diff --git a/Documentation/DocBook/libata.tmpl b/Documentation/DocBook/libata.tmpl
index 375ae76..b2ec780 100644
--- a/Documentation/DocBook/libata.tmpl
+++ b/Documentation/DocBook/libata.tmpl
@@ -415,6 +415,362 @@
      </sect1>
   </chapter>
 
+  <chapter id="libataEH">
+        <title>Error handling</title>
+
+	<para>
+	This chapter describes how errors are handled under libata.
+	Readers are advised to read SCSI EH
+	(Documentation/scsi/scsi_eh.txt) and ATA exceptions doc first.
+	</para>
+
+	<sect1><title>Origins of commands</title>
+	<para>
+	In libata, a command is represented with struct ata_queued_cmd
+	or qc.  qc's are preallocated during port initialization and
+	repetitively used for command executions.  Currently only one
+	qc is allocated per port but yet-to-be-merged NCQ branch
+	allocates one for each tag and maps each qc to NCQ tag 1-to-1.
+	</para>
+	<para>
+	libata commands can originate from two sources - libata itself
+	and SCSI midlayer.  libata internal commands are used for
+	initialization and error handling.  All normal blk requests
+	and commands for SCSI emulation are passed as SCSI commands
+	through queuecommand callback of SCSI host template.
+	</para>
+	</sect1>
+
+	<sect1><title>How commands are issued</title>
+
+	<variablelist>
+
+	<varlistentry><term>Internal commands</term>
+	<listitem>
+	<para>
+	First, qc is allocated and initialized using
+	ata_qc_new_init().  Although ata_qc_new_init() doesn't
+	implement any wait or retry mechanism when qc is not
+	available, internal commands are currently issued only during
+	initialization and error recovery, so no other command is
+	active and allocation is guaranteed to succeed.
+	</para>
+	<para>
+	Once allocated qc's taskfile is initialized for the command to
+	be executed.  qc currently has two mechanisms to notify
+	completion.  One is via qc->complete_fn() callback and the
+	other is completion qc->waiting.  qc->complete_fn() callback
+	is the asynchronous path used by normal SCSI translated
+	commands and qc->waiting is the synchronous (issuer sleeps in
+	process context) path used by internal commands.
+	</para>
+	<para>
+	Once initialization is complete, host_set lock is acquired
+	and the qc is issued.
+	</para>
+	</listitem>
+	</varlistentry>
+
+	<varlistentry><term>SCSI commands</term>
+	<listitem>
+	<para>
+	All libata drivers use ata_scsi_queuecmd() as
+	hostt->queuecommand callback.  scmds can either be simulated
+	or translated.  No qc is involved in processing a simulated
+	scmd.  The result is computed right away and the scmd is
+	completed.
+	</para>
+	<para>
+	For a translated scmd, ata_qc_new_init() is invoked to
+	allocate a qc and the scmd is translated into the qc.  SCSI
+	midlayer's completion notification function pointer is stored
+	into qc->scsidone.
+	</para>
+	<para>
+	qc->complete_fn() callback is used for completion
+	notification.  ATA commands use ata_scsi_qc_complete() while
+	ATAPI commands use atapi_qc_complete().  Both functions end up
+	calling qc->scsidone to notify upper layer when the qc is
+	finished.  After translation is completed, the qc is issued
+	with ata_qc_issue().
+	</para>
+	<para>
+	Note that SCSI midlayer invokes hostt->queuecommand while
+	holding host_set lock, so all above occur while holding
+	host_set lock.
+	</para>
+	</listitem>
+	</varlistentry>
+
+	</variablelist>
+	</sect1>
+
+	<sect1><title>How commands are processed</title>
+	<para>
+	Depending on which protocol and which controller are used,
+	commands are processed differently.  For the purpose of
+	discussion, a controller which uses taskfile interface and all
+	standard callbacks is assumed.
+	</para>
+	<para>
+	Currently 6 ATA command protocols are used.  They can be
+	sorted into the following four categories according to how
+	they are processed.
+	</para>
+
+	<variablelist>
+	   <varlistentry><term>ATA NO DATA or DMA</term>
+	   <listitem>
+	   <para>
+	   ATA_PROT_NODATA and ATA_PROT_DMA fall into this category.
+	   These types of commands don't require any software
+	   intervention once issued.  Device will raise interrupt on
+	   completion.
+	   </para>
+	   </listitem>
+	   </varlistentry>
+
+	   <varlistentry><term>ATA PIO</term>
+	   <listitem>
+	   <para>
+	   ATA_PROT_PIO is in this category.  libata currently
+	   implements PIO with polling.  ATA_NIEN bit is set to turn
+	   off interrupt and pio_task on ata_wq performs polling and
+	   IO.
+	   </para>
+	   </listitem>
+	   </varlistentry>
+
+	   <varlistentry><term>ATAPI NODATA or DMA</term>
+	   <listitem>
+	   <para>
+	   ATA_PROT_ATAPI_NODATA and ATA_PROT_ATAPI_DMA are in this
+	   category.  packet_task is used to poll BSY bit after
+	   issuing PACKET command.  Once BSY is turned off by the
+	   device, packet_task transfers CDB and hands off processing
+	   to interrupt handler.
+	   </para>
+	   </listitem>
+	   </varlistentry>
+
+	   <varlistentry><term>ATAPI PIO</term>
+	   <listitem>
+	   <para>
+	   ATA_PROT_ATAPI is in this category.  ATA_NIEN bit is set
+	   and, as in ATAPI NODATA or DMA, packet_task submits cdb.
+	   However, after submitting cdb, further processing (data
+	   transfer) is handed off to pio_task.
+	   </para>
+	   </listitem>
+	   </varlistentry>
+	</variablelist>
+        </sect1>
+
+	<sect1><title>How commands are completed</title>
+	<para>
+	Once issued, all qc's are either completed with
+	ata_qc_complete() or time out.  For commands which are handled
+	by interrupts, ata_host_intr() invokes ata_qc_complete(), and,
+	for PIO tasks, pio_task invokes ata_qc_complete().  In error
+	cases, packet_task may also complete commands.
+	</para>
+	<para>
+	ata_qc_complete() does the following.
+	</para>
+
+	<orderedlist>
+
+	<listitem>
+	<para>
+	DMA memory is unmapped.
+	</para>
+	</listitem>
+
+	<listitem>
+	<para>
+	ATA_QCFLAG_ACTIVE is clared from qc->flags.
+	</para>
+	</listitem>
+
+	<listitem>
+	<para>
+	qc->complete_fn() callback is invoked.  If the return value of
+	the callback is not zero.  Completion is short circuited and
+	ata_qc_complete() returns.
+	</para>
+	</listitem>
+
+	<listitem>
+	<para>
+	__ata_qc_complete() is called, which does
+	   <orderedlist>
+
+	   <listitem>
+	   <para>
+	   qc->flags is cleared to zero.
+	   </para>
+	   </listitem>
