Merge: perf: Intel Arrowlake support (RAPL and perfmon)

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/6881

JIRA: https://issues.redhat.com/browse/RHEL-20094

JIRA: https://issues.redhat.com/browse/RHEL-53585

This MR adds all currently known code to enable pref features on
Intel Arrow Lake.

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

Approved-by: Lenny Szubowicz <lszubowi@redhat.com>
Approved-by: ashelat <ashelat@redhat.com>
Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com>

Merged-by: Augusto Caringi <acaringi@redhat.com>

Author: caringi

arch/x86/events/intel/core.c

@@ -4598,6 +4598,28 @@ static inline bool erratum_hsw11(struct perf_event *event)
 		X86_CONFIG(.event=0xc0, .umask=0x01);
 }
 
+static struct event_constraint *
+arl_h_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
+			  struct perf_event *event)
+{
+	struct x86_hybrid_pmu *pmu = hybrid_pmu(event->pmu);
+
+	if (pmu->pmu_type == hybrid_tiny)
+		return cmt_get_event_constraints(cpuc, idx, event);
+
+	return mtl_get_event_constraints(cpuc, idx, event);
+}
+
+static int arl_h_hw_config(struct perf_event *event)
+{
+	struct x86_hybrid_pmu *pmu = hybrid_pmu(event->pmu);
+
+	if (pmu->pmu_type == hybrid_tiny)
+		return intel_pmu_hw_config(event);
+
+	return adl_hw_config(event);
+}
+
 /*
  * The HSW11 requires a period larger than 100 which is the same as the BDM11.
  * A minimum period of 128 is enforced as well for the INST_RETIRED.ALL.
@@ -4923,17 +4945,26 @@ static struct x86_hybrid_pmu *find_hybrid_pmu_for_cpu(void)
 
 	/*
 	 * This essentially just maps between the 'hybrid_cpu_type'
-	 * and 'hybrid_pmu_type' enums:
+	 * and 'hybrid_pmu_type' enums except for ARL-H processor
+	 * which needs to compare atom uarch native id since ARL-H
+	 * contains two different atom uarchs.
 	 */
 	for (i = 0; i < x86_pmu.num_hybrid_pmus; i++) {
 		enum hybrid_pmu_type pmu_type = x86_pmu.hybrid_pmu[i].pmu_type;
+		u32 native_id;
 
-		if (cpu_type == HYBRID_INTEL_CORE &&
-		    pmu_type == hybrid_big)
-			return &x86_pmu.hybrid_pmu[i];
-		if (cpu_type == HYBRID_INTEL_ATOM &&
-		    pmu_type == hybrid_small)
+		if (cpu_type == HYBRID_INTEL_CORE && pmu_type == hybrid_big)
 			return &x86_pmu.hybrid_pmu[i];
+		if (cpu_type == HYBRID_INTEL_ATOM) {
+			if (x86_pmu.num_hybrid_pmus == 2 && pmu_type == hybrid_small)
+				return &x86_pmu.hybrid_pmu[i];
+
+			native_id = get_this_hybrid_cpu_native_id();
+			if (native_id == skt_native_id && pmu_type == hybrid_small)
+				return &x86_pmu.hybrid_pmu[i];
+			if (native_id == cmt_native_id && pmu_type == hybrid_tiny)
+				return &x86_pmu.hybrid_pmu[i];
+		}
 	}
 
 	return NULL;
@@ -5971,6 +6002,37 @@ static struct attribute *lnl_hybrid_events_attrs[] = {
 	NULL
 };
 
