Merge branch 'perf/urgent' into perf/core, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

14 files changed, 443 insertions, 275 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/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+24) /* CLWB instruction */
-#define X86_FEATURE_AVX512PF	( 9*32+26) /* AVX-512 Prefetch */
-#define X86_FEATURE_AVX512ER	( 9*32+27) /* AVX-512 Exponential and Reciprocal */
-#define X86_FEATURE_AVX512CD	( 9*32+28) /* AVX-512 Conflict Detection */
-#define X86_FEATURE_SHA_NI	( 9*32+29) /* SHA1/SHA256 Instruction Extensions */
-#define X86_FEATURE_AVX512BW	( 9*32+30) /* AVX-512 BW (Byte/Word granular) Instructions */
-#define X86_FEATURE_AVX512VL	( 9*32+31) /* AVX-512 VL (128/256 Vector Length) Extensions */
+/* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */
+#define X86_FEATURE_FSGSBASE		( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE 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 instructions */
+#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) /* RDSEED instruction */
+#define X86_FEATURE_ADX			( 9*32+19) /* 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+24) /* CLWB instruction */
+#define X86_FEATURE_AVX512PF		( 9*32+26) /* AVX-512 Prefetch */
+#define X86_FEATURE_AVX512ER		( 9*32+27) /* AVX-512 Exponential and Reciprocal */
+#define X86_FEATURE_AVX512CD		( 9*32+28) /* AVX-512 Conflict Detection */
+#define X86_FEATURE_SHA_NI		( 9*32+29) /* SHA1/SHA256 Instruction Extensions */
+#define X86_FEATURE_AVX512BW		( 9*32+30) /* AVX-512 BW (Byte/Word granular) Instructions */
+#define X86_FEATURE_AVX512VL		( 9*32+31) /* AVX-512 VL (128/256 Vector Length) Extensions */
 
-/* Extended state features, CPUID level 0x0000000d:1 (eax), word 10 */
-#define X86_FEATURE_XSAVEOPT	(10*32+ 0) /* XSAVEOPT */
-#define X86_FEATURE_XSAVEC	(10*32+ 1) /* XSAVEC */
-#define X86_FEATURE_XGETBV1	(10*32+ 2) /* XGETBV with ECX = 1 */
-#define X86_FEATURE_XSAVES	(10*32+ 3) /* XSAVES/XRSTORS */
+/* Extended state features, CPUID level 0x0000000d:1 (EAX), word 10 */
+#define X86_FEATURE_XSAVEOPT		(10*32+ 0) /* XSAVEOPT instruction */
+#define X86_FEATURE_XSAVEC		(10*32+ 1) /* XSAVEC instruction */
+#define X86_FEATURE_XGETBV1		(10*32+ 2) /* XGETBV with ECX = 1 instruction */
+#define X86_FEATURE_XSAVES		(10*32+ 3) /* XSAVES/XRSTORS instructions */
 
-/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:0 (edx), word 11 */
-#define X86_FEATURE_CQM_LLC	(11*32+ 1) /* LLC QoS if 1 */
+/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:0 (EDX), word 11 */
+#define X86_FEATURE_CQM_LLC		(11*32+ 1) /* LLC QoS if 1 */
 
-/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (edx), word 12 */
-#define X86_FEATURE_CQM_OCCUP_LLC (12*32+ 0) /* LLC occupancy monitoring if 1 */
-#define X86_FEATURE_CQM_MBM_TOTAL (12*32+ 1) /* LLC Total MBM monitoring */
-#define X86_FEATURE_CQM_MBM_LOCAL (12*32+ 2) /* LLC Local MBM monitoring */
+/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (EDX), word 12 */
+#define X86_FEATURE_CQM_OCCUP_LLC	(12*32+ 0) /* LLC occupancy monitoring */
+#define X86_FEATURE_CQM_MBM_TOTAL	(12*32+ 1) /* LLC Total MBM monitoring */
+#define X86_FEATURE_CQM_MBM_LOCAL	(12*32+ 2) /* LLC Local MBM monitoring */
 
