Merge tag 'perf-core-2023-02-20' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf updates from Ingo Molnar:

 - Optimize perf_sample_data layout

 - Prepare sample data handling for BPF integration

 - Update the x86 PMU driver for Intel Meteor Lake

 - Restructure the x86 uncore code to fix a SPR (Sapphire Rapids)
   discovery breakage

 - Fix the x86 Zhaoxin PMU driver

 - Cleanups

* tag 'perf-core-2023-02-20' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (27 commits)
  perf/x86/intel/uncore: Add Meteor Lake support
  x86/perf/zhaoxin: Add stepping check for ZXC
  perf/x86/intel/ds: Fix the conversion from TSC to perf time
  perf/x86/uncore: Don't WARN_ON_ONCE() for a broken discovery table
  perf/x86/uncore: Add a quirk for UPI on SPR
  perf/x86/uncore: Ignore broken units in discovery table
  perf/x86/uncore: Fix potential NULL pointer in uncore_get_alias_name
  perf/x86/uncore: Factor out uncore_device_to_die()
  perf/core: Call perf_prepare_sample() before running BPF
  perf/core: Introduce perf_prepare_header()
  perf/core: Do not pass header for sample ID init
  perf/core: Set data->sample_flags in perf_prepare_sample()
  perf/core: Add perf_sample_save_brstack() helper
  perf/core: Add perf_sample_save_raw_data() helper
  perf/core: Add perf_sample_save_callchain() helper
  perf/core: Save the dynamic parts of sample data size
  x86/kprobes: Use switch-case for 0xFF opcodes in prepare_emulation
  perf/core: Change the layout of perf_sample_data
  perf/x86/msr: Add Meteor Lake support
  perf/x86/cstate: Add Meteor Lake support
  ...

13 files changed, 687 insertions, 134 deletions

diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index 4386b10682ce..8c45b198b62f 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -928,10 +928,8 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs)
 		if (!x86_perf_event_set_period(event))
 			continue;
 
-		if (has_branch_stack(event)) {
-			data.br_stack = &cpuc->lbr_stack;
-			data.sample_flags |= PERF_SAMPLE_BRANCH_STACK;
-		}
+		if (has_branch_stack(event))
+			perf_sample_save_brstack(&data, event, &cpuc->lbr_stack);
 
 		if (perf_event_overflow(event, &data, regs))
 			x86_pmu_stop(event, 0);
diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index da3f5ebac4e1..64582954b5f6 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -1110,8 +1110,7 @@ fail:
 				.data = ibs_data.data,
 			},
 		};
-		data.raw = &raw;
-		data.sample_flags |= PERF_SAMPLE_RAW;
+		perf_sample_save_raw_data(&data, &raw);
 	}
 
 	if (perf_ibs == &perf_ibs_op)
@@ -1122,10 +1121,8 @@ fail:
 	 * recorded as part of interrupt regs. Thus we need to use rip from
 	 * interrupt regs while unwinding call stack.
 	 */
-	if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) {
-		data.callchain = perf_callchain(event, iregs);
-		data.sample_flags |= PERF_SAMPLE_CALLCHAIN;
-	}
+	if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)
+		perf_sample_save_callchain(&data, event, iregs);
 
 	throttle = perf_event_overflow(event, &data, &regs);
 out:
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index bafdc2be479a..9fce2d1247a7 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2119,6 +2119,16 @@ static struct extra_reg intel_grt_extra_regs[] __read_mostly = {
 	EVENT_EXTRA_END
 };
 
+static struct extra_reg intel_cmt_extra_regs[] __read_mostly = {
+	/* must define OFFCORE_RSP_X first, see intel_fixup_er() */
+	INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x800ff3ffffffffffull, RSP_0),
+	INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0xff3ffffffffffull, RSP_1),
+	INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x5d0),
+	INTEL_UEVENT_EXTRA_REG(0x0127, MSR_SNOOP_RSP_0, 0xffffffffffffffffull, SNOOP_0),
+	INTEL_UEVENT_EXTRA_REG(0x0227, MSR_SNOOP_RSP_1, 0xffffffffffffffffull, SNOOP_1),
+	EVENT_EXTRA_END
+};
+
 #define KNL_OT_L2_HITE		BIT_ULL(19) /* Other Tile L2 Hit */
 #define KNL_OT_L2_HITF		BIT_ULL(20) /* Other Tile L2 Hit */
 #define KNL_MCDRAM_LOCAL	BIT_ULL(21)
@@ -3026,10 +3036,8 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
 
 		perf_sample_data_init(&data, 0, event->hw.last_period);
 
