Merge branch 'thermal-hfi'

Merge Intel Hardware Feedback Interface (HFI) thermal driver for
5.18-rc1 and update the intel-speed-select utility to support that
driver.

* thermal-hfi:
  tools/power/x86/intel-speed-select: v1.12 release
  tools/power/x86/intel-speed-select: HFI support
  tools/power/x86/intel-speed-select: OOB daemon mode
  thermal: intel: hfi: INTEL_HFI_THERMAL depends on NET
  thermal: netlink: Fix parameter type of thermal_genl_cpu_capability_event() stub
  thermal: intel: hfi: Notify user space for HFI events
  thermal: netlink: Add a new event to notify CPU capabilities change
  thermal: intel: hfi: Enable notification interrupt
  thermal: intel: hfi: Handle CPU hotplug events
  thermal: intel: hfi: Minimally initialize the Hardware Feedback Interface
  x86/cpu: Add definitions for the Intel Hardware Feedback Interface
  x86/Documentation: Describe the Intel Hardware Feedback Interface

7 files changed, 690 insertions, 0 deletions

diff --git a/drivers/thermal/intel/Kconfig b/drivers/thermal/intel/Kconfig
index c83ea5d04a1d..f0c845679250 100644
--- a/drivers/thermal/intel/Kconfig
+++ b/drivers/thermal/intel/Kconfig
@@ -99,3 +99,17 @@ config INTEL_MENLOW
 	  Intel Menlow platform.
 
