dac84289beb83bbe7b..4e17dfd0035d1f889f6e8577b42162c57dd554f1 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -43,6 +43,7 @@ static int __blk_rq_map_user(struct request_queue *q, struct request *rq,
 			     void __user *ubuf, unsigned int len)
 {
 	unsigned long uaddr;
+	unsigned int alignment;
 	struct bio *bio, *orig_bio;
 	int reading, ret;
 
@@ -53,8 +54,8 @@ static int __blk_rq_map_user(struct request_queue *q, struct request *rq,
 	 * direct dma. else, set up kernel bounce buffers
 	 */
 	uaddr = (unsigned long) ubuf;
-	if (!(uaddr & queue_dma_alignment(q)) &&
-	    !(len & queue_dma_alignment(q)))
+	alignment = queue_dma_alignment(q) | q->dma_pad_mask;
+	if (!(uaddr & alignment) && !(len & alignment))
 		bio = bio_map_user(q, NULL, uaddr, len, reading);
 	else
 		bio = bio_copy_user(q, uaddr, len, reading);
@@ -141,15 +142,20 @@ int blk_rq_map_user(struct request_queue *q, struct request *rq,
 
 	/*
 	 * __blk_rq_map_user() copies the buffers if starting address
-	 * or length isn't aligned.  As the copied buffer is always
-	 * page aligned, we know that there's enough room for padding.
-	 * Extend the last bio and update rq->data_len accordingly.
+	 * or length isn't aligned to dma_pad_mask.  As the copied
+	 * buffer is always page aligned, we know that there's enough
+	 * room for padding.  Extend the last bio and update
+	 * rq->data_len accordingly.
 	 *
 	 * On unmap, bio_uncopy_user() will use unmodified
 	 * bio_map_data pointed to by bio->bi_private.
 	 */
-	if (len & queue_dma_alignment(q)) {
-		unsigned int pad_len = (queue_dma_alignment(q) & ~len) + 1;
+	if (len & q->dma_pad_mask) {
+		unsigned int pad_len = (q->dma_pad_mask & ~len) + 1;
+		struct bio *bio = rq->biotail;
+
+		bio->bi_io_vec[bio->bi_vcnt - 1].bv_len += pad_len;
+		bio->bi_size += pad_len;
 
 		rq->extra_len += pad_len;
 	}
diff --git a/block/blk-settings.c b/block/blk-settings.c
index da923fed1f2cac3fdb1c840b81272a48271b66c5..a9f37f530b152bfb8a0c6a091ab5f1fbc342881c 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -292,6 +292,23 @@ void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b)
 }
 EXPORT_SYMBOL(blk_queue_stack_limits);
 
+/**
+ * blk_queue_dma_pad - set pad mask
+ * @q:     the request queue for the device
+ * @mask:  pad mask
+ *
+ * Set pad mask.  Direct IO requests are padded to the mask specified.
+ *
+ * Appending pad buffer to a request modifies ->data_len such that it
+ * includes the pad buffer.  The original requested data length can be
+ * obtained using blk_rq_raw_data_len().
+ **/
+void blk_queue_dma_pad(struct request_queue *q, unsigned int mask)
+{
+	q->dma_pad_mask = mask;
+}
+EXPORT_SYMBOL(blk_queue_dma_pad);
+
 /**
  * blk_queue_dma_drain - Set up a drain buffer for excess dma.
  * @q:  the request queue for the device
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index fe47922dd69ea2261278e8ce15d6f85fd5c9766c..8f0e8f2bc628a283c0000b5cab3e43287aa4bb58 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -862,9 +862,10 @@ static int ata_scsi_dev_config(struct scsi_device *sdev,
 		struct request_queue *q = sdev->request_queue;
 		void *buf;
 
-		/* set the min alignment */
+		/* set the min alignment and padding */
 		blk_queue_update_dma_alignment(sdev->request_queue,
 					       ATA_DMA_PAD_SZ - 1);
+		blk_queue_dma_pad(sdev->request_queue, ATA_DMA_PAD_SZ - 1);
 
 		/* configure draining */
 		buf = kmalloc(ATAPI_MAX_DRAIN, q->bounce_gfp | GFP_KERNEL);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index b72526c13ca04c3ce023791c2a46fe0932992292..6f79d40dd3c01f25c105b9bdae4f5e70a7c88e1e 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -362,6 +362,7 @@ struct request_queue
 	unsigned long		seg_boundary_mask;
 	void			*dma_drain_buffer;
 	unsigned int		dma_drain_size;
+	unsigned int		dma_pad_mask;
 	unsigned int		dma_alignment;
 
 	struct blk_queue_tag	*queue_tags;
@@ -701,6 +702,7 @@ extern void blk_queue_max_hw_segments(struct request_queue *, unsigned short);
 extern void blk_queue_max_segment_size(struct request_queue *, unsigned int);
 extern void blk_queue_hardsect_size(struct request_queue *, unsigned short);
 extern void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b);
+extern void blk_queue_dma_pad(struct request_queue *, unsigned int);
 extern int blk_queue_dma_drain(struct request_queue *q,
 			       dma_drain_needed_fn *dma_drain_needed,
 			       void *buf, unsigned int size);