- Explicitly clear DEBUGCTL.LBR to prevent LBRs continuing being enabled after

handoff to the OS
 
 - Check CPUID(0x23) leaf and subleafs presence properly
 
 - Remove the PEBS-via-PT feature from being supported on hybrid systems
 
 - Fix perf record/top default commands on systems without a raw PMU registered
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEEzv7L6UO9uDPlPSfHEsHwGGHeVUoFAmextCMACgkQEsHwGGHe
 VUr7ag/+PjtbKevbeqjQ0RtkA4TF0gpbYMQdE/h5myY4YnxjmsvuiZoNZztgKU6f
 48/NJ2Fjf7cjMnTf+vYSxoTh4FmBcnhz16GyRYeF+JczR3LLf0yN/UmUz6V05kti
 4pWdbgqa7pPOIVS2NQUcC+rlHNO0kvlpat42e+TGVAGiZAUOtS4jHGE1RqfXp13G
 lDdiLKVpReuHpVVtvgTuMSvJzLRV/6zJ/+XExzgZI9b2IIwgt7YVS5pPzYCykm2h
 YMuC7v4e+0epKxuwbGApzPbCquBJvoBq+aTqU4ZMltpENkEHKlm+9gotNeMBaWA9
 xMETydcWCjEIqjDHdC1yWrGTlIHSE92KAM7pHASoCuddPmhaHIh/BuTDxfeJBrNn
 xUuukR1IVzgXZItiQ/Oz/QMNLI+EBpyBZyfb9LM3wiw0jf10+XyLE9zbMZhIc2Y2
 hwuBQ1is/dkdBcWLhaSsjHQIpKwY3iYXXjQ/AToXZV4OS8MlTNL49eSlugEisObD
 AamLQa2JAvw1wzUDe/vj15hbV2dW5bg43qVcTRJpAtg45FnPHynyJo34z7vqYNcb
 M1ljZtv+LRQeM3d4EHosrDKhhxlcOiUmUxl9E7dFlmutsusz/zW1/kbNebSj0WJt
 Ssb3lDO4JTNCI1RLb5I6Soe29FukeKmq/RYwlT49ZmRWxhpU6mE=
 =ThZf
 -----END PGP SIGNATURE-----

Merge tag 'perf_urgent_for_v6.14_rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 perf fixes from Borislav Petkov:

 - Explicitly clear DEBUGCTL.LBR to prevent LBRs continuing being
   enabled after handoff to the OS

 - Check CPUID(0x23) leaf and subleafs presence properly

 - Remove the PEBS-via-PT feature from being supported on hybrid systems

 - Fix perf record/top default commands on systems without a raw PMU
   registered

* tag 'perf_urgent_for_v6.14_rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf/x86/intel: Ensure LBRs are disabled when a CPU is starting
  perf/x86/intel: Fix ARCH_PERFMON_NUM_COUNTER_LEAF
  perf/x86/intel: Clean up PEBS-via-PT on hybrid
  perf/x86/rapl: Fix the error checking order

arch/x86/events/intel/core.c

@@ -4905,20 +4905,22 @@ static inline bool intel_pmu_broken_perf_cap(void)
 
 static void update_pmu_cap(struct x86_hybrid_pmu *pmu)
 {
-	unsigned int sub_bitmaps, eax, ebx, ecx, edx;
+	unsigned int cntr, fixed_cntr, ecx, edx;
+	union cpuid35_eax eax;
+	union cpuid35_ebx ebx;
 
-	cpuid(ARCH_PERFMON_EXT_LEAF, &sub_bitmaps, &ebx, &ecx, &edx);
+	cpuid(ARCH_PERFMON_EXT_LEAF, &eax.full, &ebx.full, &ecx, &edx);
 
-	if (ebx & ARCH_PERFMON_EXT_UMASK2)
+	if (ebx.split.umask2)
 		pmu->config_mask |= ARCH_PERFMON_EVENTSEL_UMASK2;
-	if (ebx & ARCH_PERFMON_EXT_EQ)
+	if (ebx.split.eq)
 		pmu->config_mask |= ARCH_PERFMON_EVENTSEL_EQ;
 