-		if (has_branch_stack(event)) {
-			data.br_stack = &cpuc->lbr_stack;
-			data.sample_flags |= PERF_SAMPLE_BRANCH_STACK;
-		}
+		if (has_branch_stack(event))
+			perf_sample_save_brstack(&data, event, &cpuc->lbr_stack);
 
 		if (perf_event_overflow(event, &data, regs))
 			x86_pmu_stop(event, 0);
@@ -4182,6 +4190,12 @@ static int hsw_hw_config(struct perf_event *event)
 static struct event_constraint counter0_constraint =
 			INTEL_ALL_EVENT_CONSTRAINT(0, 0x1);
 
+static struct event_constraint counter1_constraint =
+			INTEL_ALL_EVENT_CONSTRAINT(0, 0x2);
+
+static struct event_constraint counter0_1_constraint =
+			INTEL_ALL_EVENT_CONSTRAINT(0, 0x3);
+
 static struct event_constraint counter2_constraint =
 			EVENT_CONSTRAINT(0, 0x4, 0);
 
@@ -4191,6 +4205,12 @@ static struct event_constraint fixed0_constraint =
 static struct event_constraint fixed0_counter0_constraint =
 			INTEL_ALL_EVENT_CONSTRAINT(0, 0x100000001ULL);
 
+static struct event_constraint fixed0_counter0_1_constraint =
+			INTEL_ALL_EVENT_CONSTRAINT(0, 0x100000003ULL);
+
+static struct event_constraint counters_1_7_constraint =
+			INTEL_ALL_EVENT_CONSTRAINT(0, 0xfeULL);
+
 static struct event_constraint *
 hsw_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 			  struct perf_event *event)
@@ -4322,6 +4342,78 @@ adl_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 	return &emptyconstraint;
 }
 
+static struct event_constraint *
+cmt_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
+			  struct perf_event *event)
+{
+	struct event_constraint *c;
+
+	c = intel_get_event_constraints(cpuc, idx, event);
+
+	/*
+	 * The :ppp indicates the Precise Distribution (PDist) facility, which
+	 * is only supported on the GP counter 0 & 1 and Fixed counter 0.
+	 * If a :ppp event which is not available on the above eligible counters,
+	 * error out.
+	 */
+	if (event->attr.precise_ip == 3) {
+		/* Force instruction:ppp on PMC0, 1 and Fixed counter 0 */
+		if (constraint_match(&fixed0_constraint, event->hw.config))
+			return &fixed0_counter0_1_constraint;
+
+		switch (c->idxmsk64 & 0x3ull) {
+		case 0x1:
+			return &counter0_constraint;
+		case 0x2:
+			return &counter1_constraint;
+		case 0x3:
+			return &counter0_1_constraint;
+		}
+		return &emptyconstraint;
+	}
+
+	return c;
+}
+
+static struct event_constraint *
+rwc_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
+			  struct perf_event *event)
+{
+	struct event_constraint *c;
+
+	c = spr_get_event_constraints(cpuc, idx, event);
+
+	/* The Retire Latency is not supported by the fixed counter 0. */
+	if (event->attr.precise_ip &&
+	    (event->attr.sample_type & PERF_SAMPLE_WEIGHT_TYPE) &&
+	    constraint_match(&fixed0_constraint, event->hw.config)) {
+		/*
+		 * The Instruction PDIR is only available
+		 * on the fixed counter 0. Error out for this case.
+		 */
+		if (event->attr.precise_ip == 3)
+			return &emptyconstraint;
+		return &counters_1_7_constraint;
+	}
+
+	return c;
+}
+
+static struct event_constraint *
+mtl_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->cpu_type == hybrid_big)
+		return rwc_get_event_constraints(cpuc, idx, event);
+	if (pmu->cpu_type == hybrid_small)
+		return cmt_get_event_constraints(cpuc, idx, event);
+
+	WARN_ON(1);
+	return &emptyconstraint;
+}
+
 static int adl_hw_config(struct perf_event *event)
 {
 	struct x86_hybrid_pmu *pmu = hybrid_pmu(event->pmu);
@@ -4494,6 +4586,25 @@ static void flip_smm_bit(void *data)
 	}
 }
 
