Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf updates from Ingo Molnar:
 "The main changes in this cycle were:

  Kernel side changes:

   - A couple of x86/cpu cleanups and changes were grandfathered in due
     to patch dependencies. These clean up the set of CPU model/family
     matching macros with a consistent namespace and C99 initializer
     style.

   - A bunch of updates to various low level PMU drivers:
       * AMD Family 19h L3 uncore PMU
       * Intel Tiger Lake uncore support
       * misc fixes to LBR TOS sampling

   - optprobe fixes

   - perf/cgroup: optimize cgroup event sched-in processing

   - misc cleanups and fixes

  Tooling side changes are to:

   - perf {annotate,expr,record,report,stat,test}

   - perl scripting

   - libapi, libperf and libtraceevent

   - vendor events on Intel and S390, ARM cs-etm

   - Intel PT updates

   - Documentation changes and updates to core facilities

   - misc cleanups, fixes and other enhancements"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (89 commits)
  cpufreq/intel_pstate: Fix wrong macro conversion
  x86/cpu: Cleanup the now unused CPU match macros
  hwrng: via_rng: Convert to new X86 CPU match macros
  crypto: Convert to new CPU match macros
  ASoC: Intel: Convert to new X86 CPU match macros
  powercap/intel_rapl: Convert to new X86 CPU match macros
  PCI: intel-mid: Convert to new X86 CPU match macros
  mmc: sdhci-acpi: Convert to new X86 CPU match macros
  intel_idle: Convert to new X86 CPU match macros
  extcon: axp288: Convert to new X86 CPU match macros
  thermal: Convert to new X86 CPU match macros
  hwmon: Convert to new X86 CPU match macros
  platform/x86: Convert to new CPU match macros
  EDAC: Convert to new X86 CPU match macros
  cpufreq: Convert to new X86 CPU match macros
  ACPI: Convert to new X86 CPU match macros
  x86/platform: Convert to new CPU match macros
  x86/kernel: Convert to new CPU match macros
  x86/kvm: Convert to new CPU match macros
  x86/perf/events: Convert to new CPU match macros
  ...

161 files changed, 3532 insertions, 2098 deletions

diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 3086055bf681..3dcfecf858f3 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -518,6 +518,7 @@ static void power_pmu_bhrb_read(struct perf_event *event, struct cpu_hw_events *
 		}
 	}
 	cpuhw->bhrb_stack.nr = u_index;
+	cpuhw->bhrb_stack.hw_idx = -1ULL;
 	return;
 }
 
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index beea77046f9b..cb3633d243cb 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1875,7 +1875,6 @@ config X86_SMAP
 
 config X86_UMIP
 	def_bool y
-	depends on CPU_SUP_INTEL || CPU_SUP_AMD
 	prompt "User Mode Instruction Prevention" if EXPERT
 	---help---
 	  User Mode Instruction Prevention (UMIP) is a security feature in
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index bbbebbd35b5d..75b6ea20491e 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -1064,7 +1064,7 @@ static struct aead_alg aesni_aeads[0];
 static struct simd_aead_alg *aesni_simd_aeads[ARRAY_SIZE(aesni_aeads)];
 
 static const struct x86_cpu_id aesni_cpu_id[] = {
-	X86_FEATURE_MATCH(X86_FEATURE_AES),
+	X86_MATCH_FEATURE(X86_FEATURE_AES, NULL),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, aesni_cpu_id);
diff --git a/arch/x86/crypto/crc32-pclmul_glue.c b/arch/x86/crypto/crc32-pclmul_glue.c
index 418bd88acac8..7c4c7b2fbf05 100644
--- a/arch/x86/crypto/crc32-pclmul_glue.c
+++ b/arch/x86/crypto/crc32-pclmul_glue.c
@@ -170,7 +170,7 @@ static struct shash_alg alg = {
 };
 
 static const struct x86_cpu_id crc32pclmul_cpu_id[] = {
-	X86_FEATURE_MATCH(X86_FEATURE_PCLMULQDQ),
+	X86_MATCH_FEATURE(X86_FEATURE_PCLMULQDQ, NULL),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, crc32pclmul_cpu_id);
diff --git a/arch/x86/crypto/crc32c-intel_glue.c b/arch/x86/crypto/crc32c-intel_glue.c
index c20d1b8a82c3..d2d069bd459b 100644
--- a/arch/x86/crypto/crc32c-intel_glue.c
+++ b/arch/x86/crypto/crc32c-intel_glue.c
@@ -221,7 +221,7 @@ static struct shash_alg alg = {
 };
 
 static const struct x86_cpu_id crc32c_cpu_id[] = {
-	X86_FEATURE_MATCH(X86_FEATURE_XMM4_2),
+	X86_MATCH_FEATURE(X86_FEATURE_XMM4_2, NULL),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, crc32c_cpu_id);
diff --git a/arch/x86/crypto/crct10dif-pclmul_glue.c b/arch/x86/crypto/crct10dif-pclmul_glue.c
index 3c81e15b0873..71291d5af9f4 100644
--- a/arch/x86/crypto/crct10dif-pclmul_glue.c
+++ b/arch/x86/crypto/crct10dif-pclmul_glue.c
@@ -114,7 +114,7 @@ static struct shash_alg alg = {
 };
 
 static const struct x86_cpu_id crct10dif_cpu_id[] = {
-	X86_FEATURE_MATCH(X86_FEATURE_PCLMULQDQ),
+	X86_MATCH_FEATURE(X86_FEATURE_PCLMULQDQ, NULL),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, crct10dif_cpu_id);
diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c
index a4b728518e28..1f1a95f3dd0c 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_glue.c
+++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c
@@ -313,7 +313,7 @@ static struct ahash_alg ghash_async_alg = {
 };
 
 static const struct x86_cpu_id pcmul_cpu_id[] = {
-	X86_FEATURE_MATCH(X86_FEATURE_PCLMULQDQ), /* Pickle-Mickle-Duck */
+	X86_MATCH_FEATURE(X86_FEATURE_PCLMULQDQ, NULL), /* Pickle-Mickle-Duck */
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, pcmul_cpu_id);
diff --git a/arch/x86/events/amd/power.c b/arch/x86/events/amd/power.c
index abef51320e3a..43b09e9c93a2 100644
--- a/arch/x86/events/amd/power.c
+++ b/arch/x86/events/amd/power.c
@@ -259,7 +259,7 @@ static int power_cpu_init(unsigned int cpu)
 }
 
 static const struct x86_cpu_id cpu_match[] = {
-	{ .vendor = X86_VENDOR_AMD, .family = 0x15 },
+	X86_MATCH_VENDOR_FAM(AMD, 0x15, NULL),
 	{},
 };
 
diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index 4d867a752f0e..76400c052b0e 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -180,6 +180,31 @@ static void amd_uncore_del(struct perf_event *event, int flags)
 	hwc->idx = -1;
 }
 
+/*
+ * Convert logical CPU number to L3 PMC Config ThreadMask format
+ */
+static u64 l3_thread_slice_mask(int cpu)
+{
+	u64 thread_mask, core = topology_core_id(cpu);
+	unsigned int shift, thread = 0;
+
+	if (topology_smt_supported() && !topology_is_primary_thread(cpu))
+		thread = 1;
+
+	if (boot_cpu_data.x86 <= 0x18) {
+		shift = AMD64_L3_THREAD_SHIFT + 2 * (core % 4) + thread;
+		thread_mask = BIT_ULL(shift);
+
+		return AMD64_L3_SLICE_MASK | thread_mask;
+	}
+
+	core = (core << AMD64_L3_COREID_SHIFT) & AMD64_L3_COREID_MASK;
+	shift = AMD64_L3_THREAD_SHIFT + thread;
+	thread_mask = BIT_ULL(shift);
+
+	return AMD64_L3_EN_ALL_SLICES | core | thread_mask;
+}
+
 static int amd_uncore_event_init(struct perf_event *event)
 {
 	struct amd_uncore *uncore;
@@ -203,18 +228,11 @@ static int amd_uncore_event_init(struct perf_event *event)
 		return -EINVAL;
 
 	/*
-	 * SliceMask and ThreadMask need to be set for certain L3 events in
-	 * Family 17h. For other events, the two fields do not affect the count.
+	 * SliceMask and ThreadMask need to be set for certain L3 events.
+	 * For other events, the two fields do not affect the count.
 	 */
-	if (l3_mask && is_llc_event(event)) {
-		int thread = 2 * (cpu_data(event->cpu).cpu_core_id % 4);
-
-		if (smp_num_siblings > 1)
-			thread += cpu_data(event->cpu).apicid & 1;
-
-		hwc->config |= (1ULL << (AMD64_L3_THREAD_SHIFT + thread) &
-				AMD64_L3_THREAD_MASK) | AMD64_L3_SLICE_MASK;
-	}
+	if (l3_mask && is_llc_event(event))
+		hwc->config |= l3_thread_slice_mask(event->cpu);
 
 	uncore = event_to_amd_uncore(event);
 	if (!uncore)
@@ -520,9 +538,9 @@ static int __init amd_uncore_init(void)
 	if (!boot_cpu_has(X86_FEATURE_TOPOEXT))
 		return -ENODEV;
 
-	if (boot_cpu_data.x86 == 0x17 || boot_cpu_data.x86 == 0x18) {
+	if (boot_cpu_data.x86 >= 0x17) {
 		/*
-		 * For F17h or F18h, the Northbridge counters are
+		 * For F17h and above, the Northbridge counters are
 		 * repurposed as Data Fabric counters. Also, L3
 		 * counters are supported too. The PMUs are exported
 		 * based on family as either L2 or L3 and NB or DF.
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index dff6623804c2..332954cccece 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -1945,6 +1945,14 @@ static __initconst const u64 knl_hw_cache_extra_regs
  * intel_bts events don't coexist with intel PMU's BTS events because of
  * x86_add_exclusive(x86_lbr_exclusive_lbr); there's no need to keep them
  * disabled around intel PMU's event batching etc, only inside the PMI handler.
+ *
+ * Avoid PEBS_ENABLE MSR access in PMIs.
+ * The GLOBAL_CTRL has been disabled. All the counters do not count anymore.
+ * It doesn't matter if the PEBS is enabled or not.
+ * Usually, the PEBS status are not changed in PMIs. It's unnecessary to
+ * access PEBS_ENABLE MSR in disable_all()/enable_all().
+ * However, there are some cases which may change PEBS status, e.g. PMI
+ * throttle. The PEBS_ENABLE should be updated where the status changes.
  */
 static void __intel_pmu_disable_all(void)
 {
@@ -1954,13 +1962,12 @@ static void __intel_pmu_disable_all(void)
 
 	if (test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask))
 		intel_pmu_disable_bts();
-
-	intel_pmu_pebs_disable_all();
 }
 
 static void intel_pmu_disable_all(void)
 {
 	__intel_pmu_disable_all();
+	intel_pmu_pebs_disable_all();
 	intel_pmu_lbr_disable_all();
 }
 
@@ -1968,7 +1975,6 @@ static void __intel_pmu_enable_all(int added, bool pmi)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
-	intel_pmu_pebs_enable_all();
 	intel_pmu_lbr_enable_all(pmi);
 	wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL,
 			x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_guest_mask);
@@ -1986,6 +1992,7 @@ static void __intel_pmu_enable_all(int added, bool pmi)
 
 static void intel_pmu_enable_all(int added)
 {
+	intel_pmu_pebs_enable_all();
 	__intel_pmu_enable_all(added, false);
 }
 
@@ -2374,9 +2381,21 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
 	 * PEBS overflow sets bit 62 in the global status register
 	 */
 	if (__test_and_clear_bit(62, (unsigned long *)&status)) {
+		u64 pebs_enabled = cpuc->pebs_enabled;
+
 		handled++;
 		x86_pmu.drain_pebs(regs);
 		status &= x86_pmu.intel_ctrl | GLOBAL_STATUS_TRACE_TOPAPMI;
+
+		/*
+		 * PMI throttle may be triggered, which stops the PEBS event.
+		 * Although cpuc->pebs_enabled is updated accordingly, the
+		 * MSR_IA32_PEBS_ENABLE is not updated. Because the
+		 * cpuc->enabled has been forced to 0 in PMI.
+		 * Update the MSR if pebs_enabled is changed.
+		 */
+		if (pebs_enabled != cpuc->pebs_enabled)
+			wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
 	}
 
 	/*
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 4814c964692c..e4aa20c0426f 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -594,63 +594,60 @@ static const struct cstate_model glm_cstates __initconst = {
 };
 
 
-#define X86_CSTATES_MODEL(model, states)				\
-	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long) &(states) }
-
 static const struct x86_cpu_id intel_cstates_match[] __initconst = {
-	X86_CSTATES_MODEL(INTEL_FAM6_NEHALEM,    nhm_cstates),
-	X86_CSTATES_MODEL(INTEL_FAM6_NEHALEM_EP, nhm_cstates),
-	X86_CSTATES_MODEL(INTEL_FAM6_NEHALEM_EX, nhm_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(NEHALEM,		&nhm_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(NEHALEM_EP,		&nhm_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(NEHALEM_EX,		&nhm_cstates),
 
-	X86_CSTATES_MODEL(INTEL_FAM6_WESTMERE,    nhm_cstates),
-	X86_CSTATES_MODEL(INTEL_FAM6_WESTMERE_EP, nhm_cstates),
-	X86_CSTATES_MODEL(INTEL_FAM6_WESTMERE_EX, nhm_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(WESTMERE,		&nhm_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(WESTMERE_EP,		&nhm_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(WESTMERE_EX,		&nhm_cstates),
 
-	X86_CSTATES_MODEL(INTEL_FAM6_SANDYBRIDGE,   snb_cstates),
-	X86_CSTATES_MODEL(INTEL_FAM6_SANDYBRIDGE_X, snb_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE,		&snb_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE_X,	&snb_cstates),
 
-	X86_CSTATES_MODEL(INTEL_FAM6_IVYBRIDGE,   snb_cstates),
-	X86_CSTATES_MODEL(INTEL_FAM6_IVYBRIDGE_X, snb_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE,		&snb_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE_X,		&snb_cstates),
 
-	X86_CSTATES_MODEL(INTEL_FAM6_HASWELL,   snb_cstates),
-	X86_CSTATES_MODEL(INTEL_FAM6_HASWELL_X, snb_cstates),
-	X86_CSTATES_MODEL(INTEL_FAM6_HASWELL_G, snb_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(HASWELL,		&snb_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(HASWELL_X,		&snb_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(HASWELL_G,		&snb_cstates),
 
-	X86_CSTATES_MODEL(INTEL_FAM6_HASWELL_L, hswult_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(HASWELL_L,		&hswult_cstates),
 
-	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_SILVERMONT,   slm_cstates),
-	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_SILVERMONT_D, slm_cstates),
-	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_AIRMONT,      slm_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT,	&slm_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT_D,	&slm_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_AIRMONT,	&slm_cstates),
 
-	X86_CSTATES_MODEL(INTEL_FAM6_BROADWELL,   snb_cstates),
-	X86_CSTATES_MODEL(INTEL_FAM6_BROADWELL_D, snb_cstates),
-	X86_CSTATES_MODEL(INTEL_FAM6_BROADWELL_G, snb_cstates),
-	X86_CSTATES_MODEL(INTEL_FAM6_BROADWELL_X, snb_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL,		&snb_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_D,		&snb_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_G,		&snb_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_X,		&snb_cstates),
 
-	X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_L, snb_cstates),
-	X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE,   snb_cstates),
-	X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_X, snb_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_L,		&snb_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE,		&snb_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X,		&snb_cstates),
 
-	X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_L, hswult_cstates),
-	X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE,   hswult_cstates),
-	X86_CSTATES_MODEL(INTEL_FAM6_COMETLAKE_L, hswult_cstates),
-	X86_CSTATES_MODEL(INTEL_FAM6_COMETLAKE, hswult_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE_L,		&hswult_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE,		&hswult_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE_L,		&hswult_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE,		&hswult_cstates),
 
-	X86_CSTATES_MODEL(INTEL_FAM6_CANNONLAKE_L, cnl_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(CANNONLAKE_L,	&cnl_cstates),
 
-	X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNL, knl_cstates),
-	X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNM, knl_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNL,	&knl_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNM,	&knl_cstates),
 
-	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT,   glm_cstates),
-	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_D, glm_cstates),
-	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_PLUS, glm_cstates),
-	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_TREMONT_D, glm_cstates),
-	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_TREMONT, glm_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT,	&glm_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_D,	&glm_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_PLUS,	&glm_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D,	&glm_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT,	&glm_cstates),
 
-	X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE_L, icl_cstates),
-	X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE,   icl_cstates),
-	X86_CSTATES_MODEL(INTEL_FAM6_TIGERLAKE_L, icl_cstates),
-	X86_CSTATES_MODEL(INTEL_FAM6_TIGERLAKE, icl_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L,		&icl_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE,		&icl_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L,		&icl_cstates),
+	X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE,		&icl_cstates),
 	{ },
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 534c76606049..65113b16804a 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -585,6 +585,7 @@ static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
 		cpuc->lbr_entries[i].reserved	= 0;
 	}
 	cpuc->lbr_stack.nr = i;
+	cpuc->lbr_stack.hw_idx = tos;
 }
 
 /*
@@ -680,6 +681,7 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 		out++;
 	}
 	cpuc->lbr_stack.nr = out;
+	cpuc->lbr_stack.hw_idx = tos;
 }
 
 void intel_pmu_lbr_read(void)
@@ -1120,6 +1122,13 @@ void intel_pmu_store_pebs_lbrs(struct pebs_lbr *lbr)
 	int i;
 
 	cpuc->lbr_stack.nr = x86_pmu.lbr_nr;
+
+	/* Cannot get TOS for large PEBS */
+	if (cpuc->n_pebs == cpuc->n_large_pebs)
+		cpuc->lbr_stack.hw_idx = -1ULL;
+	else
+		cpuc->lbr_stack.hw_idx = intel_pmu_lbr_tos();
+
 	for (i = 0; i < x86_pmu.lbr_nr; i++) {
 		u64 info = lbr->lbr[i].info;
 		struct perf_branch_entry *e = &cpuc->lbr_entries[i];
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 09913121e726..a5dbd25852cb 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -668,9 +668,6 @@ static int __init init_rapl_pmus(void)
 	return 0;
 }
 
-#define X86_RAPL_MODEL_MATCH(model, init)	\
-	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&init }
-
 static struct rapl_model model_snb = {
 	.events		= BIT(PERF_RAPL_PP0) |
 			  BIT(PERF_RAPL_PKG) |
@@ -716,36 +713,35 @@ static struct rapl_model model_skl = {
 };
 
 static const struct x86_cpu_id rapl_model_match[] __initconst = {
-	X86_RAPL_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE,		model_snb),
-	X86_RAPL_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE_X,		model_snbep),
-	X86_RAPL_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE,		model_snb),
-	X86_RAPL_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE_X,		model_snbep),
-	X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL,		model_hsw),
-	X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_X,		model_hsx),
-	X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_L,		model_hsw),
-	X86_RAPL_MODEL_MATCH(INTEL_FAM6_HASWELL_G,		model_hsw),
-	X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL,		model_hsw),
-	X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_G,		model_hsw),
-	X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_X,		model_hsx),
-	X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_D,		model_hsx),
-	X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNL,		model_knl),
-	X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNM,		model_knl),
-	X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_L,		model_skl),
-	X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE,		model_skl),
-	X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X,		model_hsx),
-	X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_L,		model_skl),
-	X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE,		model_skl),
-	X86_RAPL_MODEL_MATCH(INTEL_FAM6_CANNONLAKE_L,		model_skl),
-	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT,		model_hsw),
-	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_D,	model_hsw),
-	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_PLUS,	model_hsw),
-	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE_L,		model_skl),
-	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE,		model_skl),
-	X86_RAPL_MODEL_MATCH(INTEL_FAM6_COMETLAKE_L,		model_skl),
-	X86_RAPL_MODEL_MATCH(INTEL_FAM6_COMETLAKE,		model_skl),
+	X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE,		&model_snb),
+	X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE_X,	&model_snbep),
+	X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE,		&model_snb),
+	X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE_X,		&model_snbep),
+	X86_MATCH_INTEL_FAM6_MODEL(HASWELL,		&model_hsw),
+	X86_MATCH_INTEL_FAM6_MODEL(HASWELL_X,		&model_hsx),
+	X86_MATCH_INTEL_FAM6_MODEL(HASWELL_L,		&model_hsw),
+	X86_MATCH_INTEL_FAM6_MODEL(HASWELL_G,		&model_hsw),
+	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL,		&model_hsw),
+	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_G,		&model_hsw),
+	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_X,		&model_hsx),
+	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_D,		&model_hsx),
+	X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNL,	&model_knl),
+	X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNM,	&model_knl),
+	X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_L,		&model_skl),
+	X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE,		&model_skl),
+	X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X,		&model_hsx),
+	X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE_L,		&model_skl),
+	X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE,		&model_skl),
+	X86_MATCH_INTEL_FAM6_MODEL(CANNONLAKE_L,	&model_skl),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT,	&model_hsw),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_D,	&model_hsw),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_PLUS,	&model_hsw),
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L,		&model_skl),
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE,		&model_skl),
+	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE_L,		&model_skl),
+	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE,		&model_skl),
 	{},
 };
-
 MODULE_DEVICE_TABLE(x86cpu, rapl_model_match);
 
 static int __init rapl_pmu_init(void)
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 86467f85c383..1ba72c563313 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -1392,10 +1392,6 @@ err:
 	return ret;
 }
 
-
-#define X86_UNCORE_MODEL_MATCH(model, init)	\
-	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&init }
-
 struct intel_uncore_init_fun {
 	void	(*cpu_init)(void);
 	int	(*pci_init)(void);
@@ -1470,6 +1466,16 @@ static const struct intel_uncore_init_fun icl_uncore_init __initconst = {
 	.pci_init = skl_uncore_pci_init,
 };
 
+static const struct intel_uncore_init_fun tgl_uncore_init __initconst = {
+	.cpu_init = icl_uncore_cpu_init,
+	.mmio_init = tgl_uncore_mmio_init,
+};
+
+static const struct intel_uncore_init_fun tgl_l_uncore_init __initconst = {
+	.cpu_init = icl_uncore_cpu_init,
+	.mmio_init = tgl_l_uncore_mmio_init,
+};
+
 static const struct intel_uncore_init_fun snr_uncore_init __initconst = {
 	.cpu_init = snr_uncore_cpu_init,
 	.pci_init = snr_uncore_pci_init,
@@ -1477,38 +1483,39 @@ static const struct intel_uncore_init_fun snr_uncore_init __initconst = {
 };
 
 static const struct x86_cpu_id intel_uncore_match[] __initconst = {
-	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM_EP,	  nhm_uncore_init),
-	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM,	  nhm_uncore_init),
-	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_WESTMERE,	  nhm_uncore_init),
-	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_WESTMERE_EP,	  nhm_uncore_init),
-	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE,	  snb_uncore_init),
-	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE,	  ivb_uncore_init),
-	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_HASWELL,	  hsw_uncore_init),
-	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_HASWELL_L,	  hsw_uncore_init),
-	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_HASWELL_G,	  hsw_uncore_init),
-	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_BROADWELL,	  bdw_uncore_init),
-	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_BROADWELL_G,	  bdw_uncore_init),
-	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SANDYBRIDGE_X,  snbep_uncore_init),
-	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM_EX,	  nhmex_uncore_init),
-	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_WESTMERE_EX,	  nhmex_uncore_init),
-	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_IVYBRIDGE_X,	  ivbep_uncore_init),
-	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_HASWELL_X,	  hswep_uncore_init),
-	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_BROADWELL_X,	  bdx_uncore_init),
-	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_BROADWELL_D,	  bdx_uncore_init),
-	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNL,	  knl_uncore_init),
-	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNM,	  knl_uncore_init),
-	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE,	  skl_uncore_init),
-	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_L,	  skl_uncore_init),
-	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X,      skx_uncore_init),
-	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_L,	  skl_uncore_init),
-	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE,	  skl_uncore_init),
-	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ICELAKE_L,	  icl_uncore_init),
-	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ICELAKE_NNPI,	  icl_uncore_init),
-	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ICELAKE,	  icl_uncore_init),
-	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ATOM_TREMONT_D, snr_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(NEHALEM_EP,		&nhm_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(NEHALEM,		&nhm_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(WESTMERE,		&nhm_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(WESTMERE_EP,		&nhm_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE,		&snb_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE,		&ivb_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(HASWELL,		&hsw_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(HASWELL_L,		&hsw_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(HASWELL_G,		&hsw_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL,		&bdw_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_G,		&bdw_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE_X,	&snbep_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(NEHALEM_EX,		&nhmex_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(WESTMERE_EX,		&nhmex_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE_X,		&ivbep_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(HASWELL_X,		&hswep_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_X,		&bdx_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_D,		&bdx_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNL,	&knl_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNM,	&knl_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE,		&skl_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_L,		&skl_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X,		&skx_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE_L,		&skl_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE,		&skl_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L,		&icl_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_NNPI,	&icl_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE,		&icl_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L,		&tgl_l_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE,		&tgl_uncore_init),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D,	&snr_uncore_init),
 	{},
 };
-
 MODULE_DEVICE_TABLE(x86cpu, intel_uncore_match);
 
 static int __init intel_uncore_init(void)
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index bbfdaa720b45..b30429f8a53a 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -154,6 +154,7 @@ struct freerunning_counters {
 	unsigned int box_offset;
 	unsigned int num_counters;
 	unsigned int bits;
+	unsigned *box_offsets;
 };
 
 struct pci2phy_map {
@@ -310,7 +311,9 @@ unsigned int uncore_freerunning_counter(struct intel_uncore_box *box,
 
 	return pmu->type->freerunning[type].counter_base +
 	       pmu->type->freerunning[type].counter_offset * idx +
-	       pmu->type->freerunning[type].box_offset * pmu->pmu_idx;
+	       (pmu->type->freerunning[type].box_offsets ?
+	        pmu->type->freerunning[type].box_offsets[pmu->pmu_idx] :
+	        pmu->type->freerunning[type].box_offset * pmu->pmu_idx);
 }
 
 static inline
@@ -527,6 +530,8 @@ void snb_uncore_cpu_init(void);
 void nhm_uncore_cpu_init(void);
 void skl_uncore_cpu_init(void);
 void icl_uncore_cpu_init(void);
+void tgl_uncore_mmio_init(void);
+void tgl_l_uncore_mmio_init(void);
 int snb_pci2phy_map_init(int devid);
 
 /* uncore_snbep.c */
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index c37cb12d0ef6..3de1065eefc4 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -44,6 +44,11 @@
 #define PCI_DEVICE_ID_INTEL_WHL_UD_IMC		0x3e35
 #define PCI_DEVICE_ID_INTEL_ICL_U_IMC		0x8a02
 #define PCI_DEVICE_ID_INTEL_ICL_U2_IMC		0x8a12
+#define PCI_DEVICE_ID_INTEL_TGL_U1_IMC		0x9a02
+#define PCI_DEVICE_ID_INTEL_TGL_U2_IMC		0x9a04
+#define PCI_DEVICE_ID_INTEL_TGL_U3_IMC		0x9a12
+#define PCI_DEVICE_ID_INTEL_TGL_U4_IMC		0x9a14
+#define PCI_DEVICE_ID_INTEL_TGL_H_IMC		0x9a36
 
 
 /* SNB event control */
@@ -1002,3 +1007,157 @@ void nhm_uncore_cpu_init(void)
 }
 
 /* end of Nehalem uncore support */
+
+/* Tiger Lake MMIO uncore support */
+
+static const struct pci_device_id tgl_uncore_pci_ids[] = {
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_TGL_U1_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_TGL_U2_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_TGL_U3_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_TGL_U4_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_TGL_H_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* end: all zeroes */ }
+};
+
+enum perf_tgl_uncore_imc_freerunning_types {
+	TGL_MMIO_UNCORE_IMC_DATA_TOTAL,
+	TGL_MMIO_UNCORE_IMC_DATA_READ,
+	TGL_MMIO_UNCORE_IMC_DATA_WRITE,
+	TGL_MMIO_UNCORE_IMC_FREERUNNING_TYPE_MAX
+};
+
+static struct freerunning_counters tgl_l_uncore_imc_freerunning[] = {
+	[TGL_MMIO_UNCORE_IMC_DATA_TOTAL]	= { 0x5040, 0x0, 0x0, 1, 64 },
+	[TGL_MMIO_UNCORE_IMC_DATA_READ]		= { 0x5058, 0x0, 0x0, 1, 64 },
+	[TGL_MMIO_UNCORE_IMC_DATA_WRITE]	= { 0x50A0, 0x0, 0x0, 1, 64 },
+};
+
+static struct freerunning_counters tgl_uncore_imc_freerunning[] = {
+	[TGL_MMIO_UNCORE_IMC_DATA_TOTAL]	= { 0xd840, 0x0, 0x0, 1, 64 },
+	[TGL_MMIO_UNCORE_IMC_DATA_READ]		= { 0xd858, 0x0, 0x0, 1, 64 },
+	[TGL_MMIO_UNCORE_IMC_DATA_WRITE]	= { 0xd8A0, 0x0, 0x0, 1, 64 },
+};
+
+static struct uncore_event_desc tgl_uncore_imc_events[] = {
+	INTEL_UNCORE_EVENT_DESC(data_total,         "event=0xff,umask=0x10"),
+	INTEL_UNCORE_EVENT_DESC(data_total.scale,   "6.103515625e-5"),
+	INTEL_UNCORE_EVENT_DESC(data_total.unit,    "MiB"),
+
+	INTEL_UNCORE_EVENT_DESC(data_read,         "event=0xff,umask=0x20"),
+	INTEL_UNCORE_EVENT_DESC(data_read.scale,   "6.103515625e-5"),
+	INTEL_UNCORE_EVENT_DESC(data_read.unit,    "MiB"),
+
+	INTEL_UNCORE_EVENT_DESC(data_write,        "event=0xff,umask=0x30"),
+	INTEL_UNCORE_EVENT_DESC(data_write.scale,  "6.103515625e-5"),
+	INTEL_UNCORE_EVENT_DESC(data_write.unit,   "MiB"),
+
+	{ /* end: all zeroes */ }
+};
+
+static struct pci_dev *tgl_uncore_get_mc_dev(void)
+{
+	const struct pci_device_id *ids = tgl_uncore_pci_ids;
+	struct pci_dev *mc_dev = NULL;
+
+	while (ids && ids->vendor) {
+		mc_dev = pci_get_device(PCI_VENDOR_ID_INTEL, ids->device, NULL);
+		if (mc_dev)
+			return mc_dev;
+		ids++;
+	}
+
+	return mc_dev;
+}
+
+#define TGL_UNCORE_MMIO_IMC_MEM_OFFSET		0x10000
+
+static void tgl_uncore_imc_freerunning_init_box(struct intel_uncore_box *box)
+{
+	struct pci_dev *pdev = tgl_uncore_get_mc_dev();
+	struct intel_uncore_pmu *pmu = box->pmu;
+	resource_size_t addr;
+	u32 mch_bar;
+
+	if (!pdev) {
+		pr_warn("perf uncore: Cannot find matched IMC device.\n");
+		return;
+	}
+
+	pci_read_config_dword(pdev, SNB_UNCORE_PCI_IMC_BAR_OFFSET, &mch_bar);
+	/* MCHBAR is disabled */
+	if (!(mch_bar & BIT(0))) {
+		pr_warn("perf uncore: MCHBAR is disabled. Failed to map IMC free-running counters.\n");
+		return;
+	}
+	mch_bar &= ~BIT(0);
+	addr = (resource_size_t)(mch_bar + TGL_UNCORE_MMIO_IMC_MEM_OFFSET * pmu->pmu_idx);
+
+#ifdef CONFIG_PHYS_ADDR_T_64BIT
+	pci_read_config_dword(pdev, SNB_UNCORE_PCI_IMC_BAR_OFFSET + 4, &mch_bar);
+	addr |= ((resource_size_t)mch_bar << 32);
+#endif
+
+	box->io_addr = ioremap(addr, SNB_UNCORE_PCI_IMC_MAP_SIZE);
+}
+
+static struct intel_uncore_ops tgl_uncore_imc_freerunning_ops = {
+	.init_box	= tgl_uncore_imc_freerunning_init_box,
+	.exit_box	= uncore_mmio_exit_box,
+	.read_counter	= uncore_mmio_read_counter,
+	.hw_config	= uncore_freerunning_hw_config,
+};
+
+static struct attribute *tgl_uncore_imc_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	NULL
+};
+
+static const struct attribute_group tgl_uncore_imc_format_group = {
+	.name = "format",
+	.attrs = tgl_uncore_imc_formats_attr,
+};
+
+static struct intel_uncore_type tgl_uncore_imc_free_running = {
+	.name			= "imc_free_running",
+	.num_counters		= 3,
+	.num_boxes		= 2,
+	.num_freerunning_types	= TGL_MMIO_UNCORE_IMC_FREERUNNING_TYPE_MAX,
+	.freerunning		= tgl_uncore_imc_freerunning,
+	.ops			= &tgl_uncore_imc_freerunning_ops,
+	.event_descs		= tgl_uncore_imc_events,
+	.format_group		= &tgl_uncore_imc_format_group,
+};
+
+static struct intel_uncore_type *tgl_mmio_uncores[] = {
+	&tgl_uncore_imc_free_running,
+	NULL
+};
+
+void tgl_l_uncore_mmio_init(void)
+{
+	tgl_uncore_imc_free_running.freerunning = tgl_l_uncore_imc_freerunning;
+	uncore_mmio_uncores = tgl_mmio_uncores;
+}
+
+void tgl_uncore_mmio_init(void)
+{
+	uncore_mmio_uncores = tgl_mmio_uncores;
+}
+
+/* end of Tiger Lake MMIO uncore support */
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index ad20220af303..01023f0d935b 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -4380,10 +4380,10 @@ static struct pci_dev *snr_uncore_get_mc_dev(int id)
 	return mc_dev;
 }
 
-static void snr_uncore_mmio_init_box(struct intel_uncore_box *box)
+static void __snr_uncore_mmio_init_box(struct intel_uncore_box *box,
+				       unsigned int box_ctl, int mem_offset)
 {
 	struct pci_dev *pdev = snr_uncore_get_mc_dev(box->dieid);
-	unsigned int box_ctl = uncore_mmio_box_ctl(box);
 	resource_size_t addr;
 	u32 pci_dword;
 
@@ -4393,7 +4393,7 @@ static void snr_uncore_mmio_init_box(struct intel_uncore_box *box)
 	pci_read_config_dword(pdev, SNR_IMC_MMIO_BASE_OFFSET, &pci_dword);
 	addr = (pci_dword & SNR_IMC_MMIO_BASE_MASK) << 23;
 
-	pci_read_config_dword(pdev, SNR_IMC_MMIO_MEM0_OFFSET, &pci_dword);
+	pci_read_config_dword(pdev, mem_offset, &pci_dword);
 	addr |= (pci_dword & SNR_IMC_MMIO_MEM0_MASK) << 12;
 
 	addr += box_ctl;
@@ -4405,6 +4405,12 @@ static void snr_uncore_mmio_init_box(struct intel_uncore_box *box)
 	writel(IVBEP_PMON_BOX_CTL_INT, box->io_addr);
 }
 
+static void snr_uncore_mmio_init_box(struct intel_uncore_box *box)
+{
+	__snr_uncore_mmio_init_box(box, uncore_mmio_box_ctl(box),
+				   SNR_IMC_MMIO_MEM0_OFFSET);
+}
+
 static void snr_uncore_mmio_disable_box(struct intel_uncore_box *box)
 {
 	u32 config;
diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h
index 1ae4e5791afa..c7df20e78b09 100644
--- a/arch/x86/include/asm/amd_nb.h
+++ b/arch/x86/include/asm/amd_nb.h
@@ -12,7 +12,6 @@ struct amd_nb_bus_dev_range {
 	u8 dev_limit;
 };
 
-extern const struct pci_device_id amd_nb_misc_ids[];
 extern const struct amd_nb_bus_dev_range amd_nb_bus_dev_ranges[];
 
 extern bool early_is_amd_nb(u32 value);
diff --git a/arch/x86/include/asm/cpu_device_id.h b/arch/x86/include/asm/cpu_device_id.h
index 31c379c1da41..cf3d621c6892 100644
--- a/arch/x86/include/asm/cpu_device_id.h
+++ b/arch/x86/include/asm/cpu_device_id.h
@@ -5,9 +5,139 @@
 /*
  * Declare drivers belonging to specific x86 CPUs
  * Similar in spirit to pci_device_id and related PCI functions
+ *
+ * The wildcard initializers are in mod_devicetable.h because
+ * file2alias needs them. Sigh.
  */
-
 #include <linux/mod_devicetable.h>
+/* Get the INTEL_FAM* model defines */
+#include <asm/intel-family.h>
+/* And the X86_VENDOR_* ones */
+#include <asm/processor.h>
+
+/* Centaur FAM6 models */
+#define X86_CENTAUR_FAM6_C7_A		0xa
+#define X86_CENTAUR_FAM6_C7_D		0xd
+#define X86_CENTAUR_FAM6_NANO		0xf
+
+/**
+ * X86_MATCH_VENDOR_FAM_MODEL_FEATURE - Base macro for CPU matching
+ * @_vendor:	The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY
+ *		The name is expanded to X86_VENDOR_@_vendor
+ * @_family:	The family number or X86_FAMILY_ANY
+ * @_model:	The model number, model constant or X86_MODEL_ANY
+ * @_feature:	A X86_FEATURE bit or X86_FEATURE_ANY
+ * @_data:	Driver specific data or NULL. The internal storage
+ *		format is unsigned long. The supplied value, pointer
+ *		etc. is casted to unsigned long internally.
+ *
+ * Use only if you need all selectors. Otherwise use one of the shorter
+ * macros of the X86_MATCH_* family. If there is no matching shorthand
+ * macro, consider to add one. If you really need to wrap one of the macros
+ * into another macro at the usage site for good reasons, then please
+ * start this local macro with X86_MATCH to allow easy grepping.
+ */
+#define X86_MATCH_VENDOR_FAM_MODEL_FEATURE(_vendor, _family, _model,	\
+					   _feature, _data) {		\
+	.vendor		= X86_VENDOR_##_vendor,				\
+	.family		= _family,					\
+	.model		= _model,					\
+	.feature	= _feature,					\
+	.driver_data	= (unsigned long) _data				\
+}
+
+/**
+ * X86_MATCH_VENDOR_FAM_FEATURE - Macro for matching vendor, family and CPU feature
+ * @vendor:	The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY
+ *		The name is expanded to X86_VENDOR_@vendor
+ * @family:	The family number or X86_FAMILY_ANY
+ * @feature:	A X86_FEATURE bit
+ * @data:	Driver specific data or NULL. The internal storage
+ *		format is unsigned long. The supplied value, pointer
+ *		etc. is casted to unsigned long internally.
+ *
+ * All other missing arguments of X86_MATCH_VENDOR_FAM_MODEL_FEATURE() are
+ * set to wildcards.
+ */
+#define X86_MATCH_VENDOR_FAM_FEATURE(vendor, family, feature, data)	\
+	X86_MATCH_VENDOR_FAM_MODEL_FEATURE(vendor, family,		\
+					   X86_MODEL_ANY, feature, data)
+
+/**
+ * X86_MATCH_VENDOR_FEATURE - Macro for matching vendor and CPU feature
+ * @vendor:	The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY
+ *		The name is expanded to X86_VENDOR_@vendor
+ * @feature:	A X86_FEATURE bit
+ * @data:	Driver specific data or NULL. The internal storage
+ *		format is unsigned long. The supplied value, pointer
+ *		etc. is casted to unsigned long internally.
+ *
+ * All other missing arguments of X86_MATCH_VENDOR_FAM_MODEL_FEATURE() are
+ * set to wildcards.
+ */
+#define X86_MATCH_VENDOR_FEATURE(vendor, feature, data)			\
+	X86_MATCH_VENDOR_FAM_FEATURE(vendor, X86_FAMILY_ANY, feature, data)
+
+/**
+ * X86_MATCH_FEATURE - Macro for matching a CPU feature
+ * @feature:	A X86_FEATURE bit
+ * @data:	Driver specific data or NULL. The internal storage
+ *		format is unsigned long. The supplied value, pointer
+ *		etc. is casted to unsigned long internally.
+ *
+ * All other missing arguments of X86_MATCH_VENDOR_FAM_MODEL_FEATURE() are
+ * set to wildcards.
+ */
+#define X86_MATCH_FEATURE(feature, data)				\
+	X86_MATCH_VENDOR_FEATURE(ANY, feature, data)
+
+/**
+ * X86_MATCH_VENDOR_FAM_MODEL - Match vendor, family and model
+ * @vendor:	The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY
+ *		The name is expanded to X86_VENDOR_@vendor
+ * @family:	The family number or X86_FAMILY_ANY
+ * @model:	The model number, model constant or X86_MODEL_ANY
+ * @data:	Driver specific data or NULL. The internal storage
+ *		format is unsigned long. The supplied value, pointer
+ *		etc. is casted to unsigned long internally.
+ *
+ * All other missing arguments of X86_MATCH_VENDOR_FAM_MODEL_FEATURE() are
+ * set to wildcards.
+ */
+#define X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, data)		\
+	X86_MATCH_VENDOR_FAM_MODEL_FEATURE(vendor, family, model,	\
+					   X86_FEATURE_ANY, data)
+
+/**
+ * X86_MATCH_VENDOR_FAM - Match vendor and family
+ * @vendor:	The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY
+ *		The name is expanded to X86_VENDOR_@vendor
+ * @family:	The family number or X86_FAMILY_ANY
+ * @data:	Driver specific data or NULL. The internal storage
+ *		format is unsigned long. The supplied value, pointer
+ *		etc. is casted to unsigned long internally.
+ *
+ * All other missing arguments to X86_MATCH_VENDOR_FAM_MODEL_FEATURE() are
+ * set of wildcards.
+ */
+#define X86_MATCH_VENDOR_FAM(vendor, family, data)			\
+	X86_MATCH_VENDOR_FAM_MODEL(vendor, family, X86_MODEL_ANY, data)
+
+/**
+ * X86_MATCH_INTEL_FAM6_MODEL - Match vendor INTEL, family 6 and model
+ * @model:	The model name without the INTEL_FAM6_ prefix or ANY
+ *		The model name is expanded to INTEL_FAM6_@model internally
+ * @data:	Driver specific data or NULL. The internal storage
+ *		format is unsigned long. The supplied value, pointer
+ *		etc. is casted to unsigned long internally.
+ *
+ * The vendor is set to INTEL, the family to 6 and all other missing
+ * arguments of X86_MATCH_VENDOR_FAM_MODEL_FEATURE() are set to wildcards.
+ *
+ * See X86_MATCH_VENDOR_FAM_MODEL_FEATURE() for further information.
+ */
+#define X86_MATCH_INTEL_FAM6_MODEL(model, data)				\
+	X86_MATCH_VENDOR_FAM_MODEL(INTEL, 6, INTEL_FAM6_##model, data)
 
 /*
  * Match specific microcode revisions.
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 4b263ffb793b..242f7e872080 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -217,7 +217,7 @@
 #define X86_FEATURE_IBRS		( 7*32+25) /* Indirect Branch Restricted Speculation */
 #define X86_FEATURE_IBPB		( 7*32+26) /* Indirect Branch Prediction Barrier */
 #define X86_FEATURE_STIBP		( 7*32+27) /* Single Thread Indirect Branch Predictors */
-#define X86_FEATURE_ZEN			( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */
+#define X86_FEATURE_ZEN			( 7*32+28) /* "" CPU is AMD family 0x17 or above (Zen) */
 #define X86_FEATURE_L1TF_PTEINV		( 7*32+29) /* "" L1TF workaround PTE inversion */
 #define X86_FEATURE_IBRS_ENHANCED	( 7*32+30) /* Enhanced IBRS */
 #define X86_FEATURE_MSR_IA32_FEAT_CTL	( 7*32+31) /* "" MSR IA32_FEAT_CTL configured */
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 4981c293f926..8f1e94f29a16 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -35,6 +35,9 @@
  * The #define line may optionally include a comment including platform names.
  */
 
+/* Wildcard match for FAM6 so X86_MATCH_INTEL_FAM6_MODEL(ANY) works */
+#define INTEL_FAM6_ANY			X86_MODEL_ANY
+
 #define INTEL_FAM6_CORE_YONAH		0x0E
 
 #define INTEL_FAM6_CORE2_MEROM		0x0F
@@ -118,17 +121,7 @@
 #define INTEL_FAM6_XEON_PHI_KNL		0x57 /* Knights Landing */
 #define INTEL_FAM6_XEON_PHI_KNM		0x85 /* Knights Mill */
 