+
+	   <listitem>
+	   <para>
+	   ap->active_tag and qc->tag are poisoned.
+	   </para>
+	   </listitem>
+
+	   <listitem>
+	   <para>
+	   qc->waiting is claread &amp; completed (in that order).
+	   </para>
+	   </listitem>
+
+	   <listitem>
+	   <para>
+	   qc is deallocated by clearing appropriate bit in ap->qactive.
+	   </para>
+	   </listitem>
+
+	   </orderedlist>
+	</para>
+	</listitem>
+
+	</orderedlist>
+
+	<para>
+	So, it basically notifies upper layer and deallocates qc.  One
+	exception is short-circuit path in #3 which is used by
+	atapi_qc_complete().
+	</para>
+	<para>
+	For all non-ATAPI commands, whether it fails or not, almost
+	the same code path is taken and very little error handling
+	takes place.  A qc is completed with success status if it
+	succeeded, with failed status otherwise.
+	</para>
+	<para>
+	However, failed ATAPI commands require more handling as
+	REQUEST SENSE is needed to acquire sense data.  If an ATAPI
+	command fails, ata_qc_complete() is invoked with error status,
+	which in turn invokes atapi_qc_complete() via
+	qc->complete_fn() callback.
+	</para>
+	<para>
+	This makes atapi_qc_complete() set scmd->result to
+	SAM_STAT_CHECK_CONDITION, complete the scmd and return 1.  As
+	the sense data is empty but scmd->result is CHECK CONDITION,
+	SCSI midlayer will invoke EH for the scmd, and returning 1
+	makes ata_qc_complete() to return without deallocating the qc.
+	This leads us to ata_scsi_error() with partially completed qc.
+	</para>
+
+	</sect1>
+
+	<sect1><title>ata_scsi_error()</title>
+	<para>
+	ata_scsi_error() is the current hostt->eh_strategy_handler()
+	for libata.  As discussed above, this will be entered in two
+	cases - timeout and ATAPI error completion.  This function
+	calls low level libata driver's eng_timeout() callback, the
+	standard callback for which is ata_eng_timeout().  It checks
+	if a qc is active and calls ata_qc_timeout() on the qc if so.
+	Actual error handling occurs in ata_qc_timeout().
+	</para>
+	<para>
+	If EH is invoked for timeout, ata_qc_timeout() stops BMDMA and
+	completes the qc.  Note that as we're currently in EH, we
+	cannot call scsi_done.  As described in SCSI EH doc, a
+	recovered scmd should be either retried with
+	scsi_queue_insert() or finished with scsi_finish_command().
+	Here, we override qc->scsidone with scsi_finish_command() and
+	calls ata_qc_complete().
+	</para>
+	<para>
+	If EH is invoked due to a failed ATAPI qc, the qc here is
+	completed but not deallocated.  The purpose of this
+	half-completion is to use the qc as place holder to make EH
+	code reach this place.  This is a bit hackish, but it works.
+	</para>
+	<para>
+	Once control reaches here, the qc is deallocated by invoking
+	__ata_qc_complete() explicitly.  Then, internal qc for REQUEST
+	SENSE is issued.  Once sense data is acquired, scmd is
+	finished by directly invoking scsi_finish_command() on the
+	scmd.  Note that as we already have completed and deallocated
+	the qc which was associated with the scmd, we don't need
+	to/cannot call ata_qc_complete() again.
+	</para>
+
+	</sect1>
+
+	<sect1><title>Problems with the current EH</title>
+
+	<itemizedlist>
+
+	<listitem>
+	<para>
+	Error representation is too crude.  Currently any and all
+	error conditions are represented with ATA STATUS and ERROR
+	registers.  Errors which aren't ATA device errors are treated
+	as ATA device errors by setting ATA_ERR bit.  Better error
+	descriptor which can properly represent ATA and other
+	errors/exceptions is needed.
+	</para>
+	</listitem>
+
+	<listitem>
+	<para>
+	When handling timeouts, no action is taken to make device
+	forget about the timed out command and ready for new commands.
+	</para>
+	</listitem>
+
+	<listitem>
+	<para>
+	EH handling via ata_scsi_error() is not properly protected
+	from usual command processing.  On EH entrance, the device is
+	not in quiescent state.  Timed out commands may succeed or
+	fail any time.  pio_task and atapi_task may still be running.
+	</para>
+	</listitem>
+
+	<listitem>
+	<para>
+	Too weak error recovery.  Devices / controllers causing HSM
+	mismatch errors and other errors quite often require reset to
+	return to known state.  Also, advanced error handling is
+	necessary to support features like NCQ and hotplug.
+	</para>
+	</listitem>
+
+	<listitem>
+	<para>
+	ATA errors are directly handled in the interrupt handler and
+	PIO errors in pio_task.  This is problematic for advanced
+	error handling for the following reasons.
+	</para>
+	<para>
+	First, advanced error handling often requires context and
+	internal qc execution.
+	</para>
+	<para>
+	Second, even a simple failure (say, CRC error) needs
+	information gathering and could trigger complex error handling
+	(say, resetting &amp; reconfiguring).  Having multiple code
+	paths to gather information, enter EH and trigger actions
+	makes life painful.
+	</para>
+	<para>
+	Third, scattered EH code makes implementing low level drivers
+	difficult.  Low level drivers override libata callbacks.  If
+	EH is scattered over several places, each affected callbacks
+	should perform its part of error handling.  This can be error
+	prone and painful.
+	</para>
+	</listitem>
+
+	</itemizedlist>
+	</sect1>
+  </chapter>
+
   <chapter id="libataExt">
      <title>libata Library</title>
 !Edrivers/scsi/libata-core.c
diff --git a/drivers/scsi/libata-core.c b/drivers/scsi/libata-core.c
index e5b0199..03d422e 100644
--- a/drivers/scsi/libata-core.c
+++ b/drivers/scsi/libata-core.c
@@ -62,6 +62,7 @@
 static unsigned int ata_busy_sleep (struct ata_port *ap,
 				    unsigned long tmout_pat,
 			    	    unsigned long tmout);
+static void ata_dev_init_params(struct ata_port *ap, struct ata_device *dev);
 static void ata_set_mode(struct ata_port *ap);
 static void ata_dev_set_xfermode(struct ata_port *ap, struct ata_device *dev);
 static unsigned int ata_get_mode_mask(struct ata_port *ap, int shift);
@@ -1131,7 +1132,7 @@
 static void ata_dev_identify(struct ata_port *ap, unsigned int device)
 {
 	struct ata_device *dev = &ap->device[device];
-	unsigned int i;
+	unsigned int major_version;
 	u16 tmp;
 	unsigned long xfer_modes;
 	u8 status;
@@ -1229,9 +1230,9 @@
 	 * common ATA, ATAPI feature tests
 	 */
 
