From 7f8538ebaefc075f364f14a4f4852b1885ed897c Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Mon, 2 Jan 2017 14:40:55 +0530
Subject: PM / OPP: Fix memory leak while adding duplicate OPPs

There are two types of duplicate OPPs that get different behavior from
the core:
A) An earlier OPP is marked 'available' and has same freq/voltages as
   the new one.
B) An earlier OPP with same frequency, but is marked 'unavailable' OR
   doesn't have same voltages as the new one.

The OPP core returns 0 for the first one, but -EEXIST for the second.

While the OPP core returns 0 for the first case, its callers don't free
the newly allocated OPP structure which isn't used anymore. Fix that by
returning -EBUSY instead of 0, but make the callers return 0 eventually.

As this isn't a critical fix, its not getting marked for stable kernel.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/opp/core.c | 18 ++++++++++++++++--
 drivers/base/power/opp/of.c   |  6 +++++-
 2 files changed, 21 insertions(+), 3 deletions(-)

diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c
index 35ff06283738..a8a5e01b7756 100644
--- a/drivers/base/power/opp/core.c
+++ b/drivers/base/power/opp/core.c
@@ -1067,6 +1067,16 @@ static bool _opp_supported_by_regulators(struct dev_pm_opp *opp,
 	return true;
 }
 
+/*
+ * Returns:
+ * 0: On success. And appropriate error message for duplicate OPPs.
+ * -EBUSY: For OPP with same freq/volt and is available. The callers of
+ *  _opp_add() must return 0 if they receive -EBUSY from it. This is to make
+ *  sure we don't print error messages unnecessarily if different parts of
+ *  kernel try to initialize the OPP table.
+ * -EEXIST: For OPP with same freq but different volt or is unavailable. This
+ *  should be considered an error by the callers of _opp_add().
+ */
 int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
 	     struct opp_table *opp_table)
 {
@@ -1099,7 +1109,7 @@ int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
 
 		/* Should we compare voltages for all regulators here ? */
 		return opp->available &&
-		       new_opp->supplies[0].u_volt == opp->supplies[0].u_volt ? 0 : -EEXIST;
+		       new_opp->supplies[0].u_volt == opp->supplies[0].u_volt ? -EBUSY : -EEXIST;
 	}
 
 	new_opp->opp_table = opp_table;
@@ -1173,8 +1183,12 @@ int _opp_add_v1(struct device *dev, unsigned long freq, long u_volt,
 	new_opp->dynamic = dynamic;
 
 	ret = _opp_add(dev, new_opp, opp_table);
-	if (ret)
+	if (ret) {
+		/* Don't return error for duplicate OPPs */
+		if (ret == -EBUSY)
+			ret = 0;
 		goto free_opp;
+	}
 
 	mutex_unlock(&opp_table_lock);
 
diff --git a/drivers/base/power/opp/of.c b/drivers/base/power/opp/of.c
index 3f7d2591b173..356c75edd656 100644
--- a/drivers/base/power/opp/of.c
+++ b/drivers/base/power/opp/of.c
@@ -327,8 +327,12 @@ static int _opp_add_static_v2(struct device *dev, struct device_node *np)
 		goto free_opp;
 
 	ret = _opp_add(dev, new_opp, opp_table);
-	if (ret)
+	if (ret) {
+		/* Don't return error for duplicate OPPs */
+		if (ret == -EBUSY)
+			ret = 0;
 		goto free_opp;
+	}
 
 	/* OPP to select on device suspend */
 	if (of_property_read_bool(np, "opp-suspend")) {
-- 
cgit v1.2.3


From 1715371ddd5affdd63c7cb5220d104062c74ad66 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Mon, 2 Jan 2017 14:40:56 +0530
Subject: PM / OPP: Remove useless TODO

This TODO doesn't make sense anymore as we have all the information in a
single OPP table. Remove it.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/opp/of.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/base/power/opp/of.c b/drivers/base/power/opp/of.c
index 356c75edd656..996ca3b42f47 100644
--- a/drivers/base/power/opp/of.c
+++ b/drivers/base/power/opp/of.c
@@ -246,8 +246,6 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_of_remove_table);
 static struct device_node *_of_get_opp_desc_node(struct device *dev)
 {
 	/*
-	 * TODO: Support for multiple OPP tables.
-	 *
 	 * There should be only ONE phandle present in "operating-points-v2"
 	 * property.
 	 */
-- 
cgit v1.2.3


From 63a69ea4b88f37bda3bb13c4fb417a3218902022 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Mon, 2 Jan 2017 14:40:57 +0530
Subject: PM / OPP: Rename _allocate_opp() to _opp_allocate()

Make the naming consistent with how other routines are named.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/opp/core.c | 4 ++--
 drivers/base/power/opp/of.c   | 2 +-
 drivers/base/power/opp/opp.h  | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c
index a8a5e01b7756..422482575954 100644
--- a/drivers/base/power/opp/core.c
+++ b/drivers/base/power/opp/core.c
@@ -1014,7 +1014,7 @@ unlock:
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_remove);
 
-struct dev_pm_opp *_allocate_opp(struct device *dev,
+struct dev_pm_opp *_opp_allocate(struct device *dev,
 				 struct opp_table **opp_table)
 {
 	struct dev_pm_opp *opp;
@@ -1167,7 +1167,7 @@ int _opp_add_v1(struct device *dev, unsigned long freq, long u_volt,
 	/* Hold our table modification lock here */
 	mutex_lock(&opp_table_lock);
 
-	new_opp = _allocate_opp(dev, &opp_table);
+	new_opp = _opp_allocate(dev, &opp_table);
 	if (!new_opp) {
 		ret = -ENOMEM;
 		goto unlock;
diff --git a/drivers/base/power/opp/of.c b/drivers/base/power/opp/of.c
index 996ca3b42f47..f8512ca2bf41 100644
--- a/drivers/base/power/opp/of.c
+++ b/drivers/base/power/opp/of.c
@@ -287,7 +287,7 @@ static int _opp_add_static_v2(struct device *dev, struct device_node *np)
 	/* Hold our table modification lock here */
 	mutex_lock(&opp_table_lock);
 
-	new_opp = _allocate_opp(dev, &opp_table);
+	new_opp = _opp_allocate(dev, &opp_table);
 	if (!new_opp) {
 		ret = -ENOMEM;
 		goto unlock;
diff --git a/drivers/base/power/opp/opp.h b/drivers/base/power/opp/opp.h
index af9f2b849a66..0f23a1059605 100644
--- a/drivers/base/power/opp/opp.h
+++ b/drivers/base/power/opp/opp.h
@@ -193,7 +193,7 @@ struct opp_table {
 struct opp_table *_find_opp_table(struct device *dev);
 struct opp_device *_add_opp_dev(const struct device *dev, struct opp_table *opp_table);
 void _dev_pm_opp_remove_table(struct device *dev, bool remove_all);
-struct dev_pm_opp *_allocate_opp(struct device *dev, struct opp_table **opp_table);
+struct dev_pm_opp *_opp_allocate(struct device *dev, struct opp_table **opp_table);
 int _opp_add(struct device *dev, struct dev_pm_opp *new_opp, struct opp_table *opp_table);
 void _opp_remove(struct opp_table *opp_table, struct dev_pm_opp *opp, bool notify);
 int _opp_add_v1(struct device *dev, unsigned long freq, long u_volt, bool dynamic);
-- 
cgit v1.2.3


From 04a86a84c42ca18f37ab446127dc619b41dd3b23 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Mon, 2 Jan 2017 14:40:58 +0530
Subject: PM / OPP: Error out on failing to add static OPPs for v1 bindings

The code adding static OPPs for V2 bindings already does so. Make the V1
bindings specific code behave the same.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/opp/of.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/base/power/opp/of.c b/drivers/base/power/opp/of.c
index f8512ca2bf41..c8fe815774ff 100644
--- a/drivers/base/power/opp/of.c
+++ b/drivers/base/power/opp/of.c
@@ -433,7 +433,7 @@ static int _of_add_opp_table_v1(struct device *dev)
 {
 	const struct property *prop;
 	const __be32 *val;
-	int nr;
+	int nr, ret;
 
 	prop = of_find_property(dev->of_node, "operating-points", NULL);
 	if (!prop)
@@ -456,9 +456,13 @@ static int _of_add_opp_table_v1(struct device *dev)
 		unsigned long freq = be32_to_cpup(val++) * 1000;
 		unsigned long volt = be32_to_cpup(val++);
 
-		if (_opp_add_v1(dev, freq, volt, false))
-			dev_warn(dev, "%s: Failed to add OPP %ld\n",
-				 __func__, freq);
+		ret = _opp_add_v1(dev, freq, volt, false);
+		if (ret) {
+			dev_err(dev, "%s: Failed to add OPP %ld (%d)\n",
+				__func__, freq, ret);
+			dev_pm_opp_of_remove_table(dev);
+			return ret;
+		}
 		nr -= 2;
 	}
 
-- 
cgit v1.2.3


From 969fceb3c7e6fc7fd0419b0392435717824f7ba5 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Mon, 2 Jan 2017 14:40:59 +0530
Subject: PM / OPP: Add light weight _opp_free() routine

The OPPs which are never successfully added using _opp_add() are not
required to be freed with the _opp_remove() routine, as a simple kfree()
is enough for them.

Introduce a new light weight routine _opp_free(), which will do that.

That also helps us removing the 'notify' parameter to _opp_remove(),
which isn't required anymore.

Note that _opp_free() contains a call to _remove_opp_table() as the OPP
table might have been added for this very OPP only. The
_remove_opp_table() routine returns quickly if there are more OPPs in
the table. This will be simplified in later patches though.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/opp/core.c | 20 +++++++++++---------
 drivers/base/power/opp/of.c   |  2 +-
 drivers/base/power/opp/opp.h  |  2 +-
 3 files changed, 13 insertions(+), 11 deletions(-)

diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c
index 422482575954..ea5b90e0882c 100644
--- a/drivers/base/power/opp/core.c
+++ b/drivers/base/power/opp/core.c
@@ -929,6 +929,12 @@ static void _remove_opp_table(struct opp_table *opp_table)
 		  _kfree_device_rcu);
 }
 
+void _opp_free(struct dev_pm_opp *opp, struct opp_table *opp_table)
+{
+	kfree(opp);
+	_remove_opp_table(opp_table);
+}
+
 /**
  * _kfree_opp_rcu() - Free OPP RCU handler
  * @head:	RCU head
@@ -944,7 +950,6 @@ static void _kfree_opp_rcu(struct rcu_head *head)
  * _opp_remove()  - Remove an OPP from a table definition
  * @opp_table:	points back to the opp_table struct this opp belongs to
  * @opp:	pointer to the OPP to remove
- * @notify:	OPP_EVENT_REMOVE notification should be sent or not
  *
  * This function removes an opp definition from the opp table.
  *
@@ -952,16 +957,13 @@ static void _kfree_opp_rcu(struct rcu_head *head)
  * It is assumed that the caller holds required mutex for an RCU updater
  * strategy.
  */
-void _opp_remove(struct opp_table *opp_table, struct dev_pm_opp *opp,
-		 bool notify)
+static void _opp_remove(struct opp_table *opp_table, struct dev_pm_opp *opp)
 {
 	/*
 	 * Notify the changes in the availability of the operable
 	 * frequency/voltage list.
 	 */
-	if (notify)
-		srcu_notifier_call_chain(&opp_table->srcu_head,
-					 OPP_EVENT_REMOVE, opp);
+	srcu_notifier_call_chain(&opp_table->srcu_head, OPP_EVENT_REMOVE, opp);
 	opp_debug_remove_one(opp);
 	list_del_rcu(&opp->node);
 	call_srcu(&opp_table->srcu_head.srcu, &opp->rcu_head, _kfree_opp_rcu);
@@ -1008,7 +1010,7 @@ void dev_pm_opp_remove(struct device *dev, unsigned long freq)
 		goto unlock;
 	}
 
-	_opp_remove(opp_table, opp, true);
+	_opp_remove(opp_table, opp);
 unlock:
 	mutex_unlock(&opp_table_lock);
 }
@@ -1200,7 +1202,7 @@ int _opp_add_v1(struct device *dev, unsigned long freq, long u_volt,
 	return 0;
 
 free_opp:
-	_opp_remove(opp_table, new_opp, false);
+	_opp_free(new_opp, opp_table);
 unlock:
 	mutex_unlock(&opp_table_lock);
 	return ret;
@@ -1912,7 +1914,7 @@ void _dev_pm_opp_remove_table(struct device *dev, bool remove_all)
 		/* Free static OPPs */
 		list_for_each_entry_safe(opp, tmp, &opp_table->opp_list, node) {
 			if (remove_all || !opp->dynamic)
-				_opp_remove(opp_table, opp, true);
+				_opp_remove(opp_table, opp);
 		}
 	} else {
 		_remove_opp_dev(_find_opp_dev(dev, opp_table), opp_table);
diff --git a/drivers/base/power/opp/of.c b/drivers/base/power/opp/of.c
index c8fe815774ff..67c9eeded4e1 100644
--- a/drivers/base/power/opp/of.c
+++ b/drivers/base/power/opp/of.c
@@ -362,7 +362,7 @@ static int _opp_add_static_v2(struct device *dev, struct device_node *np)
 	return 0;
 
 free_opp:
-	_opp_remove(opp_table, new_opp, false);
+	_opp_free(new_opp, opp_table);
 unlock:
 	mutex_unlock(&opp_table_lock);
 	return ret;
diff --git a/drivers/base/power/opp/opp.h b/drivers/base/power/opp/opp.h
index 0f23a1059605..334f7570df32 100644
--- a/drivers/base/power/opp/opp.h
+++ b/drivers/base/power/opp/opp.h
@@ -194,8 +194,8 @@ struct opp_table *_find_opp_table(struct device *dev);
 struct opp_device *_add_opp_dev(const struct device *dev, struct opp_table *opp_table);
 void _dev_pm_opp_remove_table(struct device *dev, bool remove_all);
 struct dev_pm_opp *_opp_allocate(struct device *dev, struct opp_table **opp_table);
+void _opp_free(struct dev_pm_opp *opp, struct opp_table *opp_table);
 int _opp_add(struct device *dev, struct dev_pm_opp *new_opp, struct opp_table *opp_table);
-void _opp_remove(struct opp_table *opp_table, struct dev_pm_opp *opp, bool notify);
 int _opp_add_v1(struct device *dev, unsigned long freq, long u_volt, bool dynamic);
 void _dev_pm_opp_cpumask_remove_table(const struct cpumask *cpumask, bool of);
 
-- 
cgit v1.2.3


From 9274c892430ef3240acf3f336916f64fe2b67b02 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Mon, 2 Jan 2017 14:41:00 +0530
Subject: PM / OPP: Rename and split _dev_pm_opp_remove_table()

Later patches would want to remove OPP table (and its OPPs) using the
opp_table pointer instead of 'dev'.

In order to prepare for that, rename _dev_pm_opp_remove_table() as
_dev_pm_opp_find_and_remove_table() split out part of it.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/opp/core.c | 35 ++++++++++++++++++++++-------------
 drivers/base/power/opp/of.c   |  2 +-
 drivers/base/power/opp/opp.h  |  2 +-
 3 files changed, 24 insertions(+), 15 deletions(-)

diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c
index ea5b90e0882c..b3a624a4af81 100644
--- a/drivers/base/power/opp/core.c
+++ b/drivers/base/power/opp/core.c
@@ -1888,11 +1888,29 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_notifier);
  * Free OPPs either created using static entries present in DT or even the
  * dynamically added entries based on remove_all param.
  */
-void _dev_pm_opp_remove_table(struct device *dev, bool remove_all)
+static void _dev_pm_opp_remove_table(struct opp_table *opp_table,
+				     struct device *dev, bool remove_all)
 {
-	struct opp_table *opp_table;
 	struct dev_pm_opp *opp, *tmp;
 
+	opp_rcu_lockdep_assert();
+
+	/* Find if opp_table manages a single device */
+	if (list_is_singular(&opp_table->dev_list)) {
+		/* Free static OPPs */
+		list_for_each_entry_safe(opp, tmp, &opp_table->opp_list, node) {
+			if (remove_all || !opp->dynamic)
+				_opp_remove(opp_table, opp);
+		}
+	} else {
+		_remove_opp_dev(_find_opp_dev(dev, opp_table), opp_table);
+	}
+}
+
+void _dev_pm_opp_find_and_remove_table(struct device *dev, bool remove_all)
+{
+	struct opp_table *opp_table;
+
 	/* Hold our table modification lock here */
 	mutex_lock(&opp_table_lock);
 
@@ -1909,16 +1927,7 @@ void _dev_pm_opp_remove_table(struct device *dev, bool remove_all)
 		goto unlock;
 	}
 
-	/* Find if opp_table manages a single device */
-	if (list_is_singular(&opp_table->dev_list)) {
-		/* Free static OPPs */
-		list_for_each_entry_safe(opp, tmp, &opp_table->opp_list, node) {
-			if (remove_all || !opp->dynamic)
-				_opp_remove(opp_table, opp);
-		}
-	} else {
-		_remove_opp_dev(_find_opp_dev(dev, opp_table), opp_table);
-	}
+	_dev_pm_opp_remove_table(opp_table, dev, remove_all);
 
 unlock:
 	mutex_unlock(&opp_table_lock);
@@ -1939,6 +1948,6 @@ unlock:
  */
 void dev_pm_opp_remove_table(struct device *dev)
 {
-	_dev_pm_opp_remove_table(dev, true);
+	_dev_pm_opp_find_and_remove_table(dev, true);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_remove_table);
diff --git a/drivers/base/power/opp/of.c b/drivers/base/power/opp/of.c
index 67c9eeded4e1..442fa46c4f5c 100644
--- a/drivers/base/power/opp/of.c
+++ b/drivers/base/power/opp/of.c
@@ -238,7 +238,7 @@ free_microvolt:
  */
 void dev_pm_opp_of_remove_table(struct device *dev)
 {
-	_dev_pm_opp_remove_table(dev, false);
+	_dev_pm_opp_find_and_remove_table(dev, false);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_of_remove_table);
 
diff --git a/drivers/base/power/opp/opp.h b/drivers/base/power/opp/opp.h
index 334f7570df32..c4b539a8533a 100644
--- a/drivers/base/power/opp/opp.h
+++ b/drivers/base/power/opp/opp.h
@@ -192,7 +192,7 @@ struct opp_table {
 /* Routines internal to opp core */
 struct opp_table *_find_opp_table(struct device *dev);
 struct opp_device *_add_opp_dev(const struct device *dev, struct opp_table *opp_table);
-void _dev_pm_opp_remove_table(struct device *dev, bool remove_all);
+void _dev_pm_opp_find_and_remove_table(struct device *dev, bool remove_all);
 struct dev_pm_opp *_opp_allocate(struct device *dev, struct opp_table **opp_table);
 void _opp_free(struct dev_pm_opp *opp, struct opp_table *opp_table);
 int _opp_add(struct device *dev, struct dev_pm_opp *new_opp, struct opp_table *opp_table);
-- 
cgit v1.2.3


From 8cd2f6e8f34e75198063a6d84675b18bdb106824 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Mon, 2 Jan 2017 14:41:01 +0530
Subject: PM / OPP: Don't allocate OPP table from _opp_allocate()

There is no point in trying to find/allocate the table for every OPP
that is added for a device. It would be far more efficient to allocate
the table only once and pass its pointer to the routines that add the
OPP entry.

Locking is removed from _opp_add_static_v2() and _opp_add_v1() now as
the callers call them with that lock already held.

Call to _remove_opp_table() routine is also removed from _opp_free()
now, as opp_table isn't allocated from within _opp_allocate(). This is
handled by the routines which created the OPP table in the first place.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/opp/core.c | 67 +++++++++++++++++++-------------------
 drivers/base/power/opp/of.c   | 75 ++++++++++++++++++++++---------------------
 drivers/base/power/opp/opp.h  |  9 ++++--
 3 files changed, 78 insertions(+), 73 deletions(-)

diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c
index b3a624a4af81..dde7dd099aa0 100644
--- a/drivers/base/power/opp/core.c
+++ b/drivers/base/power/opp/core.c
@@ -829,7 +829,7 @@ struct opp_device *_add_opp_dev(const struct device *dev,
  *
  * Return: valid opp_table pointer if success, else NULL.
  */
-static struct opp_table *_add_opp_table(struct device *dev)
+struct opp_table *_add_opp_table(struct device *dev)
 {
 	struct opp_table *opp_table;
 	struct opp_device *opp_dev;
@@ -929,10 +929,9 @@ static void _remove_opp_table(struct opp_table *opp_table)
 		  _kfree_device_rcu);
 }
 
-void _opp_free(struct dev_pm_opp *opp, struct opp_table *opp_table)
+void _opp_free(struct dev_pm_opp *opp)
 {
 	kfree(opp);
-	_remove_opp_table(opp_table);
 }
 
 /**
@@ -1016,16 +1015,10 @@ unlock:
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_remove);
 
-struct dev_pm_opp *_opp_allocate(struct device *dev,
-				 struct opp_table **opp_table)
+struct dev_pm_opp *_opp_allocate(struct opp_table *table)
 {
 	struct dev_pm_opp *opp;
 	int count, supply_size;
-	struct opp_table *table;
-
-	table = _add_opp_table(dev);
-	if (!table)
-		return NULL;
 
 	/* Allocate space for at least one supply */
 	count = table->regulator_count ? table->regulator_count : 1;
@@ -1033,17 +1026,13 @@ struct dev_pm_opp *_opp_allocate(struct device *dev,
 
 	/* allocate new OPP node and supplies structures */
 	opp = kzalloc(sizeof(*opp) + supply_size, GFP_KERNEL);
-	if (!opp) {
-		kfree(table);
+	if (!opp)
 		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;
 }
 
@@ -1133,6 +1122,7 @@ int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
 
 /**
  * _opp_add_v1() - Allocate a OPP based on v1 bindings.
+ * @opp_table:	OPP table
  * @dev:	device for which we do this operation
  * @freq:	Frequency in Hz for this OPP
  * @u_volt:	Voltage in uVolts for this OPP
@@ -1158,22 +1148,18 @@ int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
  *		Duplicate OPPs (both freq and volt are same) and !opp->available
  * -ENOMEM	Memory allocation failure
  */
-int _opp_add_v1(struct device *dev, unsigned long freq, long u_volt,
-		bool dynamic)
+int _opp_add_v1(struct opp_table *opp_table, struct device *dev,
+		unsigned long freq, long u_volt, bool dynamic)
 {
-	struct opp_table *opp_table;
 	struct dev_pm_opp *new_opp;
 	unsigned long tol;
 	int ret;
 
-	/* Hold our table modification lock here */
-	mutex_lock(&opp_table_lock);
+	opp_rcu_lockdep_assert();
 
-	new_opp = _opp_allocate(dev, &opp_table);
-	if (!new_opp) {
-		ret = -ENOMEM;
-		goto unlock;
-	}
+	new_opp = _opp_allocate(opp_table);
+	if (!new_opp)
+		return -ENOMEM;
 
 	/* populate the opp table */
 	new_opp->rate = freq;
@@ -1192,8 +1178,6 @@ int _opp_add_v1(struct device *dev, unsigned long freq, long u_volt,
 		goto free_opp;
 	}
 
-	mutex_unlock(&opp_table_lock);
-
 	/*
 	 * Notify the changes in the availability of the operable
 	 * frequency/voltage list.
@@ -1202,9 +1186,8 @@ int _opp_add_v1(struct device *dev, unsigned long freq, long u_volt,
 	return 0;
 
 free_opp:
-	_opp_free(new_opp, opp_table);
-unlock:
-	mutex_unlock(&opp_table_lock);
+	_opp_free(new_opp);
+
 	return ret;
 }
 
@@ -1722,7 +1705,25 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_register_put_opp_helper);
  */
 int dev_pm_opp_add(struct device *dev, unsigned long freq, unsigned long u_volt)
 {
-	return _opp_add_v1(dev, freq, u_volt, true);
+	struct opp_table *opp_table;
+	int ret;
+
+	/* Hold our table modification lock here */
+	mutex_lock(&opp_table_lock);
+
+	opp_table = _add_opp_table(dev);
+	if (!opp_table) {
+		ret = -ENOMEM;
+		goto unlock;
+	}
+
+	ret = _opp_add_v1(opp_table, dev, freq, u_volt, true);
+	if (ret)
+		_remove_opp_table(opp_table);
+
+unlock:
+	mutex_unlock(&opp_table_lock);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_add);
 
