[PATCH v1 0/3] x86 / intel_pstate: Set asymmetric CPU capacity on hybrid systems

[PATCH v1 0/3] x86 / intel_pstate: Set asymmetric CPU capacity on hybrid systems

[Rafael J. Wysocki]

Hi Everyone,

The purpose of this series is to provide the scheduler with asymmetric CPU
capacity information on x86 hybrid systems based on Intel hardware.

The asymmetric CPU capacity information is important on hybrid systems as it
allows utilization to be computed for tasks in a consistent way across all
CPUs in the system, regardless of their capacity.  This, in turn, allows
the schedutil cpufreq governor to set CPU performance levels consistently
in the cases when tasks migrate between CPUs of different capacities.  It
should also help to improve task placement and load balancing decisions on
hybrid systems and it is key for anything along the lines of EAS.

The information in question comes from the MSR_HWP_CAPABILITIES register and
is provided to the scheduler by the intel_pstate driver, as per the changelog
of patch [3/3].  Patch [2/3] introduces the arch infrastructure needed for
that (in the form of a per-CPU capacity variable) and patch [1/3] is a
preliminary code adjustment.

This is based on an RFC posted previously

https://lore.kernel.org/linux-pm/7663799.EvYhyI6sBW@kreacher/

but differs from it quite a bit (except for the first patch).  The most
significant difference is based on the observation that frequency-
invariance needs to adjusted to the capacity scaling on hybrid systems
for the complete scale-invariance to work as expected.

Thank you!

[PATCH v1 1/3] x86/sched: Introduce arch_rebuild_sched_domains()

[Rafael J. Wysocki]

From: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

Add arch_rebuild_sched_domains() for rebuilding scheduling domains and
updating topology on x86 and make the ITMT code use it.

First of all, this reduces code duplication somewhat and eliminates
a need to use an extern variable, but it will also lay the ground for
subsequent work related to CPU capacity scaling.

No intentional functional impact.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 arch/x86/include/asm/topology.h |    6 ++++--
 arch/x86/kernel/itmt.c          |   12 ++++--------
 arch/x86/kernel/smpboot.c       |   10 +++++++++-
 3 files changed, 17 insertions(+), 11 deletions(-)

Index: linux-pm/arch/x86/include/asm/topology.h
===================================================================
--- linux-pm.orig/arch/x86/include/asm/topology.h
+++ linux-pm/arch/x86/include/asm/topology.h
@@ -235,8 +235,6 @@ struct pci_bus;
 int x86_pci_root_bus_node(int bus);
 void x86_pci_root_bus_resources(int bus, struct list_head *resources);
 
-extern bool x86_topology_update;
-
 #ifdef CONFIG_SCHED_MC_PRIO
 #include <asm/percpu.h>
 
@@ -284,9 +282,13 @@ static inline long arch_scale_freq_capac
 
 extern void arch_set_max_freq_ratio(bool turbo_disabled);
 extern void freq_invariance_set_perf_ratio(u64 ratio, bool turbo_disabled);
+
+void arch_rebuild_sched_domains(void);
 #else
 static inline void arch_set_max_freq_ratio(bool turbo_disabled) { }
 static inline void freq_invariance_set_perf_ratio(u64 ratio, bool turbo_disabled) { }
+
+static inline void arch_rebuild_sched_domains(void) { }
 #endif
 
 extern void arch_scale_freq_tick(void);
Index: linux-pm/arch/x86/kernel/itmt.c
===================================================================
--- linux-pm.orig/arch/x86/kernel/itmt.c
+++ linux-pm/arch/x86/kernel/itmt.c
@@ -54,10 +54,8 @@ static int sched_itmt_update_handler(str
 	old_sysctl = sysctl_sched_itmt_enabled;
 	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 
-	if (!ret && write && old_sysctl != sysctl_sched_itmt_enabled) {
-		x86_topology_update = true;
-		rebuild_sched_domains();
-	}
+	if (!ret && write && old_sysctl != sysctl_sched_itmt_enabled)
+		arch_rebuild_sched_domains();
 
 	mutex_unlock(&itmt_update_mutex);
 