-	/* we require LBA and DMA support (bits 8 & 9 of word 49) */
-	if (!ata_id_has_dma(dev->id) || !ata_id_has_lba(dev->id)) {
-		printk(KERN_DEBUG "ata%u: no dma/lba\n", ap->id);
+	/* we require DMA support (bits 8 of word 49) */
+	if (!ata_id_has_dma(dev->id)) {
+		printk(KERN_DEBUG "ata%u: no dma\n", ap->id);
 		goto err_out_nosup;
 	}
 
@@ -1251,32 +1252,69 @@
 		if (!ata_id_is_ata(dev->id))	/* sanity check */
 			goto err_out_nosup;
 
+		/* get major version */
 		tmp = dev->id[ATA_ID_MAJOR_VER];
-		for (i = 14; i >= 1; i--)
-			if (tmp & (1 << i))
+		for (major_version = 14; major_version >= 1; major_version--)
+			if (tmp & (1 << major_version))
 				break;
 
-		/* we require at least ATA-3 */
-		if (i < 3) {
-			printk(KERN_DEBUG "ata%u: no ATA-3\n", ap->id);
-			goto err_out_nosup;
-		}
+		/*
+		 * The exact sequence expected by certain pre-ATA4 drives is:
+		 * SRST RESET
+		 * IDENTIFY
+		 * INITIALIZE DEVICE PARAMETERS
+		 * anything else..
+		 * Some drives were very specific about that exact sequence.
+		 */
+		if (major_version < 4 || (!ata_id_has_lba(dev->id)))
+			ata_dev_init_params(ap, dev);
 
-		if (ata_id_has_lba48(dev->id)) {
-			dev->flags |= ATA_DFLAG_LBA48;
-			dev->n_sectors = ata_id_u64(dev->id, 100);
-		} else {
-			dev->n_sectors = ata_id_u32(dev->id, 60);
+		if (ata_id_has_lba(dev->id)) {
+			dev->flags |= ATA_DFLAG_LBA;
+
+			if (ata_id_has_lba48(dev->id)) {
+				dev->flags |= ATA_DFLAG_LBA48;
+				dev->n_sectors = ata_id_u64(dev->id, 100);
+			} else {
+				dev->n_sectors = ata_id_u32(dev->id, 60);
+			}
+
+			/* print device info to dmesg */
+			printk(KERN_INFO "ata%u: dev %u ATA-%d, max %s, %Lu sectors:%s\n",
+			       ap->id, device,
+			       major_version,
+			       ata_mode_string(xfer_modes),
+			       (unsigned long long)dev->n_sectors,
+			       dev->flags & ATA_DFLAG_LBA48 ? " LBA48" : " LBA");
+		} else { 
+			/* CHS */
+
+			/* Default translation */
+			dev->cylinders	= dev->id[1];
+			dev->heads	= dev->id[3];
+			dev->sectors	= dev->id[6];
+			dev->n_sectors	= dev->cylinders * dev->heads * dev->sectors;
+
+			if (ata_id_current_chs_valid(dev->id)) {
+				/* Current CHS translation is valid. */
+				dev->cylinders = dev->id[54];
+				dev->heads     = dev->id[55];
+				dev->sectors   = dev->id[56];
+				
+				dev->n_sectors = ata_id_u32(dev->id, 57);
+			}
+
+			/* print device info to dmesg */
+			printk(KERN_INFO "ata%u: dev %u ATA-%d, max %s, %Lu sectors: CHS %d/%d/%d\n",
+			       ap->id, device,
+			       major_version,
+			       ata_mode_string(xfer_modes),
+			       (unsigned long long)dev->n_sectors,
+			       (int)dev->cylinders, (int)dev->heads, (int)dev->sectors);
+
 		}
 
 		ap->host->max_cmd_len = 16;
-
-		/* print device info to dmesg */
-		printk(KERN_INFO "ata%u: dev %u ATA, max %s, %Lu sectors:%s\n",
-		       ap->id, device,
-		       ata_mode_string(xfer_modes),
-		       (unsigned long long)dev->n_sectors,
-		       dev->flags & ATA_DFLAG_LBA48 ? " lba48" : "");
 	}
 