@@ -1888,8 +1889,8 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_notifier);
  * Free OPPs either created using static entries present in DT or even the
  * dynamically added entries based on remove_all param.
  */
-static void _dev_pm_opp_remove_table(struct opp_table *opp_table,
-				     struct device *dev, bool remove_all)
+void _dev_pm_opp_remove_table(struct opp_table *opp_table, struct device *dev,
+			      bool remove_all)
 {
 	struct dev_pm_opp *opp, *tmp;
 
diff --git a/drivers/base/power/opp/of.c b/drivers/base/power/opp/of.c
index 442fa46c4f5c..cdbf733ac9b1 100644
--- a/drivers/base/power/opp/of.c
+++ b/drivers/base/power/opp/of.c
@@ -255,6 +255,7 @@ static struct device_node *_of_get_opp_desc_node(struct device *dev)
 
 /**
  * _opp_add_static_v2() - Allocate static OPPs (As per 'v2' DT bindings)
+ * @opp_table:	OPP table
  * @dev:	device for which we do this operation
  * @np:		device node
  *
@@ -276,22 +277,17 @@ static struct device_node *_of_get_opp_desc_node(struct device *dev)
  * -ENOMEM	Memory allocation failure
  * -EINVAL	Failed parsing the OPP node
  */
-static int _opp_add_static_v2(struct device *dev, struct device_node *np)
+static int _opp_add_static_v2(struct opp_table *opp_table, struct device *dev,
+			      struct device_node *np)
 {
-	struct opp_table *opp_table;
 	struct dev_pm_opp *new_opp;
 	u64 rate;
 	u32 val;
 	int ret;
 
-	/* Hold our table modification lock here */
-	mutex_lock(&opp_table_lock);
-
-	new_opp = _opp_allocate(dev, &opp_table);
-	if (!new_opp) {
-		ret = -ENOMEM;
-		goto unlock;
-	}
+	new_opp = _opp_allocate(opp_table);
+	if (!new_opp)
+		return -ENOMEM;
 
 	ret = of_property_read_u64(np, "opp-hz", &rate);
 	if (ret < 0) {
@@ -347,8 +343,6 @@ static int _opp_add_static_v2(struct device *dev, struct device_node *np)
 	if (new_opp->clock_latency_ns > opp_table->clock_latency_ns_max)
 		opp_table->clock_latency_ns_max = new_opp->clock_latency_ns;
 
-	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->supplies[0].u_volt, new_opp->supplies[0].u_volt_min,
@@ -362,9 +356,8 @@ static int _opp_add_static_v2(struct device *dev, struct device_node *np)
 	return 0;
 
 free_opp:
-	_opp_free(new_opp, opp_table);
-unlock:
-	mutex_unlock(&opp_table_lock);
+	_opp_free(new_opp);
+
 	return ret;
 }
 
@@ -382,16 +375,20 @@ static int _of_add_opp_table_v2(struct device *dev, struct device_node *opp_np)
 		/* OPPs are already managed */
 		if (!_add_opp_dev(dev, opp_table))
 			ret = -ENOMEM;
-		mutex_unlock(&opp_table_lock);
-		return ret;
+		goto unlock;
+	}
+
+	opp_table = _add_opp_table(dev);
+	if (!opp_table) {
+		ret = -ENOMEM;
+		goto unlock;
 	}
-	mutex_unlock(&opp_table_lock);
 
 	/* We have opp-table node now, iterate over it and add OPPs */
 	for_each_available_child_of_node(opp_np, np) {
 		count++;
 
-		ret = _opp_add_static_v2(dev, np);
+		ret = _opp_add_static_v2(opp_table, dev, np);
 		if (ret) {
 			dev_err(dev, "%s: Failed to add OPP, %d\n", __func__,
 				ret);
@@ -400,15 +397,8 @@ static int _of_add_opp_table_v2(struct device *dev, struct device_node *opp_np)
 	}
 
 	/* There should be one of more OPP defined */
-	if (WARN_ON(!count))
-		return -ENOENT;
-
-	mutex_lock(&opp_table_lock);
-
-	opp_table = _find_opp_table(dev);
-	if (WARN_ON(IS_ERR(opp_table))) {
-		ret = PTR_ERR(opp_table);
-		mutex_unlock(&opp_table_lock);
+	if (WARN_ON(!count)) {
+		ret = -ENOENT;
 		goto free_table;
 	}
 
@@ -418,12 +408,12 @@ static int _of_add_opp_table_v2(struct device *dev, struct device_node *opp_np)
 	else
 		opp_table->shared_opp = OPP_TABLE_ACCESS_EXCLUSIVE;
 
-	mutex_unlock(&opp_table_lock);
-
-	return 0;
+	goto unlock;
 
 free_table:
-	dev_pm_opp_of_remove_table(dev);
+	_dev_pm_opp_remove_table(opp_table, dev, false);
+unlock:
+	mutex_unlock(&opp_table_lock);
 
 	return ret;
 }
@@ -431,9 +421,10 @@ free_table:
 /* Initializes OPP tables based on old-deprecated bindings */
 static int _of_add_opp_table_v1(struct device *dev)
 {
+	struct opp_table *opp_table;
 	const struct property *prop;
 	const __be32 *val;
-	int nr, ret;
+	int nr, ret = 0;
 
 	prop = of_find_property(dev->of_node, "operating-points", NULL);
 	if (!prop)
@@ -451,22 +442,32 @@ static int _of_add_opp_table_v1(struct device *dev)
 		return -EINVAL;
 	}
 
+	mutex_lock(&opp_table_lock);
+
+	opp_table = _add_opp_table(dev);
+	if (!opp_table) {
+		ret = -ENOMEM;
+		goto unlock;
+	}
+
 	val = prop->value;
 	while (nr) {
 		unsigned long freq = be32_to_cpup(val++) * 1000;
 		unsigned long volt = be32_to_cpup(val++);
 
-		ret = _opp_add_v1(dev, freq, volt, false);
+		ret = _opp_add_v1(opp_table, dev, freq, volt, false);
 		if (ret) {
 			dev_err(dev, "%s: Failed to add OPP %ld (%d)\n",
 				__func__, freq, ret);
-			dev_pm_opp_of_remove_table(dev);
-			return ret;
+			_dev_pm_opp_remove_table(opp_table, dev, false);
+			break;
 		}
 		nr -= 2;
 	}
 
-	return 0;
+unlock:
+	mutex_unlock(&opp_table_lock);
+	return ret;
 }
 
 /**
diff --git a/drivers/base/power/opp/opp.h b/drivers/base/power/opp/opp.h
index c4b539a8533a..0a5eb4d1e8f7 100644
--- a/drivers/base/power/opp/opp.h
+++ b/drivers/base/power/opp/opp.h
@@ -191,13 +191,16 @@ struct opp_table {
 
 /* Routines internal to opp core */
 struct opp_table *_find_opp_table(struct device *dev);
+struct opp_table *_add_opp_table(struct device *dev);
 struct opp_device *_add_opp_dev(const struct device *dev, struct opp_table *opp_table);
+void _dev_pm_opp_remove_table(struct opp_table *opp_table, struct device *dev, bool remove_all);
 void _dev_pm_opp_find_and_remove_table(struct device *dev, bool remove_all);
-struct dev_pm_opp *_opp_allocate(struct device *dev, struct opp_table **opp_table);
-void _opp_free(struct dev_pm_opp *opp, struct opp_table *opp_table);
+struct dev_pm_opp *_opp_allocate(struct opp_table *opp_table);
+void _opp_free(struct dev_pm_opp *opp);
 int _opp_add(struct device *dev, struct dev_pm_opp *new_opp, struct opp_table *opp_table);
-int _opp_add_v1(struct device *dev, unsigned long freq, long u_volt, bool dynamic);
+int _opp_add_v1(struct opp_table *opp_table, struct device *dev, unsigned long freq, long u_volt, bool dynamic);
 void _dev_pm_opp_cpumask_remove_table(const struct cpumask *cpumask, bool of);
+struct opp_table *_add_opp_table(struct device *dev);
 
 #ifdef CONFIG_OF
 void _of_init_opp_table(struct opp_table *opp_table, struct device *dev);
-- 
cgit v1.2.3


From 3aa26a3b2ea63c4d09420e74421370655aa1cf8f Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Mon, 2 Jan 2017 14:41:02 +0530
Subject: PM / OPP: Rename dev_pm_opp_get_suspend_opp() and return OPP rate

There is only one user of dev_pm_opp_get_suspend_opp() and that uses it
to get the OPP rate for the suspend_opp.

Rename dev_pm_opp_get_suspend_opp() as dev_pm_opp_get_suspend_opp_freq()
and return the rate directly from it.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/opp/core.c | 27 +++++++++++++--------------
 drivers/cpufreq/cpufreq-dt.c  |  7 +------
 include/linux/pm_opp.h        |  6 +++---
 3 files changed, 17 insertions(+), 23 deletions(-)

diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c
index dde7dd099aa0..614d779ab6a2 100644
--- a/drivers/base/power/opp/core.c
+++ b/drivers/base/power/opp/core.c
@@ -328,32 +328,31 @@ unsigned long dev_pm_opp_get_max_transition_latency(struct device *dev)
 EXPORT_SYMBOL_GPL(dev_pm_opp_get_max_transition_latency);
 
 /**
- * dev_pm_opp_get_suspend_opp() - Get suspend opp
+ * dev_pm_opp_get_suspend_opp_freq() - Get frequency of suspend opp in Hz
  * @dev:	device for which we do this operation
  *
- * Return: This function returns pointer to the suspend opp if it is
- * defined and available, otherwise it returns NULL.
- *
- * Locking: This function must be called under rcu_read_lock(). opp is a rcu
- * protected pointer. The reason for the same is that the opp pointer which is
- * returned will remain valid for use with opp_get_{voltage, freq} only while
- * under the locked area. The pointer returned must be used prior to unlocking
- * with rcu_read_unlock() to maintain the integrity of the pointer.
+ * Return: This function returns the frequency of the OPP marked as suspend_opp
+ * if one is available, else returns 0;
  */
-struct dev_pm_opp *dev_pm_opp_get_suspend_opp(struct device *dev)
+unsigned long dev_pm_opp_get_suspend_opp_freq(struct device *dev)
 {
 	struct opp_table *opp_table;
+	unsigned long freq = 0;
 
-	opp_rcu_lockdep_assert();
+	rcu_read_lock();
 
 	opp_table = _find_opp_table(dev);
 	if (IS_ERR(opp_table) || !opp_table->suspend_opp ||
 	    !opp_table->suspend_opp->available)
-		return NULL;
+		goto unlock;
 
-	return opp_table->suspend_opp;
+	freq = dev_pm_opp_get_freq(opp_table->suspend_opp);
+
+unlock:
+	rcu_read_unlock();
+	return freq;
 }
-EXPORT_SYMBOL_GPL(dev_pm_opp_get_suspend_opp);
+EXPORT_SYMBOL_GPL(dev_pm_opp_get_suspend_opp_freq);
 
 /**
  * dev_pm_opp_get_opp_count() - Get number of opps available in the opp table
diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c
index 269013311e79..c943787d761e 100644
--- a/drivers/cpufreq/cpufreq-dt.c
+++ b/drivers/cpufreq/cpufreq-dt.c
@@ -148,7 +148,6 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 	struct private_data *priv;
 	struct device *cpu_dev;
 	struct clk *cpu_clk;
-	struct dev_pm_opp *suspend_opp;
 	unsigned int transition_latency;
 	bool fallback = false;
 	const char *name;
@@ -252,11 +251,7 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 	policy->driver_data = priv;
 	policy->clk = cpu_clk;
 
-	rcu_read_lock();
-	suspend_opp = dev_pm_opp_get_suspend_opp(cpu_dev);
-	if (suspend_opp)
-		policy->suspend_freq = dev_pm_opp_get_freq(suspend_opp) / 1000;
-	rcu_read_unlock();
+	policy->suspend_freq = dev_pm_opp_get_suspend_opp_freq(cpu_dev) / 1000;
 
 	ret = cpufreq_table_validate_and_show(policy, freq_table);
 	if (ret) {
diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h
index 0edd88f93904..7483ff291a8e 100644
--- a/include/linux/pm_opp.h
+++ b/include/linux/pm_opp.h
@@ -88,7 +88,7 @@ int dev_pm_opp_get_opp_count(struct device *dev);
 unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev);
 unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev);
 unsigned long dev_pm_opp_get_max_transition_latency(struct device *dev);
-struct dev_pm_opp *dev_pm_opp_get_suspend_opp(struct device *dev);
+unsigned long dev_pm_opp_get_suspend_opp_freq(struct device *dev);
 
 struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev,
 					      unsigned long freq,
@@ -159,9 +159,9 @@ static inline unsigned long dev_pm_opp_get_max_transition_latency(struct device
 	return 0;
 }
 
-static inline struct dev_pm_opp *dev_pm_opp_get_suspend_opp(struct device *dev)
+static inline unsigned long dev_pm_opp_get_suspend_opp_freq(struct device *dev)
 {
-	return NULL;
+	return 0;
 }
 
 static inline struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev,
-- 
cgit v1.2.3


From dc2c9ad52af45ebecf9743aacb1916ebb2f1e848 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Mon, 2 Jan 2017 14:41:03 +0530
Subject: PM / OPP: Don't expose srcu_head to register notifiers

Let the OPP core provide helpers to register notifiers for any device,
instead of exposing srcu_head outside of the core.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Acked-by: MyungJoo Ham <myungjoo.ham@samsung.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 | 66 ++++++++++++++++++++++++++++++++-----------
 drivers/devfreq/devfreq.c     | 26 ++---------------
 include/linux/pm_opp.h        | 14 ++++++---
 3 files changed, 62 insertions(+), 44 deletions(-)

diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c
index 614d779ab6a2..f35effad60d1 100644
--- a/drivers/base/power/opp/core.c
+++ b/drivers/base/power/opp/core.c
@@ -1860,29 +1860,63 @@ int dev_pm_opp_disable(struct device *dev, unsigned long freq)
 EXPORT_SYMBOL_GPL(dev_pm_opp_disable);
 
 /**
- * dev_pm_opp_get_notifier() - find notifier_head of the device with opp
- * @dev:	device pointer used to lookup OPP table.
+ * dev_pm_opp_register_notifier() - Register OPP notifier for the device
+ * @dev:	Device for which notifier needs to be registered
+ * @nb:		Notifier block to be registered
  *
- * Return: pointer to  notifier head if found, otherwise -ENODEV or
- * -EINVAL based on type of error casted as pointer. value must be checked
- *  with IS_ERR to determine valid pointer or error result.
+ * Return: 0 on success or a negative error value.
+ */
+int dev_pm_opp_register_notifier(struct device *dev, struct notifier_block *nb)
+{
+	struct opp_table *opp_table;
+	int ret;
+
+	rcu_read_lock();
+
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table)) {
+		ret = PTR_ERR(opp_table);
+		goto unlock;
+	}
+
+	ret = srcu_notifier_chain_register(&opp_table->srcu_head, nb);
+
+unlock:
+	rcu_read_unlock();
+
+	return ret;
+}
+EXPORT_SYMBOL(dev_pm_opp_register_notifier);
+
+/**
+ * dev_pm_opp_unregister_notifier() - Unregister OPP notifier for the device
+ * @dev:	Device for which notifier needs to be unregistered
+ * @nb:		Notifier block to be unregistered
  *
- * Locking: This function must be called under rcu_read_lock(). opp_table is a
- * RCU protected pointer. The reason for the same is that the opp pointer which
- * is returned will remain valid for use with opp_get_{voltage, freq} only while
- * under the locked area. The pointer returned must be used prior to unlocking
- * with rcu_read_unlock() to maintain the integrity of the pointer.
+ * Return: 0 on success or a negative error value.
  */
-struct srcu_notifier_head *dev_pm_opp_get_notifier(struct device *dev)
+int dev_pm_opp_unregister_notifier(struct device *dev,
+				   struct notifier_block *nb)
 {
-	struct opp_table *opp_table = _find_opp_table(dev);
+	struct opp_table *opp_table;
+	int ret;
 
-	if (IS_ERR(opp_table))
-		return ERR_CAST(opp_table); /* matching type */
+	rcu_read_lock();
+
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table)) {
+		ret = PTR_ERR(opp_table);
+		goto unlock;
+	}
+
+	ret = srcu_notifier_chain_unregister(&opp_table->srcu_head, nb);
 
-	return &opp_table->srcu_head;
+unlock:
+	rcu_read_unlock();
+
+	return ret;
 }
-EXPORT_SYMBOL_GPL(dev_pm_opp_get_notifier);
+EXPORT_SYMBOL(dev_pm_opp_unregister_notifier);
 
 /*
  * Free OPPs either created using static entries present in DT or even the
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index 47206a21bb90..a545c0fee6e1 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -1265,18 +1265,7 @@ EXPORT_SYMBOL(devfreq_recommended_opp);
  */
 int devfreq_register_opp_notifier(struct device *dev, struct devfreq *devfreq)
 {
-	struct srcu_notifier_head *nh;
-	int ret = 0;
-
-	rcu_read_lock();
-	nh = dev_pm_opp_get_notifier(dev);
-	if (IS_ERR(nh))
-		ret = PTR_ERR(nh);
-	rcu_read_unlock();
-	if (!ret)
-		ret = srcu_notifier_chain_register(nh, &devfreq->nb);
-
-	return ret;
+	return dev_pm_opp_register_notifier(dev, &devfreq->nb);
 }
 EXPORT_SYMBOL(devfreq_register_opp_notifier);
 
@@ -1292,18 +1281,7 @@ EXPORT_SYMBOL(devfreq_register_opp_notifier);
  */
 int devfreq_unregister_opp_notifier(struct device *dev, struct devfreq *devfreq)
 {
-	struct srcu_notifier_head *nh;
-	int ret = 0;
-
-	rcu_read_lock();
-	nh = dev_pm_opp_get_notifier(dev);
-	if (IS_ERR(nh))
-		ret = PTR_ERR(nh);
-	rcu_read_unlock();
-	if (!ret)
-		ret = srcu_notifier_chain_unregister(nh, &devfreq->nb);
-
-	return ret;
+	return dev_pm_opp_unregister_notifier(dev, &devfreq->nb);
 }
 EXPORT_SYMBOL(devfreq_unregister_opp_notifier);
 
diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h
index 7483ff291a8e..66a02deeb03f 100644
--- a/include/linux/pm_opp.h
+++ b/include/linux/pm_opp.h
@@ -108,7 +108,9 @@ int dev_pm_opp_enable(struct device *dev, unsigned long freq);
 
 int dev_pm_opp_disable(struct device *dev, unsigned long freq);
 
-struct srcu_notifier_head *dev_pm_opp_get_notifier(struct device *dev);
+int dev_pm_opp_register_notifier(struct device *dev, struct notifier_block *nb);
+int dev_pm_opp_unregister_notifier(struct device *dev, struct notifier_block *nb);
+
 int dev_pm_opp_set_supported_hw(struct device *dev, const u32 *versions,
 				unsigned int count);
 void dev_pm_opp_put_supported_hw(struct device *dev);
@@ -202,10 +204,14 @@ static inline int dev_pm_opp_disable(struct device *dev, unsigned long freq)
 	return 0;
 }
 
-static inline struct srcu_notifier_head *dev_pm_opp_get_notifier(
-							struct device *dev)
+static inline int dev_pm_opp_register_notifier(struct device *dev, struct notifier_block *nb)
 {
-	return ERR_PTR(-ENOTSUPP);
+	return -ENOTSUPP;
+}
+
+static inline int dev_pm_opp_unregister_notifier(struct device *dev, struct notifier_block *nb)
+{
+	return -ENOTSUPP;
 }
 
 static inline int dev_pm_opp_set_supported_hw(struct device *dev,
-- 
cgit v1.2.3


From b6160e26936bcf1b9181bb34ad4f420ccd3f39f0 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Mon, 2 Jan 2017 14:41:04 +0530
Subject: PM / OPP: Split out part of _add_opp_table() and _remove_opp_table()

Split out parts of _add_opp_table() and _remove_opp_table() into
separate routines. This improves readability as well.

Should result in no functional changes.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/opp/core.c | 76 +++++++++++++++++++++++++------------------
 1 file changed, 44 insertions(+), 32 deletions(-)

diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c
index f35effad60d1..622dd32f8dda 100644
--- a/drivers/base/power/opp/core.c
+++ b/drivers/base/power/opp/core.c
@@ -819,26 +819,12 @@ struct opp_device *_add_opp_dev(const struct device *dev,
 	return opp_dev;
 }
 
-/**
- * _add_opp_table() - Find OPP table or allocate a new one
- * @dev:	device for which we do this operation
- *
- * It tries to find an existing table first, if it couldn't find one, it
- * allocates a new OPP table and returns that.
- *
- * Return: valid opp_table pointer if success, else NULL.
- */
-struct opp_table *_add_opp_table(struct device *dev)
+static struct opp_table *_allocate_opp_table(struct device *dev)
 {
 	struct opp_table *opp_table;
 	struct opp_device *opp_dev;
 	int ret;
 
-	/* Check for existing table for 'dev' first */
-	opp_table = _find_opp_table(dev);
-	if (!IS_ERR(opp_table))
-		return opp_table;
-
 	/*
 	 * Allocate a new OPP table. In the infrequent case where a new
 	 * device is needed to be added, we pay this penalty.
@@ -874,6 +860,27 @@ struct opp_table *_add_opp_table(struct device *dev)
 	return opp_table;
 }
 
+/**
+ * _add_opp_table() - Find OPP table or allocate a new one
+ * @dev:	device for which we do this operation
+ *
+ * It tries to find an existing table first, if it couldn't find one, it
+ * allocates a new OPP table and returns that.
+ *
+ * Return: valid opp_table pointer if success, else NULL.
+ */
+struct opp_table *_add_opp_table(struct device *dev)
+{
+	struct opp_table *opp_table;
+
+	/* Check for existing table for 'dev' first */
+	opp_table = _find_opp_table(dev);
+	if (!IS_ERR(opp_table))
+		return opp_table;
+
+	return _allocate_opp_table(dev);
+}
+
 /**
  * _kfree_device_rcu() - Free opp_table RCU handler
  * @head:	RCU head
@@ -886,6 +893,27 @@ static void _kfree_device_rcu(struct rcu_head *head)
 	kfree_rcu(opp_table, rcu_head);
 }
 
+static void _free_opp_table(struct opp_table *opp_table)
+{
+	struct opp_device *opp_dev;
+
+	/* Release clk */
+	if (!IS_ERR(opp_table->clk))
+		clk_put(opp_table->clk);
+
+	opp_dev = list_first_entry(&opp_table->dev_list, struct opp_device,
+				   node);
+
+	_remove_opp_dev(opp_dev, opp_table);
+
+	/* dev_list must be empty now */
+	WARN_ON(!list_empty(&opp_table->dev_list));
+
+	list_del_rcu(&opp_table->node);
+	call_srcu(&opp_table->srcu_head.srcu, &opp_table->rcu_head,
+		  _kfree_device_rcu);
+}
+
 /**
  * _remove_opp_table() - Removes a OPP table
  * @opp_table: OPP table to be removed.
@@ -894,8 +922,6 @@ static void _kfree_device_rcu(struct rcu_head *head)
  */
 static void _remove_opp_table(struct opp_table *opp_table)
 {
-	struct opp_device *opp_dev;
-
 	if (!list_empty(&opp_table->opp_list))
 		return;
 
@@ -911,21 +937,7 @@ static void _remove_opp_table(struct opp_table *opp_table)
 	if (opp_table->set_opp)
 		return;
 
-	/* Release clk */
-	if (!IS_ERR(opp_table->clk))
-		clk_put(opp_table->clk);
-
-	opp_dev = list_first_entry(&opp_table->dev_list, struct opp_device,
-				   node);
-
-	_remove_opp_dev(opp_dev, opp_table);
-
-	/* dev_list must be empty now */
-	WARN_ON(!list_empty(&opp_table->dev_list));
-
-	list_del_rcu(&opp_table->node);
-	call_srcu(&opp_table->srcu_head.srcu, &opp_table->rcu_head,
-		  _kfree_device_rcu);
+	_free_opp_table(opp_table);
 }
 
 void _opp_free(struct dev_pm_opp *opp)
-- 
cgit v1.2.3


From 37a73ec0c9bbd712d24cc2035696893e5b6119a5 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Mon, 23 Jan 2017 10:11:41 +0530
Subject: PM / OPP: Add per OPP table mutex

Add per OPP table lock to protect opp_table->opp_list.

