1 files changed, 166 insertions, 64 deletions

diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 2e215369df4a..446d2833efa7 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -94,15 +94,45 @@ void __init intel_pmu_pebs_data_source_nhm(void)
 	pebs_data_source[0x07] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM);
 }
 
-void __init intel_pmu_pebs_data_source_skl(bool pmem)
+static void __init __intel_pmu_pebs_data_source_skl(bool pmem, u64 *data_source)
 {
 	u64 pmem_or_l4 = pmem ? LEVEL(PMEM) : LEVEL(L4);
 
-	pebs_data_source[0x08] = OP_LH | pmem_or_l4 | P(SNOOP, HIT);
-	pebs_data_source[0x09] = OP_LH | pmem_or_l4 | REM | P(SNOOP, HIT);
-	pebs_data_source[0x0b] = OP_LH | LEVEL(RAM) | REM | P(SNOOP, NONE);
-	pebs_data_source[0x0c] = OP_LH | LEVEL(ANY_CACHE) | REM | P(SNOOPX, FWD);
-	pebs_data_source[0x0d] = OP_LH | LEVEL(ANY_CACHE) | REM | P(SNOOP, HITM);
+	data_source[0x08] = OP_LH | pmem_or_l4 | P(SNOOP, HIT);
+	data_source[0x09] = OP_LH | pmem_or_l4 | REM | P(SNOOP, HIT);
+	data_source[0x0b] = OP_LH | LEVEL(RAM) | REM | P(SNOOP, NONE);
+	data_source[0x0c] = OP_LH | LEVEL(ANY_CACHE) | REM | P(SNOOPX, FWD);
+	data_source[0x0d] = OP_LH | LEVEL(ANY_CACHE) | REM | P(SNOOP, HITM);
+}
+
+void __init intel_pmu_pebs_data_source_skl(bool pmem)
+{
+	__intel_pmu_pebs_data_source_skl(pmem, pebs_data_source);
+}
+
+static void __init __intel_pmu_pebs_data_source_grt(u64 *data_source)
+{
+	data_source[0x05] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HIT);
+	data_source[0x06] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM);
+	data_source[0x08] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOPX, FWD);
+}
+
+void __init intel_pmu_pebs_data_source_grt(void)
+{
+	__intel_pmu_pebs_data_source_grt(pebs_data_source);
+}
+
+void __init intel_pmu_pebs_data_source_adl(void)
+{
+	u64 *data_source;
+
+	data_source = x86_pmu.hybrid_pmu[X86_HYBRID_PMU_CORE_IDX].pebs_data_source;
+	memcpy(data_source, pebs_data_source, sizeof(pebs_data_source));
+	__intel_pmu_pebs_data_source_skl(false, data_source);
+
+	data_source = x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM_IDX].pebs_data_source;
+	memcpy(data_source, pebs_data_source, sizeof(pebs_data_source));
+	__intel_pmu_pebs_data_source_grt(data_source);
 }
 
 static u64 precise_store_data(u64 status)
@@ -171,7 +201,50 @@ static u64 precise_datala_hsw(struct perf_event *event, u64 status)
 	return dse.val;
 }
 
-static u64 load_latency_data(u64 status)
+static inline void pebs_set_tlb_lock(u64 *val, bool tlb, bool lock)
+{
+	/*
+	 * TLB access
+	 * 0 = did not miss 2nd level TLB
+	 * 1 = missed 2nd level TLB
+	 */
+	if (tlb)
+		*val |= P(TLB, MISS) | P(TLB, L2);
+	else
+		*val |= P(TLB, HIT) | P(TLB, L1) | P(TLB, L2);
+
+	/* locked prefix */
+	if (lock)
+		*val |= P(LOCK, LOCKED);
+}
+
+/* Retrieve the latency data for e-core of ADL */
+u64 adl_latency_data_small(struct perf_event *event, u64 status)
+{
+	union intel_x86_pebs_dse dse;
+	u64 val;
+
+	WARN_ON_ONCE(hybrid_pmu(event->pmu)->cpu_type == hybrid_big);
+
+	dse.val = status;
+
+	val = hybrid_var(event->pmu, pebs_data_source)[dse.ld_dse];
+
+	/*
+	 * For the atom core on ADL,
+	 * bit 4: lock, bit 5: TLB access.
+	 */
+	pebs_set_tlb_lock(&val, dse.ld_locked, dse.ld_stlb_miss);
+
+	if (dse.ld_data_blk)
+		val |= P(BLK, DATA);
+	else
+		val |= P(BLK, NA);
+
+	return val;
+}
+
+static u64 load_latency_data(struct perf_event *event, u64 status)
 {
 	union intel_x86_pebs_dse dse;
 	u64 val;
@@ -181,7 +254,7 @@ static u64 load_latency_data(u64 status)
 	/*
 	 * use the mapping table for bit 0-3
 	 */
-	val = pebs_data_source[dse.ld_dse];
+	val = hybrid_var(event->pmu, pebs_data_source)[dse.ld_dse];
 
