Merge tag 'perf-tools-fixes-for-v6.4-1-2023-05-20' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tools fixes from Arnaldo Carvalho de Melo:

 - Fail graciously if BUILD_BPF_SKEL=1 is specified and clang isn't
   available

 - Add empty 'struct rq' to 'perf lock contention' to satisfy libbpf
   'runqueue' type verification. This feature is built only with
   BUILD_BPF_SKEL=1

 - Make vmlinux.h use bpf.h and perf_event.h in source directory, not
   system ones that may be old and not have things like 'union
   perf_sample_weight'

 - Add system include paths to BPF builds to pick things missing in the
   headers included by clang -target bpf

 - Update various header copies with the kernel sources

 - Change divide by zero and not supported events behavior to show
   'nan'/'not counted' in 'perf stat' output.

   This happens when using things like 'perf stat -M TopdownL2 true',
   involving JSON metrics

 - Update no event/metric expectations affected by using JSON metrics in
   'perf stat -ddd' perf test

 - Avoid segv with 'perf stat --topdown' for metrics without a group

 - Do not assume which events may have a PMU name, allowing the logic to
   keep an AUX event group together. Makes this usecase work again:

     $ perf record --no-bpf-event -c 10 -e '{intel_pt//,tlb_flush.stlb_any/aux-sample-size=8192/pp}:u' -- sleep 0.1
     [ perf record: Woken up 1 times to write data ]
     [ perf record: Captured and wrote 0.078 MB perf.data ]
     $ perf script -F-dso,+addr | grep -C5 tlb_flush.stlb_any | head -11
     sleep 20444 [003]  7939.510243:  1  branches:uH:  7f5350cc82a2 dl_main+0x9a2 => 7f5350cb38f0 _dl_add_to_namespace_list+0x0
     sleep 20444 [003]  7939.510243:  1  branches:uH:  7f5350cb3908 _dl_add_to_namespace_list+0x18 => 7f5350cbb080 rtld_mutex_dummy+0x0
     sleep 20444 [003]  7939.510243:  1  branches:uH:  7f5350cc8350 dl_main+0xa50 => 0 [unknown]
     sleep 20444 [003]  7939.510244:  1  branches:uH:  7f5350cc83ca dl_main+0xaca => 7f5350caeb60 _dl_process_pt_gnu_property+0x0
     sleep 20444 [003]  7939.510245:  1  branches:uH:  7f5350caeb60 _dl_process_pt_gnu_property+0x0 => 0 [unknown]
     sleep 20444  7939.510245:       10 tlb_flush.stlb_any/aux-sample-size=8192/pp: 0 7f5350caeb60 _dl_process_pt_gnu_property+0x0
     sleep 20444 [003]  7939.510254:  1  branches:uH:  7f5350cc87fe dl_main+0xefe => 7f5350ccd240 strcmp+0x0
     sleep 20444 [003]  7939.510254:  1  branches:uH:  7f5350cc8862 dl_main+0xf62 => 0 [unknown]

 - Add a check for the above use case in 'perf test test_intel_pt'

 - Fix build with refcount checking on arm64, it was still accessing
   fields that need to be wrapped so that the refcounted struct gets
   checked

 - Fix contextid validation in ARM's CS-ETM, so that older kernels
   without that field can still be supported

 - Skip unsupported aggregation for stat events found in perf.data files
   in 'perf script'

 - Add stat test for record and script to check the previous problem

 - Remove needless debuginfod queries from 'perf test java symbol', this
   was just making the test take a long time to complete

 - Address python SafeConfigParser() deprecation warning in 'perf test
   attr'

 - Fix __NR_execve undeclared on i386 'perf bench syscall' build error

* tag 'perf-tools-fixes-for-v6.4-1-2023-05-20' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (33 commits)
  perf bench syscall: Fix __NR_execve undeclared build error
  perf test attr: Fix python SafeConfigParser() deprecation warning
  perf test attr: Update no event/metric expectations
  tools headers disabled-features: Sync with the kernel sources
  tools headers UAPI: Sync arch prctl headers with the kernel sources
  tools headers: Update the copy of x86's mem{cpy,set}_64.S used in 'perf bench'
  tools headers x86 cpufeatures: Sync with the kernel sources
  tools headers UAPI: Sync s390 syscall table file that wires up the memfd_secret syscall
  tools headers UAPI: Sync linux/prctl.h with the kernel sources
  perf metrics: Avoid segv with --topdown for metrics without a group
  perf lock contention: Add empty 'struct rq' to satisfy libbpf 'runqueue' type verification
  perf cs-etm: Fix contextid validation
  perf arm64: Fix build with refcount checking
  perf test: Add stat test for record and script
  perf script: Skip aggregation for stat events
  perf build: Add system include paths to BPF builds
  perf bpf skels: Make vmlinux.h use bpf.h and perf_event.h in source directory
  perf parse-events: Do not break up AUX event group
  perf test test_intel_pt.sh: Test sample mode with event with PMU name
  perf evsel: Modify group pmu name for software events
  ...