 	/* ATAPI-specific feature tests */
@@ -2144,6 +2182,54 @@
 }
 
 /**
+ *	ata_dev_init_params - Issue INIT DEV PARAMS command
+ *	@ap: Port associated with device @dev
+ *	@dev: Device to which command will be sent
+ *
+ *	LOCKING:
+ */
+
+static void ata_dev_init_params(struct ata_port *ap, struct ata_device *dev)
+{
+	DECLARE_COMPLETION(wait);
+	struct ata_queued_cmd *qc;
+	int rc;
+	unsigned long flags;
+	u16 sectors = dev->id[6];
+	u16 heads   = dev->id[3];
+
+	/* Number of sectors per track 1-255. Number of heads 1-16 */
+	if (sectors < 1 || sectors > 255 || heads < 1 || heads > 16)
+		return;
+
+	/* set up init dev params taskfile */
+	DPRINTK("init dev params \n");
+
+	qc = ata_qc_new_init(ap, dev);
+	BUG_ON(qc == NULL);
+
+	qc->tf.command = ATA_CMD_INIT_DEV_PARAMS;
+	qc->tf.flags |= ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE;
+	qc->tf.protocol = ATA_PROT_NODATA;
+	qc->tf.nsect = sectors;
+	qc->tf.device |= (heads - 1) & 0x0f; /* max head = num. of heads - 1 */
+
+	qc->waiting = &wait;
+	qc->complete_fn = ata_qc_complete_noop;
+
+	spin_lock_irqsave(&ap->host_set->lock, flags);
+	rc = ata_qc_issue(qc);
+	spin_unlock_irqrestore(&ap->host_set->lock, flags);
+
+	if (rc)
+		ata_port_disable(ap);
+	else
+		wait_for_completion(&wait);
+
+	DPRINTK("EXIT\n");
+}
+
+/**
  *	ata_sg_clean - Unmap DMA memory associated with command
  *	@qc: Command containing DMA memory to be released
  *
@@ -2425,20 +2511,20 @@
 static unsigned long ata_pio_poll(struct ata_port *ap)
 {
 	u8 status;
-	unsigned int poll_state = PIO_ST_UNKNOWN;
-	unsigned int reg_state = PIO_ST_UNKNOWN;
-	const unsigned int tmout_state = PIO_ST_TMOUT;
+	unsigned int poll_state = HSM_ST_UNKNOWN;
+	unsigned int reg_state = HSM_ST_UNKNOWN;
+	const unsigned int tmout_state = HSM_ST_TMOUT;
 
-	switch (ap->pio_task_state) {
-	case PIO_ST:
-	case PIO_ST_POLL:
-		poll_state = PIO_ST_POLL;
-		reg_state = PIO_ST;
+	switch (ap->hsm_task_state) {
+	case HSM_ST:
+	case HSM_ST_POLL:
+		poll_state = HSM_ST_POLL;
+		reg_state = HSM_ST;
 		break;
-	case PIO_ST_LAST:
-	case PIO_ST_LAST_POLL:
-		poll_state = PIO_ST_LAST_POLL;
-		reg_state = PIO_ST_LAST;
+	case HSM_ST_LAST:
+	case HSM_ST_LAST_POLL:
+		poll_state = HSM_ST_LAST_POLL;
+		reg_state = HSM_ST_LAST;
 		break;
 	default:
 		BUG();
@@ -2448,14 +2534,14 @@
 	status = ata_chk_status(ap);
 	if (status & ATA_BUSY) {
 		if (time_after(jiffies, ap->pio_task_timeout)) {
-			ap->pio_task_state = tmout_state;
+			ap->hsm_task_state = tmout_state;
 			return 0;
 		}
-		ap->pio_task_state = poll_state;
+		ap->hsm_task_state = poll_state;
 		return ATA_SHORT_PAUSE;
 	}
 
-	ap->pio_task_state = reg_state;
+	ap->hsm_task_state = reg_state;
 	return 0;
 }
 
@@ -2480,14 +2566,14 @@
 	 * we enter, BSY will be cleared in a chk-status or two.  If not,
 	 * the drive is probably seeking or something.  Snooze for a couple
 	 * msecs, then chk-status again.  If still busy, fall back to
-	 * PIO_ST_POLL state.
+	 * HSM_ST_POLL state.
 	 */
 	drv_stat = ata_busy_wait(ap, ATA_BUSY | ATA_DRQ, 10);
 	if (drv_stat & (ATA_BUSY | ATA_DRQ)) {
 		msleep(2);
 		drv_stat = ata_busy_wait(ap, ATA_BUSY | ATA_DRQ, 10);
 		if (drv_stat & (ATA_BUSY | ATA_DRQ)) {
-			ap->pio_task_state = PIO_ST_LAST_POLL;
+			ap->hsm_task_state = HSM_ST_LAST_POLL;
 			ap->pio_task_timeout = jiffies + ATA_TMOUT_PIO;
 			return 0;
 		}
@@ -2495,14 +2581,14 @@
 
 	drv_stat = ata_wait_idle(ap);
 	if (!ata_ok(drv_stat)) {
-		ap->pio_task_state = PIO_ST_ERR;
+		ap->hsm_task_state = HSM_ST_ERR;
 		return 0;
 	}
 
 	qc = ata_qc_from_tag(ap, ap->active_tag);
 	assert(qc != NULL);
 
-	ap->pio_task_state = PIO_ST_IDLE;
+	ap->hsm_task_state = HSM_ST_IDLE;
 
 	ata_poll_qc_complete(qc, drv_stat);
 
@@ -2662,7 +2748,7 @@
 	unsigned char *buf;
 
 	if (qc->cursect == (qc->nsect - 1))
-		ap->pio_task_state = PIO_ST_LAST;
+		ap->hsm_task_state = HSM_ST_LAST;
 
 	page = sg[qc->cursg].page;
 	offset = sg[qc->cursg].offset + qc->cursg_ofs * ATA_SECT_SIZE;
@@ -2712,7 +2798,7 @@
 	unsigned int offset, count;
 
 	if (qc->curbytes + bytes >= qc->nbytes)
-		ap->pio_task_state = PIO_ST_LAST;
+		ap->hsm_task_state = HSM_ST_LAST;
 
 next_sg:
 	if (unlikely(qc->cursg >= qc->n_elem)) {
@@ -2734,7 +2820,7 @@
 		for (i = 0; i < words; i++)
 			ata_data_xfer(ap, (unsigned char*)pad_buf, 2, do_write);
 
-		ap->pio_task_state = PIO_ST_LAST;
+		ap->hsm_task_state = HSM_ST_LAST;
 		return;
 	}
 
@@ -2815,7 +2901,7 @@
 err_out:
 	printk(KERN_INFO "ata%u: dev %u: ATAPI check failed\n",
 	      ap->id, dev->devno);
-	ap->pio_task_state = PIO_ST_ERR;
+	ap->hsm_task_state = HSM_ST_ERR;
 }
 