-/* Useful macros */
-#define INTEL_CPU_FAM_ANY(_family, _model, _driver_data)	\
-{								\
-	.vendor		= X86_VENDOR_INTEL,			\
-	.family		= _family,				\
-	.model		= _model,				\
-	.feature	= X86_FEATURE_ANY,			\
-	.driver_data	= (kernel_ulong_t)&_driver_data		\
-}
-
-#define INTEL_CPU_FAM6(_model, _driver_data)			\
-	INTEL_CPU_FAM_ANY(6, INTEL_FAM6_##_model, _driver_data)
+/* Family 5 */
+#define INTEL_FAM5_QUARK_X1000		0x09 /* Quark X1000 SoC */
 
 #endif /* _ASM_X86_INTEL_FAMILY_H */
diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h
index 95b1f053bd96..073eb7ad2f56 100644
--- a/arch/x86/include/asm/kprobes.h
+++ b/arch/x86/include/asm/kprobes.h
@@ -36,6 +36,7 @@ typedef u8 kprobe_opcode_t;
 
 /* optinsn template addresses */
 extern __visible kprobe_opcode_t optprobe_template_entry[];
+extern __visible kprobe_opcode_t optprobe_template_clac[];
 extern __visible kprobe_opcode_t optprobe_template_val[];
 extern __visible kprobe_opcode_t optprobe_template_call[];
 extern __visible kprobe_opcode_t optprobe_template_end[];
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 29964b0e1075..e855e9cf2c37 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -50,11 +50,22 @@
 
 #define AMD64_L3_SLICE_SHIFT				48
 #define AMD64_L3_SLICE_MASK				\
-	((0xFULL) << AMD64_L3_SLICE_SHIFT)
+	(0xFULL << AMD64_L3_SLICE_SHIFT)
+#define AMD64_L3_SLICEID_MASK				\
+	(0x7ULL << AMD64_L3_SLICE_SHIFT)
 
 #define AMD64_L3_THREAD_SHIFT				56
 #define AMD64_L3_THREAD_MASK				\
-	((0xFFULL) << AMD64_L3_THREAD_SHIFT)
+	(0xFFULL << AMD64_L3_THREAD_SHIFT)
+#define AMD64_L3_F19H_THREAD_MASK			\
+	(0x3ULL << AMD64_L3_THREAD_SHIFT)
+
+#define AMD64_L3_EN_ALL_CORES				BIT_ULL(47)
+#define AMD64_L3_EN_ALL_SLICES				BIT_ULL(46)
+
+#define AMD64_L3_COREID_SHIFT				42
+#define AMD64_L3_COREID_MASK				\
+	(0x7ULL << AMD64_L3_COREID_SHIFT)
 
 #define X86_RAW_EVENT_MASK		\
 	(ARCH_PERFMON_EVENTSEL_EVENT |	\
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 69aed0ebbdfc..b6b3297851f3 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -36,10 +36,9 @@ static const struct pci_device_id amd_root_ids[] = {
 	{}
 };
 
-
 #define PCI_DEVICE_ID_AMD_CNB17H_F4     0x1704
 
-const struct pci_device_id amd_nb_misc_ids[] = {
+static const struct pci_device_id amd_nb_misc_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_MISC) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F3) },
@@ -56,7 +55,6 @@ const struct pci_device_id amd_nb_misc_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_DF_F3) },
 	{}
 };
-EXPORT_SYMBOL_GPL(amd_nb_misc_ids);
 
 static const struct pci_device_id amd_nb_link_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F4) },
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 5f973fed3c9f..81b9c63dae1b 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -546,12 +546,6 @@ static struct clock_event_device lapic_clockevent = {
 };
 static DEFINE_PER_CPU(struct clock_event_device, lapic_events);
 
-#define DEADLINE_MODEL_MATCH_FUNC(model, func)	\
-	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&func }
-
-#define DEADLINE_MODEL_MATCH_REV(model, rev)	\
-	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)rev }
-
 static u32 hsx_deadline_rev(void)
 {
 	switch (boot_cpu_data.x86_stepping) {
@@ -588,23 +582,23 @@ static u32 skx_deadline_rev(void)
 }
 
 static const struct x86_cpu_id deadline_match[] = {
-	DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_HASWELL_X,	hsx_deadline_rev),
-	DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_BROADWELL_X,	0x0b000020),
-	DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_BROADWELL_D,	bdx_deadline_rev),
-	DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_SKYLAKE_X,	skx_deadline_rev),
+	X86_MATCH_INTEL_FAM6_MODEL( HASWELL_X,		&hsx_deadline_rev),
+	X86_MATCH_INTEL_FAM6_MODEL( BROADWELL_X,	0x0b000020),
+	X86_MATCH_INTEL_FAM6_MODEL( BROADWELL_D,	&bdx_deadline_rev),
+	X86_MATCH_INTEL_FAM6_MODEL( SKYLAKE_X,		&skx_deadline_rev),
 
-	DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL,		0x22),
-	DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_L,	0x20),
-	DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_G,	0x17),
+	X86_MATCH_INTEL_FAM6_MODEL( HASWELL,		0x22),
+	X86_MATCH_INTEL_FAM6_MODEL( HASWELL_L,		0x20),
+	X86_MATCH_INTEL_FAM6_MODEL( HASWELL_G,		0x17),
 
-	DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_BROADWELL,	0x25),
-	DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_BROADWELL_G,	0x17),
+	X86_MATCH_INTEL_FAM6_MODEL( BROADWELL,		0x25),
+	X86_MATCH_INTEL_FAM6_MODEL( BROADWELL_G,	0x17),
 
-	DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_SKYLAKE_L,	0xb2),
-	DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_SKYLAKE,		0xb2),
+	X86_MATCH_INTEL_FAM6_MODEL( SKYLAKE_L,		0xb2),
+	X86_MATCH_INTEL_FAM6_MODEL( SKYLAKE,		0xb2),
 
-	DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_KABYLAKE_L,	0x52),
-	DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_KABYLAKE,		0x52),
+	X86_MATCH_INTEL_FAM6_MODEL( KABYLAKE_L,		0x52),
+	X86_MATCH_INTEL_FAM6_MODEL( KABYLAKE,		0x52),
 
 	{},
 };
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index aef06c37d338..547ad7bbf0e0 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -955,7 +955,8 @@ static void init_amd(struct cpuinfo_x86 *c)
 	case 0x12: init_amd_ln(c); break;
 	case 0x15: init_amd_bd(c); break;
 	case 0x16: init_amd_jg(c); break;
-	case 0x17: init_amd_zn(c); break;
+	case 0x17: fallthrough;
+	case 0x19: init_amd_zn(c); break;
 	}
 
 	/*
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 4cdb123ff66a..137644a52716 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1008,8 +1008,8 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
 #define NO_ITLB_MULTIHIT	BIT(7)
 #define NO_SPECTRE_V2		BIT(8)
 
-#define VULNWL(_vendor, _family, _model, _whitelist)	\
-	{ X86_VENDOR_##_vendor, _family, _model, X86_FEATURE_ANY, _whitelist }
+#define VULNWL(vendor, family, model, whitelist)	\
+	X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, whitelist)
 
 #define VULNWL_INTEL(model, whitelist)		\
 	VULNWL(INTEL, 6, INTEL_FAM6_##model, whitelist)
diff --git a/arch/x86/kernel/cpu/match.c b/arch/x86/kernel/cpu/match.c
index 6dd78d8235e4..d3482eb43ff3 100644
--- a/arch/x86/kernel/cpu/match.c
+++ b/arch/x86/kernel/cpu/match.c
@@ -16,12 +16,17 @@
  * respective wildcard entries.
  *
  * A typical table entry would be to match a specific CPU
- * { X86_VENDOR_INTEL, 6, 0x12 }
- * or to match a specific CPU feature
- * { X86_FEATURE_MATCH(X86_FEATURE_FOOBAR) }
+ *
+ * X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 6, INTEL_FAM6_BROADWELL,
+ *				      X86_FEATURE_ANY, NULL);
  *
  * Fields can be wildcarded with %X86_VENDOR_ANY, %X86_FAMILY_ANY,
- * %X86_MODEL_ANY, %X86_FEATURE_ANY or 0 (except for vendor)
+ * %X86_MODEL_ANY, %X86_FEATURE_ANY (except for vendor)
+ *
+ * asm/cpu_device_id.h contains a set of useful macros which are shortcuts
+ * for various common selections. The above can be shortened to:
+ *
+ * X86_MATCH_INTEL_FAM6_MODEL(BROADWELL, NULL);
  *
  * Arrays used to match for this should also be declared using
  * MODULE_DEVICE_TABLE(x86cpu, ...)
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 3f45b5c43a71..ea13f6888284 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -71,6 +71,21 @@ found:
 	return (unsigned long)buf;
 }
 
+static void synthesize_clac(kprobe_opcode_t *addr)
+{
+	/*
+	 * Can't be static_cpu_has() due to how objtool treats this feature bit.
+	 * This isn't a fast path anyway.
+	 */
+	if (!boot_cpu_has(X86_FEATURE_SMAP))
+		return;
+
+	/* Replace the NOP3 with CLAC */
+	addr[0] = 0x0f;
+	addr[1] = 0x01;
+	addr[2] = 0xca;
+}
+
 /* Insert a move instruction which sets a pointer to eax/rdi (1st arg). */
 static void synthesize_set_arg1(kprobe_opcode_t *addr, unsigned long val)
 {
@@ -92,6 +107,9 @@ asm (
 			/* We don't bother saving the ss register */
 			"	pushq %rsp\n"
 			"	pushfq\n"
+			".global optprobe_template_clac\n"
+			"optprobe_template_clac:\n"
+			ASM_NOP3
 			SAVE_REGS_STRING
 			"	movq %rsp, %rsi\n"
 			".global optprobe_template_val\n"
@@ -111,6 +129,9 @@ asm (
 #else /* CONFIG_X86_32 */
 			"	pushl %esp\n"
 			"	pushfl\n"
+			".global optprobe_template_clac\n"
+			"optprobe_template_clac:\n"
+			ASM_NOP3
 			SAVE_REGS_STRING
 			"	movl %esp, %edx\n"
 			".global optprobe_template_val\n"
@@ -134,6 +155,8 @@ asm (
 void optprobe_template_func(void);
 STACK_FRAME_NON_STANDARD(optprobe_template_func);
 
+#define TMPL_CLAC_IDX \
+	((long)optprobe_template_clac - (long)optprobe_template_entry)
 #define TMPL_MOVE_IDX \
 	((long)optprobe_template_val - (long)optprobe_template_entry)
 #define TMPL_CALL_IDX \
@@ -389,6 +412,8 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op,
 	op->optinsn.size = ret;
 	len = TMPL_END_IDX + op->optinsn.size;
 
+	synthesize_clac(buf + TMPL_CLAC_IDX);
+
 	/* Set probe information */
 	synthesize_set_arg1(buf + TMPL_MOVE_IDX, (unsigned long)op);
 
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 69881b2d446c..3076ef0864dd 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -466,7 +466,7 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
  */
 
 static const struct x86_cpu_id snc_cpu[] = {
-	{ X86_VENDOR_INTEL, 6, INTEL_FAM6_SKYLAKE_X },
+	X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X, NULL),
 	{}
 };
 
diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c
index e0cbe4f2af49..bf528aae8ece 100644
--- a/arch/x86/kernel/tsc_msr.c
+++ b/arch/x86/kernel/tsc_msr.c
@@ -63,13 +63,13 @@ static const struct freq_desc freq_desc_lgm = {
 };
 
 static const struct x86_cpu_id tsc_msr_cpu_ids[] = {
-	INTEL_CPU_FAM6(ATOM_SALTWELL_MID,	freq_desc_pnw),
-	INTEL_CPU_FAM6(ATOM_SALTWELL_TABLET,	freq_desc_clv),
-	INTEL_CPU_FAM6(ATOM_SILVERMONT,		freq_desc_byt),
-	INTEL_CPU_FAM6(ATOM_SILVERMONT_MID,	freq_desc_tng),
-	INTEL_CPU_FAM6(ATOM_AIRMONT,		freq_desc_cht),
-	INTEL_CPU_FAM6(ATOM_AIRMONT_MID,	freq_desc_ann),
-	INTEL_CPU_FAM6(ATOM_AIRMONT_NP,		freq_desc_lgm),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_SALTWELL_MID,	&freq_desc_pnw),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_SALTWELL_TABLET,&freq_desc_clv),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT,	&freq_desc_byt),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT_MID,	&freq_desc_tng),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_AIRMONT,	&freq_desc_cht),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_AIRMONT_MID,	&freq_desc_ann),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_AIRMONT_NP,	&freq_desc_lgm),
 	{}
 };
 
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 50d1ebafe0b3..216364cb65a3 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -48,6 +48,7 @@
 #include <asm/kvm_para.h>
 #include <asm/irq_remapping.h>
 #include <asm/spec-ctrl.h>
+#include <asm/cpu_device_id.h>
 
 #include <asm/virtext.h>
 #include "trace.h"
@@ -59,7 +60,7 @@ MODULE_LICENSE("GPL");
 
 #ifdef MODULE
 static const struct x86_cpu_id svm_cpu_id[] = {
-	X86_FEATURE_MATCH(X86_FEATURE_SVM),
+	X86_MATCH_FEATURE(X86_FEATURE_SVM, NULL),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, svm_cpu_id);
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 079d9fbf278e..22aac046a8df 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -31,6 +31,7 @@
 #include <asm/apic.h>
 #include <asm/asm.h>
 #include <asm/cpu.h>
+#include <asm/cpu_device_id.h>
 #include <asm/debugreg.h>
 #include <asm/desc.h>
 #include <asm/fpu/internal.h>
@@ -66,7 +67,7 @@ MODULE_LICENSE("GPL");
 
 #ifdef MODULE
 static const struct x86_cpu_id vmx_cpu_id[] = {
-	X86_FEATURE_MATCH(X86_FEATURE_VMX),
+	X86_MATCH_FEATURE(X86_FEATURE_VMX, NULL),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, vmx_cpu_id);
diff --git a/arch/x86/platform/atom/punit_atom_debug.c b/arch/x86/platform/atom/punit_atom_debug.c
index ee6b0780bea1..f8ed5f66cd20 100644
--- a/arch/x86/platform/atom/punit_atom_debug.c
+++ b/arch/x86/platform/atom/punit_atom_debug.c
@@ -117,17 +117,16 @@ static void punit_dbgfs_unregister(void)
 	debugfs_remove_recursive(punit_dbg_file);
 }
 
-#define ICPU(model, drv_data) \
-	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_MWAIT,\
-	  (kernel_ulong_t)&drv_data }
+#define X86_MATCH(model, data)						 \
+	X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 6, INTEL_FAM6_##model, \
+					   X86_FEATURE_MWAIT, data)
 
 static const struct x86_cpu_id intel_punit_cpu_ids[] = {
-	ICPU(INTEL_FAM6_ATOM_SILVERMONT, punit_device_byt),
-	ICPU(INTEL_FAM6_ATOM_SILVERMONT_MID,  punit_device_tng),
-	ICPU(INTEL_FAM6_ATOM_AIRMONT,	  punit_device_cht),
+	X86_MATCH(ATOM_SILVERMONT,		&punit_device_byt),
+	X86_MATCH(ATOM_SILVERMONT_MID,		&punit_device_tng),
+	X86_MATCH(ATOM_AIRMONT,			&punit_device_cht),
 	{}
 };
-
 MODULE_DEVICE_TABLE(x86cpu, intel_punit_cpu_ids);
 
 static int __init punit_atom_debug_init(void)
diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c
index ce82f497ac67..a5a469cdf5bf 100644
--- a/arch/x86/platform/efi/quirks.c
+++ b/arch/x86/platform/efi/quirks.c
@@ -663,12 +663,9 @@ static int qrk_capsule_setup_info(struct capsule_info *cap_info, void **pkbuff,
 	return 1;
 }
 
-#define ICPU(family, model, quirk_handler) \
-	{ X86_VENDOR_INTEL, family, model, X86_FEATURE_ANY, \
-	  (unsigned long)&quirk_handler }
-
 static const struct x86_cpu_id efi_capsule_quirk_ids[] = {
-	ICPU(5, 9, qrk_capsule_setup_info),	/* Intel Quark X1000 */
+	X86_MATCH_VENDOR_FAM_MODEL(INTEL, 5, INTEL_FAM5_QUARK_X1000,
+				   &qrk_capsule_setup_info),
 	{ }
 };
 
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_bt.c b/arch/x86/platform/intel-mid/device_libs/platform_bt.c
index e3f4bfc08f78..31dda18bb370 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_bt.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_bt.c
@@ -60,11 +60,8 @@ static struct bt_sfi_data tng_bt_sfi_data __initdata = {
 	.setup	= tng_bt_sfi_setup,
 };
 
-#define ICPU(model, ddata)	\
-	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (kernel_ulong_t)&ddata }
-
 static const struct x86_cpu_id bt_sfi_cpu_ids[] = {
-	ICPU(INTEL_FAM6_ATOM_SILVERMONT_MID, tng_bt_sfi_data),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT_MID,	&tng_bt_sfi_data),
 	{}
 };
 
diff --git a/arch/x86/platform/intel-quark/imr.c b/arch/x86/platform/intel-quark/imr.c
index e9d97d52475e..0286fe1b14b5 100644
--- a/arch/x86/platform/intel-quark/imr.c
+++ b/arch/x86/platform/intel-quark/imr.c
@@ -569,7 +569,7 @@ static void __init imr_fixup_memmap(struct imr_device *idev)
 }
 
 static const struct x86_cpu_id imr_ids[] __initconst = {
-	{ X86_VENDOR_INTEL, 5, 9 },	/* Intel Quark SoC X1000. */
+	X86_MATCH_VENDOR_FAM_MODEL(INTEL, 5, INTEL_FAM5_QUARK_X1000, NULL),
 	{}
 };
 
diff --git a/arch/x86/platform/intel-quark/imr_selftest.c b/arch/x86/platform/intel-quark/imr_selftest.c
index 4307830e1b6f..570e3062faac 100644
--- a/arch/x86/platform/intel-quark/imr_selftest.c
+++ b/arch/x86/platform/intel-quark/imr_selftest.c
@@ -105,7 +105,7 @@ static void __init imr_self_test(void)
 }
 
 static const struct x86_cpu_id imr_ids[] __initconst = {
-	{ X86_VENDOR_INTEL, 5, 9 },	/* Intel Quark SoC X1000. */
+	X86_MATCH_VENDOR_FAM_MODEL(INTEL, 5, INTEL_FAM5_QUARK_X1000, NULL),
 	{}
 };
 
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 915bb1639763..aaff9ed7ff45 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -475,20 +475,8 @@ static int msr_save_cpuid_features(const struct x86_cpu_id *c)
 }
 
 static const struct x86_cpu_id msr_save_cpu_table[] = {
-	{
-		.vendor = X86_VENDOR_AMD,
-		.family = 0x15,
-		.model = X86_MODEL_ANY,
-		.feature = X86_FEATURE_ANY,
-		.driver_data = (kernel_ulong_t)msr_save_cpuid_features,
-	},
-	{
-		.vendor = X86_VENDOR_AMD,
-		.family = 0x16,
-		.model = X86_MODEL_ANY,
-		.feature = X86_FEATURE_ANY,
-		.driver_data = (kernel_ulong_t)msr_save_cpuid_features,
-	},
+	X86_MATCH_VENDOR_FAM(AMD, 0x15, &msr_save_cpuid_features),
+	X86_MATCH_VENDOR_FAM(AMD, 0x16, &msr_save_cpuid_features),
 	{}
 };
 
diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index db18df6cb330..dee999938213 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -306,11 +306,9 @@ static const struct lpss_device_desc bsw_spi_dev_desc = {
 	.setup = lpss_deassert_reset,
 };
 
-#define ICPU(model)	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, }
-
 static const struct x86_cpu_id lpss_cpu_ids[] = {
-	ICPU(INTEL_FAM6_ATOM_SILVERMONT),	/* Valleyview, Bay Trail */
-	ICPU(INTEL_FAM6_ATOM_AIRMONT),	/* Braswell, Cherry Trail */
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT,	NULL),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_AIRMONT,	NULL),
 	{}
 };
 
diff --git a/drivers/acpi/x86/utils.c b/drivers/acpi/x86/utils.c
index 697a6b12d6b9..bdc1ba00aee9 100644
--- a/drivers/acpi/x86/utils.c
+++ b/drivers/acpi/x86/utils.c
@@ -37,7 +37,7 @@ struct always_present_id {
 	const char *uid;
 };
 
-#define ICPU(model)	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, }
+#define X86_MATCH(model)	X86_MATCH_INTEL_FAM6_MODEL(model, NULL)
 
 #define ENTRY(hid, uid, cpu_models, dmi...) {				\
 	{ { hid, }, {} },						\
@@ -51,29 +51,29 @@ static const struct always_present_id always_present_ids[] = {
 	 * Bay / Cherry Trail PWM directly poked by GPU driver in win10,
 	 * but Linux uses a separate PWM driver, harmless if not used.
 	 */
-	ENTRY("80860F09", "1", ICPU(INTEL_FAM6_ATOM_SILVERMONT), {}),
-	ENTRY("80862288", "1", ICPU(INTEL_FAM6_ATOM_AIRMONT), {}),
+	ENTRY("80860F09", "1", X86_MATCH(ATOM_SILVERMONT), {}),
+	ENTRY("80862288", "1", X86_MATCH(ATOM_AIRMONT), {}),
 
 	/* Lenovo Yoga Book uses PWM2 for keyboard backlight control */
-	ENTRY("80862289", "2", ICPU(INTEL_FAM6_ATOM_AIRMONT), {
+	ENTRY("80862289", "2", X86_MATCH(ATOM_AIRMONT), {
 			DMI_MATCH(DMI_PRODUCT_NAME, "Lenovo YB1-X9"),
 		}),
 	/*
 	 * The INT0002 device is necessary to clear wakeup interrupt sources
 	 * on Cherry Trail devices, without it we get nobody cared IRQ msgs.
 	 */
-	ENTRY("INT0002", "1", ICPU(INTEL_FAM6_ATOM_AIRMONT), {}),
+	ENTRY("INT0002", "1", X86_MATCH(ATOM_AIRMONT), {}),
 	/*
 	 * On the Dell Venue 11 Pro 7130 and 7139, the DSDT hides
 	 * the touchscreen ACPI device until a certain time
 	 * after _SB.PCI0.GFX0.LCD.LCD1._ON gets called has passed
 	 * *and* _STA has been called at least 3 times since.
 	 */
-	ENTRY("SYNA7500", "1", ICPU(INTEL_FAM6_HASWELL_L), {
+	ENTRY("SYNA7500", "1", X86_MATCH(HASWELL_L), {
 		DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 		DMI_MATCH(DMI_PRODUCT_NAME, "Venue 11 Pro 7130"),
 	      }),
-	ENTRY("SYNA7500", "1", ICPU(INTEL_FAM6_HASWELL_L), {
+	ENTRY("SYNA7500", "1", X86_MATCH(HASWELL_L), {
 		DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 		DMI_MATCH(DMI_PRODUCT_NAME, "Venue 11 Pro 7139"),
 	      }),
@@ -89,19 +89,19 @@ static const struct always_present_id always_present_ids[] = {
 	 * was copy-pasted from the GPD win, so it has a disabled KIOX000A
 	 * node which we should not enable, thus we also check the BIOS date.
 	 */
-	ENTRY("KIOX000A", "1", ICPU(INTEL_FAM6_ATOM_AIRMONT), {
+	ENTRY("KIOX000A", "1", X86_MATCH(ATOM_AIRMONT), {
 		DMI_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"),
 		DMI_MATCH(DMI_BOARD_NAME, "Default string"),
 		DMI_MATCH(DMI_PRODUCT_NAME, "Default string"),
 		DMI_MATCH(DMI_BIOS_DATE, "02/21/2017")
 	      }),
-	ENTRY("KIOX000A", "1", ICPU(INTEL_FAM6_ATOM_AIRMONT), {
+	ENTRY("KIOX000A", "1", X86_MATCH(ATOM_AIRMONT), {
 		DMI_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"),
 		DMI_MATCH(DMI_BOARD_NAME, "Default string"),
 		DMI_MATCH(DMI_PRODUCT_NAME, "Default string"),
 		DMI_MATCH(DMI_BIOS_DATE, "03/20/2017")
 	      }),
-	ENTRY("KIOX000A", "1", ICPU(INTEL_FAM6_ATOM_AIRMONT), {
+	ENTRY("KIOX000A", "1", X86_MATCH(ATOM_AIRMONT), {
 		DMI_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"),
 		DMI_MATCH(DMI_BOARD_NAME, "Default string"),
 		DMI_MATCH(DMI_PRODUCT_NAME, "Default string"),
diff --git a/drivers/char/agp/amd64-agp.c b/drivers/char/agp/amd64-agp.c
index 594aee281977..b40edae32817 100644
--- a/drivers/char/agp/amd64-agp.c
+++ b/drivers/char/agp/amd64-agp.c
@@ -775,7 +775,7 @@ int __init agp_amd64_init(void)
 		}
 
 		/* First check that we have at least one AMD64 NB */
-		if (!pci_dev_present(amd_nb_misc_ids)) {
+		if (!amd_nb_num()) {
 			pci_unregister_driver(&agp_amd64_pci_driver);
 			return -ENODEV;
 		}
diff --git a/drivers/char/hw_random/via-rng.c b/drivers/char/hw_random/via-rng.c
index ffe9b0c6c647..39943bc3651a 100644
--- a/drivers/char/hw_random/via-rng.c
+++ b/drivers/char/hw_random/via-rng.c
@@ -209,20 +209,19 @@ static int __init mod_init(void)
 out:
 	return err;
 }
+module_init(mod_init);
 
 static void __exit mod_exit(void)
 {
 	hwrng_unregister(&via_rng);
 }
-
-module_init(mod_init);
 module_exit(mod_exit);
 
 static struct x86_cpu_id __maybe_unused via_rng_cpu_id[] = {
-	X86_FEATURE_MATCH(X86_FEATURE_XSTORE),
+	X86_MATCH_FEATURE(X86_FEATURE_XSTORE, NULL),
 	{}
 };
+MODULE_DEVICE_TABLE(x86cpu, via_rng_cpu_id);
 
 MODULE_DESCRIPTION("H/W RNG driver for VIA CPU with PadLock");
 MODULE_LICENSE("GPL");
-MODULE_DEVICE_TABLE(x86cpu, via_rng_cpu_id);
diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index d6f7df33ab8c..289e8ce3fd13 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -30,6 +30,7 @@
 #include <asm/msr.h>
 #include <asm/processor.h>
 #include <asm/cpufeature.h>
+#include <asm/cpu_device_id.h>
 
 MODULE_AUTHOR("Paul Diefenbaugh, Dominik Brodowski");
 MODULE_DESCRIPTION("ACPI Processor P-States Driver");
@@ -991,8 +992,8 @@ late_initcall(acpi_cpufreq_init);
 module_exit(acpi_cpufreq_exit);
 
 static const struct x86_cpu_id acpi_cpufreq_ids[] = {
-	X86_FEATURE_MATCH(X86_FEATURE_ACPI),
-	X86_FEATURE_MATCH(X86_FEATURE_HW_PSTATE),
+	X86_MATCH_FEATURE(X86_FEATURE_ACPI, NULL),
+	X86_MATCH_FEATURE(X86_FEATURE_HW_PSTATE, NULL),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, acpi_cpufreq_ids);
diff --git a/drivers/cpufreq/amd_freq_sensitivity.c b/drivers/cpufreq/amd_freq_sensitivity.c
index e2df9d112106..f7c4206d4c90 100644
--- a/drivers/cpufreq/amd_freq_sensitivity.c
+++ b/drivers/cpufreq/amd_freq_sensitivity.c
@@ -18,6 +18,7 @@
 
 #include <asm/msr.h>
 #include <asm/cpufeature.h>
+#include <asm/cpu_device_id.h>
 
 #include "cpufreq_ondemand.h"
 
@@ -144,7 +145,7 @@ static void __exit amd_freq_sensitivity_exit(void)
 module_exit(amd_freq_sensitivity_exit);
 
 static const struct x86_cpu_id amd_freq_sensitivity_ids[] = {
-	X86_FEATURE_MATCH(X86_FEATURE_PROC_FEEDBACK),
+	X86_MATCH_FEATURE(X86_FEATURE_PROC_FEEDBACK, NULL),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, amd_freq_sensitivity_ids);
diff --git a/drivers/cpufreq/e_powersaver.c b/drivers/cpufreq/e_powersaver.c
index 45c18c6b8081..776a58bab0ff 100644
--- a/drivers/cpufreq/e_powersaver.c
+++ b/drivers/cpufreq/e_powersaver.c
@@ -385,7 +385,7 @@ static struct cpufreq_driver eps_driver = {
 /* This driver will work only on Centaur C7 processors with
  * Enhanced SpeedStep/PowerSaver registers */
 static const struct x86_cpu_id eps_cpu_id[] = {
-	{ X86_VENDOR_CENTAUR, 6, X86_MODEL_ANY, X86_FEATURE_EST },
+	X86_MATCH_VENDOR_FAM_FEATURE(CENTAUR, 6, X86_FEATURE_EST, NULL),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, eps_cpu_id);
diff --git a/drivers/cpufreq/elanfreq.c b/drivers/cpufreq/elanfreq.c
index 2242541f7ae3..4ce5eb35dc46 100644
--- a/drivers/cpufreq/elanfreq.c
+++ b/drivers/cpufreq/elanfreq.c
@@ -198,7 +198,7 @@ static struct cpufreq_driver elanfreq_driver = {
 };
 
 static const struct x86_cpu_id elan_id[] = {
-	{ X86_VENDOR_AMD, 4, 10, },
+	X86_MATCH_VENDOR_FAM_MODEL(AMD, 4, 10, NULL),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, elan_id);
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index d2297839374d..95abbf66e95e 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -1908,51 +1908,51 @@ static const struct pstate_funcs knl_funcs = {
 	.get_val = core_get_val,
 };
 
-#define ICPU(model, policy) \
-	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_APERFMPERF,\
-			(unsigned long)&policy }
+#define X86_MATCH(model, policy)					 \
+	X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 6, INTEL_FAM6_##model, \
+					   X86_FEATURE_APERFMPERF, &policy)
 
 static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
-	ICPU(INTEL_FAM6_SANDYBRIDGE,		core_funcs),
-	ICPU(INTEL_FAM6_SANDYBRIDGE_X,		core_funcs),
-	ICPU(INTEL_FAM6_ATOM_SILVERMONT,	silvermont_funcs),
-	ICPU(INTEL_FAM6_IVYBRIDGE,		core_funcs),
-	ICPU(INTEL_FAM6_HASWELL,		core_funcs),
-	ICPU(INTEL_FAM6_BROADWELL,		core_funcs),
-	ICPU(INTEL_FAM6_IVYBRIDGE_X,		core_funcs),
-	ICPU(INTEL_FAM6_HASWELL_X,		core_funcs),
-	ICPU(INTEL_FAM6_HASWELL_L,		core_funcs),
-	ICPU(INTEL_FAM6_HASWELL_G,		core_funcs),
-	ICPU(INTEL_FAM6_BROADWELL_G,		core_funcs),
-	ICPU(INTEL_FAM6_ATOM_AIRMONT,		airmont_funcs),
-	ICPU(INTEL_FAM6_SKYLAKE_L,		core_funcs),
-	ICPU(INTEL_FAM6_BROADWELL_X,		core_funcs),
-	ICPU(INTEL_FAM6_SKYLAKE,		core_funcs),
-	ICPU(INTEL_FAM6_BROADWELL_D,		core_funcs),
-	ICPU(INTEL_FAM6_XEON_PHI_KNL,		knl_funcs),
-	ICPU(INTEL_FAM6_XEON_PHI_KNM,		knl_funcs),
-	ICPU(INTEL_FAM6_ATOM_GOLDMONT,		core_funcs),
-	ICPU(INTEL_FAM6_ATOM_GOLDMONT_PLUS,     core_funcs),
-	ICPU(INTEL_FAM6_SKYLAKE_X,		core_funcs),
+	X86_MATCH(SANDYBRIDGE,		core_funcs),
+	X86_MATCH(SANDYBRIDGE_X,	core_funcs),
+	X86_MATCH(ATOM_SILVERMONT,	silvermont_funcs),
+	X86_MATCH(IVYBRIDGE,		core_funcs),
+	X86_MATCH(HASWELL,		core_funcs),
+	X86_MATCH(BROADWELL,		core_funcs),
+	X86_MATCH(IVYBRIDGE_X,		core_funcs),
+	X86_MATCH(HASWELL_X,		core_funcs),
+	X86_MATCH(HASWELL_L,		core_funcs),
+	X86_MATCH(HASWELL_G,		core_funcs),
+	X86_MATCH(BROADWELL_G,		core_funcs),
+	X86_MATCH(ATOM_AIRMONT,		airmont_funcs),
+	X86_MATCH(SKYLAKE_L,		core_funcs),
+	X86_MATCH(BROADWELL_X,		core_funcs),
+	X86_MATCH(SKYLAKE,		core_funcs),
+	X86_MATCH(BROADWELL_D,		core_funcs),
+	X86_MATCH(XEON_PHI_KNL,		knl_funcs),
+	X86_MATCH(XEON_PHI_KNM,		knl_funcs),
+	X86_MATCH(ATOM_GOLDMONT,	core_funcs),
+	X86_MATCH(ATOM_GOLDMONT_PLUS,	core_funcs),
+	X86_MATCH(SKYLAKE_X,		core_funcs),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids);
 
 static const struct x86_cpu_id intel_pstate_cpu_oob_ids[] __initconst = {
-	ICPU(INTEL_FAM6_BROADWELL_D, core_funcs),
-	ICPU(INTEL_FAM6_BROADWELL_X, core_funcs),
-	ICPU(INTEL_FAM6_SKYLAKE_X, core_funcs),
+	X86_MATCH(BROADWELL_D,		core_funcs),
+	X86_MATCH(BROADWELL_X,		core_funcs),
+	X86_MATCH(SKYLAKE_X,		core_funcs),
 	{}
 };
 
 static const struct x86_cpu_id intel_pstate_cpu_ee_disable_ids[] = {
-	ICPU(INTEL_FAM6_KABYLAKE, core_funcs),
+	X86_MATCH(KABYLAKE,		core_funcs),
 	{}
 };
 
 static const struct x86_cpu_id intel_pstate_hwp_boost_ids[] = {
-	ICPU(INTEL_FAM6_SKYLAKE_X, core_funcs),
-	ICPU(INTEL_FAM6_SKYLAKE, core_funcs),
+	X86_MATCH(SKYLAKE_X,		core_funcs),
+	X86_MATCH(SKYLAKE,		core_funcs),
 	{}
 };
 
@@ -2725,13 +2725,14 @@ static inline void intel_pstate_request_control_from_smm(void) {}
 
 #define INTEL_PSTATE_HWP_BROADWELL	0x01
 
-#define ICPU_HWP(model, hwp_mode) \
-	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_HWP, hwp_mode }
+#define X86_MATCH_HWP(model, hwp_mode)					\
+	X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 6, INTEL_FAM6_##model, \
+					   X86_FEATURE_HWP, hwp_mode)
 
 static const struct x86_cpu_id hwp_support_ids[] __initconst = {
-	ICPU_HWP(INTEL_FAM6_BROADWELL_X, INTEL_PSTATE_HWP_BROADWELL),
-	ICPU_HWP(INTEL_FAM6_BROADWELL_D, INTEL_PSTATE_HWP_BROADWELL),
-	ICPU_HWP(X86_MODEL_ANY, 0),
+	X86_MATCH_HWP(BROADWELL_X,	INTEL_PSTATE_HWP_BROADWELL),
+	X86_MATCH_HWP(BROADWELL_D,	INTEL_PSTATE_HWP_BROADWELL),
+	X86_MATCH_HWP(ANY,		0),
 	{}
 };
 
diff --git a/drivers/cpufreq/longhaul.c b/drivers/cpufreq/longhaul.c
index 92d92e67ae0a..123fb006810d 100644
--- a/drivers/cpufreq/longhaul.c
+++ b/drivers/cpufreq/longhaul.c
@@ -910,7 +910,7 @@ static struct cpufreq_driver longhaul_driver = {
 };
 
 static const struct x86_cpu_id longhaul_id[] = {
-	{ X86_VENDOR_CENTAUR, 6 },
+	X86_MATCH_VENDOR_FAM(CENTAUR, 6, NULL),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, longhaul_id);
diff --git a/drivers/cpufreq/longrun.c b/drivers/cpufreq/longrun.c
index 0b08be8bff76..1caaec7c280b 100644
--- a/drivers/cpufreq/longrun.c
+++ b/drivers/cpufreq/longrun.c
@@ -281,8 +281,7 @@ static struct cpufreq_driver longrun_driver = {
 };
 
 static const struct x86_cpu_id longrun_ids[] = {
-	{ X86_VENDOR_TRANSMETA, X86_FAMILY_ANY, X86_MODEL_ANY,
-	  X86_FEATURE_LONGRUN },
+	X86_MATCH_VENDOR_FEATURE(TRANSMETA, X86_FEATURE_LONGRUN, NULL),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, longrun_ids);
diff --git a/drivers/cpufreq/p4-clockmod.c b/drivers/cpufreq/p4-clockmod.c
index efc0b46efada..bb61677c11c7 100644
--- a/drivers/cpufreq/p4-clockmod.c
+++ b/drivers/cpufreq/p4-clockmod.c
@@ -231,7 +231,7 @@ static struct cpufreq_driver p4clockmod_driver = {
 };
 
 static const struct x86_cpu_id cpufreq_p4_id[] = {
-	{ X86_VENDOR_INTEL, X86_FAMILY_ANY, X86_MODEL_ANY, X86_FEATURE_ACC },
+	X86_MATCH_VENDOR_FEATURE(INTEL, X86_FEATURE_ACC, NULL),
 	{}
 };
 
diff --git a/drivers/cpufreq/powernow-k6.c b/drivers/cpufreq/powernow-k6.c
index 0196f8129597..41eefef95d87 100644
--- a/drivers/cpufreq/powernow-k6.c
+++ b/drivers/cpufreq/powernow-k6.c
@@ -258,8 +258,8 @@ static struct cpufreq_driver powernow_k6_driver = {
 };
 
 static const struct x86_cpu_id powernow_k6_ids[] = {
-	{ X86_VENDOR_AMD, 5, 12 },
-	{ X86_VENDOR_AMD, 5, 13 },
+	X86_MATCH_VENDOR_FAM_MODEL(AMD, 5, 12, NULL),
+	X86_MATCH_VENDOR_FAM_MODEL(AMD, 5, 13, NULL),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, powernow_k6_ids);
diff --git a/drivers/cpufreq/powernow-k7.c b/drivers/cpufreq/powernow-k7.c
index 5e5171d3eece..5d515fc34836 100644
--- a/drivers/cpufreq/powernow-k7.c
+++ b/drivers/cpufreq/powernow-k7.c
@@ -109,7 +109,7 @@ static int check_fsb(unsigned int fsbspeed)
 }
 
 static const struct x86_cpu_id powernow_k7_cpuids[] = {
-	{ X86_VENDOR_AMD, 6, },
+	X86_MATCH_VENDOR_FAM(AMD, 6, NULL),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, powernow_k7_cpuids);
diff --git a/drivers/cpufreq/powernow-k8.c b/drivers/cpufreq/powernow-k8.c
index 2db2f1739e09..3984959eed1d 100644
--- a/drivers/cpufreq/powernow-k8.c
+++ b/drivers/cpufreq/powernow-k8.c
@@ -452,7 +452,7 @@ static int core_voltage_post_transition(struct powernow_k8_data *data,
 
 static const struct x86_cpu_id powernow_k8_ids[] = {
 	/* IO based frequency switching */
-	{ X86_VENDOR_AMD, 0xf },
+	X86_MATCH_VENDOR_FAM(AMD, 0xf, NULL),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, powernow_k8_ids);
diff --git a/drivers/cpufreq/sc520_freq.c b/drivers/cpufreq/sc520_freq.c
index c6f647babaad..73a208559fe2 100644
--- a/drivers/cpufreq/sc520_freq.c
+++ b/drivers/cpufreq/sc520_freq.c
@@ -95,7 +95,7 @@ static struct cpufreq_driver sc520_freq_driver = {
 };
 
 static const struct x86_cpu_id sc520_ids[] = {
-	{ X86_VENDOR_AMD, 4, 9 },
+	X86_MATCH_VENDOR_FAM_MODEL(AMD, 4, 9, NULL),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, sc520_ids);
diff --git a/drivers/cpufreq/speedstep-centrino.c b/drivers/cpufreq/speedstep-centrino.c
index b49f494e0285..75b10ecdb60f 100644
--- a/drivers/cpufreq/speedstep-centrino.c
+++ b/drivers/cpufreq/speedstep-centrino.c
@@ -520,18 +520,12 @@ static struct cpufreq_driver centrino_driver = {
  * or ASCII model IDs.
  */
 static const struct x86_cpu_id centrino_ids[] = {
-	{ X86_VENDOR_INTEL, 6, 9, X86_FEATURE_EST },
-	{ X86_VENDOR_INTEL, 6, 13, X86_FEATURE_EST },
-	{ X86_VENDOR_INTEL, 6, 13, X86_FEATURE_EST },
-	{ X86_VENDOR_INTEL, 6, 13, X86_FEATURE_EST },
-	{ X86_VENDOR_INTEL, 15, 3, X86_FEATURE_EST },
-	{ X86_VENDOR_INTEL, 15, 4, X86_FEATURE_EST },
+	X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL,  6,  9, X86_FEATURE_EST, NULL),
+	X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL,  6, 13, X86_FEATURE_EST, NULL),
+	X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 15,  3, X86_FEATURE_EST, NULL),
+	X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 15,  4, X86_FEATURE_EST, NULL),
 	{}
 };
-#if 0
-/* Autoload or not? Do not for now. */
-MODULE_DEVICE_TABLE(x86cpu, centrino_ids);
-#endif
 
 /**
  * centrino_init - initializes the Enhanced SpeedStep CPUFreq driver
diff --git a/drivers/cpufreq/speedstep-ich.c b/drivers/cpufreq/speedstep-ich.c
index 547fd7af5bf5..f2076d72bf39 100644
--- a/drivers/cpufreq/speedstep-ich.c
+++ b/drivers/cpufreq/speedstep-ich.c
@@ -319,15 +319,11 @@ static struct cpufreq_driver speedstep_driver = {
 };
 
 static const struct x86_cpu_id ss_smi_ids[] = {
-	{ X86_VENDOR_INTEL, 6, 0xb, },
-	{ X86_VENDOR_INTEL, 6, 0x8, },
-	{ X86_VENDOR_INTEL, 15, 2 },
+	X86_MATCH_VENDOR_FAM_MODEL(INTEL,  6, 0x8, 0),
+	X86_MATCH_VENDOR_FAM_MODEL(INTEL,  6, 0xb, 0),
+	X86_MATCH_VENDOR_FAM_MODEL(INTEL, 15, 0x2, 0),
 	{}
 };
-#if 0
-/* Autoload or not? Do not for now. */
-MODULE_DEVICE_TABLE(x86cpu, ss_smi_ids);
-#endif
 
 /**
  * speedstep_init - initializes the SpeedStep CPUFreq driver
diff --git a/drivers/cpufreq/speedstep-smi.c b/drivers/cpufreq/speedstep-smi.c
index eeb31bc21cc9..0ce9d4b6dfcc 100644
--- a/drivers/cpufreq/speedstep-smi.c
+++ b/drivers/cpufreq/speedstep-smi.c
@@ -299,15 +299,11 @@ static struct cpufreq_driver speedstep_driver = {
 };
 
 static const struct x86_cpu_id ss_smi_ids[] = {
-	{ X86_VENDOR_INTEL, 6, 0xb, },
-	{ X86_VENDOR_INTEL, 6, 0x8, },
-	{ X86_VENDOR_INTEL, 15, 2 },
+	X86_MATCH_VENDOR_FAM_MODEL(INTEL,  6, 0x8, 0),
+	X86_MATCH_VENDOR_FAM_MODEL(INTEL,  6, 0xb, 0),
+	X86_MATCH_VENDOR_FAM_MODEL(INTEL, 15, 0x2, 0),
 	{}
 };
-#if 0
-/* Not auto loaded currently */
-MODULE_DEVICE_TABLE(x86cpu, ss_smi_ids);
-#endif
 
