2022-04-16 01:55:18

by Thomas Gleixner

Subject: [patch 04/10] x86/aperfmperf: Untangle Intel and AMD frequency invariance init

AMD boot CPU initialization happens late via ACPI/CPPC which prevents the
Intel parts from being marked __init.

Split out the common code and provide a dedicated interface for the AMD
initialization and mark the Intel specific code and data __init.

The remaining text size is almost cut in half:

text: 2614 -> 1350
init.text: 0 -> 786

Signed-off-by: Thomas Gleixner <[email protected]>
---
arch/x86/include/asm/topology.h | 13 ++------
arch/x86/kernel/acpi/cppc.c | 29 +++++++-----------
arch/x86/kernel/cpu/aperfmperf.c | 62 ++++++++++++++++++++-------------------
arch/x86/kernel/smpboot.c | 2 -
4 files changed, 49 insertions(+), 57 deletions(-)

--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -216,24 +216,19 @@ extern void arch_scale_freq_tick(void);
#define arch_scale_freq_tick arch_scale_freq_tick

extern void arch_set_max_freq_ratio(bool turbo_disabled);
-extern void bp_init_freq_invariance(bool cppc_ready);
+extern void freq_invariance_set_perf_ratio(u64 ratio, bool turbo_disabled);
+extern void bp_init_freq_invariance(void);
extern void ap_init_freq_invariance(void);
#else
static inline void arch_set_max_freq_ratio(bool turbo_disabled) { }
-static inline void bp_init_freq_invariance(bool cppc_ready) { }
+static inline void freq_invariance_set_perf_ratio(u64 ratio, bool turbo_disabled) { }
+static inline void bp_init_freq_invariance(void) { }
static inline void ap_init_freq_invariance(void) { }
#endif

#ifdef CONFIG_ACPI_CPPC_LIB
void init_freq_invariance_cppc(void);
#define arch_init_invariance_cppc init_freq_invariance_cppc
-
-bool amd_set_max_freq_ratio(u64 *ratio);
-#else
-static inline bool amd_set_max_freq_ratio(u64 *ratio)
-{
- return false;
-}
#endif

#endif /* _ASM_X86_TOPOLOGY_H */
--- a/arch/x86/kernel/acpi/cppc.c
+++ b/arch/x86/kernel/acpi/cppc.c
@@ -50,20 +50,17 @@ int cpc_write_ffh(int cpunum, struct cpc
return err;
}

-bool amd_set_max_freq_ratio(u64 *ratio)
+static void amd_set_max_freq_ratio(void)
{
struct cppc_perf_caps perf_caps;
u64 highest_perf, nominal_perf;
u64 perf_ratio;
int rc;

- if (!ratio)
- return false;
-
rc = cppc_get_perf_caps(0, &perf_caps);
if (rc) {
pr_debug("Could not retrieve perf counters (%d)\n", rc);
- return false;
+ return;
}

highest_perf = amd_get_highest_perf();
@@ -71,7 +68,7 @@ bool amd_set_max_freq_ratio(u64 *ratio)

if (!highest_perf || !nominal_perf) {
pr_debug("Could not retrieve highest or nominal performance\n");
- return false;
+ return;
}

perf_ratio = div_u64(highest_perf * SCHED_CAPACITY_SCALE, nominal_perf);
@@ -79,26 +76,24 @@ bool amd_set_max_freq_ratio(u64 *ratio)
perf_ratio = (perf_ratio + SCHED_CAPACITY_SCALE) >> 1;
if (!perf_ratio) {
pr_debug("Non-zero highest/nominal perf values led to a 0 ratio\n");
- return false;
+ return;
}

- *ratio = perf_ratio;
- arch_set_max_freq_ratio(false);
-
- return true;
+ freq_invariance_set_perf_ratio(perf_ratio, false);
}

static DEFINE_MUTEX(freq_invariance_lock);

void init_freq_invariance_cppc(void)
{
- static bool secondary;
+ static bool init_done;

- mutex_lock(&freq_invariance_lock);
-
- if (!secondary)
- bp_init_freq_invariance(true);
- secondary = true;
+ if (!cpu_feature_enabled(X86_FEATURE_APERFMPERF))
+ return;

+ mutex_lock(&freq_invariance_lock);
+ if (!init_done)
+ amd_set_max_freq_ratio();
+ init_done = true;
mutex_unlock(&freq_invariance_lock);
}
--- a/arch/x86/kernel/cpu/aperfmperf.c
+++ b/arch/x86/kernel/cpu/aperfmperf.c
@@ -206,7 +206,7 @@ void arch_set_max_freq_ratio(bool turbo_
}
EXPORT_SYMBOL_GPL(arch_set_max_freq_ratio);

-static bool turbo_disabled(void)
+static bool __init turbo_disabled(void)
{
u64 misc_en;
int err;
@@ -218,7 +218,7 @@ static bool turbo_disabled(void)
return (misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE);
}

-static bool slv_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
+static bool __init slv_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
{
int err;