@@ -114,8 +112,7 @@ int sched_set_itmt_support(void)
 
 	sysctl_sched_itmt_enabled = 1;
 
-	x86_topology_update = true;
-	rebuild_sched_domains();
+	arch_rebuild_sched_domains();
 
 	mutex_unlock(&itmt_update_mutex);
 
@@ -150,8 +147,7 @@ void sched_clear_itmt_support(void)
 	if (sysctl_sched_itmt_enabled) {
 		/* disable sched_itmt if we are no longer ITMT capable */
 		sysctl_sched_itmt_enabled = 0;
-		x86_topology_update = true;
-		rebuild_sched_domains();
+		arch_rebuild_sched_domains();
 	}
 
 	mutex_unlock(&itmt_update_mutex);
Index: linux-pm/arch/x86/kernel/smpboot.c
===================================================================
--- linux-pm.orig/arch/x86/kernel/smpboot.c
+++ linux-pm/arch/x86/kernel/smpboot.c
@@ -39,6 +39,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/cpuset.h>
 #include <linux/init.h>
 #include <linux/smp.h>
 #include <linux/export.h>
@@ -125,7 +126,7 @@ static DEFINE_PER_CPU_ALIGNED(struct mwa
 int __read_mostly __max_smt_threads = 1;
 
 /* Flag to indicate if a complete sched domain rebuild is required */
-bool x86_topology_update;
+static bool x86_topology_update;
 
 int arch_update_cpu_topology(void)
 {
@@ -135,6 +136,13 @@ int arch_update_cpu_topology(void)
 	return retval;
 }
 
+#ifdef CONFIG_X86_64
+void arch_rebuild_sched_domains(void) {
+	x86_topology_update = true;
+	rebuild_sched_domains();
+}
+#endif
+
 static unsigned int smpboot_warm_reset_vector_count;
 
 static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip)

[PATCH v1 2/3] x86/sched: Add basic support for CPU capacity scaling

[Rafael J. Wysocki]

From: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

In order be able to compute the sizes of tasks consistently across all
CPUs in a hybrid system, it is necessary to provide CPU capacity scaling
information to the scheduler via arch_scale_cpu_capacity().  Moreover,
the value returned by arch_scale_freq_capacity() for the given CPU must
correspond to the arch_scale_cpu_capacity() return value for it, or
utilization computations will be inaccurate.

Add support for it through per-CPU variables holding the capacity and
maximum-to-base frequency ratio (times SCHED_CAPACITY_SCALE) that will
be returned by arch_scale_cpu_capacity() and used by scale_freq_tick()
to compute arch_freq_scale for the current CPU, respectively.

In order to avoid adding measurable overhead for non-hybrid x86 systems,
which are the vast majority in the field, whether or not the new hybrid
CPU capacity scaling will be in effect is controlled by a static key.
This static key is set by calling arch_enable_hybrid_capacity_scale()
which also allocates memory for the per-CPU data and initializes it.
Next, arch_set_cpu_capacity() is used to set the per-CPU variables
mentioned above for each CPU and arch_rebuild_sched_domains() needs
to be called for the scheduler to realize that capacity-aware
scheduling can be used going forward.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 arch/x86/include/asm/topology.h  |   13 +++++
 arch/x86/kernel/cpu/aperfmperf.c |   91 ++++++++++++++++++++++++++++++++++++++-
 2 files changed, 103 insertions(+), 1 deletion(-)

Index: linux-pm/arch/x86/include/asm/topology.h
===================================================================
--- linux-pm.orig/arch/x86/include/asm/topology.h
+++ linux-pm/arch/x86/include/asm/topology.h
@@ -280,11 +280,24 @@ static inline long arch_scale_freq_capac
 }
 #define arch_scale_freq_capacity arch_scale_freq_capacity
 