-	if (sub_bitmaps & ARCH_PERFMON_NUM_COUNTER_LEAF_BIT) {
+	if (eax.split.cntr_subleaf) {
 		cpuid_count(ARCH_PERFMON_EXT_LEAF, ARCH_PERFMON_NUM_COUNTER_LEAF,
-			    &eax, &ebx, &ecx, &edx);
-		pmu->cntr_mask64 = eax;
-		pmu->fixed_cntr_mask64 = ebx;
+			    &cntr, &fixed_cntr, &ecx, &edx);
+		pmu->cntr_mask64 = cntr;
+		pmu->fixed_cntr_mask64 = fixed_cntr;
 	}
 
 	if (!intel_pmu_broken_perf_cap()) {
@@ -4941,11 +4943,6 @@ static void intel_pmu_check_hybrid_pmus(struct x86_hybrid_pmu *pmu)
 	else
 		pmu->intel_ctrl &= ~(1ULL << GLOBAL_CTRL_EN_PERF_METRICS);
 
-	if (pmu->intel_cap.pebs_output_pt_available)
-		pmu->pmu.capabilities |= PERF_PMU_CAP_AUX_OUTPUT;
-	else
-		pmu->pmu.capabilities &= ~PERF_PMU_CAP_AUX_OUTPUT;
-
 	intel_pmu_check_event_constraints(pmu->event_constraints,
 					  pmu->cntr_mask64,
 					  pmu->fixed_cntr_mask64,
@@ -5023,9 +5020,6 @@ static bool init_hybrid_pmu(int cpu)
 
 	pr_info("%s PMU driver: ", pmu->name);
 
-	if (pmu->intel_cap.pebs_output_pt_available)
-		pr_cont("PEBS-via-PT ");
-
 	pr_cont("\n");
 
 	x86_pmu_show_pmu_cap(&pmu->pmu);
@@ -5048,8 +5042,11 @@ static void intel_pmu_cpu_starting(int cpu)
 
 	init_debug_store_on_cpu(cpu);
 	/*
-	 * Deal with CPUs that don't clear their LBRs on power-up.
+	 * Deal with CPUs that don't clear their LBRs on power-up, and that may
+	 * even boot with LBRs enabled.
 	 */
+	if (!static_cpu_has(X86_FEATURE_ARCH_LBR) && x86_pmu.lbr_nr)
+		msr_clear_bit(MSR_IA32_DEBUGCTLMSR, DEBUGCTLMSR_LBR_BIT);
 	intel_pmu_lbr_reset();
 
 	cpuc->lbr_sel = NULL;
@@ -6370,11 +6367,9 @@ static __always_inline int intel_pmu_init_hybrid(enum hybrid_pmu_type pmus)
 		pmu->intel_cap.capabilities = x86_pmu.intel_cap.capabilities;
 		if (pmu->pmu_type & hybrid_small_tiny) {
 			pmu->intel_cap.perf_metrics = 0;
-			pmu->intel_cap.pebs_output_pt_available = 1;
 			pmu->mid_ack = true;
 		} else if (pmu->pmu_type & hybrid_big) {
 			pmu->intel_cap.perf_metrics = 1;
-			pmu->intel_cap.pebs_output_pt_available = 0;
 			pmu->late_ack = true;
 		}
 	}

arch/x86/events/intel/ds.c

@@ -2578,7 +2578,15 @@ void __init intel_ds_init(void)
 			}
 			pr_cont("PEBS fmt4%c%s, ", pebs_type, pebs_qual);
 
-			if (!is_hybrid() && x86_pmu.intel_cap.pebs_output_pt_available) {
+			/*
+			 * The PEBS-via-PT is not supported on hybrid platforms,
+			 * because not all CPUs of a hybrid machine support it.
+			 * The global x86_pmu.intel_cap, which only contains the
+			 * common capabilities, is used to check the availability
+			 * of the feature. The per-PMU pebs_output_pt_available
+			 * in a hybrid machine should be ignored.
+			 */
+			if (x86_pmu.intel_cap.pebs_output_pt_available) {
 				pr_cont("PEBS-via-PT, ");
 				x86_get_pmu(smp_processor_id())->capabilities |= PERF_PMU_CAP_AUX_OUTPUT;
 			}

arch/x86/events/rapl.c

@@ -370,6 +370,10 @@ static int rapl_pmu_event_init(struct perf_event *event)
 	unsigned int rapl_pmu_idx;
 	struct rapl_pmus *rapl_pmus;
 