 /**
  * speedstep_init - initializes the SpeedStep CPUFreq driver
diff --git a/drivers/crypto/padlock-aes.c b/drivers/crypto/padlock-aes.c
index 594d6b1695d5..62c6fe88b212 100644
--- a/drivers/crypto/padlock-aes.c
+++ b/drivers/crypto/padlock-aes.c
@@ -474,7 +474,7 @@ static struct skcipher_alg cbc_aes_alg = {
 };
 
 static const struct x86_cpu_id padlock_cpu_id[] = {
-	X86_FEATURE_MATCH(X86_FEATURE_XCRYPT),
+	X86_MATCH_FEATURE(X86_FEATURE_XCRYPT, NULL),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, padlock_cpu_id);
diff --git a/drivers/crypto/padlock-sha.c b/drivers/crypto/padlock-sha.c
index c826abe79e79..a697a4a3f2d0 100644
--- a/drivers/crypto/padlock-sha.c
+++ b/drivers/crypto/padlock-sha.c
@@ -490,7 +490,7 @@ static struct shash_alg sha256_alg_nano = {
 };
 
 static const struct x86_cpu_id padlock_sha_ids[] = {
-	X86_FEATURE_MATCH(X86_FEATURE_PHE),
+	X86_MATCH_FEATURE(X86_FEATURE_PHE, NULL),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, padlock_sha_ids);
diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index 9fbad908a854..f91f3bc1e0b2 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -3626,13 +3626,13 @@ static void setup_pci_device(void)
 }
 
 static const struct x86_cpu_id amd64_cpuids[] = {
-	{ X86_VENDOR_AMD, 0xF,	X86_MODEL_ANY,	X86_FEATURE_ANY, 0 },
-	{ X86_VENDOR_AMD, 0x10, X86_MODEL_ANY,	X86_FEATURE_ANY, 0 },
-	{ X86_VENDOR_AMD, 0x15, X86_MODEL_ANY,	X86_FEATURE_ANY, 0 },
-	{ X86_VENDOR_AMD, 0x16, X86_MODEL_ANY,	X86_FEATURE_ANY, 0 },
-	{ X86_VENDOR_AMD, 0x17, X86_MODEL_ANY,	X86_FEATURE_ANY, 0 },
-	{ X86_VENDOR_HYGON, 0x18, X86_MODEL_ANY, X86_FEATURE_ANY, 0 },
-	{ X86_VENDOR_AMD, 0x19, X86_MODEL_ANY,	X86_FEATURE_ANY, 0 },
+	X86_MATCH_VENDOR_FAM(AMD,	0x0F, NULL),
+	X86_MATCH_VENDOR_FAM(AMD,	0x10, NULL),
+	X86_MATCH_VENDOR_FAM(AMD,	0x15, NULL),
+	X86_MATCH_VENDOR_FAM(AMD,	0x16, NULL),
+	X86_MATCH_VENDOR_FAM(AMD,	0x17, NULL),
+	X86_MATCH_VENDOR_FAM(HYGON,	0x18, NULL),
+	X86_MATCH_VENDOR_FAM(AMD,	0x19, NULL),
 	{ }
 };
 MODULE_DEVICE_TABLE(x86cpu, amd64_cpuids);
diff --git a/drivers/edac/i10nm_base.c b/drivers/edac/i10nm_base.c
index 059eccf0582b..df08de963d10 100644
--- a/drivers/edac/i10nm_base.c
+++ b/drivers/edac/i10nm_base.c
@@ -123,10 +123,10 @@ static int i10nm_get_all_munits(void)
 }
 
 static const struct x86_cpu_id i10nm_cpuids[] = {
-	{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_TREMONT_D, 0, 0 },
-	{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ICELAKE_X, 0, 0 },
-	{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ICELAKE_D, 0, 0 },
-	{ }
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D,	NULL),
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X,		NULL),
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D,		NULL),
+	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, i10nm_cpuids);
 
diff --git a/drivers/edac/pnd2_edac.c b/drivers/edac/pnd2_edac.c
index 933f7722b893..bc47328eb485 100644
--- a/drivers/edac/pnd2_edac.c
+++ b/drivers/edac/pnd2_edac.c
@@ -1537,8 +1537,8 @@ static struct dunit_ops dnv_ops = {
 };
 
 static const struct x86_cpu_id pnd2_cpuids[] = {
-	{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_GOLDMONT, 0, (kernel_ulong_t)&apl_ops },
-	{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_GOLDMONT_D, 0, (kernel_ulong_t)&dnv_ops },
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT,	&apl_ops),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_D,	&dnv_ops),
 	{ }
 };
 MODULE_DEVICE_TABLE(x86cpu, pnd2_cpuids);
diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
index 4957e8ee1879..7d51c82be62b 100644
--- a/drivers/edac/sb_edac.c
+++ b/drivers/edac/sb_edac.c
@@ -3420,13 +3420,13 @@ fail0:
 }
 
 static const struct x86_cpu_id sbridge_cpuids[] = {
-	INTEL_CPU_FAM6(SANDYBRIDGE_X,	  pci_dev_descr_sbridge_table),
-	INTEL_CPU_FAM6(IVYBRIDGE_X,	  pci_dev_descr_ibridge_table),
-	INTEL_CPU_FAM6(HASWELL_X,	  pci_dev_descr_haswell_table),
-	INTEL_CPU_FAM6(BROADWELL_X,	  pci_dev_descr_broadwell_table),
-	INTEL_CPU_FAM6(BROADWELL_D,	  pci_dev_descr_broadwell_table),
-	INTEL_CPU_FAM6(XEON_PHI_KNL,	  pci_dev_descr_knl_table),
-	INTEL_CPU_FAM6(XEON_PHI_KNM,	  pci_dev_descr_knl_table),
+	X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE_X, &pci_dev_descr_sbridge_table),
+	X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE_X,	  &pci_dev_descr_ibridge_table),
+	X86_MATCH_INTEL_FAM6_MODEL(HASWELL_X,	  &pci_dev_descr_haswell_table),
+	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_X,	  &pci_dev_descr_broadwell_table),
+	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_D,	  &pci_dev_descr_broadwell_table),
+	X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNL,  &pci_dev_descr_knl_table),
+	X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNM,  &pci_dev_descr_knl_table),
 	{ }
 };
 MODULE_DEVICE_TABLE(x86cpu, sbridge_cpuids);
diff --git a/drivers/edac/skx_base.c b/drivers/edac/skx_base.c
index 83545b4facb7..46a3a3440f5e 100644
--- a/drivers/edac/skx_base.c
+++ b/drivers/edac/skx_base.c
@@ -158,7 +158,7 @@ fail:
 }
 
 static const struct x86_cpu_id skx_cpuids[] = {
-	{ X86_VENDOR_INTEL, 6, INTEL_FAM6_SKYLAKE_X, 0, 0 },
+	X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X,	NULL),
 	{ }
 };
 MODULE_DEVICE_TABLE(x86cpu, skx_cpuids);
diff --git a/drivers/extcon/extcon-axp288.c b/drivers/extcon/extcon-axp288.c
index a7f216191493..34b7afffac28 100644
--- a/drivers/extcon/extcon-axp288.c
+++ b/drivers/extcon/extcon-axp288.c
@@ -107,7 +107,7 @@ struct axp288_extcon_info {
 };
 
 static const struct x86_cpu_id cherry_trail_cpu_ids[] = {
-	{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_AIRMONT, X86_FEATURE_ANY },
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_AIRMONT,	NULL),
 	{}
 };
 
diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
index d855c78fb8be..bb9211215a68 100644
--- a/drivers/hwmon/coretemp.c
+++ b/drivers/hwmon/coretemp.c
@@ -709,7 +709,7 @@ static int coretemp_cpu_offline(unsigned int cpu)
 	return 0;
 }
 static const struct x86_cpu_id __initconst coretemp_ids[] = {
-	{ X86_VENDOR_INTEL, X86_FAMILY_ANY, X86_MODEL_ANY, X86_FEATURE_DTHERM },
+	X86_MATCH_VENDOR_FEATURE(INTEL, X86_FEATURE_DTHERM, NULL),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, coretemp_ids);
diff --git a/drivers/hwmon/via-cputemp.c b/drivers/hwmon/via-cputemp.c
index 8264e849e588..e5d18dac8ee7 100644
--- a/drivers/hwmon/via-cputemp.c
+++ b/drivers/hwmon/via-cputemp.c
@@ -270,10 +270,10 @@ static int via_cputemp_down_prep(unsigned int cpu)
 }
 
 static const struct x86_cpu_id __initconst cputemp_ids[] = {
-	{ X86_VENDOR_CENTAUR, 6, 0xa, }, /* C7 A */
-	{ X86_VENDOR_CENTAUR, 6, 0xd, }, /* C7 D */
-	{ X86_VENDOR_CENTAUR, 6, 0xf, }, /* Nano */
-	{ X86_VENDOR_CENTAUR, 7, X86_MODEL_ANY, },
+	X86_MATCH_VENDOR_FAM_MODEL(CENTAUR, 6, X86_CENTAUR_FAM6_C7_A,	NULL),
+	X86_MATCH_VENDOR_FAM_MODEL(CENTAUR, 6, X86_CENTAUR_FAM6_C7_D,	NULL),
+	X86_MATCH_VENDOR_FAM_MODEL(CENTAUR, 6, X86_CENTAUR_FAM6_NANO,	NULL),
+	X86_MATCH_VENDOR_FAM_MODEL(CENTAUR, 7, X86_MODEL_ANY,		NULL),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, cputemp_ids);
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 65b84d5dc457..f4495841bf68 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -1079,51 +1079,48 @@ static const struct idle_cpu idle_cpu_dnv __initconst = {
 };
 
 static const struct x86_cpu_id intel_idle_ids[] __initconst = {
-	INTEL_CPU_FAM6(NEHALEM_EP,		idle_cpu_nhx),
-	INTEL_CPU_FAM6(NEHALEM,			idle_cpu_nehalem),
-	INTEL_CPU_FAM6(NEHALEM_G,		idle_cpu_nehalem),
-	INTEL_CPU_FAM6(WESTMERE,		idle_cpu_nehalem),
-	INTEL_CPU_FAM6(WESTMERE_EP,		idle_cpu_nhx),
-	INTEL_CPU_FAM6(NEHALEM_EX,		idle_cpu_nhx),
-	INTEL_CPU_FAM6(ATOM_BONNELL,		idle_cpu_atom),
-	INTEL_CPU_FAM6(ATOM_BONNELL_MID,	idle_cpu_lincroft),
-	INTEL_CPU_FAM6(WESTMERE_EX,		idle_cpu_nhx),
-	INTEL_CPU_FAM6(SANDYBRIDGE,		idle_cpu_snb),
-	INTEL_CPU_FAM6(SANDYBRIDGE_X,		idle_cpu_snx),
-	INTEL_CPU_FAM6(ATOM_SALTWELL,		idle_cpu_atom),
-	INTEL_CPU_FAM6(ATOM_SILVERMONT,		idle_cpu_byt),
-	INTEL_CPU_FAM6(ATOM_SILVERMONT_MID,	idle_cpu_tangier),
-	INTEL_CPU_FAM6(ATOM_AIRMONT,		idle_cpu_cht),
-	INTEL_CPU_FAM6(IVYBRIDGE,		idle_cpu_ivb),
-	INTEL_CPU_FAM6(IVYBRIDGE_X,		idle_cpu_ivt),
-	INTEL_CPU_FAM6(HASWELL,			idle_cpu_hsw),
-	INTEL_CPU_FAM6(HASWELL_X,		idle_cpu_hsx),
-	INTEL_CPU_FAM6(HASWELL_L,		idle_cpu_hsw),
-	INTEL_CPU_FAM6(HASWELL_G,		idle_cpu_hsw),
-	INTEL_CPU_FAM6(ATOM_SILVERMONT_D,	idle_cpu_avn),
-	INTEL_CPU_FAM6(BROADWELL,		idle_cpu_bdw),
-	INTEL_CPU_FAM6(BROADWELL_G,		idle_cpu_bdw),
-	INTEL_CPU_FAM6(BROADWELL_X,		idle_cpu_bdx),
-	INTEL_CPU_FAM6(BROADWELL_D,		idle_cpu_bdx),
-	INTEL_CPU_FAM6(SKYLAKE_L,		idle_cpu_skl),
-	INTEL_CPU_FAM6(SKYLAKE,			idle_cpu_skl),
-	INTEL_CPU_FAM6(KABYLAKE_L,		idle_cpu_skl),
-	INTEL_CPU_FAM6(KABYLAKE,		idle_cpu_skl),
-	INTEL_CPU_FAM6(SKYLAKE_X,		idle_cpu_skx),
-	INTEL_CPU_FAM6(XEON_PHI_KNL,		idle_cpu_knl),
-	INTEL_CPU_FAM6(XEON_PHI_KNM,		idle_cpu_knl),
-	INTEL_CPU_FAM6(ATOM_GOLDMONT,		idle_cpu_bxt),
-	INTEL_CPU_FAM6(ATOM_GOLDMONT_PLUS,	idle_cpu_bxt),
-	INTEL_CPU_FAM6(ATOM_GOLDMONT_D,		idle_cpu_dnv),
-	INTEL_CPU_FAM6(ATOM_TREMONT_D,		idle_cpu_dnv),
+	X86_MATCH_INTEL_FAM6_MODEL(NEHALEM_EP,		&idle_cpu_nhx),
+	X86_MATCH_INTEL_FAM6_MODEL(NEHALEM,		&idle_cpu_nehalem),
+	X86_MATCH_INTEL_FAM6_MODEL(NEHALEM_G,		&idle_cpu_nehalem),
+	X86_MATCH_INTEL_FAM6_MODEL(WESTMERE,		&idle_cpu_nehalem),
+	X86_MATCH_INTEL_FAM6_MODEL(WESTMERE_EP,		&idle_cpu_nhx),
+	X86_MATCH_INTEL_FAM6_MODEL(NEHALEM_EX,		&idle_cpu_nhx),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_BONNELL,	&idle_cpu_atom),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_BONNELL_MID,	&idle_cpu_lincroft),
+	X86_MATCH_INTEL_FAM6_MODEL(WESTMERE_EX,		&idle_cpu_nhx),
+	X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE,		&idle_cpu_snb),
+	X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE_X,	&idle_cpu_snx),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_SALTWELL,	&idle_cpu_atom),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT,	&idle_cpu_byt),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT_MID,	&idle_cpu_tangier),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_AIRMONT,	&idle_cpu_cht),
+	X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE,		&idle_cpu_ivb),
+	X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE_X,		&idle_cpu_ivt),
+	X86_MATCH_INTEL_FAM6_MODEL(HASWELL,		&idle_cpu_hsw),
+	X86_MATCH_INTEL_FAM6_MODEL(HASWELL_X,		&idle_cpu_hsx),
+	X86_MATCH_INTEL_FAM6_MODEL(HASWELL_L,		&idle_cpu_hsw),
+	X86_MATCH_INTEL_FAM6_MODEL(HASWELL_G,		&idle_cpu_hsw),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT_D,	&idle_cpu_avn),
+	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL,		&idle_cpu_bdw),
+	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_G,		&idle_cpu_bdw),
+	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_X,		&idle_cpu_bdx),
+	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_D,		&idle_cpu_bdx),
+	X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_L,		&idle_cpu_skl),
+	X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE,		&idle_cpu_skl),
+	X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE_L,		&idle_cpu_skl),
+	X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE,		&idle_cpu_skl),
+	X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X,		&idle_cpu_skx),
+	X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNL,	&idle_cpu_knl),
+	X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNM,	&idle_cpu_knl),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT,	&idle_cpu_bxt),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_PLUS,	&idle_cpu_bxt),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_D,	&idle_cpu_dnv),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D,	&idle_cpu_dnv),
 	{}
 };
 
-#define INTEL_CPU_FAM6_MWAIT \
-	{ X86_VENDOR_INTEL, 6, X86_MODEL_ANY, X86_FEATURE_MWAIT, 0 }
-
 static const struct x86_cpu_id intel_mwait_ids[] __initconst = {
-	INTEL_CPU_FAM6_MWAIT,
+	X86_MATCH_VENDOR_FAM_FEATURE(INTEL, 6, X86_FEATURE_MWAIT, NULL),
 	{}
 };
 
diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c
index 2a2173d953f5..7e7d0d1aa36a 100644
--- a/drivers/mmc/host/sdhci-acpi.c
+++ b/drivers/mmc/host/sdhci-acpi.c
@@ -242,7 +242,7 @@ static const struct sdhci_acpi_chip sdhci_acpi_chip_int = {
 static bool sdhci_acpi_byt(void)
 {
 	static const struct x86_cpu_id byt[] = {
-		{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT },
+		X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT, NULL),
 		{}
 	};
 
@@ -252,7 +252,7 @@ static bool sdhci_acpi_byt(void)
 static bool sdhci_acpi_cht(void)
 {
 	static const struct x86_cpu_id cht[] = {
-		{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_AIRMONT },
+		X86_MATCH_INTEL_FAM6_MODEL(ATOM_AIRMONT, NULL),
 		{}
 	};
 
diff --git a/drivers/pci/pci-mid.c b/drivers/pci/pci-mid.c
index 30fbe2ea6eab..aafd58da3a89 100644
--- a/drivers/pci/pci-mid.c
+++ b/drivers/pci/pci-mid.c
@@ -55,15 +55,13 @@ static const struct pci_platform_pm_ops mid_pci_platform_pm = {
 	.need_resume	= mid_pci_need_resume,
 };
 
-#define ICPU(model)	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, }
-
 /*
  * This table should be in sync with the one in
  * arch/x86/platform/intel-mid/pwr.c.
  */
 static const struct x86_cpu_id lpss_cpu_ids[] = {
-	ICPU(INTEL_FAM6_ATOM_SALTWELL_MID),
-	ICPU(INTEL_FAM6_ATOM_SILVERMONT_MID),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_SALTWELL_MID, NULL),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT_MID, NULL),
 	{}
 };
 
diff --git a/drivers/platform/x86/intel-uncore-frequency.c b/drivers/platform/x86/intel-uncore-frequency.c
index 2b1a0734c3f8..859272075a8f 100644
--- a/drivers/platform/x86/intel-uncore-frequency.c
+++ b/drivers/platform/x86/intel-uncore-frequency.c
@@ -358,15 +358,13 @@ static struct notifier_block uncore_pm_nb = {
 	.notifier_call = uncore_pm_notify,
 };
 
-#define ICPU(model)     { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, }
-
 static const struct x86_cpu_id intel_uncore_cpu_ids[] = {
-	ICPU(INTEL_FAM6_BROADWELL_G),
-	ICPU(INTEL_FAM6_BROADWELL_X),
-	ICPU(INTEL_FAM6_BROADWELL_D),
-	ICPU(INTEL_FAM6_SKYLAKE_X),
-	ICPU(INTEL_FAM6_ICELAKE_X),
-	ICPU(INTEL_FAM6_ICELAKE_D),
+	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_G,	NULL),
+	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_X,	NULL),
+	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_D,	NULL),
+	X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X,	NULL),
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X,	NULL),
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D,	NULL),
 	{}
 };
 
diff --git a/drivers/platform/x86/intel_int0002_vgpio.c b/drivers/platform/x86/intel_int0002_vgpio.c
index f14e2c5f9da5..7b23efc46a43 100644
--- a/drivers/platform/x86/intel_int0002_vgpio.c
+++ b/drivers/platform/x86/intel_int0002_vgpio.c
@@ -148,8 +148,8 @@ static struct irq_chip int0002_cht_irqchip = {
 };
 
 static const struct x86_cpu_id int0002_cpu_ids[] = {
-	INTEL_CPU_FAM6(ATOM_SILVERMONT, int0002_byt_irqchip),	/* Valleyview, Bay Trail  */
-	INTEL_CPU_FAM6(ATOM_AIRMONT, int0002_cht_irqchip),	/* Braswell, Cherry Trail */
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT,	&int0002_byt_irqchip),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_AIRMONT,	&int0002_cht_irqchip),
 	{}
 };
 
diff --git a/drivers/platform/x86/intel_mid_powerbtn.c b/drivers/platform/x86/intel_mid_powerbtn.c
index 6f436836fe50..9c9f209c8a33 100644
--- a/drivers/platform/x86/intel_mid_powerbtn.c
+++ b/drivers/platform/x86/intel_mid_powerbtn.c
@@ -113,8 +113,8 @@ static const struct mid_pb_ddata mrfld_ddata = {
 };
 
 static const struct x86_cpu_id mid_pb_cpu_ids[] = {
-	INTEL_CPU_FAM6(ATOM_SALTWELL_MID,	mfld_ddata),
-	INTEL_CPU_FAM6(ATOM_SILVERMONT_MID,	mrfld_ddata),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_SALTWELL_MID,	&mfld_ddata),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT_MID,	&mrfld_ddata),
 	{}
 };
 
diff --git a/drivers/platform/x86/intel_pmc_core.c b/drivers/platform/x86/intel_pmc_core.c
index 144faa8bad3d..3df33ff50faa 100644
--- a/drivers/platform/x86/intel_pmc_core.c
+++ b/drivers/platform/x86/intel_pmc_core.c
@@ -871,18 +871,18 @@ static inline void pmc_core_dbgfs_unregister(struct pmc_dev *pmcdev)
 #endif /* CONFIG_DEBUG_FS */
 
 static const struct x86_cpu_id intel_pmc_core_ids[] = {
-	INTEL_CPU_FAM6(SKYLAKE_L, spt_reg_map),
-	INTEL_CPU_FAM6(SKYLAKE, spt_reg_map),
-	INTEL_CPU_FAM6(KABYLAKE_L, spt_reg_map),
-	INTEL_CPU_FAM6(KABYLAKE, spt_reg_map),
-	INTEL_CPU_FAM6(CANNONLAKE_L, cnp_reg_map),
-	INTEL_CPU_FAM6(ICELAKE_L, icl_reg_map),
-	INTEL_CPU_FAM6(ICELAKE_NNPI, icl_reg_map),
-	INTEL_CPU_FAM6(COMETLAKE, cnp_reg_map),
-	INTEL_CPU_FAM6(COMETLAKE_L, cnp_reg_map),
-	INTEL_CPU_FAM6(TIGERLAKE_L, tgl_reg_map),
-	INTEL_CPU_FAM6(TIGERLAKE, tgl_reg_map),
-	INTEL_CPU_FAM6(ATOM_TREMONT, tgl_reg_map),
+	X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_L,		&spt_reg_map),
+	X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE,		&spt_reg_map),
+	X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE_L,		&spt_reg_map),
+	X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE,		&spt_reg_map),
+	X86_MATCH_INTEL_FAM6_MODEL(CANNONLAKE_L,	&cnp_reg_map),
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L,		&icl_reg_map),
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_NNPI,	&icl_reg_map),
+	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE,		&cnp_reg_map),
+	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE_L,		&cnp_reg_map),
+	X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L,		&tgl_reg_map),
+	X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE,		&tgl_reg_map),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT,	&tgl_reg_map),
 	{}
 };
 
diff --git a/drivers/platform/x86/intel_pmc_core_pltdrv.c b/drivers/platform/x86/intel_pmc_core_pltdrv.c
index e1266f5c6359..731281855cc8 100644
--- a/drivers/platform/x86/intel_pmc_core_pltdrv.c
+++ b/drivers/platform/x86/intel_pmc_core_pltdrv.c
@@ -38,14 +38,14 @@ static struct platform_device pmc_core_device = {
  * other list may grow, but this list should not.
  */
 static const struct x86_cpu_id intel_pmc_core_platform_ids[] = {
-	INTEL_CPU_FAM6(SKYLAKE_L, pmc_core_device),
-	INTEL_CPU_FAM6(SKYLAKE, pmc_core_device),
-	INTEL_CPU_FAM6(KABYLAKE_L, pmc_core_device),
-	INTEL_CPU_FAM6(KABYLAKE, pmc_core_device),
-	INTEL_CPU_FAM6(CANNONLAKE_L, pmc_core_device),
-	INTEL_CPU_FAM6(ICELAKE_L, pmc_core_device),
-	INTEL_CPU_FAM6(COMETLAKE, pmc_core_device),
-	INTEL_CPU_FAM6(COMETLAKE_L, pmc_core_device),
+	X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_L,		&pmc_core_device),
+	X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE,		&pmc_core_device),
+	X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE_L,		&pmc_core_device),
+	X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE,		&pmc_core_device),
+	X86_MATCH_INTEL_FAM6_MODEL(CANNONLAKE_L,	&pmc_core_device),
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L,		&pmc_core_device),
+	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE,		&pmc_core_device),
+	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE_L,		&pmc_core_device),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_pmc_core_platform_ids);
diff --git a/drivers/platform/x86/intel_speed_select_if/isst_if_mbox_msr.c b/drivers/platform/x86/intel_speed_select_if/isst_if_mbox_msr.c
index 89b042aecef3..1b6eab071068 100644
--- a/drivers/platform/x86/intel_speed_select_if/isst_if_mbox_msr.c
+++ b/drivers/platform/x86/intel_speed_select_if/isst_if_mbox_msr.c
@@ -160,10 +160,8 @@ static struct notifier_block isst_pm_nb = {
 	.notifier_call = isst_pm_notify,
 };
 
-#define ICPU(model)     { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, }
-
 static const struct x86_cpu_id isst_if_cpu_ids[] = {
-	ICPU(INTEL_FAM6_SKYLAKE_X),
+	X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X, NULL),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, isst_if_cpu_ids);
diff --git a/drivers/platform/x86/intel_telemetry_debugfs.c b/drivers/platform/x86/intel_telemetry_debugfs.c
index 8e3fb55ac1ae..8a53d3b485b3 100644
--- a/drivers/platform/x86/intel_telemetry_debugfs.c
+++ b/drivers/platform/x86/intel_telemetry_debugfs.c
@@ -308,11 +308,10 @@ static struct telemetry_debugfs_conf telem_apl_debugfs_conf = {
 };
 
 static const struct x86_cpu_id telemetry_debugfs_cpu_ids[] = {
-	INTEL_CPU_FAM6(ATOM_GOLDMONT, telem_apl_debugfs_conf),
-	INTEL_CPU_FAM6(ATOM_GOLDMONT_PLUS, telem_apl_debugfs_conf),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT,	&telem_apl_debugfs_conf),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_PLUS,	&telem_apl_debugfs_conf),
 	{}
 };
-
 MODULE_DEVICE_TABLE(x86cpu, telemetry_debugfs_cpu_ids);
 
 static int telemetry_debugfs_check_evts(void)
diff --git a/drivers/platform/x86/intel_telemetry_pltdrv.c b/drivers/platform/x86/intel_telemetry_pltdrv.c
index c4c742bb23cf..987a24e3344e 100644
--- a/drivers/platform/x86/intel_telemetry_pltdrv.c
+++ b/drivers/platform/x86/intel_telemetry_pltdrv.c
@@ -67,9 +67,6 @@
 #define TELEM_CLEAR_VERBOSITY_BITS(x)	((x) &= ~(BIT(27) | BIT(28)))
 #define TELEM_SET_VERBOSITY_BITS(x, y)	((x) |= ((y) << 27))
 
-#define TELEM_CPU(model, data) \
-	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&data }
-
 enum telemetry_action {
 	TELEM_UPDATE = 0,
 	TELEM_ADD,
@@ -183,8 +180,8 @@ static struct telemetry_plt_config telem_glk_config = {
 };
 
 static const struct x86_cpu_id telemetry_cpu_ids[] = {
-	TELEM_CPU(INTEL_FAM6_ATOM_GOLDMONT, telem_apl_config),
-	TELEM_CPU(INTEL_FAM6_ATOM_GOLDMONT_PLUS, telem_glk_config),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT,	&telem_apl_config),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_PLUS,	&telem_glk_config),
 	{}
 };
 
diff --git a/drivers/platform/x86/intel_turbo_max_3.c b/drivers/platform/x86/intel_turbo_max_3.c
index 7b9cc841ab65..892140b62898 100644
--- a/drivers/platform/x86/intel_turbo_max_3.c
+++ b/drivers/platform/x86/intel_turbo_max_3.c
@@ -113,11 +113,9 @@ static int itmt_legacy_cpu_online(unsigned int cpu)
 	return 0;
 }
 
-#define ICPU(model)     { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, }
-
 static const struct x86_cpu_id itmt_legacy_cpu_ids[] = {
-	ICPU(INTEL_FAM6_BROADWELL_X),
-	ICPU(INTEL_FAM6_SKYLAKE_X),
+	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_X,	NULL),
+	X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X,	NULL),
 	{}
 };
 
diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c
index 73257cf107d9..eb328655bc01 100644
--- a/drivers/powercap/intel_rapl_common.c
+++ b/drivers/powercap/intel_rapl_common.c
@@ -951,52 +951,51 @@ static const struct rapl_defaults rapl_defaults_cht = {
 };
 
 static const struct x86_cpu_id rapl_ids[] __initconst = {
-	INTEL_CPU_FAM6(SANDYBRIDGE, rapl_defaults_core),
-	INTEL_CPU_FAM6(SANDYBRIDGE_X, rapl_defaults_core),
-
-	INTEL_CPU_FAM6(IVYBRIDGE, rapl_defaults_core),
-	INTEL_CPU_FAM6(IVYBRIDGE_X, rapl_defaults_core),
-
-	INTEL_CPU_FAM6(HASWELL, rapl_defaults_core),
-	INTEL_CPU_FAM6(HASWELL_L, rapl_defaults_core),
-	INTEL_CPU_FAM6(HASWELL_G, rapl_defaults_core),
-	INTEL_CPU_FAM6(HASWELL_X, rapl_defaults_hsw_server),
-
-	INTEL_CPU_FAM6(BROADWELL, rapl_defaults_core),
-	INTEL_CPU_FAM6(BROADWELL_G, rapl_defaults_core),
-	INTEL_CPU_FAM6(BROADWELL_D, rapl_defaults_core),
-	INTEL_CPU_FAM6(BROADWELL_X, rapl_defaults_hsw_server),
-
-	INTEL_CPU_FAM6(SKYLAKE, rapl_defaults_core),
-	INTEL_CPU_FAM6(SKYLAKE_L, rapl_defaults_core),
-	INTEL_CPU_FAM6(SKYLAKE_X, rapl_defaults_hsw_server),
-	INTEL_CPU_FAM6(KABYLAKE_L, rapl_defaults_core),
-	INTEL_CPU_FAM6(KABYLAKE, rapl_defaults_core),
-	INTEL_CPU_FAM6(CANNONLAKE_L, rapl_defaults_core),
-	INTEL_CPU_FAM6(ICELAKE_L, rapl_defaults_core),
-	INTEL_CPU_FAM6(ICELAKE, rapl_defaults_core),
-	INTEL_CPU_FAM6(ICELAKE_NNPI, rapl_defaults_core),
-	INTEL_CPU_FAM6(ICELAKE_X, rapl_defaults_hsw_server),
-	INTEL_CPU_FAM6(ICELAKE_D, rapl_defaults_hsw_server),
-	INTEL_CPU_FAM6(COMETLAKE_L, rapl_defaults_core),
-	INTEL_CPU_FAM6(COMETLAKE, rapl_defaults_core),
-	INTEL_CPU_FAM6(TIGERLAKE_L, rapl_defaults_core),
-
-	INTEL_CPU_FAM6(ATOM_SILVERMONT, rapl_defaults_byt),
-	INTEL_CPU_FAM6(ATOM_AIRMONT, rapl_defaults_cht),
-	INTEL_CPU_FAM6(ATOM_SILVERMONT_MID, rapl_defaults_tng),
-	INTEL_CPU_FAM6(ATOM_AIRMONT_MID, rapl_defaults_ann),
-	INTEL_CPU_FAM6(ATOM_GOLDMONT, rapl_defaults_core),
-	INTEL_CPU_FAM6(ATOM_GOLDMONT_PLUS, rapl_defaults_core),
-	INTEL_CPU_FAM6(ATOM_GOLDMONT_D, rapl_defaults_core),
-	INTEL_CPU_FAM6(ATOM_TREMONT_D, rapl_defaults_core),
-	INTEL_CPU_FAM6(ATOM_TREMONT_L, rapl_defaults_core),
-
-	INTEL_CPU_FAM6(XEON_PHI_KNL, rapl_defaults_hsw_server),
-	INTEL_CPU_FAM6(XEON_PHI_KNM, rapl_defaults_hsw_server),
+	X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE,		&rapl_defaults_core),
+	X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE_X,	&rapl_defaults_core),
+
+	X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE,		&rapl_defaults_core),
+	X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE_X,		&rapl_defaults_core),
+
+	X86_MATCH_INTEL_FAM6_MODEL(HASWELL,		&rapl_defaults_core),
+	X86_MATCH_INTEL_FAM6_MODEL(HASWELL_L,		&rapl_defaults_core),
+	X86_MATCH_INTEL_FAM6_MODEL(HASWELL_G,		&rapl_defaults_core),
+	X86_MATCH_INTEL_FAM6_MODEL(HASWELL_X,		&rapl_defaults_hsw_server),
+
+	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL,		&rapl_defaults_core),
+	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_G,		&rapl_defaults_core),
+	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_D,		&rapl_defaults_core),
+	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_X,		&rapl_defaults_hsw_server),
+
+	X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE,		&rapl_defaults_core),
+	X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_L,		&rapl_defaults_core),
+	X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X,		&rapl_defaults_hsw_server),
+	X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE_L,		&rapl_defaults_core),
+	X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE,		&rapl_defaults_core),
+	X86_MATCH_INTEL_FAM6_MODEL(CANNONLAKE_L,	&rapl_defaults_core),
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L,		&rapl_defaults_core),
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE,		&rapl_defaults_core),
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_NNPI,	&rapl_defaults_core),
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X,		&rapl_defaults_hsw_server),
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D,		&rapl_defaults_hsw_server),
+	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE_L,		&rapl_defaults_core),
+	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE,		&rapl_defaults_core),
+	X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L,		&rapl_defaults_core),
+
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT,	&rapl_defaults_byt),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_AIRMONT,	&rapl_defaults_cht),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT_MID,	&rapl_defaults_tng),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_AIRMONT_MID,	&rapl_defaults_ann),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT,	&rapl_defaults_core),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_PLUS,	&rapl_defaults_core),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_D,	&rapl_defaults_core),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D,	&rapl_defaults_core),
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_L,	&rapl_defaults_core),
+
+	X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNL,	&rapl_defaults_hsw_server),
+	X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNM,	&rapl_defaults_hsw_server),
 	{}
 };
-
 MODULE_DEVICE_TABLE(x86cpu, rapl_ids);
 
 /* Read once for all raw primitive data for domains */
diff --git a/drivers/thermal/intel/intel_powerclamp.c b/drivers/thermal/intel/intel_powerclamp.c
index 53216dcbe173..f74b2473440d 100644
--- a/drivers/thermal/intel/intel_powerclamp.c
+++ b/drivers/thermal/intel/intel_powerclamp.c
@@ -651,7 +651,7 @@ static struct thermal_cooling_device_ops powerclamp_cooling_ops = {
 };
 
 static const struct x86_cpu_id __initconst intel_powerclamp_ids[] = {
-	{ X86_VENDOR_INTEL, X86_FAMILY_ANY, X86_MODEL_ANY, X86_FEATURE_MWAIT },
+	X86_MATCH_VENDOR_FEATURE(INTEL, X86_FEATURE_MWAIT, NULL),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_powerclamp_ids);
diff --git a/drivers/thermal/intel/intel_quark_dts_thermal.c b/drivers/thermal/intel/intel_quark_dts_thermal.c
index 5d33b350da1c..d704fc104cfd 100644
--- a/drivers/thermal/intel/intel_quark_dts_thermal.c
+++ b/drivers/thermal/intel/intel_quark_dts_thermal.c
@@ -64,9 +64,6 @@
 #include <asm/cpu_device_id.h>
 #include <asm/iosf_mbi.h>
 
-#define X86_FAMILY_QUARK	0x5
-#define X86_MODEL_QUARK_X1000	0x9
-
 /* DTS reset is programmed via QRK_MBI_UNIT_SOC */
 #define QRK_DTS_REG_OFFSET_RESET	0x34
 #define QRK_DTS_RESET_BIT		BIT(0)
@@ -433,7 +430,7 @@ err_ret:
 }
 
 static const struct x86_cpu_id qrk_thermal_ids[] __initconst  = {
-	{ X86_VENDOR_INTEL, X86_FAMILY_QUARK, X86_MODEL_QUARK_X1000 },
+	X86_MATCH_VENDOR_FAM_MODEL(INTEL, 5, INTEL_FAM5_QUARK_X1000, NULL),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, qrk_thermal_ids);
diff --git a/drivers/thermal/intel/intel_soc_dts_thermal.c b/drivers/thermal/intel/intel_soc_dts_thermal.c
index f4be9c14e5d9..92e5c19d03f6 100644
--- a/drivers/thermal/intel/intel_soc_dts_thermal.c
+++ b/drivers/thermal/intel/intel_soc_dts_thermal.c
@@ -36,8 +36,7 @@ static irqreturn_t soc_irq_thread_fn(int irq, void *dev_data)
 }
 
 static const struct x86_cpu_id soc_thermal_ids[] = {
-	{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT, 0,
-		BYT_SOC_DTS_APIC_IRQ},
+	X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT, BYT_SOC_DTS_APIC_IRQ),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, soc_thermal_ids);
diff --git a/drivers/thermal/intel/x86_pkg_temp_thermal.c b/drivers/thermal/intel/x86_pkg_temp_thermal.c
index e18758a8e911..a006b9fd1d72 100644
--- a/drivers/thermal/intel/x86_pkg_temp_thermal.c
+++ b/drivers/thermal/intel/x86_pkg_temp_thermal.c
@@ -478,7 +478,7 @@ static int pkg_thermal_cpu_online(unsigned int cpu)
 }
 
 static const struct x86_cpu_id __initconst pkg_temp_thermal_ids[] = {
-	{ X86_VENDOR_INTEL, X86_FAMILY_ANY, X86_MODEL_ANY, X86_FEATURE_PTS },
+	X86_MATCH_VENDOR_FEATURE(INTEL, X86_FEATURE_PTS, NULL),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, pkg_temp_thermal_ids);
diff --git a/include/linux/min_heap.h b/include/linux/min_heap.h
new file mode 100644
index 000000000000..44077837385f
--- /dev/null
+++ b/include/linux/min_heap.h
@@ -0,0 +1,134 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_MIN_HEAP_H
+#define _LINUX_MIN_HEAP_H
+
+#include <linux/bug.h>
+#include <linux/string.h>
+#include <linux/types.h>
+
+/**
+ * struct min_heap - Data structure to hold a min-heap.
+ * @data: Start of array holding the heap elements.
+ * @nr: Number of elements currently in the heap.
+ * @size: Maximum number of elements that can be held in current storage.
+ */
+struct min_heap {
+	void *data;
+	int nr;
+	int size;
+};
+
+/**
+ * struct min_heap_callbacks - Data/functions to customise the min_heap.
+ * @elem_size: The nr of each element in bytes.
+ * @less: Partial order function for this heap.
+ * @swp: Swap elements function.
+ */
+struct min_heap_callbacks {
+	int elem_size;
+	bool (*less)(const void *lhs, const void *rhs);
+	void (*swp)(void *lhs, void *rhs);
+};
+
+/* Sift the element at pos down the heap. */
+static __always_inline
+void min_heapify(struct min_heap *heap, int pos,
+		const struct min_heap_callbacks *func)
+{
+	void *left, *right, *parent, *smallest;
+	void *data = heap->data;
+
+	for (;;) {
+		if (pos * 2 + 1 >= heap->nr)
+			break;
+
+		left = data + ((pos * 2 + 1) * func->elem_size);
+		parent = data + (pos * func->elem_size);
+		smallest = parent;
+		if (func->less(left, smallest))
+			smallest = left;
+
+		if (pos * 2 + 2 < heap->nr) {
+			right = data + ((pos * 2 + 2) * func->elem_size);
+			if (func->less(right, smallest))
+				smallest = right;
+		}
+		if (smallest == parent)
+			break;
+		func->swp(smallest, parent);
+		if (smallest == left)
+			pos = (pos * 2) + 1;
+		else
+			pos = (pos * 2) + 2;
+	}
+}
+
+/* Floyd's approach to heapification that is O(nr). */
+static __always_inline
+void min_heapify_all(struct min_heap *heap,
+		const struct min_heap_callbacks *func)
+{
+	int i;
+
+	for (i = heap->nr / 2; i >= 0; i--)
+		min_heapify(heap, i, func);
+}
+
+/* Remove minimum element from the heap, O(log2(nr)). */
+static __always_inline
+void min_heap_pop(struct min_heap *heap,
+		const struct min_heap_callbacks *func)
+{
+	void *data = heap->data;
+
+	if (WARN_ONCE(heap->nr <= 0, "Popping an empty heap"))
+		return;
+
+	/* Place last element at the root (position 0) and then sift down. */
+	heap->nr--;
+	memcpy(data, data + (heap->nr * func->elem_size), func->elem_size);
+	min_heapify(heap, 0, func);
+}
+
+/*
+ * Remove the minimum element and then push the given element. The
+ * implementation performs 1 sift (O(log2(nr))) and is therefore more
+ * efficient than a pop followed by a push that does 2.
+ */
+static __always_inline
+void min_heap_pop_push(struct min_heap *heap,
+		const void *element,
+		const struct min_heap_callbacks *func)
+{
+	memcpy(heap->data, element, func->elem_size);
+	min_heapify(heap, 0, func);
+}
+
+/* Push an element on to the heap, O(log2(nr)). */
+static __always_inline
+void min_heap_push(struct min_heap *heap, const void *element,
+		const struct min_heap_callbacks *func)
+{
+	void *data = heap->data;
+	void *child, *parent;
+	int pos;
+
+	if (WARN_ONCE(heap->nr >= heap->size, "Pushing on a full heap"))
+		return;
+
+	/* Place at the end of data. */
+	pos = heap->nr;
+	memcpy(data + (pos * func->elem_size), element, func->elem_size);
+	heap->nr++;
+
+	/* Sift child at pos up. */
+	for (; pos > 0; pos = (pos - 1) / 2) {
+		child = data + (pos * func->elem_size);
+		parent = data + ((pos - 1) / 2) * func->elem_size;
+		if (func->less(parent, child))
+			break;
+		func->swp(parent, child);
+	}
+}
+
+#endif /* _LINUX_MIN_HEAP_H */
diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h
index e3596db077dc..f8b66d43acf6 100644
--- a/include/linux/mod_devicetable.h
+++ b/include/linux/mod_devicetable.h
@@ -667,9 +667,7 @@ struct x86_cpu_id {
 	kernel_ulong_t driver_data;
 };
 
-#define X86_FEATURE_MATCH(x) \
-	{ X86_VENDOR_ANY, X86_FAMILY_ANY, X86_MODEL_ANY, x }
-
+/* Wild cards for x86_cpu_id::vendor, family, model and feature */
 #define X86_VENDOR_ANY 0xffff
 #define X86_FAMILY_ANY 0
 #define X86_MODEL_ANY  0
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 547773f5894e..8768a39b5258 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -93,14 +93,26 @@ struct perf_raw_record {
 /*
  * branch stack layout:
  *  nr: number of taken branches stored in entries[]
+ *  hw_idx: The low level index of raw branch records
+ *          for the most recent branch.
+ *          -1ULL means invalid/unknown.
  *
  * Note that nr can vary from sample to sample
  * branches (to, from) are stored from most recent
  * to least recent, i.e., entries[0] contains the most
  * recent branch.
+ * The entries[] is an abstraction of raw branch records,
+ * which may not be stored in age order in HW, e.g. Intel LBR.
+ * The hw_idx is to expose the low level index of raw
+ * branch record for the most recent branch aka entries[0].
+ * The hw_idx index is between -1 (unknown) and max depth,
+ * which can be retrieved in /sys/devices/cpu/caps/branches.
+ * For the architectures whose raw branch records are
+ * already stored in age order, the hw_idx should be 0.
  */
 struct perf_branch_stack {
 	__u64				nr;
+	__u64				hw_idx;
 	struct perf_branch_entry	entries[0];
 };
 
@@ -850,6 +862,13 @@ struct perf_cpu_context {
 	int				sched_cb_usage;
 
 	int				online;
+	/*
+	 * Per-CPU storage for iterators used in visit_groups_merge. The default
+	 * storage is of size 2 to hold the CPU and any CPU event iterators.
+	 */
+	int				heap_size;
+	struct perf_event		**heap;
+	struct perf_event		*heap_default[2];
 };
 
 struct perf_output_handle {
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 377d794d3105..397cfd65b3fe 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -181,6 +181,8 @@ enum perf_branch_sample_type_shift {
 
 	PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT	= 16, /* save branch type */
 
+	PERF_SAMPLE_BRANCH_HW_INDEX_SHIFT	= 17, /* save low level index of raw branch records */
+
 	PERF_SAMPLE_BRANCH_MAX_SHIFT		/* non-ABI */
 };
 
@@ -208,6 +210,8 @@ enum perf_branch_sample_type {
 	PERF_SAMPLE_BRANCH_TYPE_SAVE	=
 		1U << PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT,
 
+	PERF_SAMPLE_BRANCH_HW_INDEX	= 1U << PERF_SAMPLE_BRANCH_HW_INDEX_SHIFT,
+
 	PERF_SAMPLE_BRANCH_MAX		= 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT,
 };
 
