perf/x86/intel: Make anythread filter support conditional

Starting with Arch Perfmon v5, the anythread filter on generic counters may be
deprecated. The current kernel was exporting the any filter without checking.
On Icelake, it means you could do cpu/event=0x3c,any/ even though the filter
does not exist. This patch corrects the problem by relying on the CPUID 0xa leaf
function to determine if anythread is supported or not as described in the
Intel SDM Vol3b 18.2.5.1 AnyThread Deprecation section.

Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20201028194247.3160610-1-eranian@google.com

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index c37387c..af457f8 100644 (file)
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -4987,6 +4987,12 @@ __init int intel_pmu_init(void)
 
        x86_add_quirk(intel_arch_events_quirk); /* Install first, so it runs last */
 
+       if (version >= 5) {
+               x86_pmu.intel_cap.anythread_deprecated = edx.split.anythread_deprecated;
+               if (x86_pmu.intel_cap.anythread_deprecated)
+                       pr_cont(" AnyThread deprecated, ");
+       }
+
        /*
         * Install the hw-cache-events table:
         */
@@ -5512,6 +5518,10 @@ __init int intel_pmu_init(void)
        x86_pmu.intel_ctrl |=
                ((1LL << x86_pmu.num_counters_fixed)-1) << INTEL_PMC_IDX_FIXED;
 
+       /* AnyThread may be deprecated on arch perfmon v5 or later */
+       if (x86_pmu.intel_cap.anythread_deprecated)
+               x86_pmu.format_attrs = intel_arch_formats_attr;
+
        if (x86_pmu.event_constraints) {
                /*
                 * event on fixed counter2 (REF_CYCLES) only works on this

diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 1d1fe46..6a8edfe 100644 (file)
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -585,6 +585,7 @@ union perf_capabilities {
                u64     pebs_baseline:1;
                u64     perf_metrics:1;
                u64     pebs_output_pt_available:1;
+               u64     anythread_deprecated:1;
        };
        u64     capabilities;
 };

diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 6960cd6..b9a7fd0 100644 (file)
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -137,7 +137,9 @@ union cpuid10_edx {
        struct {
                unsigned int num_counters_fixed:5;
                unsigned int bit_width_fixed:8;
-               unsigned int reserved:19;
+               unsigned int reserved1:2;
+               unsigned int anythread_deprecated:1;
+               unsigned int reserved2:16;
        } split;
        unsigned int full;
 };

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 06a278b..0752dec 100644 (file)
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -672,7 +672,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 
                edx.split.num_counters_fixed = min(cap.num_counters_fixed, MAX_FIXED_COUNTERS);
                edx.split.bit_width_fixed = cap.bit_width_fixed;
-               edx.split.reserved = 0;
+               edx.split.anythread_deprecated = 1;
+               edx.split.reserved1 = 0;
+               edx.split.reserved2 = 0;
 
                entry->eax = eax.full;
                entry->ebx = cap.events_mask;