 	/*
 	 * Nehalem models do not support TLB, Lock infos
@@ -190,21 +263,8 @@ static u64 load_latency_data(u64 status)
 		val |= P(TLB, NA) | P(LOCK, NA);
 		return val;
 	}
-	/*
-	 * bit 4: TLB access
-	 * 0 = did not miss 2nd level TLB
-	 * 1 = missed 2nd level TLB
-	 */
-	if (dse.ld_stlb_miss)
-		val |= P(TLB, MISS) | P(TLB, L2);
-	else
-		val |= P(TLB, HIT) | P(TLB, L1) | P(TLB, L2);
 
-	/*
-	 * bit 5: locked prefix
-	 */
-	if (dse.ld_locked)
-		val |= P(LOCK, LOCKED);
+	pebs_set_tlb_lock(&val, dse.ld_stlb_miss, dse.ld_locked);
 
 	/*
 	 * Ice Lake and earlier models do not support block infos.
@@ -233,9 +293,10 @@ static u64 load_latency_data(u64 status)
 	return val;
 }
 
-static u64 store_latency_data(u64 status)
+static u64 store_latency_data(struct perf_event *event, u64 status)
 {
 	union intel_x86_pebs_dse dse;
+	union perf_mem_data_src src;
 	u64 val;
 
 	dse.val = status;
@@ -243,27 +304,20 @@ static u64 store_latency_data(u64 status)
 	/*
 	 * use the mapping table for bit 0-3
 	 */
-	val = pebs_data_source[dse.st_lat_dse];
+	val = hybrid_var(event->pmu, pebs_data_source)[dse.st_lat_dse];
 
-	/*
-	 * bit 4: TLB access
-	 * 0 = did not miss 2nd level TLB
-	 * 1 = missed 2nd level TLB
-	 */
-	if (dse.st_lat_stlb_miss)
-		val |= P(TLB, MISS) | P(TLB, L2);
-	else
-		val |= P(TLB, HIT) | P(TLB, L1) | P(TLB, L2);
+	pebs_set_tlb_lock(&val, dse.st_lat_stlb_miss, dse.st_lat_locked);
+
+	val |= P(BLK, NA);
 
 	/*
-	 * bit 5: locked prefix
+	 * the pebs_data_source table is only for loads
+	 * so override the mem_op to say STORE instead
 	 */
-	if (dse.st_lat_locked)
-		val |= P(LOCK, LOCKED);
+	src.val = val;
+	src.mem_op = P(OP,STORE);
 
-	val |= P(BLK, NA);
-
-	return val;
+	return src.val;
 }
 
 struct pebs_record_core {
@@ -781,8 +835,8 @@ struct event_constraint intel_glm_pebs_event_constraints[] = {
 
 struct event_constraint intel_grt_pebs_event_constraints[] = {
 	/* Allow all events as PEBS with no flags */
-	INTEL_PLD_CONSTRAINT(0x5d0, 0xf),
-	INTEL_PSD_CONSTRAINT(0x6d0, 0xf),
+	INTEL_HYBRID_LAT_CONSTRAINT(0x5d0, 0x3),
+	INTEL_HYBRID_LAT_CONSTRAINT(0x6d0, 0xf),
 	EVENT_CONSTRAINT_END
 };
 
@@ -928,8 +982,13 @@ struct event_constraint intel_icl_pebs_event_constraints[] = {
 	INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL),	/* SLOTS */
 
 	INTEL_PLD_CONSTRAINT(0x1cd, 0xff),			/* MEM_TRANS_RETIRED.LOAD_LATENCY */
-	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x1d0, 0xf),	/* MEM_INST_RETIRED.LOAD */
-	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x2d0, 0xf),	/* MEM_INST_RETIRED.STORE */
+	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), /* MEM_LOAD_*_RETIRED.* */
 
@@ -950,8 +1009,13 @@ struct event_constraint intel_spr_pebs_event_constraints[] = {
 	INTEL_FLAGS_EVENT_CONSTRAINT(0xc0, 0xfe),
 	INTEL_PLD_CONSTRAINT(0x1cd, 0xfe),
 	INTEL_PSD_CONSTRAINT(0x2cd, 0x1),
-	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x1d0, 0xf),
-	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x2d0, 0xf),
+	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),
 
