diff options
| author | Alexei Starovoitov <ast@kernel.org> | 2024-08-22 19:27:59 +0300 |
|---|---|---|
| committer | Alexei Starovoitov <ast@kernel.org> | 2024-08-22 19:48:44 +0300 |
| commit | 50c374c6d1a43db9444cb74cc09552c817db2a9b (patch) | |
| tree | b80c7befe92ef07799cf2dca3135afe56a6a646f /tools | |
| parent | d352eca2662734cdd5ef90df1f8bc28b9505e36f (diff) | |
| parent | 872cf28b8df9c5c3a1e71a88ee750df7c2513971 (diff) | |
| download | linux-50c374c6d1a43db9444cb74cc09552c817db2a9b.tar.xz | |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf
Cross-merge bpf fixes after downstream PR including
important fixes (from bpf-next point of view):
commit 41c24102af7b ("selftests/bpf: Filter out _GNU_SOURCE when compiling test_cpp")
commit fdad456cbcca ("bpf: Fix updating attached freplace prog in prog_array map")
No conflicts.
Adjacent changes in:
include/linux/bpf_verifier.h
kernel/bpf/verifier.c
tools/testing/selftests/bpf/Makefile
Link: https://lore.kernel.org/bpf/20240813234307.82773-1-alexei.starovoitov@gmail.com/
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Diffstat (limited to 'tools')
74 files changed, 3835 insertions, 1061 deletions
diff --git a/tools/arch/arm64/include/asm/cputype.h b/tools/arch/arm64/include/asm/cputype.h index 7b32b99023a2..5fd7caea4419 100644 --- a/tools/arch/arm64/include/asm/cputype.h +++ b/tools/arch/arm64/include/asm/cputype.h @@ -86,9 +86,14 @@ #define ARM_CPU_PART_CORTEX_X2 0xD48 #define ARM_CPU_PART_NEOVERSE_N2 0xD49 #define ARM_CPU_PART_CORTEX_A78C 0xD4B +#define ARM_CPU_PART_CORTEX_X1C 0xD4C +#define ARM_CPU_PART_CORTEX_X3 0xD4E #define ARM_CPU_PART_NEOVERSE_V2 0xD4F +#define ARM_CPU_PART_CORTEX_A720 0xD81 #define ARM_CPU_PART_CORTEX_X4 0xD82 #define ARM_CPU_PART_NEOVERSE_V3 0xD84 +#define ARM_CPU_PART_CORTEX_X925 0xD85 +#define ARM_CPU_PART_CORTEX_A725 0xD87 #define APM_CPU_PART_XGENE 0x000 #define APM_CPU_VAR_POTENZA 0x00 @@ -162,9 +167,14 @@ #define MIDR_CORTEX_X2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X2) #define MIDR_NEOVERSE_N2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N2) #define MIDR_CORTEX_A78C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78C) +#define MIDR_CORTEX_X1C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1C) +#define MIDR_CORTEX_X3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X3) #define MIDR_NEOVERSE_V2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V2) +#define MIDR_CORTEX_A720 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A720) #define MIDR_CORTEX_X4 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X4) #define MIDR_NEOVERSE_V3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V3) +#define MIDR_CORTEX_X925 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X925) +#define MIDR_CORTEX_A725 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A725) #define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX) #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX) #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX) diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h index 1691297a766a..eaeda001784e 100644 --- a/tools/arch/powerpc/include/uapi/asm/kvm.h +++ b/tools/arch/powerpc/include/uapi/asm/kvm.h @@ -645,6 +645,9 @@ struct kvm_ppc_cpu_char { #define KVM_REG_PPC_SIER3 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc3) #define KVM_REG_PPC_DAWR1 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc4) #define KVM_REG_PPC_DAWRX1 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc5) +#define KVM_REG_PPC_DEXCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc6) +#define KVM_REG_PPC_HASHKEYR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc7) +#define KVM_REG_PPC_HASHPKEYR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc8) /* Transactional Memory checkpointed state: * This is all GPRs, all VSX regs and a subset of SPRs diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 3c7434329661..dd4682857c12 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -18,170 +18,170 @@ /* * 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. + * in /proc/cpuinfo instead of the macro name. Otherwise, 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_FPU ( 0*32+ 0) /* "fpu" Onboard FPU */ +#define X86_FEATURE_VME ( 0*32+ 1) /* "vme" Virtual Mode Extensions */ +#define X86_FEATURE_DE ( 0*32+ 2) /* "de" Debugging Extensions */ +#define X86_FEATURE_PSE ( 0*32+ 3) /* "pse" Page Size Extensions */ +#define X86_FEATURE_TSC ( 0*32+ 4) /* "tsc" Time Stamp Counter */ +#define X86_FEATURE_MSR ( 0*32+ 5) /* "msr" Model-Specific Registers */ +#define X86_FEATURE_PAE ( 0*32+ 6) /* "pae" Physical Address Extensions */ +#define X86_FEATURE_MCE ( 0*32+ 7) /* "mce" Machine Check Exception */ +#define X86_FEATURE_CX8 ( 0*32+ 8) /* "cx8" CMPXCHG8 instruction */ +#define X86_FEATURE_APIC ( 0*32+ 9) /* "apic" Onboard APIC */ +#define X86_FEATURE_SEP ( 0*32+11) /* "sep" SYSENTER/SYSEXIT */ +#define X86_FEATURE_MTRR ( 0*32+12) /* "mtrr" Memory Type Range Registers */ +#define X86_FEATURE_PGE ( 0*32+13) /* "pge" Page Global Enable */ +#define X86_FEATURE_MCA ( 0*32+14) /* "mca" Machine Check Architecture */ +#define X86_FEATURE_CMOV ( 0*32+15) /* "cmov" CMOV instructions (plus FCMOVcc, FCOMI with FPU) */ +#define X86_FEATURE_PAT ( 0*32+16) /* "pat" Page Attribute Table */ +#define X86_FEATURE_PSE36 ( 0*32+17) /* "pse36" 36-bit PSEs */ +#define X86_FEATURE_PN ( 0*32+18) /* "pn" Processor serial number */ +#define X86_FEATURE_CLFLUSH ( 0*32+19) /* "clflush" 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_ACPI ( 0*32+22) /* "acpi" ACPI via MSR */ +#define X86_FEATURE_MMX ( 0*32+23) /* "mmx" Multimedia Extensions */ +#define X86_FEATURE_FXSR ( 0*32+24) /* "fxsr" 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_HT ( 0*32+28) /* "ht" 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 */ +#define X86_FEATURE_IA64 ( 0*32+30) /* "ia64" IA-64 processor */ +#define X86_FEATURE_PBE ( 0*32+31) /* "pbe" 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_SYSCALL ( 1*32+11) /* "syscall" SYSCALL/SYSRET */ +#define X86_FEATURE_MP ( 1*32+19) /* "mp" MP Capable */ +#define X86_FEATURE_NX ( 1*32+20) /* "nx" Execute