8 files changed, 217 insertions, 156 deletions

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 2e1e26846050..7601196d1d18 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -429,6 +429,16 @@ static struct event_constraint intel_lnc_event_constraints[] = {
 	EVENT_CONSTRAINT_END
 };
 
+static struct extra_reg intel_lnc_extra_regs[] __read_mostly = {
+	INTEL_UEVENT_EXTRA_REG(0x012a, MSR_OFFCORE_RSP_0, 0xfffffffffffull, RSP_0),
+	INTEL_UEVENT_EXTRA_REG(0x012b, MSR_OFFCORE_RSP_1, 0xfffffffffffull, RSP_1),
+	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");
@@ -2816,6 +2826,9 @@ static void intel_pmu_enable_fixed(struct perf_event *event)
 			return;
 
 		idx = INTEL_PMC_IDX_FIXED_SLOTS;
+
+		if (event->attr.config1 & INTEL_TD_CFG_METRIC_CLEAR)
+			bits |= INTEL_FIXED_3_METRICS_CLEAR;
 	}
 
 	intel_set_masks(event, idx);
@@ -4071,7 +4084,12 @@ static int intel_pmu_hw_config(struct perf_event *event)
 	 * is used in a metrics group, it too cannot support sampling.
 	 */
 	if (intel_pmu_has_cap(event, PERF_CAP_METRICS_IDX) && is_topdown_event(event)) {
-		if (event->attr.config1 || event->attr.config2)
+		/* The metrics_clear can only be set for the slots event */
+		if (event->attr.config1 &&
+		    (!is_slots_event(event) || (event->attr.config1 & ~INTEL_TD_CFG_METRIC_CLEAR)))
+			return -EINVAL;
+
+		if (event->attr.config2)
 			return -EINVAL;
 
 		/*
@@ -4680,6 +4698,8 @@ PMU_FORMAT_ATTR(in_tx,  "config:32"	);
 PMU_FORMAT_ATTR(in_tx_cp, "config:33"	);
 PMU_FORMAT_ATTR(eq,	"config:36"	); /* v6 + */
 
+PMU_FORMAT_ATTR(metrics_clear,	"config1:0"); /* PERF_CAPABILITIES.RDPMC_METRICS_CLEAR */
+
 static ssize_t umask2_show(struct device *dev,
 			   struct device_attribute *attr,
 			   char *page)
@@ -4699,6 +4719,7 @@ static struct device_attribute format_attr_umask2  =
 static struct attribute *format_evtsel_ext_attrs[] = {
 	&format_attr_umask2.attr,
 	&format_attr_eq.attr,
+	&format_attr_metrics_clear.attr,
 	NULL
 };
 
@@ -4723,6 +4744,13 @@ evtsel_ext_is_visible(struct kobject *kobj, struct attribute *attr, int i)
 	if (i == 1)
 		return (mask & ARCH_PERFMON_EVENTSEL_EQ) ? attr->mode : 0;
 
+	/* PERF_CAPABILITIES.RDPMC_METRICS_CLEAR */
+	if (i == 2) {
+		union perf_capabilities intel_cap = hybrid(dev_get_drvdata(dev), intel_cap);
+
+		return intel_cap.rdpmc_metrics_clear ? attr->mode : 0;
+	}
+
 	return 0;
 }
 
@@ -5371,42 +5399,32 @@ static __init void intel_clovertown_quirk(void)
 	x86_pmu.pebs_constraints = NULL;
 }
 