Note that at few places opp_list is used under the rcu_read_lock() and
so a mutex can't be added there for now. This will be fixed by a later
patch.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/opp/core.c | 31 +++++++++++++++++++++++++++----
 drivers/base/power/opp/opp.h  |  2 ++
 2 files changed, 29 insertions(+), 4 deletions(-)

diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c
index 622dd32f8dda..dcebd5efb6a1 100644
--- a/drivers/base/power/opp/core.c
+++ b/drivers/base/power/opp/core.c
@@ -854,6 +854,7 @@ static struct opp_table *_allocate_opp_table(struct device *dev)
 
 	srcu_init_notifier_head(&opp_table->srcu_head);
 	INIT_LIST_HEAD(&opp_table->opp_list);
+	mutex_init(&opp_table->lock);
 
 	/* Secure the device table modification */
 	list_add_rcu(&opp_table->node, &opp_tables);
@@ -909,6 +910,7 @@ static void _free_opp_table(struct opp_table *opp_table)
 	/* dev_list must be empty now */
 	WARN_ON(!list_empty(&opp_table->dev_list));
 
+	mutex_destroy(&opp_table->lock);
 	list_del_rcu(&opp_table->node);
 	call_srcu(&opp_table->srcu_head.srcu, &opp_table->rcu_head,
 		  _kfree_device_rcu);
@@ -969,6 +971,8 @@ static void _kfree_opp_rcu(struct rcu_head *head)
  */
 static void _opp_remove(struct opp_table *opp_table, struct dev_pm_opp *opp)
 {
+	mutex_lock(&opp_table->lock);
+
 	/*
 	 * Notify the changes in the availability of the operable
 	 * frequency/voltage list.
@@ -978,6 +982,8 @@ static void _opp_remove(struct opp_table *opp_table, struct dev_pm_opp *opp)
 	list_del_rcu(&opp->node);
 	call_srcu(&opp_table->srcu_head.srcu, &opp->rcu_head, _kfree_opp_rcu);
 
+	mutex_unlock(&opp_table->lock);
+
 	_remove_opp_table(opp_table);
 }
 
@@ -1007,6 +1013,8 @@ void dev_pm_opp_remove(struct device *dev, unsigned long freq)
 	if (IS_ERR(opp_table))
 		goto unlock;
 
+	mutex_lock(&opp_table->lock);
+
 	list_for_each_entry(opp, &opp_table->opp_list, node) {
 		if (opp->rate == freq) {
 			found = true;
@@ -1014,6 +1022,8 @@ void dev_pm_opp_remove(struct device *dev, unsigned long freq)
 		}
 	}
 
+	mutex_unlock(&opp_table->lock);
+
 	if (!found) {
 		dev_warn(dev, "%s: Couldn't find OPP with freq: %lu\n",
 			 __func__, freq);
@@ -1083,7 +1093,7 @@ int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
 	     struct opp_table *opp_table)
 {
 	struct dev_pm_opp *opp;
-	struct list_head *head = &opp_table->opp_list;
+	struct list_head *head;
 	int ret;
 
 	/*
@@ -1094,6 +1104,9 @@ int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
 	 * loop, don't replace it with head otherwise it will become an infinite
 	 * loop.
 	 */
+	mutex_lock(&opp_table->lock);
+	head = &opp_table->opp_list;
+
 	list_for_each_entry_rcu(opp, &opp_table->opp_list, node) {
 		if (new_opp->rate > opp->rate) {
 			head = &opp->node;
@@ -1110,12 +1123,17 @@ int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
 			 new_opp->supplies[0].u_volt, new_opp->available);
 
 		/* Should we compare voltages for all regulators here ? */
-		return opp->available &&
-		       new_opp->supplies[0].u_volt == opp->supplies[0].u_volt ? -EBUSY : -EEXIST;
+		ret = opp->available &&
+		      new_opp->supplies[0].u_volt == opp->supplies[0].u_volt ? -EBUSY : -EEXIST;
+
+		mutex_unlock(&opp_table->lock);
+		return ret;
 	}
 
-	new_opp->opp_table = opp_table;
 	list_add_rcu(&new_opp->node, head);
+	mutex_unlock(&opp_table->lock);
+
+	new_opp->opp_table = opp_table;
 
 	ret = opp_debug_create_one(new_opp, opp_table);
 	if (ret)
@@ -1779,6 +1797,8 @@ static int _opp_set_availability(struct device *dev, unsigned long freq,
 		goto unlock;
 	}
 
+	mutex_lock(&opp_table->lock);
+
 	/* Do we have the frequency? */
 	list_for_each_entry(tmp_opp, &opp_table->opp_list, node) {
 		if (tmp_opp->rate == freq) {
@@ -1786,6 +1806,9 @@ static int _opp_set_availability(struct device *dev, unsigned long freq,
 			break;
 		}
 	}
+
+	mutex_unlock(&opp_table->lock);
+
 	if (IS_ERR(opp)) {
 		r = PTR_ERR(opp);
 		goto unlock;
diff --git a/drivers/base/power/opp/opp.h b/drivers/base/power/opp/opp.h
index 0a5eb4d1e8f7..105243b06373 100644
--- a/drivers/base/power/opp/opp.h
+++ b/drivers/base/power/opp/opp.h
@@ -131,6 +131,7 @@ enum opp_table_access {
  * @rcu_head:	RCU callback head used for deferred freeing
  * @dev_list:	list of devices that share these OPPs
  * @opp_list:	table of opps
+ * @lock:	mutex protecting the opp_list.
  * @np:		struct device_node pointer for opp's DT node.
  * @clock_latency_ns_max: Max clock latency in nanoseconds.
  * @shared_opp: OPP is shared between multiple devices.
@@ -163,6 +164,7 @@ struct opp_table {
 	struct rcu_head rcu_head;
 	struct list_head dev_list;
 	struct list_head opp_list;
+	struct mutex lock;
 
 	struct device_node *np;
 	unsigned long clock_latency_ns_max;
-- 
cgit v1.2.3


From f067a982cefa8df5642212bb0c7e25974831f781 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Mon, 23 Jan 2017 10:11:42 +0530
Subject: PM / OPP: Add 'struct kref' to OPP table

Add kref to struct opp_table for easier accounting of the OPP table.

Note that the new routine dev_pm_opp_get_opp_table() takes the reference
from under the opp_table_lock, which guarantees that the OPP table
doesn't get freed unless dev_pm_opp_put_opp_table() is called for the
OPP table.

Two separate release mechanisms are added: locked and unlocked. In
unlocked version the routines aren't required to take/drop
opp_table_lock as the callers have already done that. This is required
to avoid breaking git bisect, otherwise we may get lockdeps between
commits. Once all the users of OPP table are updated the unlocked
version shall be removed.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/opp/core.c | 51 +++++++++++++++++++++++++++++++++++++++++--
 drivers/base/power/opp/opp.h  |  3 +++
 include/linux/pm_opp.h        | 10 +++++++++
 3 files changed, 62 insertions(+), 2 deletions(-)

diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c
index dcebd5efb6a1..ccc0d8913fd0 100644
--- a/drivers/base/power/opp/core.c
+++ b/drivers/base/power/opp/core.c
@@ -855,6 +855,7 @@ static struct opp_table *_allocate_opp_table(struct device *dev)
 	srcu_init_notifier_head(&opp_table->srcu_head);
 	INIT_LIST_HEAD(&opp_table->opp_list);
 	mutex_init(&opp_table->lock);
+	kref_init(&opp_table->kref);
 
 	/* Secure the device table modification */
 	list_add_rcu(&opp_table->node, &opp_tables);
@@ -894,8 +895,36 @@ static void _kfree_device_rcu(struct rcu_head *head)
 	kfree_rcu(opp_table, rcu_head);
 }
 
-static void _free_opp_table(struct opp_table *opp_table)
+void _get_opp_table_kref(struct opp_table *opp_table)
 {
+	kref_get(&opp_table->kref);
+}
+
+struct opp_table *dev_pm_opp_get_opp_table(struct device *dev)
+{
+	struct opp_table *opp_table;
+
+	/* Hold our table modification lock here */
+	mutex_lock(&opp_table_lock);
+
+	opp_table = _find_opp_table(dev);
+	if (!IS_ERR(opp_table)) {
+		_get_opp_table_kref(opp_table);
+		goto unlock;
+	}
+
+	opp_table = _allocate_opp_table(dev);
+
+unlock:
+	mutex_unlock(&opp_table_lock);
+
+	return opp_table;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_get_opp_table);
+
+static void _opp_table_kref_release_unlocked(struct kref *kref)
+{
+	struct opp_table *opp_table = container_of(kref, struct opp_table, kref);
 	struct opp_device *opp_dev;
 
 	/* Release clk */
@@ -916,6 +945,24 @@ static void _free_opp_table(struct opp_table *opp_table)
 		  _kfree_device_rcu);
 }
 
+static void dev_pm_opp_put_opp_table_unlocked(struct opp_table *opp_table)
+{
+	kref_put(&opp_table->kref, _opp_table_kref_release_unlocked);
+}
+
+static void _opp_table_kref_release(struct kref *kref)
+{
+	_opp_table_kref_release_unlocked(kref);
+	mutex_unlock(&opp_table_lock);
+}
+
+void dev_pm_opp_put_opp_table(struct opp_table *opp_table)
+{
+	kref_put_mutex(&opp_table->kref, _opp_table_kref_release,
+		       &opp_table_lock);
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_put_opp_table);
+
 /**
  * _remove_opp_table() - Removes a OPP table
  * @opp_table: OPP table to be removed.
@@ -939,7 +986,7 @@ static void _remove_opp_table(struct opp_table *opp_table)
 	if (opp_table->set_opp)
 		return;
 
-	_free_opp_table(opp_table);
+	dev_pm_opp_put_opp_table_unlocked(opp_table);
 }
 
 void _opp_free(struct dev_pm_opp *opp)
diff --git a/drivers/base/power/opp/opp.h b/drivers/base/power/opp/opp.h
index 105243b06373..aae4d8f480ef 100644
--- a/drivers/base/power/opp/opp.h
+++ b/drivers/base/power/opp/opp.h
@@ -131,6 +131,7 @@ enum opp_table_access {
  * @rcu_head:	RCU callback head used for deferred freeing
  * @dev_list:	list of devices that share these OPPs
  * @opp_list:	table of opps
+ * @kref:	for reference count of the table.
  * @lock:	mutex protecting the opp_list.
  * @np:		struct device_node pointer for opp's DT node.
  * @clock_latency_ns_max: Max clock latency in nanoseconds.
@@ -164,6 +165,7 @@ struct opp_table {
 	struct rcu_head rcu_head;
 	struct list_head dev_list;
 	struct list_head opp_list;
+	struct kref kref;
 	struct mutex lock;
 
 	struct device_node *np;
@@ -192,6 +194,7 @@ struct opp_table {
 };
 
 /* Routines internal to opp core */
+void _get_opp_table_kref(struct opp_table *opp_table);
 struct opp_table *_find_opp_table(struct device *dev);
 struct opp_table *_add_opp_table(struct device *dev);
 struct opp_device *_add_opp_dev(const struct device *dev, struct opp_table *opp_table);
diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h
index 66a02deeb03f..d867c6b25f9a 100644
--- a/include/linux/pm_opp.h
+++ b/include/linux/pm_opp.h
@@ -78,6 +78,9 @@ struct dev_pm_set_opp_data {
 
 #if defined(CONFIG_PM_OPP)
 
+struct opp_table *dev_pm_opp_get_opp_table(struct device *dev);
+void dev_pm_opp_put_opp_table(struct opp_table *opp_table);
+
 unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp);
 
 unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp);
@@ -126,6 +129,13 @@ int dev_pm_opp_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask)
 void dev_pm_opp_remove_table(struct device *dev);
 void dev_pm_opp_cpumask_remove_table(const struct cpumask *cpumask);
 #else
+static inline struct opp_table *dev_pm_opp_get_opp_table(struct device *dev)
+{
+	return ERR_PTR(-ENOTSUPP);
+}
+
+static inline void dev_pm_opp_put_opp_table(struct opp_table *opp_table) {}
+
 static inline unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp)
 {
 	return 0;
-- 
cgit v1.2.3


From fa30184d192ec78d443cf6d3abc37d9eb3b9253e Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Mon, 23 Jan 2017 10:11:43 +0530
Subject: PM / OPP: Return opp_table from dev_pm_opp_set_*() routines

Now that we have proper kernel reference infrastructure in place for OPP
tables, use it to guarantee that the OPP table isn't freed while being
used by the callers of dev_pm_opp_set_*() APIs.

Make them all return the pointer to the OPP table after taking its
reference and put the reference back with dev_pm_opp_put_*() APIs.

Now that the OPP table wouldn't get freed while these routines are
executing after dev_pm_opp_get_opp_table() is called, there is no need
to take opp_table_lock. Drop them as well.

Remove the rcu specific comments from these routines as they aren't
relevant anymore.

Note that prototypes of dev_pm_opp_{set|put}_regulators() were already
updated by another patch.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/opp/core.c | 243 +++++++++---------------------------------
 drivers/cpufreq/sti-cpufreq.c |  13 +--
 include/linux/pm_opp.h        |  35 +++---
 3 files changed, 74 insertions(+), 217 deletions(-)

diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c
index ccc0d8913fd0..1af349ab630e 100644
--- a/drivers/base/power/opp/core.c
+++ b/drivers/base/power/opp/core.c
@@ -974,18 +974,6 @@ static void _remove_opp_table(struct opp_table *opp_table)
 	if (!list_empty(&opp_table->opp_list))
 		return;
 
-	if (opp_table->supported_hw)
-		return;
-
-	if (opp_table->prop_name)
-		return;
-
-	if (opp_table->regulators)
-		return;
-
-	if (opp_table->set_opp)
-		return;
-
 	dev_pm_opp_put_opp_table_unlocked(opp_table);
 }
 
@@ -1277,27 +1265,16 @@ free_opp:
  * specify the hierarchy of versions it supports. OPP layer will then enable
  * OPPs, which are available for those versions, based on its 'opp-supported-hw'
  * property.
- *
- * 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_set_supported_hw(struct device *dev, const u32 *versions,
-				unsigned int count)
+struct opp_table *dev_pm_opp_set_supported_hw(struct device *dev,
+			const u32 *versions, unsigned int count)
 {
 	struct opp_table *opp_table;
-	int ret = 0;
-
-	/* Hold our table modification lock here */
-	mutex_lock(&opp_table_lock);
+	int ret;
 
-	opp_table = _add_opp_table(dev);
-	if (!opp_table) {
-		ret = -ENOMEM;
-		goto unlock;
-	}
+	opp_table = dev_pm_opp_get_opp_table(dev);
+	if (!opp_table)
+		return ERR_PTR(-ENOMEM);
 
 	/* Make sure there are no concurrent readers while updating opp_table */
 	WARN_ON(!list_empty(&opp_table->opp_list));
@@ -1318,65 +1295,40 @@ int dev_pm_opp_set_supported_hw(struct device *dev, const u32 *versions,
 	}
 
 	opp_table->supported_hw_count = count;
-	mutex_unlock(&opp_table_lock);
-	return 0;
+
+	return opp_table;
 
 err:
-	_remove_opp_table(opp_table);
-unlock:
-	mutex_unlock(&opp_table_lock);
+	dev_pm_opp_put_opp_table(opp_table);
 
-	return ret;
+	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_set_supported_hw);
 
 /**
  * dev_pm_opp_put_supported_hw() - Releases resources blocked for supported hw
- * @dev: Device for which supported-hw has to be put.
+ * @opp_table: OPP table returned by dev_pm_opp_set_supported_hw().
  *
  * This is required only for the V2 bindings, and is called for a matching
  * dev_pm_opp_set_supported_hw(). Until this is called, the opp_table structure
  * will not be freed.
- *
- * 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_put_supported_hw(struct device *dev)
+void dev_pm_opp_put_supported_hw(struct opp_table *opp_table)
 {
-	struct opp_table *opp_table;
-
-	/* Hold our table modification lock here */
-	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;
-	}
-
 	/* Make sure there are no concurrent readers while updating opp_table */
 	WARN_ON(!list_empty(&opp_table->opp_list));
 
 	if (!opp_table->supported_hw) {
-		dev_err(dev, "%s: Doesn't have supported hardware list\n",
-			__func__);
-		goto unlock;
+		pr_err("%s: Doesn't have supported hardware list\n",
+		       __func__);
+		return;
 	}
 
 	kfree(opp_table->supported_hw);
 	opp_table->supported_hw = NULL;
 	opp_table->supported_hw_count = 0;
 
-	/* Try freeing opp_table if this was the last blocking resource */
-	_remove_opp_table(opp_table);
-
-unlock:
-	mutex_unlock(&opp_table_lock);
+	dev_pm_opp_put_opp_table(opp_table);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_put_supported_hw);
 
@@ -1389,26 +1341,15 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_put_supported_hw);
  * specify the extn to be used for certain property names. The properties to
  * which the extension will apply are opp-microvolt and opp-microamp. OPP core
  * should postfix the property name with -<name> while looking for them.
- *
- * 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_set_prop_name(struct device *dev, const char *name)
+struct opp_table *dev_pm_opp_set_prop_name(struct device *dev, const char *name)
 {
 	struct opp_table *opp_table;
-	int ret = 0;
-
-	/* Hold our table modification lock here */
-	mutex_lock(&opp_table_lock);
+	int ret;
 
-	opp_table = _add_opp_table(dev);
-	if (!opp_table) {
-		ret = -ENOMEM;
-		goto unlock;
-	}
+	opp_table = dev_pm_opp_get_opp_table(dev);
+	if (!opp_table)
+		return ERR_PTR(-ENOMEM);
 
 	/* Make sure there are no concurrent readers while updating opp_table */
 	WARN_ON(!list_empty(&opp_table->opp_list));
@@ -1427,63 +1368,37 @@ int dev_pm_opp_set_prop_name(struct device *dev, const char *name)
 		goto err;
 	}
 
-	mutex_unlock(&opp_table_lock);
-	return 0;
+	return opp_table;
 
 err:
-	_remove_opp_table(opp_table);
-unlock:
-	mutex_unlock(&opp_table_lock);
+	dev_pm_opp_put_opp_table(opp_table);
 
-	return ret;
+	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_set_prop_name);
 
 /**
  * dev_pm_opp_put_prop_name() - Releases resources blocked for prop-name
- * @dev: Device for which the prop-name has to be put.
+ * @opp_table: OPP table returned by dev_pm_opp_set_prop_name().
  *
  * This is required only for the V2 bindings, and is called for a matching
  * dev_pm_opp_set_prop_name(). Until this is called, the opp_table structure
  * will not be freed.
- *
- * 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_put_prop_name(struct device *dev)
+void dev_pm_opp_put_prop_name(struct opp_table *opp_table)
 {
-	struct opp_table *opp_table;
-
-	/* Hold our table modification lock here */
-	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;
-	}
-
 	/* Make sure there are no concurrent readers while updating opp_table */
 	WARN_ON(!list_empty(&opp_table->opp_list));
 
 	if (!opp_table->prop_name) {
-		dev_err(dev, "%s: Doesn't have a prop-name\n", __func__);
-		goto unlock;
+		pr_err("%s: Doesn't have a prop-name\n", __func__);
+		return;
 	}
 
 	kfree(opp_table->prop_name);
 	opp_table->prop_name = NULL;
 
-	/* Try freeing opp_table if this was the last blocking resource */
-	_remove_opp_table(opp_table);
-
-unlock:
-	mutex_unlock(&opp_table_lock);
+	dev_pm_opp_put_opp_table(opp_table);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_put_prop_name);
 
@@ -1530,12 +1445,6 @@ static void _free_set_opp_data(struct opp_table *opp_table)
  * well.
  *
  * 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.
  */
 struct opp_table *dev_pm_opp_set_regulators(struct device *dev,
 					    const char * const names[],
@@ -1545,13 +1454,9 @@ struct opp_table *dev_pm_opp_set_regulators(struct device *dev,
 	struct regulator *reg;
 	int ret, i;
 
-	mutex_lock(&opp_table_lock);
-
-	opp_table = _add_opp_table(dev);
-	if (!opp_table) {
-		ret = -ENOMEM;
-		goto unlock;
-	}
+	opp_table = dev_pm_opp_get_opp_table(dev);
+	if (!opp_table)
+		return ERR_PTR(-ENOMEM);
 
 	/* This should be called before OPPs are initialized */
 	if (WARN_ON(!list_empty(&opp_table->opp_list))) {
@@ -1593,7 +1498,6 @@ struct opp_table *dev_pm_opp_set_regulators(struct device *dev,
 	if (ret)
 		goto free_regulators;
 
-	mutex_unlock(&opp_table_lock);
 	return opp_table;
 
 free_regulators:
@@ -1604,9 +1508,7 @@ free_regulators:
 	opp_table->regulators = NULL;
 	opp_table->regulator_count = 0;
 err:
-	_remove_opp_table(opp_table);
-unlock:
-	mutex_unlock(&opp_table_lock);
+	dev_pm_opp_put_opp_table(opp_table);
 
 	return ERR_PTR(ret);
 }
@@ -1615,22 +1517,14 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_set_regulators);
 /**
  * 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
- * 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_put_regulators(struct opp_table *opp_table)
 {
 	int i;
 
-	mutex_lock(&opp_table_lock);
-
 	if (!opp_table->regulators) {
 		pr_err("%s: Doesn't have regulators set\n", __func__);
-		goto unlock;
+		return;
 	}
 
 	/* Make sure there are no concurrent readers while updating opp_table */
@@ -1645,11 +1539,7 @@ void dev_pm_opp_put_regulators(struct opp_table *opp_table)
 	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);
-
-unlock:
-	mutex_unlock(&opp_table_lock);
+	dev_pm_opp_put_opp_table(opp_table);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_put_regulators);
 
@@ -1662,29 +1552,19 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_put_regulators);
  * 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,
+struct opp_table *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);
+		return ERR_PTR(-EINVAL);
 
-	opp_table = _add_opp_table(dev);
-	if (!opp_table) {
-		ret = -ENOMEM;
-		goto unlock;
-	}
+	opp_table = dev_pm_opp_get_opp_table(dev);
+	if (!opp_table)
+		return ERR_PTR(-ENOMEM);
 
 	/* This should be called before OPPs are initialized */
 	if (WARN_ON(!list_empty(&opp_table->opp_list))) {
@@ -1700,47 +1580,28 @@ int dev_pm_opp_register_set_opp_helper(struct device *dev,
 
 	opp_table->set_opp = set_opp;
 
-	mutex_unlock(&opp_table_lock);
-	return 0;
+	return opp_table;
 
 err:
-	_remove_opp_table(opp_table);
-unlock:
-	mutex_unlock(&opp_table_lock);
+	dev_pm_opp_put_opp_table(opp_table);
 
-	return ret;
+	return ERR_PTR(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.
+ * @opp_table: OPP table returned from dev_pm_opp_register_set_opp_helper().
  *
- * 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.
+ * Release resources blocked for platform specific set_opp helper.
  */
-void dev_pm_opp_register_put_opp_helper(struct device *dev)
+void dev_pm_opp_register_put_opp_helper(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 (!opp_table->set_opp) {
-		dev_err(dev, "%s: Doesn't have custom set_opp helper set\n",
-			__func__);
-		goto unlock;
+		pr_err("%s: Doesn't have custom set_opp helper set\n",
+		       __func__);
+		return;
 	}
 
 	/* Make sure there are no concurrent readers while updating opp_table */
@@ -1748,11 +1609,7 @@ void dev_pm_opp_register_put_opp_helper(struct device *dev)
 
 	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);
+	dev_pm_opp_put_opp_table(opp_table);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_register_put_opp_helper);
 
diff --git a/drivers/cpufreq/sti-cpufreq.c b/drivers/cpufreq/sti-cpufreq.c
index b366e6d830ea..a7db9011d5fe 100644
--- a/drivers/cpufreq/sti-cpufreq.c
+++ b/drivers/cpufreq/sti-cpufreq.c
@@ -160,6 +160,7 @@ static int sti_cpufreq_set_opp_info(void)
 	int pcode, substrate, major, minor;
 	int ret;
 	char name[MAX_PCODE_NAME_LEN];
+	struct opp_table *opp_table;
 
 	reg_fields = sti_cpufreq_match();
 	if (!reg_fields) {
@@ -211,20 +212,20 @@ use_defaults:
 
 	snprintf(name, MAX_PCODE_NAME_LEN, "pcode%d", pcode);
 
-	ret = dev_pm_opp_set_prop_name(dev, name);
-	if (ret) {
+	opp_table = dev_pm_opp_set_prop_name(dev, name);
+	if (IS_ERR(opp_table)) {
 		dev_err(dev, "Failed to set prop name\n");
-		return ret;
+		return PTR_ERR(opp_table);
 	}
 
 	version[0] = BIT(major);
 	version[1] = BIT(minor);
 	version[2] = BIT(substrate);
 
-	ret = dev_pm_opp_set_supported_hw(dev, version, VERSION_ELEMENTS);
-	if (ret) {
+	opp_table = dev_pm_opp_set_supported_hw(dev, version, VERSION_ELEMENTS);
+	if (IS_ERR(opp_table)) {
 		dev_err(dev, "Failed to set supported hardware\n");
-		return ret;
+		return PTR_ERR(opp_table);
 	}
 
 	dev_dbg(dev, "pcode: %d major: %d minor: %d substrate: %d\n",
diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h
index d867c6b25f9a..99787cbcaab2 100644
--- a/include/linux/pm_opp.h
+++ b/include/linux/pm_opp.h
@@ -114,15 +114,14 @@ int dev_pm_opp_disable(struct device *dev, unsigned long freq);
 int dev_pm_opp_register_notifier(struct device *dev, struct notifier_block *nb);
 int dev_pm_opp_unregister_notifier(struct device *dev, struct notifier_block *nb);
 
-int dev_pm_opp_set_supported_hw(struct device *dev, const u32 *versions,
-				unsigned int count);
-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_supported_hw(struct device *dev, const u32 *versions, unsigned int count);
+void dev_pm_opp_put_supported_hw(struct opp_table *opp_table);
+struct opp_table *dev_pm_opp_set_prop_name(struct device *dev, const char *name);
+void dev_pm_opp_put_prop_name(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_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);
+struct opp_table *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 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);
@@ -224,29 +223,29 @@ static inline int dev_pm_opp_unregister_notifier(struct device *dev, struct noti
 	return -ENOTSUPP;
 }
 
-static inline int dev_pm_opp_set_supported_hw(struct device *dev,
-					      const u32 *versions,
-					      unsigned int count)
+static inline struct opp_table *dev_pm_opp_set_supported_hw(struct device *dev,
+							    const u32 *versions,
+							    unsigned int count)
 {
-	return -ENOTSUPP;
+	return ERR_PTR(-ENOTSUPP);
 }
 
-static inline void dev_pm_opp_put_supported_hw(struct device *dev) {}
+static inline void dev_pm_opp_put_supported_hw(struct opp_table *opp_table) {}
 
-static inline int dev_pm_opp_register_set_opp_helper(struct device *dev,
+static inline struct opp_table *dev_pm_opp_register_set_opp_helper(struct device *dev,
 			int (*set_opp)(struct dev_pm_set_opp_data *data))
 {
-	return -ENOTSUPP;
+	return ERR_PTR(-ENOTSUPP);
 }
 
-static inline void dev_pm_opp_register_put_opp_helper(struct device *dev) {}
+static inline void dev_pm_opp_register_put_opp_helper(struct opp_table *opp_table) {}
 
-static inline int dev_pm_opp_set_prop_name(struct device *dev, const char *name)
+static inline struct opp_table *dev_pm_opp_set_prop_name(struct device *dev, const char *name)
 {
-	return -ENOTSUPP;
+	return ERR_PTR(-ENOTSUPP);
 }
 
-static inline void dev_pm_opp_put_prop_name(struct device *dev) {}
+static inline void dev_pm_opp_put_prop_name(struct opp_table *opp_table) {}
 
 static inline struct opp_table *dev_pm_opp_set_regulators(struct device *dev, const char * const names[], unsigned int count)
 {
-- 
cgit v1.2.3


From 31641cda53dd71c0447fca5e6d42e0e3e8391733 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Mon, 23 Jan 2017 10:11:44 +0530
Subject: PM / OPP: Take reference of the OPP table while adding/removing OPPs

Take reference of the OPP table while adding and removing OPPs, that
helps us remove special checks in _remove_opp_table().

