Merge branch 'perf/urgent' of...

Merge branch 'perf/urgent' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Pull perf tooling fixes from Arnaldo Carvalho de Melo:

"- Fix window dimensions change handling in 'perf top' (Jiri Olsa)

- Fix 'perf record -c/-F' options for CPU event aliases (Andi Kleen)

- Generate PERF_RECORD_{MMAP,COMM,EXEC} with 'perf record --delay'
  fixing symbol resolution for processes created, maps put in place
  while --delay happens (Arnaldo Carvalho de Melo)

- Fix up leftover perf_evsel_stat usage via evsel->priv, plugging
  a SEGV when using event groups as in:

     $ perf stat -e '{cpu-clock,instructions}' workload

- Fix 'perf script --per-event-dump' for auxtrace synth evsels (Arnaldo Carvalho de Melo)

- Ignore kptr_restrict when not sampling the kernel (Arnaldo Carvalho de Melo)

- Synchronize kernel ABI headers wrt SPDX tags and ABI changes,
  taking minimal action to handle new syscall args and silencing
  perf build warnings (Arnaldo Carvalho de Melo, Ingo Molnar)

- Fix header.size for namespace events (Jiri Olsa)

- Fix a bug during strstart() conversion in 'perf help' (Namhyung Kim)

- Do not truncate instruction names at 6 chars in 'perf annotate', there
  are really long instruction names in PPC (Ravi Bangoria)

- Fixup discontiguous/sparse numa nodes in 'perf bench numa' (Satheesh Rajendran)

- Fix an exit code of trace__symbols_init in 'perf trace' (Andrei Vagin)

- Fix 'perf test' entries on s/390 (Thomas Richter)

- Bring instruction decoder files used by Intel PT into line with the kernel,
  silencing build warning (Adrian Hunter)"
Signed-off-by: Ingo Molnar <mingo@kernel.org>

kernel/events/core.c

@@ -6640,6 +6640,7 @@ static void perf_event_namespaces_output(struct perf_event *event,
 	struct perf_namespaces_event *namespaces_event = data;
 	struct perf_output_handle handle;
 	struct perf_sample_data sample;
+	u16 header_size = namespaces_event->event_id.header.size;
 	int ret;
 
 	if (!perf_event_namespaces_match(event))
@@ -6650,7 +6651,7 @@ static void perf_event_namespaces_output(struct perf_event *event,
 	ret = perf_output_begin(&handle, event,
 				namespaces_event->event_id.header.size);
 	if (ret)
-		return;
+		goto out;
 
 	namespaces_event->event_id.pid = perf_event_pid(event,
 							namespaces_event->task);
@@ -6662,6 +6663,8 @@ static void perf_event_namespaces_output(struct perf_event *event,
 	perf_event__output_id_sample(event, &handle, &sample);
 
 	perf_output_end(&handle);
+out:
+	namespaces_event->event_id.header.size = header_size;
 }
 
 static void perf_fill_ns_link_info(struct perf_ns_link_info *ns_link_info,

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

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

tools/arch/x86/include/asm/cpufeatures.h

@@ -20,9 +20,12 @@
  * 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 */
+/* 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 */
@@ -37,8 +40,7 @@
 #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_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 */
@@ -58,15 +60,15 @@
 /* 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_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_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 */
@@ -79,66 +81,67 @@
 #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: */
+
+/* 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_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_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_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_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 */
+/* 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_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 */
+#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 */
+#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) /* Performance Capabilities */
+#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_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_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_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) /* The RDRAND instruction */
+#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 */
@@ -153,10 +156,10 @@
 #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 */
+/* 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_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 */
@@ -170,16 +173,16 @@
 #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_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_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_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) */
+#define X86_FEATURE_MWAITX		( 6*32+29) /* MWAIT extension (MONITORX/MWAITX instructions) */
 
 /*
  * Auxiliary flags: Linux defined - For features scattered in various
@@ -187,7 +190,7 @@
  *
  * Reuse free bits when adding new feature flags!
  */
-#define X86_FEATURE_RING3MWAIT	( 7*32+ 0) /* Ring 3 MONITOR/MWAIT */
+#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 */
@@ -201,8 +204,8 @@
 