-static const struct x86_cpu_desc isolation_ucodes[] = {
-	INTEL_CPU_DESC(INTEL_HASWELL,		 3, 0x0000001f),
-	INTEL_CPU_DESC(INTEL_HASWELL_L,		 1, 0x0000001e),
-	INTEL_CPU_DESC(INTEL_HASWELL_G,		 1, 0x00000015),
-	INTEL_CPU_DESC(INTEL_HASWELL_X,		 2, 0x00000037),
-	INTEL_CPU_DESC(INTEL_HASWELL_X,		 4, 0x0000000a),
-	INTEL_CPU_DESC(INTEL_BROADWELL,		 4, 0x00000023),
-	INTEL_CPU_DESC(INTEL_BROADWELL_G,	 1, 0x00000014),
-	INTEL_CPU_DESC(INTEL_BROADWELL_D,	 2, 0x00000010),
-	INTEL_CPU_DESC(INTEL_BROADWELL_D,	 3, 0x07000009),
-	INTEL_CPU_DESC(INTEL_BROADWELL_D,	 4, 0x0f000009),
-	INTEL_CPU_DESC(INTEL_BROADWELL_D,	 5, 0x0e000002),
-	INTEL_CPU_DESC(INTEL_BROADWELL_X,	 1, 0x0b000014),
-	INTEL_CPU_DESC(INTEL_SKYLAKE_X,		 3, 0x00000021),
-	INTEL_CPU_DESC(INTEL_SKYLAKE_X,		 4, 0x00000000),
-	INTEL_CPU_DESC(INTEL_SKYLAKE_X,		 5, 0x00000000),
-	INTEL_CPU_DESC(INTEL_SKYLAKE_X,		 6, 0x00000000),
-	INTEL_CPU_DESC(INTEL_SKYLAKE_X,		 7, 0x00000000),
-	INTEL_CPU_DESC(INTEL_SKYLAKE_X,		11, 0x00000000),
-	INTEL_CPU_DESC(INTEL_SKYLAKE_L,		 3, 0x0000007c),
-	INTEL_CPU_DESC(INTEL_SKYLAKE,		 3, 0x0000007c),
-	INTEL_CPU_DESC(INTEL_KABYLAKE,		 9, 0x0000004e),
-	INTEL_CPU_DESC(INTEL_KABYLAKE_L,	 9, 0x0000004e),
-	INTEL_CPU_DESC(INTEL_KABYLAKE_L,	10, 0x0000004e),
-	INTEL_CPU_DESC(INTEL_KABYLAKE_L,	11, 0x0000004e),
-	INTEL_CPU_DESC(INTEL_KABYLAKE_L,	12, 0x0000004e),
-	INTEL_CPU_DESC(INTEL_KABYLAKE,		10, 0x0000004e),
-	INTEL_CPU_DESC(INTEL_KABYLAKE,		11, 0x0000004e),
-	INTEL_CPU_DESC(INTEL_KABYLAKE,		12, 0x0000004e),
-	INTEL_CPU_DESC(INTEL_KABYLAKE,		13, 0x0000004e),
+static const struct x86_cpu_id isolation_ucodes[] = {
+	X86_MATCH_VFM_STEPS(INTEL_HASWELL,	 3,  3, 0x0000001f),
+	X86_MATCH_VFM_STEPS(INTEL_HASWELL_L,	 1,  1, 0x0000001e),
+	X86_MATCH_VFM_STEPS(INTEL_HASWELL_G,	 1,  1, 0x00000015),
+	X86_MATCH_VFM_STEPS(INTEL_HASWELL_X,	 2,  2, 0x00000037),
+	X86_MATCH_VFM_STEPS(INTEL_HASWELL_X,	 4,  4, 0x0000000a),
+	X86_MATCH_VFM_STEPS(INTEL_BROADWELL,	 4,  4, 0x00000023),
+	X86_MATCH_VFM_STEPS(INTEL_BROADWELL_G,	 1,  1, 0x00000014),
+	X86_MATCH_VFM_STEPS(INTEL_BROADWELL_D,	 2,  2, 0x00000010),
+	X86_MATCH_VFM_STEPS(INTEL_BROADWELL_D,	 3,  3, 0x07000009),
+	X86_MATCH_VFM_STEPS(INTEL_BROADWELL_D,	 4,  4, 0x0f000009),
+	X86_MATCH_VFM_STEPS(INTEL_BROADWELL_D,	 5,  5, 0x0e000002),
+	X86_MATCH_VFM_STEPS(INTEL_BROADWELL_X,	 1,  1, 0x0b000014),
+	X86_MATCH_VFM_STEPS(INTEL_SKYLAKE_X,	 3,  3, 0x00000021),
+	X86_MATCH_VFM_STEPS(INTEL_SKYLAKE_X,	 4,  7, 0x00000000),
+	X86_MATCH_VFM_STEPS(INTEL_SKYLAKE_X,	11, 11, 0x00000000),
+	X86_MATCH_VFM_STEPS(INTEL_SKYLAKE_L,	 3,  3, 0x0000007c),
+	X86_MATCH_VFM_STEPS(INTEL_SKYLAKE,	 3,  3, 0x0000007c),
+	X86_MATCH_VFM_STEPS(INTEL_KABYLAKE,	 9, 13, 0x0000004e),
+	X86_MATCH_VFM_STEPS(INTEL_KABYLAKE_L,	 9, 12, 0x0000004e),
 	{}
 };
 
