Merge branch 'master'
diff --git a/drivers/scsi/libata-core.c b/drivers/scsi/libata-core.c
index f53d7b8..ab8b735 100644
--- a/drivers/scsi/libata-core.c
+++ b/drivers/scsi/libata-core.c
@@ -73,6 +73,7 @@
 				u8 *xfer_mode_out,
 				unsigned int *xfer_shift_out);
 static void __ata_qc_complete(struct ata_queued_cmd *qc);
+static void ata_pio_error(struct ata_port *ap);
 
 static unsigned int ata_unique_id = 1;
 static struct workqueue_struct *ata_wq;
@@ -1334,6 +1335,9 @@
 		ap->cdb_len = (unsigned int) rc;
 		ap->host->max_cmd_len = (unsigned char) ap->cdb_len;
 
+		if (ata_id_cdb_intr(dev->id))
+			dev->flags |= ATA_DFLAG_CDB_INTR;
+
 		/* print device info to dmesg */
 		printk(KERN_INFO "ata%u: dev %u ATAPI, max %s\n",
 		       ap->id, device,
@@ -2693,7 +2697,6 @@
 	unsigned long flags;
 
 	spin_lock_irqsave(&ap->host_set->lock, flags);
-	ap->flags &= ~ATA_FLAG_NOINTR;
 	ata_irq_on(ap);
 	ata_qc_complete(qc, drv_stat);
 	spin_unlock_irqrestore(&ap->host_set->lock, flags);
@@ -2957,7 +2960,23 @@
 	page = nth_page(page, (offset >> PAGE_SHIFT));
 	offset %= PAGE_SIZE;
 
-	buf = kmap(page) + offset;
+	DPRINTK("data %s\n", qc->tf.flags & ATA_TFLAG_WRITE ? "write" : "read");
+
+	if (PageHighMem(page)) {
+		unsigned long flags;
+
+		local_irq_save(flags);
+		buf = kmap_atomic(page, KM_IRQ0);
+
+		/* do the actual data transfer */
+		ata_data_xfer(ap, buf + offset, ATA_SECT_SIZE, do_write);
+
+		kunmap_atomic(buf, KM_IRQ0);
+		local_irq_restore(flags);
+	} else {
+		buf = page_address(page);
+		ata_data_xfer(ap, buf + offset, ATA_SECT_SIZE, do_write);
+	}
 
 	qc->cursect++;
 	qc->cursg_ofs++;
@@ -2966,14 +2985,114 @@
 		qc->cursg++;
 		qc->cursg_ofs = 0;
 	}
+}
 
-	DPRINTK("data %s\n", qc->tf.flags & ATA_TFLAG_WRITE ? "write" : "read");
+/**
+ *	atapi_send_cdb - Write CDB bytes to hardware
+ *	@ap: Port to which ATAPI device is attached.
+ *	@qc: Taskfile currently active
+ *
+ *	When device has indicated its readiness to accept
+ *	a CDB, this function is called.  Send the CDB.
+ *
+ *	LOCKING:
+ *	caller.
+ */
 
-	/* do the actual data transfer */
-	do_write = (qc->tf.flags & ATA_TFLAG_WRITE);
-	ata_data_xfer(ap, buf, ATA_SECT_SIZE, do_write);
+static void atapi_send_cdb(struct ata_port *ap, struct ata_queued_cmd *qc)
+{
+	/* send SCSI cdb */
+	DPRINTK("send cdb\n");
+	assert(ap->cdb_len >= 12);
 
