Merge tag 'pm+acpi-4.6-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull more power management and ACPI updates from Rafael Wysocki:
 "The second batch of power management and ACPI updates for v4.6.

  Included are fixups on top of the previous PM/ACPI pull request and
  other material that didn't make into it but still should go into 4.6.

  Among other things, there's a fix for an intel_pstate driver issue
  uncovered by recent cpufreq changes, a workaround for a boot hang on
  Skylake-H related to the handling of deep C-states by the platform and
  a PCI/ACPI fix for the handling of IO port resources on non-x86
  architectures plus some new device IDs and similar.

  Specifics:

   - Fix for an intel_pstate driver issue related to the handling of MSR
     updates uncovered by the recent cpufreq rework (Rafael Wysocki).

   - cpufreq core cleanups related to starting governors and frequency
     synchronization during resume from system suspend and a locking fix
     for cpufreq_quick_get() (Rafael Wysocki, Richard Cochran).

   - acpi-cpufreq and powernv cpufreq driver updates (Jisheng Zhang,
     Michael Neuling, Richard Cochran, Shilpasri Bhat).

   - intel_idle driver update preventing some Skylake-H systems from
     hanging during initialization by disabling deep C-states mishandled
     by the platform in the problematic configurations (Len Brown).

   - Intel Xeon Phi Processor x200 support for intel_idle
     (Dasaratharaman Chandramouli).

   - cpuidle menu governor updates to make it always honor PM QoS
     latency constraints (and prevent C1 from being used as the fallback
     C-state on x86 when they are set below its exit latency) and to
     restore the previous behavior to fall back to C1 if the next timer
     event is set far enough in the future that was changed in 4.4 which
     led to an energy consumption regression (Rik van Riel, Rafael
     Wysocki).

   - New device ID for a future AMD UART controller in the ACPI driver
     for AMD SoCs (Wang Hongcheng).

   - Rockchip rk3399 support for the rockchip-io-domain adaptive voltage
     scaling (AVS) driver (David Wu).

   - ACPI PCI resources management fix for the handling of IO space
     resources on architectures where the IO space is memory mapped
     (IA64 and ARM64) broken by the introduction of common ACPI
     resources parsing for PCI host bridges in 4.4 (Lorenzo Pieralisi).

   - Fix for the ACPI backend of the generic device properties API to
     make it parse non-device (data node only) children of an ACPI
     device correctly (Irina Tirdea).

   - Fixes for the handling of global suspend flags (introduced in 4.4)
     during hibernation and resume from it (Lukas Wunner).

   - Support for obtaining configuration information from Device Trees
     in the PM clocks framework (Jon Hunter).

   - ACPI _DSM helper code and devfreq framework cleanups (Colin Ian
     King, Geert Uytterhoeven)"

* tag 'pm+acpi-4.6-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (23 commits)
  PM / AVS: rockchip-io: add io selectors and supplies for rk3399
  intel_idle: Support for Intel Xeon Phi Processor x200 Product Family
  intel_idle: prevent SKL-H boot failure when C8+C9+C10 enabled
  ACPI / PM: Runtime resume devices when waking from hibernate
  PM / sleep: Clear pm_suspend_global_flags upon hibernate
  cpufreq: governor: Always schedule work on the CPU running update
  cpufreq: Always update current frequency before startig governor
  cpufreq: Introduce cpufreq_update_current_freq()
  cpufreq: Introduce cpufreq_start_governor()
  cpufreq: powernv: Add sysfs attributes to show throttle stats
  cpufreq: acpi-cpufreq: make Intel/AMD MSR access, io port access static
  PCI: ACPI: IA64: fix IO port generic range check
  ACPI / util: cast data to u64 before shifting to fix sign extension
  cpufreq: powernv: Define per_cpu chip pointer to optimize hot-path
  cpuidle: menu: Fall back to polling if next timer event is near
  cpufreq: acpi-cpufreq: Clean up hot plug notifier callback
  intel_pstate: Do not call wrmsrl_on_cpu() with disabled interrupts
  cpufreq: Make cpufreq_quick_get() safe to call
  ACPI / property: fix data node parsing in acpi_get_next_subnode()
  ACPI / APD: Add device HID for future AMD UART controller
  ...

