[PATCH] libata: improve ata_bus_probe()

Improve ata_bus_probe() such that configuration failures are handled
better.  Each device is given ATA_PROBE_MAX_TRIES chances, but any
non-transient error (revalidation failure with -ENODEV, configuration
failure with -EINVAL...) disables the device directly.  Any IO error
results in SATA PHY speed down and ata_set_mode() failure lowers
transfer mode.  The last try always puts a device into PIO-0.

After each failure, the whole port is reset to make sure that the
controller and all the devices are in a known and stable state.  The
reset also applies SATA SPD configuration if necessary.

Signed-off-by: Tejun Heo <htejun@gmail.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>

2 files changed, 52 insertions, 16 deletions

diff --git a/drivers/scsi/libata-core.c b/drivers/scsi/libata-core.c
index 68fa64d24721..33b5bff58cc3 100644
--- a/drivers/scsi/libata-core.c
+++ b/drivers/scsi/libata-core.c
@@ -1370,11 +1370,18 @@ err_out_nosup:
 static int ata_bus_probe(struct ata_port *ap)
 {
         unsigned int classes[ATA_MAX_DEVICES];
-        int i, rc, found = 0;
+        int tries[ATA_MAX_DEVICES];
+        int i, rc, down_xfermask;
         struct ata_device *dev;
 
         ata_port_probe(ap);
 
+        for (i = 0; i < ATA_MAX_DEVICES; i++)
+                tries[i] = ATA_PROBE_MAX_TRIES;
+
+ retry:
+        down_xfermask = 0;
+
         /* reset and determine device classes */
         for (i = 0; i < ATA_MAX_DEVICES; i++)
                 classes[i] = ATA_DEV_UNKNOWN;
@@ -1404,21 +1411,23 @@ static int ata_bus_probe(struct ata_port *ap)
                 dev = &ap->device[i];
                 dev->class = classes[i];
 
-                if (!ata_dev_enabled(dev))
-                        continue;
-
-                WARN_ON(dev->id != NULL);
-                if (ata_dev_read_id(ap, dev, &dev->class, 1, &dev->id)) {
-                        dev->class = ATA_DEV_NONE;
-                        continue;
+                if (!tries[i]) {
+                        ata_down_xfermask_limit(ap, dev, 1);
+                        ata_dev_disable(ap, dev);
                 }
 
-                if (ata_dev_configure(ap, dev, 1)) {
-                        ata_dev_disable(ap, dev);
+                if (!ata_dev_enabled(dev))
                         continue;
-                }
 
-                found = 1;
+                kfree(dev->id);
+                dev->id = NULL;
+                rc = ata_dev_read_id(ap, dev, &dev->class, 1, &dev->id);
+                if (rc)
+                        goto fail;
+
+                rc = ata_dev_configure(ap, dev, 1);
+                if (rc)
+                        goto fail;
         }
 
         /* configure transfer mode */
@@ -1427,12 +1436,18 @@ static int ata_bus_probe(struct ata_port *ap)
                  * return error code and failing device on failure as
                  * ata_set_mode() does.
                  */
-                if (found)
-                        ap->ops->set_mode(ap);
+                for (i = 0; i < ATA_MAX_DEVICES; i++)
+                        if (ata_dev_enabled(&ap->device[i])) {
+                                ap->ops->set_mode(ap);
+                                break;
+                        }
                 rc = 0;
         } else {
-                while (ata_set_mode(ap, &dev))
-                        ata_dev_disable(ap, dev);
+                rc = ata_set_mode(ap, &dev);
+                if (rc) {
+                        down_xfermask = 1;
+                        goto fail;
+                }
         }
 
         for (i = 0; i < ATA_MAX_DEVICES; i++)
@@ -1443,6 +1458,24 @@ static int ata_bus_probe(struct ata_port *ap)
         ata_port_disable(ap);
         ap->ops->port_disable(ap);
         return -ENODEV;
+
+ fail:
+        switch (rc) {
+        case -EINVAL:
+        case -ENODEV:
+                tries[dev->devno] = 0;
+                break;
+        case -EIO:
+                ata_down_sata_spd_limit(ap);
+                /* fall through */
+        default:
+                tries[dev->devno]--;
+                if (down_xfermask &&
+                    ata_down_xfermask_limit(ap, dev, tries[dev->devno] == 1))
+                        tries[dev->devno] = 0;
+        }
+
+        goto retry;
 }
 
 /**
diff --git a/include/linux/libata.h b/include/linux/libata.h
index a5207e66ca52..a4a1e6304e78 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -211,6 +211,9 @@ enum {
         /* Masks for port functions */
         ATA_PORT_PRIMARY        = (1 << 0),
         ATA_PORT_SECONDARY      = (1 << 1),
+
+        /* how hard are we gonna try to probe/recover devices */
+        ATA_PROBE_MAX_TRIES     = 3,
 };
 
 enum hsm_task_states {