-	kunmap(page);
+	ata_data_xfer(ap, qc->cdb, ap->cdb_len, 1);
+	ata_altstatus(ap); /* flush */
+
+	switch (qc->tf.protocol) {
+	case ATA_PROT_ATAPI:
+		ap->hsm_task_state = HSM_ST;
+		break;
+	case ATA_PROT_ATAPI_NODATA:
+		ap->hsm_task_state = HSM_ST_LAST;
+		break;
+	case ATA_PROT_ATAPI_DMA:
+		ap->hsm_task_state = HSM_ST_LAST;
+		/* initiate bmdma */
+		ap->ops->bmdma_start(qc);
+		break;
+	}
+}
+
+/**
+ *	ata_dataout_task - Write first data block to hardware
+ *	@_data: Port to which ATA/ATAPI device is attached.
+ *
+ *	When device has indicated its readiness to accept
+ *	the data, this function sends out the CDB or 
+ *	the first data block by PIO.
+ *	After this, 
+ *	  - If polling, ata_pio_task() handles the rest.
+ *	  - Otherwise, interrupt handler takes over.
+ *
+ *	LOCKING:
+ *	Kernel thread context (may sleep)
+ */
+
+static void ata_dataout_task(void *_data)
+{
+	struct ata_port *ap = _data;
+	struct ata_queued_cmd *qc;
+	u8 status;
+	unsigned long flags;
+
+	qc = ata_qc_from_tag(ap, ap->active_tag);
+	assert(qc != NULL);
+	assert(qc->flags & ATA_QCFLAG_ACTIVE);
+
+	/* sleep-wait for BSY to clear */
+	DPRINTK("busy wait\n");
+	if (ata_busy_sleep(ap, ATA_TMOUT_DATAOUT_QUICK, ATA_TMOUT_DATAOUT))
+		goto err_out;
+
+	/* make sure DRQ is set */
+	status = ata_chk_status(ap);
+	if ((status & (ATA_BUSY | ATA_DRQ)) != ATA_DRQ)
+		goto err_out;
+
+	/* Send the CDB (atapi) or the first data block (ata pio out).
+	 * During the state transition, interrupt handler shouldn't
+	 * be invoked before the data transfer is complete and
+	 * hsm_task_state is changed. Hence, the following locking.
+	 */
+	spin_lock_irqsave(&ap->host_set->lock, flags);
+
+	if (qc->tf.protocol == ATA_PROT_PIO) {
+		/* PIO data out protocol.
+		 * send first data block.
+		 */
+
+		/* ata_pio_sector() might change the state to HSM_ST_LAST.
+		 * so, the state is changed here before ata_pio_sector().
+		 */
+		ap->hsm_task_state = HSM_ST;
+		ata_pio_sector(qc);
+		ata_altstatus(ap); /* flush */
+	} else
+		/* send CDB */
+		atapi_send_cdb(ap, qc);
+
+	/* if polling, ata_pio_task() handles the rest.
+	 * otherwise, interrupt handler takes over from here.
+	 */
+	if (qc->tf.flags & ATA_TFLAG_POLLING)
+		queue_work(ata_wq, &ap->pio_task);
+
+	spin_unlock_irqrestore(&ap->host_set->lock, flags);
+
+	return;
+
+err_out:
+	ata_pio_error(ap);
 }
 
 /**
@@ -3039,7 +3158,23 @@
 	/* don't cross page boundaries */
 	count = min(count, (unsigned int)PAGE_SIZE - offset);
 
-	buf = kmap(page) + offset;
+	DPRINTK("data %s\n", qc->tf.flags & ATA_TFLAG_WRITE ? "write" : "read");
+
+	if (PageHighMem(page)) {
+		unsigned long flags;
+
+		local_irq_save(flags);
+		buf = kmap_atomic(page, KM_IRQ0);
+
+		/* do the actual data transfer */
+		ata_data_xfer(ap, buf + offset, count, do_write);
+
+		kunmap_atomic(buf, KM_IRQ0);
+		local_irq_restore(flags);
+	} else {
+		buf = page_address(page);
+		ata_data_xfer(ap, buf + offset, count, do_write);
+	}
 
 	bytes -= count;
 	qc->curbytes += count;
@@ -3050,13 +3185,6 @@
 		qc->cursg_ofs = 0;
 	}
 
-	DPRINTK("data %s\n", qc->tf.flags & ATA_TFLAG_WRITE ? "write" : "read");
-
-	/* do the actual data transfer */
-	ata_data_xfer(ap, buf, count, do_write);
-
-	kunmap(page);
-
 	if (bytes)
 		goto next_sg;
 }
@@ -3093,6 +3221,8 @@
 	if (do_write != i_write)
 		goto err_out;
 
+	VPRINTK("ata%u: xfering %d bytes\n", ap->id, bytes);
+
 	__atapi_pio_bytes(qc, bytes);
 
 	return;
@@ -3293,6 +3423,8 @@
 		printk(KERN_ERR "ata%u: command 0x%x timeout, stat 0x%x host_stat 0x%x\n",
 		       ap->id, qc->tf.command, drv_stat, host_stat);
 
+		ap->hsm_task_state = HSM_ST_IDLE;
+
 		/* complete taskfile transaction */
 		ata_qc_complete(qc, drv_stat);
 		break;
@@ -3578,43 +3710,103 @@
 {
 	struct ata_port *ap = qc->ap;
 
+	/* Use polling pio if the LLD doesn't handle
+	 * interrupt driven pio and atapi CDB interrupt.
+	 */
+	if (ap->flags & ATA_FLAG_PIO_POLLING) {
+		switch (qc->tf.protocol) {
+		case ATA_PROT_PIO:
+		case ATA_PROT_ATAPI:
+		case ATA_PROT_ATAPI_NODATA:
+			qc->tf.flags |= ATA_TFLAG_POLLING;
+			break;
+		case ATA_PROT_ATAPI_DMA:
+			if (qc->dev->flags & ATA_DFLAG_CDB_INTR)
+				BUG();
+			break;
+		default:
+			break;
+		}
+	}
+
+	/* select the device */
 	ata_dev_select(ap, qc->dev->devno, 1, 0);
 