 #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_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 */
 
@@ -213,19 +216,19 @@
 #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_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 */
+/* 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 */
+#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 */
@@ -233,8 +236,8 @@
 #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_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 */
@@ -246,25 +249,25 @@
 #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 */
+/* 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 */
+/* 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 */
+/* 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 */
@@ -276,7 +279,7 @@
 #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 */
+/* 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 */
@@ -291,18 +294,25 @@
 #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 */
+/* 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)
@@ -329,4 +339,5 @@
 #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 */

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)
 

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 */
 

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;

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)

tools/include/uapi/linux/kcmp.h

+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _UAPI_LINUX_KCMP_H
 #define _UAPI_LINUX_KCMP_H
 

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
 

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)

tools/include/uapi/linux/prctl.h

+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _LINUX_PRCTL_H
 #define _LINUX_PRCTL_H
 
@@ -197,4 +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 */

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",

tools/perf/builtin-help.c

@@ -284,7 +284,7 @@ static int perf_help_config(const char *var, const char *value, void *cb)
 		add_man_viewer(value);
 		return 0;
 	}
-	if (!strstarts(var, "man."))
+	if (strstarts(var, "man."))
 		return add_man_viewer_info(var, value);
 
 	return 0;
@@ -314,7 +314,7 @@ static const char *cmd_to_page(const char *perf_cmd)
 
 	if (!perf_cmd)
 		return "perf";
-	else if (!strstarts(perf_cmd, "perf"))
+	else if (strstarts(perf_cmd, "perf"))
 		return perf_cmd;
 
 	return asprintf(&s, "perf-%s", perf_cmd) < 0 ? NULL : s;

tools/perf/builtin-record.c

@@ -339,6 +339,22 @@ static int record__open(struct record *rec)
 	struct perf_evsel_config_term *err_term;
 	int rc = 0;
 
+	/*
+	 * For initial_delay we need to add a dummy event so that we can track
+	 * PERF_RECORD_MMAP while we wait for the initial delay to enable the
+	 * real events, the ones asked by the user.
+	 */
+	if (opts->initial_delay) {
+		if (perf_evlist__add_dummy(evlist))
+			return -ENOMEM;
+
+		pos = perf_evlist__first(evlist);
+		pos->tracking = 0;
+		pos = perf_evlist__last(evlist);
+		pos->tracking = 1;
+		pos->attr.enable_on_exec = 1;
+	}
+
 	perf_evlist__config(evlist, opts, &callchain_param);
 
 	evlist__for_each_entry(evlist, pos) {
@@ -749,6 +765,7 @@ static int record__synthesize(struct record *rec, bool tail)
 			goto out;
 	}
 
+	if (!perf_evlist__exclude_kernel(rec->evlist)) {
 		err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
 							 machine);
 		WARN_ONCE(err < 0, "Couldn't record kernel reference relocation symbol\n"
@@ -760,6 +777,7 @@ static int record__synthesize(struct record *rec, bool tail)
 		WARN_ONCE(err < 0, "Couldn't record kernel module information.\n"
 				   "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
 				   "Check /proc/modules permission or run as root.\n");
+	}
 
 	if (perf_guest) {
 		machines__process_guests(&session->machines,
@@ -1693,7 +1711,7 @@ int cmd_record(int argc, const char **argv)
 
 	err = -ENOMEM;
 
-	if (symbol_conf.kptr_restrict)
+	if (symbol_conf.kptr_restrict && !perf_evlist__exclude_kernel(rec->evlist))
 		pr_warning(
 "WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted,\n"
 "check /proc/sys/kernel/kptr_restrict.\n\n"

tools/perf/builtin-report.c

@@ -441,6 +441,9 @@ static void report__warn_kptr_restrict(const struct report *rep)
 	struct map *kernel_map = machine__kernel_map(&rep->session->machines.host);
 	struct kmap *kernel_kmap = kernel_map ? map__kmap(kernel_map) : NULL;
 