19 files changed, 593 insertions, 163 deletions

diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index b683e8ee69ec..16501334b99f 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -271,3 +271,72 @@ Description:	Parameters for the CPU cache attributes
 			- WriteBack: data is written only to the cache line and
 				     the modified cache line is written to main
 				     memory only when it is replaced
+
+What:		/sys/devices/system/cpu/cpuX/cpufreq/throttle_stats
+		/sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/turbo_stat
+		/sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/sub_turbo_stat
+		/sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/unthrottle
+		/sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/powercap
+		/sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/overtemp
+		/sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/supply_fault
+		/sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/overcurrent
+		/sys/devices/system/cpu/cpuX/cpufreq/throttle_stats/occ_reset
+Date:		March 2016
+Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
+		Linux for PowerPC mailing list <linuxppc-dev@ozlabs.org>
+Description:	POWERNV CPUFreq driver's frequency throttle stats directory and
+		attributes
+
+		'cpuX/cpufreq/throttle_stats' directory contains the CPU frequency
+		throttle stat attributes for the chip. The throttle stats of a cpu
+		is common across all the cpus belonging to a chip. Below are the
+		throttle attributes exported in the 'throttle_stats' directory:
+
+		- turbo_stat : This file gives the total number of times the max
+		frequency is throttled to lower frequency in turbo (at and above
+		nominal frequency) range of frequencies.
+
+		- sub_turbo_stat : This file gives the total number of times the
+		max frequency is throttled to lower frequency in sub-turbo(below
+		nominal frequency) range of frequencies.
+
+		- unthrottle : This file gives the total number of times the max
+		frequency is unthrottled after being throttled.
+
+		- powercap : This file gives the total number of times the max
+		frequency is throttled due to 'Power Capping'.
+
+		- overtemp : This file gives the total number of times the max
+		frequency is throttled due to 'CPU Over Temperature'.
+
+		- supply_fault : This file gives the total number of times the
+		max frequency is throttled due to 'Power Supply Failure'.
+
+		- overcurrent : This file gives the total number of times the
+		max frequency is throttled due to 'Overcurrent'.
+
+		- occ_reset : This file gives the total number of times the max
+		frequency is throttled due to 'OCC Reset'.
+
+		The sysfs attributes representing different throttle reasons like
+		powercap, overtemp, supply_fault, overcurrent and occ_reset map to
+		the reasons provided by OCC firmware for throttling the frequency.
+
+What:		/sys/devices/system/cpu/cpufreq/policyX/throttle_stats
+		/sys/devices/system/cpu/cpufreq/policyX/throttle_stats/turbo_stat
+		/sys/devices/system/cpu/cpufreq/policyX/throttle_stats/sub_turbo_stat
+		/sys/devices/system/cpu/cpufreq/policyX/throttle_stats/unthrottle
+		/sys/devices/system/cpu/cpufreq/policyX/throttle_stats/powercap
+		/sys/devices/system/cpu/cpufreq/policyX/throttle_stats/overtemp
+		/sys/devices/system/cpu/cpufreq/policyX/throttle_stats/supply_fault
+		/sys/devices/system/cpu/cpufreq/policyX/throttle_stats/overcurrent
+		/sys/devices/system/cpu/cpufreq/policyX/throttle_stats/occ_reset
+Date:		March 2016
+Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
+		Linux for PowerPC mailing list <linuxppc-dev@ozlabs.org>
+Description:	POWERNV CPUFreq driver's frequency throttle stats directory and
+		attributes
+
+		'policyX/throttle_stats' directory and all the attributes are same as
+		the /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats directory and
+		attributes which give the frequency throttle information of the chip.
diff --git a/Documentation/devicetree/bindings/power/rockchip-io-domain.txt b/Documentation/devicetree/bindings/power/rockchip-io-domain.txt
index b8627e763dba..c84fb47265eb 100644
--- a/Documentation/devicetree/bindings/power/rockchip-io-domain.txt
+++ b/Documentation/devicetree/bindings/power/rockchip-io-domain.txt
@@ -35,6 +35,8 @@ Required properties:
   - "rockchip,rk3288-io-voltage-domain" for rk3288
   - "rockchip,rk3368-io-voltage-domain" for rk3368
   - "rockchip,rk3368-pmu-io-voltage-domain" for rk3368 pmu-domains
+  - "rockchip,rk3399-io-voltage-domain" for rk3399
+  - "rockchip,rk3399-pmu-io-voltage-domain" for rk3399 pmu-domains
 - rockchip,grf: phandle to the syscon managing the "general register files"
 
 
@@ -79,6 +81,15 @@ Possible supplies for rk3368 pmu-domains:
 - pmu-supply:    The supply connected to PMUIO_VDD.
 - vop-supply:    The supply connected to LCDC_VDD.
 
