diff --git a/drivers/scsi/libata-core.c b/drivers/scsi/libata-core.c
index 62340f4ef004..70efde99f652 100644
--- a/drivers/scsi/libata-core.c
+++ b/drivers/scsi/libata-core.c
@@ -2590,7 +2590,7 @@ static void ata_sg_clean(struct ata_queued_cmd *qc)
 	WARN_ON(sg == NULL);
 
 	if (qc->flags & ATA_QCFLAG_SINGLE)
-		WARN_ON(qc->n_elem != 1);
+		WARN_ON(qc->n_elem > 1);
 
 	VPRINTK("unmapping %u sg elements\n", qc->n_elem);
 
@@ -2613,7 +2613,7 @@ static void ata_sg_clean(struct ata_queued_cmd *qc)
 			kunmap_atomic(addr, KM_IRQ0);
 		}
 	} else {
-		if (sg_dma_len(&sg[0]) > 0)
+		if (qc->n_elem)
 			dma_unmap_single(ap->host_set->dev,
 				sg_dma_address(&sg[0]), sg_dma_len(&sg[0]),
 				dir);
@@ -2646,7 +2646,7 @@ static void ata_fill_sg(struct ata_queued_cmd *qc)
 	unsigned int idx;
 
 	WARN_ON(qc->__sg == NULL);
-	WARN_ON(qc->n_elem == 0);
+	WARN_ON(qc->n_elem == 0 && qc->pad_len == 0);
 
 	idx = 0;
 	ata_for_each_sg(sg, qc) {
@@ -2791,6 +2791,7 @@ static int ata_sg_setup_one(struct ata_queued_cmd *qc)
 	int dir = qc->dma_dir;
 	struct scatterlist *sg = qc->__sg;
 	dma_addr_t dma_address;
+	int trim_sg = 0;
 
 	/* we must lengthen transfers to end on a 32-bit boundary */
 	qc->pad_len = sg->length & 3;
@@ -2810,13 +2811,15 @@ static int ata_sg_setup_one(struct ata_queued_cmd *qc)
 		sg_dma_len(psg) = ATA_DMA_PAD_SZ;
 		/* trim sg */
 		sg->length -= qc->pad_len;
+		if (sg->length == 0)
+			trim_sg = 1;
 
 		DPRINTK("padding done, sg->length=%u pad_len=%u\n",
 			sg->length, qc->pad_len);
 	}
 
-	if (!sg->length) {
-		sg_dma_address(sg) = 0;
+	if (trim_sg) {
+		qc->n_elem--;
 		goto skip_map;
 	}
 
@@ -2829,9 +2832,9 @@ static int ata_sg_setup_one(struct ata_queued_cmd *qc)
 	}
 
 	sg_dma_address(sg) = dma_address;
-skip_map:
 	sg_dma_len(sg) = sg->length;
 
+skip_map:
 	DPRINTK("mapped buffer of %d bytes for %s\n", sg_dma_len(sg),
 		qc->tf.flags & ATA_TFLAG_WRITE ? "write" : "read");
 
diff --git a/drivers/scsi/sata_qstor.c b/drivers/scsi/sata_qstor.c
index 286482630be3..9602f43a298e 100644
--- a/drivers/scsi/sata_qstor.c
+++ b/drivers/scsi/sata_qstor.c
@@ -277,7 +277,7 @@ static unsigned int qs_fill_sg(struct ata_queued_cmd *qc)
 	u8 *prd = pp->pkt + QS_CPB_BYTES;
 
 	WARN_ON(qc->__sg == NULL);
-	WARN_ON(qc->n_elem == 0);
+	WARN_ON(qc->n_elem == 0 && qc->pad_len == 0);
 
 	nelem = 0;
 	ata_for_each_sg(sg, qc) {
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 0d6bf50ad029..66b6847225df 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -615,6 +615,16 @@ ata_sg_is_last(struct scatterlist *sg, struct ata_queued_cmd *qc)
 	return 0;
 }
 
+static inline struct scatterlist *
+ata_qc_first_sg(struct ata_queued_cmd *qc)
+{
+	if (qc->n_elem)
+		return qc->__sg;
+	if (qc->pad_len)
+		return &qc->pad_sgent;
+	return NULL;
+}
+
 static inline struct scatterlist *
 ata_qc_next_sg(struct scatterlist *sg, struct ata_queued_cmd *qc)
 {
@@ -622,11 +632,13 @@ ata_qc_next_sg(struct scatterlist *sg, struct ata_queued_cmd *qc)
 		return NULL;
 	if (++sg - qc->__sg < qc->n_elem)
 		return sg;
-	return qc->pad_len ? &qc->pad_sgent : NULL;
+	if (qc->pad_len)
+		return &qc->pad_sgent;
+	return NULL;
 }
 
 #define ata_for_each_sg(sg, qc) \
-	for (sg = qc->__sg; sg; sg = ata_qc_next_sg(sg, qc))
+	for (sg = ata_qc_first_sg(qc); sg; sg = ata_qc_next_sg(sg, qc))
 
 static inline unsigned int ata_tag_valid(unsigned int tag)
 {