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
  ...

6 files changed, 151 insertions, 17 deletions

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 |	\