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

Pull perf fixes from Ingo Molnar:
 "This includes perf namespace support kernel side fixes, plus an
  accumulated set of perf tooling fixes - including UAPI header
  synchronization that should make the perf build less noisy"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (31 commits)
  tooling/headers: Synchronize updated s390 and x86 UAPI headers
  tools headers: Syncronize mman.h ABI header
  tools headers: Synchronize prctl.h ABI header
  tools headers: Synchronize KVM arch ABI headers
  tools headers: Synchronize drm/i915_drm.h
  tools headers uapi: Synchronize drm/drm.h
  tools headers: Synchronize perf_event.h header
  tools headers: Synchronize kernel ABI headers wrt SPDX tags
  tools/headers: Synchronize kernel x86 UAPI headers
  perf intel-pt: Bring instruction decoder files into line with the kernel
  perf test: Fix test 21 for s390x
  perf bench numa: Fixup discontiguous/sparse numa nodes
  perf top: Use signal interface for SIGWINCH handler
  perf top: Fix window dimensions change handling
  perf: Fix header.size for namespace events
  perf top: Ignore kptr_restrict when not sampling the kernel
  perf record: Ignore kptr_restrict when not sampling the kernel
  perf report: Ignore kptr_restrict when not sampling the kernel
  perf evlist: Add helper to check if attr.exclude_kernel is set in all evsels
  perf test shell: Fix test case probe libc's inet_pton on s390x
  ...

35 files changed, 590 insertions, 337 deletions

diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h
index 1f57bbe82b6f..6edd177bb1c7 100644
--- a/tools/arch/arm/include/uapi/asm/kvm.h
+++ b/tools/arch/arm/include/uapi/asm/kvm.h
@@ -152,6 +152,12 @@ struct kvm_arch_memory_slot {
 	(__ARM_CP15_REG(op1, 0, crm, 0) | KVM_REG_SIZE_U64)
 #define ARM_CP15_REG64(...) __ARM_CP15_REG64(__VA_ARGS__)
 
+/* PL1 Physical Timer Registers */
+#define KVM_REG_ARM_PTIMER_CTL		ARM_CP15_REG32(0, 14, 2, 1)
+#define KVM_REG_ARM_PTIMER_CNT		ARM_CP15_REG64(0, 14)
+#define KVM_REG_ARM_PTIMER_CVAL		ARM_CP15_REG64(2, 14)
+
+/* Virtual Timer Registers */
 #define KVM_REG_ARM_TIMER_CTL		ARM_CP15_REG32(0, 14, 3, 1)
 #define KVM_REG_ARM_TIMER_CNT		ARM_CP15_REG64(1, 14)
 #define KVM_REG_ARM_TIMER_CVAL		ARM_CP15_REG64(3, 14)
@@ -216,6 +222,7 @@ struct kvm_arch_memory_slot {
 #define   KVM_DEV_ARM_ITS_SAVE_TABLES		1
 #define   KVM_DEV_ARM_ITS_RESTORE_TABLES	2
 #define   KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES	3
+#define   KVM_DEV_ARM_ITS_CTRL_RESET		4
 
 /* KVM_IRQ_LINE irq field index values */
 #define KVM_ARM_IRQ_TYPE_SHIFT		24
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index 51149ec75fe4..9abbf3044654 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -196,6 +196,12 @@ struct kvm_arch_memory_slot {
 
 #define ARM64_SYS_REG(...) (__ARM64_SYS_REG(__VA_ARGS__) | KVM_REG_SIZE_U64)
 
+/* Physical Timer EL0 Registers */
+#define KVM_REG_ARM_PTIMER_CTL		ARM64_SYS_REG(3, 3, 14, 2, 1)
+#define KVM_REG_ARM_PTIMER_CVAL		ARM64_SYS_REG(3, 3, 14, 2, 2)
+#define KVM_REG_ARM_PTIMER_CNT		ARM64_SYS_REG(3, 3, 14, 0, 1)
+
+/* EL0 Virtual Timer Registers */
 #define KVM_REG_ARM_TIMER_CTL		ARM64_SYS_REG(3, 3, 14, 3, 1)
 #define KVM_REG_ARM_TIMER_CNT		ARM64_SYS_REG(3, 3, 14, 3, 2)
 #define KVM_REG_ARM_TIMER_CVAL		ARM64_SYS_REG(3, 3, 14, 0, 2)
@@ -228,6 +234,7 @@ struct kvm_arch_memory_slot {
 #define   KVM_DEV_ARM_ITS_SAVE_TABLES           1
 #define   KVM_DEV_ARM_ITS_RESTORE_TABLES        2
 #define   KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES	3
+#define   KVM_DEV_ARM_ITS_CTRL_RESET		4
 
 /* Device Control API on vcpu fd */
 #define KVM_ARM_VCPU_PMU_V3_CTRL	0
diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h
index 9ad172dcd912..38535a57fef8 100644
--- a/tools/arch/s390/include/uapi/asm/kvm.h
+++ b/tools/arch/s390/include/uapi/asm/kvm.h
@@ -6,10 +6,6 @@
  *
  * Copyright IBM Corp. 2008
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
  *    Author(s): Carsten Otte <cotte@de.ibm.com>
  *               Christian Borntraeger <borntraeger@de.ibm.com>
  */
diff --git a/tools/arch/s390/include/uapi/asm/kvm_perf.h b/tools/arch/s390/include/uapi/asm/kvm_perf.h
index c36c97ffdc6f..84606b8cc49e 100644
--- a/tools/arch/s390/include/uapi/asm/kvm_perf.h
+++ b/tools/arch/s390/include/uapi/asm/kvm_perf.h
@@ -4,10 +4,6 @@
  *
  * Copyright 2014 IBM Corp.
  * Author(s): Alexander Yarygin <yarygin@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
  */
 