 static void intel_check_pebs_isolation(void)
 {
-	x86_pmu.pebs_no_isolation = !x86_cpu_has_min_microcode_rev(isolation_ucodes);
+	x86_pmu.pebs_no_isolation = !x86_match_min_microcode_rev(isolation_ucodes);
 }
 
 static __init void intel_pebs_isolation_quirk(void)
@@ -5416,16 +5434,16 @@ static __init void intel_pebs_isolation_quirk(void)
 	intel_check_pebs_isolation();
 }
 
-static const struct x86_cpu_desc pebs_ucodes[] = {
-	INTEL_CPU_DESC(INTEL_SANDYBRIDGE,	7, 0x00000028),
-	INTEL_CPU_DESC(INTEL_SANDYBRIDGE_X,	6, 0x00000618),
-	INTEL_CPU_DESC(INTEL_SANDYBRIDGE_X,	7, 0x0000070c),
+static const struct x86_cpu_id pebs_ucodes[] = {
+	X86_MATCH_VFM_STEPS(INTEL_SANDYBRIDGE,	7, 7, 0x00000028),
+	X86_MATCH_VFM_STEPS(INTEL_SANDYBRIDGE_X,	6, 6, 0x00000618),
+	X86_MATCH_VFM_STEPS(INTEL_SANDYBRIDGE_X,	7, 7, 0x0000070c),
 	{}
 };
 
 static bool intel_snb_pebs_broken(void)
 {
-	return !x86_cpu_has_min_microcode_rev(pebs_ucodes);
+	return !x86_match_min_microcode_rev(pebs_ucodes);
 }
 
 static void intel_snb_check_microcode(void)
@@ -6422,7 +6440,7 @@ static __always_inline void intel_pmu_init_lnc(struct pmu *pmu)
 	intel_pmu_init_glc(pmu);
 	hybrid(pmu, event_constraints) = intel_lnc_event_constraints;
 	hybrid(pmu, pebs_constraints) = intel_lnc_pebs_event_constraints;
-	hybrid(pmu, extra_regs) = intel_rwc_extra_regs;
+	hybrid(pmu, extra_regs) = intel_lnc_extra_regs;
 }
 
 static __always_inline void intel_pmu_init_skt(struct pmu *pmu)
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 1a4b326ca2ce..ba74e1198328 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1789,8 +1789,7 @@ 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)
-		perf_sample_save_callchain(data, event, iregs);
+	perf_sample_save_callchain(data, event, iregs);
 
 	/*
 	 * We use the interrupt regs as a base because the PEBS record does not
@@ -1889,8 +1888,7 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event,
 	if (x86_pmu.intel_cap.pebs_format >= 3)
 		setup_pebs_time(event, data, pebs->tsc);
 
-	if (has_branch_stack(event))
-		perf_sample_save_brstack(data, event, &cpuc->lbr_stack, NULL);
+	perf_sample_save_brstack(data, event, &cpuc->lbr_stack, NULL);
 }
 
 static void adaptive_pebs_save_regs(struct pt_regs *regs,
@@ -1917,8 +1915,6 @@ static void adaptive_pebs_save_regs(struct pt_regs *regs,
 }
 
 #define PEBS_LATENCY_MASK			0xffff
-#define PEBS_CACHE_LATENCY_OFFSET		32
-#define PEBS_RETIRE_LATENCY_OFFSET		32
 
 /*
  * With adaptive PEBS the layout depends on what fields are configured.
@@ -1932,8 +1928,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct pebs_basic *basic = __pebs;
 	void *next_record = basic + 1;
-	u64 sample_type;
-	u64 format_size;
+	u64 sample_type, format_group;
 	struct pebs_meminfo *meminfo = NULL;
 	struct pebs_gprs *gprs = NULL;
 	struct x86_perf_regs *perf_regs;
@@ -1945,7 +1940,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 	perf_regs->xmm_regs = NULL;
 
 	sample_type = event->attr.sample_type;
-	format_size = basic->format_size;
+	format_group = basic->format_group;
 	perf_sample_data_init(data, 0, event->hw.last_period);
 	data->period = event->hw.last_period;
 