Disable */ +#define X86_FEATURE_MMXEXT ( 1*32+22) /* "mmxext" AMD MMX extensions */ +#define X86_FEATURE_FXSR_OPT ( 1*32+25) /* "fxsr_opt" 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 */ +#define X86_FEATURE_RDTSCP ( 1*32+27) /* "rdtscp" RDTSCP */ +#define X86_FEATURE_LM ( 1*32+29) /* "lm" Long Mode (x86-64, 64-bit support) */ +#define X86_FEATURE_3DNOWEXT ( 1*32+30) /* "3dnowext" AMD 3DNow extensions */ +#define X86_FEATURE_3DNOW ( 1*32+31) /* "3dnow" 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) /* "recovery" CPU in recovery mode */ +#define X86_FEATURE_LONGRUN ( 2*32+ 1) /* "longrun" Longrun power control */ +#define X86_FEATURE_LRTI ( 2*32+ 3) /* "lrti" 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) */ -#define X86_FEATURE_K8 ( 3*32+ 4) /* "" Opteron, Athlon64 */ -#define X86_FEATURE_ZEN5 ( 3*32+ 5) /* "" CPU based on Zen5 microarchitecture */ -#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_AMD_LBR_V2 ( 3*32+17) /* AMD Last Branch Record Extension Version 2 */ -#define X86_FEATURE_CLEAR_CPU_BUF ( 3*32+18) /* "" Clear CPU buffers using VERW */ -#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_RAPL ( 3*32+29) /* AMD/Hygon RAPL interface */ -#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) /* "cxmmx" Cyrix MMX extensions */ +#define X86_FEATURE_K6_MTRR ( 3*32+ 1) /* "k6_mtrr" AMD K6 nonstandard MTRRs */ +#define X86_FEATURE_CYRIX_ARR ( 3*32+ 2) /* "cyrix_arr" Cyrix ARRs (= MTRRs) */ +#define X86_FEATURE_CENTAUR_MCR ( 3*32+ 3) /* "centaur_mcr" Centaur MCRs (= MTRRs) */ +#define X86_FEATURE_K8 ( 3*32+ 4) /* Opteron, Athlon64 */ +#define X86_FEATURE_ZEN5 ( 3*32+ 5) /* CPU based on Zen5 microarchitecture */ +#define X86_FEATURE_P3 ( 3*32+ 6) /* P3 */ +#define X86_FEATURE_P4 ( 3*32+ 7) /* P4 */ +#define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* "constant_tsc" TSC ticks at a constant rate */ +#define X86_FEATURE_UP ( 3*32+ 9) /* "up" SMP kernel running on UP */ +#define X86_FEATURE_ART ( 3*32+10) /* "art" Always running timer (ART) */ +#define X86_FEATURE_ARCH_PERFMON ( 3*32+11) /* "arch_perfmon" Intel Architectural PerfMon */ +#define X86_FEATURE_PEBS ( 3*32+12) /* "pebs" Precise-Event Based Sampling */ +#define X86_FEATURE_BTS ( 3*32+13) /* "bts" 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_good" REP microcode works well */ +#define X86_FEATURE_AMD_LBR_V2 ( 3*32+17) /* "amd_lbr_v2" AMD Last Branch Record Extension Version 2 */ +#define X86_FEATURE_CLEAR_CPU_BUF ( 3*32+18) /* Clear CPU buffers using VERW */ +#define X86_FEATURE_ACC_POWER ( 3*32+19) /* "acc_power" AMD Accumulated Power Mechanism */ +#define X86_FEATURE_NOPL ( 3*32+20) /* "nopl" The NOPL (0F 1F) instructions */ +#define X86_FEATURE_ALWAYS ( 3*32+21) /* Always-present feature */ +#define X86_FEATURE_XTOPOLOGY ( 3*32+22) /* "xtopology" CPU topology enum extensions */ +#define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* "tsc_reliable" TSC is known to be reliable */ +#define X86_FEATURE_NONSTOP_TSC ( 3*32+24) /* "nonstop_tsc" TSC does not stop in C states */ +#define X86_FEATURE_CPUID ( 3*32+25) /* "cpuid" CPU has CPUID instruction itself */ +#define X86_FEATURE_EXTD_APICID ( 3*32+26) /* "extd_apicid" Extended APICID (8 bits) */ +#define X86_FEATURE_AMD_DCM ( 3*32+27) /* "amd_dcm" AMD multi-node processor */ +#define X86_FEATURE_APERFMPERF ( 3*32+28) /* "aperfmperf" P-State hardware coordination feedback capability (APERF/MPERF MSRs) */ +#define X86_FEATURE_RAPL ( 3*32+29) /* "rapl" AMD/Hygon RAPL interface */ +#define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* "nonstop_tsc_s3" TSC doesn't stop in S3 state */ +#define X86_FEATURE_TSC_KNOWN_FREQ ( 3*32+31) /* "tsc_known_freq" 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_PCLMULQDQ ( 4*32+ 1) /* "pclmulqdq" PCLMULQDQ instruction */ +#define X86_FEATURE_DTES64 ( 4*32+ 2) /* "dtes64" 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_VMX ( 4*32+ 5) /* "vmx" Hardware virtualization */ +#define X86_FEATURE_SMX ( 4*32+ 6) /* "smx" Safer Mode eXtensions */ +#define X86_FEATURE_EST ( 4*32+ 7) /* "est" Enhanced SpeedStep */ +#define X86_FEATURE_TM2 ( 4*32+ 8) /* "tm2" Thermal Monitor 2 */ +#define X86_FEATURE_SSSE3 ( 4*32+ 9) /* "ssse3" Supplemental SSE-3 */ +#define X86_FEATURE_CID ( 4*32+10) /* "cid" Context ID */ +#define X86_FEATURE_SDBG ( 4*32+11) /* "sdbg" Silicon Debug */ +#define X86_FEATURE_FMA ( 4*32+12) /* "fma" Fused multiply-add */ +#define X86_FEATURE_CX16 ( 4*32+13) /* "cx16" CMPXCHG16B instruction */ +#define X86_FEATURE_XTPR ( 4*32+14) /* "xtpr" Send Task Priority Messages */ +#define X86_FEATURE_PDCM ( 4*32+15) /* "pdcm" Perf/Debug Capabilities MSR */ +#define X86_FEATURE_PCID ( 4*32+17) /* "pcid" Process Context Identifiers */ +#define X86_FEATURE_DCA ( 4*32+18) /* "dca" 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 */ +#define X86_FEATURE_X2APIC ( 4*32+21) /* "x2apic" X2APIC */ +#define X86_FEATURE_MOVBE ( 4*32+22) /* "movbe" MOVBE instruction */ +#define X86_FEATURE_POPCNT ( 4*32+23) /* "popcnt" POPCNT instruction */ +#define X86_FEATURE_TSC_DEADLINE_TIMER ( 4*32+24) /* "tsc_deadline_timer" TSC deadline timer */ +#define X86_FEATURE_AES ( 4*32+25) /* "aes" AES instructions */ +#define X86_FEATURE_XSAVE ( 4*32+26) /* "xsave" 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) /* "avx" Advanced Vector Extensions */ +#define X86_FEATURE_F16C ( 4*32+29) /* "f16c" 16-bit FP conversions */ +#define X86_FEATURE_RDRAND ( 4*32+30) /* "rdrand" RDRAND instruction */ +#define X86_FEATURE_HYPERVISOR ( 4*32+31) /* "hypervisor" 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_ACE2 ( 5*32+ 8) /* "ace2" Advanced Cryptography Engine v2 */ +#define X86_FEATURE_ACE2_EN ( 5*32+ 9) /* "ace2_en" ACE v2 enabled */ +#define X86_FEATURE_PHE ( 5*32+10) /* "phe" PadLock Hash Engine */ +#define X86_FEATURE_PHE_EN ( 5*32+11) /* "phe_en" PHE enabled */ +#define X86_FEATURE_PMM ( 5*32+12) /* "pmm" PadLock Montgomery Multiplier */ +#define X86_FEATURE_PMM_EN ( 5*32+13) /* "pmm_en" 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 instructions) */ +#define X86_FEATURE_LAHF_LM ( 6*32+ 0) /* "lahf_lm" LAHF/SAHF in long mode */ +#define