-/* AMD-defined CPU features, CPUID level 0x80000008 (ebx), word 13 */
-#define X86_FEATURE_CLZERO	(13*32+0) /* CLZERO instruction */
-#define X86_FEATURE_IRPERF	(13*32+1) /* Instructions Retired Count */
+/* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */
+#define X86_FEATURE_CLZERO		(13*32+ 0) /* CLZERO instruction */
+#define X86_FEATURE_IRPERF		(13*32+ 1) /* Instructions Retired Count */
 
-/* Thermal and Power Management Leaf, CPUID level 0x00000006 (eax), word 14 */
-#define X86_FEATURE_DTHERM	(14*32+ 0) /* Digital Thermal Sensor */
-#define X86_FEATURE_IDA		(14*32+ 1) /* Intel Dynamic Acceleration */
-#define X86_FEATURE_ARAT	(14*32+ 2) /* Always Running APIC Timer */
-#define X86_FEATURE_PLN		(14*32+ 4) /* Intel Power Limit Notification */
-#define X86_FEATURE_PTS		(14*32+ 6) /* Intel Package Thermal Status */
-#define X86_FEATURE_HWP		(14*32+ 7) /* Intel Hardware P-states */
-#define X86_FEATURE_HWP_NOTIFY	(14*32+ 8) /* HWP Notification */
-#define X86_FEATURE_HWP_ACT_WINDOW (14*32+ 9) /* HWP Activity Window */
-#define X86_FEATURE_HWP_EPP	(14*32+10) /* HWP Energy Perf. Preference */
-#define X86_FEATURE_HWP_PKG_REQ (14*32+11) /* HWP Package Level Request */
+/* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */
+#define X86_FEATURE_DTHERM		(14*32+ 0) /* Digital Thermal Sensor */
+#define X86_FEATURE_IDA			(14*32+ 1) /* Intel Dynamic Acceleration */
+#define X86_FEATURE_ARAT		(14*32+ 2) /* Always Running APIC Timer */
+#define X86_FEATURE_PLN			(14*32+ 4) /* Intel Power Limit Notification */
+#define X86_FEATURE_PTS			(14*32+ 6) /* Intel Package Thermal Status */
+#define X86_FEATURE_HWP			(14*32+ 7) /* Intel Hardware P-states */
+#define X86_FEATURE_HWP_NOTIFY		(14*32+ 8) /* HWP Notification */
+#define X86_FEATURE_HWP_ACT_WINDOW	(14*32+ 9) /* HWP Activity Window */
+#define X86_FEATURE_HWP_EPP		(14*32+10) /* HWP Energy Perf. Preference */
+#define X86_FEATURE_HWP_PKG_REQ		(14*32+11) /* HWP Package Level Request */
 
-/* AMD SVM Feature Identification, CPUID level 0x8000000a (edx), word 15 */
-#define X86_FEATURE_NPT		(15*32+ 0) /* Nested Page Table support */
-#define X86_FEATURE_LBRV	(15*32+ 1) /* LBR Virtualization support */
-#define X86_FEATURE_SVML	(15*32+ 2) /* "svm_lock" SVM locking MSR */
-#define X86_FEATURE_NRIPS	(15*32+ 3) /* "nrip_save" SVM next_rip save */
-#define X86_FEATURE_TSCRATEMSR  (15*32+ 4) /* "tsc_scale" TSC scaling support */
-#define X86_FEATURE_VMCBCLEAN   (15*32+ 5) /* "vmcb_clean" VMCB clean bits support */
-#define X86_FEATURE_FLUSHBYASID (15*32+ 6) /* flush-by-ASID support */
-#define X86_FEATURE_DECODEASSISTS (15*32+ 7) /* Decode Assists support */
-#define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */
-#define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */
-#define X86_FEATURE_AVIC	(15*32+13) /* Virtual Interrupt Controller */
-#define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */
-#define X86_FEATURE_VGIF	(15*32+16) /* Virtual GIF */
+/* AMD SVM Feature Identification, CPUID level 0x8000000a (EDX), word 15 */
+#define X86_FEATURE_NPT			(15*32+ 0) /* Nested Page Table support */
+#define X86_FEATURE_LBRV		(15*32+ 1) /* LBR Virtualization support */
+#define X86_FEATURE_SVML		(15*32+ 2) /* "svm_lock" SVM locking MSR */
+#define X86_FEATURE_NRIPS		(15*32+ 3) /* "nrip_save" SVM next_rip save */
+#define X86_FEATURE_TSCRATEMSR		(15*32+ 4) /* "tsc_scale" TSC scaling support */
+#define X86_FEATURE_VMCBCLEAN		(15*32+ 5) /* "vmcb_clean" VMCB clean bits support */
+#define X86_FEATURE_FLUSHBYASID		(15*32+ 6) /* flush-by-ASID support */
+#define X86_FEATURE_DECODEASSISTS	(15*32+ 7) /* Decode Assists support */
+#define X86_FEATURE_PAUSEFILTER		(15*32+10) /* filtered pause intercept */
+#define X86_FEATURE_PFTHRESHOLD		(15*32+12) /* pause filter threshold */
+#define X86_FEATURE_AVIC		(15*32+13) /* Virtual Interrupt Controller */
+#define X86_FEATURE_V_VMSAVE_VMLOAD	(15*32+15) /* Virtual VMSAVE VMLOAD */
+#define X86_FEATURE_VGIF		(15*32+16) /* Virtual GIF */
 