@@ -853,7 +857,9 @@ enum perf_event_type {
 	 *	  char                  data[size];}&& PERF_SAMPLE_RAW
 	 *
 	 *	{ u64                   nr;
-	 *        { u64 from, to, flags } lbr[nr];} && PERF_SAMPLE_BRANCH_STACK
+	 *	  { u64	hw_idx; } && PERF_SAMPLE_BRANCH_HW_INDEX
+	 *        { u64 from, to, flags } lbr[nr];
+	 *      } && PERF_SAMPLE_BRANCH_STACK
 	 *
 	 * 	{ u64			abi; # enum perf_sample_regs_abi
 	 * 	  u64			regs[weight(mask)]; } && PERF_SAMPLE_REGS_USER
diff --git a/kernel/events/core.c b/kernel/events/core.c
index e453589da97c..d22e4ba59dfa 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -49,6 +49,7 @@
 #include <linux/sched/mm.h>
 #include <linux/proc_ns.h>
 #include <linux/mount.h>
+#include <linux/min_heap.h>
 
 #include "internal.h"
 
@@ -891,6 +892,47 @@ static inline void perf_cgroup_sched_in(struct task_struct *prev,
 	rcu_read_unlock();
 }
 
+static int perf_cgroup_ensure_storage(struct perf_event *event,
+				struct cgroup_subsys_state *css)
+{
+	struct perf_cpu_context *cpuctx;
+	struct perf_event **storage;
+	int cpu, heap_size, ret = 0;
+
+	/*
+	 * Allow storage to have sufficent space for an iterator for each
+	 * possibly nested cgroup plus an iterator for events with no cgroup.
+	 */
+	for (heap_size = 1; css; css = css->parent)
+		heap_size++;
+
+	for_each_possible_cpu(cpu) {
+		cpuctx = per_cpu_ptr(event->pmu->pmu_cpu_context, cpu);
+		if (heap_size <= cpuctx->heap_size)
+			continue;
+
+		storage = kmalloc_node(heap_size * sizeof(struct perf_event *),
+				       GFP_KERNEL, cpu_to_node(cpu));
+		if (!storage) {
+			ret = -ENOMEM;
+			break;
+		}
+
+		raw_spin_lock_irq(&cpuctx->ctx.lock);
+		if (cpuctx->heap_size < heap_size) {
+			swap(cpuctx->heap, storage);
+			if (storage == cpuctx->heap_default)
+				storage = NULL;
+			cpuctx->heap_size = heap_size;
+		}
+		raw_spin_unlock_irq(&cpuctx->ctx.lock);
+
+		kfree(storage);
+	}
+
+	return ret;
+}
+
 static inline int perf_cgroup_connect(int fd, struct perf_event *event,
 				      struct perf_event_attr *attr,
 				      struct perf_event *group_leader)
@@ -910,6 +952,10 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event,
 		goto out;
 	}
 
+	ret = perf_cgroup_ensure_storage(event, css);
+	if (ret)
+		goto out;
+
 	cgrp = container_of(css, struct perf_cgroup, css);
 	event->cgrp = cgrp;
 
@@ -1531,6 +1577,30 @@ perf_event_groups_less(struct perf_event *left, struct perf_event *right)
 	if (left->cpu > right->cpu)
 		return false;
 
+#ifdef CONFIG_CGROUP_PERF
+	if (left->cgrp != right->cgrp) {
+		if (!left->cgrp || !left->cgrp->css.cgroup) {
+			/*
+			 * Left has no cgroup but right does, no cgroups come
+			 * first.
+			 */
+			return true;
+		}
+		if (!right->cgrp || !right->cgrp->css.cgroup) {
+			/*
+			 * Right has no cgroup but left does, no cgroups come
+			 * first.
+			 */
+			return false;
+		}
+		/* Two dissimilar cgroups, order by id. */
+		if (left->cgrp->css.cgroup->kn->id < right->cgrp->css.cgroup->kn->id)
+			return true;
+
+		return false;
+	}
+#endif
+
 	if (left->group_index < right->group_index)
 		return true;
 	if (left->group_index > right->group_index)
@@ -1610,25 +1680,48 @@ del_event_from_groups(struct perf_event *event, struct perf_event_context *ctx)
 }
 
 /*
- * Get the leftmost event in the @cpu subtree.
+ * Get the leftmost event in the cpu/cgroup subtree.
  */
 static struct perf_event *
-perf_event_groups_first(struct perf_event_groups *groups, int cpu)
+perf_event_groups_first(struct perf_event_groups *groups, int cpu,
+			struct cgroup *cgrp)
 {
 	struct perf_event *node_event = NULL, *match = NULL;
 	struct rb_node *node = groups->tree.rb_node;
+#ifdef CONFIG_CGROUP_PERF
+	u64 node_cgrp_id, cgrp_id = 0;
+
+	if (cgrp)
+		cgrp_id = cgrp->kn->id;
+#endif
 
 	while (node) {
 		node_event = container_of(node, struct perf_event, group_node);
 
 		if (cpu < node_event->cpu) {
 			node = node->rb_left;
-		} else if (cpu > node_event->cpu) {
+			continue;
+		}
+		if (cpu > node_event->cpu) {
 			node = node->rb_right;
-		} else {
-			match = node_event;
+			continue;
+		}
+#ifdef CONFIG_CGROUP_PERF
+		node_cgrp_id = 0;
+		if (node_event->cgrp && node_event->cgrp->css.cgroup)
+			node_cgrp_id = node_event->cgrp->css.cgroup->kn->id;
+
+		if (cgrp_id < node_cgrp_id) {
 			node = node->rb_left;
+			continue;
+		}
+		if (cgrp_id > node_cgrp_id) {
+			node = node->rb_right;
+			continue;
 		}
+#endif
+		match = node_event;
+		node = node->rb_left;
 	}
 
 	return match;
@@ -1641,12 +1734,26 @@ static struct perf_event *
 perf_event_groups_next(struct perf_event *event)
 {
 	struct perf_event *next;
+#ifdef CONFIG_CGROUP_PERF
+	u64 curr_cgrp_id = 0;
+	u64 next_cgrp_id = 0;
+#endif
 
 	next = rb_entry_safe(rb_next(&event->group_node), typeof(*event), group_node);
-	if (next && next->cpu == event->cpu)
-		return next;
+	if (next == NULL || next->cpu != event->cpu)
+		return NULL;
 
-	return NULL;
+#ifdef CONFIG_CGROUP_PERF
+	if (event->cgrp && event->cgrp->css.cgroup)
+		curr_cgrp_id = event->cgrp->css.cgroup->kn->id;
+
+	if (next->cgrp && next->cgrp->css.cgroup)
+		next_cgrp_id = next->cgrp->css.cgroup->kn->id;
+
+	if (curr_cgrp_id != next_cgrp_id)
+		return NULL;
+#endif
+	return next;
 }
 
 /*
@@ -1986,6 +2093,12 @@ static int perf_get_aux_event(struct perf_event *event,
 	return 1;
 }
 
+static inline struct list_head *get_event_list(struct perf_event *event)
+{
+	struct perf_event_context *ctx = event->ctx;
+	return event->attr.pinned ? &ctx->pinned_active : &ctx->flexible_active;
+}
+
 static void perf_group_detach(struct perf_event *event)
 {
 	struct perf_event *sibling, *tmp;
@@ -2028,12 +2141,8 @@ static void perf_group_detach(struct perf_event *event)
 		if (!RB_EMPTY_NODE(&event->group_node)) {
 			add_event_to_groups(sibling, event->ctx);
 
-			if (sibling->state == PERF_EVENT_STATE_ACTIVE) {
-				struct list_head *list = sibling->attr.pinned ?
-					&ctx->pinned_active : &ctx->flexible_active;
-
-				list_add_tail(&sibling->active_list, list);
-			}
+			if (sibling->state == PERF_EVENT_STATE_ACTIVE)
+				list_add_tail(&sibling->active_list, get_event_list(sibling));
 		}
 
 		WARN_ON_ONCE(sibling->ctx != event->ctx);
@@ -2182,6 +2291,7 @@ __perf_remove_from_context(struct perf_event *event,
 
 	if (!ctx->nr_events && ctx->is_active) {
 		ctx->is_active = 0;
+		ctx->rotate_necessary = 0;
 		if (ctx->task) {
 			WARN_ON_ONCE(cpuctx->task_ctx != ctx);
 			cpuctx->task_ctx = NULL;
@@ -2350,6 +2460,8 @@ event_sched_in(struct perf_event *event,
 {
 	int ret = 0;
 
+	WARN_ON_ONCE(event->ctx != ctx);
+
 	lockdep_assert_held(&ctx->lock);
 
 	if (event->state <= PERF_EVENT_STATE_OFF)
@@ -3077,12 +3189,6 @@ static void ctx_sched_out(struct perf_event_context *ctx,
 	if (!ctx->nr_active || !(is_active & EVENT_ALL))
 		return;
 
-	/*
-	 * If we had been multiplexing, no rotations are necessary, now no events
-	 * are active.
-	 */
-	ctx->rotate_necessary = 0;
-
 	perf_pmu_disable(ctx->pmu);
 	if (is_active & EVENT_PINNED) {
 		list_for_each_entry_safe(event, tmp, &ctx->pinned_active, active_list)
@@ -3092,6 +3198,13 @@ static void ctx_sched_out(struct perf_event_context *ctx,
 	if (is_active & EVENT_FLEXIBLE) {
 		list_for_each_entry_safe(event, tmp, &ctx->flexible_active, active_list)
 			group_sched_out(event, cpuctx, ctx);
+
+		/*
+		 * Since we cleared EVENT_FLEXIBLE, also clear
+		 * rotate_necessary, is will be reset by
+		 * ctx_flexible_sched_in() when needed.
+		 */
+		ctx->rotate_necessary = 0;
 	}
 	perf_pmu_enable(ctx->pmu);
 }
@@ -3388,71 +3501,103 @@ static void cpu_ctx_sched_out(struct perf_cpu_context *cpuctx,
 	ctx_sched_out(&cpuctx->ctx, cpuctx, event_type);
 }
 
-static int visit_groups_merge(struct perf_event_groups *groups, int cpu,
-			      int (*func)(struct perf_event *, void *), void *data)
+static bool perf_less_group_idx(const void *l, const void *r)
 {
-	struct perf_event **evt, *evt1, *evt2;
-	int ret;
-
-	evt1 = perf_event_groups_first(groups, -1);
-	evt2 = perf_event_groups_first(groups, cpu);
-
-	while (evt1 || evt2) {
-		if (evt1 && evt2) {
-			if (evt1->group_index < evt2->group_index)
-				evt = &evt1;
-			else
-				evt = &evt2;
-		} else if (evt1) {
-			evt = &evt1;
-		} else {
-			evt = &evt2;
-		}
+	const struct perf_event *le = l, *re = r;
 
-		ret = func(*evt, data);
-		if (ret)
-			return ret;
+	return le->group_index < re->group_index;
+}
 
-		*evt = perf_event_groups_next(*evt);
-	}
+static void swap_ptr(void *l, void *r)
+{
+	void **lp = l, **rp = r;
 
-	return 0;
+	swap(*lp, *rp);
 }
 
-struct sched_in_data {
-	struct perf_event_context *ctx;
-	struct perf_cpu_context *cpuctx;
-	int can_add_hw;
+static const struct min_heap_callbacks perf_min_heap = {
+	.elem_size = sizeof(struct perf_event *),
+	.less = perf_less_group_idx,
+	.swp = swap_ptr,
 };
 
-static int pinned_sched_in(struct perf_event *event, void *data)
+static void __heap_add(struct min_heap *heap, struct perf_event *event)
 {
-	struct sched_in_data *sid = data;
+	struct perf_event **itrs = heap->data;
 
-	if (event->state <= PERF_EVENT_STATE_OFF)
-		return 0;
+	if (event) {
+		itrs[heap->nr] = event;
+		heap->nr++;
+	}
+}
 
-	if (!event_filter_match(event))
-		return 0;
+static noinline int visit_groups_merge(struct perf_cpu_context *cpuctx,
+				struct perf_event_groups *groups, int cpu,
+				int (*func)(struct perf_event *, void *),
+				void *data)
+{
+#ifdef CONFIG_CGROUP_PERF
+	struct cgroup_subsys_state *css = NULL;
+#endif
+	/* Space for per CPU and/or any CPU event iterators. */
+	struct perf_event *itrs[2];
+	struct min_heap event_heap;
+	struct perf_event **evt;
+	int ret;
+
+	if (cpuctx) {
+		event_heap = (struct min_heap){
+			.data = cpuctx->heap,
+			.nr = 0,
+			.size = cpuctx->heap_size,
+		};
+
+		lockdep_assert_held(&cpuctx->ctx.lock);
 
-	if (group_can_go_on(event, sid->cpuctx, sid->can_add_hw)) {
-		if (!group_sched_in(event, sid->cpuctx, sid->ctx))
-			list_add_tail(&event->active_list, &sid->ctx->pinned_active);
+#ifdef CONFIG_CGROUP_PERF
+		if (cpuctx->cgrp)
+			css = &cpuctx->cgrp->css;
+#endif
+	} else {
+		event_heap = (struct min_heap){
+			.data = itrs,
+			.nr = 0,
+			.size = ARRAY_SIZE(itrs),
+		};
+		/* Events not within a CPU context may be on any CPU. */
+		__heap_add(&event_heap, perf_event_groups_first(groups, -1, NULL));
 	}
+	evt = event_heap.data;
 
-	/*
-	 * If this pinned group hasn't been scheduled,
-	 * put it in error state.
-	 */
-	if (event->state == PERF_EVENT_STATE_INACTIVE)
-		perf_event_set_state(event, PERF_EVENT_STATE_ERROR);
+	__heap_add(&event_heap, perf_event_groups_first(groups, cpu, NULL));
+
+#ifdef CONFIG_CGROUP_PERF
+	for (; css; css = css->parent)
+		__heap_add(&event_heap, perf_event_groups_first(groups, cpu, css->cgroup));
+#endif
+
+	min_heapify_all(&event_heap, &perf_min_heap);
+
+	while (event_heap.nr) {
+		ret = func(*evt, data);
+		if (ret)
+			return ret;
+
+		*evt = perf_event_groups_next(*evt);
+		if (*evt)
+			min_heapify(&event_heap, 0, &perf_min_heap);
+		else
+			min_heap_pop(&event_heap, &perf_min_heap);
+	}
 
 	return 0;
 }
 
-static int flexible_sched_in(struct perf_event *event, void *data)
+static int merge_sched_in(struct perf_event *event, void *data)
 {
-	struct sched_in_data *sid = data;
+	struct perf_event_context *ctx = event->ctx;
+	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
+	int *can_add_hw = data;
 
 	if (event->state <= PERF_EVENT_STATE_OFF)
 		return 0;
@@ -3460,14 +3605,17 @@ static int flexible_sched_in(struct perf_event *event, void *data)
 	if (!event_filter_match(event))
 		return 0;
 
-	if (group_can_go_on(event, sid->cpuctx, sid->can_add_hw)) {
-		int ret = group_sched_in(event, sid->cpuctx, sid->ctx);
-		if (ret) {
-			sid->can_add_hw = 0;
-			sid->ctx->rotate_necessary = 1;
-			return 0;
-		}
-		list_add_tail(&event->active_list, &sid->ctx->flexible_active);
+	if (group_can_go_on(event, cpuctx, *can_add_hw)) {
+		if (!group_sched_in(event, cpuctx, ctx))
+			list_add_tail(&event->active_list, get_event_list(event));
+	}
+
+	if (event->state == PERF_EVENT_STATE_INACTIVE) {
+		if (event->attr.pinned)
+			perf_event_set_state(event, PERF_EVENT_STATE_ERROR);
+
+		*can_add_hw = 0;
+		ctx->rotate_necessary = 1;
 	}
 
 	return 0;
@@ -3477,30 +3625,28 @@ static void
 ctx_pinned_sched_in(struct perf_event_context *ctx,
 		    struct perf_cpu_context *cpuctx)
 {
-	struct sched_in_data sid = {
-		.ctx = ctx,
-		.cpuctx = cpuctx,
-		.can_add_hw = 1,
-	};
+	int can_add_hw = 1;
 
-	visit_groups_merge(&ctx->pinned_groups,
+	if (ctx != &cpuctx->ctx)
+		cpuctx = NULL;
+
+	visit_groups_merge(cpuctx, &ctx->pinned_groups,
 			   smp_processor_id(),
-			   pinned_sched_in, &sid);
+			   merge_sched_in, &can_add_hw);
 }
 
 static void
 ctx_flexible_sched_in(struct perf_event_context *ctx,
 		      struct perf_cpu_context *cpuctx)
 {
-	struct sched_in_data sid = {
-		.ctx = ctx,
-		.cpuctx = cpuctx,
-		.can_add_hw = 1,
-	};
+	int can_add_hw = 1;
 
-	visit_groups_merge(&ctx->flexible_groups,
+	if (ctx != &cpuctx->ctx)
+		cpuctx = NULL;
+
+	visit_groups_merge(cpuctx, &ctx->flexible_groups,
 			   smp_processor_id(),
-			   flexible_sched_in, &sid);
+			   merge_sched_in, &can_add_hw);
 }
 
 static void
@@ -3841,6 +3987,12 @@ ctx_event_to_rotate(struct perf_event_context *ctx)
 				      typeof(*event), group_node);
 	}
 
+	/*
+	 * Unconditionally clear rotate_necessary; if ctx_flexible_sched_in()
+	 * finds there are unschedulable events, it will set it again.
+	 */
+	ctx->rotate_necessary = 0;
+
 	return event;
 }
 
@@ -6555,6 +6707,11 @@ static void perf_output_read(struct perf_output_handle *handle,
 		perf_output_read_one(handle, event, enabled, running);
 }
 
+static inline bool perf_sample_save_hw_index(struct perf_event *event)
+{
+	return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX;
+}
+
 void perf_output_sample(struct perf_output_handle *handle,
 			struct perf_event_header *header,
 			struct perf_sample_data *data,
@@ -6643,6 +6800,8 @@ void perf_output_sample(struct perf_output_handle *handle,
 			     * sizeof(struct perf_branch_entry);
 
 			perf_output_put(handle, data->br_stack->nr);
+			if (perf_sample_save_hw_index(event))
+				perf_output_put(handle, data->br_stack->hw_idx);
 			perf_output_copy(handle, data->br_stack->entries, size);
 		} else {
 			/*
@@ -6836,6 +6995,9 @@ void perf_prepare_sample(struct perf_event_header *header,
 	if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
 		int size = sizeof(u64); /* nr */
 		if (data->br_stack) {
+			if (perf_sample_save_hw_index(event))
+				size += sizeof(u64);
+
 			size += data->br_stack->nr
 			      * sizeof(struct perf_branch_entry);
 		}
@@ -10349,6 +10511,9 @@ skip_type:
 		cpuctx->online = cpumask_test_cpu(cpu, perf_online_mask);
 
 		__perf_mux_hrtimer_init(cpuctx, cpu);
+
+		cpuctx->heap_size = ARRAY_SIZE(cpuctx->heap_default);
+		cpuctx->heap = cpuctx->heap_default;
 	}
 
 got_cpu_context:
@@ -10794,12 +10959,6 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	if (!has_branch_stack(event))
 		event->attr.branch_sample_type = 0;
 
-	if (cgroup_fd != -1) {
-		err = perf_cgroup_connect(cgroup_fd, event, attr, group_leader);
-		if (err)
-			goto err_ns;
-	}
-
 	pmu = perf_init_event(event);
 	if (IS_ERR(pmu)) {
 		err = PTR_ERR(pmu);
@@ -10821,6 +10980,12 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 		goto err_pmu;
 	}
 
+	if (cgroup_fd != -1) {
+		err = perf_cgroup_connect(cgroup_fd, event, attr, group_leader);
+		if (err)
+			goto err_pmu;
+	}
+
 	err = exclusive_event_init(event);
 	if (err)
 		goto err_pmu;
@@ -10881,12 +11046,12 @@ err_per_task:
 	exclusive_event_destroy(event);
 
 err_pmu:
+	if (is_cgroup_event(event))
+		perf_detach_cgroup(event);
 	if (event->destroy)
 		event->destroy(event);
 	module_put(pmu->module);
 err_ns:
-	if (is_cgroup_event(event))
-		perf_detach_cgroup(event);
 	if (event->ns)
 		put_pid_ns(event->ns);
 	if (event->hw.target)
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 70813e39f911..5c315661931e 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1786,6 +1786,16 @@ config TEST_LIST_SORT
 
 	  If unsure, say N.
 
+config TEST_MIN_HEAP
+	tristate "Min heap test"
+	depends on DEBUG_KERNEL || m
+	help
+	  Enable this to turn on min heap function tests. This test is
+	  executed only once during system boot (so affects only boot time),
+	  or at module load time.
+
+	  If unsure, say N.
+
 config TEST_SORT
 	tristate "Array-based sort test"
 	depends on DEBUG_KERNEL || m
diff --git a/lib/Makefile b/lib/Makefile
index 611872c06926..09a8acb0cf92 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -67,6 +67,7 @@ CFLAGS_test_ubsan.o += $(call cc-disable-warning, vla)
 UBSAN_SANITIZE_test_ubsan.o := y
 obj-$(CONFIG_TEST_KSTRTOX) += test-kstrtox.o
 obj-$(CONFIG_TEST_LIST_SORT) += test_list_sort.o
+obj-$(CONFIG_TEST_MIN_HEAP) += test_min_heap.o
 obj-$(CONFIG_TEST_LKM) += test_module.o
 obj-$(CONFIG_TEST_VMALLOC) += test_vmalloc.o
 obj-$(CONFIG_TEST_OVERFLOW) += test_overflow.o
diff --git a/lib/test_min_heap.c b/lib/test_min_heap.c
new file mode 100644
index 000000000000..d19c8080fd4d
--- /dev/null
+++ b/lib/test_min_heap.c
@@ -0,0 +1,194 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#define pr_fmt(fmt) "min_heap_test: " fmt
+
+/*
+ * Test cases for the min max heap.
+ */
+
+#include <linux/log2.h>
+#include <linux/min_heap.h>
+#include <linux/module.h>
+#include <linux/printk.h>
+#include <linux/random.h>
+
+static __init bool less_than(const void *lhs, const void *rhs)
+{
+	return *(int *)lhs < *(int *)rhs;
+}
+
+static __init bool greater_than(const void *lhs, const void *rhs)
+{
+	return *(int *)lhs > *(int *)rhs;
+}
+
+static __init void swap_ints(void *lhs, void *rhs)
+{
+	int temp = *(int *)lhs;
+
+	*(int *)lhs = *(int *)rhs;
+	*(int *)rhs = temp;
+}
+
+static __init int pop_verify_heap(bool min_heap,
+				struct min_heap *heap,
+				const struct min_heap_callbacks *funcs)
+{
+	int *values = heap->data;
+	int err = 0;
+	int last;
+
+	last = values[0];
+	min_heap_pop(heap, funcs);
+	while (heap->nr > 0) {
+		if (min_heap) {
+			if (last > values[0]) {
+				pr_err("error: expected %d <= %d\n", last,
+					values[0]);
+				err++;
+			}
+		} else {
+			if (last < values[0]) {
+				pr_err("error: expected %d >= %d\n", last,
+					values[0]);
+				err++;
+			}
+		}
+		last = values[0];
+		min_heap_pop(heap, funcs);
+	}
+	return err;
+}
+
+static __init int test_heapify_all(bool min_heap)
+{
+	int values[] = { 3, 1, 2, 4, 0x8000000, 0x7FFFFFF, 0,
+			 -3, -1, -2, -4, 0x8000000, 0x7FFFFFF };
+	struct min_heap heap = {
+		.data = values,
+		.nr = ARRAY_SIZE(values),
+		.size =  ARRAY_SIZE(values),
+	};
+	struct min_heap_callbacks funcs = {
+		.elem_size = sizeof(int),
+		.less = min_heap ? less_than : greater_than,
+		.swp = swap_ints,
+	};
+	int i, err;
+
+	/* Test with known set of values. */
+	min_heapify_all(&heap, &funcs);
+	err = pop_verify_heap(min_heap, &heap, &funcs);
+
+
+	/* Test with randomly generated values. */
+	heap.nr = ARRAY_SIZE(values);
+	for (i = 0; i < heap.nr; i++)
+		values[i] = get_random_int();
+
+	min_heapify_all(&heap, &funcs);
+	err += pop_verify_heap(min_heap, &heap, &funcs);
+
+	return err;
+}
+
+static __init int test_heap_push(bool min_heap)
+{
+	const int data[] = { 3, 1, 2, 4, 0x80000000, 0x7FFFFFFF, 0,
+			     -3, -1, -2, -4, 0x80000000, 0x7FFFFFFF };
+	int values[ARRAY_SIZE(data)];
+	struct min_heap heap = {
+		.data = values,
+		.nr = 0,
+		.size =  ARRAY_SIZE(values),
+	};
+	struct min_heap_callbacks funcs = {
+		.elem_size = sizeof(int),
+		.less = min_heap ? less_than : greater_than,
+		.swp = swap_ints,
+	};
+	int i, temp, err;
+
+	/* Test with known set of values copied from data. */
+	for (i = 0; i < ARRAY_SIZE(data); i++)
+		min_heap_push(&heap, &data[i], &funcs);
+
+	err = pop_verify_heap(min_heap, &heap, &funcs);
+
+	/* Test with randomly generated values. */
+	while (heap.nr < heap.size) {
+		temp = get_random_int();
+		min_heap_push(&heap, &temp, &funcs);
+	}
+	err += pop_verify_heap(min_heap, &heap, &funcs);
+
+	return err;
+}
+
+static __init int test_heap_pop_push(bool min_heap)
+{
+	const int data[] = { 3, 1, 2, 4, 0x80000000, 0x7FFFFFFF, 0,
+			     -3, -1, -2, -4, 0x80000000, 0x7FFFFFFF };
+	int values[ARRAY_SIZE(data)];
+	struct min_heap heap = {
+		.data = values,
+		.nr = 0,
+		.size =  ARRAY_SIZE(values),
+	};
+	struct min_heap_callbacks funcs = {
+		.elem_size = sizeof(int),
+		.less = min_heap ? less_than : greater_than,
+		.swp = swap_ints,
+	};
+	int i, temp, err;
+
+	/* Fill values with data to pop and replace. */
+	temp = min_heap ? 0x80000000 : 0x7FFFFFFF;
+	for (i = 0; i < ARRAY_SIZE(data); i++)
+		min_heap_push(&heap, &temp, &funcs);
+
+	/* Test with known set of values copied from data. */
+	for (i = 0; i < ARRAY_SIZE(data); i++)
+		min_heap_pop_push(&heap, &data[i], &funcs);
+
+	err = pop_verify_heap(min_heap, &heap, &funcs);
+
+	heap.nr = 0;
+	for (i = 0; i < ARRAY_SIZE(data); i++)
+		min_heap_push(&heap, &temp, &funcs);
+
+	/* Test with randomly generated values. */
+	for (i = 0; i < ARRAY_SIZE(data); i++) {
+		temp = get_random_int();
+		min_heap_pop_push(&heap, &temp, &funcs);
+	}
+	err += pop_verify_heap(min_heap, &heap, &funcs);
+
+	return err;
+}
+
+static int __init test_min_heap_init(void)
+{
+	int err = 0;
+
+	err += test_heapify_all(true);
+	err += test_heapify_all(false);
+	err += test_heap_push(true);
+	err += test_heap_push(false);
+	err += test_heap_pop_push(true);
+	err += test_heap_pop_push(false);
+	if (err) {
+		pr_err("test failed with %d errors\n", err);
+		return -EINVAL;
+	}
+	pr_info("test passed\n");
+	return 0;
+}
+module_init(test_min_heap_init);
+
+static void __exit test_min_heap_exit(void)
+{
+	/* do nothing */
+}
+module_exit(test_min_heap_exit);
+
+MODULE_LICENSE("GPL");
diff --git a/sound/soc/intel/common/soc-intel-quirks.h b/sound/soc/intel/common/soc-intel-quirks.h
index 863a477d3405..a9176150c6ed 100644
--- a/sound/soc/intel/common/soc-intel-quirks.h
+++ b/sound/soc/intel/common/soc-intel-quirks.h
@@ -15,13 +15,11 @@
 #include <asm/intel-family.h>
 #include <asm/iosf_mbi.h>
 
-#define ICPU(model)	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, }
-
 #define SOC_INTEL_IS_CPU(soc, type)				\
 static inline bool soc_intel_is_##soc(void)			\
 {								\
 	static const struct x86_cpu_id soc##_cpu_ids[] = {	\
-		ICPU(type),					\
+		X86_MATCH_INTEL_FAM6_MODEL(type, NULL),		\
 		{}						\
 	};							\
 	const struct x86_cpu_id *id;				\
@@ -32,11 +30,11 @@ static inline bool soc_intel_is_##soc(void)			\
 	return false;						\
 }
 
-SOC_INTEL_IS_CPU(byt, INTEL_FAM6_ATOM_SILVERMONT);
-SOC_INTEL_IS_CPU(cht, INTEL_FAM6_ATOM_AIRMONT);
-SOC_INTEL_IS_CPU(apl, INTEL_FAM6_ATOM_GOLDMONT);
-SOC_INTEL_IS_CPU(glk, INTEL_FAM6_ATOM_GOLDMONT_PLUS);
-SOC_INTEL_IS_CPU(cml, INTEL_FAM6_KABYLAKE_L);
+SOC_INTEL_IS_CPU(byt, ATOM_SILVERMONT);
+SOC_INTEL_IS_CPU(cht, ATOM_AIRMONT);
+SOC_INTEL_IS_CPU(apl, ATOM_GOLDMONT);
+SOC_INTEL_IS_CPU(glk, ATOM_GOLDMONT_PLUS);
+SOC_INTEL_IS_CPU(cml, KABYLAKE_L);
 
 static inline bool soc_intel_is_byt_cr(struct platform_device *pdev)
 {
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index 377d794d3105..397cfd65b3fe 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -181,6 +181,8 @@ enum perf_branch_sample_type_shift {
 
 	PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT	= 16, /* save branch type */
 
+	PERF_SAMPLE_BRANCH_HW_INDEX_SHIFT	= 17, /* save low level index of raw branch records */
+
 	PERF_SAMPLE_BRANCH_MAX_SHIFT		/* non-ABI */
 };
 
@@ -208,6 +210,8 @@ enum perf_branch_sample_type {
 	PERF_SAMPLE_BRANCH_TYPE_SAVE	=
 		1U << PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT,
 
+	PERF_SAMPLE_BRANCH_HW_INDEX	= 1U << PERF_SAMPLE_BRANCH_HW_INDEX_SHIFT,
+
 	PERF_SAMPLE_BRANCH_MAX		= 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT,
 };
 
@@ -853,7 +857,9 @@ enum perf_event_type {
 	 *	  char                  data[size];}&& PERF_SAMPLE_RAW
 	 *
 	 *	{ u64                   nr;
-	 *        { u64 from, to, flags } lbr[nr];} && PERF_SAMPLE_BRANCH_STACK
+	 *	  { u64	hw_idx; } && PERF_SAMPLE_BRANCH_HW_INDEX
+	 *        { u64 from, to, flags } lbr[nr];
+	 *      } && PERF_SAMPLE_BRANCH_STACK
 	 *
 	 * 	{ u64			abi; # enum perf_sample_regs_abi
 	 * 	  u64			regs[weight(mask)]; } && PERF_SAMPLE_REGS_USER
diff --git a/tools/lib/api/fs/Build b/tools/lib/api/fs/Build
index f4ed9629ae85..0f75b28654de 100644
--- a/tools/lib/api/fs/Build
+++ b/tools/lib/api/fs/Build
@@ -1,2 +1,3 @@
 libapi-y += fs.o
 libapi-y += tracing_path.o
+libapi-y += cgroup.o
diff --git a/tools/lib/api/fs/cgroup.c b/tools/lib/api/fs/cgroup.c
new file mode 100644
index 000000000000..889a6eb4aaca
--- /dev/null
+++ b/tools/lib/api/fs/cgroup.c
@@ -0,0 +1,67 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/stringify.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include "fs.h"
+
+int cgroupfs_find_mountpoint(char *buf, size_t maxlen, const char *subsys)
+{
+	FILE *fp;
+	char mountpoint[PATH_MAX + 1], tokens[PATH_MAX + 1], type[PATH_MAX + 1];
+	char path_v1[PATH_MAX + 1], path_v2[PATH_MAX + 2], *path;
+	char *token, *saved_ptr = NULL;
+
+	fp = fopen("/proc/mounts", "r");
+	if (!fp)
+		return -1;
+
+	/*
+	 * in order to handle split hierarchy, we need to scan /proc/mounts
+	 * and inspect every cgroupfs mount point to find one that has
+	 * perf_event subsystem
+	 */
+	path_v1[0] = '\0';
+	path_v2[0] = '\0';
+
+	while (fscanf(fp, "%*s %"__stringify(PATH_MAX)"s %"__stringify(PATH_MAX)"s %"
+				__stringify(PATH_MAX)"s %*d %*d\n",
+				mountpoint, type, tokens) == 3) {
+
+		if (!path_v1[0] && !strcmp(type, "cgroup")) {
+
+			token = strtok_r(tokens, ",", &saved_ptr);
+
+			while (token != NULL) {
+				if (subsys && !strcmp(token, subsys)) {
+					strcpy(path_v1, mountpoint);
+					break;
+				}
+				token = strtok_r(NULL, ",", &saved_ptr);
+			}
+		}
+
+		if (!path_v2[0] && !strcmp(type, "cgroup2"))
+			strcpy(path_v2, mountpoint);
+
+		if (path_v1[0] && path_v2[0])
+			break;
+	}
+	fclose(fp);
+
+	if (path_v1[0])
+		path = path_v1;
+	else if (path_v2[0])
+		path = path_v2;
+	else
+		return -1;
+
+	if (strlen(path) < maxlen) {
+		strcpy(buf, path);
+		return 0;
+	}
+	return -1;
+}
diff --git a/tools/lib/api/fs/fs.h b/tools/lib/api/fs/fs.h
index 92d03b8396b1..936edb95e1f3 100644
--- a/tools/lib/api/fs/fs.h
+++ b/tools/lib/api/fs/fs.h
@@ -28,6 +28,8 @@ FS(bpf_fs)
 #undef FS
 
 
+int cgroupfs_find_mountpoint(char *buf, size_t maxlen, const char *subsys);
+
 int filename__read_int(const char *filename, int *value);
 int filename__read_ull(const char *filename, unsigned long long *value);
 int filename__read_xll(const char *filename, unsigned long long *value);
diff --git a/tools/lib/perf/Documentation/examples/counting.c b/tools/lib/perf/Documentation/examples/counting.c
new file mode 100644
index 000000000000..6085693571ef
--- /dev/null
+++ b/tools/lib/perf/Documentation/examples/counting.c
@@ -0,0 +1,83 @@
+#include <linux/perf_event.h>
+#include <perf/evlist.h>
+#include <perf/evsel.h>
+#include <perf/cpumap.h>
+#include <perf/threadmap.h>
+#include <perf/mmap.h>
+#include <perf/core.h>
+#include <perf/event.h>
+#include <stdio.h>
+#include <unistd.h>
+
+static int libperf_print(enum libperf_print_level level,
+                         const char *fmt, va_list ap)
+{
+	return vfprintf(stderr, fmt, ap);
+}
+
+int main(int argc, char **argv)
+{
+	int count = 100000, err = 0;
+	struct perf_evlist *evlist;
+	struct perf_evsel *evsel;
+	struct perf_thread_map *threads;
+	struct perf_counts_values counts;
+
+	struct perf_event_attr attr1 = {
+		.type        = PERF_TYPE_SOFTWARE,
+		.config      = PERF_COUNT_SW_CPU_CLOCK,
+		.read_format = PERF_FORMAT_TOTAL_TIME_ENABLED|PERF_FORMAT_TOTAL_TIME_RUNNING,
+		.disabled    = 1,
+	};
+	struct perf_event_attr attr2 = {
+		.type        = PERF_TYPE_SOFTWARE,
+		.config      = PERF_COUNT_SW_TASK_CLOCK,
+		.read_format = PERF_FORMAT_TOTAL_TIME_ENABLED|PERF_FORMAT_TOTAL_TIME_RUNNING,
+		.disabled    = 1,
+	};
+
+	libperf_init(libperf_print);
+	threads = perf_thread_map__new_dummy();
+	if (!threads) {
+		fprintf(stderr, "failed to create threads\n");
+		return -1;
+	}
+	perf_thread_map__set_pid(threads, 0, 0);
+	evlist = perf_evlist__new();
+	if (!evlist) {
+		fprintf(stderr, "failed to create evlist\n");
+		goto out_threads;
+	}
+	evsel = perf_evsel__new(&attr1);
+	if (!evsel) {
+		fprintf(stderr, "failed to create evsel1\n");
+		goto out_evlist;
+	}
+	perf_evlist__add(evlist, evsel);
+	evsel = perf_evsel__new(&attr2);
+	if (!evsel) {
+		fprintf(stderr, "failed to create evsel2\n");
+		goto out_evlist;
+	}
+	perf_evlist__add(evlist, evsel);
+	perf_evlist__set_maps(evlist, NULL, threads);
+	err = perf_evlist__open(evlist);
+	if (err) {
+		fprintf(stderr, "failed to open evsel\n");
+		goto out_evlist;
+	}
+	perf_evlist__enable(evlist);
+	while (count--);
+	perf_evlist__disable(evlist);
+	perf_evlist__for_each_evsel(evlist, evsel) {
+		perf_evsel__read(evsel, 0, 0, &counts);
+		fprintf(stdout, "count %llu, enabled %llu, run %llu\n",
+				counts.val, counts.ena, counts.run);
+	}
+	perf_evlist__close(evlist);
+out_evlist:
+	perf_evlist__delete(evlist);
+out_threads:
+	perf_thread_map__put(threads);
+	return err;
+}
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index beaa8b8c08ff..e1bd2a93c6db 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -5541,7 +5541,7 @@ static void print_event_time(struct tep_handle *tep, struct trace_seq *s,
 	if (p10 > 1 && p10 < time)
 		trace_seq_printf(s, "%5llu.%0*llu", time / p10, prec, time % p10);
 	else
-		trace_seq_printf(s, "%12llu\n", time);
+		trace_seq_printf(s, "%12llu", time);
 }
 
 struct print_event_type {
diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile
index adc5a7e44b98..31824d5269cc 100644
--- a/tools/perf/Documentation/Makefile
+++ b/tools/perf/Documentation/Makefile
@@ -295,7 +295,10 @@ $(OUTPUT)%.1 $(OUTPUT)%.5 $(OUTPUT)%.7 : $(OUTPUT)%.xml
 $(OUTPUT)%.xml : %.txt
 	$(QUIET_ASCIIDOC)$(RM) $@+ $@ && \
 	$(ASCIIDOC) -b docbook -d manpage \
-		$(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) -o $@+ $< && \
+		$(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) \
+		-aperf_date=$(shell git log -1 --pretty="format:%cd" \
+				--date=short $<) \
+		-o $@+ $< && \
 	mv $@+ $@
 