+static void intel_pmu_check_num_counters(int *num_counters,
+					 int *num_counters_fixed,
+					 u64 *intel_ctrl, u64 fixed_mask);
+
+static void update_pmu_cap(struct x86_hybrid_pmu *pmu)
+{
+	unsigned int sub_bitmaps = cpuid_eax(ARCH_PERFMON_EXT_LEAF);
+	unsigned int eax, ebx, ecx, edx;
+
+	if (sub_bitmaps & ARCH_PERFMON_NUM_COUNTER_LEAF_BIT) {
+		cpuid_count(ARCH_PERFMON_EXT_LEAF, ARCH_PERFMON_NUM_COUNTER_LEAF,
+			    &eax, &ebx, &ecx, &edx);
+		pmu->num_counters = fls(eax);
+		pmu->num_counters_fixed = fls(ebx);
+		intel_pmu_check_num_counters(&pmu->num_counters, &pmu->num_counters_fixed,
+					     &pmu->intel_ctrl, ebx);
+	}
+}
+
 static bool init_hybrid_pmu(int cpu)
 {
 	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
@@ -4519,6 +4630,9 @@ static bool init_hybrid_pmu(int cpu)
 	if (!cpumask_empty(&pmu->supported_cpus))
 		goto end;
 
+	if (this_cpu_has(X86_FEATURE_ARCH_PERFMON_EXT))
+		update_pmu_cap(pmu);
+
 	if (!check_hw_exists(&pmu->pmu, pmu->num_counters, pmu->num_counters_fixed))
 		return false;
 
@@ -5463,6 +5577,12 @@ static struct attribute *adl_hybrid_mem_attrs[] = {
 	NULL,
 };
 
+static struct attribute *mtl_hybrid_mem_attrs[] = {
+	EVENT_PTR(mem_ld_adl),
+	EVENT_PTR(mem_st_adl),
+	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);
@@ -5490,20 +5610,40 @@ FORMAT_ATTR_HYBRID(offcore_rsp, hybrid_big_small);
 FORMAT_ATTR_HYBRID(ldlat,       hybrid_big_small);
 FORMAT_ATTR_HYBRID(frontend,    hybrid_big);
 
+#define ADL_HYBRID_RTM_FORMAT_ATTR	\
+	FORMAT_HYBRID_PTR(in_tx),	\
+	FORMAT_HYBRID_PTR(in_tx_cp)
+
+#define ADL_HYBRID_FORMAT_ATTR		\
+	FORMAT_HYBRID_PTR(offcore_rsp),	\
+	FORMAT_HYBRID_PTR(ldlat),	\
+	FORMAT_HYBRID_PTR(frontend)
+
 static struct attribute *adl_hybrid_extra_attr_rtm[] = {
-	FORMAT_HYBRID_PTR(in_tx),
-	FORMAT_HYBRID_PTR(in_tx_cp),
-	FORMAT_HYBRID_PTR(offcore_rsp),
-	FORMAT_HYBRID_PTR(ldlat),
-	FORMAT_HYBRID_PTR(frontend),
-	NULL,
+	ADL_HYBRID_RTM_FORMAT_ATTR,
+	ADL_HYBRID_FORMAT_ATTR,
+	NULL
 };
 
 static struct attribute *adl_hybrid_extra_attr[] = {
-	FORMAT_HYBRID_PTR(offcore_rsp),
-	FORMAT_HYBRID_PTR(ldlat),
-	FORMAT_HYBRID_PTR(frontend),
-	NULL,
+	ADL_HYBRID_FORMAT_ATTR,
+	NULL
+};
+
+PMU_FORMAT_ATTR_SHOW(snoop_rsp, "config1:0-63");
+FORMAT_ATTR_HYBRID(snoop_rsp,	hybrid_small);
+
+static struct attribute *mtl_hybrid_extra_attr_rtm[] = {
+	ADL_HYBRID_RTM_FORMAT_ATTR,
+	ADL_HYBRID_FORMAT_ATTR,
+	FORMAT_HYBRID_PTR(snoop_rsp),
+	NULL
+};
+
+static struct attribute *mtl_hybrid_extra_attr[] = {
+	ADL_HYBRID_FORMAT_ATTR,
+	FORMAT_HYBRID_PTR(snoop_rsp),
+	NULL
 };
 
 static bool is_attr_for_this_pmu(struct kobject *kobj, struct attribute *attr)
@@ -5725,6 +5865,12 @@ static void intel_pmu_check_hybrid_pmus(u64 fixed_mask)
 	}
 }
 