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/opp/core.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c
index 1af349ab630e..1a38b5d8dc54 100644
--- a/drivers/base/power/opp/core.c
+++ b/drivers/base/power/opp/core.c
@@ -971,9 +971,6 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_put_opp_table);
  */
 static void _remove_opp_table(struct opp_table *opp_table)
 {
-	if (!list_empty(&opp_table->opp_list))
-		return;
-
 	dev_pm_opp_put_opp_table_unlocked(opp_table);
 }
 
@@ -1018,8 +1015,7 @@ static void _opp_remove(struct opp_table *opp_table, struct dev_pm_opp *opp)
 	call_srcu(&opp_table->srcu_head.srcu, &opp->rcu_head, _kfree_opp_rcu);
 
 	mutex_unlock(&opp_table->lock);
-
-	_remove_opp_table(opp_table);
+	dev_pm_opp_put_opp_table(opp_table);
 }
 
 /**
@@ -1170,6 +1166,9 @@ int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
 
 	new_opp->opp_table = opp_table;
 
+	/* Get a reference to the OPP table */
+	_get_opp_table_kref(opp_table);
+
 	ret = opp_debug_create_one(new_opp, opp_table);
 	if (ret)
 		dev_err(dev, "%s: Failed to register opp to debugfs (%d)\n",
-- 
cgit v1.2.3


From b83c1899a0e98cabd0997531434e1fb3b6574db8 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Mon, 23 Jan 2017 10:11:45 +0530
Subject: PM / OPP: Use dev_pm_opp_get_opp_table() instead of _add_opp_table()

Migrate all users of _add_opp_table() to use dev_pm_opp_get_opp_table()
to guarantee that the OPP table doesn't get freed while being used.

Also update _managed_opp() to get the reference to the OPP table.

Now that the OPP table wouldn't get freed while these routines are
executing after dev_pm_opp_get_opp_table() is called, there is no need
to take opp_table_lock. Drop them as well.

Now that _add_opp_table(), _remove_opp_table() and the unlocked release
routines aren't used anymore, remove them.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/opp/core.c | 63 ++++---------------------------------------
 drivers/base/power/opp/of.c   | 54 +++++++++++++++++--------------------
 drivers/base/power/opp/opp.h  |  1 -
 3 files changed, 29 insertions(+), 89 deletions(-)

diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c
index 1a38b5d8dc54..ab9499e3ba02 100644
--- a/drivers/base/power/opp/core.c
+++ b/drivers/base/power/opp/core.c
@@ -862,27 +862,6 @@ static struct opp_table *_allocate_opp_table(struct device *dev)
 	return opp_table;
 }
 
-/**
- * _add_opp_table() - Find OPP table or allocate a new one
- * @dev:	device for which we do this operation
- *
- * It tries to find an existing table first, if it couldn't find one, it
- * allocates a new OPP table and returns that.
- *
- * Return: valid opp_table pointer if success, else NULL.
- */
-struct opp_table *_add_opp_table(struct device *dev)
-{
-	struct opp_table *opp_table;
-
-	/* Check for existing table for 'dev' first */
-	opp_table = _find_opp_table(dev);
-	if (!IS_ERR(opp_table))
-		return opp_table;
-
-	return _allocate_opp_table(dev);
-}
-
 /**
  * _kfree_device_rcu() - Free opp_table RCU handler
  * @head:	RCU head
@@ -922,7 +901,7 @@ unlock:
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_get_opp_table);
 
-static void _opp_table_kref_release_unlocked(struct kref *kref)
+static void _opp_table_kref_release(struct kref *kref)
 {
 	struct opp_table *opp_table = container_of(kref, struct opp_table, kref);
 	struct opp_device *opp_dev;
@@ -943,16 +922,7 @@ static void _opp_table_kref_release_unlocked(struct kref *kref)
 	list_del_rcu(&opp_table->node);
 	call_srcu(&opp_table->srcu_head.srcu, &opp_table->rcu_head,
 		  _kfree_device_rcu);
-}
 
-static void dev_pm_opp_put_opp_table_unlocked(struct opp_table *opp_table)
-{
-	kref_put(&opp_table->kref, _opp_table_kref_release_unlocked);
-}
-
-static void _opp_table_kref_release(struct kref *kref)
-{
-	_opp_table_kref_release_unlocked(kref);
 	mutex_unlock(&opp_table_lock);
 }
 
@@ -963,17 +933,6 @@ void dev_pm_opp_put_opp_table(struct opp_table *opp_table)
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_put_opp_table);
 
-/**
- * _remove_opp_table() - Removes a OPP table
- * @opp_table: OPP table to be removed.
- *
- * Removes/frees OPP table if it doesn't contain any OPPs.
- */
-static void _remove_opp_table(struct opp_table *opp_table)
-{
-	dev_pm_opp_put_opp_table_unlocked(opp_table);
-}
-
 void _opp_free(struct dev_pm_opp *opp)
 {
 	kfree(opp);
@@ -1218,8 +1177,6 @@ int _opp_add_v1(struct opp_table *opp_table, struct device *dev,
 	unsigned long tol;
 	int ret;
 
-	opp_rcu_lockdep_assert();
-
 	new_opp = _opp_allocate(opp_table);
 	if (!new_opp)
 		return -ENOMEM;
@@ -1640,21 +1597,13 @@ int dev_pm_opp_add(struct device *dev, unsigned long freq, unsigned long u_volt)
 	struct opp_table *opp_table;
 	int ret;
 
-	/* Hold our table modification lock here */
-	mutex_lock(&opp_table_lock);
-
-	opp_table = _add_opp_table(dev);
-	if (!opp_table) {
-		ret = -ENOMEM;
-		goto unlock;
-	}
+	opp_table = dev_pm_opp_get_opp_table(dev);
+	if (!opp_table)
+		return -ENOMEM;
 
 	ret = _opp_add_v1(opp_table, dev, freq, u_volt, true);
-	if (ret)
-		_remove_opp_table(opp_table);
 
-unlock:
-	mutex_unlock(&opp_table_lock);
+	dev_pm_opp_put_opp_table(opp_table);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_add);
@@ -1865,8 +1814,6 @@ void _dev_pm_opp_remove_table(struct opp_table *opp_table, struct device *dev,
 {
 	struct dev_pm_opp *opp, *tmp;
 
-	opp_rcu_lockdep_assert();
-
 	/* Find if opp_table manages a single device */
 	if (list_is_singular(&opp_table->dev_list)) {
 		/* Free static OPPs */
diff --git a/drivers/base/power/opp/of.c b/drivers/base/power/opp/of.c
index cdbf733ac9b1..6a6e6e7846b3 100644
--- a/drivers/base/power/opp/of.c
+++ b/drivers/base/power/opp/of.c
@@ -24,7 +24,9 @@
 
 static struct opp_table *_managed_opp(const struct device_node *np)
 {
-	struct opp_table *opp_table;
+	struct opp_table *opp_table, *managed_table = NULL;
+
+	mutex_lock(&opp_table_lock);
 
 	list_for_each_entry_rcu(opp_table, &opp_tables, node) {
 		if (opp_table->np == np) {
@@ -35,14 +37,18 @@ static struct opp_table *_managed_opp(const struct device_node *np)
 			 * But the OPPs will be considered as shared only if the
 			 * OPP table contains a "opp-shared" property.
 			 */
-			if (opp_table->shared_opp == OPP_TABLE_ACCESS_SHARED)
-				return opp_table;
+			if (opp_table->shared_opp == OPP_TABLE_ACCESS_SHARED) {
+				_get_opp_table_kref(opp_table);
+				managed_table = opp_table;
+			}
 
-			return NULL;
+			break;
 		}
 	}
 
-	return NULL;
+	mutex_unlock(&opp_table_lock);
+
+	return managed_table;
 }
 
 void _of_init_opp_table(struct opp_table *opp_table, struct device *dev)
@@ -368,21 +374,17 @@ static int _of_add_opp_table_v2(struct device *dev, struct device_node *opp_np)
 	struct opp_table *opp_table;
 	int ret = 0, count = 0;
 
-	mutex_lock(&opp_table_lock);
-
 	opp_table = _managed_opp(opp_np);
 	if (opp_table) {
 		/* OPPs are already managed */
 		if (!_add_opp_dev(dev, opp_table))
 			ret = -ENOMEM;
-		goto unlock;
+		goto put_opp_table;
 	}
 
-	opp_table = _add_opp_table(dev);
-	if (!opp_table) {
-		ret = -ENOMEM;
-		goto unlock;
-	}
+	opp_table = dev_pm_opp_get_opp_table(dev);
+	if (!opp_table)
+		return -ENOMEM;
 
 	/* We have opp-table node now, iterate over it and add OPPs */
 	for_each_available_child_of_node(opp_np, np) {
@@ -392,14 +394,15 @@ static int _of_add_opp_table_v2(struct device *dev, struct device_node *opp_np)
 		if (ret) {
 			dev_err(dev, "%s: Failed to add OPP, %d\n", __func__,
 				ret);
-			goto free_table;
+			_dev_pm_opp_remove_table(opp_table, dev, false);
+			goto put_opp_table;
 		}
 	}
 
 	/* There should be one of more OPP defined */
 	if (WARN_ON(!count)) {
 		ret = -ENOENT;
-		goto free_table;
+		goto put_opp_table;
 	}
 
 	opp_table->np = opp_np;
@@ -408,12 +411,8 @@ static int _of_add_opp_table_v2(struct device *dev, struct device_node *opp_np)
 	else
 		opp_table->shared_opp = OPP_TABLE_ACCESS_EXCLUSIVE;
 
-	goto unlock;
-
-free_table:
-	_dev_pm_opp_remove_table(opp_table, dev, false);
-unlock:
-	mutex_unlock(&opp_table_lock);
+put_opp_table:
+	dev_pm_opp_put_opp_table(opp_table);
 
 	return ret;
 }
@@ -442,13 +441,9 @@ static int _of_add_opp_table_v1(struct device *dev)
 		return -EINVAL;
 	}
 
-	mutex_lock(&opp_table_lock);
-
-	opp_table = _add_opp_table(dev);
-	if (!opp_table) {
-		ret = -ENOMEM;
-		goto unlock;
-	}
+	opp_table = dev_pm_opp_get_opp_table(dev);
+	if (!opp_table)
+		return -ENOMEM;
 
 	val = prop->value;
 	while (nr) {
@@ -465,8 +460,7 @@ static int _of_add_opp_table_v1(struct device *dev)
 		nr -= 2;
 	}
 
-unlock:
-	mutex_unlock(&opp_table_lock);
+	dev_pm_opp_put_opp_table(opp_table);
 	return ret;
 }
 
diff --git a/drivers/base/power/opp/opp.h b/drivers/base/power/opp/opp.h
index aae4d8f480ef..a01724363347 100644
--- a/drivers/base/power/opp/opp.h
+++ b/drivers/base/power/opp/opp.h
@@ -196,7 +196,6 @@ struct opp_table {
 /* Routines internal to opp core */
 void _get_opp_table_kref(struct opp_table *opp_table);
 struct opp_table *_find_opp_table(struct device *dev);
-struct opp_table *_add_opp_table(struct device *dev);
 struct opp_device *_add_opp_dev(const struct device *dev, struct opp_table *opp_table);
 void _dev_pm_opp_remove_table(struct opp_table *opp_table, struct device *dev, bool remove_all);
 void _dev_pm_opp_find_and_remove_table(struct device *dev, bool remove_all);
-- 
cgit v1.2.3


From 7034764a1e4a6edbb60914e89aad8384e3fe5d17 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Mon, 23 Jan 2017 10:11:46 +0530
Subject: PM / OPP: Add 'struct kref' to struct dev_pm_opp

Add kref to struct dev_pm_opp for easier accounting of the OPPs.

Note that the OPPs are freed under the opp_table->lock mutex only.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/opp/core.c | 27 ++++++++++++---------------
 drivers/base/power/opp/opp.h  |  3 +++
 include/linux/pm_opp.h        |  3 +++
 3 files changed, 18 insertions(+), 15 deletions(-)

diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c
index ab9499e3ba02..9870ee54d708 100644
--- a/drivers/base/power/opp/core.c
+++ b/drivers/base/power/opp/core.c
@@ -949,20 +949,10 @@ static void _kfree_opp_rcu(struct rcu_head *head)
 	kfree_rcu(opp, rcu_head);
 }
 
-/**
- * _opp_remove()  - Remove an OPP from a table definition
- * @opp_table:	points back to the opp_table struct this opp belongs to
- * @opp:	pointer to the OPP to remove
- *
- * This function removes an opp definition from the opp table.
- *
- * Locking: The internal opp_table and opp structures are RCU protected.
- * It is assumed that the caller holds required mutex for an RCU updater
- * strategy.
- */
-static void _opp_remove(struct opp_table *opp_table, struct dev_pm_opp *opp)
+static void _opp_kref_release(struct kref *kref)
 {
-	mutex_lock(&opp_table->lock);
+	struct dev_pm_opp *opp = container_of(kref, struct dev_pm_opp, kref);
+	struct opp_table *opp_table = opp->opp_table;
 
 	/*
 	 * Notify the changes in the availability of the operable
@@ -977,6 +967,12 @@ static void _opp_remove(struct opp_table *opp_table, struct dev_pm_opp *opp)
 	dev_pm_opp_put_opp_table(opp_table);
 }
 
+void dev_pm_opp_put(struct dev_pm_opp *opp)
+{
+	kref_put_mutex(&opp->kref, _opp_kref_release, &opp->opp_table->lock);
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_put);
+
 /**
  * dev_pm_opp_remove()  - Remove an OPP from OPP table
  * @dev:	device for which we do this operation
@@ -1020,7 +1016,7 @@ void dev_pm_opp_remove(struct device *dev, unsigned long freq)
 		goto unlock;
 	}
 
-	_opp_remove(opp_table, opp);
+	dev_pm_opp_put(opp);
 unlock:
 	mutex_unlock(&opp_table_lock);
 }
@@ -1124,6 +1120,7 @@ int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
 	mutex_unlock(&opp_table->lock);
 
 	new_opp->opp_table = opp_table;
+	kref_init(&new_opp->kref);
 
 	/* Get a reference to the OPP table */
 	_get_opp_table_kref(opp_table);
@@ -1819,7 +1816,7 @@ void _dev_pm_opp_remove_table(struct opp_table *opp_table, struct device *dev,
 		/* Free static OPPs */
 		list_for_each_entry_safe(opp, tmp, &opp_table->opp_list, node) {
 			if (remove_all || !opp->dynamic)
-				_opp_remove(opp_table, opp);
+				dev_pm_opp_put(opp);
 		}
 	} else {
 		_remove_opp_dev(_find_opp_dev(dev, opp_table), opp_table);
diff --git a/drivers/base/power/opp/opp.h b/drivers/base/power/opp/opp.h
index a01724363347..586f36f94e28 100644
--- a/drivers/base/power/opp/opp.h
+++ b/drivers/base/power/opp/opp.h
@@ -16,6 +16,7 @@
 
 #include <linux/device.h>
 #include <linux/kernel.h>
+#include <linux/kref.h>
 #include <linux/list.h>
 #include <linux/limits.h>
 #include <linux/pm_opp.h>
@@ -56,6 +57,7 @@ extern struct list_head opp_tables;
  *		are protected by the opp_table_lock for integrity.
  *		IMPORTANT: the opp nodes should be maintained in increasing
  *		order.
+ * @kref:	for reference count of the OPP.
  * @available:	true/false - marks if this OPP as available or not
  * @dynamic:	not-created from static DT entries.
  * @turbo:	true if turbo (boost) OPP
@@ -73,6 +75,7 @@ extern struct list_head opp_tables;
  */
 struct dev_pm_opp {
 	struct list_head node;
+	struct kref kref;
 
 	bool available;
 	bool dynamic;
diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h
index 99787cbcaab2..731d548657aa 100644
--- a/include/linux/pm_opp.h
+++ b/include/linux/pm_opp.h
@@ -102,6 +102,7 @@ struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
 
 struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev,
 					     unsigned long *freq);
+void dev_pm_opp_put(struct dev_pm_opp *opp);
 
 int dev_pm_opp_add(struct device *dev, unsigned long freq,
 		   unsigned long u_volt);
@@ -193,6 +194,8 @@ static inline struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev,
 	return ERR_PTR(-ENOTSUPP);
 }
 
+static inline void dev_pm_opp_put(struct dev_pm_opp *opp) {}
+
 static inline int dev_pm_opp_add(struct device *dev, unsigned long freq,
 					unsigned long u_volt)
 {
-- 
cgit v1.2.3


From 8a31d9d94297b1ecae3012069d35d78c959693c2 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Mon, 23 Jan 2017 10:11:47 +0530
Subject: PM / OPP: Update OPP users to put reference

This patch updates dev_pm_opp_find_freq_*() routines to get a reference
to the OPPs returned by them.

Also updates the users of dev_pm_opp_find_freq_*() routines to call
dev_pm_opp_put() after they are done using the OPPs.

As it is guaranteed the that OPPs wouldn't get freed while being used,
the RCU read side locking present with the users isn't required anymore.
Drop it as well.

This patch also updates all users of devfreq_recommended_opp() which was
returning an OPP received from the OPP core.

Note that some of the OPP core routines have gained
rcu_read_{lock|unlock}() calls, as those still use RCU specific APIs
within them.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Chanwoo Choi <cw00.choi@samsung.com> [Devfreq]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 arch/arm/mach-omap2/pm.c             |   5 +-
 drivers/base/power/opp/core.c        | 114 +++++++++++++++++++----------------
 drivers/base/power/opp/cpu.c         |  22 ++-----
 drivers/clk/tegra/clk-dfll.c         |  17 ++----
 drivers/cpufreq/exynos5440-cpufreq.c |   5 +-
 drivers/cpufreq/imx6q-cpufreq.c      |  10 +--
 drivers/cpufreq/mt8173-cpufreq.c     |   8 +--
 drivers/cpufreq/omap-cpufreq.c       |   4 +-
 drivers/devfreq/devfreq.c            |  14 ++---
 drivers/devfreq/exynos-bus.c         |  14 ++---
 drivers/devfreq/governor_passive.c   |   4 +-
 drivers/devfreq/rk3399_dmc.c         |  16 ++---
 drivers/devfreq/tegra-devfreq.c      |   4 +-
 drivers/thermal/cpu_cooling.c        |  11 +---
 drivers/thermal/devfreq_cooling.c    |  15 ++---
 15 files changed, 110 insertions(+), 153 deletions(-)

diff --git a/arch/arm/mach-omap2/pm.c b/arch/arm/mach-omap2/pm.c
index 76b0454ddc49..0598630c1778 100644
--- a/arch/arm/mach-omap2/pm.c
+++ b/arch/arm/mach-omap2/pm.c
@@ -130,17 +130,16 @@ static int __init omap2_set_init_voltage(char *vdd_name, char *clk_name,
 	freq = clk_get_rate(clk);
 	clk_put(clk);
 
-	rcu_read_lock();
 	opp = dev_pm_opp_find_freq_ceil(dev, &freq);
 	if (IS_ERR(opp)) {
-		rcu_read_unlock();
 		pr_err("%s: unable to find boot up OPP for vdd_%s\n",
 			__func__, vdd_name);
 		goto exit;
 	}
 
 	bootup_volt = dev_pm_opp_get_voltage(opp);
-	rcu_read_unlock();
+	dev_pm_opp_put(opp);
+
 	if (!bootup_volt) {
 		pr_err("%s: unable to find voltage corresponding to the bootup OPP for vdd_%s\n",
 		       __func__, vdd_name);
diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c
index 9870ee54d708..a6efa818029a 100644
--- a/drivers/base/power/opp/core.c
+++ b/drivers/base/power/opp/core.c
@@ -40,6 +40,8 @@ do {									\
 			 "opp_table_lock protection");			\
 } while (0)
 
+static void dev_pm_opp_get(struct dev_pm_opp *opp);
+
 static struct opp_device *_find_opp_dev(const struct device *dev,
 					struct opp_table *opp_table)
 {
@@ -94,21 +96,13 @@ struct opp_table *_find_opp_table(struct device *dev)
  * 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
- * under RCU lock. The pointer returned by the opp_find_freq family must be
- * used in the same section as the usage of this function with the pointer
- * prior to unlocking with rcu_read_unlock() to maintain the integrity of the
- * pointer.
  */
 unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp)
 {
 	struct dev_pm_opp *tmp_opp;
 	unsigned long v = 0;
 
-	opp_rcu_lockdep_assert();
+	rcu_read_lock();
 
 	tmp_opp = rcu_dereference(opp);
 	if (IS_ERR_OR_NULL(tmp_opp))
@@ -116,6 +110,7 @@ unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp)
 	else
 		v = tmp_opp->supplies[0].u_volt;
 
+	rcu_read_unlock();
 	return v;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_get_voltage);
@@ -126,21 +121,13 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_voltage);
  *
  * Return: frequency in hertz corresponding to the opp, else
  * return 0
- *
- * 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
- * under RCU lock. The pointer returned by the opp_find_freq family must be
- * used in the same section as the usage of this function with the pointer
- * prior to unlocking with rcu_read_unlock() to maintain the integrity of the
- * pointer.
  */
 unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp)
 {
 	struct dev_pm_opp *tmp_opp;
 	unsigned long f = 0;
 
-	opp_rcu_lockdep_assert();
+	rcu_read_lock();
 
 	tmp_opp = rcu_dereference(opp);
 	if (IS_ERR_OR_NULL(tmp_opp) || !tmp_opp->available)
@@ -148,6 +135,7 @@ unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp)
 	else
 		f = tmp_opp->rate;
 
+	rcu_read_unlock();
 	return f;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_get_freq);
@@ -161,20 +149,13 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_freq);
  * quickly. Running on them for longer times may overheat the chip.
  *
  * Return: true if opp is turbo opp, else false.
- *
- * 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
- * under RCU lock. The pointer returned by the opp_find_freq family must be
- * used in the same section as the usage of this function with the pointer
- * prior to unlocking with rcu_read_unlock() to maintain the integrity of the
- * pointer.
  */
 bool dev_pm_opp_is_turbo(struct dev_pm_opp *opp)
 {
 	struct dev_pm_opp *tmp_opp;
+	bool turbo;
 
