[libata] Link power management infrastructure

Device Initiated Power Management, which is defined
in SATA 2.5 can be enabled for disks which support it.
This patch enables DIPM when the user sets the link
power management policy to "min_power".

Additionally, libata drivers can define a function
(enable_pm) that will perform hardware specific actions to
enable whatever power management policy the user set up
for Host Initiated Power management (HIPM).
This power management policy will be activated after all
disks have been enumerated and intialized.  Drivers should
also define disable_pm, which will turn off link power
management, but not change link power management policy.

Documentation/scsi/link_power_management_policy.txt has additional
information.

Signed-off-by:  Kristen Carlson Accardi <kristen.c.accardi@intel.com>
Signed-off-by: Jeff Garzik <jgarzik@redhat.com>
diff --git a/Documentation/scsi/link_power_management_policy.txt b/Documentation/scsi/link_power_management_policy.txt
new file mode 100644
index 0000000..d18993d
--- /dev/null
+++ b/Documentation/scsi/link_power_management_policy.txt
@@ -0,0 +1,19 @@
+This parameter allows the user to set the link (interface) power management.
+There are 3 possible options:
+
+Value			Effect
+----------------------------------------------------------------------------
+min_power		Tell the controller to try to make the link use the
+			least possible power when possible.  This may
+			sacrifice some performance due to increased latency
+			when coming out of lower power states.
+
+max_performance		Generally, this means no power management.  Tell
+			the controller to have performance be a priority
+			over power management.
+
+medium_power		Tell the controller to enter a lower power state
+			when possible, but do not enter the lowest power
+			state, thus improving latency over min_power setting.
+
+
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 3891cdc..513babe 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -620,6 +620,177 @@
 	}
 }
 
