Include support for Intel HWP

0631-cpufreq-Allow-restricting-to-internal-governors-only.patch

@@ -0,0 +1,62 @@
+From c0a69ba8e4210bf42cc545afd02ad7fe1135fe96 Mon Sep 17 00:00:00 2001
+From: Jason Andryuk <[email protected]>
+Date: Wed, 10 Aug 2022 15:29:32 -0400
+Subject: [PATCH 01/13] cpufreq: Allow restricting to internal governors only
+
+For hwp, the standard governors are not usable, and only the internal
+one is applicable.  Add the cpufreq_governor_internal boolean to
+indicate when an internal governor, like hwp-internal, will be used.
+This is set during presmp_initcall, so that it can suppress governor
+registration during initcall.  Only a governor with a name containing
+"-internal" will be allowed in that case.
+
+This way, the unuseable governors are not registered, so they internal
+one is the only one returned to userspace.  This means incompatible
+governors won't be advertised to userspace.
+
+Signed-off-by: Jason Andryuk <[email protected]>
+Acked-by: Jan Beulich <[email protected]>
+---
+ xen/drivers/cpufreq/cpufreq.c      | 5 +++++
+ xen/include/acpi/cpufreq/cpufreq.h | 2 ++
+ 2 files changed, 7 insertions(+)
+
+diff --git a/xen/drivers/cpufreq/cpufreq.c b/xen/drivers/cpufreq/cpufreq.c
+index a94520ee57ac..1fdd63d7b564 100644
+--- a/xen/drivers/cpufreq/cpufreq.c
++++ b/xen/drivers/cpufreq/cpufreq.c
+@@ -57,6 +57,7 @@ struct cpufreq_dom {
+ };
+ static LIST_HEAD_READ_MOSTLY(cpufreq_dom_list_head);
+
++bool __read_mostly cpufreq_governor_internal;
+ struct cpufreq_governor *__read_mostly cpufreq_opt_governor;
+ LIST_HEAD_READ_MOSTLY(cpufreq_governor_list);
+
+@@ -122,6 +123,10 @@ int __init cpufreq_register_governor(struct cpufreq_governor *governor)
+     if (!governor)
+         return -EINVAL;
+
++    if (cpufreq_governor_internal &&
++        strstr(governor->name, "-internal") == NULL)
++        return -EINVAL;
++
+     if (__find_governor(governor->name) != NULL)
+         return -EEXIST;
+
+diff --git a/xen/include/acpi/cpufreq/cpufreq.h b/xen/include/acpi/cpufreq/cpufreq.h
+index 35dcf21e8f0c..0da32ef51903 100644
+--- a/xen/include/acpi/cpufreq/cpufreq.h
++++ b/xen/include/acpi/cpufreq/cpufreq.h
+@@ -114,6 +114,8 @@ extern struct cpufreq_governor cpufreq_gov_userspace;
+ extern struct cpufreq_governor cpufreq_gov_performance;
+ extern struct cpufreq_governor cpufreq_gov_powersave;
+
++extern bool cpufreq_governor_internal;
++
+ extern struct list_head cpufreq_governor_list;
+
+ extern int cpufreq_register_governor(struct cpufreq_governor *governor);
+-- 
+2.37.3
+