 #ifndef __LINUX_KVM_PERF_S390_H
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 793690fbda36..c0b0e9e8aa66 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -13,173 +13,176 @@
 /*
  * Defines x86 CPU feature bits
  */
-#define NCAPINTS	18	/* N 32-bit words worth of info */
-#define NBUGINTS	1	/* N 32-bit bug flags */
+#define NCAPINTS			18	   /* N 32-bit words worth of info */
+#define NBUGINTS			1	   /* N 32-bit bug flags */
 
 /*
  * Note: If the comment begins with a quoted string, that string is used
  * in /proc/cpuinfo instead of the macro name.  If the string is "",
  * this feature bit is not displayed in /proc/cpuinfo at all.
+ *
+ * When adding new features here that depend on other features,
+ * please update the table in kernel/cpu/cpuid-deps.c as well.
  */
 
-/* Intel-defined CPU features, CPUID level 0x00000001 (edx), word 0 */
-#define X86_FEATURE_FPU		( 0*32+ 0) /* Onboard FPU */
-#define X86_FEATURE_VME		( 0*32+ 1) /* Virtual Mode Extensions */
-#define X86_FEATURE_DE		( 0*32+ 2) /* Debugging Extensions */
-#define X86_FEATURE_PSE		( 0*32+ 3) /* Page Size Extensions */
-#define X86_FEATURE_TSC		( 0*32+ 4) /* Time Stamp Counter */
-#define X86_FEATURE_MSR		( 0*32+ 5) /* Model-Specific Registers */
-#define X86_FEATURE_PAE		( 0*32+ 6) /* Physical Address Extensions */
-#define X86_FEATURE_MCE		( 0*32+ 7) /* Machine Check Exception */
-#define X86_FEATURE_CX8		( 0*32+ 8) /* CMPXCHG8 instruction */
-#define X86_FEATURE_APIC	( 0*32+ 9) /* Onboard APIC */
-#define X86_FEATURE_SEP		( 0*32+11) /* SYSENTER/SYSEXIT */
-#define X86_FEATURE_MTRR	( 0*32+12) /* Memory Type Range Registers */
-#define X86_FEATURE_PGE		( 0*32+13) /* Page Global Enable */
-#define X86_FEATURE_MCA		( 0*32+14) /* Machine Check Architecture */
-#define X86_FEATURE_CMOV	( 0*32+15) /* CMOV instructions */
-					  /* (plus FCMOVcc, FCOMI with FPU) */
-#define X86_FEATURE_PAT		( 0*32+16) /* Page Attribute Table */
-#define X86_FEATURE_PSE36	( 0*32+17) /* 36-bit PSEs */
-#define X86_FEATURE_PN		( 0*32+18) /* Processor serial number */
-#define X86_FEATURE_CLFLUSH	( 0*32+19) /* CLFLUSH instruction */
-#define X86_FEATURE_DS		( 0*32+21) /* "dts" Debug Store */
-#define X86_FEATURE_ACPI	( 0*32+22) /* ACPI via MSR */
-#define X86_FEATURE_MMX		( 0*32+23) /* Multimedia Extensions */
-#define X86_FEATURE_FXSR	( 0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */
-#define X86_FEATURE_XMM		( 0*32+25) /* "sse" */
-#define X86_FEATURE_XMM2	( 0*32+26) /* "sse2" */
-#define X86_FEATURE_SELFSNOOP	( 0*32+27) /* "ss" CPU self snoop */
-#define X86_FEATURE_HT		( 0*32+28) /* Hyper-Threading */
-#define X86_FEATURE_ACC		( 0*32+29) /* "tm" Automatic clock control */
-#define X86_FEATURE_IA64	( 0*32+30) /* IA-64 processor */
-#define X86_FEATURE_PBE		( 0*32+31) /* Pending Break Enable */
+/* Intel-defined CPU features, CPUID level 0x00000001 (EDX), word 0 */
+#define X86_FEATURE_FPU			( 0*32+ 0) /* Onboard FPU */
+#define X86_FEATURE_VME			( 0*32+ 1) /* Virtual Mode Extensions */
+#define X86_FEATURE_DE			( 0*32+ 2) /* Debugging Extensions */
+#define X86_FEATURE_PSE			( 0*32+ 3) /* Page Size Extensions */
+#define X86_FEATURE_TSC			( 0*32+ 4) /* Time Stamp Counter */
+#define X86_FEATURE_MSR			( 0*32+ 5) /* Model-Specific Registers */
+#define X86_FEATURE_PAE			( 0*32+ 6) /* Physical Address Extensions */
+#define X86_FEATURE_MCE			( 0*32+ 7) /* Machine Check Exception */
+#define X86_FEATURE_CX8			( 0*32+ 8) /* CMPXCHG8 instruction */
+#define X86_FEATURE_APIC		( 0*32+ 9) /* Onboard APIC */
+#define X86_FEATURE_SEP			( 0*32+11) /* SYSENTER/SYSEXIT */
+#define X86_FEATURE_MTRR		( 0*32+12) /* Memory Type Range Registers */
+#define X86_FEATURE_PGE			( 0*32+13) /* Page Global Enable */
+#define X86_FEATURE_MCA			( 0*32+14) /* Machine Check Architecture */
+#define X86_FEATURE_CMOV		( 0*32+15) /* CMOV instructions (plus FCMOVcc, FCOMI with FPU) */
+#define X86_FEATURE_PAT			( 0*32+16) /* Page Attribute Table */
+#define X86_FEATURE_PSE36		( 0*32+17) /* 36-bit PSEs */
+#define X86_FEATURE_PN			( 0*32+18) /* Processor serial number */
+#define X86_FEATURE_CLFLUSH		( 0*32+19) /* CLFLUSH instruction */
+#define X86_FEATURE_DS			( 0*32+21) /* "dts" Debug Store */
+#define X86_FEATURE_ACPI		( 0*32+22) /* ACPI via MSR */
+#define X86_FEATURE_MMX			( 0*32+23) /* Multimedia Extensions */
+#define X86_FEATURE_FXSR		( 0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */
+#define X86_FEATURE_XMM			( 0*32+25) /* "sse" */
+#define X86_FEATURE_XMM2		( 0*32+26) /* "sse2" */
+#define X86_FEATURE_SELFSNOOP		( 0*32+27) /* "ss" CPU self snoop */
+#define X86_FEATURE_HT			( 0*32+28) /* Hyper-Threading */
+#define X86_FEATURE_ACC			( 0*32+29) /* "tm" Automatic clock control */
+#define X86_FEATURE_IA64		( 0*32+30) /* IA-64 processor */
+#define X86_FEATURE_PBE			( 0*32+31) /* Pending Break Enable */
 