Author: torvalds

tools/arch/arm64/include/uapi/asm/kvm.h

@@ -198,6 +198,15 @@ struct kvm_arm_copy_mte_tags {
 	__u64 reserved[2];
 };
 
+/*
+ * Counter/Timer offset structure. Describe the virtual/physical offset.
+ * To be used with KVM_ARM_SET_COUNTER_OFFSET.
+ */
+struct kvm_arm_counter_offset {
+	__u64 counter_offset;
+	__u64 reserved;
+};
+
 #define KVM_ARM_TAGS_TO_GUEST		0
 #define KVM_ARM_TAGS_FROM_GUEST		1
 
@@ -372,6 +381,10 @@ enum {
 #endif
 };
 
+/* Device Control API on vm fd */
+#define KVM_ARM_VM_SMCCC_CTRL		0
+#define   KVM_ARM_VM_SMCCC_FILTER	0
+
 /* Device Control API: ARM VGIC */
 #define KVM_DEV_ARM_VGIC_GRP_ADDR	0
 #define KVM_DEV_ARM_VGIC_GRP_DIST_REGS	1
@@ -411,6 +424,8 @@ enum {
 #define KVM_ARM_VCPU_TIMER_CTRL		1
 #define   KVM_ARM_VCPU_TIMER_IRQ_VTIMER		0
 #define   KVM_ARM_VCPU_TIMER_IRQ_PTIMER		1
+#define   KVM_ARM_VCPU_TIMER_IRQ_HVTIMER	2
+#define   KVM_ARM_VCPU_TIMER_IRQ_HPTIMER	3
 #define KVM_ARM_VCPU_PVTIME_CTRL	2
 #define   KVM_ARM_VCPU_PVTIME_IPA	0
 
@@ -469,6 +484,27 @@ enum {
 /* run->fail_entry.hardware_entry_failure_reason codes. */
 #define KVM_EXIT_FAIL_ENTRY_CPU_UNSUPPORTED	(1ULL << 0)
 
+enum kvm_smccc_filter_action {
+	KVM_SMCCC_FILTER_HANDLE = 0,
+	KVM_SMCCC_FILTER_DENY,
+	KVM_SMCCC_FILTER_FWD_TO_USER,
+
+#ifdef __KERNEL__
+	NR_SMCCC_FILTER_ACTIONS
+#endif
+};
+
+struct kvm_smccc_filter {
+	__u32 base;
+	__u32 nr_functions;
+	__u8 action;
+	__u8 pad[15];
+};
+
+/* arm64-specific KVM_EXIT_HYPERCALL flags */
+#define KVM_HYPERCALL_EXIT_SMC		(1U << 0)
+#define KVM_HYPERCALL_EXIT_16BIT	(1U << 1)
+
 #endif
 
 #endif /* __ARM_KVM_H__ */

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

@@ -97,7 +97,7 @@
 #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_AMD_LBR_V2		( 3*32+17) /* AMD Last Branch Record Extension Version 2 */
-#define X86_FEATURE_LFENCE_RDTSC	( 3*32+18) /* "" LFENCE synchronizes RDTSC */
+/* FREE, was #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 */
@@ -226,10 +226,9 @@
 