+static __always_inline bool is_mtl(u8 x86_model)
+{
+	return (x86_model == INTEL_FAM6_METEORLAKE) ||
+	       (x86_model == INTEL_FAM6_METEORLAKE_L);
+}
+
 __init int intel_pmu_init(void)
 {
 	struct attribute **extra_skl_attr = &empty_attrs;
@@ -6382,6 +6528,8 @@ __init int intel_pmu_init(void)
 	case INTEL_FAM6_RAPTORLAKE:
 	case INTEL_FAM6_RAPTORLAKE_P:
 	case INTEL_FAM6_RAPTORLAKE_S:
+	case INTEL_FAM6_METEORLAKE:
+	case INTEL_FAM6_METEORLAKE_L:
 		/*
 		 * Alder Lake has 2 types of CPU, core and atom.
 		 *
@@ -6401,9 +6549,7 @@ __init int intel_pmu_init(void)
 		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
 		x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
 		x86_pmu.flags |= PMU_FL_INSTR_LATENCY;
-		x86_pmu.flags |= PMU_FL_MEM_LOADS_AUX;
 		x86_pmu.lbr_pt_coexist = true;
-		intel_pmu_pebs_data_source_adl();
 		x86_pmu.pebs_latency_data = adl_latency_data_small;
 		x86_pmu.num_topdown_events = 8;
 		static_call_update(intel_pmu_update_topdown_event,
@@ -6490,8 +6636,22 @@ __init int intel_pmu_init(void)
 		pmu->event_constraints = intel_slm_event_constraints;
 		pmu->pebs_constraints = intel_grt_pebs_event_constraints;
 		pmu->extra_regs = intel_grt_extra_regs;
-		pr_cont("Alderlake Hybrid events, ");
-		name = "alderlake_hybrid";
+		if (is_mtl(boot_cpu_data.x86_model)) {
+			x86_pmu.pebs_latency_data = mtl_latency_data_small;
+			extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
+				mtl_hybrid_extra_attr_rtm : mtl_hybrid_extra_attr;
+			mem_attr = mtl_hybrid_mem_attrs;
+			intel_pmu_pebs_data_source_mtl();
+			x86_pmu.get_event_constraints = mtl_get_event_constraints;
+			pmu->extra_regs = intel_cmt_extra_regs;
+			pr_cont("Meteorlake Hybrid events, ");
+			name = "meteorlake_hybrid";
+		} else {
+			x86_pmu.flags |= PMU_FL_MEM_LOADS_AUX;
+			intel_pmu_pebs_data_source_adl();
+			pr_cont("Alderlake Hybrid events, ");
+			name = "alderlake_hybrid";
+		}
 		break;
 
 	default:
@@ -6606,6 +6766,9 @@ __init int intel_pmu_init(void)
 	if (is_hybrid())
 		intel_pmu_check_hybrid_pmus((u64)fixed_mask);
 
+	if (x86_pmu.intel_cap.pebs_timing_info)
+		x86_pmu.flags |= PMU_FL_RETIRE_LATENCY;
+
 	intel_aux_output_init();
 
 	return 0;
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 88e58b6ee73c..b0354dc869d2 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -2,12 +2,14 @@
 #include <linux/bitops.h>
 #include <linux/types.h>
 #include <linux/slab.h>
+#include <linux/sched/clock.h>
 
 #include <asm/cpu_entry_area.h>
 #include <asm/perf_event.h>
 #include <asm/tlbflush.h>
 #include <asm/insn.h>
 #include <asm/io.h>
+#include <asm/timer.h>
 
 #include "../perf_event.h"
 
@@ -53,6 +55,13 @@ union intel_x86_pebs_dse {
 		unsigned int st_lat_locked:1;
 		unsigned int ld_reserved3:26;
 	};
+	struct {
+		unsigned int mtl_dse:5;
+		unsigned int mtl_locked:1;
+		unsigned int mtl_stlb_miss:1;
+		unsigned int mtl_fwd_blk:1;
+		unsigned int ld_reserved4:24;
+	};
 };
 
 
@@ -135,6 +144,29 @@ void __init intel_pmu_pebs_data_source_adl(void)
 	__intel_pmu_pebs_data_source_grt(data_source);
 }
 
+static void __init intel_pmu_pebs_data_source_cmt(u64 *data_source)
+{
+	data_source[0x07] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOPX, FWD);
+	data_source[0x08] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM);
+	data_source[0x0a] = OP_LH | P(LVL, LOC_RAM)  | LEVEL(RAM) | P(SNOOP, NONE);
+	data_source[0x0b] = OP_LH | LEVEL(RAM) | REM | P(SNOOP, NONE);
+	data_source[0x0c] = OP_LH | LEVEL(RAM) | REM | P(SNOOPX, FWD);
+	data_source[0x0d] = OP_LH | LEVEL(RAM) | REM | P(SNOOP, HITM);
+}
+
+void __init intel_pmu_pebs_data_source_mtl(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_cmt(data_source);
+}
+
 static u64 precise_store_data(u64 status)
 {
 	union intel_x86_pebs_dse dse;
@@ -219,24 +251,19 @@ static inline void pebs_set_tlb_lock(u64 *val, bool tlb, bool lock)
 }
 