+static int ata_dev_set_dipm(struct ata_device *dev, enum link_pm policy)
+{
+	struct ata_link *link = dev->link;
+	struct ata_port *ap = link->ap;
+	u32 scontrol;
+	unsigned int err_mask;
+	int rc;
+
+	/*
+	 * disallow DIPM for drivers which haven't set
+	 * ATA_FLAG_IPM.  This is because when DIPM is enabled,
+	 * phy ready will be set in the interrupt status on
+	 * state changes, which will cause some drivers to
+	 * think there are errors - additionally drivers will
+	 * need to disable hot plug.
+	 */
+	if (!(ap->flags & ATA_FLAG_IPM) || !ata_dev_enabled(dev)) {
+		ap->pm_policy = NOT_AVAILABLE;
+		return -EINVAL;
+	}
+
+	/*
+	 * For DIPM, we will only enable it for the
+	 * min_power setting.
+	 *
+	 * Why?  Because Disks are too stupid to know that
+	 * If the host rejects a request to go to SLUMBER
+	 * they should retry at PARTIAL, and instead it
+	 * just would give up.  So, for medium_power to
+	 * work at all, we need to only allow HIPM.
+	 */
+	rc = sata_scr_read(link, SCR_CONTROL, &scontrol);
+	if (rc)
+		return rc;
+
+	switch (policy) {
+	case MIN_POWER:
+		/* no restrictions on IPM transitions */
+		scontrol &= ~(0x3 << 8);
+		rc = sata_scr_write(link, SCR_CONTROL, scontrol);
+		if (rc)
+			return rc;
+
+		/* enable DIPM */
+		if (dev->flags & ATA_DFLAG_DIPM)
+			err_mask = ata_dev_set_feature(dev,
+					SETFEATURES_SATA_ENABLE, SATA_DIPM);
+		break;
+	case MEDIUM_POWER:
+		/* allow IPM to PARTIAL */
+		scontrol &= ~(0x1 << 8);
+		scontrol |= (0x2 << 8);
+		rc = sata_scr_write(link, SCR_CONTROL, scontrol);
+		if (rc)
+			return rc;
+
+		/* disable DIPM */
+		if (ata_dev_enabled(dev) && (dev->flags & ATA_DFLAG_DIPM))
+			err_mask = ata_dev_set_feature(dev,
+					SETFEATURES_SATA_DISABLE, SATA_DIPM);
+		break;
+	case NOT_AVAILABLE:
+	case MAX_PERFORMANCE:
+		/* disable all IPM transitions */
+		scontrol |= (0x3 << 8);
+		rc = sata_scr_write(link, SCR_CONTROL, scontrol);
+		if (rc)
+			return rc;
+
+		/* disable DIPM */
+		if (ata_dev_enabled(dev) && (dev->flags & ATA_DFLAG_DIPM))
+			err_mask = ata_dev_set_feature(dev,
+					SETFEATURES_SATA_DISABLE, SATA_DIPM);
+		break;
+	}
+
+	/* FIXME: handle SET FEATURES failure */
+	(void) err_mask;
+
+	return 0;
+}
+
+/**
+ *	ata_dev_enable_pm - enable SATA interface power management
+ *	@device - device to enable ipm for
+ *	@policy - the link power management policy
+ *
+ *	Enable SATA Interface power management.  This will enable
+ *	Device Interface Power Management (DIPM) for min_power
+ * 	policy, and then call driver specific callbacks for
+ *	enabling Host Initiated Power management.
+ *
+ *	Locking: Caller.
+ *	Returns: -EINVAL if IPM is not supported, 0 otherwise.
+ */
+void ata_dev_enable_pm(struct ata_device *dev, enum link_pm policy)
+{
+	int rc = 0;
+	struct ata_port *ap = dev->link->ap;
+
+	/* set HIPM first, then DIPM */
+	if (ap->ops->enable_pm)
+		rc = ap->ops->enable_pm(ap, policy);
+	if (rc)
+		goto enable_pm_out;
+	rc = ata_dev_set_dipm(dev, policy);
+
+enable_pm_out:
+	if (rc)
+		ap->pm_policy = MAX_PERFORMANCE;
+	else
+		ap->pm_policy = policy;
+	return /* rc */;	/* hopefully we can use 'rc' eventually */
+}
+
+/**
+ *	ata_dev_disable_pm - disable SATA interface power management
+ *	@device - device to enable ipm for
+ *
+ *	Disable SATA Interface power management.  This will disable
+ *	Device Interface Power Management (DIPM) without changing
+ * 	policy,  call driver specific callbacks for disabling Host
+ * 	Initiated Power management.
+ *
+ *	Locking: Caller.
+ *	Returns: void
+ */
+static void ata_dev_disable_pm(struct ata_device *dev)
+{
+	struct ata_port *ap = dev->link->ap;
+
+	ata_dev_set_dipm(dev, MAX_PERFORMANCE);
+	if (ap->ops->disable_pm)
+		ap->ops->disable_pm(ap);
+}
+
+void ata_lpm_schedule(struct ata_port *ap, enum link_pm policy)
+{
+	ap->pm_policy = policy;
+	ap->link.eh_info.action |= ATA_EHI_LPM;
+	ap->link.eh_info.flags |= ATA_EHI_NO_AUTOPSY;
+	ata_port_schedule_eh(ap);
+}
+
+static void ata_lpm_enable(struct ata_host *host)
+{
+	struct ata_link *link;
+	struct ata_port *ap;
+	struct ata_device *dev;
+	int i;
+
+	for (i = 0; i < host->n_ports; i++) {
+		ap = host->ports[i];
+		ata_port_for_each_link(link, ap) {
+			ata_link_for_each_dev(dev, link)
+				ata_dev_disable_pm(dev);
+		}
+	}
+}
+
+static void ata_lpm_disable(struct ata_host *host)
+{
+	int i;
+
+	for (i = 0; i < host->n_ports; i++) {
+		struct ata_port *ap = host->ports[i];
+		ata_lpm_schedule(ap, ap->pm_policy);
+	}
+}
+
+
 /**
  *	ata_devchk - PATA device presence detection
  *	@ap: ATA channel to examine
@@ -2101,6 +2272,13 @@
 	if (dev->flags & ATA_DFLAG_LBA48)
 		dev->max_sectors = ATA_MAX_SECTORS_LBA48;
 