+Possible supplies for rk3399:
+- bt656-supply:  The supply connected to APIO2_VDD.
+- audio-supply:  The supply connected to APIO5_VDD.
+- sdmmc-supply:  The supply connected to SDMMC0_VDD.
+- gpio1830       The supply connected to APIO4_VDD.
+
+Possible supplies for rk3399 pmu-domains:
+- pmu1830-supply:The supply connected to PMUIO2_VDD.
+
 Example:
 
 	io-domains {
diff --git a/drivers/acpi/acpi_apd.c b/drivers/acpi/acpi_apd.c
index d0aad06b3872..f245bf35bedb 100644
--- a/drivers/acpi/acpi_apd.c
+++ b/drivers/acpi/acpi_apd.c
@@ -145,6 +145,7 @@ static const struct acpi_device_id acpi_apd_device_ids[] = {
 	{ "AMD0010", APD_ADDR(cz_i2c_desc) },
 	{ "AMDI0010", APD_ADDR(cz_i2c_desc) },
 	{ "AMD0020", APD_ADDR(cz_uart_desc) },
+	{ "AMDI0020", APD_ADDR(cz_uart_desc) },
 	{ "AMD0030", },
 #endif
 #ifdef CONFIG_ARM64
diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c
index 2aee41655ce9..f2fd3fee588a 100644
--- a/drivers/acpi/property.c
+++ b/drivers/acpi/property.c
@@ -816,6 +816,7 @@ struct fwnode_handle *acpi_get_next_subnode(struct device *dev,
 			next = adev->node.next;
 			if (next == head) {
 				child = NULL;
+				adev = ACPI_COMPANION(dev);
 				goto nondev;
 			}
 			adev = list_entry(next, struct acpi_device, node);
diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index d02fd53042a5..56241eb341f4 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -27,8 +27,20 @@
 
 #ifdef CONFIG_X86
 #define valid_IRQ(i) (((i) != 0) && ((i) != 2))
+static inline bool acpi_iospace_resource_valid(struct resource *res)
+{
+	/* On X86 IO space is limited to the [0 - 64K] IO port range */
+	return res->end < 0x10003;
+}
 #else
 #define valid_IRQ(i) (true)
+/*
+ * ACPI IO descriptors on arches other than X86 contain MMIO CPU physical
+ * addresses mapping IO space in CPU physical address space, IO space
+ * resources can be placed anywhere in the 64-bit physical address space.
+ */
+static inline bool
+acpi_iospace_resource_valid(struct resource *res) { return true; }
 #endif
 
 static bool acpi_dev_resource_len_valid(u64 start, u64 end, u64 len, bool io)
@@ -127,7 +139,7 @@ static void acpi_dev_ioresource_flags(struct resource *res, u64 len,
 	if (!acpi_dev_resource_len_valid(res->start, res->end, len, true))
 		res->flags |= IORESOURCE_DISABLED | IORESOURCE_UNSET;
 
-	if (res->end >= 0x10003)
+	if (!acpi_iospace_resource_valid(res))
 		res->flags |= IORESOURCE_DISABLED | IORESOURCE_UNSET;
 
 	if (io_decode == ACPI_DECODE_16)
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index fbfcce3b5227..2a8b59644297 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -748,6 +748,7 @@ static int acpi_hibernation_enter(void)
 
 static void acpi_hibernation_leave(void)
 {
+	pm_set_resume_via_firmware();
 	/*
 	 * If ACPI is not enabled by the BIOS and the boot kernel, we need to
 	 * enable it here.
diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c
index f12a72428aac..050673f0c0b3 100644
--- a/drivers/acpi/utils.c
+++ b/drivers/acpi/utils.c
@@ -692,7 +692,7 @@ bool acpi_check_dsm(acpi_handle handle, const u8 *uuid, int rev, u64 funcs)
 		mask = obj->integer.value;
 	else if (obj->type == ACPI_TYPE_BUFFER)
 		for (i = 0; i < obj->buffer.length && i < 8; i++)
-			mask |= (((u8)obj->buffer.pointer[i]) << (i * 8));
+			mask |= (((u64)obj->buffer.pointer[i]) << (i * 8));
 	ACPI_FREE(obj);
 
 	/*
diff --git a/drivers/base/power/clock_ops.c b/drivers/base/power/clock_ops.c
index 272a52ebafc0..0e64a1b5e62a 100644
--- a/drivers/base/power/clock_ops.c
+++ b/drivers/base/power/clock_ops.c
@@ -137,6 +137,62 @@ int pm_clk_add_clk(struct device *dev, struct clk *clk)
 	return __pm_clk_add(dev, NULL, clk);
 }
 