X86_FEATURE_CMP_LEGACY ( 6*32+ 1) /* "cmp_legacy" If yes HyperThreading not valid */ +#define X86_FEATURE_SVM ( 6*32+ 2) /* "svm" Secure Virtual Machine */ +#define X86_FEATURE_EXTAPIC ( 6*32+ 3) /* "extapic" Extended APIC space */ +#define X86_FEATURE_CR8_LEGACY ( 6*32+ 4) /* "cr8_legacy" CR8 in 32-bit mode */ +#define X86_FEATURE_ABM ( 6*32+ 5) /* "abm" Advanced bit manipulation */ +#define X86_FEATURE_SSE4A ( 6*32+ 6) /* "sse4a" SSE-4A */ +#define X86_FEATURE_MISALIGNSSE ( 6*32+ 7) /* "misalignsse" Misaligned SSE mode */ +#define X86_FEATURE_3DNOWPREFETCH ( 6*32+ 8) /* "3dnowprefetch" 3DNow prefetch instructions */ +#define X86_FEATURE_OSVW ( 6*32+ 9) /* "osvw" OS Visible Workaround */ +#define X86_FEATURE_IBS ( 6*32+10) /* "ibs" Instruction Based Sampling */ +#define X86_FEATURE_XOP ( 6*32+11) /* "xop" Extended AVX instructions */ +#define X86_FEATURE_SKINIT ( 6*32+12) /* "skinit" SKINIT/STGI instructions */ +#define X86_FEATURE_WDT ( 6*32+13) /* "wdt" Watchdog timer */ +#define X86_FEATURE_LWP ( 6*32+15) /* "lwp" Light Weight Profiling */ +#define X86_FEATURE_FMA4 ( 6*32+16) /* "fma4" 4 operands MAC instructions */ +#define X86_FEATURE_TCE ( 6*32+17) /* "tce" Translation Cache Extension */ +#define X86_FEATURE_NODEID_MSR ( 6*32+19) /* "nodeid_msr" NodeId MSR */ +#define X86_FEATURE_TBM ( 6*32+21) /* "tbm" Trailing Bit Manipulations */ +#define X86_FEATURE_TOPOEXT ( 6*32+22) /* "topoext" Topology extensions CPUID leafs */ +#define X86_FEATURE_PERFCTR_CORE ( 6*32+23) /* "perfctr_core" Core performance counter extensions */ +#define X86_FEATURE_PERFCTR_NB ( 6*32+24) /* "perfctr_nb" NB performance counter extensions */ +#define X86_FEATURE_BPEXT ( 6*32+26) /* "bpext" Data breakpoint extension */ +#define X86_FEATURE_PTSC ( 6*32+27) /* "ptsc" Performance time-stamp counter */ +#define X86_FEATURE_PERFCTR_LLC ( 6*32+28) /* "perfctr_llc" Last Level Cache performance counter extensions */ +#define X86_FEATURE_MWAITX ( 6*32+29) /* "mwaitx" MWAIT extension (MONITORX/MWAITX instructions) */ /* * Auxiliary flags: Linux defined - For features scattered in various @@ -189,93 +189,93 @@ * * Reuse free bits when adding new feature flags! */ -#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_TDX_HOST_PLATFORM ( 7*32+ 7) /* Platform supports being a TDX host */ -#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ -#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ -#define X86_FEATURE_XCOMPACTED ( 7*32+10) /* "" Use compacted XSTATE (XSAVES or XSAVEC) */ -#define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */ -#define X86_FEATURE_KERNEL_IBRS ( 7*32+12) /* "" Set/clear IBRS on kernel entry/exit */ -#define X86_FEATURE_RSB_VMEXIT ( 7*32+13) /* "" Fill RSB on VM-Exit */ -#define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ -#define X86_FEATURE_CDP_L2 ( 7*32+15) /* Code and Data Prioritization L2 */ -#define X86_FEATURE_MSR_SPEC_CTRL ( 7*32+16) /* "" MSR SPEC_CTRL is implemented */ -#define X86_FEATURE_SSBD ( 7*32+17) /* Speculative Store Bypass Disable */ -#define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */ -#define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* "" Fill RSB on context switches */ -#define X86_FEATURE_PERFMON_V2 ( 7*32+20) /* AMD Performance Monitoring Version 2 */ -#define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */ -#define X86_FEATURE_USE_IBRS_FW ( 7*32+22) /* "" Use IBRS during runtime firmware calls */ -#define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE ( 7*32+23) /* "" Disable Speculative Store Bypass. */ -#define X86_FEATURE_LS_CFG_SSBD ( 7*32+24) /* "" AMD SSBD implementation via LS_CFG MSR */ -#define X86_FEATURE_IBRS ( 7*32+25) /* Indirect Branch Restricted Speculation */ -#define X86_FEATURE_IBPB ( 7*32+26) /* Indirect Branch Prediction Barrier */ -#define X86_FEATURE_STIBP ( 7*32+27) /* Single Thread Indirect Branch Predictors */ -#define X86_FEATURE_ZEN ( 7*32+28) /* "" Generic flag for all Zen and newer */ -#define X86_FEATURE_L1TF_PTEINV ( 7*32+29) /* "" L1TF workaround PTE inversion */ -#define X86_FEATURE_IBRS_ENHANCED ( 7*32+30) /* Enhanced IBRS */ -#define X86_FEATURE_MSR_IA32_FEAT_CTL ( 7*32+31) /* "" MSR IA32_FEAT_CTL configured */ +#define X86_FEATURE_RING3MWAIT ( 7*32+ 0) /* "ring3mwait" Ring 3 MONITOR/MWAIT instructions */ +#define X86_FEATURE_CPUID_FAULT ( 7*32+ 1) /* "cpuid_fault" Intel CPUID faulting */ +#define X86_FEATURE_CPB ( 7*32+ 2) /* "cpb" AMD Core Performance Boost */ +#define X86_FEATURE_EPB ( 7*32+ 3) /* "epb" IA32_ENERGY_PERF_BIAS support */ +#define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* "cat_l3" Cache Allocation Technology L3 */ +#define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* "cat_l2" Cache Allocation Technology L2 */ +#define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* "cdp_l3" Code and Data Prioritization L3 */ +#define X86_FEATURE_TDX_HOST_PLATFORM ( 7*32+ 7) /* "tdx_host_platform" Platform supports being a TDX host */ +#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* "hw_pstate" AMD HW-PState */ +#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* "proc_feedback" AMD ProcFeedbackInterface */ +#define X86_FEATURE_XCOMPACTED ( 7*32+10) /* Use compacted XSTATE (XSAVES or XSAVEC) */ +#define X86_FEATURE_PTI ( 7*32+11) /* "pti" Kernel Page Table Isolation enabled */ +#define X86_FEATURE_KERNEL_IBRS ( 7*32+12) /* Set/clear IBRS on kernel entry/exit */ +#define X86_FEATURE_RSB_VMEXIT ( 7*32+13) /* Fill RSB on VM-Exit */ +#define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* "intel_ppin" Intel Processor Inventory Number */ +#define X86_FEATURE_CDP_L2 ( 7*32+15) /* "cdp_l2" Code and Data Prioritization L2 */ +#define X86_FEATURE_MSR_SPEC_CTRL ( 7*32+16) /* MSR SPEC_CTRL is implemented */ +#define X86_FEATURE_SSBD ( 7*32+17) /* "ssbd" Speculative Store Bypass Disable */ +#define X86_FEATURE_MBA ( 7*32+18) /* "mba" Memory Bandwidth Allocation */ +#define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* Fill RSB on context switches */ +#define X86_FEATURE_PERFMON_V2 ( 7*32+20) /* "perfmon_v2" AMD Performance Monitoring Version 2 */ +#define X86_FEATURE_USE_IBPB ( 7*32+21) /* Indirect