From: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
Date: Thu, 27 Jan 2022 11:34:51 -0800
Subject: thermal: intel: hfi: Handle CPU hotplug events
Git-commit: 2d74e6319abe278981e79166b6c2d0c3ed39b1ae
Patch-mainline: 5.18-rc1
References: jsc#PED-820

All CPUs in a package are represented in an HFI table. There exists an
HFI table per package. Thus, CPUs in a package need to coordinate to
initialize and access the table. Do such coordination during CPU hotplug.
Use the first CPU to come online in a package to initialize the HFI
instance and the data structure representing it. Other CPUs in the same
package need only to register or unregister themselves in that data
structure.

The HFI depends on both the package-level thermal management and the local
APIC thermal local vector. Thus, to ensure that a CPU coming online has an
associated HFI instance when the hardware issues an HFI event, enable the
HFI only after having enabled the local APIC thermal vector. The thermal
throttle driver takes care of the needed package-level initialization.

Reviewed-by: Len Brown <len.brown@intel.com>
Signed-off-by: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 drivers/thermal/intel/intel_hfi.c   |  205 ++++++++++++++++++++++++++++++++++++
 drivers/thermal/intel/intel_hfi.h   |    4 
 drivers/thermal/intel/therm_throt.c |    9 +
 3 files changed, 218 insertions(+)

--- a/drivers/thermal/intel/intel_hfi.c
+++ b/drivers/thermal/intel/intel_hfi.c
@@ -23,14 +23,24 @@
 
 #include <linux/bitops.h>
 #include <linux/cpufeature.h>
+#include <linux/cpumask.h>
+#include <linux/gfp.h>
+#include <linux/io.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/topology.h>
 
+#include <asm/msr.h>
+
 #include "intel_hfi.h"
 
+/* Hardware Feedback Interface MSR configuration bits */
+#define HW_FEEDBACK_PTR_VALID_BIT		BIT(0)
+
 /* CPUID detection and enumeration definitions for HFI */
 
 #define CPUID_HFI_LEAF 6
@@ -86,6 +96,8 @@ struct hfi_hdr {
  *			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
  *
  * A set of parameters to parse and navigate a specific HFI table.
  */
@@ -96,6 +108,8 @@ struct hfi_instance {
 	};
 	void			*hdr;
 	void			*data;
+	cpumask_var_t		cpus;
+	void			*hw_table;
 };
 
 /**
@@ -113,10 +127,179 @@ struct hfi_features {
 	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 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);
+
+	cpumask_set_cpu(cpu, hfi_instance->cpus);
+
+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)
 {
@@ -165,6 +348,9 @@ static __init int hfi_parse_features(voi
 
 void __init intel_hfi_init(void)
 {
+	struct hfi_instance *hfi_instance;
+	int i, j;
+
 	if (hfi_parse_features())
 		return;
 
@@ -178,4 +364,23 @@ void __init intel_hfi_init(void)
 	 */
 	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;
+	}
+
+	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;
 }
--- a/drivers/thermal/intel/intel_hfi.h
+++ b/drivers/thermal/intel/intel_hfi.h
@@ -4,8 +4,12 @@
 
 #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);
 #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) { }
 #endif /* CONFIG_INTEL_HFI_THERMAL */
 
 #endif /* _INTEL_HFI_H */
--- a/drivers/thermal/intel/therm_throt.c
+++ b/drivers/thermal/intel/therm_throt.c
@@ -476,6 +476,13 @@ static int thermal_throttle_online(unsig
 	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);
@@ -493,6 +500,8 @@ static int thermal_throttle_offline(unsi
 	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);