| Message ID | 20220819162547.141333-2-jeremy.linton@arm.com |
|---|---|
| State | Superseded |
| Headers | show |
| Series | Disable FIE on machines with slow counters | expand |
Hi Jeremy, I missed the previous version (holidays) but hopefully still in time for this one. A query / comment below. Jeremy Linton <jeremy.linton@arm.com> writes: > PCC regions utilize a mailbox to set/retrieve register values used by > the CPPC code. This is fine as long as the operations are > infrequent. With the FIE code enabled though the overhead can range > from 2-11% of system CPU overhead (ex: as measured by top) on Arm > based machines. > > So, before enabling FIE assure none of the registers used by > cppc_get_perf_ctrs() are in the PCC region. Furthermore lets also > enable a module parameter which can also disable it at boot or module > reload. > > Signed-off-by: Jeremy Linton <jeremy.linton@arm.com> > --- > drivers/acpi/cppc_acpi.c | 41 ++++++++++++++++++++++++++++++++++ > drivers/cpufreq/cppc_cpufreq.c | 31 +++++++++++++++++++++---- > include/acpi/cppc_acpi.h | 5 +++++ > 3 files changed, 73 insertions(+), 4 deletions(-) > > diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c > index 1e15a9f25ae9..c840bf606b30 100644 > --- a/drivers/acpi/cppc_acpi.c > +++ b/drivers/acpi/cppc_acpi.c > @@ -1240,6 +1240,47 @@ int cppc_get_perf_caps(int cpunum, struct cppc_perf_caps *perf_caps) > } > EXPORT_SYMBOL_GPL(cppc_get_perf_caps); > > +/** > + * cppc_perf_ctrs_in_pcc - Check if any perf counters are in a PCC region. > + * > + * CPPC has flexibility about how counters describing CPU perf are delivered. > + * One of the choices is PCC regions, which can have a high access latency. This > + * routine allows callers of cppc_get_perf_ctrs() to know this ahead of time. > + * > + * Return: true if any of the counters are in PCC regions, false otherwise > + */ > +bool cppc_perf_ctrs_in_pcc(void) > +{ > + int cpu; > + > + for_each_present_cpu(cpu) { > + struct cpc_register_resource *ref_perf_reg; > + struct cpc_desc *cpc_desc; > + > + cpc_desc = per_cpu(cpc_desc_ptr, cpu); > + > + if (CPC_IN_PCC(&cpc_desc->cpc_regs[DELIVERED_CTR]) || > + CPC_IN_PCC(&cpc_desc->cpc_regs[REFERENCE_CTR]) || > + CPC_IN_PCC(&cpc_desc->cpc_regs[CTR_WRAP_TIME])) > + return true; > + > + > + ref_perf_reg = &cpc_desc->cpc_regs[REFERENCE_PERF]; > + > + /* > + * If reference perf register is not supported then we should > + * use the nominal perf value > + */ > + if (!CPC_SUPPORTED(ref_perf_reg)) > + ref_perf_reg = &cpc_desc->cpc_regs[NOMINAL_PERF]; > + > + if (CPC_IN_PCC(ref_perf_reg)) > + return true; > + } > + return false; > +} > +EXPORT_SYMBOL_GPL(cppc_perf_ctrs_in_pcc); > + > /** > * cppc_get_perf_ctrs - Read a CPU's performance feedback counters. > * @cpunum: CPU from which to read counters. > diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c > index 24eaf0ec344d..32fcb0bf74a4 100644 > --- a/drivers/cpufreq/cppc_cpufreq.c > +++ b/drivers/cpufreq/cppc_cpufreq.c > @@ -63,7 +63,15 @@ static struct cppc_workaround_oem_info wa_info[] = { > > static struct cpufreq_driver cppc_cpufreq_driver; > > +static enum { > + FIE_UNSET = -1, > + FIE_ENABLED, > + FIE_DISABLED > +} fie_disabled = FIE_UNSET; > + > #ifdef CONFIG_ACPI_CPPC_CPUFREQ_FIE > +module_param(fie_disabled, int, 0444); > +MODULE_PARM_DESC(fie_disabled, "Disable Frequency Invariance Engine (FIE)"); > > /* Frequency invariance support */ > struct cppc_freq_invariance { > @@ -158,7 +166,7 @@ static void cppc_cpufreq_cpu_fie_init(struct cpufreq_policy *policy) > struct cppc_freq_invariance *cppc_fi; > int cpu, ret; > > - if (cppc_cpufreq_driver.get == hisi_cppc_cpufreq_get_rate) > + if (fie_disabled) > return; With this change, if FIE is enabled, the rest of the function will run even if the hisi workaround is enabled. Not sure if that is an intentional change. The same applies to similar other changes in the patch as well. The rest of the changes look ok. [...]
diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index 1e15a9f25ae9..c840bf606b30 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -1240,6 +1240,47 @@ int cppc_get_perf_caps(int cpunum, struct cppc_perf_caps *perf_caps) } EXPORT_SYMBOL_GPL(cppc_get_perf_caps); +/** + * cppc_perf_ctrs_in_pcc - Check if any perf counters are in a PCC region. + * + * CPPC has flexibility about how counters describing CPU perf are delivered. + * One of the choices is PCC regions, which can have a high access latency. This + * routine allows callers of cppc_get_perf_ctrs() to know this ahead of time. + * + * Return: true if any of the counters are in PCC regions, false otherwise + */ +bool cppc_perf_ctrs_in_pcc(void) +{ + int cpu; + + for_each_present_cpu(cpu) { + struct cpc_register_resource *ref_perf_reg; + struct cpc_desc *cpc_desc; + + cpc_desc = per_cpu(cpc_desc_ptr, cpu); + + if (CPC_IN_PCC(&cpc_desc->cpc_regs[DELIVERED_CTR]) || + CPC_IN_PCC(&cpc_desc->cpc_regs[REFERENCE_CTR]) || + CPC_IN_PCC(&cpc_desc->cpc_regs[CTR_WRAP_TIME])) + return true; + + + ref_perf_reg = &cpc_desc->cpc_regs[REFERENCE_PERF]; + + /* + * If reference perf register is not supported then we should + * use the nominal perf value + */ + if (!CPC_SUPPORTED(ref_perf_reg)) + ref_perf_reg = &cpc_desc->cpc_regs[NOMINAL_PERF]; + + if (CPC_IN_PCC(ref_perf_reg)) + return true; + } + return false; +} +EXPORT_SYMBOL_GPL(cppc_perf_ctrs_in_pcc); + /** * cppc_get_perf_ctrs - Read a CPU's performance feedback counters. * @cpunum: CPU from which to read counters. diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c index 24eaf0ec344d..32fcb0bf74a4 100644 --- a/drivers/cpufreq/cppc_cpufreq.c +++ b/drivers/cpufreq/cppc_cpufreq.c @@ -63,7 +63,15 @@ static struct cppc_workaround_oem_info wa_info[] = { static struct cpufreq_driver cppc_cpufreq_driver; +static enum { + FIE_UNSET = -1, + FIE_ENABLED, + FIE_DISABLED +} fie_disabled = FIE_UNSET; + #ifdef CONFIG_ACPI_CPPC_CPUFREQ_FIE +module_param(fie_disabled, int, 0444); +MODULE_PARM_DESC(fie_disabled, "Disable Frequency Invariance Engine (FIE)"); /* Frequency invariance support */ struct cppc_freq_invariance { @@ -158,7 +166,7 @@ static void cppc_cpufreq_cpu_fie_init(struct cpufreq_policy *policy) struct cppc_freq_invariance *cppc_fi; int cpu, ret; - if (cppc_cpufreq_driver.get == hisi_cppc_cpufreq_get_rate) + if (fie_disabled) return; for_each_cpu(cpu, policy->cpus) { @@ -199,7 +207,7 @@ static void cppc_cpufreq_cpu_fie_exit(struct cpufreq_policy *policy) struct cppc_freq_invariance *cppc_fi; int cpu; - if (cppc_cpufreq_driver.get == hisi_cppc_cpufreq_get_rate) + if (fie_disabled) return; /* policy->cpus will be empty here, use related_cpus instead */ @@ -229,7 +237,21 @@ static void __init cppc_freq_invariance_init(void) }; int ret; - if (cppc_cpufreq_driver.get == hisi_cppc_cpufreq_get_rate) + switch (fie_disabled) { + /* honor user request */ + case FIE_DISABLED: + case FIE_ENABLED: + break; + case FIE_UNSET: + default: + fie_disabled = FIE_ENABLED; + if (cppc_perf_ctrs_in_pcc()) { + pr_info("FIE not enabled on systems with registers in PCC\n"); + fie_disabled = FIE_DISABLED; + } + break; + } + if (fie_disabled) return; kworker_fie = kthread_create_worker(0, "cppc_fie"); @@ -247,7 +269,7 @@ static void __init cppc_freq_invariance_init(void) static void cppc_freq_invariance_exit(void) { - if (cppc_cpufreq_driver.get == hisi_cppc_cpufreq_get_rate) + if (fie_disabled) return; kthread_destroy_worker(kworker_fie); @@ -936,6 +958,7 @@ static void cppc_check_hisi_workaround(void) wa_info[i].oem_revision == tbl->oem_revision) { /* Overwrite the get() callback */ cppc_cpufreq_driver.get = hisi_cppc_cpufreq_get_rate; + fie_disabled = FIE_DISABLED; break; } } diff --git a/include/acpi/cppc_acpi.h b/include/acpi/cppc_acpi.h index f73d357ecdf5..c5614444031f 100644 --- a/include/acpi/cppc_acpi.h +++ b/include/acpi/cppc_acpi.h @@ -140,6 +140,7 @@ extern int cppc_get_perf_ctrs(int cpu, struct cppc_perf_fb_ctrs *perf_fb_ctrs); extern int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls); extern int cppc_set_enable(int cpu, bool enable); extern int cppc_get_perf_caps(int cpu, struct cppc_perf_caps *caps); +extern bool cppc_perf_ctrs_in_pcc(void); extern bool acpi_cpc_valid(void); extern bool cppc_allow_fast_switch(void); extern int acpi_get_psd_map(unsigned int cpu, struct cppc_cpudata *cpu_data); @@ -173,6 +174,10 @@ static inline int cppc_get_perf_caps(int cpu, struct cppc_perf_caps *caps) { return -ENOTSUPP; } +static inline bool cppc_perf_ctrs_in_pcc(void) +{ + return false; +} static inline bool acpi_cpc_valid(void) { return false;
PCC regions utilize a mailbox to set/retrieve register values used by the CPPC code. This is fine as long as the operations are infrequent. With the FIE code enabled though the overhead can range from 2-11% of system CPU overhead (ex: as measured by top) on Arm based machines. So, before enabling FIE assure none of the registers used by cppc_get_perf_ctrs() are in the PCC region. Furthermore lets also enable a module parameter which can also disable it at boot or module reload. Signed-off-by: Jeremy Linton <jeremy.linton@arm.com> --- drivers/acpi/cppc_acpi.c | 41 ++++++++++++++++++++++++++++++++++ drivers/cpufreq/cppc_cpufreq.c | 31 +++++++++++++++++++++---- include/acpi/cppc_acpi.h | 5 +++++ 3 files changed, 73 insertions(+), 4 deletions(-)