[Patch v2 3/7] perf/x86/intel: Add core PMU support for DMR

[Dapeng Mi <dapeng1.mi@linux.intel.com>]

This patch enables core PMU features for Diamond Rapids (Panther Cove
microarchitecture), including Panther Cove specific counter and PEBS
constraints, a new cache events ID table, and the model-specific OMR
events extra registers table.

For detailed information about counter constraints, please refer to
section 16.3 "COUNTER RESTRICTIONS" in the ISE documentation.

ISE: https://www.intel.com/content/www/us/en/content-details/869288/intel-architecture-instruction-set-extensions-programming-reference.html

Signed-off-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
---
 arch/x86/events/intel/core.c | 182 +++++++++++++++++++++++++++++++++++
 arch/x86/events/intel/ds.c   |  27 ++++++
 arch/x86/events/perf_event.h |   2 +
 3 files changed, 211 insertions(+)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 6ea3260f6422..82fac6e8731b 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -435,6 +435,62 @@ static struct extra_reg intel_lnc_extra_regs[] __read_mostly = {
 	EVENT_EXTRA_END
 };
 
+static struct event_constraint intel_pnc_event_constraints[] = {
+	FIXED_EVENT_CONSTRAINT(0x00c0, 0),	/* INST_RETIRED.ANY */
+	FIXED_EVENT_CONSTRAINT(0x0100, 0),	/* INST_RETIRED.PREC_DIST */
+	FIXED_EVENT_CONSTRAINT(0x003c, 1),	/* CPU_CLK_UNHALTED.CORE */
+	FIXED_EVENT_CONSTRAINT(0x0300, 2),	/* CPU_CLK_UNHALTED.REF */
+	FIXED_EVENT_CONSTRAINT(0x013c, 2),	/* CPU_CLK_UNHALTED.REF_TSC_P */
+	FIXED_EVENT_CONSTRAINT(0x0400, 3),	/* SLOTS */
+	METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_RETIRING, 0),
+	METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_BAD_SPEC, 1),
+	METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_FE_BOUND, 2),
+	METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_BE_BOUND, 3),
+	METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_HEAVY_OPS, 4),
+	METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_BR_MISPREDICT, 5),
+	METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_FETCH_LAT, 6),
+	METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_MEM_BOUND, 7),
+
+	INTEL_EVENT_CONSTRAINT(0x20, 0xf),
+	INTEL_EVENT_CONSTRAINT(0x79, 0xf),
+
+	INTEL_UEVENT_CONSTRAINT(0x0275, 0xf),
+	INTEL_UEVENT_CONSTRAINT(0x0176, 0xf),
+	INTEL_UEVENT_CONSTRAINT(0x04a4, 0x1),
+	INTEL_UEVENT_CONSTRAINT(0x08a4, 0x1),
+	INTEL_UEVENT_CONSTRAINT(0x01cd, 0xfc),
+	INTEL_UEVENT_CONSTRAINT(0x02cd, 0x3),
+
+	INTEL_EVENT_CONSTRAINT(0xd0, 0xf),
+	INTEL_EVENT_CONSTRAINT(0xd1, 0xf),
+	INTEL_EVENT_CONSTRAINT(0xd4, 0xf),
+	INTEL_EVENT_CONSTRAINT(0xd6, 0xf),
+	INTEL_EVENT_CONSTRAINT(0xdf, 0xf),
+	INTEL_EVENT_CONSTRAINT(0xce, 0x1),
+
+	INTEL_UEVENT_CONSTRAINT(0x01b1, 0x8),
+	INTEL_UEVENT_CONSTRAINT(0x0847, 0xf),
+	INTEL_UEVENT_CONSTRAINT(0x0446, 0xf),
+	INTEL_UEVENT_CONSTRAINT(0x0846, 0xf),
+	INTEL_UEVENT_CONSTRAINT(0x0148, 0xf),
+
+	EVENT_CONSTRAINT_END
+};
+
+static struct extra_reg intel_pnc_extra_regs[] __read_mostly = {
+	/* must define OMR_X first, see intel_alt_er() */
+	INTEL_UEVENT_EXTRA_REG(0x012a, MSR_OMR_0, 0x40ffffff0000ffffull, OMR_0),
+	INTEL_UEVENT_EXTRA_REG(0x022a, MSR_OMR_1, 0x40ffffff0000ffffull, OMR_1),
+	INTEL_UEVENT_EXTRA_REG(0x042a, MSR_OMR_2, 0x40ffffff0000ffffull, OMR_2),
+	INTEL_UEVENT_EXTRA_REG(0x082a, MSR_OMR_3, 0x40ffffff0000ffffull, OMR_3),
+	INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
+	INTEL_UEVENT_EXTRA_REG(0x02c6, MSR_PEBS_FRONTEND, 0x9, FE),
+	INTEL_UEVENT_EXTRA_REG(0x03c6, MSR_PEBS_FRONTEND, 0x7fff1f, FE),
+	INTEL_UEVENT_EXTRA_REG(0x40ad, MSR_PEBS_FRONTEND, 0xf, FE),
+	INTEL_UEVENT_EXTRA_REG(0x04c2, MSR_PEBS_FRONTEND, 0x8, FE),
+	EVENT_EXTRA_END
+};
+
 EVENT_ATTR_STR(mem-loads,	mem_ld_nhm,	"event=0x0b,umask=0x10,ldlat=3");
 EVENT_ATTR_STR(mem-loads,	mem_ld_snb,	"event=0xcd,umask=0x1,ldlat=3");
 EVENT_ATTR_STR(mem-stores,	mem_st_snb,	"event=0xcd,umask=0x2");
@@ -650,6 +706,102 @@ static __initconst const u64 glc_hw_cache_extra_regs
  },
 };
 