@@ -1957,8 +1952,7 @@ 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)
-		perf_sample_save_callchain(data, event, iregs);
+	perf_sample_save_callchain(data, event, iregs);
 
 	*regs = *iregs;
 	/* The ip in basic is EventingIP */
@@ -1967,7 +1961,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 
 	if (sample_type & PERF_SAMPLE_WEIGHT_STRUCT) {
 		if (x86_pmu.flags & PMU_FL_RETIRE_LATENCY)
-			data->weight.var3_w = format_size >> PEBS_RETIRE_LATENCY_OFFSET & PEBS_LATENCY_MASK;
+			data->weight.var3_w = basic->retire_latency;
 		else
 			data->weight.var3_w = 0;
 	}
@@ -1977,12 +1971,12 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 	 * But PERF_SAMPLE_TRANSACTION needs gprs->ax.
 	 * Save the pointer here but process later.
 	 */
-	if (format_size & PEBS_DATACFG_MEMINFO) {
+	if (format_group & PEBS_DATACFG_MEMINFO) {
 		meminfo = next_record;
 		next_record = meminfo + 1;
 	}
 
-	if (format_size & PEBS_DATACFG_GP) {
+	if (format_group & PEBS_DATACFG_GP) {
 		gprs = next_record;
 		next_record = gprs + 1;
 
@@ -1995,14 +1989,13 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 			adaptive_pebs_save_regs(regs, gprs);
 	}
 
-	if (format_size & PEBS_DATACFG_MEMINFO) {
+	if (format_group & PEBS_DATACFG_MEMINFO) {
 		if (sample_type & PERF_SAMPLE_WEIGHT_TYPE) {
-			u64 weight = meminfo->latency;
+			u64 latency = x86_pmu.flags & PMU_FL_INSTR_LATENCY ?
+					meminfo->cache_latency : meminfo->mem_latency;
 
-			if (x86_pmu.flags & PMU_FL_INSTR_LATENCY) {
-				data->weight.var2_w = weight & PEBS_LATENCY_MASK;
-				weight >>= PEBS_CACHE_LATENCY_OFFSET;
-			}
+			if (x86_pmu.flags & PMU_FL_INSTR_LATENCY)
+				data->weight.var2_w = meminfo->instr_latency;
 
 			/*
 			 * Although meminfo::latency is defined as a u64,
@@ -2010,12 +2003,13 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 			 * in practice on Ice Lake and earlier platforms.
 			 */
 			if (sample_type & PERF_SAMPLE_WEIGHT) {
-				data->weight.full = weight ?:
+				data->weight.full = latency ?:
 					intel_get_tsx_weight(meminfo->tsx_tuning);
 			} else {
-				data->weight.var1_dw = (u32)(weight & PEBS_LATENCY_MASK) ?:
+				data->weight.var1_dw = (u32)latency ?:
 					intel_get_tsx_weight(meminfo->tsx_tuning);
 			}
+
 			data->sample_flags |= PERF_SAMPLE_WEIGHT_TYPE;
 		}
 
@@ -2036,16 +2030,16 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 		}
 	}
 
-	if (format_size & PEBS_DATACFG_XMMS) {
+	if (format_group & PEBS_DATACFG_XMMS) {
 		struct pebs_xmm *xmm = next_record;
 
 		next_record = xmm + 1;
 		perf_regs->xmm_regs = xmm->xmm;
 	}
 
-	if (format_size & PEBS_DATACFG_LBRS) {
+	if (format_group & PEBS_DATACFG_LBRS) {
 		struct lbr_entry *lbr = next_record;
-		int num_lbr = ((format_size >> PEBS_DATACFG_LBR_SHIFT)
+		int num_lbr = ((format_group >> PEBS_DATACFG_LBR_SHIFT)
 					& 0xff) + 1;
 		next_record = next_record + num_lbr * sizeof(struct lbr_entry);
 
@@ -2055,11 +2049,11 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 		}
 	}
 
