Merge branch 'pm-opp' into pm-cpufreq

145 files changed, 4029 insertions, 1556 deletions

diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index 717afcdb5f4a..88dbbb115285 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -231,7 +231,7 @@ int acpi_device_set_power(struct acpi_device *device, int state)
 		dev_warn(&device->dev, "Failed to change power state to %s\n",
 			 acpi_power_state_string(state));
 	} else {
-		device->power.state = state;
+		device->power.state = target_state;
 		ACPI_DEBUG_PRINT((ACPI_DB_INFO,
 				  "Device [%s] transitioned to %s\n",
 				  device->pnp.bus_id,
diff --git a/drivers/base/power/opp.c b/drivers/base/power/opp.c
index 677fb2843553..bb703b5ebaff 100644
--- a/drivers/base/power/opp.c
+++ b/drivers/base/power/opp.c
@@ -11,6 +11,7 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/cpu.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/err.h>
@@ -51,10 +52,17 @@
  *		order.
  * @dynamic:	not-created from static DT entries.
  * @available:	true/false - marks if this OPP as available or not
+ * @turbo:	true if turbo (boost) OPP
  * @rate:	Frequency in hertz
- * @u_volt:	Nominal voltage in microvolts corresponding to this OPP
+ * @u_volt:	Target voltage in microvolts corresponding to this OPP
+ * @u_volt_min:	Minimum voltage in microvolts corresponding to this OPP
+ * @u_volt_max:	Maximum voltage in microvolts corresponding to this OPP
+ * @u_amp:	Maximum current drawn by the device in microamperes
+ * @clock_latency_ns: Latency (in nanoseconds) of switching to this OPP's
+ *		frequency from any other OPP's frequency.
  * @dev_opp:	points back to the device_opp struct this opp belongs to
  * @rcu_head:	RCU callback head used for deferred freeing
+ * @np:		OPP's device node.
  *
  * This structure stores the OPP information for a given device.
  */
@@ -63,11 +71,34 @@ struct dev_pm_opp {
 
 	bool available;
 	bool dynamic;
+	bool turbo;
 	unsigned long rate;
+
 	unsigned long u_volt;
+	unsigned long u_volt_min;
+	unsigned long u_volt_max;
+	unsigned long u_amp;
+	unsigned long clock_latency_ns;
 
 	struct device_opp *dev_opp;
 	struct rcu_head rcu_head;
+
+	struct device_node *np;
+};
+
+/**
+ * struct device_list_opp - devices managed by 'struct device_opp'
+ * @node:	list node
+ * @dev:	device to which the struct object belongs
+ * @rcu_head:	RCU callback head used for deferred freeing
+ *
+ * This is an internal data structure maintaining the list of devices that are
+ * managed by 'struct device_opp'.
+ */
+struct device_list_opp {
+	struct list_head node;
+	const struct device *dev;
+	struct rcu_head rcu_head;
 };
 
 /**
@@ -77,10 +108,12 @@ struct dev_pm_opp {
  *		list.
  *		RCU usage: nodes are not modified in the list of device_opp,
  *		however addition is possible and is secured by dev_opp_list_lock
- * @dev:	device pointer
  * @srcu_head:	notifier head to notify the OPP availability changes.
  * @rcu_head:	RCU callback head used for deferred freeing
+ * @dev_list:	list of devices that share these OPPs
  * @opp_list:	list of opps
+ * @np:		struct device_node pointer for opp's DT node.
+ * @shared_opp: OPP is shared between multiple devices.
  *
  * 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
@@ -93,10 +126,15 @@ struct dev_pm_opp {
 struct device_opp {
 	struct list_head node;
 
-	struct device *dev;
 	struct srcu_notifier_head srcu_head;
 	struct rcu_head rcu_head;
+	struct list_head dev_list;
 	struct list_head opp_list;
+
+	struct device_node *np;
+	unsigned long clock_latency_ns_max;
+	bool shared_opp;
+	struct dev_pm_opp *suspend_opp;
 };
 
 /*
@@ -116,6 +154,38 @@ do {									\
 			   "dev_opp_list_lock protection");		\
 } while (0)
 
+static struct device_list_opp *_find_list_dev(const struct device *dev,
+					      struct device_opp *dev_opp)
+{
+	struct device_list_opp *list_dev;
+
+	list_for_each_entry(list_dev, &dev_opp->dev_list, node)
+		if (list_dev->dev == dev)
+			return list_dev;
+
+	return NULL;
+}
+
+static struct device_opp *_managed_opp(const struct device_node *np)
+{
+	struct device_opp *dev_opp;
+
+	list_for_each_entry_rcu(dev_opp, &dev_opp_list, node) {
+		if (dev_opp->np == np) {
+			/*
+			 * Multiple devices can point to the same OPP table and
+			 * so will have same node-pointer, np.
+			 *
+			 * But the OPPs will be considered as shared only if the
+			 * OPP table contains a "opp-shared" property.
+			 */
+			return dev_opp->shared_opp ? dev_opp : NULL;
+		}
+	}
+
+	return NULL;
+}
+
 /**
  * _find_device_opp() - find device_opp struct using device pointer
  * @dev:	device pointer used to lookup device OPPs
@@ -132,21 +202,18 @@ do {									\
  */
 static struct device_opp *_find_device_opp(struct device *dev)
 {
-	struct device_opp *tmp_dev_opp, *dev_opp = ERR_PTR(-ENODEV);
+	struct device_opp *dev_opp;
 
-	if (unlikely(IS_ERR_OR_NULL(dev))) {
+	if (IS_ERR_OR_NULL(dev)) {
 		pr_err("%s: Invalid parameters\n", __func__);
 		return ERR_PTR(-EINVAL);
 	}
 
-	list_for_each_entry_rcu(tmp_dev_opp, &dev_opp_list, node) {
-		if (tmp_dev_opp->dev == dev) {
-			dev_opp = tmp_dev_opp;
-			break;
-		}
-	}
+	list_for_each_entry_rcu(dev_opp, &dev_opp_list, node)
+		if (_find_list_dev(dev, dev_opp))
+			return dev_opp;
 
-	return dev_opp;
+	return ERR_PTR(-ENODEV);
 }
 
 /**
@@ -172,7 +239,7 @@ unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp)
 	opp_rcu_lockdep_assert();
 
 	tmp_opp = rcu_dereference(opp);
-	if (unlikely(IS_ERR_OR_NULL(tmp_opp)) || !tmp_opp->available)
+	if (IS_ERR_OR_NULL(tmp_opp) || !tmp_opp->available)
 		pr_err("%s: Invalid parameters\n", __func__);
 	else
 		v = tmp_opp->u_volt;
@@ -204,7 +271,7 @@ unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp)
 	opp_rcu_lockdep_assert();
 
 	tmp_opp = rcu_dereference(opp);
-	if (unlikely(IS_ERR_OR_NULL(tmp_opp)) || !tmp_opp->available)
+	if (IS_ERR_OR_NULL(tmp_opp) || !tmp_opp->available)
 		pr_err("%s: Invalid parameters\n", __func__);
 	else
 		f = tmp_opp->rate;
@@ -214,6 +281,66 @@ unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp)
 EXPORT_SYMBOL_GPL(dev_pm_opp_get_freq);
 
 /**
+ * dev_pm_opp_is_turbo() - Returns if opp is turbo OPP or not
+ * @opp: opp for which turbo mode is being verified
+ *
+ * Turbo OPPs are not for normal use, and can be enabled (under certain
+ * conditions) for short duration of times to finish high throughput work
+ * 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;
+
+	opp_rcu_lockdep_assert();
+
+	tmp_opp = rcu_dereference(opp);
+	if (IS_ERR_OR_NULL(tmp_opp) || !tmp_opp->available) {
+		pr_err("%s: Invalid parameters\n", __func__);
+		return false;
+	}
+
+	return tmp_opp->turbo;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_is_turbo);
+
+/**
+ * dev_pm_opp_get_max_clock_latency() - Get max clock latency in nanoseconds
+ * @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 device_opp *dev_opp;
+	unsigned long clock_latency_ns;
+
+	rcu_read_lock();
+
+	dev_opp = _find_device_opp(dev);
+	if (IS_ERR(dev_opp))
+		clock_latency_ns = 0;
+	else
+		clock_latency_ns = dev_opp->clock_latency_ns_max;
+
+	rcu_read_unlock();
+	return clock_latency_ns;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_get_max_clock_latency);
+
+/**
  * dev_pm_opp_get_opp_count() - Get number of opps available in the opp list
  * @dev:	device for which we do this operation
  *
@@ -407,18 +534,57 @@ struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_floor);
 
+/* List-dev Helpers */
+static void _kfree_list_dev_rcu(struct rcu_head *head)
+{
+	struct device_list_opp *list_dev;
+
+	list_dev = container_of(head, struct device_list_opp, rcu_head);
+	kfree_rcu(list_dev, rcu_head);
+}
+
+static void _remove_list_dev(struct device_list_opp *list_dev,
+			     struct device_opp *dev_opp)
+{
+	list_del(&list_dev->node);
+	call_srcu(&dev_opp->srcu_head.srcu, &list_dev->rcu_head,
+		  _kfree_list_dev_rcu);
+}
+
+static struct device_list_opp *_add_list_dev(const struct device *dev,
+					     struct device_opp *dev_opp)
+{
+	struct device_list_opp *list_dev;
+
+	list_dev = kzalloc(sizeof(*list_dev), GFP_KERNEL);
+	if (!list_dev)
+		return NULL;
+
+	/* Initialize list-dev */
+	list_dev->dev = dev;
+	list_add_rcu(&list_dev->node, &dev_opp->dev_list);
+
+	return list_dev;
+}
+
 /**
- * _add_device_opp() - Allocate a new device OPP table
+ * _add_device_opp() - Find device OPP table or allocate a new one
  * @dev:	device for which we do this operation
  *
- * New device node which uses OPPs - used when multiple devices with OPP tables
- * are maintained.
+ * 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 device_opp pointer if success, else NULL.
  */
 static struct device_opp *_add_device_opp(struct device *dev)
 {
 	struct device_opp *dev_opp;
+	struct device_list_opp *list_dev;
+
+	/* Check for existing list for 'dev' first */
+	dev_opp = _find_device_opp(dev);
+	if (!IS_ERR(dev_opp))
+		return dev_opp;
 
 	/*
 	 * Allocate a new device OPP table. In the infrequent case where a new
@@ -428,7 +594,14 @@ static struct device_opp *_add_device_opp(struct device *dev)
 	if (!dev_opp)
 		return NULL;
 
-	dev_opp->dev = dev;
+	INIT_LIST_HEAD(&dev_opp->dev_list);
+
+	list_dev = _add_list_dev(dev, dev_opp);
+	if (!list_dev) {
+		kfree(dev_opp);
+		return NULL;
+	}
+
 	srcu_init_notifier_head(&dev_opp->srcu_head);
 	INIT_LIST_HEAD(&dev_opp->opp_list);
 
@@ -438,6 +611,185 @@ static struct device_opp *_add_device_opp(struct device *dev)
 }
 
 /**
+ * _kfree_device_rcu() - Free device_opp RCU handler
+ * @head:	RCU head
+ */
+static void _kfree_device_rcu(struct rcu_head *head)
+{
+	struct device_opp *device_opp = container_of(head, struct device_opp, rcu_head);
+
+	kfree_rcu(device_opp, rcu_head);
+}
+
+/**
+ * _remove_device_opp() - Removes a device OPP table
+ * @dev_opp: device OPP table to be removed.
+ *
+ * Removes/frees device OPP table it it doesn't contain any OPPs.
+ */
+static void _remove_device_opp(struct device_opp *dev_opp)
+{
+	struct device_list_opp *list_dev;
+
+	if (!list_empty(&dev_opp->opp_list))
+		return;
+
+	list_dev = list_first_entry(&dev_opp->dev_list, struct device_list_opp,
+				    node);
+
+	_remove_list_dev(list_dev, dev_opp);
+
+	/* dev_list must be empty now */
+	WARN_ON(!list_empty(&dev_opp->dev_list));
+
+	list_del_rcu(&dev_opp->node);
+	call_srcu(&dev_opp->srcu_head.srcu, &dev_opp->rcu_head,
+		  _kfree_device_rcu);
+}
+
+/**
+ * _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);
+}
+
+/**
+ * _opp_remove()  - Remove an OPP from a table definition
+ * @dev_opp:	points back to the device_opp 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 list.
+ *
+ * Locking: The internal device_opp 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 device_opp *dev_opp,
+			struct dev_pm_opp *opp, bool notify)
+{
+	/*
+	 * Notify the changes in the availability of the operable
+	 * frequency/voltage list.
+	 */
+	if (notify)
+		srcu_notifier_call_chain(&dev_opp->srcu_head, OPP_EVENT_REMOVE, opp);
+	list_del_rcu(&opp->node);
+	call_srcu(&dev_opp->srcu_head.srcu, &opp->rcu_head, _kfree_opp_rcu);
+
+	_remove_device_opp(dev_opp);
+}
+
+/**
+ * dev_pm_opp_remove()  - Remove an OPP from OPP list
+ * @dev:	device for which we do this operation
+ * @freq:	OPP to remove with matching 'freq'
+ *
+ * This function removes an opp from the opp list.
+ *
+ * Locking: The internal device_opp 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)
+{
+	struct dev_pm_opp *opp;
+	struct device_opp *dev_opp;
+	bool found = false;
+
+	/* Hold our list modification lock here */
+	mutex_lock(&dev_opp_list_lock);
+
+	dev_opp = _find_device_opp(dev);
+	if (IS_ERR(dev_opp))
+		goto unlock;
+
+	list_for_each_entry(opp, &dev_opp->opp_list, node) {
+		if (opp->rate == freq) {
+			found = true;
+			break;
+		}
+	}
+
+	if (!found) {
+		dev_warn(dev, "%s: Couldn't find OPP with freq: %lu\n",
+			 __func__, freq);
+		goto unlock;
+	}
+
+	_opp_remove(dev_opp, opp, true);
+unlock:
+	mutex_unlock(&dev_opp_list_lock);
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_remove);
+
+static struct dev_pm_opp *_allocate_opp(struct device *dev,
+					struct device_opp **dev_opp)
+{
+	struct dev_pm_opp *opp;
+
+	/* allocate new OPP node */
+	opp = kzalloc(sizeof(*opp), GFP_KERNEL);
+	if (!opp)
+		return NULL;
+
+	INIT_LIST_HEAD(&opp->node);
+
+	*dev_opp = _add_device_opp(dev);
+	if (!*dev_opp) {
+		kfree(opp);
+		return NULL;
+	}
+
+	return opp;
+}
+
+static int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
+		    struct device_opp *dev_opp)
+{
+	struct dev_pm_opp *opp;
+	struct list_head *head = &dev_opp->opp_list;
+
+	/*
+	 * Insert new OPP in order of increasing frequency and discard if
+	 * already present.
+	 *
+	 * Need to use &dev_opp->opp_list in the condition part of the 'for'
+	 * loop, don't replace it with head otherwise it will become an infinite
+	 * loop.
+	 */
+	list_for_each_entry_rcu(opp, &dev_opp->opp_list, node) {
+		if (new_opp->rate > opp->rate) {
+			head = &opp->node;
+			continue;
+		}
+
+		if (new_opp->rate < opp->rate)
+			break;
+
+		/* Duplicate OPPs */
+		dev_warn(dev, "%s: duplicate OPPs detected. Existing: freq: %lu, volt: %lu, enabled: %d. New: freq: %lu, volt: %lu, enabled: %d\n",
+			 __func__, opp->rate, opp->u_volt, opp->available,
+			 new_opp->rate, new_opp->u_volt, new_opp->available);
+
+		return opp->available && new_opp->u_volt == opp->u_volt ?
+			0 : -EEXIST;
+	}
+
+	new_opp->dev_opp = dev_opp;
+	list_add_rcu(&new_opp->node, head);
+
+	return 0;
+}
+
+/**
  * _opp_add_dynamic() - Allocate a dynamic OPP.
  * @dev:	device for which we do this operation
  * @freq:	Frequency in Hz for this OPP
@@ -467,64 +819,29 @@ static struct device_opp *_add_device_opp(struct device *dev)
 static int _opp_add_dynamic(struct device *dev, unsigned long freq,
 			    long u_volt, bool dynamic)
 {
-	struct device_opp *dev_opp = NULL;
-	struct dev_pm_opp *opp, *new_opp;
-	struct list_head *head;
+	struct device_opp *dev_opp;
+	struct dev_pm_opp *new_opp;
 	int ret;
 
-	/* allocate new OPP node */
-	new_opp = kzalloc(sizeof(*new_opp), GFP_KERNEL);
-	if (!new_opp)
-		return -ENOMEM;
-
 	/* Hold our list modification lock here */
 	mutex_lock(&dev_opp_list_lock);
 
+	new_opp = _allocate_opp(dev, &dev_opp);
+	if (!new_opp) {
+		ret = -ENOMEM;
+		goto unlock;
+	}
+
 	/* populate the opp table */
 	new_opp->rate = freq;
 	new_opp->u_volt = u_volt;
 	new_opp->available = true;
 	new_opp->dynamic = dynamic;
 
-	/* Check for existing list for 'dev' */
-	dev_opp = _find_device_opp(dev);
-	if (IS_ERR(dev_opp)) {
-		dev_opp = _add_device_opp(dev);
-		if (!dev_opp) {
-			ret = -ENOMEM;
-			goto free_opp;
-		}
-
-		head = &dev_opp->opp_list;
-		goto list_add;
-	}
-
-	/*
-	 * Insert new OPP in order of increasing frequency
-	 * and discard if already present
-	 */
-	head = &dev_opp->opp_list;
-	list_for_each_entry_rcu(opp, &dev_opp->opp_list, node) {
-		if (new_opp->rate <= opp->rate)
-			break;
-		else
-			head = &opp->node;
-	}
-
-	/* Duplicate OPPs ? */
-	if (new_opp->rate == opp->rate) {
-		ret = opp->available && new_opp->u_volt == opp->u_volt ?
-			0 : -EEXIST;
-
-		dev_warn(dev, "%s: duplicate OPPs detected. Existing: freq: %lu, volt: %lu, enabled: %d. New: freq: %lu, volt: %lu, enabled: %d\n",
-			 __func__, opp->rate, opp->u_volt, opp->available,
-			 new_opp->rate, new_opp->u_volt, new_opp->available);
+	ret = _opp_add(dev, new_opp, dev_opp);
+	if (ret)
 		goto free_opp;
-	}
 
-list_add:
-	new_opp->dev_opp = dev_opp;
-	list_add_rcu(&new_opp->node, head);
 	mutex_unlock(&dev_opp_list_lock);
 
 	/*
@@ -535,20 +852,52 @@ list_add:
 	return 0;
 
 free_opp:
+	_opp_remove(dev_opp, new_opp, false);
+unlock:
 	mutex_unlock(&dev_opp_list_lock);
-	kfree(new_opp);
 	return ret;
 }
 
+/* TODO: Support multiple regulators */
+static int opp_get_microvolt(struct dev_pm_opp *opp, struct device *dev)
+{
+	u32 microvolt[3] = {0};
+	int count, ret;
+
+	count = of_property_count_u32_elems(opp->np, "opp-microvolt");
+	if (!count)
+		return 0;
+
+	/* There can be one or three elements here */
+	if (count != 1 && count != 3) {
+		dev_err(dev, "%s: Invalid number of elements in opp-microvolt property (%d)\n",
+			__func__, count);
+		return -EINVAL;
+	}
+
+	ret = of_property_read_u32_array(opp->np, "opp-microvolt", microvolt,
+					 count);
+	if (ret) {
+		dev_err(dev, "%s: error parsing opp-microvolt: %d\n", __func__,
+			ret);
+		return -EINVAL;
+	}
+
+	opp->u_volt = microvolt[0];
+	opp->u_volt_min = microvolt[1];
+	opp->u_volt_max = microvolt[2];
+
+	return 0;
+}
+
 /**
- * dev_pm_opp_add()  - Add an OPP table from a table definitions
+ * _opp_add_static_v2() - Allocate static OPPs (As per 'v2' DT bindings)
  * @dev:	device for which we do this operation
- * @freq:	Frequency in Hz for this OPP
- * @u_volt:	Voltage in uVolts for this OPP
+ * @np:		device node
  *
- * This function adds an opp definition to the opp list and returns status.
- * The opp is made available by default and it can be controlled using
- * dev_pm_opp_enable/disable functions.
+ * This function adds an opp definition to the opp list and returns status. The
+ * opp can be controlled using dev_pm_opp_enable/disable functions and may be
+ * removed by dev_pm_opp_remove.
  *
  * Locking: The internal device_opp and opp structures are RCU protected.
  * Hence this function internally uses RCU updater strategy with mutex locks
@@ -562,108 +911,119 @@ free_opp:
  * -EEXIST	Freq are same and volt are different OR
  *		Duplicate OPPs (both freq and volt are same) and !opp->available
  * -ENOMEM	Memory allocation failure
+ * -EINVAL	Failed parsing the OPP node
  */
-int dev_pm_opp_add(struct device *dev, unsigned long freq, unsigned long u_volt)
+static int _opp_add_static_v2(struct device *dev, struct device_node *np)
 {
-	return _opp_add_dynamic(dev, freq, u_volt, true);
-}
-EXPORT_SYMBOL_GPL(dev_pm_opp_add);
+	struct device_opp *dev_opp;
+	struct dev_pm_opp *new_opp;
+	u64 rate;
+	u32 val;
+	int ret;
 
-/**
- * _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);
+	/* Hold our list modification lock here */
+	mutex_lock(&dev_opp_list_lock);
 
-	kfree_rcu(opp, rcu_head);
-}
+	new_opp = _allocate_opp(dev, &dev_opp);
+	if (!new_opp) {
+		ret = -ENOMEM;
+		goto unlock;
+	}
 
-/**
- * _kfree_device_rcu() - Free device_opp RCU handler
- * @head:	RCU head
- */
-static void _kfree_device_rcu(struct rcu_head *head)
-{
-	struct device_opp *device_opp = container_of(head, struct device_opp, rcu_head);
+	ret = of_property_read_u64(np, "opp-hz", &rate);
+	if (ret < 0) {
+		dev_err(dev, "%s: opp-hz not found\n", __func__);
+		goto free_opp;
+	}
 
-	kfree_rcu(device_opp, rcu_head);
-}
+	/*
+	 * Rate is defined as an unsigned long in clk API, and so casting
+	 * explicitly to its type. Must be fixed once rate is 64 bit
+	 * guaranteed in clk API.
+	 */
+	new_opp->rate = (unsigned long)rate;
+	new_opp->turbo = of_property_read_bool(np, "turbo-mode");
+
+	new_opp->np = np;
+	new_opp->dynamic = false;
+	new_opp->available = true;
+
+	if (!of_property_read_u32(np, "clock-latency-ns", &val))
+		new_opp->clock_latency_ns = val;
+
+	ret = opp_get_microvolt(new_opp, dev);
+	if (ret)
+		goto free_opp;
+
+	if (!of_property_read_u32(new_opp->np, "opp-microamp", &val))
+		new_opp->u_amp = val;
+
+	ret = _opp_add(dev, new_opp, dev_opp);
+	if (ret)
+		goto free_opp;
+
+	/* OPP to select on device suspend */
+	if (of_property_read_bool(np, "opp-suspend")) {
+		if (dev_opp->suspend_opp)
+			dev_warn(dev, "%s: Multiple suspend OPPs found (%lu %lu)\n",
+				 __func__, dev_opp->suspend_opp->rate,
+				 new_opp->rate);
+		else
+			dev_opp->suspend_opp = new_opp;
+	}
+
+	if (new_opp->clock_latency_ns > dev_opp->clock_latency_ns_max)
+		dev_opp->clock_latency_ns_max = new_opp->clock_latency_ns;
+
+	mutex_unlock(&dev_opp_list_lock);
+
+	pr_debug("%s: turbo:%d rate:%lu uv:%lu uvmin:%lu uvmax:%lu latency:%lu\n",
+		 __func__, new_opp->turbo, new_opp->rate, new_opp->u_volt,
+		 new_opp->u_volt_min, new_opp->u_volt_max,
+		 new_opp->clock_latency_ns);
 
-/**
- * _opp_remove()  - Remove an OPP from a table definition
- * @dev_opp:	points back to the device_opp struct this opp belongs to
- * @opp:	pointer to the OPP to remove
- *
- * This function removes an opp definition from the opp list.
- *
- * Locking: The internal device_opp 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 device_opp *dev_opp,
-			struct dev_pm_opp *opp)
-{
 	/*
 	 * Notify the changes in the availability of the operable
 	 * frequency/voltage list.
 	 */
-	srcu_notifier_call_chain(&dev_opp->srcu_head, OPP_EVENT_REMOVE, opp);
-	list_del_rcu(&opp->node);
-	call_srcu(&dev_opp->srcu_head.srcu, &opp->rcu_head, _kfree_opp_rcu);
+	srcu_notifier_call_chain(&dev_opp->srcu_head, OPP_EVENT_ADD, new_opp);
+	return 0;
 
-	if (list_empty(&dev_opp->opp_list)) {
-		list_del_rcu(&dev_opp->node);
-		call_srcu(&dev_opp->srcu_head.srcu, &dev_opp->rcu_head,
-			  _kfree_device_rcu);
-	}
+free_opp:
+	_opp_remove(dev_opp, new_opp, false);
+unlock:
+	mutex_unlock(&dev_opp_list_lock);
+	return ret;
 }
 
 /**
- * dev_pm_opp_remove()  - Remove an OPP from OPP list
+ * dev_pm_opp_add()  - Add an OPP table from a table definitions
  * @dev:	device for which we do this operation
- * @freq:	OPP to remove with matching 'freq'
+ * @freq:	Frequency in Hz for this OPP
+ * @u_volt:	Voltage in uVolts for this OPP
  *
- * This function removes an opp from the opp list.
+ * This function adds an opp definition to the opp list and returns status.
+ * The opp is made available by default and it can be controlled using
+ * dev_pm_opp_enable/disable functions.
  *
  * Locking: The internal device_opp 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
+ * -EEXIST	Freq are same and volt are different OR
+ *		Duplicate OPPs (both freq and volt are same) and !opp->available
+ * -ENOMEM	Memory allocation failure
  */
-void dev_pm_opp_remove(struct device *dev, unsigned long freq)
+int dev_pm_opp_add(struct device *dev, unsigned long freq, unsigned long u_volt)
 {
-	struct dev_pm_opp *opp;
-	struct device_opp *dev_opp;
-	bool found = false;
-
-	/* Hold our list modification lock here */
-	mutex_lock(&dev_opp_list_lock);
-
-	dev_opp = _find_device_opp(dev);
-	if (IS_ERR(dev_opp))
-		goto unlock;
-
-	list_for_each_entry(opp, &dev_opp->opp_list, node) {
-		if (opp->rate == freq) {
-			found = true;
-			break;
-		}
-	}
-
-	if (!found) {
-		dev_warn(dev, "%s: Couldn't find OPP with freq: %lu\n",
-			 __func__, freq);
-		goto unlock;
-	}
-
-	_opp_remove(dev_opp, opp);
-unlock:
-	mutex_unlock(&dev_opp_list_lock);
+	return _opp_add_dynamic(dev, freq, u_volt, true);
 }
-EXPORT_SYMBOL_GPL(dev_pm_opp_remove);
+EXPORT_SYMBOL_GPL(dev_pm_opp_add);
 
 /**
  * _opp_set_availability() - helper to set the availability of an opp
@@ -825,28 +1185,179 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_notifier);
 
 #ifdef CONFIG_OF
 /**
- * of_init_opp_table() - Initialize opp table from device tree
+ * of_free_opp_table() - Free OPP table entries created from static DT entries
  * @dev:	device pointer used to lookup device OPPs.
  *
- * Register the initial OPP table with the OPP library for given device.
+ * Free OPPs created using static entries present in DT.
  *
  * Locking: The internal device_opp 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
- * -EEXIST	Freq are same and volt are different OR
- *		Duplicate OPPs (both freq and volt are same) and !opp->available
- * -ENOMEM	Memory allocation failure
- * -ENODEV	when 'operating-points' property is not found or is invalid data
- *		in device node.
- * -ENODATA	when empty 'operating-points' property is found
  */
-int of_init_opp_table(struct device *dev)
+void of_free_opp_table(struct device *dev)
+{
+	struct device_opp *dev_opp;
+	struct dev_pm_opp *opp, *tmp;
+
+	/* Hold our list modification lock here */
+	mutex_lock(&dev_opp_list_lock);
+
+	/* Check for existing list for 'dev' */
+	dev_opp = _find_device_opp(dev);
+	if (IS_ERR(dev_opp)) {
+		int error = PTR_ERR(dev_opp);
+
+		if (error != -ENODEV)
+			WARN(1, "%s: dev_opp: %d\n",
+			     IS_ERR_OR_NULL(dev) ?
+					"Invalid device" : dev_name(dev),
+			     error);
+		goto unlock;
+	}
+
+	/* Find if dev_opp manages a single device */
+	if (list_is_singular(&dev_opp->dev_list)) {
+		/* Free static OPPs */
+		list_for_each_entry_safe(opp, tmp, &dev_opp->opp_list, node) {
+			if (!opp->dynamic)
+				_opp_remove(dev_opp, opp, true);
+		}
+	} else {
+		_remove_list_dev(_find_list_dev(dev, dev_opp), dev_opp);
+	}
+
+unlock:
+	mutex_unlock(&dev_opp_list_lock);
+}
+EXPORT_SYMBOL_GPL(of_free_opp_table);
+
+void of_cpumask_free_opp_table(cpumask_var_t cpumask)
+{
+	struct device *cpu_dev;
+	int cpu;
+
+	WARN_ON(cpumask_empty(cpumask));
+
+	for_each_cpu(cpu, cpumask) {
+		cpu_dev = get_cpu_device(cpu);
+		if (!cpu_dev) {
+			pr_err("%s: failed to get cpu%d device\n", __func__,
+			       cpu);
+			continue;
+		}
+
+		of_free_opp_table(cpu_dev);
+	}
+}
+EXPORT_SYMBOL_GPL(of_cpumask_free_opp_table);
+
+/* Returns opp descriptor node from its phandle. Caller must do of_node_put() */
+static struct device_node *
+_of_get_opp_desc_node_from_prop(struct device *dev, const struct property *prop)
+{
+	struct device_node *opp_np;
+
+	opp_np = of_find_node_by_phandle(be32_to_cpup(prop->value));
+	if (!opp_np) {
+		dev_err(dev, "%s: Prop: %s contains invalid opp desc phandle\n",
+			__func__, prop->name);
+		return ERR_PTR(-EINVAL);
+	}
+
+	return opp_np;
+}
+
+/* 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)
+{
+	const struct property *prop;
+
+	prop = of_find_property(dev->of_node, "operating-points-v2", NULL);
+	if (!prop)
+		return ERR_PTR(-ENODEV);
+	if (!prop->value)
+		return ERR_PTR(-ENODATA);
+
+	/*
+	 * TODO: Support for multiple OPP tables.
+	 *
+	 * There should be only ONE phandle present in "operating-points-v2"
+	 * property.
+	 */
+	if (prop->length != sizeof(__be32)) {
+		dev_err(dev, "%s: Invalid opp desc phandle\n", __func__);
+		return ERR_PTR(-EINVAL);
+	}
+
+	return _of_get_opp_desc_node_from_prop(dev, prop);
+}
+
+/* Initializes OPP tables based on new bindings */
+static int _of_init_opp_table_v2(struct device *dev,
+				 const struct property *prop)
+{
+	struct device_node *opp_np, *np;
+	struct device_opp *dev_opp;
+	int ret = 0, count = 0;
+
+	if (!prop->value)
+		return -ENODATA;
+
+	/* Get opp node */
+	opp_np = _of_get_opp_desc_node_from_prop(dev, prop);
+	if (IS_ERR(opp_np))
+		return PTR_ERR(opp_np);
+
+	dev_opp = _managed_opp(opp_np);
+	if (dev_opp) {
+		/* OPPs are already managed */
+		if (!_add_list_dev(dev, dev_opp))
+			ret = -ENOMEM;
+		goto put_opp_np;
+	}
+
+	/* We have opp-list 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);
+		if (ret) {
+			dev_err(dev, "%s: Failed to add OPP, %d\n", __func__,
+				ret);
+			goto free_table;
+		}
+	}
+
+	/* There should be one of more OPP defined */
+	if (WARN_ON(!count)) {
+		ret = -ENOENT;
+		goto put_opp_np;
+	}
+
+	dev_opp = _find_device_opp(dev);
+	if (WARN_ON(IS_ERR(dev_opp))) {
+		ret = PTR_ERR(dev_opp);
+		goto free_table;
+	}
+
+	dev_opp->np = opp_np;
+	dev_opp->shared_opp = of_property_read_bool(opp_np, "opp-shared");
+
+	of_node_put(opp_np);
+	return 0;
+
+free_table:
+	of_free_opp_table(dev);
+put_opp_np:
+	of_node_put(opp_np);
+
+	return ret;
+}
+
+/* Initializes OPP tables based on old-deprecated bindings */
+static int _of_init_opp_table_v1(struct device *dev)
 {
 	const struct property *prop;
 	const __be32 *val;
@@ -881,47 +1392,177 @@ int of_init_opp_table(struct device *dev)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(of_init_opp_table);
 
 /**
- * of_free_opp_table() - Free OPP table entries created from static DT entries
+ * of_init_opp_table() - Initialize opp table from device tree
  * @dev:	device pointer used to lookup device OPPs.
  *
- * Free OPPs created using static entries present in DT.
+ * Register the initial OPP table with the OPP library for given device.
  *
  * Locking: The internal device_opp 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
+ * -EEXIST	Freq are same and volt are different OR
+ *		Duplicate OPPs (both freq and volt are same) and !opp->available
+ * -ENOMEM	Memory allocation failure
+ * -ENODEV	when 'operating-points' property is not found or is invalid data
+ *		in device node.
+ * -ENODATA	when empty 'operating-points' property is found
+ * -EINVAL	when invalid entries are found in opp-v2 table
  */
-void of_free_opp_table(struct device *dev)
+int of_init_opp_table(struct device *dev)
+{
+	const struct property *prop;
+
+	/*
+	 * OPPs have two version of bindings now. The older one is deprecated,
+	 * try for the new binding first.
+	 */
+	prop = of_find_property(dev->of_node, "operating-points-v2", NULL);
+	if (!prop) {
+		/*
+		 * Try old-deprecated bindings for backward compatibility with
+		 * older dtbs.
+		 */
+		return _of_init_opp_table_v1(dev);
+	}
+
+	return _of_init_opp_table_v2(dev, prop);
+}
+EXPORT_SYMBOL_GPL(of_init_opp_table);
+
+int of_cpumask_init_opp_table(cpumask_var_t cpumask)
+{
+	struct device *cpu_dev;
+	int cpu, ret = 0;
+
+	WARN_ON(cpumask_empty(cpumask));
+
+	for_each_cpu(cpu, cpumask) {
+		cpu_dev = get_cpu_device(cpu);
+		if (!cpu_dev) {
+			pr_err("%s: failed to get cpu%d device\n", __func__,
+			       cpu);
+			continue;
+		}
+
+		ret = of_init_opp_table(cpu_dev);
+		if (ret) {
+			pr_err("%s: couldn't find opp table for cpu:%d, %d\n",
+			       __func__, cpu, ret);
+
+			/* Free all other OPPs */
+			of_cpumask_free_opp_table(cpumask);
+			break;
+		}
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(of_cpumask_init_opp_table);
+
+/* Required only for V1 bindings, as v2 can manage it from DT itself */
+int set_cpus_sharing_opps(struct device *cpu_dev, cpumask_var_t cpumask)
 {
+	struct device_list_opp *list_dev;
 	struct device_opp *dev_opp;
-	struct dev_pm_opp *opp, *tmp;
+	struct device *dev;
+	int cpu, ret = 0;
 
-	/* Check for existing list for 'dev' */
-	dev_opp = _find_device_opp(dev);
+	rcu_read_lock();
+
+	dev_opp = _find_device_opp(cpu_dev);
 	if (IS_ERR(dev_opp)) {
-		int error = PTR_ERR(dev_opp);
-		if (error != -ENODEV)
-			WARN(1, "%s: dev_opp: %d\n",
-			     IS_ERR_OR_NULL(dev) ?
-					"Invalid device" : dev_name(dev),
-			     error);
-		return;
+		ret = -EINVAL;
+		goto out_rcu_read_unlock;
 	}
 
-	/* Hold our list modification lock here */
-	mutex_lock(&dev_opp_list_lock);
+	for_each_cpu(cpu, cpumask) {
+		if (cpu == cpu_dev->id)
+			continue;
 
-	/* Free static OPPs */
-	list_for_each_entry_safe(opp, tmp, &dev_opp->opp_list, node) {
-		if (!opp->dynamic)
-			_opp_remove(dev_opp, opp);
+		dev = get_cpu_device(cpu);
+		if (!dev) {
+			dev_err(cpu_dev, "%s: failed to get cpu%d device\n",
+				__func__, cpu);
+			continue;
+		}
+
+		list_dev = _add_list_dev(dev, dev_opp);
+		if (!list_dev) {
+			dev_err(dev, "%s: failed to add list-dev for cpu%d device\n",
+				__func__, cpu);
+			continue;
+		}
 	}
+out_rcu_read_unlock:
+	rcu_read_unlock();
 
-	mutex_unlock(&dev_opp_list_lock);
+	return 0;
 }
-EXPORT_SYMBOL_GPL(of_free_opp_table);
+EXPORT_SYMBOL_GPL(set_cpus_sharing_opps);
+
+/*
+ * Works only for OPP v2 bindings.
+ *
+ * cpumask should be already set to mask of cpu_dev->id.
+ * Returns -ENOENT if operating-points-v2 bindings aren't supported.
+ */
+int of_get_cpus_sharing_opps(struct device *cpu_dev, cpumask_var_t cpumask)
+{
+	struct device_node *np, *tmp_np;
+	struct device *tcpu_dev;
+	int cpu, ret = 0;
+
+	/* Get OPP descriptor node */
+	np = _of_get_opp_desc_node(cpu_dev);
+	if (IS_ERR(np)) {
+		dev_dbg(cpu_dev, "%s: Couldn't find opp node: %ld\n", __func__,
+			PTR_ERR(np));
+		return -ENOENT;
+	}
+
+	/* OPPs are shared ? */
+	if (!of_property_read_bool(np, "opp-shared"))
+		goto put_cpu_node;
+
+	for_each_possible_cpu(cpu) {
+		if (cpu == cpu_dev->id)
+			continue;
+
+		tcpu_dev = get_cpu_device(cpu);
+		if (!tcpu_dev) {
+			dev_err(cpu_dev, "%s: failed to get cpu%d device\n",
+				__func__, cpu);
+			ret = -ENODEV;
+			goto put_cpu_node;
+		}
+
+		/* Get OPP descriptor node */
+		tmp_np = _of_get_opp_desc_node(tcpu_dev);
+		if (IS_ERR(tmp_np)) {
+			dev_err(tcpu_dev, "%s: Couldn't find opp node: %ld\n",
+				__func__, PTR_ERR(tmp_np));
+			ret = PTR_ERR(tmp_np);
+			goto put_cpu_node;
+		}
+
+		/* CPUs are sharing opp node */
+		if (np == tmp_np)
+			cpumask_set_cpu(cpu, cpumask);
+
+		of_node_put(tmp_np);
+	}
+
+put_cpu_node:
+	of_node_put(np);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(of_get_cpus_sharing_opps);
 #endif
diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c
index 528a82bf5038..c3583cdfadbd 100644
--- a/drivers/cpufreq/cpufreq-dt.c
+++ b/drivers/cpufreq/cpufreq-dt.c
@@ -36,6 +36,12 @@ struct private_data {
 	unsigned int voltage_tolerance; /* in percentage */
 };
 
+static struct freq_attr *cpufreq_dt_attr[] = {
+	&cpufreq_freq_attr_scaling_available_freqs,
+	NULL,   /* Extra space for boost-attr if required */
+	NULL,
+};
+
 static int set_target(struct cpufreq_policy *policy, unsigned int index)
 {
 	struct dev_pm_opp *opp;
@@ -184,7 +190,6 @@ try_again:
 
 static int cpufreq_init(struct cpufreq_policy *policy)
 {
-	struct cpufreq_dt_platform_data *pd;
 	struct cpufreq_frequency_table *freq_table;
 	struct device_node *np;
 	struct private_data *priv;
@@ -193,6 +198,7 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 	struct clk *cpu_clk;
 	unsigned long min_uV = ~0, max_uV = 0;
 	unsigned int transition_latency;
+	bool need_update = false;
 	int ret;
 
 	ret = allocate_resources(policy->cpu, &cpu_dev, &cpu_reg, &cpu_clk);
@@ -208,8 +214,47 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 		goto out_put_reg_clk;
 	}
 
-	/* OPPs might be populated at runtime, don't check for error here */
-	of_init_opp_table(cpu_dev);
+	/* Get OPP-sharing information from "operating-points-v2" bindings */
+	ret = of_get_cpus_sharing_opps(cpu_dev, policy->cpus);
+	if (ret) {
+		/*
+		 * operating-points-v2 not supported, fallback to old method of
+		 * finding shared-OPPs for backward compatibility.
+		 */
+		if (ret == -ENOENT)
+			need_update = true;
+		else
+			goto out_node_put;
+	}
+
+	/*
+	 * Initialize OPP tables for all policy->cpus. They will be shared by
+	 * all CPUs which have marked their CPUs shared with OPP bindings.
+	 *
+	 * For platforms not using operating-points-v2 bindings, we do this
+	 * before updating policy->cpus. Otherwise, we will end up creating
+	 * duplicate OPPs for policy->cpus.
+	 *
+	 * OPPs might be populated at runtime, don't check for error here
+	 */
+	of_cpumask_init_opp_table(policy->cpus);
+
+	if (need_update) {
+		struct cpufreq_dt_platform_data *pd = cpufreq_get_driver_data();
+
+		if (!pd || !pd->independent_clocks)
+			cpumask_setall(policy->cpus);
+
+		/*
+		 * OPP tables are initialized only for policy->cpu, do it for
+		 * others as well.
+		 */
+		set_cpus_sharing_opps(cpu_dev, policy->cpus);
+
+		of_property_read_u32(np, "clock-latency", &transition_latency);
+	} else {
+		transition_latency = dev_pm_opp_get_max_clock_latency(cpu_dev);
+	}
 
 	/*
 	 * But we need OPP table to function so if it is not there let's
@@ -230,7 +275,7 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 
 	of_property_read_u32(np, "voltage-tolerance", &priv->voltage_tolerance);
 
-	if (of_property_read_u32(np, "clock-latency", &transition_latency))
+	if (!transition_latency)
 		transition_latency = CPUFREQ_ETERNAL;
 
 	if (!IS_ERR(cpu_reg)) {
@@ -291,11 +336,16 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 		goto out_free_cpufreq_table;
 	}
 
-	policy->cpuinfo.transition_latency = transition_latency;
+	/* Support turbo/boost mode */
+	if (policy_has_boost_freq(policy)) {
+		/* This gets disabled by core on driver unregister */
+		ret = cpufreq_enable_boost_support();
+		if (ret)
+			goto out_free_cpufreq_table;
+		cpufreq_dt_attr[1] = &cpufreq_freq_attr_scaling_boost_freqs;
+	}
 
-	pd = cpufreq_get_driver_data();
-	if (!pd || !pd->independent_clocks)
-		cpumask_setall(policy->cpus);
+	policy->cpuinfo.transition_latency = transition_latency;
 
 	of_node_put(np);
 
@@ -306,7 +356,8 @@ out_free_cpufreq_table:
 out_free_priv:
 	kfree(priv);
 out_free_opp:
-	of_free_opp_table(cpu_dev);
+	of_cpumask_free_opp_table(policy->cpus);
+out_node_put:
 	of_node_put(np);
 out_put_reg_clk:
 	clk_put(cpu_clk);
@@ -322,7 +373,7 @@ static int cpufreq_exit(struct cpufreq_policy *policy)
 
 	cpufreq_cooling_unregister(priv->cdev);
 	dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &policy->freq_table);
-	of_free_opp_table(priv->cpu_dev);
+	of_cpumask_free_opp_table(policy->related_cpus);
 	clk_put(policy->clk);
 	if (!IS_ERR(priv->cpu_reg))
 		regulator_put(priv->cpu_reg);
@@ -367,7 +418,7 @@ static struct cpufreq_driver dt_cpufreq_driver = {
 	.exit = cpufreq_exit,
 	.ready = cpufreq_ready,
 	.name = "cpufreq-dt",
-	.attr = cpufreq_generic_attr,
+	.attr = cpufreq_dt_attr,
 };
 
 static int dt_cpufreq_probe(struct platform_device *pdev)
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index a05cc75cc45d..abb776827bb1 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -2412,6 +2412,49 @@ int cpufreq_boost_supported(void)
 }
 EXPORT_SYMBOL_GPL(cpufreq_boost_supported);
 
+static int create_boost_sysfs_file(void)
+{
+	int ret;
+
+	if (!cpufreq_boost_supported())
+		return 0;
+
+	/*
+	 * Check if driver provides function to enable boost -
+	 * if not, use cpufreq_boost_set_sw as default
+	 */
+	if (!cpufreq_driver->set_boost)
+		cpufreq_driver->set_boost = cpufreq_boost_set_sw;
+
+	ret = cpufreq_sysfs_create_file(&boost.attr);
+	if (ret)
+		pr_err("%s: cannot register global BOOST sysfs file\n",
+		       __func__);
+
+	return ret;
+}
+
+static void remove_boost_sysfs_file(void)
+{
+	if (cpufreq_boost_supported())
+		cpufreq_sysfs_remove_file(&boost.attr);
+}
+
+int cpufreq_enable_boost_support(void)
+{
+	if (!cpufreq_driver)
+		return -EINVAL;
+
+	if (cpufreq_boost_supported())
+		return 0;
+
+	cpufreq_driver->boost_supported = true;
+
+	/* This will get removed on driver unregister */
+	return create_boost_sysfs_file();
+}
+EXPORT_SYMBOL_GPL(cpufreq_enable_boost_support);
+
 int cpufreq_boost_enabled(void)
 {
 	return cpufreq_driver->boost_enabled;
@@ -2465,21 +2508,9 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
 	if (driver_data->setpolicy)
 		driver_data->flags |= CPUFREQ_CONST_LOOPS;
 
-	if (cpufreq_boost_supported()) {
-		/*
-		 * Check if driver provides function to enable boost -
-		 * if not, use cpufreq_boost_set_sw as default
-		 */
-		if (!cpufreq_driver->set_boost)
-			cpufreq_driver->set_boost = cpufreq_boost_set_sw;
-
-		ret = cpufreq_sysfs_create_file(&boost.attr);
-		if (ret) {
-			pr_err("%s: cannot register global BOOST sysfs file\n",
-			       __func__);
-			goto err_null_driver;
-		}
-	}
+	ret = create_boost_sysfs_file();
+	if (ret)
+		goto err_null_driver;
 
 	ret = subsys_interface_register(&cpufreq_interface);
 	if (ret)
@@ -2503,8 +2534,7 @@ out:
 err_if_unreg:
 	subsys_interface_unregister(&cpufreq_interface);
 err_boost_unreg:
-	if (cpufreq_boost_supported())
-		cpufreq_sysfs_remove_file(&boost.attr);
+	remove_boost_sysfs_file();
 err_null_driver:
 	write_lock_irqsave(&cpufreq_driver_lock, flags);
 	cpufreq_driver = NULL;
@@ -2533,9 +2563,7 @@ int cpufreq_unregister_driver(struct cpufreq_driver *driver)
 	/* Protect against concurrent cpu hotplug */
 	get_online_cpus();
 	subsys_interface_unregister(&cpufreq_interface);
-	if (cpufreq_boost_supported())
-		cpufreq_sysfs_remove_file(&boost.attr);
-
+	remove_boost_sysfs_file();
 	unregister_hotcpu_notifier(&cpufreq_cpu_notifier);
 
 	write_lock_irqsave(&cpufreq_driver_lock, flags);
diff --git a/drivers/cpufreq/cpufreq_opp.c b/drivers/cpufreq/cpufreq_opp.c
index 773bcde893c0..0f5e6d5f6da0 100644
--- a/drivers/cpufreq/cpufreq_opp.c
+++ b/drivers/cpufreq/cpufreq_opp.c
@@ -75,6 +75,10 @@ int dev_pm_opp_init_cpufreq_table(struct device *dev,
 		}
 		freq_table[i].driver_data = i;
 		freq_table[i].frequency = rate / 1000;
+
+		/* Is Boost/turbo opp ? */
+		if (dev_pm_opp_is_turbo(opp))
+			freq_table[i].flags = CPUFREQ_BOOST_FREQ;
 	}
 
 	freq_table[i].driver_data = i;
diff --git a/drivers/cpufreq/freq_table.c b/drivers/cpufreq/freq_table.c
index dfbbf981ed56..a8f1daffc9bc 100644
--- a/drivers/cpufreq/freq_table.c
+++ b/drivers/cpufreq/freq_table.c
@@ -18,6 +18,21 @@
  *                     FREQUENCY TABLE HELPERS                       *
  *********************************************************************/
 
+bool policy_has_boost_freq(struct cpufreq_policy *policy)
+{
+	struct cpufreq_frequency_table *pos, *table = policy->freq_table;
+
+	if (!table)
+		return false;
+
+	cpufreq_for_each_valid_entry(pos, table)
+		if (pos->flags & CPUFREQ_BOOST_FREQ)
+			return true;
+
+	return false;
+}
+EXPORT_SYMBOL_GPL(policy_has_boost_freq);
+
 int cpufreq_frequency_table_cpuinfo(struct cpufreq_policy *policy,
 				    struct cpufreq_frequency_table *table)
 {
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index 59892126d175..d3629b7482dd 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -48,6 +48,8 @@
 	BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) |\
 	BIT(DMA_SLAVE_BUSWIDTH_4_BYTES))
 
+#define ATC_MAX_DSCR_TRIALS	10
+
 /*
  * Initial number of descriptors to allocate for each channel. This could
  * be increased during dma usage.
@@ -285,28 +287,19 @@ static struct at_desc *atc_get_desc_by_cookie(struct at_dma_chan *atchan,
  *
  * @current_len: the number of bytes left before reading CTRLA
  * @ctrla: the value of CTRLA
- * @desc: the descriptor containing the transfer width
  */
-static inline int atc_calc_bytes_left(int current_len, u32 ctrla,
-					struct at_desc *desc)
+static inline int atc_calc_bytes_left(int current_len, u32 ctrla)
 {
-	return current_len - ((ctrla & ATC_BTSIZE_MAX) << desc->tx_width);
-}
+	u32 btsize = (ctrla & ATC_BTSIZE_MAX);
+	u32 src_width = ATC_REG_TO_SRC_WIDTH(ctrla);
 
-/**
- * atc_calc_bytes_left_from_reg - calculates the number of bytes left according
- * to the current value of CTRLA.
- *
- * @current_len: the number of bytes left before reading CTRLA
- * @atchan: the channel to read CTRLA for
- * @desc: the descriptor containing the transfer width
- */
-static inline int atc_calc_bytes_left_from_reg(int current_len,
-			struct at_dma_chan *atchan, struct at_desc *desc)
-{
-	u32 ctrla = channel_readl(atchan, CTRLA);
-
-	return atc_calc_bytes_left(current_len, ctrla, desc);
+	/*
+	 * According to the datasheet, when reading the Control A Register
+	 * (ctrla), the Buffer Transfer Size (btsize) bitfield refers to the
+	 * number of transfers completed on the Source Interface.
+	 * So btsize is always a number of source width transfers.
+	 */
+	return current_len - (btsize << src_width);
 }
 
 /**
@@ -320,7 +313,7 @@ static int atc_get_bytes_left(struct dma_chan *chan, dma_cookie_t cookie)
 	struct at_desc *desc_first = atc_first_active(atchan);
 	struct at_desc *desc;
 	int ret;
-	u32 ctrla, dscr;
+	u32 ctrla, dscr, trials;
 
 	/*
 	 * If the cookie doesn't match to the currently running transfer then
@@ -346,15 +339,82 @@ static int atc_get_bytes_left(struct dma_chan *chan, dma_cookie_t cookie)
 		 * the channel's DSCR register and compare it against the value
 		 * of the hardware linked list structure of each child
 		 * descriptor.
+		 *
+		 * The CTRLA register provides us with the amount of data
+		 * already read from the source for the current child
+		 * descriptor. So we can compute a more accurate residue by also
+		 * removing the number of bytes corresponding to this amount of
+		 * data.
+		 *
+		 * However, the DSCR and CTRLA registers cannot be read both
+		 * atomically. Hence a race condition may occur: the first read
+		 * register may refer to one child descriptor whereas the second
+		 * read may refer to a later child descriptor in the list
+		 * because of the DMA transfer progression inbetween the two
+		 * reads.
+		 *
+		 * One solution could have been to pause the DMA transfer, read
+		 * the DSCR and CTRLA then resume the DMA transfer. Nonetheless,
+		 * this approach presents some drawbacks:
+		 * - If the DMA transfer is paused, RX overruns or TX underruns
+		 *   are more likey to occur depending on the system latency.
+		 *   Taking the USART driver as an example, it uses a cyclic DMA
+		 *   transfer to read data from the Receive Holding Register
+		 *   (RHR) to avoid RX overruns since the RHR is not protected
+		 *   by any FIFO on most Atmel SoCs. So pausing the DMA transfer
+		 *   to compute the residue would break the USART driver design.
+		 * - The atc_pause() function masks interrupts but we'd rather
+		 *   avoid to do so for system latency purpose.
+		 *
+		 * Then we'd rather use another solution: the DSCR is read a
+		 * first time, the CTRLA is read in turn, next the DSCR is read
+		 * a second time. If the two consecutive read values of the DSCR
+		 * are the same then we assume both refers to the very same
+		 * child descriptor as well as the CTRLA value read inbetween
+		 * does. For cyclic tranfers, the assumption is that a full loop
+		 * is "not so fast".
+		 * If the two DSCR values are different, we read again the CTRLA
+		 * then the DSCR till two consecutive read values from DSCR are
+		 * equal or till the maxium trials is reach.
+		 * This algorithm is very unlikely not to find a stable value for
+		 * DSCR.
 		 */
 