 /* 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_FLEXPRIORITY	( 8*32+ 1) /* Intel FlexPriority */
+#define X86_FEATURE_EPT			( 8*32+ 2) /* Intel Extended Page Table */
+#define X86_FEATURE_VPID		( 8*32+ 3) /* 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 */
@@ -307,14 +306,21 @@
 #define X86_FEATURE_SGX_EDECCSSA	(11*32+18) /* "" SGX EDECCSSA user leaf function */
 #define X86_FEATURE_CALL_DEPTH		(11*32+19) /* "" Call depth tracking for RSB stuffing */
 #define X86_FEATURE_MSR_TSX_CTRL	(11*32+20) /* "" MSR IA32_TSX_CTRL (Intel) implemented */
+#define X86_FEATURE_SMBA		(11*32+21) /* "" Slow Memory Bandwidth Allocation */
+#define X86_FEATURE_BMEC		(11*32+22) /* "" Bandwidth Monitoring Event Configuration */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
 #define X86_FEATURE_AVX_VNNI		(12*32+ 4) /* AVX VNNI instructions */
 #define X86_FEATURE_AVX512_BF16		(12*32+ 5) /* AVX512 BFLOAT16 instructions */
 #define X86_FEATURE_CMPCCXADD           (12*32+ 7) /* "" CMPccXADD instructions */
+#define X86_FEATURE_ARCH_PERFMON_EXT	(12*32+ 8) /* "" Intel Architectural PerfMon Extension */
+#define X86_FEATURE_FZRM		(12*32+10) /* "" Fast zero-length REP MOVSB */
+#define X86_FEATURE_FSRS		(12*32+11) /* "" Fast short REP STOSB */
+#define X86_FEATURE_FSRC		(12*32+12) /* "" Fast short REP {CMPSB,SCASB} */
 #define X86_FEATURE_LKGS		(12*32+18) /* "" Load "kernel" (userspace) GS */
 #define X86_FEATURE_AMX_FP16		(12*32+21) /* "" AMX fp16 Support */
 #define X86_FEATURE_AVX_IFMA            (12*32+23) /* "" Support for VPMADD52[H,L]UQ */
+#define X86_FEATURE_LAM			(12*32+26) /* Linear Address Masking */
 
 /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */
 #define X86_FEATURE_CLZERO		(13*32+ 0) /* CLZERO instruction */
@@ -331,6 +337,7 @@
 #define X86_FEATURE_VIRT_SSBD		(13*32+25) /* Virtualized Speculative Store Bypass Disable */
 #define X86_FEATURE_AMD_SSB_NO		(13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */
 #define X86_FEATURE_CPPC		(13*32+27) /* Collaborative Processor Performance Control */
+#define X86_FEATURE_AMD_PSFD            (13*32+28) /* "" Predictive Store Forwarding Disable */
 #define X86_FEATURE_BTC_NO		(13*32+29) /* "" Not vulnerable to Branch Type Confusion */
 #define X86_FEATURE_BRS			(13*32+31) /* Branch Sampling available */
 
@@ -363,6 +370,7 @@
 #define X86_FEATURE_VGIF		(15*32+16) /* Virtual GIF */
 #define X86_FEATURE_X2AVIC		(15*32+18) /* Virtual x2apic */
 #define X86_FEATURE_V_SPEC_CTRL		(15*32+20) /* Virtual SPEC_CTRL */
+#define X86_FEATURE_VNMI		(15*32+25) /* Virtual NMI */
 #define X86_FEATURE_SVME_ADDR_CHK	(15*32+28) /* "" SVME addr check */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */
@@ -427,6 +435,13 @@
 #define X86_FEATURE_V_TSC_AUX		(19*32+ 9) /* "" Virtual TSC_AUX */
 #define X86_FEATURE_SME_COHERENT	(19*32+10) /* "" AMD hardware-enforced cache coherency */
 
+/* AMD-defined Extended Feature 2 EAX, CPUID level 0x80000021 (EAX), word 20 */
+#define X86_FEATURE_NO_NESTED_DATA_BP	(20*32+ 0) /* "" No Nested Data Breakpoints */
+#define X86_FEATURE_LFENCE_RDTSC	(20*32+ 2) /* "" LFENCE always serializing / synchronizes RDTSC */
+#define X86_FEATURE_NULL_SEL_CLR_BASE	(20*32+ 6) /* "" Null Selector Clears Base */
+#define X86_FEATURE_AUTOIBRS		(20*32+ 8) /* "" Automatic IBRS */
+#define X86_FEATURE_NO_SMM_CTL_MSR	(20*32+ 9) /* "" SMM_CTL MSR is not present */
+
 /*
  * BUG word(s)
  */
@@ -467,5 +482,6 @@
 #define X86_BUG_MMIO_UNKNOWN		X86_BUG(26) /* CPU is too old and its MMIO Stale Data status is unknown */
 #define X86_BUG_RETBLEED		X86_BUG(27) /* CPU is affected by RETBleed */
 #define X86_BUG_EIBRS_PBRSB		X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */
+#define X86_BUG_SMT_RSB			X86_BUG(29) /* CPU is vulnerable to Cross-Thread Return Address Predictions */
 