-	WARN_ONCE(next_record != __pebs + (format_size >> 48),
-			"PEBS record size %llu, expected %llu, config %llx\n",
-			format_size >> 48,
+	WARN_ONCE(next_record != __pebs + basic->format_size,
+			"PEBS record size %u, expected %llu, config %llx\n",
+			basic->format_size,
 			(u64)(next_record - __pebs),
-			basic->format_size);
+			format_group);
 }
 
 static inline void *
@@ -2170,46 +2164,33 @@ intel_pmu_save_and_restart_reload(struct perf_event *event, int count)
 	return 0;
 }
 
+typedef void (*setup_fn)(struct perf_event *, struct pt_regs *, void *,
+			 struct perf_sample_data *, struct pt_regs *);
+
+static struct pt_regs dummy_iregs;
+
 static __always_inline void
 __intel_pmu_pebs_event(struct perf_event *event,
 		       struct pt_regs *iregs,
+		       struct pt_regs *regs,
 		       struct perf_sample_data *data,
-		       void *base, void *top,
-		       int bit, int count,
-		       void (*setup_sample)(struct perf_event *,
-					    struct pt_regs *,
-					    void *,
-					    struct perf_sample_data *,
-					    struct pt_regs *))
+		       void *at,
+		       setup_fn setup_sample)
 {
-	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
-	struct hw_perf_event *hwc = &event->hw;
-	struct x86_perf_regs perf_regs;
-	struct pt_regs *regs = &perf_regs.regs;
-	void *at = get_next_pebs_record_by_bit(base, top, bit);
-	static struct pt_regs dummy_iregs;
-
-	if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
-		/*
-		 * Now, auto-reload is only enabled in fixed period mode.
-		 * The reload value is always hwc->sample_period.
-		 * May need to change it, if auto-reload is enabled in
-		 * freq mode later.
-		 */
-		intel_pmu_save_and_restart_reload(event, count);
-	} else if (!intel_pmu_save_and_restart(event))
-		return;
-
-	if (!iregs)
-		iregs = &dummy_iregs;
+	setup_sample(event, iregs, at, data, regs);
+	perf_event_output(event, data, regs);
+}
 
-	while (count > 1) {
-		setup_sample(event, iregs, at, data, regs);
-		perf_event_output(event, data, regs);
-		at += cpuc->pebs_record_size;
-		at = get_next_pebs_record_by_bit(at, top, bit);
-		count--;
-	}
+static __always_inline void
+__intel_pmu_pebs_last_event(struct perf_event *event,
+			    struct pt_regs *iregs,
+			    struct pt_regs *regs,
+			    struct perf_sample_data *data,
+			    void *at,
+			    int count,
+			    setup_fn setup_sample)
+{
+	struct hw_perf_event *hwc = &event->hw;
 
 	setup_sample(event, iregs, at, data, regs);
 	if (iregs == &dummy_iregs) {
@@ -2228,6 +2209,44 @@ __intel_pmu_pebs_event(struct perf_event *event,
 		if (perf_event_overflow(event, data, regs))
 			x86_pmu_stop(event, 0);
 	}
+
+	if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
+		/*
+		 * Now, auto-reload is only enabled in fixed period mode.
+		 * The reload value is always hwc->sample_period.
+		 * May need to change it, if auto-reload is enabled in
+		 * freq mode later.
+		 */
+		intel_pmu_save_and_restart_reload(event, count);
+	} else
+		intel_pmu_save_and_restart(event);
+}
+
+static __always_inline void
+__intel_pmu_pebs_events(struct perf_event *event,
+			struct pt_regs *iregs,
+			struct perf_sample_data *data,
+			void *base, void *top,
+			int bit, int count,
+			setup_fn setup_sample)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	struct x86_perf_regs perf_regs;
+	struct pt_regs *regs = &perf_regs.regs;
+	void *at = get_next_pebs_record_by_bit(base, top, bit);
+	int cnt = count;
+
+	if (!iregs)
+		iregs = &dummy_iregs;
+
+	while (cnt > 1) {
+		__intel_pmu_pebs_event(event, iregs, regs, data, at, setup_sample);
+		at += cpuc->pebs_record_size;
+		at = get_next_pebs_record_by_bit(at, top, bit);
+		cnt--;
+	}
+
+	__intel_pmu_pebs_last_event(event, iregs, regs, data, at, count, setup_sample);
 }
 
 static void intel_pmu_drain_pebs_core(struct pt_regs *iregs, struct perf_sample_data *data)
@@ -2264,8 +2283,8 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs, struct perf_sample_
 		return;
 	}
 