 /**
@@ -2837,14 +2923,14 @@
 	 * a chk-status or two.  If not, the drive is probably seeking
 	 * or something.  Snooze for a couple msecs, then
 	 * chk-status again.  If still busy, fall back to
-	 * PIO_ST_POLL state.
+	 * HSM_ST_POLL state.
 	 */
 	status = ata_busy_wait(ap, ATA_BUSY, 5);
 	if (status & ATA_BUSY) {
 		msleep(2);
 		status = ata_busy_wait(ap, ATA_BUSY, 10);
 		if (status & ATA_BUSY) {
-			ap->pio_task_state = PIO_ST_POLL;
+			ap->hsm_task_state = HSM_ST_POLL;
 			ap->pio_task_timeout = jiffies + ATA_TMOUT_PIO;
 			return;
 		}
@@ -2856,7 +2942,7 @@
 	if (is_atapi_taskfile(&qc->tf)) {
 		/* no more data to transfer or unsupported ATAPI command */
 		if ((status & ATA_DRQ) == 0) {
-			ap->pio_task_state = PIO_ST_LAST;
+			ap->hsm_task_state = HSM_ST_LAST;
 			return;
 		}
 
@@ -2864,7 +2950,7 @@
 	} else {
 		/* handle BSY=0, DRQ=0 as error */
 		if ((status & ATA_DRQ) == 0) {
-			ap->pio_task_state = PIO_ST_ERR;
+			ap->hsm_task_state = HSM_ST_ERR;
 			return;
 		}
 
@@ -2884,7 +2970,7 @@
 	printk(KERN_WARNING "ata%u: PIO error, drv_stat 0x%x\n",
 	       ap->id, drv_stat);
 
-	ap->pio_task_state = PIO_ST_IDLE;
+	ap->hsm_task_state = HSM_ST_IDLE;
 
 	ata_poll_qc_complete(qc, drv_stat | ATA_ERR);
 }
@@ -2899,25 +2985,25 @@
 	timeout = 0;
 	qc_completed = 0;
 
-	switch (ap->pio_task_state) {
-	case PIO_ST_IDLE:
+	switch (ap->hsm_task_state) {
+	case HSM_ST_IDLE:
 		return;
 
-	case PIO_ST:
+	case HSM_ST:
 		ata_pio_block(ap);
 		break;
 
-	case PIO_ST_LAST:
+	case HSM_ST_LAST:
 		qc_completed = ata_pio_complete(ap);
 		break;
 
-	case PIO_ST_POLL:
-	case PIO_ST_LAST_POLL:
+	case HSM_ST_POLL:
+	case HSM_ST_LAST_POLL:
 		timeout = ata_pio_poll(ap);
 		break;
 
-	case PIO_ST_TMOUT:
-	case PIO_ST_ERR:
+	case HSM_ST_TMOUT:
+	case HSM_ST_ERR:
 		ata_pio_error(ap);
 		return;
 	}
@@ -3156,8 +3242,12 @@
 
 		ata_tf_init(ap, &qc->tf, dev->devno);
 
-		if (dev->flags & ATA_DFLAG_LBA48)
-			qc->tf.flags |= ATA_TFLAG_LBA48;
+		if (dev->flags & ATA_DFLAG_LBA) {
+			qc->tf.flags |= ATA_TFLAG_LBA;
+
+			if (dev->flags & ATA_DFLAG_LBA48)
+				qc->tf.flags |= ATA_TFLAG_LBA48;
+		}
 	}
 
 	return qc;
@@ -3360,7 +3450,7 @@
 	case ATA_PROT_PIO: /* load tf registers, initiate polling pio */
 		ata_qc_set_polling(qc);
 		ata_tf_to_host_nolock(ap, &qc->tf);
-		ap->pio_task_state = PIO_ST;
+		ap->hsm_task_state = HSM_ST;
 		queue_work(ata_wq, &ap->pio_task);
 		break;
 
@@ -3586,7 +3676,7 @@
 		void __iomem *mmio = (void __iomem *) ap->ioaddr.bmdma_addr;
 		host_stat = readb(mmio + ATA_DMA_STATUS);
 	} else
-	host_stat = inb(ap->ioaddr.bmdma_addr + ATA_DMA_STATUS);
+		host_stat = inb(ap->ioaddr.bmdma_addr + ATA_DMA_STATUS);
 	return host_stat;
 }
 
@@ -3806,7 +3896,7 @@
 		ata_data_xfer(ap, qc->cdb, ap->cdb_len, 1);
 
 		/* PIO commands are handled by polling */
-		ap->pio_task_state = PIO_ST;
+		ap->hsm_task_state = HSM_ST;
 		queue_work(ata_wq, &ap->pio_task);
 	}
 
diff --git a/drivers/scsi/libata-scsi.c b/drivers/scsi/libata-scsi.c
index 104fd9a..03b7a6d 100644
--- a/drivers/scsi/libata-scsi.c
+++ b/drivers/scsi/libata-scsi.c
@@ -504,78 +504,108 @@
 static unsigned int ata_scsi_verify_xlat(struct ata_queued_cmd *qc, u8 *scsicmd)
 {
 	struct ata_taskfile *tf = &qc->tf;
+	struct ata_device *dev = qc->dev;
+	unsigned int lba   = tf->flags & ATA_TFLAG_LBA;
 	unsigned int lba48 = tf->flags & ATA_TFLAG_LBA48;
 	u64 dev_sectors = qc->dev->n_sectors;
-	u64 sect = 0;
-	u32 n_sect = 0;
+	u64 block = 0;
+	u32 n_block = 0;
 
 	tf->flags |= ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE;
 	tf->protocol = ATA_PROT_NODATA;
-	tf->device |= ATA_LBA;
 
 	if (scsicmd[0] == VERIFY) {
-		sect |= ((u64)scsicmd[2]) << 24;
-		sect |= ((u64)scsicmd[3]) << 16;
-		sect |= ((u64)scsicmd[4]) << 8;
-		sect |= ((u64)scsicmd[5]);
+		block |= ((u64)scsicmd[2]) << 24;
+		block |= ((u64)scsicmd[3]) << 16;
+		block |= ((u64)scsicmd[4]) << 8;
+		block |= ((u64)scsicmd[5]);
 