 /* AMD-defined CPU features, CPUID level 0x80000001, word 1 */
 /* Don't duplicate feature flags which are redundant with Intel! */
-#define X86_FEATURE_SYSCALL	( 1*32+11) /* SYSCALL/SYSRET */
-#define X86_FEATURE_MP		( 1*32+19) /* MP Capable. */
-#define X86_FEATURE_NX		( 1*32+20) /* Execute Disable */
-#define X86_FEATURE_MMXEXT	( 1*32+22) /* AMD MMX extensions */
-#define X86_FEATURE_FXSR_OPT	( 1*32+25) /* FXSAVE/FXRSTOR optimizations */
-#define X86_FEATURE_GBPAGES	( 1*32+26) /* "pdpe1gb" GB pages */
-#define X86_FEATURE_RDTSCP	( 1*32+27) /* RDTSCP */
-#define X86_FEATURE_LM		( 1*32+29) /* Long Mode (x86-64) */
-#define X86_FEATURE_3DNOWEXT	( 1*32+30) /* AMD 3DNow! extensions */
-#define X86_FEATURE_3DNOW	( 1*32+31) /* 3DNow! */
+#define X86_FEATURE_SYSCALL		( 1*32+11) /* SYSCALL/SYSRET */
+#define X86_FEATURE_MP			( 1*32+19) /* MP Capable */
+#define X86_FEATURE_NX			( 1*32+20) /* Execute Disable */
+#define X86_FEATURE_MMXEXT		( 1*32+22) /* AMD MMX extensions */
+#define X86_FEATURE_FXSR_OPT		( 1*32+25) /* FXSAVE/FXRSTOR optimizations */
+#define X86_FEATURE_GBPAGES		( 1*32+26) /* "pdpe1gb" GB pages */
+#define X86_FEATURE_RDTSCP		( 1*32+27) /* RDTSCP */
+#define X86_FEATURE_LM			( 1*32+29) /* Long Mode (x86-64, 64-bit support) */
+#define X86_FEATURE_3DNOWEXT		( 1*32+30) /* AMD 3DNow extensions */
+#define X86_FEATURE_3DNOW		( 1*32+31) /* 3DNow */
 
 /* Transmeta-defined CPU features, CPUID level 0x80860001, word 2 */
-#define X86_FEATURE_RECOVERY	( 2*32+ 0) /* CPU in recovery mode */
-#define X86_FEATURE_LONGRUN	( 2*32+ 1) /* Longrun power control */
-#define X86_FEATURE_LRTI	( 2*32+ 3) /* LongRun table interface */
+#define X86_FEATURE_RECOVERY		( 2*32+ 0) /* CPU in recovery mode */
+#define X86_FEATURE_LONGRUN		( 2*32+ 1) /* Longrun power control */
+#define X86_FEATURE_LRTI		( 2*32+ 3) /* LongRun table interface */
 
