Re: [PATCH 05/33] perf, kvm: Support the intx/intx_cp modifiers in KVM arch perfmon emulation v3

[Gleb Natapov <gleb@redhat.com>]

On Fri, Oct 26, 2012 at 01:29:47PM -0700, Andi Kleen wrote:
> From: Andi Kleen <ak@linux.intel.com>
> 
> This is not arch perfmon, but older CPUs will just ignore it. This makes
> it possible to do at least some TSX measurements from a KVM guest
> 
> Cc: avi@redhat.com
> Cc: gleb@redhat.com
> v2: Various fixes to address review feedback
> v3: Ignore the bits when no CPUID. No #GP. Force raw events with TSX bits.
> Cc: gleb@redhat.com
> Signed-off-by: Andi Kleen <ak@linux.intel.com>
> ---
>  arch/x86/include/asm/kvm_host.h |    1 +
>  arch/x86/kvm/pmu.c              |   34 ++++++++++++++++++++++++++--------
>  2 files changed, 27 insertions(+), 8 deletions(-)
> 
> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> index b2e11f4..6783289 100644
> --- a/arch/x86/include/asm/kvm_host.h
> +++ b/arch/x86/include/asm/kvm_host.h
> @@ -318,6 +318,7 @@ struct kvm_pmu {
>  	u64 global_ovf_ctrl;
>  	u64 counter_bitmask[2];
>  	u64 global_ctrl_mask;
> +	u64 cpuid_word9;
>  	u8 version;
>  	struct kvm_pmc gp_counters[INTEL_PMC_MAX_GENERIC];
>  	struct kvm_pmc fixed_counters[INTEL_PMC_MAX_FIXED];
> diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
> index cfc258a..8bc954a 100644
> --- a/arch/x86/kvm/pmu.c
> +++ b/arch/x86/kvm/pmu.c
> @@ -160,7 +160,7 @@ static void stop_counter(struct kvm_pmc *pmc)
>  
>  static void reprogram_counter(struct kvm_pmc *pmc, u32 type,
>  		unsigned config, bool exclude_user, bool exclude_kernel,
> -		bool intr)
> +		bool intr, bool intx, bool intx_cp)
>  {
>  	struct perf_event *event;
>  	struct perf_event_attr attr = {
> @@ -173,6 +173,11 @@ static void reprogram_counter(struct kvm_pmc *pmc, u32 type,
>  		.exclude_kernel = exclude_kernel,
>  		.config = config,
>  	};
> +	/* Will be ignored on CPUs that don't support this. */
> +	if (intx)
> +		attr.config |= HSW_INTX;
> +	if (intx_cp)
> +		attr.config |= HSW_INTX_CHECKPOINTED;
>  
>  	attr.sample_period = (-pmc->counter) & pmc_bitmask(pmc);
>  
> @@ -206,7 +211,8 @@ static unsigned find_arch_event(struct kvm_pmu *pmu, u8 event_select,
>  	return arch_events[i].event_type;
>  }
>  
> -static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
> +static void reprogram_gp_counter(struct kvm_pmu *pmu, struct kvm_pmc *pmc, 
> +				 u64 eventsel)
>  {
>  	unsigned config, type = PERF_TYPE_RAW;
>  	u8 event_select, unit_mask;
> @@ -224,9 +230,16 @@ static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
>  	event_select = eventsel & ARCH_PERFMON_EVENTSEL_EVENT;
>  	unit_mask = (eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8;
>  
> +	if (!(boot_cpu_has(X86_FEATURE_HLE) ||
> +	      boot_cpu_has(X86_FEATURE_RTM)) ||
> +	    !(pmu->cpuid_word9 & (X86_FEATURE_HLE|X86_FEATURE_RTM)))
> +		eventsel &= ~(HSW_INTX|HSW_INTX_CHECKPOINTED);
If you put this check into kvm_pmu_cpuid_update() and disallow guest to
set those bits in the first place by choosing appropriate reserved mask
you will not need this check here. This will simplify the code and will
make emulation more correct.

> +
>  	if (!(eventsel & (ARCH_PERFMON_EVENTSEL_EDGE |
>  				ARCH_PERFMON_EVENTSEL_INV |
> -				ARCH_PERFMON_EVENTSEL_CMASK))) {
> +				ARCH_PERFMON_EVENTSEL_CMASK |
> +				HSW_INTX |
> +				HSW_INTX_CHECKPOINTED))) {
>  		config = find_arch_event(&pmc->vcpu->arch.pmu, event_select,
>  				unit_mask);
>  		if (config != PERF_COUNT_HW_MAX)
> @@ -239,7 +252,9 @@ static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
>  	reprogram_counter(pmc, type, config,
>  			!(eventsel & ARCH_PERFMON_EVENTSEL_USR),
>  			!(eventsel & ARCH_PERFMON_EVENTSEL_OS),
> -			eventsel & ARCH_PERFMON_EVENTSEL_INT);
> +			eventsel & ARCH_PERFMON_EVENTSEL_INT,
> +			(eventsel & HSW_INTX),
> +			(eventsel & HSW_INTX_CHECKPOINTED));
>  }
>  
>  static void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 en_pmi, int idx)
> @@ -256,7 +271,7 @@ static void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 en_pmi, int idx)
>  			arch_events[fixed_pmc_events[idx]].event_type,
>  			!(en & 0x2), /* exclude user */
>  			!(en & 0x1), /* exclude kernel */
> -			pmi);
> +			pmi, false, false);
>  }
>  
>  static inline u8 fixed_en_pmi(u64 ctrl, int idx)
> @@ -289,7 +304,7 @@ static void reprogram_idx(struct kvm_pmu *pmu, int idx)
>  		return;
>  
>  	if (pmc_is_gp(pmc))
> -		reprogram_gp_counter(pmc, pmc->eventsel);
> +		reprogram_gp_counter(pmu, pmc, pmc->eventsel);
>  	else {
>  		int fidx = idx - INTEL_PMC_IDX_FIXED;
>  		reprogram_fixed_counter(pmc,
> @@ -400,8 +415,8 @@ int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data)
>  		} else if ((pmc = get_gp_pmc(pmu, index, MSR_P6_EVNTSEL0))) {
>  			if (data == pmc->eventsel)
>  				return 0;
> -			if (!(data & 0xffffffff00200000ull)) {
> -				reprogram_gp_counter(pmc, data);
> +			if (!(data & 0xfffffffc00200000ull)) {
> +				reprogram_gp_counter(pmu, pmc, data);
>  				return 0;
>  			}
>  		}
> @@ -470,6 +485,9 @@ void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu)
>  	pmu->global_ctrl = ((1 << pmu->nr_arch_gp_counters) - 1) |
>  		(((1ull << pmu->nr_arch_fixed_counters) - 1) << INTEL_PMC_IDX_FIXED);
>  	pmu->global_ctrl_mask = ~pmu->global_ctrl;
> +
> +	entry = kvm_find_cpuid_entry(vcpu, 7, 0);
> +	pmu->cpuid_word9 = entry ? entry->ebx : 0;
>  }
>  
>  void kvm_pmu_init(struct kvm_vcpu *vcpu)
> -- 
> 1.7.7.6

--
			Gleb.