-	__intel_pmu_pebs_event(event, iregs, data, at, top, 0, n,
-			       setup_pebs_fixed_sample_data);
+	__intel_pmu_pebs_events(event, iregs, data, at, top, 0, n,
+				setup_pebs_fixed_sample_data);
 }
 
 static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, int size)
@@ -2396,9 +2415,9 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d
 		}
 
 		if (counts[bit]) {
-			__intel_pmu_pebs_event(event, iregs, data, base,
-					       top, bit, counts[bit],
-					       setup_pebs_fixed_sample_data);
+			__intel_pmu_pebs_events(event, iregs, data, base,
+						top, bit, counts[bit],
+						setup_pebs_fixed_sample_data);
 		}
 	}
 }
@@ -2406,8 +2425,12 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d
 static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_data *data)
 {
 	short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
+	void *last[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS];
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct debug_store *ds = cpuc->ds;
+	struct x86_perf_regs perf_regs;
+	struct pt_regs *regs = &perf_regs.regs;
+	struct pebs_basic *basic;
 	struct perf_event *event;
 	void *base, *at, *top;
 	int bit;
@@ -2429,30 +2452,41 @@ static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_d
 		return;
 	}
 
-	for (at = base; at < top; at += cpuc->pebs_record_size) {
+	if (!iregs)
+		iregs = &dummy_iregs;
+
+	/* Process all but the last event for each counter. */
+	for (at = base; at < top; at += basic->format_size) {
 		u64 pebs_status;
 
-		pebs_status = get_pebs_status(at) & cpuc->pebs_enabled;
-		pebs_status &= mask;
+		basic = at;
+		if (basic->format_size != cpuc->pebs_record_size)
+			continue;
 
-		for_each_set_bit(bit, (unsigned long *)&pebs_status, X86_PMC_IDX_MAX)
-			counts[bit]++;
+		pebs_status = basic->applicable_counters & cpuc->pebs_enabled & mask;
+		for_each_set_bit(bit, (unsigned long *)&pebs_status, X86_PMC_IDX_MAX) {
+			event = cpuc->events[bit];
+
+			if (WARN_ON_ONCE(!event) ||
+			    WARN_ON_ONCE(!event->attr.precise_ip))
+				continue;
+
+			if (counts[bit]++) {
+				__intel_pmu_pebs_event(event, iregs, regs, data, last[bit],
+						       setup_pebs_adaptive_sample_data);
+			}
+			last[bit] = at;
+		}
 	}
 
 	for_each_set_bit(bit, (unsigned long *)&mask, X86_PMC_IDX_MAX) {
-		if (counts[bit] == 0)
+		if (!counts[bit])
 			continue;
 
 		event = cpuc->events[bit];
-		if (WARN_ON_ONCE(!event))
-			continue;
-
-		if (WARN_ON_ONCE(!event->attr.precise_ip))
-			continue;
 
-		__intel_pmu_pebs_event(event, iregs, data, base,
-				       top, bit, counts[bit],
-				       setup_pebs_adaptive_sample_data);
+		__intel_pmu_pebs_last_event(event, iregs, regs, data, last[bit],
+					    counts[bit], setup_pebs_adaptive_sample_data);
 	}
 }
 
@@ -2517,6 +2551,7 @@ void __init intel_ds_init(void)
 			x86_pmu.large_pebs_flags |= PERF_SAMPLE_TIME;
 			break;
 
+		case 6:
 		case 5:
 			x86_pmu.pebs_ept = 1;
 			fallthrough;
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index 4b0373bc8ab4..fa37565f6418 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -18,6 +18,7 @@
 #include <linux/slab.h>
 #include <linux/device.h>
 
+#include <asm/cpuid.h>
 #include <asm/perf_event.h>
 #include <asm/insn.h>
 #include <asm/io.h>
@@ -201,10 +202,10 @@ static int __init pt_pmu_hw_init(void)
 	 * otherwise, zero for numerator stands for "not enumerated"
 	 * as per SDM
 	 */
-	if (boot_cpu_data.cpuid_level >= CPUID_TSC_LEAF) {
+	if (boot_cpu_data.cpuid_level >= CPUID_LEAF_TSC) {
 		u32 eax, ebx, ecx, edx;
 