-	opp_rcu_lockdep_assert();
+	rcu_read_lock();
 
 	tmp_opp = rcu_dereference(opp);
 	if (IS_ERR_OR_NULL(tmp_opp) || !tmp_opp->available) {
@@ -182,7 +163,10 @@ bool dev_pm_opp_is_turbo(struct dev_pm_opp *opp)
 		return false;
 	}
 
-	return tmp_opp->turbo;
+	turbo = tmp_opp->turbo;
+
+	rcu_read_unlock();
+	return turbo;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_is_turbo);
 
@@ -410,11 +394,8 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_opp_count);
  * This provides a mechanism to enable an opp which is not available currently
  * or the opposite as well.
  *
- * Locking: This function must be called under rcu_read_lock(). opp is a rcu
- * protected pointer. The reason for the same is that the opp pointer which is
- * returned will remain valid for use with opp_get_{voltage, freq} only while
- * under the locked area. The pointer returned must be used prior to unlocking
- * with rcu_read_unlock() to maintain the integrity of the pointer.
+ * The callers are required to call dev_pm_opp_put() for the returned OPP after
+ * use.
  */
 struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev,
 					      unsigned long freq,
@@ -423,13 +404,14 @@ struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev,
 	struct opp_table *opp_table;
 	struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE);
 
-	opp_rcu_lockdep_assert();
+	rcu_read_lock();
 
 	opp_table = _find_opp_table(dev);
 	if (IS_ERR(opp_table)) {
 		int r = PTR_ERR(opp_table);
 
 		dev_err(dev, "%s: OPP table not found (%d)\n", __func__, r);
+		rcu_read_unlock();
 		return ERR_PTR(r);
 	}
 
@@ -437,10 +419,15 @@ struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev,
 		if (temp_opp->available == available &&
 				temp_opp->rate == freq) {
 			opp = temp_opp;
+
+			/* Increment the reference count of OPP */
+			dev_pm_opp_get(opp);
 			break;
 		}
 	}
 
+	rcu_read_unlock();
+
 	return opp;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_exact);
@@ -454,6 +441,9 @@ static noinline struct dev_pm_opp *_find_freq_ceil(struct opp_table *opp_table,
 		if (temp_opp->available && temp_opp->rate >= *freq) {
 			opp = temp_opp;
 			*freq = opp->rate;
+
+			/* Increment the reference count of OPP */
+			dev_pm_opp_get(opp);
 			break;
 		}
 	}
@@ -476,29 +466,33 @@ static noinline struct dev_pm_opp *_find_freq_ceil(struct opp_table *opp_table,
  * ERANGE:	no match found for search
  * ENODEV:	if device not found in list of registered devices
  *
- * Locking: This function must be called under rcu_read_lock(). opp is a rcu
- * protected pointer. The reason for the same is that the opp pointer which is
- * returned will remain valid for use with opp_get_{voltage, freq} only while
- * under the locked area. The pointer returned must be used prior to unlocking
- * with rcu_read_unlock() to maintain the integrity of the pointer.
+ * The callers are required to call dev_pm_opp_put() for the returned OPP after
+ * use.
  */
 struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev,
 					     unsigned long *freq)
 {
 	struct opp_table *opp_table;
-
-	opp_rcu_lockdep_assert();
+	struct dev_pm_opp *opp;
 
 	if (!dev || !freq) {
 		dev_err(dev, "%s: Invalid argument freq=%p\n", __func__, freq);
 		return ERR_PTR(-EINVAL);
 	}
 
+	rcu_read_lock();
+
 	opp_table = _find_opp_table(dev);
-	if (IS_ERR(opp_table))
+	if (IS_ERR(opp_table)) {
+		rcu_read_unlock();
 		return ERR_CAST(opp_table);
+	}
+
+	opp = _find_freq_ceil(opp_table, freq);
 
-	return _find_freq_ceil(opp_table, freq);
+	rcu_read_unlock();
+
+	return opp;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_ceil);
 
@@ -517,11 +511,8 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_ceil);
  * ERANGE:	no match found for search
  * ENODEV:	if device not found in list of registered devices
  *
- * Locking: This function must be called under rcu_read_lock(). opp is a rcu
- * protected pointer. The reason for the same is that the opp pointer which is
- * returned will remain valid for use with opp_get_{voltage, freq} only while
- * under the locked area. The pointer returned must be used prior to unlocking
- * with rcu_read_unlock() to maintain the integrity of the pointer.
+ * The callers are required to call dev_pm_opp_put() for the returned OPP after
+ * use.
  */
 struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
 					      unsigned long *freq)
@@ -529,16 +520,18 @@ struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
 	struct opp_table *opp_table;
 	struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE);
 
-	opp_rcu_lockdep_assert();
-
 	if (!dev || !freq) {
 		dev_err(dev, "%s: Invalid argument freq=%p\n", __func__, freq);
 		return ERR_PTR(-EINVAL);
 	}
 
+	rcu_read_lock();
+
 	opp_table = _find_opp_table(dev);
-	if (IS_ERR(opp_table))
+	if (IS_ERR(opp_table)) {
+		rcu_read_unlock();
 		return ERR_CAST(opp_table);
+	}
 
 	list_for_each_entry_rcu(temp_opp, &opp_table->opp_list, node) {
 		if (temp_opp->available) {
@@ -549,6 +542,12 @@ struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
 				opp = temp_opp;
 		}
 	}
+
+	/* Increment the reference count of OPP */
+	if (!IS_ERR(opp))
+		dev_pm_opp_get(opp);
+	rcu_read_unlock();
+
 	if (!IS_ERR(opp))
 		*freq = opp->rate;
 
@@ -736,6 +735,8 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 		ret = PTR_ERR(opp);
 		dev_err(dev, "%s: failed to find OPP for freq %lu (%d)\n",
 			__func__, freq, ret);
+		if (!IS_ERR(old_opp))
+			dev_pm_opp_put(old_opp);
 		rcu_read_unlock();
 		return ret;
 	}
@@ -747,6 +748,9 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 
 	/* Only frequency scaling */
 	if (!regulators) {
+		dev_pm_opp_put(opp);
+		if (!IS_ERR(old_opp))
+			dev_pm_opp_put(old_opp);
 		rcu_read_unlock();
 		return _generic_set_opp_clk_only(dev, clk, old_freq, freq);
 	}
@@ -772,6 +776,9 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 	data->new_opp.rate = freq;
 	memcpy(data->new_opp.supplies, opp->supplies, size);
 
+	dev_pm_opp_put(opp);
+	if (!IS_ERR(old_opp))
+		dev_pm_opp_put(old_opp);
 	rcu_read_unlock();
 
 	return set_opp(data);
@@ -967,6 +974,11 @@ static void _opp_kref_release(struct kref *kref)
 	dev_pm_opp_put_opp_table(opp_table);
 }
 
+static void dev_pm_opp_get(struct dev_pm_opp *opp)
+{
+	kref_get(&opp->kref);
+}
+
 void dev_pm_opp_put(struct dev_pm_opp *opp)
 {
 	kref_put_mutex(&opp->kref, _opp_kref_release, &opp->opp_table->lock);
diff --git a/drivers/base/power/opp/cpu.c b/drivers/base/power/opp/cpu.c
index 8c3434bdb26d..adef788862d5 100644
--- a/drivers/base/power/opp/cpu.c
+++ b/drivers/base/power/opp/cpu.c
@@ -42,11 +42,6 @@
  *
  * WARNING: It is  important for the callers to ensure refreshing their copy of
  * the table if any of the mentioned functions have been invoked in the interim.
- *
- * Locking: The internal opp_table and opp structures are RCU protected.
- * Since we just use the regular accessor functions to access the internal data
- * structures, we use RCU read lock inside this function. As a result, users of
- * this function DONOT need to use explicit locks for invoking.
  */
 int dev_pm_opp_init_cpufreq_table(struct device *dev,
 				  struct cpufreq_frequency_table **table)
@@ -56,19 +51,13 @@ int dev_pm_opp_init_cpufreq_table(struct device *dev,
 	int i, max_opps, ret = 0;
 	unsigned long rate;
 
-	rcu_read_lock();
-
 	max_opps = dev_pm_opp_get_opp_count(dev);
-	if (max_opps <= 0) {
-		ret = max_opps ? max_opps : -ENODATA;
-		goto out;
-	}
+	if (max_opps <= 0)
+		return max_opps ? max_opps : -ENODATA;
 
 	freq_table = kcalloc((max_opps + 1), sizeof(*freq_table), GFP_ATOMIC);
-	if (!freq_table) {
-		ret = -ENOMEM;
-		goto out;
-	}
+	if (!freq_table)
+		return -ENOMEM;
 
 	for (i = 0, rate = 0; i < max_opps; i++, rate++) {
 		/* find next rate */
@@ -83,6 +72,8 @@ int dev_pm_opp_init_cpufreq_table(struct device *dev,
 		/* Is Boost/turbo opp ? */
 		if (dev_pm_opp_is_turbo(opp))
 			freq_table[i].flags = CPUFREQ_BOOST_FREQ;
+
+		dev_pm_opp_put(opp);
 	}
 
 	freq_table[i].driver_data = i;
@@ -91,7 +82,6 @@ int dev_pm_opp_init_cpufreq_table(struct device *dev,
 	*table = &freq_table[0];
 
 out:
-	rcu_read_unlock();
 	if (ret)
 		kfree(freq_table);
 
diff --git a/drivers/clk/tegra/clk-dfll.c b/drivers/clk/tegra/clk-dfll.c
index f010562534eb..2c44aeb0b97c 100644
--- a/drivers/clk/tegra/clk-dfll.c
+++ b/drivers/clk/tegra/clk-dfll.c
@@ -633,16 +633,12 @@ static int find_lut_index_for_rate(struct tegra_dfll *td, unsigned long rate)
 	struct dev_pm_opp *opp;
 	int i, uv;
 
-	rcu_read_lock();
-
 	opp = dev_pm_opp_find_freq_ceil(td->soc->dev, &rate);
-	if (IS_ERR(opp)) {
-		rcu_read_unlock();
+	if (IS_ERR(opp))
 		return PTR_ERR(opp);
-	}
-	uv = dev_pm_opp_get_voltage(opp);
 
-	rcu_read_unlock();
+	uv = dev_pm_opp_get_voltage(opp);
+	dev_pm_opp_put(opp);
 
 	for (i = 0; i < td->i2c_lut_size; i++) {
 		if (regulator_list_voltage(td->vdd_reg, td->i2c_lut[i]) == uv)
@@ -1440,8 +1436,6 @@ static int dfll_build_i2c_lut(struct tegra_dfll *td)
 	struct dev_pm_opp *opp;
 	int lut;
 
-	rcu_read_lock();
-
 	rate = ULONG_MAX;
 	opp = dev_pm_opp_find_freq_floor(td->soc->dev, &rate);
 	if (IS_ERR(opp)) {
@@ -1449,6 +1443,7 @@ static int dfll_build_i2c_lut(struct tegra_dfll *td)
 		goto out;
 	}
 	v_max = dev_pm_opp_get_voltage(opp);
+	dev_pm_opp_put(opp);
 
 	v = td->soc->cvb->min_millivolts * 1000;
 	lut = find_vdd_map_entry_exact(td, v);
@@ -1465,6 +1460,8 @@ static int dfll_build_i2c_lut(struct tegra_dfll *td)
 		if (v_opp <= td->soc->cvb->min_millivolts * 1000)
 			td->dvco_rate_min = dev_pm_opp_get_freq(opp);
 
+		dev_pm_opp_put(opp);
+
 		for (;;) {
 			v += max(1, (v_max - v) / (MAX_DFLL_VOLTAGES - j));
 			if (v >= v_opp)
@@ -1496,8 +1493,6 @@ static int dfll_build_i2c_lut(struct tegra_dfll *td)
 		ret = 0;
 
 out:
-	rcu_read_unlock();
-
 	return ret;
 }
 
diff --git a/drivers/cpufreq/exynos5440-cpufreq.c b/drivers/cpufreq/exynos5440-cpufreq.c
index c0f3373706f4..9180d34cc9fc 100644
--- a/drivers/cpufreq/exynos5440-cpufreq.c
+++ b/drivers/cpufreq/exynos5440-cpufreq.c
@@ -118,12 +118,10 @@ static int init_div_table(void)
 	unsigned int tmp, clk_div, ema_div, freq, volt_id;
 	struct dev_pm_opp *opp;
 
-	rcu_read_lock();
 	cpufreq_for_each_entry(pos, freq_tbl) {
 		opp = dev_pm_opp_find_freq_exact(dvfs_info->dev,
 					pos->frequency * 1000, true);
 		if (IS_ERR(opp)) {
-			rcu_read_unlock();
 			dev_err(dvfs_info->dev,
 				"failed to find valid OPP for %u KHZ\n",
 				pos->frequency);
@@ -140,6 +138,7 @@ static int init_div_table(void)
 
 		/* Calculate EMA */
 		volt_id = dev_pm_opp_get_voltage(opp);
+
 		volt_id = (MAX_VOLTAGE - volt_id) / VOLTAGE_STEP;
 		if (volt_id < PMIC_HIGH_VOLT) {
 			ema_div = (CPUEMA_HIGH << P0_7_CPUEMA_SHIFT) |
@@ -157,9 +156,9 @@ static int init_div_table(void)
 
 		__raw_writel(tmp, dvfs_info->base + XMU_PMU_P0_7 + 4 *
 						(pos - freq_tbl));
+		dev_pm_opp_put(opp);
 	}
 
-	rcu_read_unlock();
 	return 0;
 }
 
diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c
index ef1fa8145419..7719b02e04f5 100644
--- a/drivers/cpufreq/imx6q-cpufreq.c
+++ b/drivers/cpufreq/imx6q-cpufreq.c
@@ -53,16 +53,15 @@ static int imx6q_set_target(struct cpufreq_policy *policy, unsigned int index)
 	freq_hz = new_freq * 1000;
 	old_freq = clk_get_rate(arm_clk) / 1000;
 
-	rcu_read_lock();
 	opp = dev_pm_opp_find_freq_ceil(cpu_dev, &freq_hz);
 	if (IS_ERR(opp)) {
-		rcu_read_unlock();
 		dev_err(cpu_dev, "failed to find OPP for %ld\n", freq_hz);
 		return PTR_ERR(opp);
 	}
 
 	volt = dev_pm_opp_get_voltage(opp);
-	rcu_read_unlock();
+	dev_pm_opp_put(opp);
+
 	volt_old = regulator_get_voltage(arm_reg);
 
 	dev_dbg(cpu_dev, "%u MHz, %ld mV --> %u MHz, %ld mV\n",
@@ -321,14 +320,15 @@ soc_opp_out:
 	 * freq_table initialised from OPP is therefore sorted in the
 	 * same order.
 	 */
-	rcu_read_lock();
 	opp = dev_pm_opp_find_freq_exact(cpu_dev,
 				  freq_table[0].frequency * 1000, true);
 	min_volt = dev_pm_opp_get_voltage(opp);
+	dev_pm_opp_put(opp);
 	opp = dev_pm_opp_find_freq_exact(cpu_dev,
 				  freq_table[--num].frequency * 1000, true);
 	max_volt = dev_pm_opp_get_voltage(opp);
-	rcu_read_unlock();
+	dev_pm_opp_put(opp);
+
 	ret = regulator_set_voltage_time(arm_reg, min_volt, max_volt);
 	if (ret > 0)
 		transition_latency += ret * 1000;
diff --git a/drivers/cpufreq/mt8173-cpufreq.c b/drivers/cpufreq/mt8173-cpufreq.c
index 643f43179df1..ab25b1235a5e 100644
--- a/drivers/cpufreq/mt8173-cpufreq.c
+++ b/drivers/cpufreq/mt8173-cpufreq.c
@@ -232,16 +232,14 @@ static int mtk_cpufreq_set_target(struct cpufreq_policy *policy,
 
 	freq_hz = freq_table[index].frequency * 1000;
 
-	rcu_read_lock();
 	opp = dev_pm_opp_find_freq_ceil(cpu_dev, &freq_hz);
 	if (IS_ERR(opp)) {
-		rcu_read_unlock();
 		pr_err("cpu%d: failed to find OPP for %ld\n",
 		       policy->cpu, freq_hz);
 		return PTR_ERR(opp);
 	}
 	vproc = dev_pm_opp_get_voltage(opp);
-	rcu_read_unlock();
+	dev_pm_opp_put(opp);
 
 	/*
 	 * If the new voltage or the intermediate voltage is higher than the
@@ -411,16 +409,14 @@ static int mtk_cpu_dvfs_info_init(struct mtk_cpu_dvfs_info *info, int cpu)
 
 	/* Search a safe voltage for intermediate frequency. */
 	rate = clk_get_rate(inter_clk);
-	rcu_read_lock();
 	opp = dev_pm_opp_find_freq_ceil(cpu_dev, &rate);
 	if (IS_ERR(opp)) {
-		rcu_read_unlock();
 		pr_err("failed to get intermediate opp for cpu%d\n", cpu);
 		ret = PTR_ERR(opp);
 		goto out_free_opp_table;
 	}
 	info->intermediate_voltage = dev_pm_opp_get_voltage(opp);
-	rcu_read_unlock();
+	dev_pm_opp_put(opp);
 
 	info->cpu_dev = cpu_dev;
 	info->proc_reg = proc_reg;
diff --git a/drivers/cpufreq/omap-cpufreq.c b/drivers/cpufreq/omap-cpufreq.c
index 376e63ca94e8..71e81bbf031b 100644
--- a/drivers/cpufreq/omap-cpufreq.c
+++ b/drivers/cpufreq/omap-cpufreq.c
@@ -63,16 +63,14 @@ static int omap_target(struct cpufreq_policy *policy, unsigned int index)
 	freq = ret;
 
 	if (mpu_reg) {
-		rcu_read_lock();
 		opp = dev_pm_opp_find_freq_ceil(mpu_dev, &freq);
 		if (IS_ERR(opp)) {
-			rcu_read_unlock();
 			dev_err(mpu_dev, "%s: unable to find MPU OPP for %d\n",
 				__func__, new_freq);
 			return -EINVAL;
 		}
 		volt = dev_pm_opp_get_voltage(opp);
-		rcu_read_unlock();
+		dev_pm_opp_put(opp);
 		tol = volt * OPP_TOLERANCE / 100;
 		volt_old = regulator_get_voltage(mpu_reg);
 	}
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index a545c0fee6e1..253525ea17af 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -111,18 +111,16 @@ static void devfreq_set_freq_table(struct devfreq *devfreq)
 		return;
 	}
 
-	rcu_read_lock();
 	for (i = 0, freq = 0; i < profile->max_state; i++, freq++) {
 		opp = dev_pm_opp_find_freq_ceil(devfreq->dev.parent, &freq);
 		if (IS_ERR(opp)) {
 			devm_kfree(devfreq->dev.parent, profile->freq_table);
 			profile->max_state = 0;
-			rcu_read_unlock();
 			return;
 		}
+		dev_pm_opp_put(opp);
 		profile->freq_table[i] = freq;
 	}
-	rcu_read_unlock();
 }
 
 /**
@@ -1112,17 +1110,16 @@ static ssize_t available_frequencies_show(struct device *d,
 	ssize_t count = 0;
 	unsigned long freq = 0;
 
-	rcu_read_lock();
 	do {
 		opp = dev_pm_opp_find_freq_ceil(dev, &freq);
 		if (IS_ERR(opp))
 			break;
 
+		dev_pm_opp_put(opp);
 		count += scnprintf(&buf[count], (PAGE_SIZE - count - 2),
 				   "%lu ", freq);
 		freq++;
 	} while (1);
-	rcu_read_unlock();
 
 	/* Truncate the trailing space */
 	if (count)
@@ -1224,11 +1221,8 @@ subsys_initcall(devfreq_init);
  * @freq:	The frequency given to target function
  * @flags:	Flags handed from devfreq framework.
  *
- * Locking: This function must be called under rcu_read_lock(). opp is a rcu
- * protected pointer. The reason for the same is that the opp pointer which is
- * returned will remain valid for use with opp_get_{voltage, freq} only while
- * under the locked area. The pointer returned must be used prior to unlocking
- * with rcu_read_unlock() to maintain the integrity of the pointer.
+ * The callers are required to call dev_pm_opp_put() for the returned OPP after
+ * use.
  */
 struct dev_pm_opp *devfreq_recommended_opp(struct device *dev,
 					   unsigned long *freq,
diff --git a/drivers/devfreq/exynos-bus.c b/drivers/devfreq/exynos-bus.c
index 9af86f46fbec..c6d850cddd98 100644
--- a/drivers/devfreq/exynos-bus.c
+++ b/drivers/devfreq/exynos-bus.c
@@ -103,18 +103,17 @@ static int exynos_bus_target(struct device *dev, unsigned long *freq, u32 flags)
 	int ret = 0;
 
 	/* Get new opp-bus instance according to new bus clock */
-	rcu_read_lock();
 	new_opp = devfreq_recommended_opp(dev, freq, flags);
 	if (IS_ERR(new_opp)) {
 		dev_err(dev, "failed to get recommended opp instance\n");
-		rcu_read_unlock();
 		return PTR_ERR(new_opp);
 	}
 
 	new_freq = dev_pm_opp_get_freq(new_opp);
 	new_volt = dev_pm_opp_get_voltage(new_opp);
+	dev_pm_opp_put(new_opp);
+
 	old_freq = bus->curr_freq;
-	rcu_read_unlock();
 
 	if (old_freq == new_freq)
 		return 0;
@@ -214,17 +213,16 @@ static int exynos_bus_passive_target(struct device *dev, unsigned long *freq,
 	int ret = 0;
 
 	/* Get new opp-bus instance according to new bus clock */
-	rcu_read_lock();
 	new_opp = devfreq_recommended_opp(dev, freq, flags);
 	if (IS_ERR(new_opp)) {
 		dev_err(dev, "failed to get recommended opp instance\n");
-		rcu_read_unlock();
 		return PTR_ERR(new_opp);
 	}
 
 	new_freq = dev_pm_opp_get_freq(new_opp);
+	dev_pm_opp_put(new_opp);
+
 	old_freq = bus->curr_freq;
-	rcu_read_unlock();
 
 	if (old_freq == new_freq)
 		return 0;
@@ -358,16 +356,14 @@ static int exynos_bus_parse_of(struct device_node *np,
 
 	rate = clk_get_rate(bus->clk);
 
-	rcu_read_lock();
 	opp = devfreq_recommended_opp(dev, &rate, 0);
 	if (IS_ERR(opp)) {
 		dev_err(dev, "failed to find dev_pm_opp\n");
-		rcu_read_unlock();
 		ret = PTR_ERR(opp);
 		goto err_opp;
 	}
 	bus->curr_freq = dev_pm_opp_get_freq(opp);
-	rcu_read_unlock();
+	dev_pm_opp_put(opp);
 
 	return 0;
 
diff --git a/drivers/devfreq/governor_passive.c b/drivers/devfreq/governor_passive.c
index 9ef46e2592c4..bd452236dba4 100644
--- a/drivers/devfreq/governor_passive.c
+++ b/drivers/devfreq/governor_passive.c
@@ -59,14 +59,14 @@ static int devfreq_passive_get_target_freq(struct devfreq *devfreq,
 	 * list of parent device. Because in this case, *freq is temporary
 	 * value which is decided by ondemand governor.
 	 */
-	rcu_read_lock();
 	opp = devfreq_recommended_opp(parent_devfreq->dev.parent, freq, 0);
-	rcu_read_unlock();
 	if (IS_ERR(opp)) {
 		ret = PTR_ERR(opp);
 		goto out;
 	}
 
+	dev_pm_opp_put(opp);
+
 	/*
 	 * Get the OPP table's index of decided freqeuncy by governor
 	 * of parent device.
diff --git a/drivers/devfreq/rk3399_dmc.c b/drivers/devfreq/rk3399_dmc.c
index 27d2f349b53c..40a2499730fc 100644
--- a/drivers/devfreq/rk3399_dmc.c
+++ b/drivers/devfreq/rk3399_dmc.c
@@ -91,17 +91,13 @@ static int rk3399_dmcfreq_target(struct device *dev, unsigned long *freq,
 	unsigned long target_volt, target_rate;
 	int err;
 
-	rcu_read_lock();
 	opp = devfreq_recommended_opp(dev, freq, flags);
-	if (IS_ERR(opp)) {
-		rcu_read_unlock();
+	if (IS_ERR(opp))
 		return PTR_ERR(opp);
-	}
 
 	target_rate = dev_pm_opp_get_freq(opp);
 	target_volt = dev_pm_opp_get_voltage(opp);
-
-	rcu_read_unlock();
+	dev_pm_opp_put(opp);
 
 	if (dmcfreq->rate == target_rate)
 		return 0;
@@ -422,15 +418,13 @@ static int rk3399_dmcfreq_probe(struct platform_device *pdev)
 
 	data->rate = clk_get_rate(data->dmc_clk);
 