+	/* start the command */
 	switch (qc->tf.protocol) {
 	case ATA_PROT_NODATA:
+		if (qc->tf.flags & ATA_TFLAG_POLLING)
+			ata_qc_set_polling(qc);
+
 		ata_tf_to_host_nolock(ap, &qc->tf);
+		ap->hsm_task_state = HSM_ST_LAST;
+
+		if (qc->tf.flags & ATA_TFLAG_POLLING)
+			queue_work(ata_wq, &ap->pio_task);
+
 		break;
 
 	case ATA_PROT_DMA:
+		assert(!(qc->tf.flags & ATA_TFLAG_POLLING));
+
 		ap->ops->tf_load(ap, &qc->tf);	 /* load tf registers */
 		ap->ops->bmdma_setup(qc);	    /* set up bmdma */
 		ap->ops->bmdma_start(qc);	    /* initiate bmdma */
+		ap->hsm_task_state = HSM_ST_LAST;
 		break;
 
-	case ATA_PROT_PIO: /* load tf registers, initiate polling pio */
-		ata_qc_set_polling(qc);
+	case ATA_PROT_PIO:
+		if (qc->tf.flags & ATA_TFLAG_POLLING)
+			ata_qc_set_polling(qc);
+
 		ata_tf_to_host_nolock(ap, &qc->tf);
-		ap->hsm_task_state = HSM_ST;
-		queue_work(ata_wq, &ap->pio_task);
+
+		if (qc->tf.flags & ATA_TFLAG_WRITE) {
+			/* PIO data out protocol */
+			ap->hsm_task_state = HSM_ST_FIRST;
+			queue_work(ata_wq, &ap->dataout_task);
+
+			/* always send first data block using
+			 * the ata_dataout_task() codepath.
+			 */
+		} else {
+			/* PIO data in protocol */
+			ap->hsm_task_state = HSM_ST;
+
+			if (qc->tf.flags & ATA_TFLAG_POLLING)
+				queue_work(ata_wq, &ap->pio_task);
+
+			/* if polling, ata_pio_task() handles the rest.
+			 * otherwise, interrupt handler takes over from here.
+			 */
+		}
+
 		break;
 
 	case ATA_PROT_ATAPI:
-		ata_qc_set_polling(qc);
-		ata_tf_to_host_nolock(ap, &qc->tf);
-		queue_work(ata_wq, &ap->packet_task);
-		break;
-
 	case ATA_PROT_ATAPI_NODATA:
-		ap->flags |= ATA_FLAG_NOINTR;
+		if (qc->tf.flags & ATA_TFLAG_POLLING)
+			ata_qc_set_polling(qc);
+
 		ata_tf_to_host_nolock(ap, &qc->tf);
-		queue_work(ata_wq, &ap->packet_task);
+		ap->hsm_task_state = HSM_ST_FIRST;
+
+		/* send cdb by polling if no cdb interrupt */
+		if ((!(qc->dev->flags & ATA_DFLAG_CDB_INTR)) ||
+		    (qc->tf.flags & ATA_TFLAG_POLLING))
+			queue_work(ata_wq, &ap->dataout_task);
 		break;
 
 	case ATA_PROT_ATAPI_DMA:
-		ap->flags |= ATA_FLAG_NOINTR;
+		assert(!(qc->tf.flags & ATA_TFLAG_POLLING));
+
 		ap->ops->tf_load(ap, &qc->tf);	 /* load tf registers */
 		ap->ops->bmdma_setup(qc);	    /* set up bmdma */
-		queue_work(ata_wq, &ap->packet_task);
+		ap->hsm_task_state = HSM_ST_FIRST;
+
+		/* send cdb by polling if no cdb interrupt */
+		if (!(qc->dev->flags & ATA_DFLAG_CDB_INTR))
+			queue_work(ata_wq, &ap->dataout_task);
 		break;
 
 	default:
@@ -3875,47 +4067,142 @@
 inline unsigned int ata_host_intr (struct ata_port *ap,
 				   struct ata_queued_cmd *qc)
 {
-	u8 status, host_stat;
+	u8 status, host_stat = 0;
 
-	switch (qc->tf.protocol) {
+	VPRINTK("ata%u: protocol %d task_state %d\n",
+		ap->id, qc->tf.protocol, ap->hsm_task_state);
 
-	case ATA_PROT_DMA:
-	case ATA_PROT_ATAPI_DMA:
-	case ATA_PROT_ATAPI:
-		/* check status of DMA engine */
-		host_stat = ap->ops->bmdma_status(ap);
-		VPRINTK("ata%u: host_stat 0x%X\n", ap->id, host_stat);
-
-		/* if it's not our irq... */
-		if (!(host_stat & ATA_DMA_INTR))
+	/* Check whether we are expecting interrupt in this state */
+	switch (ap->hsm_task_state) {
+	case HSM_ST_FIRST:
+		/* Check the ATA_DFLAG_CDB_INTR flag is enough here.
+		 * The flag was turned on only for atapi devices.
+		 * No need to check is_atapi_taskfile(&qc->tf) again.
+		 */
+		if (!(qc->dev->flags & ATA_DFLAG_CDB_INTR))
 			goto idle_irq;
+		break;
+	case HSM_ST_LAST:
+		if (qc->tf.protocol == ATA_PROT_DMA ||
+		    qc->tf.protocol == ATA_PROT_ATAPI_DMA) {
+			/* check status of DMA engine */
+			host_stat = ap->ops->bmdma_status(ap);
+			VPRINTK("ata%u: host_stat 0x%X\n", ap->id, host_stat);
 