@@ -240,26 +240,26 @@ static bool slv_set_max_freq_ratio(u64 *
X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 6, \
INTEL_FAM6_##model, X86_FEATURE_APERFMPERF, NULL)

-static const struct x86_cpu_id has_knl_turbo_ratio_limits[] = {
+static const struct x86_cpu_id has_knl_turbo_ratio_limits[] __initconst = {
X86_MATCH(XEON_PHI_KNL),
X86_MATCH(XEON_PHI_KNM),
{}
};

-static const struct x86_cpu_id has_skx_turbo_ratio_limits[] = {
+static const struct x86_cpu_id has_skx_turbo_ratio_limits[] __initconst = {
X86_MATCH(SKYLAKE_X),
{}
};

-static const struct x86_cpu_id has_glm_turbo_ratio_limits[] = {
+static const struct x86_cpu_id has_glm_turbo_ratio_limits[] __initconst = {
X86_MATCH(ATOM_GOLDMONT),
X86_MATCH(ATOM_GOLDMONT_D),
X86_MATCH(ATOM_GOLDMONT_PLUS),
{}
};

-static bool knl_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq,
- int num_delta_fratio)
+static bool __init knl_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq,
+ int num_delta_fratio)
{
int fratio, delta_fratio, found;
int err, i;
@@ -297,7 +297,7 @@ static bool knl_set_max_freq_ratio(u64 *
return true;
}

-static bool skx_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, int size)
+static bool __init skx_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, int size)
{
u64 ratios, counts;
u32 group_size;
@@ -328,7 +328,7 @@ static bool skx_set_max_freq_ratio(u64 *
return false;
}

-static bool core_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
+static bool __init core_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
{
u64 msr;
int err;
@@ -351,7 +351,7 @@ static bool core_set_max_freq_ratio(u64
return true;
}

-static bool intel_set_max_freq_ratio(void)
+static bool __init intel_set_max_freq_ratio(void)
{
u64 base_freq, turbo_freq;
u64 turbo_ratio;
@@ -418,40 +418,42 @@ static struct syscore_ops freq_invarianc

static void register_freq_invariance_syscore_ops(void)
{
- /* Bail out if registered already. */
- if (freq_invariance_syscore_ops.node.prev)
- return;
-
register_syscore_ops(&freq_invariance_syscore_ops);
}
#else
static inline void register_freq_invariance_syscore_ops(void) {}
#endif

-void bp_init_freq_invariance(bool cppc_ready)
+static void freq_invariance_enable(void)
+{
+ if (static_branch_unlikely(&arch_scale_freq_key)) {
+ WARN_ON_ONCE(1);
+ return;
+ }
+ static_branch_enable(&arch_scale_freq_key);
+ register_freq_invariance_syscore_ops();
+ pr_info("Estimated ratio of average max frequency by base frequency (times 1024): %llu\n", arch_max_freq_ratio);
+}
+
+void freq_invariance_set_perf_ratio(u64 ratio, bool turbo_disabled)
{
- bool ret;
+ arch_turbo_freq_ratio = ratio;
+ arch_set_max_freq_ratio(turbo_disabled);
+ freq_invariance_enable();
+}

+void __init bp_init_freq_invariance(void)
+{
if (!cpu_feature_enabled(X86_FEATURE_APERFMPERF))
return;

init_counter_refs();

- if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
- ret = intel_set_max_freq_ratio();
- else if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
- if (!cppc_ready)
- return;
- ret = amd_set_max_freq_ratio(&arch_turbo_freq_ratio);
- }
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+ return;

- if (ret) {
- static_branch_enable(&arch_scale_freq_key);
- register_freq_invariance_syscore_ops();
- pr_info("Estimated ratio of average max frequency by base frequency (times 1024): %llu\n", arch_max_freq_ratio);
- } else {
- pr_debug("Couldn't determine max cpu frequency, necessary for scale-invariant accounting.\n");
- }
+ if (intel_set_max_freq_ratio())
+ freq_invariance_enable();
}

void ap_init_freq_invariance(void)
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1396,7 +1396,7 @@ void __init native_smp_prepare_cpus(unsi
{
smp_prepare_cpus_common();

- bp_init_freq_invariance(false);
+ bp_init_freq_invariance();
smp_sanity_check();

switch (apic_intr_mode) {

2022-04-21 18:37:07

by Rafael J. Wysocki

Subject: Re: [patch 04/10] x86/aperfmperf: Untangle Intel and AMD frequency invariance init

On Fri, Apr 15, 2022 at 9:19 PM Thomas Gleixner <[email protected]> wrote:
>
> AMD boot CPU initialization happens late via ACPI/CPPC which prevents the
> Intel parts from being marked __init.
>
> Split out the common code and provide a dedicated interface for the AMD
> initialization and mark the Intel specific code and data __init.
>
> The remaining text size is almost cut in half:
>
> text: 2614 -> 1350
> init.text: 0 -> 786
>
> Signed-off-by: Thomas Gleixner <[email protected]>

All good AFAICS:

Reviewed-by: Rafael J. Wysocki <[email protected]>

> ---
> arch/x86/include/asm/topology.h | 13 ++------
> arch/x86/kernel/acpi/cppc.c | 29 +++++++-----------
> arch/x86/kernel/cpu/aperfmperf.c | 62 ++++++++++++++++++++-------------------
> arch/x86/kernel/smpboot.c | 2 -
> 4 files changed, 49 insertions(+), 57 deletions(-)
>
> --- a/arch/x86/include/asm/topology.h
> +++ b/arch/x86/include/asm/topology.h
> @@ -216,24 +216,19 @@ extern void arch_scale_freq_tick(void);
> #define arch_scale_freq_tick arch_scale_freq_tick
>
> extern void arch_set_max_freq_ratio(bool turbo_disabled);
> -extern void bp_init_freq_invariance(bool cppc_ready);
> +extern void freq_invariance_set_perf_ratio(u64 ratio, bool turbo_disabled);
> +extern void bp_init_freq_invariance(void);
> extern void ap_init_freq_invariance(void);
> #else
> static inline void arch_set_max_freq_ratio(bool turbo_disabled) { }
> -static inline void bp_init_freq_invariance(bool cppc_ready) { }
> +static inline void freq_invariance_set_perf_ratio(u64 ratio, bool turbo_disabled) { }
> +static inline void bp_init_freq_invariance(void) { }
> static inline void ap_init_freq_invariance(void) { }
> #endif
>
> #ifdef CONFIG_ACPI_CPPC_LIB
> void init_freq_invariance_cppc(void);
> #define arch_init_invariance_cppc init_freq_invariance_cppc
> -
> -bool amd_set_max_freq_ratio(u64 *ratio);
> -#else
> -static inline bool amd_set_max_freq_ratio(u64 *ratio)
> -{
> - return false;
> -}
> #endif
>
> #endif /* _ASM_X86_TOPOLOGY_H */
> --- a/arch/x86/kernel/acpi/cppc.c
> +++ b/arch/x86/kernel/acpi/cppc.c
> @@ -50,20 +50,17 @@ int cpc_write_ffh(int cpunum, struct cpc
> return err;
> }
>
> -bool amd_set_max_freq_ratio(u64 *ratio)
> +static void amd_set_max_freq_ratio(void)
> {
> struct cppc_perf_caps perf_caps;
> u64 highest_perf, nominal_perf;
> u64 perf_ratio;
> int rc;
>
> - if (!ratio)
> - return false;
> -
> rc = cppc_get_perf_caps(0, &perf_caps);
> if (rc) {
> pr_debug("Could not retrieve perf counters (%d)\n", rc);
> - return false;
> + return;
> }
>
> highest_perf = amd_get_highest_perf();
> @@ -71,7 +68,7 @@ bool amd_set_max_freq_ratio(u64 *ratio)
>
> if (!highest_perf || !nominal_perf) {
> pr_debug("Could not retrieve highest or nominal performance\n");
> - return false;
> + return;
> }
>
> perf_ratio = div_u64(highest_perf * SCHED_CAPACITY_SCALE, nominal_perf);
> @@ -79,26 +76,24 @@ bool amd_set_max_freq_ratio(u64 *ratio)
> perf_ratio = (perf_ratio + SCHED_CAPACITY_SCALE) >> 1;
> if (!perf_ratio) {
> pr_debug("Non-zero highest/nominal perf values led to a 0 ratio\n");
> - return false;
> + return;
> }
>
> - *ratio = perf_ratio;
> - arch_set_max_freq_ratio(false);
> -
> - return true;
> + freq_invariance_set_perf_ratio(perf_ratio, false);
> }
>
> static DEFINE_MUTEX(freq_invariance_lock);
>
> void init_freq_invariance_cppc(void)
> {
> - static bool secondary;
> + static bool init_done;
>
> - mutex_lock(&freq_invariance_lock);
> -
> - if (!secondary)
> - bp_init_freq_invariance(true);
> - secondary = true;
> + if (!cpu_feature_enabled(X86_FEATURE_APERFMPERF))
> + return;
>
> + mutex_lock(&freq_invariance_lock);
> + if (!init_done)
> + amd_set_max_freq_ratio();
> + init_done = true;
> mutex_unlock(&freq_invariance_lock);
> }
> --- a/arch/x86/kernel/cpu/aperfmperf.c
> +++ b/arch/x86/kernel/cpu/aperfmperf.c
> @@ -206,7 +206,7 @@ void arch_set_max_freq_ratio(bool turbo_
> }
> EXPORT_SYMBOL_GPL(arch_set_max_freq_ratio);
>
> -static bool turbo_disabled(void)
> +static bool __init turbo_disabled(void)
> {
> u64 misc_en;
> int err;
> @@ -218,7 +218,7 @@ static bool turbo_disabled(void)
> return (misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE);
> }
>
> -static bool slv_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
> +static bool __init slv_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
> {
> int err;
>
> @@ -240,26 +240,26 @@ static bool slv_set_max_freq_ratio(u64 *
> X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 6, \