-	rcu_read_lock();
 	opp = devfreq_recommended_opp(dev, &data->rate, 0);
-	if (IS_ERR(opp)) {
-		rcu_read_unlock();
+	if (IS_ERR(opp))
 		return PTR_ERR(opp);
-	}
+
 	data->rate = dev_pm_opp_get_freq(opp);
 	data->volt = dev_pm_opp_get_voltage(opp);
-	rcu_read_unlock();
+	dev_pm_opp_put(opp);
 
 	rk3399_devfreq_dmc_profile.initial_freq = data->rate;
 
diff --git a/drivers/devfreq/tegra-devfreq.c b/drivers/devfreq/tegra-devfreq.c
index fe9dce0245bf..214fff96fa4a 100644
--- a/drivers/devfreq/tegra-devfreq.c
+++ b/drivers/devfreq/tegra-devfreq.c
@@ -487,15 +487,13 @@ static int tegra_devfreq_target(struct device *dev, unsigned long *freq,
 	struct dev_pm_opp *opp;
 	unsigned long rate = *freq * KHZ;
 
-	rcu_read_lock();
 	opp = devfreq_recommended_opp(dev, &rate, flags);
 	if (IS_ERR(opp)) {
-		rcu_read_unlock();
 		dev_err(dev, "Failed to find opp for %lu KHz\n", *freq);
 		return PTR_ERR(opp);
 	}
 	rate = dev_pm_opp_get_freq(opp);
-	rcu_read_unlock();
+	dev_pm_opp_put(opp);
 
 	clk_set_min_rate(tegra->emc_clock, rate);
 	clk_set_rate(tegra->emc_clock, 0);
diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c
index 9ce0e9eef923..85fdbf762fa0 100644
--- a/drivers/thermal/cpu_cooling.c
+++ b/drivers/thermal/cpu_cooling.c
@@ -297,8 +297,6 @@ static int build_dyn_power_table(struct cpufreq_cooling_device *cpufreq_device,
 	if (!power_table)
 		return -ENOMEM;
 
-	rcu_read_lock();
-
 	for (freq = 0, i = 0;
 	     opp = dev_pm_opp_find_freq_ceil(dev, &freq), !IS_ERR(opp);
 	     freq++, i++) {
@@ -306,13 +304,13 @@ static int build_dyn_power_table(struct cpufreq_cooling_device *cpufreq_device,
 		u64 power;
 
 		if (i >= num_opps) {
-			rcu_read_unlock();
 			ret = -EAGAIN;
 			goto free_power_table;
 		}
 
 		freq_mhz = freq / 1000000;
 		voltage_mv = dev_pm_opp_get_voltage(opp) / 1000;
+		dev_pm_opp_put(opp);
 
 		/*
 		 * Do the multiplication with MHz and millivolt so as
@@ -328,8 +326,6 @@ static int build_dyn_power_table(struct cpufreq_cooling_device *cpufreq_device,
 		power_table[i].power = power;
 	}
 
-	rcu_read_unlock();
-
 	if (i != num_opps) {
 		ret = PTR_ERR(opp);
 		goto free_power_table;
@@ -433,13 +429,10 @@ static int get_static_power(struct cpufreq_cooling_device *cpufreq_device,
 		return 0;
 	}
 
-	rcu_read_lock();
-
 	opp = dev_pm_opp_find_freq_exact(cpufreq_device->cpu_dev, freq_hz,
 					 true);
 	voltage = dev_pm_opp_get_voltage(opp);
-
-	rcu_read_unlock();
+	dev_pm_opp_put(opp);
 
 	if (voltage == 0) {
 		dev_warn_ratelimited(cpufreq_device->cpu_dev,
diff --git a/drivers/thermal/devfreq_cooling.c b/drivers/thermal/devfreq_cooling.c
index 5a737fd5f1aa..ba7a5cd994dc 100644
--- a/drivers/thermal/devfreq_cooling.c
+++ b/drivers/thermal/devfreq_cooling.c
@@ -113,15 +113,15 @@ static int partition_enable_opps(struct devfreq_cooling_device *dfc,
 		unsigned int freq = dfc->freq_table[i];
 		bool want_enable = i >= cdev_state ? true : false;
 
-		rcu_read_lock();
 		opp = dev_pm_opp_find_freq_exact(dev, freq, !want_enable);
-		rcu_read_unlock();
 
 		if (PTR_ERR(opp) == -ERANGE)
 			continue;
 		else if (IS_ERR(opp))
 			return PTR_ERR(opp);
 
+		dev_pm_opp_put(opp);
+
 		if (want_enable)
 			ret = dev_pm_opp_enable(dev, freq);
 		else
@@ -221,15 +221,12 @@ get_static_power(struct devfreq_cooling_device *dfc, unsigned long freq)
 	if (!dfc->power_ops->get_static_power)
 		return 0;
 
-	rcu_read_lock();
-
 	opp = dev_pm_opp_find_freq_exact(dev, freq, true);
 	if (IS_ERR(opp) && (PTR_ERR(opp) == -ERANGE))
 		opp = dev_pm_opp_find_freq_exact(dev, freq, false);
 
 	voltage = dev_pm_opp_get_voltage(opp) / 1000; /* mV */
-
-	rcu_read_unlock();
+	dev_pm_opp_put(opp);
 
 	if (voltage == 0) {
 		dev_warn_ratelimited(dev,
@@ -412,18 +409,14 @@ static int devfreq_cooling_gen_tables(struct devfreq_cooling_device *dfc)
 		unsigned long power_dyn, voltage;
 		struct dev_pm_opp *opp;
 
-		rcu_read_lock();
-
 		opp = dev_pm_opp_find_freq_floor(dev, &freq);
 		if (IS_ERR(opp)) {
-			rcu_read_unlock();
 			ret = PTR_ERR(opp);
 			goto free_tables;
 		}
 
 		voltage = dev_pm_opp_get_voltage(opp) / 1000; /* mV */
-
-		rcu_read_unlock();
+		dev_pm_opp_put(opp);
 
 		if (dfc->power_ops) {
 			power_dyn = get_dynamic_power(dfc, freq, voltage);
-- 
cgit v1.2.3


From 5b650b388844f26c61c70564865598836d05dcb3 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Mon, 23 Jan 2017 10:11:48 +0530
Subject: PM / OPP: Take kref from _find_opp_table()

Take reference of the OPP table from within _find_opp_table(). Also
update the callers of _find_opp_table() to call
dev_pm_opp_put_opp_table() after they have used the OPP table.

Note that _find_opp_table() increments the reference under the
opp_table_lock.

Now that the OPP table wouldn't get freed until the callers of
_find_opp_table() call dev_pm_opp_put_opp_table(), there is no need to
take the opp_table_lock or rcu_read_lock() around it. Drop them.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/opp/core.c | 191 +++++++++++++++++++-----------------------
 drivers/base/power/opp/cpu.c  |  26 ++----
 2 files changed, 95 insertions(+), 122 deletions(-)

diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c
index a6efa818029a..69452a4bcda7 100644
--- a/drivers/base/power/opp/core.c
+++ b/drivers/base/power/opp/core.c
@@ -54,6 +54,21 @@ static struct opp_device *_find_opp_dev(const struct device *dev,
 	return NULL;
 }
 
+struct opp_table *_find_opp_table_unlocked(struct device *dev)
+{
+	struct opp_table *opp_table;
+
+	list_for_each_entry(opp_table, &opp_tables, node) {
+		if (_find_opp_dev(dev, opp_table)) {
+			_get_opp_table_kref(opp_table);
+
+			return opp_table;
+		}
+	}
+
+	return ERR_PTR(-ENODEV);
+}
+
 /**
  * _find_opp_table() - find opp_table struct using device pointer
  * @dev:	device pointer used to lookup OPP table
@@ -64,28 +79,22 @@ static struct opp_device *_find_opp_dev(const struct device *dev,
  * Return: pointer to 'struct opp_table' if found, otherwise -ENODEV or
  * -EINVAL based on type of error.
  *
- * Locking: For readers, this function must be called under rcu_read_lock().
- * opp_table is a RCU protected pointer, which means that opp_table is valid
- * as long as we are under RCU lock.
- *
- * For Writers, this function must be called with opp_table_lock held.
+ * The callers must call dev_pm_opp_put_opp_table() after the table is used.
  */
 struct opp_table *_find_opp_table(struct device *dev)
 {
 	struct opp_table *opp_table;
 
-	opp_rcu_lockdep_assert();
-
 	if (IS_ERR_OR_NULL(dev)) {
 		pr_err("%s: Invalid parameters\n", __func__);
 		return ERR_PTR(-EINVAL);
 	}
 
-	list_for_each_entry_rcu(opp_table, &opp_tables, node)
-		if (_find_opp_dev(dev, opp_table))
-			return opp_table;
+	mutex_lock(&opp_table_lock);
+	opp_table = _find_opp_table_unlocked(dev);
+	mutex_unlock(&opp_table_lock);
 
-	return ERR_PTR(-ENODEV);
+	return opp_table;
 }
 
 /**
@@ -175,23 +184,20 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_is_turbo);
  * @dev:	device for which we do this operation
  *
  * Return: This function returns the max clock latency in nanoseconds.
- *
- * Locking: This function takes rcu_read_lock().
  */
 unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev)
 {
 	struct opp_table *opp_table;
 	unsigned long clock_latency_ns;
 
-	rcu_read_lock();
-
 	opp_table = _find_opp_table(dev);
 	if (IS_ERR(opp_table))
-		clock_latency_ns = 0;
-	else
-		clock_latency_ns = opp_table->clock_latency_ns_max;
+		return 0;
+
+	clock_latency_ns = opp_table->clock_latency_ns_max;
+
+	dev_pm_opp_put_opp_table(opp_table);
 
-	rcu_read_unlock();
 	return clock_latency_ns;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_get_max_clock_latency);
@@ -201,15 +207,13 @@ 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;
+	if (IS_ERR(opp_table))
+		return 0;
 
-	rcu_read_unlock();
+	count = opp_table->regulator_count;
+
+	dev_pm_opp_put_opp_table(opp_table);
 
 	return count;
 }
@@ -248,13 +252,11 @@ unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev)
 	if (!uV)
 		goto free_regulators;
 
-	rcu_read_lock();
-
 	opp_table = _find_opp_table(dev);
-	if (IS_ERR(opp_table)) {
-		rcu_read_unlock();
+	if (IS_ERR(opp_table))
 		goto free_uV;
-	}
+
+	rcu_read_lock();
 
 	memcpy(regulators, opp_table->regulators, count * sizeof(*regulators));
 
@@ -274,6 +276,7 @@ unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev)
 	}
 
 	rcu_read_unlock();
+	dev_pm_opp_put_opp_table(opp_table);
 
 	/*
 	 * The caller needs to ensure that opp_table (and hence the regulator)
@@ -323,17 +326,15 @@ unsigned long dev_pm_opp_get_suspend_opp_freq(struct device *dev)
 	struct opp_table *opp_table;
 	unsigned long freq = 0;
 
-	rcu_read_lock();
-
 	opp_table = _find_opp_table(dev);
-	if (IS_ERR(opp_table) || !opp_table->suspend_opp ||
-	    !opp_table->suspend_opp->available)
-		goto unlock;
+	if (IS_ERR(opp_table))
+		return 0;
 
-	freq = dev_pm_opp_get_freq(opp_table->suspend_opp);
+	if (opp_table->suspend_opp && opp_table->suspend_opp->available)
+		freq = dev_pm_opp_get_freq(opp_table->suspend_opp);
+
+	dev_pm_opp_put_opp_table(opp_table);
 
-unlock:
-	rcu_read_unlock();
 	return freq;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_get_suspend_opp_freq);
@@ -353,23 +354,24 @@ int dev_pm_opp_get_opp_count(struct device *dev)
 	struct dev_pm_opp *temp_opp;
 	int count = 0;
 
-	rcu_read_lock();
-
 	opp_table = _find_opp_table(dev);
 	if (IS_ERR(opp_table)) {
 		count = PTR_ERR(opp_table);
 		dev_err(dev, "%s: OPP table not found (%d)\n",
 			__func__, count);
-		goto out_unlock;
+		return count;
 	}
 
+	rcu_read_lock();
+
 	list_for_each_entry_rcu(temp_opp, &opp_table->opp_list, node) {
 		if (temp_opp->available)
 			count++;
 	}
 
-out_unlock:
 	rcu_read_unlock();
+	dev_pm_opp_put_opp_table(opp_table);
+
 	return count;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_get_opp_count);
@@ -404,17 +406,16 @@ struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev,
 	struct opp_table *opp_table;
 	struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE);
 
-	rcu_read_lock();
-
 	opp_table = _find_opp_table(dev);
 	if (IS_ERR(opp_table)) {
 		int r = PTR_ERR(opp_table);
 
 		dev_err(dev, "%s: OPP table not found (%d)\n", __func__, r);
-		rcu_read_unlock();
 		return ERR_PTR(r);
 	}
 
+	rcu_read_lock();
+
 	list_for_each_entry_rcu(temp_opp, &opp_table->opp_list, node) {
 		if (temp_opp->available == available &&
 				temp_opp->rate == freq) {
@@ -427,6 +428,7 @@ struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev,
 	}
 
 	rcu_read_unlock();
+	dev_pm_opp_put_opp_table(opp_table);
 
 	return opp;
 }
@@ -480,17 +482,16 @@ struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev,
 		return ERR_PTR(-EINVAL);
 	}
 
-	rcu_read_lock();
-
 	opp_table = _find_opp_table(dev);
-	if (IS_ERR(opp_table)) {
-		rcu_read_unlock();
+	if (IS_ERR(opp_table))
 		return ERR_CAST(opp_table);
-	}
+
+	rcu_read_lock();
 
 	opp = _find_freq_ceil(opp_table, freq);
 
 	rcu_read_unlock();
+	dev_pm_opp_put_opp_table(opp_table);
 
 	return opp;
 }
@@ -525,13 +526,11 @@ struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
 		return ERR_PTR(-EINVAL);
 	}
 
-	rcu_read_lock();
-
 	opp_table = _find_opp_table(dev);
-	if (IS_ERR(opp_table)) {
-		rcu_read_unlock();
+	if (IS_ERR(opp_table))
 		return ERR_CAST(opp_table);
-	}
+
+	rcu_read_lock();
 
 	list_for_each_entry_rcu(temp_opp, &opp_table->opp_list, node) {
 		if (temp_opp->available) {
@@ -547,6 +546,7 @@ struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
 	if (!IS_ERR(opp))
 		dev_pm_opp_get(opp);
 	rcu_read_unlock();
+	dev_pm_opp_put_opp_table(opp_table);
 
 	if (!IS_ERR(opp))
 		*freq = opp->rate;
@@ -564,22 +564,18 @@ static struct clk *_get_opp_clk(struct device *dev)
 	struct opp_table *opp_table;
 	struct clk *clk;
 
-	rcu_read_lock();
-
 	opp_table = _find_opp_table(dev);
 	if (IS_ERR(opp_table)) {
 		dev_err(dev, "%s: device opp doesn't exist\n", __func__);
-		clk = ERR_CAST(opp_table);
-		goto unlock;
+		return ERR_CAST(opp_table);
 	}
 
 	clk = opp_table->clk;
 	if (IS_ERR(clk))
 		dev_err(dev, "%s: No clock available for the device\n",
 			__func__);
+	dev_pm_opp_put_opp_table(opp_table);
 
-unlock:
-	rcu_read_unlock();
 	return clk;
 }
 
@@ -715,15 +711,14 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 		return 0;
 	}
 
-	rcu_read_lock();
-
 	opp_table = _find_opp_table(dev);
 	if (IS_ERR(opp_table)) {
 		dev_err(dev, "%s: device opp doesn't exist\n", __func__);
-		rcu_read_unlock();
 		return PTR_ERR(opp_table);
 	}
 
+	rcu_read_lock();
+
 	old_opp = _find_freq_ceil(opp_table, &old_freq);
 	if (IS_ERR(old_opp)) {
 		dev_err(dev, "%s: failed to find current OPP for freq %lu (%ld)\n",
@@ -738,6 +733,7 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 		if (!IS_ERR(old_opp))
 			dev_pm_opp_put(old_opp);
 		rcu_read_unlock();
+		dev_pm_opp_put_opp_table(opp_table);
 		return ret;
 	}
 
@@ -752,6 +748,7 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 		if (!IS_ERR(old_opp))
 			dev_pm_opp_put(old_opp);
 		rcu_read_unlock();
+		dev_pm_opp_put_opp_table(opp_table);
 		return _generic_set_opp_clk_only(dev, clk, old_freq, freq);
 	}
 
@@ -780,6 +777,7 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 	if (!IS_ERR(old_opp))
 		dev_pm_opp_put(old_opp);
 	rcu_read_unlock();
+	dev_pm_opp_put_opp_table(opp_table);
 
 	return set_opp(data);
 }
@@ -893,11 +891,9 @@ struct opp_table *dev_pm_opp_get_opp_table(struct device *dev)
 	/* Hold our table modification lock here */
 	mutex_lock(&opp_table_lock);
 
-	opp_table = _find_opp_table(dev);
-	if (!IS_ERR(opp_table)) {
-		_get_opp_table_kref(opp_table);
+	opp_table = _find_opp_table_unlocked(dev);
+	if (!IS_ERR(opp_table))
 		goto unlock;
-	}
 
 	opp_table = _allocate_opp_table(dev);
 
@@ -1004,12 +1000,9 @@ void dev_pm_opp_remove(struct device *dev, unsigned long freq)
 	struct opp_table *opp_table;
 	bool found = false;
 
-	/* Hold our table modification lock here */
-	mutex_lock(&opp_table_lock);
-
 	opp_table = _find_opp_table(dev);
 	if (IS_ERR(opp_table))
-		goto unlock;
+		return;
 
 	mutex_lock(&opp_table->lock);
 
@@ -1022,15 +1015,14 @@ void dev_pm_opp_remove(struct device *dev, unsigned long freq)
 
 	mutex_unlock(&opp_table->lock);
 
-	if (!found) {
+	if (found) {
+		dev_pm_opp_put(opp);
+	} else {
 		dev_warn(dev, "%s: Couldn't find OPP with freq: %lu\n",
 			 __func__, freq);
-		goto unlock;
 	}
 
-	dev_pm_opp_put(opp);
-unlock:
-	mutex_unlock(&opp_table_lock);
+	dev_pm_opp_put_opp_table(opp_table);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_remove);
 
@@ -1648,14 +1640,12 @@ static int _opp_set_availability(struct device *dev, unsigned long freq,
 	if (!new_opp)
 		return -ENOMEM;
 
-	mutex_lock(&opp_table_lock);
-
 	/* Find the opp_table */
 	opp_table = _find_opp_table(dev);
 	if (IS_ERR(opp_table)) {
 		r = PTR_ERR(opp_table);
 		dev_warn(dev, "%s: Device OPP not found (%d)\n", __func__, r);
-		goto unlock;
+		goto free_opp;
 	}
 
 	mutex_lock(&opp_table->lock);
@@ -1668,8 +1658,6 @@ static int _opp_set_availability(struct device *dev, unsigned long freq,
 		}
 	}
 
-	mutex_unlock(&opp_table->lock);
-
 	if (IS_ERR(opp)) {
 		r = PTR_ERR(opp);
 		goto unlock;
@@ -1685,7 +1673,6 @@ static int _opp_set_availability(struct device *dev, unsigned long freq,
 	new_opp->available = availability_req;
 
 	list_replace_rcu(&opp->node, &new_opp->node);
-	mutex_unlock(&opp_table_lock);
 	call_srcu(&opp_table->srcu_head.srcu, &opp->rcu_head, _kfree_opp_rcu);
 
 	/* Notify the change of the OPP availability */
@@ -1696,10 +1683,14 @@ static int _opp_set_availability(struct device *dev, unsigned long freq,
 		srcu_notifier_call_chain(&opp_table->srcu_head,
 					 OPP_EVENT_DISABLE, new_opp);
 
+	mutex_unlock(&opp_table->lock);
+	dev_pm_opp_put_opp_table(opp_table);
 	return 0;
 
 unlock:
-	mutex_unlock(&opp_table_lock);
+	mutex_unlock(&opp_table->lock);
+	dev_pm_opp_put_opp_table(opp_table);
+free_opp:
 	kfree(new_opp);
 	return r;
 }
@@ -1767,18 +1758,16 @@ int dev_pm_opp_register_notifier(struct device *dev, struct notifier_block *nb)
 	struct opp_table *opp_table;
 	int ret;
 
-	rcu_read_lock();
-
 	opp_table = _find_opp_table(dev);
-	if (IS_ERR(opp_table)) {
-		ret = PTR_ERR(opp_table);
-		goto unlock;
-	}
+	if (IS_ERR(opp_table))
+		return PTR_ERR(opp_table);
+
+	rcu_read_lock();
 
 	ret = srcu_notifier_chain_register(&opp_table->srcu_head, nb);
 
-unlock:
 	rcu_read_unlock();
+	dev_pm_opp_put_opp_table(opp_table);
 
 	return ret;
 }
@@ -1797,18 +1786,14 @@ int dev_pm_opp_unregister_notifier(struct device *dev,
 	struct opp_table *opp_table;
 	int ret;
 
-	rcu_read_lock();
-
 	opp_table = _find_opp_table(dev);
-	if (IS_ERR(opp_table)) {
-		ret = PTR_ERR(opp_table);
-		goto unlock;
-	}
+	if (IS_ERR(opp_table))
+		return PTR_ERR(opp_table);
 
 	ret = srcu_notifier_chain_unregister(&opp_table->srcu_head, nb);
 
-unlock:
 	rcu_read_unlock();
+	dev_pm_opp_put_opp_table(opp_table);
 
 	return ret;
 }
@@ -1839,9 +1824,6 @@ void _dev_pm_opp_find_and_remove_table(struct device *dev, bool remove_all)
 {
 	struct opp_table *opp_table;
 
-	/* Hold our table modification lock here */
-	mutex_lock(&opp_table_lock);
-
 	/* Check for existing table for 'dev' */
 	opp_table = _find_opp_table(dev);
 	if (IS_ERR(opp_table)) {
@@ -1852,13 +1834,12 @@ void _dev_pm_opp_find_and_remove_table(struct device *dev, bool remove_all)
 			     IS_ERR_OR_NULL(dev) ?
 					"Invalid device" : dev_name(dev),
 			     error);
-		goto unlock;
+		return;
 	}
 
 	_dev_pm_opp_remove_table(opp_table, dev, remove_all);
 
-unlock:
-	mutex_unlock(&opp_table_lock);
+	dev_pm_opp_put_opp_table(opp_table);
 }
 
 /**
diff --git a/drivers/base/power/opp/cpu.c b/drivers/base/power/opp/cpu.c
index adef788862d5..df29f08eecc4 100644
--- a/drivers/base/power/opp/cpu.c
+++ b/drivers/base/power/opp/cpu.c
@@ -174,13 +174,9 @@ int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev,
 	struct device *dev;
 	int cpu, ret = 0;
 
-	mutex_lock(&opp_table_lock);
-
 	opp_table = _find_opp_table(cpu_dev);
-	if (IS_ERR(opp_table)) {
-		ret = PTR_ERR(opp_table);
-		goto unlock;
-	}
+	if (IS_ERR(opp_table))
+		return PTR_ERR(opp_table);
 
 	for_each_cpu(cpu, cpumask) {
 		if (cpu == cpu_dev->id)
@@ -203,8 +199,8 @@ int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev,
 		/* Mark opp-table as multiple CPUs are sharing it now */
 		opp_table->shared_opp = OPP_TABLE_ACCESS_SHARED;
 	}
-unlock:
-	mutex_unlock(&opp_table_lock);
+
+	dev_pm_opp_put_opp_table(opp_table);
 
 	return ret;
 }
@@ -232,17 +228,13 @@ int dev_pm_opp_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask)
 	struct opp_table *opp_table;
 	int ret = 0;
 
-	mutex_lock(&opp_table_lock);
-
 	opp_table = _find_opp_table(cpu_dev);
-	if (IS_ERR(opp_table)) {
-		ret = PTR_ERR(opp_table);
-		goto unlock;
-	}
+	if (IS_ERR(opp_table))
+		return PTR_ERR(opp_table);
 
 	if (opp_table->shared_opp == OPP_TABLE_ACCESS_UNKNOWN) {
 		ret = -EINVAL;
-		goto unlock;
+		goto put_opp_table;
 	}
 
 	cpumask_clear(cpumask);
@@ -254,8 +246,8 @@ int dev_pm_opp_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask)
 		cpumask_set_cpu(cpu_dev->id, cpumask);
 	}
 
-unlock:
-	mutex_unlock(&opp_table_lock);
+put_opp_table:
+	dev_pm_opp_put_opp_table(opp_table);
 
 	return ret;
 }
-- 
cgit v1.2.3


From 052c6f19141dd13f266cc465fde6f38ddc93d5fb Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Mon, 23 Jan 2017 10:11:49 +0530
Subject: PM / OPP: Move away from RCU locking

The RCU locking isn't well suited for the OPP core. The RCU locking fits
better for reader heavy stuff, while the OPP core have at max one or two
readers only at a time.