+bool arch_enable_hybrid_capacity_scale(void);
+void arch_set_cpu_capacity(int cpu, unsigned long cap, unsigned long base_cap,
+			   unsigned long max_freq, unsigned long base_freq);
+
+unsigned long arch_scale_cpu_capacity(int cpu);
+#define arch_scale_cpu_capacity arch_scale_cpu_capacity
+
 extern void arch_set_max_freq_ratio(bool turbo_disabled);
 extern void freq_invariance_set_perf_ratio(u64 ratio, bool turbo_disabled);
 
 void arch_rebuild_sched_domains(void);
 #else
+static inline bool arch_enable_hybrid_capacity_scale(void) { return false; }
+static inline void arch_set_cpu_capacity(int cpu, unsigned long cap,
+					 unsigned long base_cap,
+					 unsigned long max_freq,
+					 unsigned long base_freq) { }
+
 static inline void arch_set_max_freq_ratio(bool turbo_disabled) { }
 static inline void freq_invariance_set_perf_ratio(u64 ratio, bool turbo_disabled) { }
 
Index: linux-pm/arch/x86/kernel/cpu/aperfmperf.c
===================================================================
--- linux-pm.orig/arch/x86/kernel/cpu/aperfmperf.c
+++ linux-pm/arch/x86/kernel/cpu/aperfmperf.c
@@ -300,6 +300,8 @@ static void register_freq_invariance_sys
 static inline void register_freq_invariance_syscore_ops(void) {}
 #endif
 
+static DEFINE_STATIC_KEY_FALSE(arch_hybrid_cap_scale_key);
+
 static void freq_invariance_enable(void)
 {
 	if (static_branch_unlikely(&arch_scale_freq_key)) {
@@ -332,6 +334,7 @@ static void disable_freq_invariance_work
 	int cpu;
 
 	static_branch_disable(&arch_scale_freq_key);
+	static_branch_disable(&arch_hybrid_cap_scale_key);
 
 	/*
 	 * Set arch_freq_scale to a default value on all cpus
@@ -347,9 +350,90 @@ static DECLARE_WORK(disable_freq_invaria
 DEFINE_PER_CPU(unsigned long, arch_freq_scale) = SCHED_CAPACITY_SCALE;
 EXPORT_PER_CPU_SYMBOL_GPL(arch_freq_scale);
 
+struct arch_hybrid_cpu_scale {
+	unsigned long capacity;
+	unsigned long freq_ratio;
+};
+
+static struct arch_hybrid_cpu_scale __percpu *arch_cpu_scale;
+
+/**
+ * arch_enable_hybrid_capacity_scale - Enable hybrid CPU capacity scaling
+ *
+ * Allocate memory for per-CPU data used by hybrid CPU capacity scaling,
+ * initialize it and set the static key controlling its code paths.
+ *
+ * Must be called before arch_set_cpu_capacity().
+ */
+bool arch_enable_hybrid_capacity_scale(void)
+{
+	int cpu;
+
+	if (!arch_scale_freq_invariant())
+		return false;
+
+	if (static_branch_unlikely(&arch_hybrid_cap_scale_key)) {
+		WARN_ON_ONCE(1);
+		return false;
+	}
+	arch_cpu_scale = alloc_percpu(struct arch_hybrid_cpu_scale);
+	if (!arch_cpu_scale)
+		return false;
+
+	for_each_possible_cpu(cpu) {
+		per_cpu_ptr(arch_cpu_scale, cpu)->capacity = SCHED_CAPACITY_SCALE;
+		per_cpu_ptr(arch_cpu_scale, cpu)->freq_ratio = arch_max_freq_ratio;
+	}
+
+	static_branch_enable(&arch_hybrid_cap_scale_key);
+
+	pr_info("Hybrid CPU capacity scaling enabled\n");
+
+	return true;
+}
+
+/**
+ * arch_set_cpu_capacity - Set scale-invariance parameters for a CPU
+ * @cpu: Target CPU.
+ * @cap: Capacity of @cpu, relative to @base_cap, at its maximum frequency.
+ * @base_cap: System-wide maximum CPU capacity.
+ * @max_freq: Frequency of @cpu corresponding to @cap.
+ * @base_freq: Frequency of @cpu at which APERF and MPERF count.
+ *
+ * The units in which @cap and @base_cap are expressed do not matter, so long
+ * as they are consistent, because the former is effectively divided by the
+ * latter.  Analogously for @max_freq and @base_freq.
+ *
+ * After calling this function for all CPUs, call arch_rebuild_sched_domains()
+ * to let the scheduler know that capacity-aware scheduling can be used going
+ * forward.
+ */
+void arch_set_cpu_capacity(int cpu, unsigned long cap, unsigned long base_cap,
+			   unsigned long max_freq, unsigned long base_freq)
+{
+	if (static_branch_likely(&arch_hybrid_cap_scale_key)) {
+		WRITE_ONCE(per_cpu_ptr(arch_cpu_scale, cpu)->capacity,
+			   div_u64(cap << SCHED_CAPACITY_SHIFT, base_cap));
+		WRITE_ONCE(per_cpu_ptr(arch_cpu_scale, cpu)->freq_ratio,
+			   div_u64(max_freq << SCHED_CAPACITY_SHIFT, base_freq));
+	} else {
+		WARN_ON_ONCE(1);
+	}
+}
+
+unsigned long arch_scale_cpu_capacity(int cpu)
+{
+	if (static_branch_unlikely(&arch_hybrid_cap_scale_key))
+		return READ_ONCE(per_cpu_ptr(arch_cpu_scale, cpu)->capacity);
+
+	return SCHED_CAPACITY_SCALE;
+}
+EXPORT_SYMBOL_GPL(arch_scale_cpu_capacity);
+
 static void scale_freq_tick(u64 acnt, u64 mcnt)
 {
 	u64 freq_scale;
+	u64 freq_ratio;
 