+	if (perf_evlist__exclude_kernel(rep->session->evlist))
+		return;
+
 	if (kernel_map == NULL ||
 	    (kernel_map->dso->hit &&
 	     (kernel_kmap->ref_reloc_sym == NULL ||

tools/perf/builtin-script.c

@@ -1955,6 +1955,16 @@ static int perf_script__fopen_per_event_dump(struct perf_script *script)
 	struct perf_evsel *evsel;
 
 	evlist__for_each_entry(script->session->evlist, evsel) {
+		/*
+		 * Already setup? I.e. we may be called twice in cases like
+		 * Intel PT, one for the intel_pt// and dummy events, then
+		 * for the evsels syntheized from the auxtrace info.
+		 *
+		 * Ses perf_script__process_auxtrace_info.
+		 */
+		if (evsel->priv != NULL)
+			continue;
+
 		evsel->priv = perf_evsel_script__new(evsel, script->session->data);
 		if (evsel->priv == NULL)
 			goto out_err_fclose;
@@ -2838,6 +2848,25 @@ int process_cpu_map_event(struct perf_tool *tool __maybe_unused,
 	return set_maps(script);
 }
 
+#ifdef HAVE_AUXTRACE_SUPPORT
+static int perf_script__process_auxtrace_info(struct perf_tool *tool,
+					      union perf_event *event,
+					      struct perf_session *session)
+{
+	int ret = perf_event__process_auxtrace_info(tool, event, session);
+
+	if (ret == 0) {
+		struct perf_script *script = container_of(tool, struct perf_script, tool);
+
+		ret = perf_script__setup_per_event_dump(script);
+	}
+
+	return ret;
+}
+#else
+#define perf_script__process_auxtrace_info 0
+#endif
+
 int cmd_script(int argc, const char **argv)
 {
 	bool show_full_info = false;
@@ -2866,7 +2895,7 @@ int cmd_script(int argc, const char **argv)
 			.feature	 = perf_event__process_feature,
 			.build_id	 = perf_event__process_build_id,
 			.id_index	 = perf_event__process_id_index,
-			.auxtrace_info	 = perf_event__process_auxtrace_info,
+			.auxtrace_info	 = perf_script__process_auxtrace_info,
 			.auxtrace	 = perf_event__process_auxtrace,
 			.auxtrace_error	 = perf_event__process_auxtrace_error,
 			.stat		 = perf_event__process_stat_event,

tools/perf/builtin-top.c

@@ -77,6 +77,7 @@
 #include "sane_ctype.h"
 
 static volatile int done;
+static volatile int resize;
 
 #define HEADER_LINE_NR  5
 
@@ -85,11 +86,13 @@ static void perf_top__update_print_entries(struct perf_top *top)
 	top->print_entries = top->winsize.ws_row - HEADER_LINE_NR;
 }
 
-static void perf_top__sig_winch(int sig __maybe_unused,
-				siginfo_t *info __maybe_unused, void *arg)
+static void winch_sig(int sig __maybe_unused)
 {
-	struct perf_top *top = arg;
+	resize = 1;
+}
 
+static void perf_top__resize(struct perf_top *top)
+{
 	get_term_dimensions(&top->winsize);
 	perf_top__update_print_entries(top);
 }
@@ -473,12 +476,8 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c)
 		case 'e':
 			prompt_integer(&top->print_entries, "Enter display entries (lines)");
 			if (top->print_entries == 0) {
-				struct sigaction act = {
-					.sa_sigaction = perf_top__sig_winch,
-					.sa_flags     = SA_SIGINFO,
-				};
-				perf_top__sig_winch(SIGWINCH, NULL, top);
-				sigaction(SIGWINCH, &act, NULL);
+				perf_top__resize(top);
+				signal(SIGWINCH, winch_sig);
 			} else {
 				signal(SIGWINCH, SIG_DFL);
 			}
@@ -732,6 +731,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
 	if (!machine->kptr_restrict_warned &&
 	    symbol_conf.kptr_restrict &&
 	    al.cpumode == PERF_RECORD_MISC_KERNEL) {
+		if (!perf_evlist__exclude_kernel(top->session->evlist)) {
 			ui__warning(
 "Kernel address maps (/proc/{kallsyms,modules}) are restricted.\n\n"
 "Check /proc/sys/kernel/kptr_restrict.\n\n"
@@ -740,6 +740,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
 			  " modules" : "");
 			if (use_browser <= 0)
 				sleep(5);
+		}
 		machine->kptr_restrict_warned = true;
 	}
 