-		/* before we do anything else, clear DMA-Start bit */
-		ap->ops->bmdma_stop(qc);
+			/* if it's not our irq... */
+			if (!(host_stat & ATA_DMA_INTR))
+				goto idle_irq;
 
-		/* fall through */
+			/* before we do anything else, clear DMA-Start bit */
+			ap->ops->bmdma_stop(qc);
+		}
+		break;
+	case HSM_ST:
+		break;
+	default:
+		goto idle_irq;
+	}
 
-	case ATA_PROT_ATAPI_NODATA:
-	case ATA_PROT_NODATA:
-		/* check altstatus */
-		status = ata_altstatus(ap);
-		if (status & ATA_BUSY)
-			goto idle_irq;
+	/* check altstatus */
+	status = ata_altstatus(ap);
+	if (status & ATA_BUSY)
+		goto idle_irq;
 
-		/* check main status, clearing INTRQ */
-		status = ata_chk_status(ap);
-		if (unlikely(status & ATA_BUSY))
-			goto idle_irq;
-		DPRINTK("ata%u: protocol %d (dev_stat 0x%X)\n",
-			ap->id, qc->tf.protocol, status);
+	/* check main status, clearing INTRQ */
+	status = ata_chk_status(ap);
+	if (unlikely(status & ATA_BUSY))
+		goto idle_irq;
 
-		/* ack bmdma irq events */
-		ap->ops->irq_clear(ap);
+	DPRINTK("ata%u: protocol %d task_state %d (dev_stat 0x%X)\n",
+		ap->id, qc->tf.protocol, ap->hsm_task_state, status);
+
+	/* ack bmdma irq events */
+	ap->ops->irq_clear(ap);
+
+	/* check error */
+	if (unlikely((status & ATA_ERR) || (host_stat & ATA_DMA_ERR)))
+		ap->hsm_task_state = HSM_ST_ERR;
+
+fsm_start:
+	switch (ap->hsm_task_state) {
+	case HSM_ST_FIRST:
+		/* Some pre-ATAPI-4 devices assert INTRQ 
+		 * at this state when ready to receive CDB.
+		 */
+
+		/* check device status */
+		if (unlikely((status & (ATA_BUSY | ATA_DRQ)) != ATA_DRQ)) {
+			/* Wrong status. Let EH handle this */
+			ap->hsm_task_state = HSM_ST_ERR;
+			goto fsm_start;
+		}
+
+		atapi_send_cdb(ap, qc);
+
+		break;
+
+	case HSM_ST:
+		/* complete command or read/write the data register */
+		if (qc->tf.protocol == ATA_PROT_ATAPI) {
+			/* ATAPI PIO protocol */
+			if ((status & ATA_DRQ) == 0) {
+				/* no more data to transfer */
+				ap->hsm_task_state = HSM_ST_LAST;
+				goto fsm_start;
+			}
+			
+			atapi_pio_bytes(qc);
+
+			if (unlikely(ap->hsm_task_state == HSM_ST_ERR))
+				/* bad ireason reported by device */
+				goto fsm_start;
+
+		} else {
+			/* ATA PIO protocol */
+			if (unlikely((status & ATA_DRQ) == 0)) {
+				/* handle BSY=0, DRQ=0 as error */
+				ap->hsm_task_state = HSM_ST_ERR;
+				goto fsm_start;
+			}
+
+			ata_pio_sector(qc);
+
+			if (ap->hsm_task_state == HSM_ST_LAST &&
+			    (!(qc->tf.flags & ATA_TFLAG_WRITE))) {
+				/* all data read */
+				ata_altstatus(ap);
+				status = ata_chk_status(ap);
+				goto fsm_start;
+			}
+		}
+
+		ata_altstatus(ap); /* flush */
+		break;
+
+	case HSM_ST_LAST:
+		if (unlikely(status & ATA_DRQ)) {
+			/* handle DRQ=1 as error */
+			ap->hsm_task_state = HSM_ST_ERR;
+			goto fsm_start;
+		}
+
+		/* no more data to transfer */
+		DPRINTK("ata%u: command complete, drv_stat 0x%x\n",
+			ap->id, status);
+
+		ap->hsm_task_state = HSM_ST_IDLE;
 
 		/* complete taskfile transaction */
 		ata_qc_complete(qc, status);
 		break;
 