 	if (!arch_scale_freq_invariant())
 		return;
@@ -357,7 +441,12 @@ static void scale_freq_tick(u64 acnt, u6
 	if (check_shl_overflow(acnt, 2*SCHED_CAPACITY_SHIFT, &acnt))
 		goto error;
 
-	if (check_mul_overflow(mcnt, arch_max_freq_ratio, &mcnt) || !mcnt)
+	if (static_branch_unlikely(&arch_hybrid_cap_scale_key))
+		freq_ratio = READ_ONCE(this_cpu_ptr(arch_cpu_scale)->freq_ratio);
+	else
+		freq_ratio = arch_max_freq_ratio;
+
+	if (check_mul_overflow(mcnt, freq_ratio, &mcnt) || !mcnt)
 		goto error;
 
 	freq_scale = div64_u64(acnt, mcnt);

[PATCH v1 3/3] cpufreq: intel_pstate: Set asymmetric CPU capacity on hybrid systems

[Rafael J. Wysocki]

From: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

Make intel_pstate use the HWP_HIGHEST_PERF values from
MSR_HWP_CAPABILITIES to set asymmetric CPU capacity information
via the previously introduced arch_set_cpu_capacity() on hybrid
systems without SMT.

Setting asymmetric CPU capacity is generally necessary to allow the
scheduler to compute task sizes in a consistent way across all CPUs
in a system where they differ by capacity.  That, in turn, should help
to improve scheduling decisions.  It is also necessary for the schedutil
cpufreq governor to operate as expected on hybrid systems where tasks
migrate between CPUs of different capacities.

The underlying observation is that intel_pstate already uses
MSR_HWP_CAPABILITIES to get CPU performance information which is
exposed by it via sysfs and CPU performance scaling is based on it.
Thus using this information for setting asymmetric CPU capacity is
consistent with what the driver has been doing already.  Moreover,
HWP_HIGHEST_PERF reflects the maximum capacity of a given CPU including
both the instructions-per-cycle (IPC) factor and the maximum turbo
frequency and the units in which that value is expressed are the same
for all CPUs in the system, so the maximum capacity ratio between two
CPUs can be obtained by computing the ratio of their HWP_HIGHEST_PERF
values.  Of course, in principle that capacity ratio need not be
directly applicable at lower frequencies, so using it for providing the
asymmetric CPU capacity information to the scheduler is a rough
approximation, but it is as good as it gets.  Also, measurements
indicate that this approximation is not too bad in practice.

If the given system is hybrid and non-SMT, the new code disables ITMT
support in the scheduler (because it may get in the way of asymmetric CPU
capacity code in the scheduler that automatically gets enabled by setting
asymmetric CPU capacity) after initializing all online CPUs and finds
the one with the maximum HWP_HIGHEST_PERF value.  Next, it computes the
capacity number for each (online) CPU by dividing the product of its
HWP_HIGHEST_PERF and SCHED_CAPACITY_SCALE by the maximum HWP_HIGHEST_PERF.