-		ctrla = channel_readl(atchan, CTRLA);
-		rmb(); /* ensure CTRLA is read before DSCR */
 		dscr = channel_readl(atchan, DSCR);
+		rmb(); /* ensure DSCR is read before CTRLA */
+		ctrla = channel_readl(atchan, CTRLA);
+		for (trials = 0; trials < ATC_MAX_DSCR_TRIALS; ++trials) {
+			u32 new_dscr;
+
+			rmb(); /* ensure DSCR is read after CTRLA */
+			new_dscr = channel_readl(atchan, DSCR);
+
+			/*
+			 * If the DSCR register value has not changed inside the
+			 * DMA controller since the previous read, we assume
+			 * that both the dscr and ctrla values refers to the
+			 * very same descriptor.
+			 */
+			if (likely(new_dscr == dscr))
+				break;
+
+			/*
+			 * DSCR has changed inside the DMA controller, so the
+			 * previouly read value of CTRLA may refer to an already
+			 * processed descriptor hence could be outdated.
+			 * We need to update ctrla to match the current
+			 * descriptor.
+			 */
+			dscr = new_dscr;
+			rmb(); /* ensure DSCR is read before CTRLA */
+			ctrla = channel_readl(atchan, CTRLA);
+		}
+		if (unlikely(trials >= ATC_MAX_DSCR_TRIALS))
+			return -ETIMEDOUT;
 
 		/* for the first descriptor we can be more accurate */
 		if (desc_first->lli.dscr == dscr)
-			return atc_calc_bytes_left(ret, ctrla, desc_first);
+			return atc_calc_bytes_left(ret, ctrla);
 
 		ret -= desc_first->len;
 		list_for_each_entry(desc, &desc_first->tx_list, desc_node) {
@@ -365,16 +425,14 @@ static int atc_get_bytes_left(struct dma_chan *chan, dma_cookie_t cookie)
 		}
 
 		/*
-		 * For the last descriptor in the chain we can calculate
+		 * For the current descriptor in the chain we can calculate
 		 * the remaining bytes using the channel's register.
-		 * Note that the transfer width of the first and last
-		 * descriptor may differ.
 		 */
-		if (!desc->lli.dscr)
-			ret = atc_calc_bytes_left_from_reg(ret, atchan, desc);
+		ret = atc_calc_bytes_left(ret, ctrla);
 	} else {
 		/* single transfer */
-		ret = atc_calc_bytes_left_from_reg(ret, atchan, desc_first);
+		ctrla = channel_readl(atchan, CTRLA);
+		ret = atc_calc_bytes_left(ret, ctrla);
 	}
 
 	return ret;
@@ -726,7 +784,6 @@ atc_prep_dma_interleaved(struct dma_chan *chan,
 
 	desc->txd.cookie = -EBUSY;
 	desc->total_len = desc->len = len;
-	desc->tx_width = dwidth;
 
 	/* set end-of-link to the last link descriptor of list*/
 	set_desc_eol(desc);
@@ -804,10 +861,6 @@ atc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 	first->txd.cookie = -EBUSY;
 	first->total_len = len;
 
-	/* set transfer width for the calculation of the residue */
-	first->tx_width = src_width;
-	prev->tx_width = src_width;
-
 	/* set end-of-link to the last link descriptor of list*/
 	set_desc_eol(desc);
 
@@ -956,10 +1009,6 @@ atc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 	first->txd.cookie = -EBUSY;
 	first->total_len = total_len;
 
-	/* set transfer width for the calculation of the residue */
-	first->tx_width = reg_width;
-	prev->tx_width = reg_width;
-
 	/* first link descriptor of list is responsible of flags */
 	first->txd.flags = flags; /* client is in control of this ack */
 
@@ -1077,12 +1126,6 @@ atc_prep_dma_sg(struct dma_chan *chan,
 		desc->txd.cookie = 0;
 		desc->len = len;
 
-		/*
-		 * Although we only need the transfer width for the first and
-		 * the last descriptor, its easier to set it to all descriptors.
-		 */
-		desc->tx_width = src_width;
-
 		atc_desc_chain(&first, &prev, desc);
 
 		/* update the lengths and addresses for the next loop cycle */
@@ -1256,7 +1299,6 @@ atc_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len,
 	/* First descriptor of the chain embedds additional information */
 	first->txd.cookie = -EBUSY;
 	first->total_len = buf_len;
-	first->tx_width = reg_width;
 
 	return &first->txd;
 
diff --git a/drivers/dma/at_hdmac_regs.h b/drivers/dma/at_hdmac_regs.h
index bc8d5ebedd19..7f5a08230f76 100644
--- a/drivers/dma/at_hdmac_regs.h
+++ b/drivers/dma/at_hdmac_regs.h
@@ -112,6 +112,7 @@
 #define		ATC_SRC_WIDTH_BYTE	(0x0 << 24)
 #define		ATC_SRC_WIDTH_HALFWORD	(0x1 << 24)
 #define		ATC_SRC_WIDTH_WORD	(0x2 << 24)
+#define		ATC_REG_TO_SRC_WIDTH(r)	(((r) >> 24) & 0x3)
 #define	ATC_DST_WIDTH_MASK	(0x3 << 28)	/* Destination Single Transfer Size */
 #define		ATC_DST_WIDTH(x)	((x) << 28)
 #define		ATC_DST_WIDTH_BYTE	(0x0 << 28)
@@ -182,7 +183,6 @@ struct at_lli {
  * @txd: support for the async_tx api
  * @desc_node: node on the channed descriptors list
  * @len: descriptor byte count
- * @tx_width: transfer width
  * @total_len: total transaction byte count
  */
 struct at_desc {
@@ -194,7 +194,6 @@ struct at_desc {
 	struct dma_async_tx_descriptor	txd;
 	struct list_head		desc_node;
 	size_t				len;
-	u32				tx_width;
 	size_t				total_len;
 
 	/* Interleaved data */
diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
index cf1213de7865..40afa2a16cfc 100644
--- a/drivers/dma/at_xdmac.c
+++ b/drivers/dma/at_xdmac.c
@@ -359,18 +359,19 @@ static void at_xdmac_start_xfer(struct at_xdmac_chan *atchan,
 	 * descriptor view 2 since some fields of the configuration register
 	 * depend on transfer size and src/dest addresses.
 	 */
-	if (at_xdmac_chan_is_cyclic(atchan)) {
+	if (at_xdmac_chan_is_cyclic(atchan))
 		reg = AT_XDMAC_CNDC_NDVIEW_NDV1;
-		at_xdmac_chan_write(atchan, AT_XDMAC_CC, first->lld.mbr_cfg);
-	} else if (first->lld.mbr_ubc & AT_XDMAC_MBR_UBC_NDV3) {
+	else if (first->lld.mbr_ubc & AT_XDMAC_MBR_UBC_NDV3)
 		reg = AT_XDMAC_CNDC_NDVIEW_NDV3;
-	} else {
-		/*
-		 * No need to write AT_XDMAC_CC reg, it will be done when the
-		 * descriptor is fecthed.
-		 */
+	else
 		reg = AT_XDMAC_CNDC_NDVIEW_NDV2;
-	}
+	/*
+	 * Even if the register will be updated from the configuration in the
+	 * descriptor when using view 2 or higher, the PROT bit won't be set
+	 * properly. This bit can be modified only by using the channel
+	 * configuration register.
+	 */
+	at_xdmac_chan_write(atchan, AT_XDMAC_CC, first->lld.mbr_cfg);
 
 	reg |= AT_XDMAC_CNDC_NDDUP
 	       | AT_XDMAC_CNDC_NDSUP
@@ -681,15 +682,16 @@ at_xdmac_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 			desc->lld.mbr_sa = mem;
 			desc->lld.mbr_da = atchan->sconfig.dst_addr;
 		}
-		desc->lld.mbr_cfg = atchan->cfg;
-		dwidth = at_xdmac_get_dwidth(desc->lld.mbr_cfg);
+		dwidth = at_xdmac_get_dwidth(atchan->cfg);
 		fixed_dwidth = IS_ALIGNED(len, 1 << dwidth)
-			       ? at_xdmac_get_dwidth(desc->lld.mbr_cfg)
+			       ? dwidth
 			       : AT_XDMAC_CC_DWIDTH_BYTE;
 		desc->lld.mbr_ubc = AT_XDMAC_MBR_UBC_NDV2			/* next descriptor view */
 			| AT_XDMAC_MBR_UBC_NDEN					/* next descriptor dst parameter update */
 			| AT_XDMAC_MBR_UBC_NSEN					/* next descriptor src parameter update */
 			| (len >> fixed_dwidth);				/* microblock length */
+		desc->lld.mbr_cfg = (atchan->cfg & ~AT_XDMAC_CC_DWIDTH_MASK) |
+				    AT_XDMAC_CC_DWIDTH(fixed_dwidth);
 		dev_dbg(chan2dev(chan),
 			 "%s: lld: mbr_sa=%pad, mbr_da=%pad, mbr_ubc=0x%08x\n",
 			 __func__, &desc->lld.mbr_sa, &desc->lld.mbr_da, desc->lld.mbr_ubc);
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index fbaf1ead2597..f1325f62563e 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -162,10 +162,11 @@ static void mv_chan_set_mode(struct mv_xor_chan *chan,
 	config &= ~0x7;
 	config |= op_mode;
 
-	if (IS_ENABLED(__BIG_ENDIAN))
-		config |= XOR_DESCRIPTOR_SWAP;
-	else
-		config &= ~XOR_DESCRIPTOR_SWAP;
+#if defined(__BIG_ENDIAN)
+	config |= XOR_DESCRIPTOR_SWAP;
+#else
+	config &= ~XOR_DESCRIPTOR_SWAP;
+#endif
 
 	writel_relaxed(config, XOR_CONFIG(chan));
 	chan->current_type = type;
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index f513f77b1d85..ecab4ea059b4 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -2328,7 +2328,7 @@ static dma_cookie_t pl330_tx_submit(struct dma_async_tx_descriptor *tx)
 			desc->txd.callback = last->txd.callback;
 			desc->txd.callback_param = last->txd.callback_param;
 		}
-		last->last = false;
+		desc->last = false;
 
 		dma_cookie_assign(&desc->txd);
 
@@ -2623,6 +2623,7 @@ pl330_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dst,
 		desc->rqcfg.brst_len = 1;
 
 	desc->rqcfg.brst_len = get_burst_len(desc, len);
+	desc->bytes_requested = len;
 
 	desc->txd.flags = flags;
 
diff --git a/drivers/dma/virt-dma.c b/drivers/dma/virt-dma.c
index 7d2c17d8d30f..6f80432a3f0a 100644
--- a/drivers/dma/virt-dma.c
+++ b/drivers/dma/virt-dma.c
@@ -29,7 +29,7 @@ dma_cookie_t vchan_tx_submit(struct dma_async_tx_descriptor *tx)
 	spin_lock_irqsave(&vc->lock, flags);
 	cookie = dma_cookie_assign(tx);
 
-	list_move_tail(&vd->node, &vc->desc_submitted);
+	list_add_tail(&vd->node, &vc->desc_submitted);
 	spin_unlock_irqrestore(&vc->lock, flags);
 
 	dev_dbg(vc->chan.device->dev, "vchan %p: txd %p[%x]: submitted\n",
@@ -83,10 +83,8 @@ static void vchan_complete(unsigned long arg)
 		cb_data = vd->tx.callback_param;
 
 		list_del(&vd->node);
-		if (async_tx_test_ack(&vd->tx))
-			list_add(&vd->node, &vc->desc_allocated);
-		else
-			vc->desc_free(vd);
+
+		vc->desc_free(vd);
 
 		if (cb)
 			cb(cb_data);
@@ -98,13 +96,9 @@ void vchan_dma_desc_free_list(struct virt_dma_chan *vc, struct list_head *head)
 	while (!list_empty(head)) {
 		struct virt_dma_desc *vd = list_first_entry(head,
 			struct virt_dma_desc, node);
-		if (async_tx_test_ack(&vd->tx)) {
-			list_move_tail(&vd->node, &vc->desc_allocated);
-		} else {
-			dev_dbg(vc->chan.device->dev, "txd %p: freeing\n", vd);
-			list_del(&vd->node);
-			vc->desc_free(vd);
-		}
+		list_del(&vd->node);
+		dev_dbg(vc->chan.device->dev, "txd %p: freeing\n", vd);
+		vc->desc_free(vd);
 	}
 }
 EXPORT_SYMBOL_GPL(vchan_dma_desc_free_list);
@@ -114,7 +108,6 @@ void vchan_init(struct virt_dma_chan *vc, struct dma_device *dmadev)
 	dma_cookie_init(&vc->chan);
 
 	spin_lock_init(&vc->lock);
-	INIT_LIST_HEAD(&vc->desc_allocated);
 	INIT_LIST_HEAD(&vc->desc_submitted);
 	INIT_LIST_HEAD(&vc->desc_issued);
 	INIT_LIST_HEAD(&vc->desc_completed);
diff --git a/drivers/dma/virt-dma.h b/drivers/dma/virt-dma.h
index 189e75dbcb15..181b95267866 100644
--- a/drivers/dma/virt-dma.h
+++ b/drivers/dma/virt-dma.h
@@ -29,7 +29,6 @@ struct virt_dma_chan {
 	spinlock_t lock;
 
 	/* protected by vc.lock */
-	struct list_head desc_allocated;
 	struct list_head desc_submitted;
 	struct list_head desc_issued;
 	struct list_head desc_completed;
@@ -56,16 +55,11 @@ static inline struct dma_async_tx_descriptor *vchan_tx_prep(struct virt_dma_chan
 	struct virt_dma_desc *vd, unsigned long tx_flags)
 {
 	extern dma_cookie_t vchan_tx_submit(struct dma_async_tx_descriptor *);
-	unsigned long flags;
 
 	dma_async_tx_descriptor_init(&vd->tx, &vc->chan);
 	vd->tx.flags = tx_flags;
 	vd->tx.tx_submit = vchan_tx_submit;
 
-	spin_lock_irqsave(&vc->lock, flags);
-	list_add_tail(&vd->node, &vc->desc_allocated);
-	spin_unlock_irqrestore(&vc->lock, flags);
-
 	return &vd->tx;
 }
 
@@ -128,8 +122,7 @@ static inline struct virt_dma_desc *vchan_next_desc(struct virt_dma_chan *vc)
 }
 
 /**
- * vchan_get_all_descriptors - obtain all allocated, submitted and issued
- *                             descriptors
+ * vchan_get_all_descriptors - obtain all submitted and issued descriptors
  * vc: virtual channel to get descriptors from
  * head: list of descriptors found
  *
@@ -141,7 +134,6 @@ static inline struct virt_dma_desc *vchan_next_desc(struct virt_dma_chan *vc)
 static inline void vchan_get_all_descriptors(struct virt_dma_chan *vc,
 	struct list_head *head)
 {
-	list_splice_tail_init(&vc->desc_allocated, head);
 	list_splice_tail_init(&vc->desc_submitted, head);
 	list_splice_tail_init(&vc->desc_issued, head);
 	list_splice_tail_init(&vc->desc_completed, head);
@@ -149,14 +141,11 @@ static inline void vchan_get_all_descriptors(struct virt_dma_chan *vc,
 
 static inline void vchan_free_chan_resources(struct virt_dma_chan *vc)
 {
-	struct virt_dma_desc *vd;
 	unsigned long flags;
 	LIST_HEAD(head);
 
 	spin_lock_irqsave(&vc->lock, flags);
 	vchan_get_all_descriptors(vc, &head);
-	list_for_each_entry(vd, &head, node)
-		async_tx_clear_ack(&vd->tx);
 	spin_unlock_irqrestore(&vc->lock, flags);
 
 	vchan_dma_desc_free_list(vc, &head);
diff --git a/drivers/dma/xgene-dma.c b/drivers/dma/xgene-dma.c
index 620fd55ec766..dff22ab01851 100644
--- a/drivers/dma/xgene-dma.c
+++ b/drivers/dma/xgene-dma.c
@@ -111,6 +111,7 @@
 #define XGENE_DMA_MEM_RAM_SHUTDOWN		0xD070
 #define XGENE_DMA_BLK_MEM_RDY			0xD074
 #define XGENE_DMA_BLK_MEM_RDY_VAL		0xFFFFFFFF
+#define XGENE_DMA_RING_CMD_SM_OFFSET		0x8000
 
 /* X-Gene SoC EFUSE csr register and bit defination */
 #define XGENE_SOC_JTAG1_SHADOW			0x18
@@ -1887,6 +1888,8 @@ static int xgene_dma_get_resources(struct platform_device *pdev,
 		return -ENOMEM;
 	}
 
+	pdma->csr_ring_cmd += XGENE_DMA_RING_CMD_SM_OFFSET;
+
 	/* Get efuse csr region */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 3);
 	if (!res) {
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 9fa8084a7c8d..d6144e3b97c5 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -58,6 +58,11 @@ bool efi_runtime_disabled(void)
 
 static int __init parse_efi_cmdline(char *str)
 {
+	if (!str) {
+		pr_warn("need at least one option\n");
+		return -EINVAL;
+	}
+
 	if (parse_option_str(str, "noruntime"))
 		disable_runtime = true;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index e9fde72cf038..31b00f91cfcd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1866,6 +1866,12 @@ typedef void (*amdgpu_wreg_t)(struct amdgpu_device*, uint32_t, uint32_t);
 typedef uint32_t (*amdgpu_block_rreg_t)(struct amdgpu_device*, uint32_t, uint32_t);
 typedef void (*amdgpu_block_wreg_t)(struct amdgpu_device*, uint32_t, uint32_t, uint32_t);
 
+struct amdgpu_ip_block_status {
+	bool valid;
+	bool sw;
+	bool hw;
+};
+
 struct amdgpu_device {
 	struct device			*dev;
 	struct drm_device		*ddev;
@@ -2008,7 +2014,7 @@ struct amdgpu_device {
 
 	const struct amdgpu_ip_block_version *ip_blocks;
 	int				num_ip_blocks;
-	bool				*ip_block_enabled;
+	struct amdgpu_ip_block_status	*ip_block_status;
 	struct mutex	mn_lock;
 	DECLARE_HASHTABLE(mn_hash, 7);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index d79009b65867..99f158e1baff 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1191,8 +1191,9 @@ static int amdgpu_early_init(struct amdgpu_device *adev)
 		return -EINVAL;
 	}
 
-	adev->ip_block_enabled = kcalloc(adev->num_ip_blocks, sizeof(bool), GFP_KERNEL);
-	if (adev->ip_block_enabled == NULL)
+	adev->ip_block_status = kcalloc(adev->num_ip_blocks,
+					sizeof(struct amdgpu_ip_block_status), GFP_KERNEL);
+	if (adev->ip_block_status == NULL)
 		return -ENOMEM;
 
 	if (adev->ip_blocks == NULL) {
@@ -1203,18 +1204,18 @@ static int amdgpu_early_init(struct amdgpu_device *adev)
 	for (i = 0; i < adev->num_ip_blocks; i++) {
 		if ((amdgpu_ip_block_mask & (1 << i)) == 0) {
 			DRM_ERROR("disabled ip block: %d\n", i);
-			adev->ip_block_enabled[i] = false;
+			adev->ip_block_status[i].valid = false;
 		} else {
 			if (adev->ip_blocks[i].funcs->early_init) {
 				r = adev->ip_blocks[i].funcs->early_init((void *)adev);
 				if (r == -ENOENT)
-					adev->ip_block_enabled[i] = false;
+					adev->ip_block_status[i].valid = false;
 				else if (r)
 					return r;
 				else
-					adev->ip_block_enabled[i] = true;
+					adev->ip_block_status[i].valid = true;
 			} else {
-				adev->ip_block_enabled[i] = true;
+				adev->ip_block_status[i].valid = true;
 			}
 		}
 	}
@@ -1227,11 +1228,12 @@ static int amdgpu_init(struct amdgpu_device *adev)
 	int i, r;
 
 	for (i = 0; i < adev->num_ip_blocks; i++) {
-		if (!adev->ip_block_enabled[i])
+		if (!adev->ip_block_status[i].valid)
 			continue;
 		r = adev->ip_blocks[i].funcs->sw_init((void *)adev);
 		if (r)
 			return r;
+		adev->ip_block_status[i].sw = true;
 		/* need to do gmc hw init early so we can allocate gpu mem */
 		if (adev->ip_blocks[i].type == AMD_IP_BLOCK_TYPE_GMC) {
 			r = amdgpu_vram_scratch_init(adev);
@@ -1243,11 +1245,12 @@ static int amdgpu_init(struct amdgpu_device *adev)
 			r = amdgpu_wb_init(adev);
 			if (r)
 				return r;
+			adev->ip_block_status[i].hw = true;
 		}
 	}
 
 	for (i = 0; i < adev->num_ip_blocks; i++) {
-		if (!adev->ip_block_enabled[i])
+		if (!adev->ip_block_status[i].sw)
 			continue;
 		/* gmc hw init is done early */
 		if (adev->ip_blocks[i].type == AMD_IP_BLOCK_TYPE_GMC)
@@ -1255,6 +1258,7 @@ static int amdgpu_init(struct amdgpu_device *adev)
 		r = adev->ip_blocks[i].funcs->hw_init((void *)adev);
 		if (r)
 			return r;
+		adev->ip_block_status[i].hw = true;
 	}
 
 	return 0;
@@ -1265,7 +1269,7 @@ static int amdgpu_late_init(struct amdgpu_device *adev)
 	int i = 0, r;
 
 	for (i = 0; i < adev->num_ip_blocks; i++) {
-		if (!adev->ip_block_enabled[i])
+		if (!adev->ip_block_status[i].valid)
 			continue;
 		/* enable clockgating to save power */
 		r = adev->ip_blocks[i].funcs->set_clockgating_state((void *)adev,
@@ -1287,7 +1291,7 @@ static int amdgpu_fini(struct amdgpu_device *adev)
 	int i, r;
 
 	for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
-		if (!adev->ip_block_enabled[i])
+		if (!adev->ip_block_status[i].hw)
 			continue;
 		if (adev->ip_blocks[i].type == AMD_IP_BLOCK_TYPE_GMC) {
 			amdgpu_wb_fini(adev);
@@ -1300,14 +1304,16 @@ static int amdgpu_fini(struct amdgpu_device *adev)
 			return r;
 		r = adev->ip_blocks[i].funcs->hw_fini((void *)adev);
 		/* XXX handle errors */
+		adev->ip_block_status[i].hw = false;
 	}
 
 	for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
-		if (!adev->ip_block_enabled[i])
+		if (!adev->ip_block_status[i].sw)
 			continue;
 		r = adev->ip_blocks[i].funcs->sw_fini((void *)adev);
 		/* XXX handle errors */
-		adev->ip_block_enabled[i] = false;
+		adev->ip_block_status[i].sw = false;
+		adev->ip_block_status[i].valid = false;
 	}
 
 	return 0;
@@ -1318,7 +1324,7 @@ static int amdgpu_suspend(struct amdgpu_device *adev)
 	int i, r;
 
 	for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
-		if (!adev->ip_block_enabled[i])
+		if (!adev->ip_block_status[i].valid)
 			continue;
 		/* ungate blocks so that suspend can properly shut them down */
 		r = adev->ip_blocks[i].funcs->set_clockgating_state((void *)adev,
@@ -1336,7 +1342,7 @@ static int amdgpu_resume(struct amdgpu_device *adev)
 	int i, r;
 
 	for (i = 0; i < adev->num_ip_blocks; i++) {
-		if (!adev->ip_block_enabled[i])
+		if (!adev->ip_block_status[i].valid)
 			continue;
 		r = adev->ip_blocks[i].funcs->resume(adev);
 		if (r)
@@ -1582,8 +1588,8 @@ void amdgpu_device_fini(struct amdgpu_device *adev)
 	amdgpu_fence_driver_fini(adev);
 	amdgpu_fbdev_fini(adev);
 	r = amdgpu_fini(adev);
-	kfree(adev->ip_block_enabled);
-	adev->ip_block_enabled = NULL;
+	kfree(adev->ip_block_status);
+	adev->ip_block_status = NULL;
 	adev->accel_working = false;
 	/* free i2c buses */
 	amdgpu_i2c_fini(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index ae43b58c9733..4afc507820c0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -449,7 +449,7 @@ out:
  * vital here, so they are not reported back to userspace.
  */
 static void amdgpu_gem_va_update_vm(struct amdgpu_device *adev,
-				    struct amdgpu_bo_va *bo_va)
+				    struct amdgpu_bo_va *bo_va, uint32_t operation)
 {
 	struct ttm_validate_buffer tv, *entry;
 	struct amdgpu_bo_list_entry *vm_bos;
@@ -485,7 +485,9 @@ static void amdgpu_gem_va_update_vm(struct amdgpu_device *adev,
 	if (r)
 		goto error_unlock;
 
-	r = amdgpu_vm_bo_update(adev, bo_va, &bo_va->bo->tbo.mem);
+
+	if (operation == AMDGPU_VA_OP_MAP)
+		r = amdgpu_vm_bo_update(adev, bo_va, &bo_va->bo->tbo.mem);
 
 error_unlock:
 	mutex_unlock(&bo_va->vm->mutex);
@@ -580,7 +582,7 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data,
 	}
 
 	if (!r && !(args->flags & AMDGPU_VM_DELAY_UPDATE))
-		amdgpu_gem_va_update_vm(adev, bo_va);
+		amdgpu_gem_va_update_vm(adev, bo_va, args->operation);
 
 	drm_gem_object_unreference_unlocked(gobj);
 	return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index 52dff75aac6f..bc0fac618a3f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -180,16 +180,16 @@ int amdgpu_ib_schedule(struct amdgpu_device *adev, unsigned num_ibs,
 	if (vm) {
 		/* do context switch */
 		amdgpu_vm_flush(ring, vm, ib->sync.last_vm_update);
-	}
 
-	if (vm && ring->funcs->emit_gds_switch)
-		amdgpu_ring_emit_gds_switch(ring, ib->vm->ids[ring->idx].id,
-					    ib->gds_base, ib->gds_size,
-					    ib->gws_base, ib->gws_size,
-					    ib->oa_base, ib->oa_size);
+		if (ring->funcs->emit_gds_switch)
+			amdgpu_ring_emit_gds_switch(ring, ib->vm->ids[ring->idx].id,
+						    ib->gds_base, ib->gds_size,
+						    ib->gws_base, ib->gws_size,
+						    ib->oa_base, ib->oa_size);
 
-	if (ring->funcs->emit_hdp_flush)
-		amdgpu_ring_emit_hdp_flush(ring);
+		if (ring->funcs->emit_hdp_flush)
+			amdgpu_ring_emit_hdp_flush(ring);
+	}
 
 	old_ctx = ring->current_ctx;
 	for (i = 0; i < num_ibs; ++i) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 31ad444c6386..9736892bcdf9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -235,7 +235,7 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 
 		for (i = 0; i < adev->num_ip_blocks; i++) {
 			if (adev->ip_blocks[i].type == type &&
-			    adev->ip_block_enabled[i]) {
+			    adev->ip_block_status[i].valid) {
 				ip.hw_ip_version_major = adev->ip_blocks[i].major;
 				ip.hw_ip_version_minor = adev->ip_blocks[i].minor;
 				ip.capabilities_flags = 0;
@@ -274,7 +274,7 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 
 		for (i = 0; i < adev->num_ip_blocks; i++)
 			if (adev->ip_blocks[i].type == type &&
-			    adev->ip_block_enabled[i] &&
+			    adev->ip_block_status[i].valid &&
 			    count < AMDGPU_HW_IP_INSTANCE_MAX_COUNT)
 				count++;
 
@@ -416,7 +416,7 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 		return n ? -EFAULT : 0;
 	}
 	case AMDGPU_INFO_DEV_INFO: {
-		struct drm_amdgpu_info_device dev_info;
+		struct drm_amdgpu_info_device dev_info = {};
 		struct amdgpu_cu_info cu_info;
 
 		dev_info.device_id = dev->pdev->device;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index 2c188fb9fd22..2db6ab0a543d 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -2561,7 +2561,7 @@ static bool gfx_v7_0_ring_emit_semaphore(struct amdgpu_ring *ring,
  * sheduling on the ring.  This function schedules the IB
  * on the gfx ring for execution by the GPU.
  */
-static void gfx_v7_0_ring_emit_ib(struct amdgpu_ring *ring,
+static void gfx_v7_0_ring_emit_ib_gfx(struct amdgpu_ring *ring,
 				  struct amdgpu_ib *ib)
 {
 	bool need_ctx_switch = ring->current_ctx != ib->ctx;
@@ -2569,15 +2569,10 @@ static void gfx_v7_0_ring_emit_ib(struct amdgpu_ring *ring,
 	u32 next_rptr = ring->wptr + 5;
 
 	/* drop the CE preamble IB for the same context */
-	if ((ring->type == AMDGPU_RING_TYPE_GFX) &&
-	    (ib->flags & AMDGPU_IB_FLAG_PREAMBLE) &&
-	    !need_ctx_switch)
+	if ((ib->flags & AMDGPU_IB_FLAG_PREAMBLE) && !need_ctx_switch)
 		return;
 
-	if (ring->type == AMDGPU_RING_TYPE_COMPUTE)
-		control |= INDIRECT_BUFFER_VALID;
-
-	if (need_ctx_switch && ring->type == AMDGPU_RING_TYPE_GFX)
+	if (need_ctx_switch)
 		next_rptr += 2;
 
 	next_rptr += 4;
@@ -2588,7 +2583,7 @@ static void gfx_v7_0_ring_emit_ib(struct amdgpu_ring *ring,
 	amdgpu_ring_write(ring, next_rptr);
 
 	/* insert SWITCH_BUFFER packet before first IB in the ring frame */
-	if (need_ctx_switch && ring->type == AMDGPU_RING_TYPE_GFX) {
+	if (need_ctx_switch) {
 		amdgpu_ring_write(ring, PACKET3(PACKET3_SWITCH_BUFFER, 0));
 		amdgpu_ring_write(ring, 0);
 	}
@@ -2611,6 +2606,35 @@ static void gfx_v7_0_ring_emit_ib(struct amdgpu_ring *ring,
 	amdgpu_ring_write(ring, control);
 }
 
+static void gfx_v7_0_ring_emit_ib_compute(struct amdgpu_ring *ring,
+				  struct amdgpu_ib *ib)
+{
+	u32 header, control = 0;
+	u32 next_rptr = ring->wptr + 5;
+
+	control |= INDIRECT_BUFFER_VALID;
+	next_rptr += 4;
+	amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
+	amdgpu_ring_write(ring, WRITE_DATA_DST_SEL(5) | WR_CONFIRM);
+	amdgpu_ring_write(ring, ring->next_rptr_gpu_addr & 0xfffffffc);
+	amdgpu_ring_write(ring, upper_32_bits(ring->next_rptr_gpu_addr) & 0xffffffff);
+	amdgpu_ring_write(ring, next_rptr);
+
+	header = PACKET3(PACKET3_INDIRECT_BUFFER, 2);
+
+	control |= ib->length_dw |
+			   (ib->vm ? (ib->vm->ids[ring->idx].id << 24) : 0);
+
+	amdgpu_ring_write(ring, header);
+	amdgpu_ring_write(ring,
+#ifdef __BIG_ENDIAN
+					  (2 << 0) |
+#endif
+					  (ib->gpu_addr & 0xFFFFFFFC));
+	amdgpu_ring_write(ring, upper_32_bits(ib->gpu_addr) & 0xFFFF);
+	amdgpu_ring_write(ring, control);
+}
+
 /**
  * gfx_v7_0_ring_test_ib - basic ring IB test
  *
@@ -5555,7 +5579,7 @@ static const struct amdgpu_ring_funcs gfx_v7_0_ring_funcs_gfx = {
 	.get_wptr = gfx_v7_0_ring_get_wptr_gfx,
 	.set_wptr = gfx_v7_0_ring_set_wptr_gfx,
 	.parse_cs = NULL,
-	.emit_ib = gfx_v7_0_ring_emit_ib,
+	.emit_ib = gfx_v7_0_ring_emit_ib_gfx,
 	.emit_fence = gfx_v7_0_ring_emit_fence_gfx,
 	.emit_semaphore = gfx_v7_0_ring_emit_semaphore,
 	.emit_vm_flush = gfx_v7_0_ring_emit_vm_flush,
@@ -5571,7 +5595,7 @@ static const struct amdgpu_ring_funcs gfx_v7_0_ring_funcs_compute = {
 	.get_wptr = gfx_v7_0_ring_get_wptr_compute,
 	.set_wptr = gfx_v7_0_ring_set_wptr_compute,
 	.parse_cs = NULL,
-	.emit_ib = gfx_v7_0_ring_emit_ib,
+	.emit_ib = gfx_v7_0_ring_emit_ib_compute,
 	.emit_fence = gfx_v7_0_ring_emit_fence_compute,
 	.emit_semaphore = gfx_v7_0_ring_emit_semaphore,
 	.emit_vm_flush = gfx_v7_0_ring_emit_vm_flush,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 1c7c992dea37..9e1d4ddbf475 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -3753,7 +3753,7 @@ static void gfx_v8_0_ring_emit_hdp_flush(struct amdgpu_ring *ring)
 	amdgpu_ring_write(ring, 0x20); /* poll interval */
 }
 
-static void gfx_v8_0_ring_emit_ib(struct amdgpu_ring *ring,
+static void gfx_v8_0_ring_emit_ib_gfx(struct amdgpu_ring *ring,
 				  struct amdgpu_ib *ib)
 {
 	bool need_ctx_switch = ring->current_ctx != ib->ctx;
@@ -3761,15 +3761,10 @@ static void gfx_v8_0_ring_emit_ib(struct amdgpu_ring *ring,
 	u32 next_rptr = ring->wptr + 5;
 
 	/* drop the CE preamble IB for the same context */
-	if ((ring->type == AMDGPU_RING_TYPE_GFX) &&
-	    (ib->flags & AMDGPU_IB_FLAG_PREAMBLE) &&
-	    !need_ctx_switch)
+	if ((ib->flags & AMDGPU_IB_FLAG_PREAMBLE) && !need_ctx_switch)
 		return;
 
-	if (ring->type == AMDGPU_RING_TYPE_COMPUTE)
-		control |= INDIRECT_BUFFER_VALID;
-
-	if (need_ctx_switch && ring->type == AMDGPU_RING_TYPE_GFX)
+	if (need_ctx_switch)
 		next_rptr += 2;
 
 	next_rptr += 4;
@@ -3780,7 +3775,7 @@ static void gfx_v8_0_ring_emit_ib(struct amdgpu_ring *ring,
 	amdgpu_ring_write(ring, next_rptr);
 
 	/* insert SWITCH_BUFFER packet before first IB in the ring frame */
-	if (need_ctx_switch && ring->type == AMDGPU_RING_TYPE_GFX) {
+	if (need_ctx_switch) {
 		amdgpu_ring_write(ring, PACKET3(PACKET3_SWITCH_BUFFER, 0));
 		amdgpu_ring_write(ring, 0);
 	}
@@ -3803,6 +3798,36 @@ static void gfx_v8_0_ring_emit_ib(struct amdgpu_ring *ring,
 	amdgpu_ring_write(ring, control);
 }
 
+static void gfx_v8_0_ring_emit_ib_compute(struct amdgpu_ring *ring,
+				  struct amdgpu_ib *ib)
+{
+	u32 header, control = 0;
+	u32 next_rptr = ring->wptr + 5;
+
+	control |= INDIRECT_BUFFER_VALID;
+
+	next_rptr += 4;
+	amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
+	amdgpu_ring_write(ring, WRITE_DATA_DST_SEL(5) | WR_CONFIRM);
+	amdgpu_ring_write(ring, ring->next_rptr_gpu_addr & 0xfffffffc);
+	amdgpu_ring_write(ring, upper_32_bits(ring->next_rptr_gpu_addr) & 0xffffffff);
+	amdgpu_ring_write(ring, next_rptr);
+
+	header = PACKET3(PACKET3_INDIRECT_BUFFER, 2);
+
+	control |= ib->length_dw |
+			   (ib->vm ? (ib->vm->ids[ring->idx].id << 24) : 0);
+
+	amdgpu_ring_write(ring, header);
+	amdgpu_ring_write(ring,
+#ifdef __BIG_ENDIAN
+					  (2 << 0) |
+#endif
+					  (ib->gpu_addr & 0xFFFFFFFC));
+	amdgpu_ring_write(ring, upper_32_bits(ib->gpu_addr) & 0xFFFF);
+	amdgpu_ring_write(ring, control);
+}
+
 static void gfx_v8_0_ring_emit_fence_gfx(struct amdgpu_ring *ring, u64 addr,
 					 u64 seq, unsigned flags)
 {
@@ -4224,7 +4249,7 @@ static const struct amdgpu_ring_funcs gfx_v8_0_ring_funcs_gfx = {
 	.get_wptr = gfx_v8_0_ring_get_wptr_gfx,
 	.set_wptr = gfx_v8_0_ring_set_wptr_gfx,
 	.parse_cs = NULL,
-	.emit_ib = gfx_v8_0_ring_emit_ib,
+	.emit_ib = gfx_v8_0_ring_emit_ib_gfx,
 	.emit_fence = gfx_v8_0_ring_emit_fence_gfx,
 	.emit_semaphore = gfx_v8_0_ring_emit_semaphore,
 	.emit_vm_flush = gfx_v8_0_ring_emit_vm_flush,
@@ -4240,7 +4265,7 @@ static const struct amdgpu_ring_funcs gfx_v8_0_ring_funcs_compute = {
 	.get_wptr = gfx_v8_0_ring_get_wptr_compute,
 	.set_wptr = gfx_v8_0_ring_set_wptr_compute,
 	.parse_cs = NULL,
-	.emit_ib = gfx_v8_0_ring_emit_ib,
+	.emit_ib = gfx_v8_0_ring_emit_ib_compute,
 	.emit_fence = gfx_v8_0_ring_emit_fence_compute,
 	.emit_semaphore = gfx_v8_0_ring_emit_semaphore,
 	.emit_vm_flush = gfx_v8_0_ring_emit_vm_flush,
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index 5b59d5ad7d1c..aac212297b49 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -230,10 +230,12 @@ update_connector_routing(struct drm_atomic_state *state, int conn_idx)
 	}
 
 	connector_state->best_encoder = new_encoder;
-	idx = drm_crtc_index(connector_state->crtc);
+	if (connector_state->crtc) {
+		idx = drm_crtc_index(connector_state->crtc);
 
-	crtc_state = state->crtc_states[idx];
-	crtc_state->mode_changed = true;
+		crtc_state = state->crtc_states[idx];
+		crtc_state->mode_changed = true;
+	}
 
 	DRM_DEBUG_ATOMIC("[CONNECTOR:%d:%s] using [ENCODER:%d:%s] on [CRTC:%d]\n",
 			 connector->base.id,
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 5f27290201e0..fd1de451c8c6 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -3303,15 +3303,14 @@ int intel_freq_opcode(struct drm_i915_private *dev_priv, int val);
 #define I915_READ64(reg)	dev_priv->uncore.funcs.mmio_readq(dev_priv, (reg), true)
 
 #define I915_READ64_2x32(lower_reg, upper_reg) ({			\
-		u32 upper = I915_READ(upper_reg);			\
-		u32 lower = I915_READ(lower_reg);			\
-		u32 tmp = I915_READ(upper_reg);				\
-		if (upper != tmp) {					\
-			upper = tmp;					\
-			lower = I915_READ(lower_reg);			\
-			WARN_ON(I915_READ(upper_reg) != upper);		\
-		}							\
-		(u64)upper << 32 | lower; })
+	u32 upper, lower, tmp;						\
+	tmp = I915_READ(upper_reg);					\
+	do {								\
+		upper = tmp;						\
+		lower = I915_READ(lower_reg);				\
+		tmp = I915_READ(upper_reg);				\
+	} while (upper != tmp);						\
+	(u64)upper << 32 | lower; })
 
 #define POSTING_READ(reg)	(void)I915_READ_NOTRACE(reg)
 #define POSTING_READ16(reg)	(void)I915_READ16_NOTRACE(reg)
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 56b52a4767d4..31e8269e6e3d 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1923,6 +1923,17 @@ static int ggtt_bind_vma(struct i915_vma *vma,
 		vma->vm->insert_entries(vma->vm, pages,
 					vma->node.start,
 					cache_level, pte_flags);
+
+		/* Note the inconsistency here is due to absence of the
+		 * aliasing ppgtt on gen4 and earlier. Though we always
+		 * request PIN_USER for execbuffer (translated to LOCAL_BIND),
+		 * without the appgtt, we cannot honour that request and so
+		 * must substitute it with a global binding. Since we do this
+		 * behind the upper layers back, we need to explicitly set
+		 * the bound flag ourselves.
+		 */
+		vma->bound |= GLOBAL_BIND;
+
 	}
 
 	if (dev_priv->mm.aliasing_ppgtt && flags & LOCAL_BIND) {
diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c
index 633bd1fcab69..d19c9db5e18c 100644
--- a/drivers/gpu/drm/i915/i915_gem_tiling.c
+++ b/drivers/gpu/drm/i915/i915_gem_tiling.c
@@ -464,7 +464,10 @@ i915_gem_get_tiling(struct drm_device *dev, void *data,
 	}
 
 	/* Hide bit 17 from the user -- see comment in i915_gem_set_tiling */
-	args->phys_swizzle_mode = args->swizzle_mode;
+	if (dev_priv->quirks & QUIRK_PIN_SWIZZLED_PAGES)
+		args->phys_swizzle_mode = I915_BIT_6_SWIZZLE_UNKNOWN;
+	else
+		args->phys_swizzle_mode = args->swizzle_mode;
 	if (args->swizzle_mode == I915_BIT_6_SWIZZLE_9_17)
 		args->swizzle_mode = I915_BIT_6_SWIZZLE_9;
 	if (args->swizzle_mode == I915_BIT_6_SWIZZLE_9_10_17)
diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_plane.c b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_plane.c
index 0d1dbb737933..247a424445f7 100644
--- a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_plane.c
+++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_plane.c
@@ -220,13 +220,15 @@ static int mdp4_plane_mode_set(struct drm_plane *plane,
 	uint32_t op_mode = 0;
 	uint32_t phasex_step = MDP4_VG_PHASE_STEP_DEFAULT;
 	uint32_t phasey_step = MDP4_VG_PHASE_STEP_DEFAULT;
-	enum mdp4_frame_format frame_type = mdp4_get_frame_format(fb);
+	enum mdp4_frame_format frame_type;
 
 	if (!(crtc && fb)) {
 		DBG("%s: disabled!", mdp4_plane->name);
 		return 0;
 	}
 
+	frame_type = mdp4_get_frame_format(fb);
+
 	/* src values are in Q16 fixed point, convert to integer: */
 	src_x = src_x >> 16;
 	src_y = src_y >> 16;
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c
index 206f758f7d64..e253db5de5aa 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c
@@ -76,7 +76,20 @@ static void mdp5_prepare_commit(struct msm_kms *kms, struct drm_atomic_state *st
 
 static void mdp5_complete_commit(struct msm_kms *kms, struct drm_atomic_state *state)
 {
+	int i;
 	struct mdp5_kms *mdp5_kms = to_mdp5_kms(to_mdp_kms(kms));
+	int nplanes = mdp5_kms->dev->mode_config.num_total_plane;
+
+	for (i = 0; i < nplanes; i++) {
+		struct drm_plane *plane = state->planes[i];
+		struct drm_plane_state *plane_state = state->plane_states[i];
+
+		if (!plane)
+			continue;
+
+		mdp5_plane_complete_commit(plane, plane_state);
+	}
+
 	mdp5_disable(mdp5_kms);
 }
 
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h
index e0eb24587c84..e79ac09b7216 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h
@@ -227,6 +227,8 @@ void mdp5_plane_install_properties(struct drm_plane *plane,
 		struct drm_mode_object *obj);
 uint32_t mdp5_plane_get_flush(struct drm_plane *plane);
 void mdp5_plane_complete_flip(struct drm_plane *plane);
+void mdp5_plane_complete_commit(struct drm_plane *plane,
+	struct drm_plane_state *state);
 enum mdp5_pipe mdp5_plane_pipe(struct drm_plane *plane);
 struct drm_plane *mdp5_plane_init(struct drm_device *dev,
 		enum mdp5_pipe pipe, bool private_plane, uint32_t reg_offset);
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c
index 57b8f56ae9d0..22275568ab8b 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c
@@ -31,8 +31,6 @@ struct mdp5_plane {
 
 	uint32_t nformats;
 	uint32_t formats[32];
-
-	bool enabled;
 };
 #define to_mdp5_plane(x) container_of(x, struct mdp5_plane, base)
 
@@ -56,22 +54,6 @@ static bool plane_enabled(struct drm_plane_state *state)
 	return state->fb && state->crtc;
 }
 
-static int mdp5_plane_disable(struct drm_plane *plane)
-{
-	struct mdp5_plane *mdp5_plane = to_mdp5_plane(plane);
-	struct mdp5_kms *mdp5_kms = get_kms(plane);
-	enum mdp5_pipe pipe = mdp5_plane->pipe;
-
-	DBG("%s: disable", mdp5_plane->name);
-
-	if (mdp5_kms) {
-		/* Release the memory we requested earlier from the SMP: */
-		mdp5_smp_release(mdp5_kms->smp, pipe);
-	}
-
-	return 0;
-}
-
 static void mdp5_plane_destroy(struct drm_plane *plane)
 {
 	struct mdp5_plane *mdp5_plane = to_mdp5_plane(plane);
@@ -224,7 +206,6 @@ static void mdp5_plane_atomic_update(struct drm_plane *plane,
 
 	if (!plane_enabled(state)) {
 		to_mdp5_plane_state(state)->pending = true;
-		mdp5_plane_disable(plane);
 	} else if (to_mdp5_plane_state(state)->mode_changed) {
 		int ret;
 		to_mdp5_plane_state(state)->pending = true;
@@ -602,6 +583,20 @@ uint32_t mdp5_plane_get_flush(struct drm_plane *plane)
 	return mdp5_plane->flush_mask;
 }
 
+/* called after vsync in thread context */
+void mdp5_plane_complete_commit(struct drm_plane *plane,
+	struct drm_plane_state *state)
+{
+	struct mdp5_kms *mdp5_kms = get_kms(plane);
+	struct mdp5_plane *mdp5_plane = to_mdp5_plane(plane);
+	enum mdp5_pipe pipe = mdp5_plane->pipe;
+
+	if (!plane_enabled(plane->state)) {
+		DBG("%s: free SMP", mdp5_plane->name);
+		mdp5_smp_release(mdp5_kms->smp, pipe);
+	}
+}
+
 /* initialize plane */
 struct drm_plane *mdp5_plane_init(struct drm_device *dev,
 		enum mdp5_pipe pipe, bool private_plane, uint32_t reg_offset)
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_smp.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_smp.c
index 16702aecf0df..64a27d86f2f5 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_smp.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_smp.c
@@ -34,22 +34,44 @@
  * and CANNOT be re-allocated (eg: MMB0 and MMB1 both tied to RGB0).
  *
  * For each block that can be dynamically allocated, it can be either
- * free, or pending/in-use by a client. The updates happen in three steps:
+ *     free:
+ *     The block is free.
+ *
+ *     pending:
+ *     The block is allocated to some client and not free.
+ *
+ *     configured:
+ *     The block is allocated to some client, and assigned to that
+ *     client in MDP5_MDP_SMP_ALLOC registers.
+ *
+ *     inuse:
+ *     The block is being actively used by a client.
+ *
+ * The updates happen in the following steps:
  *
  *  1) mdp5_smp_request():
  *     When plane scanout is setup, calculate required number of
- *     blocks needed per client, and request.  Blocks not inuse or
- *     pending by any other client are added to client's pending
- *     set.
+ *     blocks needed per client, and request. Blocks neither inuse nor
+ *     configured nor pending by any other client are added to client's
+ *     pending set.
+ *     For shrinking, blocks in pending but not in configured can be freed
+ *     directly, but those already in configured will be freed later by
+ *     mdp5_smp_commit.
  *
  *  2) mdp5_smp_configure():
  *     As hw is programmed, before FLUSH, MDP5_MDP_SMP_ALLOC registers
  *     are configured for the union(pending, inuse)
+ *     Current pending is copied to configured.
+ *     It is assumed that mdp5_smp_request and mdp5_smp_configure not run
+ *     concurrently for the same pipe.
  *
  *  3) mdp5_smp_commit():
- *     After next vblank, copy pending -> inuse.  Optionally update
+ *     After next vblank, copy configured -> inuse.  Optionally update
  *     MDP5_SMP_ALLOC registers if there are newly unused blocks
  *
+ *  4) mdp5_smp_release():
+ *     Must be called after the pipe is disabled and no longer uses any SMB
+ *
  * On the next vblank after changes have been committed to hw, the
  * client's pending blocks become it's in-use blocks (and no-longer
  * in-use blocks become available to other clients).
@@ -77,6 +99,9 @@ struct mdp5_smp {
 	struct mdp5_client_smp_state client_state[MAX_CLIENTS];
 };
 
+static void update_smp_state(struct mdp5_smp *smp,
+		u32 cid, mdp5_smp_state_t *assigned);
+
 static inline
 struct mdp5_kms *get_kms(struct mdp5_smp *smp)
 {
@@ -149,7 +174,12 @@ static int smp_request_block(struct mdp5_smp *smp,
 		for (i = cur_nblks; i > nblks; i--) {
 			int blk = find_first_bit(ps->pending, cnt);
 			clear_bit(blk, ps->pending);
-			/* don't clear in global smp_state until _commit() */
+
+			/* clear in global smp_state if not in configured
+			 * otherwise until _commit()
+			 */
+			if (!test_bit(blk, ps->configured))
+				clear_bit(blk, smp->state);
 		}
 	}
 
@@ -223,10 +253,33 @@ int mdp5_smp_request(struct mdp5_smp *smp, enum mdp5_pipe pipe, u32 fmt, u32 wid
 /* Release SMP blocks for all clients of the pipe */
 void mdp5_smp_release(struct mdp5_smp *smp, enum mdp5_pipe pipe)
 {
-	int i, nblks;
+	int i;
+	unsigned long flags;
+	int cnt = smp->blk_cnt;
+
+	for (i = 0; i < pipe2nclients(pipe); i++) {
+		mdp5_smp_state_t assigned;
+		u32 cid = pipe2client(pipe, i);
+		struct mdp5_client_smp_state *ps = &smp->client_state[cid];
+
+		spin_lock_irqsave(&smp->state_lock, flags);
+
+		/* clear hw assignment */
+		bitmap_or(assigned, ps->inuse, ps->configured, cnt);
+		update_smp_state(smp, CID_UNUSED, &assigned);
+
+		/* free to global pool */
+		bitmap_andnot(smp->state, smp->state, ps->pending, cnt);
+		bitmap_andnot(smp->state, smp->state, assigned, cnt);
+
+		/* clear client's infor */
+		bitmap_zero(ps->pending, cnt);
+		bitmap_zero(ps->configured, cnt);
+		bitmap_zero(ps->inuse, cnt);
+
+		spin_unlock_irqrestore(&smp->state_lock, flags);
+	}
 
-	for (i = 0, nblks = 0; i < pipe2nclients(pipe); i++)
-		smp_request_block(smp, pipe2client(pipe, i), 0);
 	set_fifo_thresholds(smp, pipe, 0);
 }
 
@@ -274,12 +327,20 @@ void mdp5_smp_configure(struct mdp5_smp *smp, enum mdp5_pipe pipe)
 		u32 cid = pipe2client(pipe, i);
 		struct mdp5_client_smp_state *ps = &smp->client_state[cid];
 
-		bitmap_or(assigned, ps->inuse, ps->pending, cnt);
+		/*
+		 * if vblank has not happened since last smp_configure
+		 * skip the configure for now
+		 */
+		if (!bitmap_equal(ps->inuse, ps->configured, cnt))
+			continue;
+
+		bitmap_copy(ps->configured, ps->pending, cnt);
+		bitmap_or(assigned, ps->inuse, ps->configured, cnt);
 		update_smp_state(smp, cid, &assigned);
 	}
 }
 