Over that, it was getting very confusing the way RCU locking was used
with the OPP core. The individual OPPs are mostly well handled, i.e. for
an update a new structure was created and then that replaced the older
one. But the OPP tables were updated directly all the time from various
parts of the core. Though they were mostly used from within RCU locked
region, they didn't had much to do with RCU and were governed by the
mutex instead.

And that mixed with the 'opp_table_lock' has made the core even more
confusing.

Now that we are already managing the OPPs and the OPP tables with kernel
reference infrastructure, we can get rid of RCU locking completely and
simplify the code a lot.

Remove all RCU references from code and comments.

Acquire opp_table->lock while parsing the list of OPPs though.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/opp/core.c | 294 +++++++++++-------------------------------
 drivers/base/power/opp/cpu.c  |  18 ---
 drivers/base/power/opp/of.c   |  40 +-----
 drivers/base/power/opp/opp.h  |  22 +---
 4 files changed, 80 insertions(+), 294 deletions(-)

diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c
index 69452a4bcda7..c40d9868bd97 100644
--- a/drivers/base/power/opp/core.c
+++ b/drivers/base/power/opp/core.c
@@ -32,14 +32,6 @@ LIST_HEAD(opp_tables);
 /* Lock to allow exclusive modification to the device and opp lists */
 DEFINE_MUTEX(opp_table_lock);
 
-#define opp_rcu_lockdep_assert()					\
-do {									\
-	RCU_LOCKDEP_WARN(!rcu_read_lock_held() &&			\
-			 !lockdep_is_held(&opp_table_lock),		\
-			 "Missing rcu_read_lock() or "			\
-			 "opp_table_lock protection");			\
-} while (0)
-
 static void dev_pm_opp_get(struct dev_pm_opp *opp);
 
 static struct opp_device *_find_opp_dev(const struct device *dev,
@@ -73,8 +65,7 @@ struct opp_table *_find_opp_table_unlocked(struct device *dev)
  * _find_opp_table() - find opp_table struct using device pointer
  * @dev:	device pointer used to lookup OPP table
  *
- * Search OPP table for one containing matching device. Does a RCU reader
- * operation to grab the pointer needed.
+ * Search OPP table for one containing matching device.
  *
  * Return: pointer to 'struct opp_table' if found, otherwise -ENODEV or
  * -EINVAL based on type of error.
@@ -108,19 +99,12 @@ struct opp_table *_find_opp_table(struct device *dev)
  */
 unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp)
 {
-	struct dev_pm_opp *tmp_opp;
-	unsigned long v = 0;
-
-	rcu_read_lock();
-
-	tmp_opp = rcu_dereference(opp);
-	if (IS_ERR_OR_NULL(tmp_opp))
+	if (IS_ERR_OR_NULL(opp)) {
 		pr_err("%s: Invalid parameters\n", __func__);
-	else
-		v = tmp_opp->supplies[0].u_volt;
+		return 0;
+	}
 
-	rcu_read_unlock();
-	return v;
+	return opp->supplies[0].u_volt;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_get_voltage);
 
@@ -133,19 +117,12 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_voltage);
  */
 unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp)
 {
-	struct dev_pm_opp *tmp_opp;
-	unsigned long f = 0;
-
-	rcu_read_lock();
-
-	tmp_opp = rcu_dereference(opp);
-	if (IS_ERR_OR_NULL(tmp_opp) || !tmp_opp->available)
+	if (IS_ERR_OR_NULL(opp) || !opp->available) {
 		pr_err("%s: Invalid parameters\n", __func__);
-	else
-		f = tmp_opp->rate;
+		return 0;
+	}
 
-	rcu_read_unlock();
-	return f;
+	return opp->rate;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_get_freq);
 
@@ -161,21 +138,12 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_freq);
  */
 bool dev_pm_opp_is_turbo(struct dev_pm_opp *opp)
 {
-	struct dev_pm_opp *tmp_opp;
-	bool turbo;
-
-	rcu_read_lock();
-
-	tmp_opp = rcu_dereference(opp);
-	if (IS_ERR_OR_NULL(tmp_opp) || !tmp_opp->available) {
+	if (IS_ERR_OR_NULL(opp) || !opp->available) {
 		pr_err("%s: Invalid parameters\n", __func__);
 		return false;
 	}
 
-	turbo = tmp_opp->turbo;
-
-	rcu_read_unlock();
-	return turbo;
+	return opp->turbo;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_is_turbo);
 
@@ -223,8 +191,6 @@ static int _get_regulator_count(struct device *dev)
  * @dev: device for which we do this operation
  *
  * Return: This function returns the max voltage latency in nanoseconds.
- *
- * Locking: This function takes rcu_read_lock().
  */
 unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev)
 {
@@ -256,15 +222,15 @@ unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev)
 	if (IS_ERR(opp_table))
 		goto free_uV;
 
-	rcu_read_lock();
-
 	memcpy(regulators, opp_table->regulators, count * sizeof(*regulators));
 
+	mutex_lock(&opp_table->lock);
+
 	for (i = 0; i < count; i++) {
 		uV[i].min = ~0;
 		uV[i].max = 0;
 
-		list_for_each_entry_rcu(opp, &opp_table->opp_list, node) {
+		list_for_each_entry(opp, &opp_table->opp_list, node) {
 			if (!opp->available)
 				continue;
 
@@ -275,7 +241,7 @@ unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev)
 		}
 	}
 
-	rcu_read_unlock();
+	mutex_unlock(&opp_table->lock);
 	dev_pm_opp_put_opp_table(opp_table);
 
 	/*
@@ -304,8 +270,6 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_max_volt_latency);
  *
  * Return: This function returns the max transition latency, in nanoseconds, to
  * switch from one OPP to other.
- *
- * Locking: This function takes rcu_read_lock().
  */
 unsigned long dev_pm_opp_get_max_transition_latency(struct device *dev)
 {
@@ -345,8 +309,6 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_suspend_opp_freq);
  *
  * Return: This function returns the number of available opps if there are any,
  * else returns 0 if none or the corresponding error value.
- *
- * Locking: This function takes rcu_read_lock().
  */
 int dev_pm_opp_get_opp_count(struct device *dev)
 {
@@ -362,14 +324,14 @@ int dev_pm_opp_get_opp_count(struct device *dev)
 		return count;
 	}
 
-	rcu_read_lock();
+	mutex_lock(&opp_table->lock);
 
-	list_for_each_entry_rcu(temp_opp, &opp_table->opp_list, node) {
+	list_for_each_entry(temp_opp, &opp_table->opp_list, node) {
 		if (temp_opp->available)
 			count++;
 	}
 
-	rcu_read_unlock();
+	mutex_unlock(&opp_table->lock);
 	dev_pm_opp_put_opp_table(opp_table);
 
 	return count;
@@ -414,9 +376,9 @@ struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev,
 		return ERR_PTR(r);
 	}
 
-	rcu_read_lock();
+	mutex_lock(&opp_table->lock);
 
-	list_for_each_entry_rcu(temp_opp, &opp_table->opp_list, node) {
+	list_for_each_entry(temp_opp, &opp_table->opp_list, node) {
 		if (temp_opp->available == available &&
 				temp_opp->rate == freq) {
 			opp = temp_opp;
@@ -427,7 +389,7 @@ struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev,
 		}
 	}
 
-	rcu_read_unlock();
+	mutex_unlock(&opp_table->lock);
 	dev_pm_opp_put_opp_table(opp_table);
 
 	return opp;
@@ -439,7 +401,9 @@ static noinline struct dev_pm_opp *_find_freq_ceil(struct opp_table *opp_table,
 {
 	struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE);
 
-	list_for_each_entry_rcu(temp_opp, &opp_table->opp_list, node) {
+	mutex_lock(&opp_table->lock);
+
+	list_for_each_entry(temp_opp, &opp_table->opp_list, node) {
 		if (temp_opp->available && temp_opp->rate >= *freq) {
 			opp = temp_opp;
 			*freq = opp->rate;
@@ -450,6 +414,8 @@ static noinline struct dev_pm_opp *_find_freq_ceil(struct opp_table *opp_table,
 		}
 	}
 
+	mutex_unlock(&opp_table->lock);
+
 	return opp;
 }
 
@@ -486,11 +452,8 @@ struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev,
 	if (IS_ERR(opp_table))
 		return ERR_CAST(opp_table);
 
-	rcu_read_lock();
-
 	opp = _find_freq_ceil(opp_table, freq);
 
-	rcu_read_unlock();
 	dev_pm_opp_put_opp_table(opp_table);
 
 	return opp;
@@ -530,9 +493,9 @@ struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
 	if (IS_ERR(opp_table))
 		return ERR_CAST(opp_table);
 
-	rcu_read_lock();
+	mutex_lock(&opp_table->lock);
 
-	list_for_each_entry_rcu(temp_opp, &opp_table->opp_list, node) {
+	list_for_each_entry(temp_opp, &opp_table->opp_list, node) {
 		if (temp_opp->available) {
 			/* go to the next node, before choosing prev */
 			if (temp_opp->rate > *freq)
@@ -545,7 +508,7 @@ struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
 	/* Increment the reference count of OPP */
 	if (!IS_ERR(opp))
 		dev_pm_opp_get(opp);
-	rcu_read_unlock();
+	mutex_unlock(&opp_table->lock);
 	dev_pm_opp_put_opp_table(opp_table);
 
 	if (!IS_ERR(opp))
@@ -555,30 +518,6 @@ struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_floor);
 
-/*
- * The caller needs to ensure that opp_table (and hence the clk) isn't freed,
- * while clk returned here is used.
- */
-static struct clk *_get_opp_clk(struct device *dev)
-{
-	struct opp_table *opp_table;
-	struct clk *clk;
-
-	opp_table = _find_opp_table(dev);
-	if (IS_ERR(opp_table)) {
-		dev_err(dev, "%s: device opp doesn't exist\n", __func__);
-		return ERR_CAST(opp_table);
-	}
-
-	clk = opp_table->clk;
-	if (IS_ERR(clk))
-		dev_err(dev, "%s: No clock available for the device\n",
-			__func__);
-	dev_pm_opp_put_opp_table(opp_table);
-
-	return clk;
-}
-
 static int _set_opp_voltage(struct device *dev, struct regulator *reg,
 			    struct dev_pm_opp_supply *supply)
 {
@@ -674,8 +613,6 @@ restore_voltage:
  *
  * This configures the power-supplies and clock source to the levels specified
  * by the OPP corresponding to the target_freq.
- *
- * Locking: This function takes rcu_read_lock().
  */
 int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 {
@@ -694,9 +631,19 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 		return -EINVAL;
 	}
 
-	clk = _get_opp_clk(dev);
-	if (IS_ERR(clk))
-		return PTR_ERR(clk);
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table)) {
+		dev_err(dev, "%s: device opp doesn't exist\n", __func__);
+		return PTR_ERR(opp_table);
+	}
+
+	clk = opp_table->clk;
+	if (IS_ERR(clk)) {
+		dev_err(dev, "%s: No clock available for the device\n",
+			__func__);
+		ret = PTR_ERR(clk);
+		goto put_opp_table;
+	}
 
 	freq = clk_round_rate(clk, target_freq);
 	if ((long)freq <= 0)
@@ -708,17 +655,10 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 	if (old_freq == freq) {
 		dev_dbg(dev, "%s: old/new frequencies (%lu Hz) are same, nothing to do\n",
 			__func__, freq);
-		return 0;
-	}
-
-	opp_table = _find_opp_table(dev);
-	if (IS_ERR(opp_table)) {
-		dev_err(dev, "%s: device opp doesn't exist\n", __func__);
-		return PTR_ERR(opp_table);
+		ret = 0;
+		goto put_opp_table;
 	}
 
-	rcu_read_lock();
-
 	old_opp = _find_freq_ceil(opp_table, &old_freq);
 	if (IS_ERR(old_opp)) {
 		dev_err(dev, "%s: failed to find current OPP for freq %lu (%ld)\n",
@@ -730,11 +670,7 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 		ret = PTR_ERR(opp);
 		dev_err(dev, "%s: failed to find OPP for freq %lu (%d)\n",
 			__func__, freq, ret);
-		if (!IS_ERR(old_opp))
-			dev_pm_opp_put(old_opp);
-		rcu_read_unlock();
-		dev_pm_opp_put_opp_table(opp_table);
-		return ret;
+		goto put_old_opp;
 	}
 
 	dev_dbg(dev, "%s: switching OPP: %lu Hz --> %lu Hz\n", __func__,
@@ -744,12 +680,8 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 
 	/* Only frequency scaling */
 	if (!regulators) {
-		dev_pm_opp_put(opp);
-		if (!IS_ERR(old_opp))
-			dev_pm_opp_put(old_opp);
-		rcu_read_unlock();
-		dev_pm_opp_put_opp_table(opp_table);
-		return _generic_set_opp_clk_only(dev, clk, old_freq, freq);
+		ret = _generic_set_opp_clk_only(dev, clk, old_freq, freq);
+		goto put_opps;
 	}
 
 	if (opp_table->set_opp)
@@ -773,32 +705,26 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 	data->new_opp.rate = freq;
 	memcpy(data->new_opp.supplies, opp->supplies, size);
 
+	ret = set_opp(data);
+
+put_opps:
 	dev_pm_opp_put(opp);
+put_old_opp:
 	if (!IS_ERR(old_opp))
 		dev_pm_opp_put(old_opp);
-	rcu_read_unlock();
+put_opp_table:
 	dev_pm_opp_put_opp_table(opp_table);
-
-	return set_opp(data);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_set_rate);
 
 /* OPP-dev Helpers */
-static void _kfree_opp_dev_rcu(struct rcu_head *head)
-{
-	struct opp_device *opp_dev;
-
-	opp_dev = container_of(head, struct opp_device, rcu_head);
-	kfree_rcu(opp_dev, rcu_head);
-}
-
 static void _remove_opp_dev(struct opp_device *opp_dev,
 			    struct opp_table *opp_table)
 {
 	opp_debug_unregister(opp_dev, opp_table);
 	list_del(&opp_dev->node);
-	call_srcu(&opp_table->srcu_head.srcu, &opp_dev->rcu_head,
-		  _kfree_opp_dev_rcu);
+	kfree(opp_dev);
 }
 
 struct opp_device *_add_opp_dev(const struct device *dev,
@@ -813,7 +739,7 @@ struct opp_device *_add_opp_dev(const struct device *dev,
 
 	/* Initialize opp-dev */
 	opp_dev->dev = dev;
-	list_add_rcu(&opp_dev->node, &opp_table->dev_list);
+	list_add(&opp_dev->node, &opp_table->dev_list);
 
 	/* Create debugfs entries for the opp_table */
 	ret = opp_debug_register(opp_dev, opp_table);
@@ -857,28 +783,16 @@ static struct opp_table *_allocate_opp_table(struct device *dev)
 				ret);
 	}
 
-	srcu_init_notifier_head(&opp_table->srcu_head);
+	BLOCKING_INIT_NOTIFIER_HEAD(&opp_table->head);
 	INIT_LIST_HEAD(&opp_table->opp_list);
 	mutex_init(&opp_table->lock);
 	kref_init(&opp_table->kref);
 
 	/* Secure the device table modification */
-	list_add_rcu(&opp_table->node, &opp_tables);
+	list_add(&opp_table->node, &opp_tables);
 	return opp_table;
 }
 
-/**
- * _kfree_device_rcu() - Free opp_table RCU handler
- * @head:	RCU head
- */
-static void _kfree_device_rcu(struct rcu_head *head)
-{
-	struct opp_table *opp_table = container_of(head, struct opp_table,
-						   rcu_head);
-
-	kfree_rcu(opp_table, rcu_head);
-}
-
 void _get_opp_table_kref(struct opp_table *opp_table)
 {
 	kref_get(&opp_table->kref);
@@ -922,9 +836,8 @@ static void _opp_table_kref_release(struct kref *kref)
 	WARN_ON(!list_empty(&opp_table->dev_list));
 
 	mutex_destroy(&opp_table->lock);
-	list_del_rcu(&opp_table->node);
-	call_srcu(&opp_table->srcu_head.srcu, &opp_table->rcu_head,
-		  _kfree_device_rcu);
+	list_del(&opp_table->node);
+	kfree(opp_table);
 
 	mutex_unlock(&opp_table_lock);
 }
@@ -941,17 +854,6 @@ void _opp_free(struct dev_pm_opp *opp)
 	kfree(opp);
 }
 
-/**
- * _kfree_opp_rcu() - Free OPP RCU handler
- * @head:	RCU head
- */
-static void _kfree_opp_rcu(struct rcu_head *head)
-{
-	struct dev_pm_opp *opp = container_of(head, struct dev_pm_opp, rcu_head);
-
-	kfree_rcu(opp, rcu_head);
-}
-
 static void _opp_kref_release(struct kref *kref)
 {
 	struct dev_pm_opp *opp = container_of(kref, struct dev_pm_opp, kref);
@@ -961,10 +863,10 @@ static void _opp_kref_release(struct kref *kref)
 	 * Notify the changes in the availability of the operable
 	 * frequency/voltage list.
 	 */
-	srcu_notifier_call_chain(&opp_table->srcu_head, OPP_EVENT_REMOVE, opp);
+	blocking_notifier_call_chain(&opp_table->head, OPP_EVENT_REMOVE, opp);
 	opp_debug_remove_one(opp);
-	list_del_rcu(&opp->node);
-	call_srcu(&opp_table->srcu_head.srcu, &opp->rcu_head, _kfree_opp_rcu);
+	list_del(&opp->node);
+	kfree(opp);
 
 	mutex_unlock(&opp_table->lock);
 	dev_pm_opp_put_opp_table(opp_table);
@@ -987,12 +889,6 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_put);
  * @freq:	OPP to remove with matching 'freq'
  *
  * This function removes an opp from the opp table.
- *
- * 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_remove(struct device *dev, unsigned long freq)
 {
@@ -1097,7 +993,7 @@ int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
 	mutex_lock(&opp_table->lock);
 	head = &opp_table->opp_list;
 
-	list_for_each_entry_rcu(opp, &opp_table->opp_list, node) {
+	list_for_each_entry(opp, &opp_table->opp_list, node) {
 		if (new_opp->rate > opp->rate) {
 			head = &opp->node;
 			continue;
@@ -1120,7 +1016,7 @@ int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
 		return ret;
 	}
 
-	list_add_rcu(&new_opp->node, head);
+	list_add(&new_opp->node, head);
 	mutex_unlock(&opp_table->lock);
 
 	new_opp->opp_table = opp_table;
@@ -1158,12 +1054,6 @@ int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
  * NOTE: "dynamic" parameter impacts OPPs added by the dev_pm_opp_of_add_table
  * and freed by dev_pm_opp_of_remove_table.
  *
- * 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.
- *
  * Return:
  * 0		On success OR
  *		Duplicate OPPs (both freq and volt are same) and opp->available
@@ -1203,7 +1093,7 @@ int _opp_add_v1(struct opp_table *opp_table, struct device *dev,
 	 * Notify the changes in the availability of the operable
 	 * frequency/voltage list.
 	 */
-	srcu_notifier_call_chain(&opp_table->srcu_head, OPP_EVENT_ADD, new_opp);
+	blocking_notifier_call_chain(&opp_table->head, OPP_EVENT_ADD, new_opp);
 	return 0;
 
 free_opp:
@@ -1580,12 +1470,6 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_register_put_opp_helper);
  * The opp is made available by default and it can be controlled using
  * dev_pm_opp_enable/disable functions.
  *
- * 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.
- *
  * Return:
  * 0		On success OR
  *		Duplicate OPPs (both freq and volt are same) and opp->available
@@ -1615,18 +1499,12 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_add);
  * @freq:		OPP frequency to modify availability
  * @availability_req:	availability status requested for this opp
  *
- * Set the availability of an OPP with an RCU operation, opp_{enable,disable}
- * share a common logic which is isolated here.
+ * Set the availability of an OPP, opp_{enable,disable} share a common logic
+ * which is isolated here.
  *
  * Return: -EINVAL for bad pointers, -ENOMEM if no memory available for the
  * copy operation, returns 0 if no modification was done OR modification was
  * successful.
- *
- * 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 locking or synchronize_rcu() blocking calls cannot be used.
  */
 static int _opp_set_availability(struct device *dev, unsigned long freq,
 				 bool availability_req)
@@ -1672,16 +1550,16 @@ static int _opp_set_availability(struct device *dev, unsigned long freq,
 	/* plug in new node */
 	new_opp->available = availability_req;
 
-	list_replace_rcu(&opp->node, &new_opp->node);
-	call_srcu(&opp_table->srcu_head.srcu, &opp->rcu_head, _kfree_opp_rcu);
+	list_replace(&opp->node, &new_opp->node);
+	kfree(opp);
 
 	/* Notify the change of the OPP availability */
 	if (availability_req)
-		srcu_notifier_call_chain(&opp_table->srcu_head,
-					 OPP_EVENT_ENABLE, new_opp);
+		blocking_notifier_call_chain(&opp_table->head, OPP_EVENT_ENABLE,
+					     new_opp);
 	else
-		srcu_notifier_call_chain(&opp_table->srcu_head,
-					 OPP_EVENT_DISABLE, new_opp);
+		blocking_notifier_call_chain(&opp_table->head,
+					     OPP_EVENT_DISABLE, new_opp);
 
 	mutex_unlock(&opp_table->lock);
 	dev_pm_opp_put_opp_table(opp_table);
@@ -1704,12 +1582,6 @@ free_opp:
  * corresponding error value. It is meant to be used for users an OPP available
  * after being temporarily made unavailable with dev_pm_opp_disable.
  *
- * Locking: The internal opp_table and opp structures are RCU protected.
- * Hence this function indirectly uses RCU and 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 locking or synchronize_rcu() blocking calls cannot be used.
- *
  * Return: -EINVAL for bad pointers, -ENOMEM if no memory available for the
  * copy operation, returns 0 if no modification was done OR modification was
  * successful.
@@ -1730,12 +1602,6 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_enable);
  * control by users to make this OPP not available until the circumstances are
  * right to make it available again (with a call to dev_pm_opp_enable).
  *
- * Locking: The internal opp_table and opp structures are RCU protected.
- * Hence this function indirectly uses RCU and 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 locking or synchronize_rcu() blocking calls cannot be used.
- *
  * Return: -EINVAL for bad pointers, -ENOMEM if no memory available for the
  * copy operation, returns 0 if no modification was done OR modification was
  * successful.
@@ -1762,11 +1628,8 @@ int dev_pm_opp_register_notifier(struct device *dev, struct notifier_block *nb)
 	if (IS_ERR(opp_table))
 		return PTR_ERR(opp_table);
 
-	rcu_read_lock();
-
-	ret = srcu_notifier_chain_register(&opp_table->srcu_head, nb);
+	ret = blocking_notifier_chain_register(&opp_table->head, nb);
 
-	rcu_read_unlock();
 	dev_pm_opp_put_opp_table(opp_table);
 
 	return ret;
@@ -1790,9 +1653,8 @@ int dev_pm_opp_unregister_notifier(struct device *dev,
 	if (IS_ERR(opp_table))
 		return PTR_ERR(opp_table);
 
-	ret = srcu_notifier_chain_unregister(&opp_table->srcu_head, nb);
+	ret = blocking_notifier_chain_unregister(&opp_table->head, nb);
 
-	rcu_read_unlock();
 	dev_pm_opp_put_opp_table(opp_table);
 
 	return ret;
@@ -1848,12 +1710,6 @@ void _dev_pm_opp_find_and_remove_table(struct device *dev, bool remove_all)
  *
  * Free both OPPs created using static entries present in DT and the
  * dynamically added entries.
- *
- * Locking: The internal opp_table and opp structures are RCU protected.
- * Hence this function indirectly 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_remove_table(struct device *dev)
 {
diff --git a/drivers/base/power/opp/cpu.c b/drivers/base/power/opp/cpu.c
index df29f08eecc4..2d87bc1adf38 100644
--- a/drivers/base/power/opp/cpu.c
+++ b/drivers/base/power/opp/cpu.c
@@ -137,12 +137,6 @@ void _dev_pm_opp_cpumask_remove_table(const struct cpumask *cpumask, bool of)
  * This removes the OPP tables for CPUs present in the @cpumask.
  * This should be used to remove all the OPPs entries associated with
  * the cpus in @cpumask.
- *
- * 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_cpumask_remove_table(const struct cpumask *cpumask)
 {
@@ -159,12 +153,6 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_cpumask_remove_table);
  * @cpumask.
  *
  * Returns -ENODEV if OPP table isn't already present.
- *
- * 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_set_sharing_cpus(struct device *cpu_dev,
 				const struct cpumask *cpumask)
@@ -215,12 +203,6 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_set_sharing_cpus);
  *
  * Returns -ENODEV if OPP table isn't already present and -EINVAL if the OPP
  * table's status is access-unknown.
- *
- * 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_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask)
 {
diff --git a/drivers/base/power/opp/of.c b/drivers/base/power/opp/of.c
index 6a6e6e7846b3..083b79fa0c62 100644
--- a/drivers/base/power/opp/of.c
+++ b/drivers/base/power/opp/of.c
@@ -28,7 +28,7 @@ static struct opp_table *_managed_opp(const struct device_node *np)
 
 	mutex_lock(&opp_table_lock);
 
