Excerpts from Nicholas Piggin's message of July 2, 2021 10:27 am:
> Excerpts from Madhavan Srinivasan's message of July 1, 2021 11:17 pm:
>>
>> On 6/22/21 4:27 PM, Nicholas Piggin wrote:
>>> KVM PMU management code looks for particular frozen/disabled bits in
>>> the PMU registers so it knows whether it must clear them when coming
>>> out of a guest or not. Setting this up helps KVM make these optimisations
>>> without getting confused. Longer term the better approach might be to
>>> move guest/host PMU switching to the perf subsystem.
>>>
>>> Signed-off-by: Nicholas Piggin <npiggin@xxxxxxxxx>
>>> ---
>>> arch/powerpc/kernel/cpu_setup_power.c | 4 ++--
>>> arch/powerpc/kernel/dt_cpu_ftrs.c | 6 +++---
>>> arch/powerpc/kvm/book3s_hv.c | 5 +++++
>>> arch/powerpc/perf/core-book3s.c | 7 +++++++
>>> 4 files changed, 17 insertions(+), 5 deletions(-)
>>>
>>> diff --git a/arch/powerpc/kernel/cpu_setup_power.c b/arch/powerpc/kernel/cpu_setup_power.c
>>> index a29dc8326622..3dc61e203f37 100644
>>> --- a/arch/powerpc/kernel/cpu_setup_power.c
>>> +++ b/arch/powerpc/kernel/cpu_setup_power.c
>>> @@ -109,7 +109,7 @@ static void init_PMU_HV_ISA207(void)
>>> static void init_PMU(void)
>>> {
>>> mtspr(SPRN_MMCRA, 0);
>>> - mtspr(SPRN_MMCR0, 0);
>>> + mtspr(SPRN_MMCR0, MMCR0_FC);
>>
>> Sticky point here is, currently if not frozen, pmc5/6 will
>> keep countering. And not freezing them at boot is quiet useful
>> sometime, like say when running in a simulation where we could calculate
>> approx CPIs for micro benchmarks without perf subsystem.
>
> You even can't use the sysfs files in this sim environment? In that case
> what if we added a boot option that could set some things up? In that
> case possibly you could even gather some more types of events too.
What if we added this to allow sim environments to run PMC5/6 and
additionally specify MMCR1 without userspace involvement?
Thanks,
Nick
---
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index af8a4981c6f6..454771243529 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -2425,8 +2425,24 @@ int register_power_pmu(struct power_pmu *pmu)
}
#ifdef CONFIG_PPC64
+static bool pmu_override = false;
+static unsigned long pmu_override_val;
+static void do_pmu_override(void *data)
+{
+ ppc_set_pmu_inuse(1);
+ if (pmu_override_val)
+ mtspr(SPRN_MMCR1, pmu_override_val);
+ mtspr(SPRN_MMCR0, mfspr(SPRN_MMCR0) & ~MMCR0_FC);
+}
+
static int __init init_ppc64_pmu(void)
{
+ if (cpu_has_feature(CPU_FTR_HVMODE) && pmu_override) {
+ printk(KERN_WARNING "perf: disabling perf due to pmu= command line option.\n");
+ on_each_cpu(do_pmu_override, NULL, 1);
+ return 0;
+ }
+
/* run through all the pmu drivers one at a time */
if (!init_power5_pmu())
return 0;
@@ -2448,4 +2464,23 @@ static int __init init_ppc64_pmu(void)
return init_generic_compat_pmu();
}
early_initcall(init_ppc64_pmu);
+
+static int __init pmu_setup(char *str)
+{
+ unsigned long val;
+
+ if (!early_cpu_has_feature(CPU_FTR_HVMODE))
+ return 0;
+
+ pmu_override = true;
+
+ if (kstrtoul(str, 0, &val))
+ val = 0;
+
+ pmu_override_val = val;
+
+ return 1;
+}
+__setup("pmu=", pmu_setup);
+
#endif