-/* step #3: after vblank, copy pending -> inuse: */
+/* step #3: after vblank, copy configured -> inuse: */
 void mdp5_smp_commit(struct mdp5_smp *smp, enum mdp5_pipe pipe)
 {
 	int cnt = smp->blk_cnt;
@@ -295,7 +356,7 @@ void mdp5_smp_commit(struct mdp5_smp *smp, enum mdp5_pipe pipe)
 		 * using, which can be released and made available to other
 		 * clients:
 		 */
-		if (bitmap_andnot(released, ps->inuse, ps->pending, cnt)) {
+		if (bitmap_andnot(released, ps->inuse, ps->configured, cnt)) {
 			unsigned long flags;
 
 			spin_lock_irqsave(&smp->state_lock, flags);
@@ -306,7 +367,7 @@ void mdp5_smp_commit(struct mdp5_smp *smp, enum mdp5_pipe pipe)
 			update_smp_state(smp, CID_UNUSED, &released);
 		}
 
-		bitmap_copy(ps->inuse, ps->pending, cnt);
+		bitmap_copy(ps->inuse, ps->configured, cnt);
 	}
 }
 
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_smp.h b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_smp.h
index e47179f63585..5b6c2363f592 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_smp.h
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_smp.h
@@ -23,6 +23,7 @@
 
 struct mdp5_client_smp_state {
 	mdp5_smp_state_t inuse;
+	mdp5_smp_state_t configured;
 	mdp5_smp_state_t pending;
 };
 
diff --git a/drivers/gpu/drm/msm/msm_atomic.c b/drivers/gpu/drm/msm/msm_atomic.c
index 1b22d8bfe142..1ceb4f22dd89 100644
--- a/drivers/gpu/drm/msm/msm_atomic.c
+++ b/drivers/gpu/drm/msm/msm_atomic.c
@@ -283,12 +283,8 @@ int msm_atomic_commit(struct drm_device *dev,
 
 	timeout = ktime_add_ms(ktime_get(), 1000);
 
-	ret = msm_wait_fence_interruptable(dev, c->fence, &timeout);
-	if (ret) {
-		WARN_ON(ret);  // TODO unswap state back?  or??
-		commit_destroy(c);
-		return ret;
-	}
+	/* uninterruptible wait */
+	msm_wait_fence(dev, c->fence, &timeout, false);
 
 	complete_commit(c);
 
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index b7ef56ed8d1c..d3467b115e04 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -637,8 +637,8 @@ static void msm_debugfs_cleanup(struct drm_minor *minor)
  * Fences:
  */
 
-int msm_wait_fence_interruptable(struct drm_device *dev, uint32_t fence,
-		ktime_t *timeout)
+int msm_wait_fence(struct drm_device *dev, uint32_t fence,
+		ktime_t *timeout , bool interruptible)
 {
 	struct msm_drm_private *priv = dev->dev_private;
 	int ret;
@@ -667,7 +667,12 @@ int msm_wait_fence_interruptable(struct drm_device *dev, uint32_t fence,
 			remaining_jiffies = timespec_to_jiffies(&ts);
 		}
 
-		ret = wait_event_interruptible_timeout(priv->fence_event,
+		if (interruptible)
+			ret = wait_event_interruptible_timeout(priv->fence_event,
+				fence_completed(dev, fence),
+				remaining_jiffies);
+		else
+			ret = wait_event_timeout(priv->fence_event,
 				fence_completed(dev, fence),
 				remaining_jiffies);
 
@@ -853,7 +858,7 @@ static int msm_ioctl_wait_fence(struct drm_device *dev, void *data,
 		return -EINVAL;
 	}
 
-	return msm_wait_fence_interruptable(dev, args->fence, &timeout);
+	return msm_wait_fence(dev, args->fence, &timeout, true);
 }
 
 static const struct drm_ioctl_desc msm_ioctls[] = {
diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index e7c5ea125d45..4ff0ec9c994b 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -164,8 +164,8 @@ int msm_atomic_commit(struct drm_device *dev,
 
 int msm_register_mmu(struct drm_device *dev, struct msm_mmu *mmu);
 
-int msm_wait_fence_interruptable(struct drm_device *dev, uint32_t fence,
-		ktime_t *timeout);
+int msm_wait_fence(struct drm_device *dev, uint32_t fence,
+		ktime_t *timeout, bool interruptible);
 int msm_queue_fence_cb(struct drm_device *dev,
 		struct msm_fence_cb *cb, uint32_t fence);
 void msm_update_fence(struct drm_device *dev, uint32_t fence);
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index f211b80e3a1e..c76cc853b08a 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -460,7 +460,7 @@ int msm_gem_cpu_prep(struct drm_gem_object *obj, uint32_t op, ktime_t *timeout)
 		if (op & MSM_PREP_NOSYNC)
 			timeout = NULL;
 
-		ret = msm_wait_fence_interruptable(dev, fence, timeout);
+		ret = msm_wait_fence(dev, fence, timeout, true);
 	}
 
 	/* TODO cache maintenance */
diff --git a/drivers/gpu/drm/msm/msm_gem_prime.c b/drivers/gpu/drm/msm/msm_gem_prime.c
index dd7a7ab603e2..831461bc98a5 100644
--- a/drivers/gpu/drm/msm/msm_gem_prime.c
+++ b/drivers/gpu/drm/msm/msm_gem_prime.c
@@ -23,8 +23,12 @@
 struct sg_table *msm_gem_prime_get_sg_table(struct drm_gem_object *obj)
 {
 	struct msm_gem_object *msm_obj = to_msm_bo(obj);
-	BUG_ON(!msm_obj->sgt);  /* should have already pinned! */
-	return msm_obj->sgt;
+	int npages = obj->size >> PAGE_SHIFT;
+
+	if (WARN_ON(!msm_obj->pages))  /* should have already pinned! */
+		return NULL;
+
+	return drm_prime_pages_to_sg(msm_obj->pages, npages);
 }
 
 void *msm_gem_prime_vmap(struct drm_gem_object *obj)
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 649024d4daf1..477cbb12809b 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -128,6 +128,7 @@ nouveau_cli_destroy(struct nouveau_cli *cli)
 	nvkm_vm_ref(NULL, &nvxx_client(&cli->base)->vm, NULL);
 	nvif_client_fini(&cli->base);
 	usif_client_fini(cli);
+	kfree(cli);
 }
 
 static void
@@ -865,8 +866,10 @@ nouveau_drm_preclose(struct drm_device *dev, struct drm_file *fpriv)
 
 	pm_runtime_get_sync(dev->dev);
 
+	mutex_lock(&cli->mutex);
 	if (cli->abi16)
 		nouveau_abi16_fini(cli->abi16);
+	mutex_unlock(&cli->mutex);
 
 	mutex_lock(&drm->client.mutex);
 	list_del(&cli->head);
diff --git a/drivers/gpu/drm/nouveau/nouveau_platform.c b/drivers/gpu/drm/nouveau/nouveau_platform.c
index 775277f1edb0..dcfbbfaf1739 100644
--- a/drivers/gpu/drm/nouveau/nouveau_platform.c
+++ b/drivers/gpu/drm/nouveau/nouveau_platform.c
@@ -92,6 +92,8 @@ static int nouveau_platform_power_down(struct nouveau_platform_gpu *gpu)
 	return 0;
 }
 
+#if IS_ENABLED(CONFIG_IOMMU_API)
+
 static void nouveau_platform_probe_iommu(struct device *dev,
 					 struct nouveau_platform_gpu *gpu)
 {
@@ -158,6 +160,20 @@ static void nouveau_platform_remove_iommu(struct device *dev,
 	}
 }
 
+#else
+
+static void nouveau_platform_probe_iommu(struct device *dev,
+					 struct nouveau_platform_gpu *gpu)
+{
+}
+
+static void nouveau_platform_remove_iommu(struct device *dev,
+					  struct nouveau_platform_gpu *gpu)
+{
+}
+
+#endif
+
 static int nouveau_platform_probe(struct platform_device *pdev)
 {
 	struct nouveau_platform_gpu *gpu;
diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c
index 18f449715788..7464aef34674 100644
--- a/drivers/gpu/drm/nouveau/nouveau_ttm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_ttm.c
@@ -175,15 +175,24 @@ nouveau_gart_manager_new(struct ttm_mem_type_manager *man,
 	node->page_shift = 12;
 
 	switch (drm->device.info.family) {
+	case NV_DEVICE_INFO_V0_TNT:
+	case NV_DEVICE_INFO_V0_CELSIUS:
+	case NV_DEVICE_INFO_V0_KELVIN:
+	case NV_DEVICE_INFO_V0_RANKINE:
+	case NV_DEVICE_INFO_V0_CURIE:
+		break;
 	case NV_DEVICE_INFO_V0_TESLA:
 		if (drm->device.info.chipset != 0x50)
 			node->memtype = (nvbo->tile_flags & 0x7f00) >> 8;
 		break;
 	case NV_DEVICE_INFO_V0_FERMI:
 	case NV_DEVICE_INFO_V0_KEPLER:
+	case NV_DEVICE_INFO_V0_MAXWELL:
 		node->memtype = (nvbo->tile_flags & 0xff00) >> 8;
 		break;
 	default:
+		NV_WARN(drm, "%s: unhandled family type %x\n", __func__,
+			drm->device.info.family);
 		break;
 	}
 
diff --git a/drivers/gpu/drm/nouveau/nv04_fbcon.c b/drivers/gpu/drm/nouveau/nv04_fbcon.c
index 4ef602c5469d..495c57644ced 100644
--- a/drivers/gpu/drm/nouveau/nv04_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nv04_fbcon.c
@@ -203,7 +203,7 @@ nv04_fbcon_accel_init(struct fb_info *info)
 	if (ret)
 		return ret;
 
-	if (RING_SPACE(chan, 49)) {
+	if (RING_SPACE(chan, 49 + (device->info.chipset >= 0x11 ? 4 : 0))) {
 		nouveau_fbcon_gpu_lockup(info);
 		return 0;
 	}
diff --git a/drivers/gpu/drm/nouveau/nv50_display.c b/drivers/gpu/drm/nouveau/nv50_display.c
index 7da7958556a3..981342d142ff 100644
--- a/drivers/gpu/drm/nouveau/nv50_display.c
+++ b/drivers/gpu/drm/nouveau/nv50_display.c
@@ -979,7 +979,7 @@ nv50_crtc_cursor_show_hide(struct nouveau_crtc *nv_crtc, bool show, bool update)
 {
 	struct nv50_mast *mast = nv50_mast(nv_crtc->base.dev);
 
-	if (show && nv_crtc->cursor.nvbo)
+	if (show && nv_crtc->cursor.nvbo && nv_crtc->base.enabled)
 		nv50_crtc_cursor_show(nv_crtc);
 	else
 		nv50_crtc_cursor_hide(nv_crtc);
diff --git a/drivers/gpu/drm/nouveau/nv50_fbcon.c b/drivers/gpu/drm/nouveau/nv50_fbcon.c
index 394c89abcc97..901130b06072 100644
--- a/drivers/gpu/drm/nouveau/nv50_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nv50_fbcon.c
@@ -188,7 +188,7 @@ nv50_fbcon_accel_init(struct fb_info *info)
 	if (ret)
 		return ret;
 
-	ret = RING_SPACE(chan, 59);
+	ret = RING_SPACE(chan, 58);
 	if (ret) {
 		nouveau_fbcon_gpu_lockup(info);
 		return ret;
@@ -252,6 +252,7 @@ nv50_fbcon_accel_init(struct fb_info *info)
 	OUT_RING(chan, info->var.yres_virtual);
 	OUT_RING(chan, upper_32_bits(fb->vma.offset));
 	OUT_RING(chan, lower_32_bits(fb->vma.offset));
+	FIRE_RING(chan);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/nvc0_fbcon.c b/drivers/gpu/drm/nouveau/nvc0_fbcon.c
index 61246677e8dc..fcd2e5f27bb9 100644
--- a/drivers/gpu/drm/nouveau/nvc0_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nvc0_fbcon.c
@@ -188,7 +188,7 @@ nvc0_fbcon_accel_init(struct fb_info *info)
 		return -EINVAL;
 	}
 
-	ret = RING_SPACE(chan, 60);
+	ret = RING_SPACE(chan, 58);
 	if (ret) {
 		WARN_ON(1);
 		nouveau_fbcon_gpu_lockup(info);
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gf110.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gf110.c
index 9ef6728c528d..7f2f05f78cc8 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gf110.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gf110.c
@@ -809,7 +809,7 @@ exec_lookup(struct nv50_disp_priv *priv, int head, int or, u32 ctrl,
 		case 0x00000900: type = DCB_OUTPUT_DP; mask = 2; break;
 		default:
 			nv_error(priv, "unknown SOR mc 0x%08x\n", ctrl);
-			return 0x0000;
+			return NULL;
 		}
 	}
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk104.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk104.c
index e10f9644140f..52c22b026005 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk104.c
@@ -166,14 +166,30 @@ gk104_fifo_context_attach(struct nvkm_object *parent,
 }
 
 static int
+gk104_fifo_chan_kick(struct gk104_fifo_chan *chan)
+{
+	struct nvkm_object *obj = (void *)chan;
+	struct gk104_fifo_priv *priv = (void *)obj->engine;
+
+	nv_wr32(priv, 0x002634, chan->base.chid);
+	if (!nv_wait(priv, 0x002634, 0x100000, 0x000000)) {
+		nv_error(priv, "channel %d [%s] kick timeout\n",
+			 chan->base.chid, nvkm_client_name(chan));
+		return -EBUSY;
+	}
+
+	return 0;
+}
+
+static int
 gk104_fifo_context_detach(struct nvkm_object *parent, bool suspend,
 			  struct nvkm_object *object)
 {
 	struct nvkm_bar *bar = nvkm_bar(parent);
-	struct gk104_fifo_priv *priv = (void *)parent->engine;
 	struct gk104_fifo_base *base = (void *)parent->parent;
 	struct gk104_fifo_chan *chan = (void *)parent;
 	u32 addr;
+	int ret;
 
 	switch (nv_engidx(object->engine)) {
 	case NVDEV_ENGINE_SW    : return 0;
@@ -188,13 +204,9 @@ gk104_fifo_context_detach(struct nvkm_object *parent, bool suspend,
 		return -EINVAL;
 	}
 
-	nv_wr32(priv, 0x002634, chan->base.chid);
-	if (!nv_wait(priv, 0x002634, 0xffffffff, chan->base.chid)) {
-		nv_error(priv, "channel %d [%s] kick timeout\n",
-			 chan->base.chid, nvkm_client_name(chan));
-		if (suspend)
-			return -EBUSY;
-	}
+	ret = gk104_fifo_chan_kick(chan);
+	if (ret && suspend)
+		return ret;
 
 	if (addr) {
 		nv_wo32(base, addr + 0x00, 0x00000000);
@@ -319,6 +331,7 @@ gk104_fifo_chan_fini(struct nvkm_object *object, bool suspend)
 		gk104_fifo_runlist_update(priv, chan->engine);
 	}
 
+	gk104_fifo_chan_kick(chan);
 	nv_wr32(priv, 0x800000 + (chid * 8), 0x00000000);
 	return nvkm_fifo_channel_fini(&chan->base, suspend);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
index 5606c25e5d02..ca11ddb6ed46 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
@@ -663,6 +663,37 @@ gf100_gr_zbc_init(struct gf100_gr_priv *priv)
 		gf100_gr_zbc_clear_depth(priv, index);
 }
 
+/**
+ * Wait until GR goes idle. GR is considered idle if it is disabled by the
+ * MC (0x200) register, or GR is not busy and a context switch is not in
+ * progress.
+ */
+int
+gf100_gr_wait_idle(struct gf100_gr_priv *priv)
+{
+	unsigned long end_jiffies = jiffies + msecs_to_jiffies(2000);
+	bool gr_enabled, ctxsw_active, gr_busy;
+
+	do {
+		/*
+		 * required to make sure FIFO_ENGINE_STATUS (0x2640) is
+		 * up-to-date
+		 */
+		nv_rd32(priv, 0x400700);
+
+		gr_enabled = nv_rd32(priv, 0x200) & 0x1000;
+		ctxsw_active = nv_rd32(priv, 0x2640) & 0x8000;
+		gr_busy = nv_rd32(priv, 0x40060c) & 0x1;
+
+		if (!gr_enabled || (!gr_busy && !ctxsw_active))
+			return 0;
+	} while (time_before(jiffies, end_jiffies));
+
+	nv_error(priv, "wait for idle timeout (en: %d, ctxsw: %d, busy: %d)\n",
+		 gr_enabled, ctxsw_active, gr_busy);
+	return -EAGAIN;
+}
+
 void
 gf100_gr_mmio(struct gf100_gr_priv *priv, const struct gf100_gr_pack *p)
 {
@@ -699,7 +730,13 @@ gf100_gr_icmd(struct gf100_gr_priv *priv, const struct gf100_gr_pack *p)
 
 		while (addr < next) {
 			nv_wr32(priv, 0x400200, addr);
-			nv_wait(priv, 0x400700, 0x00000002, 0x00000000);
+			/**
+			 * Wait for GR to go idle after submitting a
+			 * GO_IDLE bundle
+			 */
+			if ((addr & 0xffff) == 0xe100)
+				gf100_gr_wait_idle(priv);
+			nv_wait(priv, 0x400700, 0x00000004, 0x00000000);
 			addr += init->pitch;
 		}
 	}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h
index 8af1a89eda84..c9533fdac4fc 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h
@@ -181,6 +181,7 @@ struct gf100_gr_oclass {
 	int ppc_nr;
 };
 
+int  gf100_gr_wait_idle(struct gf100_gr_priv *);
 void gf100_gr_mmio(struct gf100_gr_priv *, const struct gf100_gr_pack *);
 void gf100_gr_icmd(struct gf100_gr_priv *, const struct gf100_gr_pack *);
 void gf100_gr_mthd(struct gf100_gr_priv *, const struct gf100_gr_pack *);
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/pm/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/pm/base.c
index 2006c445938d..4cf36a3aa814 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/pm/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/pm/base.c
@@ -332,9 +332,12 @@ static void
 nvkm_perfctx_dtor(struct nvkm_object *object)
 {
 	struct nvkm_pm *ppm = (void *)object->engine;
+	struct nvkm_perfctx *ctx = (void *)object;
+
 	mutex_lock(&nv_subdev(ppm)->mutex);
-	nvkm_engctx_destroy(&ppm->context->base);
-	ppm->context = NULL;
+	nvkm_engctx_destroy(&ctx->base);
+	if (ppm->context == ctx)
+		ppm->context = NULL;
 	mutex_unlock(&nv_subdev(ppm)->mutex);
 }
 
@@ -355,12 +358,11 @@ nvkm_perfctx_ctor(struct nvkm_object *parent, struct nvkm_object *engine,
 	mutex_lock(&nv_subdev(ppm)->mutex);
 	if (ppm->context == NULL)
 		ppm->context = ctx;
-	mutex_unlock(&nv_subdev(ppm)->mutex);
-
 	if (ctx != ppm->context)
-		return -EBUSY;
+		ret = -EBUSY;
+	mutex_unlock(&nv_subdev(ppm)->mutex);
 
-	return 0;
+	return ret;
 }
 
 struct nvkm_oclass
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/init.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/init.c
index f67cdae1e90a..f4611e3f0971 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/init.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/init.c
@@ -1285,6 +1285,44 @@ init_zm_reg_sequence(struct nvbios_init *init)
 }
 
 /**
+ * INIT_PLL_INDIRECT - opcode 0x59
+ *
+ */
+static void
+init_pll_indirect(struct nvbios_init *init)
+{
+	struct nvkm_bios *bios = init->bios;
+	u32  reg = nv_ro32(bios, init->offset + 1);
+	u16 addr = nv_ro16(bios, init->offset + 5);
+	u32 freq = (u32)nv_ro16(bios, addr) * 1000;
+
+	trace("PLL_INDIRECT\tR[0x%06x] =PLL= VBIOS[%04x] = %dkHz\n",
+	      reg, addr, freq);
+	init->offset += 7;
+
+	init_prog_pll(init, reg, freq);
+}
+
+/**
+ * INIT_ZM_REG_INDIRECT - opcode 0x5a
+ *
+ */
+static void
+init_zm_reg_indirect(struct nvbios_init *init)
+{
+	struct nvkm_bios *bios = init->bios;
+	u32  reg = nv_ro32(bios, init->offset + 1);
+	u16 addr = nv_ro16(bios, init->offset + 5);
+	u32 data = nv_ro32(bios, addr);
+
+	trace("ZM_REG_INDIRECT\tR[0x%06x] = VBIOS[0x%04x] = 0x%08x\n",
+	      reg, addr, data);
+	init->offset += 7;
+
+	init_wr32(init, addr, data);
+}
+
+/**
  * INIT_SUB_DIRECT - opcode 0x5b
  *
  */
@@ -2145,6 +2183,8 @@ static struct nvbios_init_opcode {
 	[0x56] = { init_condition_time },
 	[0x57] = { init_ltime },
 	[0x58] = { init_zm_reg_sequence },
+	[0x59] = { init_pll_indirect },
+	[0x5a] = { init_zm_reg_indirect },
 	[0x5b] = { init_sub_direct },
 	[0x5c] = { init_jump },
 	[0x5e] = { init_i2c_if },
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gt215.c b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gt215.c
index 822d32a28d6e..065e9f5c8db9 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gt215.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gt215.c
@@ -180,7 +180,8 @@ gt215_clk_info(struct nvkm_clk *clock, int clk, u32 khz,
 	       struct gt215_clk_info *info)
 {
 	struct gt215_clk_priv *priv = (void *)clock;
-	u32 oclk, sclk, sdiv, diff;
+	u32 oclk, sclk, sdiv;
+	s32 diff;
 
 	info->clk = 0;
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gk20a.c b/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gk20a.c
index c0fdb89e74ac..24dcdfb58a8d 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gk20a.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gk20a.c
@@ -38,6 +38,14 @@ gk20a_ibus_init_priv_ring(struct gk20a_ibus_priv *priv)
 	nv_wr32(priv, 0x12004c, 0x4);
 	nv_wr32(priv, 0x122204, 0x2);
 	nv_rd32(priv, 0x122204);
+
+	/*
+	 * Bug: increase clock timeout to avoid operation failure at high
+	 * gpcclk rate.
+	 */
+	nv_wr32(priv, 0x122354, 0x800);
+	nv_wr32(priv, 0x128328, 0x800);
+	nv_wr32(priv, 0x124320, 0x800);
 }
 
 static void
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv04.c b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv04.c
index 80614f1b2074..282143f49d72 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv04.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv04.c
@@ -50,7 +50,12 @@ nv04_instobj_dtor(struct nvkm_object *object)
 {
 	struct nv04_instmem_priv *priv = (void *)nvkm_instmem(object);
 	struct nv04_instobj_priv *node = (void *)object;
+	struct nvkm_subdev *subdev = (void *)priv;
+
+	mutex_lock(&subdev->mutex);
 	nvkm_mm_free(&priv->heap, &node->mem);
+	mutex_unlock(&subdev->mutex);
+
 	nvkm_instobj_destroy(&node->base);
 }
 
@@ -62,6 +67,7 @@ nv04_instobj_ctor(struct nvkm_object *parent, struct nvkm_object *engine,
 	struct nv04_instmem_priv *priv = (void *)nvkm_instmem(parent);
 	struct nv04_instobj_priv *node;
 	struct nvkm_instobj_args *args = data;
+	struct nvkm_subdev *subdev = (void *)priv;
 	int ret;
 
 	if (!args->align)
@@ -72,8 +78,10 @@ nv04_instobj_ctor(struct nvkm_object *parent, struct nvkm_object *engine,
 	if (ret)
 		return ret;
 
+	mutex_lock(&subdev->mutex);
 	ret = nvkm_mm_head(&priv->heap, 0, 1, args->size, args->size,
 			   args->align, &node->mem);
+	mutex_unlock(&subdev->mutex);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c
index dd39f434b4a7..c3872598b85a 100644
--- a/drivers/gpu/drm/radeon/atombios_encoders.c
+++ b/drivers/gpu/drm/radeon/atombios_encoders.c
@@ -2299,8 +2299,7 @@ radeon_atom_encoder_mode_set(struct drm_encoder *encoder,
 	encoder_mode = atombios_get_encoder_mode(encoder);
 	if (connector && (radeon_audio != 0) &&
 	    ((encoder_mode == ATOM_ENCODER_MODE_HDMI) ||
-	     (ENCODER_MODE_IS_DP(encoder_mode) &&
-	      drm_detect_monitor_audio(radeon_connector_edid(connector)))))
+	     ENCODER_MODE_IS_DP(encoder_mode)))
 		radeon_audio_mode_set(encoder, adjusted_mode);
 }
 
diff --git a/drivers/gpu/drm/radeon/dce6_afmt.c b/drivers/gpu/drm/radeon/dce6_afmt.c
index 68fd9fc677e3..44480c1b9738 100644
--- a/drivers/gpu/drm/radeon/dce6_afmt.c
+++ b/drivers/gpu/drm/radeon/dce6_afmt.c
@@ -93,30 +93,26 @@ void dce6_afmt_select_pin(struct drm_encoder *encoder)
 	struct radeon_device *rdev = encoder->dev->dev_private;
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
-	u32 offset;
 
-	if (!dig || !dig->afmt || !dig->afmt->pin)
+	if (!dig || !dig->afmt || !dig->pin)
 		return;
 
-	offset = dig->afmt->offset;
-
-	WREG32(AFMT_AUDIO_SRC_CONTROL + offset,
-	       AFMT_AUDIO_SRC_SELECT(dig->afmt->pin->id));
+	WREG32(AFMT_AUDIO_SRC_CONTROL +  dig->afmt->offset,
+	       AFMT_AUDIO_SRC_SELECT(dig->pin->id));
 }
 
 void dce6_afmt_write_latency_fields(struct drm_encoder *encoder,
-		struct drm_connector *connector, struct drm_display_mode *mode)
+				    struct drm_connector *connector,
+				    struct drm_display_mode *mode)
 {
 	struct radeon_device *rdev = encoder->dev->dev_private;
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
-	u32 tmp = 0, offset;
+	u32 tmp = 0;
 
-	if (!dig || !dig->afmt || !dig->afmt->pin)
+	if (!dig || !dig->afmt || !dig->pin)
 		return;
 
-	offset = dig->afmt->pin->offset;
-
 	if (mode->flags & DRM_MODE_FLAG_INTERLACE) {
 		if (connector->latency_present[1])
 			tmp = VIDEO_LIPSYNC(connector->video_latency[1]) |
@@ -130,24 +126,24 @@ void dce6_afmt_write_latency_fields(struct drm_encoder *encoder,
 		else
 			tmp = VIDEO_LIPSYNC(0) | AUDIO_LIPSYNC(0);
 	}
-	WREG32_ENDPOINT(offset, AZ_F0_CODEC_PIN_CONTROL_RESPONSE_LIPSYNC, tmp);
+	WREG32_ENDPOINT(dig->pin->offset,
+			AZ_F0_CODEC_PIN_CONTROL_RESPONSE_LIPSYNC, tmp);
 }
 
 void dce6_afmt_hdmi_write_speaker_allocation(struct drm_encoder *encoder,
-	u8 *sadb, int sad_count)
+					     u8 *sadb, int sad_count)
 {
 	struct radeon_device *rdev = encoder->dev->dev_private;
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
-	u32 offset, tmp;
+	u32 tmp;
 
-	if (!dig || !dig->afmt || !dig->afmt->pin)
+	if (!dig || !dig->afmt || !dig->pin)
 		return;
 
-	offset = dig->afmt->pin->offset;
-
 	/* program the speaker allocation */
-	tmp = RREG32_ENDPOINT(offset, AZ_F0_CODEC_PIN_CONTROL_CHANNEL_SPEAKER);
+	tmp = RREG32_ENDPOINT(dig->pin->offset,
+			      AZ_F0_CODEC_PIN_CONTROL_CHANNEL_SPEAKER);
 	tmp &= ~(DP_CONNECTION | SPEAKER_ALLOCATION_MASK);
 	/* set HDMI mode */
 	tmp |= HDMI_CONNECTION;
@@ -155,24 +151,24 @@ void dce6_afmt_hdmi_write_speaker_allocation(struct drm_encoder *encoder,
 		tmp |= SPEAKER_ALLOCATION(sadb[0]);
 	else
 		tmp |= SPEAKER_ALLOCATION(5); /* stereo */
-	WREG32_ENDPOINT(offset, AZ_F0_CODEC_PIN_CONTROL_CHANNEL_SPEAKER, tmp);
+	WREG32_ENDPOINT(dig->pin->offset,
+			AZ_F0_CODEC_PIN_CONTROL_CHANNEL_SPEAKER, tmp);
 }
 
 void dce6_afmt_dp_write_speaker_allocation(struct drm_encoder *encoder,
-	u8 *sadb, int sad_count)
+					   u8 *sadb, int sad_count)
 {
 	struct radeon_device *rdev = encoder->dev->dev_private;
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
-	u32 offset, tmp;
+	u32 tmp;
 
-	if (!dig || !dig->afmt || !dig->afmt->pin)
+	if (!dig || !dig->afmt || !dig->pin)
 		return;
 
-	offset = dig->afmt->pin->offset;
-
 	/* program the speaker allocation */
-	tmp = RREG32_ENDPOINT(offset, AZ_F0_CODEC_PIN_CONTROL_CHANNEL_SPEAKER);
+	tmp = RREG32_ENDPOINT(dig->pin->offset,
+			      AZ_F0_CODEC_PIN_CONTROL_CHANNEL_SPEAKER);
 	tmp &= ~(HDMI_CONNECTION | SPEAKER_ALLOCATION_MASK);
 	/* set DP mode */
 	tmp |= DP_CONNECTION;
@@ -180,13 +176,13 @@ void dce6_afmt_dp_write_speaker_allocation(struct drm_encoder *encoder,
 		tmp |= SPEAKER_ALLOCATION(sadb[0]);
 	else
 		tmp |= SPEAKER_ALLOCATION(5); /* stereo */
-	WREG32_ENDPOINT(offset, AZ_F0_CODEC_PIN_CONTROL_CHANNEL_SPEAKER, tmp);
+	WREG32_ENDPOINT(dig->pin->offset,
+			AZ_F0_CODEC_PIN_CONTROL_CHANNEL_SPEAKER, tmp);
 }
 
 void dce6_afmt_write_sad_regs(struct drm_encoder *encoder,
-	struct cea_sad *sads, int sad_count)
+			      struct cea_sad *sads, int sad_count)
 {
-	u32 offset;
 	int i;
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
@@ -206,11 +202,9 @@ void dce6_afmt_write_sad_regs(struct drm_encoder *encoder,
 		{ AZ_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR13, HDMI_AUDIO_CODING_TYPE_WMA_PRO },
 	};
 
-	if (!dig || !dig->afmt || !dig->afmt->pin)
+	if (!dig || !dig->afmt || !dig->pin)
 		return;
 
-	offset = dig->afmt->pin->offset;
-
 	for (i = 0; i < ARRAY_SIZE(eld_reg_to_type); i++) {
 		u32 value = 0;
 		u8 stereo_freqs = 0;
@@ -237,7 +231,7 @@ void dce6_afmt_write_sad_regs(struct drm_encoder *encoder,
 
 		value |= SUPPORTED_FREQUENCIES_STEREO(stereo_freqs);
 
-		WREG32_ENDPOINT(offset, eld_reg_to_type[i][0], value);
+		WREG32_ENDPOINT(dig->pin->offset, eld_reg_to_type[i][0], value);
 	}
 }
 
@@ -253,7 +247,7 @@ void dce6_audio_enable(struct radeon_device *rdev,
 }
 
 void dce6_hdmi_audio_set_dto(struct radeon_device *rdev,
-	struct radeon_crtc *crtc, unsigned int clock)
+			     struct radeon_crtc *crtc, unsigned int clock)
 {
 	/* Two dtos; generally use dto0 for HDMI */
 	u32 value = 0;
@@ -272,7 +266,7 @@ void dce6_hdmi_audio_set_dto(struct radeon_device *rdev,
 }
 
 void dce6_dp_audio_set_dto(struct radeon_device *rdev,
-	struct radeon_crtc *crtc, unsigned int clock)
+			   struct radeon_crtc *crtc, unsigned int clock)
 {
 	/* Two dtos; generally use dto1 for DP */
 	u32 value = 0;
diff --git a/drivers/gpu/drm/radeon/radeon_audio.c b/drivers/gpu/drm/radeon/radeon_audio.c
index fa719c53449b..fbc8d88d6e5d 100644
--- a/drivers/gpu/drm/radeon/radeon_audio.c
+++ b/drivers/gpu/drm/radeon/radeon_audio.c
@@ -245,6 +245,28 @@ static struct radeon_audio_funcs dce6_dp_funcs = {
 static void radeon_audio_enable(struct radeon_device *rdev,
 				struct r600_audio_pin *pin, u8 enable_mask)
 {
+	struct drm_encoder *encoder;
+	struct radeon_encoder *radeon_encoder;
+	struct radeon_encoder_atom_dig *dig;
+	int pin_count = 0;
+
+	if (!pin)
+		return;
+
+	if (rdev->mode_info.mode_config_initialized) {
+		list_for_each_entry(encoder, &rdev->ddev->mode_config.encoder_list, head) {
+			if (radeon_encoder_is_digital(encoder)) {
+				radeon_encoder = to_radeon_encoder(encoder);
+				dig = radeon_encoder->enc_priv;
+				if (dig->pin == pin)
+					pin_count++;
+			}
+		}
+
+		if ((pin_count > 1) && (enable_mask == 0))
+			return;
+	}
+
 	if (rdev->audio.funcs->enable)
 		rdev->audio.funcs->enable(rdev, pin, enable_mask);
 }
@@ -336,24 +358,13 @@ void radeon_audio_endpoint_wreg(struct radeon_device *rdev, u32 offset,
 
 static void radeon_audio_write_sad_regs(struct drm_encoder *encoder)
 {
-	struct radeon_encoder *radeon_encoder;
-	struct drm_connector *connector;
-	struct radeon_connector *radeon_connector = NULL;
+	struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
+	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 	struct cea_sad *sads;
 	int sad_count;
 
-	list_for_each_entry(connector,
-		&encoder->dev->mode_config.connector_list, head) {
-		if (connector->encoder == encoder) {
-			radeon_connector = to_radeon_connector(connector);
-			break;
-		}
-	}
-
-	if (!radeon_connector) {
-		DRM_ERROR("Couldn't find encoder's connector\n");
+	if (!connector)
 		return;
-	}
 
 	sad_count = drm_edid_to_sad(radeon_connector_edid(connector), &sads);
 	if (sad_count <= 0) {
@@ -362,8 +373,6 @@ static void radeon_audio_write_sad_regs(struct drm_encoder *encoder)
 	}
 	BUG_ON(!sads);
 
-	radeon_encoder = to_radeon_encoder(encoder);
-
 	if (radeon_encoder->audio && radeon_encoder->audio->write_sad_regs)
 		radeon_encoder->audio->write_sad_regs(encoder, sads, sad_count);
 
@@ -372,27 +381,16 @@ static void radeon_audio_write_sad_regs(struct drm_encoder *encoder)
 
 static void radeon_audio_write_speaker_allocation(struct drm_encoder *encoder)
 {
+	struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
-	struct drm_connector *connector;
-	struct radeon_connector *radeon_connector = NULL;
 	u8 *sadb = NULL;
 	int sad_count;
 
-	list_for_each_entry(connector,
-			    &encoder->dev->mode_config.connector_list, head) {
-		if (connector->encoder == encoder) {
-			radeon_connector = to_radeon_connector(connector);
-			break;
-		}
-	}
-
-	if (!radeon_connector) {
-		DRM_ERROR("Couldn't find encoder's connector\n");
+	if (!connector)
 		return;
-	}
 
-	sad_count = drm_edid_to_speaker_allocation(
-		radeon_connector_edid(connector), &sadb);
+	sad_count = drm_edid_to_speaker_allocation(radeon_connector_edid(connector),
+						   &sadb);
 	if (sad_count < 0) {
 		DRM_DEBUG("Couldn't read Speaker Allocation Data Block: %d\n",
 			  sad_count);
@@ -406,26 +404,13 @@ static void radeon_audio_write_speaker_allocation(struct drm_encoder *encoder)
 }
 
 static void radeon_audio_write_latency_fields(struct drm_encoder *encoder,
-	struct drm_display_mode *mode)
+					      struct drm_display_mode *mode)
 {
-	struct radeon_encoder *radeon_encoder;
-	struct drm_connector *connector;
-	struct radeon_connector *radeon_connector = 0;
-
-	list_for_each_entry(connector,
-		&encoder->dev->mode_config.connector_list, head) {
-		if (connector->encoder == encoder) {
-			radeon_connector = to_radeon_connector(connector);
-			break;
-		}
-	}
+	struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
+	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 
-	if (!radeon_connector) {
-		DRM_ERROR("Couldn't find encoder's connector\n");
+	if (!connector)
 		return;
-	}
-
-	radeon_encoder = to_radeon_encoder(encoder);
 
 	if (radeon_encoder->audio && radeon_encoder->audio->write_latency_fields)
 		radeon_encoder->audio->write_latency_fields(encoder, connector, mode);
@@ -451,29 +436,23 @@ static void radeon_audio_select_pin(struct drm_encoder *encoder)
 }
 
 void radeon_audio_detect(struct drm_connector *connector,
+			 struct drm_encoder *encoder,
 			 enum drm_connector_status status)
 {
-	struct radeon_device *rdev;
-	struct radeon_encoder *radeon_encoder;
+	struct drm_device *dev = connector->dev;
+	struct radeon_device *rdev = dev->dev_private;
+	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 	struct radeon_encoder_atom_dig *dig;
 
-	if (!connector || !connector->encoder)
+	if (!radeon_audio_chipset_supported(rdev))
 		return;
 
-	rdev = connector->encoder->dev->dev_private;
-
-	if (!radeon_audio_chipset_supported(rdev))
+	if (!radeon_encoder_is_digital(encoder))
 		return;
 
-	radeon_encoder = to_radeon_encoder(connector->encoder);
 	dig = radeon_encoder->enc_priv;
 
 	if (status == connector_status_connected) {
-		if (!drm_detect_monitor_audio(radeon_connector_edid(connector))) {
-			radeon_encoder->audio = NULL;
-			return;
-		}
-
 		if (connector->connector_type == DRM_MODE_CONNECTOR_DisplayPort) {
 			struct radeon_connector *radeon_connector = to_radeon_connector(connector);
 
@@ -486,11 +465,17 @@ void radeon_audio_detect(struct drm_connector *connector,
 			radeon_encoder->audio = rdev->audio.hdmi_funcs;
 		}
 
-		dig->afmt->pin = radeon_audio_get_pin(connector->encoder);
-		radeon_audio_enable(rdev, dig->afmt->pin, 0xf);
+		if (drm_detect_monitor_audio(radeon_connector_edid(connector))) {
+			if (!dig->pin)
+				dig->pin = radeon_audio_get_pin(encoder);
+			radeon_audio_enable(rdev, dig->pin, 0xf);
+		} else {
+			radeon_audio_enable(rdev, dig->pin, 0);
+			dig->pin = NULL;
+		}
 	} else {
-		radeon_audio_enable(rdev, dig->afmt->pin, 0);
-		dig->afmt->pin = NULL;
+		radeon_audio_enable(rdev, dig->pin, 0);
+		dig->pin = NULL;
 	}
 }
 
@@ -518,29 +503,18 @@ static void radeon_audio_set_dto(struct drm_encoder *encoder, unsigned int clock
 }
 
 static int radeon_audio_set_avi_packet(struct drm_encoder *encoder,
-	struct drm_display_mode *mode)
+				       struct drm_display_mode *mode)
 {
 	struct radeon_device *rdev = encoder->dev->dev_private;
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
-	struct drm_connector *connector;
-	struct radeon_connector *radeon_connector = NULL;
+	struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
 	u8 buffer[HDMI_INFOFRAME_HEADER_SIZE + HDMI_AVI_INFOFRAME_SIZE];
 	struct hdmi_avi_infoframe frame;
 	int err;
 
-	list_for_each_entry(connector,
-		&encoder->dev->mode_config.connector_list, head) {
-		if (connector->encoder == encoder) {
-			radeon_connector = to_radeon_connector(connector);
-			break;
-		}
-	}
-
-	if (!radeon_connector) {
-		DRM_ERROR("Couldn't find encoder's connector\n");
-		return -ENOENT;
-	}
+	if (!connector)
+		return -EINVAL;
 
 	err = drm_hdmi_avi_infoframe_from_display_mode(&frame, mode);
 	if (err < 0) {
@@ -563,8 +537,8 @@ static int radeon_audio_set_avi_packet(struct drm_encoder *encoder,
 		return err;
 	}
 
-	if (dig && dig->afmt &&
-		radeon_encoder->audio && radeon_encoder->audio->set_avi_packet)
+	if (dig && dig->afmt && radeon_encoder->audio &&
+	    radeon_encoder->audio->set_avi_packet)
 		radeon_encoder->audio->set_avi_packet(rdev, dig->afmt->offset,
 			buffer, sizeof(buffer));
 
@@ -722,30 +696,41 @@ static void radeon_audio_hdmi_mode_set(struct drm_encoder *encoder,
 {
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
+	struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
 
 	if (!dig || !dig->afmt)
 		return;
 
-	radeon_audio_set_mute(encoder, true);
+	if (!connector)
+		return;
 
-	radeon_audio_write_speaker_allocation(encoder);
-	radeon_audio_write_sad_regs(encoder);
-	radeon_audio_write_latency_fields(encoder, mode);
-	radeon_audio_set_dto(encoder, mode->clock);
-	radeon_audio_set_vbi_packet(encoder);
-	radeon_hdmi_set_color_depth(encoder);
-	radeon_audio_update_acr(encoder, mode->clock);
-	radeon_audio_set_audio_packet(encoder);
-	radeon_audio_select_pin(encoder);
+	if (drm_detect_monitor_audio(radeon_connector_edid(connector))) {
+		radeon_audio_set_mute(encoder, true);
 
-	if (radeon_audio_set_avi_packet(encoder, mode) < 0)
-		return;
+		radeon_audio_write_speaker_allocation(encoder);
+		radeon_audio_write_sad_regs(encoder);
+		radeon_audio_write_latency_fields(encoder, mode);
+		radeon_audio_set_dto(encoder, mode->clock);
+		radeon_audio_set_vbi_packet(encoder);
+		radeon_hdmi_set_color_depth(encoder);
+		radeon_audio_update_acr(encoder, mode->clock);
+		radeon_audio_set_audio_packet(encoder);
+		radeon_audio_select_pin(encoder);
+
+		if (radeon_audio_set_avi_packet(encoder, mode) < 0)
+			return;
 
-	radeon_audio_set_mute(encoder, false);
+		radeon_audio_set_mute(encoder, false);
+	} else {
+		radeon_hdmi_set_color_depth(encoder);
+
+		if (radeon_audio_set_avi_packet(encoder, mode) < 0)
+			return;
+	}
 }
 
 static void radeon_audio_dp_mode_set(struct drm_encoder *encoder,
-	struct drm_display_mode *mode)
+				     struct drm_display_mode *mode)
 {
 	struct drm_device *dev = encoder->dev;
 	struct radeon_device *rdev = dev->dev_private;
@@ -759,22 +744,27 @@ static void radeon_audio_dp_mode_set(struct drm_encoder *encoder,
 	if (!dig || !dig->afmt)
 		return;
 
-	radeon_audio_write_speaker_allocation(encoder);
-	radeon_audio_write_sad_regs(encoder);
-	radeon_audio_write_latency_fields(encoder, mode);
-	if (rdev->clock.dp_extclk || ASIC_IS_DCE5(rdev))
-		radeon_audio_set_dto(encoder, rdev->clock.default_dispclk * 10);
-	else
-		radeon_audio_set_dto(encoder, dig_connector->dp_clock);
-	radeon_audio_set_audio_packet(encoder);
-	radeon_audio_select_pin(encoder);
-
-	if (radeon_audio_set_avi_packet(encoder, mode) < 0)
+	if (!connector)
 		return;
+
+	if (drm_detect_monitor_audio(radeon_connector_edid(connector))) {
+		radeon_audio_write_speaker_allocation(encoder);
+		radeon_audio_write_sad_regs(encoder);
+		radeon_audio_write_latency_fields(encoder, mode);
+		if (rdev->clock.dp_extclk || ASIC_IS_DCE5(rdev))
+			radeon_audio_set_dto(encoder, rdev->clock.default_dispclk * 10);
+		else
+			radeon_audio_set_dto(encoder, dig_connector->dp_clock);
+		radeon_audio_set_audio_packet(encoder);
+		radeon_audio_select_pin(encoder);
+
+		if (radeon_audio_set_avi_packet(encoder, mode) < 0)
+			return;
+	}
 }
 
 void radeon_audio_mode_set(struct drm_encoder *encoder,
-	struct drm_display_mode *mode)
+			   struct drm_display_mode *mode)
 {
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 
diff --git a/drivers/gpu/drm/radeon/radeon_audio.h b/drivers/gpu/drm/radeon/radeon_audio.h
index 8438304f7139..059cc3012062 100644
--- a/drivers/gpu/drm/radeon/radeon_audio.h
+++ b/drivers/gpu/drm/radeon/radeon_audio.h
@@ -68,7 +68,8 @@ struct radeon_audio_funcs
 
 int radeon_audio_init(struct radeon_device *rdev);
 void radeon_audio_detect(struct drm_connector *connector,
-	enum drm_connector_status status);
+			 struct drm_encoder *encoder,
+			 enum drm_connector_status status);
 u32 radeon_audio_endpoint_rreg(struct radeon_device *rdev,
 	u32 offset, u32 reg);
 void radeon_audio_endpoint_wreg(struct radeon_device *rdev,
diff --git a/drivers/gpu/drm/radeon/radeon_combios.c b/drivers/gpu/drm/radeon/radeon_combios.c
index 3e5f6b71f3ad..c097d3a82bda 100644
--- a/drivers/gpu/drm/radeon/radeon_combios.c
+++ b/drivers/gpu/drm/radeon/radeon_combios.c
@@ -1255,10 +1255,15 @@ struct radeon_encoder_lvds *radeon_combios_get_lvds_info(struct radeon_encoder
 
 			if ((RBIOS16(tmp) == lvds->native_mode.hdisplay) &&
 			    (RBIOS16(tmp + 2) == lvds->native_mode.vdisplay)) {
+				u32 hss = (RBIOS16(tmp + 21) - RBIOS16(tmp + 19) - 1) * 8;
+
+				if (hss > lvds->native_mode.hdisplay)
+					hss = (10 - 1) * 8;
+
 				lvds->native_mode.htotal = lvds->native_mode.hdisplay +
 					(RBIOS16(tmp + 17) - RBIOS16(tmp + 19)) * 8;
 				lvds->native_mode.hsync_start = lvds->native_mode.hdisplay +
-					(RBIOS16(tmp + 21) - RBIOS16(tmp + 19) - 1) * 8;
+					hss;
 				lvds->native_mode.hsync_end = lvds->native_mode.hsync_start +
 					(RBIOS8(tmp + 23) * 8);
 
diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index cebb65e07e1d..94b21ae70ef7 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -1379,8 +1379,16 @@ out:
 	/* updated in get modes as well since we need to know if it's analog or digital */
 	radeon_connector_update_scratch_regs(connector, ret);
 
-	if (radeon_audio != 0)
-		radeon_audio_detect(connector, ret);
+	if ((radeon_audio != 0) && radeon_connector->use_digital) {
+		const struct drm_connector_helper_funcs *connector_funcs =
+			connector->helper_private;
+
+		encoder = connector_funcs->best_encoder(connector);
+		if (encoder && (encoder->encoder_type == DRM_MODE_ENCODER_TMDS)) {
+			radeon_connector_get_edid(connector);
+			radeon_audio_detect(connector, encoder, ret);
+		}
+	}
 
 exit:
 	pm_runtime_mark_last_busy(connector->dev->dev);
@@ -1717,8 +1725,10 @@ radeon_dp_detect(struct drm_connector *connector, bool force)
 
 	radeon_connector_update_scratch_regs(connector, ret);
 
-	if (radeon_audio != 0)
-		radeon_audio_detect(connector, ret);
+	if ((radeon_audio != 0) && encoder) {
+		radeon_connector_get_edid(connector);
+		radeon_audio_detect(connector, encoder, ret);
+	}
 
 out:
 	pm_runtime_mark_last_busy(connector->dev->dev);
diff --git a/drivers/gpu/drm/radeon/radeon_mode.h b/drivers/gpu/drm/radeon/radeon_mode.h
index 07909d817381..aecc3e3dec0c 100644
--- a/drivers/gpu/drm/radeon/radeon_mode.h
+++ b/drivers/gpu/drm/radeon/radeon_mode.h
@@ -237,7 +237,6 @@ struct radeon_afmt {
 	int offset;
 	bool last_buffer_filled_status;
 	int id;
-	struct r600_audio_pin *pin;
 };
 
 struct radeon_mode_info {
@@ -439,6 +438,7 @@ struct radeon_encoder_atom_dig {
 	uint8_t backlight_level;
 	int panel_mode;
 	struct radeon_afmt *afmt;
+	struct r600_audio_pin *pin;
 	int active_mst_links;
 };
 
diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c
index f822fd2a1ada..884d82f9190e 100644
--- a/drivers/hid/hid-apple.c
+++ b/drivers/hid/hid-apple.c
@@ -546,6 +546,12 @@ static const struct hid_device_id apple_devices[] = {
 		.driver_data = APPLE_HAS_FN | APPLE_ISO_KEYBOARD },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING8_JIS),
 		.driver_data = APPLE_HAS_FN | APPLE_RDESC_JIS },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING9_ANSI),
+		.driver_data = APPLE_HAS_FN },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING9_ISO),
+		.driver_data = APPLE_HAS_FN | APPLE_ISO_KEYBOARD },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING9_JIS),
+		.driver_data = APPLE_HAS_FN | APPLE_RDESC_JIS },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ANSI),
 		.driver_data = APPLE_NUMLOCK_EMULATION | APPLE_HAS_FN },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ISO),
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index 157c62775053..e6fce23b121a 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -1782,6 +1782,9 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING8_ANSI) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING8_ISO) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING8_JIS) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING9_ANSI) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING9_ISO) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING9_JIS) },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ANSI) },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ISO) },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_JIS) },
@@ -2463,6 +2466,9 @@ static const struct hid_device_id hid_mouse_ignore_list[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING8_ANSI) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING8_ISO) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING8_JIS) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING9_ANSI) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING9_ISO) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING9_JIS) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_FOUNTAIN_TP_ONLY) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_GEYSER1_TP_ONLY) },
 	{ }
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index b04b0820d816..b3b225b75d0a 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -142,6 +142,9 @@
 #define USB_DEVICE_ID_APPLE_WELLSPRING8_ANSI	0x0290
 #define USB_DEVICE_ID_APPLE_WELLSPRING8_ISO	0x0291
 #define USB_DEVICE_ID_APPLE_WELLSPRING8_JIS	0x0292
+#define USB_DEVICE_ID_APPLE_WELLSPRING9_ANSI	0x0272
+#define USB_DEVICE_ID_APPLE_WELLSPRING9_ISO		0x0273
+#define USB_DEVICE_ID_APPLE_WELLSPRING9_JIS		0x0274
 #define USB_DEVICE_ID_APPLE_FOUNTAIN_TP_ONLY	0x030a
 #define USB_DEVICE_ID_APPLE_GEYSER1_TP_ONLY	0x030b
 #define USB_DEVICE_ID_APPLE_IRCONTROL	0x8240
diff --git a/drivers/hwmon/nct7802.c b/drivers/hwmon/nct7802.c
index 28fcb2e246d5..fbfc02bb2cfa 100644
--- a/drivers/hwmon/nct7802.c
+++ b/drivers/hwmon/nct7802.c
@@ -195,7 +195,7 @@ abort:
 }
 
 static int nct7802_write_voltage(struct nct7802_data *data, int nr, int index,
-				 unsigned int voltage)
+				 unsigned long voltage)
 {
 	int shift = 8 - REG_VOLTAGE_LIMIT_MSB_SHIFT[index - 1][nr];
 	int err;
diff --git a/drivers/hwmon/nct7904.c b/drivers/hwmon/nct7904.c
index b77b82f24480..6153df735e82 100644
--- a/drivers/hwmon/nct7904.c
+++ b/drivers/hwmon/nct7904.c
@@ -412,8 +412,9 @@ static ssize_t show_pwm(struct device *dev,
 	return sprintf(buf, "%d\n", val);
 }
 