+/* The event string must be in PMU IDX order. */
+EVENT_ATTR_STR_HYBRID(topdown-retiring,
+		      td_retiring_arl_h,
+		      "event=0xc2,umask=0x02;event=0x00,umask=0x80;event=0xc2,umask=0x0",
+		      hybrid_big_small_tiny);
+EVENT_ATTR_STR_HYBRID(topdown-bad-spec,
+		      td_bad_spec_arl_h,
+		      "event=0x73,umask=0x0;event=0x00,umask=0x81;event=0x73,umask=0x0",
+		      hybrid_big_small_tiny);
+EVENT_ATTR_STR_HYBRID(topdown-fe-bound,
+		      td_fe_bound_arl_h,
+		      "event=0x9c,umask=0x01;event=0x00,umask=0x82;event=0x71,umask=0x0",
+		      hybrid_big_small_tiny);
+EVENT_ATTR_STR_HYBRID(topdown-be-bound,
+		      td_be_bound_arl_h,
+		      "event=0xa4,umask=0x02;event=0x00,umask=0x83;event=0x74,umask=0x0",
+		      hybrid_big_small_tiny);
+
+static struct attribute *arl_h_hybrid_events_attrs[] = {
+	EVENT_PTR(slots_adl),
+	EVENT_PTR(td_retiring_arl_h),
+	EVENT_PTR(td_bad_spec_arl_h),
+	EVENT_PTR(td_fe_bound_arl_h),
+	EVENT_PTR(td_be_bound_arl_h),
+	EVENT_PTR(td_heavy_ops_adl),
+	EVENT_PTR(td_br_mis_adl),
+	EVENT_PTR(td_fetch_lat_adl),
+	EVENT_PTR(td_mem_bound_adl),
+	NULL,
+};
+
 /* Must be in IDX order */
 EVENT_ATTR_STR_HYBRID(mem-loads,     mem_ld_adl,     "event=0xd0,umask=0x5,ldlat=3;event=0xcd,umask=0x1,ldlat=3", hybrid_big_small);
 EVENT_ATTR_STR_HYBRID(mem-stores,    mem_st_adl,     "event=0xd0,umask=0x6;event=0xcd,umask=0x2",                 hybrid_big_small);
@@ -5989,6 +6051,21 @@ static struct attribute *mtl_hybrid_mem_attrs[] = {
 	NULL
 };
 
+EVENT_ATTR_STR_HYBRID(mem-loads,
+		      mem_ld_arl_h,
+		      "event=0xd0,umask=0x5,ldlat=3;event=0xcd,umask=0x1,ldlat=3;event=0xd0,umask=0x5,ldlat=3",
+		      hybrid_big_small_tiny);
+EVENT_ATTR_STR_HYBRID(mem-stores,
+		      mem_st_arl_h,
+		      "event=0xd0,umask=0x6;event=0xcd,umask=0x2;event=0xd0,umask=0x6",
+		      hybrid_big_small_tiny);
+
+static struct attribute *arl_h_hybrid_mem_attrs[] = {
+	EVENT_PTR(mem_ld_arl_h),
+	EVENT_PTR(mem_st_arl_h),
+	NULL,
+};
+
 EVENT_ATTR_STR_HYBRID(tx-start,          tx_start_adl,          "event=0xc9,umask=0x1",          hybrid_big);
 EVENT_ATTR_STR_HYBRID(tx-commit,         tx_commit_adl,         "event=0xc9,umask=0x2",          hybrid_big);
 EVENT_ATTR_STR_HYBRID(tx-abort,          tx_abort_adl,          "event=0xc9,umask=0x4",          hybrid_big);
@@ -6012,8 +6089,8 @@ static struct attribute *adl_hybrid_tsx_attrs[] = {
 
 FORMAT_ATTR_HYBRID(in_tx,       hybrid_big);
 FORMAT_ATTR_HYBRID(in_tx_cp,    hybrid_big);
-FORMAT_ATTR_HYBRID(offcore_rsp, hybrid_big_small);
-FORMAT_ATTR_HYBRID(ldlat,       hybrid_big_small);
+FORMAT_ATTR_HYBRID(offcore_rsp, hybrid_big_small_tiny);
+FORMAT_ATTR_HYBRID(ldlat,       hybrid_big_small_tiny);
 FORMAT_ATTR_HYBRID(frontend,    hybrid_big);
 
 #define ADL_HYBRID_RTM_FORMAT_ATTR	\
@@ -6036,7 +6113,7 @@ static struct attribute *adl_hybrid_extra_attr[] = {
 	NULL
 };
 
-FORMAT_ATTR_HYBRID(snoop_rsp,	hybrid_small);
+FORMAT_ATTR_HYBRID(snoop_rsp,	hybrid_small_tiny);
 
 static struct attribute *mtl_hybrid_extra_attr_rtm[] = {
 	ADL_HYBRID_RTM_FORMAT_ATTR,
@@ -6244,8 +6321,9 @@ static inline int intel_pmu_v6_addr_offset(int index, bool eventsel)
 }
 
 static const struct { enum hybrid_pmu_type id; char *name; } intel_hybrid_pmu_type_map[] __initconst = {
-	{ hybrid_small, "cpu_atom" },
-	{ hybrid_big, "cpu_core" },
+	{ hybrid_small,	"cpu_atom" },
+	{ hybrid_big,	"cpu_core" },
+	{ hybrid_tiny,	"cpu_lowpower" },
 };
 