 #endif /* _ASM_X86_CPUFEATURES_H */

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

@@ -75,6 +75,12 @@
 # define DISABLE_CALL_DEPTH_TRACKING	(1 << (X86_FEATURE_CALL_DEPTH & 31))
 #endif
 
+#ifdef CONFIG_ADDRESS_MASKING
+# define DISABLE_LAM		0
+#else
+# define DISABLE_LAM		(1 << (X86_FEATURE_LAM & 31))
+#endif
+
 #ifdef CONFIG_INTEL_IOMMU_SVM
 # define DISABLE_ENQCMD		0
 #else
@@ -115,7 +121,7 @@
 #define DISABLED_MASK10	0
 #define DISABLED_MASK11	(DISABLE_RETPOLINE|DISABLE_RETHUNK|DISABLE_UNRET| \
 			 DISABLE_CALL_DEPTH_TRACKING)
-#define DISABLED_MASK12	0
+#define DISABLED_MASK12	(DISABLE_LAM)
 #define DISABLED_MASK13	0
 #define DISABLED_MASK14	0
 #define DISABLED_MASK15	0

tools/arch/x86/include/asm/msr-index.h

@@ -206,6 +206,8 @@
 
 /* Abbreviated from Intel SDM name IA32_INTEGRITY_CAPABILITIES */
 #define MSR_INTEGRITY_CAPS			0x000002d9
+#define MSR_INTEGRITY_CAPS_ARRAY_BIST_BIT      2
+#define MSR_INTEGRITY_CAPS_ARRAY_BIST          BIT(MSR_INTEGRITY_CAPS_ARRAY_BIST_BIT)
 #define MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT	4
 #define MSR_INTEGRITY_CAPS_PERIODIC_BIST	BIT(MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT)
 

tools/arch/x86/include/uapi/asm/kvm.h

@@ -559,4 +559,7 @@ struct kvm_pmu_event_filter {
 #define KVM_VCPU_TSC_CTRL 0 /* control group for the timestamp counter (TSC) */
 #define   KVM_VCPU_TSC_OFFSET 0 /* attribute for the TSC offset */
 
+/* x86-specific KVM_EXIT_HYPERCALL flags. */
+#define KVM_EXIT_HYPERCALL_LONG_MODE	BIT(0)
+
 #endif /* _ASM_X86_KVM_H */

tools/arch/x86/include/uapi/asm/prctl.h

@@ -16,8 +16,16 @@
 #define ARCH_GET_XCOMP_GUEST_PERM	0x1024
 #define ARCH_REQ_XCOMP_GUEST_PERM	0x1025
 
+#define ARCH_XCOMP_TILECFG		17
+#define ARCH_XCOMP_TILEDATA		18
+
 #define ARCH_MAP_VDSO_X32		0x2001
 #define ARCH_MAP_VDSO_32		0x2002
 #define ARCH_MAP_VDSO_64		0x2003
 
+#define ARCH_GET_UNTAG_MASK		0x4001
+#define ARCH_ENABLE_TAGGED_ADDR		0x4002
+#define ARCH_GET_MAX_TAG_BITS		0x4003
+#define ARCH_FORCE_TAGGED_SVA		0x4004
+
 #endif /* _ASM_X86_PRCTL_H */

tools/arch/x86/include/uapi/asm/unistd_32.h

@@ -2,6 +2,9 @@
 #ifndef __NR_fork
 #define __NR_fork 2
 #endif
+#ifndef __NR_execve
+#define __NR_execve 11
+#endif
 #ifndef __NR_getppid
 #define __NR_getppid 64
 #endif

tools/arch/x86/lib/memcpy_64.S

@@ -9,13 +9,6 @@
 
 .section .noinstr.text, "ax"
 