+	case HSM_ST_ERR:
+		printk(KERN_ERR "ata%u: command error, drv_stat 0x%x host_stat 0x%x\n",
+		       ap->id, status, host_stat);
+
+		ap->hsm_task_state = HSM_ST_IDLE;
+		ata_qc_complete(qc, status | ATA_ERR);
+		break;
 	default:
 		goto idle_irq;
 	}
@@ -3966,11 +4253,11 @@
 
 		ap = host_set->ports[i];
 		if (ap &&
-		    !(ap->flags & (ATA_FLAG_PORT_DISABLED | ATA_FLAG_NOINTR))) {
+		    !(ap->flags & ATA_FLAG_PORT_DISABLED)) {
 			struct ata_queued_cmd *qc;
 
 			qc = ata_qc_from_tag(ap, ap->active_tag);
-			if (qc && (!(qc->tf.ctl & ATA_NIEN)) &&
+			if (qc && (!(qc->tf.flags & ATA_TFLAG_POLLING)) &&
 			    (qc->flags & ATA_QCFLAG_ACTIVE))
 				handled |= ata_host_intr(ap, qc);
 		}
@@ -3982,75 +4269,6 @@
 }
 
 /**
- *	atapi_packet_task - Write CDB bytes to hardware
- *	@_data: Port to which ATAPI device is attached.
- *
- *	When device has indicated its readiness to accept
- *	a CDB, this function is called.  Send the CDB.
- *	If DMA is to be performed, exit immediately.
- *	Otherwise, we are in polling mode, so poll
- *	status under operation succeeds or fails.
- *
- *	LOCKING:
- *	Kernel thread context (may sleep)
- */
-
-static void atapi_packet_task(void *_data)
-{
-	struct ata_port *ap = _data;
-	struct ata_queued_cmd *qc;
-	u8 status;
-
-	qc = ata_qc_from_tag(ap, ap->active_tag);
-	assert(qc != NULL);
-	assert(qc->flags & ATA_QCFLAG_ACTIVE);
-
-	/* sleep-wait for BSY to clear */
-	DPRINTK("busy wait\n");
-	if (ata_busy_sleep(ap, ATA_TMOUT_CDB_QUICK, ATA_TMOUT_CDB))
-		goto err_out;
-
-	/* make sure DRQ is set */
-	status = ata_chk_status(ap);
-	if ((status & (ATA_BUSY | ATA_DRQ)) != ATA_DRQ)
-		goto err_out;
-
-	/* send SCSI cdb */
-	DPRINTK("send cdb\n");
-	assert(ap->cdb_len >= 12);
-
-	if (qc->tf.protocol == ATA_PROT_ATAPI_DMA ||
-	    qc->tf.protocol == ATA_PROT_ATAPI_NODATA) {
-		unsigned long flags;
-
-		/* Once we're done issuing command and kicking bmdma,
-		 * irq handler takes over.  To not lose irq, we need
-		 * to clear NOINTR flag before sending cdb, but
-		 * interrupt handler shouldn't be invoked before we're
-		 * finished.  Hence, the following locking.
-		 */
-		spin_lock_irqsave(&ap->host_set->lock, flags);
-		ap->flags &= ~ATA_FLAG_NOINTR;
-		ata_data_xfer(ap, qc->cdb, ap->cdb_len, 1);
-		if (qc->tf.protocol == ATA_PROT_ATAPI_DMA)
-			ap->ops->bmdma_start(qc);	/* initiate bmdma */
-		spin_unlock_irqrestore(&ap->host_set->lock, flags);
-	} else {
-		ata_data_xfer(ap, qc->cdb, ap->cdb_len, 1);
-
-		/* PIO commands are handled by polling */
-		ap->hsm_task_state = HSM_ST;
-		queue_work(ata_wq, &ap->pio_task);
-	}
-
-	return;
-
-err_out:
-	ata_poll_qc_complete(qc, ATA_ERR);
-}
-
-
-/**
  *	ata_port_start - Set port up for dma.
  *	@ap: Port to initialize
  *
@@ -4170,7 +4388,7 @@
 	ap->active_tag = ATA_TAG_POISON;
 	ap->last_ctl = 0xFF;
 
-	INIT_WORK(&ap->packet_task, atapi_packet_task, ap);
+	INIT_WORK(&ap->dataout_task, ata_dataout_task, ap);
 	INIT_WORK(&ap->pio_task, ata_pio_task, ap);
 
 	for (i = 0; i < ATA_MAX_DEVICES; i++)
diff --git a/drivers/scsi/pdc_adma.c b/drivers/scsi/pdc_adma.c
index 9820f27..1701e31 100644
--- a/drivers/scsi/pdc_adma.c
+++ b/drivers/scsi/pdc_adma.c
@@ -481,13 +481,13 @@
 	for (port_no = 0; port_no < host_set->n_ports; ++port_no) {
 		struct ata_port *ap;
 		ap = host_set->ports[port_no];
-		if (ap && (!(ap->flags & (ATA_FLAG_PORT_DISABLED | ATA_FLAG_NOINTR)))) {
+		if (ap && (!(ap->flags & ATA_FLAG_PORT_DISABLED))) {
 			struct ata_queued_cmd *qc;
 			struct adma_port_priv *pp = ap->private_data;
 			if (!pp || pp->state != adma_state_mmio)
 				continue;
 			qc = ata_qc_from_tag(ap, ap->active_tag);
-			if (qc && (!(qc->tf.ctl & ATA_NIEN))) {
+			if (qc && (!(qc->tf.flags & ATA_TFLAG_POLLING))) {
 