 XSLT = docbook.xsl
diff --git a/tools/perf/Documentation/intel-pt.txt b/tools/perf/Documentation/intel-pt.txt
index 2cf2d9e9d0da..fd9241a1b987 100644
--- a/tools/perf/Documentation/intel-pt.txt
+++ b/tools/perf/Documentation/intel-pt.txt
@@ -1,991 +1 @@
-Intel Processor Trace
-=====================
-
-Overview
-========
-
-Intel Processor Trace (Intel PT) is an extension of Intel Architecture that
-collects information about software execution such as control flow, execution
-modes and timings and formats it into highly compressed binary packets.
-Technical details are documented in the Intel 64 and IA-32 Architectures
-Software Developer Manuals, Chapter 36 Intel Processor Trace.
-
-Intel PT is first supported in Intel Core M and 5th generation Intel Core
-processors that are based on the Intel micro-architecture code name Broadwell.
-
-Trace data is collected by 'perf record' and stored within the perf.data file.
-See below for options to 'perf record'.
-
-Trace data must be 'decoded' which involves walking the object code and matching
-the trace data packets. For example a TNT packet only tells whether a
-conditional branch was taken or not taken, so to make use of that packet the
-decoder must know precisely which instruction was being executed.
-
-Decoding is done on-the-fly.  The decoder outputs samples in the same format as
-samples output by perf hardware events, for example as though the "instructions"
-or "branches" events had been recorded.  Presently 3 tools support this:
-'perf script', 'perf report' and 'perf inject'.  See below for more information
-on using those tools.
-
-The main distinguishing feature of Intel PT is that the decoder can determine
-the exact flow of software execution.  Intel PT can be used to understand why
-and how did software get to a certain point, or behave a certain way.  The
-software does not have to be recompiled, so Intel PT works with debug or release
-builds, however the executed images are needed - which makes use in JIT-compiled
-environments, or with self-modified code, a challenge.  Also symbols need to be
-provided to make sense of addresses.
-
-A limitation of Intel PT is that it produces huge amounts of trace data
-(hundreds of megabytes per second per core) which takes a long time to decode,
-for example two or three orders of magnitude longer than it took to collect.
-Another limitation is the performance impact of tracing, something that will
-vary depending on the use-case and architecture.
-
-
-Quickstart
-==========
-
-It is important to start small.  That is because it is easy to capture vastly
-more data than can possibly be processed.
-
-The simplest thing to do with Intel PT is userspace profiling of small programs.
-Data is captured with 'perf record' e.g. to trace 'ls' userspace-only:
-
-	perf record -e intel_pt//u ls
-
-And profiled with 'perf report' e.g.
-
-	perf report
-
-To also trace kernel space presents a problem, namely kernel self-modifying
-code.  A fairly good kernel image is available in /proc/kcore but to get an
-accurate image a copy of /proc/kcore needs to be made under the same conditions
-as the data capture.  A script perf-with-kcore can do that, but beware that the
-script makes use of 'sudo' to copy /proc/kcore.  If you have perf installed
-locally from the source tree you can do:
-
-	~/libexec/perf-core/perf-with-kcore record pt_ls -e intel_pt// -- ls
-
-which will create a directory named 'pt_ls' and put the perf.data file and
-copies of /proc/kcore, /proc/kallsyms and /proc/modules into it.  Then to use
-'perf report' becomes:
-
-	~/libexec/perf-core/perf-with-kcore report pt_ls
-
-Because samples are synthesized after-the-fact, the sampling period can be
-selected for reporting. e.g. sample every microsecond
-
-	~/libexec/perf-core/perf-with-kcore report pt_ls --itrace=i1usge
-
-See the sections below for more information about the --itrace option.
-
-Beware the smaller the period, the more samples that are produced, and the
-longer it takes to process them.
-
-Also note that the coarseness of Intel PT timing information will start to
-distort the statistical value of the sampling as the sampling period becomes
-smaller.
-
-To represent software control flow, "branches" samples are produced.  By default
-a branch sample is synthesized for every single branch.  To get an idea what
-data is available you can use the 'perf script' tool with all itrace sampling
-options, which will list all the samples.
-
-	perf record -e intel_pt//u ls
-	perf script --itrace=ibxwpe
-
-An interesting field that is not printed by default is 'flags' which can be
-displayed as follows:
-
-	perf script --itrace=ibxwpe -F+flags
-
-The flags are "bcrosyiABEx" which stand for branch, call, return, conditional,
-system, asynchronous, interrupt, transaction abort, trace begin, trace end, and
-in transaction, respectively.
-
-Another interesting field that is not printed by default is 'ipc' which can be
-displayed as follows:
-
-	perf script --itrace=be -F+ipc
-
-There are two ways that instructions-per-cycle (IPC) can be calculated depending
-on the recording.
-
-If the 'cyc' config term (see config terms section below) was used, then IPC is
-calculated using the cycle count from CYC packets, otherwise MTC packets are
-used - refer to the 'mtc' config term.  When MTC is used, however, the values
-are less accurate because the timing is less accurate.
-
-Because Intel PT does not update the cycle count on every branch or instruction,
-the values will often be zero.  When there are values, they will be the number
-of instructions and number of cycles since the last update, and thus represent
-the average IPC since the last IPC for that event type.  Note IPC for "branches"
-events is calculated separately from IPC for "instructions" events.
-
-Also note that the IPC instruction count may or may not include the current
-instruction.  If the cycle count is associated with an asynchronous branch
-(e.g. page fault or interrupt), then the instruction count does not include the
-current instruction, otherwise it does.  That is consistent with whether or not
-that instruction has retired when the cycle count is updated.
-
-Another note, in the case of "branches" events, non-taken branches are not
-presently sampled, so IPC values for them do not appear e.g. a CYC packet with a
-TNT packet that starts with a non-taken branch.  To see every possible IPC
-value, "instructions" events can be used e.g. --itrace=i0ns
-
-While it is possible to create scripts to analyze the data, an alternative
-approach is available to export the data to a sqlite or postgresql database.
-Refer to script export-to-sqlite.py or export-to-postgresql.py for more details,
-and to script exported-sql-viewer.py for an example of using the database.
-
-There is also script intel-pt-events.py which provides an example of how to
-unpack the raw data for power events and PTWRITE.
-
-As mentioned above, it is easy to capture too much data.  One way to limit the
-data captured is to use 'snapshot' mode which is explained further below.
-Refer to 'new snapshot option' and 'Intel PT modes of operation' further below.
-
-Another problem that will be experienced is decoder errors.  They can be caused
-by inability to access the executed image, self-modified or JIT-ed code, or the
-inability to match side-band information (such as context switches and mmaps)
-which results in the decoder not knowing what code was executed.
-
-There is also the problem of perf not being able to copy the data fast enough,
-resulting in data lost because the buffer was full.  See 'Buffer handling' below
-for more details.
-
-
-perf record
-===========
-
-new event
----------
-
-The Intel PT kernel driver creates a new PMU for Intel PT.  PMU events are
-selected by providing the PMU name followed by the "config" separated by slashes.
-An enhancement has been made to allow default "config" e.g. the option
-
-	-e intel_pt//
-
-will use a default config value.  Currently that is the same as
-
-	-e intel_pt/tsc,noretcomp=0/
-
-which is the same as
-
-	-e intel_pt/tsc=1,noretcomp=0/
-
-Note there are now new config terms - see section 'config terms' further below.
-
-The config terms are listed in /sys/devices/intel_pt/format.  They are bit
-fields within the config member of the struct perf_event_attr which is
-passed to the kernel by the perf_event_open system call.  They correspond to bit
-fields in the IA32_RTIT_CTL MSR.  Here is a list of them and their definitions:
-
-	$ grep -H . /sys/bus/event_source/devices/intel_pt/format/*
-	/sys/bus/event_source/devices/intel_pt/format/cyc:config:1
-	/sys/bus/event_source/devices/intel_pt/format/cyc_thresh:config:19-22
-	/sys/bus/event_source/devices/intel_pt/format/mtc:config:9
-	/sys/bus/event_source/devices/intel_pt/format/mtc_period:config:14-17
-	/sys/bus/event_source/devices/intel_pt/format/noretcomp:config:11
-	/sys/bus/event_source/devices/intel_pt/format/psb_period:config:24-27
-	/sys/bus/event_source/devices/intel_pt/format/tsc:config:10
-
-Note that the default config must be overridden for each term i.e.
-
-	-e intel_pt/noretcomp=0/
-
-is the same as:
-
-	-e intel_pt/tsc=1,noretcomp=0/
-
-So, to disable TSC packets use:
-
-	-e intel_pt/tsc=0/
-
-It is also possible to specify the config value explicitly:
-
-	-e intel_pt/config=0x400/
-
-Note that, as with all events, the event is suffixed with event modifiers:
-
-	u	userspace
-	k	kernel
-	h	hypervisor
-	G	guest
-	H	host
-	p	precise ip
-
-'h', 'G' and 'H' are for virtualization which is not supported by Intel PT.
-'p' is also not relevant to Intel PT.  So only options 'u' and 'k' are
-meaningful for Intel PT.
-
-perf_event_attr is displayed if the -vv option is used e.g.
-
-	------------------------------------------------------------
-	perf_event_attr:
-	type                             6
-	size                             112
-	config                           0x400
-	{ sample_period, sample_freq }   1
-	sample_type                      IP|TID|TIME|CPU|IDENTIFIER
-	read_format                      ID
-	disabled                         1
-	inherit                          1
-	exclude_kernel                   1
-	exclude_hv                       1
-	enable_on_exec                   1
-	sample_id_all                    1
-	------------------------------------------------------------
-	sys_perf_event_open: pid 31104  cpu 0  group_fd -1  flags 0x8
-	sys_perf_event_open: pid 31104  cpu 1  group_fd -1  flags 0x8
-	sys_perf_event_open: pid 31104  cpu 2  group_fd -1  flags 0x8
-	sys_perf_event_open: pid 31104  cpu 3  group_fd -1  flags 0x8
-	------------------------------------------------------------
-
-
-config terms
-------------
-
-The June 2015 version of Intel 64 and IA-32 Architectures Software Developer
-Manuals, Chapter 36 Intel Processor Trace, defined new Intel PT features.
-Some of the features are reflect in new config terms.  All the config terms are
-described below.
-
-tsc		Always supported.  Produces TSC timestamp packets to provide
-		timing information.  In some cases it is possible to decode
-		without timing information, for example a per-thread context
-		that does not overlap executable memory maps.
-
-		The default config selects tsc (i.e. tsc=1).
-
-noretcomp	Always supported.  Disables "return compression" so a TIP packet
-		is produced when a function returns.  Causes more packets to be
-		produced but might make decoding more reliable.
-
-		The default config does not select noretcomp (i.e. noretcomp=0).
-
-psb_period	Allows the frequency of PSB packets to be specified.
-
-		The PSB packet is a synchronization packet that provides a
-		starting point for decoding or recovery from errors.
-
-		Support for psb_period is indicated by:
-
-			/sys/bus/event_source/devices/intel_pt/caps/psb_cyc
-
-		which contains "1" if the feature is supported and "0"
-		otherwise.
-
-		Valid values are given by:
-
-			/sys/bus/event_source/devices/intel_pt/caps/psb_periods
-
-		which contains a hexadecimal value, the bits of which represent
-		valid values e.g. bit 2 set means value 2 is valid.
-
-		The psb_period value is converted to the approximate number of
-		trace bytes between PSB packets as:
-
-			2 ^ (value + 11)
-
-		e.g. value 3 means 16KiB bytes between PSBs
-
-		If an invalid value is entered, the error message
-		will give a list of valid values e.g.
-
-			$ perf record -e intel_pt/psb_period=15/u uname
-			Invalid psb_period for intel_pt. Valid values are: 0-5
-
-		If MTC packets are selected, the default config selects a value
-		of 3 (i.e. psb_period=3) or the nearest lower value that is
-		supported (0 is always supported).  Otherwise the default is 0.
-
-		If decoding is expected to be reliable and the buffer is large
-		then a large PSB period can be used.
-
-		Because a TSC packet is produced with PSB, the PSB period can
-		also affect the granularity to timing information in the absence
-		of MTC or CYC.
-
-mtc		Produces MTC timing packets.
-
-		MTC packets provide finer grain timestamp information than TSC
-		packets.  MTC packets record time using the hardware crystal
-		clock (CTC) which is related to TSC packets using a TMA packet.
-
-		Support for this feature is indicated by:
-
-			/sys/bus/event_source/devices/intel_pt/caps/mtc
-
-		which contains "1" if the feature is supported and
-		"0" otherwise.
-
-		The frequency of MTC packets can also be specified - see
-		mtc_period below.
-
-mtc_period	Specifies how frequently MTC packets are produced - see mtc
-		above for how to determine if MTC packets are supported.
-
-		Valid values are given by:
-
-			/sys/bus/event_source/devices/intel_pt/caps/mtc_periods
-
-		which contains a hexadecimal value, the bits of which represent
-		valid values e.g. bit 2 set means value 2 is valid.
-
-		The mtc_period value is converted to the MTC frequency as:
-
-			CTC-frequency / (2 ^ value)
-
-		e.g. value 3 means one eighth of CTC-frequency
-
-		Where CTC is the hardware crystal clock, the frequency of which
-		can be related to TSC via values provided in cpuid leaf 0x15.
-
-		If an invalid value is entered, the error message
-		will give a list of valid values e.g.
-
-			$ perf record -e intel_pt/mtc_period=15/u uname
-			Invalid mtc_period for intel_pt. Valid values are: 0,3,6,9
-
-		The default value is 3 or the nearest lower value
-		that is supported (0 is always supported).
-
-cyc		Produces CYC timing packets.
-
-		CYC packets provide even finer grain timestamp information than
-		MTC and TSC packets.  A CYC packet contains the number of CPU
-		cycles since the last CYC packet. Unlike MTC and TSC packets,
-		CYC packets are only sent when another packet is also sent.
-
-		Support for this feature is indicated by:
-
-			/sys/bus/event_source/devices/intel_pt/caps/psb_cyc
-
-		which contains "1" if the feature is supported and
-		"0" otherwise.
-
-		The number of CYC packets produced can be reduced by specifying
-		a threshold - see cyc_thresh below.
-
-cyc_thresh	Specifies how frequently CYC packets are produced - see cyc
-		above for how to determine if CYC packets are supported.
-
-		Valid cyc_thresh values are given by:
-
-			/sys/bus/event_source/devices/intel_pt/caps/cycle_thresholds
-
-		which contains a hexadecimal value, the bits of which represent
-		valid values e.g. bit 2 set means value 2 is valid.
-
-		The cyc_thresh value represents the minimum number of CPU cycles
-		that must have passed before a CYC packet can be sent.  The
-		number of CPU cycles is:
-
-			2 ^ (value - 1)
-
-		e.g. value 4 means 8 CPU cycles must pass before a CYC packet
-		can be sent.  Note a CYC packet is still only sent when another
-		packet is sent, not at, e.g. every 8 CPU cycles.
-
-		If an invalid value is entered, the error message
-		will give a list of valid values e.g.
-
-			$ perf record -e intel_pt/cyc,cyc_thresh=15/u uname
-			Invalid cyc_thresh for intel_pt. Valid values are: 0-12
-
-		CYC packets are not requested by default.
-
-pt		Specifies pass-through which enables the 'branch' config term.
-
-		The default config selects 'pt' if it is available, so a user will
-		never need to specify this term.
-
-branch		Enable branch tracing.  Branch tracing is enabled by default so to
-		disable branch tracing use 'branch=0'.
-
-		The default config selects 'branch' if it is available.
-
-ptw		Enable PTWRITE packets which are produced when a ptwrite instruction
-		is executed.
-
-		Support for this feature is indicated by:
-
-			/sys/bus/event_source/devices/intel_pt/caps/ptwrite
-
-		which contains "1" if the feature is supported and
-		"0" otherwise.
-
-fup_on_ptw	Enable a FUP packet to follow the PTWRITE packet.  The FUP packet
-		provides the address of the ptwrite instruction.  In the absence of
-		fup_on_ptw, the decoder will use the address of the previous branch
-		if branch tracing is enabled, otherwise the address will be zero.
-		Note that fup_on_ptw will work even when branch tracing is disabled.
-
-pwr_evt		Enable power events.  The power events provide information about
-		changes to the CPU C-state.
-
-		Support for this feature is indicated by:
-
-			/sys/bus/event_source/devices/intel_pt/caps/power_event_trace
-
-		which contains "1" if the feature is supported and
-		"0" otherwise.
-
-
-AUX area sampling option
-------------------------
-
-To select Intel PT "sampling" the AUX area sampling option can be used:
-
-	--aux-sample
-
-Optionally it can be followed by the sample size in bytes e.g.
-
-	--aux-sample=8192
-
-In addition, the Intel PT event to sample must be defined e.g.
-
-	-e intel_pt//u
-
-Samples on other events will be created containing Intel PT data e.g. the
-following will create Intel PT samples on the branch-misses event, note the
-events must be grouped using {}:
-
-	perf record --aux-sample -e '{intel_pt//u,branch-misses:u}'
-
-An alternative to '--aux-sample' is to add the config term 'aux-sample-size' to
-events.  In this case, the grouping is implied e.g.
-
-	perf record -e intel_pt//u -e branch-misses/aux-sample-size=8192/u
-
-is the same as:
-
-	perf record -e '{intel_pt//u,branch-misses/aux-sample-size=8192/u}'
-
-but allows for also using an address filter e.g.:
-
-	perf record -e intel_pt//u --filter 'filter * @/bin/ls' -e branch-misses/aux-sample-size=8192/u -- ls
-
-It is important to select a sample size that is big enough to contain at least
-one PSB packet.  If not a warning will be displayed:
-
-	Intel PT sample size (%zu) may be too small for PSB period (%zu)
-
-The calculation used for that is: if sample_size <= psb_period + 256 display the
-warning.  When sampling is used, psb_period defaults to 0 (2KiB).
-
-The default sample size is 4KiB.
-
-The sample size is passed in aux_sample_size in struct perf_event_attr.  The
-sample size is limited by the maximum event size which is 64KiB.  It is
-difficult to know how big the event might be without the trace sample attached,
-but the tool validates that the sample size is not greater than 60KiB.
-
-
-new snapshot option
--------------------
-
-The difference between full trace and snapshot from the kernel's perspective is
-that in full trace we don't overwrite trace data that the user hasn't collected
-yet (and indicated that by advancing aux_tail), whereas in snapshot mode we let
-the trace run and overwrite older data in the buffer so that whenever something
-interesting happens, we can stop it and grab a snapshot of what was going on
-around that interesting moment.
-
-To select snapshot mode a new option has been added:
-
-	-S
-
-Optionally it can be followed by the snapshot size e.g.
-
-	-S0x100000
-
-The default snapshot size is the auxtrace mmap size.  If neither auxtrace mmap size
-nor snapshot size is specified, then the default is 4MiB for privileged users
-(or if /proc/sys/kernel/perf_event_paranoid < 0), 128KiB for unprivileged users.
-If an unprivileged user does not specify mmap pages, the mmap pages will be
-reduced as described in the 'new auxtrace mmap size option' section below.
-
-The snapshot size is displayed if the option -vv is used e.g.
-
-	Intel PT snapshot size: %zu
-
-
-new auxtrace mmap size option
----------------------------
-
-Intel PT buffer size is specified by an addition to the -m option e.g.
-
-	-m,16
-
-selects a buffer size of 16 pages i.e. 64KiB.
-
-Note that the existing functionality of -m is unchanged.  The auxtrace mmap size
-is specified by the optional addition of a comma and the value.
-
-The default auxtrace mmap size for Intel PT is 4MiB/page_size for privileged users
-(or if /proc/sys/kernel/perf_event_paranoid < 0), 128KiB for unprivileged users.
-If an unprivileged user does not specify mmap pages, the mmap pages will be
-reduced from the default 512KiB/page_size to 256KiB/page_size, otherwise the
-user is likely to get an error as they exceed their mlock limit (Max locked
-memory as shown in /proc/self/limits).  Note that perf does not count the first
-512KiB (actually /proc/sys/kernel/perf_event_mlock_kb minus 1 page) per cpu
-against the mlock limit so an unprivileged user is allowed 512KiB per cpu plus
-their mlock limit (which defaults to 64KiB but is not multiplied by the number
-of cpus).
-
-In full-trace mode, powers of two are allowed for buffer size, with a minimum
-size of 2 pages.  In snapshot mode or sampling mode, it is the same but the
-minimum size is 1 page.
-
-The mmap size and auxtrace mmap size are displayed if the -vv option is used e.g.
-
-	mmap length 528384
-	auxtrace mmap length 4198400
-
-
-Intel PT modes of operation
----------------------------
-
-Intel PT can be used in 2 modes:
-	full-trace mode
-	sample mode
-	snapshot mode
-
-Full-trace mode traces continuously e.g.
-
-	perf record -e intel_pt//u uname
-
-Sample mode attaches a Intel PT sample to other events e.g.
-
-	perf record --aux-sample -e intel_pt//u -e branch-misses:u
-
-Snapshot mode captures the available data when a signal is sent e.g.
-
-	perf record -v -e intel_pt//u -S ./loopy 1000000000 &
-	[1] 11435
-	kill -USR2 11435
-	Recording AUX area tracing snapshot
-
-Note that the signal sent is SIGUSR2.
-Note that "Recording AUX area tracing snapshot" is displayed because the -v
-option is used.
-
-The 2 modes cannot be used together.
-
-
-Buffer handling
----------------
-
-There may be buffer limitations (i.e. single ToPa entry) which means that actual
-buffer sizes are limited to powers of 2 up to 4MiB (MAX_ORDER).  In order to
-provide other sizes, and in particular an arbitrarily large size, multiple
-buffers are logically concatenated.  However an interrupt must be used to switch
-between buffers.  That has two potential problems:
-	a) the interrupt may not be handled in time so that the current buffer
-	becomes full and some trace data is lost.
-	b) the interrupts may slow the system and affect the performance
-	results.
-
-If trace data is lost, the driver sets 'truncated' in the PERF_RECORD_AUX event
-which the tools report as an error.
-
-In full-trace mode, the driver waits for data to be copied out before allowing
-the (logical) buffer to wrap-around.  If data is not copied out quickly enough,
-again 'truncated' is set in the PERF_RECORD_AUX event.  If the driver has to
-wait, the intel_pt event gets disabled.  Because it is difficult to know when
-that happens, perf tools always re-enable the intel_pt event after copying out
-data.
-
-
-Intel PT and build ids
-----------------------
-
-By default "perf record" post-processes the event stream to find all build ids
-for executables for all addresses sampled.  Deliberately, Intel PT is not
-decoded for that purpose (it would take too long).  Instead the build ids for
-all executables encountered (due to mmap, comm or task events) are included
-in the perf.data file.
-
-To see buildids included in the perf.data file use the command:
-
-	perf buildid-list
-
-If the perf.data file contains Intel PT data, that is the same as:
-
-	perf buildid-list --with-hits
-
-
-Snapshot mode and event disabling
----------------------------------
-
-In order to make a snapshot, the intel_pt event is disabled using an IOCTL,
-namely PERF_EVENT_IOC_DISABLE.  However doing that can also disable the
-collection of side-band information.  In order to prevent that,  a dummy
-software event has been introduced that permits tracking events (like mmaps) to
-continue to be recorded while intel_pt is disabled.  That is important to ensure
-there is complete side-band information to allow the decoding of subsequent
-snapshots.
-
-A test has been created for that.  To find the test:
-
-	perf test list
-	...
-	23: Test using a dummy software event to keep tracking
-
-To run the test:
-
-	perf test 23
-	23: Test using a dummy software event to keep tracking     : Ok
-
-
-perf record modes (nothing new here)
-------------------------------------
-
-perf record essentially operates in one of three modes:
-	per thread
-	per cpu
-	workload only
-
-"per thread" mode is selected by -t or by --per-thread (with -p or -u or just a
-workload).
-"per cpu" is selected by -C or -a.
-"workload only" mode is selected by not using the other options but providing a
-command to run (i.e. the workload).
-
-In per-thread mode an exact list of threads is traced.  There is no inheritance.
-Each thread has its own event buffer.
-
-In per-cpu mode all processes (or processes from the selected cgroup i.e. -G
-option, or processes selected with -p or -u) are traced.  Each cpu has its own
-buffer. Inheritance is allowed.
-
-In workload-only mode, the workload is traced but with per-cpu buffers.
-Inheritance is allowed.  Note that you can now trace a workload in per-thread
-mode by using the --per-thread option.
-
-
-Privileged vs non-privileged users
-----------------------------------
-
-Unless /proc/sys/kernel/perf_event_paranoid is set to -1, unprivileged users
-have memory limits imposed upon them.  That affects what buffer sizes they can
-have as outlined above.
-
-The v4.2 kernel introduced support for a context switch metadata event,
-PERF_RECORD_SWITCH, which allows unprivileged users to see when their processes
-are scheduled out and in, just not by whom, which is left for the
-PERF_RECORD_SWITCH_CPU_WIDE, that is only accessible in system wide context,
-which in turn requires CAP_SYS_ADMIN.
-
-Please see the 45ac1403f564 ("perf: Add PERF_RECORD_SWITCH to indicate context
-switches") commit, that introduces these metadata events for further info.
-
-When working with kernels < v4.2, the following considerations must be taken,
-as the sched:sched_switch tracepoints will be used to receive such information:
-
-Unless /proc/sys/kernel/perf_event_paranoid is set to -1, unprivileged users are
-not permitted to use tracepoints which means there is insufficient side-band
-information to decode Intel PT in per-cpu mode, and potentially workload-only
-mode too if the workload creates new processes.
-
-Note also, that to use tracepoints, read-access to debugfs is required.  So if
-debugfs is not mounted or the user does not have read-access, it will again not
-be possible to decode Intel PT in per-cpu mode.
-
-
-sched_switch tracepoint
------------------------
-
-The sched_switch tracepoint is used to provide side-band data for Intel PT
-decoding in kernels where the PERF_RECORD_SWITCH metadata event isn't
-available.
-
-The sched_switch events are automatically added. e.g. the second event shown
-below:
-
-	$ perf record -vv -e intel_pt//u uname
-	------------------------------------------------------------
-	perf_event_attr:
-	type                             6
-	size                             112
-	config                           0x400
-	{ sample_period, sample_freq }   1
-	sample_type                      IP|TID|TIME|CPU|IDENTIFIER
-	read_format                      ID
-	disabled                         1
-	inherit                          1
-	exclude_kernel                   1
-	exclude_hv                       1
-	enable_on_exec                   1
-	sample_id_all                    1
-	------------------------------------------------------------
-	sys_perf_event_open: pid 31104  cpu 0  group_fd -1  flags 0x8
-	sys_perf_event_open: pid 31104  cpu 1  group_fd -1  flags 0x8
-	sys_perf_event_open: pid 31104  cpu 2  group_fd -1  flags 0x8
-	sys_perf_event_open: pid 31104  cpu 3  group_fd -1  flags 0x8
-	------------------------------------------------------------
-	perf_event_attr:
-	type                             2
-	size                             112
-	config                           0x108
-	{ sample_period, sample_freq }   1
-	sample_type                      IP|TID|TIME|CPU|PERIOD|RAW|IDENTIFIER
-	read_format                      ID
-	inherit                          1
-	sample_id_all                    1
-	exclude_guest                    1
-	------------------------------------------------------------
-	sys_perf_event_open: pid -1  cpu 0  group_fd -1  flags 0x8
-	sys_perf_event_open: pid -1  cpu 1  group_fd -1  flags 0x8
-	sys_perf_event_open: pid -1  cpu 2  group_fd -1  flags 0x8
-	sys_perf_event_open: pid -1  cpu 3  group_fd -1  flags 0x8
-	------------------------------------------------------------
-	perf_event_attr:
-	type                             1
-	size                             112
-	config                           0x9
-	{ sample_period, sample_freq }   1
-	sample_type                      IP|TID|TIME|IDENTIFIER
-	read_format                      ID
-	disabled                         1
-	inherit                          1
-	exclude_kernel                   1
-	exclude_hv                       1
-	mmap                             1
-	comm                             1
-	enable_on_exec                   1
-	task                             1
-	sample_id_all                    1
-	mmap2                            1
-	comm_exec                        1
-	------------------------------------------------------------
-	sys_perf_event_open: pid 31104  cpu 0  group_fd -1  flags 0x8
-	sys_perf_event_open: pid 31104  cpu 1  group_fd -1  flags 0x8
-	sys_perf_event_open: pid 31104  cpu 2  group_fd -1  flags 0x8
-	sys_perf_event_open: pid 31104  cpu 3  group_fd -1  flags 0x8
-	mmap size 528384B
-	AUX area mmap length 4194304
-	perf event ring buffer mmapped per cpu
-	Synthesizing auxtrace information
-	Linux
-	[ perf record: Woken up 1 times to write data ]
-	[ perf record: Captured and wrote 0.042 MB perf.data ]
-
-Note, the sched_switch event is only added if the user is permitted to use it
-and only in per-cpu mode.
-
-Note also, the sched_switch event is only added if TSC packets are requested.
-That is because, in the absence of timing information, the sched_switch events
-cannot be matched against the Intel PT trace.
-
-
-perf script
-===========
-
-By default, perf script will decode trace data found in the perf.data file.
-This can be further controlled by new option --itrace.
-
-
-New --itrace option
--------------------
-
-Having no option is the same as
-
-	--itrace
-
-which, in turn, is the same as
-
-	--itrace=cepwx
-
-The letters are:
-
-	i	synthesize "instructions" events
-	b	synthesize "branches" events
-	x	synthesize "transactions" events
-	w	synthesize "ptwrite" events
-	p	synthesize "power" events
-	c	synthesize branches events (calls only)
-	r	synthesize branches events (returns only)
-	e	synthesize tracing error events
-	d	create a debug log
-	g	synthesize a call chain (use with i or x)
-	l	synthesize last branch entries (use with i or x)
-	s	skip initial number of events
-
-"Instructions" events look like they were recorded by "perf record -e
-instructions".
-
-"Branches" events look like they were recorded by "perf record -e branches". "c"
-and "r" can be combined to get calls and returns.
-
-"Transactions" events correspond to the start or end of transactions. The
-'flags' field can be used in perf script to determine whether the event is a
-tranasaction start, commit or abort.
-
-Note that "instructions", "branches" and "transactions" events depend on code
-flow packets which can be disabled by using the config term "branch=0".  Refer
-to the config terms section above.
-
-"ptwrite" events record the payload of the ptwrite instruction and whether
-"fup_on_ptw" was used.  "ptwrite" events depend on PTWRITE packets which are
-recorded only if the "ptw" config term was used.  Refer to the config terms
-section above.  perf script "synth" field displays "ptwrite" information like
-this: "ip: 0 payload: 0x123456789abcdef0"  where "ip" is 1 if "fup_on_ptw" was
-used.
-
-"Power" events correspond to power event packets and CBR (core-to-bus ratio)
-packets.  While CBR packets are always recorded when tracing is enabled, power
-event packets are recorded only if the "pwr_evt" config term was used.  Refer to
-the config terms section above.  The power events record information about
-C-state changes, whereas CBR is indicative of CPU frequency.  perf script
-"event,synth" fields display information like this:
-	cbr:  cbr: 22 freq: 2189 MHz (200%)
-	mwait:  hints: 0x60 extensions: 0x1
-	pwre:  hw: 0 cstate: 2 sub-cstate: 0
-	exstop:  ip: 1
-	pwrx:  deepest cstate: 2 last cstate: 2 wake reason: 0x4
-Where:
-	"cbr" includes the frequency and the percentage of maximum non-turbo
-	"mwait" shows mwait hints and extensions
-	"pwre" shows C-state transitions (to a C-state deeper than C0) and
-	whether	initiated by hardware
-	"exstop" indicates execution stopped and whether the IP was recorded
-	exactly,
-	"pwrx" indicates return to C0
-For more details refer to the Intel 64 and IA-32 Architectures Software
-Developer Manuals.
-
-Error events show where the decoder lost the trace.  Error events
-are quite important.  Users must know if what they are seeing is a complete
-picture or not.
-
-The "d" option will cause the creation of a file "intel_pt.log" containing all
-decoded packets and instructions.  Note that this option slows down the decoder
-and that the resulting file may be very large.
-
-In addition, the period of the "instructions" event can be specified. e.g.
-
-	--itrace=i10us
-
-sets the period to 10us i.e. one  instruction sample is synthesized for each 10
-microseconds of trace.  Alternatives to "us" are "ms" (milliseconds),
-"ns" (nanoseconds), "t" (TSC ticks) or "i" (instructions).
-
-"ms", "us" and "ns" are converted to TSC ticks.
-
-The timing information included with Intel PT does not give the time of every
-instruction.  Consequently, for the purpose of sampling, the decoder estimates
-the time since the last timing packet based on 1 tick per instruction.  The time
-on the sample is *not* adjusted and reflects the last known value of TSC.
-
-For Intel PT, the default period is 100us.
-
-Setting it to a zero period means "as often as possible".
-
-In the case of Intel PT that is the same as a period of 1 and a unit of
-'instructions' (i.e. --itrace=i1i).
-
-Also the call chain size (default 16, max. 1024) for instructions or
-transactions events can be specified. e.g.
-
-	--itrace=ig32
-	--itrace=xg32
-
-Also the number of last branch entries (default 64, max. 1024) for instructions or
-transactions events can be specified. e.g.
-
-       --itrace=il10
-       --itrace=xl10
-
-Note that last branch entries are cleared for each sample, so there is no overlap
-from one sample to the next.
-
-To disable trace decoding entirely, use the option --no-itrace.
-
-It is also possible to skip events generated (instructions, branches, transactions)
-at the beginning. This is useful to ignore initialization code.
-
-	--itrace=i0nss1000000
-
-skips the first million instructions.
-
-dump option
------------
-
-perf script has an option (-D) to "dump" the events i.e. display the binary
-data.
-
-When -D is used, Intel PT packets are displayed.  The packet decoder does not
-pay attention to PSB packets, but just decodes the bytes - so the packets seen
-by the actual decoder may not be identical in places where the data is corrupt.
-One example of that would be when the buffer-switching interrupt has been too
-slow, and the buffer has been filled completely.  In that case, the last packet
-in the buffer might be truncated and immediately followed by a PSB as the trace
-continues in the next buffer.
-
-To disable the display of Intel PT packets, combine the -D option with
---no-itrace.
-
-
-perf report
-===========
-
-By default, perf report will decode trace data found in the perf.data file.
-This can be further controlled by new option --itrace exactly the same as
-perf script, with the exception that the default is --itrace=igxe.
-
-
-perf inject
-===========
-
-perf inject also accepts the --itrace option in which case tracing data is
-removed and replaced with the synthesized events. e.g.
-
-	perf inject --itrace -i perf.data -o perf.data.new
-
-Below is an example of using Intel PT with autofdo.  It requires autofdo
-(https://github.com/google/autofdo) and gcc version 5.  The bubble
-sort example is from the AutoFDO tutorial (https://gcc.gnu.org/wiki/AutoFDO/Tutorial)
-amended to take the number of elements as a parameter.
-
-	$ gcc-5 -O3 sort.c -o sort_optimized
-	$ ./sort_optimized 30000
-	Bubble sorting array of 30000 elements
-	2254 ms
-
-	$ cat ~/.perfconfig
-	[intel-pt]
-		mispred-all = on
-
-	$ perf record -e intel_pt//u ./sort 3000
-	Bubble sorting array of 3000 elements
-	58 ms
-	[ perf record: Woken up 2 times to write data ]
-	[ perf record: Captured and wrote 3.939 MB perf.data ]
-	$ perf inject -i perf.data -o inj --itrace=i100usle --strip
-	$ ./create_gcov --binary=./sort --profile=inj --gcov=sort.gcov -gcov_version=1
-	$ gcc-5 -O3 -fauto-profile=sort.gcov sort.c -o sort_autofdo
-	$ ./sort_autofdo 30000
-	Bubble sorting array of 30000 elements
-	2155 ms
-
-Note there is currently no advantage to using Intel PT instead of LBR, but
-that may change in the future if greater use is made of the data.
-
-
-PEBS via Intel PT
-=================
-
-Some hardware has the feature to redirect PEBS records to the Intel PT trace.
-Recording is selected by using the aux-output config term e.g.
-
-	perf record -c 10000 -e '{intel_pt/branch=0/,cycles/aux-output/ppp}' uname
-
-Note that currently, software only supports redirecting at most one PEBS event.
-
-To display PEBS events from the Intel PT trace, use the itrace 'o' option e.g.
-
-	perf script --itrace=oe
+Documentation for support for Intel Processor Trace within perf tools' has moved to file perf-intel-pt.txt
diff --git a/tools/perf/Documentation/perf-inject.txt b/tools/perf/Documentation/perf-inject.txt
index a64d6588470e..70969ea73e01 100644
--- a/tools/perf/Documentation/perf-inject.txt
+++ b/tools/perf/Documentation/perf-inject.txt
@@ -66,4 +66,5 @@ include::itrace.txt[]
 