-/*
- * We build a jump to memcpy_orig by default which gets NOPped out on
- * the majority of x86 CPUs which set REP_GOOD. In addition, CPUs which
- * have the enhanced REP MOVSB/STOSB feature (ERMS), change those NOPs
- * to a jmp to memcpy_erms which does the REP; MOVSB mem copy.
- */
-
 /*
  * memcpy - Copy a memory block.
  *
@@ -26,17 +19,21 @@
  *
  * Output:
  * rax original destination
+ *
+ * The FSRM alternative should be done inline (avoiding the call and
+ * the disgusting return handling), but that would require some help
+ * from the compiler for better calling conventions.
+ *
+ * The 'rep movsb' itself is small enough to replace the call, but the
+ * two register moves blow up the code. And one of them is "needed"
+ * only for the return value that is the same as the source input,
+ * which the compiler could/should do much better anyway.
  */
 SYM_TYPED_FUNC_START(__memcpy)
-	ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \
-		      "jmp memcpy_erms", X86_FEATURE_ERMS
+	ALTERNATIVE "jmp memcpy_orig", "", X86_FEATURE_FSRM
 
 	movq %rdi, %rax
 	movq %rdx, %rcx
-	shrq $3, %rcx
-	andl $7, %edx
-	rep movsq
-	movl %edx, %ecx
 	rep movsb
 	RET
 SYM_FUNC_END(__memcpy)
@@ -45,17 +42,6 @@ EXPORT_SYMBOL(__memcpy)
 SYM_FUNC_ALIAS(memcpy, __memcpy)
 EXPORT_SYMBOL(memcpy)
 
-/*
- * memcpy_erms() - enhanced fast string memcpy. This is faster and
- * simpler than memcpy. Use memcpy_erms when possible.
- */
-SYM_FUNC_START_LOCAL(memcpy_erms)
-	movq %rdi, %rax
-	movq %rdx, %rcx
-	rep movsb
-	RET
-SYM_FUNC_END(memcpy_erms)
-
 SYM_FUNC_START_LOCAL(memcpy_orig)
 	movq %rdi, %rax
 

tools/arch/x86/lib/memset_64.S

@@ -18,27 +18,22 @@
  * rdx   count (bytes)
  *
  * rax   original destination
+ *
+ * The FSRS alternative should be done inline (avoiding the call and
+ * the disgusting return handling), but that would require some help
+ * from the compiler for better calling conventions.
+ *
+ * The 'rep stosb' itself is small enough to replace the call, but all
+ * the register moves blow up the code. And two of them are "needed"
+ * only for the return value that is the same as the source input,
+ * which the compiler could/should do much better anyway.
  */
 SYM_FUNC_START(__memset)
-	/*
-	 * Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended
-	 * to use it when possible. If not available, use fast string instructions.
-	 *
-	 * Otherwise, use original memset function.
-	 */
-	ALTERNATIVE_2 "jmp memset_orig", "", X86_FEATURE_REP_GOOD, \
-		      "jmp memset_erms", X86_FEATURE_ERMS
+	ALTERNATIVE "jmp memset_orig", "", X86_FEATURE_FSRS
 
 	movq %rdi,%r9
+	movb %sil,%al
 	movq %rdx,%rcx
-	andl $7,%edx
-	shrq $3,%rcx
-	/* expand byte value  */
-	movzbl %sil,%esi
-	movabs $0x0101010101010101,%rax
-	imulq %rsi,%rax
-	rep stosq
-	movl %edx,%ecx
 	rep stosb
 	movq %r9,%rax
 	RET
@@ -48,26 +43,6 @@ EXPORT_SYMBOL(__memset)
 SYM_FUNC_ALIAS(memset, __memset)
 EXPORT_SYMBOL(memset)
 
-/*
- * ISO C memset - set a memory block to a byte value. This function uses
- * enhanced rep stosb to override the fast string function.
- * The code is simpler and shorter than the fast string function as well.
- *
- * rdi   destination
- * rsi   value (char)
- * rdx   count (bytes)
- *
- * rax   original destination
- */
-SYM_FUNC_START_LOCAL(memset_erms)
-	movq %rdi,%r9
-	movb %sil,%al
-	movq %rdx,%rcx
-	rep stosb
-	movq %r9,%rax
-	RET
-SYM_FUNC_END(memset_erms)
-
 SYM_FUNC_START_LOCAL(memset_orig)
 	movq %rdi,%r10
 

tools/include/asm/alternative.h

@@ -4,7 +4,6 @@
 
 /* Just disable it so we can build arch/x86/lib/memcpy_64.S for perf bench: */
 
-#define altinstruction_entry #
-#define ALTERNATIVE_2 #
+#define ALTERNATIVE #
 
 #endif