libata: Implement disk shock protection support

On user request (through sysfs), the IDLE IMMEDIATE command with UNLOAD
FEATURE as specified in ATA-7 is issued to the device and processing of
the request queue is stopped thereafter until the specified timeout
expires or user space asks to resume normal operation. This is supposed
to prevent the heads of a hard drive from accidentally crashing onto the
platter when a heavy shock is anticipated (like a falling laptop
expected to hit the floor). In fact, the whole port stops processing
commands until the timeout has expired in order to avoid any resets due
to failed commands on another device.

Signed-off-by: Elias Oltmanns <eo@nebensachen.de>
Signed-off-by: Jeff Garzik <jgarzik@redhat.com>
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 6acea41..aeadd00 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -316,6 +316,7 @@
 
 static struct device_attribute *ahci_sdev_attrs[] = {
 	&dev_attr_sw_activity,
+	&dev_attr_unload_heads,
 	NULL
 };
 
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 6eed58e..1ee9499 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -5378,6 +5378,7 @@
 	INIT_WORK(&ap->scsi_rescan_task, ata_scsi_dev_rescan);
 	INIT_LIST_HEAD(&ap->eh_done_q);
 	init_waitqueue_head(&ap->eh_wait_q);
+	init_completion(&ap->park_req_pending);
 	init_timer_deferrable(&ap->fastdrain_timer);
 	ap->fastdrain_timer.function = ata_eh_fastdrain_timerfn;
 	ap->fastdrain_timer.data = (unsigned long)ap;
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index 99037a4..33ac5ea 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -2536,6 +2536,80 @@
 	goto retry;
 }
 
+static inline void ata_eh_pull_park_action(struct ata_port *ap)
+{
+	struct ata_link *link;
+	struct ata_device *dev;
+	unsigned long flags;
+
+	/*
+	 * This function can be thought of as an extended version of
+	 * ata_eh_about_to_do() specially crafted to accommodate the
+	 * requirements of ATA_EH_PARK handling. Since the EH thread
+	 * does not leave the do {} while () loop in ata_eh_recover as
+	 * long as the timeout for a park request to *one* device on
+	 * the port has not expired, and since we still want to pick
+	 * up park requests to other devices on the same port or
+	 * timeout updates for the same device, we have to pull
+	 * ATA_EH_PARK actions from eh_info into eh_context.i
+	 * ourselves at the beginning of each pass over the loop.
+	 *
+	 * Additionally, all write accesses to &ap->park_req_pending
+	 * through INIT_COMPLETION() (see below) or complete_all()
+	 * (see ata_scsi_park_store()) are protected by the host lock.
+	 * As a result we have that park_req_pending.done is zero on
+	 * exit from this function, i.e. when ATA_EH_PARK actions for
+	 * *all* devices on port ap have been pulled into the
+	 * respective eh_context structs. If, and only if,
+	 * park_req_pending.done is non-zero by the time we reach
+	 * wait_for_completion_timeout(), another ATA_EH_PARK action
+	 * has been scheduled for at least one of the devices on port
+	 * ap and we have to cycle over the do {} while () loop in
+	 * ata_eh_recover() again.
+	 */
+
+	spin_lock_irqsave(ap->lock, flags);
+	INIT_COMPLETION(ap->park_req_pending);
+	ata_port_for_each_link(link, ap) {
+		ata_link_for_each_dev(dev, link) {
+			struct ata_eh_info *ehi = &link->eh_info;
+
+			link->eh_context.i.dev_action[dev->devno] |=
+				ehi->dev_action[dev->devno] & ATA_EH_PARK;
+			ata_eh_clear_action(link, dev, ehi, ATA_EH_PARK);
+		}
+	}
+	spin_unlock_irqrestore(ap->lock, flags);
+}
+
+static void ata_eh_park_issue_cmd(struct ata_device *dev, int park)
+{
+	struct ata_eh_context *ehc = &dev->link->eh_context;
+	struct ata_taskfile tf;
+	unsigned int err_mask;
+
+	ata_tf_init(dev, &tf);
+	if (park) {
+		ehc->unloaded_mask |= 1 << dev->devno;
+		tf.command = ATA_CMD_IDLEIMMEDIATE;
+		tf.feature = 0x44;
+		tf.lbal = 0x4c;
+		tf.lbam = 0x4e;
+		tf.lbah = 0x55;
+	} else {
+		ehc->unloaded_mask &= ~(1 << dev->devno);
+		tf.command = ATA_CMD_CHK_POWER;
+	}
+
+	tf.flags |= ATA_TFLAG_DEVICE | ATA_TFLAG_ISADDR;
+	tf.protocol |= ATA_PROT_NODATA;
+	err_mask = ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, 0);
+	if (park && (err_mask || tf.lbal != 0xc4)) {
+		ata_dev_printk(dev, KERN_ERR, "head unload failed!\n");
+		ehc->unloaded_mask &= ~(1 << dev->devno);
+	}
+}
+
 static int ata_eh_revalidate_and_attach(struct ata_link *link,
 					struct ata_device **r_failed_dev)
 {
@@ -2845,7 +2919,7 @@
 	struct ata_device *dev;
 	int nr_failed_devs;
 	int rc;
-	unsigned long flags;
+	unsigned long flags, deadline;
 