+
+/**
+ * of_pm_clk_add_clks - Start using device clock(s) for power management.
+ * @dev: Device whose clock(s) is going to be used for power management.
+ *
+ * Add a series of clocks described in the 'clocks' device-tree node for
+ * a device to the list of clocks used for the power management of @dev.
+ * On success, returns the number of clocks added. Returns a negative
+ * error code if there are no clocks in the device node for the device
+ * or if adding a clock fails.
+ */
+int of_pm_clk_add_clks(struct device *dev)
+{
+	struct clk **clks;
+	unsigned int i, count;
+	int ret;
+
+	if (!dev || !dev->of_node)
+		return -EINVAL;
+
+	count = of_count_phandle_with_args(dev->of_node, "clocks",
+					   "#clock-cells");
+	if (count == 0)
+		return -ENODEV;
+
+	clks = kcalloc(count, sizeof(*clks), GFP_KERNEL);
+	if (!clks)
+		return -ENOMEM;
+
+	for (i = 0; i < count; i++) {
+		clks[i] = of_clk_get(dev->of_node, i);
+		if (IS_ERR(clks[i])) {
+			ret = PTR_ERR(clks[i]);
+			goto error;
+		}
+
+		ret = pm_clk_add_clk(dev, clks[i]);
+		if (ret) {
+			clk_put(clks[i]);
+			goto error;
+		}
+	}
+
+	kfree(clks);
+
+	return i;
+
+error:
+	while (i--)
+		pm_clk_remove_clk(dev, clks[i]);
+
+	kfree(clks);
+
+	return ret;
+}
+
 /**
  * __pm_clk_remove - Destroy PM clock entry.
  * @ce: PM clock entry to destroy.
@@ -198,6 +254,39 @@ void pm_clk_remove(struct device *dev, const char *con_id)
 }
 
 /**
+ * pm_clk_remove_clk - Stop using a device clock for power management.
+ * @dev: Device whose clock should not be used for PM any more.
+ * @clk: Clock pointer
+ *
+ * Remove the clock pointed to by @clk from the list of clocks used for
+ * the power management of @dev.
+ */
+void pm_clk_remove_clk(struct device *dev, struct clk *clk)
+{
+	struct pm_subsys_data *psd = dev_to_psd(dev);
+	struct pm_clock_entry *ce;
+
+	if (!psd || !clk)
+		return;
+
+	spin_lock_irq(&psd->lock);
+
+	list_for_each_entry(ce, &psd->clock_list, node) {
+		if (clk == ce->clk)
+			goto remove;
+	}
+
+	spin_unlock_irq(&psd->lock);
+	return;
+
+ remove:
+	list_del(&ce->node);
+	spin_unlock_irq(&psd->lock);
+
+	__pm_clk_remove(ce);
+}
+
+/**
  * pm_clk_init - Initialize a device's list of power management clocks.
  * @dev: Device to initialize the list of PM clocks for.
  *
diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index 59a7b380fbe2..fb5712141040 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -245,7 +245,7 @@ static unsigned extract_freq(u32 val, struct acpi_cpufreq_data *data)
 	}
 }
 
-u32 cpu_freq_read_intel(struct acpi_pct_register *not_used)
+static u32 cpu_freq_read_intel(struct acpi_pct_register *not_used)
 {
 	u32 val, dummy;
 
@@ -253,7 +253,7 @@ u32 cpu_freq_read_intel(struct acpi_pct_register *not_used)
 	return val;
 }
 
-void cpu_freq_write_intel(struct acpi_pct_register *not_used, u32 val)
+static void cpu_freq_write_intel(struct acpi_pct_register *not_used, u32 val)
 {
 	u32 lo, hi;
 
@@ -262,7 +262,7 @@ void cpu_freq_write_intel(struct acpi_pct_register *not_used, u32 val)
 	wrmsr(MSR_IA32_PERF_CTL, lo, hi);
 }
 
-u32 cpu_freq_read_amd(struct acpi_pct_register *not_used)
+static u32 cpu_freq_read_amd(struct acpi_pct_register *not_used)
 {
 	u32 val, dummy;
 
@@ -270,12 +270,12 @@ u32 cpu_freq_read_amd(struct acpi_pct_register *not_used)
 	return val;
 }
 
-void cpu_freq_write_amd(struct acpi_pct_register *not_used, u32 val)
+static void cpu_freq_write_amd(struct acpi_pct_register *not_used, u32 val)
 {
 	wrmsr(MSR_AMD_PERF_CTL, val, 0);
 }
 