 	  If unsure, say N.
+
+config INTEL_HFI_THERMAL
+	bool "Intel Hardware Feedback Interface"
+	depends on NET
+	depends on CPU_SUP_INTEL
+	depends on X86_THERMAL_VECTOR
+	select THERMAL_NETLINK
+	help
+	  Select this option to enable the Hardware Feedback Interface. If
+	  selected, hardware provides guidance to the operating system on
+	  the performance and energy efficiency capabilities of each CPU.
+	  These capabilities may change as a result of changes in the operating
+	  conditions of the system such power and thermal limits. If selected,
+	  the kernel relays updates in CPUs' capabilities to userspace.
diff --git a/drivers/thermal/intel/Makefile b/drivers/thermal/intel/Makefile
index 960b56268b4a..9a8d8054f316 100644
--- a/drivers/thermal/intel/Makefile
+++ b/drivers/thermal/intel/Makefile
@@ -13,3 +13,4 @@ obj-$(CONFIG_INTEL_PCH_THERMAL)	+= intel_pch_thermal.o
 obj-$(CONFIG_INTEL_TCC_COOLING)	+= intel_tcc_cooling.o
 obj-$(CONFIG_X86_THERMAL_VECTOR) += therm_throt.o
 obj-$(CONFIG_INTEL_MENLOW)	+= intel_menlow.o
+obj-$(CONFIG_INTEL_HFI_THERMAL) += intel_hfi.o
diff --git a/drivers/thermal/intel/intel_hfi.c b/drivers/thermal/intel/intel_hfi.c
new file mode 100644
index 000000000000..730fd121df6e
--- /dev/null
+++ b/drivers/thermal/intel/intel_hfi.c
@@ -0,0 +1,569 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Hardware Feedback Interface Driver
+ *
+ * Copyright (c) 2021, Intel Corporation.
+ *
+ * Authors: Aubrey Li <aubrey.li@linux.intel.com>
+ *          Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
+ *
+ *
+ * The Hardware Feedback Interface provides a performance and energy efficiency
+ * capability information for each CPU in the system. Depending on the processor
+ * model, hardware may periodically update these capabilities as a result of
+ * changes in the operating conditions (e.g., power limits or thermal
+ * constraints). On other processor models, there is a single HFI update
+ * at boot.
+ *
+ * This file provides functionality to process HFI updates and relay these
+ * updates to userspace.
+ */
+
+#define pr_fmt(fmt)  "intel-hfi: " fmt
+
+#include <linux/bitops.h>
+#include <linux/cpufeature.h>
+#include <linux/cpumask.h>
+#include <linux/gfp.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/math.h>
+#include <linux/mutex.h>
+#include <linux/percpu-defs.h>
+#include <linux/printk.h>
+#include <linux/processor.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/string.h>
+#include <linux/topology.h>
+#include <linux/workqueue.h>
+
+#include <asm/msr.h>
+
+#include "../thermal_core.h"
+#include "intel_hfi.h"
+
+#define THERM_STATUS_CLEAR_PKG_MASK (BIT(1) | BIT(3) | BIT(5) | BIT(7) | \
+				     BIT(9) | BIT(11) | BIT(26))
+
+/* Hardware Feedback Interface MSR configuration bits */
+#define HW_FEEDBACK_PTR_VALID_BIT		BIT(0)
+#define HW_FEEDBACK_CONFIG_HFI_ENABLE_BIT	BIT(0)
+
+/* CPUID detection and enumeration definitions for HFI */
+
+#define CPUID_HFI_LEAF 6
+
+union hfi_capabilities {
+	struct {
+		u8	performance:1;
+		u8	energy_efficiency:1;
+		u8	__reserved:6;
+	} split;
+	u8 bits;
+};
+
+union cpuid6_edx {
+	struct {
+		union hfi_capabilities	capabilities;
+		u32			table_pages:4;
+		u32			__reserved:4;
+		s32			index:16;
+	} split;
+	u32 full;
+};
+
+/**
+ * struct hfi_cpu_data - HFI capabilities per CPU
+ * @perf_cap:		Performance capability
+ * @ee_cap:		Energy efficiency capability
+ *
+ * Capabilities of a logical processor in the HFI table. These capabilities are
+ * unitless.
+ */
+struct hfi_cpu_data {
+	u8	perf_cap;
+	u8	ee_cap;
+} __packed;
+
+/**
+ * struct hfi_hdr - Header of the HFI table
+ * @perf_updated:	Hardware updated performance capabilities
+ * @ee_updated:		Hardware updated energy efficiency capabilities
+ *
+ * Properties of the data in an HFI table.
+ */
+struct hfi_hdr {
+	u8	perf_updated;
+	u8	ee_updated;
+} __packed;
+
+/**
+ * struct hfi_instance - Representation of an HFI instance (i.e., a table)
+ * @local_table:	Base of the local copy of the HFI table
+ * @timestamp:		Timestamp of the last update of the local table.
+ *			Located at the base of the local table.
+ * @hdr:		Base address of the header of the local table
+ * @data:		Base address of the data of the local table
+ * @cpus:		CPUs represented in this HFI table instance
+ * @hw_table:		Pointer to the HFI table of this instance
+ * @update_work:	Delayed work to process HFI updates
+ * @table_lock:		Lock to protect acceses to the table of this instance
+ * @event_lock:		Lock to process HFI interrupts
+ *
+ * A set of parameters to parse and navigate a specific HFI table.
+ */
+struct hfi_instance {
+	union {