0632-cpufreq-Add-perf_freq-to-cpuinfo.patch

@@ -0,0 +1,61 @@
+From fed49894b171851eefce5a91900217a57cac396e Mon Sep 17 00:00:00 2001
+From: Jason Andryuk <[email protected]>
+Date: Wed, 10 Aug 2022 15:29:33 -0400
+Subject: [PATCH 02/13] cpufreq: Add perf_freq to cpuinfo
+
+acpi-cpufreq scales the aperf/mperf measurements by max_freq, but HWP
+needs to scale by base frequency.  Settings max_freq to base_freq
+"works" but the code is not obvious, and returning values to userspace
+is tricky.  Add an additonal perf_freq member which is used for scaling
+aperf/mperf measurements.
+
+Signed-off-by: Jason Andryuk <[email protected]>
+Acked-by: Jan Beulich <[email protected]>
+---
+ xen/arch/x86/acpi/cpufreq/cpufreq.c | 2 +-
+ xen/drivers/cpufreq/utility.c       | 1 +
+ xen/include/acpi/cpufreq/cpufreq.h  | 3 +++
+ 3 files changed, 5 insertions(+), 1 deletion(-)
+
+diff --git a/xen/arch/x86/acpi/cpufreq/cpufreq.c b/xen/arch/x86/acpi/cpufreq/cpufreq.c
+index c27cbb2304f2..ded0150b3b00 100644
+--- a/xen/arch/x86/acpi/cpufreq/cpufreq.c
++++ b/xen/arch/x86/acpi/cpufreq/cpufreq.c
+@@ -317,7 +317,7 @@ unsigned int get_measured_perf(unsigned int cpu, unsigned int flag)
+     else
+         perf_percent = 0;
+
+-    return policy->cpuinfo.max_freq * perf_percent / 100;
++    return policy->cpuinfo.perf_freq * perf_percent / 100;
+ }
+
+ static unsigned int cf_check get_cur_freq_on_cpu(unsigned int cpu)
+diff --git a/xen/drivers/cpufreq/utility.c b/xen/drivers/cpufreq/utility.c
+index 9eb7ecedcd29..6831f62851cd 100644
+--- a/xen/drivers/cpufreq/utility.c
++++ b/xen/drivers/cpufreq/utility.c
+@@ -236,6 +236,7 @@ int cpufreq_frequency_table_cpuinfo(struct cpufreq_policy *policy,
+
+     policy->min = policy->cpuinfo.min_freq = min_freq;
+     policy->max = policy->cpuinfo.max_freq = max_freq;
++    policy->cpuinfo.perf_freq = max_freq;
+     policy->cpuinfo.second_max_freq = second_max_freq;
+
+     if (policy->min == ~0)
+diff --git a/xen/include/acpi/cpufreq/cpufreq.h b/xen/include/acpi/cpufreq/cpufreq.h
+index 0da32ef51903..a06aa92f6209 100644
+--- a/xen/include/acpi/cpufreq/cpufreq.h
++++ b/xen/include/acpi/cpufreq/cpufreq.h
+@@ -37,6 +37,9 @@ extern struct acpi_cpufreq_data *cpufreq_drv_data[NR_CPUS];
+ struct cpufreq_cpuinfo {
+     unsigned int        max_freq;
+     unsigned int        second_max_freq;    /* P1 if Turbo Mode is on */
++    unsigned int        perf_freq; /* Scaling freq for aperf/mpref.
++                                      acpi-cpufreq uses max_freq, but HWP uses
++                                      base_freq.*/
+     unsigned int        min_freq;
+     unsigned int        transition_latency; /* in 10^(-9) s = nanoseconds */
+ };
+-- 
+2.37.3
+

0633-cpufreq-Export-intel_feature_detect.patch

@@ -0,0 +1,55 @@
+From 6b5101014c6e4ee32d13993e0d3d19857817c228 Mon Sep 17 00:00:00 2001
+From: Jason Andryuk <[email protected]>
+Date: Wed, 10 Aug 2022 15:29:34 -0400
+Subject: [PATCH 03/13] cpufreq: Export intel_feature_detect
+
+Export feature_detect as intel_feature_detect so it can be re-used by
+HWP.
+
+Signed-off-by: Jason Andryuk <[email protected]>
+---
+ xen/arch/x86/acpi/cpufreq/cpufreq.c | 8 ++++++--
+ xen/include/acpi/cpufreq/cpufreq.h  | 2 ++
+ 2 files changed, 8 insertions(+), 2 deletions(-)
+
+diff --git a/xen/arch/x86/acpi/cpufreq/cpufreq.c b/xen/arch/x86/acpi/cpufreq/cpufreq.c
+index ded0150b3b00..b5eb869227a7 100644
+--- a/xen/arch/x86/acpi/cpufreq/cpufreq.c
++++ b/xen/arch/x86/acpi/cpufreq/cpufreq.c
+@@ -340,9 +340,8 @@ static unsigned int cf_check get_cur_freq_on_cpu(unsigned int cpu)
+     return extract_freq(get_cur_val(cpumask_of(cpu)), data);
+ }
+
+-static void cf_check feature_detect(void *info)
++void intel_feature_detect(struct cpufreq_policy *policy)
+ {
+-    struct cpufreq_policy *policy = info;
+     unsigned int eax;
+
+     eax = cpuid_eax(6);
+@@ -354,6 +353,11 @@ static void cf_check feature_detect(void *info)
+     }
+ }
+
++static void cf_check feature_detect(void *info)
++{
++    intel_feature_detect((struct cpufreq_policy *)info);
++}
++
+ static unsigned int check_freqs(const cpumask_t *mask, unsigned int freq,
+                                 struct acpi_cpufreq_data *data)
+ {
+diff --git a/xen/include/acpi/cpufreq/cpufreq.h b/xen/include/acpi/cpufreq/cpufreq.h
+index a06aa92f6209..0f334d2a432b 100644
+--- a/xen/include/acpi/cpufreq/cpufreq.h
++++ b/xen/include/acpi/cpufreq/cpufreq.h
+@@ -243,4 +243,6 @@ int write_userspace_scaling_setspeed(unsigned int cpu, unsigned int freq);
+ void cpufreq_dbs_timer_suspend(void);
+ void cpufreq_dbs_timer_resume(void);
+
++void intel_feature_detect(struct cpufreq_policy *policy);
++
+ #endif /* __XEN_CPUFREQ_PM_H__ */
+-- 
+2.37.3
+