-		cpuid(CPUID_TSC_LEAF, &eax, &ebx, &ecx, &edx);
+		cpuid(CPUID_LEAF_TSC, &eax, &ebx, &ecx, &edx);
 
 		pt_pmu.tsc_art_num = ebx;
 		pt_pmu.tsc_art_den = eax;
diff --git a/arch/x86/events/intel/pt.h b/arch/x86/events/intel/pt.h
index 7ee94fc6d7cb..2ac36250b656 100644
--- a/arch/x86/events/intel/pt.h
+++ b/arch/x86/events/intel/pt.h
@@ -37,9 +37,6 @@ struct topa_entry {
 	u64	rsvd4	: 12;
 };
 
-/* TSC to Core Crystal Clock Ratio */
-#define CPUID_TSC_LEAF		0x15
-
 struct pt_pmu {
 	struct pmu		pmu;
 	u32			caps[PT_CPUID_REGS_NUM * PT_CPUID_LEAVES];
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index d98fac567684..60b3078b7502 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -745,7 +745,7 @@ static int uncore_pmu_event_init(struct perf_event *event)
 
 	pmu = uncore_event_to_pmu(event);
 	/* no device found for this pmu */
-	if (pmu->func_id < 0)
+	if (!pmu->registered)
 		return -ENOENT;
 
 	/* Sampling not supported yet */
@@ -992,7 +992,7 @@ static void uncore_types_exit(struct intel_uncore_type **types)
 		uncore_type_exit(*types);
 }
 
-static int __init uncore_type_init(struct intel_uncore_type *type, bool setid)
+static int __init uncore_type_init(struct intel_uncore_type *type)
 {
 	struct intel_uncore_pmu *pmus;
 	size_t size;
@@ -1005,7 +1005,6 @@ static int __init uncore_type_init(struct intel_uncore_type *type, bool setid)
 	size = uncore_max_dies() * sizeof(struct intel_uncore_box *);
 
 	for (i = 0; i < type->num_boxes; i++) {
-		pmus[i].func_id	= setid ? i : -1;
 		pmus[i].pmu_idx	= i;
 		pmus[i].type	= type;
 		pmus[i].boxes	= kzalloc(size, GFP_KERNEL);
@@ -1055,12 +1054,12 @@ err:
 }
 
 static int __init
-uncore_types_init(struct intel_uncore_type **types, bool setid)
+uncore_types_init(struct intel_uncore_type **types)
 {
 	int ret;
 
 	for (; *types; types++) {
-		ret = uncore_type_init(*types, setid);
+		ret = uncore_type_init(*types);
 		if (ret)
 			return ret;
 	}
@@ -1160,11 +1159,6 @@ static int uncore_pci_pmu_register(struct pci_dev *pdev,
 	if (!box)
 		return -ENOMEM;
 
-	if (pmu->func_id < 0)
-		pmu->func_id = pdev->devfn;
-	else
-		WARN_ON_ONCE(pmu->func_id != pdev->devfn);
-
 	atomic_inc(&box->refcnt);
 	box->dieid = die;
 	box->pci_dev = pdev;
@@ -1410,7 +1404,7 @@ static int __init uncore_pci_init(void)
 		goto err;
 	}
 
-	ret = uncore_types_init(uncore_pci_uncores, false);
+	ret = uncore_types_init(uncore_pci_uncores);
 	if (ret)
 		goto errtype;
 
@@ -1678,7 +1672,7 @@ static int __init uncore_cpu_init(void)
 {
 	int ret;
 
-	ret = uncore_types_init(uncore_msr_uncores, true);
+	ret = uncore_types_init(uncore_msr_uncores);
 	if (ret)
 		goto err;
 
@@ -1697,7 +1691,7 @@ static int __init uncore_mmio_init(void)
 	struct intel_uncore_type **types = uncore_mmio_uncores;
 	int ret;
 
-	ret = uncore_types_init(types, true);
+	ret = uncore_types_init(types);
 	if (ret)
 		goto err;
 