 	DPRINTK("ENTER\n");
 
@@ -2919,6 +2993,56 @@
 		}
 	}
 
+	do {
+		unsigned long now;
+
+		/*
+		 * clears ATA_EH_PARK in eh_info and resets
+		 * ap->park_req_pending
+		 */
+		ata_eh_pull_park_action(ap);
+
+		deadline = jiffies;
+		ata_port_for_each_link(link, ap) {
+			ata_link_for_each_dev(dev, link) {
+				struct ata_eh_context *ehc = &link->eh_context;
+				unsigned long tmp;
+
+				if (dev->class != ATA_DEV_ATA)
+					continue;
+				if (!(ehc->i.dev_action[dev->devno] &
+				      ATA_EH_PARK))
+					continue;
+				tmp = dev->unpark_deadline;
+				if (time_before(deadline, tmp))
+					deadline = tmp;
+				else if (time_before_eq(tmp, jiffies))
+					continue;
+				if (ehc->unloaded_mask & (1 << dev->devno))
+					continue;
+
+				ata_eh_park_issue_cmd(dev, 1);
+			}
+		}
+
+		now = jiffies;
+		if (time_before_eq(deadline, now))
+			break;
+
+		deadline = wait_for_completion_timeout(&ap->park_req_pending,
+						       deadline - now);
+	} while (deadline);
+	ata_port_for_each_link(link, ap) {
+		ata_link_for_each_dev(dev, link) {
+			if (!(link->eh_context.unloaded_mask &
+			      (1 << dev->devno)))
+				continue;
+
+			ata_eh_park_issue_cmd(dev, 0);
+			ata_eh_done(link, dev, ATA_EH_PARK);
+		}
+	}
+
 	/* the rest */
 	ata_port_for_each_link(link, ap) {
 		struct ata_eh_context *ehc = &link->eh_context;
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index b9d3ba4..fccd5e4 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -183,6 +183,105 @@
 		ata_scsi_lpm_show, ata_scsi_lpm_put);
 EXPORT_SYMBOL_GPL(dev_attr_link_power_management_policy);
 