 SEE ALSO
 --------
-linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-archive[1]
+linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-archive[1],
+linkperf:perf-intel-pt[1]
diff --git a/tools/perf/Documentation/perf-intel-pt.txt b/tools/perf/Documentation/perf-intel-pt.txt
new file mode 100644
index 000000000000..456fdcbf26ac
--- /dev/null
+++ b/tools/perf/Documentation/perf-intel-pt.txt
@@ -0,0 +1,1007 @@
+perf-intel-pt(1)
+================
+
+NAME
+----
+perf-intel-pt - Support for Intel Processor Trace within perf tools
+
+SYNOPSIS
+--------
+[verse]
+'perf record' -e intel_pt//
+
+DESCRIPTION
+-----------
+
+Intel Processor Trace (Intel PT) is an extension of Intel Architecture that
+collects information about software execution such as control flow, execution
+modes and timings and formats it into highly compressed binary packets.
+Technical details are documented in the Intel 64 and IA-32 Architectures
+Software Developer Manuals, Chapter 36 Intel Processor Trace.
+
+Intel PT is first supported in Intel Core M and 5th generation Intel Core
+processors that are based on the Intel micro-architecture code name Broadwell.
+
+Trace data is collected by 'perf record' and stored within the perf.data file.
+See below for options to 'perf record'.
+
+Trace data must be 'decoded' which involves walking the object code and matching
+the trace data packets. For example a TNT packet only tells whether a
+conditional branch was taken or not taken, so to make use of that packet the
+decoder must know precisely which instruction was being executed.
+
+Decoding is done on-the-fly.  The decoder outputs samples in the same format as
+samples output by perf hardware events, for example as though the "instructions"
+or "branches" events had been recorded.  Presently 3 tools support this:
+'perf script', 'perf report' and 'perf inject'.  See below for more information
+on using those tools.
+
+The main distinguishing feature of Intel PT is that the decoder can determine
+the exact flow of software execution.  Intel PT can be used to understand why
+and how did software get to a certain point, or behave a certain way.  The
+software does not have to be recompiled, so Intel PT works with debug or release
+builds, however the executed images are needed - which makes use in JIT-compiled
+environments, or with self-modified code, a challenge.  Also symbols need to be
+provided to make sense of addresses.
+
+A limitation of Intel PT is that it produces huge amounts of trace data
+(hundreds of megabytes per second per core) which takes a long time to decode,
+for example two or three orders of magnitude longer than it took to collect.
+Another limitation is the performance impact of tracing, something that will
+vary depending on the use-case and architecture.
+
+
+Quickstart
+----------
+
+It is important to start small.  That is because it is easy to capture vastly
+more data than can possibly be processed.
+
+The simplest thing to do with Intel PT is userspace profiling of small programs.
+Data is captured with 'perf record' e.g. to trace 'ls' userspace-only:
+
+	perf record -e intel_pt//u ls
+
+And profiled with 'perf report' e.g.
+
+	perf report
+
+To also trace kernel space presents a problem, namely kernel self-modifying
+code.  A fairly good kernel image is available in /proc/kcore but to get an
+accurate image a copy of /proc/kcore needs to be made under the same conditions
+as the data capture.  A script perf-with-kcore can do that, but beware that the
+script makes use of 'sudo' to copy /proc/kcore.  If you have perf installed
+locally from the source tree you can do:
+
+	~/libexec/perf-core/perf-with-kcore record pt_ls -e intel_pt// -- ls
+
+which will create a directory named 'pt_ls' and put the perf.data file and
+copies of /proc/kcore, /proc/kallsyms and /proc/modules into it.  Then to use
+'perf report' becomes:
+
+	~/libexec/perf-core/perf-with-kcore report pt_ls
+
+Because samples are synthesized after-the-fact, the sampling period can be
+selected for reporting. e.g. sample every microsecond
+
+	~/libexec/perf-core/perf-with-kcore report pt_ls --itrace=i1usge
+
+See the sections below for more information about the --itrace option.
+
+Beware the smaller the period, the more samples that are produced, and the
+longer it takes to process them.
+
+Also note that the coarseness of Intel PT timing information will start to
+distort the statistical value of the sampling as the sampling period becomes
+smaller.
+
+To represent software control flow, "branches" samples are produced.  By default
+a branch sample is synthesized for every single branch.  To get an idea what
+data is available you can use the 'perf script' tool with all itrace sampling
+options, which will list all the samples.
+
+	perf record -e intel_pt//u ls
+	perf script --itrace=ibxwpe
+
+An interesting field that is not printed by default is 'flags' which can be
+displayed as follows:
+
+	perf script --itrace=ibxwpe -F+flags
+
+The flags are "bcrosyiABEx" which stand for branch, call, return, conditional,
+system, asynchronous, interrupt, transaction abort, trace begin, trace end, and
+in transaction, respectively.
+
+Another interesting field that is not printed by default is 'ipc' which can be
+displayed as follows:
+
+	perf script --itrace=be -F+ipc
+
+There are two ways that instructions-per-cycle (IPC) can be calculated depending
+on the recording.
+
+If the 'cyc' config term (see config terms section below) was used, then IPC is
+calculated using the cycle count from CYC packets, otherwise MTC packets are
+used - refer to the 'mtc' config term.  When MTC is used, however, the values
+are less accurate because the timing is less accurate.
+
+Because Intel PT does not update the cycle count on every branch or instruction,
+the values will often be zero.  When there are values, they will be the number
+of instructions and number of cycles since the last update, and thus represent
+the average IPC since the last IPC for that event type.  Note IPC for "branches"
+events is calculated separately from IPC for "instructions" events.
+
+Also note that the IPC instruction count may or may not include the current
+instruction.  If the cycle count is associated with an asynchronous branch
+(e.g. page fault or interrupt), then the instruction count does not include the
+current instruction, otherwise it does.  That is consistent with whether or not
+that instruction has retired when the cycle count is updated.
+
+Another note, in the case of "branches" events, non-taken branches are not
+presently sampled, so IPC values for them do not appear e.g. a CYC packet with a
+TNT packet that starts with a non-taken branch.  To see every possible IPC
+value, "instructions" events can be used e.g. --itrace=i0ns
+
+While it is possible to create scripts to analyze the data, an alternative
+approach is available to export the data to a sqlite or postgresql database.
+Refer to script export-to-sqlite.py or export-to-postgresql.py for more details,
+and to script exported-sql-viewer.py for an example of using the database.
+
+There is also script intel-pt-events.py which provides an example of how to
+unpack the raw data for power events and PTWRITE.
+
+As mentioned above, it is easy to capture too much data.  One way to limit the
+data captured is to use 'snapshot' mode which is explained further below.
+Refer to 'new snapshot option' and 'Intel PT modes of operation' further below.
+
+Another problem that will be experienced is decoder errors.  They can be caused
+by inability to access the executed image, self-modified or JIT-ed code, or the
+inability to match side-band information (such as context switches and mmaps)
+which results in the decoder not knowing what code was executed.
+
+There is also the problem of perf not being able to copy the data fast enough,
+resulting in data lost because the buffer was full.  See 'Buffer handling' below
+for more details.
+
+
+perf record
+-----------
+
+new event
+~~~~~~~~~
+
+The Intel PT kernel driver creates a new PMU for Intel PT.  PMU events are
+selected by providing the PMU name followed by the "config" separated by slashes.
+An enhancement has been made to allow default "config" e.g. the option
+
+	-e intel_pt//
+
+will use a default config value.  Currently that is the same as
+
+	-e intel_pt/tsc,noretcomp=0/
+
+which is the same as
+
+	-e intel_pt/tsc=1,noretcomp=0/
+
+Note there are now new config terms - see section 'config terms' further below.
+
+The config terms are listed in /sys/devices/intel_pt/format.  They are bit
+fields within the config member of the struct perf_event_attr which is
+passed to the kernel by the perf_event_open system call.  They correspond to bit
+fields in the IA32_RTIT_CTL MSR.  Here is a list of them and their definitions:
+
+	$ grep -H . /sys/bus/event_source/devices/intel_pt/format/*
+	/sys/bus/event_source/devices/intel_pt/format/cyc:config:1
+	/sys/bus/event_source/devices/intel_pt/format/cyc_thresh:config:19-22
+	/sys/bus/event_source/devices/intel_pt/format/mtc:config:9
+	/sys/bus/event_source/devices/intel_pt/format/mtc_period:config:14-17
+	/sys/bus/event_source/devices/intel_pt/format/noretcomp:config:11
+	/sys/bus/event_source/devices/intel_pt/format/psb_period:config:24-27
+	/sys/bus/event_source/devices/intel_pt/format/tsc:config:10
+
+Note that the default config must be overridden for each term i.e.
+
+	-e intel_pt/noretcomp=0/
+
+is the same as:
+
+	-e intel_pt/tsc=1,noretcomp=0/
+
+So, to disable TSC packets use:
+
+	-e intel_pt/tsc=0/
+
+It is also possible to specify the config value explicitly:
+
+	-e intel_pt/config=0x400/
+
+Note that, as with all events, the event is suffixed with event modifiers:
+
+	u	userspace
+	k	kernel
+	h	hypervisor
+	G	guest
+	H	host
+	p	precise ip
+
+'h', 'G' and 'H' are for virtualization which is not supported by Intel PT.
+'p' is also not relevant to Intel PT.  So only options 'u' and 'k' are
+meaningful for Intel PT.
+
+perf_event_attr is displayed if the -vv option is used e.g.
+
+	------------------------------------------------------------
+	perf_event_attr:
+	type                             6
+	size                             112
+	config                           0x400
+	{ sample_period, sample_freq }   1
+	sample_type                      IP|TID|TIME|CPU|IDENTIFIER
+	read_format                      ID
+	disabled                         1
+	inherit                          1
+	exclude_kernel                   1
+	exclude_hv                       1
+	enable_on_exec                   1
+	sample_id_all                    1
+	------------------------------------------------------------
+	sys_perf_event_open: pid 31104  cpu 0  group_fd -1  flags 0x8
+	sys_perf_event_open: pid 31104  cpu 1  group_fd -1  flags 0x8
+	sys_perf_event_open: pid 31104  cpu 2  group_fd -1  flags 0x8
+	sys_perf_event_open: pid 31104  cpu 3  group_fd -1  flags 0x8
+	------------------------------------------------------------
+
+
+config terms
+~~~~~~~~~~~~
+
+The June 2015 version of Intel 64 and IA-32 Architectures Software Developer
+Manuals, Chapter 36 Intel Processor Trace, defined new Intel PT features.
+Some of the features are reflect in new config terms.  All the config terms are
+described below.
+
+tsc		Always supported.  Produces TSC timestamp packets to provide
+		timing information.  In some cases it is possible to decode
+		without timing information, for example a per-thread context
+		that does not overlap executable memory maps.
+
+		The default config selects tsc (i.e. tsc=1).
+
+noretcomp	Always supported.  Disables "return compression" so a TIP packet
+		is produced when a function returns.  Causes more packets to be
+		produced but might make decoding more reliable.
+
+		The default config does not select noretcomp (i.e. noretcomp=0).
+
+psb_period	Allows the frequency of PSB packets to be specified.
+
+		The PSB packet is a synchronization packet that provides a
+		starting point for decoding or recovery from errors.
+
+		Support for psb_period is indicated by:
+
+			/sys/bus/event_source/devices/intel_pt/caps/psb_cyc
+
+		which contains "1" if the feature is supported and "0"
+		otherwise.
+
+		Valid values are given by:
+
+			/sys/bus/event_source/devices/intel_pt/caps/psb_periods
+
+		which contains a hexadecimal value, the bits of which represent
+		valid values e.g. bit 2 set means value 2 is valid.
+
+		The psb_period value is converted to the approximate number of
+		trace bytes between PSB packets as:
+
+			2 ^ (value + 11)
+
+		e.g. value 3 means 16KiB bytes between PSBs
+
+		If an invalid value is entered, the error message
+		will give a list of valid values e.g.
+
+			$ perf record -e intel_pt/psb_period=15/u uname
+			Invalid psb_period for intel_pt. Valid values are: 0-5
+
+		If MTC packets are selected, the default config selects a value
+		of 3 (i.e. psb_period=3) or the nearest lower value that is
+		supported (0 is always supported).  Otherwise the default is 0.
+
+		If decoding is expected to be reliable and the buffer is large
+		then a large PSB period can be used.
+
+		Because a TSC packet is produced with PSB, the PSB period can
+		also affect the granularity to timing information in the absence
+		of MTC or CYC.
+
+mtc		Produces MTC timing packets.
+
+		MTC packets provide finer grain timestamp information than TSC
+		packets.  MTC packets record time using the hardware crystal
+		clock (CTC) which is related to TSC packets using a TMA packet.
+
+		Support for this feature is indicated by:
+
+			/sys/bus/event_source/devices/intel_pt/caps/mtc
+
+		which contains "1" if the feature is supported and
+		"0" otherwise.
+
+		The frequency of MTC packets can also be specified - see
+		mtc_period below.
+
+mtc_period	Specifies how frequently MTC packets are produced - see mtc
+		above for how to determine if MTC packets are supported.
+
+		Valid values are given by:
+
+			/sys/bus/event_source/devices/intel_pt/caps/mtc_periods
+
+		which contains a hexadecimal value, the bits of which represent
+		valid values e.g. bit 2 set means value 2 is valid.
+
+		The mtc_period value is converted to the MTC frequency as:
+
+			CTC-frequency / (2 ^ value)
+
+		e.g. value 3 means one eighth of CTC-frequency
+
+		Where CTC is the hardware crystal clock, the frequency of which
+		can be related to TSC via values provided in cpuid leaf 0x15.
+
+		If an invalid value is entered, the error message
+		will give a list of valid values e.g.
+
+			$ perf record -e intel_pt/mtc_period=15/u uname
+			Invalid mtc_period for intel_pt. Valid values are: 0,3,6,9
+
+		The default value is 3 or the nearest lower value
+		that is supported (0 is always supported).
+
+cyc		Produces CYC timing packets.
+
+		CYC packets provide even finer grain timestamp information than
+		MTC and TSC packets.  A CYC packet contains the number of CPU
+		cycles since the last CYC packet. Unlike MTC and TSC packets,
+		CYC packets are only sent when another packet is also sent.
+
+		Support for this feature is indicated by:
+
+			/sys/bus/event_source/devices/intel_pt/caps/psb_cyc
+
+		which contains "1" if the feature is supported and
+		"0" otherwise.
+
+		The number of CYC packets produced can be reduced by specifying
+		a threshold - see cyc_thresh below.
+
+cyc_thresh	Specifies how frequently CYC packets are produced - see cyc
+		above for how to determine if CYC packets are supported.
+
+		Valid cyc_thresh values are given by:
+
+			/sys/bus/event_source/devices/intel_pt/caps/cycle_thresholds
+
+		which contains a hexadecimal value, the bits of which represent
+		valid values e.g. bit 2 set means value 2 is valid.
+
+		The cyc_thresh value represents the minimum number of CPU cycles
+		that must have passed before a CYC packet can be sent.  The
+		number of CPU cycles is:
+
+			2 ^ (value - 1)
+
+		e.g. value 4 means 8 CPU cycles must pass before a CYC packet
+		can be sent.  Note a CYC packet is still only sent when another
+		packet is sent, not at, e.g. every 8 CPU cycles.
+
+		If an invalid value is entered, the error message
+		will give a list of valid values e.g.
+
+			$ perf record -e intel_pt/cyc,cyc_thresh=15/u uname
+			Invalid cyc_thresh for intel_pt. Valid values are: 0-12
+
+		CYC packets are not requested by default.
+
+pt		Specifies pass-through which enables the 'branch' config term.
+
+		The default config selects 'pt' if it is available, so a user will
+		never need to specify this term.
+
+branch		Enable branch tracing.  Branch tracing is enabled by default so to
+		disable branch tracing use 'branch=0'.
+
+		The default config selects 'branch' if it is available.
+
+ptw		Enable PTWRITE packets which are produced when a ptwrite instruction
+		is executed.
+
+		Support for this feature is indicated by:
+
+			/sys/bus/event_source/devices/intel_pt/caps/ptwrite
+
+		which contains "1" if the feature is supported and
+		"0" otherwise.
+
+fup_on_ptw	Enable a FUP packet to follow the PTWRITE packet.  The FUP packet
+		provides the address of the ptwrite instruction.  In the absence of
+		fup_on_ptw, the decoder will use the address of the previous branch
+		if branch tracing is enabled, otherwise the address will be zero.
+		Note that fup_on_ptw will work even when branch tracing is disabled.
+
+pwr_evt		Enable power events.  The power events provide information about
+		changes to the CPU C-state.
+
+		Support for this feature is indicated by:
+
+			/sys/bus/event_source/devices/intel_pt/caps/power_event_trace
+
+		which contains "1" if the feature is supported and
+		"0" otherwise.
+
+
+AUX area sampling option
+~~~~~~~~~~~~~~~~~~~~~~~~
+
+To select Intel PT "sampling" the AUX area sampling option can be used:
+
+	--aux-sample
+
+Optionally it can be followed by the sample size in bytes e.g.
+
+	--aux-sample=8192
+
+In addition, the Intel PT event to sample must be defined e.g.
+
+	-e intel_pt//u
+
+Samples on other events will be created containing Intel PT data e.g. the
+following will create Intel PT samples on the branch-misses event, note the
+events must be grouped using {}:
+
+	perf record --aux-sample -e '{intel_pt//u,branch-misses:u}'
+
+An alternative to '--aux-sample' is to add the config term 'aux-sample-size' to
+events.  In this case, the grouping is implied e.g.
+
+	perf record -e intel_pt//u -e branch-misses/aux-sample-size=8192/u
+
+is the same as:
+
+	perf record -e '{intel_pt//u,branch-misses/aux-sample-size=8192/u}'
+
+but allows for also using an address filter e.g.:
+
+	perf record -e intel_pt//u --filter 'filter * @/bin/ls' -e branch-misses/aux-sample-size=8192/u -- ls
+
+It is important to select a sample size that is big enough to contain at least
+one PSB packet.  If not a warning will be displayed:
+
+	Intel PT sample size (%zu) may be too small for PSB period (%zu)
+
+The calculation used for that is: if sample_size <= psb_period + 256 display the
+warning.  When sampling is used, psb_period defaults to 0 (2KiB).
+
+The default sample size is 4KiB.
+
+The sample size is passed in aux_sample_size in struct perf_event_attr.  The
+sample size is limited by the maximum event size which is 64KiB.  It is
+difficult to know how big the event might be without the trace sample attached,
+but the tool validates that the sample size is not greater than 60KiB.
+
+
+new snapshot option
+~~~~~~~~~~~~~~~~~~~
+
+The difference between full trace and snapshot from the kernel's perspective is
+that in full trace we don't overwrite trace data that the user hasn't collected
+yet (and indicated that by advancing aux_tail), whereas in snapshot mode we let
+the trace run and overwrite older data in the buffer so that whenever something
+interesting happens, we can stop it and grab a snapshot of what was going on
+around that interesting moment.
+
+To select snapshot mode a new option has been added:
+
+	-S
+
+Optionally it can be followed by the snapshot size e.g.
+
+	-S0x100000
+
+The default snapshot size is the auxtrace mmap size.  If neither auxtrace mmap size
+nor snapshot size is specified, then the default is 4MiB for privileged users
+(or if /proc/sys/kernel/perf_event_paranoid < 0), 128KiB for unprivileged users.
+If an unprivileged user does not specify mmap pages, the mmap pages will be
+reduced as described in the 'new auxtrace mmap size option' section below.
+
+The snapshot size is displayed if the option -vv is used e.g.
+
+	Intel PT snapshot size: %zu
+
+
+new auxtrace mmap size option
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Intel PT buffer size is specified by an addition to the -m option e.g.
+
+	-m,16
+
+selects a buffer size of 16 pages i.e. 64KiB.
+
+Note that the existing functionality of -m is unchanged.  The auxtrace mmap size
+is specified by the optional addition of a comma and the value.
+
+The default auxtrace mmap size for Intel PT is 4MiB/page_size for privileged users
+(or if /proc/sys/kernel/perf_event_paranoid < 0), 128KiB for unprivileged users.
+If an unprivileged user does not specify mmap pages, the mmap pages will be
+reduced from the default 512KiB/page_size to 256KiB/page_size, otherwise the
+user is likely to get an error as they exceed their mlock limit (Max locked
+memory as shown in /proc/self/limits).  Note that perf does not count the first
+512KiB (actually /proc/sys/kernel/perf_event_mlock_kb minus 1 page) per cpu
+against the mlock limit so an unprivileged user is allowed 512KiB per cpu plus
+their mlock limit (which defaults to 64KiB but is not multiplied by the number
+of cpus).
+
+In full-trace mode, powers of two are allowed for buffer size, with a minimum
+size of 2 pages.  In snapshot mode or sampling mode, it is the same but the
+minimum size is 1 page.
+
+The mmap size and auxtrace mmap size are displayed if the -vv option is used e.g.
+
+	mmap length 528384
+	auxtrace mmap length 4198400
+
+
+Intel PT modes of operation
+~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Intel PT can be used in 2 modes:
+	full-trace mode
+	sample mode
+	snapshot mode
+
+Full-trace mode traces continuously e.g.
+
+	perf record -e intel_pt//u uname
+
+Sample mode attaches a Intel PT sample to other events e.g.
+
+	perf record --aux-sample -e intel_pt//u -e branch-misses:u
+
+Snapshot mode captures the available data when a signal is sent e.g.
+
+	perf record -v -e intel_pt//u -S ./loopy 1000000000 &
+	[1] 11435
+	kill -USR2 11435
+	Recording AUX area tracing snapshot
+
+Note that the signal sent is SIGUSR2.
+Note that "Recording AUX area tracing snapshot" is displayed because the -v
+option is used.
+
+The 2 modes cannot be used together.
+
+
+Buffer handling
+~~~~~~~~~~~~~~~
+
+There may be buffer limitations (i.e. single ToPa entry) which means that actual
+buffer sizes are limited to powers of 2 up to 4MiB (MAX_ORDER).  In order to
+provide other sizes, and in particular an arbitrarily large size, multiple
+buffers are logically concatenated.  However an interrupt must be used to switch
+between buffers.  That has two potential problems:
+	a) the interrupt may not be handled in time so that the current buffer
+	becomes full and some trace data is lost.
+	b) the interrupts may slow the system and affect the performance
+	results.
+
+If trace data is lost, the driver sets 'truncated' in the PERF_RECORD_AUX event
+which the tools report as an error.
+
+In full-trace mode, the driver waits for data to be copied out before allowing
+the (logical) buffer to wrap-around.  If data is not copied out quickly enough,
+again 'truncated' is set in the PERF_RECORD_AUX event.  If the driver has to
+wait, the intel_pt event gets disabled.  Because it is difficult to know when
+that happens, perf tools always re-enable the intel_pt event after copying out
+data.
+
+
+Intel PT and build ids
+~~~~~~~~~~~~~~~~~~~~~~
+
+By default "perf record" post-processes the event stream to find all build ids
+for executables for all addresses sampled.  Deliberately, Intel PT is not
+decoded for that purpose (it would take too long).  Instead the build ids for
+all executables encountered (due to mmap, comm or task events) are included
+in the perf.data file.
+
+To see buildids included in the perf.data file use the command:
+
+	perf buildid-list
+
+If the perf.data file contains Intel PT data, that is the same as:
+
+	perf buildid-list --with-hits
+
+
+Snapshot mode and event disabling
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+In order to make a snapshot, the intel_pt event is disabled using an IOCTL,
+namely PERF_EVENT_IOC_DISABLE.  However doing that can also disable the
+collection of side-band information.  In order to prevent that,  a dummy
+software event has been introduced that permits tracking events (like mmaps) to
+continue to be recorded while intel_pt is disabled.  That is important to ensure
+there is complete side-band information to allow the decoding of subsequent
+snapshots.
+
+A test has been created for that.  To find the test:
+
+	perf test list
+	...
+	23: Test using a dummy software event to keep tracking
+
+To run the test:
+
+	perf test 23
+	23: Test using a dummy software event to keep tracking     : Ok
+
+
+perf record modes (nothing new here)
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+perf record essentially operates in one of three modes:
+	per thread
+	per cpu
+	workload only
+
+"per thread" mode is selected by -t or by --per-thread (with -p or -u or just a
+workload).
+"per cpu" is selected by -C or -a.
+"workload only" mode is selected by not using the other options but providing a
+command to run (i.e. the workload).
+
+In per-thread mode an exact list of threads is traced.  There is no inheritance.
+Each thread has its own event buffer.
+
+In per-cpu mode all processes (or processes from the selected cgroup i.e. -G
+option, or processes selected with -p or -u) are traced.  Each cpu has its own
+buffer. Inheritance is allowed.
+
+In workload-only mode, the workload is traced but with per-cpu buffers.
+Inheritance is allowed.  Note that you can now trace a workload in per-thread
+mode by using the --per-thread option.
+
+
+Privileged vs non-privileged users
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Unless /proc/sys/kernel/perf_event_paranoid is set to -1, unprivileged users
+have memory limits imposed upon them.  That affects what buffer sizes they can
+have as outlined above.
+
+The v4.2 kernel introduced support for a context switch metadata event,
+PERF_RECORD_SWITCH, which allows unprivileged users to see when their processes
+are scheduled out and in, just not by whom, which is left for the
+PERF_RECORD_SWITCH_CPU_WIDE, that is only accessible in system wide context,
+which in turn requires CAP_SYS_ADMIN.
+
+Please see the 45ac1403f564 ("perf: Add PERF_RECORD_SWITCH to indicate context
+switches") commit, that introduces these metadata events for further info.
+
+When working with kernels < v4.2, the following considerations must be taken,
+as the sched:sched_switch tracepoints will be used to receive such information:
+
+Unless /proc/sys/kernel/perf_event_paranoid is set to -1, unprivileged users are
+not permitted to use tracepoints which means there is insufficient side-band
+information to decode Intel PT in per-cpu mode, and potentially workload-only
+mode too if the workload creates new processes.
+
+Note also, that to use tracepoints, read-access to debugfs is required.  So if
+debugfs is not mounted or the user does not have read-access, it will again not
+be possible to decode Intel PT in per-cpu mode.
+
+
+sched_switch tracepoint
+~~~~~~~~~~~~~~~~~~~~~~~
+
+The sched_switch tracepoint is used to provide side-band data for Intel PT
+decoding in kernels where the PERF_RECORD_SWITCH metadata event isn't
+available.
+
+The sched_switch events are automatically added. e.g. the second event shown
+below:
+
+	$ perf record -vv -e intel_pt//u uname
+	------------------------------------------------------------
+	perf_event_attr:
+	type                             6
+	size                             112
+	config                           0x400
+	{ sample_period, sample_freq }   1
+	sample_type                      IP|TID|TIME|CPU|IDENTIFIER
+	read_format                      ID
+	disabled                         1
+	inherit                          1
+	exclude_kernel                   1
+	exclude_hv                       1
+	enable_on_exec                   1
+	sample_id_all                    1
+	------------------------------------------------------------
+	sys_perf_event_open: pid 31104  cpu 0  group_fd -1  flags 0x8
+	sys_perf_event_open: pid 31104  cpu 1  group_fd -1  flags 0x8
+	sys_perf_event_open: pid 31104  cpu 2  group_fd -1  flags 0x8
+	sys_perf_event_open: pid 31104  cpu 3  group_fd -1  flags 0x8
+	------------------------------------------------------------
+	perf_event_attr:
+	type                             2
+	size                             112
+	config                           0x108
+	{ sample_period, sample_freq }   1
+	sample_type                      IP|TID|TIME|CPU|PERIOD|RAW|IDENTIFIER
+	read_format                      ID
+	inherit                          1
+	sample_id_all                    1
+	exclude_guest                    1
+	------------------------------------------------------------
+	sys_perf_event_open: pid -1  cpu 0  group_fd -1  flags 0x8
+	sys_perf_event_open: pid -1  cpu 1  group_fd -1  flags 0x8
+	sys_perf_event_open: pid -1  cpu 2  group_fd -1  flags 0x8
+	sys_perf_event_open: pid -1  cpu 3  group_fd -1  flags 0x8
+	------------------------------------------------------------
+	perf_event_attr:
+	type                             1
+	size                             112
+	config                           0x9
+	{ sample_period, sample_freq }   1
+	sample_type                      IP|TID|TIME|IDENTIFIER
+	read_format                      ID
+	disabled                         1
+	inherit                          1
+	exclude_kernel                   1
+	exclude_hv                       1
+	mmap                             1
+	comm                             1
+	enable_on_exec                   1
+	task                             1
+	sample_id_all                    1
+	mmap2                            1
+	comm_exec                        1
+	------------------------------------------------------------
+	sys_perf_event_open: pid 31104  cpu 0  group_fd -1  flags 0x8
+	sys_perf_event_open: pid 31104  cpu 1  group_fd -1  flags 0x8
+	sys_perf_event_open: pid 31104  cpu 2  group_fd -1  flags 0x8
+	sys_perf_event_open: pid 31104  cpu 3  group_fd -1  flags 0x8
+	mmap size 528384B
+	AUX area mmap length 4194304
+	perf event ring buffer mmapped per cpu
+	Synthesizing auxtrace information
+	Linux
+	[ perf record: Woken up 1 times to write data ]
+	[ perf record: Captured and wrote 0.042 MB perf.data ]
+
+Note, the sched_switch event is only added if the user is permitted to use it
+and only in per-cpu mode.
+
+Note also, the sched_switch event is only added if TSC packets are requested.
+That is because, in the absence of timing information, the sched_switch events
+cannot be matched against the Intel PT trace.
+
+
+perf script
+-----------
+
+By default, perf script will decode trace data found in the perf.data file.
+This can be further controlled by new option --itrace.
+
+
+New --itrace option
+~~~~~~~~~~~~~~~~~~~
+
+Having no option is the same as
+
+	--itrace
+
+which, in turn, is the same as
+
+	--itrace=cepwx
+
+The letters are:
+
+	i	synthesize "instructions" events
+	b	synthesize "branches" events
+	x	synthesize "transactions" events
+	w	synthesize "ptwrite" events
+	p	synthesize "power" events
+	c	synthesize branches events (calls only)
+	r	synthesize branches events (returns only)
+	e	synthesize tracing error events
+	d	create a debug log
+	g	synthesize a call chain (use with i or x)
+	l	synthesize last branch entries (use with i or x)
+	s	skip initial number of events
+
+"Instructions" events look like they were recorded by "perf record -e
+instructions".
+
+"Branches" events look like they were recorded by "perf record -e branches". "c"
+and "r" can be combined to get calls and returns.
+
+"Transactions" events correspond to the start or end of transactions. The
+'flags' field can be used in perf script to determine whether the event is a
+tranasaction start, commit or abort.
+
+Note that "instructions", "branches" and "transactions" events depend on code
+flow packets which can be disabled by using the config term "branch=0".  Refer
+to the config terms section above.
+
+"ptwrite" events record the payload of the ptwrite instruction and whether
+"fup_on_ptw" was used.  "ptwrite" events depend on PTWRITE packets which are
+recorded only if the "ptw" config term was used.  Refer to the config terms
+section above.  perf script "synth" field displays "ptwrite" information like
+this: "ip: 0 payload: 0x123456789abcdef0"  where "ip" is 1 if "fup_on_ptw" was
+used.
+
+"Power" events correspond to power event packets and CBR (core-to-bus ratio)
+packets.  While CBR packets are always recorded when tracing is enabled, power
+event packets are recorded only if the "pwr_evt" config term was used.  Refer to
+the config terms section above.  The power events record information about
+C-state changes, whereas CBR is indicative of CPU frequency.  perf script
+"event,synth" fields display information like this:
+	cbr:  cbr: 22 freq: 2189 MHz (200%)
+	mwait:  hints: 0x60 extensions: 0x1
+	pwre:  hw: 0 cstate: 2 sub-cstate: 0
+	exstop:  ip: 1
+	pwrx:  deepest cstate: 2 last cstate: 2 wake reason: 0x4
+Where:
+	"cbr" includes the frequency and the percentage of maximum non-turbo
+	"mwait" shows mwait hints and extensions
+	"pwre" shows C-state transitions (to a C-state deeper than C0) and
+	whether	initiated by hardware
+	"exstop" indicates execution stopped and whether the IP was recorded
+	exactly,
+	"pwrx" indicates return to C0
+For more details refer to the Intel 64 and IA-32 Architectures Software
+Developer Manuals.
+
+Error events show where the decoder lost the trace.  Error events
+are quite important.  Users must know if what they are seeing is a complete
+picture or not.
+
+The "d" option will cause the creation of a file "intel_pt.log" containing all
+decoded packets and instructions.  Note that this option slows down the decoder
+and that the resulting file may be very large.
+
+In addition, the period of the "instructions" event can be specified. e.g.
+
+	--itrace=i10us
+
+sets the period to 10us i.e. one  instruction sample is synthesized for each 10
+microseconds of trace.  Alternatives to "us" are "ms" (milliseconds),
+"ns" (nanoseconds), "t" (TSC ticks) or "i" (instructions).
+
+"ms", "us" and "ns" are converted to TSC ticks.
+
+The timing information included with Intel PT does not give the time of every
+instruction.  Consequently, for the purpose of sampling, the decoder estimates
+the time since the last timing packet based on 1 tick per instruction.  The time
+on the sample is *not* adjusted and reflects the last known value of TSC.
+
+For Intel PT, the default period is 100us.
+
+Setting it to a zero period means "as often as possible".
+
+In the case of Intel PT that is the same as a period of 1 and a unit of
+'instructions' (i.e. --itrace=i1i).
+
+Also the call chain size (default 16, max. 1024) for instructions or
+transactions events can be specified. e.g.
+
+	--itrace=ig32
+	--itrace=xg32
+
+Also the number of last branch entries (default 64, max. 1024) for instructions or
+transactions events can be specified. e.g.
+
+       --itrace=il10
+       --itrace=xl10
+
+Note that last branch entries are cleared for each sample, so there is no overlap
+from one sample to the next.
+
+To disable trace decoding entirely, use the option --no-itrace.
+
+It is also possible to skip events generated (instructions, branches, transactions)
+at the beginning. This is useful to ignore initialization code.
+
+	--itrace=i0nss1000000
+
+skips the first million instructions.
+
+dump option
+~~~~~~~~~~~
+
+perf script has an option (-D) to "dump" the events i.e. display the binary
+data.
+
+When -D is used, Intel PT packets are displayed.  The packet decoder does not
+pay attention to PSB packets, but just decodes the bytes - so the packets seen
+by the actual decoder may not be identical in places where the data is corrupt.
+One example of that would be when the buffer-switching interrupt has been too
+slow, and the buffer has been filled completely.  In that case, the last packet
+in the buffer might be truncated and immediately followed by a PSB as the trace
+continues in the next buffer.
+
+To disable the display of Intel PT packets, combine the -D option with
+--no-itrace.
+
+
+perf report
+-----------
+
+By default, perf report will decode trace data found in the perf.data file.
+This can be further controlled by new option --itrace exactly the same as
+perf script, with the exception that the default is --itrace=igxe.
+
+
+perf inject
+-----------
+
+perf inject also accepts the --itrace option in which case tracing data is
+removed and replaced with the synthesized events. e.g.
+
+	perf inject --itrace -i perf.data -o perf.data.new
+
+Below is an example of using Intel PT with autofdo.  It requires autofdo
+(https://github.com/google/autofdo) and gcc version 5.  The bubble
+sort example is from the AutoFDO tutorial (https://gcc.gnu.org/wiki/AutoFDO/Tutorial)
+amended to take the number of elements as a parameter.
+
+	$ gcc-5 -O3 sort.c -o sort_optimized
+	$ ./sort_optimized 30000
+	Bubble sorting array of 30000 elements
+	2254 ms
+
+	$ cat ~/.perfconfig
+	[intel-pt]
+		mispred-all = on
+
+	$ perf record -e intel_pt//u ./sort 3000
+	Bubble sorting array of 3000 elements
+	58 ms
+	[ perf record: Woken up 2 times to write data ]
+	[ perf record: Captured and wrote 3.939 MB perf.data ]
+	$ perf inject -i perf.data -o inj --itrace=i100usle --strip
+	$ ./create_gcov --binary=./sort --profile=inj --gcov=sort.gcov -gcov_version=1
+	$ gcc-5 -O3 -fauto-profile=sort.gcov sort.c -o sort_autofdo
+	$ ./sort_autofdo 30000
+	Bubble sorting array of 30000 elements
+	2155 ms
+
+Note there is currently no advantage to using Intel PT instead of LBR, but
+that may change in the future if greater use is made of the data.
+
+
+PEBS via Intel PT
+-----------------
+
+Some hardware has the feature to redirect PEBS records to the Intel PT trace.
+Recording is selected by using the aux-output config term e.g.
+
+	perf record -c 10000 -e '{intel_pt/branch=0/,cycles/aux-output/ppp}' uname
+
+Note that currently, software only supports redirecting at most one PEBS event.
+
+To display PEBS events from the Intel PT trace, use the itrace 'o' option e.g.
+
+	perf script --itrace=oe
+
+
+SEE ALSO
+--------
+
+linkperf:perf-record[1], linkperf:perf-script[1], linkperf:perf-report[1],
+linkperf:perf-inject[1]
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index b23a4012a606..7f4db7592467 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -589,4 +589,4 @@ appended unit character - B/K/M/G
 
 SEE ALSO
 --------
-linkperf:perf-stat[1], linkperf:perf-list[1]
+linkperf:perf-stat[1], linkperf:perf-list[1], linkperf:perf-intel-pt[1]
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index db61f16ffa56..bd0a029d4c08 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -546,4 +546,5 @@ include::callchain-overhead-calculation.txt[]
 
 SEE ALSO
 --------
-linkperf:perf-stat[1], linkperf:perf-annotate[1], linkperf:perf-record[1]
+linkperf:perf-stat[1], linkperf:perf-annotate[1], linkperf:perf-record[1],
+linkperf:perf-intel-pt[1]
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 2599b057e47b..db6a36aac47e 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -429,4 +429,4 @@ include::itrace.txt[]
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script-perl[1],
-linkperf:perf-script-python[1]
+linkperf:perf-script-python[1], linkperf:perf-intel-pt[1]
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 9431b8066fb4..4d56586b2fb9 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -334,6 +334,15 @@ Configure all used events to run in kernel space.
 --all-user::
 Configure all used events to run in user space.
 
+--percore-show-thread::
+The event modifier "percore" has supported to sum up the event counts
+for all hardware threads in a core and show the counts per core.
+
+This option with event modifier "percore" enabled also sums up the event
+counts for all hardware threads in a core but show the sum counts per
+hardware thread. This is essentially a replacement for the any bit and
+convenient for post processing.
+
 EXAMPLES
 --------
 
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index c03c36fde7e2..5e697cd2224a 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -572,29 +572,12 @@ static void init_block_hist(struct block_hist *bh)
 	bh->valid = true;
 }
 
-static int block_pair_cmp(struct hist_entry *a, struct hist_entry *b)
-{
-	struct block_info *bi_a = a->block_info;
-	struct block_info *bi_b = b->block_info;
-	int cmp;
-
-	if (!bi_a->sym || !bi_b->sym)
-		return -1;
-
-	cmp = strcmp(bi_a->sym->name, bi_b->sym->name);
-
-	if ((!cmp) && (bi_a->start == bi_b->start) && (bi_a->end == bi_b->end))
-		return 0;
-
-	return -1;
-}
-
 static struct hist_entry *get_block_pair(struct hist_entry *he,
 					 struct hists *hists_pair)
 {
 	struct rb_root_cached *root = hists_pair->entries_in;
 	struct rb_node *next = rb_first_cached(root);
-	int cmp;
+	int64_t cmp;
 
 	while (next != NULL) {
 		struct hist_entry *he_pair = rb_entry(next, struct hist_entry,
@@ -602,7 +585,7 @@ static struct hist_entry *get_block_pair(struct hist_entry *he,
 
 		next = rb_next(&he_pair->rb_node_in);
 
-		cmp = block_pair_cmp(he_pair, he);
+		cmp = __block_info__cmp(he_pair, he);
 		if (!cmp)
 			return he_pair;
 	}
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 72a12b69f120..5f4045df76f4 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -104,6 +104,7 @@ struct report {
 	bool			symbol_ipc;
 	bool			total_cycles_mode;
 	struct block_report	*block_reports;
+	int			nr_block_reports;
 };
 
 static int report__config(const char *var, const char *value, void *cb)
@@ -185,24 +186,23 @@ static int hist_iter__branch_callback(struct hist_entry_iter *iter,
 {
 	struct hist_entry *he = iter->he;
 	struct report *rep = arg;
-	struct branch_info *bi;
+	struct branch_info *bi = he->branch_info;
 	struct perf_sample *sample = iter->sample;
 	struct evsel *evsel = iter->evsel;
 	int err;
 
+	branch_type_count(&rep->brtype_stat, &bi->flags,
+			  bi->from.addr, bi->to.addr);
+
 	if (!ui__has_annotation() && !rep->symbol_ipc)
 		return 0;
 
-	bi = he->branch_info;
 	err = addr_map_symbol__inc_samples(&bi->from, sample, evsel);
 	if (err)
 		goto out;
 
 	err = addr_map_symbol__inc_samples(&bi->to, sample, evsel);
 
-	branch_type_count(&rep->brtype_stat, &bi->flags,
-			  bi->from.addr, bi->to.addr);
-
 out:
 	return err;
 }
@@ -966,8 +966,19 @@ static int __cmd_report(struct report *rep)
 	report__output_resort(rep);
 
 	if (rep->total_cycles_mode) {
+		int block_hpps[6] = {
+			PERF_HPP_REPORT__BLOCK_TOTAL_CYCLES_PCT,
+			PERF_HPP_REPORT__BLOCK_LBR_CYCLES,
+			PERF_HPP_REPORT__BLOCK_CYCLES_PCT,
+			PERF_HPP_REPORT__BLOCK_AVG_CYCLES,
+			PERF_HPP_REPORT__BLOCK_RANGE,
+			PERF_HPP_REPORT__BLOCK_DSO,
+		};
+
 		rep->block_reports = block_info__create_report(session->evlist,
-							       rep->total_cycles);
+							       rep->total_cycles,
+							       block_hpps, 6,
+							       &rep->nr_block_reports);
 		if (!rep->block_reports)
 			return -1;
 	}
@@ -1551,8 +1562,11 @@ error:
 		zfree(&report.ptime_range);
 	}
 
-	if (report.block_reports)
-		zfree(&report.block_reports);
+	if (report.block_reports) {
+		block_info__free_report(report.block_reports,
+					report.nr_block_reports);
+		report.block_reports = NULL;
+	}
 
 	zstd_fini(&(session->zstd_data));
 	perf_session__delete(session);
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index e2406b291c1c..656b347f6dd8 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -735,6 +735,7 @@ static int perf_sample__fprintf_brstack(struct perf_sample *sample,
 					struct perf_event_attr *attr, FILE *fp)
 {
 	struct branch_stack *br = sample->branch_stack;
+	struct branch_entry *entries = perf_sample__branch_entries(sample);
 	struct addr_location alf, alt;
 	u64 i, from, to;
 	int printed = 0;
@@ -743,8 +744,8 @@ static int perf_sample__fprintf_brstack(struct perf_sample *sample,
 		return 0;
 
 	for (i = 0; i < br->nr; i++) {
-		from = br->entries[i].from;
-		to   = br->entries[i].to;
+		from = entries[i].from;
+		to   = entries[i].to;
 
 		if (PRINT_FIELD(DSO)) {
 			memset(&alf, 0, sizeof(alf));
@@ -768,10 +769,10 @@ static int perf_sample__fprintf_brstack(struct perf_sample *sample,
 		}
 
 		printed += fprintf(fp, "/%c/%c/%c/%d ",
-			mispred_str( br->entries + i),
-			br->entries[i].flags.in_tx? 'X' : '-',
-			br->entries[i].flags.abort? 'A' : '-',
-			br->entries[i].flags.cycles);
+			mispred_str(entries + i),
+			entries[i].flags.in_tx ? 'X' : '-',
+			entries[i].flags.abort ? 'A' : '-',
+			entries[i].flags.cycles);
 	}
 
 	return printed;
@@ -782,6 +783,7 @@ static int perf_sample__fprintf_brstacksym(struct perf_sample *sample,
 					   struct perf_event_attr *attr, FILE *fp)
 {
 	struct branch_stack *br = sample->branch_stack;
+	struct branch_entry *entries = perf_sample__branch_entries(sample);
 	struct addr_location alf, alt;
 	u64 i, from, to;
 	int printed = 0;
@@ -793,8 +795,8 @@ static int perf_sample__fprintf_brstacksym(struct perf_sample *sample,
 
 		memset(&alf, 0, sizeof(alf));
 		memset(&alt, 0, sizeof(alt));
-		from = br->entries[i].from;
-		to   = br->entries[i].to;
+		from = entries[i].from;
+		to   = entries[i].to;
 
 		thread__find_symbol_fb(thread, sample->cpumode, from, &alf);
 		thread__find_symbol_fb(thread, sample->cpumode, to, &alt);
@@ -813,10 +815,10 @@ static int perf_sample__fprintf_brstacksym(struct perf_sample *sample,
 			printed += fprintf(fp, ")");
 		}
 		printed += fprintf(fp, "/%c/%c/%c/%d ",
-			mispred_str( br->entries + i),
-			br->entries[i].flags.in_tx? 'X' : '-',
-			br->entries[i].flags.abort? 'A' : '-',
-			br->entries[i].flags.cycles);
+			mispred_str(entries + i),
+			entries[i].flags.in_tx ? 'X' : '-',
+			entries[i].flags.abort ? 'A' : '-',
+			entries[i].flags.cycles);
 	}
 
 	return printed;
@@ -827,6 +829,7 @@ static int perf_sample__fprintf_brstackoff(struct perf_sample *sample,
 					   struct perf_event_attr *attr, FILE *fp)
 {
 	struct branch_stack *br = sample->branch_stack;
+	struct branch_entry *entries = perf_sample__branch_entries(sample);
 	struct addr_location alf, alt;
 	u64 i, from, to;
 	int printed = 0;
@@ -838,8 +841,8 @@ static int perf_sample__fprintf_brstackoff(struct perf_sample *sample,
 
 		memset(&alf, 0, sizeof(alf));
 		memset(&alt, 0, sizeof(alt));
-		from = br->entries[i].from;
-		to   = br->entries[i].to;
+		from = entries[i].from;
+		to   = entries[i].to;
 
 		if (thread__find_map_fb(thread, sample->cpumode, from, &alf) &&
 		    !alf.map->dso->adjust_symbols)
@@ -862,10 +865,10 @@ static int perf_sample__fprintf_brstackoff(struct perf_sample *sample,
 			printed += fprintf(fp, ")");
 		}
 		printed += fprintf(fp, "/%c/%c/%c/%d ",
-			mispred_str(br->entries + i),
-			br->entries[i].flags.in_tx ? 'X' : '-',
-			br->entries[i].flags.abort ? 'A' : '-',
-			br->entries[i].flags.cycles);
+			mispred_str(entries + i),
+			entries[i].flags.in_tx ? 'X' : '-',
+			entries[i].flags.abort ? 'A' : '-',
+			entries[i].flags.cycles);
 	}
 
 	return printed;
@@ -1053,6 +1056,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 					    struct machine *machine, FILE *fp)
 {
 	struct branch_stack *br = sample->branch_stack;
+	struct branch_entry *entries = perf_sample__branch_entries(sample);
 	u64 start, end;
 	int i, insn, len, nr, ilen, printed = 0;
 	struct perf_insn x;
@@ -1073,31 +1077,31 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 	printed += fprintf(fp, "%c", '\n');
 
 	/* Handle first from jump, of which we don't know the entry. */
-	len = grab_bb(buffer, br->entries[nr-1].from,
-			br->entries[nr-1].from,
+	len = grab_bb(buffer, entries[nr-1].from,
+			entries[nr-1].from,
 			machine, thread, &x.is64bit, &x.cpumode, false);
 	if (len > 0) {
-		printed += ip__fprintf_sym(br->entries[nr - 1].from, thread,
+		printed += ip__fprintf_sym(entries[nr - 1].from, thread,
 					   x.cpumode, x.cpu, &lastsym, attr, fp);
-		printed += ip__fprintf_jump(br->entries[nr - 1].from, &br->entries[nr - 1],
+		printed += ip__fprintf_jump(entries[nr - 1].from, &entries[nr - 1],
 					    &x, buffer, len, 0, fp, &total_cycles);
 		if (PRINT_FIELD(SRCCODE))
-			printed += print_srccode(thread, x.cpumode, br->entries[nr - 1].from);
+			printed += print_srccode(thread, x.cpumode, entries[nr - 1].from);
 	}
 
 	/* Print all blocks */
 	for (i = nr - 2; i >= 0; i--) {
-		if (br->entries[i].from || br->entries[i].to)
+		if (entries[i].from || entries[i].to)
 			pr_debug("%d: %" PRIx64 "-%" PRIx64 "\n", i,
-				 br->entries[i].from,
-				 br->entries[i].to);
-		start = br->entries[i + 1].to;
-		end   = br->entries[i].from;
+				 entries[i].from,
+				 entries[i].to);
+		start = entries[i + 1].to;
+		end   = entries[i].from;
 
 		len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, false);
 		/* Patch up missing kernel transfers due to ring filters */
 		if (len == -ENXIO && i > 0) {
-			end = br->entries[--i].from;
+			end = entries[--i].from;
 			pr_debug("\tpatching up to %" PRIx64 "-%" PRIx64 "\n", start, end);
 			len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, false);
 		}
@@ -1110,7 +1114,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 
 			printed += ip__fprintf_sym(ip, thread, x.cpumode, x.cpu, &lastsym, attr, fp);
 			if (ip == end) {
-				printed += ip__fprintf_jump(ip, &br->entries[i], &x, buffer + off, len - off, ++insn, fp,
+				printed += ip__fprintf_jump(ip, &entries[i], &x, buffer + off, len - off, ++insn, fp,
 							    &total_cycles);
 				if (PRINT_FIELD(SRCCODE))
 					printed += print_srccode(thread, x.cpumode, ip);
@@ -1134,9 +1138,9 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 	 * Hit the branch? In this case we are already done, and the target
 	 * has not been executed yet.
 	 */
-	if (br->entries[0].from == sample->ip)
+	if (entries[0].from == sample->ip)
 		goto out;
-	if (br->entries[0].flags.abort)
+	if (entries[0].flags.abort)
 		goto out;
 
 	/*
@@ -1147,7 +1151,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 	 * between final branch and sample. When this happens just
 	 * continue walking after the last TO until we hit a branch.
 	 */
-	start = br->entries[0].to;
+	start = entries[0].to;
 	end = sample->ip;
 	if (end < start) {
 		/* Missing jump. Scan 128 bytes for the next branch */
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index a098c2ebf4ea..ec053dc1e35c 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -929,6 +929,10 @@ static struct option stat_options[] = {
 	OPT_BOOLEAN_FLAG(0, "all-user", &stat_config.all_user,
 			 "Configure all used events to run in user space.",
 			 PARSE_OPT_EXCLUSIVE),
+	OPT_BOOLEAN(0, "percore-show-thread", &stat_config.percore_show_thread,
+		    "Use with 'percore' event qualifier to show the event "
+		    "counts of one hardware thread by sum up total hardware "
+		    "threads of same physical core"),
 	OPT_END()
 };
 
diff --git a/tools/perf/pmu-events/arch/s390/cf_z15/crypto6.json b/tools/perf/pmu-events/arch/s390/cf_z15/crypto6.json
index 5e36bc2468d0..c998e4f1d1d2 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z15/crypto6.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z15/crypto6.json
@@ -4,27 +4,27 @@
 		"EventCode": "80",
 		"EventName": "ECC_FUNCTION_COUNT",
 		"BriefDescription": "ECC Function Count",
-		"PublicDescription": "Long ECC function Count"
+		"PublicDescription": "This counter counts the total number of the elliptic-curve cryptography (ECC) functions issued by the CPU."
 	},
 	{
 		"Unit": "CPU-M-CF",
 		"EventCode": "81",
 		"EventName": "ECC_CYCLES_COUNT",
 		"BriefDescription": "ECC Cycles Count",
-		"PublicDescription": "Long ECC Function cycles count"
+		"PublicDescription": "This counter counts the total number of CPU cycles when the ECC coprocessor is busy performing the elliptic-curve cryptography (ECC) functions issued by the CPU."
 	},
 	{
 		"Unit": "CPU-M-CF",
 		"EventCode": "82",
 		"EventName": "ECC_BLOCKED_FUNCTION_COUNT",
 		"BriefDescription": "Ecc Blocked Function Count",
-		"PublicDescription": "Long ECC blocked function count"
+		"PublicDescription": "This counter counts the total number of the elliptic-curve cryptography (ECC) functions that are issued by the CPU and are blocked because the ECC coprocessor is busy performing a function issued by another CPU."
 	},
 	{
 		"Unit": "CPU-M-CF",
 		"EventCode": "83",
 		"EventName": "ECC_BLOCKED_CYCLES_COUNT",
 		"BriefDescription": "ECC Blocked Cycles Count",
-		"PublicDescription": "Long ECC blocked cycles count"
+		"PublicDescription": "This counter counts the total number of CPU cycles blocked for the elliptic-curve cryptography (ECC) functions issued by the CPU because the ECC coprocessor is busy performing a function issued by another CPU."
 	},
 ]
diff --git a/tools/perf/pmu-events/arch/s390/cf_z15/extended.json b/tools/perf/pmu-events/arch/s390/cf_z15/extended.json
index 89e070727e1b..2df2e231e9ee 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z15/extended.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z15/extended.json
@@ -25,7 +25,7 @@
 		"EventCode": "131",
 		"EventName": "DTLB2_HPAGE_WRITES",
 		"BriefDescription": "DTLB2 One-Megabyte Page Writes",
-		"PublicDescription": "A translation entry was written into the Combined Region and Segment Table Entry array in the Level-2 TLB for a one-megabyte page or a Last Host Translation was done"
+		"PublicDescription": "A translation entry was written into the Combined Region and Segment Table Entry array in the Level-2 TLB for a one-megabyte page"
 	},
 	{
 		"Unit": "CPU-M-CF",
@@ -358,6 +358,34 @@
 	},
 	{
 		"Unit": "CPU-M-CF",
+		"EventCode": "247",
+		"EventName": "DFLT_ACCESS",
+		"BriefDescription": "Cycles CPU spent obtaining access to Deflate unit",
+		"PublicDescription": "Cycles CPU spent obtaining access to Deflate unit"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "252",
+		"EventName": "DFLT_CYCLES",
+		"BriefDescription": "Cycles CPU is using Deflate unit",
+		"PublicDescription": "Cycles CPU is using Deflate unit"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "264",
+		"EventName": "DFLT_CC",
+		"BriefDescription": "Increments by one for every DEFLATE CONVERSION CALL instruction executed",
+		"PublicDescription": "Increments by one for every DEFLATE CONVERSION CALL instruction executed"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "265",
+		"EventName": "DFLT_CCERROR",
+		"BriefDescription": "Increments by one for every DEFLATE CONVERSION CALL instruction executed that ended in Condition Codes 0, 1 or 2",
+		"PublicDescription": "Increments by one for every DEFLATE CONVERSION CALL instruction executed that ended in Condition Codes 0, 1 or 2"
+	},
+	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "448",
 		"EventName": "MT_DIAG_CYCLES_ONE_THR_ACTIVE",
 		"BriefDescription": "Cycle count with one thread active",
diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
index f94653229dd4..a728c6e5119b 100644
--- a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
@@ -215,7 +215,8 @@
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
         "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * cycles )",
         "MetricGroup": "TLB",
-        "MetricName": "Page_Walks_Utilization"
+        "MetricName": "Page_Walks_Utilization",
+        "MetricConstraint": "NO_NMI_WATCHDOG"
     },
     {
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
diff --git a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json
index e7feb60f9fa9..f97e8316ad2f 100644
--- a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json
@@ -215,7 +215,8 @@
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
         "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * cycles )",
         "MetricGroup": "TLB",
-        "MetricName": "Page_Walks_Utilization"
+        "MetricName": "Page_Walks_Utilization",
+        "MetricConstraint": "NO_NMI_WATCHDOG"
     },
     {
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
index 21d7a0c2c2e8..35f5db1786f7 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
@@ -215,7 +215,8 @@
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
         "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * cycles )",
         "MetricGroup": "TLB",
-        "MetricName": "Page_Walks_Utilization"
+        "MetricName": "Page_Walks_Utilization",
+        "MetricConstraint": "NO_NMI_WATCHDOG"
     },
     {
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c
index 27b4da80f751..3c4236a5bad8 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -323,7 +323,7 @@ static int print_events_table_entry(void *data, char *name, char *event,
 				    char *pmu, char *unit, char *perpkg,
 				    char *metric_expr,
 				    char *metric_name, char *metric_group,
-				    char *deprecated)
+				    char *deprecated, char *metric_constraint)
 {
 	struct perf_entry_data *pd = data;
 	FILE *outfp = pd->outfp;
@@ -357,6 +357,8 @@ static int print_events_table_entry(void *data, char *name, char *event,
 		fprintf(outfp, "\t.metric_group = \"%s\",\n", metric_group);
 	if (deprecated)
 		fprintf(outfp, "\t.deprecated = \"%s\",\n", deprecated);
+	if (metric_constraint)
+		fprintf(outfp, "\t.metric_constraint = \"%s\",\n", metric_constraint);
 	fprintf(outfp, "},\n");
 
 	return 0;
@@ -375,6 +377,7 @@ struct event_struct {
 	char *metric_name;
 	char *metric_group;
 	char *deprecated;
+	char *metric_constraint;
 };
 
 #define ADD_EVENT_FIELD(field) do { if (field) {		\
@@ -422,7 +425,7 @@ static int save_arch_std_events(void *data, char *name, char *event,
 				char *desc, char *long_desc, char *pmu,
 				char *unit, char *perpkg, char *metric_expr,
 				char *metric_name, char *metric_group,
-				char *deprecated)
+				char *deprecated, char *metric_constraint)
 {
 	struct event_struct *es;
 