@@ -1910,6 +1904,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = {
 	X86_MATCH_VFM(INTEL_ATOM_GRACEMONT,	&adl_uncore_init),
 	X86_MATCH_VFM(INTEL_ATOM_CRESTMONT_X,	&gnr_uncore_init),
 	X86_MATCH_VFM(INTEL_ATOM_CRESTMONT,	&gnr_uncore_init),
+	X86_MATCH_VFM(INTEL_ATOM_DARKMONT_X,	&gnr_uncore_init),
 	{},
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_uncore_match);
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index 79ff32e13dcc..3dcb88c0ecfa 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -125,7 +125,6 @@ struct intel_uncore_pmu {
 	struct pmu			pmu;
 	char				name[UNCORE_PMU_NAME_LEN];
 	int				pmu_idx;
-	int				func_id;
 	bool				registered;
 	atomic_t			activeboxes;
 	cpumask_t			cpu_mask;
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index 3934e1e4e3b1..edb7fd50efe0 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -910,7 +910,7 @@ static int snb_uncore_imc_event_init(struct perf_event *event)
 
 	pmu = uncore_event_to_pmu(event);
 	/* no device found for this pmu */
-	if (pmu->func_id < 0)
+	if (!pmu->registered)
 		return -ENOENT;
 
 	/* Sampling not supported yet */
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index ca98744343b8..60973c209c0e 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -6684,17 +6684,8 @@ void spr_uncore_mmio_init(void)
 /* GNR uncore support */
 
 #define UNCORE_GNR_NUM_UNCORE_TYPES	23
-#define UNCORE_GNR_TYPE_15		15
-#define UNCORE_GNR_B2UPI		18
-#define UNCORE_GNR_TYPE_21		21
-#define UNCORE_GNR_TYPE_22		22
 
 int gnr_uncore_units_ignore[] = {
-	UNCORE_SPR_UPI,
-	UNCORE_GNR_TYPE_15,
-	UNCORE_GNR_B2UPI,
-	UNCORE_GNR_TYPE_21,
-	UNCORE_GNR_TYPE_22,
 	UNCORE_IGNORE_END
 };
 
@@ -6703,6 +6694,31 @@ static struct intel_uncore_type gnr_uncore_ubox = {
 	.attr_update		= uncore_alias_groups,
 };
 
+static struct intel_uncore_type gnr_uncore_pciex8 = {
+	SPR_UNCORE_PCI_COMMON_FORMAT(),
+	.name			= "pciex8",
+};
+
+static struct intel_uncore_type gnr_uncore_pciex16 = {
+	SPR_UNCORE_PCI_COMMON_FORMAT(),
+	.name			= "pciex16",
+};
+
+static struct intel_uncore_type gnr_uncore_upi = {
+	SPR_UNCORE_PCI_COMMON_FORMAT(),
+	.name			= "upi",
+};
+
+static struct intel_uncore_type gnr_uncore_b2upi = {
+	SPR_UNCORE_PCI_COMMON_FORMAT(),
+	.name			= "b2upi",
+};
+
+static struct intel_uncore_type gnr_uncore_b2hot = {
+	.name			= "b2hot",
+	.attr_update		= uncore_alias_groups,
+};
+
 static struct intel_uncore_type gnr_uncore_b2cmi = {
 	SPR_UNCORE_PCI_COMMON_FORMAT(),
 	.name			= "b2cmi",
@@ -6727,21 +6743,21 @@ static struct intel_uncore_type *gnr_uncores[UNCORE_GNR_NUM_UNCORE_TYPES] = {
 	&gnr_uncore_ubox,
 	&spr_uncore_imc,
 	NULL,
+	&gnr_uncore_upi,
 	NULL,
 	NULL,
 	NULL,
+	&spr_uncore_cxlcm,
+	&spr_uncore_cxldp,
 	NULL,
-	NULL,
-	NULL,
-	NULL,
-	NULL,
+	&gnr_uncore_b2hot,
 	&gnr_uncore_b2cmi,
 	&gnr_uncore_b2cxl,
-	NULL,
+	&gnr_uncore_b2upi,
 	NULL,
 	&gnr_uncore_mdf_sbo,
-	NULL,
-	NULL,
+	&gnr_uncore_pciex16,
+	&gnr_uncore_pciex8,
 };
 
 static struct freerunning_counters gnr_iio_freerunning[] = {