> INTEL_FAM6_##model, X86_FEATURE_APERFMPERF, NULL)
>
> -static const struct x86_cpu_id has_knl_turbo_ratio_limits[] = {
> +static const struct x86_cpu_id has_knl_turbo_ratio_limits[] __initconst = {
> X86_MATCH(XEON_PHI_KNL),
> X86_MATCH(XEON_PHI_KNM),
> {}
> };
>
> -static const struct x86_cpu_id has_skx_turbo_ratio_limits[] = {
> +static const struct x86_cpu_id has_skx_turbo_ratio_limits[] __initconst = {
> X86_MATCH(SKYLAKE_X),
> {}
> };
>
> -static const struct x86_cpu_id has_glm_turbo_ratio_limits[] = {
> +static const struct x86_cpu_id has_glm_turbo_ratio_limits[] __initconst = {
> X86_MATCH(ATOM_GOLDMONT),
> X86_MATCH(ATOM_GOLDMONT_D),
> X86_MATCH(ATOM_GOLDMONT_PLUS),
> {}
> };
>
> -static bool knl_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq,
> - int num_delta_fratio)
> +static bool __init knl_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq,
> + int num_delta_fratio)
> {
> int fratio, delta_fratio, found;
> int err, i;
> @@ -297,7 +297,7 @@ static bool knl_set_max_freq_ratio(u64 *
> return true;
> }
>
> -static bool skx_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, int size)
> +static bool __init skx_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, int size)
> {
> u64 ratios, counts;
> u32 group_size;
> @@ -328,7 +328,7 @@ static bool skx_set_max_freq_ratio(u64 *
> return false;
> }
>
> -static bool core_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
> +static bool __init core_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
> {
> u64 msr;
> int err;
> @@ -351,7 +351,7 @@ static bool core_set_max_freq_ratio(u64
> return true;
> }
>
> -static bool intel_set_max_freq_ratio(void)
> +static bool __init intel_set_max_freq_ratio(void)
> {
> u64 base_freq, turbo_freq;
> u64 turbo_ratio;
> @@ -418,40 +418,42 @@ static struct syscore_ops freq_invarianc
>
> static void register_freq_invariance_syscore_ops(void)
> {
> - /* Bail out if registered already. */
> - if (freq_invariance_syscore_ops.node.prev)
> - return;
> -
> register_syscore_ops(&freq_invariance_syscore_ops);
> }
> #else
> static inline void register_freq_invariance_syscore_ops(void) {}
> #endif
>
> -void bp_init_freq_invariance(bool cppc_ready)
> +static void freq_invariance_enable(void)
> +{
> + if (static_branch_unlikely(&arch_scale_freq_key)) {
> + WARN_ON_ONCE(1);
> + return;
> + }
> + static_branch_enable(&arch_scale_freq_key);
> + register_freq_invariance_syscore_ops();
> + pr_info("Estimated ratio of average max frequency by base frequency (times 1024): %llu\n", arch_max_freq_ratio);
> +}
> +
> +void freq_invariance_set_perf_ratio(u64 ratio, bool turbo_disabled)
> {
> - bool ret;
> + arch_turbo_freq_ratio = ratio;
> + arch_set_max_freq_ratio(turbo_disabled);
> + freq_invariance_enable();
> +}
>
> +void __init bp_init_freq_invariance(void)
> +{
> if (!cpu_feature_enabled(X86_FEATURE_APERFMPERF))
> return;
>
> init_counter_refs();
>
> - if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
> - ret = intel_set_max_freq_ratio();
> - else if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
> - if (!cppc_ready)
> - return;
> - ret = amd_set_max_freq_ratio(&arch_turbo_freq_ratio);
> - }
> + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
> + return;
>
> - if (ret) {
> - static_branch_enable(&arch_scale_freq_key);
> - register_freq_invariance_syscore_ops();
> - pr_info("Estimated ratio of average max frequency by base frequency (times 1024): %llu\n", arch_max_freq_ratio);
> - } else {
> - pr_debug("Couldn't determine max cpu frequency, necessary for scale-invariant accounting.\n");
> - }
> + if (intel_set_max_freq_ratio())
> + freq_invariance_enable();
> }
>
> void ap_init_freq_invariance(void)
> --- a/arch/x86/kernel/smpboot.c
> +++ b/arch/x86/kernel/smpboot.c
> @@ -1396,7 +1396,7 @@ void __init native_smp_prepare_cpus(unsi
> {
> smp_prepare_cpus_common();
>
> - bp_init_freq_invariance(false);
> + bp_init_freq_invariance();
> smp_sanity_check();
>
> switch (apic_intr_mode) {
>