 				/* check main status, clearing INTRQ */
 				u8 status = ata_chk_status(ap);
diff --git a/drivers/scsi/sata_mv.c b/drivers/scsi/sata_mv.c
index 422e0b6..c40e9843 100644
--- a/drivers/scsi/sata_mv.c
+++ b/drivers/scsi/sata_mv.c
@@ -87,7 +87,8 @@
 	MV_FLAG_IRQ_COALESCE	= (1 << 29),  /* IRQ coalescing capability */
 	MV_FLAG_GLBL_SFT_RST	= (1 << 28),  /* Global Soft Reset support */
 	MV_COMMON_FLAGS		= (ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
-				   ATA_FLAG_SATA_RESET | ATA_FLAG_MMIO),
+				   ATA_FLAG_SATA_RESET | ATA_FLAG_MMIO |
+				   ATA_FLAG_PIO_POLLING),
 	MV_6XXX_FLAGS		= (MV_FLAG_IRQ_COALESCE | 
 				   MV_FLAG_GLBL_SFT_RST),
 
diff --git a/drivers/scsi/sata_nv.c b/drivers/scsi/sata_nv.c
index 1a56d6c..73c2c5a 100644
--- a/drivers/scsi/sata_nv.c
+++ b/drivers/scsi/sata_nv.c
@@ -304,11 +304,11 @@
 
 		ap = host_set->ports[i];
 		if (ap &&
-		    !(ap->flags & (ATA_FLAG_PORT_DISABLED | ATA_FLAG_NOINTR))) {
+		    !(ap->flags & ATA_FLAG_PORT_DISABLED)) {
 			struct ata_queued_cmd *qc;
 
 			qc = ata_qc_from_tag(ap, ap->active_tag);
-			if (qc && (!(qc->tf.ctl & ATA_NIEN)))
+			if (qc && (!(qc->tf.flags & ATA_TFLAG_POLLING)))
 				handled += ata_host_intr(ap, qc);
 		}
 
diff --git a/drivers/scsi/sata_promise.c b/drivers/scsi/sata_promise.c
index eee93b0..9ca07be 100644
--- a/drivers/scsi/sata_promise.c
+++ b/drivers/scsi/sata_promise.c
@@ -162,7 +162,8 @@
 	{
 		.sht		= &pdc_ata_sht,
 		.host_flags	= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
-				  ATA_FLAG_SRST | ATA_FLAG_MMIO,
+				  ATA_FLAG_SRST | ATA_FLAG_MMIO |
+				  ATA_FLAG_PIO_POLLING,
 		.pio_mask	= 0x1f, /* pio0-4 */
 		.mwdma_mask	= 0x07, /* mwdma0-2 */
 		.udma_mask	= 0x7f, /* udma0-6 ; FIXME */
@@ -173,7 +174,8 @@
 	{
 		.sht		= &pdc_ata_sht,
 		.host_flags	= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
-				  ATA_FLAG_SRST | ATA_FLAG_MMIO,
+				  ATA_FLAG_SRST | ATA_FLAG_MMIO |
+				  ATA_FLAG_PIO_POLLING,
 		.pio_mask	= 0x1f, /* pio0-4 */
 		.mwdma_mask	= 0x07, /* mwdma0-2 */
 		.udma_mask	= 0x7f, /* udma0-6 ; FIXME */
@@ -184,7 +186,8 @@
 	{
 		.sht		= &pdc_ata_sht,
 		.host_flags	= ATA_FLAG_NO_LEGACY | ATA_FLAG_SRST |
-				  ATA_FLAG_MMIO | ATA_FLAG_SLAVE_POSS,
+				  ATA_FLAG_MMIO | ATA_FLAG_SLAVE_POSS |
+				  ATA_FLAG_PIO_POLLING,
 		.pio_mask	= 0x1f, /* pio0-4 */
 		.mwdma_mask	= 0x07, /* mwdma0-2 */
 		.udma_mask	= 0x7f, /* udma0-6 ; FIXME */
@@ -493,11 +496,11 @@
 		ap = host_set->ports[i];
 		tmp = mask & (1 << (i + 1));
 		if (tmp && ap &&
-		    !(ap->flags & (ATA_FLAG_PORT_DISABLED | ATA_FLAG_NOINTR))) {
+		    !(ap->flags & ATA_FLAG_PORT_DISABLED)) {
 			struct ata_queued_cmd *qc;
 