+		void			*local_table;
+		u64			*timestamp;
+	};
+	void			*hdr;
+	void			*data;
+	cpumask_var_t		cpus;
+	void			*hw_table;
+	struct delayed_work	update_work;
+	raw_spinlock_t		table_lock;
+	raw_spinlock_t		event_lock;
+};
+
+/**
+ * struct hfi_features - Supported HFI features
+ * @nr_table_pages:	Size of the HFI table in 4KB pages
+ * @cpu_stride:		Stride size to locate the capability data of a logical
+ *			processor within the table (i.e., row stride)
+ * @hdr_size:		Size of the table header
+ *
+ * Parameters and supported features that are common to all HFI instances
+ */
+struct hfi_features {
+	unsigned int	nr_table_pages;
+	unsigned int	cpu_stride;
+	unsigned int	hdr_size;
+};
+
+/**
+ * struct hfi_cpu_info - Per-CPU attributes to consume HFI data
+ * @index:		Row of this CPU in its HFI table
+ * @hfi_instance:	Attributes of the HFI table to which this CPU belongs
+ *
+ * Parameters to link a logical processor to an HFI table and a row within it.
+ */
+struct hfi_cpu_info {
+	s16			index;
+	struct hfi_instance	*hfi_instance;
+};
+
+static DEFINE_PER_CPU(struct hfi_cpu_info, hfi_cpu_info) = { .index = -1 };
+
+static int max_hfi_instances;
+static struct hfi_instance *hfi_instances;
+
+static struct hfi_features hfi_features;
+static DEFINE_MUTEX(hfi_instance_lock);
+
+static struct workqueue_struct *hfi_updates_wq;
+#define HFI_UPDATE_INTERVAL		HZ
+#define HFI_MAX_THERM_NOTIFY_COUNT	16
+
+static void get_hfi_caps(struct hfi_instance *hfi_instance,
+			 struct thermal_genl_cpu_caps *cpu_caps)
+{
+	int cpu, i = 0;
+
+	raw_spin_lock_irq(&hfi_instance->table_lock);
+	for_each_cpu(cpu, hfi_instance->cpus) {
+		struct hfi_cpu_data *caps;
+		s16 index;
+
+		index = per_cpu(hfi_cpu_info, cpu).index;
+		caps = hfi_instance->data + index * hfi_features.cpu_stride;
+		cpu_caps[i].cpu = cpu;
+
+		/*
+		 * Scale performance and energy efficiency to
+		 * the [0, 1023] interval that thermal netlink uses.
+		 */
+		cpu_caps[i].performance = caps->perf_cap << 2;
+		cpu_caps[i].efficiency = caps->ee_cap << 2;
+
+		++i;
+	}
+	raw_spin_unlock_irq(&hfi_instance->table_lock);
+}
+
+/*
+ * Call update_capabilities() when there are changes in the HFI table.
+ */
+static void update_capabilities(struct hfi_instance *hfi_instance)
+{
+	struct thermal_genl_cpu_caps *cpu_caps;
+	int i = 0, cpu_count;
+
+	/* CPUs may come online/offline while processing an HFI update. */
+	mutex_lock(&hfi_instance_lock);
+
+	cpu_count = cpumask_weight(hfi_instance->cpus);
+
+	/* No CPUs to report in this hfi_instance. */
+	if (!cpu_count)
+		goto out;
+
+	cpu_caps = kcalloc(cpu_count, sizeof(*cpu_caps), GFP_KERNEL);
+	if (!cpu_caps)
+		goto out;
+
+	get_hfi_caps(hfi_instance, cpu_caps);
+
+	if (cpu_count < HFI_MAX_THERM_NOTIFY_COUNT)
+		goto last_cmd;
+
+	/* Process complete chunks of HFI_MAX_THERM_NOTIFY_COUNT capabilities. */
+	for (i = 0;
+	     (i + HFI_MAX_THERM_NOTIFY_COUNT) <= cpu_count;
+	     i += HFI_MAX_THERM_NOTIFY_COUNT)
+		thermal_genl_cpu_capability_event(HFI_MAX_THERM_NOTIFY_COUNT,
+						  &cpu_caps[i]);
+
+	cpu_count = cpu_count - i;
+
+last_cmd:
+	/* Process the remaining capabilities if any. */
+	if (cpu_count)
+		thermal_genl_cpu_capability_event(cpu_count, &cpu_caps[i]);
+
+	kfree(cpu_caps);
+out:
+	mutex_unlock(&hfi_instance_lock);
+}
+
+static void hfi_update_work_fn(struct work_struct *work)
+{
+	struct hfi_instance *hfi_instance;
+
+	hfi_instance = container_of(to_delayed_work(work), struct hfi_instance,
+				    update_work);
+	if (!hfi_instance)
+		return;
+
+	update_capabilities(hfi_instance);
+}
+
+void intel_hfi_process_event(__u64 pkg_therm_status_msr_val)
+{
+	struct hfi_instance *hfi_instance;
+	int cpu = smp_processor_id();
+	struct hfi_cpu_info *info;
+	u64 new_timestamp;
+
+	if (!pkg_therm_status_msr_val)
+		return;
+
+	info = &per_cpu(hfi_cpu_info, cpu);
+	if (!info)
+		return;
+
+	/*
+	 * A CPU is linked to its HFI instance before the thermal vector in the
+	 * local APIC is unmasked. Hence, info->hfi_instance cannot be NULL
+	 * when receiving an HFI event.
+	 */
+	hfi_instance = info->hfi_instance;
+	if (unlikely(!hfi_instance)) {
+		pr_debug("Received event on CPU %d but instance was null", cpu);
+		return;
+	}
+
+	/*
+	 * On most systems, all CPUs in the package receive a package-level
+	 * thermal interrupt when there is an HFI update. It is sufficient to
+	 * let a single CPU to acknowledge the update and queue work to
+	 * process it. The remaining CPUs can resume their work.
+	 */
+	if (!raw_spin_trylock(&hfi_instance->event_lock))
+		return;
+
+	/* Skip duplicated updates. */
+	new_timestamp = *(u64 *)hfi_instance->hw_table;