-u32 cpu_freq_read_io(struct acpi_pct_register *reg)
+static u32 cpu_freq_read_io(struct acpi_pct_register *reg)
 {
 	u32 val;
 
@@ -283,7 +283,7 @@ u32 cpu_freq_read_io(struct acpi_pct_register *reg)
 	return val;
 }
 
-void cpu_freq_write_io(struct acpi_pct_register *reg, u32 val)
+static void cpu_freq_write_io(struct acpi_pct_register *reg, u32 val)
 {
 	acpi_os_write_port(reg->address, val, reg->bit_width);
 }
@@ -514,8 +514,10 @@ static int boost_notify(struct notifier_block *nb, unsigned long action,
 	 */
 
 	switch (action) {
-	case CPU_UP_PREPARE:
-	case CPU_UP_PREPARE_FROZEN:
+	case CPU_DOWN_FAILED:
+	case CPU_DOWN_FAILED_FROZEN:
+	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
 		boost_set_msrs(acpi_cpufreq_driver.boost_enabled, cpumask);
 		break;
 
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 4c7825856eab..b87596b591b3 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -76,6 +76,7 @@ static inline bool has_target(void)
 /* internal prototypes */
 static int cpufreq_governor(struct cpufreq_policy *policy, unsigned int event);
 static unsigned int __cpufreq_get(struct cpufreq_policy *policy);
+static int cpufreq_start_governor(struct cpufreq_policy *policy);
 
 /**
  * Two notifier lists: the "policy" list is involved in the
@@ -964,10 +965,7 @@ static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy, unsigned int cp
 	cpumask_set_cpu(cpu, policy->cpus);
 
 	if (has_target()) {
-		ret = cpufreq_governor(policy, CPUFREQ_GOV_START);
-		if (!ret)
-			ret = cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
-
+		ret = cpufreq_start_governor(policy);
 		if (ret)
 			pr_err("%s: Failed to start governor\n", __func__);
 	}
@@ -1308,10 +1306,7 @@ static void cpufreq_offline(unsigned int cpu)
 	/* Start governor again for active policy */
 	if (!policy_is_inactive(policy)) {
 		if (has_target()) {
-			ret = cpufreq_governor(policy, CPUFREQ_GOV_START);
-			if (!ret)
-				ret = cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
-
+			ret = cpufreq_start_governor(policy);
 			if (ret)
 				pr_err("%s: Failed to start governor\n", __func__);
 		}
@@ -1401,9 +1396,17 @@ unsigned int cpufreq_quick_get(unsigned int cpu)
 {
 	struct cpufreq_policy *policy;
 	unsigned int ret_freq = 0;
+	unsigned long flags;
 
-	if (cpufreq_driver && cpufreq_driver->setpolicy && cpufreq_driver->get)
-		return cpufreq_driver->get(cpu);
+	read_lock_irqsave(&cpufreq_driver_lock, flags);
+
+	if (cpufreq_driver && cpufreq_driver->setpolicy && cpufreq_driver->get) {
+		ret_freq = cpufreq_driver->get(cpu);
+		read_unlock_irqrestore(&cpufreq_driver_lock, flags);
+		return ret_freq;
+	}
+
+	read_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
 	policy = cpufreq_cpu_get(cpu);
 	if (policy) {
@@ -1484,6 +1487,24 @@ unsigned int cpufreq_get(unsigned int cpu)
 }
 EXPORT_SYMBOL(cpufreq_get);
 
+static unsigned int cpufreq_update_current_freq(struct cpufreq_policy *policy)
+{
+	unsigned int new_freq;
+
+	new_freq = cpufreq_driver->get(policy->cpu);
+	if (!new_freq)
+		return 0;
+
+	if (!policy->cur) {
+		pr_debug("cpufreq: Driver did not initialize current freq\n");
+		policy->cur = new_freq;
+	} else if (policy->cur != new_freq && has_target()) {
+		cpufreq_out_of_sync(policy, new_freq);
+	}
+
+	return new_freq;
+}
+
 static struct subsys_interface cpufreq_interface = {
 	.name		= "cpufreq",
 	.subsys		= &cpu_subsys,
@@ -1583,9 +1604,7 @@ void cpufreq_resume(void)
 				policy);
 		} else {
 			down_write(&policy->rwsem);
-			ret = cpufreq_governor(policy, CPUFREQ_GOV_START);
-			if (!ret)
-				cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
+			ret = cpufreq_start_governor(policy);
 			up_write(&policy->rwsem);
 
 			if (ret)
@@ -1593,17 +1612,6 @@ void cpufreq_resume(void)
 				       __func__, policy);
 		}
 	}
-
-	/*
-	 * schedule call cpufreq_update_policy() for first-online CPU, as that
-	 * wouldn't be hotplugged-out on suspend. It will verify that the
-	 * current freq is in sync with what we believe it to be.
-	 */
-	policy = cpufreq_cpu_get_raw(cpumask_first(cpu_online_mask));
-	if (WARN_ON(!policy))
-		return;
-
-	schedule_work(&policy->update);
 }
 