 /* Retrieve the latency data for e-core of ADL */
-u64 adl_latency_data_small(struct perf_event *event, u64 status)
+static u64 __adl_latency_data_small(struct perf_event *event, u64 status,
+				     u8 dse, bool tlb, bool lock, bool blk)
 {
-	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];
+	dse &= PERF_PEBS_DATA_SOURCE_MASK;
+	val = hybrid_var(event->pmu, pebs_data_source)[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);
+	pebs_set_tlb_lock(&val, tlb, lock);
 
-	if (dse.ld_data_blk)
+	if (blk)
 		val |= P(BLK, DATA);
 	else
 		val |= P(BLK, NA);
@@ -244,6 +271,29 @@ u64 adl_latency_data_small(struct perf_event *event, u64 status)
 	return val;
 }
 
+u64 adl_latency_data_small(struct perf_event *event, u64 status)
+{
+	union intel_x86_pebs_dse dse;
+
+	dse.val = status;
+
+	return __adl_latency_data_small(event, status, dse.ld_dse,
+					dse.ld_locked, dse.ld_stlb_miss,
+					dse.ld_data_blk);
+}
+
+/* Retrieve the latency data for e-core of MTL */
+u64 mtl_latency_data_small(struct perf_event *event, u64 status)
+{
+	union intel_x86_pebs_dse dse;
+
+	dse.val = status;
+
+	return __adl_latency_data_small(event, status, dse.mtl_dse,
+					dse.mtl_stlb_miss, dse.mtl_locked,
+					dse.mtl_fwd_blk);
+}
+
 static u64 load_latency_data(struct perf_event *event, u64 status)
 {
 	union intel_x86_pebs_dse dse;
@@ -759,7 +809,8 @@ int intel_pmu_drain_bts_buffer(void)
 	 * the sample.
 	 */
 	rcu_read_lock();
-	perf_prepare_sample(&header, &data, event, &regs);
+	perf_prepare_sample(&data, event, &regs);
+	perf_prepare_header(&header, &data, event, &regs);
 
 	if (perf_output_begin(&handle, &data, event,
 			      header.size * (top - base - skip)))
@@ -1519,6 +1570,27 @@ static u64 get_data_src(struct perf_event *event, u64 aux)
 	return val;
 }
 
+static void setup_pebs_time(struct perf_event *event,
+			    struct perf_sample_data *data,
+			    u64 tsc)
+{
+	/* Converting to a user-defined clock is not supported yet. */
+	if (event->attr.use_clockid != 0)
+		return;
+
+	/*
+	 * Doesn't support the conversion when the TSC is unstable.
+	 * The TSC unstable case is a corner case and very unlikely to
+	 * happen. If it happens, the TSC in a PEBS record will be
+	 * dropped and fall back to perf_event_clock().
+	 */
+	if (!using_native_sched_clock() || !sched_clock_stable())
+		return;
+
+	data->time = native_sched_clock_from_tsc(tsc) + __sched_clock_offset;
+	data->sample_flags |= PERF_SAMPLE_TIME;
+}
+
 #define PERF_SAMPLE_ADDR_TYPE	(PERF_SAMPLE_ADDR |		\
 				 PERF_SAMPLE_PHYS_ADDR |	\
 				 PERF_SAMPLE_DATA_PAGE_SIZE)
@@ -1569,10 +1641,8 @@ 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) {
-		data->callchain = perf_callchain(event, iregs);
-		data->sample_flags |= PERF_SAMPLE_CALLCHAIN;
-	}
+	if (sample_type & PERF_SAMPLE_CALLCHAIN)
+		perf_sample_save_callchain(data, event, iregs);
 
 	/*
 	 * We use the interrupt regs as a base because the PEBS record does not
@@ -1668,16 +1738,11 @@ 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) {
-		data->time = native_sched_clock_from_tsc(pebs->tsc);
-		data->sample_flags |= PERF_SAMPLE_TIME;
-	}
+	if (x86_pmu.intel_cap.pebs_format >= 3)
+		setup_pebs_time(event, data, pebs->tsc);
 