-/* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */
-#define X86_FEATURE_AVX512VBMI  (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/
-#define X86_FEATURE_PKU		(16*32+ 3) /* Protection Keys for Userspace */
-#define X86_FEATURE_OSPKE	(16*32+ 4) /* OS Protection Keys Enable */
-#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */
-#define X86_FEATURE_LA57	(16*32+16) /* 5-level page tables */
-#define X86_FEATURE_RDPID	(16*32+22) /* RDPID instruction */
+/* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */
+#define X86_FEATURE_AVX512VBMI		(16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/
+#define X86_FEATURE_UMIP		(16*32+ 2) /* User Mode Instruction Protection */
+#define X86_FEATURE_PKU			(16*32+ 3) /* Protection Keys for Userspace */
+#define X86_FEATURE_OSPKE		(16*32+ 4) /* OS Protection Keys Enable */
+#define X86_FEATURE_AVX512_VBMI2	(16*32+ 6) /* Additional AVX512 Vector Bit Manipulation Instructions */
+#define X86_FEATURE_GFNI		(16*32+ 8) /* Galois Field New Instructions */
+#define X86_FEATURE_VAES		(16*32+ 9) /* Vector AES */
+#define X86_FEATURE_VPCLMULQDQ		(16*32+10) /* Carry-Less Multiplication Double Quadword */
+#define X86_FEATURE_AVX512_VNNI		(16*32+11) /* Vector Neural Network Instructions */
+#define X86_FEATURE_AVX512_BITALG	(16*32+12) /* Support for VPOPCNT[B,W] and VPSHUF-BITQMB instructions */
+#define X86_FEATURE_AVX512_VPOPCNTDQ	(16*32+14) /* POPCNT for vectors of DW/QW */
+#define X86_FEATURE_LA57		(16*32+16) /* 5-level page tables */
+#define X86_FEATURE_RDPID		(16*32+22) /* RDPID instruction */
 
-/* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */
-#define X86_FEATURE_OVERFLOW_RECOV (17*32+0) /* MCA overflow recovery support */
-#define X86_FEATURE_SUCCOR	(17*32+1) /* Uncorrectable error containment and recovery */
-#define X86_FEATURE_SMCA	(17*32+3) /* Scalable MCA */
+/* AMD-defined CPU features, CPUID level 0x80000007 (EBX), word 17 */
+#define X86_FEATURE_OVERFLOW_RECOV	(17*32+ 0) /* MCA overflow recovery support */
+#define X86_FEATURE_SUCCOR		(17*32+ 1) /* Uncorrectable error containment and recovery */
+#define X86_FEATURE_SMCA		(17*32+ 3) /* Scalable MCA */
 
 /*
  * BUG word(s)
  */
-#define X86_BUG(x)		(NCAPINTS*32 + (x))
+#define X86_BUG(x)			(NCAPINTS*32 + (x))
 