+	if (*hfi_instance->timestamp == new_timestamp) {
+		raw_spin_unlock(&hfi_instance->event_lock);
+		return;
+	}
+
+	raw_spin_lock(&hfi_instance->table_lock);
+
+	/*
+	 * Copy the updated table into our local copy. This includes the new
+	 * timestamp.
+	 */
+	memcpy(hfi_instance->local_table, hfi_instance->hw_table,
+	       hfi_features.nr_table_pages << PAGE_SHIFT);
+
+	raw_spin_unlock(&hfi_instance->table_lock);
+	raw_spin_unlock(&hfi_instance->event_lock);
+
+	/*
+	 * Let hardware know that we are done reading the HFI table and it is
+	 * free to update it again.
+	 */
+	pkg_therm_status_msr_val &= THERM_STATUS_CLEAR_PKG_MASK &
+				    ~PACKAGE_THERM_STATUS_HFI_UPDATED;
+	wrmsrl(MSR_IA32_PACKAGE_THERM_STATUS, pkg_therm_status_msr_val);
+
+	queue_delayed_work(hfi_updates_wq, &hfi_instance->update_work,
+			   HFI_UPDATE_INTERVAL);
+}
+
+static void init_hfi_cpu_index(struct hfi_cpu_info *info)
+{
+	union cpuid6_edx edx;
+
+	/* Do not re-read @cpu's index if it has already been initialized. */
+	if (info->index > -1)
+		return;
+
+	edx.full = cpuid_edx(CPUID_HFI_LEAF);
+	info->index = edx.split.index;
+}
+
+/*
+ * The format of the HFI table depends on the number of capabilities that the
+ * hardware supports. Keep a data structure to navigate the table.
+ */
+static void init_hfi_instance(struct hfi_instance *hfi_instance)
+{
+	/* The HFI header is below the time-stamp. */
+	hfi_instance->hdr = hfi_instance->local_table +
+			    sizeof(*hfi_instance->timestamp);
+
+	/* The HFI data starts below the header. */
+	hfi_instance->data = hfi_instance->hdr + hfi_features.hdr_size;
+}
+
+/**
+ * intel_hfi_online() - Enable HFI on @cpu
+ * @cpu:	CPU in which the HFI will be enabled
+ *
+ * Enable the HFI to be used in @cpu. The HFI is enabled at the die/package
+ * level. The first CPU in the die/package to come online does the full HFI
+ * initialization. Subsequent CPUs will just link themselves to the HFI
+ * instance of their die/package.
+ *
+ * This function is called before enabling the thermal vector in the local APIC
+ * in order to ensure that @cpu has an associated HFI instance when it receives
+ * an HFI event.
+ */
+void intel_hfi_online(unsigned int cpu)
+{
+	struct hfi_instance *hfi_instance;
+	struct hfi_cpu_info *info;
+	phys_addr_t hw_table_pa;
+	u64 msr_val;
+	u16 die_id;
+
+	/* Nothing to do if hfi_instances are missing. */
+	if (!hfi_instances)
+		return;
+
+	/*
+	 * Link @cpu to the HFI instance of its package/die. It does not
+	 * matter whether the instance has been initialized.
+	 */
+	info = &per_cpu(hfi_cpu_info, cpu);
+	die_id = topology_logical_die_id(cpu);
+	hfi_instance = info->hfi_instance;
+	if (!hfi_instance) {
+		if (die_id < 0 || die_id >= max_hfi_instances)
+			return;
+
+		hfi_instance = &hfi_instances[die_id];
+		info->hfi_instance = hfi_instance;
+	}
+
+	init_hfi_cpu_index(info);
+
+	/*
+	 * Now check if the HFI instance of the package/die of @cpu has been
+	 * initialized (by checking its header). In such case, all we have to
+	 * do is to add @cpu to this instance's cpumask.
+	 */
+	mutex_lock(&hfi_instance_lock);
+	if (hfi_instance->hdr) {
+		cpumask_set_cpu(cpu, hfi_instance->cpus);
+		goto unlock;
+	}
+
+	/*
+	 * Hardware is programmed with the physical address of the first page
+	 * frame of the table. Hence, the allocated memory must be page-aligned.
+	 */
+	hfi_instance->hw_table = alloc_pages_exact(hfi_features.nr_table_pages,
+						   GFP_KERNEL | __GFP_ZERO);
+	if (!hfi_instance->hw_table)
+		goto unlock;
+
+	hw_table_pa = virt_to_phys(hfi_instance->hw_table);
+
+	/*
+	 * Allocate memory to keep a local copy of the table that
+	 * hardware generates.
+	 */
+	hfi_instance->local_table = kzalloc(hfi_features.nr_table_pages << PAGE_SHIFT,
+					    GFP_KERNEL);
+	if (!hfi_instance->local_table)
+		goto free_hw_table;
+
+	/*
+	 * Program the address of the feedback table of this die/package. On
+	 * some processors, hardware remembers the old address of the HFI table
+	 * even after having been reprogrammed and re-enabled. Thus, do not free
+	 * the pages allocated for the table or reprogram the hardware with a
+	 * new base address. Namely, program the hardware only once.
+	 */
+	msr_val = hw_table_pa | HW_FEEDBACK_PTR_VALID_BIT;
+	wrmsrl(MSR_IA32_HW_FEEDBACK_PTR, msr_val);
+
+	init_hfi_instance(hfi_instance);
+
+	INIT_DELAYED_WORK(&hfi_instance->update_work, hfi_update_work_fn);
+	raw_spin_lock_init(&hfi_instance->table_lock);
+	raw_spin_lock_init(&hfi_instance->event_lock);
+
+	cpumask_set_cpu(cpu, hfi_instance->cpus);
+
+	/*
+	 * Enable the hardware feedback interface and never disable it. See
