From e5f1b245870d59be0e6cc3b33edf5406a3b59648 Mon Sep 17 00:00:00 2001
From: Daniel Lezcano <daniel.lezcano@linaro.org>
Date: Wed, 5 Oct 2016 09:33:12 +0200
Subject: cpuidle: governors: Remove remaining old module code

The governor's code use try_module_get() and put_module() to refcount
the governor's module. But the governors are not compiled as module.

The refcount does not prevent to switch the governor or unload
a module as they aren't compiled as modules. The code is pointless,
so remove it.

Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/cpuidle.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index bb31373c3478..15deea449edc 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -235,8 +235,6 @@ struct cpuidle_governor {
 	int  (*select)		(struct cpuidle_driver *drv,
 					struct cpuidle_device *dev);
 	void (*reflect)		(struct cpuidle_device *dev, int index);
-
-	struct module 		*owner;
 };
 
 #ifdef CONFIG_CPU_IDLE
-- 
cgit v1.2.3-71-gd317


From 62006c1702b3b1be0c0726949e0ee0ea2326be9c Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Mon, 17 Oct 2016 20:16:58 +0200
Subject: PM / Runtime: Remove the exported function pm_children_suspended()

The exported function pm_children_suspended() has only one caller, which is
the runtime PM internal function, rpm_check_suspend_allowed().

Let's clean-up this code, by removing pm_children_suspended() altogether
and instead do the one-liner check directly in rpm_check_suspend_allowed().

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/runtime.c | 3 ++-
 include/linux/pm_runtime.h   | 7 -------
 2 files changed, 2 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 82a081ea4317..53b427dfc403 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -241,7 +241,8 @@ static int rpm_check_suspend_allowed(struct device *dev)
 		retval = -EACCES;
 	else if (atomic_read(&dev->power.usage_count) > 0)
 		retval = -EAGAIN;
-	else if (!pm_children_suspended(dev))
+	else if (!dev->power.ignore_children &&
+			atomic_read(&dev->power.child_count))
 		retval = -EBUSY;
 
 	/* Pending resume requests take precedence over suspends. */
diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h
index 2e14d2667b6c..61ea5666c94c 100644
--- a/include/linux/pm_runtime.h
+++ b/include/linux/pm_runtime.h
@@ -61,12 +61,6 @@ static inline void pm_suspend_ignore_children(struct device *dev, bool enable)
 	dev->power.ignore_children = enable;
 }
 
-static inline bool pm_children_suspended(struct device *dev)
-{
-	return dev->power.ignore_children
-		|| !atomic_read(&dev->power.child_count);
-}
-
 static inline void pm_runtime_get_noresume(struct device *dev)
 {
 	atomic_inc(&dev->power.usage_count);
@@ -162,7 +156,6 @@ static inline void pm_runtime_allow(struct device *dev) {}
 static inline void pm_runtime_forbid(struct device *dev) {}
 
 static inline void pm_suspend_ignore_children(struct device *dev, bool enable) {}
-static inline bool pm_children_suspended(struct device *dev) { return false; }
 static inline void pm_runtime_get_noresume(struct device *dev) {}
 static inline void pm_runtime_put_noidle(struct device *dev) {}
 static inline bool device_run_wake(struct device *dev) { return false; }
-- 
cgit v1.2.3-71-gd317


From b1a60995a684f2b6052cda640b0704361ab40089 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Mon, 17 Oct 2016 20:17:00 +0200
Subject: PM / Runtime: Convert pm_runtime_set_suspended() to return an int

Because pm_runtime_set_suspended() invokes __pm_runtime_set_status(), which
can fail, pm_runtime_set_suspended() can also fail.

Instead of hiding a potential error, let's propagate it by converting
pm_runtime_set_suspended() from a void to return an int. In this way users
are able to check the error code and act accordingly.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/pm_runtime.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h
index 61ea5666c94c..4957fc185ea9 100644
--- a/include/linux/pm_runtime.h
+++ b/include/linux/pm_runtime.h
@@ -258,9 +258,9 @@ static inline int pm_runtime_set_active(struct device *dev)
 	return __pm_runtime_set_status(dev, RPM_ACTIVE);
 }
 
-static inline void pm_runtime_set_suspended(struct device *dev)
+static inline int pm_runtime_set_suspended(struct device *dev)
 {
-	__pm_runtime_set_status(dev, RPM_SUSPENDED);
+	return __pm_runtime_set_status(dev, RPM_SUSPENDED);
 }
 
 static inline void pm_runtime_disable(struct device *dev)
-- 
cgit v1.2.3-71-gd317


From 59d65b73a23cee48e6f3e44686f199d79b7ee854 Mon Sep 17 00:00:00 2001
From: Lina Iyer <lina.iyer@linaro.org>
Date: Fri, 14 Oct 2016 10:47:49 -0700
Subject: PM / Domains: Make genpd state allocation dynamic

Allow PM Domain states to be defined dynamically by the drivers. This
removes the limitation on the maximum number of states possible for a
domain.

Suggested-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Lina Iyer <lina.iyer@linaro.org>
Acked-by: Ulf Hansson <ulf.hansson@linaro.org>
Reviewed-by: Kevin Hilman <khilman@baylibre.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 arch/arm/mach-imx/gpc.c     | 17 ++++++++++-------
 drivers/base/power/domain.c | 35 +++++++++++++++++++++++------------
 include/linux/pm_domain.h   |  5 ++---
 3 files changed, 35 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/mach-imx/gpc.c b/arch/arm/mach-imx/gpc.c
index 0df062d8b2c9..57a410bbb6a2 100644
--- a/arch/arm/mach-imx/gpc.c
+++ b/arch/arm/mach-imx/gpc.c
@@ -380,13 +380,6 @@ static struct pu_domain imx6q_pu_domain = {
 		.name = "PU",
 		.power_off = imx6q_pm_pu_power_off,
 		.power_on = imx6q_pm_pu_power_on,
-		.states = {
-			[0] = {
-				.power_off_latency_ns = 25000,
-				.power_on_latency_ns = 2000000,
-			},
-		},
-		.state_count = 1,
 	},
 };
 
@@ -430,6 +423,16 @@ static int imx_gpc_genpd_init(struct device *dev, struct regulator *pu_reg)
 	if (!IS_ENABLED(CONFIG_PM_GENERIC_DOMAINS))
 		return 0;
 
+	imx6q_pu_domain.base.states = devm_kzalloc(dev,
+					sizeof(*imx6q_pu_domain.base.states),
+					GFP_KERNEL);
+	if (!imx6q_pu_domain.base.states)
+		return -ENOMEM;
+
+	imx6q_pu_domain.base.states[0].power_off_latency_ns = 25000;
+	imx6q_pu_domain.base.states[0].power_on_latency_ns = 2000000;
+	imx6q_pu_domain.base.state_count = 1;
+
 	pm_genpd_init(&imx6q_pu_domain.base, NULL, false);
 	return of_genpd_add_provider_onecell(dev->of_node,
 					     &imx_gpc_onecell_data);
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index e023066e4215..37ab7f1ef178 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -1282,6 +1282,21 @@ out:
 }
 EXPORT_SYMBOL_GPL(pm_genpd_remove_subdomain);
 
+static int genpd_set_default_power_state(struct generic_pm_domain *genpd)
+{
+	struct genpd_power_state *state;
+
+	state = kzalloc(sizeof(*state), GFP_KERNEL);
+	if (!state)
+		return -ENOMEM;
+
+	genpd->states = state;
+	genpd->state_count = 1;
+	genpd->free = state;
+
+	return 0;
+}
+
 /**
  * pm_genpd_init - Initialize a generic I/O PM domain object.
  * @genpd: PM domain object to initialize.
@@ -1293,6 +1308,8 @@ EXPORT_SYMBOL_GPL(pm_genpd_remove_subdomain);
 int pm_genpd_init(struct generic_pm_domain *genpd,
 		  struct dev_power_governor *gov, bool is_off)
 {
+	int ret;
+
 	if (IS_ERR_OR_NULL(genpd))
 		return -EINVAL;
 
@@ -1325,19 +1342,12 @@ int pm_genpd_init(struct generic_pm_domain *genpd,
 		genpd->dev_ops.start = pm_clk_resume;
 	}
 
-	if (genpd->state_idx >= GENPD_MAX_NUM_STATES) {
-		pr_warn("Initial state index out of bounds.\n");
-		genpd->state_idx = GENPD_MAX_NUM_STATES - 1;
-	}
-
-	if (genpd->state_count > GENPD_MAX_NUM_STATES) {
-		pr_warn("Limiting states to  %d\n", GENPD_MAX_NUM_STATES);
-		genpd->state_count = GENPD_MAX_NUM_STATES;
-	}
-
 	/* Use only one "off" state if there were no states declared */
-	if (genpd->state_count == 0)
-		genpd->state_count = 1;
+	if (genpd->state_count == 0) {
+		ret = genpd_set_default_power_state(genpd);
+		if (ret)
+			return ret;
+	}
 
 	mutex_lock(&gpd_list_lock);
 	list_add(&genpd->gpd_list_node, &gpd_list);
@@ -1377,6 +1387,7 @@ static int genpd_remove(struct generic_pm_domain *genpd)
 	list_del(&genpd->gpd_list_node);
 	mutex_unlock(&genpd->lock);
 	cancel_work_sync(&genpd->power_off_work);
+	kfree(genpd->free);
 	pr_debug("%s: removed %s\n", __func__, genpd->name);
 
 	return 0;
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index a09fe5c009c8..de1d8f331b03 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -19,8 +19,6 @@
 /* Defines used for the flags field in the struct generic_pm_domain */
 #define GENPD_FLAG_PM_CLK	(1U << 0) /* PM domain uses PM clk */
 
-#define GENPD_MAX_NUM_STATES	8 /* Number of possible low power states */
-
 enum gpd_status {
 	GPD_STATE_ACTIVE = 0,	/* PM domain is active */
 	GPD_STATE_POWER_OFF,	/* PM domain is off */
@@ -70,9 +68,10 @@ struct generic_pm_domain {
 	void (*detach_dev)(struct generic_pm_domain *domain,
 			   struct device *dev);
 	unsigned int flags;		/* Bit field of configs for genpd */
-	struct genpd_power_state states[GENPD_MAX_NUM_STATES];
+	struct genpd_power_state *states;
 	unsigned int state_count; /* number of states */
 	unsigned int state_idx; /* state that genpd will go to when off */
+	void *free; /* Free the state that was allocated for default */
 
 };
 
-- 
cgit v1.2.3-71-gd317


From 405f7226014093a2809f27ba32a8230e770ac876 Mon Sep 17 00:00:00 2001
From: Lina Iyer <lina.iyer@linaro.org>
Date: Fri, 14 Oct 2016 10:47:50 -0700
Subject: PM / Domains: Add residency property to genpd states

Residency of a domain's idle state indicates that the minimum idle time
for the domain's idle state to be beneficial for power. Add the
parameter to the state node. Future patches, will use the residency
value in the genpd governor to determine if it is worth while to enter
an idle state.

Signed-off-by: Lina Iyer <lina.iyer@linaro.org>
Acked-by: Ulf Hansson <ulf.hansson@linaro.org>
Reviewed-by: Kevin Hilman <khilman@baylibre.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/pm_domain.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index de1d8f331b03..f4492eb71701 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -38,6 +38,7 @@ struct gpd_dev_ops {
 struct genpd_power_state {
 	s64 power_off_latency_ns;
 	s64 power_on_latency_ns;
+	s64 residency_ns;
 };
 
 struct generic_pm_domain {
-- 
cgit v1.2.3-71-gd317


From 30f604283e05d34cb10108c7ba017e5f4fc9d62c Mon Sep 17 00:00:00 2001
From: Lina Iyer <lina.iyer@linaro.org>
Date: Fri, 14 Oct 2016 10:47:51 -0700
Subject: PM / Domains: Allow domain power states to be read from DT

This patch allows domains to define idle states in the DT. SoC's can
define domain idle states in DT using the "domain-idle-states" property
of the domain provider. Add API to read the idle states from DT that can
be set in the genpd object.

This patch is based on the original patch by Marc Titinger.

Signed-off-by: Marc Titinger <mtitinger+renesas@baylibre.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Lina Iyer <lina.iyer@linaro.org>
Reviewed-by: Kevin Hilman <khilman@baylibre.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/domain.c | 94 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/pm_domain.h   |  8 ++++
 2 files changed, 102 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 37ab7f1ef178..9af75ba0472a 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -1916,6 +1916,100 @@ out:
 	return ret ? -EPROBE_DEFER : 0;
 }
 EXPORT_SYMBOL_GPL(genpd_dev_pm_attach);
+
+static const struct of_device_id idle_state_match[] = {
+	{ .compatible = "arm,idle-state", },
+	{ }
+};
+
+static int genpd_parse_state(struct genpd_power_state *genpd_state,
+				    struct device_node *state_node)
+{
+	int err;
+	u32 residency;
+	u32 entry_latency, exit_latency;
+	const struct of_device_id *match_id;
+
+	match_id = of_match_node(idle_state_match, state_node);
+	if (!match_id)
+		return -EINVAL;
+
+	err = of_property_read_u32(state_node, "entry-latency-us",
+						&entry_latency);
+	if (err) {
+		pr_debug(" * %s missing entry-latency-us property\n",
+						state_node->full_name);
+		return -EINVAL;
+	}
+
+	err = of_property_read_u32(state_node, "exit-latency-us",
+						&exit_latency);
+	if (err) {
+		pr_debug(" * %s missing exit-latency-us property\n",
+						state_node->full_name);
+		return -EINVAL;
+	}
+
+	err = of_property_read_u32(state_node, "min-residency-us", &residency);
+	if (!err)
+		genpd_state->residency_ns = 1000 * residency;
+
+	genpd_state->power_on_latency_ns = 1000 * exit_latency;
+	genpd_state->power_off_latency_ns = 1000 * entry_latency;
+
+	return 0;
+}
+
+/**
+ * of_genpd_parse_idle_states: Return array of idle states for the genpd.
+ *
+ * @dn: The genpd device node
+ * @states: The pointer to which the state array will be saved.
+ * @n: The count of elements in the array returned from this function.
+ *
+ * Returns the device states parsed from the OF node. The memory for the states
+ * is allocated by this function and is the responsibility of the caller to
+ * free the memory after use.
+ */
+int of_genpd_parse_idle_states(struct device_node *dn,
+			struct genpd_power_state **states, int *n)
+{
+	struct genpd_power_state *st;
+	struct device_node *np;
+	int i = 0;
+	int err, ret;
+	int count;
+	struct of_phandle_iterator it;
+
+	count = of_count_phandle_with_args(dn, "domain-idle-states", NULL);
+	if (!count)
+		return -EINVAL;
+
+	st = kcalloc(count, sizeof(*st), GFP_KERNEL);
+	if (!st)
+		return -ENOMEM;
+
+	/* Loop over the phandles until all the requested entry is found */
+	of_for_each_phandle(&it, err, dn, "domain-idle-states", NULL, 0) {
+		np = it.node;
+		ret = genpd_parse_state(&st[i++], np);
+		if (ret) {
+			pr_err
+			("Parsing idle state node %s failed with err %d\n",
+							np->full_name, ret);
+			of_node_put(np);
+			kfree(st);
+			return ret;
+		}
+	}
+
+	*n = count;
+	*states = st;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(of_genpd_parse_idle_states);
+
 #endif /* CONFIG_PM_GENERIC_DOMAINS_OF */
 
 
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index f4492eb71701..b4894969fbec 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -205,6 +205,8 @@ extern int of_genpd_add_device(struct of_phandle_args *args,
 extern int of_genpd_add_subdomain(struct of_phandle_args *parent,
 				  struct of_phandle_args *new_subdomain);
 extern struct generic_pm_domain *of_genpd_remove_last(struct device_node *np);
+extern int of_genpd_parse_idle_states(struct device_node *dn,
+			struct genpd_power_state **states, int *n);
 
 int genpd_dev_pm_attach(struct device *dev);
 #else /* !CONFIG_PM_GENERIC_DOMAINS_OF */
@@ -234,6 +236,12 @@ static inline int of_genpd_add_subdomain(struct of_phandle_args *parent,
 	return -ENODEV;
 }
 
+static inline int of_genpd_parse_idle_states(struct device_node *dn,
+			struct genpd_power_state **states, int *n)
+{
+	return -ENODEV;
+}
+
 static inline int genpd_dev_pm_attach(struct device *dev)
 {
 	return -ENODEV;
-- 
cgit v1.2.3-71-gd317


From 0c9b694a8a7d4853318c4f2ce315afa2bd3664b6 Mon Sep 17 00:00:00 2001
From: Lina Iyer <lina.iyer@linaro.org>
Date: Fri, 14 Oct 2016 10:47:52 -0700
Subject: PM / Domains: Save the fwnode in genpd_power_state

Save the fwnode for the genpd state in the state node. PM Domain clients
may use the fwnode to read in the platform specific domain state
properties and associate them with the state.