 			qc = ata_qc_from_tag(ap, ap->active_tag);
-			if (qc && (!(qc->tf.ctl & ATA_NIEN)))
+			if (qc && (!(qc->tf.flags & ATA_TFLAG_POLLING)))
 				handled += pdc_host_intr(ap, qc);
 		}
 	}
diff --git a/drivers/scsi/sata_qstor.c b/drivers/scsi/sata_qstor.c
index 250dafa..6e0c749 100644
--- a/drivers/scsi/sata_qstor.c
+++ b/drivers/scsi/sata_qstor.c
@@ -177,7 +177,7 @@
 		.host_flags	= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
 				  ATA_FLAG_SATA_RESET |
 				  //FIXME ATA_FLAG_SRST |
-				  ATA_FLAG_MMIO,
+				  ATA_FLAG_MMIO | ATA_FLAG_PIO_POLLING,
 		.pio_mask	= 0x10, /* pio4 */
 		.udma_mask	= 0x7f, /* udma0-6 */
 		.port_ops	= &qs_ata_ops,
@@ -391,14 +391,13 @@
 			DPRINTK("SFF=%08x%08x: sCHAN=%u sHST=%d sDST=%02x\n",
 					sff1, sff0, port_no, sHST, sDST);
 			handled = 1;
-			if (ap && !(ap->flags &
-				    (ATA_FLAG_PORT_DISABLED|ATA_FLAG_NOINTR))) {
+			if (ap && !(ap->flags & ATA_FLAG_PORT_DISABLED)) {
 				struct ata_queued_cmd *qc;
 				struct qs_port_priv *pp = ap->private_data;
 				if (!pp || pp->state != qs_state_pkt)
 					continue;
 				qc = ata_qc_from_tag(ap, ap->active_tag);
-				if (qc && (!(qc->tf.ctl & ATA_NIEN))) {
+				if (qc && (!(qc->tf.flags & ATA_TFLAG_POLLING))) {
 					switch (sHST) {
 					case 0: /* sucessful CPB */
 					case 3: /* device error */
@@ -424,13 +423,13 @@
 		struct ata_port *ap;
 		ap = host_set->ports[port_no];
 		if (ap &&
-		    !(ap->flags & (ATA_FLAG_PORT_DISABLED | ATA_FLAG_NOINTR))) {
+		    !(ap->flags & ATA_FLAG_PORT_DISABLED)) {
 			struct ata_queued_cmd *qc;
 			struct qs_port_priv *pp = ap->private_data;
 			if (!pp || pp->state != qs_state_mmio)
 				continue;
 			qc = ata_qc_from_tag(ap, ap->active_tag);
-			if (qc && (!(qc->tf.ctl & ATA_NIEN))) {
+			if (qc && (!(qc->tf.flags & ATA_TFLAG_POLLING))) {
 
 				/* check main status, clearing INTRQ */
 				u8 status = ata_chk_status(ap);
diff --git a/drivers/scsi/sata_sx4.c b/drivers/scsi/sata_sx4.c
index af08f4f..1908c58 100644
--- a/drivers/scsi/sata_sx4.c
+++ b/drivers/scsi/sata_sx4.c
@@ -219,7 +219,8 @@
 	{
 		.sht		= &pdc_sata_sht,
 		.host_flags	= ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY |
-				  ATA_FLAG_SRST | ATA_FLAG_MMIO,
+				  ATA_FLAG_SRST | ATA_FLAG_MMIO |
+				  ATA_FLAG_PIO_POLLING,
 		.pio_mask	= 0x1f, /* pio0-4 */
 		.mwdma_mask	= 0x07, /* mwdma0-2 */
 		.udma_mask	= 0x7f, /* udma0-6 ; FIXME */
@@ -832,11 +833,11 @@
 		tmp = mask & (1 << i);
 		VPRINTK("seq %u, port_no %u, ap %p, tmp %x\n", i, port_no, ap, tmp);
 		if (tmp && ap &&
-		    !(ap->flags & (ATA_FLAG_PORT_DISABLED | ATA_FLAG_NOINTR))) {
+		    !(ap->flags & ATA_FLAG_PORT_DISABLED)) {
 			struct ata_queued_cmd *qc;
 
 			qc = ata_qc_from_tag(ap, ap->active_tag);
-			if (qc && (!(qc->tf.ctl & ATA_NIEN)))
+			if (qc && (!(qc->tf.flags & ATA_TFLAG_POLLING)))
 				handled += pdc20621_host_intr(ap, qc, (i > 4),
 							      mmio_base);
 		}
diff --git a/drivers/scsi/sata_vsc.c b/drivers/scsi/sata_vsc.c
index 5af05fd..028d4ab 100644
--- a/drivers/scsi/sata_vsc.c
+++ b/drivers/scsi/sata_vsc.c
@@ -193,12 +193,12 @@
 			struct ata_port *ap;
 
 			ap = host_set->ports[i];
-			if (ap && !(ap->flags &
-				    (ATA_FLAG_PORT_DISABLED|ATA_FLAG_NOINTR))) {
+			if (ap &&
+			    !(ap->flags & ATA_FLAG_PORT_DISABLED)) {
 				struct ata_queued_cmd *qc;
 
