1 files changed, 130 insertions, 20 deletions

diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index a04488f0de88..0ea97c942ced 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -110,6 +110,13 @@ static const unsigned long ata_eh_identify_timeouts[] = {
 	ULONG_MAX,
 };
 
+static const unsigned long ata_eh_flush_timeouts[] = {
+	15000,	/* be generous with flush */
+	15000,  /* ditto */
+	30000,	/* and even more generous */
+	ULONG_MAX,
+};
+
 static const unsigned long ata_eh_other_timeouts[] = {
 	 5000,	/* same rationale as identify timeout */
 	10000,	/* ditto */
@@ -147,6 +154,8 @@ ata_eh_cmd_timeout_table[ATA_EH_CMD_TIMEOUT_TABLE_SIZE] = {
 	  .timeouts = ata_eh_other_timeouts, },
 	{ .commands = CMDS(ATA_CMD_INIT_DEV_PARAMS),
 	  .timeouts = ata_eh_other_timeouts, },
+	{ .commands = CMDS(ATA_CMD_FLUSH, ATA_CMD_FLUSH_EXT),
+	  .timeouts = ata_eh_flush_timeouts },
 };
 #undef CMDS
 
@@ -2667,14 +2676,14 @@ int ata_eh_reset(struct ata_link *link, int classify,
 		dev->pio_mode = XFER_PIO_0;
 		dev->flags &= ~ATA_DFLAG_SLEEPING;
 
-		if (!ata_phys_link_offline(ata_dev_phys_link(dev))) {
-			/* apply class override */
-			if (lflags & ATA_LFLAG_ASSUME_ATA)
-				classes[dev->devno] = ATA_DEV_ATA;
-			else if (lflags & ATA_LFLAG_ASSUME_SEMB)
-				classes[dev->devno] = ATA_DEV_SEMB_UNSUP;
-		} else
-			classes[dev->devno] = ATA_DEV_NONE;
+		if (ata_phys_link_offline(ata_dev_phys_link(dev)))
+			continue;
+
+		/* apply class override */
+		if (lflags & ATA_LFLAG_ASSUME_ATA)
+			classes[dev->devno] = ATA_DEV_ATA;
+		else if (lflags & ATA_LFLAG_ASSUME_SEMB)
+			classes[dev->devno] = ATA_DEV_SEMB_UNSUP;
 	}
 
 	/* record current link speed */
@@ -2713,34 +2722,48 @@ int ata_eh_reset(struct ata_link *link, int classify,
 	ap->pflags &= ~ATA_PFLAG_EH_PENDING;
 	spin_unlock_irqrestore(link->ap->lock, flags);
 
-	/* Make sure onlineness and classification result correspond.
+	/*
+	 * Make sure onlineness and classification result correspond.
 	 * Hotplug could have happened during reset and some
 	 * controllers fail to wait while a drive is spinning up after
 	 * being hotplugged causing misdetection.  By cross checking
-	 * link onlineness and classification result, those conditions
-	 * can be reliably detected and retried.
+	 * link on/offlineness and classification result, those
+	 * conditions can be reliably detected and retried.
 	 */
 	nr_unknown = 0;
 	ata_for_each_dev(dev, link, ALL) {
-		/* convert all ATA_DEV_UNKNOWN to ATA_DEV_NONE */
-		if (classes[dev->devno] == ATA_DEV_UNKNOWN) {
-			classes[dev->devno] = ATA_DEV_NONE;
-			if (ata_phys_link_online(ata_dev_phys_link(dev)))
+		if (ata_phys_link_online(ata_dev_phys_link(dev))) {
+			if (classes[dev->devno] == ATA_DEV_UNKNOWN) {
+				ata_dev_printk(dev, KERN_DEBUG, "link online "
+					       "but device misclassifed\n");
+				classes[dev->devno] = ATA_DEV_NONE;
 				nr_unknown++;
+			}
+		} else if (ata_phys_link_offline(ata_dev_phys_link(dev))) {
+			if (ata_class_enabled(classes[dev->devno]))
+				ata_dev_printk(dev, KERN_DEBUG, "link offline, "
+					       "clearing class %d to NONE\n",
+					       classes[dev->devno]);
+			classes[dev->devno] = ATA_DEV_NONE;
+		} else if (classes[dev->devno] == ATA_DEV_UNKNOWN) {
+			ata_dev_printk(dev, KERN_DEBUG, "link status unknown, "
+				       "clearing UNKNOWN to NONE\n");
+			classes[dev->devno] = ATA_DEV_NONE;
 		}
 	}
 
 	if (classify && nr_unknown) {
 		if (try < max_tries) {
 			ata_link_printk(link, KERN_WARNING, "link online but "
-				       "device misclassified, retrying\n");
+					"%d devices misclassified, retrying\n",
+					nr_unknown);
 			failed_link = link;
 			rc = -EAGAIN;
 			goto fail;
 		}
 		ata_link_printk(link, KERN_WARNING,
-			       "link online but device misclassified, "
-			       "device detection might fail\n");
+				"link online but %d devices misclassified, "
+				"device detection might fail\n", nr_unknown);
 	}
 