Signed-off-by: Lina Iyer <lina.iyer@linaro.org>
Acked-by: Ulf Hansson <ulf.hansson@linaro.org>
Reviewed-by: Kevin Hilman <khilman@baylibre.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/domain.c | 1 +
 include/linux/pm_domain.h   | 1 +
 2 files changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 9af75ba0472a..1a6073aaca0e 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -1956,6 +1956,7 @@ static int genpd_parse_state(struct genpd_power_state *genpd_state,
 
 	genpd_state->power_on_latency_ns = 1000 * exit_latency;
 	genpd_state->power_off_latency_ns = 1000 * entry_latency;
+	genpd_state->fwnode = &state_node->fwnode;
 
 	return 0;
 }
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index b4894969fbec..6a8988166899 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -39,6 +39,7 @@ struct genpd_power_state {
 	s64 power_off_latency_ns;
 	s64 power_on_latency_ns;
 	s64 residency_ns;
+	struct fwnode_handle *fwnode;
 };
 
 struct generic_pm_domain {
-- 
cgit v1.2.3-71-gd317


From 35241d12f750d2f1556a9c85f175ce7044716881 Mon Sep 17 00:00:00 2001
From: Lina Iyer <lina.iyer@linaro.org>
Date: Fri, 14 Oct 2016 10:47:54 -0700
Subject: PM / Domains: Abstract genpd locking

Abstract genpd lock/unlock calls, in preparation for domain specific
locks added in the following patches.

Signed-off-by: Lina Iyer <lina.iyer@linaro.org>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Reviewed-by: Kevin Hilman <khilman@baylibre.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/domain.c | 121 +++++++++++++++++++++++++++++---------------
 include/linux/pm_domain.h   |   5 +-
 2 files changed, 85 insertions(+), 41 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 1a6073aaca0e..4194012cdf86 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -39,6 +39,46 @@
 static LIST_HEAD(gpd_list);
 static DEFINE_MUTEX(gpd_list_lock);
 
+struct genpd_lock_ops {
+	void (*lock)(struct generic_pm_domain *genpd);
+	void (*lock_nested)(struct generic_pm_domain *genpd, int depth);
+	int (*lock_interruptible)(struct generic_pm_domain *genpd);
+	void (*unlock)(struct generic_pm_domain *genpd);
+};
+
+static void genpd_lock_mtx(struct generic_pm_domain *genpd)
+{
+	mutex_lock(&genpd->mlock);
+}
+
+static void genpd_lock_nested_mtx(struct generic_pm_domain *genpd,
+					int depth)
+{
+	mutex_lock_nested(&genpd->mlock, depth);
+}
+
+static int genpd_lock_interruptible_mtx(struct generic_pm_domain *genpd)
+{
+	return mutex_lock_interruptible(&genpd->mlock);
+}
+
+static void genpd_unlock_mtx(struct generic_pm_domain *genpd)
+{
+	return mutex_unlock(&genpd->mlock);
+}
+
+static const struct genpd_lock_ops genpd_mtx_ops = {
+	.lock = genpd_lock_mtx,
+	.lock_nested = genpd_lock_nested_mtx,
+	.lock_interruptible = genpd_lock_interruptible_mtx,
+	.unlock = genpd_unlock_mtx,
+};
+
+#define genpd_lock(p)			p->lock_ops->lock(p)
+#define genpd_lock_nested(p, d)		p->lock_ops->lock_nested(p, d)
+#define genpd_lock_interruptible(p)	p->lock_ops->lock_interruptible(p)
+#define genpd_unlock(p)			p->lock_ops->unlock(p)
+
 /*
  * Get the generic PM domain for a particular struct device.
  * This validates the struct device pointer, the PM domain pointer,
@@ -200,9 +240,9 @@ static int genpd_poweron(struct generic_pm_domain *genpd, unsigned int depth)
 
 		genpd_sd_counter_inc(master);
 
-		mutex_lock_nested(&master->lock, depth + 1);
+		genpd_lock_nested(master, depth + 1);
 		ret = genpd_poweron(master, depth + 1);
-		mutex_unlock(&master->lock);
+		genpd_unlock(master);
 
 		if (ret) {
 			genpd_sd_counter_dec(master);
@@ -255,9 +295,9 @@ static int genpd_dev_pm_qos_notifier(struct notifier_block *nb,
 		spin_unlock_irq(&dev->power.lock);
 
 		if (!IS_ERR(genpd)) {
-			mutex_lock(&genpd->lock);
+			genpd_lock(genpd);
 			genpd->max_off_time_changed = true;
-			mutex_unlock(&genpd->lock);
+			genpd_unlock(genpd);
 		}
 
 		dev = dev->parent;
@@ -354,9 +394,9 @@ static void genpd_power_off_work_fn(struct work_struct *work)
 
 	genpd = container_of(work, struct generic_pm_domain, power_off_work);
 
-	mutex_lock(&genpd->lock);
+	genpd_lock(genpd);
 	genpd_poweroff(genpd, true);
-	mutex_unlock(&genpd->lock);
+	genpd_unlock(genpd);
 }
 
 /**
@@ -472,9 +512,9 @@ static int genpd_runtime_suspend(struct device *dev)
 	if (dev->power.irq_safe)
 		return 0;
 
-	mutex_lock(&genpd->lock);
+	genpd_lock(genpd);
 	genpd_poweroff(genpd, false);
-	mutex_unlock(&genpd->lock);
+	genpd_unlock(genpd);
 
 	return 0;
 }
@@ -509,9 +549,9 @@ static int genpd_runtime_resume(struct device *dev)
 		goto out;
 	}
 
-	mutex_lock(&genpd->lock);
+	genpd_lock(genpd);
 	ret = genpd_poweron(genpd, 0);
-	mutex_unlock(&genpd->lock);
+	genpd_unlock(genpd);
 
 	if (ret)
 		return ret;
@@ -547,9 +587,9 @@ err_stop:
 	genpd_stop_dev(genpd, dev);
 err_poweroff:
 	if (!dev->power.irq_safe) {
-		mutex_lock(&genpd->lock);
+		genpd_lock(genpd);
 		genpd_poweroff(genpd, 0);
-		mutex_unlock(&genpd->lock);
+		genpd_unlock(genpd);
 	}
 
 	return ret;
@@ -732,20 +772,20 @@ static int pm_genpd_prepare(struct device *dev)
 	if (resume_needed(dev, genpd))
 		pm_runtime_resume(dev);
 
-	mutex_lock(&genpd->lock);
+	genpd_lock(genpd);
 
 	if (genpd->prepared_count++ == 0)
 		genpd->suspended_count = 0;
 
-	mutex_unlock(&genpd->lock);
+	genpd_unlock(genpd);
 
 	ret = pm_generic_prepare(dev);
 	if (ret) {
-		mutex_lock(&genpd->lock);
+		genpd_lock(genpd);
 
 		genpd->prepared_count--;
 
-		mutex_unlock(&genpd->lock);
+		genpd_unlock(genpd);
 	}
 
 	return ret;
@@ -936,13 +976,13 @@ static void pm_genpd_complete(struct device *dev)
 
 	pm_generic_complete(dev);
 
-	mutex_lock(&genpd->lock);
+	genpd_lock(genpd);
 
 	genpd->prepared_count--;
 	if (!genpd->prepared_count)
 		genpd_queue_power_off_work(genpd);
 
-	mutex_unlock(&genpd->lock);
+	genpd_unlock(genpd);
 }
 
 /**
@@ -1071,7 +1111,7 @@ static int genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
 	if (IS_ERR(gpd_data))
 		return PTR_ERR(gpd_data);
 
-	mutex_lock(&genpd->lock);
+	genpd_lock(genpd);
 
 	if (genpd->prepared_count > 0) {
 		ret = -EAGAIN;
@@ -1088,7 +1128,7 @@ static int genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
 	list_add_tail(&gpd_data->base.list_node, &genpd->dev_list);
 
  out:
-	mutex_unlock(&genpd->lock);
+	genpd_unlock(genpd);
 
 	if (ret)
 		genpd_free_dev_data(dev, gpd_data);
@@ -1130,7 +1170,7 @@ static int genpd_remove_device(struct generic_pm_domain *genpd,
 	gpd_data = to_gpd_data(pdd);
 	dev_pm_qos_remove_notifier(dev, &gpd_data->nb);
 
-	mutex_lock(&genpd->lock);
+	genpd_lock(genpd);
 
 	if (genpd->prepared_count > 0) {
 		ret = -EAGAIN;
@@ -1145,14 +1185,14 @@ static int genpd_remove_device(struct generic_pm_domain *genpd,
 
 	list_del_init(&pdd->list_node);
 
-	mutex_unlock(&genpd->lock);
+	genpd_unlock(genpd);
 
 	genpd_free_dev_data(dev, gpd_data);
 
 	return 0;
 
  out:
-	mutex_unlock(&genpd->lock);
+	genpd_unlock(genpd);
 	dev_pm_qos_add_notifier(dev, &gpd_data->nb);
 
 	return ret;
@@ -1187,8 +1227,8 @@ static int genpd_add_subdomain(struct generic_pm_domain *genpd,
 	if (!link)
 		return -ENOMEM;
 
-	mutex_lock(&subdomain->lock);
-	mutex_lock_nested(&genpd->lock, SINGLE_DEPTH_NESTING);
+	genpd_lock(subdomain);
+	genpd_lock_nested(genpd, SINGLE_DEPTH_NESTING);
 
 	if (genpd->status == GPD_STATE_POWER_OFF
 	    &&  subdomain->status != GPD_STATE_POWER_OFF) {
@@ -1211,8 +1251,8 @@ static int genpd_add_subdomain(struct generic_pm_domain *genpd,
 		genpd_sd_counter_inc(genpd);
 
  out:
-	mutex_unlock(&genpd->lock);
-	mutex_unlock(&subdomain->lock);
+	genpd_unlock(genpd);
+	genpd_unlock(subdomain);
 	if (ret)
 		kfree(link);
 	return ret;
@@ -1250,8 +1290,8 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd,
 	if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(subdomain))
 		return -EINVAL;
 
-	mutex_lock(&subdomain->lock);
-	mutex_lock_nested(&genpd->lock, SINGLE_DEPTH_NESTING);
+	genpd_lock(subdomain);
+	genpd_lock_nested(genpd, SINGLE_DEPTH_NESTING);
 
 	if (!list_empty(&subdomain->master_links) || subdomain->device_count) {
 		pr_warn("%s: unable to remove subdomain %s\n", genpd->name,
@@ -1275,8 +1315,8 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd,
 	}
 
 out:
-	mutex_unlock(&genpd->lock);
-	mutex_unlock(&subdomain->lock);
+	genpd_unlock(genpd);
+	genpd_unlock(subdomain);
 
 	return ret;
 }
@@ -1316,7 +1356,8 @@ int pm_genpd_init(struct generic_pm_domain *genpd,
 	INIT_LIST_HEAD(&genpd->master_links);
 	INIT_LIST_HEAD(&genpd->slave_links);
 	INIT_LIST_HEAD(&genpd->dev_list);
-	mutex_init(&genpd->lock);
+	mutex_init(&genpd->mlock);
+	genpd->lock_ops = &genpd_mtx_ops;
 	genpd->gov = gov;
 	INIT_WORK(&genpd->power_off_work, genpd_power_off_work_fn);
 	atomic_set(&genpd->sd_count, 0);
@@ -1364,16 +1405,16 @@ static int genpd_remove(struct generic_pm_domain *genpd)
 	if (IS_ERR_OR_NULL(genpd))
 		return -EINVAL;
 
-	mutex_lock(&genpd->lock);
+	genpd_lock(genpd);
 
 	if (genpd->has_provider) {
-		mutex_unlock(&genpd->lock);
+		genpd_unlock(genpd);
 		pr_err("Provider present, unable to remove %s\n", genpd->name);
 		return -EBUSY;
 	}
 
 	if (!list_empty(&genpd->master_links) || genpd->device_count) {
-		mutex_unlock(&genpd->lock);
+		genpd_unlock(genpd);
 		pr_err("%s: unable to remove %s\n", __func__, genpd->name);
 		return -EBUSY;
 	}
@@ -1385,7 +1426,7 @@ static int genpd_remove(struct generic_pm_domain *genpd)
 	}
 
 	list_del(&genpd->gpd_list_node);
-	mutex_unlock(&genpd->lock);
+	genpd_unlock(genpd);
 	cancel_work_sync(&genpd->power_off_work);
 	kfree(genpd->free);
 	pr_debug("%s: removed %s\n", __func__, genpd->name);
@@ -1909,9 +1950,9 @@ int genpd_dev_pm_attach(struct device *dev)
 	dev->pm_domain->detach = genpd_dev_pm_detach;
 	dev->pm_domain->sync = genpd_dev_pm_sync;
 
-	mutex_lock(&pd->lock);
+	genpd_lock(pd);
 	ret = genpd_poweron(pd, 0);
-	mutex_unlock(&pd->lock);
+	genpd_unlock(pd);
 out:
 	return ret ? -EPROBE_DEFER : 0;
 }
@@ -2064,7 +2105,7 @@ static int pm_genpd_summary_one(struct seq_file *s,
 	char state[16];
 	int ret;
 
-	ret = mutex_lock_interruptible(&genpd->lock);
+	ret = genpd_lock_interruptible(genpd);
 	if (ret)
 		return -ERESTARTSYS;
 
@@ -2101,7 +2142,7 @@ static int pm_genpd_summary_one(struct seq_file *s,
 
 	seq_puts(s, "\n");
 exit:
-	mutex_unlock(&genpd->lock);
+	genpd_unlock(genpd);
 
 	return 0;
 }
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 6a8988166899..811b968eb740 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -42,13 +42,14 @@ struct genpd_power_state {
 	struct fwnode_handle *fwnode;
 };
 
+struct genpd_lock_ops;
+
 struct generic_pm_domain {
 	struct dev_pm_domain domain;	/* PM domain operations */
 	struct list_head gpd_list_node;	/* Node in the global PM domains list */
 	struct list_head master_links;	/* Links with PM domain as a master */
 	struct list_head slave_links;	/* Links with PM domain as a slave */
 	struct list_head dev_list;	/* List of devices */
-	struct mutex lock;
 	struct dev_power_governor *gov;
 	struct work_struct power_off_work;
 	struct fwnode_handle *provider;	/* Identity of the domain provider */
@@ -74,6 +75,8 @@ struct generic_pm_domain {
 	unsigned int state_count; /* number of states */
 	unsigned int state_idx; /* state that genpd will go to when off */
 	void *free; /* Free the state that was allocated for default */
+	const struct genpd_lock_ops *lock_ops;
+	struct mutex mlock;
 
 };
 
-- 
cgit v1.2.3-71-gd317


From d716f4798ff8c65ace4a6ab291f9a4ff265df4ba Mon Sep 17 00:00:00 2001
From: Lina Iyer <lina.iyer@linaro.org>
Date: Fri, 14 Oct 2016 10:47:55 -0700
Subject: PM / Domains: Support IRQ safe PM domains

Generic Power Domains currently support turning on/off only in process
context. This prevents the usage of PM domains for domains that could be
powered on/off in a context where IRQs are disabled. Many such domains
exist today and do not get powered off, when the IRQ safe devices in
that domain are powered off, because of this limitation.

However, not all domains can operate in IRQ safe contexts. Genpd
therefore, has to support both cases where the domain may or may not
operate in IRQ safe contexts. Configuring genpd to use an appropriate
lock for that domain, would allow domains that have IRQ safe devices to
runtime suspend and resume, in atomic context.

To achieve domain specific locking, set the domain's ->flag to
GENPD_FLAG_IRQ_SAFE while defining the domain. This indicates that genpd
should use a spinlock instead of a mutex for locking the domain. Locking
is abstracted through genpd_lock() and genpd_unlock() functions that use
the flag to determine the appropriate lock to be used for that domain.

Domains that have lower latency to suspend and resume and can operate
with IRQs disabled may now be able to save power, when the component
devices and sub-domains are idle at runtime.

The restriction this imposes on the domain hierarchy is that non-IRQ
safe domains may not have IRQ-safe subdomains, but IRQ safe domains may
have IRQ safe and non-IRQ safe subdomains and devices.