 /**
@@ -1927,6 +1935,17 @@ static int cpufreq_governor(struct cpufreq_policy *policy, unsigned int event)
 	return ret;
 }
 
+static int cpufreq_start_governor(struct cpufreq_policy *policy)
+{
+	int ret;
+
+	if (cpufreq_driver->get && !cpufreq_driver->setpolicy)
+		cpufreq_update_current_freq(policy);
+
+	ret = cpufreq_governor(policy, CPUFREQ_GOV_START);
+	return ret ? ret : cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
+}
+
 int cpufreq_register_governor(struct cpufreq_governor *governor)
 {
 	int err;
@@ -2063,8 +2082,10 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 		return cpufreq_driver->setpolicy(new_policy);
 	}
 
-	if (new_policy->governor == policy->governor)
-		goto out;
+	if (new_policy->governor == policy->governor) {
+		pr_debug("cpufreq: governor limits update\n");
+		return cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
+	}
 
 	pr_debug("governor switch\n");
 
@@ -2092,10 +2113,11 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 	policy->governor = new_policy->governor;
 	ret = cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT);
 	if (!ret) {
-		ret = cpufreq_governor(policy, CPUFREQ_GOV_START);
-		if (!ret)
-			goto out;
-
+		ret = cpufreq_start_governor(policy);
+		if (!ret) {
+			pr_debug("cpufreq: governor change\n");
+			return 0;
+		}
 		cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
 	}
 
@@ -2106,14 +2128,10 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 		if (cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT))
 			policy->governor = NULL;
 		else
-			cpufreq_governor(policy, CPUFREQ_GOV_START);
+			cpufreq_start_governor(policy);
 	}
 
 	return ret;
-
- out:
-	pr_debug("governor: change or update limits\n");
-	return cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
 }
 
 /**
@@ -2144,19 +2162,11 @@ int cpufreq_update_policy(unsigned int cpu)
 	 * -> ask driver for current freq and notify governors about a change
 	 */
 	if (cpufreq_driver->get && !cpufreq_driver->setpolicy) {
-		new_policy.cur = cpufreq_driver->get(cpu);
+		new_policy.cur = cpufreq_update_current_freq(policy);
 		if (WARN_ON(!new_policy.cur)) {
 			ret = -EIO;
 			goto unlock;
 		}
-
-		if (!policy->cur) {
-			pr_debug("Driver did not initialize current freq\n");
-			policy->cur = new_policy.cur;
-		} else {
-			if (policy->cur != new_policy.cur && has_target())
-				cpufreq_out_of_sync(policy, new_policy.cur);
-		}
 	}
 
 	ret = cpufreq_set_policy(policy, &new_policy);
diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c
index 1c25ef405616..10a5cfeae8c5 100644
--- a/drivers/cpufreq/cpufreq_governor.c
+++ b/drivers/cpufreq/cpufreq_governor.c
@@ -329,7 +329,7 @@ static void dbs_irq_work(struct irq_work *irq_work)
 	struct policy_dbs_info *policy_dbs;
 
 	policy_dbs = container_of(irq_work, struct policy_dbs_info, irq_work);
-	schedule_work(&policy_dbs->work);
+	schedule_work_on(smp_processor_id(), &policy_dbs->work);
 }
 
 static void dbs_update_util_handler(struct update_util_data *data, u64 time,
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index cb5607495816..4b644526fd59 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -134,7 +134,7 @@ struct pstate_funcs {
 	int (*get_min)(void);
 	int (*get_turbo)(void);
 	int (*get_scaling)(void);
-	void (*set)(struct cpudata*, int pstate);
+	u64 (*get_val)(struct cpudata*, int pstate);
 	void (*get_vid)(struct cpudata *);
 	int32_t (*get_target_pstate)(struct cpudata *);
 };
@@ -565,7 +565,7 @@ static int atom_get_turbo_pstate(void)
 	return value & 0x7F;
 }
 