2022-04-27 14:27:13

by tip-bot2 for Alexey Makhalov

Subject: [tip: x86/cleanups] x86/aperfmperf: Untangle Intel and AMD frequency invariance init

The following commit has been merged into the x86/cleanups branch of tip:

Commit-ID: 39a80f50743fd38d4a96603ca3ddbe4fc8723c01
Gitweb: https://git.kernel.org/tip/39a80f50743fd38d4a96603ca3ddbe4fc8723c01
Author: Thomas Gleixner <[email protected]>
AuthorDate: Fri, 15 Apr 2022 21:19:54 +02:00
Committer: Thomas Gleixner <[email protected]>
CommitterDate: Wed, 27 Apr 2022 15:51:08 +02:00

x86/aperfmperf: Untangle Intel and AMD frequency invariance init

AMD boot CPU initialization happens late via ACPI/CPPC which prevents the
Intel parts from being marked __init.

Split out the common code and provide a dedicated interface for the AMD
initialization and mark the Intel specific code and data __init.

The remaining text size is almost cut in half:

text: 2614 -> 1350
init.text: 0 -> 786

Signed-off-by: Thomas Gleixner <[email protected]>
Reviewed-by: Rafael J. Wysocki <[email protected]>
Acked-by: Peter Zijlstra (Intel) <[email protected]>
Acked-by: Paul E. McKenney <[email protected]>
Link: https://lore.kernel.org/r/[email protected]

---
arch/x86/include/asm/topology.h | 13 ++-----
arch/x86/kernel/acpi/cppc.c | 29 ++++++---------
arch/x86/kernel/cpu/aperfmperf.c | 62 ++++++++++++++++---------------
arch/x86/kernel/smpboot.c | 2 +-
4 files changed, 49 insertions(+), 57 deletions(-)

diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index e2faedc..cc31707 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -216,24 +216,19 @@ extern void arch_scale_freq_tick(void);
#define arch_scale_freq_tick arch_scale_freq_tick

extern void arch_set_max_freq_ratio(bool turbo_disabled);
-extern void bp_init_freq_invariance(bool cppc_ready);
+extern void freq_invariance_set_perf_ratio(u64 ratio, bool turbo_disabled);
+extern void bp_init_freq_invariance(void);
extern void ap_init_freq_invariance(void);
#else
static inline void arch_set_max_freq_ratio(bool turbo_disabled) { }
-static inline void bp_init_freq_invariance(bool cppc_ready) { }
+static inline void freq_invariance_set_perf_ratio(u64 ratio, bool turbo_disabled) { }
+static inline void bp_init_freq_invariance(void) { }
static inline void ap_init_freq_invariance(void) { }
#endif

#ifdef CONFIG_ACPI_CPPC_LIB
void init_freq_invariance_cppc(void);
#define arch_init_invariance_cppc init_freq_invariance_cppc
-
-bool amd_set_max_freq_ratio(u64 *ratio);
-#else
-static inline bool amd_set_max_freq_ratio(u64 *ratio)
-{
- return false;
-}
#endif

#endif /* _ASM_X86_TOPOLOGY_H */
diff --git a/arch/x86/kernel/acpi/cppc.c b/arch/x86/kernel/acpi/cppc.c
index 06109d9..79a0e92 100644
--- a/arch/x86/kernel/acpi/cppc.c
+++ b/arch/x86/kernel/acpi/cppc.c
@@ -50,20 +50,17 @@ int cpc_write_ffh(int cpunum, struct cpc_reg *reg, u64 val)
return err;
}

-bool amd_set_max_freq_ratio(u64 *ratio)
+static void amd_set_max_freq_ratio(void)
{
struct cppc_perf_caps perf_caps;
u64 highest_perf, nominal_perf;
u64 perf_ratio;
int rc;

- if (!ratio)
- return false;
-
rc = cppc_get_perf_caps(0, &perf_caps);
if (rc) {
pr_debug("Could not retrieve perf counters (%d)\n", rc);
- return false;
+ return;
}

highest_perf = amd_get_highest_perf();
@@ -71,7 +68,7 @@ bool amd_set_max_freq_ratio(u64 *ratio)

if (!highest_perf || !nominal_perf) {
pr_debug("Could not retrieve highest or nominal performance\n");
- return false;
+ return;
}

perf_ratio = div_u64(highest_perf * SCHED_CAPACITY_SCALE, nominal_perf);
@@ -79,26 +76,24 @@ bool amd_set_max_freq_ratio(u64 *ratio)
perf_ratio = (perf_ratio + SCHED_CAPACITY_SCALE) >> 1;
if (!perf_ratio) {
pr_debug("Non-zero highest/nominal perf values led to a 0 ratio\n");
- return false;
+ return;
}

- *ratio = perf_ratio;
- arch_set_max_freq_ratio(false);
-
- return true;
+ freq_invariance_set_perf_ratio(perf_ratio, false);
}

static DEFINE_MUTEX(freq_invariance_lock);

void init_freq_invariance_cppc(void)
{
- static bool secondary;
+ static bool init_done;

- mutex_lock(&freq_invariance_lock);
-
- if (!secondary)
- bp_init_freq_invariance(true);
- secondary = true;
+ if (!cpu_feature_enabled(X86_FEATURE_APERFMPERF))
+ return;