Signed-off-by: Lina Iyer <lina.iyer@linaro.org>
Acked-by: Ulf Hansson <ulf.hansson@linaro.org>
Reviewed-by: Kevin Hilman <khilman@baylibre.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/domain.c | 111 ++++++++++++++++++++++++++++++++++++++++----
 include/linux/pm_domain.h   |  10 +++-
 2 files changed, 110 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 4194012cdf86..aac656a889dc 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -74,11 +74,70 @@ static const struct genpd_lock_ops genpd_mtx_ops = {
 	.unlock = genpd_unlock_mtx,
 };
 
+static void genpd_lock_spin(struct generic_pm_domain *genpd)
+	__acquires(&genpd->slock)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&genpd->slock, flags);
+	genpd->lock_flags = flags;
+}
+
+static void genpd_lock_nested_spin(struct generic_pm_domain *genpd,
+					int depth)
+	__acquires(&genpd->slock)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave_nested(&genpd->slock, flags, depth);
+	genpd->lock_flags = flags;
+}
+
+static int genpd_lock_interruptible_spin(struct generic_pm_domain *genpd)
+	__acquires(&genpd->slock)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&genpd->slock, flags);
+	genpd->lock_flags = flags;
+	return 0;
+}
+
+static void genpd_unlock_spin(struct generic_pm_domain *genpd)
+	__releases(&genpd->slock)
+{
+	spin_unlock_irqrestore(&genpd->slock, genpd->lock_flags);
+}
+
+static const struct genpd_lock_ops genpd_spin_ops = {
+	.lock = genpd_lock_spin,
+	.lock_nested = genpd_lock_nested_spin,
+	.lock_interruptible = genpd_lock_interruptible_spin,
+	.unlock = genpd_unlock_spin,
+};
+
 #define genpd_lock(p)			p->lock_ops->lock(p)
 #define genpd_lock_nested(p, d)		p->lock_ops->lock_nested(p, d)
 #define genpd_lock_interruptible(p)	p->lock_ops->lock_interruptible(p)
 #define genpd_unlock(p)			p->lock_ops->unlock(p)
 
+#define genpd_is_irq_safe(genpd)	(genpd->flags & GENPD_FLAG_IRQ_SAFE)
+
+static inline bool irq_safe_dev_in_no_sleep_domain(struct device *dev,
+		struct generic_pm_domain *genpd)
+{
+	bool ret;
+
+	ret = pm_runtime_is_irq_safe(dev) && !genpd_is_irq_safe(genpd);
+
+	/* Warn once for each IRQ safe dev in no sleep domain */
+	if (ret)
+		dev_warn_once(dev, "PM domain %s will not be powered off\n",
+				genpd->name);
+
+	return ret;
+}
+
 /*
  * Get the generic PM domain for a particular struct device.
  * This validates the struct device pointer, the PM domain pointer,
@@ -343,7 +402,12 @@ static int genpd_poweroff(struct generic_pm_domain *genpd, bool is_async)
 		if (stat > PM_QOS_FLAGS_NONE)
 			return -EBUSY;
 
-		if (!pm_runtime_suspended(pdd->dev) || pdd->dev->power.irq_safe)
+		/*
+		 * Do not allow PM domain to be powered off, when an IRQ safe
+		 * device is part of a non-IRQ safe domain.
+		 */
+		if (!pm_runtime_suspended(pdd->dev) ||
+			irq_safe_dev_in_no_sleep_domain(pdd->dev, genpd))
 			not_suspended++;
 	}
 
@@ -506,10 +570,10 @@ static int genpd_runtime_suspend(struct device *dev)
 	}
 
 	/*
-	 * If power.irq_safe is set, this routine will be run with interrupts
-	 * off, so it can't use mutexes.
+	 * If power.irq_safe is set, this routine may be run with
+	 * IRQs disabled, so suspend only if the PM domain also is irq_safe.
 	 */
-	if (dev->power.irq_safe)
+	if (irq_safe_dev_in_no_sleep_domain(dev, genpd))
 		return 0;
 
 	genpd_lock(genpd);
@@ -543,8 +607,11 @@ static int genpd_runtime_resume(struct device *dev)
 	if (IS_ERR(genpd))
 		return -EINVAL;
 
-	/* If power.irq_safe, the PM domain is never powered off. */
-	if (dev->power.irq_safe) {
+	/*
+	 * As we don't power off a non IRQ safe domain, which holds
+	 * an IRQ safe device, we don't need to restore power to it.
+	 */
+	if (irq_safe_dev_in_no_sleep_domain(dev, genpd)) {
 		timed = false;
 		goto out;
 	}
@@ -586,7 +653,8 @@ static int genpd_runtime_resume(struct device *dev)
 err_stop:
 	genpd_stop_dev(genpd, dev);
 err_poweroff:
-	if (!dev->power.irq_safe) {
+	if (!pm_runtime_is_irq_safe(dev) ||
+		(pm_runtime_is_irq_safe(dev) && genpd_is_irq_safe(genpd))) {
 		genpd_lock(genpd);
 		genpd_poweroff(genpd, 0);
 		genpd_unlock(genpd);
@@ -1223,6 +1291,17 @@ static int genpd_add_subdomain(struct generic_pm_domain *genpd,
 	    || genpd == subdomain)
 		return -EINVAL;
 
+	/*
+	 * If the domain can be powered on/off in an IRQ safe
+	 * context, ensure that the subdomain can also be
+	 * powered on/off in that context.
+	 */
+	if (!genpd_is_irq_safe(genpd) && genpd_is_irq_safe(subdomain)) {
+		WARN("Parent %s of subdomain %s must be IRQ safe\n",
+				genpd->name, subdomain->name);
+		return -EINVAL;
+	}
+
 	link = kzalloc(sizeof(*link), GFP_KERNEL);
 	if (!link)
 		return -ENOMEM;
@@ -1337,6 +1416,17 @@ static int genpd_set_default_power_state(struct generic_pm_domain *genpd)
 	return 0;
 }
 
+static void genpd_lock_init(struct generic_pm_domain *genpd)
+{
+	if (genpd->flags & GENPD_FLAG_IRQ_SAFE) {
+		spin_lock_init(&genpd->slock);
+		genpd->lock_ops = &genpd_spin_ops;
+	} else {
+		mutex_init(&genpd->mlock);
+		genpd->lock_ops = &genpd_mtx_ops;
+	}
+}
+
 /**
  * pm_genpd_init - Initialize a generic I/O PM domain object.
  * @genpd: PM domain object to initialize.
@@ -1356,8 +1446,7 @@ int pm_genpd_init(struct generic_pm_domain *genpd,
 	INIT_LIST_HEAD(&genpd->master_links);
 	INIT_LIST_HEAD(&genpd->slave_links);
 	INIT_LIST_HEAD(&genpd->dev_list);
-	mutex_init(&genpd->mlock);
-	genpd->lock_ops = &genpd_mtx_ops;
+	genpd_lock_init(genpd);
 	genpd->gov = gov;
 	INIT_WORK(&genpd->power_off_work, genpd_power_off_work_fn);
 	atomic_set(&genpd->sd_count, 0);
@@ -2131,7 +2220,9 @@ static int pm_genpd_summary_one(struct seq_file *s,
 	}
 
 	list_for_each_entry(pm_data, &genpd->dev_list, list_node) {
-		kobj_path = kobject_get_path(&pm_data->dev->kobj, GFP_KERNEL);
+		kobj_path = kobject_get_path(&pm_data->dev->kobj,
+				genpd_is_irq_safe(genpd) ?
+				GFP_ATOMIC : GFP_KERNEL);
 		if (kobj_path == NULL)
 			continue;
 
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 811b968eb740..81ece61075df 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -15,9 +15,11 @@
 #include <linux/err.h>
 #include <linux/of.h>
 #include <linux/notifier.h>
+#include <linux/spinlock.h>
 
 /* Defines used for the flags field in the struct generic_pm_domain */
 #define GENPD_FLAG_PM_CLK	(1U << 0) /* PM domain uses PM clk */
+#define GENPD_FLAG_IRQ_SAFE	(1U << 1) /* PM domain operates in atomic */
 
 enum gpd_status {
 	GPD_STATE_ACTIVE = 0,	/* PM domain is active */
@@ -76,7 +78,13 @@ struct generic_pm_domain {
 	unsigned int state_idx; /* state that genpd will go to when off */
 	void *free; /* Free the state that was allocated for default */
 	const struct genpd_lock_ops *lock_ops;
-	struct mutex mlock;
+	union {
+		struct mutex mlock;
+		struct {
+			spinlock_t slock;
+			unsigned long lock_flags;
+		};
+	};
 
 };
 
-- 
cgit v1.2.3-71-gd317


From ee7930ee27fe5240398cc302fa8eb4454725f188 Mon Sep 17 00:00:00 2001
From: Markus Mayer <mmayer@broadcom.com>
Date: Mon, 7 Nov 2016 10:02:23 -0800
Subject: cpufreq: stats: New sysfs attribute for clearing statistics

Allow CPUfreq statistics to be cleared by writing anything to
/sys/.../cpufreq/stats/reset.

Signed-off-by: Markus Mayer <mmayer@broadcom.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/cpu-freq/cpufreq-stats.txt |  6 ++++++
 drivers/cpufreq/cpufreq_stats.c          | 22 ++++++++++++++++++++++
 include/linux/cpufreq.h                  |  4 ++++
 3 files changed, 32 insertions(+)

(limited to 'include/linux')

diff --git a/Documentation/cpu-freq/cpufreq-stats.txt b/Documentation/cpu-freq/cpufreq-stats.txt
index 8d9773f23550..3c355f6ad834 100644
--- a/Documentation/cpu-freq/cpufreq-stats.txt
+++ b/Documentation/cpu-freq/cpufreq-stats.txt
@@ -44,11 +44,17 @@ the stats driver insertion.
 total 0
 drwxr-xr-x  2 root root    0 May 14 16:06 .
 drwxr-xr-x  3 root root    0 May 14 15:58 ..
+--w-------  1 root root 4096 May 14 16:06 reset
 -r--r--r--  1 root root 4096 May 14 16:06 time_in_state
 -r--r--r--  1 root root 4096 May 14 16:06 total_trans
 -r--r--r--  1 root root 4096 May 14 16:06 trans_table
 --------------------------------------------------------------------------------
 
+-  reset
+Write-only attribute that can be used to reset the stat counters. This can be
+useful for evaluating system behaviour under different governors without the
+need for a reboot.
+
 -  time_in_state
 This gives the amount of time spent in each of the frequencies supported by
 this CPU. The cat output will have "<frequency> <time>" pair in each line, which
diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c
index 06d3abdffd3a..ac284e66839c 100644
--- a/drivers/cpufreq/cpufreq_stats.c
+++ b/drivers/cpufreq/cpufreq_stats.c
@@ -41,6 +41,18 @@ static int cpufreq_stats_update(struct cpufreq_stats *stats)
 	return 0;
 }
 
+static void cpufreq_stats_clear_table(struct cpufreq_stats *stats)
+{
+	unsigned int count = stats->max_state;
+
+	memset(stats->time_in_state, 0, count * sizeof(u64));
+#ifdef CONFIG_CPU_FREQ_STAT_DETAILS
+	memset(stats->trans_table, 0, count * count * sizeof(int));
+#endif
+	stats->last_time = get_jiffies_64();
+	stats->total_trans = 0;
+}
+
 static ssize_t show_total_trans(struct cpufreq_policy *policy, char *buf)
 {
 	return sprintf(buf, "%d\n", policy->stats->total_trans);
@@ -64,6 +76,14 @@ static ssize_t show_time_in_state(struct cpufreq_policy *policy, char *buf)
 	return len;
 }
 
+static ssize_t store_reset(struct cpufreq_policy *policy, const char *buf,
+			   size_t count)
+{
+	/* We don't care what is written to the attribute. */
+	cpufreq_stats_clear_table(policy->stats);
+	return count;
+}
+
 #ifdef CONFIG_CPU_FREQ_STAT_DETAILS
 static ssize_t show_trans_table(struct cpufreq_policy *policy, char *buf)
 {
@@ -113,10 +133,12 @@ cpufreq_freq_attr_ro(trans_table);
 
 cpufreq_freq_attr_ro(total_trans);
 cpufreq_freq_attr_ro(time_in_state);
+cpufreq_freq_attr_wo(reset);
 
 static struct attribute *default_attrs[] = {
 	&total_trans.attr,
 	&time_in_state.attr,
+	&reset.attr,
 #ifdef CONFIG_CPU_FREQ_STAT_DETAILS
 	&trans_table.attr,
 #endif
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 32dc0cbd51ca..40dc2e29f480 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -234,6 +234,10 @@ __ATTR(_name, _perm, show_##_name, NULL)
 static struct freq_attr _name =			\
 __ATTR(_name, 0644, show_##_name, store_##_name)
 
+#define cpufreq_freq_attr_wo(_name)		\
+static struct freq_attr _name =			\
+__ATTR(_name, 0200, NULL, store_##_name)
+
 struct global_attr {
 	struct attribute attr;
 	ssize_t (*show)(struct kobject *kobj,
-- 
cgit v1.2.3-71-gd317


From 30248feff5e5c6a01ade5e6126009e296ed8bd35 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Fri, 18 Nov 2016 13:59:21 +0100
Subject: cpufreq: Make cpufreq_update_policy() void

The return value of cpufreq_update_policy() is never used, so make
it void.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
---
 drivers/cpufreq/cpufreq.c | 21 +++++++--------------
 include/linux/cpufreq.h   |  2 +-
 2 files changed, 8 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index ad3b319486bd..cc475eff90b3 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -2257,21 +2257,18 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
  *	Useful for policy notifiers which have different necessities
  *	at different times.
  */
-int cpufreq_update_policy(unsigned int cpu)
+void cpufreq_update_policy(unsigned int cpu)
 {
 	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
 	struct cpufreq_policy new_policy;
-	int ret;
 
 	if (!policy)
-		return -ENODEV;
+		return;
 
 	down_write(&policy->rwsem);
 
-	if (policy_is_inactive(policy)) {
-		ret = -ENODEV;
+	if (policy_is_inactive(policy))
 		goto unlock;
-	}
 
 	pr_debug("updating policy for CPU %u\n", cpu);
 	memcpy(&new_policy, policy, sizeof(*policy));
@@ -2283,24 +2280,20 @@ int cpufreq_update_policy(unsigned int cpu)
 	 * -> ask driver for current freq and notify governors about a change
 	 */
 	if (cpufreq_driver->get && !cpufreq_driver->setpolicy) {
-		if (cpufreq_suspended) {
-			ret = -EAGAIN;
+		if (cpufreq_suspended)
 			goto unlock;
-		}
+
 		new_policy.cur = cpufreq_update_current_freq(policy);
-		if (WARN_ON(!new_policy.cur)) {
-			ret = -EIO;
+		if (WARN_ON(!new_policy.cur))
 			goto unlock;
-		}
 	}
 
-	ret = cpufreq_set_policy(policy, &new_policy);
+	cpufreq_set_policy(policy, &new_policy);
 
 unlock:
 	up_write(&policy->rwsem);
 
 	cpufreq_cpu_put(policy);
-	return ret;
 }
 EXPORT_SYMBOL(cpufreq_update_policy);
 
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 40dc2e29f480..7e05c5e4e45c 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -175,7 +175,7 @@ void disable_cpufreq(void);
 
 u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy);
 int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu);
-int cpufreq_update_policy(unsigned int cpu);
+void cpufreq_update_policy(unsigned int cpu);
 bool have_governor_per_policy(void);
 struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy);
 void cpufreq_enable_fast_switch(struct cpufreq_policy *policy);
-- 
cgit v1.2.3-71-gd317


From 08b98d3291652bdcd1029a059e39fbcae5ad93e2 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Thu, 17 Nov 2016 03:28:53 +0100
Subject: PM / sleep / ACPI: Use the ACPI_FADT_LOW_POWER_S0 flag

Modify the ACPI system sleep support setup code to select
suspend-to-idle as the default system sleep state if the
ACPI_FADT_LOW_POWER_S0 flag is set in the FADT and the
default sleep state was not selected from the kernel command
line.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Tested-by: Mario Limonciello <mario.limonciello@dell.com>
---
 Documentation/power/states.txt | 4 +++-
 drivers/acpi/sleep.c           | 8 ++++++++
 include/linux/suspend.h        | 2 ++
 kernel/power/suspend.c         | 4 ++--
 4 files changed, 15 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/power/states.txt b/Documentation/power/states.txt
index 008ecb588317..8a39ce45d8a0 100644
--- a/Documentation/power/states.txt
+++ b/Documentation/power/states.txt
@@ -35,7 +35,9 @@ only one way to cause the system to go into the Suspend-To-RAM state (write
 The default suspend mode (ie. the one to be used without writing anything into
 /sys/power/mem_sleep) is either "deep" (if Suspend-To-RAM is supported) or
 "s2idle", but it can be overridden by the value of the "mem_sleep_default"
-parameter in the kernel command line.
+parameter in the kernel command line.  On some ACPI-based systems, depending on
+the information in the FADT, the default may be "s2idle" even if Suspend-To-RAM
+is supported.
 
 The properties of all of the sleep states are described below.
 