 /* Other features, Linux-defined mapping, word 3 */
 /* This range is used for feature bits which conflict or are synthesized */
-#define X86_FEATURE_CXMMX	( 3*32+ 0) /* Cyrix MMX extensions */
-#define X86_FEATURE_K6_MTRR	( 3*32+ 1) /* AMD K6 nonstandard MTRRs */
-#define X86_FEATURE_CYRIX_ARR	( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */
-#define X86_FEATURE_CENTAUR_MCR	( 3*32+ 3) /* Centaur MCRs (= MTRRs) */
-/* cpu types for specific tunings: */
-#define X86_FEATURE_K8		( 3*32+ 4) /* "" Opteron, Athlon64 */
-#define X86_FEATURE_K7		( 3*32+ 5) /* "" Athlon */
-#define X86_FEATURE_P3		( 3*32+ 6) /* "" P3 */
-#define X86_FEATURE_P4		( 3*32+ 7) /* "" P4 */
-#define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */
-#define X86_FEATURE_UP		( 3*32+ 9) /* smp kernel running on up */
-#define X86_FEATURE_ART		( 3*32+10) /* Platform has always running timer (ART) */
-#define X86_FEATURE_ARCH_PERFMON ( 3*32+11) /* Intel Architectural PerfMon */
-#define X86_FEATURE_PEBS	( 3*32+12) /* Precise-Event Based Sampling */
-#define X86_FEATURE_BTS		( 3*32+13) /* Branch Trace Store */
-#define X86_FEATURE_SYSCALL32	( 3*32+14) /* "" syscall in ia32 userspace */
-#define X86_FEATURE_SYSENTER32	( 3*32+15) /* "" sysenter in ia32 userspace */
-#define X86_FEATURE_REP_GOOD	( 3*32+16) /* rep microcode works well */
-#define X86_FEATURE_MFENCE_RDTSC ( 3*32+17) /* "" Mfence synchronizes RDTSC */
-#define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" Lfence synchronizes RDTSC */
-#define X86_FEATURE_ACC_POWER	( 3*32+19) /* AMD Accumulated Power Mechanism */
-#define X86_FEATURE_NOPL	( 3*32+20) /* The NOPL (0F 1F) instructions */
-#define X86_FEATURE_ALWAYS	( 3*32+21) /* "" Always-present feature */
-#define X86_FEATURE_XTOPOLOGY	( 3*32+22) /* cpu topology enum extensions */
-#define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* TSC is known to be reliable */
-#define X86_FEATURE_NONSTOP_TSC	( 3*32+24) /* TSC does not stop in C states */
-#define X86_FEATURE_CPUID	( 3*32+25) /* CPU has CPUID instruction itself */
-#define X86_FEATURE_EXTD_APICID	( 3*32+26) /* has extended APICID (8 bits) */
-#define X86_FEATURE_AMD_DCM     ( 3*32+27) /* multi-node processor */
-#define X86_FEATURE_APERFMPERF	( 3*32+28) /* APERFMPERF */
-#define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */
-#define X86_FEATURE_TSC_KNOWN_FREQ ( 3*32+31) /* TSC has known frequency */
+#define X86_FEATURE_CXMMX		( 3*32+ 0) /* Cyrix MMX extensions */
+#define X86_FEATURE_K6_MTRR		( 3*32+ 1) /* AMD K6 nonstandard MTRRs */
+#define X86_FEATURE_CYRIX_ARR		( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */
+#define X86_FEATURE_CENTAUR_MCR		( 3*32+ 3) /* Centaur MCRs (= MTRRs) */
+
+/* CPU types for specific tunings: */
+#define X86_FEATURE_K8			( 3*32+ 4) /* "" Opteron, Athlon64 */
+#define X86_FEATURE_K7			( 3*32+ 5) /* "" Athlon */
+#define X86_FEATURE_P3			( 3*32+ 6) /* "" P3 */
+#define X86_FEATURE_P4			( 3*32+ 7) /* "" P4 */
+#define X86_FEATURE_CONSTANT_TSC	( 3*32+ 8) /* TSC ticks at a constant rate */
+#define X86_FEATURE_UP			( 3*32+ 9) /* SMP kernel running on UP */
+#define X86_FEATURE_ART			( 3*32+10) /* Always running timer (ART) */
+#define X86_FEATURE_ARCH_PERFMON	( 3*32+11) /* Intel Architectural PerfMon */
+#define X86_FEATURE_PEBS		( 3*32+12) /* Precise-Event Based Sampling */
+#define X86_FEATURE_BTS			( 3*32+13) /* Branch Trace Store */
+#define X86_FEATURE_SYSCALL32		( 3*32+14) /* "" syscall in IA32 userspace */
+#define X86_FEATURE_SYSENTER32		( 3*32+15) /* "" sysenter in IA32 userspace */
+#define X86_FEATURE_REP_GOOD		( 3*32+16) /* REP microcode works well */
+#define X86_FEATURE_MFENCE_RDTSC	( 3*32+17) /* "" MFENCE synchronizes RDTSC */
+#define X86_FEATURE_LFENCE_RDTSC	( 3*32+18) /* "" LFENCE synchronizes RDTSC */
+#define X86_FEATURE_ACC_POWER		( 3*32+19) /* AMD Accumulated Power Mechanism */
+#define X86_FEATURE_NOPL		( 3*32+20) /* The NOPL (0F 1F) instructions */
+#define X86_FEATURE_ALWAYS		( 3*32+21) /* "" Always-present feature */
+#define X86_FEATURE_XTOPOLOGY		( 3*32+22) /* CPU topology enum extensions */
+#define X86_FEATURE_TSC_RELIABLE	( 3*32+23) /* TSC is known to be reliable */
+#define X86_FEATURE_NONSTOP_TSC		( 3*32+24) /* TSC does not stop in C states */
+#define X86_FEATURE_CPUID		( 3*32+25) /* CPU has CPUID instruction itself */
+#define X86_FEATURE_EXTD_APICID		( 3*32+26) /* Extended APICID (8 bits) */
+#define X86_FEATURE_AMD_DCM		( 3*32+27) /* AMD multi-node processor */
+#define X86_FEATURE_APERFMPERF		( 3*32+28) /* P-State hardware coordination feedback capability (APERF/MPERF MSRs) */
+#define X86_FEATURE_NONSTOP_TSC_S3	( 3*32+30) /* TSC doesn't stop in S3 state */
+#define X86_FEATURE_TSC_KNOWN_FREQ	( 3*32+31) /* TSC has known frequency */
 