@@ -1030,6 +1031,11 @@ static int __cmd_top(struct perf_top *top)
 
 		if (hits == top->samples)
 			ret = perf_evlist__poll(top->evlist, 100);
+
+		if (resize) {
+			perf_top__resize(top);
+			resize = 0;
+		}
 	}
 
 	ret = 0;
@@ -1352,12 +1358,8 @@ int cmd_top(int argc, const char **argv)
 
 	get_term_dimensions(&top.winsize);
 	if (top.print_entries == 0) {
-		struct sigaction act = {
-			.sa_sigaction = perf_top__sig_winch,
-			.sa_flags     = SA_SIGINFO,
-		};
 		perf_top__update_print_entries(&top);
-		sigaction(SIGWINCH, &act, NULL);
+		signal(SIGWINCH, winch_sig);
 	}
 
 	status = __cmd_top(&top);

tools/perf/builtin-trace.c

@@ -1152,12 +1152,14 @@ static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist)
 	if (trace->host == NULL)
 		return -ENOMEM;
 
-	if (trace_event__register_resolver(trace->host, trace__machine__resolve_kernel_addr) < 0)
-		return -errno;
+	err = trace_event__register_resolver(trace->host, trace__machine__resolve_kernel_addr);
+	if (err < 0)
+		goto out;
 
 	err = __machine__synthesize_threads(trace->host, &trace->tool, &trace->opts.target,
 					    evlist->threads, trace__tool_process, false,
 					    trace->opts.proc_map_timeout, 1);
+out:
 	if (err)
 		symbol__exit();
 

tools/perf/tests/shell/trace+probe_libc_inet_pton.sh

@@ -10,8 +10,8 @@
 
 . $(dirname $0)/lib/probe.sh
 
-ld=$(realpath /lib64/ld*.so.* | uniq)
-libc=$(echo $ld | sed 's/ld/libc/g')
+libc=$(grep -w libc /proc/self/maps | head -1 | sed -r 's/.*[[:space:]](\/.*)/\1/g')
+nm -g $libc 2>/dev/null | fgrep -q inet_pton || exit 254
 
 trace_libc_inet_pton_backtrace() {
 	idx=0
@@ -37,6 +37,9 @@ trace_libc_inet_pton_backtrace() {
 	done
 }
 
+# Check for IPv6 interface existence
+ip a sh lo | fgrep -q inet6 || exit 2
+
 skip_if_no_perf_probe && \
 perf probe -q $libc inet_pton && \
 trace_libc_inet_pton_backtrace

tools/perf/tests/shell/trace+probe_vfs_getname.sh

@@ -17,8 +17,10 @@ skip_if_no_perf_probe || exit 2
 file=$(mktemp /tmp/temporary_file.XXXXX)
 
 trace_open_vfs_getname() {
-	perf trace -e open touch $file 2>&1 | \
-	egrep " +[0-9]+\.[0-9]+ +\( +[0-9]+\.[0-9]+ ms\): +touch\/[0-9]+ open\(filename: +${file}, +flags: CREAT\|NOCTTY\|NONBLOCK\|WRONLY, +mode: +IRUGO\|IWUGO\) += +[0-9]+$"
+	test "$(uname -m)" = s390x && { svc="openat"; txt="dfd: +CWD, +"; }
+
+	perf trace -e ${svc:-open} touch $file 2>&1 | \
+	egrep " +[0-9]+\.[0-9]+ +\( +[0-9]+\.[0-9]+ ms\): +touch\/[0-9]+ ${svc:-open}\(${txt}filename: +${file}, +flags: CREAT\|NOCTTY\|NONBLOCK\|WRONLY, +mode: +IRUGO\|IWUGO\) += +[0-9]+$"
 }
 
 

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;