When a CPU goes offline, its capacity is reset to SCHED_CAPACITY_SCALE
and if it is the one with the maximum HWP_HIGHEST_PERF value, the
capacity numbers for all of the other online CPUs are recomputed.  This
also takes care of a cleanup during driver operation mode changes.

Analogously, when a new CPU goes online, its capacity number is updated
and if its HWP_HIGHEST_PERF value is greater than the current maximum
one, the capacity numbers for all of the other online CPUs are
recomputed.

The case when the driver is notified of a CPU capacity change, either
through the HWP interrupt or through an ACPI notification, is handled
similarly to the CPU online case above, except that if the target CPU
is the current highest-capacity one and its capacity is reduced, the
capacity numbers for all of the other online CPUs need to be recomputed
either.

If the driver's "no_trubo" sysfs attribute is updated, all of the CPU
capacity information is computed from scratch to reflect the new turbo
status.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/intel_pstate.c |  210 ++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 206 insertions(+), 4 deletions(-)

Index: linux-pm/drivers/cpufreq/intel_pstate.c
===================================================================
--- linux-pm.orig/drivers/cpufreq/intel_pstate.c
+++ linux-pm/drivers/cpufreq/intel_pstate.c
@@ -16,6 +16,7 @@
 #include <linux/tick.h>
 #include <linux/slab.h>
 #include <linux/sched/cpufreq.h>
+#include <linux/sched/smt.h>
 #include <linux/list.h>
 #include <linux/cpu.h>
 #include <linux/cpufreq.h>
@@ -215,6 +216,7 @@ struct global_params {
  * @hwp_req_cached:	Cached value of the last HWP Request MSR
  * @hwp_cap_cached:	Cached value of the last HWP Capabilities MSR
  * @last_io_update:	Last time when IO wake flag was set
+ * @capacity_perf:	Highest perf used for scale invariance
  * @sched_flags:	Store scheduler flags for possible cross CPU update
  * @hwp_boost_min:	Last HWP boosted min performance
  * @suspended:		Whether or not the driver has been suspended.
@@ -253,6 +255,7 @@ struct cpudata {
 	u64 hwp_req_cached;
 	u64 hwp_cap_cached;
 	u64 last_io_update;
+	unsigned int capacity_perf;
 	unsigned int sched_flags;
 	u32 hwp_boost_min;
 	bool suspended;
@@ -295,6 +298,7 @@ static int hwp_mode_bdw __ro_after_init;
 static bool per_cpu_limits __ro_after_init;
 static bool hwp_forced __ro_after_init;
 static bool hwp_boost __read_mostly;
+static bool hwp_is_hybrid;
 
 static struct cpufreq_driver *intel_pstate_driver __read_mostly;
 
@@ -934,6 +938,106 @@ static struct freq_attr *hwp_cpufreq_att
 	NULL,
 };
 