-		n_sect |= ((u32)scsicmd[7]) << 8;
-		n_sect |= ((u32)scsicmd[8]);
+		n_block |= ((u32)scsicmd[7]) << 8;
+		n_block |= ((u32)scsicmd[8]);
 	}
 
 	else if (scsicmd[0] == VERIFY_16) {
-		sect |= ((u64)scsicmd[2]) << 56;
-		sect |= ((u64)scsicmd[3]) << 48;
-		sect |= ((u64)scsicmd[4]) << 40;
-		sect |= ((u64)scsicmd[5]) << 32;
-		sect |= ((u64)scsicmd[6]) << 24;
-		sect |= ((u64)scsicmd[7]) << 16;
-		sect |= ((u64)scsicmd[8]) << 8;
-		sect |= ((u64)scsicmd[9]);
+		block |= ((u64)scsicmd[2]) << 56;
+		block |= ((u64)scsicmd[3]) << 48;
+		block |= ((u64)scsicmd[4]) << 40;
+		block |= ((u64)scsicmd[5]) << 32;
+		block |= ((u64)scsicmd[6]) << 24;
+		block |= ((u64)scsicmd[7]) << 16;
+		block |= ((u64)scsicmd[8]) << 8;
+		block |= ((u64)scsicmd[9]);
 
-		n_sect |= ((u32)scsicmd[10]) << 24;
-		n_sect |= ((u32)scsicmd[11]) << 16;
-		n_sect |= ((u32)scsicmd[12]) << 8;
-		n_sect |= ((u32)scsicmd[13]);
+		n_block |= ((u32)scsicmd[10]) << 24;
+		n_block |= ((u32)scsicmd[11]) << 16;
+		n_block |= ((u32)scsicmd[12]) << 8;
+		n_block |= ((u32)scsicmd[13]);
 	}
 
 	else
 		return 1;
 
-	if (!n_sect)
+	if (!n_block)
 		return 1;
-	if (sect >= dev_sectors)
+	if (block >= dev_sectors)
 		return 1;
-	if ((sect + n_sect) > dev_sectors)
+	if ((block + n_block) > dev_sectors)
 		return 1;
 	if (lba48) {
-		if (n_sect > (64 * 1024))
+		if (n_block > (64 * 1024))
 			return 1;
 	} else {
-		if (n_sect > 256)
+		if (n_block > 256)
 			return 1;
 	}
 
-	if (lba48) {
-		tf->command = ATA_CMD_VERIFY_EXT;
+	if (lba) {
+		if (lba48) {
+			tf->command = ATA_CMD_VERIFY_EXT;
 
-		tf->hob_nsect = (n_sect >> 8) & 0xff;
+			tf->hob_nsect = (n_block >> 8) & 0xff;
 
-		tf->hob_lbah = (sect >> 40) & 0xff;
-		tf->hob_lbam = (sect >> 32) & 0xff;
-		tf->hob_lbal = (sect >> 24) & 0xff;
+			tf->hob_lbah = (block >> 40) & 0xff;
+			tf->hob_lbam = (block >> 32) & 0xff;
+			tf->hob_lbal = (block >> 24) & 0xff;
+		} else {
+			tf->command = ATA_CMD_VERIFY;
+
+			tf->device |= (block >> 24) & 0xf;
+		}
+
+		tf->nsect = n_block & 0xff;
+
+		tf->lbah = (block >> 16) & 0xff;
+		tf->lbam = (block >> 8) & 0xff;
+		tf->lbal = block & 0xff;
+
+		tf->device |= ATA_LBA;
 	} else {
+		/* CHS */
+		u32 sect, head, cyl, track;
+
+		/* Convert LBA to CHS */
+		track = (u32)block / dev->sectors;
+		cyl   = track / dev->heads;
+		head  = track % dev->heads;
+		sect  = (u32)block % dev->sectors + 1;
+
+		DPRINTK("block[%u] track[%u] cyl[%u] head[%u] sect[%u] \n", (u32)block, track, cyl, head, sect);
+		
+		/* Check whether the converted CHS can fit. 
+		   Cylinder: 0-65535 
+		   Head: 0-15
+		   Sector: 1-255*/
+		if ((cyl >> 16) || (head >> 4) || (sect >> 8) || (!sect)) 
+			return 1;
+		
 		tf->command = ATA_CMD_VERIFY;
-
-		tf->device |= (sect >> 24) & 0xf;
+		tf->nsect = n_block & 0xff; /* Sector count 0 means 256 sectors */
+		tf->lbal = sect;
+		tf->lbam = cyl;
+		tf->lbah = cyl >> 8;
+		tf->device |= head;
 	}
 
-	tf->nsect = n_sect & 0xff;
-
-	tf->lbah = (sect >> 16) & 0xff;
-	tf->lbam = (sect >> 8) & 0xff;
-	tf->lbal = sect & 0xff;
-
 	return 0;
 }
 
@@ -602,11 +632,14 @@
 static unsigned int ata_scsi_rw_xlat(struct ata_queued_cmd *qc, u8 *scsicmd)
 {
 	struct ata_taskfile *tf = &qc->tf;
+	struct ata_device *dev = qc->dev;
+	unsigned int lba   = tf->flags & ATA_TFLAG_LBA;
 	unsigned int lba48 = tf->flags & ATA_TFLAG_LBA48;
+	u64 block = 0;
+	u32 n_block = 0;
 
 	tf->flags |= ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE;
 	tf->protocol = qc->dev->xfer_protocol;
-	tf->device |= ATA_LBA;
 
 	if (scsicmd[0] == READ_10 || scsicmd[0] == READ_6 ||
 	    scsicmd[0] == READ_16) {
@@ -616,90 +649,114 @@
 		tf->flags |= ATA_TFLAG_WRITE;
 	}
 
+	/* Calculate the SCSI LBA and transfer length. */
 	if (scsicmd[0] == READ_10 || scsicmd[0] == WRITE_10) {
-		if (lba48) {
-			tf->hob_nsect = scsicmd[7];
-			tf->hob_lbal = scsicmd[2];
+		block |= ((u64)scsicmd[2]) << 24;
+		block |= ((u64)scsicmd[3]) << 16;
+		block |= ((u64)scsicmd[4]) << 8;
+		block |= ((u64)scsicmd[5]);
 