 static __always_inline int intel_pmu_init_hybrid(enum hybrid_pmu_type pmus)
@@ -6278,7 +6356,7 @@ static __always_inline int intel_pmu_init_hybrid(enum hybrid_pmu_type pmus)
 							0, x86_pmu_num_counters(&pmu->pmu), 0, 0);
 
 		pmu->intel_cap.capabilities = x86_pmu.intel_cap.capabilities;
-		if (pmu->pmu_type & hybrid_small) {
+		if (pmu->pmu_type & hybrid_small_tiny) {
 			pmu->intel_cap.perf_metrics = 0;
 			pmu->intel_cap.pebs_output_pt_available = 1;
 			pmu->mid_ack = true;
@@ -7118,6 +7196,37 @@ __init int intel_pmu_init(void)
 		name = "lunarlake_hybrid";
 		break;
 
+	case INTEL_ARROWLAKE_H:
+		intel_pmu_init_hybrid(hybrid_big_small_tiny);
+
+		x86_pmu.pebs_latency_data = arl_h_latency_data;
+		x86_pmu.get_event_constraints = arl_h_get_event_constraints;
+		x86_pmu.hw_config = arl_h_hw_config;
+
+		td_attr = arl_h_hybrid_events_attrs;
+		mem_attr = arl_h_hybrid_mem_attrs;
+		tsx_attr = adl_hybrid_tsx_attrs;
+		extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
+			mtl_hybrid_extra_attr_rtm : mtl_hybrid_extra_attr;
+
+		/* Initialize big core specific PerfMon capabilities. */
+		pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_CORE_IDX];
+		intel_pmu_init_lnc(&pmu->pmu);
+
+		/* Initialize Atom core specific PerfMon capabilities. */
+		pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM_IDX];
+		intel_pmu_init_skt(&pmu->pmu);
+
+		/* Initialize Lower Power Atom specific PerfMon capabilities. */
+		pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_TINY_IDX];
+		intel_pmu_init_grt(&pmu->pmu);
+		pmu->extra_regs = intel_cmt_extra_regs;
+
+		intel_pmu_pebs_data_source_arl_h();
+		pr_cont("ArrowLake-H Hybrid events, ");
+		name = "arrowlake_h_hybrid";
+		break;
+
 	default:
 		switch (x86_pmu.version) {
 		case 1:

arch/x86/events/intel/ds.c

@@ -176,6 +176,17 @@ void __init intel_pmu_pebs_data_source_mtl(void)
 	__intel_pmu_pebs_data_source_cmt(data_source);
 }
 
+void __init intel_pmu_pebs_data_source_arl_h(void)
+{
+	u64 *data_source;
+
+	intel_pmu_pebs_data_source_lnl();
+
+	data_source = x86_pmu.hybrid_pmu[X86_HYBRID_PMU_TINY_IDX].pebs_data_source;
+	memcpy(data_source, pebs_data_source, sizeof(pebs_data_source));
+	__intel_pmu_pebs_data_source_cmt(data_source);
+}
+
 void __init intel_pmu_pebs_data_source_cmt(void)
 {
 	__intel_pmu_pebs_data_source_cmt(pebs_data_source);
@@ -387,6 +398,16 @@ u64 lnl_latency_data(struct perf_event *event, u64 status)
 	return lnc_latency_data(event, status);
 }
 
+u64 arl_h_latency_data(struct perf_event *event, u64 status)
+{
+	struct x86_hybrid_pmu *pmu = hybrid_pmu(event->pmu);
+
+	if (pmu->pmu_type == hybrid_tiny)
+		return cmt_latency_data(event, status);
+
+	return lnl_latency_data(event, status);
+}
+
 static u64 load_latency_data(struct perf_event *event, u64 status)
 {
 	union intel_x86_pebs_dse dse;

arch/x86/events/perf_event.h

@@ -668,24 +668,38 @@ enum {
 #define PERF_PEBS_DATA_SOURCE_GRT_MAX	0x10
 #define PERF_PEBS_DATA_SOURCE_GRT_MASK	(PERF_PEBS_DATA_SOURCE_GRT_MAX - 1)
 
+/*
+ * CPUID.1AH.EAX[31:0] uniquely identifies the microarchitecture
+ * of the core. Bits 31-24 indicates its core type (Core or Atom)
+ * and Bits [23:0] indicates the native model ID of the core.
+ * Core type and native model ID are defined in below enumerations.
+ */
 enum hybrid_cpu_type {
 	HYBRID_INTEL_NONE,
 	HYBRID_INTEL_ATOM	= 0x20,
 	HYBRID_INTEL_CORE	= 0x40,
 };
 