-/* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
-#define X86_FEATURE_XMM3	( 4*32+ 0) /* "pni" SSE-3 */
-#define X86_FEATURE_PCLMULQDQ	( 4*32+ 1) /* PCLMULQDQ instruction */
-#define X86_FEATURE_DTES64	( 4*32+ 2) /* 64-bit Debug Store */
-#define X86_FEATURE_MWAIT	( 4*32+ 3) /* "monitor" Monitor/Mwait support */
-#define X86_FEATURE_DSCPL	( 4*32+ 4) /* "ds_cpl" CPL Qual. Debug Store */
-#define X86_FEATURE_VMX		( 4*32+ 5) /* Hardware virtualization */
-#define X86_FEATURE_SMX		( 4*32+ 6) /* Safer mode */
-#define X86_FEATURE_EST		( 4*32+ 7) /* Enhanced SpeedStep */
-#define X86_FEATURE_TM2		( 4*32+ 8) /* Thermal Monitor 2 */
-#define X86_FEATURE_SSSE3	( 4*32+ 9) /* Supplemental SSE-3 */
-#define X86_FEATURE_CID		( 4*32+10) /* Context ID */
-#define X86_FEATURE_SDBG	( 4*32+11) /* Silicon Debug */
-#define X86_FEATURE_FMA		( 4*32+12) /* Fused multiply-add */
-#define X86_FEATURE_CX16	( 4*32+13) /* CMPXCHG16B */
-#define X86_FEATURE_XTPR	( 4*32+14) /* Send Task Priority Messages */
-#define X86_FEATURE_PDCM	( 4*32+15) /* Performance Capabilities */
-#define X86_FEATURE_PCID	( 4*32+17) /* Process Context Identifiers */
-#define X86_FEATURE_DCA		( 4*32+18) /* Direct Cache Access */
-#define X86_FEATURE_XMM4_1	( 4*32+19) /* "sse4_1" SSE-4.1 */
-#define X86_FEATURE_XMM4_2	( 4*32+20) /* "sse4_2" SSE-4.2 */
-#define X86_FEATURE_X2APIC	( 4*32+21) /* x2APIC */
-#define X86_FEATURE_MOVBE	( 4*32+22) /* MOVBE instruction */
-#define X86_FEATURE_POPCNT      ( 4*32+23) /* POPCNT instruction */
-#define X86_FEATURE_TSC_DEADLINE_TIMER	( 4*32+24) /* Tsc deadline timer */
-#define X86_FEATURE_AES		( 4*32+25) /* AES instructions */
-#define X86_FEATURE_XSAVE	( 4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */
-#define X86_FEATURE_OSXSAVE	( 4*32+27) /* "" XSAVE enabled in the OS */
-#define X86_FEATURE_AVX		( 4*32+28) /* Advanced Vector Extensions */
-#define X86_FEATURE_F16C	( 4*32+29) /* 16-bit fp conversions */
-#define X86_FEATURE_RDRAND	( 4*32+30) /* The RDRAND instruction */
-#define X86_FEATURE_HYPERVISOR	( 4*32+31) /* Running on a hypervisor */
+/* Intel-defined CPU features, CPUID level 0x00000001 (ECX), word 4 */
+#define X86_FEATURE_XMM3		( 4*32+ 0) /* "pni" SSE-3 */
+#define X86_FEATURE_PCLMULQDQ		( 4*32+ 1) /* PCLMULQDQ instruction */
+#define X86_FEATURE_DTES64		( 4*32+ 2) /* 64-bit Debug Store */
+#define X86_FEATURE_MWAIT		( 4*32+ 3) /* "monitor" MONITOR/MWAIT support */
+#define X86_FEATURE_DSCPL		( 4*32+ 4) /* "ds_cpl" CPL-qualified (filtered) Debug Store */
+#define X86_FEATURE_VMX			( 4*32+ 5) /* Hardware virtualization */
+#define X86_FEATURE_SMX			( 4*32+ 6) /* Safer Mode eXtensions */
+#define X86_FEATURE_EST			( 4*32+ 7) /* Enhanced SpeedStep */
+#define X86_FEATURE_TM2			( 4*32+ 8) /* Thermal Monitor 2 */
+#define X86_FEATURE_SSSE3		( 4*32+ 9) /* Supplemental SSE-3 */
+#define X86_FEATURE_CID			( 4*32+10) /* Context ID */
+#define X86_FEATURE_SDBG		( 4*32+11) /* Silicon Debug */
+#define X86_FEATURE_FMA			( 4*32+12) /* Fused multiply-add */
+#define X86_FEATURE_CX16		( 4*32+13) /* CMPXCHG16B instruction */
+#define X86_FEATURE_XTPR		( 4*32+14) /* Send Task Priority Messages */
+#define X86_FEATURE_PDCM		( 4*32+15) /* Perf/Debug Capabilities MSR */
+#define X86_FEATURE_PCID		( 4*32+17) /* Process Context Identifiers */
+#define X86_FEATURE_DCA			( 4*32+18) /* Direct Cache Access */
+#define X86_FEATURE_XMM4_1		( 4*32+19) /* "sse4_1" SSE-4.1 */
+#define X86_FEATURE_XMM4_2		( 4*32+20) /* "sse4_2" SSE-4.2 */
+#define X86_FEATURE_X2APIC		( 4*32+21) /* X2APIC */
+#define X86_FEATURE_MOVBE		( 4*32+22) /* MOVBE instruction */
+#define X86_FEATURE_POPCNT		( 4*32+23) /* POPCNT instruction */
+#define X86_FEATURE_TSC_DEADLINE_TIMER	( 4*32+24) /* TSC deadline timer */
+#define X86_FEATURE_AES			( 4*32+25) /* AES instructions */
+#define X86_FEATURE_XSAVE		( 4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV instructions */
+#define X86_FEATURE_OSXSAVE		( 4*32+27) /* "" XSAVE instruction enabled in the OS */
+#define X86_FEATURE_AVX			( 4*32+28) /* Advanced Vector Extensions */
+#define X86_FEATURE_F16C		( 4*32+29) /* 16-bit FP conversions */
+#define X86_FEATURE_RDRAND		( 4*32+30) /* RDRAND instruction */
+#define X86_FEATURE_HYPERVISOR		( 4*32+31) /* Running on a hypervisor */
 