+	if (!(dev->horkage & ATA_HORKAGE_IPM)) {
+		if (ata_id_has_hipm(dev->id))
+			dev->flags |= ATA_DFLAG_HIPM;
+		if (ata_id_has_dipm(dev->id))
+			dev->flags |= ATA_DFLAG_DIPM;
+	}
+
 	if (dev->horkage & ATA_HORKAGE_DIAGNOSTIC) {
 		/* Let the user know. We don't want to disallow opens for
 		   rescue purposes, or in case the vendor is just a blithering
@@ -2126,6 +2304,13 @@
 		dev->max_sectors = min_t(unsigned int, ATA_MAX_SECTORS_128,
 					 dev->max_sectors);
 
+	if (ata_dev_blacklisted(dev) & ATA_HORKAGE_IPM) {
+		dev->horkage |= ATA_HORKAGE_IPM;
+
+		/* reset link pm_policy for this port to no pm */
+		ap->pm_policy = MAX_PERFORMANCE;
+	}
+
 	if (ap->ops->dev_config)
 		ap->ops->dev_config(dev);
 
@@ -6361,6 +6546,12 @@
 {
 	int rc;
 
+	/*
+	 * disable link pm on all ports before requesting
+	 * any pm activity
+	 */
+	ata_lpm_enable(host);
+
 	rc = ata_host_request_pm(host, mesg, 0, ATA_EHI_QUIET, 1);
 	if (rc == 0)
 		host->dev->power.power_state = mesg;
@@ -6383,6 +6574,9 @@
 	ata_host_request_pm(host, PMSG_ON, ATA_EH_SOFTRESET,
 			    ATA_EHI_NO_AUTOPSY | ATA_EHI_QUIET, 0);
 	host->dev->power.power_state = PMSG_ON;
+
+	/* reenable link pm */
+	ata_lpm_disable(host);
 }
 #endif
 
@@ -6925,6 +7119,7 @@
 		struct ata_port *ap = host->ports[i];
 
 		ata_scsi_scan_host(ap, 1);
+		ata_lpm_schedule(ap, ap->pm_policy);
 	}
 
 	return 0;
@@ -7321,7 +7516,6 @@
  * likely to change as new drivers are added and updated.
  * Do not depend on ABI/API stability.
  */
-
 EXPORT_SYMBOL_GPL(sata_deb_timing_normal);
 EXPORT_SYMBOL_GPL(sata_deb_timing_hotplug);
 EXPORT_SYMBOL_GPL(sata_deb_timing_long);
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index ec55d63..fefea74 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -2628,6 +2628,10 @@
 			ehc->i.flags &= ~ATA_EHI_SETMODE;
 		}
 
+		if (ehc->i.action & ATA_EHI_LPM)
+			ata_link_for_each_dev(dev, link)
+				ata_dev_enable_pm(dev, ap->pm_policy);
+
 		/* this link is okay now */
 		ehc->i.flags = 0;
 		continue;
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index f752edd..93bd36c 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -110,6 +110,74 @@
 };
 