-static ssize_t store_mode(struct device *dev, struct device_attribute *devattr,
-			  const char *buf, size_t count)
+static ssize_t store_enable(struct device *dev,
+			    struct device_attribute *devattr,
+			    const char *buf, size_t count)
 {
 	int index = to_sensor_dev_attr(devattr)->index;
 	struct nct7904_data *data = dev_get_drvdata(dev);
@@ -422,18 +423,18 @@ static ssize_t store_mode(struct device *dev, struct device_attribute *devattr,
 
 	if (kstrtoul(buf, 10, &val) < 0)
 		return -EINVAL;
-	if (val > 1 || (val && !data->fan_mode[index]))
+	if (val < 1 || val > 2 || (val == 2 && !data->fan_mode[index]))
 		return -EINVAL;
 
 	ret = nct7904_write_reg(data, BANK_3, FANCTL1_FMR_REG + index,
-				val ? data->fan_mode[index] : 0);
+				val == 2 ? data->fan_mode[index] : 0);
 
 	return ret ? ret : count;
 }
 
-/* Return 0 for manual mode or 1 for SmartFan mode */
-static ssize_t show_mode(struct device *dev,
-			 struct device_attribute *devattr, char *buf)
+/* Return 1 for manual mode or 2 for SmartFan mode */
+static ssize_t show_enable(struct device *dev,
+			   struct device_attribute *devattr, char *buf)
 {
 	int index = to_sensor_dev_attr(devattr)->index;
 	struct nct7904_data *data = dev_get_drvdata(dev);
@@ -443,36 +444,36 @@ static ssize_t show_mode(struct device *dev,
 	if (val < 0)
 		return val;
 
-	return sprintf(buf, "%d\n", val ? 1 : 0);
+	return sprintf(buf, "%d\n", val ? 2 : 1);
 }
 
 /* 2 attributes per channel: pwm and mode */
-static SENSOR_DEVICE_ATTR(fan1_pwm, S_IRUGO | S_IWUSR,
+static SENSOR_DEVICE_ATTR(pwm1, S_IRUGO | S_IWUSR,
 			show_pwm, store_pwm, 0);
-static SENSOR_DEVICE_ATTR(fan1_mode, S_IRUGO | S_IWUSR,
-			show_mode, store_mode, 0);
-static SENSOR_DEVICE_ATTR(fan2_pwm, S_IRUGO | S_IWUSR,
+static SENSOR_DEVICE_ATTR(pwm1_enable, S_IRUGO | S_IWUSR,
+			show_enable, store_enable, 0);
+static SENSOR_DEVICE_ATTR(pwm2, S_IRUGO | S_IWUSR,
 			show_pwm, store_pwm, 1);
-static SENSOR_DEVICE_ATTR(fan2_mode, S_IRUGO | S_IWUSR,
-			show_mode, store_mode, 1);
-static SENSOR_DEVICE_ATTR(fan3_pwm, S_IRUGO | S_IWUSR,
+static SENSOR_DEVICE_ATTR(pwm2_enable, S_IRUGO | S_IWUSR,
+			show_enable, store_enable, 1);
+static SENSOR_DEVICE_ATTR(pwm3, S_IRUGO | S_IWUSR,
 			show_pwm, store_pwm, 2);
-static SENSOR_DEVICE_ATTR(fan3_mode, S_IRUGO | S_IWUSR,
-			show_mode, store_mode, 2);
-static SENSOR_DEVICE_ATTR(fan4_pwm, S_IRUGO | S_IWUSR,
+static SENSOR_DEVICE_ATTR(pwm3_enable, S_IRUGO | S_IWUSR,
+			show_enable, store_enable, 2);
+static SENSOR_DEVICE_ATTR(pwm4, S_IRUGO | S_IWUSR,
 			show_pwm, store_pwm, 3);
-static SENSOR_DEVICE_ATTR(fan4_mode, S_IRUGO | S_IWUSR,
-			show_mode, store_mode, 3);
+static SENSOR_DEVICE_ATTR(pwm4_enable, S_IRUGO | S_IWUSR,
+			show_enable, store_enable, 3);
 
 static struct attribute *nct7904_fanctl_attrs[] = {
-	&sensor_dev_attr_fan1_pwm.dev_attr.attr,
-	&sensor_dev_attr_fan1_mode.dev_attr.attr,
-	&sensor_dev_attr_fan2_pwm.dev_attr.attr,
-	&sensor_dev_attr_fan2_mode.dev_attr.attr,
-	&sensor_dev_attr_fan3_pwm.dev_attr.attr,
-	&sensor_dev_attr_fan3_mode.dev_attr.attr,
-	&sensor_dev_attr_fan4_pwm.dev_attr.attr,
-	&sensor_dev_attr_fan4_mode.dev_attr.attr,
+	&sensor_dev_attr_pwm1.dev_attr.attr,
+	&sensor_dev_attr_pwm1_enable.dev_attr.attr,
+	&sensor_dev_attr_pwm2.dev_attr.attr,
+	&sensor_dev_attr_pwm2_enable.dev_attr.attr,
+	&sensor_dev_attr_pwm3.dev_attr.attr,
+	&sensor_dev_attr_pwm3_enable.dev_attr.attr,
+	&sensor_dev_attr_pwm4.dev_attr.attr,
+	&sensor_dev_attr_pwm4_enable.dev_attr.attr,
 	NULL
 };
 
diff --git a/drivers/infiniband/hw/cxgb3/iwch_provider.c b/drivers/infiniband/hw/cxgb3/iwch_provider.c
index b1b73232f217..bbbe0184e592 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_provider.c
+++ b/drivers/infiniband/hw/cxgb3/iwch_provider.c
@@ -736,6 +736,10 @@ static struct ib_mr *iwch_get_dma_mr(struct ib_pd *pd, int acc)
 	/*
 	 * T3 only supports 32 bits of size.
 	 */
+	if (sizeof(phys_addr_t) > 4) {
+		pr_warn_once(MOD "Cannot support dma_mrs on this platform.\n");
+		return ERR_PTR(-ENOTSUPP);
+	}
 	bl.size = 0xffffffff;
 	bl.addr = 0;
 	kva = 0;
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma.h b/drivers/infiniband/hw/ocrdma/ocrdma.h
index b396344fae16..6a36338593cd 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma.h
@@ -1,21 +1,36 @@
-/*******************************************************************
- * This file is part of the Emulex RoCE Device Driver for          *
- * RoCE (RDMA over Converged Ethernet) adapters.                   *
- * Copyright (C) 2008-2012 Emulex. All rights reserved.            *
- * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
- *                                                                 *
- * This program is free software; you can redistribute it and/or   *
- * modify it under the terms of version 2 of the GNU General       *
- * Public License as published by the Free Software Foundation.    *
- * This program is distributed in the hope that it will be useful. *
- * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
- * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
- * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
- * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
- * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
- * more details, a copy of which can be found in the file COPYING  *
- * included with this package.                                     *
+/* This file is part of the Emulex RoCE Device Driver for
+ * RoCE (RDMA over Converged Ethernet) adapters.
+ * Copyright (C) 2012-2015 Emulex. All rights reserved.
+ * EMULEX and SLI are trademarks of Emulex.
+ * www.emulex.com
+ *
+ * This software is available to you under a choice of one of two licenses.
+ * You may choose to be licensed under the terms of the GNU General Public
+ * License (GPL) Version 2, available from the file COPYING in the main
+ * directory of this source tree, or the BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * - Redistributions of source code must retain the above copyright notice,
+ *   this list of conditions and the following disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above copyright
+ *   notice, this list of conditions and the following disclaimer in
+ *   the documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
  * Contact Information:
  * linux-drivers@emulex.com
@@ -23,7 +38,7 @@
  * Emulex
  * 3333 Susan Street
  * Costa Mesa, CA 92626
- *******************************************************************/
+ */
 
 #ifndef __OCRDMA_H__
 #define __OCRDMA_H__
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_abi.h b/drivers/infiniband/hw/ocrdma/ocrdma_abi.h
index 1554cca5712a..430b1350fe96 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_abi.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_abi.h
@@ -1,21 +1,36 @@
-/*******************************************************************
- * This file is part of the Emulex RoCE Device Driver for          *
- * RoCE (RDMA over Converged Ethernet) adapters.                   *
- * Copyright (C) 2008-2012 Emulex. All rights reserved.            *
- * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
- *                                                                 *
- * This program is free software; you can redistribute it and/or   *
- * modify it under the terms of version 2 of the GNU General       *
- * Public License as published by the Free Software Foundation.    *
- * This program is distributed in the hope that it will be useful. *
- * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
- * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
- * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
- * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
- * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
- * more details, a copy of which can be found in the file COPYING  *
- * included with this package.                                     *
+/* This file is part of the Emulex RoCE Device Driver for
+ * RoCE (RDMA over Converged Ethernet) adapters.
+ * Copyright (C) 2012-2015 Emulex. All rights reserved.
+ * EMULEX and SLI are trademarks of Emulex.
+ * www.emulex.com
+ *
+ * This software is available to you under a choice of one of two licenses.
+ * You may choose to be licensed under the terms of the GNU General Public
+ * License (GPL) Version 2, available from the file COPYING in the main
+ * directory of this source tree, or the BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * - Redistributions of source code must retain the above copyright notice,
+ *   this list of conditions and the following disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above copyright
+ *   notice, this list of conditions and the following disclaimer in
+ *   the documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
  * Contact Information:
  * linux-drivers@emulex.com
@@ -23,7 +38,7 @@
  * Emulex
  * 3333 Susan Street
  * Costa Mesa, CA 92626
- *******************************************************************/
+ */
 
 #ifndef __OCRDMA_ABI_H__
 #define __OCRDMA_ABI_H__
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_ah.c b/drivers/infiniband/hw/ocrdma/ocrdma_ah.c
index 29b27675dd70..44766fee1f4e 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_ah.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_ah.c
@@ -1,21 +1,36 @@
-/*******************************************************************
- * This file is part of the Emulex RoCE Device Driver for          *
- * RoCE (RDMA over Converged Ethernet) adapters.                   *
- * Copyright (C) 2008-2012 Emulex. All rights reserved.            *
- * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
- *                                                                 *
- * This program is free software; you can redistribute it and/or   *
- * modify it under the terms of version 2 of the GNU General       *
- * Public License as published by the Free Software Foundation.    *
- * This program is distributed in the hope that it will be useful. *
- * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
- * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
- * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
- * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
- * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
- * more details, a copy of which can be found in the file COPYING  *
- * included with this package.                                     *
+/* This file is part of the Emulex RoCE Device Driver for
+ * RoCE (RDMA over Converged Ethernet) adapters.
+ * Copyright (C) 2012-2015 Emulex. All rights reserved.
+ * EMULEX and SLI are trademarks of Emulex.
+ * www.emulex.com
+ *
+ * This software is available to you under a choice of one of two licenses.
+ * You may choose to be licensed under the terms of the GNU General Public
+ * License (GPL) Version 2, available from the file COPYING in the main
+ * directory of this source tree, or the BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * - Redistributions of source code must retain the above copyright notice,
+ *   this list of conditions and the following disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above copyright
+ *   notice, this list of conditions and the following disclaimer in
+ *   the documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
  * Contact Information:
  * linux-drivers@emulex.com
@@ -23,7 +38,7 @@
  * Emulex
  * 3333 Susan Street
  * Costa Mesa, CA 92626
- *******************************************************************/
+ */
 
 #include <net/neighbour.h>
 #include <net/netevent.h>
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_ah.h b/drivers/infiniband/hw/ocrdma/ocrdma_ah.h
index cf366fe03cb8..04a30ae67473 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_ah.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_ah.h
@@ -1,21 +1,36 @@
-/*******************************************************************
- * This file is part of the Emulex RoCE Device Driver for          *
- * RoCE (RDMA over Converged Ethernet) adapters.                   *
- * Copyright (C) 2008-2012 Emulex. All rights reserved.            *
- * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
- *                                                                 *
- * This program is free software; you can redistribute it and/or   *
- * modify it under the terms of version 2 of the GNU General       *
- * Public License as published by the Free Software Foundation.    *
- * This program is distributed in the hope that it will be useful. *
- * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
- * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
- * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
- * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
- * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
- * more details, a copy of which can be found in the file COPYING  *
- * included with this package.                                     *
+/* This file is part of the Emulex RoCE Device Driver for
+ * RoCE (RDMA over Converged Ethernet) adapters.
+ * Copyright (C) 2012-2015 Emulex. All rights reserved.
+ * EMULEX and SLI are trademarks of Emulex.
+ * www.emulex.com
+ *
+ * This software is available to you under a choice of one of two licenses.
+ * You may choose to be licensed under the terms of the GNU General Public
+ * License (GPL) Version 2, available from the file COPYING in the main
+ * directory of this source tree, or the BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * - Redistributions of source code must retain the above copyright notice,
+ *   this list of conditions and the following disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above copyright
+ *   notice, this list of conditions and the following disclaimer in
+ *   the documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
  * Contact Information:
  * linux-drivers@emulex.com
@@ -23,7 +38,7 @@
  * Emulex
  * 3333 Susan Street
  * Costa Mesa, CA 92626
- *******************************************************************/
+ */
 
 #ifndef __OCRDMA_AH_H__
 #define __OCRDMA_AH_H__
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c
index 47615ff33bc6..aab391a15db4 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c
@@ -1,21 +1,36 @@
-/*******************************************************************
- * This file is part of the Emulex RoCE Device Driver for          *
- * RoCE (RDMA over Converged Ethernet) CNA Adapters.              *
- * Copyright (C) 2008-2012 Emulex. All rights reserved.            *
- * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
- *                                                                 *
- * This program is free software; you can redistribute it and/or   *
- * modify it under the terms of version 2 of the GNU General       *
- * Public License as published by the Free Software Foundation.    *
- * This program is distributed in the hope that it will be useful. *
- * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
- * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
- * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
- * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
- * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
- * more details, a copy of which can be found in the file COPYING  *
- * included with this package.                                     *
+/* This file is part of the Emulex RoCE Device Driver for
+ * RoCE (RDMA over Converged Ethernet) adapters.
+ * Copyright (C) 2012-2015 Emulex. All rights reserved.
+ * EMULEX and SLI are trademarks of Emulex.
+ * www.emulex.com
+ *
+ * This software is available to you under a choice of one of two licenses.
+ * You may choose to be licensed under the terms of the GNU General Public
+ * License (GPL) Version 2, available from the file COPYING in the main
+ * directory of this source tree, or the BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * - Redistributions of source code must retain the above copyright notice,
+ *   this list of conditions and the following disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above copyright
+ *   notice, this list of conditions and the following disclaimer in
+ *   the documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
  * Contact Information:
  * linux-drivers@emulex.com
@@ -23,7 +38,7 @@
  * Emulex
  * 3333 Susan Street
  * Costa Mesa, CA 92626
- *******************************************************************/
+ */
 
 #include <linux/sched.h>
 #include <linux/interrupt.h>
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_hw.h b/drivers/infiniband/hw/ocrdma/ocrdma_hw.h
index e905972fceb7..7ed885c1851e 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_hw.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_hw.h
@@ -1,21 +1,36 @@
-/*******************************************************************
- * This file is part of the Emulex RoCE Device Driver for          *
- * RoCE (RDMA over Converged Ethernet) CNA Adapters.              *
- * Copyright (C) 2008-2012 Emulex. All rights reserved.            *
- * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
- *                                                                 *
- * This program is free software; you can redistribute it and/or   *
- * modify it under the terms of version 2 of the GNU General       *
- * Public License as published by the Free Software Foundation.    *
- * This program is distributed in the hope that it will be useful. *
- * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
- * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
- * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
- * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
- * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
- * more details, a copy of which can be found in the file COPYING  *
- * included with this package.                                     *
+/* This file is part of the Emulex RoCE Device Driver for
+ * RoCE (RDMA over Converged Ethernet) adapters.
+ * Copyright (C) 2012-2015 Emulex. All rights reserved.
+ * EMULEX and SLI are trademarks of Emulex.
+ * www.emulex.com
+ *
+ * This software is available to you under a choice of one of two licenses.
+ * You may choose to be licensed under the terms of the GNU General Public
+ * License (GPL) Version 2, available from the file COPYING in the main
+ * directory of this source tree, or the BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * - Redistributions of source code must retain the above copyright notice,
+ *   this list of conditions and the following disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above copyright
+ *   notice, this list of conditions and the following disclaimer in
+ *   the documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
  * Contact Information:
  * linux-drivers@emulex.com
@@ -23,7 +38,7 @@
  * Emulex
  * 3333 Susan Street
  * Costa Mesa, CA 92626
- *******************************************************************/
+ */
 
 #ifndef __OCRDMA_HW_H__
 #define __OCRDMA_HW_H__
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_main.c b/drivers/infiniband/hw/ocrdma/ocrdma_main.c
index d98a707a5eb9..b119a3413a15 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_main.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_main.c
@@ -1,21 +1,36 @@
-/*******************************************************************
- * This file is part of the Emulex RoCE Device Driver for          *
- * RoCE (RDMA over Converged Ethernet) adapters.                   *
- * Copyright (C) 2008-2012 Emulex. All rights reserved.            *
- * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
- *                                                                 *
- * This program is free software; you can redistribute it and/or   *
- * modify it under the terms of version 2 of the GNU General       *
- * Public License as published by the Free Software Foundation.    *
- * This program is distributed in the hope that it will be useful. *
- * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
- * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
- * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
- * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
- * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
- * more details, a copy of which can be found in the file COPYING  *
- * included with this package.                                     *
+/* This file is part of the Emulex RoCE Device Driver for
+ * RoCE (RDMA over Converged Ethernet) adapters.
+ * Copyright (C) 2012-2015 Emulex. All rights reserved.
+ * EMULEX and SLI are trademarks of Emulex.
+ * www.emulex.com
+ *
+ * This software is available to you under a choice of one of two licenses.
+ * You may choose to be licensed under the terms of the GNU General Public
+ * License (GPL) Version 2, available from the file COPYING in the main
+ * directory of this source tree, or the BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * - Redistributions of source code must retain the above copyright notice,
+ *   this list of conditions and the following disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above copyright
+ *   notice, this list of conditions and the following disclaimer in
+ *   the documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
  * Contact Information:
  * linux-drivers@emulex.com
@@ -23,7 +38,7 @@
  * Emulex
  * 3333 Susan Street
  * Costa Mesa, CA 92626
- *******************************************************************/
+ */
 
 #include <linux/module.h>
 #include <linux/idr.h>
@@ -46,7 +61,7 @@
 MODULE_VERSION(OCRDMA_ROCE_DRV_VERSION);
 MODULE_DESCRIPTION(OCRDMA_ROCE_DRV_DESC " " OCRDMA_ROCE_DRV_VERSION);
 MODULE_AUTHOR("Emulex Corporation");
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("Dual BSD/GPL");
 
 static LIST_HEAD(ocrdma_dev_list);
 static DEFINE_SPINLOCK(ocrdma_devlist_lock);
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_sli.h b/drivers/infiniband/hw/ocrdma/ocrdma_sli.h
index 02ad0aee99af..80006b24aa11 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_sli.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_sli.h
@@ -1,21 +1,36 @@
-/*******************************************************************
- * This file is part of the Emulex RoCE Device Driver for          *
- * RoCE (RDMA over Converged Ethernet) adapters.                   *
- * Copyright (C) 2008-2012 Emulex. All rights reserved.            *
- * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
- *                                                                 *
- * This program is free software; you can redistribute it and/or   *
- * modify it under the terms of version 2 of the GNU General       *
- * Public License as published by the Free Software Foundation.    *
- * This program is distributed in the hope that it will be useful. *
- * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
- * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
- * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
- * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
- * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
- * more details, a copy of which can be found in the file COPYING  *
- * included with this package.                                     *
+/* This file is part of the Emulex RoCE Device Driver for
+ * RoCE (RDMA over Converged Ethernet) adapters.
+ * Copyright (C) 2012-2015 Emulex. All rights reserved.
+ * EMULEX and SLI are trademarks of Emulex.
+ * www.emulex.com
+ *
+ * This software is available to you under a choice of one of two licenses.
+ * You may choose to be licensed under the terms of the GNU General Public
+ * License (GPL) Version 2, available from the file COPYING in the main
+ * directory of this source tree, or the BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * - Redistributions of source code must retain the above copyright notice,
+ *   this list of conditions and the following disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above copyright
+ *   notice, this list of conditions and the following disclaimer in
+ *   the documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
  * Contact Information:
  * linux-drivers@emulex.com
@@ -23,7 +38,7 @@
  * Emulex
  * 3333 Susan Street
  * Costa Mesa, CA 92626
- *******************************************************************/
+ */
 
 #ifndef __OCRDMA_SLI_H__
 #define __OCRDMA_SLI_H__
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_stats.c b/drivers/infiniband/hw/ocrdma/ocrdma_stats.c
index 48d7ef51aa0c..69334e214571 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_stats.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_stats.c
@@ -1,21 +1,36 @@
-/*******************************************************************
- * This file is part of the Emulex RoCE Device Driver for          *
- * RoCE (RDMA over Converged Ethernet) adapters.                   *
- * Copyright (C) 2008-2014 Emulex. All rights reserved.            *
- * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
- *                                                                 *
- * This program is free software; you can redistribute it and/or   *
- * modify it under the terms of version 2 of the GNU General       *
- * Public License as published by the Free Software Foundation.    *
- * This program is distributed in the hope that it will be useful. *
- * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
- * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
- * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
- * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
- * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
- * more details, a copy of which can be found in the file COPYING  *
- * included with this package.                                     *
+/* This file is part of the Emulex RoCE Device Driver for
+ * RoCE (RDMA over Converged Ethernet) adapters.
+ * Copyright (C) 2012-2015 Emulex. All rights reserved.
+ * EMULEX and SLI are trademarks of Emulex.
+ * www.emulex.com
+ *
+ * This software is available to you under a choice of one of two licenses.
+ * You may choose to be licensed under the terms of the GNU General Public
+ * License (GPL) Version 2, available from the file COPYING in the main
+ * directory of this source tree, or the BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * - Redistributions of source code must retain the above copyright notice,
+ *   this list of conditions and the following disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above copyright
+ *   notice, this list of conditions and the following disclaimer in
+ *   the documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
  * Contact Information:
  * linux-drivers@emulex.com
@@ -23,7 +38,7 @@
  * Emulex
  * 3333 Susan Street
  * Costa Mesa, CA 92626
- *******************************************************************/
+ */
 
 #include <rdma/ib_addr.h>
 #include <rdma/ib_pma.h>
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_stats.h b/drivers/infiniband/hw/ocrdma/ocrdma_stats.h
index 091edd68a8a3..c9e58d04c7b8 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_stats.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_stats.h
@@ -1,21 +1,36 @@
-/*******************************************************************
- * This file is part of the Emulex RoCE Device Driver for          *
- * RoCE (RDMA over Converged Ethernet) adapters.                   *
- * Copyright (C) 2008-2014 Emulex. All rights reserved.            *
- * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
- *                                                                 *
- * This program is free software; you can redistribute it and/or   *
- * modify it under the terms of version 2 of the GNU General       *
- * Public License as published by the Free Software Foundation.    *
- * This program is distributed in the hope that it will be useful. *
- * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
- * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
- * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
- * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
- * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
- * more details, a copy of which can be found in the file COPYING  *
- * included with this package.                                     *
+/* This file is part of the Emulex RoCE Device Driver for
+ * RoCE (RDMA over Converged Ethernet) adapters.
+ * Copyright (C) 2012-2015 Emulex. All rights reserved.
+ * EMULEX and SLI are trademarks of Emulex.
+ * www.emulex.com
+ *
+ * This software is available to you under a choice of one of two licenses.
+ * You may choose to be licensed under the terms of the GNU General Public
+ * License (GPL) Version 2, available from the file COPYING in the main
+ * directory of this source tree, or the BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * - Redistributions of source code must retain the above copyright notice,
+ *   this list of conditions and the following disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above copyright
+ *   notice, this list of conditions and the following disclaimer in
+ *   the documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
  * Contact Information:
  * linux-drivers@emulex.com
@@ -23,7 +38,7 @@
  * Emulex
  * 3333 Susan Street
  * Costa Mesa, CA 92626
- *******************************************************************/
+ */
 
 #ifndef __OCRDMA_STATS_H__
 #define __OCRDMA_STATS_H__
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
index 5bb61eb58f2c..bc84cd462ecf 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
@@ -1,21 +1,36 @@
-/*******************************************************************
- * This file is part of the Emulex RoCE Device Driver for          *
- * RoCE (RDMA over Converged Ethernet) adapters.                   *
- * Copyright (C) 2008-2012 Emulex. All rights reserved.            *
- * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
- *                                                                 *
- * This program is free software; you can redistribute it and/or   *
- * modify it under the terms of version 2 of the GNU General       *
- * Public License as published by the Free Software Foundation.    *
- * This program is distributed in the hope that it will be useful. *
- * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
- * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
- * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
- * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
- * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
- * more details, a copy of which can be found in the file COPYING  *
- * included with this package.                                     *
+/* This file is part of the Emulex RoCE Device Driver for
+ * RoCE (RDMA over Converged Ethernet) adapters.
+ * Copyright (C) 2012-2015 Emulex. All rights reserved.
+ * EMULEX and SLI are trademarks of Emulex.
+ * www.emulex.com
+ *
+ * This software is available to you under a choice of one of two licenses.
+ * You may choose to be licensed under the terms of the GNU General Public
+ * License (GPL) Version 2, available from the file COPYING in the main
+ * directory of this source tree, or the BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * - Redistributions of source code must retain the above copyright notice,
+ *   this list of conditions and the following disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above copyright
+ *   notice, this list of conditions and the following disclaimer in
+ *   the documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
  * Contact Information:
  * linux-drivers@emulex.com
@@ -23,7 +38,7 @@
  * Emulex
  * 3333 Susan Street
  * Costa Mesa, CA 92626
- *******************************************************************/
+ */
 
 #include <linux/dma-mapping.h>
 #include <rdma/ib_verbs.h>
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h
index b15c608efa7b..eaccb2d3cb9f 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h
@@ -1,21 +1,36 @@
-/*******************************************************************
- * This file is part of the Emulex RoCE Device Driver for          *
- * RoCE (RDMA over Converged Ethernet) adapters.                   *
- * Copyright (C) 2008-2012 Emulex. All rights reserved.            *
- * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
- *                                                                 *
- * This program is free software; you can redistribute it and/or   *
- * modify it under the terms of version 2 of the GNU General       *
- * Public License as published by the Free Software Foundation.    *
- * This program is distributed in the hope that it will be useful. *
- * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
- * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
- * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
- * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
- * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
- * more details, a copy of which can be found in the file COPYING  *
- * included with this package.                                     *
+/* This file is part of the Emulex RoCE Device Driver for
+ * RoCE (RDMA over Converged Ethernet) adapters.
+ * Copyright (C) 2012-2015 Emulex. All rights reserved.
+ * EMULEX and SLI are trademarks of Emulex.
+ * www.emulex.com
+ *
+ * This software is available to you under a choice of one of two licenses.
+ * You may choose to be licensed under the terms of the GNU General Public
+ * License (GPL) Version 2, available from the file COPYING in the main
+ * directory of this source tree, or the BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * - Redistributions of source code must retain the above copyright notice,
+ *   this list of conditions and the following disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above copyright
+ *   notice, this list of conditions and the following disclaimer in
+ *   the documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
  * Contact Information:
  * linux-drivers@emulex.com
@@ -23,7 +38,7 @@
  * Emulex
  * 3333 Susan Street
  * Costa Mesa, CA 92626
- *******************************************************************/
+ */
 
 #ifndef __OCRDMA_VERBS_H__
 #define __OCRDMA_VERBS_H__
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
index 9e6ee82a8fd7..851c8219d501 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
@@ -177,7 +177,8 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca)
 		else
 			size += ipoib_recvq_size * ipoib_max_conn_qp;
 	} else
-		goto out_free_wq;
+		if (ret != -ENOSYS)
+			goto out_free_wq;
 
 	cq_attr.cqe = size;
 	priv->recv_cq = ib_create_cq(priv->ca, ipoib_ib_completion, NULL,
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index 771700963127..d851e1828d6f 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -775,6 +775,17 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 	ret = isert_rdma_post_recvl(isert_conn);
 	if (ret)
 		goto out_conn_dev;
+	/*
+	 * Obtain the second reference now before isert_rdma_accept() to
+	 * ensure that any initiator generated REJECT CM event that occurs
+	 * asynchronously won't drop the last reference until the error path
+	 * in iscsi_target_login_sess_out() does it's ->iscsit_free_conn() ->
+	 * isert_free_conn() -> isert_put_conn() -> kref_put().
+	 */
+	if (!kref_get_unless_zero(&isert_conn->kref)) {
+		isert_warn("conn %p connect_release is running\n", isert_conn);
+		goto out_conn_dev;
+	}
 
 	ret = isert_rdma_accept(isert_conn);
 	if (ret)
@@ -836,11 +847,6 @@ isert_connected_handler(struct rdma_cm_id *cma_id)
 
 	isert_info("conn %p\n", isert_conn);
 
-	if (!kref_get_unless_zero(&isert_conn->kref)) {
-		isert_warn("conn %p connect_release is running\n", isert_conn);
-		return;
-	}
-
 	mutex_lock(&isert_conn->mutex);
 	if (isert_conn->state != ISER_CONN_FULL_FEATURE)
 		isert_conn->state = ISER_CONN_UP;
diff --git a/drivers/input/mouse/bcm5974.c b/drivers/input/mouse/bcm5974.c
index b10709f04615..30e3442518f8 100644
--- a/drivers/input/mouse/bcm5974.c
+++ b/drivers/input/mouse/bcm5974.c
@@ -2,6 +2,7 @@
  * Apple USB BCM5974 (Macbook Air and Penryn Macbook Pro) multitouch driver
  *
  * Copyright (C) 2008	   Henrik Rydberg (rydberg@euromail.se)
+ * Copyright (C) 2015      John Horan (knasher@gmail.com)
  *
  * The USB initialization and package decoding was made by
  * Scott Shawcroft as part of the touchd user-space driver project:
@@ -91,6 +92,10 @@
 #define USB_DEVICE_ID_APPLE_WELLSPRING8_ANSI	0x0290
 #define USB_DEVICE_ID_APPLE_WELLSPRING8_ISO	0x0291
 #define USB_DEVICE_ID_APPLE_WELLSPRING8_JIS	0x0292
+/* MacbookPro12,1 (2015) */
+#define USB_DEVICE_ID_APPLE_WELLSPRING9_ANSI	0x0272
+#define USB_DEVICE_ID_APPLE_WELLSPRING9_ISO	0x0273
+#define USB_DEVICE_ID_APPLE_WELLSPRING9_JIS	0x0274
 
 #define BCM5974_DEVICE(prod) {					\
 	.match_flags = (USB_DEVICE_ID_MATCH_DEVICE |		\
@@ -152,6 +157,10 @@ static const struct usb_device_id bcm5974_table[] = {
 	BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING8_ANSI),
 	BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING8_ISO),
 	BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING8_JIS),
+	/* MacbookPro12,1 */
+	BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING9_ANSI),
+	BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING9_ISO),
+	BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING9_JIS),
 	/* Terminating entry */
 	{}
 };
@@ -180,21 +189,47 @@ struct bt_data {
 enum tp_type {
 	TYPE1,			/* plain trackpad */
 	TYPE2,			/* button integrated in trackpad */
-	TYPE3			/* additional header fields since June 2013 */
+	TYPE3,			/* additional header fields since June 2013 */
+	TYPE4			/* additional header field for pressure data */
 };
 
 /* trackpad finger data offsets, le16-aligned */
-#define FINGER_TYPE1		(13 * sizeof(__le16))
-#define FINGER_TYPE2		(15 * sizeof(__le16))
-#define FINGER_TYPE3		(19 * sizeof(__le16))
+#define HEADER_TYPE1		(13 * sizeof(__le16))
+#define HEADER_TYPE2		(15 * sizeof(__le16))
+#define HEADER_TYPE3		(19 * sizeof(__le16))
+#define HEADER_TYPE4		(23 * sizeof(__le16))
 
 /* trackpad button data offsets */
+#define BUTTON_TYPE1		0
 #define BUTTON_TYPE2		15
 #define BUTTON_TYPE3		23
+#define BUTTON_TYPE4		31
 
 /* list of device capability bits */
 #define HAS_INTEGRATED_BUTTON	1
 
+/* trackpad finger data block size */
+#define FSIZE_TYPE1		(14 * sizeof(__le16))
+#define FSIZE_TYPE2		(14 * sizeof(__le16))
+#define FSIZE_TYPE3		(14 * sizeof(__le16))
+#define FSIZE_TYPE4		(15 * sizeof(__le16))
+
+/* offset from header to finger struct */
+#define DELTA_TYPE1		(0 * sizeof(__le16))
+#define DELTA_TYPE2		(0 * sizeof(__le16))
+#define DELTA_TYPE3		(0 * sizeof(__le16))
+#define DELTA_TYPE4		(1 * sizeof(__le16))
+
+/* usb control message mode switch data */
+#define USBMSG_TYPE1		8, 0x300, 0, 0, 0x1, 0x8
+#define USBMSG_TYPE2		8, 0x300, 0, 0, 0x1, 0x8
+#define USBMSG_TYPE3		8, 0x300, 0, 0, 0x1, 0x8
+#define USBMSG_TYPE4		2, 0x302, 2, 1, 0x1, 0x0
+
+/* Wellspring initialization constants */
+#define BCM5974_WELLSPRING_MODE_READ_REQUEST_ID		1
+#define BCM5974_WELLSPRING_MODE_WRITE_REQUEST_ID	9
+
 /* trackpad finger structure, le16-aligned */
 struct tp_finger {
 	__le16 origin;		/* zero when switching track finger */
@@ -207,14 +242,13 @@ struct tp_finger {
 	__le16 orientation;	/* 16384 when point, else 15 bit angle */
 	__le16 touch_major;	/* touch area, major axis */
 	__le16 touch_minor;	/* touch area, minor axis */
-	__le16 unused[3];	/* zeros */
+	__le16 unused[2];	/* zeros */
+	__le16 pressure;	/* pressure on forcetouch touchpad */
 	__le16 multi;		/* one finger: varies, more fingers: constant */
 } __attribute__((packed,aligned(2)));
 
 /* trackpad finger data size, empirically at least ten fingers */
 #define MAX_FINGERS		16
-#define SIZEOF_FINGER		sizeof(struct tp_finger)
-#define SIZEOF_ALL_FINGERS	(MAX_FINGERS * SIZEOF_FINGER)
 #define MAX_FINGER_ORIENTATION	16384
 
 /* device-specific parameters */
@@ -232,8 +266,17 @@ struct bcm5974_config {
 	int bt_datalen;		/* data length of the button interface */
 	int tp_ep;		/* the endpoint of the trackpad interface */
 	enum tp_type tp_type;	/* type of trackpad interface */
-	int tp_offset;		/* offset to trackpad finger data */
+	int tp_header;		/* bytes in header block */
 	int tp_datalen;		/* data length of the trackpad interface */
+	int tp_button;		/* offset to button data */
+	int tp_fsize;		/* bytes in single finger block */
+	int tp_delta;		/* offset from header to finger struct */
+	int um_size;		/* usb control message length */
+	int um_req_val;		/* usb control message value */
+	int um_req_idx;		/* usb control message index */
+	int um_switch_idx;	/* usb control message mode switch index */
+	int um_switch_on;	/* usb control message mode switch on */
+	int um_switch_off;	/* usb control message mode switch off */
 	struct bcm5974_param p;	/* finger pressure limits */
 	struct bcm5974_param w;	/* finger width limits */
 	struct bcm5974_param x;	/* horizontal limits */
@@ -259,6 +302,24 @@ struct bcm5974 {
 	int slots[MAX_FINGERS];				/* slot assignments */
 };
 
+/* trackpad finger block data, le16-aligned */
+static const struct tp_finger *get_tp_finger(const struct bcm5974 *dev, int i)
+{
+	const struct bcm5974_config *c = &dev->cfg;
+	u8 *f_base = dev->tp_data + c->tp_header + c->tp_delta;
+
+	return (const struct tp_finger *)(f_base + i * c->tp_fsize);
+}
+
+#define DATAFORMAT(type)				\
+	type,						\
+	HEADER_##type,					\
+	HEADER_##type + (MAX_FINGERS) * (FSIZE_##type),	\
+	BUTTON_##type,					\
+	FSIZE_##type,					\
+	DELTA_##type,					\
+	USBMSG_##type
+
 /* logical signal quality */
 #define SN_PRESSURE	45		/* pressure signal-to-noise ratio */
 #define SN_WIDTH	25		/* width signal-to-noise ratio */
@@ -273,7 +334,7 @@ static const struct bcm5974_config bcm5974_config_table[] = {
 		USB_DEVICE_ID_APPLE_WELLSPRING_JIS,
 		0,
 		0x84, sizeof(struct bt_data),
-		0x81, TYPE1, FINGER_TYPE1, FINGER_TYPE1 + SIZEOF_ALL_FINGERS,
+		0x81, DATAFORMAT(TYPE1),
 		{ SN_PRESSURE, 0, 256 },
 		{ SN_WIDTH, 0, 2048 },
 		{ SN_COORD, -4824, 5342 },
@@ -286,7 +347,7 @@ static const struct bcm5974_config bcm5974_config_table[] = {
 		USB_DEVICE_ID_APPLE_WELLSPRING2_JIS,
 		0,
 		0x84, sizeof(struct bt_data),
-		0x81, TYPE1, FINGER_TYPE1, FINGER_TYPE1 + SIZEOF_ALL_FINGERS,
+		0x81, DATAFORMAT(TYPE1),
 		{ SN_PRESSURE, 0, 256 },
 		{ SN_WIDTH, 0, 2048 },
 		{ SN_COORD, -4824, 4824 },
@@ -299,7 +360,7 @@ static const struct bcm5974_config bcm5974_config_table[] = {
 		USB_DEVICE_ID_APPLE_WELLSPRING3_JIS,
 		HAS_INTEGRATED_BUTTON,
 		0x84, sizeof(struct bt_data),
-		0x81, TYPE2, FINGER_TYPE2, FINGER_TYPE2 + SIZEOF_ALL_FINGERS,
+		0x81, DATAFORMAT(TYPE2),
 		{ SN_PRESSURE, 0, 300 },
 		{ SN_WIDTH, 0, 2048 },
 		{ SN_COORD, -4460, 5166 },
@@ -312,7 +373,7 @@ static const struct bcm5974_config bcm5974_config_table[] = {
 		USB_DEVICE_ID_APPLE_WELLSPRING4_JIS,
 		HAS_INTEGRATED_BUTTON,
 		0x84, sizeof(struct bt_data),
-		0x81, TYPE2, FINGER_TYPE2, FINGER_TYPE2 + SIZEOF_ALL_FINGERS,
+		0x81, DATAFORMAT(TYPE2),
 		{ SN_PRESSURE, 0, 300 },
 		{ SN_WIDTH, 0, 2048 },
 		{ SN_COORD, -4620, 5140 },
@@ -325,7 +386,7 @@ static const struct bcm5974_config bcm5974_config_table[] = {
 		USB_DEVICE_ID_APPLE_WELLSPRING4A_JIS,
 		HAS_INTEGRATED_BUTTON,
 		0x84, sizeof(struct bt_data),
-		0x81, TYPE2, FINGER_TYPE2, FINGER_TYPE2 + SIZEOF_ALL_FINGERS,
+		0x81, DATAFORMAT(TYPE2),
 		{ SN_PRESSURE, 0, 300 },
 		{ SN_WIDTH, 0, 2048 },
 		{ SN_COORD, -4616, 5112 },
@@ -338,7 +399,7 @@ static const struct bcm5974_config bcm5974_config_table[] = {
 		USB_DEVICE_ID_APPLE_WELLSPRING5_JIS,
 		HAS_INTEGRATED_BUTTON,
 		0x84, sizeof(struct bt_data),
-		0x81, TYPE2, FINGER_TYPE2, FINGER_TYPE2 + SIZEOF_ALL_FINGERS,
+		0x81, DATAFORMAT(TYPE2),
 		{ SN_PRESSURE, 0, 300 },
 		{ SN_WIDTH, 0, 2048 },
 		{ SN_COORD, -4415, 5050 },
@@ -351,7 +412,7 @@ static const struct bcm5974_config bcm5974_config_table[] = {
 		USB_DEVICE_ID_APPLE_WELLSPRING6_JIS,
 		HAS_INTEGRATED_BUTTON,
 		0x84, sizeof(struct bt_data),
-		0x81, TYPE2, FINGER_TYPE2, FINGER_TYPE2 + SIZEOF_ALL_FINGERS,
+		0x81, DATAFORMAT(TYPE2),
 		{ SN_PRESSURE, 0, 300 },
 		{ SN_WIDTH, 0, 2048 },
 		{ SN_COORD, -4620, 5140 },
@@ -364,7 +425,7 @@ static const struct bcm5974_config bcm5974_config_table[] = {
 		USB_DEVICE_ID_APPLE_WELLSPRING5A_JIS,
 		HAS_INTEGRATED_BUTTON,
 		0x84, sizeof(struct bt_data),
-		0x81, TYPE2, FINGER_TYPE2, FINGER_TYPE2 + SIZEOF_ALL_FINGERS,
+		0x81, DATAFORMAT(TYPE2),
 		{ SN_PRESSURE, 0, 300 },
 		{ SN_WIDTH, 0, 2048 },
 		{ SN_COORD, -4750, 5280 },
@@ -377,7 +438,7 @@ static const struct bcm5974_config bcm5974_config_table[] = {
 		USB_DEVICE_ID_APPLE_WELLSPRING6A_JIS,
 		HAS_INTEGRATED_BUTTON,
 		0x84, sizeof(struct bt_data),
-		0x81, TYPE2, FINGER_TYPE2, FINGER_TYPE2 + SIZEOF_ALL_FINGERS,
+		0x81, DATAFORMAT(TYPE2),
 		{ SN_PRESSURE, 0, 300 },
 		{ SN_WIDTH, 0, 2048 },
 		{ SN_COORD, -4620, 5140 },
@@ -390,7 +451,7 @@ static const struct bcm5974_config bcm5974_config_table[] = {
 		USB_DEVICE_ID_APPLE_WELLSPRING7_JIS,
 		HAS_INTEGRATED_BUTTON,
 		0x84, sizeof(struct bt_data),
-		0x81, TYPE2, FINGER_TYPE2, FINGER_TYPE2 + SIZEOF_ALL_FINGERS,
+		0x81, DATAFORMAT(TYPE2),
 		{ SN_PRESSURE, 0, 300 },
 		{ SN_WIDTH, 0, 2048 },
 		{ SN_COORD, -4750, 5280 },
@@ -403,7 +464,7 @@ static const struct bcm5974_config bcm5974_config_table[] = {
 		USB_DEVICE_ID_APPLE_WELLSPRING7A_JIS,
 		HAS_INTEGRATED_BUTTON,
 		0x84, sizeof(struct bt_data),
-		0x81, TYPE2, FINGER_TYPE2, FINGER_TYPE2 + SIZEOF_ALL_FINGERS,
+		0x81, DATAFORMAT(TYPE2),
 		{ SN_PRESSURE, 0, 300 },
 		{ SN_WIDTH, 0, 2048 },
 		{ SN_COORD, -4750, 5280 },
@@ -416,13 +477,26 @@ static const struct bcm5974_config bcm5974_config_table[] = {
 		USB_DEVICE_ID_APPLE_WELLSPRING8_JIS,
 		HAS_INTEGRATED_BUTTON,
 		0, sizeof(struct bt_data),
-		0x83, TYPE3, FINGER_TYPE3, FINGER_TYPE3 + SIZEOF_ALL_FINGERS,
+		0x83, DATAFORMAT(TYPE3),
 		{ SN_PRESSURE, 0, 300 },
 		{ SN_WIDTH, 0, 2048 },
 		{ SN_COORD, -4620, 5140 },
 		{ SN_COORD, -150, 6600 },
 		{ SN_ORIENT, -MAX_FINGER_ORIENTATION, MAX_FINGER_ORIENTATION }
 	},
+	{
+		USB_DEVICE_ID_APPLE_WELLSPRING9_ANSI,
+		USB_DEVICE_ID_APPLE_WELLSPRING9_ISO,
+		USB_DEVICE_ID_APPLE_WELLSPRING9_JIS,
+		HAS_INTEGRATED_BUTTON,
+		0, sizeof(struct bt_data),
+		0x83, DATAFORMAT(TYPE4),
+		{ SN_PRESSURE, 0, 300 },
+		{ SN_WIDTH, 0, 2048 },
+		{ SN_COORD, -4828, 5345 },
+		{ SN_COORD, -203, 6803 },
+		{ SN_ORIENT, -MAX_FINGER_ORIENTATION, MAX_FINGER_ORIENTATION }
+	},
 	{}
 };
 
@@ -549,19 +623,18 @@ static int report_tp_state(struct bcm5974 *dev, int size)
 	struct input_dev *input = dev->input;
 	int raw_n, i, n = 0;
 
-	if (size < c->tp_offset || (size - c->tp_offset) % SIZEOF_FINGER != 0)
+	if (size < c->tp_header || (size - c->tp_header) % c->tp_fsize != 0)
 		return -EIO;
 
-	/* finger data, le16-aligned */
-	f = (const struct tp_finger *)(dev->tp_data + c->tp_offset);
-	raw_n = (size - c->tp_offset) / SIZEOF_FINGER;
+	raw_n = (size - c->tp_header) / c->tp_fsize;
 
 	for (i = 0; i < raw_n; i++) {
-		if (raw2int(f[i].touch_major) == 0)
+		f = get_tp_finger(dev, i);
+		if (raw2int(f->touch_major) == 0)
 			continue;
-		dev->pos[n].x = raw2int(f[i].abs_x);
-		dev->pos[n].y = c->y.min + c->y.max - raw2int(f[i].abs_y);
-		dev->index[n++] = &f[i];
+		dev->pos[n].x = raw2int(f->abs_x);
+		dev->pos[n].y = c->y.min + c->y.max - raw2int(f->abs_y);
+		dev->index[n++] = f;
 	}
 
 	input_mt_assign_slots(input, dev->slots, dev->pos, n, 0);
@@ -572,32 +645,22 @@ static int report_tp_state(struct bcm5974 *dev, int size)
 
 	input_mt_sync_frame(input);
 
-	report_synaptics_data(input, c, f, raw_n);
+	report_synaptics_data(input, c, get_tp_finger(dev, 0), raw_n);
 
-	/* type 2 reports button events via ibt only */
-	if (c->tp_type == TYPE2) {
-		int ibt = raw2int(dev->tp_data[BUTTON_TYPE2]);
+	/* later types report button events via integrated button only */
+	if (c->caps & HAS_INTEGRATED_BUTTON) {
+		int ibt = raw2int(dev->tp_data[c->tp_button]);
 		input_report_key(input, BTN_LEFT, ibt);
 	}
 
-	if (c->tp_type == TYPE3)
-		input_report_key(input, BTN_LEFT, dev->tp_data[BUTTON_TYPE3]);
-
 	input_sync(input);
 
 	return 0;
 }
 
-/* Wellspring initialization constants */
-#define BCM5974_WELLSPRING_MODE_READ_REQUEST_ID		1
-#define BCM5974_WELLSPRING_MODE_WRITE_REQUEST_ID	9
-#define BCM5974_WELLSPRING_MODE_REQUEST_VALUE		0x300
-#define BCM5974_WELLSPRING_MODE_REQUEST_INDEX		0
-#define BCM5974_WELLSPRING_MODE_VENDOR_VALUE		0x01
-#define BCM5974_WELLSPRING_MODE_NORMAL_VALUE		0x08
-
 static int bcm5974_wellspring_mode(struct bcm5974 *dev, bool on)
 {
+	const struct bcm5974_config *c = &dev->cfg;
 	int retval = 0, size;
 	char *data;
 
@@ -605,7 +668,7 @@ static int bcm5974_wellspring_mode(struct bcm5974 *dev, bool on)
 	if (dev->cfg.tp_type == TYPE3)
 		return 0;
 
-	data = kmalloc(8, GFP_KERNEL);
+	data = kmalloc(c->um_size, GFP_KERNEL);
 	if (!data) {
 		dev_err(&dev->intf->dev, "out of memory\n");
 		retval = -ENOMEM;
@@ -616,28 +679,24 @@ static int bcm5974_wellspring_mode(struct bcm5974 *dev, bool on)
 	size = usb_control_msg(dev->udev, usb_rcvctrlpipe(dev->udev, 0),
 			BCM5974_WELLSPRING_MODE_READ_REQUEST_ID,
 			USB_DIR_IN | USB_TYPE_CLASS | USB_RECIP_INTERFACE,
-			BCM5974_WELLSPRING_MODE_REQUEST_VALUE,
-			BCM5974_WELLSPRING_MODE_REQUEST_INDEX, data, 8, 5000);
+			c->um_req_val, c->um_req_idx, data, c->um_size, 5000);
 
-	if (size != 8) {
+	if (size != c->um_size) {
 		dev_err(&dev->intf->dev, "could not read from device\n");
 		retval = -EIO;
 		goto out;
 	}
 
 	/* apply the mode switch */
-	data[0] = on ?
-		BCM5974_WELLSPRING_MODE_VENDOR_VALUE :
-		BCM5974_WELLSPRING_MODE_NORMAL_VALUE;
+	data[c->um_switch_idx] = on ? c->um_switch_on : c->um_switch_off;
 
 	/* write configuration */
 	size = usb_control_msg(dev->udev, usb_sndctrlpipe(dev->udev, 0),
 			BCM5974_WELLSPRING_MODE_WRITE_REQUEST_ID,
 			USB_DIR_OUT | USB_TYPE_CLASS | USB_RECIP_INTERFACE,
-			BCM5974_WELLSPRING_MODE_REQUEST_VALUE,
-			BCM5974_WELLSPRING_MODE_REQUEST_INDEX, data, 8, 5000);
+			c->um_req_val, c->um_req_idx, data, c->um_size, 5000);
 
-	if (size != 8) {
+	if (size != c->um_size) {
 		dev_err(&dev->intf->dev, "could not write to device\n");
 		retval = -EIO;
 		goto out;
diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index 3a32caf06bf1..6025eb430c0a 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -1484,12 +1484,12 @@ static int __synaptics_init(struct psmouse *psmouse, bool absolute_mode)
 	priv->pkt_type = SYN_MODEL_NEWABS(priv->model_id) ? SYN_NEWABS : SYN_OLDABS;
 
 	psmouse_info(psmouse,
-		     "Touchpad model: %ld, fw: %ld.%ld, id: %#lx, caps: %#lx/%#lx/%#lx, board id: %lu, fw id: %lu\n",
+		     "Touchpad model: %ld, fw: %ld.%ld, id: %#lx, caps: %#lx/%#lx/%#lx/%#lx, board id: %lu, fw id: %lu\n",
 		     SYN_ID_MODEL(priv->identity),
 		     SYN_ID_MAJOR(priv->identity), SYN_ID_MINOR(priv->identity),
 		     priv->model_id,
 		     priv->capabilities, priv->ext_cap, priv->ext_cap_0c,
-		     priv->board_id, priv->firmware_id);
+		     priv->ext_cap_10, priv->board_id, priv->firmware_id);
 
 	set_input_params(psmouse, priv);
 
diff --git a/drivers/input/touchscreen/zforce_ts.c b/drivers/input/touchscreen/zforce_ts.c
index 80285c71786e..f58a196521a9 100644
--- a/drivers/input/touchscreen/zforce_ts.c
+++ b/drivers/input/touchscreen/zforce_ts.c
@@ -429,7 +429,7 @@ static int zforce_read_packet(struct zforce_ts *ts, u8 *buf)
 		goto unlock;
 	}
 
-	if (buf[PAYLOAD_LENGTH] == 0 || buf[PAYLOAD_LENGTH] > FRAME_MAXSIZE) {
+	if (buf[PAYLOAD_LENGTH] == 0) {
 		dev_err(&client->dev, "invalid payload length: %d\n",
 			buf[PAYLOAD_LENGTH]);
 		ret = -EIO;
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index a57e9b749895..658ee39e6569 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -76,8 +76,6 @@ LIST_HEAD(hpet_map);
  * Domain for untranslated devices - only allocated
  * if iommu=pt passed on kernel cmd line.
  */
-static struct protection_domain *pt_domain;
-
 static const struct iommu_ops amd_iommu_ops;
 
 static ATOMIC_NOTIFIER_HEAD(ppr_notifier);
@@ -96,7 +94,7 @@ struct iommu_dev_data {
 	struct protection_domain *domain; /* Domain the device is bound to */
 	u16 devid;			  /* PCI Device ID */
 	bool iommu_v2;			  /* Device can make use of IOMMUv2 */
-	bool passthrough;		  /* Default for device is pt_domain */
+	bool passthrough;		  /* Device is identity mapped */
 	struct {
 		bool enabled;
 		int qdep;
@@ -116,7 +114,6 @@ struct iommu_cmd {
 struct kmem_cache *amd_iommu_irq_cache;
 
 static void update_domain(struct protection_domain *domain);
-static int alloc_passthrough_domain(void);
 static int protection_domain_init(struct protection_domain *domain);
 
 /****************************************************************************
@@ -2167,15 +2164,17 @@ static int attach_device(struct device *dev,
 	dev_data = get_dev_data(dev);
 
 	if (domain->flags & PD_IOMMUV2_MASK) {
-		if (!dev_data->iommu_v2 || !dev_data->passthrough)
+		if (!dev_data->passthrough)
 			return -EINVAL;
 
-		if (pdev_iommuv2_enable(pdev) != 0)
-			return -EINVAL;
+		if (dev_data->iommu_v2) {
+			if (pdev_iommuv2_enable(pdev) != 0)
+				return -EINVAL;
 