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)

tools/perf/util/annotate.c

@@ -165,7 +165,7 @@ static void ins__delete(struct ins_operands *ops)
 static int ins__raw_scnprintf(struct ins *ins, char *bf, size_t size,
 			      struct ins_operands *ops)
 {
-	return scnprintf(bf, size, "%-6.6s %s", ins->name, ops->raw);
+	return scnprintf(bf, size, "%-6s %s", ins->name, ops->raw);
 }
 
 int ins__scnprintf(struct ins *ins, char *bf, size_t size,
@@ -230,12 +230,12 @@ static int call__scnprintf(struct ins *ins, char *bf, size_t size,
 			   struct ins_operands *ops)
 {
 	if (ops->target.name)
-		return scnprintf(bf, size, "%-6.6s %s", ins->name, ops->target.name);
+		return scnprintf(bf, size, "%-6s %s", ins->name, ops->target.name);
 
 	if (ops->target.addr == 0)
 		return ins__raw_scnprintf(ins, bf, size, ops);
 
-	return scnprintf(bf, size, "%-6.6s *%" PRIx64, ins->name, ops->target.addr);
+	return scnprintf(bf, size, "%-6s *%" PRIx64, ins->name, ops->target.addr);
 }
 
 static struct ins_ops call_ops = {
@@ -299,7 +299,7 @@ static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
 			c++;
 	}
 
-	return scnprintf(bf, size, "%-6.6s %.*s%" PRIx64,
+	return scnprintf(bf, size, "%-6s %.*s%" PRIx64,
 			 ins->name, c ? c - ops->raw : 0, ops->raw,
 			 ops->target.offset);
 }
@@ -372,7 +372,7 @@ static int lock__scnprintf(struct ins *ins, char *bf, size_t size,
 	if (ops->locked.ins.ops == NULL)
 		return ins__raw_scnprintf(ins, bf, size, ops);
 
-	printed = scnprintf(bf, size, "%-6.6s ", ins->name);
+	printed = scnprintf(bf, size, "%-6s ", ins->name);
 	return printed + ins__scnprintf(&ops->locked.ins, bf + printed,
 					size - printed, ops->locked.ops);
 }
@@ -448,7 +448,7 @@ static int mov__parse(struct arch *arch, struct ins_operands *ops, struct map *m
 static int mov__scnprintf(struct ins *ins, char *bf, size_t size,
 			   struct ins_operands *ops)
 {
-	return scnprintf(bf, size, "%-6.6s %s,%s", ins->name,
+	return scnprintf(bf, size, "%-6s %s,%s", ins->name,
 			 ops->source.name ?: ops->source.raw,
 			 ops->target.name ?: ops->target.raw);
 }
@@ -488,7 +488,7 @@ static int dec__parse(struct arch *arch __maybe_unused, struct ins_operands *ops
 static int dec__scnprintf(struct ins *ins, char *bf, size_t size,
 			   struct ins_operands *ops)
 {
-	return scnprintf(bf, size, "%-6.6s %s", ins->name,
+	return scnprintf(bf, size, "%-6s %s", ins->name,
 			 ops->target.name ?: ops->target.raw);
 }
 
@@ -500,7 +500,7 @@ static struct ins_ops dec_ops = {
 static int nop__scnprintf(struct ins *ins __maybe_unused, char *bf, size_t size,
 			  struct ins_operands *ops __maybe_unused)
 {
-	return scnprintf(bf, size, "%-6.6s", "nop");
+	return scnprintf(bf, size, "%-6s", "nop");
 }
 
 static struct ins_ops nop_ops = {
@@ -924,7 +924,7 @@ void disasm_line__free(struct disasm_line *dl)
 int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw)
 {
 	if (raw || !dl->ins.ops)
-		return scnprintf(bf, size, "%-6.6s %s", dl->ins.name, dl->ops.raw);
+		return scnprintf(bf, size, "%-6s %s", dl->ins.name, dl->ops.raw);
 
 	return ins__scnprintf(&dl->ins, bf, size, &dl->ops);
 }

tools/perf/util/evlist.c

@@ -257,7 +257,7 @@ int perf_evlist__add_dummy(struct perf_evlist *evlist)
 		.config = PERF_COUNT_SW_DUMMY,
 		.size	= sizeof(attr), /* to capture ABI version */
 	};
-	struct perf_evsel *evsel = perf_evsel__new(&attr);
+	struct perf_evsel *evsel = perf_evsel__new_idx(&attr, evlist->nr_entries);
 