 /* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */
-#define X86_FEATURE_XSTORE	( 5*32+ 2) /* "rng" RNG present (xstore) */
-#define X86_FEATURE_XSTORE_EN	( 5*32+ 3) /* "rng_en" RNG enabled */
-#define X86_FEATURE_XCRYPT	( 5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */
-#define X86_FEATURE_XCRYPT_EN	( 5*32+ 7) /* "ace_en" on-CPU crypto enabled */
-#define X86_FEATURE_ACE2	( 5*32+ 8) /* Advanced Cryptography Engine v2 */
-#define X86_FEATURE_ACE2_EN	( 5*32+ 9) /* ACE v2 enabled */
-#define X86_FEATURE_PHE		( 5*32+10) /* PadLock Hash Engine */
-#define X86_FEATURE_PHE_EN	( 5*32+11) /* PHE enabled */
-#define X86_FEATURE_PMM		( 5*32+12) /* PadLock Montgomery Multiplier */
-#define X86_FEATURE_PMM_EN	( 5*32+13) /* PMM enabled */
+#define X86_FEATURE_XSTORE		( 5*32+ 2) /* "rng" RNG present (xstore) */
+#define X86_FEATURE_XSTORE_EN		( 5*32+ 3) /* "rng_en" RNG enabled */
+#define X86_FEATURE_XCRYPT		( 5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */
+#define X86_FEATURE_XCRYPT_EN		( 5*32+ 7) /* "ace_en" on-CPU crypto enabled */
+#define X86_FEATURE_ACE2		( 5*32+ 8) /* Advanced Cryptography Engine v2 */
+#define X86_FEATURE_ACE2_EN		( 5*32+ 9) /* ACE v2 enabled */
+#define X86_FEATURE_PHE			( 5*32+10) /* PadLock Hash Engine */
+#define X86_FEATURE_PHE_EN		( 5*32+11) /* PHE enabled */
+#define X86_FEATURE_PMM			( 5*32+12) /* PadLock Montgomery Multiplier */
+#define X86_FEATURE_PMM_EN		( 5*32+13) /* PMM enabled */
 
