On 9/19/2024 6:30 PM, Liang, Kan wrote:
>
>
> On 2024-09-19 2:02 a.m., Manali Shukla wrote:
>> On 8/1/2024 10:28 AM, Mingwei Zhang wrote:
>>> From: Kan Liang <kan.liang@xxxxxxxxxxxxxxx>
>>>
>>> There will be a dedicated interrupt vector for guests on some platforms,
>>> e.g., Intel. Add an interface to switch the interrupt vector while
>>> entering/exiting a guest.
>>>
>>> When PMI switch into a new guest vector, guest_lvtpc value need to be
>>> reflected onto HW, e,g., guest clear PMI mask bit, the HW PMI mask
>>> bit should be cleared also, then PMI can be generated continuously
>>> for guest. So guest_lvtpc parameter is added into perf_guest_enter()
>>> and switch_interrupt().
>>>
>>> At switch_interrupt(), the target pmu with PASSTHROUGH cap should
>>> be found. Since only one passthrough pmu is supported, we keep the
>>> implementation simply by tracking the pmu as a global variable.
>>>
>>> Signed-off-by: Kan Liang <kan.liang@xxxxxxxxxxxxxxx>
>>>
>>> [Simplify the commit with removal of srcu lock/unlock since only one pmu is
>>> supported.]
>>>
>>> Signed-off-by: Mingwei Zhang <mizhang@xxxxxxxxxx>
>>> ---
>>> include/linux/perf_event.h | 9 +++++++--
>>> kernel/events/core.c | 36 ++++++++++++++++++++++++++++++++++--
>>> 2 files changed, 41 insertions(+), 4 deletions(-)
>>>
>>> diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
>>> index 75773f9890cc..aeb08f78f539 100644
>>> --- a/include/linux/perf_event.h
>>> +++ b/include/linux/perf_event.h
>>> @@ -541,6 +541,11 @@ struct pmu {
>>> * Check period value for PERF_EVENT_IOC_PERIOD ioctl.
>>> */
>>> int (*check_period) (struct perf_event *event, u64 value); /* optional */
>>> +
>>> + /*
>>> + * Switch the interrupt vectors, e.g., guest enter/exit.
>>> + */
>>> + void (*switch_interrupt) (bool enter, u32 guest_lvtpc); /* optional */
>>> };
>>>
>>> enum perf_addr_filter_action_t {
>>> @@ -1738,7 +1743,7 @@ extern int perf_event_period(struct perf_event *event, u64 value);
>>> extern u64 perf_event_pause(struct perf_event *event, bool reset);
>>> int perf_get_mediated_pmu(void);
>>> void perf_put_mediated_pmu(void);
>>> -void perf_guest_enter(void);
>>> +void perf_guest_enter(u32 guest_lvtpc);
>>> void perf_guest_exit(void);
>>> #else /* !CONFIG_PERF_EVENTS: */
>>> static inline void *
>>> @@ -1833,7 +1838,7 @@ static inline int perf_get_mediated_pmu(void)
>>> }
>>>
>>> static inline void perf_put_mediated_pmu(void) { }
>>> -static inline void perf_guest_enter(void) { }
>>> +static inline void perf_guest_enter(u32 guest_lvtpc) { }
>>> static inline void perf_guest_exit(void) { }
>>> #endif
>>>
>>> diff --git a/kernel/events/core.c b/kernel/events/core.c
>>> index 57ff737b922b..047ca5748ee2 100644
>>> --- a/kernel/events/core.c
>>> +++ b/kernel/events/core.c
>>> @@ -422,6 +422,7 @@ static inline bool is_include_guest_event(struct perf_event *event)
>>>
>>> static LIST_HEAD(pmus);
>>> static DEFINE_MUTEX(pmus_lock);