+static __initconst const u64 pnc_hw_cache_event_ids
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(L1D ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x81d0,
+		[ C(RESULT_MISS)   ] = 0xe124,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x82d0,
+	},
+ },
+ [ C(L1I ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_MISS)   ] = 0xe424,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+ [ C(LL  ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x12a,
+		[ C(RESULT_MISS)   ] = 0x12a,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x12a,
+		[ C(RESULT_MISS)   ] = 0x12a,
+	},
+ },
+ [ C(DTLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x81d0,
+		[ C(RESULT_MISS)   ] = 0xe12,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x82d0,
+		[ C(RESULT_MISS)   ] = 0xe13,
+	},
+ },
+ [ C(ITLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = 0xe11,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+ [ C(BPU ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x4c4,
+		[ C(RESULT_MISS)   ] = 0x4c5,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+ [ C(NODE) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+};
+
+static __initconst const u64 pnc_hw_cache_extra_regs
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(LL  ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x4000000000000001,
+		[ C(RESULT_MISS)   ] = 0xFFFFF000000001,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x4000000000000002,
+		[ C(RESULT_MISS)   ] = 0xFFFFF000000002,
+	},
+ },
+};
+
 /*
  * Notes on the events:
  * - data reads do not include code reads (comparable to earlier tables)
@@ -7230,6 +7382,20 @@ static __always_inline void intel_pmu_init_lnc(struct pmu *pmu)
 	hybrid(pmu, extra_regs) = intel_lnc_extra_regs;
 }
 
+static __always_inline void intel_pmu_init_pnc(struct pmu *pmu)
+{
+	intel_pmu_init_glc(pmu);
+	x86_pmu.flags &= ~PMU_FL_HAS_RSP_1;
+	x86_pmu.flags |= PMU_FL_HAS_OMR;
+	memcpy(hybrid_var(pmu, hw_cache_event_ids),
+	       pnc_hw_cache_event_ids, sizeof(hw_cache_event_ids));
+	memcpy(hybrid_var(pmu, hw_cache_extra_regs),
+	       pnc_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
+	hybrid(pmu, event_constraints) = intel_pnc_event_constraints;
+	hybrid(pmu, pebs_constraints) = intel_pnc_pebs_event_constraints;
+	hybrid(pmu, extra_regs) = intel_pnc_extra_regs;
+}
+
 static __always_inline void intel_pmu_init_skt(struct pmu *pmu)
 {
 	intel_pmu_init_grt(pmu);
@@ -7906,6 +8072,22 @@ __init int intel_pmu_init(void)
 		intel_pmu_pebs_data_source_skl(true);
 		break;
 
+	case INTEL_DIAMONDRAPIDS_X:
+		intel_pmu_init_pnc(NULL);
+		x86_pmu.pebs_ept = 1;
+		x86_pmu.hw_config = hsw_hw_config;
+		x86_pmu.pebs_latency_data = pnc_latency_data;
+		x86_pmu.get_event_constraints = glc_get_event_constraints;
+		extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
+			hsw_format_attr : nhm_format_attr;
+		extra_skl_attr = skl_format_attr;
+		mem_attr = glc_events_attrs;
+		td_attr = glc_td_events_attrs;
+		tsx_attr = glc_tsx_events_attrs;
+		pr_cont("Panthercove events, ");
+		name = "panthercove";
+		break;
+
 	case INTEL_ALDERLAKE:
 	case INTEL_ALDERLAKE_L:
 	case INTEL_RAPTORLAKE:
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 272e652f25fc..06e42ac33749 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1425,6 +1425,33 @@ struct event_constraint intel_lnc_pebs_event_constraints[] = {
 	EVENT_CONSTRAINT_END
 };
 
+struct event_constraint intel_pnc_pebs_event_constraints[] = {
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x100, 0x100000000ULL),	/* INST_RETIRED.PREC_DIST */
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL),
+
+	INTEL_HYBRID_LDLAT_CONSTRAINT(0x1cd, 0xfc),
+	INTEL_HYBRID_STLAT_CONSTRAINT(0x2cd, 0x3),
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf),	/* MEM_INST_RETIRED.STLB_MISS_LOADS */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf),	/* MEM_INST_RETIRED.STLB_MISS_STORES */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf),	/* MEM_INST_RETIRED.LOCK_LOADS */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x41d0, 0xf),	/* MEM_INST_RETIRED.SPLIT_LOADS */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x42d0, 0xf),	/* MEM_INST_RETIRED.SPLIT_STORES */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x81d0, 0xf),	/* MEM_INST_RETIRED.ALL_LOADS */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x82d0, 0xf),	/* MEM_INST_RETIRED.ALL_STORES */
+
+	INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(0xd1, 0xd4, 0xf),
+
+	INTEL_FLAGS_EVENT_CONSTRAINT(0xd0, 0xf),
+	INTEL_FLAGS_EVENT_CONSTRAINT(0xd6, 0xf),
+
+	/*
+	 * Everything else is handled by PMU_FL_PEBS_ALL, because we
+	 * need the full constraints from the main table.
+	 */
+
+	EVENT_CONSTRAINT_END
+};
+
 struct event_constraint *intel_pebs_constraints(struct perf_event *event)
 {
 	struct event_constraint *pebs_constraints = hybrid(event->pmu, pebs_constraints);
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index bd501c2a0f73..cbca1888e8f7 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -1698,6 +1698,8 @@ extern struct event_constraint intel_glc_pebs_event_constraints[];
 
 extern struct event_constraint intel_lnc_pebs_event_constraints[];
 
+extern struct event_constraint intel_pnc_pebs_event_constraints[];
+
 struct event_constraint *intel_pebs_constraints(struct perf_event *event);
 
 void intel_pmu_pebs_add(struct perf_event *event);
-- 
2.34.1