-#define X86_BUG_F00F		X86_BUG(0) /* Intel F00F */
-#define X86_BUG_FDIV		X86_BUG(1) /* FPU FDIV */
-#define X86_BUG_COMA		X86_BUG(2) /* Cyrix 6x86 coma */
-#define X86_BUG_AMD_TLB_MMATCH	X86_BUG(3) /* "tlb_mmatch" AMD Erratum 383 */
-#define X86_BUG_AMD_APIC_C1E	X86_BUG(4) /* "apic_c1e" AMD Erratum 400 */
-#define X86_BUG_11AP		X86_BUG(5) /* Bad local APIC aka 11AP */
-#define X86_BUG_FXSAVE_LEAK	X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */
-#define X86_BUG_CLFLUSH_MONITOR	X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */
-#define X86_BUG_SYSRET_SS_ATTRS	X86_BUG(8) /* SYSRET doesn't fix up SS attrs */
+#define X86_BUG_F00F			X86_BUG(0) /* Intel F00F */
+#define X86_BUG_FDIV			X86_BUG(1) /* FPU FDIV */
+#define X86_BUG_COMA			X86_BUG(2) /* Cyrix 6x86 coma */
+#define X86_BUG_AMD_TLB_MMATCH		X86_BUG(3) /* "tlb_mmatch" AMD Erratum 383 */
+#define X86_BUG_AMD_APIC_C1E		X86_BUG(4) /* "apic_c1e" AMD Erratum 400 */
+#define X86_BUG_11AP			X86_BUG(5) /* Bad local APIC aka 11AP */
+#define X86_BUG_FXSAVE_LEAK		X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */
+#define X86_BUG_CLFLUSH_MONITOR		X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */
+#define X86_BUG_SYSRET_SS_ATTRS		X86_BUG(8) /* SYSRET doesn't fix up SS attrs */
 #ifdef CONFIG_X86_32
 /*
  * 64-bit kernels don't use X86_BUG_ESPFIX.  Make the define conditional
  * to avoid confusion.
  */
-#define X86_BUG_ESPFIX		X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */
+#define X86_BUG_ESPFIX			X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */
 #endif
-#define X86_BUG_NULL_SEG	X86_BUG(10) /* Nulling a selector preserves the base */
-#define X86_BUG_SWAPGS_FENCE	X86_BUG(11) /* SWAPGS without input dep on GS */
-#define X86_BUG_MONITOR		X86_BUG(12) /* IPI required to wake up remote CPU */
-#define X86_BUG_AMD_E400	X86_BUG(13) /* CPU is among the affected by Erratum 400 */
+#define X86_BUG_NULL_SEG		X86_BUG(10) /* Nulling a selector preserves the base */
+#define X86_BUG_SWAPGS_FENCE		X86_BUG(11) /* SWAPGS without input dep on GS */
+#define X86_BUG_MONITOR			X86_BUG(12) /* IPI required to wake up remote CPU */
+#define X86_BUG_AMD_E400		X86_BUG(13) /* CPU is among the affected by Erratum 400 */
+
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
index c10c9128f54e..14d6d5007314 100644
--- a/tools/arch/x86/include/asm/disabled-features.h
+++ b/tools/arch/x86/include/asm/disabled-features.h
@@ -16,6 +16,12 @@
 # define DISABLE_MPX	(1<<(X86_FEATURE_MPX & 31))
 #endif
 
+#ifdef CONFIG_X86_INTEL_UMIP
+# define DISABLE_UMIP	0
+#else
+# define DISABLE_UMIP	(1<<(X86_FEATURE_UMIP & 31))
+#endif
+
 #ifdef CONFIG_X86_64
 # define DISABLE_VME		(1<<(X86_FEATURE_VME & 31))
 # define DISABLE_K6_MTRR	(1<<(X86_FEATURE_K6_MTRR & 31))
@@ -63,7 +69,7 @@
 #define DISABLED_MASK13	0
 #define DISABLED_MASK14	0
 #define DISABLED_MASK15	0
-#define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57)
+#define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP)
 #define DISABLED_MASK17	0
 #define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
 