 				qc = ata_qc_from_tag(ap, ap->active_tag);
-				if (qc && (!(qc->tf.ctl & ATA_NIEN)))
+				if (qc && (!(qc->tf.flags & ATA_TFLAG_POLLING)))
 					handled += ata_host_intr(ap, qc);
 			}
 		}
diff --git a/include/linux/ata.h b/include/linux/ata.h
index d2873b7..d54da33 100644
--- a/include/linux/ata.h
+++ b/include/linux/ata.h
@@ -192,6 +192,7 @@
 	ATA_TFLAG_DEVICE	= (1 << 2), /* enable r/w to device reg */
 	ATA_TFLAG_WRITE		= (1 << 3), /* data dir: host->dev==1 (write) */
 	ATA_TFLAG_LBA		= (1 << 4), /* enable LBA */
+	ATA_TFLAG_POLLING	= (1 << 5), /* set nIEN to 1 and use polling */
 };
 
 enum ata_tf_protocols {
@@ -261,6 +262,8 @@
 	  ((u64) (id)[(n) + 1] << 16) |	\
 	  ((u64) (id)[(n) + 0]) )
 
+#define ata_id_cdb_intr(id)	(((id)[0] & 0x60) == 0x20)
+
 static inline int ata_id_current_chs_valid(const u16 *id)
 {
 	/* For ATA-1 devices, if the INITIALIZE DEVICE PARAMETERS command 
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 00a8a57..d1b2166 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -98,6 +98,7 @@
 	ATA_DFLAG_PIO		= (1 << 1), /* device currently in PIO mode */
 	ATA_DFLAG_LOCK_SECTORS	= (1 << 2), /* don't adjust max_sectors */
 	ATA_DFLAG_LBA		= (1 << 3), /* device supports LBA */
+	ATA_DFLAG_CDB_INTR	= (1 << 4), /* device asserts INTRQ when ready for CDB */
 
 	ATA_DEV_UNKNOWN		= 0,	/* unknown device */
 	ATA_DEV_ATA		= 1,	/* ATA device */
@@ -116,8 +117,8 @@
 	ATA_FLAG_MMIO		= (1 << 6), /* use MMIO, not PIO */
 	ATA_FLAG_SATA_RESET	= (1 << 7), /* use COMRESET */
 	ATA_FLAG_PIO_DMA	= (1 << 8), /* PIO cmds via DMA */
-	ATA_FLAG_NOINTR		= (1 << 9), /* FIXME: Remove this once
-					     * proper HSM is in place. */
+	ATA_FLAG_PIO_POLLING	= (1 << 9), /* use polling PIO if LLD
+					     * doesn't handle PIO interrupts */
 
 	ATA_QCFLAG_ACTIVE	= (1 << 1), /* cmd not yet ack'd to scsi lyer */
 	ATA_QCFLAG_SG		= (1 << 3), /* have s/g table? */
@@ -129,8 +130,8 @@
 	ATA_TMOUT_PIO		= 30 * HZ,
 	ATA_TMOUT_BOOT		= 30 * HZ,	/* hueristic */
 	ATA_TMOUT_BOOT_QUICK	= 7 * HZ,	/* hueristic */
-	ATA_TMOUT_CDB		= 30 * HZ,
-	ATA_TMOUT_CDB_QUICK	= 5 * HZ,
+	ATA_TMOUT_DATAOUT	= 30 * HZ,
+	ATA_TMOUT_DATAOUT_QUICK	= 5 * HZ,
 
 	/* ATA bus states */
 	BUS_UNKNOWN		= 0,
@@ -162,14 +163,16 @@
 };
 
 enum hsm_task_states {
-	HSM_ST_UNKNOWN,
-	HSM_ST_IDLE,
-	HSM_ST_POLL,
-	HSM_ST_TMOUT,
-	HSM_ST,
-	HSM_ST_LAST,
-	HSM_ST_LAST_POLL,
-	HSM_ST_ERR,
+	HSM_ST_UNKNOWN,		/* state unknown */
+	HSM_ST_IDLE,		/* no command on going */
+	HSM_ST_POLL,		/* same as HSM_ST, waits longer */
+	HSM_ST_TMOUT,		/* timeout */
+	HSM_ST,			/* (waiting the device to) transfer data */
+	HSM_ST_LAST,		/* (waiting the device to) complete command */
+	HSM_ST_LAST_POLL,	/* same as HSM_ST_LAST, waits longer */
+	HSM_ST_ERR,		/* error */
+	HSM_ST_FIRST,		/* (waiting the device to)
+				   write CDB or first data block */
 };
 
 /* forward declarations */
@@ -324,7 +327,7 @@
 	struct ata_host_stats	stats;
 	struct ata_host_set	*host_set;
 
-	struct work_struct	packet_task;
+	struct work_struct	dataout_task;
 
 	struct work_struct	pio_task;
 	unsigned int		hsm_task_state;