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index deb0ff78eba8..ce1855fd584b 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -691,6 +691,14 @@ static void acpi_sleep_suspend_setup(void)
 		if (acpi_sleep_state_supported(i))
 			sleep_states[i] = 1;
 
+	/*
+	 * Use suspend-to-idle by default if ACPI_FADT_LOW_POWER_S0 is set and
+	 * the default suspend mode was not selected from the command line.
+	 */
+	if (acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0 &&
+	    mem_sleep_default > PM_SUSPEND_MEM)
+		mem_sleep_default = PM_SUSPEND_FREEZE;
+
 	suspend_set_ops(old_suspend_ordering ?
 		&acpi_suspend_ops_old : &acpi_suspend_ops);
 	freeze_set_ops(&acpi_freeze_ops);
diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index d9718378a8be..0c729c3c8549 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -194,6 +194,8 @@ struct platform_freeze_ops {
 };
 
 #ifdef CONFIG_SUSPEND
+extern suspend_state_t mem_sleep_default;
+
 /**
  * suspend_set_ops - set platform dependent suspend operations
  * @ops: The new suspend operations to set.
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 15e6baef5c73..f67ceb7768b8 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -46,7 +46,7 @@ static const char * const mem_sleep_labels[] = {
 const char *mem_sleep_states[PM_SUSPEND_MAX];
 
 suspend_state_t mem_sleep_current = PM_SUSPEND_FREEZE;
-static suspend_state_t mem_sleep_default = PM_SUSPEND_MEM;
+suspend_state_t mem_sleep_default = PM_SUSPEND_MAX;
 
 unsigned int pm_suspend_global_flags;
 EXPORT_SYMBOL_GPL(pm_suspend_global_flags);
@@ -168,7 +168,7 @@ void suspend_set_ops(const struct platform_suspend_ops *ops)
 	}
 	if (valid_state(PM_SUSPEND_MEM)) {
 		mem_sleep_states[PM_SUSPEND_MEM] = mem_sleep_labels[PM_SUSPEND_MEM];
-		if (mem_sleep_default == PM_SUSPEND_MEM)
+		if (mem_sleep_default >= PM_SUSPEND_MEM)
 			mem_sleep_current = PM_SUSPEND_MEM;
 	}
 
-- 
cgit v1.2.3-71-gd317


From bb8313b603eb8fd52de48a079bfcd72dcab2ef1e Mon Sep 17 00:00:00 2001
From: Jacob Pan <jacob.jun.pan@linux.intel.com>
Date: Mon, 28 Nov 2016 23:03:04 -0800
Subject: cpuidle: Allow enforcing deepest idle state selection

When idle injection is used to cap power, we need to override the
governor's choice of idle states.

For this reason, make it possible the deepest idle state selection to
be enforced by setting a flag on a given CPU to achieve the maximum
potential power draw reduction.

Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
[ rjw: Subject & changelog ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpuidle/cpuidle.c | 13 ++++++++++++-
 include/linux/cpuidle.h   |  7 ++++++-
 kernel/sched/idle.c       | 13 ++++++++-----
 3 files changed, 26 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index c73207abb5a4..afc005b917fe 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -97,7 +97,17 @@ static int find_deepest_state(struct cpuidle_driver *drv,
 	return ret;
 }
 
-#ifdef CONFIG_SUSPEND
+/* Set the current cpu to use the deepest idle state, override governors */
+void cpuidle_use_deepest_state(bool enable)
+{
+	struct cpuidle_device *dev;
+
+	preempt_disable();
+	dev = cpuidle_get_device();
+	dev->use_deepest_state = enable;
+	preempt_enable();
+}
+
 /**
  * cpuidle_find_deepest_state - Find the deepest available idle state.
  * @drv: cpuidle driver for the given CPU.
@@ -109,6 +119,7 @@ int cpuidle_find_deepest_state(struct cpuidle_driver *drv,
 	return find_deepest_state(drv, dev, UINT_MAX, 0, false);
 }
 
+#ifdef CONFIG_SUSPEND
 static void enter_freeze_proper(struct cpuidle_driver *drv,
 				struct cpuidle_device *dev, int index)
 {
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index 15deea449edc..da346f2817a8 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -74,6 +74,7 @@ struct cpuidle_driver_kobj;
 struct cpuidle_device {
 	unsigned int		registered:1;
 	unsigned int		enabled:1;
+	unsigned int		use_deepest_state:1;
 	unsigned int		cpu;
 
 	int			last_residency;
@@ -192,11 +193,12 @@ static inline struct cpuidle_driver *cpuidle_get_cpu_driver(
 static inline struct cpuidle_device *cpuidle_get_device(void) {return NULL; }
 #endif
 
-#if defined(CONFIG_CPU_IDLE) && defined(CONFIG_SUSPEND)
+#ifdef CONFIG_CPU_IDLE
 extern int cpuidle_find_deepest_state(struct cpuidle_driver *drv,
 				      struct cpuidle_device *dev);
 extern int cpuidle_enter_freeze(struct cpuidle_driver *drv,
 				struct cpuidle_device *dev);
+extern void cpuidle_use_deepest_state(bool enable);
 #else
 static inline int cpuidle_find_deepest_state(struct cpuidle_driver *drv,
 					     struct cpuidle_device *dev)
@@ -204,6 +206,9 @@ static inline int cpuidle_find_deepest_state(struct cpuidle_driver *drv,
 static inline int cpuidle_enter_freeze(struct cpuidle_driver *drv,
 				       struct cpuidle_device *dev)
 {return -ENODEV; }
+static inline void cpuidle_use_deepest_state(bool enable)
+{
+}
 #endif
 
 /* kernel/sched/idle.c */
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 1d8718d5300d..513e4dfeeae7 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -164,11 +164,14 @@ static void cpuidle_idle_call(void)
 	 * timekeeping to prevent timer interrupts from kicking us out of idle
 	 * until a proper wakeup interrupt happens.
 	 */
-	if (idle_should_freeze()) {
-		entered_state = cpuidle_enter_freeze(drv, dev);
-		if (entered_state > 0) {
-			local_irq_enable();
-			goto exit_idle;
+
+	if (idle_should_freeze() || dev->use_deepest_state) {
+		if (idle_should_freeze()) {
+			entered_state = cpuidle_enter_freeze(drv, dev);
+			if (entered_state > 0) {
+				local_irq_enable();
+				goto exit_idle;
+			}
 		}
 
 		next_state = cpuidle_find_deepest_state(drv, dev);
-- 
cgit v1.2.3-71-gd317


From c1de45ca831acee9b72c9320dde447edafadb43f Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 28 Nov 2016 23:03:05 -0800
Subject: sched/idle: Add support for tasks that inject idle

Idle injection drivers such as Intel powerclamp and ACPI PAD drivers use
realtime tasks to take control of CPU then inject idle. There are two
issues with this approach:

 1. Low efficiency: injected idle task is treated as busy so sched ticks
    do not stop during injected idle period, the result of these
    unwanted wakeups can be ~20% loss in power savings.

 2. Idle accounting: injected idle time is presented to user as busy.

This patch addresses the issues by introducing a new PF_IDLE flag which
allows any given task to be treated as idle task while the flag is set.
Therefore, idle injection tasks can run through the normal flow of NOHZ
idle enter/exit to get the correct accounting as well as tick stop when
possible.

The implication is that idle task is then no longer limited to PID == 0.

Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/cpu.h   |   2 +
 include/linux/sched.h |   3 +-
 kernel/fork.c         |   2 +-
 kernel/sched/core.c   |   1 +
 kernel/sched/idle.c   | 162 +++++++++++++++++++++++++++++++-------------------
 5 files changed, 107 insertions(+), 63 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index b886dc17f2f3..ac0efae38072 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -245,6 +245,8 @@ void arch_cpu_idle_dead(void);
 int cpu_report_state(int cpu);
 int cpu_check_up_prepare(int cpu);
 void cpu_set_state_online(int cpu);
+void play_idle(unsigned long duration_ms);
+
 #ifdef CONFIG_HOTPLUG_CPU
 bool cpu_wait_death(unsigned int cpu, int seconds);
 bool cpu_report_death(void);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 348f51b0ec92..114c7fcb6af6 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2254,6 +2254,7 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut,
 /*
  * Per process flags
  */
+#define PF_IDLE		0x00000002	/* I am an IDLE thread */
 #define PF_EXITING	0x00000004	/* getting shut down */
 #define PF_EXITPIDONE	0x00000008	/* pi exit done on shut down */
 #define PF_VCPU		0x00000010	/* I'm a virtual CPU */
@@ -2609,7 +2610,7 @@ extern struct task_struct *idle_task(int cpu);
  */
 static inline bool is_idle_task(const struct task_struct *p)
 {
-	return p->pid == 0;
+	return !!(p->flags & PF_IDLE);
 }
 extern struct task_struct *curr_task(int cpu);
 extern void ia64_set_curr_task(int cpu, struct task_struct *p);
diff --git a/kernel/fork.c b/kernel/fork.c
index 623259fc794d..5074b2f0827b 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1537,7 +1537,7 @@ static __latent_entropy struct task_struct *copy_process(
 		goto bad_fork_cleanup_count;
 
 	delayacct_tsk_init(p);	/* Must remain after dup_task_struct() */
-	p->flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER);
+	p->flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER | PF_IDLE);
 	p->flags |= PF_FORKNOEXEC;
 	INIT_LIST_HEAD(&p->children);
 	INIT_LIST_HEAD(&p->sibling);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 94732d1ab00a..63b3a8a49884 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5285,6 +5285,7 @@ void init_idle(struct task_struct *idle, int cpu)
 	__sched_fork(0, idle);
 	idle->state = TASK_RUNNING;
 	idle->se.exec_start = sched_clock();
+	idle->flags |= PF_IDLE;
 
 	kasan_unpoison_task_stack(idle);
 
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 513e4dfeeae7..6a4bae0a649d 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -205,76 +205,65 @@ exit_idle:
  *
  * Called with polling cleared.
  */
-static void cpu_idle_loop(void)
+static void do_idle(void)
 {
-	int cpu = smp_processor_id();
-
-	while (1) {
-		/*
-		 * If the arch has a polling bit, we maintain an invariant:
-		 *
-		 * Our polling bit is clear if we're not scheduled (i.e. if
-		 * rq->curr != rq->idle).  This means that, if rq->idle has
-		 * the polling bit set, then setting need_resched is
-		 * guaranteed to cause the cpu to reschedule.
-		 */
-
-		__current_set_polling();
-		quiet_vmstat();
-		tick_nohz_idle_enter();
+	/*
+	 * If the arch has a polling bit, we maintain an invariant:
+	 *
+	 * Our polling bit is clear if we're not scheduled (i.e. if rq->curr !=
+	 * rq->idle). This means that, if rq->idle has the polling bit set,
+	 * then setting need_resched is guaranteed to cause the CPU to
+	 * reschedule.
+	 */
 
-		while (!need_resched()) {
-			check_pgt_cache();
-			rmb();
+	__current_set_polling();
+	tick_nohz_idle_enter();
 
-			if (cpu_is_offline(cpu)) {
-				cpuhp_report_idle_dead();
-				arch_cpu_idle_dead();
-			}
+	while (!need_resched()) {
+		check_pgt_cache();
+		rmb();
 
-			local_irq_disable();
-			arch_cpu_idle_enter();
-
-			/*
-			 * In poll mode we reenable interrupts and spin.
-			 *
-			 * Also if we detected in the wakeup from idle
-			 * path that the tick broadcast device expired
-			 * for us, we don't want to go deep idle as we
-			 * know that the IPI is going to arrive right
-			 * away
-			 */
-			if (cpu_idle_force_poll || tick_check_broadcast_expired())
-				cpu_idle_poll();
-			else
-				cpuidle_idle_call();
-
-			arch_cpu_idle_exit();
+		if (cpu_is_offline(smp_processor_id())) {
+			cpuhp_report_idle_dead();
+			arch_cpu_idle_dead();
 		}
 
-		/*
-		 * Since we fell out of the loop above, we know
-		 * TIF_NEED_RESCHED must be set, propagate it into
-		 * PREEMPT_NEED_RESCHED.
-		 *
-		 * This is required because for polling idle loops we will
-		 * not have had an IPI to fold the state for us.
-		 */
-		preempt_set_need_resched();
-		tick_nohz_idle_exit();
-		__current_clr_polling();
+		local_irq_disable();
+		arch_cpu_idle_enter();
 
 		/*
-		 * We promise to call sched_ttwu_pending and reschedule
-		 * if need_resched is set while polling is set.  That
-		 * means that clearing polling needs to be visible
-		 * before doing these things.
+		 * In poll mode we reenable interrupts and spin. Also if we
+		 * detected in the wakeup from idle path that the tick
+		 * broadcast device expired for us, we don't want to go deep
+		 * idle as we know that the IPI is going to arrive right away.
 		 */
-		smp_mb__after_atomic();
-
-		sched_ttwu_pending();
-		schedule_preempt_disabled();
+		if (cpu_idle_force_poll || tick_check_broadcast_expired())
+			cpu_idle_poll();
+		else
+			cpuidle_idle_call();
+		arch_cpu_idle_exit();
 	}
+
+	/*
+	 * Since we fell out of the loop above, we know TIF_NEED_RESCHED must
+	 * be set, propagate it into PREEMPT_NEED_RESCHED.
+	 *
+	 * This is required because for polling idle loops we will not have had
+	 * an IPI to fold the state for us.
+	 */
+	preempt_set_need_resched();
+	tick_nohz_idle_exit();
+	__current_clr_polling();
+
+	/*
+	 * We promise to call sched_ttwu_pending() and reschedule if
+	 * need_resched() is set while polling is set. That means that clearing
+	 * polling needs to be visible before doing these things.
+	 */
+	smp_mb__after_atomic();
+
+	sched_ttwu_pending();
+	schedule_preempt_disabled();
 }
 
 bool cpu_in_idle(unsigned long pc)
@@ -283,6 +272,56 @@ bool cpu_in_idle(unsigned long pc)
 		pc < (unsigned long)__cpuidle_text_end;
 }
 
+struct idle_timer {
+	struct hrtimer timer;
+	int done;
+};
+
+static enum hrtimer_restart idle_inject_timer_fn(struct hrtimer *timer)
+{
+	struct idle_timer *it = container_of(timer, struct idle_timer, timer);
+
+	WRITE_ONCE(it->done, 1);
+	set_tsk_need_resched(current);
+
+	return HRTIMER_NORESTART;
+}
+
+void play_idle(unsigned long duration_ms)
+{
+	struct idle_timer it;
+
+	/*
+	 * Only FIFO tasks can disable the tick since they don't need the forced
+	 * preemption.
+	 */
+	WARN_ON_ONCE(current->policy != SCHED_FIFO);
+	WARN_ON_ONCE(current->nr_cpus_allowed != 1);
+	WARN_ON_ONCE(!(current->flags & PF_KTHREAD));
+	WARN_ON_ONCE(!(current->flags & PF_NO_SETAFFINITY));
+	WARN_ON_ONCE(!duration_ms);
+
+	rcu_sleep_check();
+	preempt_disable();
+	current->flags |= PF_IDLE;
+	cpuidle_use_deepest_state(true);
+
+	it.done = 0;
+	hrtimer_init_on_stack(&it.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	it.timer.function = idle_inject_timer_fn;
+	hrtimer_start(&it.timer, ms_to_ktime(duration_ms), HRTIMER_MODE_REL_PINNED);
+
+	while (!READ_ONCE(it.done))
+		do_idle();
+
+	cpuidle_use_deepest_state(false);
+	current->flags &= ~PF_IDLE;
+
+	preempt_fold_need_resched();
+	preempt_enable();
+}
+EXPORT_SYMBOL_GPL(play_idle);
+
 void cpu_startup_entry(enum cpuhp_state state)
 {
 	/*
@@ -302,5 +341,6 @@ void cpu_startup_entry(enum cpuhp_state state)
 #endif
 	arch_cpu_idle_prepare();
 	cpuhp_online_idle(state);
-	cpu_idle_loop();
+	while (1)
+		do_idle();
 }
-- 
cgit v1.2.3-71-gd317


From 91291d9ad92faa65a56a9a19d658d8049b78d3d4 Mon Sep 17 00:00:00 2001
From: Stephen Boyd <sboyd@codeaurora.org>
Date: Wed, 30 Nov 2016 16:21:25 +0530
Subject: PM / OPP: Pass opp_table to dev_pm_opp_put_regulator()

Joonyoung Shim reported an interesting problem on his ARM octa-core
Odoroid-XU3 platform. During system suspend, dev_pm_opp_put_regulator()
was failing for a struct device for which dev_pm_opp_set_regulator() is
called earlier.

This happened because an earlier call to
dev_pm_opp_of_cpumask_remove_table() function (from cpufreq-dt.c file)
removed all the entries from opp_table->dev_list apart from the last CPU
device in the cpumask of CPUs sharing the OPP.

But both dev_pm_opp_set_regulator() and dev_pm_opp_put_regulator()
routines get CPU device for the first CPU in the cpumask. And so the OPP
core failed to find the OPP table for the struct device.

This patch attempts to fix this problem by returning a pointer to the
opp_table from dev_pm_opp_set_regulator() and using that as the
parameter to dev_pm_opp_put_regulator(). This ensures that the
dev_pm_opp_put_regulator() doesn't fail to find the opp table.

Note that similar design problem also exists with other
dev_pm_opp_put_*() APIs, but those aren't used currently by anyone and
so we don't need to update them for now.

