perf/x86/intel: Support Perfmon MSRs aliasing

JIRA: https://issues.redhat.com/browse/RHEL-20059

upstream
========
commit 149fd47
Author: Kan Liang <kan.liang@linux.intel.com>
Date: Wed Jun 26 07:35:40 2024 -0700

description
===========
The architectural performance monitoring V6 supports a new range of
counters' MSRs in the 19xxH address range. They include all the GP
counter MSRs, the GP control MSRs, and the fixed counter MSRs.

The step between each sibling counter is 4. Add intel_pmu_addr_offset()
to calculate the correct offset.

Add fixedctr in struct x86_pmu to store the address of the fixed counter
0. It can be used to calculate the rest of the fixed counters.

The MSR address of the fixed counter control is not changed.

    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/20240626143545.480761-9-kan.liang@linux.intel.com

Signed-off-by: Michael Petlan <mpetlan@redhat.com>

Author: rfmvh

arch/x86/events/core.c

@@ -1236,8 +1236,7 @@ static inline void x86_assign_hw_event(struct perf_event *event,
 		fallthrough;
 	case INTEL_PMC_IDX_FIXED ... INTEL_PMC_IDX_FIXED_BTS-1:
 		hwc->config_base = MSR_ARCH_PERFMON_FIXED_CTR_CTRL;
-		hwc->event_base = MSR_ARCH_PERFMON_FIXED_CTR0 +
-				(idx - INTEL_PMC_IDX_FIXED);
+		hwc->event_base = x86_pmu_fixed_ctr_addr(idx - INTEL_PMC_IDX_FIXED);
 		hwc->event_base_rdpmc = (idx - INTEL_PMC_IDX_FIXED) |
 					INTEL_PMC_FIXED_RDPMC_BASE;
 		break;
@@ -1573,7 +1572,7 @@ void perf_event_print_debug(void)
 	for_each_set_bit(idx, fixed_cntr_mask, X86_PMC_IDX_MAX) {
 		if (fixed_counter_disabled(idx, cpuc->pmu))
 			continue;
-		rdmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, pmc_count);
+		rdmsrl(x86_pmu_fixed_ctr_addr(idx), pmc_count);
 
 		pr_info("CPU#%d: fixed-PMC%d count: %016llx\n",
 			cpu, idx, pmc_count);
@@ -2483,7 +2482,7 @@ void perf_clear_dirty_counters(void)
 			if (!test_bit(i - INTEL_PMC_IDX_FIXED, hybrid(cpuc->pmu, fixed_cntr_mask)))
 				continue;
 
-			wrmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + (i - INTEL_PMC_IDX_FIXED), 0);
+			wrmsrl(x86_pmu_fixed_ctr_addr(i - INTEL_PMC_IDX_FIXED), 0);
 		} else {
 			wrmsrl(x86_pmu_event_addr(i), 0);
 		}

arch/x86/events/intel/core.c

@@ -2952,7 +2952,7 @@ static void intel_pmu_reset(void)
 	for_each_set_bit(idx, fixed_cntr_mask, INTEL_PMC_MAX_FIXED) {
 		if (fixed_counter_disabled(idx, cpuc->pmu))
 			continue;
-		wrmsrl_safe(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, 0ull);
+		wrmsrl_safe(x86_pmu_fixed_ctr_addr(idx), 0ull);
 	}
 
 	if (ds)
@@ -5187,6 +5187,7 @@ static __initconst const struct x86_pmu core_pmu = {
 	.schedule_events	= x86_schedule_events,
 	.eventsel		= MSR_ARCH_PERFMON_EVENTSEL0,
 	.perfctr		= MSR_ARCH_PERFMON_PERFCTR0,
+	.fixedctr		= MSR_ARCH_PERFMON_FIXED_CTR0,
 	.event_map		= intel_pmu_event_map,
 	.max_events		= ARRAY_SIZE(intel_perfmon_event_map),
 	.apic			= 1,
@@ -5240,6 +5241,7 @@ static __initconst const struct x86_pmu intel_pmu = {
 	.schedule_events	= x86_schedule_events,
 	.eventsel		= MSR_ARCH_PERFMON_EVENTSEL0,
 	.perfctr		= MSR_ARCH_PERFMON_PERFCTR0,
+	.fixedctr		= MSR_ARCH_PERFMON_FIXED_CTR0,
 	.event_map		= intel_pmu_event_map,
 	.max_events		= ARRAY_SIZE(intel_perfmon_event_map),
 	.apic			= 1,
@@ -6182,6 +6184,11 @@ static void intel_pmu_check_extra_regs(struct extra_reg *extra_regs)
 	}
 }
 
+static inline int intel_pmu_v6_addr_offset(int index, bool eventsel)
+{
+	return MSR_IA32_PMC_V6_STEP * index;
+}
+
 static const struct { enum hybrid_pmu_type id; char *name; } intel_hybrid_pmu_type_map[] __initconst = {
 	{ hybrid_small, "cpu_atom" },
 	{ hybrid_big, "cpu_core" },
@@ -7156,6 +7163,14 @@ __init int intel_pmu_init(void)
 		pr_cont("full-width counters, ");
 	}
 
+	/* Support V6+ MSR Aliasing */
+	if (x86_pmu.version >= 6) {
+		x86_pmu.perfctr = MSR_IA32_PMC_V6_GP0_CTR;
+		x86_pmu.eventsel = MSR_IA32_PMC_V6_GP0_CFG_A;
+		x86_pmu.fixedctr = MSR_IA32_PMC_V6_FX0_CTR;
+		x86_pmu.addr_offset = intel_pmu_v6_addr_offset;
+	}
+
 	if (!is_hybrid() && x86_pmu.intel_cap.perf_metrics)
 		x86_pmu.intel_ctrl |= 1ULL << GLOBAL_CTRL_EN_PERF_METRICS;
 

arch/x86/events/perf_event.h

@@ -787,6 +787,7 @@ struct x86_pmu {
 	int		(*schedule_events)(struct cpu_hw_events *cpuc, int n, int *assign);
 	unsigned	eventsel;
 	unsigned	perfctr;
+	unsigned	fixedctr;
 	int		(*addr_offset)(int index, bool eventsel);
 	int		(*rdpmc_index)(int index);
 	u64		(*event_map)(int);
@@ -1144,6 +1145,12 @@ static inline unsigned int x86_pmu_event_addr(int index)
 				  x86_pmu.addr_offset(index, false) : index);
 }
 
+static inline unsigned int x86_pmu_fixed_ctr_addr(int index)
+{
+	return x86_pmu.fixedctr + (x86_pmu.addr_offset ?
+				   x86_pmu.addr_offset(index, false) : index);
+}
+
 static inline int x86_pmu_rdpmc_index(int index)
 {
 	return x86_pmu.rdpmc_index ? x86_pmu.rdpmc_index(index) : index;

arch/x86/include/asm/msr-index.h

@@ -556,6 +556,12 @@
 #define MSR_RELOAD_PMC0			0x000014c1
 #define MSR_RELOAD_FIXED_CTR0		0x00001309
 
+/* V6 PMON MSR range */
+#define MSR_IA32_PMC_V6_GP0_CTR		0x1900
+#define MSR_IA32_PMC_V6_GP0_CFG_A	0x1901
+#define MSR_IA32_PMC_V6_FX0_CTR		0x1980
+#define MSR_IA32_PMC_V6_STEP		4
+
 /* KeyID partitioning between MKTME and TDX */
 #define MSR_IA32_MKTME_KEYID_PARTITIONING	0x00000087