Re: 2.6.31-rc5 regression: hd don't show up

[Tejun Heo <tj@kernel.org>]

[-- Attachment #1: Type: text/plain, Size: 459 bytes --]

Tim Blechmann wrote:
>> Can you please try the attached patch and report the result?  The bug
>> shouldn't happen now and for cases where it would have happened,
>> libata will report "link online but device misclassified" and retry.
> 
> this patch cannot be applied onto stable-2.6.31/master ... e.g. the
> first chunk is already in there ....

Eh... the first chunk was for the current devel branch.  Here's a
version without that one.

Thanks.

-- 
tejun

[-- Attachment #2: fix-link-onoffline-handling.patch --]
[-- Type: text/x-patch, Size: 3348 bytes --]

---
 drivers/ata/libata-eh.c |   50 ++++++++++++++++++++++++++++++------------------
 1 file changed, 32 insertions(+), 18 deletions(-)

Index: tree0/drivers/ata/libata-eh.c
===================================================================
--- tree0.orig/drivers/ata/libata-eh.c
+++ tree0/drivers/ata/libata-eh.c
@@ -2541,14 +2541,14 @@ int ata_eh_reset(struct ata_link *link,
 		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 */
@@ -2581,34 +2581,48 @@ int ata_eh_reset(struct ata_link *link,
 		slave->eh_info.serror = 0;
 	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 */