Cc: 4.4+ <stable@vger.kernel.org> # 4.4+
Reported-by: Joonyoung Shim <jy0922.shim@samsung.com>
Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
[ Viresh: Wrote commit log and tested on exynos 5250 ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/opp/core.c | 22 ++++++----------------
 drivers/cpufreq/cpufreq-dt.c  | 12 ++++++++----
 include/linux/pm_opp.h        | 11 ++++++-----
 3 files changed, 20 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c
index 4c7c6da7a989..2824d3a5e9f0 100644
--- a/drivers/base/power/opp/core.c
+++ b/drivers/base/power/opp/core.c
@@ -1316,7 +1316,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_put_prop_name);
  * that this function is *NOT* called under RCU protection or in contexts where
  * mutex cannot be locked.
  */
-int dev_pm_opp_set_regulator(struct device *dev, const char *name)
+struct opp_table *dev_pm_opp_set_regulator(struct device *dev, const char *name)
 {
 	struct opp_table *opp_table;
 	struct regulator *reg;
@@ -1354,20 +1354,20 @@ int dev_pm_opp_set_regulator(struct device *dev, const char *name)
 	opp_table->regulator = reg;
 
 	mutex_unlock(&opp_table_lock);
-	return 0;
+	return opp_table;
 
 err:
 	_remove_opp_table(opp_table);
 unlock:
 	mutex_unlock(&opp_table_lock);
 
-	return ret;
+	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_set_regulator);
 
 /**
  * dev_pm_opp_put_regulator() - Releases resources blocked for regulator
- * @dev: Device for which regulator was set.
+ * @opp_table: OPP table returned from dev_pm_opp_set_regulator().
  *
  * Locking: The internal opp_table and opp structures are RCU protected.
  * Hence this function internally uses RCU updater strategy with mutex locks
@@ -1375,22 +1375,12 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_set_regulator);
  * that this function is *NOT* called under RCU protection or in contexts where
  * mutex cannot be locked.
  */
-void dev_pm_opp_put_regulator(struct device *dev)
+void dev_pm_opp_put_regulator(struct opp_table *opp_table)
 {
-	struct opp_table *opp_table;
-
 	mutex_lock(&opp_table_lock);
 
-	/* Check for existing table for 'dev' first */
-	opp_table = _find_opp_table(dev);
-	if (IS_ERR(opp_table)) {
-		dev_err(dev, "Failed to find opp_table: %ld\n",
-			PTR_ERR(opp_table));
-		goto unlock;
-	}
-
 	if (IS_ERR(opp_table->regulator)) {
-		dev_err(dev, "%s: Doesn't have regulator set\n", __func__);
+		pr_err("%s: Doesn't have regulator set\n", __func__);
 		goto unlock;
 	}
 
diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c
index 5c07ae05d69a..4d3ec92cbabf 100644
--- a/drivers/cpufreq/cpufreq-dt.c
+++ b/drivers/cpufreq/cpufreq-dt.c
@@ -28,6 +28,7 @@
 #include "cpufreq-dt.h"
 
 struct private_data {
+	struct opp_table *opp_table;
 	struct device *cpu_dev;
 	struct thermal_cooling_device *cdev;
 	const char *reg_name;
@@ -143,6 +144,7 @@ static int resources_available(void)
 static int cpufreq_init(struct cpufreq_policy *policy)
 {
 	struct cpufreq_frequency_table *freq_table;
+	struct opp_table *opp_table = NULL;
 	struct private_data *priv;
 	struct device *cpu_dev;
 	struct clk *cpu_clk;
@@ -186,8 +188,9 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 	 */
 	name = find_supply_name(cpu_dev);
 	if (name) {
-		ret = dev_pm_opp_set_regulator(cpu_dev, name);
-		if (ret) {
+		opp_table = dev_pm_opp_set_regulator(cpu_dev, name);
+		if (IS_ERR(opp_table)) {
+			ret = PTR_ERR(opp_table);
 			dev_err(cpu_dev, "Failed to set regulator for cpu%d: %d\n",
 				policy->cpu, ret);
 			goto out_put_clk;
@@ -237,6 +240,7 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 	}
 
 	priv->reg_name = name;
+	priv->opp_table = opp_table;
 
 	ret = dev_pm_opp_init_cpufreq_table(cpu_dev, &freq_table);
 	if (ret) {
@@ -285,7 +289,7 @@ out_free_priv:
 out_free_opp:
 	dev_pm_opp_of_cpumask_remove_table(policy->cpus);
 	if (name)
-		dev_pm_opp_put_regulator(cpu_dev);
+		dev_pm_opp_put_regulator(opp_table);
 out_put_clk:
 	clk_put(cpu_clk);
 
@@ -300,7 +304,7 @@ static int cpufreq_exit(struct cpufreq_policy *policy)
 	dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &policy->freq_table);
 	dev_pm_opp_of_cpumask_remove_table(policy->related_cpus);
 	if (priv->reg_name)
-		dev_pm_opp_put_regulator(priv->cpu_dev);
+		dev_pm_opp_put_regulator(priv->opp_table);
 
 	clk_put(policy->clk);
 	kfree(priv);
diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h
index bca26157f5b6..f6bc76501912 100644
--- a/include/linux/pm_opp.h
+++ b/include/linux/pm_opp.h
@@ -19,6 +19,7 @@
 
 struct dev_pm_opp;
 struct device;
+struct opp_table;
 
 enum dev_pm_opp_event {
 	OPP_EVENT_ADD, OPP_EVENT_REMOVE, OPP_EVENT_ENABLE, OPP_EVENT_DISABLE,
@@ -62,8 +63,8 @@ int dev_pm_opp_set_supported_hw(struct device *dev, const u32 *versions,
 void dev_pm_opp_put_supported_hw(struct device *dev);
 int dev_pm_opp_set_prop_name(struct device *dev, const char *name);
 void dev_pm_opp_put_prop_name(struct device *dev);
-int dev_pm_opp_set_regulator(struct device *dev, const char *name);
-void dev_pm_opp_put_regulator(struct device *dev);
+struct opp_table *dev_pm_opp_set_regulator(struct device *dev, const char *name);
+void dev_pm_opp_put_regulator(struct opp_table *opp_table);
 int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq);
 int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, const struct cpumask *cpumask);
 int dev_pm_opp_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask);
@@ -170,12 +171,12 @@ static inline int dev_pm_opp_set_prop_name(struct device *dev, const char *name)
 
 static inline void dev_pm_opp_put_prop_name(struct device *dev) {}
 
-static inline int dev_pm_opp_set_regulator(struct device *dev, const char *name)
+static inline struct opp_table *dev_pm_opp_set_regulator(struct device *dev, const char *name)
 {
-	return -ENOTSUPP;
+	return ERR_PTR(-ENOTSUPP);
 }
 
-static inline void dev_pm_opp_put_regulator(struct device *dev) {}
+static inline void dev_pm_opp_put_regulator(struct opp_table *opp_table) {}
 
 static inline int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 {
-- 
cgit v1.2.3-71-gd317


From 0f0fe7e01327b3d524787a2e8b7e78f010db2bb8 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Thu, 1 Dec 2016 16:28:17 +0530
Subject: PM / OPP: Manage supply's voltage/current in a separate structure

This is a preparatory step for multiple regulator per device support.
Move the voltage/current variables to a new structure.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Tested-by: Dave Gerlach <d-gerlach@ti.com>
Reviewed-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/opp/core.c    | 44 +++++++++++++++++++++-------------------
 drivers/base/power/opp/debugfs.c |  8 ++++----
 drivers/base/power/opp/of.c      | 18 ++++++++--------
 drivers/base/power/opp/opp.h     | 11 +++-------
 include/linux/pm_opp.h           | 16 +++++++++++++++
 5 files changed, 55 insertions(+), 42 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c
index 6441dfda489f..188048d3d203 100644
--- a/drivers/base/power/opp/core.c
+++ b/drivers/base/power/opp/core.c
@@ -112,7 +112,7 @@ unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp)
 	if (IS_ERR_OR_NULL(tmp_opp))
 		pr_err("%s: Invalid parameters\n", __func__);
 	else
-		v = tmp_opp->u_volt;
+		v = tmp_opp->supply.u_volt;
 
 	return v;
 }
@@ -246,10 +246,10 @@ unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev)
 		if (!opp->available)
 			continue;
 
-		if (opp->u_volt_min < min_uV)
-			min_uV = opp->u_volt_min;
-		if (opp->u_volt_max > max_uV)
-			max_uV = opp->u_volt_max;
+		if (opp->supply.u_volt_min < min_uV)
+			min_uV = opp->supply.u_volt_min;
+		if (opp->supply.u_volt_max > max_uV)
+			max_uV = opp->supply.u_volt_max;
 	}
 
 	rcu_read_unlock();
@@ -637,14 +637,14 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 	if (IS_ERR(old_opp)) {
 		old_u_volt = 0;
 	} else {
-		old_u_volt = old_opp->u_volt;
-		old_u_volt_min = old_opp->u_volt_min;
-		old_u_volt_max = old_opp->u_volt_max;
+		old_u_volt = old_opp->supply.u_volt;
+		old_u_volt_min = old_opp->supply.u_volt_min;
+		old_u_volt_max = old_opp->supply.u_volt_max;
 	}
 
-	u_volt = opp->u_volt;
-	u_volt_min = opp->u_volt_min;
-	u_volt_max = opp->u_volt_max;
+	u_volt = opp->supply.u_volt;
+	u_volt_min = opp->supply.u_volt_min;
+	u_volt_max = opp->supply.u_volt_max;
 
 	reg = opp_table->regulator;
 
@@ -957,10 +957,11 @@ static bool _opp_supported_by_regulators(struct dev_pm_opp *opp,
 	struct regulator *reg = opp_table->regulator;
 
 	if (!IS_ERR(reg) &&
-	    !regulator_is_supported_voltage(reg, opp->u_volt_min,
-					    opp->u_volt_max)) {
+	    !regulator_is_supported_voltage(reg, opp->supply.u_volt_min,
+					    opp->supply.u_volt_max)) {
 		pr_warn("%s: OPP minuV: %lu maxuV: %lu, not supported by regulator\n",
-			__func__, opp->u_volt_min, opp->u_volt_max);
+			__func__, opp->supply.u_volt_min,
+			opp->supply.u_volt_max);
 		return false;
 	}
 
@@ -993,11 +994,12 @@ int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
 
 		/* Duplicate OPPs */
 		dev_warn(dev, "%s: duplicate OPPs detected. Existing: freq: %lu, volt: %lu, enabled: %d. New: freq: %lu, volt: %lu, enabled: %d\n",
-			 __func__, opp->rate, opp->u_volt, opp->available,
-			 new_opp->rate, new_opp->u_volt, new_opp->available);
+			 __func__, opp->rate, opp->supply.u_volt,
+			 opp->available, new_opp->rate, new_opp->supply.u_volt,
+			 new_opp->available);
 
-		return opp->available && new_opp->u_volt == opp->u_volt ?
-			0 : -EEXIST;
+		return opp->available &&
+		       new_opp->supply.u_volt == opp->supply.u_volt ? 0 : -EEXIST;
 	}
 
 	new_opp->opp_table = opp_table;
@@ -1064,9 +1066,9 @@ int _opp_add_v1(struct device *dev, unsigned long freq, long u_volt,
 	/* populate the opp table */
 	new_opp->rate = freq;
 	tol = u_volt * opp_table->voltage_tolerance_v1 / 100;
-	new_opp->u_volt = u_volt;
-	new_opp->u_volt_min = u_volt - tol;
-	new_opp->u_volt_max = u_volt + tol;
+	new_opp->supply.u_volt = u_volt;
+	new_opp->supply.u_volt_min = u_volt - tol;
+	new_opp->supply.u_volt_max = u_volt + tol;
 	new_opp->available = true;
 	new_opp->dynamic = dynamic;
 
diff --git a/drivers/base/power/opp/debugfs.c b/drivers/base/power/opp/debugfs.c
index ef1ae6b52042..c897676ca35f 100644
--- a/drivers/base/power/opp/debugfs.c
+++ b/drivers/base/power/opp/debugfs.c
@@ -63,16 +63,16 @@ int opp_debug_create_one(struct dev_pm_opp *opp, struct opp_table *opp_table)
 	if (!debugfs_create_ulong("rate_hz", S_IRUGO, d, &opp->rate))
 		return -ENOMEM;
 
-	if (!debugfs_create_ulong("u_volt_target", S_IRUGO, d, &opp->u_volt))
+	if (!debugfs_create_ulong("u_volt_target", S_IRUGO, d, &opp->supply.u_volt))
 		return -ENOMEM;
 
-	if (!debugfs_create_ulong("u_volt_min", S_IRUGO, d, &opp->u_volt_min))
+	if (!debugfs_create_ulong("u_volt_min", S_IRUGO, d, &opp->supply.u_volt_min))
 		return -ENOMEM;
 
-	if (!debugfs_create_ulong("u_volt_max", S_IRUGO, d, &opp->u_volt_max))
+	if (!debugfs_create_ulong("u_volt_max", S_IRUGO, d, &opp->supply.u_volt_max))
 		return -ENOMEM;
 
-	if (!debugfs_create_ulong("u_amp", S_IRUGO, d, &opp->u_amp))
+	if (!debugfs_create_ulong("u_amp", S_IRUGO, d, &opp->supply.u_amp))
 		return -ENOMEM;
 
 	if (!debugfs_create_ulong("clock_latency_ns", S_IRUGO, d,
diff --git a/drivers/base/power/opp/of.c b/drivers/base/power/opp/of.c
index 5b3755e49731..bdf409d42126 100644
--- a/drivers/base/power/opp/of.c
+++ b/drivers/base/power/opp/of.c
@@ -148,14 +148,14 @@ static int opp_parse_supplies(struct dev_pm_opp *opp, struct device *dev,
 		return -EINVAL;
 	}
 
-	opp->u_volt = microvolt[0];
+	opp->supply.u_volt = microvolt[0];
 
 	if (count == 1) {
-		opp->u_volt_min = opp->u_volt;
-		opp->u_volt_max = opp->u_volt;
+		opp->supply.u_volt_min = opp->supply.u_volt;
+		opp->supply.u_volt_max = opp->supply.u_volt;
 	} else {
-		opp->u_volt_min = microvolt[1];
-		opp->u_volt_max = microvolt[2];
+		opp->supply.u_volt_min = microvolt[1];
+		opp->supply.u_volt_max = microvolt[2];
 	}
 
 	/* Search for "opp-microamp-<name>" */
@@ -173,7 +173,7 @@ static int opp_parse_supplies(struct dev_pm_opp *opp, struct device *dev,
 	}
 
 	if (prop && !of_property_read_u32(opp->np, name, &val))
-		opp->u_amp = val;
+		opp->supply.u_amp = val;
 
 	return 0;
 }
@@ -303,9 +303,9 @@ static int _opp_add_static_v2(struct device *dev, struct device_node *np)
 	mutex_unlock(&opp_table_lock);
 
 	pr_debug("%s: turbo:%d rate:%lu uv:%lu uvmin:%lu uvmax:%lu latency:%lu\n",
-		 __func__, new_opp->turbo, new_opp->rate, new_opp->u_volt,
-		 new_opp->u_volt_min, new_opp->u_volt_max,
-		 new_opp->clock_latency_ns);
+		 __func__, new_opp->turbo, new_opp->rate,
+		 new_opp->supply.u_volt, new_opp->supply.u_volt_min,
+		 new_opp->supply.u_volt_max, new_opp->clock_latency_ns);
 
 	/*
 	 * Notify the changes in the availability of the operable
diff --git a/drivers/base/power/opp/opp.h b/drivers/base/power/opp/opp.h
index 96cd30ac6c1d..8a02516542c2 100644
--- a/drivers/base/power/opp/opp.h
+++ b/drivers/base/power/opp/opp.h
@@ -61,10 +61,7 @@ extern struct list_head opp_tables;
  * @turbo:	true if turbo (boost) OPP
  * @suspend:	true if suspend OPP
  * @rate:	Frequency in hertz
- * @u_volt:	Target voltage in microvolts corresponding to this OPP
- * @u_volt_min:	Minimum voltage in microvolts corresponding to this OPP
- * @u_volt_max:	Maximum voltage in microvolts corresponding to this OPP
- * @u_amp:	Maximum current drawn by the device in microamperes
+ * @supply:	Power supply voltage/current values
  * @clock_latency_ns: Latency (in nanoseconds) of switching to this OPP's
  *		frequency from any other OPP's frequency.
  * @opp_table:	points back to the opp_table struct this opp belongs to
@@ -83,10 +80,8 @@ struct dev_pm_opp {
 	bool suspend;
 	unsigned long rate;
 
-	unsigned long u_volt;
-	unsigned long u_volt_min;
-	unsigned long u_volt_max;
-	unsigned long u_amp;
+	struct dev_pm_opp_supply supply;
+
 	unsigned long clock_latency_ns;
 
 	struct opp_table *opp_table;
diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h
index f6bc76501912..824f7268f687 100644
--- a/include/linux/pm_opp.h
+++ b/include/linux/pm_opp.h
@@ -25,6 +25,22 @@ enum dev_pm_opp_event {
 	OPP_EVENT_ADD, OPP_EVENT_REMOVE, OPP_EVENT_ENABLE, OPP_EVENT_DISABLE,
 };
 
+/**
+ * struct dev_pm_opp_supply - Power supply voltage/current values
+ * @u_volt:	Target voltage in microvolts corresponding to this OPP
+ * @u_volt_min:	Minimum voltage in microvolts corresponding to this OPP
+ * @u_volt_max:	Maximum voltage in microvolts corresponding to this OPP
+ * @u_amp:	Maximum current drawn by the device in microamperes
+ *
+ * This structure stores the voltage/current values for a single power supply.
+ */
+struct dev_pm_opp_supply {
+	unsigned long u_volt;
+	unsigned long u_volt_min;
+	unsigned long u_volt_max;
+	unsigned long u_amp;
+};
+
 #if defined(CONFIG_PM_OPP)
 
 unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp);
-- 
cgit v1.2.3-71-gd317


From dfbe4678d709e25e0f36e6b6333e2a7a67aefb7e Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Thu, 1 Dec 2016 16:28:19 +0530
Subject: PM / OPP: Add infrastructure to manage multiple regulators

This patch adds infrastructure to manage multiple regulators and updates
the only user (cpufreq-dt) of dev_pm_opp_set{put}_regulator().