Branch Prediction Barrier enabled */ +#define X86_FEATURE_USE_IBRS_FW ( 7*32+22) /* Use IBRS during runtime firmware calls */ +#define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE ( 7*32+23) /* Disable Speculative Store Bypass. */ +#define X86_FEATURE_LS_CFG_SSBD ( 7*32+24) /* AMD SSBD implementation via LS_CFG MSR */ +#define X86_FEATURE_IBRS ( 7*32+25) /* "ibrs" Indirect Branch Restricted Speculation */ +#define X86_FEATURE_IBPB ( 7*32+26) /* "ibpb" Indirect Branch Prediction Barrier */ +#define X86_FEATURE_STIBP ( 7*32+27) /* "stibp" Single Thread Indirect Branch Predictors */ +#define X86_FEATURE_ZEN ( 7*32+28) /* Generic flag for all Zen and newer */ +#define X86_FEATURE_L1TF_PTEINV ( 7*32+29) /* L1TF workaround PTE inversion */ +#define X86_FEATURE_IBRS_ENHANCED ( 7*32+30) /* "ibrs_enhanced" Enhanced IBRS */ +#define X86_FEATURE_MSR_IA32_FEAT_CTL ( 7*32+31) /* MSR IA32_FEAT_CTL configured */ /* Virtualization flags: Linux defined, word 8 */ -#define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ -#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_TPR_SHADOW ( 8*32+ 0) /* "tpr_shadow" Intel TPR Shadow */ +#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 1) /* "flexpriority" Intel FlexPriority */ +#define X86_FEATURE_EPT ( 8*32+ 2) /* "ept" Intel Extended Page Table */ +#define X86_FEATURE_VPID ( 8*32+ 3) /* "vpid" 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_EPT_AD ( 8*32+17) /* Intel Extended Page Table access-dirty bit */ -#define X86_FEATURE_VMCALL ( 8*32+18) /* "" Hypervisor supports the VMCALL instruction */ -#define X86_FEATURE_VMW_VMMCALL ( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */ -#define X86_FEATURE_PVUNLOCK ( 8*32+20) /* "" PV unlock function */ -#define X86_FEATURE_VCPUPREEMPT ( 8*32+21) /* "" PV vcpu_is_preempted function */ -#define X86_FEATURE_TDX_GUEST ( 8*32+22) /* Intel Trust Domain Extensions Guest */ +#define X86_FEATURE_VMMCALL ( 8*32+15) /* "vmmcall" Prefer VMMCALL to VMCALL */ +#define X86_FEATURE_XENPV ( 8*32+16) /* Xen paravirtual guest */ +#define X86_FEATURE_EPT_AD ( 8*32+17) /* "ept_ad" Intel Extended Page Table access-dirty bit */ +#define X86_FEATURE_VMCALL ( 8*32+18) /* Hypervisor supports the VMCALL instruction */ +#define X86_FEATURE_VMW_VMMCALL ( 8*32+19) /* VMware prefers VMMCALL hypercall instruction */ +#define X86_FEATURE_PVUNLOCK ( 8*32+20) /* PV unlock function */ +#define X86_FEATURE_VCPUPREEMPT ( 8*32+21) /* PV vcpu_is_preempted function */ +#define X86_FEATURE_TDX_GUEST ( 8*32+22) /* "tdx_guest" Intel Trust Domain Extensions Guest */ /* 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_SGX ( 9*32+ 2) /* Software Guard Extensions */ -#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_FDP_EXCPTN_ONLY ( 9*32+ 6) /* "" FPU data pointer updated only on x87 exceptions */ -#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_ZERO_FCS_FDS ( 9*32+13) /* "" Zero out FPU CS and FPU DS */ -#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_INTEL_PT ( 9*32+25) /* Intel Processor Trace */ -#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 */ +#define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* "fsgsbase" RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/ +#define X86_FEATURE_TSC_ADJUST ( 9*32+ 1) /* "tsc_adjust" TSC adjustment MSR 0x3B */ +#define X86_FEATURE_SGX ( 9*32+ 2) /* "sgx" Software Guard Extensions */ +#define X86_FEATURE_BMI1 ( 9*32+ 3) /* "bmi1" 1st group bit manipulation extensions */ +#define X86_FEATURE_HLE ( 9*32+ 4) /* "hle" Hardware Lock Elision */ +#define X86_FEATURE_AVX2 ( 9*32+ 5) /* "avx2" AVX2 instructions */ +#define X86_FEATURE_FDP_EXCPTN_ONLY ( 9*32+ 6) /* FPU data pointer updated only on x87 exceptions */ +#define X86_FEATURE_SMEP ( 9*32+ 7) /* "smep" Supervisor Mode Execution Protection */ +#define X86_FEATURE_BMI2 ( 9*32+ 8) /* "bmi2" 2nd group bit manipulation extensions */ +#define X86_FEATURE_ERMS ( 9*32+ 9) /* "erms" Enhanced REP MOVSB/STOSB instructions */ +#define X86_FEATURE_INVPCID ( 9*32+10) /* "invpcid" Invalidate Processor Context ID */ +#define X86_FEATURE_RTM ( 9*32+11) /* "rtm" Restricted Transactional Memory */ +#define X86_FEATURE_CQM ( 9*32+12) /* "cqm" Cache QoS Monitoring */ +#define X86_FEATURE_ZERO_FCS_FDS ( 9*32+13) /* Zero out FPU CS and FPU DS */ +#define X86_FEATURE_MPX ( 9*32+14) /* "mpx" Memory Protection Extension */ +#define X86_FEATURE_RDT_A ( 9*32+15) /* "rdt_a" Resource Director Technology Allocation */ +#define X86_FEATURE_AVX512F ( 9*32+16) /* "avx512f" AVX-512 Foundation */ +#define X86_FEATURE_AVX512DQ ( 9*32+17) /* "avx512dq" AVX-512 DQ (Double/Quad granular) Instructions */ +#define X86_FEATURE_RDSEED ( 9*32+18) /* "rdseed" RDSEED instruction */ +#define X86_FEATURE_ADX ( 9*32+19) /* "adx" ADCX and ADOX instructions */ +#define X86_FEATURE_SMAP ( 9*32+20) /* "smap" Supervisor Mode Access Prevention */ +#define X86_FEATURE_AVX512IFMA ( 9*32+21) /* "avx512ifma" AVX-512 Integer Fused Multiply-Add instructions */ +#define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* "clflushopt" CLFLUSHOPT instruction */ +#define X86_FEATURE_CLWB ( 9*32+24) /* "clwb" CLWB instruction */ +#define X86_FEATURE_INTEL_PT ( 9*32+25) /* "intel_pt" Intel Processor Trace */ +#define X86_FEATURE_AVX512PF ( 9*32+26) /* "avx512pf" AVX-512 Prefetch */ +#define X86_FEATURE_AVX512ER ( 9*32+27) /* "avx512er" AVX-512 Exponential and Reciprocal */ +#define X86_FEATURE_AVX512CD ( 9*32+28) /* "avx512cd" AVX-512 Conflict Detection */ +#define X86_FEATURE_SHA_NI ( 9*32+29) /* "sha_ni" SHA1/SHA256 Instruction Extensions */ +#define X86_FEATURE_AVX512BW ( 9*32+30) /* "avx512bw" AVX-512 BW (Byte/Word granular) Instructions */ +#define X86_FEATURE_AVX512VL ( 9*32+31) /* "avx512vl" 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 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 */ -#define X86_FEATURE_XFD (10*32+ 4) /* "" eXtended Feature Disabling */ +#define X86_FEATURE_XSAVEOPT (10*32+ 0) /* "xsaveopt" XSAVEOPT instruction */ +#define X86_FEATURE_XSAVEC (10*32+ 1) /* "xsavec" XSAVEC instruction */ +#define X86_FEATURE_XGETBV1 (10*32+ 2) /* "xgetbv1" XGETBV with ECX = 1 