@@ -1203,7 +1267,10 @@ static void intel_pmu_pebs_via_pt_enable(struct perf_event *event)
 	if (hwc->idx >= INTEL_PMC_IDX_FIXED) {
 		base = MSR_RELOAD_FIXED_CTR0;
 		idx = hwc->idx - INTEL_PMC_IDX_FIXED;
-		value = ds->pebs_event_reset[MAX_PEBS_EVENTS + idx];
+		if (x86_pmu.intel_cap.pebs_format < 5)
+			value = ds->pebs_event_reset[MAX_PEBS_EVENTS_FMT4 + idx];
+		else
+			value = ds->pebs_event_reset[MAX_PEBS_EVENTS + idx];
 	}
 	wrmsrl(base + idx, value);
 }
@@ -1232,8 +1299,12 @@ void intel_pmu_pebs_enable(struct perf_event *event)
 		}
 	}
 
-	if (idx >= INTEL_PMC_IDX_FIXED)
-		idx = MAX_PEBS_EVENTS + (idx - INTEL_PMC_IDX_FIXED);
+	if (idx >= INTEL_PMC_IDX_FIXED) {
+		if (x86_pmu.intel_cap.pebs_format < 5)
+			idx = MAX_PEBS_EVENTS_FMT4 + (idx - INTEL_PMC_IDX_FIXED);
+		else
+			idx = MAX_PEBS_EVENTS + (idx - INTEL_PMC_IDX_FIXED);
+	}
 
 	/*
 	 * Use auto-reload if possible to save a MSR write in the PMI.
@@ -1436,9 +1507,11 @@ static u64 get_data_src(struct perf_event *event, u64 aux)
 	bool fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC);
 
 	if (fl & PERF_X86_EVENT_PEBS_LDLAT)
-		val = load_latency_data(aux);
+		val = load_latency_data(event, aux);
 	else if (fl & PERF_X86_EVENT_PEBS_STLAT)
-		val = store_latency_data(aux);
+		val = store_latency_data(event, aux);
+	else if (fl & PERF_X86_EVENT_PEBS_LAT_HYBRID)
+		val = x86_pmu.pebs_latency_data(event, aux);
 	else if (fst && (fl & PERF_X86_EVENT_PEBS_HSW_PREC))
 		val = precise_datala_hsw(event, aux);
 	else if (fst)
@@ -1477,14 +1550,18 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event,
 	/*
 	 * Use latency for weight (only avail with PEBS-LL)
 	 */
-	if (fll && (sample_type & PERF_SAMPLE_WEIGHT_TYPE))
+	if (fll && (sample_type & PERF_SAMPLE_WEIGHT_TYPE)) {
 		data->weight.full = pebs->lat;
+		data->sample_flags |= PERF_SAMPLE_WEIGHT_TYPE;
+	}
 
 	/*
 	 * data.data_src encodes the data source
 	 */
-	if (sample_type & PERF_SAMPLE_DATA_SRC)
+	if (sample_type & PERF_SAMPLE_DATA_SRC) {
 		data->data_src.val = get_data_src(event, pebs->dse);
+		data->sample_flags |= PERF_SAMPLE_DATA_SRC;
+	}
 
 	/*
 	 * We must however always use iregs for the unwinder to stay sane; the
@@ -1492,8 +1569,10 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event,
 	 * previous PMI context or an (I)RET happened between the record and
 	 * PMI.
 	 */
-	if (sample_type & PERF_SAMPLE_CALLCHAIN)
+	if (sample_type & PERF_SAMPLE_CALLCHAIN) {
 		data->callchain = perf_callchain(event, iregs);
+		data->sample_flags |= PERF_SAMPLE_CALLCHAIN;
+	}
 
 	/*
 	 * We use the interrupt regs as a base because the PEBS record does not
@@ -1565,17 +1644,22 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event,
 
 
 	if ((sample_type & PERF_SAMPLE_ADDR_TYPE) &&
-	    x86_pmu.intel_cap.pebs_format >= 1)
+	    x86_pmu.intel_cap.pebs_format >= 1) {
 		data->addr = pebs->dla;
+		data->sample_flags |= PERF_SAMPLE_ADDR;
+	}
 
 	if (x86_pmu.intel_cap.pebs_format >= 2) {
 		/* Only set the TSX weight when no memory weight. */
-		if ((sample_type & PERF_SAMPLE_WEIGHT_TYPE) && !fll)
+		if ((sample_type & PERF_SAMPLE_WEIGHT_TYPE) && !fll) {
 			data->weight.full = intel_get_tsx_weight(pebs->tsx_tuning);
-
-		if (sample_type & PERF_SAMPLE_TRANSACTION)
+			data->sample_flags |= PERF_SAMPLE_WEIGHT_TYPE;
+		}
+		if (sample_type & PERF_SAMPLE_TRANSACTION) {
 			data->txn = intel_get_tsx_transaction(pebs->tsx_tuning,
 							      pebs->ax);
+			data->sample_flags |= PERF_SAMPLE_TRANSACTION;
+		}
 	}
 
