Merge tag 'perf_urgent_for_v6.9_rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 perf fixes from Borislav Petkov:

 - Define the correct set of default hw events on AMD Zen4

 - Use the correct stalled cycles PMCs on AMD Zen2 and newer

 - Fix detection of the LBR freeze feature on AMD

* tag 'perf_urgent_for_v6.9_rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf/x86/amd/core: Define a proper ref-cycles event for Zen 4 and later
  perf/x86/amd/core: Update and fix stalled-cycles-* events for Zen 2 and later
  perf/x86/amd/lbr: Use freeze based on availability
  x86/cpufeatures: Add new word for scattered features

Author: torvalds

arch/x86/events/amd/core.c

@@ -250,7 +250,7 @@ static const u64 amd_perfmon_event_map[PERF_COUNT_HW_MAX] =
 /*
  * AMD Performance Monitor Family 17h and later:
  */
-static const u64 amd_f17h_perfmon_event_map[PERF_COUNT_HW_MAX] =
+static const u64 amd_zen1_perfmon_event_map[PERF_COUNT_HW_MAX] =
 {
 	[PERF_COUNT_HW_CPU_CYCLES]		= 0x0076,
 	[PERF_COUNT_HW_INSTRUCTIONS]		= 0x00c0,
@@ -262,10 +262,39 @@ static const u64 amd_f17h_perfmon_event_map[PERF_COUNT_HW_MAX] =
 	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= 0x0187,
 };
 
+static const u64 amd_zen2_perfmon_event_map[PERF_COUNT_HW_MAX] =
+{
+	[PERF_COUNT_HW_CPU_CYCLES]		= 0x0076,
+	[PERF_COUNT_HW_INSTRUCTIONS]		= 0x00c0,
+	[PERF_COUNT_HW_CACHE_REFERENCES]	= 0xff60,
+	[PERF_COUNT_HW_CACHE_MISSES]		= 0x0964,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x00c2,
+	[PERF_COUNT_HW_BRANCH_MISSES]		= 0x00c3,
+	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= 0x00a9,
+};
+
+static const u64 amd_zen4_perfmon_event_map[PERF_COUNT_HW_MAX] =
+{
+	[PERF_COUNT_HW_CPU_CYCLES]		= 0x0076,
+	[PERF_COUNT_HW_INSTRUCTIONS]		= 0x00c0,
+	[PERF_COUNT_HW_CACHE_REFERENCES]	= 0xff60,
+	[PERF_COUNT_HW_CACHE_MISSES]		= 0x0964,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x00c2,
+	[PERF_COUNT_HW_BRANCH_MISSES]		= 0x00c3,
+	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= 0x00a9,
+	[PERF_COUNT_HW_REF_CPU_CYCLES]		= 0x100000120,
+};
+
 static u64 amd_pmu_event_map(int hw_event)
 {
-	if (boot_cpu_data.x86 >= 0x17)
-		return amd_f17h_perfmon_event_map[hw_event];
+	if (cpu_feature_enabled(X86_FEATURE_ZEN4) || boot_cpu_data.x86 >= 0x1a)
+		return amd_zen4_perfmon_event_map[hw_event];
+
+	if (cpu_feature_enabled(X86_FEATURE_ZEN2) || boot_cpu_data.x86 >= 0x19)
+		return amd_zen2_perfmon_event_map[hw_event];
+
+	if (cpu_feature_enabled(X86_FEATURE_ZEN1))
+		return amd_zen1_perfmon_event_map[hw_event];
 
 	return amd_perfmon_event_map[hw_event];
 }
@@ -904,8 +933,8 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs)
 	if (!status)
 		goto done;
 
-	/* Read branch records before unfreezing */
-	if (status & GLOBAL_STATUS_LBRS_FROZEN) {
+	/* Read branch records */
+	if (x86_pmu.lbr_nr) {
 		amd_pmu_lbr_read();
 		status &= ~GLOBAL_STATUS_LBRS_FROZEN;
 	}

arch/x86/events/amd/lbr.c

@@ -402,10 +402,12 @@ void amd_pmu_lbr_enable_all(void)
 		wrmsrl(MSR_AMD64_LBR_SELECT, lbr_select);
 	}
 
-	rdmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl);
-	rdmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg);
+	if (cpu_feature_enabled(X86_FEATURE_AMD_LBR_PMC_FREEZE)) {
+		rdmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl);
+		wrmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
+	}
 