instruction */ +#define X86_FEATURE_XSAVES (10*32+ 3) /* "xsaves" XSAVES/XRSTORS instructions */ +#define X86_FEATURE_XFD (10*32+ 4) /* eXtended Feature Disabling */ /* * Extended auxiliary flags: Linux defined - for features scattered in various @@ -283,181 +283,183 @@ * * Reuse free bits when adding new feature flags! */ -#define X86_FEATURE_CQM_LLC (11*32+ 0) /* LLC QoS if 1 */ -#define X86_FEATURE_CQM_OCCUP_LLC (11*32+ 1) /* LLC occupancy monitoring */ -#define X86_FEATURE_CQM_MBM_TOTAL (11*32+ 2) /* LLC Total MBM monitoring */ -#define X86_FEATURE_CQM_MBM_LOCAL (11*32+ 3) /* LLC Local MBM monitoring */ -#define X86_FEATURE_FENCE_SWAPGS_USER (11*32+ 4) /* "" LFENCE in user entry SWAPGS path */ -#define X86_FEATURE_FENCE_SWAPGS_KERNEL (11*32+ 5) /* "" LFENCE in kernel entry SWAPGS path */ -#define X86_FEATURE_SPLIT_LOCK_DETECT (11*32+ 6) /* #AC for split lock */ -#define X86_FEATURE_PER_THREAD_MBA (11*32+ 7) /* "" Per-thread Memory Bandwidth Allocation */ -#define X86_FEATURE_SGX1 (11*32+ 8) /* "" Basic SGX */ -#define X86_FEATURE_SGX2 (11*32+ 9) /* "" SGX Enclave Dynamic Memory Management (EDMM) */ -#define X86_FEATURE_ENTRY_IBPB (11*32+10) /* "" Issue an IBPB on kernel entry */ -#define X86_FEATURE_RRSBA_CTRL (11*32+11) /* "" RET prediction control */ -#define X86_FEATURE_RETPOLINE (11*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */ -#define X86_FEATURE_RETPOLINE_LFENCE (11*32+13) /* "" Use LFENCE for Spectre variant 2 */ -#define X86_FEATURE_RETHUNK (11*32+14) /* "" Use REturn THUNK */ -#define X86_FEATURE_UNRET (11*32+15) /* "" AMD BTB untrain return */ -#define X86_FEATURE_USE_IBPB_FW (11*32+16) /* "" Use IBPB during runtime firmware calls */ -#define X86_FEATURE_RSB_VMEXIT_LITE (11*32+17) /* "" Fill RSB on VM exit when EIBRS is enabled */ -#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 */ -#define X86_FEATURE_USER_SHSTK (11*32+23) /* Shadow stack support for user mode applications */ -#define X86_FEATURE_SRSO (11*32+24) /* "" AMD BTB untrain RETs */ -#define X86_FEATURE_SRSO_ALIAS (11*32+25) /* "" AMD BTB untrain RETs through aliasing */ -#define X86_FEATURE_IBPB_ON_VMEXIT (11*32+26) /* "" Issue an IBPB only on VMEXIT */ -#define X86_FEATURE_APIC_MSRS_FENCE (11*32+27) /* "" IA32_TSC_DEADLINE and X2APIC MSRs need fencing */ -#define X86_FEATURE_ZEN2 (11*32+28) /* "" CPU based on Zen2 microarchitecture */ -#define X86_FEATURE_ZEN3 (11*32+29) /* "" CPU based on Zen3 microarchitecture */ -#define X86_FEATURE_ZEN4 (11*32+30) /* "" CPU based on Zen4 microarchitecture */ -#define X86_FEATURE_ZEN1 (11*32+31) /* "" CPU based on Zen1 microarchitecture */ +#define X86_FEATURE_CQM_LLC (11*32+ 0) /* "cqm_llc" LLC QoS if 1 */ +#define X86_FEATURE_CQM_OCCUP_LLC (11*32+ 1) /* "cqm_occup_llc" LLC occupancy monitoring */ +#define X86_FEATURE_CQM_MBM_TOTAL (11*32+ 2) /* "cqm_mbm_total" LLC Total MBM monitoring */ +#define X86_FEATURE_CQM_MBM_LOCAL (11*32+ 3) /* "cqm_mbm_local" LLC Local MBM monitoring */ +#define X86_FEATURE_FENCE_SWAPGS_USER (11*32+ 4) /* LFENCE in user entry SWAPGS path */ +#define X86_FEATURE_FENCE_SWAPGS_KERNEL (11*32+ 5) /* LFENCE in kernel entry SWAPGS path */ +#define X86_FEATURE_SPLIT_LOCK_DETECT (11*32+ 6) /* "split_lock_detect" #AC for split lock */ +#define X86_FEATURE_PER_THREAD_MBA (11*32+ 7) /* Per-thread Memory Bandwidth Allocation */ +#define X86_FEATURE_SGX1 (11*32+ 8) /* Basic SGX */ +#define X86_FEATURE_SGX2 (11*32+ 9) /* SGX Enclave Dynamic Memory Management (EDMM) */ +#define X86_FEATURE_ENTRY_IBPB (11*32+10) /* Issue an IBPB on kernel entry */ +#define X86_FEATURE_RRSBA_CTRL (11*32+11) /* RET prediction control */ +#define X86_FEATURE_RETPOLINE (11*32+12) /* Generic Retpoline mitigation for Spectre variant 2 */ +#define X86_FEATURE_RETPOLINE_LFENCE (11*32+13) /* Use LFENCE for Spectre variant 2 */ +#define X86_FEATURE_RETHUNK (11*32+14) /* Use REturn THUNK */ +#define X86_FEATURE_UNRET (11*32+15) /* AMD BTB untrain return */ +#define X86_FEATURE_USE_IBPB_FW (11*32+16) /* Use IBPB during runtime firmware calls */ +#define X86_FEATURE_RSB_VMEXIT_LITE (11*32+17) /* Fill RSB on VM exit when EIBRS is enabled */ +#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 */ +#define X86_FEATURE_USER_SHSTK (11*32+23) /* "user_shstk" Shadow stack support for user mode applications */ +#define X86_FEATURE_SRSO (11*32+24) /* AMD BTB untrain RETs */ +#define X86_FEATURE_SRSO_ALIAS (11*32+25) /* AMD BTB untrain RETs through aliasing */ +#define X86_FEATURE_IBPB_ON_VMEXIT (11*32+26) /* Issue an IBPB only on VMEXIT */ +#define X86_FEATURE_APIC_MSRS_FENCE (11*32+27) /* IA32_TSC_DEADLINE and X2APIC MSRs need fencing */ +#define X86_FEATURE_ZEN2 (11*32+28) /* CPU based on Zen2 microarchitecture */ +#define X86_FEATURE_ZEN3 (11*32+29) /* CPU based on Zen3 microarchitecture */ +#define X86_FEATURE_ZEN4 (11*32+30) /* CPU based on Zen4 microarchitecture */ +#define X86_FEATURE_ZEN1 (11*32+31) /* CPU based on Zen1 microarchitecture */ /* 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_FRED (12*32+17) /* Flexible Return and Event Delivery */ -#define X86_FEATURE_LKGS (12*32+18) /* "" Load "kernel" (userspace) GS */ -#define X86_FEATURE_WRMSRNS (12*32+19) /* "" Non-serializing WRMSR */ -#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 */ +#define X86_FEATURE_AVX_VNNI (12*32+ 4) /* "avx_vnni" AVX VNNI instructions */ +#define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* "avx512_bf16" 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_FRED (12*32+17) /* "fred" Flexible Return and Event Delivery */ +#define X86_FEATURE_LKGS (12*32+18) /* Load "kernel" (userspace) GS */ +#define X86_FEATURE_WRMSRNS (12*32+19) /* Non-serializing WRMSR */ +#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) /* "lam" Linear Address Masking */ /* 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 */ -#define X86_FEATURE_XSAVEERPTR (13*32+ 2) /* Always save/restore FP error pointers */ -#define X86_FEATURE_RDPRU (13*32+ 4) /* Read processor register at user level */ -#define X86_FEATURE_WBNOINVD (13*32+ 9) /* WBNOINVD instruction */ -#define X86_FEATURE_AMD_IBPB (13*32+12) /* "" Indirect Branch Prediction Barrier */ -#define X86_FEATURE_AMD_IBRS (13*32+14) /* "" Indirect Branch Restricted Speculation */ -#define X86_FEATURE_AMD_STIBP (13*32+15) /* "" Single Thread Indirect Branch Predictors */ -#define X86_FEATURE_AMD_STIBP_ALWAYS_ON (13*32+17) /* "" Single Thread Indirect Branch Predictors always-on preferred */ -#define X86_FEATURE_AMD_PPIN (13*32+23) /* Protected Processor Inventory Number */ -#define X86_FEATURE_AMD_SSBD (13*32+24) /* "" Speculative Store Bypass Disable */ -#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 */ +#define X86_FEATURE_CLZERO (13*32+ 0) /* "clzero" CLZERO instruction */ +#define X86_FEATURE_IRPERF (13*32+ 1) /* "irperf" Instructions Retired Count */ +#define X86_FEATURE_XSAVEERPTR (13*32+ 2) /* "xsaveerptr" Always save/restore FP error pointers */ +#define X86_FEATURE_RDPRU (13*32+ 4) /* "rdpru" Read processor register at user level */ +#define X86_FEATURE_WBNOINVD (13*32+ 9) /* "wbnoinvd" WBNOINVD instruction */ +#define X86_FEATURE_AMD_IBPB (13*32+12) /* Indirect Branch Prediction Barrier */ +#define X86_FEATURE_AMD_IBRS (13*32+14) /* Indirect Branch Restricted Speculation */ +#define X86_FEATURE_AMD_STIBP (13*32+15) /* Single Thread Indirect Branch Predictors */ +#define X86_FEATURE_AMD_STIBP_ALWAYS_ON (13*32+17) /* Single Thread Indirect Branch Predictors always-on preferred */ +#define X86_FEATURE_AMD_PPIN (13*32+23) /* "amd_ppin" Protected Processor Inventory Number */ +#define X86_FEATURE_AMD_SSBD (13*32+24) /* Speculative Store Bypass Disable */ +#define X86_FEATURE_VIRT_SSBD (13*32+25) /* "virt_ssbd" 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) /* "cppc" 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) /* "brs" Branch Sampling available */ /* 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 */ -#define X86_FEATURE_HFI (14*32+19) /* Hardware Feedback Interface */ +#define X86_FEATURE_DTHERM (14*32+ 0) /* "dtherm" Digital Thermal Sensor */ +#define X86_FEATURE_IDA (14*32+ 1) /* "ida" Intel Dynamic Acceleration */ +#define X86_FEATURE_ARAT (14*32+ 2) /* "arat" Always Running APIC Timer */ +#define X86_FEATURE_PLN (14*32+ 4) /* "pln" Intel Power Limit Notification */ +#define X86_FEATURE_PTS (14*32+ 6) /* "pts" Intel Package Thermal Status */ +#define X86_FEATURE_HWP (14*32+ 7) /* "hwp" Intel Hardware P-states */ +#define X86_FEATURE_HWP_NOTIFY (14*32+ 8) /* "hwp_notify" HWP Notification */ +#define X86_FEATURE_HWP_ACT_WINDOW (14*32+ 9) /* "hwp_act_window" HWP Activity Window */ +#define X86_FEATURE_HWP_EPP (14*32+10) /* "hwp_epp" HWP Energy Perf. Preference */ +#define X86_FEATURE_HWP_PKG_REQ (14*32+11) /* "hwp_pkg_req" HWP Package Level Request */ +#define X86_FEATURE_HWP_HIGHEST_PERF_CHANGE (14*32+15) /* HWP Highest perf change */ +#define X86_FEATURE_HFI (14*32+19) /* "hfi" Hardware Feedback Interface */ /* 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_NPT (15*32+ 0) /* "npt" Nested Page Table support */ +#define X86_FEATURE_LBRV (15*32+ 1) /* "lbrv" 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 */ -#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 */ +#define X86_FEATURE_FLUSHBYASID (15*32+ 6) /* "flushbyasid" Flush-by-ASID support */ +#define X86_FEATURE_DECODEASSISTS (15*32+ 7) /* "decodeassists" Decode Assists support */ +#define X86_FEATURE_PAUSEFILTER (15*32+10) /* "pausefilter" Filtered pause intercept */ +#define X86_FEATURE_PFTHRESHOLD (15*32+12) /* "pfthreshold" Pause filter threshold */ +#define X86_FEATURE_AVIC (15*32+13) /* "avic" Virtual Interrupt Controller */ +#define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* "v_vmsave_vmload" Virtual VMSAVE VMLOAD */ +#define X86_FEATURE_VGIF (15*32+16) /* "vgif" Virtual GIF */ +#define X86_FEATURE_X2AVIC (15*32+18) /* "x2avic" Virtual x2apic */ +#define X86_FEATURE_V_SPEC_CTRL (15*32+20) /* "v_spec_ctrl" Virtual SPEC_CTRL */ +#define X86_FEATURE_VNMI (15*32+25) /* "vnmi" 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 */ -#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_WAITPKG (16*32+ 5) /* UMONITOR/UMWAIT/TPAUSE Instructions */ -#define X86_FEATURE_AVX512_VBMI2 (16*32+ 6) /* Additional AVX512 Vector Bit Manipulation Instructions */ -#define X86_FEATURE_SHSTK (16*32+ 7) /* "" Shadow stack */ -#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_TME (16*32+13) /* Intel Total Memory Encryption */ -#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 */ -#define X86_FEATURE_BUS_LOCK_DETECT (16*32+24) /* Bus Lock detect */ -#define X86_FEATURE_CLDEMOTE (16*32+25) /* CLDEMOTE instruction */ -#define X86_FEATURE_MOVDIRI (16*32+27) /* MOVDIRI instruction */ -#define X86_FEATURE_MOVDIR64B (16*32+28) /* MOVDIR64B instruction */ -#define X86_FEATURE_ENQCMD (16*32+29) /* ENQCMD and ENQCMDS instructions */ -#define X86_FEATURE_SGX_LC (16*32+30) /* Software Guard Extensions Launch Control */ +#define X86_FEATURE_AVX512VBMI (16*32+ 1) /* "avx512vbmi" AVX512 Vector Bit Manipulation instructions*/ +#define X86_FEATURE_UMIP (16*32+ 2) /* "umip" User Mode Instruction Protection */ +#define X86_FEATURE_PKU (16*32+ 3) /* "pku" Protection Keys for Userspace */ +#define X86_FEATURE_OSPKE (16*32+ 4) /* "ospke" OS Protection Keys Enable */ +#define X86_FEATURE_WAITPKG (16*32+ 5) /* "waitpkg" UMONITOR/UMWAIT/TPAUSE Instructions */ +#define X86_FEATURE_AVX512_VBMI2 (16*32+ 6) /* "avx512_vbmi2" Additional AVX512 Vector Bit Manipulation Instructions */ +#define X86_FEATURE_SHSTK (16*32+ 7) /* Shadow stack */ +#define X86_FEATURE_GFNI (16*32+ 8) /* "gfni" Galois Field New Instructions */ +#define X86_FEATURE_VAES (16*32+ 9) /* "vaes" Vector AES */ +#define X86_FEATURE_VPCLMULQDQ (16*32+10) /* "vpclmulqdq" Carry-Less Multiplication Double Quadword */ +#define X86_FEATURE_AVX512_VNNI (16*32+11) /* "avx512_vnni" Vector Neural Network Instructions */ +#define X86_FEATURE_AVX512_BITALG (16*32+12) /* "avx512_bitalg" Support for VPOPCNT[B,W] and VPSHUF-BITQMB instructions */ +#define X86_FEATURE_TME (16*32+13) /* "tme" Intel Total Memory Encryption */ +#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* "avx512_vpopcntdq" POPCNT for vectors of DW/QW */ +#define X86_FEATURE_LA57 (16*32+16) /* "la57" 5-level page tables */ +#define X86_FEATURE_RDPID (16*32+22) /* "rdpid" RDPID instruction */ +#define X86_FEATURE_BUS_LOCK_DETECT (16*32+24) /* "bus_lock_detect" Bus Lock detect */ +#define X86_FEATURE_CLDEMOTE (16*32+25) /* "cldemote" CLDEMOTE instruction */ +#define X86_FEATURE_MOVDIRI (16*32+27) /* "movdiri" MOVDIRI instruction */ +#define X86_FEATURE_MOVDIR64B (16*32+28) /* "movdir64b" MOVDIR64B instruction */ +#define X86_FEATURE_ENQCMD (16*32+29) /* "enqcmd" ENQCMD and ENQCMDS instructions */ +#define X86_FEATURE_SGX_LC (16*32+30) /* "sgx_lc" Software Guard Extensions Launch Control */ /* 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 */ +#define X86_FEATURE_OVERFLOW_RECOV (17*32+ 0) /* "overflow_recov" MCA overflow recovery support */ +#define X86_FEATURE_SUCCOR (17*32+ 1) /* "succor" Uncorrectable error containment and recovery */ +#define X86_FEATURE_SMCA (17*32+ 3) /* "smca" Scalable MCA */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */ -#define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */ -#define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */ -#define X86_FEATURE_FSRM (18*32+ 4) /* Fast Short Rep Mov */ -#define X86_FEATURE_AVX512_VP2INTERSECT (18*32+ 8) /* AVX-512 Intersect for D/Q */ -#define X86_FEATURE_SRBDS_CTRL (18*32+ 9) /* "" SRBDS mitigation MSR available */ -#define X86_FEATURE_MD_CLEAR (18*32+10) /* VERW clears CPU buffers */ -#define X86_FEATURE_RTM_ALWAYS_ABORT (18*32+11) /* "" RTM transaction always aborts */ -#define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */ -#define X86_FEATURE_SERIALIZE (18*32+14) /* SERIALIZE instruction */ -#define X86_FEATURE_HYBRID_CPU (18*32+15) /* "" This part has CPUs of more than one type */ -#define X86_FEATURE_TSXLDTRK (18*32+16) /* TSX Suspend Load Address Tracking */ -#define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */ -#define X86_FEATURE_ARCH_LBR (18*32+19) /* Intel ARCH LBR */ -#define X86_FEATURE_IBT (18*32+20) /* Indirect Branch Tracking */ -#define X86_FEATURE_AMX_BF16 (18*32+22) /* AMX bf16 Support */ -#define X86_FEATURE_AVX512_FP16 (18*32+23) /* AVX512 FP16 */ -#define X86_FEATURE_AMX_TILE (18*32+24) /* AMX tile Support */ -#define X86_FEATURE_AMX_INT8 (18*32+25) /* AMX int8 Support */ -#define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */ -#define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */ -#define X86_FEATURE_FLUSH_L1D (18*32+28) /* Flush L1D cache */ -#define X86_FEATURE_ARCH_CAPABILITIES (18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */ -#define X86_FEATURE_CORE_CAPABILITIES (18*32+30) /* "" IA32_CORE_CAPABILITIES MSR */ -#define X86_FEATURE_SPEC_CTRL_SSBD (18*32+31) /* "" Speculative Store Bypass Disable */ +#define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* "avx512_4vnniw" AVX-512 Neural Network Instructions */ +#define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* "avx512_4fmaps" AVX-512 Multiply Accumulation Single precision */ +#define X86_FEATURE_FSRM (18*32+ 4) /* "fsrm" Fast Short Rep Mov */ +#define X86_FEATURE_AVX512_VP2INTERSECT (18*32+ 8) /* "avx512_vp2intersect" AVX-512 Intersect for D/Q */ +#define X86_FEATURE_SRBDS_CTRL (18*32+ 9) /* SRBDS mitigation MSR available */ +#define X86_FEATURE_MD_CLEAR (18*32+10) /* "md_clear" VERW clears CPU buffers */ +#define X86_FEATURE_RTM_ALWAYS_ABORT (18*32+11) /* RTM transaction always aborts */ +#define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* TSX_FORCE_ABORT */ +#define X86_FEATURE_SERIALIZE (18*32+14) /* "serialize" SERIALIZE instruction */ +#define X86_FEATURE_HYBRID_CPU (18*32+15) /* This part has CPUs of more than one type */ +#define X86_FEATURE_TSXLDTRK (18*32+16) /* "tsxldtrk" TSX Suspend Load Address Tracking */ +#define X86_FEATURE_PCONFIG (18*32+18) /* "pconfig" Intel PCONFIG */ +#define X86_FEATURE_ARCH_LBR (18*32+19) /* "arch_lbr" Intel ARCH LBR */ +#define X86_FEATURE_IBT (18*32+20) /* "ibt" Indirect Branch Tracking */ +#define X86_FEATURE_AMX_BF16 (18*32+22) /* "amx_bf16" AMX bf16 Support */ +#define X86_FEATURE_AVX512_FP16 (18*32+23) /* "avx512_fp16" AVX512 FP16 */ +#define X86_FEATURE_AMX_TILE (18*32+24) /* "amx_tile" AMX tile Support */ +#define X86_FEATURE_AMX_INT8 (18*32+25) /* "amx_int8" AMX int8 Support */ +#define X86_FEATURE_SPEC_CTRL (18*32+26) /* Speculation Control (IBRS + IBPB) */ +#define X86_FEATURE_INTEL_STIBP (18*32+27) /* Single Thread Indirect Branch Predictors */ +#define X86_FEATURE_FLUSH_L1D (18*32+28) /* "flush_l1d" Flush L1D cache */ +#define X86_FEATURE_ARCH_CAPABILITIES (18*32+29) /* "arch_capabilities" IA32_ARCH_CAPABILITIES MSR (Intel) */ +#define X86_FEATURE_CORE_CAPABILITIES (18*32+30) /* IA32_CORE_CAPABILITIES MSR */ +#define X86_FEATURE_SPEC_CTRL_SSBD (18*32+31) /* Speculative Store Bypass Disable */ /* AMD-defined memory encryption features, CPUID level 0x8000001f (EAX), word 19 */ -#define X86_FEATURE_SME (19*32+ 0) /* AMD Secure Memory Encryption */ -#define X86_FEATURE_SEV (19*32+ 1) /* AMD Secure Encrypted Virtualization */ -#define X86_FEATURE_VM_PAGE_FLUSH (19*32+ 2) /* "" VM Page Flush MSR is supported */ -#define X86_FEATURE_SEV_ES (19*32+ 3) /* AMD Secure Encrypted Virtualization - Encrypted State */ -#define X86_FEATURE_SEV_SNP (19*32+ 4) /* AMD Secure Encrypted Virtualization - Secure Nested Paging */ -#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 */ -#define X86_FEATURE_DEBUG_SWAP (19*32+14) /* AMD SEV-ES full debug state swap support */ +#define X86_FEATURE_SME (19*32+ 0) /* "sme" AMD Secure Memory Encryption */ +#define X86_FEATURE_SEV (19*32+ 1) /* "sev" AMD Secure Encrypted Virtualization */ +#define X86_FEATURE_VM_PAGE_FLUSH (19*32+ 2) /* VM Page Flush MSR is supported */ +#define X86_FEATURE_SEV_ES (19*32+ 3) /* "sev_es" AMD Secure Encrypted Virtualization - Encrypted State */ +#define X86_FEATURE_SEV_SNP (19*32+ 4) /* "sev_snp" AMD Secure Encrypted Virtualization - Secure Nested Paging */ +#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 */ +#define X86_FEATURE_DEBUG_SWAP (19*32+14) /* "debug_swap" AMD SEV-ES full debug state swap support */ +#define X86_FEATURE_SVSM (19*32+28) /* "svsm" SVSM present */ /* 