@@ -486,7 +489,7 @@ try_fixup(const char *fn, char *arch_std, char **event, char **desc,
 	  char **name, char **long_desc, char **pmu, char **filter,
 	  char **perpkg, char **unit, char **metric_expr, char **metric_name,
 	  char **metric_group, unsigned long long eventcode,
-	  char **deprecated)
+	  char **deprecated, char **metric_constraint)
 {
 	/* try to find matching event from arch standard values */
 	struct event_struct *es;
@@ -515,7 +518,7 @@ int json_events(const char *fn,
 		      char *pmu, char *unit, char *perpkg,
 		      char *metric_expr,
 		      char *metric_name, char *metric_group,
-		      char *deprecated),
+		      char *deprecated, char *metric_constraint),
 	  void *data)
 {
 	int err;
@@ -545,6 +548,7 @@ int json_events(const char *fn,
 		char *metric_name = NULL;
 		char *metric_group = NULL;
 		char *deprecated = NULL;
+		char *metric_constraint = NULL;
 		char *arch_std = NULL;
 		unsigned long long eventcode = 0;
 		struct msrmap *msr = NULL;
@@ -629,6 +633,8 @@ int json_events(const char *fn,
 				addfield(map, &metric_name, "", "", val);
 			} else if (json_streq(map, field, "MetricGroup")) {
 				addfield(map, &metric_group, "", "", val);
+			} else if (json_streq(map, field, "MetricConstraint")) {
+				addfield(map, &metric_constraint, "", "", val);
 			} else if (json_streq(map, field, "MetricExpr")) {
 				addfield(map, &metric_expr, "", "", val);
 				for (s = metric_expr; *s; s++)
@@ -670,13 +676,13 @@ int json_events(const char *fn,
 					&long_desc, &pmu, &filter, &perpkg,
 					&unit, &metric_expr, &metric_name,
 					&metric_group, eventcode,
-					&deprecated);
+					&deprecated, &metric_constraint);
 			if (err)
 				goto free_strings;
 		}
 		err = func(data, name, real_event(name, event), desc, long_desc,
 			   pmu, unit, perpkg, metric_expr, metric_name,
-			   metric_group, deprecated);
+			   metric_group, deprecated, metric_constraint);
 free_strings:
 		free(event);
 		free(desc);
@@ -691,6 +697,7 @@ free_strings:
 		free(metric_expr);
 		free(metric_name);
 		free(metric_group);
+		free(metric_constraint);
 		free(arch_std);
 
 		if (err)
diff --git a/tools/perf/pmu-events/jevents.h b/tools/perf/pmu-events/jevents.h
index 5cda49a42143..2afc8304529e 100644
--- a/tools/perf/pmu-events/jevents.h
+++ b/tools/perf/pmu-events/jevents.h
@@ -8,7 +8,7 @@ int json_events(const char *fn,
 				char *pmu,
 				char *unit, char *perpkg, char *metric_expr,
 				char *metric_name, char *metric_group,
-				char *deprecated),
+				char *deprecated, char *metric_constraint),
 		void *data);
 char *get_cpu_str(void);
 
diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h
index caeb577d36c9..53e76d5d5b37 100644
--- a/tools/perf/pmu-events/pmu-events.h
+++ b/tools/perf/pmu-events/pmu-events.h
@@ -18,6 +18,7 @@ struct pmu_event {
 	const char *metric_name;
 	const char *metric_group;
 	const char *deprecated;
+	const char *metric_constraint;
 };
 
 /*
diff --git a/tools/perf/scripts/perl/check-perf-trace.pl b/tools/perf/scripts/perl/check-perf-trace.pl
index 4e7076c20616..d307ce8fd6ed 100644
--- a/tools/perf/scripts/perl/check-perf-trace.pl
+++ b/tools/perf/scripts/perl/check-perf-trace.pl
@@ -28,7 +28,7 @@ sub trace_end
 sub irq::softirq_entry
 {
 	my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	    $common_pid, $common_comm,
+	    $common_pid, $common_comm, $common_callchain,
 	    $vec) = @_;
 
 	print_header($event_name, $common_cpu, $common_secs, $common_nsecs,
@@ -43,7 +43,7 @@ sub irq::softirq_entry
 sub kmem::kmalloc
 {
 	my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	    $common_pid, $common_comm,
+	    $common_pid, $common_comm, $common_callchain,
 	    $call_site, $ptr, $bytes_req, $bytes_alloc,
 	    $gfp_flags) = @_;
 
@@ -92,7 +92,7 @@ sub print_unhandled
 sub trace_unhandled
 {
     my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm) = @_;
+	$common_pid, $common_comm, $common_callchain) = @_;
 
     $unhandled{$event_name}++;
 }
diff --git a/tools/perf/scripts/perl/failed-syscalls.pl b/tools/perf/scripts/perl/failed-syscalls.pl
index 55e7ae4c5c88..05954a8f363a 100644
--- a/tools/perf/scripts/perl/failed-syscalls.pl
+++ b/tools/perf/scripts/perl/failed-syscalls.pl
@@ -18,7 +18,7 @@ my %failed_syscalls;
 sub raw_syscalls::sys_exit
 {
 	my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	    $common_pid, $common_comm,
+	    $common_pid, $common_comm, $common_callchain,
 	    $id, $ret) = @_;
 
 	if ($ret < 0) {
diff --git a/tools/perf/scripts/perl/rw-by-file.pl b/tools/perf/scripts/perl/rw-by-file.pl
index 168fa5e94b44..92a750b8552b 100644
--- a/tools/perf/scripts/perl/rw-by-file.pl
+++ b/tools/perf/scripts/perl/rw-by-file.pl
@@ -28,7 +28,7 @@ my %writes;
 sub syscalls::sys_enter_read
 {
     my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm, $nr, $fd, $buf, $count) = @_;
+	$common_pid, $common_comm, $common_callchain, $nr, $fd, $buf, $count) = @_;
 
     if ($common_comm eq $for_comm) {
 	$reads{$fd}{bytes_requested} += $count;
@@ -39,7 +39,7 @@ sub syscalls::sys_enter_read
 sub syscalls::sys_enter_write
 {
     my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm, $nr, $fd, $buf, $count) = @_;
+	$common_pid, $common_comm, $common_callchain, $nr, $fd, $buf, $count) = @_;
 
     if ($common_comm eq $for_comm) {
 	$writes{$fd}{bytes_written} += $count;
@@ -98,7 +98,7 @@ sub print_unhandled
 sub trace_unhandled
 {
     my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm) = @_;
+	$common_pid, $common_comm, $common_callchain) = @_;
 
     $unhandled{$event_name}++;
 }
diff --git a/tools/perf/scripts/perl/rw-by-pid.pl b/tools/perf/scripts/perl/rw-by-pid.pl
index 495698250b2f..d789fe39caab 100644
--- a/tools/perf/scripts/perl/rw-by-pid.pl
+++ b/tools/perf/scripts/perl/rw-by-pid.pl
@@ -24,7 +24,7 @@ my %writes;
 sub syscalls::sys_exit_read
 {
     my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm,
+	$common_pid, $common_comm, $common_callchain,
 	$nr, $ret) = @_;
 
     if ($ret > 0) {
@@ -40,7 +40,7 @@ sub syscalls::sys_exit_read
 sub syscalls::sys_enter_read
 {
     my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm,
+	$common_pid, $common_comm, $common_callchain,
 	$nr, $fd, $buf, $count) = @_;
 
     $reads{$common_pid}{bytes_requested} += $count;
@@ -51,7 +51,7 @@ sub syscalls::sys_enter_read
 sub syscalls::sys_exit_write
 {
     my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm,
+	$common_pid, $common_comm, $common_callchain,
 	$nr, $ret) = @_;
 
     if ($ret <= 0) {
@@ -62,7 +62,7 @@ sub syscalls::sys_exit_write
 sub syscalls::sys_enter_write
 {
     my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm,
+	$common_pid, $common_comm, $common_callchain,
 	$nr, $fd, $buf, $count) = @_;
 
     $writes{$common_pid}{bytes_written} += $count;
@@ -178,7 +178,7 @@ sub print_unhandled
 sub trace_unhandled
 {
     my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm) = @_;
+	$common_pid, $common_comm, $common_callchain) = @_;
 
     $unhandled{$event_name}++;
 }
diff --git a/tools/perf/scripts/perl/rwtop.pl b/tools/perf/scripts/perl/rwtop.pl
index 6473442568a2..eba4df67af6b 100644
--- a/tools/perf/scripts/perl/rwtop.pl
+++ b/tools/perf/scripts/perl/rwtop.pl
@@ -35,7 +35,7 @@ if (!$interval) {
 sub syscalls::sys_exit_read
 {
     my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm,
+	$common_pid, $common_comm, $common_callchain,
 	$nr, $ret) = @_;
 
     print_check();
@@ -53,7 +53,7 @@ sub syscalls::sys_exit_read
 sub syscalls::sys_enter_read
 {
     my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm,
+	$common_pid, $common_comm, $common_callchain,
 	$nr, $fd, $buf, $count) = @_;
 
     print_check();
@@ -66,7 +66,7 @@ sub syscalls::sys_enter_read
 sub syscalls::sys_exit_write
 {
     my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm,
+	$common_pid, $common_comm, $common_callchain,
 	$nr, $ret) = @_;
 
     print_check();
@@ -79,7 +79,7 @@ sub syscalls::sys_exit_write
 sub syscalls::sys_enter_write
 {
     my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm,
+	$common_pid, $common_comm, $common_callchain,
 	$nr, $fd, $buf, $count) = @_;
 
     print_check();
@@ -197,7 +197,7 @@ sub print_unhandled
 sub trace_unhandled
 {
     my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm) = @_;
+	$common_pid, $common_comm, $common_callchain) = @_;
 
     $unhandled{$event_name}++;
 }
diff --git a/tools/perf/scripts/perl/wakeup-latency.pl b/tools/perf/scripts/perl/wakeup-latency.pl
index efcfec5e347a..53444ff4ec7f 100644
--- a/tools/perf/scripts/perl/wakeup-latency.pl
+++ b/tools/perf/scripts/perl/wakeup-latency.pl
@@ -28,7 +28,7 @@ my $total_wakeups = 0;
 sub sched::sched_switch
 {
     my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm,
+	$common_pid, $common_comm, $common_callchain,
 	$prev_comm, $prev_pid, $prev_prio, $prev_state, $next_comm, $next_pid,
 	$next_prio) = @_;
 
@@ -51,7 +51,7 @@ sub sched::sched_switch
 sub sched::sched_wakeup
 {
     my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm,
+	$common_pid, $common_comm, $common_callchain,
 	$comm, $pid, $prio, $success, $target_cpu) = @_;
 
     $last_wakeup{$target_cpu}{ts} = nsecs($common_secs, $common_nsecs);
@@ -101,7 +101,7 @@ sub print_unhandled
 sub trace_unhandled
 {
     my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
-	$common_pid, $common_comm) = @_;
+	$common_pid, $common_comm, $common_callchain) = @_;
 
     $unhandled{$event_name}++;
 }
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 5f05db75cdd8..54d9516c9839 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -543,8 +543,11 @@ static int run_shell_tests(int argc, const char *argv[], int i, int width)
 		return -1;
 
 	dir = opendir(st.dir);
-	if (!dir)
+	if (!dir) {
+		pr_err("failed to open shell test directory: %s\n",
+			st.dir);
 		return -1;
+	}
 
 	for_each_shell_test(dir, st.dir, ent) {
 		int curr = i++;
diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c
index 87843af4c118..28313e59d6f6 100644
--- a/tools/perf/tests/expr.c
+++ b/tools/perf/tests/expr.c
@@ -10,7 +10,7 @@ static int test(struct parse_ctx *ctx, const char *e, double val2)
 {
 	double val;
 
-	if (expr__parse(&val, ctx, &e))
+	if (expr__parse(&val, ctx, e))
 		TEST_ASSERT_VAL("parse test failed", 0);
 	TEST_ASSERT_VAL("unexpected value", val == val2);
 	return 0;
@@ -44,12 +44,12 @@ int test__expr(struct test *t __maybe_unused, int subtest __maybe_unused)
 		return ret;
 
 	p = "FOO/0";
-	ret = expr__parse(&val, &ctx, &p);
-	TEST_ASSERT_VAL("division by zero", ret == 1);
+	ret = expr__parse(&val, &ctx, p);
+	TEST_ASSERT_VAL("division by zero", ret == -1);
 
 	p = "BAR/";
-	ret = expr__parse(&val, &ctx, &p);
-	TEST_ASSERT_VAL("missing operand", ret == 1);
+	ret = expr__parse(&val, &ctx, p);
+	TEST_ASSERT_VAL("missing operand", ret == -1);
 
 	TEST_ASSERT_VAL("find other",
 			expr__find_other("FOO + BAR + BAZ + BOZO", "FOO", &other, &num_other) == 0);
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index 2762e1155238..14239e472187 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -99,6 +99,7 @@ static bool samples_same(const struct perf_sample *s1,
 
 	if (type & PERF_SAMPLE_BRANCH_STACK) {
 		COMP(branch_stack->nr);
+		COMP(branch_stack->hw_idx);
 		for (i = 0; i < s1->branch_stack->nr; i++)
 			MCOMP(branch_stack->entries[i]);
 	}
@@ -186,7 +187,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
 		u64 data[64];
 	} branch_stack = {
 		/* 1 branch_entry */
-		.data = {1, 211, 212, 213},
+		.data = {1, -1ULL, 211, 212, 213},
 	};
 	u64 regs[64];
 	const u64 raw_data[] = {0x123456780a0b0c0dULL, 0x1102030405060708ULL};
@@ -208,6 +209,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
 		.transaction	= 112,
 		.raw_data	= (void *)raw_data,
 		.callchain	= &callchain.callchain,
+		.no_hw_idx      = false,
 		.branch_stack	= &branch_stack.branch_stack,
 		.user_regs	= {
 			.abi	= PERF_SAMPLE_REGS_ABI_64,
@@ -244,6 +246,9 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
 	if (sample_type & PERF_SAMPLE_REGS_INTR)
 		evsel.core.attr.sample_regs_intr = sample_regs;
 
+	if (sample_type & PERF_SAMPLE_BRANCH_STACK)
+		evsel.core.attr.branch_sample_type |= PERF_SAMPLE_BRANCH_HW_INDEX;
+
 	for (i = 0; i < sizeof(regs); i++)
 		*(i + (u8 *)regs) = i & 0xfe;
 
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 07da6c790b63..c0cf8dff694e 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -121,7 +121,9 @@ perf-y += mem-events.o
 perf-y += vsprintf.o
 perf-y += units.o
 perf-y += time-utils.o
+perf-y += expr-flex.o
 perf-y += expr-bison.o
+perf-y += expr.o
 perf-y += branch.o
 perf-y += mem2node.o
 
@@ -189,9 +191,13 @@ $(OUTPUT)util/parse-events-bison.c: util/parse-events.y
 	$(call rule_mkdir)
 	$(Q)$(call echo-cmd,bison)$(BISON) -v util/parse-events.y -d $(PARSER_DEBUG_BISON) -o $@ -p parse_events_
 
+$(OUTPUT)util/expr-flex.c: util/expr.l $(OUTPUT)util/expr-bison.c
+	$(call rule_mkdir)
+	$(Q)$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/expr-flex.h $(PARSER_DEBUG_FLEX) util/expr.l
+
 $(OUTPUT)util/expr-bison.c: util/expr.y
 	$(call rule_mkdir)
-	$(Q)$(call echo-cmd,bison)$(BISON) -v util/expr.y -d $(PARSER_DEBUG_BISON) -o $@ -p expr__
+	$(Q)$(call echo-cmd,bison)$(BISON) -v util/expr.y -d $(PARSER_DEBUG_BISON) -o $@ -p expr_
 
 $(OUTPUT)util/pmu-flex.c: util/pmu.l $(OUTPUT)util/pmu-bison.c
 	$(call rule_mkdir)
@@ -203,12 +209,14 @@ $(OUTPUT)util/pmu-bison.c: util/pmu.y
 
 CFLAGS_parse-events-flex.o  += -w
 CFLAGS_pmu-flex.o           += -w
+CFLAGS_expr-flex.o          += -w
 CFLAGS_parse-events-bison.o += -DYYENABLE_NLS=0 -w
 CFLAGS_pmu-bison.o          += -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w
 CFLAGS_expr-bison.o         += -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w
 
 $(OUTPUT)util/parse-events.o: $(OUTPUT)util/parse-events-flex.c $(OUTPUT)util/parse-events-bison.c
 $(OUTPUT)util/pmu.o: $(OUTPUT)util/pmu-flex.c $(OUTPUT)util/pmu-bison.c
+$(OUTPUT)util/expr.o: $(OUTPUT)util/expr-flex.c $(OUTPUT)util/expr-bison.c
 
 CFLAGS_bitmap.o        += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
 CFLAGS_find_bit.o      += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
@@ -216,6 +224,7 @@ CFLAGS_rbtree.o        += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ET
 CFLAGS_libstring.o     += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
 CFLAGS_hweight.o       += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
 CFLAGS_parse-events.o  += -Wno-redundant-decls
+CFLAGS_expr.o          += -Wno-redundant-decls
 CFLAGS_header.o        += -include $(OUTPUT)PERF-VERSION-FILE
 
 $(OUTPUT)util/kallsyms.o: ../lib/symbol/kallsyms.c FORCE
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 0ea95be84b3b..f1ea0d61eb5b 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -2611,8 +2611,6 @@ void annotation__mark_jump_targets(struct annotation *notes, struct symbol *sym)
 
 		if (++al->jump_sources > notes->max_jump_sources)
 			notes->max_jump_sources = al->jump_sources;
-
-		++notes->nr_jumps;
 	}
 }
 
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 001258601a37..07c775938d46 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -279,7 +279,6 @@ struct annotation {
 	struct annotation_options *options;
 	struct annotation_line	**offsets;
 	int			nr_events;
-	int			nr_jumps;
 	int			max_jump_sources;
 	int			nr_entries;
 	int			nr_asm_entries;
diff --git a/tools/perf/util/block-info.c b/tools/perf/util/block-info.c
index fbbb6d640dad..423ec69bda6c 100644
--- a/tools/perf/util/block-info.c
+++ b/tools/perf/util/block-info.c
@@ -65,8 +65,7 @@ struct block_info *block_info__new(void)
 	return bi;
 }
 
-int64_t block_info__cmp(struct perf_hpp_fmt *fmt __maybe_unused,
-			struct hist_entry *left, struct hist_entry *right)
+int64_t __block_info__cmp(struct hist_entry *left, struct hist_entry *right)
 {
 	struct block_info *bi_l = left->block_info;
 	struct block_info *bi_r = right->block_info;
@@ -74,30 +73,27 @@ int64_t block_info__cmp(struct perf_hpp_fmt *fmt __maybe_unused,
 
 	if (!bi_l->sym || !bi_r->sym) {
 		if (!bi_l->sym && !bi_r->sym)
-			return 0;
+			return -1;
 		else if (!bi_l->sym)
 			return -1;
 		else
 			return 1;
 	}
 
-	if (bi_l->sym == bi_r->sym) {
-		if (bi_l->start == bi_r->start) {
-			if (bi_l->end == bi_r->end)
-				return 0;
-			else
-				return (int64_t)(bi_r->end - bi_l->end);
-		} else
-			return (int64_t)(bi_r->start - bi_l->start);
-	} else {
-		cmp = strcmp(bi_l->sym->name, bi_r->sym->name);
+	cmp = strcmp(bi_l->sym->name, bi_r->sym->name);
+	if (cmp)
 		return cmp;
-	}
 
-	if (bi_l->sym->start != bi_r->sym->start)
-		return (int64_t)(bi_r->sym->start - bi_l->sym->start);
+	if (bi_l->start != bi_r->start)
+		return (int64_t)(bi_r->start - bi_l->start);
 
-	return (int64_t)(bi_r->sym->end - bi_l->sym->end);
+	return (int64_t)(bi_r->end - bi_l->end);
+}
+
+int64_t block_info__cmp(struct perf_hpp_fmt *fmt __maybe_unused,
+			struct hist_entry *left, struct hist_entry *right)
+{
+	return __block_info__cmp(left, right);
 }
 
 static void init_block_info(struct block_info *bi, struct symbol *sym,
@@ -185,6 +181,17 @@ static int block_column_width(struct perf_hpp_fmt *fmt,
 	return block_fmt->width;
 }
 
+static int color_pct(struct perf_hpp *hpp, int width, double pct)
+{
+#ifdef HAVE_SLANG_SUPPORT
+	if (use_browser) {
+		return __hpp__slsmg_color_printf(hpp, "%*.2f%%",
+						 width - 1, pct);
+	}
+#endif
+	return hpp_color_scnprintf(hpp, "%*.2f%%", width - 1, pct);
+}
+
 static int block_total_cycles_pct_entry(struct perf_hpp_fmt *fmt,
 					struct perf_hpp *hpp,
 					struct hist_entry *he)
@@ -192,14 +199,11 @@ static int block_total_cycles_pct_entry(struct perf_hpp_fmt *fmt,
 	struct block_fmt *block_fmt = container_of(fmt, struct block_fmt, fmt);
 	struct block_info *bi = he->block_info;
 	double ratio = 0.0;
-	char buf[16];
 
 	if (block_fmt->total_cycles)
 		ratio = (double)bi->cycles / (double)block_fmt->total_cycles;
 
-	sprintf(buf, "%.2f%%", 100.0 * ratio);
-
-	return scnprintf(hpp->buf, hpp->size, "%*s", block_fmt->width, buf);
+	return color_pct(hpp, block_fmt->width, 100.0 * ratio);
 }
 
 static int64_t block_total_cycles_pct_sort(struct perf_hpp_fmt *fmt,
@@ -252,16 +256,13 @@ static int block_cycles_pct_entry(struct perf_hpp_fmt *fmt,
 	struct block_info *bi = he->block_info;
 	double ratio = 0.0;
 	u64 avg;
-	char buf[16];
 
 	if (block_fmt->block_cycles && bi->num_aggr) {
 		avg = bi->cycles_aggr / bi->num_aggr;
 		ratio = (double)avg / (double)block_fmt->block_cycles;
 	}
 
-	sprintf(buf, "%.2f%%", 100.0 * ratio);
-
-	return scnprintf(hpp->buf, hpp->size, "%*s", block_fmt->width, buf);
+	return color_pct(hpp, block_fmt->width, 100.0 * ratio);
 }
 
 static int block_avg_cycles_entry(struct perf_hpp_fmt *fmt,
@@ -349,7 +350,7 @@ static void hpp_register(struct block_fmt *block_fmt, int idx,
 
 	switch (idx) {
 	case PERF_HPP_REPORT__BLOCK_TOTAL_CYCLES_PCT:
-		fmt->entry = block_total_cycles_pct_entry;
+		fmt->color = block_total_cycles_pct_entry;
 		fmt->cmp = block_info__cmp;
 		fmt->sort = block_total_cycles_pct_sort;
 		break;
@@ -357,7 +358,7 @@ static void hpp_register(struct block_fmt *block_fmt, int idx,
 		fmt->entry = block_cycles_lbr_entry;
 		break;
 	case PERF_HPP_REPORT__BLOCK_CYCLES_PCT:
-		fmt->entry = block_cycles_pct_entry;
+		fmt->color = block_cycles_pct_entry;
 		break;
 	case PERF_HPP_REPORT__BLOCK_AVG_CYCLES:
 		fmt->entry = block_avg_cycles_entry;
@@ -377,33 +378,41 @@ static void hpp_register(struct block_fmt *block_fmt, int idx,
 }
 
 static void register_block_columns(struct perf_hpp_list *hpp_list,
-				   struct block_fmt *block_fmts)
+				   struct block_fmt *block_fmts,
+				   int *block_hpps, int nr_hpps)
 {
-	for (int i = 0; i < PERF_HPP_REPORT__BLOCK_MAX_INDEX; i++)
-		hpp_register(&block_fmts[i], i, hpp_list);
+	for (int i = 0; i < nr_hpps; i++)
+		hpp_register(&block_fmts[i], block_hpps[i], hpp_list);
 }
 
-static void init_block_hist(struct block_hist *bh, struct block_fmt *block_fmts)
+static void init_block_hist(struct block_hist *bh, struct block_fmt *block_fmts,
+			    int *block_hpps, int nr_hpps)
 {
 	__hists__init(&bh->block_hists, &bh->block_list);
 	perf_hpp_list__init(&bh->block_list);
 	bh->block_list.nr_header_lines = 1;
 
-	register_block_columns(&bh->block_list, block_fmts);
+	register_block_columns(&bh->block_list, block_fmts,
+			       block_hpps, nr_hpps);
 
-	perf_hpp_list__register_sort_field(&bh->block_list,
-		&block_fmts[PERF_HPP_REPORT__BLOCK_TOTAL_CYCLES_PCT].fmt);
+	/* Sort by the first fmt */
+	perf_hpp_list__register_sort_field(&bh->block_list, &block_fmts[0].fmt);
 }
 
-static void process_block_report(struct hists *hists,
-				 struct block_report *block_report,
-				 u64 total_cycles)
+static int process_block_report(struct hists *hists,
+				struct block_report *block_report,
+				u64 total_cycles, int *block_hpps,
+				int nr_hpps)
 {
 	struct rb_node *next = rb_first_cached(&hists->entries);
 	struct block_hist *bh = &block_report->hist;
 	struct hist_entry *he;
 
-	init_block_hist(bh, block_report->fmts);
+	if (nr_hpps > PERF_HPP_REPORT__BLOCK_MAX_INDEX)
+		return -1;
+
+	block_report->nr_fmts = nr_hpps;
+	init_block_hist(bh, block_report->fmts, block_hpps, nr_hpps);
 
 	while (next) {
 		he = rb_entry(next, struct hist_entry, rb_node);
@@ -412,16 +421,19 @@ static void process_block_report(struct hists *hists,
 		next = rb_next(&he->rb_node);
 	}
 
-	for (int i = 0; i < PERF_HPP_REPORT__BLOCK_MAX_INDEX; i++) {
+	for (int i = 0; i < nr_hpps; i++) {
 		block_report->fmts[i].total_cycles = total_cycles;
 		block_report->fmts[i].block_cycles = block_report->cycles;
 	}
 
 	hists__output_resort(&bh->block_hists, NULL);
+	return 0;
 }
 
 struct block_report *block_info__create_report(struct evlist *evlist,
-					       u64 total_cycles)
+					       u64 total_cycles,
+					       int *block_hpps, int nr_hpps,
+					       int *nr_reps)
 {
 	struct block_report *block_reports;
 	int nr_hists = evlist->core.nr_entries, i = 0;
@@ -434,13 +446,23 @@ struct block_report *block_info__create_report(struct evlist *evlist,
 	evlist__for_each_entry(evlist, pos) {
 		struct hists *hists = evsel__hists(pos);
 
-		process_block_report(hists, &block_reports[i], total_cycles);
+		process_block_report(hists, &block_reports[i], total_cycles,
+				     block_hpps, nr_hpps);
 		i++;
 	}
 
+	*nr_reps = nr_hists;
 	return block_reports;
 }
 
+void block_info__free_report(struct block_report *reps, int nr_reps)
+{
+	for (int i = 0; i < nr_reps; i++)
+		hists__delete_entries(&reps[i].hist.block_hists);
+
+	free(reps);
+}
+
 int report__browse_block_hists(struct block_hist *bh, float min_percent,
 			       struct evsel *evsel, struct perf_env *env,
 			       struct annotation_options *annotation_opts)
@@ -452,13 +474,11 @@ int report__browse_block_hists(struct block_hist *bh, float min_percent,
 		symbol_conf.report_individual_block = true;
 		hists__fprintf(&bh->block_hists, true, 0, 0, min_percent,
 			       stdout, true);
-		hists__delete_entries(&bh->block_hists);
 		return 0;
 	case 1:
 		symbol_conf.report_individual_block = true;
 		ret = block_hists_tui_browse(bh, evsel, min_percent,
 					     env, annotation_opts);
-		hists__delete_entries(&bh->block_hists);
 		return ret;
 	default:
 		return -1;
diff --git a/tools/perf/util/block-info.h b/tools/perf/util/block-info.h
index bef0d75e9819..42e9dcc4cf0a 100644
--- a/tools/perf/util/block-info.h
+++ b/tools/perf/util/block-info.h
@@ -45,6 +45,7 @@ struct block_report {
 	struct block_hist	hist;
 	u64			cycles;
 	struct block_fmt	fmts[PERF_HPP_REPORT__BLOCK_MAX_INDEX];
+	int			nr_fmts;
 };
 
 struct block_hist;
@@ -61,6 +62,8 @@ static inline void __block_info__zput(struct block_info **bi)
 
 #define block_info__zput(bi) __block_info__zput(&bi)
 
+int64_t __block_info__cmp(struct hist_entry *left, struct hist_entry *right);
+
 int64_t block_info__cmp(struct perf_hpp_fmt *fmt __maybe_unused,
 			struct hist_entry *left, struct hist_entry *right);
 
@@ -68,7 +71,11 @@ int block_info__process_sym(struct hist_entry *he, struct block_hist *bh,
 			    u64 *block_cycles_aggr, u64 total_cycles);
 
 struct block_report *block_info__create_report(struct evlist *evlist,
-					       u64 total_cycles);
+					       u64 total_cycles,
+					       int *block_hpps, int nr_hpps,
+					       int *nr_reps);
+
+void block_info__free_report(struct block_report *reps, int nr_reps);
 
 int report__browse_block_hists(struct block_hist *bh, float min_percent,
 			       struct evsel *evsel, struct perf_env *env,
diff --git a/tools/perf/util/branch.h b/tools/perf/util/branch.h
index 88e00d268f6f..154a05cd03af 100644
--- a/tools/perf/util/branch.h
+++ b/tools/perf/util/branch.h
@@ -12,6 +12,7 @@
 #include <linux/stddef.h>
 #include <linux/perf_event.h>
 #include <linux/types.h>
+#include "event.h"
 
 struct branch_flags {
 	u64 mispred:1;
@@ -39,9 +40,30 @@ struct branch_entry {
 
 struct branch_stack {
 	u64			nr;
+	u64			hw_idx;
 	struct branch_entry	entries[0];
 };
 
+/*
+ * The hw_idx is only available when PERF_SAMPLE_BRANCH_HW_INDEX is applied.
+ * Otherwise, the output format of a sample with branch stack is
+ * struct branch_stack {
+ *	u64			nr;
+ *	struct branch_entry	entries[0];
+ * }
+ * Check whether the hw_idx is available,
+ * and return the corresponding pointer of entries[0].
+ */
+static inline struct branch_entry *perf_sample__branch_entries(struct perf_sample *sample)
+{
+	u64 *entry = (u64 *)sample->branch_stack;
+
+	entry++;
+	if (sample->no_hw_idx)
+		return (struct branch_entry *)entry;
+	return (struct branch_entry *)(++entry);
+}
+
 struct branch_type_stat {
 	bool	branch_to;
 	u64	counts[PERF_BR_MAX];
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index 4881d4af3381..5bc9d3b01bd9 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -3,75 +3,16 @@
 #include "evsel.h"
 #include "cgroup.h"
 #include "evlist.h"
-#include <linux/stringify.h>
 #include <linux/zalloc.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <fcntl.h>
 #include <stdlib.h>
 #include <string.h>
+#include <api/fs/fs.h>
 
 int nr_cgroups;
 
-static int
-cgroupfs_find_mountpoint(char *buf, size_t maxlen)
-{
-	FILE *fp;
-	char mountpoint[PATH_MAX + 1], tokens[PATH_MAX + 1], type[PATH_MAX + 1];
-	char path_v1[PATH_MAX + 1], path_v2[PATH_MAX + 2], *path;
-	char *token, *saved_ptr = NULL;
-
-	fp = fopen("/proc/mounts", "r");
-	if (!fp)
-		return -1;
-
-	/*
-	 * in order to handle split hierarchy, we need to scan /proc/mounts
-	 * and inspect every cgroupfs mount point to find one that has
-	 * perf_event subsystem
-	 */
-	path_v1[0] = '\0';
-	path_v2[0] = '\0';
-
-	while (fscanf(fp, "%*s %"__stringify(PATH_MAX)"s %"__stringify(PATH_MAX)"s %"
-				__stringify(PATH_MAX)"s %*d %*d\n",
-				mountpoint, type, tokens) == 3) {
-
-		if (!path_v1[0] && !strcmp(type, "cgroup")) {
-
-			token = strtok_r(tokens, ",", &saved_ptr);
-
-			while (token != NULL) {
-				if (!strcmp(token, "perf_event")) {
-					strcpy(path_v1, mountpoint);
-					break;
-				}
-				token = strtok_r(NULL, ",", &saved_ptr);
-			}
-		}
-
-		if (!path_v2[0] && !strcmp(type, "cgroup2"))
-			strcpy(path_v2, mountpoint);
-
-		if (path_v1[0] && path_v2[0])
-			break;
-	}
-	fclose(fp);
-
-	if (path_v1[0])
-		path = path_v1;
-	else if (path_v2[0])
-		path = path_v2;
-	else
-		return -1;
-
-	if (strlen(path) < maxlen) {
-		strcpy(buf, path);
-		return 0;
-	}
-	return -1;
-}
-
 static int open_cgroup(const char *name)
 {
 	char path[PATH_MAX + 1];
@@ -79,7 +20,7 @@ static int open_cgroup(const char *name)
 	int fd;
 
 
-	if (cgroupfs_find_mountpoint(mnt, PATH_MAX + 1))
+	if (cgroupfs_find_mountpoint(mnt, PATH_MAX + 1, "perf_event"))
 		return -1;
 
 	scnprintf(path, PATH_MAX, "%s/%s", mnt, name);
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 5471045ebf5c..62d2f9b9ce1b 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -363,6 +363,23 @@ struct cs_etm_packet_queue
 	return NULL;
 }
 
+static void cs_etm__packet_swap(struct cs_etm_auxtrace *etm,
+				struct cs_etm_traceid_queue *tidq)
+{
+	struct cs_etm_packet *tmp;
+
+	if (etm->sample_branches || etm->synth_opts.last_branch ||
+	    etm->sample_instructions) {
+		/*
+		 * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
+		 * the next incoming packet.
+		 */
+		tmp = tidq->packet;
+		tidq->packet = tidq->prev_packet;
+		tidq->prev_packet = tmp;
+	}
+}
+
 static void cs_etm__packet_dump(const char *pkt_string)
 {
 	const char *color = PERF_COLOR_BLUE;
@@ -945,7 +962,7 @@ static inline u64 cs_etm__instr_addr(struct cs_etm_queue *etmq,
 	if (packet->isa == CS_ETM_ISA_T32) {
 		u64 addr = packet->start_addr;
 
-		while (offset > 0) {
+		while (offset) {
 			addr += cs_etm__t32_instr_size(etmq,
 						       trace_chan_id, addr);
 			offset--;
@@ -1134,10 +1151,8 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
 
 	cs_etm__copy_insn(etmq, tidq->trace_chan_id, tidq->packet, &sample);
 
-	if (etm->synth_opts.last_branch) {
-		cs_etm__copy_last_branch_rb(etmq, tidq);
+	if (etm->synth_opts.last_branch)
 		sample.branch_stack = tidq->last_branch;
-	}
 
 	if (etm->synth_opts.inject) {
 		ret = cs_etm__inject_event(event, &sample,
@@ -1153,9 +1168,6 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
 			"CS ETM Trace: failed to deliver instruction event, error %d\n",
 			ret);
 
-	if (etm->synth_opts.last_branch)
-		cs_etm__reset_last_branch_rb(tidq);
-
 	return ret;
 }
 
@@ -1172,6 +1184,7 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq,
 	union perf_event *event = tidq->event_buf;
 	struct dummy_branch_stack {
 		u64			nr;
+		u64			hw_idx;
 		struct branch_entry	entries;
 	} dummy_bs;
 	u64 ip;
@@ -1202,6 +1215,7 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq,
 	if (etm->synth_opts.last_branch) {
 		dummy_bs = (struct dummy_branch_stack){
 			.nr = 1,
+			.hw_idx = -1ULL,
 			.entries = {
 				.from = sample.ip,
 				.to = sample.addr,
@@ -1340,12 +1354,14 @@ static int cs_etm__sample(struct cs_etm_queue *etmq,
 			  struct cs_etm_traceid_queue *tidq)
 {
 	struct cs_etm_auxtrace *etm = etmq->etm;
-	struct cs_etm_packet *tmp;
 	int ret;
 	u8 trace_chan_id = tidq->trace_chan_id;
-	u64 instrs_executed = tidq->packet->instr_count;
+	u64 instrs_prev;
+
+	/* Get instructions remainder from previous packet */
+	instrs_prev = tidq->period_instructions;
 
-	tidq->period_instructions += instrs_executed;
+	tidq->period_instructions += tidq->packet->instr_count;
 
 	/*
 	 * Record a branch when the last instruction in
@@ -1363,26 +1379,80 @@ static int cs_etm__sample(struct cs_etm_queue *etmq,
 		 * TODO: allow period to be defined in cycles and clock time
 		 */
 
-		/* Get number of instructions executed after the sample point */
-		u64 instrs_over = tidq->period_instructions -
-			etm->instructions_sample_period;
+		/*
+		 * Below diagram demonstrates the instruction samples
+		 * generation flows:
+		 *
+		 *    Instrs     Instrs       Instrs       Instrs
+		 *   Sample(n)  Sample(n+1)  Sample(n+2)  Sample(n+3)
+		 *    |            |            |            |
+		 *    V            V            V            V
+		 *   --------------------------------------------------
+		 *            ^                                  ^
+		 *            |                                  |
+		 *         Period                             Period
+		 *    instructions(Pi)                   instructions(Pi')
+		 *
+		 *            |                                  |
+		 *            \---------------- -----------------/
+		 *                             V
+		 *                 tidq->packet->instr_count
+		 *
+		 * Instrs Sample(n...) are the synthesised samples occurring
+		 * every etm->instructions_sample_period instructions - as
+		 * defined on the perf command line.  Sample(n) is being the
+		 * last sample before the current etm packet, n+1 to n+3
+		 * samples are generated from the current etm packet.
+		 *
+		 * tidq->packet->instr_count represents the number of
+		 * instructions in the current etm packet.
+		 *
+		 * Period instructions (Pi) contains the the number of
+		 * instructions executed after the sample point(n) from the
+		 * previous etm packet.  This will always be less than
+		 * etm->instructions_sample_period.
+		 *
+		 * When generate new samples, it combines with two parts
+		 * instructions, one is the tail of the old packet and another
+		 * is the head of the new coming packet, to generate
+		 * sample(n+1); sample(n+2) and sample(n+3) consume the
+		 * instructions with sample period.  After sample(n+3), the rest
+		 * instructions will be used by later packet and it is assigned
+		 * to tidq->period_instructions for next round calculation.
+		 */
 
 		/*
-		 * Calculate the address of the sampled instruction (-1 as
-		 * sample is reported as though instruction has just been
-		 * executed, but PC has not advanced to next instruction)
+		 * Get the initial offset into the current packet instructions;
+		 * entry conditions ensure that instrs_prev is less than
+		 * etm->instructions_sample_period.
 		 */
-		u64 offset = (instrs_executed - instrs_over - 1);
-		u64 addr = cs_etm__instr_addr(etmq, trace_chan_id,
-					      tidq->packet, offset);
+		u64 offset = etm->instructions_sample_period - instrs_prev;
+		u64 addr;
 
-		ret = cs_etm__synth_instruction_sample(
-			etmq, tidq, addr, etm->instructions_sample_period);
-		if (ret)
-			return ret;
+		/* Prepare last branches for instruction sample */
+		if (etm->synth_opts.last_branch)
+			cs_etm__copy_last_branch_rb(etmq, tidq);
 
-		/* Carry remaining instructions into next sample period */
-		tidq->period_instructions = instrs_over;
+		while (tidq->period_instructions >=
+				etm->instructions_sample_period) {
+			/*
+			 * Calculate the address of the sampled instruction (-1
+			 * as sample is reported as though instruction has just
+			 * been executed, but PC has not advanced to next
+			 * instruction)
+			 */
+			addr = cs_etm__instr_addr(etmq, trace_chan_id,
+						  tidq->packet, offset - 1);
+			ret = cs_etm__synth_instruction_sample(
+				etmq, tidq, addr,
+				etm->instructions_sample_period);
+			if (ret)
+				return ret;
+
+			offset += etm->instructions_sample_period;
+			tidq->period_instructions -=
+				etm->instructions_sample_period;
+		}
 	}
 
 	if (etm->sample_branches) {
@@ -1404,15 +1474,7 @@ static int cs_etm__sample(struct cs_etm_queue *etmq,
 		}
 	}
 
-	if (etm->sample_branches || etm->synth_opts.last_branch) {
-		/*
-		 * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
-		 * the next incoming packet.
-		 */
-		tmp = tidq->packet;
-		tidq->packet = tidq->prev_packet;
-		tidq->prev_packet = tmp;
-	}
+	cs_etm__packet_swap(etm, tidq);
 
 	return 0;
 }
@@ -1441,7 +1503,6 @@ static int cs_etm__flush(struct cs_etm_queue *etmq,
 {
 	int err = 0;
 	struct cs_etm_auxtrace *etm = etmq->etm;
-	struct cs_etm_packet *tmp;
 
 	/* Handle start tracing packet */
 	if (tidq->prev_packet->sample_type == CS_ETM_EMPTY)
@@ -1449,6 +1510,11 @@ static int cs_etm__flush(struct cs_etm_queue *etmq,
 
 	if (etmq->etm->synth_opts.last_branch &&
 	    tidq->prev_packet->sample_type == CS_ETM_RANGE) {
+		u64 addr;
+
+		/* Prepare last branches for instruction sample */
+		cs_etm__copy_last_branch_rb(etmq, tidq);
+
 		/*
 		 * Generate a last branch event for the branches left in the
 		 * circular buffer at the end of the trace.
@@ -1456,7 +1522,7 @@ static int cs_etm__flush(struct cs_etm_queue *etmq,
 		 * Use the address of the end of the last reported execution
 		 * range
 		 */
-		u64 addr = cs_etm__last_executed_instr(tidq->prev_packet);
+		addr = cs_etm__last_executed_instr(tidq->prev_packet);
 
 		err = cs_etm__synth_instruction_sample(
 			etmq, tidq, addr,
@@ -1476,15 +1542,11 @@ static int cs_etm__flush(struct cs_etm_queue *etmq,
 	}
 
 swap_packet:
-	if (etm->sample_branches || etm->synth_opts.last_branch) {
-		/*
-		 * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
-		 * the next incoming packet.
-		 */
-		tmp = tidq->packet;
-		tidq->packet = tidq->prev_packet;
-		tidq->prev_packet = tmp;
-	}
+	cs_etm__packet_swap(etm, tidq);
+
+	/* Reset last branches after flush the trace */
+	if (etm->synth_opts.last_branch)
+		cs_etm__reset_last_branch_rb(tidq);
 
 	return err;
 }
@@ -1505,11 +1567,16 @@ static int cs_etm__end_block(struct cs_etm_queue *etmq,
 	 */
 	if (etmq->etm->synth_opts.last_branch &&
 	    tidq->prev_packet->sample_type == CS_ETM_RANGE) {
+		u64 addr;
+
+		/* Prepare last branches for instruction sample */
+		cs_etm__copy_last_branch_rb(etmq, tidq);
+
 		/*
 		 * Use the address of the end of the last reported execution
 		 * range.
 		 */
-		u64 addr = cs_etm__last_executed_instr(tidq->prev_packet);
+		addr = cs_etm__last_executed_instr(tidq->prev_packet);
 
 		err = cs_etm__synth_instruction_sample(
 			etmq, tidq, addr,
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 85223159737c..3cda40a2fafc 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -139,6 +139,7 @@ struct perf_sample {
 	u16 insn_len;
 	u8  cpumode;
 	u16 misc;
+	bool no_hw_idx;		/* No hw_idx collected in branch_stack */
 	char insn[MAX_INSN];
 	void *raw_data;
 	struct ip_callchain *callchain;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index c8dc4450884c..816d930d774e 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -712,7 +712,8 @@ static void __perf_evsel__config_callchain(struct evsel *evsel,
 				attr->branch_sample_type = PERF_SAMPLE_BRANCH_USER |
 							PERF_SAMPLE_BRANCH_CALL_STACK |
 							PERF_SAMPLE_BRANCH_NO_CYCLES |
-							PERF_SAMPLE_BRANCH_NO_FLAGS;
+							PERF_SAMPLE_BRANCH_NO_FLAGS |
+							PERF_SAMPLE_BRANCH_HW_INDEX;
 			}
 		} else
 			 pr_warning("Cannot use LBR callstack with branch stack. "
@@ -763,7 +764,8 @@ perf_evsel__reset_callgraph(struct evsel *evsel,
 	if (param->record_mode == CALLCHAIN_LBR) {
 		perf_evsel__reset_sample_bit(evsel, BRANCH_STACK);
 		attr->branch_sample_type &= ~(PERF_SAMPLE_BRANCH_USER |
-					      PERF_SAMPLE_BRANCH_CALL_STACK);
+					      PERF_SAMPLE_BRANCH_CALL_STACK |
+					      PERF_SAMPLE_BRANCH_HW_INDEX);
 	}
 	if (param->record_mode == CALLCHAIN_DWARF) {
 		perf_evsel__reset_sample_bit(evsel, REGS_USER);
@@ -1673,6 +1675,8 @@ fallback_missing_features:
 		evsel->core.attr.ksymbol = 0;
 	if (perf_missing_features.bpf)
 		evsel->core.attr.bpf_event = 0;
+	if (perf_missing_features.branch_hw_idx)
+		evsel->core.attr.branch_sample_type &= ~PERF_SAMPLE_BRANCH_HW_INDEX;
 retry_sample_id:
 	if (perf_missing_features.sample_id_all)
 		evsel->core.attr.sample_id_all = 0;
@@ -1784,7 +1788,12 @@ try_fallback:
 	 * Must probe features in the order they were added to the
 	 * perf_event_attr interface.
 	 */
-	if (!perf_missing_features.aux_output && evsel->core.attr.aux_output) {
+	if (!perf_missing_features.branch_hw_idx &&
+	    (evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX)) {
+		perf_missing_features.branch_hw_idx = true;
+		pr_debug2("switching off branch HW index support\n");
+		goto fallback_missing_features;
+	} else if (!perf_missing_features.aux_output && evsel->core.attr.aux_output) {
 		perf_missing_features.aux_output = true;
 		pr_debug2_peo("Kernel has no attr.aux_output support, bailing out\n");
 		goto out_close;
@@ -2169,7 +2178,12 @@ int perf_evsel__parse_sample(struct evsel *evsel, union perf_event *event,
 
 		if (data->branch_stack->nr > max_branch_nr)
 			return -EFAULT;
+
 		sz = data->branch_stack->nr * sizeof(struct branch_entry);
+		if (perf_evsel__has_branch_hw_idx(evsel))
+			sz += sizeof(u64);
+		else
+			data->no_hw_idx = true;
 		OVERFLOW_CHECK(array, sz, max_size);
 		array = (void *)array + sz;
 	}
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index dc14f4a823cd..33804740e2ca 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -119,6 +119,7 @@ struct perf_missing_features {
 	bool ksymbol;
 	bool bpf;
 	bool aux_output;
+	bool branch_hw_idx;
 };
 
 extern struct perf_missing_features perf_missing_features;
@@ -389,6 +390,11 @@ static inline bool perf_evsel__has_branch_callstack(const struct evsel *evsel)
 	return evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK;
 }
 