+ mutex_lock(&freq_invariance_lock);
+ if (!init_done)
+ amd_set_max_freq_ratio();
+ init_done = true;
mutex_unlock(&freq_invariance_lock);
}
diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c
index 87f34f2..b4f4ea5 100644
--- a/arch/x86/kernel/cpu/aperfmperf.c
+++ b/arch/x86/kernel/cpu/aperfmperf.c
@@ -206,7 +206,7 @@ void arch_set_max_freq_ratio(bool turbo_disabled)
}
EXPORT_SYMBOL_GPL(arch_set_max_freq_ratio);

-static bool turbo_disabled(void)
+static bool __init turbo_disabled(void)
{
u64 misc_en;
int err;
@@ -218,7 +218,7 @@ static bool turbo_disabled(void)
return (misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE);
}

-static bool slv_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
+static bool __init slv_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
{
int err;

@@ -240,26 +240,26 @@ static bool slv_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 6, \
INTEL_FAM6_##model, X86_FEATURE_APERFMPERF, NULL)

-static const struct x86_cpu_id has_knl_turbo_ratio_limits[] = {
+static const struct x86_cpu_id has_knl_turbo_ratio_limits[] __initconst = {
X86_MATCH(XEON_PHI_KNL),
X86_MATCH(XEON_PHI_KNM),
{}
};

-static const struct x86_cpu_id has_skx_turbo_ratio_limits[] = {
+static const struct x86_cpu_id has_skx_turbo_ratio_limits[] __initconst = {
X86_MATCH(SKYLAKE_X),
{}
};

-static const struct x86_cpu_id has_glm_turbo_ratio_limits[] = {
+static const struct x86_cpu_id has_glm_turbo_ratio_limits[] __initconst = {
X86_MATCH(ATOM_GOLDMONT),
X86_MATCH(ATOM_GOLDMONT_D),
X86_MATCH(ATOM_GOLDMONT_PLUS),
{}
};

-static bool knl_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq,
- int num_delta_fratio)
+static bool __init knl_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq,
+ int num_delta_fratio)
{
int fratio, delta_fratio, found;
int err, i;
@@ -297,7 +297,7 @@ static bool knl_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq,
return true;
}

-static bool skx_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, int size)
+static bool __init skx_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, int size)
{
u64 ratios, counts;
u32 group_size;
@@ -328,7 +328,7 @@ static bool skx_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, int size)
return false;
}

-static bool core_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
+static bool __init core_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
{
u64 msr;
int err;
@@ -351,7 +351,7 @@ static bool core_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
return true;
}

-static bool intel_set_max_freq_ratio(void)
+static bool __init intel_set_max_freq_ratio(void)
{
u64 base_freq, turbo_freq;
u64 turbo_ratio;
@@ -418,40 +418,42 @@ static struct syscore_ops freq_invariance_syscore_ops = {

static void register_freq_invariance_syscore_ops(void)
{
- /* Bail out if registered already. */
- if (freq_invariance_syscore_ops.node.prev)
- return;
-
register_syscore_ops(&freq_invariance_syscore_ops);
}
#else
static inline void register_freq_invariance_syscore_ops(void) {}
#endif

-void bp_init_freq_invariance(bool cppc_ready)
+static void freq_invariance_enable(void)
+{
+ if (static_branch_unlikely(&arch_scale_freq_key)) {
+ WARN_ON_ONCE(1);
+ return;
+ }
+ static_branch_enable(&arch_scale_freq_key);
+ register_freq_invariance_syscore_ops();
+ pr_info("Estimated ratio of average max frequency by base frequency (times 1024): %llu\n", arch_max_freq_ratio);
+}
+
+void freq_invariance_set_perf_ratio(u64 ratio, bool turbo_disabled)
{
- bool ret;
+ arch_turbo_freq_ratio = ratio;
+ arch_set_max_freq_ratio(turbo_disabled);
+ freq_invariance_enable();
+}

+void __init bp_init_freq_invariance(void)
+{
if (!cpu_feature_enabled(X86_FEATURE_APERFMPERF))
return;

init_counter_refs();

- if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
- ret = intel_set_max_freq_ratio();
- else if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
- if (!cppc_ready)
- return;
- ret = amd_set_max_freq_ratio(&arch_turbo_freq_ratio);
- }
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+ return;

- if (ret) {
- static_branch_enable(&arch_scale_freq_key);
- register_freq_invariance_syscore_ops();
- pr_info("Estimated ratio of average max frequency by base frequency (times 1024): %llu\n", arch_max_freq_ratio);
- } else {
- pr_debug("Couldn't determine max cpu frequency, necessary for scale-invariant accounting.\n");
- }
+ if (intel_set_max_freq_ratio())
+ freq_invariance_enable();
}

void ap_init_freq_invariance(void)
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 023feb4..b1ba7dd 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1396,7 +1396,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
{
smp_prepare_cpus_common();

- bp_init_freq_invariance(false);
+ bp_init_freq_invariance();
smp_sanity_check();

switch (apic_intr_mode) {

2022-04-27 19:04:10

by tip-bot2 for Alexey Makhalov

Subject: [tip: x86/cleanups] x86/aperfmperf: Untangle Intel and AMD frequency invariance init

The following commit has been merged into the x86/cleanups branch of tip:

Commit-ID: 0dfaf3f6ecc0c7f4f876255aa82e8959d3721365
Gitweb: https://git.kernel.org/tip/0dfaf3f6ecc0c7f4f876255aa82e8959d3721365
Author: Thomas Gleixner <[email protected]>
AuthorDate: Fri, 15 Apr 2022 21:19:54 +02:00
Committer: Thomas Gleixner <[email protected]>
CommitterDate: Wed, 27 Apr 2022 20:22:19 +02:00

x86/aperfmperf: Untangle Intel and AMD frequency invariance init

AMD boot CPU initialization happens late via ACPI/CPPC which prevents the
Intel parts from being marked __init.