+	/* only look at RAPL events */
+	if (event->attr.type != event->pmu->type)
+		return -ENOENT;
+
 	/* unsupported modes and filters */
 	if (event->attr.sample_period) /* no sampling */
 		return -EINVAL;
@@ -387,10 +391,6 @@ static int rapl_pmu_event_init(struct perf_event *event)
 	rapl_pmus_scope = rapl_pmus->pmu.scope;
 
 	if (rapl_pmus_scope == PERF_PMU_SCOPE_PKG || rapl_pmus_scope == PERF_PMU_SCOPE_DIE) {
-		/* only look at RAPL package events */
-		if (event->attr.type != rapl_pmus_pkg->pmu.type)
-			return -ENOENT;
-
 		cfg = array_index_nospec((long)cfg, NR_RAPL_PKG_DOMAINS + 1);
 		if (!cfg || cfg >= NR_RAPL_PKG_DOMAINS + 1)
 			return -EINVAL;
@@ -398,10 +398,6 @@ static int rapl_pmu_event_init(struct perf_event *event)
 		bit = cfg - 1;
 		event->hw.event_base = rapl_model->rapl_pkg_msrs[bit].msr;
 	} else if (rapl_pmus_scope == PERF_PMU_SCOPE_CORE) {
-		/* only look at RAPL core events */
-		if (event->attr.type != rapl_pmus_core->pmu.type)
-			return -ENOENT;
-
 		cfg = array_index_nospec((long)cfg, NR_RAPL_CORE_DOMAINS + 1);
 		if (!cfg || cfg >= NR_RAPL_PKG_DOMAINS + 1)
 			return -EINVAL;

arch/x86/include/asm/msr-index.h

@@ -395,7 +395,8 @@
 #define MSR_IA32_PASID_VALID		BIT_ULL(31)
 
 /* DEBUGCTLMSR bits (others vary by model): */
-#define DEBUGCTLMSR_LBR			(1UL <<  0) /* last branch recording */
+#define DEBUGCTLMSR_LBR_BIT		0	     /* last branch recording */
+#define DEBUGCTLMSR_LBR			(1UL <<  DEBUGCTLMSR_LBR_BIT)
 #define DEBUGCTLMSR_BTF_SHIFT		1
 #define DEBUGCTLMSR_BTF			(1UL <<  1) /* single-step on branches */
 #define DEBUGCTLMSR_BUS_LOCK_DETECT	(1UL <<  2)

arch/x86/include/asm/perf_event.h

@@ -188,11 +188,33 @@ union cpuid10_edx {
  * detection/enumeration details:
  */
 #define ARCH_PERFMON_EXT_LEAF			0x00000023
-#define ARCH_PERFMON_EXT_UMASK2			0x1
-#define ARCH_PERFMON_EXT_EQ			0x2
-#define ARCH_PERFMON_NUM_COUNTER_LEAF_BIT	0x1
 #define ARCH_PERFMON_NUM_COUNTER_LEAF		0x1
 
+union cpuid35_eax {
+	struct {
+		unsigned int	leaf0:1;
+		/* Counters Sub-Leaf */
+		unsigned int    cntr_subleaf:1;
+		/* Auto Counter Reload Sub-Leaf */
+		unsigned int    acr_subleaf:1;
+		/* Events Sub-Leaf */
+		unsigned int    events_subleaf:1;
+		unsigned int	reserved:28;
+	} split;
+	unsigned int            full;
+};
+
+union cpuid35_ebx {
+	struct {
+		/* UnitMask2 Supported */
+		unsigned int    umask2:1;
+		/* EQ-bit Supported */
+		unsigned int    eq:1;
+		unsigned int	reserved:30;
+	} split;
+	unsigned int            full;
+};
+
 /*
  * Intel Architectural LBR CPUID detection/enumeration details:
  */