+#define X86_HYBRID_PMU_ATOM_IDX		0
+#define X86_HYBRID_PMU_CORE_IDX		1
+#define X86_HYBRID_PMU_TINY_IDX		2
+
 enum hybrid_pmu_type {
 	not_hybrid,
-	hybrid_small		= BIT(0),
-	hybrid_big		= BIT(1),
-
-	hybrid_big_small	= hybrid_big | hybrid_small, /* only used for matching */
+	hybrid_small		= BIT(X86_HYBRID_PMU_ATOM_IDX),
+	hybrid_big		= BIT(X86_HYBRID_PMU_CORE_IDX),
+	hybrid_tiny		= BIT(X86_HYBRID_PMU_TINY_IDX),
+
+	/* The belows are only used for matching */
+	hybrid_big_small	= hybrid_big   | hybrid_small,
+	hybrid_small_tiny	= hybrid_small | hybrid_tiny,
+	hybrid_big_small_tiny	= hybrid_big   | hybrid_small_tiny,
 };
 
-#define X86_HYBRID_PMU_ATOM_IDX		0
-#define X86_HYBRID_PMU_CORE_IDX		1
-
-#define X86_HYBRID_NUM_PMUS		2
+enum atom_native_id {
+	cmt_native_id           = 0x2,  /* Crestmont */
+	skt_native_id           = 0x3,  /* Skymont */
+};
 
 struct x86_hybrid_pmu {
 	struct pmu			pmu;
@@ -1578,6 +1592,8 @@ u64 cmt_latency_data(struct perf_event *event, u64 status);
 
 u64 lnl_latency_data(struct perf_event *event, u64 status);
 
+u64 arl_h_latency_data(struct perf_event *event, u64 status);
+
 extern struct event_constraint intel_core2_pebs_event_constraints[];
 
 extern struct event_constraint intel_atom_pebs_event_constraints[];
@@ -1697,6 +1713,8 @@ void intel_pmu_pebs_data_source_grt(void);
 
 void intel_pmu_pebs_data_source_mtl(void);
 
+void intel_pmu_pebs_data_source_arl_h(void);
+
 void intel_pmu_pebs_data_source_cmt(void);
 
 void intel_pmu_pebs_data_source_lnl(void);

arch/x86/events/rapl.c

@@ -846,6 +846,7 @@ static const struct x86_cpu_id rapl_model_match[] __initconst = {
 	X86_MATCH_VFM(INTEL_METEORLAKE_L,	&model_skl),
 	X86_MATCH_VFM(INTEL_ARROWLAKE_H,	&model_skl),
 	X86_MATCH_VFM(INTEL_ARROWLAKE,		&model_skl),
+	X86_MATCH_VFM(INTEL_ARROWLAKE_U,	&model_skl),
 	X86_MATCH_VFM(INTEL_LUNARLAKE_M,	&model_skl),
 	{},
 };

arch/x86/include/asm/cpu.h

@@ -36,6 +36,7 @@ extern bool handle_user_split_lock(struct pt_regs *regs, long error_code);
 extern bool handle_guest_split_lock(unsigned long ip);
 extern void handle_bus_lock(struct pt_regs *regs);
 u8 get_this_hybrid_cpu_type(void);
+u32 get_this_hybrid_cpu_native_id(void);
 #else
 static inline void __init sld_setup(struct cpuinfo_x86 *c) {}
 static inline bool handle_user_split_lock(struct pt_regs *regs, long error_code)
@@ -54,6 +55,11 @@ static inline u8 get_this_hybrid_cpu_type(void)
 {
 	return 0;
 }
+
+static inline u32 get_this_hybrid_cpu_native_id(void)
+{
+	return 0;
+}
 #endif
 #ifdef CONFIG_IA32_FEAT_CTL
 void init_ia32_feat_ctl(struct cpuinfo_x86 *c);

arch/x86/kernel/cpu/intel.c

@@ -1348,3 +1348,18 @@ u8 get_this_hybrid_cpu_type(void)
 
 	return cpuid_eax(0x0000001a) >> X86_HYBRID_CPU_TYPE_ID_SHIFT;
 }
+
+/**
+ * get_this_hybrid_cpu_native_id() - Get the native id of this hybrid CPU
+ *
+ * Returns the uarch native ID [23:0] of a CPU in a hybrid processor.
+ * If the processor is not hybrid, returns 0.
+ */
+u32 get_this_hybrid_cpu_native_id(void)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_HYBRID_CPU))
+		return 0;
+
+	return cpuid_eax(0x0000001a) &
+	       (BIT_ULL(X86_HYBRID_CPU_TYPE_ID_SHIFT) - 1);
+}