-		dev_data->ats.enabled = true;
-		dev_data->ats.qdep    = pci_ats_queue_depth(pdev);
-		dev_data->pri_tlp     = pci_pri_tlp_required(pdev);
+			dev_data->ats.enabled = true;
+			dev_data->ats.qdep    = pci_ats_queue_depth(pdev);
+			dev_data->pri_tlp     = pci_pri_tlp_required(pdev);
+		}
 	} else if (amd_iommu_iotlb_sup &&
 		   pci_enable_ats(pdev, PAGE_SHIFT) == 0) {
 		dev_data->ats.enabled = true;
@@ -2221,15 +2220,6 @@ static void __detach_device(struct iommu_dev_data *dev_data)
 	do_detach(head);
 
 	spin_unlock_irqrestore(&domain->lock, flags);
-
-	/*
-	 * If we run in passthrough mode the device must be assigned to the
-	 * passthrough domain if it is detached from any other domain.
-	 * Make sure we can deassign from the pt_domain itself.
-	 */
-	if (dev_data->passthrough &&
-	    (dev_data->domain == NULL && domain != pt_domain))
-		__attach_device(dev_data, pt_domain);
 }
 
 /*
@@ -2249,7 +2239,7 @@ static void detach_device(struct device *dev)
 	__detach_device(dev_data);
 	write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
 
-	if (domain->flags & PD_IOMMUV2_MASK)
+	if (domain->flags & PD_IOMMUV2_MASK && dev_data->iommu_v2)
 		pdev_iommuv2_disable(to_pci_dev(dev));
 	else if (dev_data->ats.enabled)
 		pci_disable_ats(to_pci_dev(dev));
@@ -2287,17 +2277,15 @@ static int amd_iommu_add_device(struct device *dev)
 
 	BUG_ON(!dev_data);
 
-	if (dev_data->iommu_v2)
+	if (iommu_pass_through || dev_data->iommu_v2)
 		iommu_request_dm_for_dev(dev);
 
 	/* Domains are initialized for this device - have a look what we ended up with */
 	domain = iommu_get_domain_for_dev(dev);
-	if (domain->type == IOMMU_DOMAIN_IDENTITY) {
+	if (domain->type == IOMMU_DOMAIN_IDENTITY)
 		dev_data->passthrough = true;
-		dev->archdata.dma_ops = &nommu_dma_ops;
-	} else {
+	else
 		dev->archdata.dma_ops = &amd_iommu_dma_ops;
-	}
 
 out:
 	iommu_completion_wait(iommu);
@@ -2862,8 +2850,17 @@ int __init amd_iommu_init_api(void)
 
 int __init amd_iommu_init_dma_ops(void)
 {
+	swiotlb        = iommu_pass_through ? 1 : 0;
 	iommu_detected = 1;
-	swiotlb = 0;
+
+	/*
+	 * In case we don't initialize SWIOTLB (actually the common case
+	 * when AMD IOMMU is enabled), make sure there are global
+	 * dma_ops set as a fall-back for devices not handled by this
+	 * driver (for example non-PCI devices).
+	 */
+	if (!swiotlb)
+		dma_ops = &nommu_dma_ops;
 
 	amd_iommu_stats_init();
 
@@ -2947,21 +2944,6 @@ out_err:
 	return NULL;
 }
 
-static int alloc_passthrough_domain(void)
-{
-	if (pt_domain != NULL)
-		return 0;
-
-	/* allocate passthrough domain */
-	pt_domain = protection_domain_alloc();
-	if (!pt_domain)
-		return -ENOMEM;
-
-	pt_domain->mode = PAGE_MODE_NONE;
-
-	return 0;
-}
-
 static struct iommu_domain *amd_iommu_domain_alloc(unsigned type)
 {
 	struct protection_domain *pdomain;
@@ -3222,33 +3204,6 @@ static const struct iommu_ops amd_iommu_ops = {
  *
  *****************************************************************************/
 
-int __init amd_iommu_init_passthrough(void)
-{
-	struct iommu_dev_data *dev_data;
-	struct pci_dev *dev = NULL;
-	int ret;
-
-	ret = alloc_passthrough_domain();
-	if (ret)
-		return ret;
-
-	for_each_pci_dev(dev) {
-		if (!check_device(&dev->dev))
-			continue;
-
-		dev_data = get_dev_data(&dev->dev);
-		dev_data->passthrough = true;
-
-		attach_device(&dev->dev, pt_domain);
-	}
-
-	amd_iommu_stats_init();
-
-	pr_info("AMD-Vi: Initialized for Passthrough Mode\n");
-
-	return 0;
-}
-
 /* IOMMUv2 specific functions */
 int amd_iommu_register_ppr_notifier(struct notifier_block *nb)
 {
@@ -3363,7 +3318,12 @@ static int __flush_pasid(struct protection_domain *domain, int pasid,
 		struct amd_iommu *iommu;
 		int qdep;
 
-		BUG_ON(!dev_data->ats.enabled);
+		/*
+		   There might be non-IOMMUv2 capable devices in an IOMMUv2
+		 * domain.
+		 */
+		if (!dev_data->ats.enabled)
+			continue;
 
 		qdep  = dev_data->ats.qdep;
 		iommu = amd_iommu_rlookup_table[dev_data->devid];
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index dbda9ae68c5d..a24495eb4e26 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -2026,14 +2026,6 @@ static bool detect_ivrs(void)
 	return true;
 }
 
-static int amd_iommu_init_dma(void)
-{
-	if (iommu_pass_through)
-		return amd_iommu_init_passthrough();
-	else
-		return amd_iommu_init_dma_ops();
-}
-
 /****************************************************************************
  *
  * AMD IOMMU Initialization State Machine
@@ -2073,7 +2065,7 @@ static int __init state_next(void)
 		init_state = ret ? IOMMU_INIT_ERROR : IOMMU_INTERRUPTS_EN;
 		break;
 	case IOMMU_INTERRUPTS_EN:
-		ret = amd_iommu_init_dma();
+		ret = amd_iommu_init_dma_ops();
 		init_state = ret ? IOMMU_INIT_ERROR : IOMMU_DMA_OPS;
 		break;
 	case IOMMU_DMA_OPS:
diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c
index 3465faf1809e..f7b875bb70d4 100644
--- a/drivers/iommu/amd_iommu_v2.c
+++ b/drivers/iommu/amd_iommu_v2.c
@@ -132,11 +132,19 @@ static struct device_state *get_device_state(u16 devid)
 
 static void free_device_state(struct device_state *dev_state)
 {
+	struct iommu_group *group;
+
 	/*
 	 * First detach device from domain - No more PRI requests will arrive
 	 * from that device after it is unbound from the IOMMUv2 domain.
 	 */
-	iommu_detach_device(dev_state->domain, &dev_state->pdev->dev);
+	group = iommu_group_get(&dev_state->pdev->dev);
+	if (WARN_ON(!group))
+		return;
+
+	iommu_detach_group(dev_state->domain, group);
+
+	iommu_group_put(group);
 
 	/* Everything is down now, free the IOMMUv2 domain */
 	iommu_domain_free(dev_state->domain);
@@ -731,6 +739,7 @@ EXPORT_SYMBOL(amd_iommu_unbind_pasid);
 int amd_iommu_init_device(struct pci_dev *pdev, int pasids)
 {
 	struct device_state *dev_state;
+	struct iommu_group *group;
 	unsigned long flags;
 	int ret, tmp;
 	u16 devid;
@@ -776,10 +785,16 @@ int amd_iommu_init_device(struct pci_dev *pdev, int pasids)
 	if (ret)
 		goto out_free_domain;
 
-	ret = iommu_attach_device(dev_state->domain, &pdev->dev);
-	if (ret != 0)
+	group = iommu_group_get(&pdev->dev);
+	if (!group)
 		goto out_free_domain;
 
+	ret = iommu_attach_group(dev_state->domain, group);
+	if (ret != 0)
+		goto out_drop_group;
+
+	iommu_group_put(group);
+
 	spin_lock_irqsave(&state_lock, flags);
 
 	if (__get_device_state(devid) != NULL) {
@@ -794,6 +809,9 @@ int amd_iommu_init_device(struct pci_dev *pdev, int pasids)
 
 	return 0;
 
+out_drop_group:
+	iommu_group_put(group);
+
 out_free_domain:
 	iommu_domain_free(dev_state->domain);
 
diff --git a/drivers/macintosh/ans-lcd.c b/drivers/macintosh/ans-lcd.c
index 1a57e88a38f7..cd35079c8c98 100644
--- a/drivers/macintosh/ans-lcd.c
+++ b/drivers/macintosh/ans-lcd.c
@@ -7,7 +7,7 @@
 #include <linux/kernel.h>
 #include <linux/miscdevice.h>
 #include <linux/fcntl.h>
-#include <linux/init.h>
+#include <linux/module.h>
 #include <linux/delay.h>
 #include <linux/fs.h>
 
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index b59727309072..bfec3bdfe598 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -259,7 +259,7 @@ config DM_CRYPT
 	  the ciphers you're going to use in the cryptoapi configuration.
 
 	  For further information on dm-crypt and userspace tools see:
-	  <http://code.google.com/p/cryptsetup/wiki/DMCrypt>
+	  <https://gitlab.com/cryptsetup/cryptsetup/wikis/DMCrypt>
 
 	  To compile this code as a module, choose M here: the module will
 	  be called dm-crypt.
diff --git a/drivers/md/dm-cache-policy-smq.c b/drivers/md/dm-cache-policy-smq.c
index b6f22651dd35..48a4a826ae07 100644
--- a/drivers/md/dm-cache-policy-smq.c
+++ b/drivers/md/dm-cache-policy-smq.c
@@ -1686,7 +1686,7 @@ static struct dm_cache_policy *smq_create(dm_cblock_t cache_size,
 
 	if (from_cblock(cache_size)) {
 		mq->cache_hit_bits = alloc_bitset(from_cblock(cache_size));
-		if (!mq->cache_hit_bits && mq->cache_hit_bits) {
+		if (!mq->cache_hit_bits) {
 			DMERR("couldn't allocate cache hit bitset");
 			goto bad_cache_hit_bits;
 		}
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index b680da5d7b93..1fe93cfea7d3 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -424,6 +424,7 @@ static void free_migration(struct dm_cache_migration *mg)
 		wake_up(&cache->migration_wait);
 
 	mempool_free(mg, cache->migration_pool);
+	wake_worker(cache);
 }
 
 static int prealloc_data_structs(struct cache *cache, struct prealloc *p)
@@ -1966,6 +1967,7 @@ static void process_deferred_bios(struct cache *cache)
 		 * this bio might require one, we pause until there are some
 		 * prepared mappings to process.
 		 */
+		prealloc_used = true;
 		if (prealloc_data_structs(cache, &structs)) {
 			spin_lock_irqsave(&cache->lock, flags);
 			bio_list_merge(&cache->deferred_bios, &bios);
@@ -1981,7 +1983,6 @@ static void process_deferred_bios(struct cache *cache)
 			process_discard_bio(cache, &structs, bio);
 		else
 			process_bio(cache, &structs, bio);
-		prealloc_used = true;
 	}
 
 	if (prealloc_used)
@@ -2010,6 +2011,7 @@ static void process_deferred_cells(struct cache *cache)
 		 * this bio might require one, we pause until there are some
 		 * prepared mappings to process.
 		 */
+		prealloc_used = true;
 		if (prealloc_data_structs(cache, &structs)) {
 			spin_lock_irqsave(&cache->lock, flags);
 			list_splice(&cells, &cache->deferred_cells);
@@ -2018,7 +2020,6 @@ static void process_deferred_cells(struct cache *cache)
 		}
 
 		process_cell(cache, &structs, cell);
-		prealloc_used = true;
 	}
 
 	if (prealloc_used)
@@ -2080,6 +2081,7 @@ static void writeback_some_dirty_blocks(struct cache *cache)
 		if (policy_writeback_work(cache->policy, &oblock, &cblock, busy))
 			break; /* no work to do */
 
+		prealloc_used = true;
 		if (prealloc_data_structs(cache, &structs) ||
 		    get_cell(cache, oblock, &structs, &old_ocell)) {
 			policy_set_dirty(cache->policy, oblock);
@@ -2087,7 +2089,6 @@ static void writeback_some_dirty_blocks(struct cache *cache)
 		}
 
 		writeback(cache, &structs, oblock, cblock, old_ocell);
-		prealloc_used = true;
 	}
 
 	if (prealloc_used)
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 1c50c580215c..d2bbe8cc1e97 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -666,16 +666,21 @@ static void requeue_io(struct thin_c *tc)
 	requeue_deferred_cells(tc);
 }
 
-static void error_retry_list(struct pool *pool)
+static void error_retry_list_with_code(struct pool *pool, int error)
 {
 	struct thin_c *tc;
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(tc, &pool->active_thins, list)
-		error_thin_bio_list(tc, &tc->retry_on_resume_list, -EIO);
+		error_thin_bio_list(tc, &tc->retry_on_resume_list, error);
 	rcu_read_unlock();
 }
 
+static void error_retry_list(struct pool *pool)
+{
+	return error_retry_list_with_code(pool, -EIO);
+}
+
 /*
  * This section of code contains the logic for processing a thin device's IO.
  * Much of the code depends on pool object resources (lists, workqueues, etc)
@@ -2297,7 +2302,7 @@ static void do_no_space_timeout(struct work_struct *ws)
 	if (get_pool_mode(pool) == PM_OUT_OF_DATA_SPACE && !pool->pf.error_if_no_space) {
 		pool->pf.error_if_no_space = true;
 		notify_of_pool_mode_change_to_oods(pool);
-		error_retry_list(pool);
+		error_retry_list_with_code(pool, -ENOSPC);
 	}
 }
 
diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c
index caeb39561567..bf9eb2ecf960 100644
--- a/drivers/net/ethernet/cadence/macb.c
+++ b/drivers/net/ethernet/cadence/macb.c
@@ -104,6 +104,57 @@ static void *macb_rx_buffer(struct macb *bp, unsigned int index)
 	return bp->rx_buffers + bp->rx_buffer_size * macb_rx_ring_wrap(index);
 }
 
+/* I/O accessors */
+static u32 hw_readl_native(struct macb *bp, int offset)
+{
+	return __raw_readl(bp->regs + offset);
+}
+
+static void hw_writel_native(struct macb *bp, int offset, u32 value)
+{
+	__raw_writel(value, bp->regs + offset);
+}
+
+static u32 hw_readl(struct macb *bp, int offset)
+{
+	return readl_relaxed(bp->regs + offset);
+}
+
+static void hw_writel(struct macb *bp, int offset, u32 value)
+{
+	writel_relaxed(value, bp->regs + offset);
+}
+
+/*
+ * Find the CPU endianness by using the loopback bit of NCR register. When the
+ * CPU is in big endian we need to program swaped mode for management
+ * descriptor access.
+ */
+static bool hw_is_native_io(void __iomem *addr)
+{
+	u32 value = MACB_BIT(LLB);
+
+	__raw_writel(value, addr + MACB_NCR);
+	value = __raw_readl(addr + MACB_NCR);
+
+	/* Write 0 back to disable everything */
+	__raw_writel(0, addr + MACB_NCR);
+
+	return value == MACB_BIT(LLB);
+}
+
+static bool hw_is_gem(void __iomem *addr, bool native_io)
+{
+	u32 id;
+
+	if (native_io)
+		id = __raw_readl(addr + MACB_MID);
+	else
+		id = readl_relaxed(addr + MACB_MID);
+
+	return MACB_BFEXT(IDNUM, id) >= 0x2;
+}
+
 static void macb_set_hwaddr(struct macb *bp)
 {
 	u32 bottom;
@@ -160,7 +211,7 @@ static void macb_get_hwaddr(struct macb *bp)
 		}
 	}
 
-	netdev_info(bp->dev, "invalid hw address, using random\n");
+	dev_info(&bp->pdev->dev, "invalid hw address, using random\n");
 	eth_hw_addr_random(bp->dev);
 }
 
@@ -252,7 +303,6 @@ static void macb_handle_link_change(struct net_device *dev)
 	struct macb *bp = netdev_priv(dev);
 	struct phy_device *phydev = bp->phy_dev;
 	unsigned long flags;
-
 	int status_change = 0;
 
 	spin_lock_irqsave(&bp->lock, flags);
@@ -449,14 +499,14 @@ err_out:
 
 static void macb_update_stats(struct macb *bp)
 {
-	u32 __iomem *reg = bp->regs + MACB_PFR;
 	u32 *p = &bp->hw_stats.macb.rx_pause_frames;
 	u32 *end = &bp->hw_stats.macb.tx_pause_frames + 1;
+	int offset = MACB_PFR;
 
 	WARN_ON((unsigned long)(end - p - 1) != (MACB_TPF - MACB_PFR) / 4);
 
-	for(; p < end; p++, reg++)
-		*p += readl_relaxed(reg);
+	for(; p < end; p++, offset += 4)
+		*p += bp->macb_reg_readl(bp, offset);
 }
 
 static int macb_halt_tx(struct macb *bp)
@@ -1107,12 +1157,6 @@ static void macb_poll_controller(struct net_device *dev)
 }
 #endif
 
-static inline unsigned int macb_count_tx_descriptors(struct macb *bp,
-						     unsigned int len)
-{
-	return (len + bp->max_tx_length - 1) / bp->max_tx_length;
-}
-
 static unsigned int macb_tx_map(struct macb *bp,
 				struct macb_queue *queue,
 				struct sk_buff *skb)
@@ -1263,11 +1307,11 @@ static int macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	 * socket buffer: skb fragments of jumbo frames may need to be
 	 * splitted into many buffer descriptors.
 	 */
-	count = macb_count_tx_descriptors(bp, skb_headlen(skb));
+	count = DIV_ROUND_UP(skb_headlen(skb), bp->max_tx_length);
 	nr_frags = skb_shinfo(skb)->nr_frags;
 	for (f = 0; f < nr_frags; f++) {
 		frag_size = skb_frag_size(&skb_shinfo(skb)->frags[f]);
-		count += macb_count_tx_descriptors(bp, frag_size);
+		count += DIV_ROUND_UP(frag_size, bp->max_tx_length);
 	}
 
 	spin_lock_irqsave(&bp->lock, flags);
@@ -1603,7 +1647,6 @@ static u32 macb_dbw(struct macb *bp)
 static void macb_configure_dma(struct macb *bp)
 {
 	u32 dmacfg;
-	u32 tmp, ncr;
 
 	if (macb_is_gem(bp)) {
 		dmacfg = gem_readl(bp, DMACFG) & ~GEM_BF(RXBS, -1L);
@@ -1613,22 +1656,11 @@ static void macb_configure_dma(struct macb *bp)
 		dmacfg |= GEM_BIT(TXPBMS) | GEM_BF(RXBMS, -1L);
 		dmacfg &= ~GEM_BIT(ENDIA_PKT);
 
-		/* Find the CPU endianness by using the loopback bit of net_ctrl
-		 * register. save it first. When the CPU is in big endian we
-		 * need to program swaped mode for management descriptor access.
-		 */
-		ncr = macb_readl(bp, NCR);
-		__raw_writel(MACB_BIT(LLB), bp->regs + MACB_NCR);
-		tmp =  __raw_readl(bp->regs + MACB_NCR);
-
-		if (tmp == MACB_BIT(LLB))
+		if (bp->native_io)
 			dmacfg &= ~GEM_BIT(ENDIA_DESC);
 		else
 			dmacfg |= GEM_BIT(ENDIA_DESC); /* CPU in big endian */
 
-		/* Restore net_ctrl */
-		macb_writel(bp, NCR, ncr);
-
 		if (bp->dev->features & NETIF_F_HW_CSUM)
 			dmacfg |= GEM_BIT(TXCOEN);
 		else
@@ -1897,19 +1929,19 @@ static int macb_change_mtu(struct net_device *dev, int new_mtu)
 
 static void gem_update_stats(struct macb *bp)
 {
-	int i;
+	unsigned int i;
 	u32 *p = &bp->hw_stats.gem.tx_octets_31_0;
 
 	for (i = 0; i < GEM_STATS_LEN; ++i, ++p) {
 		u32 offset = gem_statistics[i].offset;
-		u64 val = readl_relaxed(bp->regs + offset);
+		u64 val = bp->macb_reg_readl(bp, offset);
 
 		bp->ethtool_stats[i] += val;
 		*p += val;
 
 		if (offset == GEM_OCTTXL || offset == GEM_OCTRXL) {
 			/* Add GEM_OCTTXH, GEM_OCTRXH */
-			val = readl_relaxed(bp->regs + offset + 4);
+			val = bp->macb_reg_readl(bp, offset + 4);
 			bp->ethtool_stats[i] += ((u64)val) << 32;
 			*(++p) += val;
 		}
@@ -1976,7 +2008,7 @@ static int gem_get_sset_count(struct net_device *dev, int sset)
 
 static void gem_get_ethtool_strings(struct net_device *dev, u32 sset, u8 *p)
 {
-	int i;
+	unsigned int i;
 
 	switch (sset) {
 	case ETH_SS_STATS:
@@ -2190,7 +2222,7 @@ static void macb_configure_caps(struct macb *bp, const struct macb_config *dt_co
 	if (dt_conf)
 		bp->caps = dt_conf->caps;
 
-	if (macb_is_gem_hw(bp->regs)) {
+	if (hw_is_gem(bp->regs, bp->native_io)) {
 		bp->caps |= MACB_CAPS_MACB_IS_GEM;
 
 		dcfg = gem_readl(bp, DCFG1);
@@ -2201,10 +2233,11 @@ static void macb_configure_caps(struct macb *bp, const struct macb_config *dt_co
 			bp->caps |= MACB_CAPS_FIFO_MODE;
 	}
 
-	netdev_dbg(bp->dev, "Cadence caps 0x%08x\n", bp->caps);
+	dev_dbg(&bp->pdev->dev, "Cadence caps 0x%08x\n", bp->caps);
 }
 
 static void macb_probe_queues(void __iomem *mem,
+			      bool native_io,
 			      unsigned int *queue_mask,
 			      unsigned int *num_queues)
 {
@@ -2219,7 +2252,7 @@ static void macb_probe_queues(void __iomem *mem,
 	 * we are early in the probe process and don't have the
 	 * MACB_CAPS_MACB_IS_GEM flag positioned
 	 */
-	if (!macb_is_gem_hw(mem))
+	if (!hw_is_gem(mem, native_io))
 		return;
 
 	/* bit 0 is never set but queue 0 always exists */
@@ -2786,6 +2819,7 @@ static int macb_probe(struct platform_device *pdev)
 	struct clk *pclk, *hclk, *tx_clk;
 	unsigned int queue_mask, num_queues;
 	struct macb_platform_data *pdata;
+	bool native_io;
 	struct phy_device *phydev;
 	struct net_device *dev;
 	struct resource *regs;
@@ -2794,6 +2828,11 @@ static int macb_probe(struct platform_device *pdev)
 	struct macb *bp;
 	int err;
 
+	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	mem = devm_ioremap_resource(&pdev->dev, regs);
+	if (IS_ERR(mem))
+		return PTR_ERR(mem);
+
 	if (np) {
 		const struct of_device_id *match;
 
@@ -2809,14 +2848,9 @@ static int macb_probe(struct platform_device *pdev)
 	if (err)
 		return err;
 
-	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	mem = devm_ioremap_resource(&pdev->dev, regs);
-	if (IS_ERR(mem)) {
-		err = PTR_ERR(mem);
-		goto err_disable_clocks;
-	}
+	native_io = hw_is_native_io(mem);
 
-	macb_probe_queues(mem, &queue_mask, &num_queues);
+	macb_probe_queues(mem, native_io, &queue_mask, &num_queues);
 	dev = alloc_etherdev_mq(sizeof(*bp), num_queues);
 	if (!dev) {
 		err = -ENOMEM;
@@ -2831,6 +2865,14 @@ static int macb_probe(struct platform_device *pdev)
 	bp->pdev = pdev;
 	bp->dev = dev;
 	bp->regs = mem;
+	bp->native_io = native_io;
+	if (native_io) {
+		bp->macb_reg_readl = hw_readl_native;
+		bp->macb_reg_writel = hw_writel_native;
+	} else {
+		bp->macb_reg_readl = hw_readl;
+		bp->macb_reg_writel = hw_writel;
+	}
 	bp->num_queues = num_queues;
 	bp->queue_mask = queue_mask;
 	if (macb_config)
@@ -2838,9 +2880,8 @@ static int macb_probe(struct platform_device *pdev)
 	bp->pclk = pclk;
 	bp->hclk = hclk;
 	bp->tx_clk = tx_clk;
-	if (macb_config->jumbo_max_len) {
+	if (macb_config)
 		bp->jumbo_max_len = macb_config->jumbo_max_len;
-	}
 
 	spin_lock_init(&bp->lock);
 
diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index d74655993d4b..1895b6b2addd 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -429,18 +429,12 @@
 	 | GEM_BF(name, value))
 
 /* Register access macros */
-#define macb_readl(port,reg)				\
-	readl_relaxed((port)->regs + MACB_##reg)
-#define macb_writel(port,reg,value)			\
-	writel_relaxed((value), (port)->regs + MACB_##reg)
-#define gem_readl(port, reg)				\
-	readl_relaxed((port)->regs + GEM_##reg)
-#define gem_writel(port, reg, value)			\
-	writel_relaxed((value), (port)->regs + GEM_##reg)
-#define queue_readl(queue, reg)				\
-	readl_relaxed((queue)->bp->regs + (queue)->reg)
-#define queue_writel(queue, reg, value)			\
-	writel_relaxed((value), (queue)->bp->regs + (queue)->reg)
+#define macb_readl(port, reg)		(port)->macb_reg_readl((port), MACB_##reg)
+#define macb_writel(port, reg, value)	(port)->macb_reg_writel((port), MACB_##reg, (value))
+#define gem_readl(port, reg)		(port)->macb_reg_readl((port), GEM_##reg)
+#define gem_writel(port, reg, value)	(port)->macb_reg_writel((port), GEM_##reg, (value))
+#define queue_readl(queue, reg)		(queue)->bp->macb_reg_readl((queue)->bp, (queue)->reg)
+#define queue_writel(queue, reg, value)	(queue)->bp->macb_reg_writel((queue)->bp, (queue)->reg, (value))
 
 /* Conditional GEM/MACB macros.  These perform the operation to the correct
  * register dependent on whether the device is a GEM or a MACB.  For registers
@@ -785,6 +779,11 @@ struct macb_queue {
 
 struct macb {
 	void __iomem		*regs;
+	bool			native_io;
+
+	/* hardware IO accessors */
+	u32	(*macb_reg_readl)(struct macb *bp, int offset);
+	void	(*macb_reg_writel)(struct macb *bp, int offset, u32 value);
 
 	unsigned int		rx_tail;
 	unsigned int		rx_prepared_head;
@@ -817,9 +816,9 @@ struct macb {
 
 	struct mii_bus		*mii_bus;
 	struct phy_device	*phy_dev;
-	unsigned int 		link;
-	unsigned int 		speed;
-	unsigned int 		duplex;
+	int 			link;
+	int 			speed;
+	int 			duplex;
 
 	u32			caps;
 	unsigned int		dma_burst_length;
@@ -843,9 +842,4 @@ static inline bool macb_is_gem(struct macb *bp)
 	return !!(bp->caps & MACB_CAPS_MACB_IS_GEM);
 }
 
-static inline bool macb_is_gem_hw(void __iomem *addr)
-{
-	return !!(MACB_BFEXT(IDNUM, readl_relaxed(addr + MACB_MID)) >= 0x2);
-}
-
 #endif /* _MACB_H */
diff --git a/drivers/net/ethernet/cavium/thunder/nic.h b/drivers/net/ethernet/cavium/thunder/nic.h
index dda8a02b7322..8aee250904ec 100644
--- a/drivers/net/ethernet/cavium/thunder/nic.h
+++ b/drivers/net/ethernet/cavium/thunder/nic.h
@@ -125,6 +125,15 @@
  */
 #define NICPF_CLK_PER_INT_TICK		2
 
+/* Time to wait before we decide that a SQ is stuck.
+ *
+ * Since both pkt rx and tx notifications are done with same CQ,
+ * when packets are being received at very high rate (eg: L2 forwarding)
+ * then freeing transmitted skbs will be delayed and watchdog
+ * will kick in, resetting interface. Hence keeping this value high.
+ */
+#define	NICVF_TX_TIMEOUT		(50 * HZ)
+
 struct nicvf_cq_poll {
 	u8	cq_idx;		/* Completion queue index */
 	struct	napi_struct napi;
@@ -216,8 +225,9 @@ struct nicvf_drv_stats {
 	/* Tx */
 	u64 tx_frames_ok;
 	u64 tx_drops;
-	u64 tx_busy;
 	u64 tx_tso;
+	u64 txq_stop;
+	u64 txq_wake;
 };
 
 struct nicvf {
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
index 16bd2d772db9..a4228e664567 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
@@ -66,9 +66,10 @@ static const struct nicvf_stat nicvf_drv_stats[] = {
 	NICVF_DRV_STAT(rx_frames_jumbo),
 	NICVF_DRV_STAT(rx_drops),
 	NICVF_DRV_STAT(tx_frames_ok),
-	NICVF_DRV_STAT(tx_busy),
 	NICVF_DRV_STAT(tx_tso),
 	NICVF_DRV_STAT(tx_drops),
+	NICVF_DRV_STAT(txq_stop),
+	NICVF_DRV_STAT(txq_wake),
 };
 
 static const struct nicvf_stat nicvf_queue_stats[] = {
@@ -126,6 +127,7 @@ static void nicvf_set_msglevel(struct net_device *netdev, u32 lvl)
 
 static void nicvf_get_strings(struct net_device *netdev, u32 sset, u8 *data)
 {
+	struct nicvf *nic = netdev_priv(netdev);
 	int stats, qidx;
 
 	if (sset != ETH_SS_STATS)
@@ -141,7 +143,7 @@ static void nicvf_get_strings(struct net_device *netdev, u32 sset, u8 *data)
 		data += ETH_GSTRING_LEN;
 	}
 
-	for (qidx = 0; qidx < MAX_RCV_QUEUES_PER_QS; qidx++) {
+	for (qidx = 0; qidx < nic->qs->rq_cnt; qidx++) {
 		for (stats = 0; stats < nicvf_n_queue_stats; stats++) {
 			sprintf(data, "rxq%d: %s", qidx,
 				nicvf_queue_stats[stats].name);
@@ -149,7 +151,7 @@ static void nicvf_get_strings(struct net_device *netdev, u32 sset, u8 *data)
 		}
 	}
 
-	for (qidx = 0; qidx < MAX_SND_QUEUES_PER_QS; qidx++) {
+	for (qidx = 0; qidx < nic->qs->sq_cnt; qidx++) {
 		for (stats = 0; stats < nicvf_n_queue_stats; stats++) {
 			sprintf(data, "txq%d: %s", qidx,
 				nicvf_queue_stats[stats].name);
@@ -170,12 +172,14 @@ static void nicvf_get_strings(struct net_device *netdev, u32 sset, u8 *data)
 
 static int nicvf_get_sset_count(struct net_device *netdev, int sset)
 {
+	struct nicvf *nic = netdev_priv(netdev);
+
 	if (sset != ETH_SS_STATS)
 		return -EINVAL;
 
 	return nicvf_n_hw_stats + nicvf_n_drv_stats +
 		(nicvf_n_queue_stats *
-		 (MAX_RCV_QUEUES_PER_QS + MAX_SND_QUEUES_PER_QS)) +
+		 (nic->qs->rq_cnt + nic->qs->sq_cnt)) +
 		BGX_RX_STATS_COUNT + BGX_TX_STATS_COUNT;
 }
 
@@ -197,13 +201,13 @@ static void nicvf_get_ethtool_stats(struct net_device *netdev,
 		*(data++) = ((u64 *)&nic->drv_stats)
 				[nicvf_drv_stats[stat].index];
 
-	for (qidx = 0; qidx < MAX_RCV_QUEUES_PER_QS; qidx++) {
+	for (qidx = 0; qidx < nic->qs->rq_cnt; qidx++) {
 		for (stat = 0; stat < nicvf_n_queue_stats; stat++)
 			*(data++) = ((u64 *)&nic->qs->rq[qidx].stats)
 					[nicvf_queue_stats[stat].index];
 	}
 
-	for (qidx = 0; qidx < MAX_SND_QUEUES_PER_QS; qidx++) {
+	for (qidx = 0; qidx < nic->qs->sq_cnt; qidx++) {
 		for (stat = 0; stat < nicvf_n_queue_stats; stat++)
 			*(data++) = ((u64 *)&nic->qs->sq[qidx].stats)
 					[nicvf_queue_stats[stat].index];
@@ -543,6 +547,7 @@ static int nicvf_set_channels(struct net_device *dev,
 {
 	struct nicvf *nic = netdev_priv(dev);
 	int err = 0;
+	bool if_up = netif_running(dev);
 
 	if (!channel->rx_count || !channel->tx_count)
 		return -EINVAL;
@@ -551,6 +556,9 @@ static int nicvf_set_channels(struct net_device *dev,
 	if (channel->tx_count > MAX_SND_QUEUES_PER_QS)
 		return -EINVAL;
 
+	if (if_up)
+		nicvf_stop(dev);
+
 	nic->qs->rq_cnt = channel->rx_count;
 	nic->qs->sq_cnt = channel->tx_count;
 	nic->qs->cq_cnt = max(nic->qs->rq_cnt, nic->qs->sq_cnt);
@@ -559,11 +567,9 @@ static int nicvf_set_channels(struct net_device *dev,
 	if (err)
 		return err;
 
-	if (!netif_running(dev))
-		return err;
+	if (if_up)
+		nicvf_open(dev);
 
-	nicvf_stop(dev);
-	nicvf_open(dev);
 	netdev_info(dev, "Setting num Tx rings to %d, Rx rings to %d success\n",
 		    nic->qs->sq_cnt, nic->qs->rq_cnt);
 
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index 8b119a035b7e..3b90afb8c293 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -234,7 +234,7 @@ static void  nicvf_handle_mbx_intr(struct nicvf *nic)
 				    nic->duplex == DUPLEX_FULL ?
 				"Full duplex" : "Half duplex");
 			netif_carrier_on(nic->netdev);
-			netif_tx_wake_all_queues(nic->netdev);
+			netif_tx_start_all_queues(nic->netdev);
 		} else {
 			netdev_info(nic->netdev, "%s: Link is Down\n",
 				    nic->netdev->name);
@@ -425,6 +425,7 @@ static void nicvf_snd_pkt_handler(struct net_device *netdev,
 	if (skb) {
 		prefetch(skb);
 		dev_consume_skb_any(skb);
+		sq->skbuff[cqe_tx->sqe_ptr] = (u64)NULL;
 	}
 }
 
@@ -476,12 +477,13 @@ static void nicvf_rcv_pkt_handler(struct net_device *netdev,
 static int nicvf_cq_intr_handler(struct net_device *netdev, u8 cq_idx,
 				 struct napi_struct *napi, int budget)
 {
-	int processed_cqe, work_done = 0;
+	int processed_cqe, work_done = 0, tx_done = 0;
 	int cqe_count, cqe_head;
 	struct nicvf *nic = netdev_priv(netdev);
 	struct queue_set *qs = nic->qs;
 	struct cmp_queue *cq = &qs->cq[cq_idx];
 	struct cqe_rx_t *cq_desc;
+	struct netdev_queue *txq;
 
 	spin_lock_bh(&cq->lock);
 loop:
@@ -496,8 +498,8 @@ loop:
 	cqe_head = nicvf_queue_reg_read(nic, NIC_QSET_CQ_0_7_HEAD, cq_idx) >> 9;
 	cqe_head &= 0xFFFF;
 
-	netdev_dbg(nic->netdev, "%s cqe_count %d cqe_head %d\n",
-		   __func__, cqe_count, cqe_head);
+	netdev_dbg(nic->netdev, "%s CQ%d cqe_count %d cqe_head %d\n",
+		   __func__, cq_idx, cqe_count, cqe_head);
 	while (processed_cqe < cqe_count) {
 		/* Get the CQ descriptor */
 		cq_desc = (struct cqe_rx_t *)GET_CQ_DESC(cq, cqe_head);
@@ -511,8 +513,8 @@ loop:
 			break;
 		}
 
-		netdev_dbg(nic->netdev, "cq_desc->cqe_type %d\n",
-			   cq_desc->cqe_type);
+		netdev_dbg(nic->netdev, "CQ%d cq_desc->cqe_type %d\n",
+			   cq_idx, cq_desc->cqe_type);
 		switch (cq_desc->cqe_type) {
 		case CQE_TYPE_RX:
 			nicvf_rcv_pkt_handler(netdev, napi, cq,
@@ -522,6 +524,7 @@ loop:
 		case CQE_TYPE_SEND:
 			nicvf_snd_pkt_handler(netdev, cq,
 					      (void *)cq_desc, CQE_TYPE_SEND);
+			tx_done++;
 		break;
 		case CQE_TYPE_INVALID:
 		case CQE_TYPE_RX_SPLIT:
@@ -532,8 +535,9 @@ loop:
 		}
 		processed_cqe++;
 	}
-	netdev_dbg(nic->netdev, "%s processed_cqe %d work_done %d budget %d\n",
-		   __func__, processed_cqe, work_done, budget);
+	netdev_dbg(nic->netdev,
+		   "%s CQ%d processed_cqe %d work_done %d budget %d\n",
+		   __func__, cq_idx, processed_cqe, work_done, budget);
 
 	/* Ring doorbell to inform H/W to reuse processed CQEs */
 	nicvf_queue_reg_write(nic, NIC_QSET_CQ_0_7_DOOR,
@@ -543,6 +547,19 @@ loop:
 		goto loop;
 
 done:
+	/* Wakeup TXQ if its stopped earlier due to SQ full */
+	if (tx_done) {
+		txq = netdev_get_tx_queue(netdev, cq_idx);
+		if (netif_tx_queue_stopped(txq)) {
+			netif_tx_start_queue(txq);
+			nic->drv_stats.txq_wake++;
+			if (netif_msg_tx_err(nic))
+				netdev_warn(netdev,
+					    "%s: Transmit queue wakeup SQ%d\n",
+					    netdev->name, cq_idx);
+		}
+	}
+
 	spin_unlock_bh(&cq->lock);
 	return work_done;
 }
@@ -554,15 +571,10 @@ static int nicvf_poll(struct napi_struct *napi, int budget)
 	struct net_device *netdev = napi->dev;
 	struct nicvf *nic = netdev_priv(netdev);
 	struct nicvf_cq_poll *cq;
-	struct netdev_queue *txq;
 
 	cq = container_of(napi, struct nicvf_cq_poll, napi);
 	work_done = nicvf_cq_intr_handler(netdev, cq->cq_idx, napi, budget);
 
-	txq = netdev_get_tx_queue(netdev, cq->cq_idx);
-	if (netif_tx_queue_stopped(txq))
-		netif_tx_wake_queue(txq);
-
 	if (work_done < budget) {
 		/* Slow packet rate, exit polling */
 		napi_complete(napi);
@@ -833,9 +845,9 @@ static netdev_tx_t nicvf_xmit(struct sk_buff *skb, struct net_device *netdev)
 		return NETDEV_TX_OK;
 	}
 
-	if (!nicvf_sq_append_skb(nic, skb) && !netif_tx_queue_stopped(txq)) {
+	if (!netif_tx_queue_stopped(txq) && !nicvf_sq_append_skb(nic, skb)) {
 		netif_tx_stop_queue(txq);
-		nic->drv_stats.tx_busy++;
+		nic->drv_stats.txq_stop++;
 		if (netif_msg_tx_err(nic))
 			netdev_warn(netdev,
 				    "%s: Transmit ring full, stopping SQ%d\n",
@@ -859,7 +871,6 @@ int nicvf_stop(struct net_device *netdev)
 	nicvf_send_msg_to_pf(nic, &mbx);
 
 	netif_carrier_off(netdev);
-	netif_tx_disable(netdev);
 
 	/* Disable RBDR & QS error interrupts */
 	for (qidx = 0; qidx < qs->rbdr_cnt; qidx++) {
@@ -894,6 +905,8 @@ int nicvf_stop(struct net_device *netdev)
 		kfree(cq_poll);
 	}
 
+	netif_tx_disable(netdev);
+
 	/* Free resources */
 	nicvf_config_data_transfer(nic, false);
 
@@ -988,6 +1001,9 @@ int nicvf_open(struct net_device *netdev)
 	for (qidx = 0; qidx < qs->rbdr_cnt; qidx++)
 		nicvf_enable_intr(nic, NICVF_INTR_RBDR, qidx);
 
+	nic->drv_stats.txq_stop = 0;
+	nic->drv_stats.txq_wake = 0;
+
 	netif_carrier_on(netdev);
 	netif_tx_start_all_queues(netdev);
 
@@ -1278,6 +1294,7 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	netdev->hw_features = netdev->features;
 
 	netdev->netdev_ops = &nicvf_netdev_ops;
+	netdev->watchdog_timeo = NICVF_TX_TIMEOUT;
 
 	INIT_WORK(&nic->reset_task, nicvf_reset_task);
 
@@ -1318,11 +1335,17 @@ static void nicvf_remove(struct pci_dev *pdev)
 	pci_disable_device(pdev);
 }
 
+static void nicvf_shutdown(struct pci_dev *pdev)
+{
+	nicvf_remove(pdev);
+}
+
 static struct pci_driver nicvf_driver = {
 	.name = DRV_NAME,
 	.id_table = nicvf_id_table,
 	.probe = nicvf_probe,
 	.remove = nicvf_remove,
+	.shutdown = nicvf_shutdown,
 };
 
 static int __init nicvf_init_module(void)
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
index d69d228d11a0..ca4240aa6d15 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
@@ -103,9 +103,11 @@ static inline int nicvf_alloc_rcv_buffer(struct nicvf *nic, gfp_t gfp,
 
 	/* Allocate a new page */
 	if (!nic->rb_page) {
-		nic->rb_page = alloc_pages(gfp | __GFP_COMP, order);
+		nic->rb_page = alloc_pages(gfp | __GFP_COMP | __GFP_NOWARN,
+					   order);
 		if (!nic->rb_page) {
-			netdev_err(nic->netdev, "Failed to allocate new rcv buffer\n");
+			netdev_err(nic->netdev,
+				   "Failed to allocate new rcv buffer\n");
 			return -ENOMEM;
 		}
 		nic->rb_page_offset = 0;
@@ -382,7 +384,8 @@ static void nicvf_free_snd_queue(struct nicvf *nic, struct snd_queue *sq)
 		return;
 
 	if (sq->tso_hdrs)
-		dma_free_coherent(&nic->pdev->dev, sq->dmem.q_len,
+		dma_free_coherent(&nic->pdev->dev,
+				  sq->dmem.q_len * TSO_HEADER_SIZE,
 				  sq->tso_hdrs, sq->tso_hdrs_phys);
 
 	kfree(sq->skbuff);
@@ -863,10 +866,11 @@ void nicvf_sq_free_used_descs(struct net_device *netdev, struct snd_queue *sq,
 			continue;
 		}
 		skb = (struct sk_buff *)sq->skbuff[sq->head];
+		if (skb)
+			dev_kfree_skb_any(skb);
 		atomic64_add(1, (atomic64_t *)&netdev->stats.tx_packets);
 		atomic64_add(hdr->tot_len,
 			     (atomic64_t *)&netdev->stats.tx_bytes);
-		dev_kfree_skb_any(skb);
 		nicvf_put_sq_desc(sq, hdr->subdesc_cnt + 1);
 	}
 }
@@ -992,7 +996,7 @@ static inline void nicvf_sq_add_gather_subdesc(struct snd_queue *sq, int qentry,
 
 	memset(gather, 0, SND_QUEUE_DESC_SIZE);
 	gather->subdesc_type = SQ_DESC_TYPE_GATHER;
-	gather->ld_type = NIC_SEND_LD_TYPE_E_LDWB;
+	gather->ld_type = NIC_SEND_LD_TYPE_E_LDD;
 	gather->size = size;
 	gather->addr = data;
 }
@@ -1048,7 +1052,7 @@ static int nicvf_sq_append_tso(struct nicvf *nic, struct snd_queue *sq,
 		}
 		nicvf_sq_add_hdr_subdesc(sq, hdr_qentry,
 					 seg_subdescs - 1, skb, seg_len);
-		sq->skbuff[hdr_qentry] = 0;
+		sq->skbuff[hdr_qentry] = (u64)NULL;
 		qentry = nicvf_get_nxt_sqentry(sq, qentry);
 
 		desc_cnt += seg_subdescs;
@@ -1062,6 +1066,7 @@ static int nicvf_sq_append_tso(struct nicvf *nic, struct snd_queue *sq,
 	/* Inform HW to xmit all TSO segments */
 	nicvf_queue_reg_write(nic, NIC_QSET_SQ_0_7_DOOR,
 			      skb_get_queue_mapping(skb), desc_cnt);
+	nic->drv_stats.tx_tso++;
 	return 1;
 }
 
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
index 8341bdf755d1..f0937b7bfe9f 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
@@ -62,7 +62,7 @@
 #define SND_QUEUE_CNT		8
 #define CMP_QUEUE_CNT		8 /* Max of RCV and SND qcount */
 
-#define SND_QSIZE		SND_QUEUE_SIZE4
+#define SND_QSIZE		SND_QUEUE_SIZE2
 #define SND_QUEUE_LEN		(1ULL << (SND_QSIZE + 10))
 #define MAX_SND_QUEUE_LEN	(1ULL << (SND_QUEUE_SIZE6 + 10))
 #define SND_QUEUE_THRESH	2ULL
@@ -70,7 +70,10 @@
 /* Since timestamp not enabled, otherwise 2 */
 #define MAX_CQE_PER_PKT_XMIT		1
 
-#define CMP_QSIZE		CMP_QUEUE_SIZE4
+/* Keep CQ and SQ sizes same, if timestamping
+ * is enabled this equation will change.
+ */
+#define CMP_QSIZE		CMP_QUEUE_SIZE2
 #define CMP_QUEUE_LEN		(1ULL << (CMP_QSIZE + 10))
 #define CMP_QUEUE_CQE_THRESH	0
 #define CMP_QUEUE_TIMER_THRESH	220 /* 10usec */
@@ -87,7 +90,12 @@
 
 #define MAX_CQES_FOR_TX		((SND_QUEUE_LEN / MIN_SQ_DESC_PER_PKT_XMIT) * \
 				 MAX_CQE_PER_PKT_XMIT)
-#define RQ_CQ_DROP		((CMP_QUEUE_LEN - MAX_CQES_FOR_TX) / 256)
+/* Calculate number of CQEs to reserve for all SQEs.
+ * Its 1/256th level of CQ size.
+ * '+ 1' to account for pipelining
+ */
+#define RQ_CQ_DROP		((256 / (CMP_QUEUE_LEN / \
+				 (CMP_QUEUE_LEN - MAX_CQES_FOR_TX))) + 1)
 
 /* Descriptor size in bytes */
 #define SND_QUEUE_DESC_SIZE	16
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
index 633ec05dfe05..b961a89dc626 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
@@ -673,7 +673,10 @@ static void bgx_lmac_disable(struct bgx *bgx, u8 lmacid)
 	bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cmrx_cfg);
 	bgx_flush_dmac_addrs(bgx, lmacid);
 
-	if (lmac->phydev)
+	if ((bgx->lmac_type != BGX_MODE_XFI) &&
+	    (bgx->lmac_type != BGX_MODE_XLAUI) &&
+	    (bgx->lmac_type != BGX_MODE_40G_KR) &&
+	    (bgx->lmac_type != BGX_MODE_10G_KR) && lmac->phydev)
 		phy_disconnect(lmac->phydev);
 
 	lmac->phydev = NULL;
diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index 1eee73cccdf5..99d33e2d35e6 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -562,6 +562,7 @@ struct fec_enet_private {
 };
 
 void fec_ptp_init(struct platform_device *pdev);
+void fec_ptp_stop(struct platform_device *pdev);
 void fec_ptp_start_cyclecounter(struct net_device *ndev);
 int fec_ptp_set(struct net_device *ndev, struct ifreq *ifr);
 int fec_ptp_get(struct net_device *ndev, struct ifreq *ifr);
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 1f89c59b4353..32e3807c650e 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -24,6 +24,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
+#include <linux/pm_runtime.h>
 #include <linux/ptrace.h>
 #include <linux/errno.h>
 #include <linux/ioport.h>
@@ -77,6 +78,7 @@ static void fec_enet_itr_coal_init(struct net_device *ndev);
 #define FEC_ENET_RAEM_V	0x8
 #define FEC_ENET_RAFL_V	0x8
 #define FEC_ENET_OPD_V	0xFFF0
+#define FEC_MDIO_PM_TIMEOUT  100 /* ms */
 
 static struct platform_device_id fec_devtype[] = {
 	{
@@ -1767,7 +1769,13 @@ static void fec_enet_adjust_link(struct net_device *ndev)
 static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
 {
 	struct fec_enet_private *fep = bus->priv;
+	struct device *dev = &fep->pdev->dev;
 	unsigned long time_left;
+	int ret = 0;
+
+	ret = pm_runtime_get_sync(dev);
+	if (IS_ERR_VALUE(ret))
+		return ret;
 
 	fep->mii_timeout = 0;
 	init_completion(&fep->mdio_done);
@@ -1783,18 +1791,30 @@ static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
 	if (time_left == 0) {
 		fep->mii_timeout = 1;
 		netdev_err(fep->netdev, "MDIO read timeout\n");
-		return -ETIMEDOUT;
+		ret = -ETIMEDOUT;
+		goto out;
 	}
 
-	/* return value */
-	return FEC_MMFR_DATA(readl(fep->hwp + FEC_MII_DATA));
+	ret = FEC_MMFR_DATA(readl(fep->hwp + FEC_MII_DATA));
+
+out:
+	pm_runtime_mark_last_busy(dev);
+	pm_runtime_put_autosuspend(dev);
+
+	return ret;
 }
 
 static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
 			   u16 value)
 {
 	struct fec_enet_private *fep = bus->priv;
+	struct device *dev = &fep->pdev->dev;
 	unsigned long time_left;
+	int ret = 0;
+
+	ret = pm_runtime_get_sync(dev);
+	if (IS_ERR_VALUE(ret))
+		return ret;
 
 	fep->mii_timeout = 0;
 	init_completion(&fep->mdio_done);
@@ -1811,10 +1831,13 @@ static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
 	if (time_left == 0) {
 		fep->mii_timeout = 1;
 		netdev_err(fep->netdev, "MDIO write timeout\n");
-		return -ETIMEDOUT;
+		ret  = -ETIMEDOUT;
 	}
 
-	return 0;
+	pm_runtime_mark_last_busy(dev);
+	pm_runtime_put_autosuspend(dev);
+
+	return ret;
 }
 
 static int fec_enet_clk_enable(struct net_device *ndev, bool enable)
@@ -1826,9 +1849,6 @@ static int fec_enet_clk_enable(struct net_device *ndev, bool enable)
 		ret = clk_prepare_enable(fep->clk_ahb);
 		if (ret)
 			return ret;
-		ret = clk_prepare_enable(fep->clk_ipg);
-		if (ret)
-			goto failed_clk_ipg;
 		if (fep->clk_enet_out) {
 			ret = clk_prepare_enable(fep->clk_enet_out);
 			if (ret)
@@ -1852,7 +1872,6 @@ static int fec_enet_clk_enable(struct net_device *ndev, bool enable)
 		}
 	} else {
 		clk_disable_unprepare(fep->clk_ahb);
-		clk_disable_unprepare(fep->clk_ipg);
 		if (fep->clk_enet_out)
 			clk_disable_unprepare(fep->clk_enet_out);
 		if (fep->clk_ptp) {
@@ -1874,8 +1893,6 @@ failed_clk_ptp:
 	if (fep->clk_enet_out)
 		clk_disable_unprepare(fep->clk_enet_out);
 failed_clk_enet_out:
-		clk_disable_unprepare(fep->clk_ipg);
-failed_clk_ipg:
 		clk_disable_unprepare(fep->clk_ahb);
 
 	return ret;
@@ -2847,10 +2864,14 @@ fec_enet_open(struct net_device *ndev)
 	struct fec_enet_private *fep = netdev_priv(ndev);
 	int ret;
 
+	ret = pm_runtime_get_sync(&fep->pdev->dev);
+	if (IS_ERR_VALUE(ret))
+		return ret;
+
 	pinctrl_pm_select_default_state(&fep->pdev->dev);
 	ret = fec_enet_clk_enable(ndev, true);
 	if (ret)
-		return ret;
+		goto clk_enable;
 
 	/* I should reset the ring buffers here, but I don't yet know
 	 * a simple way to do that.
@@ -2881,6 +2902,9 @@ err_enet_mii_probe:
 	fec_enet_free_buffers(ndev);
 err_enet_alloc:
 	fec_enet_clk_enable(ndev, false);
+clk_enable:
+	pm_runtime_mark_last_busy(&fep->pdev->dev);
+	pm_runtime_put_autosuspend(&fep->pdev->dev);
 	pinctrl_pm_select_sleep_state(&fep->pdev->dev);
 	return ret;
 }
@@ -2903,6 +2927,9 @@ fec_enet_close(struct net_device *ndev)
 
 	fec_enet_clk_enable(ndev, false);
 	pinctrl_pm_select_sleep_state(&fep->pdev->dev);
+	pm_runtime_mark_last_busy(&fep->pdev->dev);
+	pm_runtime_put_autosuspend(&fep->pdev->dev);
+
 	fec_enet_free_buffers(ndev);
 
 	return 0;
@@ -3115,8 +3142,8 @@ static int fec_enet_init(struct net_device *ndev)
 			fep->bufdesc_size;
 
