diff --git a/drivers/scsi/libata-core.c b/drivers/scsi/libata-core.c
--- a/drivers/scsi/libata-core.c
+++ b/drivers/scsi/libata-core.c
@@ -2467,7 +2467,7 @@ static unsigned long ata_pio_poll(struct
  *	None.  (executing in kernel thread context)
  */
 
-static void ata_pio_complete (struct ata_port *ap)
+static int ata_pio_complete (struct ata_port *ap)
 {
 	struct ata_queued_cmd *qc;
 	u8 drv_stat;
@@ -2486,14 +2486,14 @@ static void ata_pio_complete (struct ata
 		if (drv_stat & (ATA_BUSY | ATA_DRQ)) {
 			ap->pio_task_state = PIO_ST_LAST_POLL;
 			ap->pio_task_timeout = jiffies + ATA_TMOUT_PIO;
-			return;
+			return 0;
 		}
 	}
 
 	drv_stat = ata_wait_idle(ap);
 	if (!ata_ok(drv_stat)) {
 		ap->pio_task_state = PIO_ST_ERR;
-		return;
+		return 0;
 	}
 
 	qc = ata_qc_from_tag(ap, ap->active_tag);
@@ -2502,6 +2502,10 @@ static void ata_pio_complete (struct ata
 	ap->pio_task_state = PIO_ST_IDLE;
 
 	ata_poll_qc_complete(qc, drv_stat);
+
+	/* another command may start at this point */
+
+	return 1;
 }
 
 
@@ -2887,7 +2891,12 @@ static void ata_pio_error(struct ata_por
 static void ata_pio_task(void *_data)
 {
 	struct ata_port *ap = _data;
-	unsigned long timeout = 0;
+	unsigned long timeout;
+	int qc_completed;
+
+fsm_start:
+	timeout = 0;
+	qc_completed = 0;
 
 	switch (ap->pio_task_state) {
 	case PIO_ST_IDLE:
@@ -2898,7 +2907,7 @@ static void ata_pio_task(void *_data)
 		break;
 
 	case PIO_ST_LAST:
-		ata_pio_complete(ap);
+		qc_completed = ata_pio_complete(ap);
 		break;
 
 	case PIO_ST_POLL:
@@ -2915,8 +2924,8 @@ static void ata_pio_task(void *_data)
 	if (timeout)
 		queue_delayed_work(ata_wq, &ap->pio_task,
 				   timeout);
-	else
-		queue_work(ata_wq, &ap->pio_task);
+	else if (!completed)
+		goto fsm_start;
 }
 
 static void atapi_request_sense(struct ata_port *ap, struct ata_device *dev,