+	 * comment on programming the address of the table.
+	 */
+	rdmsrl(MSR_IA32_HW_FEEDBACK_CONFIG, msr_val);
+	msr_val |= HW_FEEDBACK_CONFIG_HFI_ENABLE_BIT;
+	wrmsrl(MSR_IA32_HW_FEEDBACK_CONFIG, msr_val);
+
+unlock:
+	mutex_unlock(&hfi_instance_lock);
+	return;
+
+free_hw_table:
+	free_pages_exact(hfi_instance->hw_table, hfi_features.nr_table_pages);
+	goto unlock;
+}
+
+/**
+ * intel_hfi_offline() - Disable HFI on @cpu
+ * @cpu:	CPU in which the HFI will be disabled
+ *
+ * Remove @cpu from those covered by its HFI instance.
+ *
+ * On some processors, hardware remembers previous programming settings even
+ * after being reprogrammed. Thus, keep HFI enabled even if all CPUs in the
+ * die/package of @cpu are offline. See note in intel_hfi_online().
+ */
+void intel_hfi_offline(unsigned int cpu)
+{
+	struct hfi_cpu_info *info = &per_cpu(hfi_cpu_info, cpu);
+	struct hfi_instance *hfi_instance;
+
+	/*
+	 * Check if @cpu as an associated, initialized (i.e., with a non-NULL
+	 * header). Also, HFI instances are only initialized if X86_FEATURE_HFI
+	 * is present.
+	 */
+	hfi_instance = info->hfi_instance;
+	if (!hfi_instance)
+		return;
+
+	if (!hfi_instance->hdr)
+		return;
+
+	mutex_lock(&hfi_instance_lock);
+	cpumask_clear_cpu(cpu, hfi_instance->cpus);
+	mutex_unlock(&hfi_instance_lock);
+}
+
+static __init int hfi_parse_features(void)
+{
+	unsigned int nr_capabilities;
+	union cpuid6_edx edx;
+
+	if (!boot_cpu_has(X86_FEATURE_HFI))
+		return -ENODEV;
+
+	/*
+	 * If we are here we know that CPUID_HFI_LEAF exists. Parse the
+	 * supported capabilities and the size of the HFI table.
+	 */
+	edx.full = cpuid_edx(CPUID_HFI_LEAF);
+
+	if (!edx.split.capabilities.split.performance) {
+		pr_debug("Performance reporting not supported! Not using HFI\n");
+		return -ENODEV;
+	}
+
+	/*
+	 * The number of supported capabilities determines the number of
+	 * columns in the HFI table. Exclude the reserved bits.
+	 */
+	edx.split.capabilities.split.__reserved = 0;
+	nr_capabilities = hweight8(edx.split.capabilities.bits);
+
+	/* The number of 4KB pages required by the table */
+	hfi_features.nr_table_pages = edx.split.table_pages + 1;
+
+	/*
+	 * The header contains change indications for each supported feature.
+	 * The size of the table header is rounded up to be a multiple of 8
+	 * bytes.
+	 */
+	hfi_features.hdr_size = DIV_ROUND_UP(nr_capabilities, 8) * 8;
+
+	/*
+	 * Data of each logical processor is also rounded up to be a multiple
+	 * of 8 bytes.
+	 */
+	hfi_features.cpu_stride = DIV_ROUND_UP(nr_capabilities, 8) * 8;
+
+	return 0;
+}
+
+void __init intel_hfi_init(void)
+{
+	struct hfi_instance *hfi_instance;
+	int i, j;
+
+	if (hfi_parse_features())
+		return;
+
+	/* There is one HFI instance per die/package. */
+	max_hfi_instances = topology_max_packages() *
+			    topology_max_die_per_package();
+
+	/*
+	 * This allocation may fail. CPU hotplug callbacks must check
+	 * for a null pointer.
+	 */
+	hfi_instances = kcalloc(max_hfi_instances, sizeof(*hfi_instances),
+				GFP_KERNEL);
+	if (!hfi_instances)
+		return;
+
+	for (i = 0; i < max_hfi_instances; i++) {
+		hfi_instance = &hfi_instances[i];
+		if (!zalloc_cpumask_var(&hfi_instance->cpus, GFP_KERNEL))
+			goto err_nomem;
+	}
+
+	hfi_updates_wq = create_singlethread_workqueue("hfi-updates");
+	if (!hfi_updates_wq)
+		goto err_nomem;
+
+	return;
+
+err_nomem:
+	for (j = 0; j < i; ++j) {
+		hfi_instance = &hfi_instances[j];
+		free_cpumask_var(hfi_instance->cpus);
+	}
+
+	kfree(hfi_instances);
+	hfi_instances = NULL;
+}
diff --git a/drivers/thermal/intel/intel_hfi.h b/drivers/thermal/intel/intel_hfi.h
new file mode 100644
index 000000000000..325aa78b745c
--- /dev/null
+++ b/drivers/thermal/intel/intel_hfi.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _INTEL_HFI_H
+#define _INTEL_HFI_H
+
+#if defined(CONFIG_INTEL_HFI_THERMAL)
+void __init intel_hfi_init(void);
+void intel_hfi_online(unsigned int cpu);
+void intel_hfi_offline(unsigned int cpu);
+void intel_hfi_process_event(__u64 pkg_therm_status_msr_val);
+#else
+static inline void intel_hfi_init(void) { }
+static inline void intel_hfi_online(unsigned int cpu) { }
+static inline void intel_hfi_offline(unsigned int cpu) { }
+static inline void intel_hfi_process_event(__u64 pkg_therm_status_msr_val) { }
+#endif /* CONFIG_INTEL_HFI_THERMAL */
+
+#endif /* _INTEL_HFI_H */
diff --git a/drivers/thermal/intel/therm_throt.c b/drivers/thermal/intel/therm_throt.c
index dab7e8fb1059..8352083b87c7 100644
--- a/drivers/thermal/intel/therm_throt.c
+++ b/drivers/thermal/intel/therm_throt.c
@@ -32,6 +32,7 @@
 #include <asm/irq.h>
 #include <asm/msr.h>
 