-static void atom_set_pstate(struct cpudata *cpudata, int pstate)
+static u64 atom_get_val(struct cpudata *cpudata, int pstate)
 {
 	u64 val;
 	int32_t vid_fp;
@@ -585,9 +585,7 @@ static void atom_set_pstate(struct cpudata *cpudata, int pstate)
 	if (pstate > cpudata->pstate.max_pstate)
 		vid = cpudata->vid.turbo;
 
-	val |= vid;
-
-	wrmsrl_on_cpu(cpudata->cpu, MSR_IA32_PERF_CTL, val);
+	return val | vid;
 }
 
 static int silvermont_get_scaling(void)
@@ -711,7 +709,7 @@ static inline int core_get_scaling(void)
 	return 100000;
 }
 
-static void core_set_pstate(struct cpudata *cpudata, int pstate)
+static u64 core_get_val(struct cpudata *cpudata, int pstate)
 {
 	u64 val;
 
@@ -719,7 +717,7 @@ static void core_set_pstate(struct cpudata *cpudata, int pstate)
 	if (limits->no_turbo && !limits->turbo_disabled)
 		val |= (u64)1 << 32;
 
-	wrmsrl(MSR_IA32_PERF_CTL, val);
+	return val;
 }
 
 static int knl_get_turbo_pstate(void)
@@ -750,7 +748,7 @@ static struct cpu_defaults core_params = {
 		.get_min = core_get_min_pstate,
 		.get_turbo = core_get_turbo_pstate,
 		.get_scaling = core_get_scaling,
-		.set = core_set_pstate,
+		.get_val = core_get_val,
 		.get_target_pstate = get_target_pstate_use_performance,
 	},
 };
@@ -769,7 +767,7 @@ static struct cpu_defaults silvermont_params = {
 		.get_max_physical = atom_get_max_pstate,
 		.get_min = atom_get_min_pstate,
 		.get_turbo = atom_get_turbo_pstate,
-		.set = atom_set_pstate,
+		.get_val = atom_get_val,
 		.get_scaling = silvermont_get_scaling,
 		.get_vid = atom_get_vid,
 		.get_target_pstate = get_target_pstate_use_cpu_load,
@@ -790,7 +788,7 @@ static struct cpu_defaults airmont_params = {
 		.get_max_physical = atom_get_max_pstate,
 		.get_min = atom_get_min_pstate,
 		.get_turbo = atom_get_turbo_pstate,
-		.set = atom_set_pstate,
+		.get_val = atom_get_val,
 		.get_scaling = airmont_get_scaling,
 		.get_vid = atom_get_vid,
 		.get_target_pstate = get_target_pstate_use_cpu_load,
@@ -812,7 +810,7 @@ static struct cpu_defaults knl_params = {
 		.get_min = core_get_min_pstate,
 		.get_turbo = knl_get_turbo_pstate,
 		.get_scaling = core_get_scaling,
-		.set = core_set_pstate,
+		.get_val = core_get_val,
 		.get_target_pstate = get_target_pstate_use_performance,
 	},
 };
@@ -839,25 +837,24 @@ static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max)
 	*min = clamp_t(int, min_perf, cpu->pstate.min_pstate, max_perf);
 }
 
-static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate, bool force)
+static inline void intel_pstate_record_pstate(struct cpudata *cpu, int pstate)
 {
-	int max_perf, min_perf;
-
-	if (force) {
-		update_turbo_state();
-
-		intel_pstate_get_min_max(cpu, &min_perf, &max_perf);
-
-		pstate = clamp_t(int, pstate, min_perf, max_perf);
-
-		if (pstate == cpu->pstate.current_pstate)
-			return;
-	}
 	trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu);
-
 	cpu->pstate.current_pstate = pstate;
+}
 
-	pstate_funcs.set(cpu, pstate);
+static void intel_pstate_set_min_pstate(struct cpudata *cpu)
+{
+	int pstate = cpu->pstate.min_pstate;
+
+	intel_pstate_record_pstate(cpu, pstate);
+	/*
+	 * Generally, there is no guarantee that this code will always run on
+	 * the CPU being updated, so force the register update to run on the
+	 * right CPU.
+	 */
+	wrmsrl_on_cpu(cpu->cpu, MSR_IA32_PERF_CTL,
+		      pstate_funcs.get_val(cpu, pstate));
 }
 
 static void intel_pstate_get_cpu_pstates(struct cpudata *cpu)
@@ -870,7 +867,8 @@ static void intel_pstate_get_cpu_pstates(struct cpudata *cpu)
 
 	if (pstate_funcs.get_vid)
 		pstate_funcs.get_vid(cpu);
-	intel_pstate_set_pstate(cpu, cpu->pstate.min_pstate, false);
+
+	intel_pstate_set_min_pstate(cpu);
 }
 
 static inline void intel_pstate_calc_busy(struct cpudata *cpu)
@@ -997,6 +995,21 @@ static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu)
 	return cpu->pstate.current_pstate - pid_calc(&cpu->pid, core_busy);
 }
 