 	/*
@@ -1585,11 +1669,15 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event,
 	 * We can only do this for the default trace clock.
 	 */
 	if (x86_pmu.intel_cap.pebs_format >= 3 &&
-		event->attr.use_clockid == 0)
+		event->attr.use_clockid == 0) {
 		data->time = native_sched_clock_from_tsc(pebs->tsc);
+		data->sample_flags |= PERF_SAMPLE_TIME;
+	}
 
-	if (has_branch_stack(event))
+	if (has_branch_stack(event)) {
 		data->br_stack = &cpuc->lbr_stack;
+		data->sample_flags |= PERF_SAMPLE_BRANCH_STACK;
+	}
 }
 
 static void adaptive_pebs_save_regs(struct pt_regs *regs,
@@ -1647,8 +1735,10 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 	perf_sample_data_init(data, 0, event->hw.last_period);
 	data->period = event->hw.last_period;
 
-	if (event->attr.use_clockid == 0)
+	if (event->attr.use_clockid == 0) {
 		data->time = native_sched_clock_from_tsc(basic->tsc);
+		data->sample_flags |= PERF_SAMPLE_TIME;
+	}
 
 	/*
 	 * We must however always use iregs for the unwinder to stay sane; the
@@ -1656,8 +1746,10 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 	 * previous PMI context or an (I)RET happened between the record and
 	 * PMI.
 	 */
-	if (sample_type & PERF_SAMPLE_CALLCHAIN)
+	if (sample_type & PERF_SAMPLE_CALLCHAIN) {
 		data->callchain = perf_callchain(event, iregs);
+		data->sample_flags |= PERF_SAMPLE_CALLCHAIN;
+	}
 
 	*regs = *iregs;
 	/* The ip in basic is EventingIP */
@@ -1708,17 +1800,24 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 				data->weight.var1_dw = (u32)(weight & PEBS_LATENCY_MASK) ?:
 					intel_get_tsx_weight(meminfo->tsx_tuning);
 			}
+			data->sample_flags |= PERF_SAMPLE_WEIGHT_TYPE;
 		}
 
-		if (sample_type & PERF_SAMPLE_DATA_SRC)
+		if (sample_type & PERF_SAMPLE_DATA_SRC) {
 			data->data_src.val = get_data_src(event, meminfo->aux);
+			data->sample_flags |= PERF_SAMPLE_DATA_SRC;
+		}
 
-		if (sample_type & PERF_SAMPLE_ADDR_TYPE)
+		if (sample_type & PERF_SAMPLE_ADDR_TYPE) {
 			data->addr = meminfo->address;
+			data->sample_flags |= PERF_SAMPLE_ADDR;
+		}
 
-		if (sample_type & PERF_SAMPLE_TRANSACTION)
+		if (sample_type & PERF_SAMPLE_TRANSACTION) {
 			data->txn = intel_get_tsx_transaction(meminfo->tsx_tuning,
 							  gprs ? gprs->ax : 0);
+			data->sample_flags |= PERF_SAMPLE_TRANSACTION;
+		}
 	}
 
 	if (format_size & PEBS_DATACFG_XMMS) {
@@ -1737,6 +1836,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 		if (has_branch_stack(event)) {
 			intel_pmu_store_pebs_lbrs(lbr);
 			data->br_stack = &cpuc->lbr_stack;
+			data->sample_flags |= PERF_SAMPLE_BRANCH_STACK;
 		}
 	}
 
@@ -2204,6 +2304,7 @@ void __init intel_ds_init(void)
 			break;
 
 		case 4:
+		case 5:
 			x86_pmu.drain_pebs = intel_pmu_drain_pebs_icl;
 			x86_pmu.pebs_record_size = sizeof(struct pebs_basic);
 			if (x86_pmu.intel_cap.pebs_baseline) {
@@ -2211,6 +2312,7 @@ void __init intel_ds_init(void)
 					PERF_SAMPLE_BRANCH_STACK |
 					PERF_SAMPLE_TIME;
 				x86_pmu.flags |= PMU_FL_PEBS_ALL;
+				x86_pmu.pebs_capable = ~0ULL;
 				pebs_qual = "-baseline";
 				x86_get_pmu(smp_processor_id())->capabilities |= PERF_PMU_CAP_EXTENDED_REGS;
 			} else {