diff --git a/tools/include/uapi/asm-generic/mman.h b/tools/include/uapi/asm-generic/mman.h
index 2dffcbf705b3..653687d9771b 100644
--- a/tools/include/uapi/asm-generic/mman.h
+++ b/tools/include/uapi/asm-generic/mman.h
@@ -13,6 +13,7 @@
 #define MAP_NONBLOCK	0x10000		/* do not block on IO */
 #define MAP_STACK	0x20000		/* give out an address that is best suited for process/thread stacks */
 #define MAP_HUGETLB	0x40000		/* create a huge page mapping */
+#define MAP_SYNC	0x80000		/* perform synchronous page faults for the mapping */
 
 /* Bits [26:31] are reserved, see mman-common.h for MAP_HUGETLB usage */
 
diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h
index 97677cd6964d..6fdff5945c8a 100644
--- a/tools/include/uapi/drm/drm.h
+++ b/tools/include/uapi/drm/drm.h
@@ -737,6 +737,28 @@ struct drm_syncobj_array {
 	__u32 pad;
 };
 
+/* Query current scanout sequence number */
+struct drm_crtc_get_sequence {
+	__u32 crtc_id;		/* requested crtc_id */
+	__u32 active;		/* return: crtc output is active */
+	__u64 sequence;		/* return: most recent vblank sequence */
+	__s64 sequence_ns;	/* return: most recent time of first pixel out */
+};
+
+/* Queue event to be delivered at specified sequence. Time stamp marks
+ * when the first pixel of the refresh cycle leaves the display engine
+ * for the display
+ */
+#define DRM_CRTC_SEQUENCE_RELATIVE		0x00000001	/* sequence is relative to current */
+#define DRM_CRTC_SEQUENCE_NEXT_ON_MISS		0x00000002	/* Use next sequence if we've missed */
+
+struct drm_crtc_queue_sequence {
+	__u32 crtc_id;
+	__u32 flags;
+	__u64 sequence;		/* on input, target sequence. on output, actual sequence */
+	__u64 user_data;	/* user data passed to event */
+};
+
 #if defined(__cplusplus)
 }
 #endif
@@ -819,6 +841,9 @@ extern "C" {
 
 #define DRM_IOCTL_WAIT_VBLANK		DRM_IOWR(0x3a, union drm_wait_vblank)
 
+#define DRM_IOCTL_CRTC_GET_SEQUENCE	DRM_IOWR(0x3b, struct drm_crtc_get_sequence)
+#define DRM_IOCTL_CRTC_QUEUE_SEQUENCE	DRM_IOWR(0x3c, struct drm_crtc_queue_sequence)
+
 #define DRM_IOCTL_UPDATE_DRAW		DRM_IOW(0x3f, struct drm_update_draw)
 
 #define DRM_IOCTL_MODE_GETRESOURCES	DRM_IOWR(0xA0, struct drm_mode_card_res)
@@ -863,6 +888,11 @@ extern "C" {
 #define DRM_IOCTL_SYNCOBJ_RESET		DRM_IOWR(0xC4, struct drm_syncobj_array)
 #define DRM_IOCTL_SYNCOBJ_SIGNAL	DRM_IOWR(0xC5, struct drm_syncobj_array)
 
+#define DRM_IOCTL_MODE_CREATE_LEASE	DRM_IOWR(0xC6, struct drm_mode_create_lease)
+#define DRM_IOCTL_MODE_LIST_LESSEES	DRM_IOWR(0xC7, struct drm_mode_list_lessees)
+#define DRM_IOCTL_MODE_GET_LEASE	DRM_IOWR(0xC8, struct drm_mode_get_lease)
+#define DRM_IOCTL_MODE_REVOKE_LEASE	DRM_IOWR(0xC9, struct drm_mode_revoke_lease)
+
 /**
  * Device specific ioctls should only be in their respective headers
  * The device specific ioctl range is from 0x40 to 0x9f.
@@ -893,6 +923,7 @@ struct drm_event {
 