+static inline void intel_pstate_update_pstate(struct cpudata *cpu, int pstate)
+{
+	int max_perf, min_perf;
+
+	update_turbo_state();
+
+	intel_pstate_get_min_max(cpu, &min_perf, &max_perf);
+	pstate = clamp_t(int, pstate, min_perf, max_perf);
+	if (pstate == cpu->pstate.current_pstate)
+		return;
+
+	intel_pstate_record_pstate(cpu, pstate);
+	wrmsrl(MSR_IA32_PERF_CTL, pstate_funcs.get_val(cpu, pstate));
+}
+
 static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu)
 {
 	int from, target_pstate;
@@ -1006,7 +1019,7 @@ static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu)
 
 	target_pstate = pstate_funcs.get_target_pstate(cpu);
 
-	intel_pstate_set_pstate(cpu, target_pstate, true);
+	intel_pstate_update_pstate(cpu, target_pstate);
 
 	sample = &cpu->sample;
 	trace_pstate_sample(fp_toint(sample->core_pct_busy),
@@ -1180,7 +1193,7 @@ static void intel_pstate_stop_cpu(struct cpufreq_policy *policy)
 	if (hwp_active)
 		return;
 
-	intel_pstate_set_pstate(cpu, cpu->pstate.min_pstate, false);
+	intel_pstate_set_min_pstate(cpu);
 }
 
 static int intel_pstate_cpu_init(struct cpufreq_policy *policy)
@@ -1255,7 +1268,7 @@ static void copy_cpu_funcs(struct pstate_funcs *funcs)
 	pstate_funcs.get_min   = funcs->get_min;
 	pstate_funcs.get_turbo = funcs->get_turbo;
 	pstate_funcs.get_scaling = funcs->get_scaling;
-	pstate_funcs.set       = funcs->set;
+	pstate_funcs.get_val   = funcs->get_val;
 	pstate_funcs.get_vid   = funcs->get_vid;
 	pstate_funcs.get_target_pstate = funcs->get_target_pstate;
 
diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c
index 50bf12033bbc..39ac78c94be0 100644
--- a/drivers/cpufreq/powernv-cpufreq.c
+++ b/drivers/cpufreq/powernv-cpufreq.c
@@ -44,7 +44,6 @@
 
 static struct cpufreq_frequency_table powernv_freqs[POWERNV_MAX_PSTATES+1];
 static bool rebooting, throttled, occ_reset;
-static unsigned int *core_to_chip_map;
 
 static const char * const throttle_reason[] = {
 	"No throttling",
@@ -55,6 +54,16 @@ static const char * const throttle_reason[] = {
 	"OCC Reset"
 };
 
+enum throttle_reason_type {
+	NO_THROTTLE = 0,
+	POWERCAP,
+	CPU_OVERTEMP,
+	POWER_SUPPLY_FAILURE,
+	OVERCURRENT,
+	OCC_RESET_THROTTLE,
+	OCC_MAX_REASON
+};
+
 static struct chip {
 	unsigned int id;
 	bool throttled;
@@ -62,9 +71,13 @@ static struct chip {
 	u8 throttle_reason;
 	cpumask_t mask;
 	struct work_struct throttle;
+	int throttle_turbo;
+	int throttle_sub_turbo;
+	int reason[OCC_MAX_REASON];
 } *chips;
 
 static int nr_chips;
+static DEFINE_PER_CPU(struct chip *, chip_info);
 
 /*
  * Note: The set of pstates consists of contiguous integers, the
@@ -196,6 +209,42 @@ static struct freq_attr *powernv_cpu_freq_attr[] = {
 	NULL,
 };
 
+#define throttle_attr(name, member)					\
+static ssize_t name##_show(struct cpufreq_policy *policy, char *buf)	\
+{									\
+	struct chip *chip = per_cpu(chip_info, policy->cpu);		\
+									\
+	return sprintf(buf, "%u\n", chip->member);			\
+}									\
+									\
+static struct freq_attr throttle_attr_##name = __ATTR_RO(name)		\
+
+throttle_attr(unthrottle, reason[NO_THROTTLE]);
+throttle_attr(powercap, reason[POWERCAP]);
+throttle_attr(overtemp, reason[CPU_OVERTEMP]);
+throttle_attr(supply_fault, reason[P