This is preparatory work for adding full support for devices with
multiple regulators.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Tested-by: Dave Gerlach <d-gerlach@ti.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/opp/core.c    | 248 +++++++++++++++++++++++++++------------
 drivers/base/power/opp/debugfs.c |  52 ++++++--
 drivers/base/power/opp/of.c      | 103 +++++++++++-----
 drivers/base/power/opp/opp.h     |  10 +-
 drivers/cpufreq/cpufreq-dt.c     |   6 +-
 include/linux/pm_opp.h           |   8 +-
 6 files changed, 300 insertions(+), 127 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c
index 46ad8470c438..b4da31c5a5eb 100644
--- a/drivers/base/power/opp/core.c
+++ b/drivers/base/power/opp/core.c
@@ -93,6 +93,8 @@ struct opp_table *_find_opp_table(struct device *dev)
  * Return: voltage in micro volt corresponding to the opp, else
  * return 0
  *
+ * This is useful only for devices with single power supply.
+ *
  * Locking: This function must be called under rcu_read_lock(). opp is a rcu
  * protected pointer. This means that opp which could have been fetched by
  * opp_find_freq_{exact,ceil,floor} functions is valid as long as we are
@@ -112,7 +114,7 @@ unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp)
 	if (IS_ERR_OR_NULL(tmp_opp))
 		pr_err("%s: Invalid parameters\n", __func__);
 	else
-		v = tmp_opp->supply.u_volt;
+		v = tmp_opp->supplies[0].u_volt;
 
 	return v;
 }
@@ -210,6 +212,24 @@ unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_get_max_clock_latency);
 
+static int _get_regulator_count(struct device *dev)
+{
+	struct opp_table *opp_table;
+	int count;
+
+	rcu_read_lock();
+
+	opp_table = _find_opp_table(dev);
+	if (!IS_ERR(opp_table))
+		count = opp_table->regulator_count;
+	else
+		count = 0;
+
+	rcu_read_unlock();
+
+	return count;
+}
+
 /**
  * dev_pm_opp_get_max_volt_latency() - Get max voltage latency in nanoseconds
  * @dev: device for which we do this operation
@@ -222,34 +242,51 @@ unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev)
 {
 	struct opp_table *opp_table;
 	struct dev_pm_opp *opp;
-	struct regulator *reg;
+	struct regulator *reg, **regulators;
 	unsigned long latency_ns = 0;
-	unsigned long min_uV = ~0, max_uV = 0;
-	int ret;
+	int ret, i, count;
+	struct {
+		unsigned long min;
+		unsigned long max;
+	} *uV;
+
+	count = _get_regulator_count(dev);
+
+	/* Regulator may not be required for the device */
+	if (!count)
+		return 0;
+
+	regulators = kmalloc_array(count, sizeof(*regulators), GFP_KERNEL);
+	if (!regulators)
+		return 0;
+
+	uV = kmalloc_array(count, sizeof(*uV), GFP_KERNEL);
+	if (!uV)
+		goto free_regulators;
 
 	rcu_read_lock();
 
 	opp_table = _find_opp_table(dev);
 	if (IS_ERR(opp_table)) {
 		rcu_read_unlock();
-		return 0;
+		goto free_uV;
 	}
 
-	reg = opp_table->regulator;
-	if (IS_ERR(reg)) {
-		/* Regulator may not be required for device */
-		rcu_read_unlock();
-		return 0;
-	}
+	memcpy(regulators, opp_table->regulators, count * sizeof(*regulators));
 
-	list_for_each_entry_rcu(opp, &opp_table->opp_list, node) {
-		if (!opp->available)
-			continue;
+	for (i = 0; i < count; i++) {
+		uV[i].min = ~0;
+		uV[i].max = 0;
 
-		if (opp->supply.u_volt_min < min_uV)
-			min_uV = opp->supply.u_volt_min;
-		if (opp->supply.u_volt_max > max_uV)
-			max_uV = opp->supply.u_volt_max;
+		list_for_each_entry_rcu(opp, &opp_table->opp_list, node) {
+			if (!opp->available)
+				continue;
+
+			if (opp->supplies[i].u_volt_min < uV[i].min)
+				uV[i].min = opp->supplies[i].u_volt_min;
+			if (opp->supplies[i].u_volt_max > uV[i].max)
+				uV[i].max = opp->supplies[i].u_volt_max;
+		}
 	}
 
 	rcu_read_unlock();
@@ -258,9 +295,16 @@ unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev)
 	 * The caller needs to ensure that opp_table (and hence the regulator)
 	 * isn't freed, while we are executing this routine.
 	 */
-	ret = regulator_set_voltage_time(reg, min_uV, max_uV);
-	if (ret > 0)
-		latency_ns = ret * 1000;
+	for (i = 0; reg = regulators[i], i < count; i++) {
+		ret = regulator_set_voltage_time(reg, uV[i].min, uV[i].max);
+		if (ret > 0)
+			latency_ns += ret * 1000;
+	}
+
+free_uV:
+	kfree(uV);
+free_regulators:
+	kfree(regulators);
 
 	return latency_ns;
 }
@@ -580,7 +624,7 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 {
 	struct opp_table *opp_table;
 	struct dev_pm_opp *old_opp, *opp;
-	struct regulator *reg;
+	struct regulator *reg = ERR_PTR(-ENXIO);
 	struct clk *clk;
 	unsigned long freq, old_freq;
 	struct dev_pm_opp_supply old_supply, new_supply;
@@ -633,14 +677,23 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 		return ret;
 	}
 
+	if (opp_table->regulators) {
+		/* This function only supports single regulator per device */
+		if (WARN_ON(opp_table->regulator_count > 1)) {
+			dev_err(dev, "multiple regulators not supported\n");
+			rcu_read_unlock();
+			return -EINVAL;
+		}
+
+		reg = opp_table->regulators[0];
+	}
+
 	if (IS_ERR(old_opp))
 		old_supply.u_volt = 0;
 	else
-		memcpy(&old_supply, &old_opp->supply, sizeof(old_supply));
-
-	memcpy(&new_supply, &opp->supply, sizeof(new_supply));
+		memcpy(&old_supply, old_opp->supplies, sizeof(old_supply));
 
-	reg = opp_table->regulator;
+	memcpy(&new_supply, opp->supplies, sizeof(new_supply));
 
 	rcu_read_unlock();
 
@@ -764,9 +817,6 @@ static struct opp_table *_add_opp_table(struct device *dev)
 
 	_of_init_opp_table(opp_table, dev);
 
-	/* Set regulator to a non-NULL error value */
-	opp_table->regulator = ERR_PTR(-ENXIO);
-
 	/* Find clk for the device */
 	opp_table->clk = clk_get(dev, NULL);
 	if (IS_ERR(opp_table->clk)) {
@@ -815,7 +865,7 @@ static void _remove_opp_table(struct opp_table *opp_table)
 	if (opp_table->prop_name)
 		return;
 
-	if (!IS_ERR(opp_table->regulator))
+	if (opp_table->regulators)
 		return;
 
 	/* Release clk */
@@ -924,35 +974,50 @@ struct dev_pm_opp *_allocate_opp(struct device *dev,
 				 struct opp_table **opp_table)
 {
 	struct dev_pm_opp *opp;
+	int count, supply_size;
+	struct opp_table *table;
 
-	/* allocate new OPP node */
-	opp = kzalloc(sizeof(*opp), GFP_KERNEL);
-	if (!opp)
+	table = _add_opp_table(dev);
+	if (!table)
 		return NULL;
 
-	INIT_LIST_HEAD(&opp->node);
+	/* Allocate space for at least one supply */
+	count = table->regulator_count ? table->regulator_count : 1;
+	supply_size = sizeof(*opp->supplies) * count;
 
-	*opp_table = _add_opp_table(dev);
-	if (!*opp_table) {
-		kfree(opp);
+	/* allocate new OPP node and supplies structures */
+	opp = kzalloc(sizeof(*opp) + supply_size, GFP_KERNEL);
+	if (!opp) {
+		kfree(table);
 		return NULL;
 	}
 
+	/* Put the supplies at the end of the OPP structure as an empty array */
+	opp->supplies = (struct dev_pm_opp_supply *)(opp + 1);
+	INIT_LIST_HEAD(&opp->node);
+
+	*opp_table = table;
+
 	return opp;
 }
 
 static bool _opp_supported_by_regulators(struct dev_pm_opp *opp,
 					 struct opp_table *opp_table)
 {
-	struct regulator *reg = opp_table->regulator;
-
-	if (!IS_ERR(reg) &&
-	    !regulator_is_supported_voltage(reg, opp->supply.u_volt_min,
-					    opp->supply.u_volt_max)) {
-		pr_warn("%s: OPP minuV: %lu maxuV: %lu, not supported by regulator\n",
-			__func__, opp->supply.u_volt_min,
-			opp->supply.u_volt_max);
-		return false;
+	struct regulator *reg;
+	int i;
+
+	for (i = 0; i < opp_table->regulator_count; i++) {
+		reg = opp_table->regulators[i];
+
+		if (!regulator_is_supported_voltage(reg,
+					opp->supplies[i].u_volt_min,
+					opp->supplies[i].u_volt_max)) {
+			pr_warn("%s: OPP minuV: %lu maxuV: %lu, not supported by regulator\n",
+				__func__, opp->supplies[i].u_volt_min,
+				opp->supplies[i].u_volt_max);
+			return false;
+		}
 	}
 
 	return true;
@@ -984,12 +1049,13 @@ int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
 
 		/* Duplicate OPPs */
 		dev_warn(dev, "%s: duplicate OPPs detected. Existing: freq: %lu, volt: %lu, enabled: %d. New: freq: %lu, volt: %lu, enabled: %d\n",
-			 __func__, opp->rate, opp->supply.u_volt,
-			 opp->available, new_opp->rate, new_opp->supply.u_volt,
-			 new_opp->available);
+			 __func__, opp->rate, opp->supplies[0].u_volt,
+			 opp->available, new_opp->rate,
+			 new_opp->supplies[0].u_volt, new_opp->available);
 
+		/* Should we compare voltages for all regulators here ? */
 		return opp->available &&
-		       new_opp->supply.u_volt == opp->supply.u_volt ? 0 : -EEXIST;
+		       new_opp->supplies[0].u_volt == opp->supplies[0].u_volt ? 0 : -EEXIST;
 	}
 
 	new_opp->opp_table = opp_table;
@@ -1056,9 +1122,9 @@ int _opp_add_v1(struct device *dev, unsigned long freq, long u_volt,
 	/* populate the opp table */
 	new_opp->rate = freq;
 	tol = u_volt * opp_table->voltage_tolerance_v1 / 100;
-	new_opp->supply.u_volt = u_volt;
-	new_opp->supply.u_volt_min = u_volt - tol;
-	new_opp->supply.u_volt_max = u_volt + tol;
+	new_opp->supplies[0].u_volt = u_volt;
+	new_opp->supplies[0].u_volt_min = u_volt - tol;
+	new_opp->supplies[0].u_volt_max = u_volt + tol;
 	new_opp->available = true;
 	new_opp->dynamic = dynamic;
 
@@ -1303,12 +1369,14 @@ unlock:
 EXPORT_SYMBOL_GPL(dev_pm_opp_put_prop_name);
 
 /**
- * dev_pm_opp_set_regulator() - Set regulator name for the device
+ * dev_pm_opp_set_regulators() - Set regulator names for the device
  * @dev: Device for which regulator name is being set.
- * @name: Name of the regulator.
+ * @names: Array of pointers to the names of the regulator.
+ * @count: Number of regulators.
  *
  * In order to support OPP switching, OPP layer needs to know the name of the
- * device's regulator, as the core would be required to switch voltages as well.
+ * device's regulators, as the core would be required to switch voltages as
+ * well.
  *
  * This must be called before any OPPs are initialized for the device.
  *
@@ -1318,11 +1386,13 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_put_prop_name);
  * that this function is *NOT* called under RCU protection or in contexts where
  * mutex cannot be locked.
  */
-struct opp_table *dev_pm_opp_set_regulator(struct device *dev, const char *name)
+struct opp_table *dev_pm_opp_set_regulators(struct device *dev,
+					    const char * const names[],
+					    unsigned int count)
 {
 	struct opp_table *opp_table;
 	struct regulator *reg;
-	int ret;
+	int ret, i;
 
 	mutex_lock(&opp_table_lock);
 
@@ -1338,26 +1408,44 @@ struct opp_table *dev_pm_opp_set_regulator(struct device *dev, const char *name)
 		goto err;
 	}
 
-	/* Already have a regulator set */
-	if (WARN_ON(!IS_ERR(opp_table->regulator))) {
+	/* Already have regulators set */
+	if (WARN_ON(opp_table->regulators)) {
 		ret = -EBUSY;
 		goto err;
 	}
-	/* Allocate the regulator */
-	reg = regulator_get_optional(dev, name);
-	if (IS_ERR(reg)) {
-		ret = PTR_ERR(reg);
-		if (ret != -EPROBE_DEFER)
-			dev_err(dev, "%s: no regulator (%s) found: %d\n",
-				__func__, name, ret);
+
+	opp_table->regulators = kmalloc_array(count,
+					      sizeof(*opp_table->regulators),
+					      GFP_KERNEL);
+	if (!opp_table->regulators) {
+		ret = -ENOMEM;
 		goto err;
 	}
 
-	opp_table->regulator = reg;
+	for (i = 0; i < count; i++) {
+		reg = regulator_get_optional(dev, names[i]);
+		if (IS_ERR(reg)) {
+			ret = PTR_ERR(reg);
+			if (ret != -EPROBE_DEFER)
+				dev_err(dev, "%s: no regulator (%s) found: %d\n",
+					__func__, names[i], ret);
+			goto free_regulators;
+		}
+
+		opp_table->regulators[i] = reg;
+	}
+
+	opp_table->regulator_count = count;
 
 	mutex_unlock(&opp_table_lock);
 	return opp_table;
 
+free_regulators:
+	while (i != 0)
+		regulator_put(opp_table->regulators[--i]);
+
+	kfree(opp_table->regulators);
+	opp_table->regulators = NULL;
 err:
 	_remove_opp_table(opp_table);
 unlock:
@@ -1365,11 +1453,11 @@ unlock:
 
 	return ERR_PTR(ret);
 }
-EXPORT_SYMBOL_GPL(dev_pm_opp_set_regulator);
+EXPORT_SYMBOL_GPL(dev_pm_opp_set_regulators);
 
 /**
- * dev_pm_opp_put_regulator() - Releases resources blocked for regulator
- * @opp_table: OPP table returned from dev_pm_opp_set_regulator().
+ * dev_pm_opp_put_regulators() - Releases resources blocked for regulator
+ * @opp_table: OPP table returned from dev_pm_opp_set_regulators().
  *
  * Locking: The internal opp_table and opp structures are RCU protected.
  * Hence this function internally uses RCU updater strategy with mutex locks
@@ -1377,20 +1465,26 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_set_regulator);
  * that this function is *NOT* called under RCU protection or in contexts where
  * mutex cannot be locked.
  */
-void dev_pm_opp_put_regulator(struct opp_table *opp_table)
+void dev_pm_opp_put_regulators(struct opp_table *opp_table)
 {
+	int i;
+
 	mutex_lock(&opp_table_lock);
 
-	if (IS_ERR(opp_table->regulator)) {
-		pr_err("%s: Doesn't have regulator set\n", __func__);
+	if (!opp_table->regulators) {
+		pr_err("%s: Doesn't have regulators set\n", __func__);
 		goto unlock;
 	}
 
 	/* Make sure there are no concurrent readers while updating opp_table */
 	WARN_ON(!list_empty(&opp_table->opp_list));
 