Split out the common code and provide a dedicated interface for the AMD
initialization and mark the Intel specific code and data __init.

The remaining text size is almost cut in half:

text: 2614 -> 1350
init.text: 0 -> 786

Signed-off-by: Thomas Gleixner <[email protected]>
Reviewed-by: Rafael J. Wysocki <[email protected]>
Acked-by: Peter Zijlstra (Intel) <[email protected]>
Acked-by: Paul E. McKenney <[email protected]>
Link: https://lore.kernel.org/r/[email protected]

---
arch/x86/include/asm/topology.h | 13 ++-----
arch/x86/kernel/acpi/cppc.c | 30 +++++++--------
arch/x86/kernel/cpu/aperfmperf.c | 62 ++++++++++++++++---------------
arch/x86/kernel/smpboot.c | 2 +-
4 files changed, 51 insertions(+), 56 deletions(-)

diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index e2faedc..cc31707 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -216,24 +216,19 @@ extern void arch_scale_freq_tick(void);
#define arch_scale_freq_tick arch_scale_freq_tick

extern void arch_set_max_freq_ratio(bool turbo_disabled);
-extern void bp_init_freq_invariance(bool cppc_ready);
+extern void freq_invariance_set_perf_ratio(u64 ratio, bool turbo_disabled);
+extern void bp_init_freq_invariance(void);
extern void ap_init_freq_invariance(void);
#else
static inline void arch_set_max_freq_ratio(bool turbo_disabled) { }
-static inline void bp_init_freq_invariance(bool cppc_ready) { }
+static inline void freq_invariance_set_perf_ratio(u64 ratio, bool turbo_disabled) { }
+static inline void bp_init_freq_invariance(void) { }
static inline void ap_init_freq_invariance(void) { }
#endif

#ifdef CONFIG_ACPI_CPPC_LIB
void init_freq_invariance_cppc(void);
#define arch_init_invariance_cppc init_freq_invariance_cppc
-
-bool amd_set_max_freq_ratio(u64 *ratio);
-#else
-static inline bool amd_set_max_freq_ratio(u64 *ratio)
-{
- return false;
-}
#endif

#endif /* _ASM_X86_TOPOLOGY_H */
diff --git a/arch/x86/kernel/acpi/cppc.c b/arch/x86/kernel/acpi/cppc.c
index 06109d9..8b8cbf2 100644
--- a/arch/x86/kernel/acpi/cppc.c
+++ b/arch/x86/kernel/acpi/cppc.c
@@ -50,20 +50,17 @@ int cpc_write_ffh(int cpunum, struct cpc_reg *reg, u64 val)
return err;
}

-bool amd_set_max_freq_ratio(u64 *ratio)
+static void amd_set_max_freq_ratio(void)
{
struct cppc_perf_caps perf_caps;
u64 highest_perf, nominal_perf;
u64 perf_ratio;
int rc;

- if (!ratio)
- return false;
-
rc = cppc_get_perf_caps(0, &perf_caps);
if (rc) {
pr_debug("Could not retrieve perf counters (%d)\n", rc);
- return false;
+ return;
}

highest_perf = amd_get_highest_perf();
@@ -71,7 +68,7 @@ bool amd_set_max_freq_ratio(u64 *ratio)

if (!highest_perf || !nominal_perf) {
pr_debug("Could not retrieve highest or nominal performance\n");
- return false;
+ return;
}

perf_ratio = div_u64(highest_perf * SCHED_CAPACITY_SCALE, nominal_perf);
@@ -79,26 +76,27 @@ bool amd_set_max_freq_ratio(u64 *ratio)
perf_ratio = (perf_ratio + SCHED_CAPACITY_SCALE) >> 1;
if (!perf_ratio) {
pr_debug("Non-zero highest/nominal perf values led to a 0 ratio\n");
- return false;
+ return;
}

- *ratio = perf_ratio;
- arch_set_max_freq_ratio(false);
-
- return true;
+ freq_invariance_set_perf_ratio(perf_ratio, false);
}

static DEFINE_MUTEX(freq_invariance_lock);

void init_freq_invariance_cppc(void)
{
- static bool secondary;
+ static bool init_done;

- mutex_lock(&freq_invariance_lock);
+ if (!cpu_feature_enabled(X86_FEATURE_APERFMPERF))
+ return;

- if (!secondary)
- bp_init_freq_invariance(true);
- secondary = true;
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
+ return;