 	/* reset successful, schedule revalidation */
@@ -2967,12 +2990,14 @@ static int ata_eh_revalidate_and_attach(struct ata_link *link,
 	 * device detection messages backwards.
 	 */
 	ata_for_each_dev(dev, link, ALL) {
-		if (!(new_mask & (1 << dev->devno)) ||
-		    dev->class == ATA_DEV_PMP)
+		if (!(new_mask & (1 << dev->devno)))
 			continue;
 
 		dev->class = ehc->classes[dev->devno];
 
+		if (dev->class == ATA_DEV_PMP)
+			continue;
+
 		ehc->i.flags |= ATA_EHI_PRINTINFO;
 		rc = ata_dev_configure(dev);
 		ehc->i.flags &= ~ATA_EHI_PRINTINFO;
@@ -3096,6 +3121,82 @@ static int atapi_eh_clear_ua(struct ata_device *dev)
 	return 0;
 }
 
+/**
+ *	ata_eh_maybe_retry_flush - Retry FLUSH if necessary
+ *	@dev: ATA device which may need FLUSH retry
+ *
+ *	If @dev failed FLUSH, it needs to be reported upper layer
+ *	immediately as it means that @dev failed to remap and already
+ *	lost at least a sector and further FLUSH retrials won't make
+ *	any difference to the lost sector.  However, if FLUSH failed
+ *	for other reasons, for example transmission error, FLUSH needs
+ *	to be retried.
+ *
+ *	This function determines whether FLUSH failure retry is
+ *	necessary and performs it if so.
+ *
+ *	RETURNS:
+ *	0 if EH can continue, -errno if EH needs to be repeated.
+ */
+static int ata_eh_maybe_retry_flush(struct ata_device *dev)
+{
+	struct ata_link *link = dev->link;
+	struct ata_port *ap = link->ap;
+	struct ata_queued_cmd *qc;
+	struct ata_taskfile tf;
+	unsigned int err_mask;
+	int rc = 0;
+
+	/* did flush fail for this device? */
+	if (!ata_tag_valid(link->active_tag))
+		return 0;
+
+	qc = __ata_qc_from_tag(ap, link->active_tag);
+	if (qc->dev != dev || (qc->tf.command != ATA_CMD_FLUSH_EXT &&
+			       qc->tf.command != ATA_CMD_FLUSH))
+		return 0;
+
+	/* if the device failed it, it should be reported to upper layers */
+	if (qc->err_mask & AC_ERR_DEV)
+		return 0;
+
+	/* flush failed for some other reason, give it another shot */
+	ata_tf_init(dev, &tf);
+
+	tf.command = qc->tf.command;
+	tf.flags |= ATA_TFLAG_DEVICE;
+	tf.protocol = ATA_PROT_NODATA;
+
+	ata_dev_printk(dev, KERN_WARNING, "retrying FLUSH 0x%x Emask 0x%x\n",
+		       tf.command, qc->err_mask);
+
+	err_mask = ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, 0);
+	if (!err_mask) {
+		/*
+		 * FLUSH is complete but there's no way to
+		 * successfully complete a failed command from EH.
+		 * Making sure retry is allowed at least once and
+		 * retrying it should do the trick - whatever was in
+		 * the cache is already on the platter and this won't
+		 * cause infinite loop.
+		 */
+		qc->scsicmd->allowed = max(qc->scsicmd->allowed, 1);
+	} else {
+		ata_dev_printk(dev, KERN_WARNING, "FLUSH failed Emask 0x%x\n",
+			       err_mask);
+		rc = -EIO;
+
+		/* if device failed it, report it to upper layers */
+		if (err_mask & AC_ERR_DEV) {
+			qc->err_mask |= AC_ERR_DEV;
+			qc->result_tf = tf;
+			if (!(ap->pflags & ATA_PFLAG_FROZEN))
+				rc = 0;
+		}
+	}
+	return rc;
+}
+
 static int ata_link_nr_enabled(struct ata_link *link)
 {
 	struct ata_device *dev;
@@ -3439,6 +3540,15 @@ int ata_eh_recover(struct ata_port *ap, ata_prereset_fn_t prereset,
 			}
 		}
 
+		/* retry flush if necessary */
+		ata_for_each_dev(dev, link, ALL) {
+			if (dev->class != ATA_DEV_ATA)
+				continue;
+			rc = ata_eh_maybe_retry_flush(dev);
+			if (rc)
+				goto dev_fail;
+		}
+
 		/* configure link power saving */
 		if (ehc->i.action & ATA_EH_LPM)
 			ata_for_each_dev(dev, link, ALL)