+static ssize_t ata_scsi_park_show(struct device *device,
+				  struct device_attribute *attr, char *buf)
+{
+	struct scsi_device *sdev = to_scsi_device(device);
+	struct ata_port *ap;
+	struct ata_link *link;
+	struct ata_device *dev;
+	unsigned long flags;
+	unsigned int uninitialized_var(msecs);
+	int rc = 0;
+
+	ap = ata_shost_to_port(sdev->host);
+
+	spin_lock_irqsave(ap->lock, flags);
+	dev = ata_scsi_find_dev(ap, sdev);
+	if (!dev) {
+		rc = -ENODEV;
+		goto unlock;
+	}
+	if (dev->flags & ATA_DFLAG_NO_UNLOAD) {
+		rc = -EOPNOTSUPP;
+		goto unlock;
+	}
+
+	link = dev->link;
+	if (ap->pflags & ATA_PFLAG_EH_IN_PROGRESS &&
+	    link->eh_context.unloaded_mask & (1 << dev->devno) &&
+	    time_after(dev->unpark_deadline, jiffies))
+		msecs = jiffies_to_msecs(dev->unpark_deadline - jiffies);
+	else
+		msecs = 0;
+
+unlock:
+	spin_unlock_irq(ap->lock);
+
+	return rc ? rc : snprintf(buf, 20, "%u\n", msecs);
+}
+
+static ssize_t ata_scsi_park_store(struct device *device,
+				   struct device_attribute *attr,
+				   const char *buf, size_t len)
+{
+	struct scsi_device *sdev = to_scsi_device(device);
+	struct ata_port *ap;
+	struct ata_device *dev;
+	long int input;
+	unsigned long flags;
+	int rc;
+
+	rc = strict_strtol(buf, 10, &input);
+	if (rc || input < -2)
+		return -EINVAL;
+	if (input > ATA_TMOUT_MAX_PARK) {
+		rc = -EOVERFLOW;
+		input = ATA_TMOUT_MAX_PARK;
+	}
+
+	ap = ata_shost_to_port(sdev->host);
+
+	spin_lock_irqsave(ap->lock, flags);
+	dev = ata_scsi_find_dev(ap, sdev);
+	if (unlikely(!dev)) {
+		rc = -ENODEV;
+		goto unlock;
+	}
+	if (dev->class != ATA_DEV_ATA) {
+		rc = -EOPNOTSUPP;
+		goto unlock;
+	}
+
+	if (input >= 0) {
+		if (dev->flags & ATA_DFLAG_NO_UNLOAD) {
+			rc = -EOPNOTSUPP;
+			goto unlock;
+		}
+
+		dev->unpark_deadline = ata_deadline(jiffies, input);
+		dev->link->eh_info.dev_action[dev->devno] |= ATA_EH_PARK;
+		ata_port_schedule_eh(ap);
+		complete(&ap->park_req_pending);
+	} else {
+		switch (input) {
+		case -1:
+			dev->flags &= ~ATA_DFLAG_NO_UNLOAD;
+			break;
+		case -2:
+			dev->flags |= ATA_DFLAG_NO_UNLOAD;
+			break;
+		}
+	}
+unlock:
+	spin_unlock_irqrestore(ap->lock, flags);
+
+	return rc ? rc : len;
+}
+DEVICE_ATTR(unload_heads, S_IRUGO | S_IWUSR,
+	    ata_scsi_park_show, ata_scsi_park_store);
+EXPORT_SYMBOL_GPL(dev_attr_unload_heads);
+
 static void ata_scsi_set_sense(struct scsi_cmnd *cmd, u8 sk, u8 asc, u8 ascq)
 {
 	cmd->result = (DRIVER_SENSE << 24) | SAM_STAT_CHECK_CONDITION;
@@ -269,6 +368,12 @@
 			ata_scsi_activity_store);
 EXPORT_SYMBOL_GPL(dev_attr_sw_activity);
 
+struct device_attribute *ata_common_sdev_attrs[] = {
+	&dev_attr_unload_heads,
+	NULL
+};
+EXPORT_SYMBOL_GPL(ata_common_sdev_attrs);
+
 static void ata_scsi_invalid_field(struct scsi_cmnd *cmd,
 				   void (*done)(struct scsi_cmnd *))
 {
@@ -954,6 +1059,9 @@
 static int ata_scsi_dev_config(struct scsi_device *sdev,
 			       struct ata_device *dev)
 {
+	if (!ata_id_has_unload(dev->id))
+		dev->flags |= ATA_DFLAG_NO_UNLOAD;
+
 	/* configure max sectors */
 	blk_queue_max_sectors(sdev->request_queue, dev->max_sectors);