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
  ...

5 files changed, 197 insertions, 118 deletions

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[POWER_SUPPLY_FAILURE]);
+throttle_attr(overcurrent, reason[OVERCURRENT]);
+throttle_attr(occ_reset, reason[OCC_RESET_THROTTLE]);
+throttle_attr(turbo_stat, throttle_turbo);
+throttle_attr(sub_turbo_stat, throttle_sub_turbo);
+
+static struct attribute *throttle_attrs[] = {
+	&throttle_attr_unthrottle.attr,
+	&throttle_attr_powercap.attr,
+	&throttle_attr_overtemp.attr,
+	&throttle_attr_supply_fault.attr,
+	&throttle_attr_overcurrent.attr,
+	&throttle_attr_occ_reset.attr,
+	&throttle_attr_turbo_stat.attr,
+	&throttle_attr_sub_turbo_stat.attr,
+	NULL,
+};
+
+static const struct attribute_group throttle_attr_grp = {
+	.name	= "throttle_stats",
+	.attrs	= throttle_attrs,
+};
+
 /* Helper routines */
 
 /* Access helpers to power mgt SPR */
@@ -324,34 +373,35 @@ static inline unsigned int get_nominal_index(void)
 
 static void powernv_cpufreq_throttle_check(void *data)
 {
+	struct chip *chip;
 	unsigned int cpu = smp_processor_id();
-	unsigned int chip_id = core_to_chip_map[cpu_core_index_of_thread(cpu)];
 	unsigned long pmsr;
-	int pmsr_pmax, i;
+	int pmsr_pmax;
 
 	pmsr = get_pmspr(SPRN_PMSR);
-
-	for (i = 0; i < nr_chips; i++)
-		if (chips[i].id == chip_id)
-			break;
+	chip = this_cpu_read(chip_info);
 
 	/* Check for Pmax Capping */
 	pmsr_pmax = (s8)PMSR_MAX(pmsr);
 	if (pmsr_pmax != powernv_pstate_info.max) {
-		if (chips[i].throttled)
+		if (chip->throttled)
 			goto next;
-		chips[i].throttled = true;
-		if (pmsr_pmax < powernv_pstate_info.nominal)
+		chip->throttled = true;
+		if (pmsr_pmax < powernv_pstate_info.nominal) {
 			pr_warn_once("CPU %d on Chip %u has Pmax reduced below nominal frequency (%d < %d)\n",
-				     cpu, chips[i].id, pmsr_pmax,
+				     cpu, chip->id, pmsr_pmax,
 				     powernv_pstate_info.nominal);
-		trace_powernv_throttle(chips[i].id,
-				      throttle_reason[chips[i].throttle_reason],
+			chip->throttle_sub_turbo++;
+		} else {
+			chip->throttle_turbo++;
+		}
+		trace_powernv_throttle(chip->id,
+				      throttle_reason[chip->throttle_reason],
 				      pmsr_pmax);
-	} else if (chips[i].throttled) {
-		chips[i].throttled = false;
-		trace_powernv_throttle(chips[i].id,
-				      throttle_reason[chips[i].throttle_reason],
+	} else if (chip->throttled) {
+		chip->throttled = false;
+		trace_powernv_throttle(chip->id,
+				      throttle_reason[chip->throttle_reason],
 				      pmsr_pmax);
 	}
 
@@ -411,6 +461,21 @@ static int powernv_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	for (i = 0; i < threads_per_core; i++)
 		cpumask_set_cpu(base + i, policy->cpus);
 
+	if (!policy->driver_data) {
+		int ret;
+
+		ret = sysfs_create_group(&policy->kobj, &throttle_attr_grp);
+		if (ret) {
+			pr_info("Failed to create throttle stats directory for cpu %d\n",
+				policy->cpu);
+			return ret;
+		}
+		/*
+		 * policy->driver_data is used as a flag for one-time
+		 * creation of throttle sysfs files.
+		 */
+		policy->driver_data = policy;
+	}
 	return cpufreq_table_validate_and_show(policy, powernv_freqs);
 }
 
@@ -517,8 +582,10 @@ static int powernv_cpufreq_occ_msg(struct notifier_block *nb,
 				break;
 
 		if (omsg.throttle_status >= 0 &&
-		    omsg.throttle_status <= OCC_MAX_THROTTLE_STATUS)
+		    omsg.throttle_status <= OCC_MAX_THROTTLE_STATUS) {
 			chips[i].throttle_reason = omsg.throttle_status;
+			chips[i].reason[omsg.throttle_status]++;
+		}
 
 		if (!omsg.throttle_status)
 			chips[i].restore = true;
@@ -558,47 +625,34 @@ static int init_chip_info(void)
 	unsigned int chip[256];
 	unsigned int cpu, i;
 	unsigned int prev_chip_id = UINT_MAX;
-	cpumask_t cpu_mask;
-	int ret = -ENOMEM;
-
-	core_to_chip_map = kcalloc(cpu_nr_cores(), sizeof(unsigned int),
-				   GFP_KERNEL);
-	if (!core_to_chip_map)
-		goto out;
 
-	cpumask_copy(&cpu_mask, cpu_possible_mask);
-	for_each_cpu(cpu, &cpu_mask) {
+	for_each_possible_cpu(cpu) {
 		unsigned int id = cpu_to_chip_id(cpu);
 
 		if (prev_chip_id != id) {
 			prev_chip_id = id;
 			chip[nr_chips++] = id;
 		}
-		core_to_chip_map[cpu_core_index_of_thread(cpu)] = id;
-		cpumask_andnot(&cpu_mask, &cpu_mask, cpu_sibling_mask(cpu));
 	}
 
 	chips = kcalloc(nr_chips, sizeof(struct chip), GFP_KERNEL);
 	if (!chips)
-		goto free_chip_map;
+		return -ENOMEM;
 
 	for (i = 0; i < nr_chips; i++) {
 		chips[i].id = chip[i];
 		cpumask_copy(&chips[i].mask, cpumask_of_node(chip[i]));
 		INIT_WORK(&chips[i].throttle, powernv_cpufreq_work_fn);
+		for_each_cpu(cpu, &chips[i].mask)
+			per_cpu(chip_info, cpu) =  &chips[i];
 	}
 
 	return 0;
-free_chip_map:
-	kfree(core_to_chip_map);
-out:
-	return ret;
 }
 
 static inline void clean_chip_info(void)
 {
 	kfree(chips);
-	kfree(core_to_chip_map);
 }
 
 static inline void unregister_all_notifiers(void)