+#include "intel_hfi.h"
 #include "thermal_interrupt.h"
 
 /* How long to wait between reporting thermal events */
@@ -475,6 +476,13 @@ static int thermal_throttle_online(unsigned int cpu)
 	INIT_DELAYED_WORK(&state->package_throttle.therm_work, throttle_active_work);
 	INIT_DELAYED_WORK(&state->core_throttle.therm_work, throttle_active_work);
 
+	/*
+	 * The first CPU coming online will enable the HFI. Usually this causes
+	 * hardware to issue an HFI thermal interrupt. Such interrupt will reach
+	 * the CPU once we enable the thermal vector in the local APIC.
+	 */
+	intel_hfi_online(cpu);
+
 	/* Unmask the thermal vector after the above workqueues are initialized. */
 	l = apic_read(APIC_LVTTHMR);
 	apic_write(APIC_LVTTHMR, l & ~APIC_LVT_MASKED);
@@ -492,6 +500,8 @@ static int thermal_throttle_offline(unsigned int cpu)
 	l = apic_read(APIC_LVTTHMR);
 	apic_write(APIC_LVTTHMR, l | APIC_LVT_MASKED);
 
+	intel_hfi_offline(cpu);
+
 	cancel_delayed_work_sync(&state->package_throttle.therm_work);
 	cancel_delayed_work_sync(&state->core_throttle.therm_work);
 