+ mutex_lock(&freq_invariance_lock);
+ if (!init_done)
+ amd_set_max_freq_ratio();
+ init_done = true;
mutex_unlock(&freq_invariance_lock);
}
diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c
index 87f34f2..b4f4ea5 100644
--- a/arch/x86/kernel/cpu/aperfmperf.c
+++ b/arch/x86/kernel/cpu/aperfmperf.c
@@ -206,7 +206,7 @@ void arch_set_max_freq_ratio(bool turbo_disabled)
}
EXPORT_SYMBOL_GPL(arch_set_max_freq_ratio);

-static bool turbo_disabled(void)
+static bool __init turbo_disabled(void)
{
u64 misc_en;
int err;
@@ -218,7 +218,7 @@ static bool turbo_disabled(void)
return (misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE);
}

-static bool slv_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
+static bool __init slv_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
{
int err;

@@ -240,26 +240,26 @@ static bool slv_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 6, \
INTEL_FAM6_##model, X86_FEATURE_APERFMPERF, NULL)

-static const struct x86_cpu_id has_knl_turbo_ratio_limits[] = {
+static const struct x86_cpu_id has_knl_turbo_ratio_limits[] __initconst = {
X86_MATCH(XEON_PHI_KNL),
X86_MATCH(XEON_PHI_KNM),
{}
};

-static const struct x86_cpu_id has_skx_turbo_ratio_limits[] = {
+static const struct x86_cpu_id has_skx_turbo_ratio_limits[] __initconst = {
X86_MATCH(SKYLAKE_X),
{}
};

-static const struct x86_cpu_id has_glm_turbo_ratio_limits[] = {
+static const struct x86_cpu_id has_glm_turbo_ratio_limits[] __initconst = {
X86_MATCH(ATOM_GOLDMONT),
X86_MATCH(ATOM_GOLDMONT_D),
X86_MATCH(ATOM_GOLDMONT_PLUS),
{}
};

-static bool knl_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq,
- int num_delta_fratio)
+static bool __init knl_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq,
+ int num_delta_fratio)
{
int fratio, delta_fratio, found;
int err, i;
@@ -297,7 +297,7 @@ static bool knl_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq,
return true;
}

-static bool skx_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, int size)
+static bool __init skx_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, int size)
{
u64 ratios, counts;
u32 group_size;
@@ -328,7 +328,7 @@ static bool skx_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, int size)
return false;
}

-static bool core_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
+static bool __init core_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
{
u64 msr;
int err;
@@ -351,7 +351,7 @@ static bool core_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
return true;
}

-static bool intel_set_max_freq_ratio(void)
+static bool __init intel_set_max_freq_ratio(void)
{
u64 base_freq, turbo_freq;
u64 turbo_ratio;
@@ -418,40 +418,42 @@ static struct syscore_ops freq_invariance_syscore_ops = {

static void register_freq_invariance_syscore_ops(void)
{
- /* Bail out if registered already. */
- if (freq_invariance_syscore_ops.node.prev)
- return;
-
register_syscore_ops(&freq_invariance_syscore_ops);
}
#else
static inline void register_freq_invariance_syscore_ops(void) {}
#endif

-void bp_init_freq_invariance(bool cppc_ready)
+static void freq_invariance_enable(void)
+{
+ if (static_branch_unlikely(&arch_scale_freq_key)) {
+ WARN_ON_ONCE(1);
+ return;
+ }
+ static_branch_enable(&arch_scale_freq_key);
+ register_freq_invariance_syscore_ops();
+ pr_info("Estimated ratio of average max frequency by base frequency (times 1024): %llu\n", arch_max_freq_ratio);
+}
+
+void freq_invariance_set_perf_ratio(u64 ratio, bool turbo_disabled)
{
- bool ret;
+ arch_turbo_freq_ratio = ratio;
+ arch_set_max_freq_ratio(turbo_disabled);
+ freq_invariance_enable();
+}

+void __init bp_init_freq_invariance(void)
+{
if (!cpu_feature_enabled(X86_FEATURE_APERFMPERF))
return;

init_counter_refs();

- if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
- ret = intel_set_max_freq_ratio();
- else if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
- if (!cppc_ready)
- return;
- ret = amd_set_max_freq_ratio(&arch_turbo_freq_ratio);
- }
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+ return;

- if (ret) {
- static_branch_enable(&arch_scale_freq_key);
- register_freq_invariance_syscore_ops();
- pr_info("Estimated ratio of average max frequency by base frequency (times 1024): %llu\n", arch_max_freq_ratio);
- } else {
- pr_debug("Couldn't determine max cpu frequency, necessary for scale-invariant accounting.\n");
- }
+ if (intel_set_max_freq_ratio())
+ freq_invariance_enable();
}

void ap_init_freq_invariance(void)
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 023feb4..b1ba7dd 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1396,7 +1396,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
{
smp_prepare_cpus_common();

- bp_init_freq_invariance(false);
+ bp_init_freq_invariance();
smp_sanity_check();

switch (apic_intr_mode) {