 #define DRM_EVENT_VBLANK 0x01
 #define DRM_EVENT_FLIP_COMPLETE 0x02
+#define DRM_EVENT_CRTC_SEQUENCE	0x03
 
 struct drm_event_vblank {
 	struct drm_event base;
@@ -903,6 +934,16 @@ struct drm_event_vblank {
 	__u32 crtc_id; /* 0 on older kernels that do not support this */
 };
 
+/* Event delivered at sequence. Time stamp marks when the first pixel
+ * of the refresh cycle leaves the display engine for the display
+ */
+struct drm_event_crtc_sequence {
+	struct drm_event	base;
+	__u64			user_data;
+	__s64			time_ns;
+	__u64			sequence;
+};
+
 /* typedef area */
 #ifndef __KERNEL__
 typedef struct drm_clip_rect drm_clip_rect_t;
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index 9816590d3ad2..ac3c6503ca27 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -397,10 +397,20 @@ typedef struct drm_i915_irq_wait {
 #define I915_PARAM_MIN_EU_IN_POOL	 39
 #define I915_PARAM_MMAP_GTT_VERSION	 40
 
-/* Query whether DRM_I915_GEM_EXECBUFFER2 supports user defined execution
+/*
+ * Query whether DRM_I915_GEM_EXECBUFFER2 supports user defined execution
  * priorities and the driver will attempt to execute batches in priority order.
+ * The param returns a capability bitmask, nonzero implies that the scheduler
+ * is enabled, with different features present according to the mask.
+ *
+ * The initial priority for each batch is supplied by the context and is
+ * controlled via I915_CONTEXT_PARAM_PRIORITY.
  */
 #define I915_PARAM_HAS_SCHEDULER	 41
+#define   I915_SCHEDULER_CAP_ENABLED	(1ul << 0)
+#define   I915_SCHEDULER_CAP_PRIORITY	(1ul << 1)
+#define   I915_SCHEDULER_CAP_PREEMPTION	(1ul << 2)
+
 #define I915_PARAM_HUC_STATUS		 42
 
 /* Query whether DRM_I915_GEM_EXECBUFFER2 supports the ability to opt-out of
@@ -1309,14 +1319,16 @@ struct drm_i915_reg_read {
 	 * be specified
 	 */
 	__u64 offset;
+#define I915_REG_READ_8B_WA (1ul << 0)
+
 	__u64 val; /* Return value */
 };
 /* Known registers:
  *
  * Render engine timestamp - 0x2358 + 64bit - gen7+
  * - Note this register returns an invalid value if using the default
- *   single instruction 8byte read, in order to workaround that use
- *   offset (0x2538 | 1) instead.
+ *   single instruction 8byte read, in order to workaround that pass
+ *   flag I915_REG_READ_8B_WA in offset field.
  *
  */
 
@@ -1359,6 +1371,10 @@ struct drm_i915_gem_context_param {
 #define I915_CONTEXT_PARAM_GTT_SIZE	0x3
 #define I915_CONTEXT_PARAM_NO_ERROR_CAPTURE	0x4
 #define I915_CONTEXT_PARAM_BANNABLE	0x5
+#define I915_CONTEXT_PARAM_PRIORITY	0x6
+#define   I915_CONTEXT_MAX_USER_PRIORITY	1023 /* inclusive */
+#define   I915_CONTEXT_DEFAULT_PRIORITY		0
+#define   I915_CONTEXT_MIN_USER_PRIORITY	-1023 /* inclusive */
 	__u64 value;
 };
 
@@ -1510,9 +1526,14 @@ struct drm_i915_perf_oa_config {
 	__u32 n_boolean_regs;
 	__u32 n_flex_regs;
 
-	__u64 __user mux_regs_ptr;
-	__u64 __user boolean_regs_ptr;
-	__u64 __user flex_regs_ptr;
+	/*
+	 * These fields are pointers to tuples of u32 values (register
+	 * address, value). For example the expected length of the buffer
+	 * pointed by mux_regs_ptr is (2 * sizeof(u32) * n_mux_regs).
+	 */
+	__u64 mux_regs_ptr;
+	__u64 boolean_regs_ptr;
+	__u64 flex_regs_ptr;
 };
 