+static struct cpudata *hybrid_max_perf_cpu __read_mostly;
+/*
+ * Protects hybrid_max_perf_cpu, the capacity_perf fields in struct cpudata,
+ * and the x86 arch scale-invariance information from concurrent updates.
+ */
+static DEFINE_MUTEX(hybrid_capacity_lock);
+
+static void hybrid_set_cpu_capacity(struct cpudata *cpu)
+{
+	arch_set_cpu_capacity(cpu->cpu, cpu->capacity_perf,
+			      hybrid_max_perf_cpu->capacity_perf,
+			      cpu->capacity_perf,
+			      cpu->pstate.max_pstate_physical);
+
+	pr_debug("CPU%d: perf = %u, max. perf = %u, base perf = %d\n", cpu->cpu,
+		 cpu->capacity_perf, hybrid_max_perf_cpu->capacity_perf,
+		 cpu->pstate.max_pstate_physical);
+}
+
+static void hybrid_clear_cpu_capacity(unsigned int cpunum)
+{
+	arch_set_cpu_capacity(cpunum, 1, 1, 1, 1);
+}
+
+static void hybrid_get_capacity_perf(struct cpudata *cpu)
+{
+	if (READ_ONCE(global.no_turbo)) {
+		cpu->capacity_perf = cpu->pstate.max_pstate_physical;
+		return;
+	}
+
+	cpu->capacity_perf = HWP_HIGHEST_PERF(READ_ONCE(cpu->hwp_cap_cached));
+}
+
+static void hybrid_set_capacity_of_cpus(void)
+{
+	int cpunum;
+
+	for_each_online_cpu(cpunum) {
+		struct cpudata *cpu = all_cpu_data[cpunum];
+
+		if (cpu)
+			hybrid_set_cpu_capacity(cpu);
+	}
+}
+
+static void hybrid_update_cpu_scaling(void)
+{
+	struct cpudata *max_perf_cpu = NULL;
+	unsigned int max_cap_perf = 0;
+	int cpunum;
+
+	for_each_online_cpu(cpunum) {
+		struct cpudata *cpu = all_cpu_data[cpunum];
+
+		if (!cpu)
+			continue;
+
+		/*
+		 * During initialization, CPU performance at full capacity needs
+		 * to be determined.
+		 */
+		if (!hybrid_max_perf_cpu)
+			hybrid_get_capacity_perf(cpu);
+
+		/*
+		 * If hybrid_max_perf_cpu is not NULL at this point, it is
+		 * being replaced, so don't take it into account when looking
+		 * for the new one.
+		 */
+		if (cpu == hybrid_max_perf_cpu)
+			continue;
+
+		if (cpu->capacity_perf > max_cap_perf) {
+			max_cap_perf = cpu->capacity_perf;
+			max_perf_cpu = cpu;
+		}
+	}
+
+	if (max_perf_cpu) {
+		hybrid_max_perf_cpu = max_perf_cpu;
+		hybrid_set_capacity_of_cpus();
+	} else {
+		pr_info("Found no CPUs with nonzero maximum performance\n");
+		/* Revert to the flat CPU capacity structure. */
+		for_each_online_cpu(cpunum)
+			hybrid_clear_cpu_capacity(cpunum);
+	}
+}
+
+static void hybrid_init_cpu_scaling(void)
+{
+	mutex_lock(&hybrid_capacity_lock);
+
+	hybrid_max_perf_cpu = NULL;
+	hybrid_update_cpu_scaling();
+
+	mutex_unlock(&hybrid_capacity_lock);
+}
+
 static void __intel_pstate_get_hwp_cap(struct cpudata *cpu)
 {
 	u64 cap;
@@ -962,6 +1066,43 @@ static void intel_pstate_get_hwp_cap(str
 	}
 }
 
+static void hybrid_update_capacity(struct cpudata *cpu)
+{
+	unsigned int max_cap_perf;
+
+	mutex_lock(&hybrid_capacity_lock);
+
+	if (!hybrid_max_perf_cpu)
+		goto unlock;
+
+	/*
+	 * The maximum performance of the CPU may have changed, but assume
+	 * that the performance of the other CPUs has not changed.
+	 */
+	max_cap_perf = hybrid_max_perf_cpu->capacity_perf;
+
+	intel_pstate_get_hwp_cap(cpu);
+
+	hybrid_get_capacity_perf(cpu);
+	/* Should hybrid_max_perf_cpu be replaced by this CPU? */
+	if (cpu->capacity_perf > max_cap_perf) {
+		hybrid_max_perf_cpu = cpu;
+		hybrid_set_capacity_of_cpus();
+		goto unlock;
+	}
+
+	/* If this CPU is hybrid_max_perf_cpu, should it be replaced? */
+	if (cpu == hybrid_max_perf_cpu && cpu->capacity_perf < max_cap_perf) {
+		hybrid_update_cpu_scaling();
+		goto unlock;
+	}
+
+	hybrid_set_cpu_capacity(cpu);
+
+unlock:
+	mutex_unlock(&hybrid_capacity_lock);
+}
+
 static void intel_pstate_hwp_set(unsigned int cpu)
 {
 	struct cpudata *cpu_data = all_cpu_data[cpu];
@@ -1070,6 +1211,22 @@ static void intel_pstate_hwp_offline(str
 		value |= HWP_ENERGY_PERF_PREFERENCE(HWP_EPP_POWERSAVE);
 