-			qc->nsect = ((unsigned int)scsicmd[7] << 8) |
-					scsicmd[8];
-		} else {
-			/* if we don't support LBA48 addressing, the request
-			 * -may- be too large. */
-			if ((scsicmd[2] & 0xf0) || scsicmd[7])
-				return 1;
-
-			/* stores LBA27:24 in lower 4 bits of device reg */
-			tf->device |= scsicmd[2];
-
-			qc->nsect = scsicmd[8];
-		}
-
-		tf->nsect = scsicmd[8];
-		tf->lbal = scsicmd[5];
-		tf->lbam = scsicmd[4];
-		tf->lbah = scsicmd[3];
+		n_block |= ((u32)scsicmd[7]) << 8;
+		n_block |= ((u32)scsicmd[8]);
 
 		VPRINTK("ten-byte command\n");
-		if (qc->nsect == 0) /* we don't support length==0 cmds */
-			return 1;
-		return 0;
-	}
+	} else if (scsicmd[0] == READ_6 || scsicmd[0] == WRITE_6) {
+		block |= ((u64)scsicmd[2]) << 8;
+		block |= ((u64)scsicmd[3]);
 
-	if (scsicmd[0] == READ_6 || scsicmd[0] == WRITE_6) {
-		qc->nsect = tf->nsect = scsicmd[4];
-		if (!qc->nsect) {
-			qc->nsect = 256;
-			if (lba48)
-				tf->hob_nsect = 1;
-		}
-
-		tf->lbal = scsicmd[3];
-		tf->lbam = scsicmd[2];
-		tf->lbah = scsicmd[1] & 0x1f; /* mask out reserved bits */
-
+		n_block |= ((u32)scsicmd[4]);
+		if (!n_block)
+			n_block = 256;
+	
 		VPRINTK("six-byte command\n");
-		return 0;
-	}
+	} else if (scsicmd[0] == READ_16 || scsicmd[0] == WRITE_16) {
+		block |= ((u64)scsicmd[2]) << 56;
+		block |= ((u64)scsicmd[3]) << 48;
+		block |= ((u64)scsicmd[4]) << 40;
+		block |= ((u64)scsicmd[5]) << 32;
+		block |= ((u64)scsicmd[6]) << 24;
+		block |= ((u64)scsicmd[7]) << 16;
+		block |= ((u64)scsicmd[8]) << 8;
+		block |= ((u64)scsicmd[9]);
 
-	if (scsicmd[0] == READ_16 || scsicmd[0] == WRITE_16) {
-		/* rule out impossible LBAs and sector counts */
-		if (scsicmd[2] || scsicmd[3] || scsicmd[10] || scsicmd[11])
-			return 1;
-
-		if (lba48) {
-			tf->hob_nsect = scsicmd[12];
-			tf->hob_lbal = scsicmd[6];
-			tf->hob_lbam = scsicmd[5];
-			tf->hob_lbah = scsicmd[4];
-
-			qc->nsect = ((unsigned int)scsicmd[12] << 8) |
-					scsicmd[13];
-		} else {
-			/* once again, filter out impossible non-zero values */
-			if (scsicmd[4] || scsicmd[5] || scsicmd[12] ||
-			    (scsicmd[6] & 0xf0))
-				return 1;
-
-			/* stores LBA27:24 in lower 4 bits of device reg */
-			tf->device |= scsicmd[6];
-
-			qc->nsect = scsicmd[13];
-		}
-
-		tf->nsect = scsicmd[13];
-		tf->lbal = scsicmd[9];
-		tf->lbam = scsicmd[8];
-		tf->lbah = scsicmd[7];
+		n_block |= ((u32)scsicmd[10]) << 24;
+		n_block |= ((u32)scsicmd[11]) << 16;
+		n_block |= ((u32)scsicmd[12]) << 8;
+		n_block |= ((u32)scsicmd[13]);
 
 		VPRINTK("sixteen-byte command\n");
-		if (qc->nsect == 0) /* we don't support length==0 cmds */
-			return 1;
-		return 0;
+	} else {
+		DPRINTK("no-byte command\n");
+		return 1;
 	}
 
-	DPRINTK("no-byte command\n");
-	return 1;
+	/* Check and compose ATA command */
+	if (!n_block)
+		/* In ATA, sector count 0 means 256 or 65536 sectors, not 0 sectors. */
+		return 1;
+
+	if (lba) {
+		if (lba48) {
+			/* The request -may- be too large for LBA48. */
+			if ((block >> 48) || (n_block > 65536))
+				return 1;
+
+			tf->hob_nsect = (n_block >> 8) & 0xff;
+
+			tf->hob_lbah = (block >> 40) & 0xff;
+			tf->hob_lbam = (block >> 32) & 0xff;
+			tf->hob_lbal = (block >> 24) & 0xff;
+		} else { 
+			/* LBA28 */
+
+			/* The request -may- be too large for LBA28. */
+			if ((block >> 28) || (n_block > 256))
+				return 1;
+
+			tf->device |= (block >> 24) & 0xf;
+		}
+	
+		qc->nsect = n_block;
+		tf->nsect = n_block & 0xff;
+
+		tf->lbah = (block >> 16) & 0xff;
+		tf->lbam = (block >> 8) & 0xff;
+		tf->lbal = block & 0xff;
+
+		tf->device |= ATA_LBA;
+	} else { 
+		/* CHS */
+		u32 sect, head, cyl, track;
+
+		/* The request -may- be too large for CHS addressing. */
+		if ((block >> 28) || (n_block > 256))
+			return 1;
+			
+		/* Convert LBA to CHS */
+		track = (u32)block / dev->sectors;
+		cyl   = track / dev->heads;
+		head  = track % dev->heads;
+		sect  = (u32)block % dev->sectors + 1;
+
+		DPRINTK("block[%u] track[%u] cyl[%u] head[%u] sect[%u] \n", 
+			(u32)block, track, cyl, head, sect);
+		
+		/* Check whether the converted CHS can fit. 
+		   Cylinder: 0-65535 
+		   Head: 0-15
+		   Sector: 1-255*/
+		if ((cyl >> 16) || (head >> 4) || (sect >> 8) || (!sect)) 
+			return 1;
+		
+		qc->nsect = n_block;
+		tf->nsect = n_block & 0xff; /* Sector count 0 means 256 sectors */
+		tf->lbal = sect;
+		tf->lbam = cyl;
+		tf->lbah = cyl >> 8;
+		tf->device |= head;
+	}
+
+	return 0;
 }
 
 static int ata_scsi_qc_complete(struct ata_queued_cmd *qc, u8 drv_stat)
@@ -1246,10 +1303,20 @@
 