-	regulator_put(opp_table->regulator);
-	opp_table->regulator = ERR_PTR(-ENXIO);
+	for (i = opp_table->regulator_count - 1; i >= 0; i--)
+		regulator_put(opp_table->regulators[i]);
+
+	kfree(opp_table->regulators);
+	opp_table->regulators = NULL;
+	opp_table->regulator_count = 0;
 
 	/* Try freeing opp_table if this was the last blocking resource */
 	_remove_opp_table(opp_table);
@@ -1398,7 +1492,7 @@ void dev_pm_opp_put_regulator(struct opp_table *opp_table)
 unlock:
 	mutex_unlock(&opp_table_lock);
 }
-EXPORT_SYMBOL_GPL(dev_pm_opp_put_regulator);
+EXPORT_SYMBOL_GPL(dev_pm_opp_put_regulators);
 
 /**
  * dev_pm_opp_add()  - Add an OPP table from a table definitions
diff --git a/drivers/base/power/opp/debugfs.c b/drivers/base/power/opp/debugfs.c
index c897676ca35f..95f433db4ac7 100644
--- a/drivers/base/power/opp/debugfs.c
+++ b/drivers/base/power/opp/debugfs.c
@@ -15,6 +15,7 @@
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/limits.h>
+#include <linux/slab.h>
 
 #include "opp.h"
 
@@ -34,6 +35,46 @@ void opp_debug_remove_one(struct dev_pm_opp *opp)
 	debugfs_remove_recursive(opp->dentry);
 }
 
+static bool opp_debug_create_supplies(struct dev_pm_opp *opp,
+				      struct opp_table *opp_table,
+				      struct dentry *pdentry)
+{
+	struct dentry *d;
+	int i = 0;
+	char *name;
+
+	/* Always create at least supply-0 directory */
+	do {
+		name = kasprintf(GFP_KERNEL, "supply-%d", i);
+
+		/* Create per-opp directory */
+		d = debugfs_create_dir(name, pdentry);
+
+		kfree(name);
+
+		if (!d)
+			return false;
+
+		if (!debugfs_create_ulong("u_volt_target", S_IRUGO, d,
+					  &opp->supplies[i].u_volt))
+			return false;
+
+		if (!debugfs_create_ulong("u_volt_min", S_IRUGO, d,
+					  &opp->supplies[i].u_volt_min))
+			return false;
+
+		if (!debugfs_create_ulong("u_volt_max", S_IRUGO, d,
+					  &opp->supplies[i].u_volt_max))
+			return false;
+
+		if (!debugfs_create_ulong("u_amp", S_IRUGO, d,
+					  &opp->supplies[i].u_amp))
+			return false;
+	} while (++i < opp_table->regulator_count);
+
+	return true;
+}
+
 int opp_debug_create_one(struct dev_pm_opp *opp, struct opp_table *opp_table)
 {
 	struct dentry *pdentry = opp_table->dentry;
@@ -63,16 +104,7 @@ int opp_debug_create_one(struct dev_pm_opp *opp, struct opp_table *opp_table)
 	if (!debugfs_create_ulong("rate_hz", S_IRUGO, d, &opp->rate))
 		return -ENOMEM;
 
-	if (!debugfs_create_ulong("u_volt_target", S_IRUGO, d, &opp->supply.u_volt))
-		return -ENOMEM;
-
-	if (!debugfs_create_ulong("u_volt_min", S_IRUGO, d, &opp->supply.u_volt_min))
-		return -ENOMEM;
-
-	if (!debugfs_create_ulong("u_volt_max", S_IRUGO, d, &opp->supply.u_volt_max))
-		return -ENOMEM;
-
-	if (!debugfs_create_ulong("u_amp", S_IRUGO, d, &opp->supply.u_amp))
+	if (!opp_debug_create_supplies(opp, opp_table, d))
 		return -ENOMEM;
 
 	if (!debugfs_create_ulong("clock_latency_ns", S_IRUGO, d,
diff --git a/drivers/base/power/opp/of.c b/drivers/base/power/opp/of.c
index bdf409d42126..3f7d2591b173 100644
--- a/drivers/base/power/opp/of.c
+++ b/drivers/base/power/opp/of.c
@@ -17,6 +17,7 @@
 #include <linux/errno.h>
 #include <linux/device.h>
 #include <linux/of.h>
+#include <linux/slab.h>
 #include <linux/export.h>
 
 #include "opp.h"
@@ -101,16 +102,16 @@ static bool _opp_is_supported(struct device *dev, struct opp_table *opp_table,
 	return true;
 }
 
-/* TODO: Support multiple regulators */
 static int opp_parse_supplies(struct dev_pm_opp *opp, struct device *dev,
 			      struct opp_table *opp_table)
 {
-	u32 microvolt[3] = {0};
-	u32 val;
-	int count, ret;
+	u32 *microvolt, *microamp = NULL;
+	int supplies, vcount, icount, ret, i, j;
 	struct property *prop = NULL;
 	char name[NAME_MAX];
 
+	supplies = opp_table->regulator_count ? opp_table->regulator_count : 1;
+
 	/* Search for "opp-microvolt-<name>" */
 	if (opp_table->prop_name) {
 		snprintf(name, sizeof(name), "opp-microvolt-%s",
@@ -128,34 +129,29 @@ static int opp_parse_supplies(struct dev_pm_opp *opp, struct device *dev,
 			return 0;
 	}
 
-	count = of_property_count_u32_elems(opp->np, name);
-	if (count < 0) {
+	vcount = of_property_count_u32_elems(opp->np, name);
+	if (vcount < 0) {
 		dev_err(dev, "%s: Invalid %s property (%d)\n",
-			__func__, name, count);
-		return count;
+			__func__, name, vcount);
+		return vcount;
 	}
 
-	/* There can be one or three elements here */
-	if (count != 1 && count != 3) {
-		dev_err(dev, "%s: Invalid number of elements in %s property (%d)\n",
-			__func__, name, count);
+	/* There can be one or three elements per supply */
+	if (vcount != supplies && vcount != supplies * 3) {
+		dev_err(dev, "%s: Invalid number of elements in %s property (%d) with supplies (%d)\n",
+			__func__, name, vcount, supplies);
 		return -EINVAL;
 	}
 
-	ret = of_property_read_u32_array(opp->np, name, microvolt, count);
+	microvolt = kmalloc_array(vcount, sizeof(*microvolt), GFP_KERNEL);
+	if (!microvolt)
+		return -ENOMEM;
+
+	ret = of_property_read_u32_array(opp->np, name, microvolt, vcount);
 	if (ret) {
 		dev_err(dev, "%s: error parsing %s: %d\n", __func__, name, ret);
-		return -EINVAL;
-	}
-
-	opp->supply.u_volt = microvolt[0];
-
-	if (count == 1) {
-		opp->supply.u_volt_min = opp->supply.u_volt;
-		opp->supply.u_volt_max = opp->supply.u_volt;
-	} else {
-		opp->supply.u_volt_min = microvolt[1];
-		opp->supply.u_volt_max = microvolt[2];
+		ret = -EINVAL;
+		goto free_microvolt;
 	}
 
 	/* Search for "opp-microamp-<name>" */
@@ -172,10 +168,59 @@ static int opp_parse_supplies(struct dev_pm_opp *opp, struct device *dev,
 		prop = of_find_property(opp->np, name, NULL);
 	}
 
-	if (prop && !of_property_read_u32(opp->np, name, &val))
-		opp->supply.u_amp = val;
+	if (prop) {
+		icount = of_property_count_u32_elems(opp->np, name);
+		if (icount < 0) {
+			dev_err(dev, "%s: Invalid %s property (%d)\n", __func__,
+				name, icount);
+			ret = icount;
+			goto free_microvolt;
+		}
 
-	return 0;
+		if (icount != supplies) {
+			dev_err(dev, "%s: Invalid number of elements in %s property (%d) with supplies (%d)\n",
+				__func__, name, icount, supplies);
+			ret = -EINVAL;
+			goto free_microvolt;
+		}
+
+		microamp = kmalloc_array(icount, sizeof(*microamp), GFP_KERNEL);
+		if (!microamp) {
+			ret = -EINVAL;
+			goto free_microvolt;
+		}
+
+		ret = of_property_read_u32_array(opp->np, name, microamp,
+						 icount);
+		if (ret) {
+			dev_err(dev, "%s: error parsing %s: %d\n", __func__,
+				name, ret);
+			ret = -EINVAL;
+			goto free_microamp;
+		}
+	}
+
+	for (i = 0, j = 0; i < supplies; i++) {
+		opp->supplies[i].u_volt = microvolt[j++];
+
+		if (vcount == supplies) {
+			opp->supplies[i].u_volt_min = opp->supplies[i].u_volt;
+			opp->supplies[i].u_volt_max = opp->supplies[i].u_volt;
+		} else {
+			opp->supplies[i].u_volt_min = microvolt[j++];
+			opp->supplies[i].u_volt_max = microvolt[j++];
+		}
+
+		if (microamp)
+			opp->supplies[i].u_amp = microamp[i];
+	}
+
+free_microamp:
+	kfree(microamp);
+free_microvolt:
+	kfree(microvolt);
+
+	return ret;
 }
 
 /**
@@ -304,8 +349,8 @@ static int _opp_add_static_v2(struct device *dev, struct device_node *np)
 
 	pr_debug("%s: turbo:%d rate:%lu uv:%lu uvmin:%lu uvmax:%lu latency:%lu\n",
 		 __func__, new_opp->turbo, new_opp->rate,
-		 new_opp->supply.u_volt, new_opp->supply.u_volt_min,
-		 new_opp->supply.u_volt_max, new_opp->clock_latency_ns);
+		 new_opp->supplies[0].u_volt, new_opp->supplies[0].u_volt_min,
+		 new_opp->supplies[0].u_volt_max, new_opp->clock_latency_ns);
 
 	/*
 	 * Notify the changes in the availability of the operable
diff --git a/drivers/base/power/opp/opp.h b/drivers/base/power/opp/opp.h
index 8a02516542c2..5b0f7e53bede 100644
--- a/drivers/base/power/opp/opp.h
+++ b/drivers/base/power/opp/opp.h
@@ -61,7 +61,7 @@ extern struct list_head opp_tables;
  * @turbo:	true if turbo (boost) OPP
  * @suspend:	true if suspend OPP
  * @rate:	Frequency in hertz
- * @supply:	Power supply voltage/current values
+ * @supplies:	Power supplies voltage/current values
  * @clock_latency_ns: Latency (in nanoseconds) of switching to this OPP's
  *		frequency from any other OPP's frequency.
  * @opp_table:	points back to the opp_table struct this opp belongs to
@@ -80,7 +80,7 @@ struct dev_pm_opp {
 	bool suspend;
 	unsigned long rate;
 
-	struct dev_pm_opp_supply supply;
+	struct dev_pm_opp_supply *supplies;
 
 	unsigned long clock_latency_ns;
 
@@ -139,7 +139,8 @@ enum opp_table_access {
  * @supported_hw_count: Number of elements in supported_hw array.
  * @prop_name: A name to postfix to many DT properties, while parsing them.
  * @clk: Device's clock handle
- * @regulator: Supply regulator
+ * @regulators: Supply regulators
+ * @regulator_count: Number of power supply regulators
  * @dentry:	debugfs dentry pointer of the real device directory (not links).
  * @dentry_name: Name of the real dentry.
  *
@@ -174,7 +175,8 @@ struct opp_table {
 	unsigned int supported_hw_count;
 	const char *prop_name;
 	struct clk *clk;
-	struct regulator *regulator;
+	struct regulator **regulators;
+	unsigned int regulator_count;
 
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *dentry;
diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c
index 4d3ec92cbabf..269013311e79 100644
--- a/drivers/cpufreq/cpufreq-dt.c
+++ b/drivers/cpufreq/cpufreq-dt.c
@@ -188,7 +188,7 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 	 */
 	name = find_supply_name(cpu_dev);
 	if (name) {
-		opp_table = dev_pm_opp_set_regulator(cpu_dev, name);
+		opp_table = dev_pm_opp_set_regulators(cpu_dev, &name, 1);
 		if (IS_ERR(opp_table)) {
 			ret = PTR_ERR(opp_table);
 			dev_err(cpu_dev, "Failed to set regulator for cpu%d: %d\n",
@@ -289,7 +289,7 @@ out_free_priv:
 out_free_opp:
 	dev_pm_opp_of_cpumask_remove_table(policy->cpus);
 	if (name)
-		dev_pm_opp_put_regulator(opp_table);
+		dev_pm_opp_put_regulators(opp_table);
 out_put_clk:
 	clk_put(cpu_clk);
 
@@ -304,7 +304,7 @@ static int cpufreq_exit(struct cpufreq_policy *policy)
 	dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &policy->freq_table);
 	dev_pm_opp_of_cpumask_remove_table(policy->related_cpus);
 	if (priv->reg_name)
-		dev_pm_opp_put_regulator(priv->opp_table);
+		dev_pm_opp_put_regulators(priv->opp_table);
 
 	clk_put(policy->clk);
 	kfree(priv);
diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h
index 824f7268f687..9a825ae78653 100644
--- a/include/linux/pm_opp.h
+++ b/include/linux/pm_opp.h
@@ -79,8 +79,8 @@ int dev_pm_opp_set_supported_hw(struct device *dev, const u32 *versions,
 void dev_pm_opp_put_supported_hw(struct device *dev);
 int dev_pm_opp_set_prop_name(struct device *dev, const char *name);
 void dev_pm_opp_put_prop_name(struct device *dev);
-struct opp_table *dev_pm_opp_set_regulator(struct device *dev, const char *name);
-void dev_pm_opp_put_regulator(struct opp_table *opp_table);
+struct opp_table *dev_pm_opp_set_regulators(struct device *dev, const char * const names[], unsigned int count);
+void dev_pm_opp_put_regulators(struct opp_table *opp_table);
 int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq);
 int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, const struct cpumask *cpumask);
 int dev_pm_opp_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask);
@@ -187,12 +187,12 @@ static inline int dev_pm_opp_set_prop_name(struct device *dev, const char *name)
 
 static inline void dev_pm_opp_put_prop_name(struct device *dev) {}
 
-static inline struct opp_table *dev_pm_opp_set_regulator(struct device *dev, const char *name)
+static inline struct opp_table *dev_pm_opp_set_regulators(struct device *dev, const char * const names[], unsigned int count)
 {
 	return ERR_PTR(-ENOTSUPP);
 }
 
-static inline void dev_pm_opp_put_regulator(struct opp_table *opp_table) {}
+static inline void dev_pm_opp_put_regulators(struct opp_table *opp_table) {}
 
 static inline int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 {
-- 
cgit v1.2.3-71-gd317


From 947355850fcb3bb6549294316667d0f53bc03082 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Thu, 1 Dec 2016 16:28:20 +0530
Subject: PM / OPP: Separate out _generic_set_opp()

Later patches would add support for custom set_opp() callbacks. This
patch separates out the code for _generic_set_opp() handler in order to
prepare for that.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Tested-by: Dave Gerlach <d-gerlach@ti.com>
Reviewed-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/opp/core.c | 181 +++++++++++++++++++++++++++++-------------
 drivers/base/power/opp/opp.h  |   3 +
 include/linux/pm_opp.h        |  35 ++++++++
 3 files changed, 166 insertions(+), 53 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c
index b4da31c5a5eb..e33198ce41b4 100644
--- a/drivers/base/power/opp/core.c
+++ b/drivers/base/power/opp/core.c
@@ -610,6 +610,69 @@ static int _set_opp_voltage(struct device *dev, struct regulator *reg,
 	return ret;
 }
 
