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
  ...

1 files changed, 21 insertions, 5 deletions

diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index b89005819cd5..cb8ca46213be 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/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 */