 	VPRINTK("ENTER\n");
 
-	if (ata_id_has_lba48(args->id))
-		n_sectors = ata_id_u64(args->id, 100);
-	else
-		n_sectors = ata_id_u32(args->id, 60);
+	if (ata_id_has_lba(args->id)) {
+		if (ata_id_has_lba48(args->id))
+			n_sectors = ata_id_u64(args->id, 100);
+		else
+			n_sectors = ata_id_u32(args->id, 60);
+	} else {
+		/* CHS default translation */
+		n_sectors = args->id[1] * args->id[3] * args->id[6];
+
+		if (ata_id_current_chs_valid(args->id))
+			/* CHS current translation */
+			n_sectors = ata_id_u32(args->id, 57);
+	}
+
 	n_sectors--;		/* ATA TotalUserSectors - 1 */
 
 	if (args->cmd->cmnd[0] == READ_CAPACITY) {
diff --git a/drivers/scsi/sata_promise.c b/drivers/scsi/sata_promise.c
index 538ad72..def7e0d 100644
--- a/drivers/scsi/sata_promise.c
+++ b/drivers/scsi/sata_promise.c
@@ -438,11 +438,11 @@
 		break;
 
         default:
-                ap->stats.idle_irq++;
-                break;
+		ap->stats.idle_irq++;
+		break;
         }
 
-        return handled;
+	return handled;
 }
 
 static void pdc_irq_clear(struct ata_port *ap)
diff --git a/include/linux/ata.h b/include/linux/ata.h
index a5b74ef..ecb7346 100644
--- a/include/linux/ata.h
+++ b/include/linux/ata.h
@@ -132,6 +132,7 @@
 	ATA_CMD_PACKET		= 0xA0,
 	ATA_CMD_VERIFY		= 0x40,
 	ATA_CMD_VERIFY_EXT	= 0x42,
+	ATA_CMD_INIT_DEV_PARAMS	= 0x91,
 
 	/* SETFEATURES stuff */
 	SETFEATURES_XFER	= 0x03,
@@ -146,14 +147,14 @@
 	XFER_MW_DMA_2		= 0x22,
 	XFER_MW_DMA_1		= 0x21,
 	XFER_MW_DMA_0		= 0x20,
+	XFER_SW_DMA_2		= 0x12,
+	XFER_SW_DMA_1		= 0x11,
+	XFER_SW_DMA_0		= 0x10,
 	XFER_PIO_4		= 0x0C,
 	XFER_PIO_3		= 0x0B,
 	XFER_PIO_2		= 0x0A,
 	XFER_PIO_1		= 0x09,
 	XFER_PIO_0		= 0x08,
-	XFER_SW_DMA_2		= 0x12,
-	XFER_SW_DMA_1		= 0x11,
-	XFER_SW_DMA_0		= 0x10,
 	XFER_PIO_SLOW		= 0x00,
 
 	/* ATAPI stuff */
@@ -181,6 +182,7 @@
 	ATA_TFLAG_ISADDR	= (1 << 1), /* enable r/w to nsect/lba regs */
 	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 */
 };
 
 enum ata_tf_protocols {
@@ -250,6 +252,18 @@
 	  ((u64) (id)[(n) + 1] << 16) |	\
 	  ((u64) (id)[(n) + 0]) )
 
+static inline int ata_id_current_chs_valid(u16 *id)
+{
+	/* For ATA-1 devices, if the INITIALIZE DEVICE PARAMETERS command 
+	   has not been issued to the device then the values of 
+	   id[54] to id[56] are vendor specific. */
+	return (id[53] & 0x01) && /* Current translation valid */
+		id[54] &&  /* cylinders in current translation */
+		id[55] &&  /* heads in current translation */
+		id[55] <= 16 &&
+		id[56];    /* sectors in current translation */
+}
+
 static inline int atapi_cdb_len(u16 *dev_id)
 {
 	u16 tmp = dev_id[0] & 0x3;
diff --git a/include/linux/libata.h b/include/linux/libata.h
index ceee1fc..4739a75 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -97,6 +97,7 @@
 	ATA_DFLAG_LBA48		= (1 << 0), /* device supports LBA48 */
 	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_DEV_UNKNOWN		= 0,	/* unknown device */
 	ATA_DEV_ATA		= 1,	/* ATA device */
@@ -156,15 +157,15 @@
 	ATA_SHIFT_PIO		= 11,
 };
 
-enum pio_task_states {
-	PIO_ST_UNKNOWN,
-	PIO_ST_IDLE,
-	PIO_ST_POLL,
-	PIO_ST_TMOUT,
-	PIO_ST,
-	PIO_ST_LAST,
-	PIO_ST_LAST_POLL,
-	PIO_ST_ERR,
+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,
 };
 
 /* forward declarations */
@@ -282,6 +283,11 @@
 	u8			xfer_protocol;	/* taskfile xfer protocol */
 	u8			read_cmd;	/* opcode to use on read */
 	u8			write_cmd;	/* opcode to use on write */
+
+	/* for CHS addressing */
+	u16			cylinders;	/* Number of cylinders */
+	u16			heads;		/* Number of heads */
+	u16			sectors;	/* Number of sectors per track */
 };
 
 struct ata_port {
@@ -319,7 +325,7 @@
 	struct work_struct	packet_task;
 
 	struct work_struct	pio_task;
-	unsigned int		pio_task_state;
+	unsigned int		hsm_task_state;
 	unsigned long		pio_task_timeout;
 
 	void			*private_data;