+static inline bool perf_evsel__has_branch_hw_idx(const struct evsel *evsel)
+{
+	return evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX;
+}
+
 static inline bool evsel__has_callchain(const struct evsel *evsel)
 {
 	return (evsel->core.attr.sample_type & PERF_SAMPLE_CALLCHAIN) != 0;
diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c
new file mode 100644
index 000000000000..fd192ddf93c1
--- /dev/null
+++ b/tools/perf/util/expr.c
@@ -0,0 +1,112 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdbool.h>
+#include <assert.h>
+#include "expr.h"
+#include "expr-bison.h"
+#define YY_EXTRA_TYPE int
+#include "expr-flex.h"
+
+#ifdef PARSER_DEBUG
+extern int expr_debug;
+#endif
+
+/* Caller must make sure id is allocated */
+void expr__add_id(struct parse_ctx *ctx, const char *name, double val)
+{
+	int idx;
+
+	assert(ctx->num_ids < MAX_PARSE_ID);
+	idx = ctx->num_ids++;
+	ctx->ids[idx].name = name;
+	ctx->ids[idx].val = val;
+}
+
+void expr__ctx_init(struct parse_ctx *ctx)
+{
+	ctx->num_ids = 0;
+}
+
+static int
+__expr__parse(double *val, struct parse_ctx *ctx, const char *expr,
+	      int start)
+{
+	YY_BUFFER_STATE buffer;
+	void *scanner;
+	int ret;
+
+	ret = expr_lex_init_extra(start, &scanner);
+	if (ret)
+		return ret;
+
+	buffer = expr__scan_string(expr, scanner);
+
+#ifdef PARSER_DEBUG
+	expr_debug = 1;
+#endif
+
+	ret = expr_parse(val, ctx, scanner);
+
+	expr__flush_buffer(buffer, scanner);
+	expr__delete_buffer(buffer, scanner);
+	expr_lex_destroy(scanner);
+	return ret;
+}
+
+int expr__parse(double *final_val, struct parse_ctx *ctx, const char *expr)
+{
+	return __expr__parse(final_val, ctx, expr, EXPR_PARSE) ? -1 : 0;
+}
+
+static bool
+already_seen(const char *val, const char *one, const char **other,
+	     int num_other)
+{
+	int i;
+
+	if (one && !strcasecmp(one, val))
+		return true;
+	for (i = 0; i < num_other; i++)
+		if (!strcasecmp(other[i], val))
+			return true;
+	return false;
+}
+
+int expr__find_other(const char *expr, const char *one, const char ***other,
+		     int *num_other)
+{
+	int err, i = 0, j = 0;
+	struct parse_ctx ctx;
+
+	expr__ctx_init(&ctx);
+	err = __expr__parse(NULL, &ctx, expr, EXPR_OTHER);
+	if (err)
+		return -1;
+
+	*other = malloc((ctx.num_ids + 1) * sizeof(char *));
+	if (!*other)
+		return -ENOMEM;
+
+	for (i = 0, j = 0; i < ctx.num_ids; i++) {
+		const char *str = ctx.ids[i].name;
+
+		if (already_seen(str, one, *other, j))
+			continue;
+
+		str = strdup(str);
+		if (!str)
+			goto out;
+		(*other)[j++] = str;
+	}
+	(*other)[j] = NULL;
+
+out:
+	if (i != ctx.num_ids) {
+		while (--j)
+			free((char *) (*other)[i]);
+		free(*other);
+		err = -1;
+	}
+
+	*num_other = j;
+	return err;
+}
diff --git a/tools/perf/util/expr.h b/tools/perf/util/expr.h
index 046160831f90..9377538f4097 100644
--- a/tools/perf/util/expr.h
+++ b/tools/perf/util/expr.h
@@ -2,7 +2,7 @@
 #ifndef PARSE_CTX_H
 #define PARSE_CTX_H 1
 
-#define EXPR_MAX_OTHER 15
+#define EXPR_MAX_OTHER 20
 #define MAX_PARSE_ID EXPR_MAX_OTHER
 
 struct parse_id {
@@ -17,10 +17,8 @@ struct parse_ctx {
 
 void expr__ctx_init(struct parse_ctx *ctx);
 void expr__add_id(struct parse_ctx *ctx, const char *id, double val);
-#ifndef IN_EXPR_Y
-int expr__parse(double *final_val, struct parse_ctx *ctx, const char **pp);
-#endif
-int expr__find_other(const char *p, const char *one, const char ***other,
+int expr__parse(double *final_val, struct parse_ctx *ctx, const char *expr);
+int expr__find_other(const char *expr, const char *one, const char ***other,
 		int *num_other);
 
 #endif
diff --git a/tools/perf/util/expr.l b/tools/perf/util/expr.l
new file mode 100644
index 000000000000..eaad29243c23
--- /dev/null
+++ b/tools/perf/util/expr.l
@@ -0,0 +1,114 @@
+%option prefix="expr_"
+%option reentrant
+%option bison-bridge
+
+%{
+#include <linux/compiler.h>
+#include "expr.h"
+#include "expr-bison.h"
+
+char *expr_get_text(yyscan_t yyscanner);
+YYSTYPE *expr_get_lval(yyscan_t yyscanner);
+
+static int __value(YYSTYPE *yylval, char *str, int base, int token)
+{
+	u64 num;
+
+	errno = 0;
+	num = strtoull(str, NULL, base);
+	if (errno)
+		return EXPR_ERROR;
+
+	yylval->num = num;
+	return token;
+}
+
+static int value(yyscan_t scanner, int base)
+{
+	YYSTYPE *yylval = expr_get_lval(scanner);
+	char *text = expr_get_text(scanner);
+
+	return __value(yylval, text, base, NUMBER);
+}
+
+/*
+ * Allow @ instead of / to be able to specify pmu/event/ without
+ * conflicts with normal division.
+ */
+static char *normalize(char *str)
+{
+	char *ret = str;
+	char *dst = str;
+
+	while (*str) {
+		if (*str == '@')
+			*dst++ = '/';
+		else if (*str == '\\')
+			*dst++ = *++str;
+		else
+			*dst++ = *str;
+		str++;
+	}
+
+	*dst = 0x0;
+	return ret;
+}
+
+static int str(yyscan_t scanner, int token)
+{
+	YYSTYPE *yylval = expr_get_lval(scanner);
+	char *text = expr_get_text(scanner);
+
+	yylval->str = normalize(strdup(text));
+	if (!yylval->str)
+		return EXPR_ERROR;
+
+	yylval->str = normalize(yylval->str);
+	return token;
+}
+%}
+
+number		[0-9]+
+
+sch		[-,=]
+spec		\\{sch}
+sym		[0-9a-zA-Z_\.:@]+
+symbol		{spec}*{sym}*{spec}*{sym}*
+
+%%
+	{
+		int start_token;
+
+		start_token = expr_get_extra(yyscanner);
+
+		if (start_token) {
+			expr_set_extra(NULL, yyscanner);
+			return start_token;
+		}
+	}
+
+max		{ return MAX; }
+min		{ return MIN; }
+if		{ return IF; }
+else		{ return ELSE; }
+#smt_on		{ return SMT_ON; }
+{number}	{ return value(yyscanner, 10); }
+{symbol}	{ return str(yyscanner, ID); }
+"|"		{ return '|'; }
+"^"		{ return '^'; }
+"&"		{ return '&'; }
+"-"		{ return '-'; }
+"+"		{ return '+'; }
+"*"		{ return '*'; }
+"/"		{ return '/'; }
+"%"		{ return '%'; }
+"("		{ return '('; }
+")"		{ return ')'; }
+","		{ return ','; }
+.		{ }
+%%
+
+int expr_wrap(void *scanner __maybe_unused)
+{
+	return 1;
+}
diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y
index 7d226241f1d7..4720cbe79357 100644
--- a/tools/perf/util/expr.y
+++ b/tools/perf/util/expr.y
@@ -1,31 +1,32 @@
 /* Simple expression parser */
 %{
+#define YYDEBUG 1
+#include <stdio.h>
 #include "util.h"
 #include "util/debug.h"
 #include <stdlib.h> // strtod()
 #define IN_EXPR_Y 1
 #include "expr.h"
 #include "smt.h"
-#include <assert.h>
 #include <string.h>
 
-#define MAXIDLEN 256
 %}
 
 %define api.pure full
 
 %parse-param { double *final_val }
 %parse-param { struct parse_ctx *ctx }
-%parse-param { const char **pp }
-%lex-param { const char **pp }
+%parse-param {void *scanner}
+%lex-param {void* scanner}
 
 %union {
-	double num;
-	char id[MAXIDLEN+1];
+	double	 num;
+	char	*str;
 }
 
+%token EXPR_PARSE EXPR_OTHER EXPR_ERROR
 %token <num> NUMBER
-%token <id> ID
+%token <str> ID
 %token MIN MAX IF ELSE SMT_ON
 %left MIN MAX IF
 %left '|'
@@ -37,11 +38,9 @@
 %type <num> expr if_expr
 
 %{
-static int expr__lex(YYSTYPE *res, const char **pp);
-
-static void expr__error(double *final_val __maybe_unused,
+static void expr_error(double *final_val __maybe_unused,
 		       struct parse_ctx *ctx __maybe_unused,
-		       const char **pp __maybe_unused,
+		       void *scanner,
 		       const char *s)
 {
 	pr_debug("%s\n", s);
@@ -63,6 +62,27 @@ static int lookup_id(struct parse_ctx *ctx, char *id, double *val)
 %}
 %%
 
+start:
+EXPR_PARSE all_expr
+|
+EXPR_OTHER all_other
+
+all_other: all_other other
+|
+
+other: ID
+{
+	if (ctx->num_ids + 1 >= EXPR_MAX_OTHER) {
+		pr_err("failed: way too many variables");
+		YYABORT;
+	}
+
+	ctx->ids[ctx->num_ids++].name = $1;
+}
+|
+MIN | MAX | IF | ELSE | SMT_ON | NUMBER | '|' | '^' | '&' | '-' | '+' | '*' | '/' | '%' | '(' | ')'
+
+
 all_expr: if_expr			{ *final_val = $1; }
 	;
 
@@ -93,146 +113,3 @@ expr:	  NUMBER
 	;
 
 %%
-
-static int expr__symbol(YYSTYPE *res, const char *p, const char **pp)
-{
-	char *dst = res->id;
-	const char *s = p;
-
-	if (*p == '#')
-		*dst++ = *p++;
-
-	while (isalnum(*p) || *p == '_' || *p == '.' || *p == ':' || *p == '@' || *p == '\\') {
-		if (p - s >= MAXIDLEN)
-			return -1;
-		/*
-		 * Allow @ instead of / to be able to specify pmu/event/ without
-		 * conflicts with normal division.
-		 */
-		if (*p == '@')
-			*dst++ = '/';
-		else if (*p == '\\')
-			*dst++ = *++p;
-		else
-			*dst++ = *p;
-		p++;
-	}
-	*dst = 0;
-	*pp = p;
-	dst = res->id;
-	switch (dst[0]) {
-	case 'm':
-		if (!strcmp(dst, "min"))
-			return MIN;
-		if (!strcmp(dst, "max"))
-			return MAX;
-		break;
-	case 'i':
-		if (!strcmp(dst, "if"))
-			return IF;
-		break;
-	case 'e':
-		if (!strcmp(dst, "else"))
-			return ELSE;
-		break;
-	case '#':
-		if (!strcasecmp(dst, "#smt_on"))
-			return SMT_ON;
-		break;
-	}
-	return ID;
-}
-
-static int expr__lex(YYSTYPE *res, const char **pp)
-{
-	int tok;
-	const char *s;
-	const char *p = *pp;
-
-	while (isspace(*p))
-		p++;
-	s = p;
-	switch (*p++) {
-	case '#':
-	case 'a' ... 'z':
-	case 'A' ... 'Z':
-		return expr__symbol(res, p - 1, pp);
-	case '0' ... '9': case '.':
-		res->num = strtod(s, (char **)&p);
-		tok = NUMBER;
-		break;
-	default:
-		tok = *s;
-		break;
-	}
-	*pp = p;
-	return tok;
-}
-
-/* Caller must make sure id is allocated */
-void expr__add_id(struct parse_ctx *ctx, const char *name, double val)
-{
-	int idx;
-	assert(ctx->num_ids < MAX_PARSE_ID);
-	idx = ctx->num_ids++;
-	ctx->ids[idx].name = name;
-	ctx->ids[idx].val = val;
-}
-
-void expr__ctx_init(struct parse_ctx *ctx)
-{
-	ctx->num_ids = 0;
-}
-
-static bool already_seen(const char *val, const char *one, const char **other,
-			 int num_other)
-{
-	int i;
-
-	if (one && !strcasecmp(one, val))
-		return true;
-	for (i = 0; i < num_other; i++)
-		if (!strcasecmp(other[i], val))
-			return true;
-	return false;
-}
-
-int expr__find_other(const char *p, const char *one, const char ***other,
-		     int *num_otherp)
-{
-	const char *orig = p;
-	int err = -1;
-	int num_other;
-
-	*other = malloc((EXPR_MAX_OTHER + 1) * sizeof(char *));
-	if (!*other)
-		return -1;
-
-	num_other = 0;
-	for (;;) {
-		YYSTYPE val;
-		int tok = expr__lex(&val, &p);
-		if (tok == 0) {
-			err = 0;
-			break;
-		}
-		if (tok == ID && !already_seen(val.id, one, *other, num_other)) {
-			if (num_other >= EXPR_MAX_OTHER - 1) {
-				pr_debug("Too many extra events in %s\n", orig);
-				break;
-			}
-			(*other)[num_other] = strdup(val.id);
-			if (!(*other)[num_other])
-				return -1;
-			num_other++;
-		}
-	}
-	(*other)[num_other] = NULL;
-	*num_otherp = num_other;
-	if (err) {
-		*num_otherp = 0;
-		free(*other);
-		*other = NULL;
-	}
-	return err;
-}
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 4246e7447e54..acbd046bf95c 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1590,6 +1590,40 @@ static void free_event_desc(struct evsel *events)
 	free(events);
 }
 
+static bool perf_attr_check(struct perf_event_attr *attr)
+{
+	if (attr->__reserved_1 || attr->__reserved_2 || attr->__reserved_3) {
+		pr_warning("Reserved bits are set unexpectedly. "
+			   "Please update perf tool.\n");
+		return false;
+	}
+
+	if (attr->sample_type & ~(PERF_SAMPLE_MAX-1)) {
+		pr_warning("Unknown sample type (0x%llx) is detected. "
+			   "Please update perf tool.\n",
+			   attr->sample_type);
+		return false;
+	}
+
+	if (attr->read_format & ~(PERF_FORMAT_MAX-1)) {
+		pr_warning("Unknown read format (0x%llx) is detected. "
+			   "Please update perf tool.\n",
+			   attr->read_format);
+		return false;
+	}
+
+	if ((attr->sample_type & PERF_SAMPLE_BRANCH_STACK) &&
+	    (attr->branch_sample_type & ~(PERF_SAMPLE_BRANCH_MAX-1))) {
+		pr_warning("Unknown branch sample type (0x%llx) is detected. "
+			   "Please update perf tool.\n",
+			   attr->branch_sample_type);
+
+		return false;
+	}
+
+	return true;
+}
+
 static struct evsel *read_event_desc(struct feat_fd *ff)
 {
 	struct evsel *evsel, *events = NULL;
@@ -1634,6 +1668,9 @@ static struct evsel *read_event_desc(struct feat_fd *ff)
 
 		memcpy(&evsel->core.attr, buf, msz);
 
+		if (!perf_attr_check(&evsel->core.attr))
+			goto error;
+
 		if (do_read_u32(ff, &nr))
 			goto error;
 
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index ca5a8f4d007e..e74a5acf66d9 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -2584,9 +2584,10 @@ void hist__account_cycles(struct branch_stack *bs, struct addr_location *al,
 			  u64 *total_cycles)
 {
 	struct branch_info *bi;
+	struct branch_entry *entries = perf_sample__branch_entries(sample);
 
 	/* If we have branch cycles always annotate them. */
-	if (bs && bs->nr && bs->entries[0].flags.cycles) {
+	if (bs && bs->nr && entries[0].flags.cycles) {
 		int i;
 
 		bi = sample__resolve_bstack(sample, al);
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 33cf8928cf05..23c8289c2472 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -1295,6 +1295,7 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq)
 	struct perf_sample sample = { .ip = 0, };
 	struct dummy_branch_stack {
 		u64			nr;
+		u64			hw_idx;
 		struct branch_entry	entries;
 	} dummy_bs;
 
@@ -1316,6 +1317,7 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq)
 	if (pt->synth_opts.last_branch && sort__mode == SORT_MODE__BRANCH) {
 		dummy_bs = (struct dummy_branch_stack){
 			.nr = 1,
+			.hw_idx = -1ULL,
 			.entries = {
 				.from = sample.ip,
 				.to = sample.addr,
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index b5af680fc667..dbdffb6673fe 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -265,6 +265,8 @@ static int detect_kbuild_dir(char **kbuild_dir)
 			return -ENOMEM;
 		return 0;
 	}
+	pr_debug("%s: Couldn't find \"%s\", missing kernel-devel package?.\n",
+		 __func__, autoconf_path);
 	free(autoconf_path);
 	return -ENOENT;
 }
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index fb5c2cd44d30..fd14f1489802 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -2081,15 +2081,16 @@ struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
 {
 	unsigned int i;
 	const struct branch_stack *bs = sample->branch_stack;
+	struct branch_entry *entries = perf_sample__branch_entries(sample);
 	struct branch_info *bi = calloc(bs->nr, sizeof(struct branch_info));
 
 	if (!bi)
 		return NULL;
 
 	for (i = 0; i < bs->nr; i++) {
-		ip__resolve_ams(al->thread, &bi[i].to, bs->entries[i].to);
-		ip__resolve_ams(al->thread, &bi[i].from, bs->entries[i].from);
-		bi[i].flags = bs->entries[i].flags;
+		ip__resolve_ams(al->thread, &bi[i].to, entries[i].to);
+		ip__resolve_ams(al->thread, &bi[i].from, entries[i].from);
+		bi[i].flags = entries[i].flags;
 	}
 	return bi;
 }
@@ -2185,6 +2186,7 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
 	/* LBR only affects the user callchain */
 	if (i != chain_nr) {
 		struct branch_stack *lbr_stack = sample->branch_stack;
+		struct branch_entry *entries = perf_sample__branch_entries(sample);
 		int lbr_nr = lbr_stack->nr, j, k;
 		bool branch;
 		struct branch_flags *flags;
@@ -2210,31 +2212,29 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
 					ip = chain->ips[j];
 				else if (j > i + 1) {
 					k = j - i - 2;
-					ip = lbr_stack->entries[k].from;
+					ip = entries[k].from;
 					branch = true;
-					flags = &lbr_stack->entries[k].flags;
+					flags = &entries[k].flags;
 				} else {
-					ip = lbr_stack->entries[0].to;
+					ip = entries[0].to;
 					branch = true;
-					flags = &lbr_stack->entries[0].flags;
-					branch_from =
-						lbr_stack->entries[0].from;
+					flags = &entries[0].flags;
+					branch_from = entries[0].from;
 				}
 			} else {
 				if (j < lbr_nr) {
 					k = lbr_nr - j - 1;
-					ip = lbr_stack->entries[k].from;
+					ip = entries[k].from;
 					branch = true;
-					flags = &lbr_stack->entries[k].flags;
+					flags = &entries[k].flags;
 				}
 				else if (j > lbr_nr)
 					ip = chain->ips[i + 1 - (j - lbr_nr)];
 				else {
-					ip = lbr_stack->entries[0].to;
+					ip = entries[0].to;
 					branch = true;
-					flags = &lbr_stack->entries[0].flags;
-					branch_from =
-						lbr_stack->entries[0].from;
+					flags = &entries[0].flags;
+					branch_from = entries[0].from;
 				}
 			}
 
@@ -2281,6 +2281,7 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 					    int max_stack)
 {
 	struct branch_stack *branch = sample->branch_stack;
+	struct branch_entry *entries = perf_sample__branch_entries(sample);
 	struct ip_callchain *chain = sample->callchain;
 	int chain_nr = 0;
 	u8 cpumode = PERF_RECORD_MISC_USER;
@@ -2328,7 +2329,7 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 
 		for (i = 0; i < nr; i++) {
 			if (callchain_param.order == ORDER_CALLEE) {
-				be[i] = branch->entries[i];
+				be[i] = entries[i];
 
 				if (chain == NULL)
 					continue;
@@ -2347,7 +2348,7 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 				    be[i].from >= chain->ips[first_call] - 8)
 					first_call++;
 			} else
-				be[i] = branch->entries[branch->nr - i - 1];
+				be[i] = entries[branch->nr - i - 1];
 		}
 
 		memset(iter, 0, sizeof(struct iterations) * nr);
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index b342f744b1fc..53d96611e6a6 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -44,8 +44,8 @@ static inline int is_no_dso_memory(const char *filename)
 
 static inline int is_android_lib(const char *filename)
 {
-	return !strncmp(filename, "/data/app-lib", 13) ||
-	       !strncmp(filename, "/system/lib", 11);
+	return strstarts(filename, "/data/app-lib/") ||
+	       strstarts(filename, "/system/lib/");
 }
 
 static inline bool replace_android_lib(const char *filename, char *newfilename)
@@ -65,7 +65,7 @@ static inline bool replace_android_lib(const char *filename, char *newfilename)
 
 	app_abi_length = strlen(app_abi);
 
-	if (!strncmp(filename, "/data/app-lib", 13)) {
+	if (strstarts(filename, "/data/app-lib/")) {
 		char *apk_path;
 
 		if (!app_abi_length)
@@ -89,7 +89,7 @@ static inline bool replace_android_lib(const char *filename, char *newfilename)
 		return true;
 	}
 
-	if (!strncmp(filename, "/system/lib/", 12)) {
+	if (strstarts(filename, "/system/lib/")) {
 		char *ndk, *app;
 		const char *arch;
 		size_t ndk_length;
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 02aee946b6c1..c3a8c701609a 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -22,6 +22,8 @@
 #include <linux/string.h>
 #include <linux/zalloc.h>
 #include <subcmd/parse-options.h>
+#include <api/fs/fs.h>
+#include "util.h"
 
 struct metric_event *metricgroup__lookup(struct rblist *metric_events,
 					 struct evsel *evsel,
@@ -399,13 +401,85 @@ void metricgroup__print(bool metrics, bool metricgroups, char *filter,
 	strlist__delete(metriclist);
 }
 
+static void metricgroup__add_metric_weak_group(struct strbuf *events,
+					       const char **ids,
+					       int idnum)
+{
+	bool no_group = false;
+	int i;
+
+	for (i = 0; i < idnum; i++) {
+		pr_debug("found event %s\n", ids[i]);
+		/*
+		 * Duration time maps to a software event and can make
+		 * groups not count. Always use it outside a
+		 * group.
+		 */
+		if (!strcmp(ids[i], "duration_time")) {
+			if (i > 0)
+				strbuf_addf(events, "}:W,");
+			strbuf_addf(events, "duration_time");
+			no_group = true;
+			continue;
+		}
+		strbuf_addf(events, "%s%s",
+			i == 0 || no_group ? "{" : ",",
+			ids[i]);
+		no_group = false;
+	}
+	if (!no_group)
+		strbuf_addf(events, "}:W");
+}
+
+static void metricgroup__add_metric_non_group(struct strbuf *events,
+					      const char **ids,
+					      int idnum)
+{
+	int i;
+
+	for (i = 0; i < idnum; i++)
+		strbuf_addf(events, ",%s", ids[i]);
+}
+
+static void metricgroup___watchdog_constraint_hint(const char *name, bool foot)
+{
+	static bool violate_nmi_constraint;
+
+	if (!foot) {
+		pr_warning("Splitting metric group %s into standalone metrics.\n", name);
+		violate_nmi_constraint = true;
+		return;
+	}
+
+	if (!violate_nmi_constraint)
+		return;
+
+	pr_warning("Try disabling the NMI watchdog to comply NO_NMI_WATCHDOG metric constraint:\n"
+		   "    echo 0 > /proc/sys/kernel/nmi_watchdog\n"
+		   "    perf stat ...\n"
+		   "    echo 1 > /proc/sys/kernel/nmi_watchdog\n");
+}
+
+static bool metricgroup__has_constraint(struct pmu_event *pe)
+{
+	if (!pe->metric_constraint)
+		return false;
+
+	if (!strcmp(pe->metric_constraint, "NO_NMI_WATCHDOG") &&
+	    sysctl__nmi_watchdog_enabled()) {
+		metricgroup___watchdog_constraint_hint(pe->metric_name, false);
+		return true;
+	}
+
+	return false;
+}
+
 static int metricgroup__add_metric(const char *metric, struct strbuf *events,
 				   struct list_head *group_list)
 {
 	struct pmu_events_map *map = perf_pmu__find_map(NULL);
 	struct pmu_event *pe;
-	int ret = -EINVAL;
-	int i, j;
+	int i, ret = -EINVAL;
 
 	if (!map)
 		return 0;
@@ -422,7 +496,6 @@ static int metricgroup__add_metric(const char *metric, struct strbuf *events,
 			const char **ids;
 			int idnum;
 			struct egroup *eg;
-			bool no_group = false;
 
 			pr_debug("metric expr %s for %s\n", pe->metric_expr, pe->metric_name);
 
@@ -431,27 +504,11 @@ static int metricgroup__add_metric(const char *metric, struct strbuf *events,
 				continue;
 			if (events->len > 0)
 				strbuf_addf(events, ",");
-			for (j = 0; j < idnum; j++) {
-				pr_debug("found event %s\n", ids[j]);
-				/*
-				 * Duration time maps to a software event and can make
-				 * groups not count. Always use it outside a
-				 * group.
-				 */
-				if (!strcmp(ids[j], "duration_time")) {
-					if (j > 0)
-						strbuf_addf(events, "}:W,");
-					strbuf_addf(events, "duration_time");
-					no_group = true;
-					continue;
-				}
-				strbuf_addf(events, "%s%s",
-					j == 0 || no_group ? "{" : ",",
-					ids[j]);
-				no_group = false;
-			}
-			if (!no_group)
-				strbuf_addf(events, "}:W");
+
+			if (metricgroup__has_constraint(pe))
+				metricgroup__add_metric_non_group(events, ids, idnum);
+			else
+				metricgroup__add_metric_weak_group(events, ids, idnum);
 
 			eg = malloc(sizeof(struct egroup));
 			if (!eg) {
@@ -493,6 +550,10 @@ static int metricgroup__add_metric_list(const char *list, struct strbuf *events,
 		}
 	}
 	free(nlist);
+
+	if (!ret)
+		metricgroup___watchdog_constraint_hint(NULL, true);
+
 	return ret;
 }
 
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 3b664fa673a6..ab7108d22428 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -98,20 +98,29 @@ static int perf_mmap__aio_bind(struct mmap *map, int idx, int cpu, int affinity)
 {
 	void *data;
 	size_t mmap_len;
-	unsigned long node_mask;
+	unsigned long *node_mask;
+	unsigned long node_index;
+	int err = 0;
 
 	if (affinity != PERF_AFFINITY_SYS && cpu__max_node() > 1) {
 		data = map->aio.data[idx];
 		mmap_len = mmap__mmap_len(map);
-		node_mask = 1UL << cpu__get_node(cpu);
-		if (mbind(data, mmap_len, MPOL_BIND, &node_mask, 1, 0)) {
-			pr_err("Failed to bind [%p-%p] AIO buffer to node %d: error %m\n",
-				data, data + mmap_len, cpu__get_node(cpu));
+		node_index = cpu__get_node(cpu);
+		node_mask = bitmap_alloc(node_index + 1);
+		if (!node_mask) {
+			pr_err("Failed to allocate node mask for mbind: error %m\n");
 			return -1;
 		}
+		set_bit(node_index, node_mask);
+		if (mbind(data, mmap_len, MPOL_BIND, node_mask, node_index + 1 + 1, 0)) {
+			pr_err("Failed to bind [%p-%p] AIO buffer to node %lu: error %m\n",
+				data, data + mmap_len, node_index);
+			err = -1;
+		}
+		bitmap_free(node_mask);
 	}
 
-	return 0;
+	return err;
 }
 #else /* !HAVE_LIBNUMA_SUPPORT */
 static int perf_mmap__aio_alloc(struct mmap *map, int idx)
diff --git a/tools/perf/util/perf_event_attr_fprintf.c b/tools/perf/util/perf_event_attr_fprintf.c
index 651203126c71..355d3458d4e6 100644
--- a/tools/perf/util/perf_event_attr_fprintf.c
+++ b/tools/perf/util/perf_event_attr_fprintf.c
@@ -50,6 +50,7 @@ static void __p_branch_sample_type(char *buf, size_t size, u64 value)
 		bit_name(ABORT_TX), bit_name(IN_TX), bit_name(NO_TX),
 		bit_name(COND), bit_name(CALL_STACK), bit_name(IND_JUMP),
 		bit_name(CALL), bit_name(NO_FLAGS), bit_name(NO_CYCLES),
+		bit_name(HW_INDEX),
 		{ .name = NULL, }
 	};
 #undef bit_name
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 80ca5d0ab7fe..8c1b27cd8b99 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -464,6 +464,7 @@ static PyObject *python_process_brstack(struct perf_sample *sample,
 					struct thread *thread)
 {
 	struct branch_stack *br = sample->branch_stack;
+	struct branch_entry *entries = perf_sample__branch_entries(sample);
 	PyObject *pylist;
 	u64 i;
 
@@ -484,28 +485,28 @@ static PyObject *python_process_brstack(struct perf_sample *sample,
 			Py_FatalError("couldn't create Python dictionary");
 
 		pydict_set_item_string_decref(pyelem, "from",
-		    PyLong_FromUnsignedLongLong(br->entries[i].from));
+		    PyLong_FromUnsignedLongLong(entries[i].from));
 		pydict_set_item_string_decref(pyelem, "to",
-		    PyLong_FromUnsignedLongLong(br->entries[i].to));
+		    PyLong_FromUnsignedLongLong(entries[i].to));
 		pydict_set_item_string_decref(pyelem, "mispred",
-		    PyBool_FromLong(br->entries[i].flags.mispred));
+		    PyBool_FromLong(entries[i].flags.mispred));
 		pydict_set_item_string_decref(pyelem, "predicted",
-		    PyBool_FromLong(br->entries[i].flags.predicted));
+		    PyBool_FromLong(entries[i].flags.predicted));
 		pydict_set_item_string_decref(pyelem, "in_tx",
-		    PyBool_FromLong(br->entries[i].flags.in_tx));
+		    PyBool_FromLong(entries[i].flags.in_tx));
 		pydict_set_item_string_decref(pyelem, "abort",
-		    PyBool_FromLong(br->entries[i].flags.abort));
+		    PyBool_FromLong(entries[i].flags.abort));
 		pydict_set_item_string_decref(pyelem, "cycles",
-		    PyLong_FromUnsignedLongLong(br->entries[i].flags.cycles));
+		    PyLong_FromUnsignedLongLong(entries[i].flags.cycles));
 
 		thread__find_map_fb(thread, sample->cpumode,
-				    br->entries[i].from, &al);
+				    entries[i].from, &al);
 		dsoname = get_dsoname(al.map);
 		pydict_set_item_string_decref(pyelem, "from_dsoname",
 					      _PyUnicode_FromString(dsoname));
 
 		thread__find_map_fb(thread, sample->cpumode,
-				    br->entries[i].to, &al);
+				    entries[i].to, &al);
 		dsoname = get_dsoname(al.map);
 		pydict_set_item_string_decref(pyelem, "to_dsoname",
 					      _PyUnicode_FromString(dsoname));
@@ -561,6 +562,7 @@ static PyObject *python_process_brstacksym(struct perf_sample *sample,
 					   struct thread *thread)
 {
 	struct branch_stack *br = sample->branch_stack;
+	struct branch_entry *entries = perf_sample__branch_entries(sample);
 	PyObject *pylist;
 	u64 i;
 	char bf[512];
@@ -581,22 +583,22 @@ static PyObject *python_process_brstacksym(struct perf_sample *sample,
 			Py_FatalError("couldn't create Python dictionary");
 
 		thread__find_symbol_fb(thread, sample->cpumode,
-				       br->entries[i].from, &al);
+				       entries[i].from, &al);
 		get_symoff(al.sym, &al, true, bf, sizeof(bf));
 		pydict_set_item_string_decref(pyelem, "from",
 					      _PyUnicode_FromString(bf));
 
 		thread__find_symbol_fb(thread, sample->cpumode,
-				       br->entries[i].to, &al);
+				       entries[i].to, &al);
 		get_symoff(al.sym, &al, true, bf, sizeof(bf));
 		pydict_set_item_string_decref(pyelem, "to",
 					      _PyUnicode_FromString(bf));
 
-		get_br_mspred(&br->entries[i].flags, bf, sizeof(bf));
+		get_br_mspred(&entries[i].flags, bf, sizeof(bf));
 		pydict_set_item_string_decref(pyelem, "pred",
 					      _PyUnicode_FromString(bf));
 
-		if (br->entries[i].flags.in_tx) {
+		if (entries[i].flags.in_tx) {
 			pydict_set_item_string_decref(pyelem, "in_tx",
 					      _PyUnicode_FromString("X"));
 		} else {
@@ -604,7 +606,7 @@ static PyObject *python_process_brstacksym(struct perf_sample *sample,
 					      _PyUnicode_FromString("-"));
 		}
 
-		if (br->entries[i].flags.abort) {
+		if (entries[i].flags.abort) {
 			pydict_set_item_string_decref(pyelem, "abort",
 					      _PyUnicode_FromString("A"));
 		} else {
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index d0d7d25b23e3..055b00abd56d 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1007,6 +1007,7 @@ static void callchain__lbr_callstack_printf(struct perf_sample *sample)
 {
 	struct ip_callchain *callchain = sample->callchain;
 	struct branch_stack *lbr_stack = sample->branch_stack;
+	struct branch_entry *entries = perf_sample__branch_entries(sample);
 	u64 kernel_callchain_nr = callchain->nr;
 	unsigned int i;
 
@@ -1043,10 +1044,10 @@ static void callchain__lbr_callstack_printf(struct perf_sample *sample)
 			       i, callchain->ips[i]);
 
 		printf("..... %2d: %016" PRIx64 "\n",
-		       (int)(kernel_callchain_nr), lbr_stack->entries[0].to);
+		       (int)(kernel_callchain_nr), entries[0].to);
 		for (i = 0; i < lbr_stack->nr; i++)
 			printf("..... %2d: %016" PRIx64 "\n",
-			       (int)(i + kernel_callchain_nr + 1), lbr_stack->entries[i].from);
+			       (int)(i + kernel_callchain_nr + 1), entries[i].from);
 	}
 }
 
@@ -1068,6 +1069,7 @@ static void callchain__printf(struct evsel *evsel,
 
 static void branch_stack__printf(struct perf_sample *sample, bool callstack)
 {
+	struct branch_entry *entries = perf_sample__branch_entries(sample);
 	uint64_t i;
 
 	printf("%s: nr:%" PRIu64 "\n",
@@ -1075,7 +1077,7 @@ static void branch_stack__printf(struct perf_sample *sample, bool callstack)
 		sample->branch_stack->nr);
 
 	for (i = 0; i < sample->branch_stack->nr; i++) {
-		struct branch_entry *e = &sample->branch_stack->entries[i];
+		struct branch_entry *e = &entries[i];
 
 		if (!callstack) {
 			printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 " %hu cycles %s%s%s%s %x\n",
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index bc31fccc0057..76c6052b12e2 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -16,6 +16,7 @@
 #include <linux/ctype.h>
 #include "cgroup.h"
 #include <api/fs/fs.h>
+#include "util.h"
 
 #define CNTR_NOT_SUPPORTED	"<not supported>"
 #define CNTR_NOT_COUNTED	"<not counted>"
@@ -110,7 +111,7 @@ static void aggr_printout(struct perf_stat_config *config,
 			config->csv_sep);
 			break;
 	case AGGR_NONE:
-		if (evsel->percore) {
+		if (evsel->percore && !config->percore_show_thread) {
 			fprintf(config->output, "S%d-D%d-C%*d%s",
 				cpu_map__id_to_socket(id),
 				cpu_map__id_to_die(id),
@@ -628,7 +629,7 @@ static void aggr_cb(struct perf_stat_config *config,
 static void print_counter_aggrdata(struct perf_stat_config *config,
 				   struct evsel *counter, int s,
 				   char *prefix, bool metric_only,
-				   bool *first)
+				   bool *first, int cpu)
 {
 	struct aggr_data ad;
 	FILE *output = config->output;
@@ -654,7 +655,7 @@ static void print_counter_aggrdata(struct perf_stat_config *config,
 		fprintf(output, "%s", prefix);
 
 	uval = val * counter->scale;
-	printout(config, id, nr, counter, uval, prefix,
+	printout(config, cpu != -1 ? cpu : id, nr, counter, uval, prefix,
 		 run, ena, 1.0, &rt_stat);
 	if (!metric_only)
 		fputc('\n', output);
@@ -687,7 +688,7 @@ static void print_aggr(struct perf_stat_config *config,
 		evlist__for_each_entry(evlist, counter) {
 			print_counter_aggrdata(config, counter, s,
 					       prefix, metric_only,
-					       &first);
+					       &first, -1);
 		}
 		if (metric_only)
 			fputc('\n', output);
@@ -1097,7 +1098,6 @@ static void print_footer(struct perf_stat_config *config)
 {
 	double avg = avg_stats(config->walltime_nsecs_stats) / NSEC_PER_SEC;
 	FILE *output = config->output;
-	int n;
 
 	if (!config->null_run)
 		fprintf(output, "\n");
@@ -1131,9 +1131,7 @@ static void print_footer(struct perf_stat_config *config)
 	}
 	fprintf(output, "\n\n");
 
-	if (config->print_free_counters_hint &&
-	    sysctl__read_int("kernel/nmi_watchdog", &n) >= 0 &&
-	    n > 0)
+	if (config->print_free_counters_hint && sysctl__nmi_watchdog_enabled())
 		fprintf(output,
 "Some events weren't counted. Try disabling the NMI watchdog:\n"
 "	echo 0 > /proc/sys/kernel/nmi_watchdog\n"
@@ -1146,6 +1144,26 @@ static void print_footer(struct perf_stat_config *config)
 			"the same PMU. Try reorganizing the group.\n");
 }
 
+static void print_percore_thread(struct perf_stat_config *config,
+				 struct evsel *counter, char *prefix)
+{
+	int s, s2, id;
+	bool first = true;
+
+	for (int i = 0; i < perf_evsel__nr_cpus(counter); i++) {
+		s2 = config->aggr_get_id(config, evsel__cpus(counter), i);
+		for (s = 0; s < config->aggr_map->nr; s++) {
+			id = config->aggr_map->map[s];
+			if (s2 == id)
+				break;
+		}
+
+		print_counter_aggrdata(config, counter, s,
+				       prefix, false,
+				       &first, i);
+	}
+}
+
 static void print_percore(struct perf_stat_config *config,
 			  struct evsel *counter, char *prefix)
 {
@@ -1157,13 +1175,16 @@ static void print_percore(struct perf_stat_config *config,
 	if (!(config->aggr_map || config->aggr_get_id))
 		return;
 
+	if (config->percore_show_thread)
+		return print_percore_thread(config, counter, prefix);
+
 	for (s = 0; s < config->aggr_map->nr; s++) {
 		if (prefix && metric_only)
 			fprintf(output, "%s", prefix);
 
 		print_counter_aggrdata(config, counter, s,
 				       prefix, metric_only,
-				       &first);
+				       &first, -1);
 	}
 
 	if (metric_only)
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 90d23cc3c8d4..0fd713d3674f 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -777,9 +777,7 @@ static void generic_metric(struct perf_stat_config *config,
 	}
 
 	if (!metric_events[i]) {
-		const char *p = metric_expr;
-
-		if (expr__parse(&ratio, &pctx, &p) == 0) {
+		if (expr__parse(&ratio, &pctx, metric_expr) == 0) {
 			char *unit;
 			char metric_bf[64];
 
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index fb990efa54a8..b4fdfaa7f2c0 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -109,6 +109,7 @@ struct perf_stat_config {
 	bool			 walltime_run_table;
 	bool			 all_kernel;
 	bool			 all_user;
+	bool			 percore_show_thread;
 	FILE			*output;
 	unsigned int		 interval;
 	unsigned int		 timeout;
diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index c423298fe62d..3f28af39f9c6 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -345,6 +345,7 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 			continue;
 
 		event->mmap2.ino = (u64)ino;
+		event->mmap2.ino_generation = 0;
 
 		/*
 		 * Just like the kernel, see __perf_event_mmap in kernel/perf_event.c
@@ -1183,7 +1184,8 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
 
 	if (type & PERF_SAMPLE_BRANCH_STACK) {
 		sz = sample->branch_stack->nr * sizeof(struct branch_entry);
-		sz += sizeof(u64);
+		/* nr, hw_idx */
+		sz += 2 * sizeof(u64);
 		result += sz;
 	}
 
@@ -1344,7 +1346,8 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_fo
 
 	if (type & PERF_SAMPLE_BRANCH_STACK) {
 		sz = sample->branch_stack->nr * sizeof(struct branch_entry);
-		sz += sizeof(u64);
+		/* nr, hw_idx */
+		sz += 2 * sizeof(u64);
 		memcpy(array, sample->branch_stack, sz);
 		array = (void *)array + sz;
 	}
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 969ae560dad9..d707c9624dd9 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -55,6 +55,24 @@ int sysctl__max_stack(void)
 	return sysctl_perf_event_max_stack;
 }
 
+bool sysctl__nmi_watchdog_enabled(void)
+{
+	static bool cached;
+	static bool nmi_watchdog;
+	int value;
+
+	if (cached)
+		return nmi_watchdog;
+
+	if (sysctl__read_int("kernel/nmi_watchdog", &value) < 0)
+		return false;
+
+	nmi_watchdog = (value > 0) ? true : false;
+	cached = true;
+
+	return nmi_watchdog;
+}
+
 bool test_attr__enabled;
 
 bool perf_host  = true;
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 9969b8b46f7c..f486fdd3a538 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -29,6 +29,8 @@ size_t hex_width(u64 v);
 
 int sysctl__max_stack(void);
 
+bool sysctl__nmi_watchdog_enabled(void);
+
 int fetch_kernel_version(unsigned int *puint,
 			 char *str, size_t str_sz);
 #define KVER_VERSION(x)		(((x) >> 16) & 0xff)