-/* More extended AMD flags: CPUID level 0x80000001, ecx, word 6 */
-#define X86_FEATURE_LAHF_LM	( 6*32+ 0) /* LAHF/SAHF in long mode */
-#define X86_FEATURE_CMP_LEGACY	( 6*32+ 1) /* If yes HyperThreading not valid */
-#define X86_FEATURE_SVM		( 6*32+ 2) /* Secure virtual machine */
-#define X86_FEATURE_EXTAPIC	( 6*32+ 3) /* Extended APIC space */
-#define X86_FEATURE_CR8_LEGACY	( 6*32+ 4) /* CR8 in 32-bit mode */
-#define X86_FEATURE_ABM		( 6*32+ 5) /* Advanced bit manipulation */
-#define X86_FEATURE_SSE4A	( 6*32+ 6) /* SSE-4A */
-#define X86_FEATURE_MISALIGNSSE ( 6*32+ 7) /* Misaligned SSE mode */
-#define X86_FEATURE_3DNOWPREFETCH ( 6*32+ 8) /* 3DNow prefetch instructions */
-#define X86_FEATURE_OSVW	( 6*32+ 9) /* OS Visible Workaround */
-#define X86_FEATURE_IBS		( 6*32+10) /* Instruction Based Sampling */
-#define X86_FEATURE_XOP		( 6*32+11) /* extended AVX instructions */
-#define X86_FEATURE_SKINIT	( 6*32+12) /* SKINIT/STGI instructions */
-#define X86_FEATURE_WDT		( 6*32+13) /* Watchdog timer */
-#define X86_FEATURE_LWP		( 6*32+15) /* Light Weight Profiling */
-#define X86_FEATURE_FMA4	( 6*32+16) /* 4 operands MAC instructions */
-#define X86_FEATURE_TCE		( 6*32+17) /* translation cache extension */
-#define X86_FEATURE_NODEID_MSR	( 6*32+19) /* NodeId MSR */
-#define X86_FEATURE_TBM		( 6*32+21) /* trailing bit manipulations */
-#define X86_FEATURE_TOPOEXT	( 6*32+22) /* topology extensions CPUID leafs */
-#define X86_FEATURE_PERFCTR_CORE ( 6*32+23) /* core performance counter extensions */
-#define X86_FEATURE_PERFCTR_NB  ( 6*32+24) /* NB performance counter extensions */
-#define X86_FEATURE_BPEXT	(6*32+26) /* data breakpoint extension */
-#define X86_FEATURE_PTSC	( 6*32+27) /* performance time-stamp counter */
-#define X86_FEATURE_PERFCTR_LLC	( 6*32+28) /* Last Level Cache performance counter extensions */
-#define X86_FEATURE_MWAITX	( 6*32+29) /* MWAIT extension (MONITORX/MWAITX) */
+/* More extended AMD flags: CPUID level 0x80000001, ECX, word 6 */
+#define X86_FEATURE_LAHF_LM		( 6*32+ 0) /* LAHF/SAHF in long mode */
+#define X86_FEATURE_CMP_LEGACY		( 6*32+ 1) /* If yes HyperThreading not valid */
+#define X86_FEATURE_SVM			( 6*32+ 2) /* Secure Virtual Machine */
+#define X86_FEATURE_EXTAPIC		( 6*32+ 3) /* Extended APIC space */
+#define X86_FEATURE_CR8_LEGACY		( 6*32+ 4) /* CR8 in 32-bit mode */
+#define X86_FEATURE_ABM			( 6*32+ 5) /* Advanced bit manipulation */
+#define X86_FEATURE_SSE4A		( 6*32+ 6) /* SSE-4A */
+#define X86_FEATURE_MISALIGNSSE		( 6*32+ 7) /* Misaligned SSE mode */
+#define X86_FEATURE_3DNOWPREFETCH	( 6*32+ 8) /* 3DNow prefetch instructions */
+#define X86_FEATURE_OSVW		( 6*32+ 9) /* OS Visible Workaround */
+#define X86_FEATURE_IBS			( 6*32+10) /* Instruction Based Sampling */
+#define X86_FEATURE_XOP			( 6*32+11) /* extended AVX instructions */
+#define X86_FEATURE_SKINIT		( 6*32+12) /* SKINIT/STGI instructions */
+#define X86_FEATURE_WDT			( 6*32+13) /* Watchdog timer */
+#define X86_FEATURE_LWP			( 6*32+15) /* Light Weight Profiling */
+#define X86_FEATURE_FMA4		( 6*32+16) /* 4 operands MAC instructions */
+#define X86_FEATURE_TCE			( 6*32+17) /* Translation Cache Extension */
+#define X86_FEATURE_NODEID_MSR		( 6*32+19) /* NodeId MSR */
+#define X86_FEATURE_TBM			( 6*32+21) /* Trailing Bit Manipulations */
+#define X86_FEATURE_TOPOEXT		( 6*32+22) /* Topology extensions CPUID leafs */
+#define X86_FEATURE_PERFCTR_CORE	( 6*32+23) /* Core performance counter extensions */
+#define X86_FEATURE_PERFCTR_NB		( 6*32+24) /* NB performance counter extensions */
+#define X86_FEATURE_BPEXT		( 6*32+26) /* Data breakpoint extension */
+#define X86_FEATURE_PTSC		( 6*32+27) /* Performance time-stamp counter */
+#define X86_FEATURE_PERFCTR_LLC		( 6*32+28) /* Last Level Cache performance counter extensions */
+#define X86_FEATURE_MWAITX		( 6*32+29) /* MWAIT extension (MONITORX/MWAITX instructions) */
 
 /*
  * Auxiliary flags: Linux defined - For features scattered in various
@@ -187,146 +190,154 @@
  *
  * Reuse free bits when adding new feature flags!
  */
-#define X86_FEATURE_RING3MWAIT	( 7*32+ 0) /* Ring 3 MONITOR/MWAIT */
-#define X86_FEATURE_CPUID_FAULT ( 7*32+ 1) /* Intel CPUID faulting */
-#define X86_FEATURE_CPB		( 7*32+ 2) /* AMD Core Performance Boost */
-#define X86_FEATURE_EPB		( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
-#define X86_FEATURE_CAT_L3	( 7*32+ 4) /* Cache Allocation Technology L3 */
-#define X86_FEATURE_CAT_L2	( 7*32+ 5) /* Cache Allocation Technology L2 */
-#define X86_FEATURE_CDP_L3	( 7*32+ 6) /* Code and Data Prioritization L3 */
+#define X86_FEATURE_RING3MWAIT		( 7*32+ 0) /* Ring 3 MONITOR/MWAIT instructions */
+#define X86_FEATURE_CPUID_FAULT		( 7*32+ 1) /* Intel CPUID faulting */
+#define X86_FEATURE_CPB			( 7*32+ 2) /* AMD Core Performance Boost */
+#define X86_FEATURE_EPB			( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
+#define X86_FEATURE_CAT_L3		( 7*32+ 4) /* Cache Allocation Technology L3 */
+#define X86_FEATURE_CAT_L2		( 7*32+ 5) /* Cache Allocation Technology L2 */
+#define X86_FEATURE_CDP_L3		( 7*32+ 6) /* Code and Data Prioritization L3 */
 