 	/* Allocate memory for buffer descriptors. */
-	cbd_base = dma_alloc_coherent(NULL, bd_size, &bd_dma,
-				      GFP_KERNEL);
+	cbd_base = dmam_alloc_coherent(&fep->pdev->dev, bd_size, &bd_dma,
+				       GFP_KERNEL);
 	if (!cbd_base) {
 		return -ENOMEM;
 	}
@@ -3388,6 +3415,10 @@ fec_probe(struct platform_device *pdev)
 	if (ret)
 		goto failed_clk;
 
+	ret = clk_prepare_enable(fep->clk_ipg);
+	if (ret)
+		goto failed_clk_ipg;
+
 	fep->reg_phy = devm_regulator_get(&pdev->dev, "phy");
 	if (!IS_ERR(fep->reg_phy)) {
 		ret = regulator_enable(fep->reg_phy);
@@ -3400,6 +3431,11 @@ fec_probe(struct platform_device *pdev)
 		fep->reg_phy = NULL;
 	}
 
+	pm_runtime_set_autosuspend_delay(&pdev->dev, FEC_MDIO_PM_TIMEOUT);
+	pm_runtime_use_autosuspend(&pdev->dev);
+	pm_runtime_set_active(&pdev->dev);
+	pm_runtime_enable(&pdev->dev);
+
 	fec_reset_phy(pdev);
 
 	if (fep->bufdesc_ex)
@@ -3447,6 +3483,10 @@ fec_probe(struct platform_device *pdev)
 
 	fep->rx_copybreak = COPYBREAK_DEFAULT;
 	INIT_WORK(&fep->tx_timeout_work, fec_enet_timeout_work);
+
+	pm_runtime_mark_last_busy(&pdev->dev);
+	pm_runtime_put_autosuspend(&pdev->dev);
+
 	return 0;
 
 failed_register:
@@ -3454,9 +3494,12 @@ failed_register:
 failed_mii_init:
 failed_irq:
 failed_init:
+	fec_ptp_stop(pdev);
 	if (fep->reg_phy)
 		regulator_disable(fep->reg_phy);
 failed_regulator:
+	clk_disable_unprepare(fep->clk_ipg);
+failed_clk_ipg:
 	fec_enet_clk_enable(ndev, false);
 failed_clk:
 failed_phy:
@@ -3473,14 +3516,12 @@ fec_drv_remove(struct platform_device *pdev)
 	struct net_device *ndev = platform_get_drvdata(pdev);
 	struct fec_enet_private *fep = netdev_priv(ndev);
 
-	cancel_delayed_work_sync(&fep->time_keep);
 	cancel_work_sync(&fep->tx_timeout_work);
+	fec_ptp_stop(pdev);
 	unregister_netdev(ndev);
 	fec_enet_mii_remove(fep);
 	if (fep->reg_phy)
 		regulator_disable(fep->reg_phy);
-	if (fep->ptp_clock)
-		ptp_clock_unregister(fep->ptp_clock);
 	of_node_put(fep->phy_node);
 	free_netdev(ndev);
 
@@ -3568,7 +3609,28 @@ failed_clk:
 	return ret;
 }
 
-static SIMPLE_DEV_PM_OPS(fec_pm_ops, fec_suspend, fec_resume);
+static int __maybe_unused fec_runtime_suspend(struct device *dev)
+{
+	struct net_device *ndev = dev_get_drvdata(dev);
+	struct fec_enet_private *fep = netdev_priv(ndev);
+
+	clk_disable_unprepare(fep->clk_ipg);
+
+	return 0;
+}
+
+static int __maybe_unused fec_runtime_resume(struct device *dev)
+{
+	struct net_device *ndev = dev_get_drvdata(dev);
+	struct fec_enet_private *fep = netdev_priv(ndev);
+
+	return clk_prepare_enable(fep->clk_ipg);
+}
+
+static const struct dev_pm_ops fec_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(fec_suspend, fec_resume)
+	SET_RUNTIME_PM_OPS(fec_runtime_suspend, fec_runtime_resume, NULL)
+};
 
 static struct platform_driver fec_driver = {
 	.driver	= {
diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c
index a15663ad7f5e..f457a23d0bfb 100644
--- a/drivers/net/ethernet/freescale/fec_ptp.c
+++ b/drivers/net/ethernet/freescale/fec_ptp.c
@@ -604,6 +604,16 @@ void fec_ptp_init(struct platform_device *pdev)
 	schedule_delayed_work(&fep->time_keep, HZ);
 }
 
+void fec_ptp_stop(struct platform_device *pdev)
+{
+	struct net_device *ndev = platform_get_drvdata(pdev);
+	struct fec_enet_private *fep = netdev_priv(ndev);
+
+	cancel_delayed_work_sync(&fep->time_keep);
+	if (fep->ptp_clock)
+		ptp_clock_unregister(fep->ptp_clock);
+}
+
 /**
  * fec_ptp_check_pps_event
  * @fep: the fec_enet_private structure handle
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index ff875028fdff..2b7610f341b0 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -565,22 +565,6 @@ static void gfar_ints_enable(struct gfar_private *priv)
 	}
 }
 
-static void lock_tx_qs(struct gfar_private *priv)
-{
-	int i;
-
-	for (i = 0; i < priv->num_tx_queues; i++)
-		spin_lock(&priv->tx_queue[i]->txlock);
-}
-
-static void unlock_tx_qs(struct gfar_private *priv)
-{
-	int i;
-
-	for (i = 0; i < priv->num_tx_queues; i++)
-		spin_unlock(&priv->tx_queue[i]->txlock);
-}
-
 static int gfar_alloc_tx_queues(struct gfar_private *priv)
 {
 	int i;
@@ -1376,7 +1360,6 @@ static int gfar_probe(struct platform_device *ofdev)
 	priv->dev = &ofdev->dev;
 	SET_NETDEV_DEV(dev, &ofdev->dev);
 
-	spin_lock_init(&priv->bflock);
 	INIT_WORK(&priv->reset_task, gfar_reset_task);
 
 	platform_set_drvdata(ofdev, priv);
@@ -1470,9 +1453,8 @@ static int gfar_probe(struct platform_device *ofdev)
 		goto register_fail;
 	}
 
-	device_init_wakeup(&dev->dev,
-			   priv->device_flags &
-			   FSL_GIANFAR_DEV_HAS_MAGIC_PACKET);
+	device_set_wakeup_capable(&dev->dev, priv->device_flags &
+				  FSL_GIANFAR_DEV_HAS_MAGIC_PACKET);
 
 	/* fill out IRQ number and name fields */
 	for (i = 0; i < priv->num_grps; i++) {
@@ -1540,48 +1522,37 @@ static int gfar_suspend(struct device *dev)
 	struct gfar_private *priv = dev_get_drvdata(dev);
 	struct net_device *ndev = priv->ndev;
 	struct gfar __iomem *regs = priv->gfargrp[0].regs;
-	unsigned long flags;
 	u32 tempval;
-
 	int magic_packet = priv->wol_en &&
 			   (priv->device_flags &
 			    FSL_GIANFAR_DEV_HAS_MAGIC_PACKET);
 
+	if (!netif_running(ndev))
+		return 0;
+
+	disable_napi(priv);
+	netif_tx_lock(ndev);
 	netif_device_detach(ndev);
+	netif_tx_unlock(ndev);
 
-	if (netif_running(ndev)) {
+	gfar_halt(priv);
 
-		local_irq_save(flags);
-		lock_tx_qs(priv);
+	if (magic_packet) {
+		/* Enable interrupt on Magic Packet */
+		gfar_write(&regs->imask, IMASK_MAG);
 
-		gfar_halt_nodisable(priv);
+		/* Enable Magic Packet mode */
+		tempval = gfar_read(&regs->maccfg2);
+		tempval |= MACCFG2_MPEN;
+		gfar_write(&regs->maccfg2, tempval);
 
-		/* Disable Tx, and Rx if wake-on-LAN is disabled. */
+		/* re-enable the Rx block */
 		tempval = gfar_read(&regs->maccfg1);
-
-		tempval &= ~MACCFG1_TX_EN;
-
-		if (!magic_packet)
-			tempval &= ~MACCFG1_RX_EN;
-
+		tempval |= MACCFG1_RX_EN;
 		gfar_write(&regs->maccfg1, tempval);
 
-		unlock_tx_qs(priv);
-		local_irq_restore(flags);
-
-		disable_napi(priv);
-
-		if (magic_packet) {
-			/* Enable interrupt on Magic Packet */
-			gfar_write(&regs->imask, IMASK_MAG);
-
-			/* Enable Magic Packet mode */
-			tempval = gfar_read(&regs->maccfg2);
-			tempval |= MACCFG2_MPEN;
-			gfar_write(&regs->maccfg2, tempval);
-		} else {
-			phy_stop(priv->phydev);
-		}
+	} else {
+		phy_stop(priv->phydev);
 	}
 
 	return 0;
@@ -1592,37 +1563,26 @@ static int gfar_resume(struct device *dev)
 	struct gfar_private *priv = dev_get_drvdata(dev);
 	struct net_device *ndev = priv->ndev;
 	struct gfar __iomem *regs = priv->gfargrp[0].regs;
-	unsigned long flags;
 	u32 tempval;
 	int magic_packet = priv->wol_en &&
 			   (priv->device_flags &
 			    FSL_GIANFAR_DEV_HAS_MAGIC_PACKET);
 
-	if (!netif_running(ndev)) {
-		netif_device_attach(ndev);
+	if (!netif_running(ndev))
 		return 0;
-	}
 
-	if (!magic_packet && priv->phydev)
+	if (magic_packet) {
+		/* Disable Magic Packet mode */
+		tempval = gfar_read(&regs->maccfg2);
+		tempval &= ~MACCFG2_MPEN;
+		gfar_write(&regs->maccfg2, tempval);
+	} else {
 		phy_start(priv->phydev);
-
-	/* Disable Magic Packet mode, in case something
-	 * else woke us up.
-	 */
-	local_irq_save(flags);
-	lock_tx_qs(priv);
-
-	tempval = gfar_read(&regs->maccfg2);
-	tempval &= ~MACCFG2_MPEN;
-	gfar_write(&regs->maccfg2, tempval);
+	}
 
 	gfar_start(priv);
 
-	unlock_tx_qs(priv);
-	local_irq_restore(flags);
-
 	netif_device_attach(ndev);
-
 	enable_napi(priv);
 
 	return 0;
@@ -2045,7 +2005,8 @@ static int register_grp_irqs(struct gfar_priv_grp *grp)
 		/* Install our interrupt handlers for Error,
 		 * Transmit, and Receive
 		 */
-		err = request_irq(gfar_irq(grp, ER)->irq, gfar_error, 0,
+		err = request_irq(gfar_irq(grp, ER)->irq, gfar_error,
+				  IRQF_NO_SUSPEND,
 				  gfar_irq(grp, ER)->name, grp);
 		if (err < 0) {
 			netif_err(priv, intr, dev, "Can't get IRQ %d\n",
@@ -2068,7 +2029,8 @@ static int register_grp_irqs(struct gfar_priv_grp *grp)
 			goto rx_irq_fail;
 		}
 	} else {
-		err = request_irq(gfar_irq(grp, TX)->irq, gfar_interrupt, 0,
+		err = request_irq(gfar_irq(grp, TX)->irq, gfar_interrupt,
+				  IRQF_NO_SUSPEND,
 				  gfar_irq(grp, TX)->name, grp);
 		if (err < 0) {
 			netif_err(priv, intr, dev, "Can't get IRQ %d\n",
@@ -2169,8 +2131,6 @@ static int gfar_enet_open(struct net_device *dev)
 	if (err)
 		return err;
 
-	device_set_wakeup_enable(&dev->dev, priv->wol_en);
-
 	return err;
 }
 
diff --git a/drivers/net/ethernet/freescale/gianfar.h b/drivers/net/ethernet/freescale/gianfar.h
index daa1d37de642..5545e4103368 100644
--- a/drivers/net/ethernet/freescale/gianfar.h
+++ b/drivers/net/ethernet/freescale/gianfar.h
@@ -1145,9 +1145,6 @@ struct gfar_private {
 	int oldduplex;
 	int oldlink;
 
-	/* Bitfield update lock */
-	spinlock_t bflock;
-
 	uint32_t msg_enable;
 
 	struct work_struct reset_task;
diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c
index fda12fb32ec7..3c0a8f825b63 100644
--- a/drivers/net/ethernet/freescale/gianfar_ethtool.c
+++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c
@@ -653,7 +653,6 @@ static void gfar_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 static int gfar_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 {
 	struct gfar_private *priv = netdev_priv(dev);
-	unsigned long flags;
 
 	if (!(priv->device_flags & FSL_GIANFAR_DEV_HAS_MAGIC_PACKET) &&
 	    wol->wolopts != 0)
@@ -664,9 +663,7 @@ static int gfar_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 
 	device_set_wakeup_enable(&dev->dev, wol->wolopts & WAKE_MAGIC);
 
-	spin_lock_irqsave(&priv->bflock, flags);
-	priv->wol_en =  !!device_may_wakeup(&dev->dev);
-	spin_unlock_irqrestore(&priv->bflock, flags);
+	priv->wol_en = !!device_may_wakeup(&dev->dev);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index 82040137d7d9..0a3202047569 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -686,6 +686,7 @@ static int mlx4_cmd_wait(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
 {
 	struct mlx4_cmd *cmd = &mlx4_priv(dev)->cmd;
 	struct mlx4_cmd_context *context;
+	long ret_wait;
 	int err = 0;
 
 	down(&cmd->event_sem);
@@ -711,8 +712,20 @@ static int mlx4_cmd_wait(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
 	if (err)
 		goto out_reset;
 
-	if (!wait_for_completion_timeout(&context->done,
-					 msecs_to_jiffies(timeout))) {
+	if (op == MLX4_CMD_SENSE_PORT) {
+		ret_wait =
+			wait_for_completion_interruptible_timeout(&context->done,
+								  msecs_to_jiffies(timeout));
+		if (ret_wait < 0) {
+			context->fw_status = 0;
+			context->out_param = 0;
+			context->result = 0;
+		}
+	} else {
+		ret_wait = (long)wait_for_completion_timeout(&context->done,
+							     msecs_to_jiffies(timeout));
+	}
+	if (!ret_wait) {
 		mlx4_warn(dev, "command 0x%x timed out (go bit not cleared)\n",
 			  op);
 		if (op == MLX4_CMD_NOP) {
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 7a4f20bb7fcb..9c145dddd717 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -246,7 +246,6 @@ static int mlx4_en_prepare_rx_desc(struct mlx4_en_priv *priv,
 
 static inline bool mlx4_en_is_ring_empty(struct mlx4_en_rx_ring *ring)
 {
-	BUG_ON((u32)(ring->prod - ring->cons) > ring->actual_size);
 	return ring->prod == ring->cons;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index aae13adfb492..8e81e53c370e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -601,7 +601,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 							continue;
 						mlx4_dbg(dev, "%s: Sending MLX4_PORT_CHANGE_SUBTYPE_DOWN to slave: %d, port:%d\n",
 							 __func__, i, port);
-						s_info = &priv->mfunc.master.vf_oper[slave].vport[port].state;
+						s_info = &priv->mfunc.master.vf_oper[i].vport[port].state;
 						if (IFLA_VF_LINK_STATE_AUTO == s_info->link_state) {
 							eqe->event.port_change.port =
 								cpu_to_be32(
@@ -640,7 +640,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 							continue;
 						if (i == mlx4_master_func_num(dev))
 							continue;
-						s_info = &priv->mfunc.master.vf_oper[slave].vport[port].state;
+						s_info = &priv->mfunc.master.vf_oper[i].vport[port].state;
 						if (IFLA_VF_LINK_STATE_AUTO == s_info->link_state) {
 							eqe->event.port_change.port =
 								cpu_to_be32(
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 12fbfcb44d8a..29c2a017a450 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -2273,6 +2273,11 @@ static int mlx4_allocate_default_counters(struct mlx4_dev *dev)
 		} else if (err == -ENOENT) {
 			err = 0;
 			continue;
+		} else if (mlx4_is_slave(dev) && err == -EINVAL) {
+			priv->def_counter[port] = MLX4_SINK_COUNTER_INDEX(dev);
+			mlx4_warn(dev, "can't allocate counter from old PF driver, using index %d\n",
+				  MLX4_SINK_COUNTER_INDEX(dev));
+			err = 0;
 		} else {
 			mlx4_err(dev, "%s: failed to allocate default counter port %d err %d\n",
 				 __func__, port + 1, err);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
index 33669c29b341..753ea8bad953 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
@@ -1415,7 +1415,7 @@ static int qlcnic_83xx_copy_fw_file(struct qlcnic_adapter *adapter)
 	if (fw->size & 0xF) {
 		addr = dest + size;
 		for (i = 0; i < (fw->size & 0xF); i++)
-			data[i] = temp[size + i];
+			data[i] = ((u8 *)temp)[size + i];
 		for (; i < 16; i++)
 			data[i] = 0;
 		ret = qlcnic_ms_mem_write128(adapter, addr,
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index f3918c7e7eeb..bcdc8955c719 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -413,3 +413,7 @@ static int stmmac_pltfr_resume(struct device *dev)
 SIMPLE_DEV_PM_OPS(stmmac_pltfr_pm_ops, stmmac_pltfr_suspend,
 				       stmmac_pltfr_resume);
 EXPORT_SYMBOL_GPL(stmmac_pltfr_pm_ops);
+
+MODULE_DESCRIPTION("STMMAC 10/100/1000 Ethernet platform support");
+MODULE_AUTHOR("Giuseppe Cavallaro <peppe.cavallaro@st.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c
index 0c5842aeb807..ab6051a43134 100644
--- a/drivers/net/ethernet/sun/niu.c
+++ b/drivers/net/ethernet/sun/niu.c
@@ -6658,10 +6658,8 @@ static netdev_tx_t niu_start_xmit(struct sk_buff *skb,
 		struct sk_buff *skb_new;
 
 		skb_new = skb_realloc_headroom(skb, len);
-		if (!skb_new) {
-			rp->tx_errors++;
+		if (!skb_new)
 			goto out_drop;
-		}
 		kfree_skb(skb);
 		skb = skb_new;
 	} else
diff --git a/drivers/net/ethernet/ti/netcp.h b/drivers/net/ethernet/ti/netcp.h
index bbacf5cccec2..a8a730641bbb 100644
--- a/drivers/net/ethernet/ti/netcp.h
+++ b/drivers/net/ethernet/ti/netcp.h
@@ -223,6 +223,7 @@ void *netcp_device_find_module(struct netcp_device *netcp_device,
 
 /* SGMII functions */
 int netcp_sgmii_reset(void __iomem *sgmii_ofs, int port);
+bool netcp_sgmii_rtreset(void __iomem *sgmii_ofs, int port, bool set);
 int netcp_sgmii_get_port_link(void __iomem *sgmii_ofs, int port);
 int netcp_sgmii_config(void __iomem *sgmii_ofs, int port, u32 interface);
 
diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c
index ec8ed30196f3..9749dfd78c43 100644
--- a/drivers/net/ethernet/ti/netcp_core.c
+++ b/drivers/net/ethernet/ti/netcp_core.c
@@ -2112,6 +2112,7 @@ probe_quit:
 static int netcp_remove(struct platform_device *pdev)
 {
 	struct netcp_device *netcp_device = platform_get_drvdata(pdev);
+	struct netcp_intf *netcp_intf, *netcp_tmp;
 	struct netcp_inst_modpriv *inst_modpriv, *tmp;
 	struct netcp_module *module;
 
@@ -2123,10 +2124,17 @@ static int netcp_remove(struct platform_device *pdev)
 		list_del(&inst_modpriv->inst_list);
 		kfree(inst_modpriv);
 	}
-	WARN(!list_empty(&netcp_device->interface_head), "%s interface list not empty!\n",
-	     pdev->name);
 
-	devm_kfree(&pdev->dev, netcp_device);
+	/* now that all modules are removed, clean up the interfaces */
+	list_for_each_entry_safe(netcp_intf, netcp_tmp,
+				 &netcp_device->interface_head,
+				 interface_list) {
+		netcp_delete_interface(netcp_device, netcp_intf->ndev);
+	}
+
+	WARN(!list_empty(&netcp_device->interface_head),
+	     "%s interface list not empty!\n", pdev->name);
+
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 	platform_set_drvdata(pdev, NULL);
diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c
index 9b7e0a34c98b..1974a8ae764a 100644
--- a/drivers/net/ethernet/ti/netcp_ethss.c
+++ b/drivers/net/ethernet/ti/netcp_ethss.c
@@ -1901,11 +1901,28 @@ static void gbe_port_config(struct gbe_priv *gbe_dev, struct gbe_slave *slave,
 	writel(slave->mac_control, GBE_REG_ADDR(slave, emac_regs, mac_control));
 }
 
+static void gbe_sgmii_rtreset(struct gbe_priv *priv,
+			      struct gbe_slave *slave, bool set)
+{
+	void __iomem *sgmii_port_regs;
+
+	if (SLAVE_LINK_IS_XGMII(slave))
+		return;
+
+	if ((priv->ss_version == GBE_SS_VERSION_14) && (slave->slave_num >= 2))
+		sgmii_port_regs = priv->sgmii_port34_regs;
+	else
+		sgmii_port_regs = priv->sgmii_port_regs;
+
+	netcp_sgmii_rtreset(sgmii_port_regs, slave->slave_num, set);
+}
+
 static void gbe_slave_stop(struct gbe_intf *intf)
 {
 	struct gbe_priv *gbe_dev = intf->gbe_dev;
 	struct gbe_slave *slave = intf->slave;
 
+	gbe_sgmii_rtreset(gbe_dev, slave, true);
 	gbe_port_reset(slave);
 	/* Disable forwarding */
 	cpsw_ale_control_set(gbe_dev->ale, slave->port_num,
@@ -1947,6 +1964,7 @@ static int gbe_slave_open(struct gbe_intf *gbe_intf)
 
 	gbe_sgmii_config(priv, slave);
 	gbe_port_reset(slave);
+	gbe_sgmii_rtreset(priv, slave, false);
 	gbe_port_config(priv, slave, priv->rx_packet_max);
 	gbe_set_slave_mac(slave, gbe_intf);
 	/* enable forwarding */
@@ -2490,10 +2508,9 @@ static void free_secondary_ports(struct gbe_priv *gbe_dev)
 {
 	struct gbe_slave *slave;
 
-	for (;;) {
+	while (!list_empty(&gbe_dev->secondary_slaves)) {
 		slave = first_sec_slave(gbe_dev);
-		if (!slave)
-			break;
+
 		if (slave->phy)
 			phy_disconnect(slave->phy);
 		list_del(&slave->slave_list);
@@ -2839,14 +2856,13 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev,
 				      &gbe_dev->dma_chan_name);
 	if (ret < 0) {
 		dev_err(dev, "missing \"tx-channel\" parameter\n");
-		ret = -ENODEV;
-		goto quit;
+		return -EINVAL;
 	}
 
 	if (!strcmp(node->name, "gbe")) {
 		ret = get_gbe_resource_version(gbe_dev, node);
 		if (ret)
-			goto quit;
+			return ret;
 
 		dev_dbg(dev, "ss_version: 0x%08x\n", gbe_dev->ss_version);
 
@@ -2857,22 +2873,20 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev,
 		else
 			ret = -ENODEV;
 
-		if (ret)
-			goto quit;
 	} else if (!strcmp(node->name, "xgbe")) {
 		ret = set_xgbe_ethss10_priv(gbe_dev, node);
 		if (ret)
-			goto quit;
+			return ret;
 		ret = netcp_xgbe_serdes_init(gbe_dev->xgbe_serdes_regs,
 					     gbe_dev->ss_regs);
-		if (ret)
-			goto quit;
 	} else {
 		dev_err(dev, "unknown GBE node(%s)\n", node->name);
 		ret = -ENODEV;
-		goto quit;
 	}
 
+	if (ret)
+		return ret;
+
 	interfaces = of_get_child_by_name(node, "interfaces");
 	if (!interfaces)
 		dev_err(dev, "could not find interfaces\n");
@@ -2880,11 +2894,11 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev,
 	ret = netcp_txpipe_init(&gbe_dev->tx_pipe, netcp_device,
 				gbe_dev->dma_chan_name, gbe_dev->tx_queue_id);
 	if (ret)
-		goto quit;
+		return ret;
 
 	ret = netcp_txpipe_open(&gbe_dev->tx_pipe);
 	if (ret)
-		goto quit;
+		return ret;
 
 	/* Create network interfaces */
 	INIT_LIST_HEAD(&gbe_dev->gbe_intf_head);
@@ -2899,6 +2913,7 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev,
 		if (gbe_dev->num_slaves >= gbe_dev->max_num_slaves)
 			break;
 	}
+	of_node_put(interfaces);
 
 	if (!gbe_dev->num_slaves)
 		dev_warn(dev, "No network interface configured\n");
@@ -2911,9 +2926,10 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev,
 	of_node_put(secondary_ports);
 
 	if (!gbe_dev->num_slaves) {
-		dev_err(dev, "No network interface or secondary ports configured\n");
+		dev_err(dev,
+			"No network interface or secondary ports configured\n");
 		ret = -ENODEV;
-		goto quit;
+		goto free_sec_ports;
 	}
 
 	memset(&ale_params, 0, sizeof(ale_params));
@@ -2927,7 +2943,7 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev,
 	if (!gbe_dev->ale) {
 		dev_err(gbe_dev->dev, "error initializing ale engine\n");
 		ret = -ENODEV;
-		goto quit;
+		goto free_sec_ports;
 	} else {
 		dev_dbg(gbe_dev->dev, "Created a gbe ale engine\n");
 	}
@@ -2943,14 +2959,8 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev,
 	*inst_priv = gbe_dev;
 	return 0;
 
-quit:
-	if (gbe_dev->hw_stats)
-		devm_kfree(dev, gbe_dev->hw_stats);
-	cpsw_ale_destroy(gbe_dev->ale);
-	if (gbe_dev->ss_regs)
-		devm_iounmap(dev, gbe_dev->ss_regs);
-	of_node_put(interfaces);
-	devm_kfree(dev, gbe_dev);
+free_sec_ports:
+	free_secondary_ports(gbe_dev);
 	return ret;
 }
 
@@ -3023,12 +3033,9 @@ static int gbe_remove(struct netcp_device *netcp_device, void *inst_priv)
 	free_secondary_ports(gbe_dev);
 
 	if (!list_empty(&gbe_dev->gbe_intf_head))
-		dev_alert(gbe_dev->dev, "unreleased ethss interfaces present\n");
+		dev_alert(gbe_dev->dev,
+			  "unreleased ethss interfaces present\n");
 
-	devm_kfree(gbe_dev->dev, gbe_dev->hw_stats);
-	devm_iounmap(gbe_dev->dev, gbe_dev->ss_regs);
-	memset(gbe_dev, 0x00, sizeof(*gbe_dev));
-	devm_kfree(gbe_dev->dev, gbe_dev);
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/ti/netcp_sgmii.c b/drivers/net/ethernet/ti/netcp_sgmii.c
index dbeb14266e2f..5d8419f658d0 100644
--- a/drivers/net/ethernet/ti/netcp_sgmii.c
+++ b/drivers/net/ethernet/ti/netcp_sgmii.c
@@ -18,6 +18,9 @@
 
 #include "netcp.h"
 
+#define SGMII_SRESET_RESET		BIT(0)
+#define SGMII_SRESET_RTRESET		BIT(1)
+
 #define SGMII_REG_STATUS_LOCK		BIT(4)
 #define	SGMII_REG_STATUS_LINK		BIT(0)
 #define SGMII_REG_STATUS_AUTONEG	BIT(2)
@@ -51,12 +54,35 @@ static void sgmii_write_reg_bit(void __iomem *base, int reg, u32 val)
 int netcp_sgmii_reset(void __iomem *sgmii_ofs, int port)
 {
 	/* Soft reset */
-	sgmii_write_reg_bit(sgmii_ofs, SGMII_SRESET_REG(port), 0x1);
-	while (sgmii_read_reg(sgmii_ofs, SGMII_SRESET_REG(port)) != 0x0)
+	sgmii_write_reg_bit(sgmii_ofs, SGMII_SRESET_REG(port),
+			    SGMII_SRESET_RESET);
+
+	while ((sgmii_read_reg(sgmii_ofs, SGMII_SRESET_REG(port)) &
+		SGMII_SRESET_RESET) != 0x0)
 		;
+
 	return 0;
 }
 
+/* port is 0 based */
+bool netcp_sgmii_rtreset(void __iomem *sgmii_ofs, int port, bool set)
+{
+	u32 reg;
+	bool oldval;
+
+	/* Initiate a soft reset */
+	reg = sgmii_read_reg(sgmii_ofs, SGMII_SRESET_REG(port));
+	oldval = (reg & SGMII_SRESET_RTRESET) != 0x0;
+	if (set)
+		reg |= SGMII_SRESET_RTRESET;
+	else
+		reg &= ~SGMII_SRESET_RTRESET;
+	sgmii_write_reg(sgmii_ofs, SGMII_SRESET_REG(port), reg);
+	wmb();
+
+	return oldval;
+}
+
 int netcp_sgmii_get_port_link(void __iomem *sgmii_ofs, int port)
 {
 	u32 status = 0, link = 0;
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 3b933bb5a8d5..edd77342773a 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -719,6 +719,7 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
 	struct virtio_net_hdr vnet_hdr = { 0 };
 	int vnet_hdr_len = 0;
 	int copylen = 0;
+	int depth;
 	bool zerocopy = false;
 	size_t linear;
 	ssize_t n;
@@ -804,6 +805,12 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
 
 	skb_probe_transport_header(skb, ETH_HLEN);
 
+	/* Move network header to the right position for VLAN tagged packets */
+	if ((skb->protocol == htons(ETH_P_8021Q) ||
+	     skb->protocol == htons(ETH_P_8021AD)) &&
+	    __vlan_get_protocol(skb, skb->protocol, &depth) != 0)
+		skb_set_network_header(skb, depth);
+
 	rcu_read_lock();
 	vlan = rcu_dereference(q->vlan);
 	/* copy skb_ubuf_info for callback when skb has no error */
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 7f6419ebb5e1..ad8cbc6c9ee7 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -27,7 +27,7 @@
 #include <linux/usb/cdc.h>
 
 /* Version Information */
-#define DRIVER_VERSION "v1.08.0 (2015/01/13)"
+#define DRIVER_VERSION "v1.08.1 (2015/07/28)"
 #define DRIVER_AUTHOR "Realtek linux nic maintainers <nic_swsd@realtek.com>"
 #define DRIVER_DESC "Realtek RTL8152/RTL8153 Based USB Ethernet Adapters"
 #define MODULENAME "r8152"
@@ -1902,11 +1902,10 @@ static void rtl_drop_queued_tx(struct r8152 *tp)
 static void rtl8152_tx_timeout(struct net_device *netdev)
 {
 	struct r8152 *tp = netdev_priv(netdev);
-	int i;
 
 	netif_warn(tp, tx_err, netdev, "Tx timeout\n");
-	for (i = 0; i < RTL8152_MAX_TX; i++)
-		usb_unlink_urb(tp->tx_info[i].urb);
+
+	usb_queue_reset_device(tp->intf);
 }
 
 static void rtl8152_set_rx_mode(struct net_device *netdev)
@@ -2075,7 +2074,6 @@ static int rtl_start_rx(struct r8152 *tp)
 {
 	int i, ret = 0;
 
-	napi_disable(&tp->napi);
 	INIT_LIST_HEAD(&tp->rx_done);
 	for (i = 0; i < RTL8152_MAX_RX; i++) {
 		INIT_LIST_HEAD(&tp->rx_info[i].list);
@@ -2083,7 +2081,6 @@ static int rtl_start_rx(struct r8152 *tp)
 		if (ret)
 			break;
 	}
-	napi_enable(&tp->napi);
 
 	if (ret && ++i < RTL8152_MAX_RX) {
 		struct list_head rx_queue;
@@ -2166,6 +2163,7 @@ static int rtl8153_enable(struct r8152 *tp)
 	if (test_bit(RTL8152_UNPLUG, &tp->flags))
 		return -ENODEV;
 
+	usb_disable_lpm(tp->udev);
 	set_tx_qlen(tp);
 	rtl_set_eee_plus(tp);
 	r8153_set_rx_early_timeout(tp);
@@ -2337,11 +2335,61 @@ static void __rtl_set_wol(struct r8152 *tp, u32 wolopts)
 		device_set_wakeup_enable(&tp->udev->dev, false);
 }
 
+static void r8153_u1u2en(struct r8152 *tp, bool enable)
+{
+	u8 u1u2[8];
+
+	if (enable)
+		memset(u1u2, 0xff, sizeof(u1u2));
+	else
+		memset(u1u2, 0x00, sizeof(u1u2));
+
+	usb_ocp_write(tp, USB_TOLERANCE, BYTE_EN_SIX_BYTES, sizeof(u1u2), u1u2);
+}
+
+static void r8153_u2p3en(struct r8152 *tp, bool enable)
+{
+	u32 ocp_data;
+
+	ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_U2P3_CTRL);
+	if (enable && tp->version != RTL_VER_03 && tp->version != RTL_VER_04)
+		ocp_data |= U2P3_ENABLE;
+	else
+		ocp_data &= ~U2P3_ENABLE;
+	ocp_write_word(tp, MCU_TYPE_USB, USB_U2P3_CTRL, ocp_data);
+}
+
+static void r8153_power_cut_en(struct r8152 *tp, bool enable)
+{
+	u32 ocp_data;
+
+	ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_POWER_CUT);
+	if (enable)
+		ocp_data |= PWR_EN | PHASE2_EN;
+	else
+		ocp_data &= ~(PWR_EN | PHASE2_EN);
+	ocp_write_word(tp, MCU_TYPE_USB, USB_POWER_CUT, ocp_data);
+
+	ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_MISC_0);
+	ocp_data &= ~PCUT_STATUS;
+	ocp_write_word(tp, MCU_TYPE_USB, USB_MISC_0, ocp_data);
+}
+
+static bool rtl_can_wakeup(struct r8152 *tp)
+{
+	struct usb_device *udev = tp->udev;
+
+	return (udev->actconfig->desc.bmAttributes & USB_CONFIG_ATT_WAKEUP);
+}
+
 static void rtl_runtime_suspend_enable(struct r8152 *tp, bool enable)
 {
 	if (enable) {
 		u32 ocp_data;
 
+		r8153_u1u2en(tp, false);
+		r8153_u2p3en(tp, false);
+
 		__rtl_set_wol(tp, WAKE_ANY);
 
 		ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_CONFIG);
@@ -2353,6 +2401,8 @@ static void rtl_runtime_suspend_enable(struct r8152 *tp, bool enable)
 		ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_NORAML);
 	} else {
 		__rtl_set_wol(tp, tp->saved_wolopts);
+		r8153_u2p3en(tp, true);
+		r8153_u1u2en(tp, true);
 	}
 }
 
@@ -2599,46 +2649,6 @@ static void r8153_hw_phy_cfg(struct r8152 *tp)
 	set_bit(PHY_RESET, &tp->flags);
 }
 
-static void r8153_u1u2en(struct r8152 *tp, bool enable)
-{
-	u8 u1u2[8];
-
-	if (enable)
-		memset(u1u2, 0xff, sizeof(u1u2));
-	else
-		memset(u1u2, 0x00, sizeof(u1u2));
-
-	usb_ocp_write(tp, USB_TOLERANCE, BYTE_EN_SIX_BYTES, sizeof(u1u2), u1u2);
-}
-
-static void r8153_u2p3en(struct r8152 *tp, bool enable)
-{
-	u32 ocp_data;
-
-	ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_U2P3_CTRL);
-	if (enable)
-		ocp_data |= U2P3_ENABLE;
-	else
-		ocp_data &= ~U2P3_ENABLE;
-	ocp_write_word(tp, MCU_TYPE_USB, USB_U2P3_CTRL, ocp_data);
-}
-
-static void r8153_power_cut_en(struct r8152 *tp, bool enable)
-{
-	u32 ocp_data;
-
-	ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_POWER_CUT);
-	if (enable)
-		ocp_data |= PWR_EN | PHASE2_EN;
-	else
-		ocp_data &= ~(PWR_EN | PHASE2_EN);
-	ocp_write_word(tp, MCU_TYPE_USB, USB_POWER_CUT, ocp_data);
-
-	ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_MISC_0);
-	ocp_data &= ~PCUT_STATUS;
-	ocp_write_word(tp, MCU_TYPE_USB, USB_MISC_0, ocp_data);
-}
-
 static void r8153_first_init(struct r8152 *tp)
 {
 	u32 ocp_data;
@@ -2781,6 +2791,7 @@ static void rtl8153_disable(struct r8152 *tp)
 	r8153_disable_aldps(tp);
 	rtl_disable(tp);
 	r8153_enable_aldps(tp);
+	usb_enable_lpm(tp->udev);
 }
 
 static int rtl8152_set_speed(struct r8152 *tp, u8 autoneg, u16 speed, u8 duplex)
@@ -2901,9 +2912,13 @@ static void rtl8153_up(struct r8152 *tp)
 	if (test_bit(RTL8152_UNPLUG, &tp->flags))
 		return;
 
+	r8153_u1u2en(tp, false);
 	r8153_disable_aldps(tp);
 	r8153_first_init(tp);
 	r8153_enable_aldps(tp);
+	r8153_u2p3en(tp, true);
+	r8153_u1u2en(tp, true);
+	usb_enable_lpm(tp->udev);
 }
 
 static void rtl8153_down(struct r8152 *tp)
@@ -2914,6 +2929,7 @@ static void rtl8153_down(struct r8152 *tp)
 	}
 
 	r8153_u1u2en(tp, false);
+	r8153_u2p3en(tp, false);
 	r8153_power_cut_en(tp, false);
 	r8153_disable_aldps(tp);
 	r8153_enter_oob(tp);
@@ -2932,8 +2948,10 @@ static void set_carrier(struct r8152 *tp)
 		if (!netif_carrier_ok(netdev)) {
 			tp->rtl_ops.enable(tp);
 			set_bit(RTL8152_SET_RX_MODE, &tp->flags);
+			napi_disable(&tp->napi);
 			netif_carrier_on(netdev);
 			rtl_start_rx(tp);
+			napi_enable(&tp->napi);
 		}
 	} else {
 		if (netif_carrier_ok(netdev)) {
@@ -3252,6 +3270,7 @@ static void r8153_init(struct r8152 *tp)
 		msleep(20);
 	}
 
+	usb_disable_lpm(tp->udev);
 	r8153_u2p3en(tp, false);
 
 	if (tp->version == RTL_VER_04) {
@@ -3319,6 +3338,59 @@ static void r8153_init(struct r8152 *tp)
 	r8153_enable_aldps(tp);
 	r8152b_enable_fc(tp);
 	rtl_tally_reset(tp);
+	r8153_u2p3en(tp, true);
+}
+
+static int rtl8152_pre_reset(struct usb_interface *intf)
+{
+	struct r8152 *tp = usb_get_intfdata(intf);
+	struct net_device *netdev;
+
+	if (!tp)
+		return 0;
+
+	netdev = tp->netdev;
+	if (!netif_running(netdev))
+		return 0;
+
+	napi_disable(&tp->napi);
+	clear_bit(WORK_ENABLE, &tp->flags);
+	usb_kill_urb(tp->intr_urb);
+	cancel_delayed_work_sync(&tp->schedule);
+	if (netif_carrier_ok(netdev)) {
+		netif_stop_queue(netdev);
+		mutex_lock(&tp->control);
+		tp->rtl_ops.disable(tp);
+		mutex_unlock(&tp->control);
+	}
+
+	return 0;
+}
+
+static int rtl8152_post_reset(struct usb_interface *intf)
+{
+	struct r8152 *tp = usb_get_intfdata(intf);
+	struct net_device *netdev;
+
+	if (!tp)
+		return 0;
+
+	netdev = tp->netdev;
+	if (!netif_running(netdev))
+		return 0;
+
+	set_bit(WORK_ENABLE, &tp->flags);
+	if (netif_carrier_ok(netdev)) {
+		mutex_lock(&tp->control);
+		tp->rtl_ops.enable(tp);
+		rtl8152_set_rx_mode(netdev);
+		mutex_unlock(&tp->control);
+		netif_wake_queue(netdev);
+	}
+
+	napi_enable(&tp->napi);
+
+	return 0;
 }
 
 static int rtl8152_suspend(struct usb_interface *intf, pm_message_t message)
@@ -3374,9 +3446,11 @@ static int rtl8152_resume(struct usb_interface *intf)
 		if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) {
 			rtl_runtime_suspend_enable(tp, false);
 			clear_bit(SELECTIVE_SUSPEND, &tp->flags);
+			napi_disable(&tp->napi);
 			set_bit(WORK_ENABLE, &tp->flags);
 			if (netif_carrier_ok(tp->netdev))
 				rtl_start_rx(tp);
+			napi_enable(&tp->napi);
 		} else {
 			tp->rtl_ops.up(tp);
 			rtl8152_set_speed(tp, AUTONEG_ENABLE,
@@ -3403,12 +3477,15 @@ static void rtl8152_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 	if (usb_autopm_get_interface(tp->intf) < 0)
 		return;
 
-	mutex_lock(&tp->control);
-
-	wol->supported = WAKE_ANY;
-	wol->wolopts = __rtl_get_wol(tp);
-
-	mutex_unlock(&tp->control);
+	if (!rtl_can_wakeup(tp)) {
+		wol->supported = 0;
+		wol->wolopts = 0;
+	} else {
+		mutex_lock(&tp->control);
+		wol->supported = WAKE_ANY;
+		wol->wolopts = __rtl_get_wol(tp);
+		mutex_unlock(&tp->control);
+	}
 
 	usb_autopm_put_interface(tp->intf);
 }
@@ -3418,6 +3495,9 @@ static int rtl8152_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 	struct r8152 *tp = netdev_priv(dev);
 	int ret;
 
+	if (!rtl_can_wakeup(tp))
+		return -EOPNOTSUPP;
+
 	ret = usb_autopm_get_interface(tp->intf);
 	if (ret < 0)
 		goto out_set_wol;
@@ -4059,6 +4139,9 @@ static int rtl8152_probe(struct usb_interface *intf,
 		goto out1;
 	}
 
+	if (!rtl_can_wakeup(tp))
+		__rtl_set_wol(tp, 0);
+
 	tp->saved_wolopts = __rtl_get_wol(tp);
 	if (tp->saved_wolopts)
 		device_set_wakeup_enable(&udev->dev, true);
@@ -4132,6 +4215,8 @@ static struct usb_driver rtl8152_driver = {
 	.suspend =	rtl8152_suspend,
 	.resume =	rtl8152_resume,
 	.reset_resume =	rtl8152_resume,
+	.pre_reset =	rtl8152_pre_reset,
+	.post_reset =	rtl8152_post_reset,
 	.supports_autosuspend = 1,
 	.disable_hub_initiated_lpm = 1,
 };
diff --git a/drivers/of/Kconfig b/drivers/of/Kconfig
index 8df1b1777745..59bb8556e43a 100644
--- a/drivers/of/Kconfig
+++ b/drivers/of/Kconfig
@@ -47,7 +47,7 @@ config OF_DYNAMIC
 
 config OF_ADDRESS
 	def_bool y
-	depends on !SPARC
+	depends on !SPARC && HAS_IOMEM
 	select OF_ADDRESS_PCI if PCI
 
 config OF_ADDRESS_PCI
diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c
index 18016341d5a9..9f71770b6226 100644
--- a/drivers/of/unittest.c
+++ b/drivers/of/unittest.c
@@ -979,7 +979,6 @@ static struct platform_driver unittest_driver = {
 	.remove			= unittest_remove,
 	.driver = {
 		.name		= "unittest",
-		.owner		= THIS_MODULE,
 		.of_match_table	= of_match_ptr(unittest_match),
 	},
 };
@@ -1666,7 +1665,6 @@ static const struct i2c_device_id unittest_i2c_dev_id[] = {
 static struct i2c_driver unittest_i2c_dev_driver = {
 	.driver = {
 		.name = "unittest-i2c-dev",
-		.owner = THIS_MODULE,
 	},
 	.probe = unittest_i2c_dev_probe,
 	.remove = unittest_i2c_dev_remove,
@@ -1761,7 +1759,6 @@ static const struct i2c_device_id unittest_i2c_mux_id[] = {
 static struct i2c_driver unittest_i2c_mux_driver = {
 	.driver = {
 		.name = "unittest-i2c-mux",
-		.owner = THIS_MODULE,
 	},
 	.probe = unittest_i2c_mux_probe,
 	.remove = unittest_i2c_mux_remove,
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index 882744852aac..a9aa38903efe 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -599,9 +599,10 @@ static void ipr_trc_hook(struct ipr_cmnd *ipr_cmd,
 {
 	struct ipr_trace_entry *trace_entry;
 	struct ipr_ioa_cfg *ioa_cfg = ipr_cmd->ioa_cfg;
+	unsigned int trace_index;
 
-	trace_entry = &ioa_cfg->trace[atomic_add_return
-			(1, &ioa_cfg->trace_index)%IPR_NUM_TRACE_ENTRIES];
+	trace_index = atomic_add_return(1, &ioa_cfg->trace_index) & IPR_TRACE_INDEX_MASK;
+	trace_entry = &ioa_cfg->trace[trace_index];
 	trace_entry->time = jiffies;
 	trace_entry->op_code = ipr_cmd->ioarcb.cmd_pkt.cdb[0];
 	trace_entry->type = type;
@@ -1051,10 +1052,15 @@ static void ipr_send_blocking_cmd(struct ipr_cmnd *ipr_cmd,
 
 static int ipr_get_hrrq_index(struct ipr_ioa_cfg *ioa_cfg)
 {
+	unsigned int hrrq;
+
 	if (ioa_cfg->hrrq_num == 1)
-		return 0;
-	else
-		return (atomic_add_return(1, &ioa_cfg->hrrq_index) % (ioa_cfg->hrrq_num - 1)) + 1;
+		hrrq = 0;
+	else {
+		hrrq = atomic_add_return(1, &ioa_cfg->hrrq_index);
+		hrrq = (hrrq % (ioa_cfg->hrrq_num - 1)) + 1;
+	}
+	return hrrq;
 }
 
 /**
@@ -6263,21 +6269,23 @@ static void ipr_scsi_done(struct ipr_cmnd *ipr_cmd)
 	struct ipr_ioa_cfg *ioa_cfg = ipr_cmd->ioa_cfg;
 	struct scsi_cmnd *scsi_cmd = ipr_cmd->scsi_cmd;
 	u32 ioasc = be32_to_cpu(ipr_cmd->s.ioasa.hdr.ioasc);
-	unsigned long hrrq_flags;
+	unsigned long lock_flags;
 
 	scsi_set_resid(scsi_cmd, be32_to_cpu(ipr_cmd->s.ioasa.hdr.residual_data_len));
 
 	if (likely(IPR_IOASC_SENSE_KEY(ioasc) == 0)) {
 		scsi_dma_unmap(scsi_cmd);
 
-		spin_lock_irqsave(ipr_cmd->hrrq->lock, hrrq_flags);
+		spin_lock_irqsave(ipr_cmd->hrrq->lock, lock_flags);
 		list_add_tail(&ipr_cmd->queue, &ipr_cmd->hrrq->hrrq_free_q);
 		scsi_cmd->scsi_done(scsi_cmd);
-		spin_unlock_irqrestore(ipr_cmd->hrrq->lock, hrrq_flags);
+		spin_unlock_irqrestore(ipr_cmd->hrrq->lock, lock_flags);
 	} else {
-		spin_lock_irqsave(ipr_cmd->hrrq->lock, hrrq_flags);
+		spin_lock_irqsave(ioa_cfg->host->host_lock, lock_flags);
+		spin_lock(&ipr_cmd->hrrq->_lock);
 		ipr_erp_start(ioa_cfg, ipr_cmd);
-		spin_unlock_irqrestore(ipr_cmd->hrrq->lock, hrrq_flags);
+		spin_unlock(&ipr_cmd->hrrq->_lock);
+		spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags);
 	}
 }
 
diff --git a/drivers/scsi/ipr.h b/drivers/scsi/ipr.h
index 73790a1d0969..6b97ee45c7b4 100644
--- a/drivers/scsi/ipr.h
+++ b/drivers/scsi/ipr.h
@@ -1486,6 +1486,7 @@ struct ipr_ioa_cfg {
 
 #define IPR_NUM_TRACE_INDEX_BITS	8
 #define IPR_NUM_TRACE_ENTRIES		(1 << IPR_NUM_TRACE_INDEX_BITS)
+#define IPR_TRACE_INDEX_MASK		(IPR_NUM_TRACE_ENTRIES - 1)
 #define IPR_TRACE_SIZE	(sizeof(struct ipr_trace_entry) * IPR_NUM_TRACE_ENTRIES)
 	char trace_start[8];
 #define IPR_TRACE_START_LABEL			"trace"
diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c
index 82b92c414a9c..437254e1c4de 100644
--- a/drivers/scsi/qla2xxx/qla_attr.c
+++ b/drivers/scsi/qla2xxx/qla_attr.c
@@ -738,7 +738,7 @@ qla2x00_sysfs_write_reset(struct file *filp, struct kobject *kobj,
 		ql_log(ql_log_info, vha, 0x706f,
 		    "Issuing MPI reset.\n");
 
-		if (IS_QLA83XX(ha)) {
+		if (IS_QLA83XX(ha) || IS_QLA27XX(ha)) {
 			uint32_t idc_control;
 
 			qla83xx_idc_lock(vha, 0);
diff --git a/drivers/scsi/qla2xxx/qla_dbg.c b/drivers/scsi/qla2xxx/qla_dbg.c
index 0e6ee3ca30e6..8b011aef12bd 100644
--- a/drivers/scsi/qla2xxx/qla_dbg.c
+++ b/drivers/scsi/qla2xxx/qla_dbg.c
@@ -67,10 +67,10 @@
  * |                              |                    | 0xd031-0xd0ff	|
  * |                              |                    | 0xd101-0xd1fe	|
  * |                              |                    | 0xd214-0xd2fe	|
- * | Target Mode		  |	  0xe079       |		|
- * | Target Mode Management	  |	  0xf072       | 0xf002		|
+ * | Target Mode		  |	  0xe080       |		|
+ * | Target Mode Management	  |	  0xf096       | 0xf002		|
  * |                              |                    | 0xf046-0xf049  |
- * | Target Mode Task Management  |	  0x1000b      |		|
+ * | Target Mode Task Management  |	  0x1000d      |		|
  * ----------------------------------------------------------------------
  */
 
diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index e86201d3b8c6..9ad819edcd67 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -274,6 +274,7 @@
 #define RESPONSE_ENTRY_CNT_FX00		256     /* Number of response entries.*/
 
 struct req_que;
+struct qla_tgt_sess;
 
 /*
  * (sd.h is not exported, hence local inclusion)
@@ -2026,6 +2027,7 @@ typedef struct fc_port {
 	uint16_t port_id;
 
 	unsigned long retry_delay_timestamp;
+	struct qla_tgt_sess *tgt_session;
 } fc_port_t;
 
 #include "qla_mr.h"
@@ -3154,13 +3156,13 @@ struct qla_hw_data {
 /* Bit 21 of fw_attributes decides the MCTP capabilities */
 #define IS_MCTP_CAPABLE(ha)	(IS_QLA2031(ha) && \
 				((ha)->fw_attributes_ext[0] & BIT_0))
-#define IS_PI_UNINIT_CAPABLE(ha)	(IS_QLA83XX(ha))
-#define IS_PI_IPGUARD_CAPABLE(ha)	(IS_QLA83XX(ha))
+#define IS_PI_UNINIT_CAPABLE(ha)	(IS_QLA83XX(ha) || IS_QLA27XX(ha))
+#define IS_PI_IPGUARD_CAPABLE(ha)	(IS_QLA83XX(ha) || IS_QLA27XX(ha))
 #define IS_PI_DIFB_DIX0_CAPABLE(ha)	(0)
-#define IS_PI_SPLIT_DET_CAPABLE_HBA(ha)	(IS_QLA83XX(ha))
+#define IS_PI_SPLIT_DET_CAPABLE_HBA(ha)	(IS_QLA83XX(ha) || IS_QLA27XX(ha))
 #define IS_PI_SPLIT_DET_CAPABLE(ha)	(IS_PI_SPLIT_DET_CAPABLE_HBA(ha) && \
     (((ha)->fw_attributes_h << 16 | (ha)->fw_attributes) & BIT_22))
-#define IS_ATIO_MSIX_CAPABLE(ha) (IS_QLA83XX(ha))
+#define IS_ATIO_MSIX_CAPABLE(ha) (IS_QLA83XX(ha) || IS_QLA27XX(ha))
 #define IS_TGT_MODE_CAPABLE(ha)	(ha->tgt.atio_q_length)
 #define IS_SHADOW_REG_CAPABLE(ha)  (IS_QLA27XX(ha))
 #define IS_DPORT_CAPABLE(ha)  (IS_QLA83XX(ha) || IS_QLA27XX(ha))
@@ -3579,6 +3581,16 @@ typedef struct scsi_qla_host {
 	uint16_t	fcoe_fcf_idx;
 	uint8_t		fcoe_vn_port_mac[6];
 