@@ -509,6 +519,8 @@ static __init int thermal_throttle_init_device(void)
 	if (!atomic_read(&therm_throt_en))
 		return 0;
 
+	intel_hfi_init();
+
 	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/therm:online",
 				thermal_throttle_online,
 				thermal_throttle_offline);
@@ -608,6 +620,10 @@ void intel_thermal_interrupt(void)
 					PACKAGE_THERM_STATUS_POWER_LIMIT,
 					POWER_LIMIT_EVENT,
 					PACKAGE_LEVEL);
+
+		if (this_cpu_has(X86_FEATURE_HFI))
+			intel_hfi_process_event(msr_val &
+						PACKAGE_THERM_STATUS_HFI_UPDATED);
 	}
 }
 
@@ -717,6 +733,12 @@ void intel_init_thermal(struct cpuinfo_x86 *c)
 			wrmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT,
 			      l | (PACKAGE_THERM_INT_LOW_ENABLE
 				| PACKAGE_THERM_INT_HIGH_ENABLE), h);
+
+		if (cpu_has(c, X86_FEATURE_HFI)) {
+			rdmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT, l, h);
+			wrmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT,
+			      l | PACKAGE_THERM_INT_HFI_ENABLE, h);
+		}
 	}
 
 	rdmsr(MSR_IA32_MISC_ENABLE, l, h);
diff --git a/drivers/thermal/thermal_netlink.c b/drivers/thermal/thermal_netlink.c
index 73e68cce292e..32fea5174cc0 100644
--- a/drivers/thermal/thermal_netlink.c
+++ b/drivers/thermal/thermal_netlink.c
@@ -43,6 +43,11 @@ static const struct nla_policy thermal_genl_policy[THERMAL_GENL_ATTR_MAX + 1] =
 	[THERMAL_GENL_ATTR_CDEV_MAX_STATE]	= { .type = NLA_U32 },
 	[THERMAL_GENL_ATTR_CDEV_NAME]		= { .type = NLA_STRING,
 						    .len = THERMAL_NAME_LENGTH },
+	/* CPU capabilities */
+	[THERMAL_GENL_ATTR_CPU_CAPABILITY]		= { .type = NLA_NESTED },
+	[THERMAL_GENL_ATTR_CPU_CAPABILITY_ID]		= { .type = NLA_U32 },
+	[THERMAL_GENL_ATTR_CPU_CAPABILITY_PERFORMANCE]	= { .type = NLA_U32 },
+	[THERMAL_GENL_ATTR_CPU_CAPABILITY_EFFICIENCY]	= { .type = NLA_U32 },
 };
 
 struct param {
@@ -58,6 +63,8 @@ struct param {
 	int temp;
 	int cdev_state;
 	int cdev_max_state;
+	struct thermal_genl_cpu_caps *cpu_capabilities;
+	int cpu_capabilities_count;
 };
 
 typedef int (*cb_t)(struct param *);
@@ -190,6 +197,42 @@ static int thermal_genl_event_gov_change(struct param *p)
 	return 0;
 }
 