-	list_for_each_entry_rcu(opp_table, &opp_tables, node) {
+	list_for_each_entry(opp_table, &opp_tables, node) {
 		if (opp_table->np == np) {
 			/*
 			 * Multiple devices can point to the same OPP table and
@@ -235,12 +235,6 @@ free_microvolt:
  * @dev:	device pointer used to lookup OPP table.
  *
  * Free OPPs created using static entries present in DT.
- *
- * Locking: The internal opp_table and opp structures are RCU protected.
- * Hence this function indirectly 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_of_remove_table(struct device *dev)
 {
@@ -269,12 +263,6 @@ static struct device_node *_of_get_opp_desc_node(struct device *dev)
  * opp can be controlled using dev_pm_opp_enable/disable functions and may be
  * removed by dev_pm_opp_remove.
  *
- * 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.
- *
  * Return:
  * 0		On success OR
  *		Duplicate OPPs (both freq and volt are same) and opp->available
@@ -358,7 +346,7 @@ static int _opp_add_static_v2(struct opp_table *opp_table, struct device *dev,
 	 * Notify the changes in the availability of the operable
 	 * frequency/voltage list.
 	 */
-	srcu_notifier_call_chain(&opp_table->srcu_head, OPP_EVENT_ADD, new_opp);
+	blocking_notifier_call_chain(&opp_table->head, OPP_EVENT_ADD, new_opp);
 	return 0;
 
 free_opp:
@@ -470,12 +458,6 @@ static int _of_add_opp_table_v1(struct device *dev)
  *
  * Register the initial OPP table with the OPP library for given device.
  *
- * Locking: The internal opp_table and opp structures are RCU protected.
- * Hence this function indirectly 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.
- *
  * Return:
  * 0		On success OR
  *		Duplicate OPPs (both freq and volt are same) and opp->available
@@ -520,12 +502,6 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_of_add_table);
  *
  * This removes the OPP tables for CPUs present in the @cpumask.
  * This should be used only to remove static entries created from DT.
- *
- * 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_of_cpumask_remove_table(const struct cpumask *cpumask)
 {
@@ -538,12 +514,6 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_of_cpumask_remove_table);
  * @cpumask:	cpumask for which OPP table needs to be added.
  *
  * This adds the OPP tables for CPUs present in the @cpumask.
- *
- * 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_of_cpumask_add_table(const struct cpumask *cpumask)
 {
@@ -591,12 +561,6 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_of_cpumask_add_table);
  * This updates the @cpumask with CPUs that are sharing OPPs with @cpu_dev.
  *
  * Returns -ENOENT if operating-points-v2 isn't present for @cpu_dev.
- *
- * 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_of_get_sharing_cpus(struct device *cpu_dev,
 				   struct cpumask *cpumask)
diff --git a/drivers/base/power/opp/opp.h b/drivers/base/power/opp/opp.h
index 586f36f94e28..166eef990599 100644
--- a/drivers/base/power/opp/opp.h
+++ b/drivers/base/power/opp/opp.h
@@ -20,8 +20,7 @@
 #include <linux/list.h>
 #include <linux/limits.h>
 #include <linux/pm_opp.h>
-#include <linux/rculist.h>
-#include <linux/rcupdate.h>
+#include <linux/notifier.h>
 
 struct clk;
 struct regulator;
@@ -52,9 +51,6 @@ extern struct list_head opp_tables;
  * @node:	opp table node. The nodes are maintained throughout the lifetime
  *		of boot. It is expected only an optimal set of OPPs are
  *		added to the library by the SoC framework.
- *		RCU usage: opp table is traversed with RCU locks. node
- *		modification is possible realtime, hence the modifications
- *		are protected by the opp_table_lock for integrity.
  *		IMPORTANT: the opp nodes should be maintained in increasing
  *		order.
  * @kref:	for reference count of the OPP.
@@ -67,7 +63,6 @@ extern struct list_head opp_tables;
  * @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
- * @rcu_head:	RCU callback head used for deferred freeing
  * @np:		OPP's device node.
  * @dentry:	debugfs dentry pointer (per opp)
  *
@@ -88,7 +83,6 @@ struct dev_pm_opp {
 	unsigned long clock_latency_ns;
 
 	struct opp_table *opp_table;
-	struct rcu_head rcu_head;
 
 	struct device_node *np;
 
@@ -101,7 +95,6 @@ struct dev_pm_opp {
  * struct opp_device - devices managed by 'struct opp_table'
  * @node:	list node
  * @dev:	device to which the struct object belongs
- * @rcu_head:	RCU callback head used for deferred freeing
  * @dentry:	debugfs dentry pointer (per device)
  *
  * This is an internal data structure maintaining the devices that are managed
@@ -110,7 +103,6 @@ struct dev_pm_opp {
 struct opp_device {
 	struct list_head node;
 	const struct device *dev;
-	struct rcu_head rcu_head;
 
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *dentry;
@@ -128,10 +120,7 @@ enum opp_table_access {
  * @node:	table node - contains the devices with OPPs that
  *		have been registered. Nodes once added are not modified in this
  *		table.
- *		RCU usage: nodes are not modified in the table of opp_table,
- *		however addition is possible and is secured by opp_table_lock
- * @srcu_head:	notifier head to notify the OPP availability changes.
- * @rcu_head:	RCU callback head used for deferred freeing
+ * @head:	notifier head to notify the OPP availability changes.
  * @dev_list:	list of devices that share these OPPs
  * @opp_list:	table of opps
  * @kref:	for reference count of the table.
@@ -156,16 +145,11 @@ enum opp_table_access {
  * This is an internal data structure maintaining the link to opps attached to
  * a device. This structure is not meant to be shared to users as it is
  * meant for book keeping and private to OPP library.
- *
- * Because the opp structures can be used from both rcu and srcu readers, we
- * need to wait for the grace period of both of them before freeing any
- * resources. And so we have used kfree_rcu() from within call_srcu() handlers.
  */
 struct opp_table {
 	struct list_head node;
 
-	struct srcu_notifier_head srcu_head;
-	struct rcu_head rcu_head;
+	struct blocking_notifier_head head;
 	struct list_head dev_list;
 	struct list_head opp_list;
 	struct kref kref;
-- 
cgit v1.2.3


From a7f3987ea1af0a4b5a9003d4b22b2260e4afad03 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Mon, 23 Jan 2017 10:11:50 +0530
Subject: PM / OPP: Simplify _opp_set_availability()

As we don't use RCU locking anymore, there is no need to replace an
earlier OPP node with a new one. Just update the existing one.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/opp/core.c | 27 +++++----------------------
 1 file changed, 5 insertions(+), 22 deletions(-)

diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c
index c40d9868bd97..f54ac2484723 100644
--- a/drivers/base/power/opp/core.c
+++ b/drivers/base/power/opp/core.c
@@ -1510,20 +1510,15 @@ static int _opp_set_availability(struct device *dev, unsigned long freq,
 				 bool availability_req)
 {
 	struct opp_table *opp_table;
-	struct dev_pm_opp *new_opp, *tmp_opp, *opp = ERR_PTR(-ENODEV);
+	struct dev_pm_opp *tmp_opp, *opp = ERR_PTR(-ENODEV);
 	int r = 0;
 
-	/* keep the node allocated */
-	new_opp = kmalloc(sizeof(*new_opp), GFP_KERNEL);
-	if (!new_opp)
-		return -ENOMEM;
-
 	/* Find the opp_table */
 	opp_table = _find_opp_table(dev);
 	if (IS_ERR(opp_table)) {
 		r = PTR_ERR(opp_table);
 		dev_warn(dev, "%s: Device OPP not found (%d)\n", __func__, r);
-		goto free_opp;
+		return r;
 	}
 
 	mutex_lock(&opp_table->lock);
@@ -1544,32 +1539,20 @@ static int _opp_set_availability(struct device *dev, unsigned long freq,
 	/* Is update really needed? */
 	if (opp->available == availability_req)
 		goto unlock;
-	/* copy the old data over */
-	*new_opp = *opp;
-
-	/* plug in new node */
-	new_opp->available = availability_req;
 
-	list_replace(&opp->node, &new_opp->node);
-	kfree(opp);
+	opp->available = availability_req;
 
 	/* Notify the change of the OPP availability */
 	if (availability_req)
 		blocking_notifier_call_chain(&opp_table->head, OPP_EVENT_ENABLE,
-					     new_opp);
+					     opp);
 	else
 		blocking_notifier_call_chain(&opp_table->head,
-					     OPP_EVENT_DISABLE, new_opp);
-
-	mutex_unlock(&opp_table->lock);
-	dev_pm_opp_put_opp_table(opp_table);
-	return 0;
+					     OPP_EVENT_DISABLE, opp);
 
 unlock:
 	mutex_unlock(&opp_table->lock);
 	dev_pm_opp_put_opp_table(opp_table);
-free_opp:
-	kfree(new_opp);
 	return r;
 }
 
-- 
cgit v1.2.3


From cdd3e614cfda724826ec8a522022709380b84597 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Mon, 23 Jan 2017 10:11:51 +0530
Subject: PM / OPP: Simplify dev_pm_opp_get_max_volt_latency()

dev_pm_opp_get_max_volt_latency() calls _find_opp_table() two times
effectively.

Merge _get_regulator_count() into dev_pm_opp_get_max_volt_latency() to
avoid that.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/opp/core.c | 34 +++++++++-------------------------
 1 file changed, 9 insertions(+), 25 deletions(-)

diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c
index f54ac2484723..541d32c00cbc 100644
--- a/drivers/base/power/opp/core.c
+++ b/drivers/base/power/opp/core.c
@@ -170,22 +170,6 @@ 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;
-
-	opp_table = _find_opp_table(dev);
-	if (IS_ERR(opp_table))
-		return 0;
-
-	count = opp_table->regulator_count;
-
-	dev_pm_opp_put_opp_table(opp_table);
-
-	return count;
-}
-
 /**
  * dev_pm_opp_get_max_volt_latency() - Get max voltage latency in nanoseconds
  * @dev: device for which we do this operation
@@ -204,24 +188,24 @@ unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev)
 		unsigned long max;
 	} *uV;
 
-	count = _get_regulator_count(dev);
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table))
+		return 0;
+
+	count = opp_table->regulator_count;
 
 	/* Regulator may not be required for the device */
 	if (!count)
-		return 0;
+		goto put_opp_table;
 
 	regulators = kmalloc_array(count, sizeof(*regulators), GFP_KERNEL);
 	if (!regulators)
-		return 0;
+		goto put_opp_table;
 
 	uV = kmalloc_array(count, sizeof(*uV), GFP_KERNEL);
 	if (!uV)
 		goto free_regulators;
 
-	opp_table = _find_opp_table(dev);
-	if (IS_ERR(opp_table))
-		goto free_uV;
-
 	memcpy(regulators, opp_table->regulators, count * sizeof(*regulators));
 
 	mutex_lock(&opp_table->lock);
@@ -242,7 +226,6 @@ unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev)
 	}
 
 	mutex_unlock(&opp_table->lock);
-	dev_pm_opp_put_opp_table(opp_table);
 
 	/*
 	 * The caller needs to ensure that opp_table (and hence the regulator)
@@ -254,10 +237,11 @@ unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev)
 			latency_ns += ret * 1000;
 	}
 
-free_uV:
 	kfree(uV);
 free_regulators:
 	kfree(regulators);
+put_opp_table:
+	dev_pm_opp_put_opp_table(opp_table);
 
 	return latency_ns;
 }
-- 
cgit v1.2.3


From 6185deaac579d5f6b1f811ba83ebcb92c53e94c8 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Mon, 23 Jan 2017 10:11:52 +0530
Subject: PM / OPP: Update Documentation to remove RCU specific bits

Update OPP documentation to remove the RCU specific bits.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/power/opp.txt | 52 ++++++++++++++-------------------------------
 1 file changed, 16 insertions(+), 36 deletions(-)

diff --git a/Documentation/power/opp.txt b/Documentation/power/opp.txt
index c6279c2be47c..0c007e250cd1 100644
--- a/Documentation/power/opp.txt
+++ b/Documentation/power/opp.txt
@@ -79,22 +79,6 @@ dependent subsystems such as cpufreq are left to the discretion of the SoC
 specific framework which uses the OPP library. Similar care needs to be taken
 care to refresh the cpufreq table in cases of these operations.
 
-WARNING on OPP List locking mechanism:
--------------------------------------------------
-OPP library uses RCU for exclusivity. RCU allows the query functions to operate
-in multiple contexts and this synchronization mechanism is optimal for a read
-intensive operations on data structure as the OPP library caters to.
-
-To ensure that the data retrieved are sane, the users such as SoC framework
-should ensure that the section of code operating on OPP queries are locked
-using RCU read locks. The opp_find_freq_{exact,ceil,floor},
-opp_get_{voltage, freq, opp_count} fall into this category.
-
-opp_{add,enable,disable} are updaters which use mutex and implement it's own
-RCU locking mechanisms. These functions should *NOT* be called under RCU locks
-and other contexts that prevent blocking functions in RCU or mutex operations
-from working.
-
 2. Initial OPP List Registration
 ================================
 The SoC implementation calls dev_pm_opp_add function iteratively to add OPPs per
@@ -137,15 +121,18 @@ functions return the matching pointer representing the opp if a match is
 found, else returns error. These errors are expected to be handled by standard
 error checks such as IS_ERR() and appropriate actions taken by the caller.
 
+Callers of these functions shall call dev_pm_opp_put() after they have used the
+OPP. Otherwise the memory for the OPP will never get freed and result in
+memleak.
+
 dev_pm_opp_find_freq_exact - Search for an OPP based on an *exact* frequency and
 	availability. This function is especially useful to enable an OPP which
 	is not available by default.
 	Example: In a case when SoC framework detects a situation where a
 	higher frequency could be made available, it can use this function to
 	find the OPP prior to call the dev_pm_opp_enable to actually make it available.
-	 rcu_read_lock();
 	 opp = dev_pm_opp_find_freq_exact(dev, 1000000000, false);
-	 rcu_read_unlock();
+	 dev_pm_opp_put(opp);
 	 /* dont operate on the pointer.. just do a sanity check.. */
 	 if (IS_ERR(opp)) {
 		pr_err("frequency not disabled!\n");
@@ -163,9 +150,8 @@ dev_pm_opp_find_freq_floor - Search for an available OPP which is *at most* the
 	frequency.
 	Example: To find the highest opp for a device:
 	 freq = ULONG_MAX;
-	 rcu_read_lock();
-	 dev_pm_opp_find_freq_floor(dev, &freq);
-	 rcu_read_unlock();
+	 opp = dev_pm_opp_find_freq_floor(dev, &freq);
+	 dev_pm_opp_put(opp);
 
 dev_pm_opp_find_freq_ceil - Search for an available OPP which is *at least* the
 	provided frequency. This function is useful while searching for a
@@ -173,17 +159,15 @@ dev_pm_opp_find_freq_ceil - Search for an available OPP which is *at least* the
 	frequency.
 	Example 1: To find the lowest opp for a device:
 	 freq = 0;
-	 rcu_read_lock();
-	 dev_pm_opp_find_freq_ceil(dev, &freq);
-	 rcu_read_unlock();
+	 opp = dev_pm_opp_find_freq_ceil(dev, &freq);
+	 dev_pm_opp_put(opp);
 	Example 2: A simplified implementation of a SoC cpufreq_driver->target:
 	 soc_cpufreq_target(..)
 	 {
 		/* Do stuff like policy checks etc. */
 		/* Find the best frequency match for the req */
-		rcu_read_lock();
 		opp = dev_pm_opp_find_freq_ceil(dev, &freq);
-		rcu_read_unlock();
+		dev_pm_opp_put(opp);
 		if (!IS_ERR(opp))
 			soc_switch_to_freq_voltage(freq);
 		else
@@ -208,9 +192,8 @@ dev_pm_opp_enable - Make a OPP available for operation.
 	implementation might choose to do something as follows:
 	 if (cur_temp < temp_low_thresh) {
 		/* Enable 1GHz if it was disabled */
-		rcu_read_lock();
 		opp = dev_pm_opp_find_freq_exact(dev, 1000000000, false);
-		rcu_read_unlock();
+		dev_pm_opp_put(opp);
 		/* just error check */
 		if (!IS_ERR(opp))
 			ret = dev_pm_opp_enable(dev, 1000000000);
@@ -224,9 +207,8 @@ dev_pm_opp_disable - Make an OPP to be not available for operation
 	choose to do something as follows:
 	 if (cur_temp > temp_high_thresh) {
 		/* Disable 1GHz if it was enabled */
-		rcu_read_lock();
 		opp = dev_pm_opp_find_freq_exact(dev, 1000000000, true);
-		rcu_read_unlock();
+		dev_pm_opp_put(opp);
 		/* just error check */
 		if (!IS_ERR(opp))
 			ret = dev_pm_opp_disable(dev, 1000000000);
@@ -249,10 +231,9 @@ dev_pm_opp_get_voltage - Retrieve the voltage represented by the opp pointer.
 	 soc_switch_to_freq_voltage(freq)
 	 {
 		/* do things */
-		rcu_read_lock();
 		opp = dev_pm_opp_find_freq_ceil(dev, &freq);
 		v = dev_pm_opp_get_voltage(opp);
-		rcu_read_unlock();
+		dev_pm_opp_put(opp);
 		if (v)
 			regulator_set_voltage(.., v);
 		/* do other things */
@@ -266,12 +247,12 @@ dev_pm_opp_get_freq - Retrieve the freq represented by the opp pointer.
 	 {
 		/* do things.. */
 		 max_freq = ULONG_MAX;
-		 rcu_read_lock();
 		 max_opp = dev_pm_opp_find_freq_floor(dev,&max_freq);
 		 requested_opp = dev_pm_opp_find_freq_ceil(dev,&freq);
 		 if (!IS_ERR(max_opp) && !IS_ERR(requested_opp))
 			r = soc_test_validity(max_opp, requested_opp);
-		 rcu_read_unlock();
+		 dev_pm_opp_put(max_opp);
+		 dev_pm_opp_put(requested_opp);
 		/* do other things */
 	 }
 	 soc_test_validity(..)
@@ -289,7 +270,6 @@ dev_pm_opp_get_opp_count - Retrieve the number of available opps for a device
 	 soc_notify_coproc_available_frequencies()
 	 {
 		/* Do things */
-		rcu_read_lock();
 		num_available = dev_pm_opp_get_opp_count(dev);
 		speeds = kzalloc(sizeof(u32) * num_available, GFP_KERNEL);
 		/* populate the table in increasing order */
@@ -298,8 +278,8 @@ dev_pm_opp_get_opp_count - Retrieve the number of available opps for a device
 			speeds[i] = freq;
 			freq++;
 			i++;
+			dev_pm_opp_put(opp);
 		}
-		rcu_read_unlock();
 
 		soc_notify_coproc(AVAILABLE_FREQs, speeds, num_available);
 		/* Do other things */
-- 
cgit v1.2.3


From 6ac423973397d17684528e89fbbca49b2ff7bb43 Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Mon, 6 Feb 2017 14:29:55 +0000
Subject: PM / OPP: Make _find_opp_table_unlocked() static

Fixes the following sparse warning:

drivers/base/power/opp/core.c:49:18: warning:
 symbol '_find_opp_table_unlocked' was not declared. Should it be static?

Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Reviewed-by: Stephen Boyd <sboyd@codeaurora.org>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/opp/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c
index 541d32c00cbc..91ec3232d630 100644
--- a/drivers/base/power/opp/core.c
+++ b/drivers/base/power/opp/core.c
@@ -46,7 +46,7 @@ static struct opp_device *_find_opp_dev(const struct device *dev,
 	return NULL;
 }
 
-struct opp_table *_find_opp_table_unlocked(struct device *dev)
+static struct opp_table *_find_opp_table_unlocked(struct device *dev)
 {
 	struct opp_table *opp_table;
 
-- 
cgit v1.2.3


From 0764c604c8128f17fd740ff8b1701d0a1301eb7e Mon Sep 17 00:00:00 2001
From: Dave Gerlach <d-gerlach@ti.com>
Date: Fri, 3 Feb 2017 11:29:26 -0600
Subject: PM / OPP: Expose _of_get_opp_desc_node as dev_pm_opp API

Rename _of_get_opp_desc_node to dev_pm_opp_of_get_opp_desc_node and add it
to include/linux/pm_opp.h to allow other drivers, such as platform OPP
and cpufreq drivers, to make use of it.

Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Dave Gerlach <d-gerlach@ti.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/opp/of.c | 9 +++++----
 include/linux/pm_opp.h      | 6 ++++++
 2 files changed, 11 insertions(+), 4 deletions(-)

diff --git a/drivers/base/power/opp/of.c b/drivers/base/power/opp/of.c
index 083b79fa0c62..779428676f63 100644
--- a/drivers/base/power/opp/of.c
+++ b/drivers/base/power/opp/of.c
@@ -243,7 +243,7 @@ void dev_pm_opp_of_remove_table(struct device *dev)
 EXPORT_SYMBOL_GPL(dev_pm_opp_of_remove_table);
 
 /* Returns opp descriptor node for a device, caller must do of_node_put() */
-static struct device_node *_of_get_opp_desc_node(struct device *dev)
+struct device_node *dev_pm_opp_of_get_opp_desc_node(struct device *dev)
 {
 	/*
 	 * There should be only ONE phandle present in "operating-points-v2"
@@ -252,6 +252,7 @@ static struct device_node *_of_get_opp_desc_node(struct device *dev)
 
 	return of_parse_phandle(dev->of_node, "operating-points-v2", 0);
 }
+EXPORT_SYMBOL_GPL(dev_pm_opp_of_get_opp_desc_node);
 
 /**
  * _opp_add_static_v2() - Allocate static OPPs (As per 'v2' DT bindings)
@@ -478,7 +479,7 @@ int dev_pm_opp_of_add_table(struct device *dev)
 	 * OPPs have two version of bindings now. The older one is deprecated,
 	 * try for the new binding first.
 	 */
-	opp_np = _of_get_opp_desc_node(dev);
+	opp_np = dev_pm_opp_of_get_opp_desc_node(dev);
 	if (!opp_np) {
 		/*
 		 * Try old-deprecated bindings for backward compatibility with
@@ -570,7 +571,7 @@ int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev,
 	int cpu, ret = 0;
 
 	/* Get OPP descriptor node */
-	np = _of_get_opp_desc_node(cpu_dev);
+	np = dev_pm_opp_of_get_opp_desc_node(cpu_dev);
 	if (!np) {
 		dev_dbg(cpu_dev, "%s: Couldn't find opp node.\n", __func__);
 		return -ENOENT;
@@ -595,7 +596,7 @@ int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev,
 		}
 
 		/* Get OPP descriptor node */
-		tmp_np = _of_get_opp_desc_node(tcpu_dev);
+		tmp_np = dev_pm_opp_of_get_opp_desc_node(tcpu_dev);
 		if (!tmp_np) {
 			dev_err(tcpu_dev, "%s: Couldn't find opp node.\n",
 				__func__);
diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h
index 731d548657aa..a6685b3dde26 100644
--- a/include/linux/pm_opp.h
+++ b/include/linux/pm_opp.h
@@ -288,6 +288,7 @@ void dev_pm_opp_of_remove_table(struct device *dev);
 int dev_pm_opp_of_cpumask_add_table(const struct cpumask *cpumask);
 void dev_pm_opp_of_cpumask_remove_table(const struct cpumask *cpumask);
 int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask);
+struct device_node *dev_pm_opp_of_get_opp_desc_node(struct device *dev);
 #else
 static inline int dev_pm_opp_of_add_table(struct device *dev)
 {
@@ -311,6 +312,11 @@ static inline int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev, struct
 {
 	return -ENOTSUPP;
 }
+
+static inline struct device_node *dev_pm_opp_of_get_opp_desc_node(struct device *dev)
+{
+	return NULL;
+}
 #endif
 
 #endif		/* __LINUX_OPP_H__ */
-- 
cgit v1.2.3