 	if (evsel == NULL)
 		return -ENOMEM;
@@ -1786,3 +1786,15 @@ void perf_evlist__toggle_bkw_mmap(struct perf_evlist *evlist,
 state_err:
 	return;
 }
+
+bool perf_evlist__exclude_kernel(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each_entry(evlist, evsel) {
+		if (!evsel->attr.exclude_kernel)
+			return false;
+	}
+
+	return true;
+}

tools/perf/util/evlist.h

@@ -312,4 +312,6 @@ perf_evlist__find_evsel_by_str(struct perf_evlist *evlist, const char *str);
 
 struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist,
 					    union perf_event *event);
+
+bool perf_evlist__exclude_kernel(struct perf_evlist *evlist);
 #endif /* __PERF_EVLIST_H */

tools/perf/util/evsel.c

@@ -733,12 +733,16 @@ static void apply_config_terms(struct perf_evsel *evsel,
 	list_for_each_entry(term, config_terms, list) {
 		switch (term->type) {
 		case PERF_EVSEL__CONFIG_TERM_PERIOD:
+			if (!(term->weak && opts->user_interval != ULLONG_MAX)) {
 				attr->sample_period = term->val.period;
 				attr->freq = 0;
+			}
 			break;
 		case PERF_EVSEL__CONFIG_TERM_FREQ:
+			if (!(term->weak && opts->user_freq != UINT_MAX)) {
 				attr->sample_freq = term->val.freq;
 				attr->freq = 1;
+			}
 			break;
 		case PERF_EVSEL__CONFIG_TERM_TIME:
 			if (term->val.time)
@@ -1371,7 +1375,7 @@ perf_evsel__process_group_data(struct perf_evsel *leader,
 static int
 perf_evsel__read_group(struct perf_evsel *leader, int cpu, int thread)
 {
-	struct perf_stat_evsel *ps = leader->priv;
+	struct perf_stat_evsel *ps = leader->stats;
 	u64 read_format = leader->attr.read_format;
 	int size = perf_evsel__read_size(leader);
 	u64 *data = ps->group_data;

tools/perf/util/evsel.h

@@ -67,6 +67,7 @@ struct perf_evsel_config_term {
 		bool	overwrite;
 		char	*branch;
 	} val;
+	bool weak;
 };
 
 struct perf_stat_evsel;

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);

tools/perf/util/machine.c

@@ -172,6 +172,9 @@ void machine__exit(struct machine *machine)
 {
 	int i;
 
+	if (machine == NULL)
+		return;
+
 	machine__destroy_kernel_maps(machine);
 	map_groups__exit(&machine->kmaps);
 	dsos__exit(&machine->dsos);

tools/perf/util/parse-events.c

@@ -1116,6 +1116,7 @@ do {								\
 	INIT_LIST_HEAD(&__t->list);				\
 	__t->type       = PERF_EVSEL__CONFIG_TERM_ ## __type;	\
 	__t->val.__name = __val;				\
+	__t->weak	= term->weak;				\
 	list_add_tail(&__t->list, head_terms);			\
 } while (0)
 
@@ -2410,6 +2411,7 @@ static int new_term(struct parse_events_term **_term,
 
 	*term = *temp;
 	INIT_LIST_HEAD(&term->list);
+	term->weak = false;
 
 	switch (term->type_val) {
 	case PARSE_EVENTS__TERM_TYPE_NUM:

tools/perf/util/parse-events.h

@@ -101,6 +101,9 @@ struct parse_events_term {
 	/* error string indexes for within parsed string */
 	int err_term;
 	int err_val;
+
+	/* Coming from implicit alias */
+	bool weak;
 };
 
 struct parse_events_error {

tools/perf/util/pmu.c

@@ -405,6 +405,11 @@ static int pmu_alias_terms(struct perf_pmu_alias *alias,
 			parse_events_terms__purge(&list);
 			return ret;
 		}
+		/*
+		 * Weak terms don't override command line options,
+		 * which we don't want for implicit terms in aliases.
+		 */
+		cloned->weak = true;
 		list_add_tail(&cloned->list, &list);
 	}
 	list_splice(&list, terms);