+static int thermal_genl_event_cpu_capability_change(struct param *p)
+{
+	struct thermal_genl_cpu_caps *cpu_cap = p->cpu_capabilities;
+	struct sk_buff *msg = p->msg;
+	struct nlattr *start_cap;
+	int i;
+
+	start_cap = nla_nest_start(msg, THERMAL_GENL_ATTR_CPU_CAPABILITY);
+	if (!start_cap)
+		return -EMSGSIZE;
+
+	for (i = 0; i < p->cpu_capabilities_count; ++i) {
+		if (nla_put_u32(msg, THERMAL_GENL_ATTR_CPU_CAPABILITY_ID,
+				cpu_cap->cpu))
+			goto out_cancel_nest;
+
+		if (nla_put_u32(msg, THERMAL_GENL_ATTR_CPU_CAPABILITY_PERFORMANCE,
+				cpu_cap->performance))
+			goto out_cancel_nest;
+
+		if (nla_put_u32(msg, THERMAL_GENL_ATTR_CPU_CAPABILITY_EFFICIENCY,
+				cpu_cap->efficiency))
+			goto out_cancel_nest;
+
+		++cpu_cap;
+	}
+
+	nla_nest_end(msg, start_cap);
+
+	return 0;
+out_cancel_nest:
+	nla_nest_cancel(msg, start_cap);
+
+	return -EMSGSIZE;
+}
+
 int thermal_genl_event_tz_delete(struct param *p)
 	__attribute__((alias("thermal_genl_event_tz")));
 
@@ -219,6 +262,7 @@ static cb_t event_cb[] = {
 	[THERMAL_GENL_EVENT_CDEV_DELETE]	= thermal_genl_event_cdev_delete,
 	[THERMAL_GENL_EVENT_CDEV_STATE_UPDATE]	= thermal_genl_event_cdev_state_update,
 	[THERMAL_GENL_EVENT_TZ_GOV_CHANGE]	= thermal_genl_event_gov_change,
+	[THERMAL_GENL_EVENT_CPU_CAPABILITY_CHANGE] = thermal_genl_event_cpu_capability_change,
 };
 
 /*
@@ -356,6 +400,15 @@ int thermal_notify_tz_gov_change(int tz_id, const char *name)
 	return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_GOV_CHANGE, &p);
 }
 
+int thermal_genl_cpu_capability_event(int count,
+				      struct thermal_genl_cpu_caps *caps)
+{
+	struct param p = { .cpu_capabilities_count = count, .cpu_capabilities = caps };
+
+	return thermal_genl_send_event(THERMAL_GENL_EVENT_CPU_CAPABILITY_CHANGE, &p);
+}
+EXPORT_SYMBOL_GPL(thermal_genl_cpu_capability_event);
+
 /*************************** Command encoding ********************************/
 
 static int __thermal_genl_cmd_tz_get_id(struct thermal_zone_device *tz,
diff --git a/drivers/thermal/thermal_netlink.h b/drivers/thermal/thermal_netlink.h
index e554f76291f4..1052f523188d 100644
--- a/drivers/thermal/thermal_netlink.h
+++ b/drivers/thermal/thermal_netlink.h
@@ -4,6 +4,12 @@
  *  Author: Daniel Lezcano <daniel.lezcano@linaro.org>
  */
 
+struct thermal_genl_cpu_caps {
+	int cpu;
+	int performance;
+	int efficiency;
+};
+
 /* Netlink notification function */
 #ifdef CONFIG_THERMAL_NETLINK
 int __init thermal_netlink_init(void);
@@ -23,6 +29,8 @@ int thermal_notify_cdev_add(int cdev_id, const char *name, int max_state);
 int thermal_notify_cdev_delete(int cdev_id);
 int thermal_notify_tz_gov_change(int tz_id, const char *name);
 int thermal_genl_sampling_temp(int id, int temp);
+int thermal_genl_cpu_capability_event(int count,
+				      struct thermal_genl_cpu_caps *caps);
 #else
 static inline int thermal_netlink_init(void)
 {
@@ -101,4 +109,10 @@ static inline int thermal_genl_sampling_temp(int id, int temp)
 {
 	return 0;
 }
+
+static inline int thermal_genl_cpu_capability_event(int count, struct thermal_genl_cpu_caps *caps)
+{
+	return 0;
+}
+
 #endif /* CONFIG_THERMAL_NETLINK */