-	if (has_branch_stack(event)) {
-		data->br_stack = &cpuc->lbr_stack;
-		data->sample_flags |= PERF_SAMPLE_BRANCH_STACK;
-	}
+	if (has_branch_stack(event))
+		perf_sample_save_brstack(data, event, &cpuc->lbr_stack);
 }
 
 static void adaptive_pebs_save_regs(struct pt_regs *regs,
@@ -1705,6 +1770,7 @@ 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.
@@ -1735,10 +1801,7 @@ 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) {
-		data->time = native_sched_clock_from_tsc(basic->tsc);
-		data->sample_flags |= PERF_SAMPLE_TIME;
-	}
+	setup_pebs_time(event, data, basic->tsc);
 
 	/*
 	 * We must however always use iregs for the unwinder to stay sane; the
@@ -1746,16 +1809,17 @@ 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) {
-		data->callchain = perf_callchain(event, iregs);
-		data->sample_flags |= PERF_SAMPLE_CALLCHAIN;
-	}
+	if (sample_type & PERF_SAMPLE_CALLCHAIN)
+		perf_sample_save_callchain(data, event, iregs);
 
 	*regs = *iregs;
 	/* The ip in basic is EventingIP */
 	set_linear_ip(regs, basic->ip);
 	regs->flags = PERF_EFLAGS_EXACT;
 
+	if ((sample_type & PERF_SAMPLE_WEIGHT_STRUCT) && (x86_pmu.flags & PMU_FL_RETIRE_LATENCY))
+		data->weight.var3_w = format_size >> PEBS_RETIRE_LATENCY_OFFSET & PEBS_LATENCY_MASK;
+
 	/*
 	 * The record for MEMINFO is in front of GP
 	 * But PERF_SAMPLE_TRANSACTION needs gprs->ax.
@@ -1835,8 +1899,7 @@ 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;
+			perf_sample_save_brstack(data, event, &cpuc->lbr_stack);
 		}
 	}
 
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 1f21f576ca77..c3b0d15a9841 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -1606,12 +1606,10 @@ clear_arch_lbr:
  */
 void x86_perf_get_lbr(struct x86_pmu_lbr *lbr)
 {
-	int lbr_fmt = x86_pmu.intel_cap.lbr_format;
-
 	lbr->nr = x86_pmu.lbr_nr;
 	lbr->from = x86_pmu.lbr_from;
 	lbr->to = x86_pmu.lbr_to;
-	lbr->info = (lbr_fmt == LBR_FORMAT_INFO) ? x86_pmu.lbr_info : 0;
+	lbr->info = x86_pmu.lbr_info;
 }
 EXPORT_SYMBOL_GPL(x86_perf_get_lbr);
 
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 459b1aafd4d4..bc226603ef3e 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -65,6 +65,21 @@ int uncore_die_to_segment(int die)
 	return bus ? pci_domain_nr(bus) : -EINVAL;
 }
 
+int uncore_device_to_die(struct pci_dev *dev)
+{
+	int node = pcibus_to_node(dev->bus);
+	int cpu;
+
+	for_each_cpu(cpu, cpumask_of_pcibus(dev->bus)) {
+		struct cpuinfo_x86 *c = &cpu_data(cpu);
+
+		if (c->initialized && cpu_to_node(cpu) == node)
+			return c->logical_die_id;
+	}
+
+	return -1;
+}
+
 static void uncore_free_pcibus_map(void)
 {
 	struct pci2phy_map *map, *tmp;
@@ -842,6 +857,12 @@ static const struct attribute_group uncore_pmu_attr_group = {
 	.attrs = uncore_pmu_attrs,
 };
 
+static inline int uncore_get_box_id(struct intel_uncore_type *type,
+				    struct intel_uncore_pmu *pmu)
+{
+	return type->box_ids ? type->box_ids[pmu->pmu_idx] : pmu->pmu_idx;
+}
+
 void uncore_get_alias_name(char *pmu_name, struct intel_uncore_pmu *pmu)
 {
 	struct intel_uncore_type *type = pmu->type;
@@ -850,7 +871,7 @@ void uncore_get_alias_name(char *pmu_name, struct intel_uncore_pmu *pmu)
 		sprintf(pmu_name, "uncore_type_%u", type->type_id);
 	else {
 		sprintf(pmu_name, "uncore_type_%u_%d",
-			type->type_id, type->box_ids[pmu->pmu_idx]);
+			type->type_id, uncore_get_box_id(type, pmu));
 	}
 }
 