 #if defined(__cplusplus)
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 7e99999d6236..282d7613fce8 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -931,6 +931,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_PPC_SMT_POSSIBLE 147
 #define KVM_CAP_HYPERV_SYNIC2 148
 #define KVM_CAP_HYPERV_VP_INDEX 149
+#define KVM_CAP_S390_AIS_MIGRATION 150
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index 362493a2f950..b9a4953018ed 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -942,6 +942,7 @@ enum perf_callchain_context {
 #define PERF_AUX_FLAG_TRUNCATED		0x01	/* record was truncated to fit */
 #define PERF_AUX_FLAG_OVERWRITE		0x02	/* snapshot from overwrite mode */
 #define PERF_AUX_FLAG_PARTIAL		0x04	/* record contains gaps */
+#define PERF_AUX_FLAG_COLLISION		0x08	/* sample collided with another */
 
 #define PERF_FLAG_FD_NO_GROUP		(1UL << 0)
 #define PERF_FLAG_FD_OUTPUT		(1UL << 1)
diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h
index b640071421f7..af5f8c2df87a 100644
--- a/tools/include/uapi/linux/prctl.h
+++ b/tools/include/uapi/linux/prctl.h
@@ -198,4 +198,13 @@ struct prctl_mm_map {
 # define PR_CAP_AMBIENT_LOWER		3
 # define PR_CAP_AMBIENT_CLEAR_ALL	4
 
+/* arm64 Scalable Vector Extension controls */
+/* Flag values must be kept in sync with ptrace NT_ARM_SVE interface */
+#define PR_SVE_SET_VL			50	/* set task vector length */
+# define PR_SVE_SET_VL_ONEXEC		(1 << 18) /* defer effect until exec */
+#define PR_SVE_GET_VL			51	/* get task vector length */
+/* Bits common to PR_SVE_SET_VL and PR_SVE_GET_VL */
+# define PR_SVE_VL_LEN_MASK		0xffff
+# define PR_SVE_VL_INHERIT		(1 << 17) /* inherit across exec */
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index d95fdcc26f4b..944070e98a2c 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -216,6 +216,47 @@ static const char * const numa_usage[] = {
 	NULL
 };
 
+/*
+ * To get number of numa nodes present.
+ */
+static int nr_numa_nodes(void)
+{
+	int i, nr_nodes = 0;
+
+	for (i = 0; i < g->p.nr_nodes; i++) {
+		if (numa_bitmask_isbitset(numa_nodes_ptr, i))
+			nr_nodes++;
+	}
+
+	return nr_nodes;
+}
+
+/*
+ * To check if given numa node is present.
+ */
+static int is_node_present(int node)
+{
+	return numa_bitmask_isbitset(numa_nodes_ptr, node);
+}
+
+/*
+ * To check given numa node has cpus.
+ */
+static bool node_has_cpus(int node)
+{
+	struct bitmask *cpu = numa_allocate_cpumask();
+	unsigned int i;
+
+	if (cpu && !numa_node_to_cpus(node, cpu)) {
+		for (i = 0; i < cpu->size; i++) {
+			if (numa_bitmask_isbitset(cpu, i))
+				return true;
+		}
+	}
+
+	return false; /* lets fall back to nocpus safely */
+}
+
 static cpu_set_t bind_to_cpu(int target_cpu)
 {
 	cpu_set_t orig_mask, mask;
@@ -244,12 +285,12 @@ static cpu_set_t bind_to_cpu(int target_cpu)
 
 static cpu_set_t bind_to_node(int target_node)
 {
-	int cpus_per_node = g->p.nr_cpus/g->p.nr_nodes;
+	int cpus_per_node = g->p.nr_cpus / nr_numa_nodes();
 	cpu_set_t orig_mask, mask;
 	int cpu;
 	int ret;
 
