[PATCH v4 0/3] arch_topology, ACPI: populate cpu capacity from CPPC

[PATCH v4 0/3] arch_topology, ACPI: populate cpu capacity from CPPC

[Ionela Voinescu]

Hi all,

v3->v4:
 - v3 can be found at [3]
 - rebased on linux-next 20220310 which contains patches at [4]
   requested by Rafael
 - 2/3 fixed obsolete comment as reported by Yicong at [5]
 - Kept Acked-by,Tested-by as v4 has no code changes compared
   to v3, but only a comment fix.

v2->v3:
 - v2 can be found at [2]
 - Added sanity checking on perf_caps.highest_perf

v1->v2:
 - v1 can be found at [1]
 - Changed debug prints to the format used on the DT path
 - s/init_cpu_capacity_cppc/topology_init_cpu_capacity_cppc

Patches are based on linux next 20220310.

[1] https://lore.kernel.org/lkml/20210514095339.12979-1-ionela.voinescu@arm.com/
[2] https://lore.kernel.org/lkml/20210824105651.28660-1-ionela.voinescu@arm.com/
[3] https://lore.kernel.org/lkml/20220302180913.13229-1-ionela.voinescu@arm.com/
[4] https://lore.kernel.org/linux-acpi/20220214101450.356047-1-ray.huang@amd.com/
[5] https://lore.kernel.org/lkml/477748c7-ae9e-712b-90ad-b04a6767a996@huawei.com/


Thanks,
Ionela.

Ionela Voinescu (3):
  x86, ACPI: rename init_freq_invariance_cppc to
    arch_init_invariance_cppc
  arch_topology: obtain cpu capacity using information from CPPC
  arm64, topology: enable use of init_cpu_capacity_cppc()

 arch/arm64/include/asm/topology.h |  4 +++
 arch/x86/include/asm/topology.h   |  2 +-
 drivers/acpi/cppc_acpi.c          |  6 ++---
 drivers/base/arch_topology.c      | 45 ++++++++++++++++++++++++++++---
 include/linux/arch_topology.h     |  4 +++
 5 files changed, 54 insertions(+), 7 deletions(-)

-- 
2.25.1

[PATCH v4 1/3] x86, ACPI: rename init_freq_invariance_cppc to arch_init_invariance_cppc

[Ionela Voinescu]

init_freq_invariance_cppc() was called in acpi_cppc_processor_probe(),
after CPU performance information and controls were populated from the
per-cpu _CPC objects.

But these _CPC objects provide information that helps with both CPU
(u-arch) and frequency invariance. Therefore, change the function name
to a more generic one, while adding the arch_ prefix, as this function
is expected to be defined differently by different architectures.

Signed-off-by: Ionela Voinescu <ionela.voinescu@arm.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Tested-by: Valentin Schneider <valentin.schneider@arm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Giovanni Gherdovich <ggherdovich@suse.cz>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
---
 arch/x86/include/asm/topology.h | 2 +-
 drivers/acpi/cppc_acpi.c        | 6 +++---
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 127b693273e3..9619385bf749 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -228,7 +228,7 @@ static inline void init_freq_invariance(bool secondary, bool cppc_ready)
 
 #ifdef CONFIG_ACPI_CPPC_LIB
 void init_freq_invariance_cppc(void);
-#define init_freq_invariance_cppc init_freq_invariance_cppc
+#define arch_init_invariance_cppc init_freq_invariance_cppc
 
 bool amd_set_max_freq_ratio(u64 *ratio);
 #else
diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index 866560cbb082..bfd142ab4e07 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -633,8 +633,8 @@ static bool is_cppc_supported(int revision, int num_ent)
  *  )
  */
 
-#ifndef init_freq_invariance_cppc
-static inline void init_freq_invariance_cppc(void) { }
+#ifndef arch_init_invariance_cppc
+static inline void arch_init_invariance_cppc(void) { }
 #endif
 
 /**
@@ -816,7 +816,7 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr)
 		goto out_free;
 	}
 
-	init_freq_invariance_cppc();
+	arch_init_invariance_cppc();
 
 	kfree(output.pointer);
 	return 0;
-- 
2.25.1

[PATCH v4 2/3] arch_topology: obtain cpu capacity using information from CPPC

[Ionela Voinescu]

Define topology_init_cpu_capacity_cppc() to use highest performance
values from _CPC objects to obtain and set maximum capacity information
for each CPU. acpi_cppc_processor_probe() is a good point at which to
trigger the initialization of CPU (u-arch) capacity values, as at this
point the highest performance values can be obtained from each CPU's
_CPC objects. Architectures can therefore use this functionality
through arch_init_invariance_cppc().

The performance scale used by CPPC is a unified scale for all CPUs in
the system. Therefore, by obtaining the raw highest performance values
from the _CPC objects, and normalizing them on the [0, 1024] capacity
scale, used by the task scheduler, we obtain the CPU capacity of each
CPU.

While an ACPI Notify(0x85) could alert about a change in the highest
performance value, which should in turn retrigger the CPU capacity
computations, this notification is not currently handled by the ACPI
processor driver. When supported, a call to arch_init_invariance_cppc()
would perform the update.