+	/* list of commands waiting on workqueue */
+	struct list_head	qla_cmd_list;
+	struct list_head	qla_sess_op_cmd_list;
+	spinlock_t		cmd_list_lock;
+
+	/* Counter to detect races between ELS and RSCN events */
+	atomic_t		generation_tick;
+	/* Time when global fcport update has been scheduled */
+	int			total_fcport_update_gen;
+
 	uint32_t	vp_abort_cnt;
 
 	struct fc_vport	*fc_vport;	/* holds fc_vport * for each vport */
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 664013115c9d..11f2f3279eab 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -115,6 +115,8 @@ qla2x00_async_iocb_timeout(void *data)
 			QLA_LOGIO_LOGIN_RETRIED : 0;
 		qla2x00_post_async_login_done_work(fcport->vha, fcport,
 			lio->u.logio.data);
+	} else if (sp->type == SRB_LOGOUT_CMD) {
+		qlt_logo_completion_handler(fcport, QLA_FUNCTION_TIMEOUT);
 	}
 }
 
@@ -497,7 +499,10 @@ void
 qla2x00_async_logout_done(struct scsi_qla_host *vha, fc_port_t *fcport,
     uint16_t *data)
 {
-	qla2x00_mark_device_lost(vha, fcport, 1, 0);
+	/* Don't re-login in target mode */
+	if (!fcport->tgt_session)
+		qla2x00_mark_device_lost(vha, fcport, 1, 0);
+	qlt_logo_completion_handler(fcport, data[0]);
 	return;
 }
 
@@ -1538,7 +1543,7 @@ qla2x00_alloc_fw_dump(scsi_qla_host_t *vha)
 		mem_size = (ha->fw_memory_size - 0x11000 + 1) *
 		    sizeof(uint16_t);
 	} else if (IS_FWI2_CAPABLE(ha)) {
-		if (IS_QLA83XX(ha))
+		if (IS_QLA83XX(ha) || IS_QLA27XX(ha))
 			fixed_size = offsetof(struct qla83xx_fw_dump, ext_mem);
 		else if (IS_QLA81XX(ha))
 			fixed_size = offsetof(struct qla81xx_fw_dump, ext_mem);
@@ -1550,7 +1555,7 @@ qla2x00_alloc_fw_dump(scsi_qla_host_t *vha)
 		mem_size = (ha->fw_memory_size - 0x100000 + 1) *
 		    sizeof(uint32_t);
 		if (ha->mqenable) {
-			if (!IS_QLA83XX(ha))
+			if (!IS_QLA83XX(ha) && !IS_QLA27XX(ha))
 				mq_size = sizeof(struct qla2xxx_mq_chain);
 			/*
 			 * Allocate maximum buffer size for all queues.
@@ -2922,21 +2927,14 @@ qla2x00_rport_del(void *data)
 {
 	fc_port_t *fcport = data;
 	struct fc_rport *rport;
-	scsi_qla_host_t *vha = fcport->vha;
 	unsigned long flags;
 
 	spin_lock_irqsave(fcport->vha->host->host_lock, flags);
 	rport = fcport->drport ? fcport->drport: fcport->rport;
 	fcport->drport = NULL;
 	spin_unlock_irqrestore(fcport->vha->host->host_lock, flags);
-	if (rport) {
+	if (rport)
 		fc_remote_port_delete(rport);
-		/*
-		 * Release the target mode FC NEXUS in qla_target.c code
-		 * if target mod is enabled.
-		 */
-		qlt_fc_port_deleted(vha, fcport);
-	}
 }
 
 /**
@@ -3303,6 +3301,7 @@ qla2x00_reg_remote_port(scsi_qla_host_t *vha, fc_port_t *fcport)
 	 * Create target mode FC NEXUS in qla_target.c if target mode is
 	 * enabled..
 	 */
+
 	qlt_fc_port_added(vha, fcport);
 
 	spin_lock_irqsave(fcport->vha->host->host_lock, flags);
@@ -3341,8 +3340,7 @@ qla2x00_update_fcport(scsi_qla_host_t *vha, fc_port_t *fcport)
 
 	if (IS_QLAFX00(vha->hw)) {
 		qla2x00_set_fcport_state(fcport, FCS_ONLINE);
-		qla2x00_reg_remote_port(vha, fcport);
-		return;
+		goto reg_port;
 	}
 	fcport->login_retry = 0;
 	fcport->flags &= ~(FCF_LOGIN_NEEDED | FCF_ASYNC_SENT);
@@ -3350,7 +3348,16 @@ qla2x00_update_fcport(scsi_qla_host_t *vha, fc_port_t *fcport)
 	qla2x00_set_fcport_state(fcport, FCS_ONLINE);
 	qla2x00_iidma_fcport(vha, fcport);
 	qla24xx_update_fcport_fcp_prio(vha, fcport);
-	qla2x00_reg_remote_port(vha, fcport);
+
+reg_port:
+	if (qla_ini_mode_enabled(vha))
+		qla2x00_reg_remote_port(vha, fcport);
+	else {
+		/*
+		 * Create target mode FC NEXUS in qla_target.c
+		 */
+		qlt_fc_port_added(vha, fcport);
+	}
 }
 
 /*
@@ -3375,6 +3382,7 @@ qla2x00_configure_fabric(scsi_qla_host_t *vha)
 	LIST_HEAD(new_fcports);
 	struct qla_hw_data *ha = vha->hw;
 	struct scsi_qla_host *base_vha = pci_get_drvdata(ha->pdev);
+	int		discovery_gen;
 
 	/* If FL port exists, then SNS is present */
 	if (IS_FWI2_CAPABLE(ha))
@@ -3445,6 +3453,14 @@ qla2x00_configure_fabric(scsi_qla_host_t *vha)
 			fcport->scan_state = QLA_FCPORT_SCAN;
 		}
 
+		/* Mark the time right before querying FW for connected ports.
+		 * This process is long, asynchronous and by the time it's done,
+		 * collected information might not be accurate anymore. E.g.
+		 * disconnected port might have re-connected and a brand new
+		 * session has been created. In this case session's generation
+		 * will be newer than discovery_gen. */
+		qlt_do_generation_tick(vha, &discovery_gen);
+
 		rval = qla2x00_find_all_fabric_devs(vha, &new_fcports);
 		if (rval != QLA_SUCCESS)
 			break;
@@ -3460,20 +3476,44 @@ qla2x00_configure_fabric(scsi_qla_host_t *vha)
 			if ((fcport->flags & FCF_FABRIC_DEVICE) == 0)
 				continue;
 
-			if (fcport->scan_state == QLA_FCPORT_SCAN &&
-			    atomic_read(&fcport->state) == FCS_ONLINE) {
-				qla2x00_mark_device_lost(vha, fcport,
-				    ql2xplogiabsentdevice, 0);
-				if (fcport->loop_id != FC_NO_LOOP_ID &&
-				    (fcport->flags & FCF_FCP2_DEVICE) == 0 &&
-				    fcport->port_type != FCT_INITIATOR &&
-				    fcport->port_type != FCT_BROADCAST) {
-					ha->isp_ops->fabric_logout(vha,
-					    fcport->loop_id,
-					    fcport->d_id.b.domain,
-					    fcport->d_id.b.area,
-					    fcport->d_id.b.al_pa);
-					qla2x00_clear_loop_id(fcport);
+			if (fcport->scan_state == QLA_FCPORT_SCAN) {
+				if (qla_ini_mode_enabled(base_vha) &&
+				    atomic_read(&fcport->state) == FCS_ONLINE) {
+					qla2x00_mark_device_lost(vha, fcport,
+					    ql2xplogiabsentdevice, 0);
+					if (fcport->loop_id != FC_NO_LOOP_ID &&
+					    (fcport->flags & FCF_FCP2_DEVICE) == 0 &&
+					    fcport->port_type != FCT_INITIATOR &&
+					    fcport->port_type != FCT_BROADCAST) {
+						ha->isp_ops->fabric_logout(vha,
+						    fcport->loop_id,
+						    fcport->d_id.b.domain,
+						    fcport->d_id.b.area,
+						    fcport->d_id.b.al_pa);
+						qla2x00_clear_loop_id(fcport);
+					}
+				} else if (!qla_ini_mode_enabled(base_vha)) {
+					/*
+					 * In target mode, explicitly kill
+					 * sessions and log out of devices
+					 * that are gone, so that we don't
+					 * end up with an initiator using the
+					 * wrong ACL (if the fabric recycles
+					 * an FC address and we have a stale
+					 * session around) and so that we don't
+					 * report initiators that are no longer
+					 * on the fabric.
+					 */
+					ql_dbg(ql_dbg_tgt_mgt, vha, 0xf077,
+					    "port gone, logging out/killing session: "
+					    "%8phC state 0x%x flags 0x%x fc4_type 0x%x "
+					    "scan_state %d\n",
+					    fcport->port_name,
+					    atomic_read(&fcport->state),
+					    fcport->flags, fcport->fc4_type,
+					    fcport->scan_state);
+					qlt_fc_port_deleted(vha, fcport,
+					    discovery_gen);
 				}
 			}
 		}
@@ -3494,6 +3534,28 @@ qla2x00_configure_fabric(scsi_qla_host_t *vha)
 			    (fcport->flags & FCF_LOGIN_NEEDED) == 0)
 				continue;
 
+			/*
+			 * If we're not an initiator, skip looking for devices
+			 * and logging in.  There's no reason for us to do it,
+			 * and it seems to actively cause problems in target
+			 * mode if we race with the initiator logging into us
+			 * (we might get the "port ID used" status back from
+			 * our login command and log out the initiator, which
+			 * seems to cause havoc).
+			 */
+			if (!qla_ini_mode_enabled(base_vha)) {
+				if (fcport->scan_state == QLA_FCPORT_FOUND) {
+					ql_dbg(ql_dbg_tgt_mgt, vha, 0xf078,
+					    "port %8phC state 0x%x flags 0x%x fc4_type 0x%x "
+					    "scan_state %d (initiator mode disabled; skipping "
+					    "login)\n", fcport->port_name,
+					    atomic_read(&fcport->state),
+					    fcport->flags, fcport->fc4_type,
+					    fcport->scan_state);
+				}
+				continue;
+			}
+
 			if (fcport->loop_id == FC_NO_LOOP_ID) {
 				fcport->loop_id = next_loopid;
 				rval = qla2x00_find_new_loop_id(
@@ -3520,16 +3582,38 @@ qla2x00_configure_fabric(scsi_qla_host_t *vha)
 			    test_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags))
 				break;
 
-			/* Find a new loop ID to use. */
-			fcport->loop_id = next_loopid;
-			rval = qla2x00_find_new_loop_id(base_vha, fcport);
-			if (rval != QLA_SUCCESS) {
-				/* Ran out of IDs to use */
-				break;
-			}
+			/*
+			 * If we're not an initiator, skip looking for devices
+			 * and logging in.  There's no reason for us to do it,
+			 * and it seems to actively cause problems in target
+			 * mode if we race with the initiator logging into us
+			 * (we might get the "port ID used" status back from
+			 * our login command and log out the initiator, which
+			 * seems to cause havoc).
+			 */
+			if (qla_ini_mode_enabled(base_vha)) {
+				/* Find a new loop ID to use. */
+				fcport->loop_id = next_loopid;
+				rval = qla2x00_find_new_loop_id(base_vha,
+				    fcport);
+				if (rval != QLA_SUCCESS) {
+					/* Ran out of IDs to use */
+					break;
+				}
 
-			/* Login and update database */
-			qla2x00_fabric_dev_login(vha, fcport, &next_loopid);
+				/* Login and update database */
+				qla2x00_fabric_dev_login(vha, fcport,
+				    &next_loopid);
+			} else {
+				ql_dbg(ql_dbg_tgt_mgt, vha, 0xf079,
+					"new port %8phC state 0x%x flags 0x%x fc4_type "
+					"0x%x scan_state %d (initiator mode disabled; "
+					"skipping login)\n",
+					fcport->port_name,
+					atomic_read(&fcport->state),
+					fcport->flags, fcport->fc4_type,
+					fcport->scan_state);
+			}
 
 			list_move_tail(&fcport->list, &vha->vp_fcports);
 		}
@@ -3725,11 +3809,12 @@ qla2x00_find_all_fabric_devs(scsi_qla_host_t *vha,
 			fcport->fp_speed = new_fcport->fp_speed;
 
 			/*
-			 * If address the same and state FCS_ONLINE, nothing
-			 * changed.
+			 * If address the same and state FCS_ONLINE
+			 * (or in target mode), nothing changed.
 			 */
 			if (fcport->d_id.b24 == new_fcport->d_id.b24 &&
-			    atomic_read(&fcport->state) == FCS_ONLINE) {
+			    (atomic_read(&fcport->state) == FCS_ONLINE ||
+			     !qla_ini_mode_enabled(base_vha))) {
 				break;
 			}
 
@@ -3749,6 +3834,22 @@ qla2x00_find_all_fabric_devs(scsi_qla_host_t *vha,
 			 * Log it out if still logged in and mark it for
 			 * relogin later.
 			 */
+			if (!qla_ini_mode_enabled(base_vha)) {
+				ql_dbg(ql_dbg_tgt_mgt, vha, 0xf080,
+					 "port changed FC ID, %8phC"
+					 " old %x:%x:%x (loop_id 0x%04x)-> new %x:%x:%x\n",
+					 fcport->port_name,
+					 fcport->d_id.b.domain,
+					 fcport->d_id.b.area,
+					 fcport->d_id.b.al_pa,
+					 fcport->loop_id,
+					 new_fcport->d_id.b.domain,
+					 new_fcport->d_id.b.area,
+					 new_fcport->d_id.b.al_pa);
+				fcport->d_id.b24 = new_fcport->d_id.b24;
+				break;
+			}
+
 			fcport->d_id.b24 = new_fcport->d_id.b24;
 			fcport->flags |= FCF_LOGIN_NEEDED;
 			if (fcport->loop_id != FC_NO_LOOP_ID &&
@@ -3768,6 +3869,7 @@ qla2x00_find_all_fabric_devs(scsi_qla_host_t *vha,
 		if (found)
 			continue;
 		/* If device was not in our fcports list, then add it. */
+		new_fcport->scan_state = QLA_FCPORT_FOUND;
 		list_add_tail(&new_fcport->list, new_fcports);
 
 		/* Allocate a new replacement fcport. */
@@ -4188,6 +4290,14 @@ qla2x00_update_fcports(scsi_qla_host_t *base_vha)
 			    atomic_read(&fcport->state) != FCS_UNCONFIGURED) {
 				spin_unlock_irqrestore(&ha->vport_slock, flags);
 				qla2x00_rport_del(fcport);
+
+				/*
+				 * Release the target mode FC NEXUS in
+				 * qla_target.c, if target mod is enabled.
+				 */
+				qlt_fc_port_deleted(vha, fcport,
+				    base_vha->total_fcport_update_gen);
+
 				spin_lock_irqsave(&ha->vport_slock, flags);
 			}
 		}
diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c
index 36fbd4c7af8f..6f02b26a35cf 100644
--- a/drivers/scsi/qla2xxx/qla_iocb.c
+++ b/drivers/scsi/qla2xxx/qla_iocb.c
@@ -1943,6 +1943,9 @@ qla24xx_logout_iocb(srb_t *sp, struct logio_entry_24xx *logio)
 	logio->entry_type = LOGINOUT_PORT_IOCB_TYPE;
 	logio->control_flags =
 	    cpu_to_le16(LCF_COMMAND_LOGO|LCF_IMPL_LOGO);
+	if (!sp->fcport->tgt_session ||
+	    !sp->fcport->tgt_session->keep_nport_handle)
+		logio->control_flags |= cpu_to_le16(LCF_FREE_NPORT);
 	logio->nport_handle = cpu_to_le16(sp->fcport->loop_id);
 	logio->port_id[0] = sp->fcport->d_id.b.al_pa;
 	logio->port_id[1] = sp->fcport->d_id.b.area;
diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c
index 02b1c1c5355b..b2f713ad9034 100644
--- a/drivers/scsi/qla2xxx/qla_mbx.c
+++ b/drivers/scsi/qla2xxx/qla_mbx.c
@@ -2415,7 +2415,8 @@ qla2x00_get_resource_cnts(scsi_qla_host_t *vha, uint16_t *cur_xchg_cnt,
 			*orig_iocb_cnt = mcp->mb[10];
 		if (vha->hw->flags.npiv_supported && max_npiv_vports)
 			*max_npiv_vports = mcp->mb[11];
-		if ((IS_QLA81XX(vha->hw) || IS_QLA83XX(vha->hw)) && max_fcfs)
+		if ((IS_QLA81XX(vha->hw) || IS_QLA83XX(vha->hw) ||
+		    IS_QLA27XX(vha->hw)) && max_fcfs)
 			*max_fcfs = mcp->mb[12];
 	}
 
@@ -3898,7 +3899,7 @@ qla25xx_init_rsp_que(struct scsi_qla_host *vha, struct rsp_que *rsp)
 	spin_lock_irqsave(&ha->hardware_lock, flags);
 	if (!(rsp->options & BIT_0)) {
 		WRT_REG_DWORD(rsp->rsp_q_out, 0);
-		if (!IS_QLA83XX(ha))
+		if (!IS_QLA83XX(ha) && !IS_QLA27XX(ha))
 			WRT_REG_DWORD(rsp->rsp_q_in, 0);
 	}
 
@@ -5345,7 +5346,7 @@ qla83xx_restart_nic_firmware(scsi_qla_host_t *vha)
 	mbx_cmd_t *mcp = &mc;
 	struct qla_hw_data *ha = vha->hw;
 
-	if (!IS_QLA83XX(ha))
+	if (!IS_QLA83XX(ha) && !IS_QLA27XX(ha))
 		return QLA_FUNCTION_FAILED;
 
 	ql_dbg(ql_dbg_mbx, vha, 0x1143, "Entered %s.\n", __func__);
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index a28815b8276f..8a5cac8448c7 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -2504,6 +2504,7 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 		ha->mbx_count = MAILBOX_REGISTER_COUNT;
 		req_length = REQUEST_ENTRY_CNT_24XX;
 		rsp_length = RESPONSE_ENTRY_CNT_2300;
+		ha->tgt.atio_q_length = ATIO_ENTRY_CNT_24XX;
 		ha->max_loop_id = SNS_LAST_LOOP_ID_2300;
 		ha->init_cb_size = sizeof(struct mid_init_cb_81xx);
 		ha->gid_list_info_size = 8;
@@ -3229,11 +3230,15 @@ qla2x00_schedule_rport_del(struct scsi_qla_host *vha, fc_port_t *fcport,
 		spin_lock_irqsave(vha->host->host_lock, flags);
 		fcport->drport = rport;
 		spin_unlock_irqrestore(vha->host->host_lock, flags);
+		qlt_do_generation_tick(vha, &base_vha->total_fcport_update_gen);
 		set_bit(FCPORT_UPDATE_NEEDED, &base_vha->dpc_flags);
 		qla2xxx_wake_dpc(base_vha);
 	} else {
-		fc_remote_port_delete(rport);
-		qlt_fc_port_deleted(vha, fcport);
+		int now;
+		if (rport)
+			fc_remote_port_delete(rport);
+		qlt_do_generation_tick(vha, &now);
+		qlt_fc_port_deleted(vha, fcport, now);
 	}
 }
 
@@ -3763,8 +3768,11 @@ struct scsi_qla_host *qla2x00_create_host(struct scsi_host_template *sht,
 	INIT_LIST_HEAD(&vha->vp_fcports);
 	INIT_LIST_HEAD(&vha->work_list);
 	INIT_LIST_HEAD(&vha->list);
+	INIT_LIST_HEAD(&vha->qla_cmd_list);
+	INIT_LIST_HEAD(&vha->qla_sess_op_cmd_list);
 
 	spin_lock_init(&vha->work_lock);
+	spin_lock_init(&vha->cmd_list_lock);
 
 	sprintf(vha->host_str, "%s_%ld", QLA2XXX_DRIVER_NAME, vha->host_no);
 	ql_dbg(ql_dbg_init, vha, 0x0041,
diff --git a/drivers/scsi/qla2xxx/qla_sup.c b/drivers/scsi/qla2xxx/qla_sup.c
index 028e8c8a7de9..2feb5f38edcd 100644
--- a/drivers/scsi/qla2xxx/qla_sup.c
+++ b/drivers/scsi/qla2xxx/qla_sup.c
@@ -1697,7 +1697,7 @@ qla83xx_select_led_port(struct qla_hw_data *ha)
 {
 	uint32_t led_select_value = 0;
 
-	if (!IS_QLA83XX(ha))
+	if (!IS_QLA83XX(ha) && !IS_QLA27XX(ha))
 		goto out;
 
 	if (ha->port_no == 0)
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index b749026aa592..58651ecbd88c 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -113,6 +113,11 @@ static void qlt_abort_cmd_on_host_reset(struct scsi_qla_host *vha,
 static void qlt_alloc_qfull_cmd(struct scsi_qla_host *vha,
 	struct atio_from_isp *atio, uint16_t status, int qfull);
 static void qlt_disable_vha(struct scsi_qla_host *vha);
+static void qlt_clear_tgt_db(struct qla_tgt *tgt);
+static void qlt_send_notify_ack(struct scsi_qla_host *vha,
+	struct imm_ntfy_from_isp *ntfy,
+	uint32_t add_flags, uint16_t resp_code, int resp_code_valid,
+	uint16_t srr_flags, uint16_t srr_reject_code, uint8_t srr_explan);
 /*
  * Global Variables
  */
@@ -122,6 +127,16 @@ static struct workqueue_struct *qla_tgt_wq;
 static DEFINE_MUTEX(qla_tgt_mutex);
 static LIST_HEAD(qla_tgt_glist);
 
+/* This API intentionally takes dest as a parameter, rather than returning
+ * int value to avoid caller forgetting to issue wmb() after the store */
+void qlt_do_generation_tick(struct scsi_qla_host *vha, int *dest)
+{
+	scsi_qla_host_t *base_vha = pci_get_drvdata(vha->hw->pdev);
+	*dest = atomic_inc_return(&base_vha->generation_tick);
+	/* memory barrier */
+	wmb();
+}
+
 /* ha->hardware_lock supposed to be held on entry (to protect tgt->sess_list) */
 static struct qla_tgt_sess *qlt_find_sess_by_port_name(
 	struct qla_tgt *tgt,
@@ -381,14 +396,73 @@ static void qlt_free_session_done(struct work_struct *work)
 	struct qla_tgt *tgt = sess->tgt;
 	struct scsi_qla_host *vha = sess->vha;
 	struct qla_hw_data *ha = vha->hw;
+	unsigned long flags;
+	bool logout_started = false;
+	fc_port_t fcport;
+
+	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf084,
+		"%s: se_sess %p / sess %p from port %8phC loop_id %#04x"
+		" s_id %02x:%02x:%02x logout %d keep %d plogi %d\n",
+		__func__, sess->se_sess, sess, sess->port_name, sess->loop_id,
+		sess->s_id.b.domain, sess->s_id.b.area, sess->s_id.b.al_pa,
+		sess->logout_on_delete, sess->keep_nport_handle,
+		sess->plogi_ack_needed);
 
 	BUG_ON(!tgt);
+
+	if (sess->logout_on_delete) {
+		int rc;
+
+		memset(&fcport, 0, sizeof(fcport));
+		fcport.loop_id = sess->loop_id;
+		fcport.d_id = sess->s_id;
+		memcpy(fcport.port_name, sess->port_name, WWN_SIZE);
+		fcport.vha = vha;
+		fcport.tgt_session = sess;
+
+		rc = qla2x00_post_async_logout_work(vha, &fcport, NULL);
+		if (rc != QLA_SUCCESS)
+			ql_log(ql_log_warn, vha, 0xf085,
+			       "Schedule logo failed sess %p rc %d\n",
+			       sess, rc);
+		else
+			logout_started = true;
+	}
+
 	/*
 	 * Release the target session for FC Nexus from fabric module code.
 	 */
 	if (sess->se_sess != NULL)
 		ha->tgt.tgt_ops->free_session(sess);
 
+	if (logout_started) {
+		bool traced = false;
+
+		while (!ACCESS_ONCE(sess->logout_completed)) {
+			if (!traced) {
+				ql_dbg(ql_dbg_tgt_mgt, vha, 0xf086,
+					"%s: waiting for sess %p logout\n",
+					__func__, sess);
+				traced = true;
+			}
+			msleep(100);
+		}
+
+		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf087,
+			"%s: sess %p logout completed\n",
+			__func__, sess);
+	}
+
+	spin_lock_irqsave(&ha->hardware_lock, flags);
+
+	if (sess->plogi_ack_needed)
+		qlt_send_notify_ack(vha, &sess->tm_iocb,
+				    0, 0, 0, 0, 0, 0);
+
+	list_del(&sess->sess_list_entry);
+
+	spin_unlock_irqrestore(&ha->hardware_lock, flags);
+
 	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf001,
 	    "Unregistration of sess %p finished\n", sess);
 
@@ -409,9 +483,9 @@ void qlt_unreg_sess(struct qla_tgt_sess *sess)
 
 	vha->hw->tgt.tgt_ops->clear_nacl_from_fcport_map(sess);
 
-	list_del(&sess->sess_list_entry);
-	if (sess->deleted)
-		list_del(&sess->del_list_entry);
+	if (!list_empty(&sess->del_list_entry))
+		list_del_init(&sess->del_list_entry);
+	sess->deleted = QLA_SESS_DELETION_IN_PROGRESS;
 
 	INIT_WORK(&sess->free_work, qlt_free_session_done);
 	schedule_work(&sess->free_work);
@@ -431,10 +505,10 @@ static int qlt_reset(struct scsi_qla_host *vha, void *iocb, int mcmd)
 
 	loop_id = le16_to_cpu(n->u.isp24.nport_handle);
 	if (loop_id == 0xFFFF) {
-#if 0 /* FIXME: Re-enable Global event handling.. */
 		/* Global event */
-		atomic_inc(&ha->tgt.qla_tgt->tgt_global_resets_count);
-		qlt_clear_tgt_db(ha->tgt.qla_tgt);
+		atomic_inc(&vha->vha_tgt.qla_tgt->tgt_global_resets_count);
+		qlt_clear_tgt_db(vha->vha_tgt.qla_tgt);
+#if 0 /* FIXME: do we need to choose a session here? */
 		if (!list_empty(&ha->tgt.qla_tgt->sess_list)) {
 			sess = list_entry(ha->tgt.qla_tgt->sess_list.next,
 			    typeof(*sess), sess_list_entry);
@@ -489,27 +563,38 @@ static void qlt_schedule_sess_for_deletion(struct qla_tgt_sess *sess,
 	struct qla_tgt *tgt = sess->tgt;
 	uint32_t dev_loss_tmo = tgt->ha->port_down_retry_count + 5;
 
-	if (sess->deleted)
-		return;
+	if (sess->deleted) {
+		/* Upgrade to unconditional deletion in case it was temporary */
+		if (immediate && sess->deleted == QLA_SESS_DELETION_PENDING)
+			list_del(&sess->del_list_entry);
+		else
+			return;
+	}
 
 	ql_dbg(ql_dbg_tgt, sess->vha, 0xe001,
 	    "Scheduling sess %p for deletion\n", sess);
-	list_add_tail(&sess->del_list_entry, &tgt->del_sess_list);
-	sess->deleted = 1;
 
-	if (immediate)
+	if (immediate) {
 		dev_loss_tmo = 0;
+		sess->deleted = QLA_SESS_DELETION_IN_PROGRESS;
+		list_add(&sess->del_list_entry, &tgt->del_sess_list);
+	} else {
+		sess->deleted = QLA_SESS_DELETION_PENDING;
+		list_add_tail(&sess->del_list_entry, &tgt->del_sess_list);
+	}
 
 	sess->expires = jiffies + dev_loss_tmo * HZ;
 
 	ql_dbg(ql_dbg_tgt, sess->vha, 0xe048,
-	    "qla_target(%d): session for port %8phC (loop ID %d) scheduled for "
-	    "deletion in %u secs (expires: %lu) immed: %d\n",
-	    sess->vha->vp_idx, sess->port_name, sess->loop_id, dev_loss_tmo,
-	    sess->expires, immediate);
+	    "qla_target(%d): session for port %8phC (loop ID %d s_id %02x:%02x:%02x)"
+	    " scheduled for deletion in %u secs (expires: %lu) immed: %d, logout: %d, gen: %#x\n",
+	    sess->vha->vp_idx, sess->port_name, sess->loop_id,
+	    sess->s_id.b.domain, sess->s_id.b.area, sess->s_id.b.al_pa,
+	    dev_loss_tmo, sess->expires, immediate, sess->logout_on_delete,
+	    sess->generation);
 
 	if (immediate)
-		schedule_delayed_work(&tgt->sess_del_work, 0);
+		mod_delayed_work(system_wq, &tgt->sess_del_work, 0);
 	else
 		schedule_delayed_work(&tgt->sess_del_work,
 		    sess->expires - jiffies);
@@ -578,9 +663,9 @@ out_free_id_list:
 /* ha->hardware_lock supposed to be held on entry */
 static void qlt_undelete_sess(struct qla_tgt_sess *sess)
 {
-	BUG_ON(!sess->deleted);
+	BUG_ON(sess->deleted != QLA_SESS_DELETION_PENDING);
 
-	list_del(&sess->del_list_entry);
+	list_del_init(&sess->del_list_entry);
 	sess->deleted = 0;
 }
 
@@ -599,7 +684,9 @@ static void qlt_del_sess_work_fn(struct delayed_work *work)
 		    del_list_entry);
 		elapsed = jiffies;
 		if (time_after_eq(elapsed, sess->expires)) {
-			qlt_undelete_sess(sess);
+			/* No turning back */
+			list_del_init(&sess->del_list_entry);
+			sess->deleted = QLA_SESS_DELETION_IN_PROGRESS;
 
 			ql_dbg(ql_dbg_tgt_mgt, vha, 0xf004,
 			    "Timeout: sess %p about to be deleted\n",
@@ -643,6 +730,13 @@ static struct qla_tgt_sess *qlt_create_sess(
 			    fcport->d_id.b.al_pa, fcport->d_id.b.area,
 			    fcport->loop_id);
 
+			/* Cannot undelete at this point */
+			if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) {
+				spin_unlock_irqrestore(&ha->hardware_lock,
+				    flags);
+				return NULL;
+			}
+
 			if (sess->deleted)
 				qlt_undelete_sess(sess);
 
@@ -652,6 +746,9 @@ static struct qla_tgt_sess *qlt_create_sess(
 
 			if (sess->local && !local)
 				sess->local = 0;
+
+			qlt_do_generation_tick(vha, &sess->generation);
+
 			spin_unlock_irqrestore(&ha->hardware_lock, flags);
 
 			return sess;
@@ -673,6 +770,14 @@ static struct qla_tgt_sess *qlt_create_sess(
 	sess->s_id = fcport->d_id;
 	sess->loop_id = fcport->loop_id;
 	sess->local = local;
+	INIT_LIST_HEAD(&sess->del_list_entry);
+
+	/* Under normal circumstances we want to logout from firmware when
+	 * session eventually ends and release corresponding nport handle.
+	 * In the exception cases (e.g. when new PLOGI is waiting) corresponding
+	 * code will adjust these flags as necessary. */
+	sess->logout_on_delete = 1;
+	sess->keep_nport_handle = 0;
 
 	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf006,
 	    "Adding sess %p to tgt %p via ->check_initiator_node_acl()\n",
@@ -705,6 +810,7 @@ static struct qla_tgt_sess *qlt_create_sess(
 	spin_lock_irqsave(&ha->hardware_lock, flags);
 	list_add_tail(&sess->sess_list_entry, &vha->vha_tgt.qla_tgt->sess_list);
 	vha->vha_tgt.qla_tgt->sess_count++;
+	qlt_do_generation_tick(vha, &sess->generation);
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 
 	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf04b,
@@ -718,7 +824,7 @@ static struct qla_tgt_sess *qlt_create_sess(
 }
 
 /*
- * Called from drivers/scsi/qla2xxx/qla_init.c:qla2x00_reg_remote_port()
+ * Called from qla2x00_reg_remote_port()
  */
 void qlt_fc_port_added(struct scsi_qla_host *vha, fc_port_t *fcport)
 {
@@ -750,6 +856,10 @@ void qlt_fc_port_added(struct scsi_qla_host *vha, fc_port_t *fcport)
 		mutex_unlock(&vha->vha_tgt.tgt_mutex);
 
 		spin_lock_irqsave(&ha->hardware_lock, flags);
+	} else if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) {
+		/* Point of no return */
+		spin_unlock_irqrestore(&ha->hardware_lock, flags);
+		return;
 	} else {
 		kref_get(&sess->se_sess->sess_kref);
 
@@ -780,27 +890,36 @@ void qlt_fc_port_added(struct scsi_qla_host *vha, fc_port_t *fcport)
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 }
 
-void qlt_fc_port_deleted(struct scsi_qla_host *vha, fc_port_t *fcport)
+/*
+ * max_gen - specifies maximum session generation
+ * at which this deletion requestion is still valid
+ */
+void
+qlt_fc_port_deleted(struct scsi_qla_host *vha, fc_port_t *fcport, int max_gen)
 {
-	struct qla_hw_data *ha = vha->hw;
 	struct qla_tgt *tgt = vha->vha_tgt.qla_tgt;
 	struct qla_tgt_sess *sess;
-	unsigned long flags;
 
 	if (!vha->hw->tgt.tgt_ops)
 		return;
 
-	if (!tgt || (fcport->port_type != FCT_INITIATOR))
+	if (!tgt)
 		return;
 
-	spin_lock_irqsave(&ha->hardware_lock, flags);
 	if (tgt->tgt_stop) {
-		spin_unlock_irqrestore(&ha->hardware_lock, flags);
 		return;
 	}
 	sess = qlt_find_sess_by_port_name(tgt, fcport->port_name);
 	if (!sess) {
-		spin_unlock_irqrestore(&ha->hardware_lock, flags);
+		return;
+	}
+
+	if (max_gen - sess->generation < 0) {
+		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf092,
+		    "Ignoring stale deletion request for se_sess %p / sess %p"
+		    " for port %8phC, req_gen %d, sess_gen %d\n",
+		    sess->se_sess, sess, sess->port_name, max_gen,
+		    sess->generation);
 		return;
 	}
 
@@ -808,7 +927,6 @@ void qlt_fc_port_deleted(struct scsi_qla_host *vha, fc_port_t *fcport)
 
 	sess->local = 1;
 	qlt_schedule_sess_for_deletion(sess, false);
-	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 }
 
 static inline int test_tgt_sess_count(struct qla_tgt *tgt)
@@ -1175,6 +1293,70 @@ static void qlt_24xx_retry_term_exchange(struct scsi_qla_host *vha,
 	    FCP_TMF_CMPL, true);
 }
 
+static int abort_cmd_for_tag(struct scsi_qla_host *vha, uint32_t tag)
+{
+	struct qla_tgt_sess_op *op;
+	struct qla_tgt_cmd *cmd;
+
+	spin_lock(&vha->cmd_list_lock);
+
+	list_for_each_entry(op, &vha->qla_sess_op_cmd_list, cmd_list) {
+		if (tag == op->atio.u.isp24.exchange_addr) {
+			op->aborted = true;
+			spin_unlock(&vha->cmd_list_lock);
+			return 1;
+		}
+	}
+
+	list_for_each_entry(cmd, &vha->qla_cmd_list, cmd_list) {
+		if (tag == cmd->atio.u.isp24.exchange_addr) {
+			cmd->state = QLA_TGT_STATE_ABORTED;
+			spin_unlock(&vha->cmd_list_lock);
+			return 1;
+		}
+	}
+
+	spin_unlock(&vha->cmd_list_lock);
+	return 0;
+}
+
+/* drop cmds for the given lun
+ * XXX only looks for cmds on the port through which lun reset was recieved
+ * XXX does not go through the list of other port (which may have cmds
+ *     for the same lun)
+ */
+static void abort_cmds_for_lun(struct scsi_qla_host *vha,
+				uint32_t lun, uint8_t *s_id)
+{
+	struct qla_tgt_sess_op *op;
+	struct qla_tgt_cmd *cmd;
+	uint32_t key;
+
+	key = sid_to_key(s_id);
+	spin_lock(&vha->cmd_list_lock);
+	list_for_each_entry(op, &vha->qla_sess_op_cmd_list, cmd_list) {
+		uint32_t op_key;
+		uint32_t op_lun;
+
+		op_key = sid_to_key(op->atio.u.isp24.fcp_hdr.s_id);
+		op_lun = scsilun_to_int(
+			(struct scsi_lun *)&op->atio.u.isp24.fcp_cmnd.lun);
+		if (op_key == key && op_lun == lun)
+			op->aborted = true;
+	}
+	list_for_each_entry(cmd, &vha->qla_cmd_list, cmd_list) {
+		uint32_t cmd_key;
+		uint32_t cmd_lun;
+
+		cmd_key = sid_to_key(cmd->atio.u.isp24.fcp_hdr.s_id);
+		cmd_lun = scsilun_to_int(
+			(struct scsi_lun *)&cmd->atio.u.isp24.fcp_cmnd.lun);
+		if (cmd_key == key && cmd_lun == lun)
+			cmd->state = QLA_TGT_STATE_ABORTED;
+	}
+	spin_unlock(&vha->cmd_list_lock);
+}
+
 /* ha->hardware_lock supposed to be held on entry */
 static int __qlt_24xx_handle_abts(struct scsi_qla_host *vha,
 	struct abts_recv_from_24xx *abts, struct qla_tgt_sess *sess)
@@ -1199,8 +1381,19 @@ static int __qlt_24xx_handle_abts(struct scsi_qla_host *vha,
 	}
 	spin_unlock(&se_sess->sess_cmd_lock);
 
-	if (!found_lun)
-		return -ENOENT;
+	/* cmd not in LIO lists, look in qla list */
+	if (!found_lun) {
+		if (abort_cmd_for_tag(vha, abts->exchange_addr_to_abort)) {
+			/* send TASK_ABORT response immediately */
+			qlt_24xx_send_abts_resp(vha, abts, FCP_TMF_CMPL, false);
+			return 0;
+		} else {
+			ql_dbg(ql_dbg_tgt_mgt, vha, 0xf081,
+			    "unable to find cmd in driver or LIO for tag 0x%x\n",
+			    abts->exchange_addr_to_abort);
+			return -ENOENT;
+		}
+	}
 
 	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf00f,
 	    "qla_target(%d): task abort (tag=%d)\n",
@@ -1284,6 +1477,11 @@ static void qlt_24xx_handle_abts(struct scsi_qla_host *vha,
 		return;
 	}
 
+	if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) {
+		qlt_24xx_send_abts_resp(vha, abts, FCP_TMF_REJECTED, false);
+		return;
+	}
+
 	rc = __qlt_24xx_handle_abts(vha, abts, sess);
 	if (rc != 0) {
 		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf054,
@@ -1726,20 +1924,6 @@ static int qlt_pre_xmit_response(struct qla_tgt_cmd *cmd,
 	struct qla_hw_data *ha = vha->hw;
 	struct se_cmd *se_cmd = &cmd->se_cmd;
 
-	if (unlikely(cmd->aborted)) {
-		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf014,
-		       "qla_target(%d): terminating exchange for aborted cmd=%p (se_cmd=%p, tag=%lld)",
-		       vha->vp_idx, cmd, se_cmd, se_cmd->tag);
-
-		cmd->state = QLA_TGT_STATE_ABORTED;
-		cmd->cmd_flags |= BIT_6;
-
-		qlt_send_term_exchange(vha, cmd, &cmd->atio, 0);
-
-		/* !! At this point cmd could be already freed !! */
-		return QLA_TGT_PRE_XMIT_RESP_CMD_ABORTED;
-	}
-
 	prm->cmd = cmd;
 	prm->tgt = tgt;
 	prm->rq_result = scsi_status;
@@ -2301,6 +2485,19 @@ int qlt_xmit_response(struct qla_tgt_cmd *cmd, int xmit_type,
 	unsigned long flags = 0;
 	int res;
 
+	spin_lock_irqsave(&ha->hardware_lock, flags);
+	if (cmd->sess && cmd->sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) {
+		cmd->state = QLA_TGT_STATE_PROCESSED;
+		if (cmd->sess->logout_completed)
+			/* no need to terminate. FW already freed exchange. */
+			qlt_abort_cmd_on_host_reset(cmd->vha, cmd);
+		else
+			qlt_send_term_exchange(vha, cmd, &cmd->atio, 1);
+		spin_unlock_irqrestore(&ha->hardware_lock, flags);
+		return 0;
+	}
+	spin_unlock_irqrestore(&ha->hardware_lock, flags);
+
 	memset(&prm, 0, sizeof(prm));
 	qlt_check_srr_debug(cmd, &xmit_type);
 
@@ -2313,9 +2510,6 @@ int qlt_xmit_response(struct qla_tgt_cmd *cmd, int xmit_type,
 	res = qlt_pre_xmit_response(cmd, &prm, xmit_type, scsi_status,
 	    &full_req_cnt);
 	if (unlikely(res != 0)) {
-		if (res == QLA_TGT_PRE_XMIT_RESP_CMD_ABORTED)
-			return 0;
-
 		return res;
 	}
 
@@ -2345,9 +2539,10 @@ int qlt_xmit_response(struct qla_tgt_cmd *cmd, int xmit_type,
 		res = qlt_build_ctio_crc2_pkt(&prm, vha);
 	else
 		res = qlt_24xx_build_ctio_pkt(&prm, vha);
-	if (unlikely(res != 0))
+	if (unlikely(res != 0)) {
+		vha->req->cnt += full_req_cnt;
 		goto out_unmap_unlock;
-
+	}
 
 	pkt = (struct ctio7_to_24xx *)prm.pkt;
 
@@ -2461,7 +2656,8 @@ int qlt_rdy_to_xfer(struct qla_tgt_cmd *cmd)
 
 	spin_lock_irqsave(&ha->hardware_lock, flags);
 
-	if (qla2x00_reset_active(vha) || cmd->reset_count != ha->chip_reset) {
+	if (qla2x00_reset_active(vha) || (cmd->reset_count != ha->chip_reset) ||
+	    (cmd->sess && cmd->sess->deleted == QLA_SESS_DELETION_IN_PROGRESS)) {
 		/*
 		 * Either a chip reset is active or this request was from
 		 * previous life, just abort the processing.
@@ -2485,8 +2681,11 @@ int qlt_rdy_to_xfer(struct qla_tgt_cmd *cmd)
 	else
 		res = qlt_24xx_build_ctio_pkt(&prm, vha);
 
-	if (unlikely(res != 0))
+	if (unlikely(res != 0)) {
+		vha->req->cnt += prm.req_cnt;
 		goto out_unlock_free_unmap;
+	}
+
 	pkt = (struct ctio7_to_24xx *)prm.pkt;
 	pkt->u.status0.flags |= __constant_cpu_to_le16(CTIO7_FLAGS_DATA_OUT |
 	    CTIO7_FLAGS_STATUS_MODE_0);
@@ -2651,6 +2850,89 @@ out:
 
 /* If hardware_lock held on entry, might drop it, then reaquire */
 /* This function sends the appropriate CTIO to ISP 2xxx or 24xx */
+static int __qlt_send_term_imm_notif(struct scsi_qla_host *vha,
+	struct imm_ntfy_from_isp *ntfy)
+{
+	struct nack_to_isp *nack;
+	struct qla_hw_data *ha = vha->hw;
+	request_t *pkt;
+	int ret = 0;
+
+	ql_dbg(ql_dbg_tgt_tmr, vha, 0xe01c,
+	    "Sending TERM ELS CTIO (ha=%p)\n", ha);
+
+	pkt = (request_t *)qla2x00_alloc_iocbs_ready(vha, NULL);
+	if (pkt == NULL) {
+		ql_dbg(ql_dbg_tgt, vha, 0xe080,
+		    "qla_target(%d): %s failed: unable to allocate "
+		    "request packet\n", vha->vp_idx, __func__);
+		return -ENOMEM;
+	}
+
+	pkt->entry_type = NOTIFY_ACK_TYPE;
+	pkt->entry_count = 1;
+	pkt->handle = QLA_TGT_SKIP_HANDLE | CTIO_COMPLETION_HANDLE_MARK;
+
+	nack = (struct nack_to_isp *)pkt;
+	nack->ox_id = ntfy->ox_id;
+
+	nack->u.isp24.nport_handle = ntfy->u.isp24.nport_handle;
+	if (le16_to_cpu(ntfy->u.isp24.status) == IMM_NTFY_ELS) {
+		nack->u.isp24.flags = ntfy->u.isp24.flags &
+			__constant_cpu_to_le32(NOTIFY24XX_FLAGS_PUREX_IOCB);
+	}
+
+	/* terminate */
+	nack->u.isp24.flags |=
+		__constant_cpu_to_le16(NOTIFY_ACK_FLAGS_TERMINATE);
+
+	nack->u.isp24.srr_rx_id = ntfy->u.isp24.srr_rx_id;
+	nack->u.isp24.status = ntfy->u.isp24.status;
+	nack->u.isp24.status_subcode = ntfy->u.isp24.status_subcode;
+	nack->u.isp24.fw_handle = ntfy->u.isp24.fw_handle;
+	nack->u.isp24.exchange_address = ntfy->u.isp24.exchange_address;
+	nack->u.isp24.srr_rel_offs = ntfy->u.isp24.srr_rel_offs;
+	nack->u.isp24.srr_ui = ntfy->u.isp24.srr_ui;
+	nack->u.isp24.vp_index = ntfy->u.isp24.vp_index;
+
+	qla2x00_start_iocbs(vha, vha->req);
+	return ret;
+}
+
+static void qlt_send_term_imm_notif(struct scsi_qla_host *vha,
+	struct imm_ntfy_from_isp *imm, int ha_locked)
+{
+	unsigned long flags = 0;
+	int rc;
+
+	if (qlt_issue_marker(vha, ha_locked) < 0)
+		return;
+
+	if (ha_locked) {
+		rc = __qlt_send_term_imm_notif(vha, imm);
+
+#if 0	/* Todo  */
+		if (rc == -ENOMEM)
+			qlt_alloc_qfull_cmd(vha, imm, 0, 0);
+#endif
+		goto done;
+	}
+
+	spin_lock_irqsave(&vha->hw->hardware_lock, flags);
+	rc = __qlt_send_term_imm_notif(vha, imm);
+
+#if 0	/* Todo */
+	if (rc == -ENOMEM)
+		qlt_alloc_qfull_cmd(vha, imm, 0, 0);
+#endif
+
+done:
+	if (!ha_locked)
+		spin_unlock_irqrestore(&vha->hw->hardware_lock, flags);
+}
+
+/* If hardware_lock held on entry, might drop it, then reaquire */
+/* This function sends the appropriate CTIO to ISP 2xxx or 24xx */
 static int __qlt_send_term_exchange(struct scsi_qla_host *vha,
 	struct qla_tgt_cmd *cmd,
 	struct atio_from_isp *atio)
@@ -2715,7 +2997,7 @@ static int __qlt_send_term_exchange(struct scsi_qla_host *vha,
 static void qlt_send_term_exchange(struct scsi_qla_host *vha,
 	struct qla_tgt_cmd *cmd, struct atio_from_isp *atio, int ha_locked)
 {
-	unsigned long flags;
+	unsigned long flags = 0;
 	int rc;
 
 	if (qlt_issue_marker(vha, ha_locked) < 0)
@@ -2731,17 +3013,18 @@ static void qlt_send_term_exchange(struct scsi_qla_host *vha,
 	rc = __qlt_send_term_exchange(vha, cmd, atio);
 	if (rc == -ENOMEM)
 		qlt_alloc_qfull_cmd(vha, atio, 0, 0);
-	spin_unlock_irqrestore(&vha->hw->hardware_lock, flags);
 
 done:
 	if (cmd && ((cmd->state != QLA_TGT_STATE_ABORTED) ||
 	    !cmd->cmd_sent_to_fw)) {
-		if (!ha_locked && !in_interrupt())
-			msleep(250); /* just in case */
-
-		qlt_unmap_sg(vha, cmd);
+		if (cmd->sg_mapped)
+			qlt_unmap_sg(vha, cmd);
 		vha->hw->tgt.tgt_ops->free_cmd(cmd);
 	}
+
+	if (!ha_locked)
+		spin_unlock_irqrestore(&vha->hw->hardware_lock, flags);
+
 	return;
 }
 
@@ -2792,6 +3075,24 @@ static void qlt_chk_exch_leak_thresh_hold(struct scsi_qla_host *vha)
 
 }
 
+void qlt_abort_cmd(struct qla_tgt_cmd *cmd)
+{
+	struct qla_tgt *tgt = cmd->tgt;
+	struct scsi_qla_host *vha = tgt->vha;
+	struct se_cmd *se_cmd = &cmd->se_cmd;
+
+	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf014,
+	    "qla_target(%d): terminating exchange for aborted cmd=%p "
+	    "(se_cmd=%p, tag=%llu)", vha->vp_idx, cmd, &cmd->se_cmd,
+	    se_cmd->tag);
+
+	cmd->state = QLA_TGT_STATE_ABORTED;
+	cmd->cmd_flags |= BIT_6;
+
+	qlt_send_term_exchange(vha, cmd, &cmd->atio, 0);
+}
+EXPORT_SYMBOL(qlt_abort_cmd);
+
 void qlt_free_cmd(struct qla_tgt_cmd *cmd)
 {
 	struct qla_tgt_sess *sess = cmd->sess;
@@ -3015,7 +3316,7 @@ qlt_abort_cmd_on_host_reset(struct scsi_qla_host *vha, struct qla_tgt_cmd *cmd)
 		dump_stack();
 	}
 
-	cmd->cmd_flags |= BIT_12;
+	cmd->cmd_flags |= BIT_17;
 	ha->tgt.tgt_ops->free_cmd(cmd);
 }
 
@@ -3177,7 +3478,7 @@ static void qlt_do_ctio_completion(struct scsi_qla_host *vha, uint32_t handle,
 skip_term:
 
 	if (cmd->state == QLA_TGT_STATE_PROCESSED) {
-		;
+		cmd->cmd_flags |= BIT_12;
 	} else if (cmd->state == QLA_TGT_STATE_NEED_DATA) {
 		int rx_status = 0;
 
@@ -3191,9 +3492,11 @@ skip_term:
 		ha->tgt.tgt_ops->handle_data(cmd);
 		return;
 	} else if (cmd->state == QLA_TGT_STATE_ABORTED) {
+		cmd->cmd_flags |= BIT_18;
 		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf01e,
 		  "Aborted command %p (tag %lld) finished\n", cmd, se_cmd->tag);
 	} else {
+		cmd->cmd_flags |= BIT_19;
 		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf05c,
 		    "qla_target(%d): A command in state (%d) should "
 		    "not return a CTIO complete\n", vha->vp_idx, cmd->state);
@@ -3205,7 +3508,6 @@ skip_term:
 		dump_stack();
 	}
 
-
 	ha->tgt.tgt_ops->free_cmd(cmd);
 }
 
@@ -3263,6 +3565,13 @@ static void __qlt_do_work(struct qla_tgt_cmd *cmd)
 	if (tgt->tgt_stop)
 		goto out_term;
 
+	if (cmd->state == QLA_TGT_STATE_ABORTED) {
+		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf082,
+		    "cmd with tag %u is aborted\n",
+		    cmd->atio.u.isp24.exchange_addr);
+		goto out_term;
+	}
+
 	cdb = &atio->u.isp24.fcp_cmnd.cdb[0];
 	cmd->se_cmd.tag = atio->u.isp24.exchange_addr;
 	cmd->unpacked_lun = scsilun_to_int(
@@ -3316,6 +3625,12 @@ out_term:
 static void qlt_do_work(struct work_struct *work)
 {
 	struct qla_tgt_cmd *cmd = container_of(work, struct qla_tgt_cmd, work);
+	scsi_qla_host_t *vha = cmd->vha;
+	unsigned long flags;
+
+	spin_lock_irqsave(&vha->cmd_list_lock, flags);
+	list_del(&cmd->cmd_list);
+	spin_unlock_irqrestore(&vha->cmd_list_lock, flags);
 
 	__qlt_do_work(cmd);
 }
@@ -3345,6 +3660,11 @@ static struct qla_tgt_cmd *qlt_get_tag(scsi_qla_host_t *vha,
 	cmd->loop_id = sess->loop_id;
 	cmd->conf_compl_supported = sess->conf_compl_supported;
 
+	cmd->cmd_flags = 0;
+	cmd->jiffies_at_alloc = get_jiffies_64();
+
+	cmd->reset_count = vha->hw->chip_reset;
+
 	return cmd;
 }
 
@@ -3362,14 +3682,25 @@ static void qlt_create_sess_from_atio(struct work_struct *work)
 	unsigned long flags;
 	uint8_t *s_id = op->atio.u.isp24.fcp_hdr.s_id;
 