 
+static const struct {
+	enum link_pm	value;
+	const char	*name;
+} link_pm_policy[] = {
+	{ NOT_AVAILABLE, "max_performance" },
+	{ MIN_POWER, "min_power" },
+	{ MAX_PERFORMANCE, "max_performance" },
+	{ MEDIUM_POWER, "medium_power" },
+};
+
+const char *ata_scsi_lpm_get(enum link_pm policy)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(link_pm_policy); i++)
+		if (link_pm_policy[i].value == policy)
+			return link_pm_policy[i].name;
+
+	return NULL;
+}
+
+static ssize_t ata_scsi_lpm_put(struct class_device *class_dev,
+	const char *buf, size_t count)
+{
+	struct Scsi_Host *shost = class_to_shost(class_dev);
+	struct ata_port *ap = ata_shost_to_port(shost);
+	enum link_pm policy = 0;
+	int i;
+
+	/*
+	 * we are skipping array location 0 on purpose - this
+	 * is because a value of NOT_AVAILABLE is displayed
+	 * to the user as max_performance, but when the user
+	 * writes "max_performance", they actually want the
+	 * value to match MAX_PERFORMANCE.
+	 */
+	for (i = 1; i < ARRAY_SIZE(link_pm_policy); i++) {
+		const int len = strlen(link_pm_policy[i].name);
+		if (strncmp(link_pm_policy[i].name, buf, len) == 0 &&
+		   buf[len] == '\n') {
+			policy = link_pm_policy[i].value;
+			break;
+		}
+	}
+	if (!policy)
+		return -EINVAL;
+
+	ata_lpm_schedule(ap, policy);
+	return count;
+}
+
+static ssize_t
+ata_scsi_lpm_show(struct class_device *class_dev, char *buf)
+{
+	struct Scsi_Host *shost = class_to_shost(class_dev);
+	struct ata_port *ap = ata_shost_to_port(shost);
+	const char *policy =
+		ata_scsi_lpm_get(ap->pm_policy);
+
+	if (!policy)
+		return -EINVAL;
+
+	return snprintf(buf, 23, "%s\n", policy);
+}
+CLASS_DEVICE_ATTR(link_power_management_policy, S_IRUGO | S_IWUSR,
+		ata_scsi_lpm_show, ata_scsi_lpm_put);
+EXPORT_SYMBOL_GPL(class_device_attr_link_power_management_policy);
+
 static void ata_scsi_invalid_field(struct scsi_cmnd *cmd,
 				   void (*done)(struct scsi_cmnd *))
 {
diff --git a/drivers/ata/libata.h b/drivers/ata/libata.h
index 90df58a..0e6cf3a 100644
--- a/drivers/ata/libata.h
+++ b/drivers/ata/libata.h
@@ -101,6 +101,8 @@
 extern int ata_task_ioctl(struct scsi_device *scsidev, void __user *arg);
 extern int ata_cmd_ioctl(struct scsi_device *scsidev, void __user *arg);
 extern struct ata_port *ata_port_alloc(struct ata_host *host);
+extern void ata_dev_enable_pm(struct ata_device *dev, enum link_pm policy);
+extern void ata_lpm_schedule(struct ata_port *ap, enum link_pm);
 
 /* libata-acpi.c */
 #ifdef CONFIG_ATA_ACPI
diff --git a/include/linux/ata.h b/include/linux/ata.h
index e21c002..128dc7a 100644
--- a/include/linux/ata.h
+++ b/include/linux/ata.h
@@ -236,6 +236,7 @@
 
 	/* SETFEATURE Sector counts for SATA features */
 	SATA_AN			= 0x05,  /* Asynchronous Notification */
+	SATA_DIPM		= 0x03,  /* Device Initiated Power Management */
 
 	/* ATAPI stuff */
 	ATAPI_PKT_DMA		= (1 << 0),
@@ -378,6 +379,26 @@
 
 #define ata_id_cdb_intr(id)	(((id)[0] & 0x60) == 0x20)
 
