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

…nux/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
  ...

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;
 }
 

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

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);

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);

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);

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);

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);

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),
 	{},
 };
 

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.

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)
 {
@@ -1954,21 +1962,19 @@ 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();
 }
 
 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);
 	}
 
 	/*

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);

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];