+	spin_lock_irqsave(&vha->cmd_list_lock, flags);
+	list_del(&op->cmd_list);
+	spin_unlock_irqrestore(&vha->cmd_list_lock, flags);
+
+	if (op->aborted) {
+		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf083,
+		    "sess_op with tag %u is aborted\n",
+		    op->atio.u.isp24.exchange_addr);
+		goto out_term;
+	}
+
 	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf022,
-		"qla_target(%d): Unable to find wwn login"
-		" (s_id %x:%x:%x), trying to create it manually\n",
-		vha->vp_idx, s_id[0], s_id[1], s_id[2]);
+	    "qla_target(%d): Unable to find wwn login"
+	    " (s_id %x:%x:%x), trying to create it manually\n",
+	    vha->vp_idx, s_id[0], s_id[1], s_id[2]);
 
 	if (op->atio.u.raw.entry_count > 1) {
 		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf023,
-		        "Dropping multy entry atio %p\n", &op->atio);
+		    "Dropping multy entry atio %p\n", &op->atio);
 		goto out_term;
 	}
 
@@ -3434,10 +3765,25 @@ static int qlt_handle_cmd_for_atio(struct scsi_qla_host *vha,
 
 		memcpy(&op->atio, atio, sizeof(*atio));
 		op->vha = vha;
+
+		spin_lock(&vha->cmd_list_lock);
+		list_add_tail(&op->cmd_list, &vha->qla_sess_op_cmd_list);
+		spin_unlock(&vha->cmd_list_lock);
+
 		INIT_WORK(&op->work, qlt_create_sess_from_atio);
 		queue_work(qla_tgt_wq, &op->work);
 		return 0;
 	}
+
+	/* Another WWN used to have our s_id. Our PLOGI scheduled its
+	 * session deletion, but it's still in sess_del_work wq */
+	if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) {
+		ql_dbg(ql_dbg_io, vha, 0x3061,
+		    "New command while old session %p is being deleted\n",
+		    sess);
+		return -EFAULT;
+	}
+
 	/*
 	 * Do kref_get() before returning + dropping qla_hw_data->hardware_lock.
 	 */
@@ -3451,13 +3797,13 @@ static int qlt_handle_cmd_for_atio(struct scsi_qla_host *vha,
 		return -ENOMEM;
 	}
 
-	cmd->cmd_flags = 0;
-	cmd->jiffies_at_alloc = get_jiffies_64();
-
-	cmd->reset_count = vha->hw->chip_reset;
-
 	cmd->cmd_in_wq = 1;
 	cmd->cmd_flags |= BIT_0;
+
+	spin_lock(&vha->cmd_list_lock);
+	list_add_tail(&cmd->cmd_list, &vha->qla_cmd_list);
+	spin_unlock(&vha->cmd_list_lock);
+
 	INIT_WORK(&cmd->work, qlt_do_work);
 	queue_work(qla_tgt_wq, &cmd->work);
 	return 0;
@@ -3471,6 +3817,7 @@ static int qlt_issue_task_mgmt(struct qla_tgt_sess *sess, uint32_t lun,
 	struct scsi_qla_host *vha = sess->vha;
 	struct qla_hw_data *ha = vha->hw;
 	struct qla_tgt_mgmt_cmd *mcmd;
+	struct atio_from_isp *a = (struct atio_from_isp *)iocb;
 	int res;
 	uint8_t tmr_func;
 
@@ -3511,6 +3858,7 @@ static int qlt_issue_task_mgmt(struct qla_tgt_sess *sess, uint32_t lun,
 		ql_dbg(ql_dbg_tgt_tmr, vha, 0x10002,
 		    "qla_target(%d): LUN_RESET received\n", sess->vha->vp_idx);
 		tmr_func = TMR_LUN_RESET;
+		abort_cmds_for_lun(vha, lun, a->u.isp24.fcp_hdr.s_id);
 		break;
 
 	case QLA_TGT_CLEAR_TS:
@@ -3599,6 +3947,9 @@ static int qlt_handle_task_mgmt(struct scsi_qla_host *vha, void *iocb)
 		    sizeof(struct atio_from_isp));
 	}
 
+	if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS)
+		return -EFAULT;
+
 	return qlt_issue_task_mgmt(sess, unpacked_lun, fn, iocb, 0);
 }
 
@@ -3664,22 +4015,280 @@ static int qlt_abort_task(struct scsi_qla_host *vha,
 	return __qlt_abort_task(vha, iocb, sess);
 }
 
+void qlt_logo_completion_handler(fc_port_t *fcport, int rc)
+{
+	if (fcport->tgt_session) {
+		if (rc != MBS_COMMAND_COMPLETE) {
+			ql_dbg(ql_dbg_tgt_mgt, fcport->vha, 0xf093,
+				"%s: se_sess %p / sess %p from"
+				" port %8phC loop_id %#04x s_id %02x:%02x:%02x"
+				" LOGO failed: %#x\n",
+				__func__,
+				fcport->tgt_session->se_sess,
+				fcport->tgt_session,
+				fcport->port_name, fcport->loop_id,
+				fcport->d_id.b.domain, fcport->d_id.b.area,
+				fcport->d_id.b.al_pa, rc);
+		}
+
+		fcport->tgt_session->logout_completed = 1;
+	}
+}
+
+static void qlt_swap_imm_ntfy_iocb(struct imm_ntfy_from_isp *a,
+    struct imm_ntfy_from_isp *b)
+{
+	struct imm_ntfy_from_isp tmp;
+	memcpy(&tmp, a, sizeof(struct imm_ntfy_from_isp));
+	memcpy(a, b, sizeof(struct imm_ntfy_from_isp));
+	memcpy(b, &tmp, sizeof(struct imm_ntfy_from_isp));
+}
+
+/*
+* ha->hardware_lock supposed to be held on entry (to protect tgt->sess_list)
+*
+* Schedules sessions with matching port_id/loop_id but different wwn for
+* deletion. Returns existing session with matching wwn if present.
+* Null otherwise.
+*/
+static struct qla_tgt_sess *
+qlt_find_sess_invalidate_other(struct qla_tgt *tgt, uint64_t wwn,
+    port_id_t port_id, uint16_t loop_id)
+{
+	struct qla_tgt_sess *sess = NULL, *other_sess;
+	uint64_t other_wwn;
+
+	list_for_each_entry(other_sess, &tgt->sess_list, sess_list_entry) {
+
+		other_wwn = wwn_to_u64(other_sess->port_name);
+
+		if (wwn == other_wwn) {
+			WARN_ON(sess);
+			sess = other_sess;
+			continue;
+		}
+
+		/* find other sess with nport_id collision */
+		if (port_id.b24 == other_sess->s_id.b24) {
+			if (loop_id != other_sess->loop_id) {
+				ql_dbg(ql_dbg_tgt_tmr, tgt->vha, 0x1000c,
+				    "Invalidating sess %p loop_id %d wwn %llx.\n",
+				    other_sess, other_sess->loop_id, other_wwn);
+
+				/*
+				 * logout_on_delete is set by default, but another
+				 * session that has the same s_id/loop_id combo
+				 * might have cleared it when requested this session
+				 * deletion, so don't touch it
+				 */
+				qlt_schedule_sess_for_deletion(other_sess, true);
+			} else {
+				/*
+				 * Another wwn used to have our s_id/loop_id
+				 * combo - kill the session, but don't log out
+				 */
+				sess->logout_on_delete = 0;
+				qlt_schedule_sess_for_deletion(other_sess,
+				    true);
+			}
+			continue;
+		}
+
+		/* find other sess with nport handle collision */
+		if (loop_id == other_sess->loop_id) {
+			ql_dbg(ql_dbg_tgt_tmr, tgt->vha, 0x1000d,
+			       "Invalidating sess %p loop_id %d wwn %llx.\n",
+			       other_sess, other_sess->loop_id, other_wwn);
+
+			/* Same loop_id but different s_id
+			 * Ok to kill and logout */
+			qlt_schedule_sess_for_deletion(other_sess, true);
+		}
+	}
+
+	return sess;
+}
+
+/* Abort any commands for this s_id waiting on qla_tgt_wq workqueue */
+static int abort_cmds_for_s_id(struct scsi_qla_host *vha, port_id_t *s_id)
+{
+	struct qla_tgt_sess_op *op;
+	struct qla_tgt_cmd *cmd;
+	uint32_t key;
+	int count = 0;
+
+	key = (((u32)s_id->b.domain << 16) |
+	       ((u32)s_id->b.area   <<  8) |
+	       ((u32)s_id->b.al_pa));
+
+	spin_lock(&vha->cmd_list_lock);
+	list_for_each_entry(op, &vha->qla_sess_op_cmd_list, cmd_list) {
+		uint32_t op_key = sid_to_key(op->atio.u.isp24.fcp_hdr.s_id);
+		if (op_key == key) {
+			op->aborted = true;
+			count++;
+		}
+	}
+	list_for_each_entry(cmd, &vha->qla_cmd_list, cmd_list) {
+		uint32_t cmd_key = sid_to_key(cmd->atio.u.isp24.fcp_hdr.s_id);
+		if (cmd_key == key) {
+			cmd->state = QLA_TGT_STATE_ABORTED;
+			count++;
+		}
+	}
+	spin_unlock(&vha->cmd_list_lock);
+
+	return count;
+}
+
 /*
  * ha->hardware_lock supposed to be held on entry. Might drop it, then reaquire
  */
 static int qlt_24xx_handle_els(struct scsi_qla_host *vha,
 	struct imm_ntfy_from_isp *iocb)
 {
+	struct qla_tgt *tgt = vha->vha_tgt.qla_tgt;
+	struct qla_hw_data *ha = vha->hw;
+	struct qla_tgt_sess *sess = NULL;
+	uint64_t wwn;
+	port_id_t port_id;
+	uint16_t loop_id;
+	uint16_t wd3_lo;
 	int res = 0;
 
+	wwn = wwn_to_u64(iocb->u.isp24.port_name);
+
+	port_id.b.domain = iocb->u.isp24.port_id[2];
+	port_id.b.area   = iocb->u.isp24.port_id[1];
+	port_id.b.al_pa  = iocb->u.isp24.port_id[0];
+	port_id.b.rsvd_1 = 0;
+
+	loop_id = le16_to_cpu(iocb->u.isp24.nport_handle);
+
 	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf026,
 	    "qla_target(%d): Port ID: 0x%3phC ELS opcode: 0x%02x\n",
 	    vha->vp_idx, iocb->u.isp24.port_id, iocb->u.isp24.status_subcode);
 
+	/* res = 1 means ack at the end of thread
+	 * res = 0 means ack async/later.
+	 */
 	switch (iocb->u.isp24.status_subcode) {
 	case ELS_PLOGI:
-	case ELS_FLOGI:
+
+		/* Mark all stale commands in qla_tgt_wq for deletion */
+		abort_cmds_for_s_id(vha, &port_id);
+
+		if (wwn)
+			sess = qlt_find_sess_invalidate_other(tgt, wwn,
+			    port_id, loop_id);
+
+		if (!sess || IS_SW_RESV_ADDR(sess->s_id)) {
+			res = 1;
+			break;
+		}
+
+		if (sess->plogi_ack_needed) {
+			/*
+			 * Initiator sent another PLOGI before last PLOGI could
+			 * finish. Swap plogi iocbs and terminate old one
+			 * without acking, new one will get acked when session
+			 * deletion completes.
+			 */
+			ql_log(ql_log_warn, sess->vha, 0xf094,
+			    "sess %p received double plogi.\n", sess);
+
+			qlt_swap_imm_ntfy_iocb(iocb, &sess->tm_iocb);
+
+			qlt_send_term_imm_notif(vha, iocb, 1);
+
+			res = 0;
+			break;
+		}
+
+		res = 0;
+
+		/*
+		 * Save immediate Notif IOCB for Ack when sess is done
+		 * and being deleted.
+		 */
+		memcpy(&sess->tm_iocb, iocb, sizeof(sess->tm_iocb));
+		sess->plogi_ack_needed  = 1;
+
+		 /*
+		  * Under normal circumstances we want to release nport handle
+		  * during LOGO process to avoid nport handle leaks inside FW.
+		  * The exception is when LOGO is done while another PLOGI with
+		  * the same nport handle is waiting as might be the case here.
+		  * Note: there is always a possibily of a race where session
+		  * deletion has already started for other reasons (e.g. ACL
+		  * removal) and now PLOGI arrives:
+		  * 1. if PLOGI arrived in FW after nport handle has been freed,
+		  *    FW must have assigned this PLOGI a new/same handle and we
+		  *    can proceed ACK'ing it as usual when session deletion
+		  *    completes.
+		  * 2. if PLOGI arrived in FW before LOGO with LCF_FREE_NPORT
+		  *    bit reached it, the handle has now been released. We'll
+		  *    get an error when we ACK this PLOGI. Nothing will be sent
+		  *    back to initiator. Initiator should eventually retry
+		  *    PLOGI and situation will correct itself.
+		  */
+		sess->keep_nport_handle = ((sess->loop_id == loop_id) &&
+					   (sess->s_id.b24 == port_id.b24));
+		qlt_schedule_sess_for_deletion(sess, true);
+		break;
+
 	case ELS_PRLI:
+		wd3_lo = le16_to_cpu(iocb->u.isp24.u.prli.wd3_lo);
+
+		if (wwn)
+			sess = qlt_find_sess_invalidate_other(tgt, wwn, port_id,
+			    loop_id);
+
+		if (sess != NULL) {
+			if (sess->deleted) {
+				/*
+				 * Impatient initiator sent PRLI before last
+				 * PLOGI could finish. Will force him to re-try,
+				 * while last one finishes.
+				 */
+				ql_log(ql_log_warn, sess->vha, 0xf095,
+				    "sess %p PRLI received, before plogi ack.\n",
+				    sess);
+				qlt_send_term_imm_notif(vha, iocb, 1);
+				res = 0;
+				break;
+			}
+
+			/*
+			 * This shouldn't happen under normal circumstances,
+			 * since we have deleted the old session during PLOGI
+			 */
+			ql_dbg(ql_dbg_tgt_mgt, vha, 0xf096,
+			    "PRLI (loop_id %#04x) for existing sess %p (loop_id %#04x)\n",
+			    sess->loop_id, sess, iocb->u.isp24.nport_handle);
+
+			sess->local = 0;
+			sess->loop_id = loop_id;
+			sess->s_id = port_id;
+
+			if (wd3_lo & BIT_7)
+				sess->conf_compl_supported = 1;
+
+		}
+		res = 1; /* send notify ack */
+
+		/* Make session global (not used in fabric mode) */
+		if (ha->current_topology != ISP_CFG_F) {
+			set_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags);
+			set_bit(LOCAL_LOOP_UPDATE, &vha->dpc_flags);
+			qla2xxx_wake_dpc(vha);
+		} else {
+			/* todo: else - create sess here. */
+			res = 1; /* send notify ack */
+		}
+
+		break;
+
 	case ELS_LOGO:
 	case ELS_PRLO:
 		res = qlt_reset(vha, iocb, QLA_TGT_NEXUS_LOSS_SESS);
@@ -3697,6 +4306,7 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha,
 		break;
 	}
 
+	case ELS_FLOGI:	/* should never happen */
 	default:
 		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf061,
 		    "qla_target(%d): Unsupported ELS command %x "
@@ -5012,6 +5622,11 @@ static void qlt_abort_work(struct qla_tgt *tgt,
 		if (!sess)
 			goto out_term;
 	} else {
+		if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) {
+			sess = NULL;
+			goto out_term;
+		}
+
 		kref_get(&sess->se_sess->sess_kref);
 	}
 
@@ -5066,6 +5681,11 @@ static void qlt_tmr_work(struct qla_tgt *tgt,
 		if (!sess)
 			goto out_term;
 	} else {
+		if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) {
+			sess = NULL;
+			goto out_term;
+		}
+
 		kref_get(&sess->se_sess->sess_kref);
 	}
 
@@ -5552,6 +6172,7 @@ qlt_24xx_process_atio_queue(struct scsi_qla_host *vha)
 
 	/* Adjust ring index */
 	WRT_REG_DWORD(ISP_ATIO_Q_OUT(vha), ha->tgt.atio_ring_index);
+	RD_REG_DWORD_RELAXED(ISP_ATIO_Q_OUT(vha));
 }
 
 void
@@ -5793,7 +6414,7 @@ qlt_probe_one_stage1(struct scsi_qla_host *base_vha, struct qla_hw_data *ha)
 	if (!QLA_TGT_MODE_ENABLED())
 		return;
 
-	if  (ha->mqenable || IS_QLA83XX(ha)) {
+	if  (ha->mqenable || IS_QLA83XX(ha) || IS_QLA27XX(ha)) {
 		ISP_ATIO_Q_IN(base_vha) = &ha->mqiobase->isp25mq.atio_q_in;
 		ISP_ATIO_Q_OUT(base_vha) = &ha->mqiobase->isp25mq.atio_q_out;
 	} else {
diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h
index 985d76dd706b..bca584ae45b7 100644
--- a/drivers/scsi/qla2xxx/qla_target.h
+++ b/drivers/scsi/qla2xxx/qla_target.h
@@ -167,7 +167,24 @@ struct imm_ntfy_from_isp {
 			uint32_t srr_rel_offs;
 			uint16_t srr_ui;
 			uint16_t srr_ox_id;
-			uint8_t  reserved_4[19];
+			union {
+				struct {
+					uint8_t node_name[8];
+				} plogi; /* PLOGI/ADISC/PDISC */
+				struct {
+					/* PRLI word 3 bit 0-15 */
+					uint16_t wd3_lo;
+					uint8_t resv0[6];
+				} prli;
+				struct {
+					uint8_t port_id[3];
+					uint8_t resv1;
+					uint16_t nport_handle;
+					uint16_t resv2;
+				} req_els;
+			} u;
+			uint8_t port_name[8];
+			uint8_t resv3[3];
 			uint8_t  vp_index;
 			uint32_t reserved_5;
 			uint8_t  port_id[3];
@@ -234,6 +251,7 @@ struct nack_to_isp {
 	uint8_t  reserved[2];
 	uint16_t ox_id;
 } __packed;
+#define NOTIFY_ACK_FLAGS_TERMINATE	BIT_3
 #define NOTIFY_ACK_SRR_FLAGS_ACCEPT	0
 #define NOTIFY_ACK_SRR_FLAGS_REJECT	1
 
@@ -790,13 +808,6 @@ int qla2x00_wait_for_hba_online(struct scsi_qla_host *);
 #define	FC_TM_REJECT                4
 #define FC_TM_FAILED                5
 
-/*
- * Error code of qlt_pre_xmit_response() meaning that cmd's exchange was
- * terminated, so no more actions is needed and success should be returned
- * to target.
- */
-#define QLA_TGT_PRE_XMIT_RESP_CMD_ABORTED	0x1717
-
 #if (BITS_PER_LONG > 32) || defined(CONFIG_HIGHMEM64G)
 #define pci_dma_lo32(a) (a & 0xffffffff)
 #define pci_dma_hi32(a) ((((a) >> 16)>>16) & 0xffffffff)
@@ -874,6 +885,15 @@ struct qla_tgt_sess_op {
 	struct scsi_qla_host *vha;
 	struct atio_from_isp atio;
 	struct work_struct work;
+	struct list_head cmd_list;
+	bool aborted;
+};
+
+enum qla_sess_deletion {
+	QLA_SESS_DELETION_NONE		= 0,
+	QLA_SESS_DELETION_PENDING	= 1, /* hopefully we can get rid of
+					      * this one */
+	QLA_SESS_DELETION_IN_PROGRESS	= 2,
 };
 
 /*
@@ -884,8 +904,15 @@ struct qla_tgt_sess {
 	port_id_t s_id;
 
 	unsigned int conf_compl_supported:1;
-	unsigned int deleted:1;
+	unsigned int deleted:2;
 	unsigned int local:1;
+	unsigned int logout_on_delete:1;
+	unsigned int plogi_ack_needed:1;
+	unsigned int keep_nport_handle:1;
+
+	unsigned char logout_completed;
+
+	int generation;
 
 	struct se_session *se_sess;
 	struct scsi_qla_host *vha;
@@ -897,6 +924,10 @@ struct qla_tgt_sess {
 
 	uint8_t port_name[WWN_SIZE];
 	struct work_struct free_work;
+
+	union {
+		struct imm_ntfy_from_isp tm_iocb;
+	};
 };
 
 struct qla_tgt_cmd {
@@ -912,7 +943,6 @@ struct qla_tgt_cmd {
 	unsigned int conf_compl_supported:1;
 	unsigned int sg_mapped:1;
 	unsigned int free_sg:1;
-	unsigned int aborted:1; /* Needed in case of SRR */
 	unsigned int write_data_transferred:1;
 	unsigned int ctx_dsd_alloced:1;
 	unsigned int q_full:1;
@@ -961,6 +991,9 @@ struct qla_tgt_cmd {
 	 * BIT_14 - Back end data received/sent.
 	 * BIT_15 - SRR prepare ctio
 	 * BIT_16 - complete free
+	 * BIT_17 - flush - qlt_abort_cmd_on_host_reset
+	 * BIT_18 - completion w/abort status
+	 * BIT_19 - completion w/unknown status
 	 */
 	uint32_t cmd_flags;
 };
@@ -1026,6 +1059,10 @@ struct qla_tgt_srr_ctio {
 	struct qla_tgt_cmd *cmd;
 };
 
+/* Check for Switch reserved address */
+#define IS_SW_RESV_ADDR(_s_id) \
+	((_s_id.b.domain == 0xff) && (_s_id.b.area == 0xfc))
+
 #define QLA_TGT_XMIT_DATA		1
 #define QLA_TGT_XMIT_STATUS		2
 #define QLA_TGT_XMIT_ALL		(QLA_TGT_XMIT_STATUS|QLA_TGT_XMIT_DATA)
@@ -1043,7 +1080,7 @@ extern int qlt_lport_register(void *, u64, u64, u64,
 extern void qlt_lport_deregister(struct scsi_qla_host *);
 extern void qlt_unreg_sess(struct qla_tgt_sess *);
 extern void qlt_fc_port_added(struct scsi_qla_host *, fc_port_t *);
-extern void qlt_fc_port_deleted(struct scsi_qla_host *, fc_port_t *);
+extern void qlt_fc_port_deleted(struct scsi_qla_host *, fc_port_t *, int);
 extern int __init qlt_init(void);
 extern void qlt_exit(void);
 extern void qlt_update_vp_map(struct scsi_qla_host *, int);
@@ -1073,12 +1110,23 @@ static inline void qla_reverse_ini_mode(struct scsi_qla_host *ha)
 		ha->host->active_mode |= MODE_INITIATOR;
 }
 
+static inline uint32_t sid_to_key(const uint8_t *s_id)
+{
+	uint32_t key;
+
+	key = (((unsigned long)s_id[0] << 16) |
+	       ((unsigned long)s_id[1] << 8) |
+	       (unsigned long)s_id[2]);
+	return key;
+}
+
 /*
  * Exported symbols from qla_target.c LLD logic used by qla2xxx code..
  */
 extern void qlt_response_pkt_all_vps(struct scsi_qla_host *, response_t *);
 extern int qlt_rdy_to_xfer(struct qla_tgt_cmd *);
 extern int qlt_xmit_response(struct qla_tgt_cmd *, int, uint8_t);
+extern void qlt_abort_cmd(struct qla_tgt_cmd *);
 extern void qlt_xmit_tm_rsp(struct qla_tgt_mgmt_cmd *);
 extern void qlt_free_mcmd(struct qla_tgt_mgmt_cmd *);
 extern void qlt_free_cmd(struct qla_tgt_cmd *cmd);
@@ -1109,5 +1157,7 @@ extern void qlt_stop_phase2(struct qla_tgt *);
 extern irqreturn_t qla83xx_msix_atio_q(int, void *);
 extern void qlt_83xx_iospace_config(struct qla_hw_data *);
 extern int qlt_free_qfull_cmds(struct scsi_qla_host *);
+extern void qlt_logo_completion_handler(fc_port_t *, int);
+extern void qlt_do_generation_tick(struct scsi_qla_host *, int *);
 
 #endif /* __QLA_TARGET_H */
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index d9a8c6084346..9224a06646e6 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -374,7 +374,7 @@ static int tcm_qla2xxx_write_pending(struct se_cmd *se_cmd)
 {
 	struct qla_tgt_cmd *cmd = container_of(se_cmd,
 				struct qla_tgt_cmd, se_cmd);
-
+	cmd->cmd_flags |= BIT_3;
 	cmd->bufflen = se_cmd->data_length;
 	cmd->dma_data_direction = target_reverse_dma_direction(se_cmd);
 
@@ -405,7 +405,7 @@ static int tcm_qla2xxx_write_pending_status(struct se_cmd *se_cmd)
 	    se_cmd->t_state == TRANSPORT_COMPLETE_QF_WP) {
 		spin_unlock_irqrestore(&se_cmd->t_state_lock, flags);
 		wait_for_completion_timeout(&se_cmd->t_transport_stop_comp,
-						3000);
+					    3 * HZ);
 		return 0;
 	}
 	spin_unlock_irqrestore(&se_cmd->t_state_lock, flags);
@@ -541,12 +541,10 @@ static int tcm_qla2xxx_queue_data_in(struct se_cmd *se_cmd)
 	cmd->cmd_flags |= BIT_4;
 	cmd->bufflen = se_cmd->data_length;
 	cmd->dma_data_direction = target_reverse_dma_direction(se_cmd);
-	cmd->aborted = (se_cmd->transport_state & CMD_T_ABORTED);
 
 	cmd->sg_cnt = se_cmd->t_data_nents;
 	cmd->sg = se_cmd->t_data_sg;
 	cmd->offset = 0;
-	cmd->cmd_flags |= BIT_3;
 
 	cmd->prot_sg_cnt = se_cmd->t_prot_nents;
 	cmd->prot_sg = se_cmd->t_prot_sg;
@@ -571,7 +569,6 @@ static int tcm_qla2xxx_queue_status(struct se_cmd *se_cmd)
 	cmd->sg_cnt = 0;
 	cmd->offset = 0;
 	cmd->dma_data_direction = target_reverse_dma_direction(se_cmd);
-	cmd->aborted = (se_cmd->transport_state & CMD_T_ABORTED);
 	if (cmd->cmd_flags &  BIT_5) {
 		pr_crit("Bit_5 already set for cmd = %p.\n", cmd);
 		dump_stack();
@@ -636,14 +633,7 @@ static void tcm_qla2xxx_aborted_task(struct se_cmd *se_cmd)
 {
 	struct qla_tgt_cmd *cmd = container_of(se_cmd,
 				struct qla_tgt_cmd, se_cmd);
-	struct scsi_qla_host *vha = cmd->vha;
-	struct qla_hw_data *ha = vha->hw;
-
-	if (!cmd->sg_mapped)
-		return;
-
-	pci_unmap_sg(ha->pdev, cmd->sg, cmd->sg_cnt, cmd->dma_data_direction);
-	cmd->sg_mapped = 0;
+	qlt_abort_cmd(cmd);
 }
 
 static void tcm_qla2xxx_clear_sess_lookup(struct tcm_qla2xxx_lport *,
@@ -1149,9 +1139,7 @@ static struct qla_tgt_sess *tcm_qla2xxx_find_sess_by_s_id(
 		return NULL;
 	}
 
-	key = (((unsigned long)s_id[0] << 16) |
-	       ((unsigned long)s_id[1] << 8) |
-	       (unsigned long)s_id[2]);
+	key = sid_to_key(s_id);
 	pr_debug("find_sess_by_s_id: 0x%06x\n", key);
 
 	se_nacl = btree_lookup32(&lport->lport_fcport_map, key);
@@ -1186,9 +1174,7 @@ static void tcm_qla2xxx_set_sess_by_s_id(
 	void *slot;
 	int rc;
 
-	key = (((unsigned long)s_id[0] << 16) |
-	       ((unsigned long)s_id[1] << 8) |
-	       (unsigned long)s_id[2]);
+	key = sid_to_key(s_id);
 	pr_debug("set_sess_by_s_id: %06x\n", key);
 
 	slot = btree_lookup32(&lport->lport_fcport_map, key);
@@ -1544,6 +1530,10 @@ static void tcm_qla2xxx_update_sess(struct qla_tgt_sess *sess, port_id_t s_id,
 	}
 
 	sess->conf_compl_supported = conf_compl_supported;
+
+	/* Reset logout parameters to default */
+	sess->logout_on_delete = 1;
+	sess->keep_nport_handle = 0;
 }
 
 /*
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 106884a5444e..cfadccef045c 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -944,7 +944,7 @@ void scsi_eh_prep_cmnd(struct scsi_cmnd *scmd, struct scsi_eh_save *ses,
 			    scmd->sdb.length);
 		scmd->sdb.table.sgl = &ses->sense_sgl;
 		scmd->sc_data_direction = DMA_FROM_DEVICE;
-		scmd->sdb.table.nents = 1;
+		scmd->sdb.table.nents = scmd->sdb.table.orig_nents = 1;
 		scmd->cmnd[0] = REQUEST_SENSE;
 		scmd->cmnd[4] = scmd->sdb.length;
 		scmd->cmd_len = COMMAND_SIZE(scmd->cmnd[0]);
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index b1a263137a23..448ebdaa3d69 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -583,7 +583,7 @@ static struct scatterlist *scsi_sg_alloc(unsigned int nents, gfp_t gfp_mask)
 
 static void scsi_free_sgtable(struct scsi_data_buffer *sdb, bool mq)
 {
-	if (mq && sdb->table.nents <= SCSI_MAX_SG_SEGMENTS)
+	if (mq && sdb->table.orig_nents <= SCSI_MAX_SG_SEGMENTS)
 		return;
 	__sg_free_table(&sdb->table, SCSI_MAX_SG_SEGMENTS, mq, scsi_sg_free);
 }
@@ -597,8 +597,8 @@ static int scsi_alloc_sgtable(struct scsi_data_buffer *sdb, int nents, bool mq)
 
 	if (mq) {
 		if (nents <= SCSI_MAX_SG_SEGMENTS) {
-			sdb->table.nents = nents;
-			sg_init_table(sdb->table.sgl, sdb->table.nents);
+			sdb->table.nents = sdb->table.orig_nents = nents;
+			sg_init_table(sdb->table.sgl, nents);
 			return 0;
 		}
 		first_chunk = sdb->table.sgl;
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index 4e68b62193ed..cd77a064c772 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -3998,7 +3998,13 @@ get_immediate:
 	}
 
 transport_err:
-	iscsit_take_action_for_connection_exit(conn);
+	/*
+	 * Avoid the normal connection failure code-path if this connection
+	 * is still within LOGIN mode, and iscsi_np process context is
+	 * responsible for cleaning up the early connection failure.
+	 */
+	if (conn->conn_state != TARG_CONN_STATE_IN_LOGIN)
+		iscsit_take_action_for_connection_exit(conn);
 out:
 	return 0;
 }
@@ -4082,7 +4088,7 @@ reject:
 
 int iscsi_target_rx_thread(void *arg)
 {
-	int ret;
+	int ret, rc;
 	u8 buffer[ISCSI_HDR_LEN], opcode;
 	u32 checksum = 0, digest = 0;
 	struct iscsi_conn *conn = arg;
@@ -4092,10 +4098,16 @@ int iscsi_target_rx_thread(void *arg)
 	 * connection recovery / failure event can be triggered externally.
 	 */
 	allow_signal(SIGINT);
+	/*
+	 * Wait for iscsi_post_login_handler() to complete before allowing
+	 * incoming iscsi/tcp socket I/O, and/or failing the connection.
+	 */
+	rc = wait_for_completion_interruptible(&conn->rx_login_comp);
+	if (rc < 0)
+		return 0;
 
 	if (conn->conn_transport->transport_type == ISCSI_INFINIBAND) {
 		struct completion comp;
-		int rc;
 
 		init_completion(&comp);
 		rc = wait_for_completion_interruptible(&comp);
@@ -4532,7 +4544,18 @@ static void iscsit_logout_post_handler_closesession(
 	struct iscsi_conn *conn)
 {
 	struct iscsi_session *sess = conn->sess;
-	int sleep = cmpxchg(&conn->tx_thread_active, true, false);
+	int sleep = 1;
+	/*
+	 * Traditional iscsi/tcp will invoke this logic from TX thread
+	 * context during session logout, so clear tx_thread_active and
+	 * sleep if iscsit_close_connection() has not already occured.
+	 *
+	 * Since iser-target invokes this logic from it's own workqueue,
+	 * always sleep waiting for RX/TX thread shutdown to complete
+	 * within iscsit_close_connection().
+	 */
+	if (conn->conn_transport->transport_type == ISCSI_TCP)
+		sleep = cmpxchg(&conn->tx_thread_active, true, false);
 
 	atomic_set(&conn->conn_logout_remove, 0);
 	complete(&conn->conn_logout_comp);
@@ -4546,7 +4569,10 @@ static void iscsit_logout_post_handler_closesession(
 static void iscsit_logout_post_handler_samecid(
 	struct iscsi_conn *conn)
 {
-	int sleep = cmpxchg(&conn->tx_thread_active, true, false);
+	int sleep = 1;
+
+	if (conn->conn_transport->transport_type == ISCSI_TCP)
+		sleep = cmpxchg(&conn->tx_thread_active, true, false);
 
 	atomic_set(&conn->conn_logout_remove, 0);
 	complete(&conn->conn_logout_comp);
@@ -4765,6 +4791,7 @@ int iscsit_release_sessions_for_tpg(struct iscsi_portal_group *tpg, int force)
 	struct iscsi_session *sess;
 	struct se_portal_group *se_tpg = &tpg->tpg_se_tpg;
 	struct se_session *se_sess, *se_sess_tmp;
+	LIST_HEAD(free_list);
 	int session_count = 0;
 
 	spin_lock_bh(&se_tpg->session_lock);
@@ -4786,14 +4813,17 @@ int iscsit_release_sessions_for_tpg(struct iscsi_portal_group *tpg, int force)
 		}
 		atomic_set(&sess->session_reinstatement, 1);
 		spin_unlock(&sess->conn_lock);
-		spin_unlock_bh(&se_tpg->session_lock);
 
-		iscsit_free_session(sess);
-		spin_lock_bh(&se_tpg->session_lock);
+		list_move_tail(&se_sess->sess_list, &free_list);
+	}
+	spin_unlock_bh(&se_tpg->session_lock);
+
+	list_for_each_entry_safe(se_sess, se_sess_tmp, &free_list, sess_list) {
+		sess = (struct iscsi_session *)se_sess->fabric_sess_ptr;
 
+		iscsit_free_session(sess);
 		session_count++;
 	}
-	spin_unlock_bh(&se_tpg->session_lock);
 
 	pr_debug("Released %d iSCSI Session(s) from Target Portal"
 			" Group: %hu\n", session_count, tpg->tpgt);
diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c
index 3d0fe4ff5590..7e8f65e5448f 100644
--- a/drivers/target/iscsi/iscsi_target_login.c
+++ b/drivers/target/iscsi/iscsi_target_login.c
@@ -82,6 +82,7 @@ static struct iscsi_login *iscsi_login_init_conn(struct iscsi_conn *conn)
 	init_completion(&conn->conn_logout_comp);
 	init_completion(&conn->rx_half_close_comp);
 	init_completion(&conn->tx_half_close_comp);
+	init_completion(&conn->rx_login_comp);
 	spin_lock_init(&conn->cmd_lock);
 	spin_lock_init(&conn->conn_usage_lock);
 	spin_lock_init(&conn->immed_queue_lock);
@@ -644,7 +645,7 @@ static void iscsi_post_login_start_timers(struct iscsi_conn *conn)
 		iscsit_start_nopin_timer(conn);
 }
 
-static int iscsit_start_kthreads(struct iscsi_conn *conn)
+int iscsit_start_kthreads(struct iscsi_conn *conn)
 {
 	int ret = 0;
 
@@ -679,6 +680,7 @@ static int iscsit_start_kthreads(struct iscsi_conn *conn)
 
 	return 0;
 out_tx:
+	send_sig(SIGINT, conn->tx_thread, 1);
 	kthread_stop(conn->tx_thread);
 	conn->tx_thread_active = false;
 out_bitmap:
@@ -689,7 +691,7 @@ out_bitmap:
 	return ret;
 }
 
-int iscsi_post_login_handler(
+void iscsi_post_login_handler(
 	struct iscsi_np *np,
 	struct iscsi_conn *conn,
 	u8 zero_tsih)
@@ -699,7 +701,6 @@ int iscsi_post_login_handler(
 	struct se_session *se_sess = sess->se_sess;
 	struct iscsi_portal_group *tpg = sess->tpg;
 	struct se_portal_group *se_tpg = &tpg->tpg_se_tpg;
-	int rc;
 
 	iscsit_inc_conn_usage_count(conn);
 
@@ -739,10 +740,6 @@ int iscsi_post_login_handler(
 			sess->sess_ops->InitiatorName);
 		spin_unlock_bh(&sess->conn_lock);
 
-		rc = iscsit_start_kthreads(conn);
-		if (rc)
-			return rc;
-
 		iscsi_post_login_start_timers(conn);
 		/*
 		 * Determine CPU mask to ensure connection's RX and TX kthreads
@@ -751,15 +748,20 @@ int iscsi_post_login_handler(
 		iscsit_thread_get_cpumask(conn);
 		conn->conn_rx_reset_cpumask = 1;
 		conn->conn_tx_reset_cpumask = 1;
-
+		/*
+		 * Wakeup the sleeping iscsi_target_rx_thread() now that
+		 * iscsi_conn is in TARG_CONN_STATE_LOGGED_IN state.
+		 */
+		complete(&conn->rx_login_comp);
 		iscsit_dec_conn_usage_count(conn);
+
 		if (stop_timer) {
 			spin_lock_bh(&se_tpg->session_lock);
 			iscsit_stop_time2retain_timer(sess);
 			spin_unlock_bh(&se_tpg->session_lock);
 		}
 		iscsit_dec_session_usage_count(sess);
-		return 0;
+		return;
 	}
 
 	iscsi_set_session_parameters(sess->sess_ops, conn->param_list, 1);
@@ -800,10 +802,6 @@ int iscsi_post_login_handler(
 		" iSCSI Target Portal Group: %hu\n", tpg->nsessions, tpg->tpgt);
 	spin_unlock_bh(&se_tpg->session_lock);
 
-	rc = iscsit_start_kthreads(conn);
-	if (rc)
-		return rc;
-
 	iscsi_post_login_start_timers(conn);
 	/*
 	 * Determine CPU mask to ensure connection's RX and TX kthreads
@@ -812,10 +810,12 @@ int iscsi_post_login_handler(
 	iscsit_thread_get_cpumask(conn);
 	conn->conn_rx_reset_cpumask = 1;
 	conn->conn_tx_reset_cpumask = 1;
-
+	/*
+	 * Wakeup the sleeping iscsi_target_rx_thread() now that
+	 * iscsi_conn is in TARG_CONN_STATE_LOGGED_IN state.
+	 */
+	complete(&conn->rx_login_comp);
 	iscsit_dec_conn_usage_count(conn);
-
-	return 0;
 }
 
 static void iscsi_handle_login_thread_timeout(unsigned long data)
@@ -1380,23 +1380,12 @@ static int __iscsi_target_login_thread(struct iscsi_np *np)
 	if (ret < 0)
 		goto new_sess_out;
 
-	if (!conn->sess) {
-		pr_err("struct iscsi_conn session pointer is NULL!\n");
-		goto new_sess_out;
-	}
-
 	iscsi_stop_login_thread_timer(np);
 
-	if (signal_pending(current))
-		goto new_sess_out;
-
 	if (ret == 1) {
 		tpg_np = conn->tpg_np;
 
-		ret = iscsi_post_login_handler(np, conn, zero_tsih);
-		if (ret < 0)
-			goto new_sess_out;
-
+		iscsi_post_login_handler(np, conn, zero_tsih);
 		iscsit_deaccess_np(np, tpg, tpg_np);
 	}
 
diff --git a/drivers/target/iscsi/iscsi_target_login.h b/drivers/target/iscsi/iscsi_target_login.h
index 1c7358081533..57aa0d0fd820 100644
--- a/drivers/target/iscsi/iscsi_target_login.h
+++ b/drivers/target/iscsi/iscsi_target_login.h
@@ -12,7 +12,8 @@ extern int iscsit_accept_np(struct iscsi_np *, struct iscsi_conn *);
 extern int iscsit_get_login_rx(struct iscsi_conn *, struct iscsi_login *);
 extern int iscsit_put_login_tx(struct iscsi_conn *, struct iscsi_login *, u32);
 extern void iscsit_free_conn(struct iscsi_np *, struct iscsi_conn *);
-extern int iscsi_post_login_handler(struct iscsi_np *, struct iscsi_conn *, u8);
+extern int iscsit_start_kthreads(struct iscsi_conn *);
+extern void iscsi_post_login_handler(struct iscsi_np *, struct iscsi_conn *, u8);
 extern void iscsi_target_login_sess_out(struct iscsi_conn *, struct iscsi_np *,
 				bool, bool);
 extern int iscsi_target_login_thread(void *);
diff --git a/drivers/target/iscsi/iscsi_target_nego.c b/drivers/target/iscsi/iscsi_target_nego.c
index 8c02fa34716f..f9cde9141836 100644
--- a/drivers/target/iscsi/iscsi_target_nego.c
+++ b/drivers/target/iscsi/iscsi_target_nego.c
@@ -17,6 +17,7 @@
  ******************************************************************************/
 
 #include <linux/ctype.h>
+#include <linux/kthread.h>
 #include <scsi/iscsi_proto.h>
 #include <target/target_core_base.h>
 #include <target/target_core_fabric.h>
@@ -361,10 +362,24 @@ static int iscsi_target_do_tx_login_io(struct iscsi_conn *conn, struct iscsi_log
 		ntohl(login_rsp->statsn), login->rsp_length);
 
 	padding = ((-login->rsp_length) & 3);
+	/*
+	 * Before sending the last login response containing the transition
+	 * bit for full-feature-phase, go ahead and start up TX/RX threads
+	 * now to avoid potential resource allocation failures after the
+	 * final login response has been sent.
+	 */
+	if (login->login_complete) {
+		int rc = iscsit_start_kthreads(conn);
+		if (rc) {
+			iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
+					    ISCSI_LOGIN_STATUS_NO_RESOURCES);
+			return -1;
+		}
+	}
 
 	if (conn->conn_transport->iscsit_put_login_tx(conn, login,
 					login->rsp_length + padding) < 0)
-		return -1;
+		goto err;
 
 	login->rsp_length		= 0;
 	mutex_lock(&sess->cmdsn_mutex);
@@ -373,6 +388,23 @@ static int iscsi_target_do_tx_login_io(struct iscsi_conn *conn, struct iscsi_log
 	mutex_unlock(&sess->cmdsn_mutex);
 
 	return 0;
+
+err:
+	if (login->login_complete) {
+		if (conn->rx_thread && conn->rx_thread_active) {
+			send_sig(SIGINT, conn->rx_thread, 1);
+			kthread_stop(conn->rx_thread);
+		}
+		if (conn->tx_thread && conn->tx_thread_active) {
+			send_sig(SIGINT, conn->tx_thread, 1);
+			kthread_stop(conn->tx_thread);
+		}
+		spin_lock(&iscsit_global->ts_bitmap_lock);
+		bitmap_release_region(iscsit_global->ts_bitmap, conn->bitmap_id,
+				      get_order(1));
+		spin_unlock(&iscsit_global->ts_bitmap_lock);
+	}
+	return -1;
 }
 
 static void iscsi_target_sk_data_ready(struct sock *sk)
diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index 0b0de3647478..c2e9fea90b4a 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -747,7 +747,7 @@ static ssize_t store_pi_prot_type(struct se_dev_attrib *da,
 	if (!dev->transport->init_prot || !dev->transport->free_prot) {
 		/* 0 is only allowed value for non-supporting backends */
 		if (flag == 0)
-			return 0;
+			return count;
 
 		pr_err("DIF protection not supported by backend: %s\n",
 		       dev->transport->name);
@@ -1590,9 +1590,9 @@ static ssize_t target_core_dev_pr_store_attr_res_aptpl_metadata(
 	u8 type = 0;
 
 	if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)
-		return 0;
+		return count;
 	if (dev->dev_reservation_flags & DRF_SPC2_RESERVATIONS)
-		return 0;
+		return count;
 
 	if (dev->export_count) {
 		pr_debug("Unable to process APTPL metadata while"
@@ -1658,22 +1658,32 @@ static ssize_t target_core_dev_pr_store_attr_res_aptpl_metadata(
 		 * PR APTPL Metadata for Reservation
 		 */
 		case Opt_res_holder:
-			match_int(args, &arg);
+			ret = match_int(args, &arg);
+			if (ret)
+				goto out;
 			res_holder = arg;
 			break;
 		case Opt_res_type:
-			match_int(args, &arg);
+			ret = match_int(args, &arg);
+			if (ret)
+				goto out;
 			type = (u8)arg;
 			break;
 		case Opt_res_scope:
-			match_int(args, &arg);
+			ret = match_int(args, &arg);
+			if (ret)
+				goto out;
 			break;
 		case Opt_res_all_tg_pt:
-			match_int(args, &arg);
+			ret = match_int(args, &arg);
+			if (ret)
+				goto out;
 			all_tg_pt = (int)arg;
 			break;
 		case Opt_mapped_lun:
-			match_int(args, &arg);
+			ret = match_int(args, &arg);
+			if (ret)
+				goto out;
 			mapped_lun = (u64)arg;
 			break;
 		/*
@@ -1701,14 +1711,20 @@ static ssize_t target_core_dev_pr_store_attr_res_aptpl_metadata(
 			}
 			break;
 		case Opt_tpgt:
-			match_int(args, &arg);
+			ret = match_int(args, &arg);
+			if (ret)
+				goto out;
 			tpgt = (u16)arg;
 			break;
 		case Opt_port_rtpi:
-			match_int(args, &arg);
+			ret = match_int(args, &arg);
+			if (ret)
+				goto out;
 			break;
 		case Opt_target_lun:
-			match_int(args, &arg);
+			ret = match_int(args, &arg);
+			if (ret)
+				goto out;
 			target_lun = (u64)arg;
 			break;
 		default:
@@ -1985,7 +2001,7 @@ static ssize_t target_core_store_alua_lu_gp(
 
 	lu_gp_mem = dev->dev_alua_lu_gp_mem;
 	if (!lu_gp_mem)
-		return 0;
+		return count;
 
 	if (count > LU_GROUP_NAME_BUF) {
 		pr_err("ALUA LU Group Alias too large!\n");
diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c
index 0fdbe43b7dad..5ab7100de17e 100644
--- a/drivers/target/target_core_pr.c
+++ b/drivers/target/target_core_pr.c
@@ -1474,7 +1474,7 @@ core_scsi3_decode_spec_i_port(
 	LIST_HEAD(tid_dest_list);
 	struct pr_transport_id_holder *tidh_new, *tidh, *tidh_tmp;
 	unsigned char *buf, *ptr, proto_ident;
-	const unsigned char *i_str;
+	const unsigned char *i_str = NULL;
 	char *iport_ptr = NULL, i_buf[PR_REG_ISID_ID_LEN];
 	sense_reason_t ret;
 	u32 tpdl, tid_len = 0;
diff --git a/drivers/target/target_core_rd.c b/drivers/target/target_core_rd.c
index 4703f403f31c..384cf8894411 100644
--- a/drivers/target/target_core_rd.c
+++ b/drivers/target/target_core_rd.c
@@ -333,6 +333,7 @@ static int rd_configure_device(struct se_device *dev)
 	dev->dev_attrib.hw_block_size = RD_BLOCKSIZE;
 	dev->dev_attrib.hw_max_sectors = UINT_MAX;
 	dev->dev_attrib.hw_queue_depth = RD_MAX_DEVICE_QUEUE_DEPTH;
+	dev->dev_attrib.is_nonrot = 1;
 
 	rd_dev->rd_dev_id = rd_host->rd_host_dev_id_count++;
 
diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c
index b0744433315a..b5ba1ec3c354 100644
--- a/drivers/target/target_core_spc.c
+++ b/drivers/target/target_core_spc.c
@@ -454,10 +454,17 @@ spc_emulate_evpd_86(struct se_cmd *cmd, unsigned char *buf)
 		    cmd->se_sess->sess_prot_type == TARGET_DIF_TYPE1_PROT)
 			buf[4] = 0x5;
 		else if (dev->dev_attrib.pi_prot_type == TARGET_DIF_TYPE3_PROT ||
-			cmd->se_sess->sess_prot_type == TARGET_DIF_TYPE3_PROT)
+			 cmd->se_sess->sess_prot_type == TARGET_DIF_TYPE3_PROT)
 			buf[4] = 0x4;
 	}
 
+	/* logical unit supports type 1 and type 3 protection */
+	if ((dev->transport->get_device_type(dev) == TYPE_DISK) &&
+	    (sess->sup_prot_ops & (TARGET_PROT_DIN_PASS | TARGET_PROT_DOUT_PASS)) &&
+	    (dev->dev_attrib.pi_prot_type || cmd->se_sess->sess_prot_type)) {
+		buf[4] |= (0x3 << 3);
+	}
+
 	/* Set HEADSUP, ORDSUP, SIMPSUP */
 	buf[5] = 0x07;
 
diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index 2fb29dfeffbd..563c510f285c 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -689,6 +689,23 @@ struct vfio_device *vfio_device_get_from_dev(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(vfio_device_get_from_dev);
 
+static struct vfio_device *vfio_device_get_from_name(struct vfio_group *group,
+						     char *buf)
+{
+	struct vfio_device *device;
+
+	mutex_lock(&group->device_lock);
+	list_for_each_entry(device, &group->device_list, group_next) {
+		if (!strcmp(dev_name(device->dev), buf)) {
+			vfio_device_get(device);
+			break;
+		}
+	}
+	mutex_unlock(&group->device_lock);
+
+	return device;
+}
+
 /*
  * Caller must hold a reference to the vfio_device
  */
@@ -1198,53 +1215,53 @@ static int vfio_group_get_device_fd(struct vfio_group *group, char *buf)
 {
 	struct vfio_device *device;
 	struct file *filep;
-	int ret = -ENODEV;
+	int ret;
 
 	if (0 == atomic_read(&group->container_users) ||
 	    !group->container->iommu_driver || !vfio_group_viable(group))
 		return -EINVAL;
 
-	mutex_lock(&group->device_lock);
-	list_for_each_entry(device, &group->device_list, group_next) {
-		if (strcmp(dev_name(device->dev), buf))
-			continue;
+	device = vfio_device_get_from_name(group, buf);
+	if (!device)
+		return -ENODEV;
 
-		ret = device->ops->open(device->device_data);
-		if (ret)
-			break;
-		/*
-		 * We can't use anon_inode_getfd() because we need to modify
-		 * the f_mode flags directly to allow more than just ioctls
-		 */
-		ret = get_unused_fd_flags(O_CLOEXEC);
-		if (ret < 0) {
-			device->ops->release(device->device_data);
-			break;
-		}
+	ret = device->ops->open(device->device_data);
+	if (ret) {
+		vfio_device_put(device);
+		return ret;
+	}
 
-		filep = anon_inode_getfile("[vfio-device]", &vfio_device_fops,
-					   device, O_RDWR);
-		if (IS_ERR(filep)) {
-			put_unused_fd(ret);
-			ret = PTR_ERR(filep);
-			device->ops->release(device->device_data);
-			break;
-		}
+	/*
+	 * We can't use anon_inode_getfd() because we need to modify
+	 * the f_mode flags directly to allow more than just ioctls
+	 */
+	ret = get_unused_fd_flags(O_CLOEXEC);
+	if (ret < 0) {
+		device->ops->release(device->device_data);
+		vfio_device_put(device);
+		return ret;
+	}
 
-		/*
-		 * TODO: add an anon_inode interface to do this.
-		 * Appears to be missing by lack of need rather than
-		 * explicitly prevented.  Now there's need.
-		 */
-		filep->f_mode |= (FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE);
+	filep = anon_inode_getfile("[vfio-device]", &vfio_device_fops,
+				   device, O_RDWR);
+	if (IS_ERR(filep)) {
+		put_unused_fd(ret);
+		ret = PTR_ERR(filep);
+		device->ops->release(device->device_data);
+		vfio_device_put(device);
+		return ret;
+	}
+
+	/*
+	 * TODO: add an anon_inode interface to do this.
+	 * Appears to be missing by lack of need rather than
+	 * explicitly prevented.  Now there's need.
+	 */
+	filep->f_mode |= (FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE);
 
-		vfio_device_get(device);
-		atomic_inc(&group->container_users);
+	atomic_inc(&group->container_users);
 
-		fd_install(ret, filep);
-		break;
-	}
-	mutex_unlock(&group->device_lock);
+	fd_install(ret, filep);
 
 	return ret;
 }
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index a9fe859f43c8..eec2f11809ff 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -683,11 +683,8 @@ static void *vhost_kvzalloc(unsigned long size)
 {
 	void *n = kzalloc(size, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
 
-	if (!n) {
+	if (!n)
 		n = vzalloc(size);
-		if (!n)
-			return ERR_PTR(-ENOMEM);
-	}
 	return n;
 }
 
@@ -995,6 +992,7 @@ long vhost_dev_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *argp)
 		}
 		if (eventfp != d->log_file) {
 			filep = d->log_file;
+			d->log_file = eventfp;
 			ctx = d->log_ctx;
 			d->log_ctx = eventfp ?
 				eventfd_ctx_fileget(eventfp) : NULL;