-#define X86_FEATURE_HW_PSTATE	( 7*32+ 8) /* AMD HW-PState */
-#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
-#define X86_FEATURE_SME		( 7*32+10) /* AMD Secure Memory Encryption */
+#define X86_FEATURE_HW_PSTATE		( 7*32+ 8) /* AMD HW-PState */
+#define X86_FEATURE_PROC_FEEDBACK	( 7*32+ 9) /* AMD ProcFeedbackInterface */
+#define X86_FEATURE_SME			( 7*32+10) /* AMD Secure Memory Encryption */
 
-#define X86_FEATURE_INTEL_PPIN	( 7*32+14) /* Intel Processor Inventory Number */
-#define X86_FEATURE_INTEL_PT	( 7*32+15) /* Intel Processor Trace */
-#define X86_FEATURE_AVX512_4VNNIW (7*32+16) /* AVX-512 Neural Network Instructions */
-#define X86_FEATURE_AVX512_4FMAPS (7*32+17) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_INTEL_PPIN		( 7*32+14) /* Intel Processor Inventory Number */
+#define X86_FEATURE_INTEL_PT		( 7*32+15) /* Intel Processor Trace */
+#define X86_FEATURE_AVX512_4VNNIW	( 7*32+16) /* AVX-512 Neural Network Instructions */
+#define X86_FEATURE_AVX512_4FMAPS	( 7*32+17) /* AVX-512 Multiply Accumulation Single precision */
 
-#define X86_FEATURE_MBA         ( 7*32+18) /* Memory Bandwidth Allocation */
+#define X86_FEATURE_MBA			( 7*32+18) /* Memory Bandwidth Allocation */
 
 /* Virtualization flags: Linux defined, word 8 */
-#define X86_FEATURE_TPR_SHADOW  ( 8*32+ 0) /* Intel TPR Shadow */
-#define X86_FEATURE_VNMI        ( 8*32+ 1) /* Intel Virtual NMI */
-#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 2) /* Intel FlexPriority */
-#define X86_FEATURE_EPT         ( 8*32+ 3) /* Intel Extended Page Table */
-#define X86_FEATURE_VPID        ( 8*32+ 4) /* Intel Virtual Processor ID */
+#define X86_FEATURE_TPR_SHADOW		( 8*32+ 0) /* Intel TPR Shadow */
+#define X86_FEATURE_VNMI		( 8*32+ 1) /* Intel Virtual NMI */
+#define X86_FEATURE_FLEXPRIORITY	( 8*32+ 2) /* Intel FlexPriority */
+#define X86_FEATURE_EPT			( 8*32+ 3) /* Intel Extended Page Table */
+#define X86_FEATURE_VPID		( 8*32+ 4) /* Intel Virtual Processor ID */
 
-#define X86_FEATURE_VMMCALL     ( 8*32+15) /* Prefer vmmcall to vmcall */
-#define X86_FEATURE_XENPV       ( 8*32+16) /* "" Xen paravirtual guest */
+#define X86_FEATURE_VMMCALL		( 8*32+15) /* Prefer VMMCALL to VMCALL */
+#define X86_FEATURE_XENPV		( 8*32+16) /* "" Xen paravirtual guest */
 
 
-/* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */
-#define X86_FEATURE_FSGSBASE	( 9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/
-#define X86_FEATURE_TSC_ADJUST	( 9*32+ 1) /* TSC adjustment MSR 0x3b */
-#define X86_FEATURE_BMI1	( 9*32+ 3) /* 1st group bit manipulation extensions */
-#define X86_FEATURE_HLE		( 9*32+ 4) /* Hardware Lock Elision */
-#define X86_FEATURE_AVX2	( 9*32+ 5) /* AVX2 instructions */
-#define X86_FEATURE_SMEP	( 9*32+ 7) /* Supervisor Mode Execution Protection */
-#define X86_FEATURE_BMI2	( 9*32+ 8) /* 2nd group bit manipulation extensions */
-#define X86_FEATURE_ERMS	( 9*32+ 9) /* Enhanced REP MOVSB/STOSB */
-#define X86_FEATURE_INVPCID	( 9*32+10) /* Invalidate Processor Context ID */
-#define X86_FEATURE_RTM		( 9*32+11) /* Restricted Transactional Memory */
-#define X86_FEATURE_CQM		( 9*32+12) /* Cache QoS Monitoring */
-#define X86_FEATURE_MPX		( 9*32+14) /* Memory Protection Extension */
-#define X86_FEATURE_RDT_A	( 9*32+15) /* Resource Director Technology Allocation */
-#define X86_FEATURE_AVX512F	( 9*32+16) /* AVX-512 Foundation */
-#define X86_FEATURE_AVX512DQ	( 9*32+17) /* AVX-512 DQ (Double/Quad granular) Instructions */
-#define X86_FEATURE_RDSEED	( 9*32+18) /* The RDSEED instruction */
-#define X86_FEATURE_ADX		( 9*32+19) /* The ADCX and ADOX instructions */
-#define X86_FEATURE_SMAP	( 9*32+20) /* Supervisor Mode Access Prevention */
-#define X86_FEATURE_AVX512IFMA  ( 9*32+21) /* AVX-512 Integer Fused Multiply-Add instructions */
-#define X86_FEATURE_CLFLUSHOPT	( 9*32+23) /* CLFLUSHOPT instruction */
-#define X86_FEATURE_CLWB	( 9*32+