-	BUG_ON(cpus_per_node*g->p.nr_nodes != g->p.nr_cpus);
+	BUG_ON(cpus_per_node * nr_numa_nodes() != g->p.nr_cpus);
 	BUG_ON(!cpus_per_node);
 
 	ret = sched_getaffinity(0, sizeof(orig_mask), &orig_mask);
@@ -649,7 +690,7 @@ static int parse_setup_node_list(void)
 			int i;
 
 			for (i = 0; i < mul; i++) {
-				if (t >= g->p.nr_tasks) {
+				if (t >= g->p.nr_tasks || !node_has_cpus(bind_node)) {
 					printf("\n# NOTE: ignoring bind NODEs starting at NODE#%d\n", bind_node);
 					goto out;
 				}
@@ -964,6 +1005,8 @@ static void calc_convergence(double runtime_ns_max, double *convergence)
 	sum = 0;
 
 	for (node = 0; node < g->p.nr_nodes; node++) {
+		if (!is_node_present(node))
+			continue;
 		nr = nodes[node];
 		nr_min = min(nr, nr_min);
 		nr_max = max(nr, nr_max);
@@ -984,8 +1027,11 @@ static void calc_convergence(double runtime_ns_max, double *convergence)
 	process_groups = 0;
 
 	for (node = 0; node < g->p.nr_nodes; node++) {
-		int processes = count_node_processes(node);
+		int processes;
 
+		if (!is_node_present(node))
+			continue;
+		processes = count_node_processes(node);
 		nr = nodes[node];
 		tprintf(" %2d/%-2d", nr, processes);
 
@@ -1291,7 +1337,7 @@ static void print_summary(void)
 
 	printf("\n ###\n");
 	printf(" # %d %s will execute (on %d nodes, %d CPUs):\n",
-		g->p.nr_tasks, g->p.nr_tasks == 1 ? "task" : "tasks", g->p.nr_nodes, g->p.nr_cpus);
+		g->p.nr_tasks, g->p.nr_tasks == 1 ? "task" : "tasks", nr_numa_nodes(), g->p.nr_cpus);
 	printf(" #      %5dx %5ldMB global  shared mem operations\n",
 			g->p.nr_loops, g->p.bytes_global/1024/1024);
 	printf(" #      %5dx %5ldMB process shared mem operations\n",
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index 98c098475e71..5d06ac81f7f1 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -84,7 +84,11 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused
 
 	evsel = perf_evlist__first(evlist);
 	evsel->attr.task = 1;
+#ifdef __s390x__
+	evsel->attr.sample_freq = 1000000;
+#else
 	evsel->attr.sample_freq = 1;
+#endif
 	evsel->attr.inherit = 0;
 	evsel->attr.watermark = 0;
 	evsel->attr.wakeup_events = 1;
diff --git a/tools/perf/trace/beauty/mmap.c b/tools/perf/trace/beauty/mmap.c
index 9e1668b2c5d7..417e3ecfe9d7 100644
--- a/tools/perf/trace/beauty/mmap.c
+++ b/tools/perf/trace/beauty/mmap.c
@@ -62,6 +62,9 @@ static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
 	P_MMAP_FLAG(POPULATE);
 	P_MMAP_FLAG(STACK);
 	P_MMAP_FLAG(UNINITIALIZED);
+#ifdef MAP_SYNC
+	P_MMAP_FLAG(SYNC);
+#endif
 #undef P_MMAP_FLAG
 
 	if (flags)
diff --git a/tools/perf/util/intel-pt-decoder/inat.h b/tools/perf/util/intel-pt-decoder/inat.h
index 125ecd2a300d..52dc8d911173 100644
--- a/tools/perf/util/intel-pt-decoder/inat.h
+++ b/tools/perf/util/intel-pt-decoder/inat.h
@@ -97,6 +97,16 @@
 #define INAT_MAKE_GROUP(grp)	((grp << INAT_GRP_OFFS) | INAT_MODRM)
 #define INAT_MAKE_IMM(imm)	(imm << INAT_IMM_OFFS)
 
+/* Identifiers for segment registers */
+#define INAT_SEG_REG_IGNORE	0
+#define INAT_SEG_REG_DEFAULT	1
+#define INAT_SEG_REG_CS		2
+#define INAT_SEG_REG_SS		3
+#define INAT_SEG_REG_DS		4
+#define INAT_SEG_REG_ES		5
+#define INAT_SEG_REG_FS		6
+#define INAT_SEG_REG_GS		7
+
 /* Attribute search APIs */
 extern insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode);
 extern int inat_get_last_prefix_id(insn_byte_t last_pfx);