+static inline bool ata_id_has_hipm(const u16 *id)
+{
+	u16 val = id[76];
+
+	if (val == 0 || val == 0xffff)
+		return false;
+
+	return val & (1 << 9);
+}
+
+static inline bool ata_id_has_dipm(const u16 *id)
+{
+	u16 val = id[78];
+
+	if (val == 0 || val == 0xffff)
+		return false;
+
+	return val & (1 << 3);
+}
+
 static inline int ata_id_has_fua(const u16 *id)
 {
 	if ((id[84] & 0xC000) != 0x4000)
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 439d40f..147ccc4 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -133,6 +133,8 @@
 	ATA_DFLAG_ACPI_PENDING	= (1 << 5), /* ACPI resume action pending */
 	ATA_DFLAG_ACPI_FAILED	= (1 << 6), /* ACPI on devcfg has failed */
 	ATA_DFLAG_AN		= (1 << 7), /* AN configured */
+	ATA_DFLAG_HIPM		= (1 << 8), /* device supports HIPM */
+	ATA_DFLAG_DIPM		= (1 << 9), /* device supports DIPM */
 	ATA_DFLAG_CFG_MASK	= (1 << 12) - 1,
 
 	ATA_DFLAG_PIO		= (1 << 12), /* device limited to PIO mode */
@@ -186,6 +188,7 @@
 	ATA_FLAG_ACPI_SATA	= (1 << 17), /* need native SATA ACPI layout */
 	ATA_FLAG_AN		= (1 << 18), /* controller supports AN */
 	ATA_FLAG_PMP		= (1 << 19), /* controller supports PMP */
+	ATA_FLAG_IPM		= (1 << 20), /* driver can handle IPM */
 
 	/* The following flag belongs to ap->pflags but is kept in
 	 * ap->flags because it's referenced in many LLDs and will be
@@ -302,6 +305,7 @@
 	ATA_EHI_RESUME_LINK	= (1 << 1),  /* resume link (reset modifier) */
 	ATA_EHI_NO_AUTOPSY	= (1 << 2),  /* no autopsy */
 	ATA_EHI_QUIET		= (1 << 3),  /* be quiet */
+	ATA_EHI_LPM		= (1 << 4),  /* link power management action */
 
 	ATA_EHI_DID_SOFTRESET	= (1 << 16), /* already soft-reset this port */
 	ATA_EHI_DID_HARDRESET	= (1 << 17), /* already soft-reset this port */
@@ -333,6 +337,7 @@
 	ATA_HORKAGE_BROKEN_HPA	= (1 << 4),	/* Broken HPA */
 	ATA_HORKAGE_SKIP_PM	= (1 << 5),	/* Skip PM operations */
 	ATA_HORKAGE_HPA_SIZE	= (1 << 6),	/* native size off by one */
+	ATA_HORKAGE_IPM		= (1 << 7),	/* Link PM problems */
 
 	 /* DMA mask for user DMA control: User visible values; DO NOT
 	    renumber */
@@ -378,6 +383,18 @@
 			      unsigned long deadline);
 typedef void (*ata_postreset_fn_t)(struct ata_link *link, unsigned int *classes);
 
+/*
+ * host pm policy: If you alter this, you also need to alter libata-scsi.c
+ * (for the ascii descriptions)
+ */
+enum link_pm {
+	NOT_AVAILABLE,
+	MIN_POWER,
+	MAX_PERFORMANCE,
+	MEDIUM_POWER,
+};
+extern struct class_device_attribute class_device_attr_link_power_management_policy;
+
 struct ata_ioports {
 	void __iomem		*cmd_addr;
 	void __iomem		*data_addr;
@@ -624,6 +641,7 @@
 
 	pm_message_t		pm_mesg;
 	int			*pm_result;
+	enum link_pm		pm_policy;
 
 	struct timer_list	fastdrain_timer;
 	unsigned long		fastdrain_cnt;
@@ -691,7 +709,8 @@
 
 	int (*port_suspend) (struct ata_port *ap, pm_message_t mesg);
 	int (*port_resume) (struct ata_port *ap);
-
+	int (*enable_pm) (struct ata_port *ap, enum link_pm policy);
+	void (*disable_pm) (struct ata_port *ap);
 	int (*port_start) (struct ata_port *ap);
 	void (*port_stop) (struct ata_port *ap);