@@ -877,7 +898,7 @@ static void uncore_get_pmu_name(struct intel_uncore_pmu *pmu)
 		 * Use the box ID from the discovery table if applicable.
 		 */
 		sprintf(pmu->name, "uncore_%s_%d", type->name,
-			type->box_ids ? type->box_ids[pmu->pmu_idx] : pmu->pmu_idx);
+			uncore_get_box_id(type, pmu));
 	}
 }
 
@@ -1674,7 +1695,10 @@ struct intel_uncore_init_fun {
 	void	(*cpu_init)(void);
 	int	(*pci_init)(void);
 	void	(*mmio_init)(void);
+	/* Discovery table is required */
 	bool	use_discovery;
+	/* The units in the discovery table should be ignored. */
+	int	*uncore_units_ignore;
 };
 
 static const struct intel_uncore_init_fun nhm_uncore_init __initconst = {
@@ -1765,6 +1789,11 @@ static const struct intel_uncore_init_fun adl_uncore_init __initconst = {
 	.mmio_init = adl_uncore_mmio_init,
 };
 
+static const struct intel_uncore_init_fun mtl_uncore_init __initconst = {
+	.cpu_init = mtl_uncore_cpu_init,
+	.mmio_init = adl_uncore_mmio_init,
+};
+
 static const struct intel_uncore_init_fun icx_uncore_init __initconst = {
 	.cpu_init = icx_uncore_cpu_init,
 	.pci_init = icx_uncore_pci_init,
@@ -1782,6 +1811,7 @@ static const struct intel_uncore_init_fun spr_uncore_init __initconst = {
 	.pci_init = spr_uncore_pci_init,
 	.mmio_init = spr_uncore_mmio_init,
 	.use_discovery = true,
+	.uncore_units_ignore = spr_uncore_units_ignore,
 };
 
 static const struct intel_uncore_init_fun generic_uncore_init __initconst = {
@@ -1832,6 +1862,8 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE,		&adl_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P,	&adl_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S,	&adl_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE,		&mtl_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L,	&mtl_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X,	&spr_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X,	&spr_uncore_init),
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D,	&snr_uncore_init),
@@ -1853,7 +1885,7 @@ static int __init intel_uncore_init(void)
 
 	id = x86_match_cpu(intel_uncore_match);
 	if (!id) {
-		if (!uncore_no_discover && intel_uncore_has_discovery_tables())
+		if (!uncore_no_discover && intel_uncore_has_discovery_tables(NULL))
 			uncore_init = (struct intel_uncore_init_fun *)&generic_uncore_init;
 		else
 			return -ENODEV;
@@ -1861,7 +1893,8 @@ static int __init intel_uncore_init(void)
 		uncore_init = (struct intel_uncore_init_fun *)id->driver_data;
 		if (uncore_no_discover && uncore_init->use_discovery)
 			return -ENODEV;
-		if (uncore_init->use_discovery && !intel_uncore_has_discovery_tables())
+		if (uncore_init->use_discovery &&
+		    !intel_uncore_has_discovery_tables(uncore_init->uncore_units_ignore))
 			return -ENODEV;
 	}
 
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index e278e2e7c051..c30fb5bb1222 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -34,6 +34,8 @@
 
 #define UNCORE_EVENT_CONSTRAINT(c, n) EVENT_CONSTRAINT(c, n, 0xff)
 
+#define UNCORE_IGNORE_END		-1
+
 struct pci_extra_dev {
 	struct pci_dev *dev[UNCORE_EXTRA_PCI_DEV_MAX];
 };
@@ -208,6 +210,7 @@ struct pci2phy_map {
 struct pci2phy_map *__find_pci2phy_map(int segment);
 int uncore_pcibus_to_dieid(struct pci_bus *bus);
 int uncore_die_to_segment(int die);
+int uncore_device_to_die(struct pci_dev *dev);
 
 ssize_t uncore_event_show(struct device *dev,
 			  struct device_attribute *attr, char *buf);
@@ -589,6 +592,7 @@ extern raw_spinlock_t pci2phy_map_lock;
 extern struct list_head pci2phy_map_head;
 extern struct pci_extra_dev *uncore_extra_pci_dev;
 extern struct event_constraint uncore_constraint_empty;
+extern int spr_uncore_units_ignore[];
 