 	wrmsrl_on_cpu(cpu->cpu, MSR_HWP_REQUEST, value);
+
+	mutex_lock(&hybrid_capacity_lock);
+
+	if (!hybrid_max_perf_cpu) {
+		mutex_unlock(&hybrid_capacity_lock);
+
+		return;
+	}
+
+	if (hybrid_max_perf_cpu == cpu)
+		hybrid_update_cpu_scaling();
+
+	mutex_unlock(&hybrid_capacity_lock);
+
+	/* Reset the capacity of the CPU going offline to the initial value. */
+	hybrid_clear_cpu_capacity(cpu->cpu);
 }
 
 #define POWER_CTL_EE_ENABLE	1
@@ -1165,21 +1322,41 @@ static void __intel_pstate_update_max_fr
 static void intel_pstate_update_limits(unsigned int cpu)
 {
 	struct cpufreq_policy *policy = cpufreq_cpu_acquire(cpu);
+	struct cpudata *cpudata;
 
 	if (!policy)
 		return;
 
-	__intel_pstate_update_max_freq(all_cpu_data[cpu], policy);
+	cpudata = all_cpu_data[cpu];
+
+	__intel_pstate_update_max_freq(cpudata, policy);
+
+	/* Prevent the driver from being unregistered now. */
+	mutex_lock(&intel_pstate_driver_lock);
 
 	cpufreq_cpu_release(policy);
+
+	hybrid_update_capacity(cpudata);
+
+	mutex_unlock(&intel_pstate_driver_lock);
 }
 
 static void intel_pstate_update_limits_for_all(void)
 {
 	int cpu;
 
-	for_each_possible_cpu(cpu)
-		intel_pstate_update_limits(cpu);
+	for_each_possible_cpu(cpu) {
+		struct cpufreq_policy *policy = cpufreq_cpu_acquire(cpu);
+
+		if (!policy)
+			continue;
+
+		__intel_pstate_update_max_freq(all_cpu_data[cpu], policy);
+
+		cpufreq_cpu_release(policy);
+	}
+
+	hybrid_init_cpu_scaling();
 }
 
 /************************** sysfs begin ************************/
@@ -1618,6 +1795,13 @@ static void intel_pstate_notify_work(str
 		__intel_pstate_update_max_freq(cpudata, policy);
 
 		cpufreq_cpu_release(policy);
+
+		/*
+		 * The driver will not be unregistered while this function is
+		 * running, so update the capacity without acquiring the driver
+		 * lock.
+		 */
+		hybrid_update_capacity(cpudata);
 	}
 
 	wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_STATUS, 0);
@@ -2034,8 +2218,10 @@ static void intel_pstate_get_cpu_pstates
 
 		if (pstate_funcs.get_cpu_scaling) {
 			cpu->pstate.scaling = pstate_funcs.get_cpu_scaling(cpu->cpu);
-			if (cpu->pstate.scaling != perf_ctl_scaling)
+			if (cpu->pstate.scaling != perf_ctl_scaling) {
 				intel_pstate_hybrid_hwp_adjust(cpu);
+				hwp_is_hybrid = true;
+			}
 		} else {
 			cpu->pstate.scaling = perf_ctl_scaling;
 		}
@@ -2703,6 +2889,8 @@ static int intel_pstate_cpu_online(struc
 		 */
 		intel_pstate_hwp_reenable(cpu);
 		cpu->suspended = false;
+
+		hybrid_update_capacity(cpu);
 	}
 
 	return 0;
@@ -3143,6 +3331,20 @@ static int intel_pstate_register_driver(
 
 	global.min_perf_pct = min_perf_pct_min();
 
+	/*
+	 * On hybrid systems, use asym capacity instead of ITMT, but because
+	 * the capacity of SMT threads is not deterministic even approximately,
+	 * do not do that when SMT is in use.
+	 */
+	if (hwp_is_hybrid && !sched_smt_active() &&
+	    arch_enable_hybrid_capacity_scale()) {
+		sched_clear_itmt_support();
+
+		hybrid_init_cpu_scaling();
+
+		arch_rebuild_sched_domains();
+	}
+
 	return 0;
 }