-	wrmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
+	rdmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg);
 	wrmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg | DBG_EXTN_CFG_LBRV2EN);
 }
 
@@ -418,10 +420,12 @@ void amd_pmu_lbr_disable_all(void)
 		return;
 
 	rdmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg);
-	rdmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl);
-
 	wrmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg & ~DBG_EXTN_CFG_LBRV2EN);
-	wrmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl & ~DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
+
+	if (cpu_feature_enabled(X86_FEATURE_AMD_LBR_PMC_FREEZE)) {
+		rdmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl);
+		wrmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl & ~DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
+	}
 }
 
 __init int amd_pmu_lbr_init(void)

arch/x86/include/asm/cpufeature.h

@@ -91,8 +91,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 18, feature_bit) ||	\
 	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 19, feature_bit) ||	\
 	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 20, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 21, feature_bit) ||	\
 	   REQUIRED_MASK_CHECK					  ||	\
-	   BUILD_BUG_ON_ZERO(NCAPINTS != 21))
+	   BUILD_BUG_ON_ZERO(NCAPINTS != 22))
 
 #define DISABLED_MASK_BIT_SET(feature_bit)				\
 	 ( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  0, feature_bit) ||	\
@@ -116,8 +117,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 18, feature_bit) ||	\
 	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 19, feature_bit) ||	\
 	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 20, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 21, feature_bit) ||	\
 	   DISABLED_MASK_CHECK					  ||	\
-	   BUILD_BUG_ON_ZERO(NCAPINTS != 21))
+	   BUILD_BUG_ON_ZERO(NCAPINTS != 22))
 
 #define cpu_has(c, bit)							\
 	(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 :	\

arch/x86/include/asm/cpufeatures.h

@@ -13,7 +13,7 @@
 /*
  * Defines x86 CPU feature bits
  */
-#define NCAPINTS			21	   /* N 32-bit words worth of info */
+#define NCAPINTS			22	   /* N 32-bit words worth of info */
 #define NBUGINTS			2	   /* N 32-bit bug flags */
 
 /*
@@ -459,6 +459,14 @@
 #define X86_FEATURE_IBPB_BRTYPE		(20*32+28) /* "" MSR_PRED_CMD[IBPB] flushes all branch type predictions */
 #define X86_FEATURE_SRSO_NO		(20*32+29) /* "" CPU is not affected by SRSO */
 
+/*
+ * Extended auxiliary flags: Linux defined - for features scattered in various
+ * CPUID levels like 0x80000022, etc.
+ *
+ * Reuse free bits when adding new feature flags!
+ */
+#define X86_FEATURE_AMD_LBR_PMC_FREEZE	(21*32+ 0) /* AMD LBR and PMC Freeze */
+
 /*
  * BUG word(s)
  */

arch/x86/include/asm/disabled-features.h

@@ -155,6 +155,7 @@
 #define DISABLED_MASK18	(DISABLE_IBT)
 #define DISABLED_MASK19	(DISABLE_SEV_SNP)
 #define DISABLED_MASK20	0
-#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21)
+#define DISABLED_MASK21	0
+#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22)
 
 #endif /* _ASM_X86_DISABLED_FEATURES_H */

arch/x86/include/asm/required-features.h

@@ -99,6 +99,7 @@
 #define REQUIRED_MASK18	0
 #define REQUIRED_MASK19	0
 #define REQUIRED_MASK20	0
-#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21)
+#define REQUIRED_MASK21	0
+#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22)
 
 #endif /* _ASM_X86_REQUIRED_FEATURES_H */

arch/x86/kernel/cpu/scattered.c

@@ -49,6 +49,7 @@ static const struct cpuid_bit cpuid_bits[] = {
 	{ X86_FEATURE_BMEC,		CPUID_EBX,  3, 0x80000020, 0 },
 	{ X86_FEATURE_PERFMON_V2,	CPUID_EAX,  0, 0x80000022, 0 },
 	{ X86_FEATURE_AMD_LBR_V2,	CPUID_EAX,  1, 0x80000022, 0 },
+	{ X86_FEATURE_AMD_LBR_PMC_FREEZE,	CPUID_EAX,  2, 0x80000022, 0 },
 	{ 0, 0, 0, 0, 0 }
 };