+static inline int
+_generic_set_opp_clk_only(struct device *dev, struct clk *clk,
+			  unsigned long old_freq, unsigned long freq)
+{
+	int ret;
+
+	ret = clk_set_rate(clk, freq);
+	if (ret) {
+		dev_err(dev, "%s: failed to set clock rate: %d\n", __func__,
+			ret);
+	}
+
+	return ret;
+}
+
+static int _generic_set_opp(struct dev_pm_set_opp_data *data)
+{
+	struct dev_pm_opp_supply *old_supply = data->old_opp.supplies;
+	struct dev_pm_opp_supply *new_supply = data->new_opp.supplies;
+	unsigned long old_freq = data->old_opp.rate, freq = data->new_opp.rate;
+	struct regulator *reg = data->regulators[0];
+	struct device *dev= data->dev;
+	int ret;
+
+	/* This function only supports single regulator per device */
+	if (WARN_ON(data->regulator_count > 1)) {
+		dev_err(dev, "multiple regulators are not supported\n");
+		return -EINVAL;
+	}
+
+	/* Scaling up? Scale voltage before frequency */
+	if (freq > old_freq) {
+		ret = _set_opp_voltage(dev, reg, new_supply);
+		if (ret)
+			goto restore_voltage;
+	}
+
+	/* Change frequency */
+	ret = _generic_set_opp_clk_only(dev, data->clk, old_freq, freq);
+	if (ret)
+		goto restore_voltage;
+
+	/* Scaling down? Scale voltage after frequency */
+	if (freq < old_freq) {
+		ret = _set_opp_voltage(dev, reg, new_supply);
+		if (ret)
+			goto restore_freq;
+	}
+
+	return 0;
+
+restore_freq:
+	if (_generic_set_opp_clk_only(dev, data->clk, freq, old_freq))
+		dev_err(dev, "%s: failed to restore old-freq (%lu Hz)\n",
+			__func__, old_freq);
+restore_voltage:
+	/* This shouldn't harm even if the voltages weren't updated earlier */
+	if (old_supply->u_volt)
+		_set_opp_voltage(dev, reg, old_supply);
+
+	return ret;
+}
+
 /**
  * dev_pm_opp_set_rate() - Configure new OPP based on frequency
  * @dev:	 device for which we do this operation
@@ -623,12 +686,12 @@ static int _set_opp_voltage(struct device *dev, struct regulator *reg,
 int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 {
 	struct opp_table *opp_table;
+	unsigned long freq, old_freq;
 	struct dev_pm_opp *old_opp, *opp;
-	struct regulator *reg = ERR_PTR(-ENXIO);
+	struct regulator **regulators;
+	struct dev_pm_set_opp_data *data;
 	struct clk *clk;
-	unsigned long freq, old_freq;
-	struct dev_pm_opp_supply old_supply, new_supply;
-	int ret;
+	int ret, size;
 
 	if (unlikely(!target_freq)) {
 		dev_err(dev, "%s: Invalid target frequency %lu\n", __func__,
@@ -677,64 +740,36 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 		return ret;
 	}
 
-	if (opp_table->regulators) {
-		/* This function only supports single regulator per device */
-		if (WARN_ON(opp_table->regulator_count > 1)) {
-			dev_err(dev, "multiple regulators not supported\n");
-			rcu_read_unlock();
-			return -EINVAL;
-		}
+	dev_dbg(dev, "%s: switching OPP: %lu Hz --> %lu Hz\n", __func__,
+		old_freq, freq);
 
-		reg = opp_table->regulators[0];
+	regulators = opp_table->regulators;
+
+	/* Only frequency scaling */
+	if (!regulators) {
+		rcu_read_unlock();
+		return _generic_set_opp_clk_only(dev, clk, old_freq, freq);
 	}
 
+	data = opp_table->set_opp_data;
+	data->regulators = regulators;
+	data->regulator_count = opp_table->regulator_count;
+	data->clk = clk;
+	data->dev = dev;
+
+	data->old_opp.rate = old_freq;
+	size = sizeof(*opp->supplies) * opp_table->regulator_count;
 	if (IS_ERR(old_opp))
-		old_supply.u_volt = 0;
+		memset(data->old_opp.supplies, 0, size);
 	else
-		memcpy(&old_supply, old_opp->supplies, sizeof(old_supply));
+		memcpy(data->old_opp.supplies, old_opp->supplies, size);
 
-	memcpy(&new_supply, opp->supplies, sizeof(new_supply));
+	data->new_opp.rate = freq;
+	memcpy(data->new_opp.supplies, opp->supplies, size);
 
 	rcu_read_unlock();
 
-	/* Scaling up? Scale voltage before frequency */
-	if (freq > old_freq) {
-		ret = _set_opp_voltage(dev, reg, &new_supply);
-		if (ret)
-			goto restore_voltage;
-	}
-
-	/* Change frequency */
-
-	dev_dbg(dev, "%s: switching OPP: %lu Hz --> %lu Hz\n",
-		__func__, old_freq, freq);
-
-	ret = clk_set_rate(clk, freq);
-	if (ret) {
-		dev_err(dev, "%s: failed to set clock rate: %d\n", __func__,
-			ret);
-		goto restore_voltage;
-	}
-
-	/* Scaling down? Scale voltage after frequency */
-	if (freq < old_freq) {
-		ret = _set_opp_voltage(dev, reg, &new_supply);
-		if (ret)
-			goto restore_freq;
-	}
-
-	return 0;
-
-restore_freq:
-	if (clk_set_rate(clk, old_freq))
-		dev_err(dev, "%s: failed to restore old-freq (%lu Hz)\n",
-			__func__, old_freq);
-restore_voltage:
-	/* This shouldn't harm even if the voltages weren't updated earlier */
-	if (old_supply.u_volt)
-		_set_opp_voltage(dev, reg, &old_supply);
-
-	return ret;
+	return _generic_set_opp(data);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_set_rate);
 
@@ -1368,6 +1403,38 @@ unlock:
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_put_prop_name);
 
+static int _allocate_set_opp_data(struct opp_table *opp_table)
+{
+	struct dev_pm_set_opp_data *data;
+	int len, count = opp_table->regulator_count;
+
+	if (WARN_ON(!count))
+		return -EINVAL;
+
+	/* space for set_opp_data */
+	len = sizeof(*data);
+
+	/* space for old_opp.supplies and new_opp.supplies */
+	len += 2 * sizeof(struct dev_pm_opp_supply) * count;
+
+	data = kzalloc(len, GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->old_opp.supplies = (void *)(data + 1);
+	data->new_opp.supplies = data->old_opp.supplies + count;
+
+	opp_table->set_opp_data = data;
+
+	return 0;
+}
+
+static void _free_set_opp_data(struct opp_table *opp_table)
+{
+	kfree(opp_table->set_opp_data);
+	opp_table->set_opp_data = NULL;
+}
+
 /**
  * dev_pm_opp_set_regulators() - Set regulator names for the device
  * @dev: Device for which regulator name is being set.
@@ -1437,6 +1504,11 @@ struct opp_table *dev_pm_opp_set_regulators(struct device *dev,
 
 	opp_table->regulator_count = count;
 
+	/* Allocate block only once to pass to set_opp() routines */
+	ret = _allocate_set_opp_data(opp_table);
+	if (ret)
+		goto free_regulators;
+
 	mutex_unlock(&opp_table_lock);
 	return opp_table;
 
@@ -1446,6 +1518,7 @@ free_regulators:
 
 	kfree(opp_table->regulators);
 	opp_table->regulators = NULL;
+	opp_table->regulator_count = 0;
 err:
 	_remove_opp_table(opp_table);
 unlock:
@@ -1482,6 +1555,8 @@ void dev_pm_opp_put_regulators(struct opp_table *opp_table)
 	for (i = opp_table->regulator_count - 1; i >= 0; i--)
 		regulator_put(opp_table->regulators[i]);
 
+	_free_set_opp_data(opp_table);
+
 	kfree(opp_table->regulators);
 	opp_table->regulators = NULL;
 	opp_table->regulator_count = 0;
diff --git a/drivers/base/power/opp/opp.h b/drivers/base/power/opp/opp.h
index 5b0f7e53bede..a05e43912c6b 100644
--- a/drivers/base/power/opp/opp.h
+++ b/drivers/base/power/opp/opp.h
@@ -141,6 +141,7 @@ enum opp_table_access {
  * @clk: Device's clock handle
  * @regulators: Supply regulators
  * @regulator_count: Number of power supply regulators
+ * @set_opp_data: Data to be passed to set_opp callback
  * @dentry:	debugfs dentry pointer of the real device directory (not links).
  * @dentry_name: Name of the real dentry.
  *
@@ -178,6 +179,8 @@ struct opp_table {
 	struct regulator **regulators;
 	unsigned int regulator_count;
 
+	struct dev_pm_set_opp_data *set_opp_data;
+
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *dentry;
 	char dentry_name[NAME_MAX];
diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h
index 9a825ae78653..779b40a9287d 100644
--- a/include/linux/pm_opp.h
+++ b/include/linux/pm_opp.h
@@ -17,6 +17,8 @@
 #include <linux/err.h>
 #include <linux/notifier.h>
 
+struct clk;
+struct regulator;
 struct dev_pm_opp;
 struct device;
 struct opp_table;
@@ -41,6 +43,39 @@ struct dev_pm_opp_supply {
 	unsigned long u_amp;
 };
 
+/**
+ * struct dev_pm_opp_info - OPP freq/voltage/current values
+ * @rate:	Target clk rate in hz
+ * @supplies:	Array of voltage/current values for all power supplies
+ *
+ * This structure stores the freq/voltage/current values for a single OPP.
+ */
+struct dev_pm_opp_info {
+	unsigned long rate;
+	struct dev_pm_opp_supply *supplies;
+};
+
+/**
+ * struct dev_pm_set_opp_data - Set OPP data
+ * @old_opp:	Old OPP info
+ * @new_opp:	New OPP info
+ * @regulators:	Array of regulator pointers
+ * @regulator_count: Number of regulators
+ * @clk:	Pointer to clk
+ * @dev:	Pointer to the struct device
+ *
+ * This structure contains all information required for setting an OPP.
+ */
+struct dev_pm_set_opp_data {
+	struct dev_pm_opp_info old_opp;
+	struct dev_pm_opp_info new_opp;
+
+	struct regulator **regulators;
+	unsigned int regulator_count;
+	struct clk *clk;
+	struct device *dev;
+};
+
 #if defined(CONFIG_PM_OPP)
 
 unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp);
-- 
cgit v1.2.3-71-gd317


From 4dab160eb1586f67e8ba7c55ffdd2373f7a5553e Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Thu, 1 Dec 2016 16:28:21 +0530
Subject: PM / OPP: Allow platform specific custom set_opp() callbacks

The generic set_opp() handler isn't sufficient for platforms with
complex DVFS.  For example, some TI platforms have multiple regulators
for a CPU device. The order in which various supplies need to be
programmed is only known to the platform code and its best to leave it
to it.

This patch implements APIs to register platform specific set_opp()
callback.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Tested-by: Dave Gerlach <d-gerlach@ti.com>
Reviewed-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/opp/core.c | 114 +++++++++++++++++++++++++++++++++++++++++-
 drivers/base/power/opp/opp.h  |   2 +
 include/linux/pm_opp.h        |  10 ++++
 3 files changed, 125 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c
index e33198ce41b4..eceebef36f21 100644
--- a/drivers/base/power/opp/core.c
+++ b/drivers/base/power/opp/core.c
@@ -687,6 +687,7 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 {
 	struct opp_table *opp_table;
 	unsigned long freq, old_freq;
+	int (*set_opp)(struct dev_pm_set_opp_data *data);
 	struct dev_pm_opp *old_opp, *opp;
 	struct regulator **regulators;
 	struct dev_pm_set_opp_data *data;
@@ -751,6 +752,11 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 		return _generic_set_opp_clk_only(dev, clk, old_freq, freq);
 	}
 
+	if (opp_table->set_opp)
+		set_opp = opp_table->set_opp;
+	else
+		set_opp = _generic_set_opp;
+
 	data = opp_table->set_opp_data;
 	data->regulators = regulators;
 	data->regulator_count = opp_table->regulator_count;
@@ -769,7 +775,7 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 
 	rcu_read_unlock();
 
-	return _generic_set_opp(data);
+	return set_opp(data);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_set_rate);
 
@@ -903,6 +909,9 @@ static void _remove_opp_table(struct opp_table *opp_table)
 	if (opp_table->regulators)
 		return;
 
+	if (opp_table->set_opp)
+		return;
+
 	/* Release clk */
 	if (!IS_ERR(opp_table->clk))
 		clk_put(opp_table->clk);
@@ -1569,6 +1578,109 @@ unlock:
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_put_regulators);
 
+/**
+ * dev_pm_opp_register_set_opp_helper() - Register custom set OPP helper
+ * @dev: Device for which the helper is getting registered.
+ * @set_opp: Custom set OPP helper.
+ *
+ * This is useful to support complex platforms (like platforms with multiple
+ * regulators per device), instead of the generic OPP set rate helper.
+ *
+ * This must be called before any OPPs are initialized for the device.
+ *
+ * Locking: The internal opp_table and opp structures are RCU protected.
+ * Hence this function internally uses RCU updater strategy with mutex locks
+ * to keep the integrity of the internal data structures. Callers should ensure
+ * that this function is *NOT* called under RCU protection or in contexts where
+ * mutex cannot be locked.
+ */
+int dev_pm_opp_register_set_opp_helper(struct device *dev,
+			int (*set_opp)(struct dev_pm_set_opp_data *data))
+{
+	struct opp_table *opp_table;
+	int ret;
+
+	if (!set_opp)
+		return -EINVAL;
+
+	mutex_lock(&opp_table_lock);
+
+	opp_table = _add_opp_table(dev);
+	if (!opp_table) {
+		ret = -ENOMEM;
+		goto unlock;
+	}
+
+	/* This should be called before OPPs are initialized */
+	if (WARN_ON(!list_empty(&opp_table->opp_list))) {
+		ret = -EBUSY;
+		goto err;
+	}
+
+	/* Already have custom set_opp helper */
+	if (WARN_ON(opp_table->set_opp)) {
+		ret = -EBUSY;
+		goto err;
+	}
+
+	opp_table->set_opp = set_opp;
+
+	mutex_unlock(&opp_table_lock);
+	return 0;
+
+err:
+	_remove_opp_table(opp_table);
+unlock:
+	mutex_unlock(&opp_table_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_register_set_opp_helper);
+
+/**
+ * dev_pm_opp_register_put_opp_helper() - Releases resources blocked for
+ *					   set_opp helper
+ * @dev: Device for which custom set_opp helper has to be cleared.
+ *
+ * Locking: The internal opp_table and opp structures are RCU protected.
+ * Hence this function internally uses RCU updater strategy with mutex locks
+ * to keep the integrity of the internal data structures. Callers should ensure
+ * that this function is *NOT* called under RCU protection or in contexts where
+ * mutex cannot be locked.
+ */
+void dev_pm_opp_register_put_opp_helper(struct device *dev)
+{
+	struct opp_table *opp_table;
+
+	mutex_lock(&opp_table_lock);
+
+	/* Check for existing table for 'dev' first */
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table)) {
+		dev_err(dev, "Failed to find opp_table: %ld\n",
+			PTR_ERR(opp_table));
+		goto unlock;
+	}
+
+	if (!opp_table->set_opp) {
+		dev_err(dev, "%s: Doesn't have custom set_opp helper set\n",
+			__func__);
+		goto unlock;
+	}
+
+	/* Make sure there are no concurrent readers while updating opp_table */
+	WARN_ON(!list_empty(&opp_table->opp_list));
+
+	opp_table->set_opp = NULL;
+
+	/* Try freeing opp_table if this was the last blocking resource */
+	_remove_opp_table(opp_table);
+
+unlock:
+	mutex_unlock(&opp_table_lock);
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_register_put_opp_helper);
+
 /**
  * dev_pm_opp_add()  - Add an OPP table from a table definitions
  * @dev:	device for which we do this operation
diff --git a/drivers/base/power/opp/opp.h b/drivers/base/power/opp/opp.h
index a05e43912c6b..af9f2b849a66 100644
--- a/drivers/base/power/opp/opp.h
+++ b/drivers/base/power/opp/opp.h
@@ -141,6 +141,7 @@ enum opp_table_access {
  * @clk: Device's clock handle
  * @regulators: Supply regulators
  * @regulator_count: Number of power supply regulators
+ * @set_opp: Platform specific set_opp callback
  * @set_opp_data: Data to be passed to set_opp callback
  * @dentry:	debugfs dentry pointer of the real device directory (not links).
  * @dentry_name: Name of the real dentry.
@@ -179,6 +180,7 @@ struct opp_table {
 	struct regulator **regulators;
 	unsigned int regulator_count;
 
+	int (*set_opp)(struct dev_pm_set_opp_data *data);
 	struct dev_pm_set_opp_data *set_opp_data;
 
 #ifdef CONFIG_DEBUG_FS
diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h
index 779b40a9287d..0edd88f93904 100644
--- a/include/linux/pm_opp.h
+++ b/include/linux/pm_opp.h
@@ -116,6 +116,8 @@ int dev_pm_opp_set_prop_name(struct device *dev, const char *name);
 void dev_pm_opp_put_prop_name(struct device *dev);
 struct opp_table *dev_pm_opp_set_regulators(struct device *dev, const char * const names[], unsigned int count);
 void dev_pm_opp_put_regulators(struct opp_table *opp_table);
+int dev_pm_opp_register_set_opp_helper(struct device *dev, int (*set_opp)(struct dev_pm_set_opp_data *data));
+void dev_pm_opp_register_put_opp_helper(struct device *dev);
 int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq);
 int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, const struct cpumask *cpumask);
 int dev_pm_opp_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask);
@@ -215,6 +217,14 @@ static inline int dev_pm_opp_set_supported_hw(struct device *dev,
 
 static inline void dev_pm_opp_put_supported_hw(struct device *dev) {}
 
+static inline int dev_pm_opp_register_set_opp_helper(struct device *dev,
+			int (*set_opp)(struct dev_pm_set_opp_data *data))
+{
+	return -ENOTSUPP;
+}
+
+static inline void dev_pm_opp_register_put_opp_helper(struct device *dev) {}
+
 static inline int dev_pm_opp_set_prop_name(struct device *dev, const char *name)
 {
 	return -ENOTSUPP;
-- 
cgit v1.2.3-71-gd317