>>> +static struct pmu *passthru_pmu;
>>> static struct srcu_struct pmus_srcu;
>>> static cpumask_var_t perf_online_mask;
>>> static struct kmem_cache *perf_event_cache;
>>> @@ -5941,8 +5942,21 @@ void perf_put_mediated_pmu(void)
>>> }
>>> EXPORT_SYMBOL_GPL(perf_put_mediated_pmu);
>>>
>>> +static void perf_switch_interrupt(bool enter, u32 guest_lvtpc)
>>> +{
>>> + /* Mediated passthrough PMU should have PASSTHROUGH_VPMU cap. */
>>> + if (!passthru_pmu)
>>> + return;
>>> +
>>> + if (passthru_pmu->switch_interrupt &&
>>> + try_module_get(passthru_pmu->module)) {
>>> + passthru_pmu->switch_interrupt(enter, guest_lvtpc);
>>> + module_put(passthru_pmu->module);
>>> + }
>>> +}
>>> +
>>> /* When entering a guest, schedule out all exclude_guest events. */
>>> -void perf_guest_enter(void)
>>> +void perf_guest_enter(u32 guest_lvtpc)
>>> {
>>> struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context);
>>>
>>> @@ -5962,6 +5976,8 @@ void perf_guest_enter(void)
>>> perf_ctx_enable(cpuctx->task_ctx, EVENT_GUEST);
>>> }
>>>
>>> + perf_switch_interrupt(true, guest_lvtpc);
>>> +
>>> __this_cpu_write(perf_in_guest, true);
>>>
>>> unlock:
>>> @@ -5980,6 +5996,8 @@ void perf_guest_exit(void)
>>> if (WARN_ON_ONCE(!__this_cpu_read(perf_in_guest)))
>>> goto unlock;
>>>
>>> + perf_switch_interrupt(false, 0);
>>> +
>>> perf_ctx_disable(&cpuctx->ctx, EVENT_GUEST);
>>> ctx_sched_in(&cpuctx->ctx, EVENT_GUEST);
>>> perf_ctx_enable(&cpuctx->ctx, EVENT_GUEST);
>>> @@ -11842,7 +11860,21 @@ int perf_pmu_register(struct pmu *pmu, const char *name, int type)
>>> if (!pmu->event_idx)
>>> pmu->event_idx = perf_event_idx_default;
>>>
>>> - list_add_rcu(&pmu->entry, &pmus);
>>> + /*
>>> + * Initialize passthru_pmu with the core pmu that has
>>> + * PERF_PMU_CAP_PASSTHROUGH_VPMU capability.
>>> + */
>>> + if (pmu->capabilities & PERF_PMU_CAP_PASSTHROUGH_VPMU) {
>>> + if (!passthru_pmu)
>>> + passthru_pmu = pmu;
>>> +
>>> + if (WARN_ONCE(passthru_pmu != pmu, "Only one passthrough PMU is supported\n")) {
>>> + ret = -EINVAL;
>>> + goto free_dev;
>>> + }
>>> + }
>>
>>
>> Our intention is to virtualize IBS PMUs (Op and Fetch) using the same framework. However,
>> if IBS PMUs are also using the PERF_PMU_CAP_PASSTHROUGH_VPMU capability, IBS PMU registration
>> fails at this point because the Core PMU is already registered with PERF_PMU_CAP_PASSTHROUGH_VPMU.
>>
>
> The original implementation doesn't limit the number of PMUs with
> PERF_PMU_CAP_PASSTHROUGH_VPMU. But at that time, we could not find a
> case of more than one PMU with the flag. After several debates, the
> patch was simplified only to support one PMU with the flag.
> It should not be hard to change it back.
>
> Thanks,
> Kan
>
Yes, we have a use case to use mediated passthrough vPMU framework for IBS virtualization.
So, we will need it.
- Manali
>>> +
>>> + list_add_tail_rcu(&pmu->entry, &pmus);
>>> atomic_set(&pmu->exclusive_cnt, 0);
>>> ret = 0;
>>> unlock:
>>
>>