Signed-off-by: Ionela Voinescu <ionela.voinescu@arm.com>
Acked-by: Sudeep Holla <sudeep.holla@arm.com>
Tested-by: Valentin Schneider <valentin.schneider@arm.com>
Tested-by: Yicong Yang <yangyicong@hisilicon.com>
Cc: Sudeep Holla <sudeep.holla@arm.com>
---
 drivers/base/arch_topology.c  | 45 ++++++++++++++++++++++++++++++++---
 include/linux/arch_topology.h |  4 ++++
 2 files changed, 46 insertions(+), 3 deletions(-)

diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
index 976154140f0b..1d6636ebaac5 100644
--- a/drivers/base/arch_topology.c
+++ b/drivers/base/arch_topology.c
@@ -339,6 +339,46 @@ bool __init topology_parse_cpu_capacity(struct device_node *cpu_node, int cpu)
 	return !ret;
 }
 
+#ifdef CONFIG_ACPI_CPPC_LIB
+#include <acpi/cppc_acpi.h>
+
+void topology_init_cpu_capacity_cppc(void)
+{
+	struct cppc_perf_caps perf_caps;
+	int cpu;
+
+	if (likely(acpi_disabled || !acpi_cpc_valid()))
+		return;
+
+	raw_capacity = kcalloc(num_possible_cpus(), sizeof(*raw_capacity),
+			       GFP_KERNEL);
+	if (!raw_capacity)
+		return;
+
+	for_each_possible_cpu(cpu) {
+		if (!cppc_get_perf_caps(cpu, &perf_caps) &&
+		    (perf_caps.highest_perf >= perf_caps.nominal_perf) &&
+		    (perf_caps.highest_perf >= perf_caps.lowest_perf)) {
+			raw_capacity[cpu] = perf_caps.highest_perf;
+			pr_debug("cpu_capacity: CPU%d cpu_capacity=%u (raw).\n",
+				 cpu, raw_capacity[cpu]);
+			continue;
+		}
+
+		pr_err("cpu_capacity: CPU%d missing/invalid highest performance.\n", cpu);
+		pr_err("cpu_capacity: partial information: fallback to 1024 for all CPUs\n");
+		goto exit;
+	}
+
+	topology_normalize_cpu_scale();
+	schedule_work(&update_topology_flags_work);
+	pr_debug("cpu_capacity: cpu_capacity initialization done\n");
+
+exit:
+	free_raw_capacity();
+}
+#endif
+
 #ifdef CONFIG_CPU_FREQ
 static cpumask_var_t cpus_to_visit;
 static void parsing_done_workfn(struct work_struct *work);
@@ -387,9 +427,8 @@ static int __init register_cpufreq_notifier(void)
 	int ret;
 
 	/*
-	 * on ACPI-based systems we need to use the default cpu capacity
-	 * until we have the necessary code to parse the cpu capacity, so
-	 * skip registering cpufreq notifier.
+	 * On ACPI-based systems skip registering cpufreq notifier as cpufreq
+	 * information is not needed for cpu capacity initialization.
 	 */
 	if (!acpi_disabled || !raw_capacity)
 		return -EINVAL;
diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h
index cce6136b300a..58cbe18d825c 100644
--- a/include/linux/arch_topology.h
+++ b/include/linux/arch_topology.h
@@ -11,6 +11,10 @@
 void topology_normalize_cpu_scale(void);
 int topology_update_cpu_topology(void);
 
+#ifdef CONFIG_ACPI_CPPC_LIB
+void topology_init_cpu_capacity_cppc(void);
+#endif
+
 struct device_node;
 bool topology_parse_cpu_capacity(struct device_node *cpu_node, int cpu);
 
-- 
2.25.1

[PATCH v4 3/3] arm64, topology: enable use of init_cpu_capacity_cppc()

[Ionela Voinescu]

Now that the arch topology driver provides a method of setting CPU
capacity values based on information on highest performance from CPPC,
use this functionality on arm64 platforms.

Signed-off-by: Ionela Voinescu <ionela.voinescu@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Tested-by: Valentin Schneider <valentin.schneider@arm.com>
Tested-by: Yicong Yang <yangyicong@hisilicon.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/topology.h | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
index f386b90a79c8..9fab663dd2de 100644
--- a/arch/arm64/include/asm/topology.h
+++ b/arch/arm64/include/asm/topology.h
@@ -24,6 +24,10 @@ void update_freq_counters_refs(void);
 #define arch_scale_freq_capacity topology_get_freq_scale
 #define arch_scale_freq_invariant topology_scale_freq_invariant
 
+#ifdef CONFIG_ACPI_CPPC_LIB
+#define arch_init_invariance_cppc topology_init_cpu_capacity_cppc
+#endif
+
 /* Replace task scheduler's default cpu-invariant accounting */
 #define arch_scale_cpu_capacity topology_get_cpu_scale
 
-- 
2.25.1

Re: [PATCH v4 0/3] arch_topology, ACPI: populate cpu capacity from CPPC

[Rafael J. Wysocki]

On Thu, Mar 10, 2022 at 4:05 PM Ionela Voinescu <ionela.voinescu@arm.com> wrote:
>
> Hi all,
>
> v3->v4:
>  - v3 can be found at [3]
>  - rebased on linux-next 20220310 which contains patches at [4]
>    requested by Rafael
>  - 2/3 fixed obsolete comment as reported by Yicong at [5]
>  - Kept Acked-by,Tested-by as v4 has no code changes compared
>    to v3, but only a comment fix.

All patches in the series applied as 5.18 material, thanks!