 /* uncore_snb.c */
 int snb_uncore_pci_init(void);
@@ -602,6 +606,7 @@ void skl_uncore_cpu_init(void);
 void icl_uncore_cpu_init(void);
 void tgl_uncore_cpu_init(void);
 void adl_uncore_cpu_init(void);
+void mtl_uncore_cpu_init(void);
 void tgl_uncore_mmio_init(void);
 void tgl_l_uncore_mmio_init(void);
 void adl_uncore_mmio_init(void);
diff --git a/arch/x86/events/intel/uncore_discovery.c b/arch/x86/events/intel/uncore_discovery.c
index 5fd72d4b8bbb..cb488e41807c 100644
--- a/arch/x86/events/intel/uncore_discovery.c
+++ b/arch/x86/events/intel/uncore_discovery.c
@@ -33,7 +33,7 @@ static int logical_die_id;
 
 static int get_device_die_id(struct pci_dev *dev)
 {
-	int cpu, node = pcibus_to_node(dev->bus);
+	int node = pcibus_to_node(dev->bus);
 
 	/*
 	 * If the NUMA info is not available, assume that the logical die id is
@@ -43,19 +43,7 @@ static int get_device_die_id(struct pci_dev *dev)
 	if (node < 0)
 		return logical_die_id++;
 
-	for_each_cpu(cpu, cpumask_of_node(node)) {
-		struct cpuinfo_x86 *c = &cpu_data(cpu);
-
-		if (c->initialized && cpu_to_node(cpu) == node)
-			return c->logical_die_id;
-	}
-
-	/*
-	 * All CPUs of a node may be offlined. For this case,
-	 * the PCI and MMIO type of uncore blocks which are
-	 * enumerated by the device will be unavailable.
-	 */
-	return -1;
+	return uncore_device_to_die(dev);
 }
 
 #define __node_2_type(cur)	\
@@ -140,13 +128,21 @@ uncore_insert_box_info(struct uncore_unit_discovery *unit,
 	unsigned int *box_offset, *ids;
 	int i;
 
-	if (WARN_ON_ONCE(!unit->ctl || !unit->ctl_offset || !unit->ctr_offset))
+	if (!unit->ctl || !unit->ctl_offset || !unit->ctr_offset) {
+		pr_info("Invalid address is detected for uncore type %d box %d, "
+			"Disable the uncore unit.\n",
+			unit->box_type, unit->box_id);
 		return;
+	}
 
 	if (parsed) {
 		type = search_uncore_discovery_type(unit->box_type);
-		if (WARN_ON_ONCE(!type))
+		if (!type) {
+			pr_info("A spurious uncore type %d is detected, "
+				"Disable the uncore type.\n",
+				unit->box_type);
 			return;
+		}
 		/* Store the first box of each die */
 		if (!type->box_ctrl_die[die])
 			type->box_ctrl_die[die] = unit->ctl;
@@ -181,8 +177,12 @@ uncore_insert_box_info(struct uncore_unit_discovery *unit,
 		ids[i] = type->ids[i];
 		box_offset[i] = type->box_offset[i];
 
-		if (WARN_ON_ONCE(unit->box_id == ids[i]))
+		if (unit->box_id == ids[i]) {
+			pr_info("Duplicate uncore type %d box ID %d is detected, "
+				"Drop the duplicate uncore unit.\n",
+				unit->box_type, unit->box_id);
 			goto free_ids;
+		}
 	}
 	ids[i] = unit->box_id;
 	box_offset[i] = unit->ctl - type->box_ctrl;
@@ -202,8 +202,25 @@ free_box_offset:
 
 }
 
+static bool
+uncore_ignore_unit(struct uncore_unit_discovery *unit, int *ignore)
+{
+	int i;
+
+	if (!ignore)
+		return false;
+
+	for (i = 0; ignore[i] != UNCORE_IGNORE_END ; i++) {
+		if (unit->box_type == ignore[i])
+			return true;
+	}
+
+	return false;
+}
+
 static int parse_discovery_table(struct pci_dev *dev, int die,
-				 u32 bar_offset, bool *parsed)
+				 u32 bar_offset, bool *parsed,
+				 int *ignore)
 {
 	struct uncore_global_discovery global;
 	struct uncore_unit_discovery unit;
@@ -258,6 +275,9 @@ static int parse_discovery_table(struct pci_dev *dev, int die,
 		if (unit.access_type >= UNCORE_ACCESS_MAX)
 			continue;
 
+		if (uncore_ignore_unit(&unit, ignore))
+			continue;
+
 		uncore_insert_box_info(&unit, die, *parsed);
 	}
 
@@ -266,7 +286,7 @@ static int parse_discovery_table(struct pci_dev *dev, int die,
 	return 0;
 }
 
-bool intel_uncore_has_discovery_tables(void)
+bool intel_uncore_has_discovery_tables(int *ignore)
 {
 	u32 device, val, entry_id, bar_of