perf/x86: Support counter mask

The current perf assumes that both GP and fixed counters are contiguous.
But it's not guaranteed on newer Intel platforms or in a virtualization
environment.

Use the counter mask to replace the number of counters for both GP and
the fixed counters. For the other ARCHs or old platforms which don't
support a counter mask, using GENMASK_ULL(num_counter - 1, 0) to
replace. There is no functional change for them.

The interface to KVM is not changed. The number of counters still be
passed to KVM. It can be updated later separately.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Reviewed-by: Ian Rogers <irogers@google.com>
Link: https://lkml.kernel.org/r/20240626143545.480761-3-kan.liang@linux.intel.com

1 files changed, 8 insertions, 11 deletions

diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index f6105b8dcf87..6f834a7d852a 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1138,7 +1138,6 @@ static inline void pebs_update_threshold(struct cpu_hw_events *cpuc)
 {
 	struct debug_store *ds = cpuc->ds;
 	int max_pebs_events = intel_pmu_max_num_pebs(cpuc->pmu);
-	int num_counters_fixed = hybrid(cpuc->pmu, num_counters_fixed);
 	u64 threshold;
 	int reserved;
 
@@ -1146,7 +1145,7 @@ static inline void pebs_update_threshold(struct cpu_hw_events *cpuc)
 		return;
 
 	if (x86_pmu.flags & PMU_FL_PEBS_ALL)
-		reserved = max_pebs_events + num_counters_fixed;
+		reserved = max_pebs_events + x86_pmu_max_num_counters_fixed(cpuc->pmu);
 	else
 		reserved = max_pebs_events;
 
@@ -2172,8 +2171,8 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d
 	mask = x86_pmu.pebs_events_mask;
 	size = max_pebs_events;
 	if (x86_pmu.flags & PMU_FL_PEBS_ALL) {
-		mask |= ((1ULL << x86_pmu.num_counters_fixed) - 1) << INTEL_PMC_IDX_FIXED;
-		size = INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed;
+		mask |= x86_pmu.fixed_cntr_mask64 << INTEL_PMC_IDX_FIXED;
+		size = INTEL_PMC_IDX_FIXED + x86_pmu_max_num_counters_fixed(NULL);
 	}
 
 	if (unlikely(base >= top)) {
@@ -2269,11 +2268,10 @@ static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_d
 {
 	short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
-	int num_counters_fixed = hybrid(cpuc->pmu, num_counters_fixed);
 	struct debug_store *ds = cpuc->ds;
 	struct perf_event *event;
 	void *base, *at, *top;
-	int bit, size;
+	int bit;
 	u64 mask;
 
 	if (!x86_pmu.pebs_active)
@@ -2285,11 +2283,10 @@ static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_d
 	ds->pebs_index = ds->pebs_buffer_base;
 
 	mask = hybrid(cpuc->pmu, pebs_events_mask) |
-	       (((1ULL << num_counters_fixed) - 1) << INTEL_PMC_IDX_FIXED);
-	size = INTEL_PMC_IDX_FIXED + num_counters_fixed;
+	       (hybrid(cpuc->pmu, fixed_cntr_mask64) << INTEL_PMC_IDX_FIXED);
 
 	if (unlikely(base >= top)) {
-		intel_pmu_pebs_event_update_no_drain(cpuc, size);
+		intel_pmu_pebs_event_update_no_drain(cpuc, X86_PMC_IDX_MAX);
 		return;
 	}
 
@@ -2299,11 +2296,11 @@ static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_d
 		pebs_status = get_pebs_status(at) & cpuc->pebs_enabled;
 		pebs_status &= mask;
 
-		for_each_set_bit(bit, (unsigned long *)&pebs_status, size)
+		for_each_set_bit(bit, (unsigned long *)&pebs_status, X86_PMC_IDX_MAX)
 			counts[bit]++;
 	}
 
-	for_each_set_bit(bit, (unsigned long *)&mask, size) {
+	for_each_set_bit(bit, (unsigned long *)&mask, X86_PMC_IDX_MAX) {
 		if (counts[bit] == 0)
 			continue;