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_WRMSR_XX_BASE_NS (20*32+ 1) /* "" WRMSR to {FS,GS,KERNEL_GS}_BASE is non-serializing */ -#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 */ +#define X86_FEATURE_NO_NESTED_DATA_BP (20*32+ 0) /* No Nested Data Breakpoints */ +#define X86_FEATURE_WRMSR_XX_BASE_NS (20*32+ 1) /* WRMSR to {FS,GS,KERNEL_GS}_BASE is non-serializing */ +#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 */ -#define X86_FEATURE_SBPB (20*32+27) /* "" Selective Branch Prediction Barrier */ -#define X86_FEATURE_IBPB_BRTYPE (20*32+28) /* "" MSR_PRED_CMD[IBPB] flushes all branch type predictions */ -#define X86_FEATURE_SRSO_NO (20*32+29) /* "" CPU is not affected by SRSO */ +#define X86_FEATURE_SBPB (20*32+27) /* Selective Branch Prediction Barrier */ +#define X86_FEATURE_IBPB_BRTYPE (20*32+28) /* MSR_PRED_CMD[IBPB] flushes all branch type predictions */ +#define X86_FEATURE_SRSO_NO (20*32+29) /* CPU is not affected by SRSO */ /* * Extended auxiliary flags: Linux defined - for features scattered in various @@ -465,59 +467,60 @@ * * Reuse free bits when adding new feature flags! */ -#define X86_FEATURE_AMD_LBR_PMC_FREEZE (21*32+ 0) /* AMD LBR and PMC Freeze */ -#define X86_FEATURE_CLEAR_BHB_LOOP (21*32+ 1) /* "" Clear branch history at syscall entry using SW loop */ -#define X86_FEATURE_BHI_CTRL (21*32+ 2) /* "" BHI_DIS_S HW control available */ -#define X86_FEATURE_CLEAR_BHB_HW (21*32+ 3) /* "" BHI_DIS_S HW control enabled */ -#define X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT (21*32+ 4) /* "" Clear branch history at vmexit using SW loop */ +#define X86_FEATURE_AMD_LBR_PMC_FREEZE (21*32+ 0) /* "amd_lbr_pmc_freeze" AMD LBR and PMC Freeze */ +#define X86_FEATURE_CLEAR_BHB_LOOP (21*32+ 1) /* Clear branch history at syscall entry using SW loop */ +#define X86_FEATURE_BHI_CTRL (21*32+ 2) /* BHI_DIS_S HW control available */ +#define X86_FEATURE_CLEAR_BHB_HW (21*32+ 3) /* BHI_DIS_S HW control enabled */ +#define X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT (21*32+ 4) /* Clear branch history at vmexit using SW loop */ +#define X86_FEATURE_FAST_CPPC (21*32 + 5) /* AMD Fast CPPC */ /* * BUG word(s) */ #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_F00F X86_BUG(0) /* "f00f" Intel F00F */ +#define X86_BUG_FDIV X86_BUG(1) /* "fdiv" FPU FDIV */ +#define X86_BUG_COMA X86_BUG(2) /* "coma" 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_11AP X86_BUG(5) /* "11ap" Bad local APIC aka 11AP */ +#define X86_BUG_FXSAVE_LEAK X86_BUG(6) /* "fxsave_leak" FXSAVE leaks FOP/FIP/FOP */ +#define X86_BUG_CLFLUSH_MONITOR X86_BUG(7) /* "clflush_monitor" AAI65, CLFLUSH required before MONITOR */ +#define X86_BUG_SYSRET_SS_ATTRS X86_BUG(8) /* "sysret_ss_attrs" 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_CPU_MELTDOWN X86_BUG(14) /* CPU is affected by meltdown attack and needs kernel page table isolation */ -#define X86_BUG_SPECTRE_V1 X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */ -#define X86_BUG_SPECTRE_V2 X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */ -#define X86_BUG_SPEC_STORE_BYPASS X86_BUG(17) /* CPU is affected by speculative store bypass attack */ -#define X86_BUG_L1TF X86_BUG(18) /* CPU is affected by L1 Terminal Fault */ -#define X86_BUG_MDS X86_BUG(19) /* CPU is affected by Microarchitectural data sampling */ -#define X86_BUG_MSBDS_ONLY X86_BUG(20) /* CPU is only affected by the MSDBS variant of BUG_MDS */ -#define X86_BUG_SWAPGS X86_BUG(21) /* CPU is affected by speculation through SWAPGS */ -#define X86_BUG_TAA X86_BUG(22) /* CPU is affected by TSX Async Abort(TAA) */ -#define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */ -#define X86_BUG_SRBDS X86_BUG(24) /* CPU may leak RNG bits if not mitigated */ -#define X86_BUG_MMIO_STALE_DATA X86_BUG(25) /* CPU is affected by Processor MMIO Stale Data vulnerabilities */ -#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 */ -#define X86_BUG_GDS X86_BUG(30) /* CPU is affected by Gather Data Sampling */ -#define X86_BUG_TDX_PW_MCE X86_BUG(31) /* CPU may incur #MC if non-TD software does partial write to TDX private memory */ +#define X86_BUG_NULL_SEG X86_BUG(10) /* "null_seg" Nulling a selector preserves the base */ +#define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* "swapgs_fence" SWAPGS without input dep on GS */ +#define X86_BUG_MONITOR X86_BUG(12) /* "monitor" IPI required to wake up remote CPU */ +#define X86_BUG_AMD_E400 X86_BUG(13) /* "amd_e400" CPU is among the affected by Erratum 400 */ +#define X86_BUG_CPU_MELTDOWN X86_BUG(14) /* "cpu_meltdown" CPU is affected by meltdown attack and needs kernel page table isolation */ +#define X86_BUG_SPECTRE_V1 X86_BUG(15) /* "spectre_v1" CPU is affected by Spectre variant 1 attack with conditional branches */ +#define X86_BUG_SPECTRE_V2 X86_BUG(16) /* "spectre_v2" CPU is affected by Spectre variant 2 attack with indirect branches */ +#define X86_BUG_SPEC_STORE_BYPASS X86_BUG(17) /* "spec_store_bypass" CPU is affected by speculative store bypass attack */ +#define X86_BUG_L1TF X86_BUG(18) /* "l1tf" CPU is affected by L1 Terminal Fault */ +#define X86_BUG_MDS X86_BUG(19) /* "mds" CPU is affected by Microarchitectural data sampling */ +#define X86_BUG_MSBDS_ONLY X86_BUG(20) /* "msbds_only" CPU is only affected by the MSDBS variant of BUG_MDS */ +#define X86_BUG_SWAPGS X86_BUG(21) /* "swapgs" CPU is affected by speculation through SWAPGS */ +#define X86_BUG_TAA X86_BUG(22) /* "taa" CPU is affected by TSX Async Abort(TAA) */ +#define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* "itlb_multihit" CPU may incur MCE during certain page attribute changes */ +#define X86_BUG_SRBDS X86_BUG(24) /* "srbds" CPU may leak RNG bits if not mitigated */ +#define X86_BUG_MMIO_STALE_DATA X86_BUG(25) /* "mmio_stale_data" CPU is affected by Processor MMIO Stale Data vulnerabilities */ +#define X86_BUG_MMIO_UNKNOWN X86_BUG(26) /* "mmio_unknown" CPU is too old and its MMIO Stale Data status is unknown */ +#define X86_BUG_RETBLEED X86_BUG(27) /* "retbleed" CPU is affected by RETBleed */ +#define X86_BUG_EIBRS_PBRSB X86_BUG(28) /* "eibrs_pbrsb" EIBRS is vulnerable to Post Barrier RSB Predictions */ +#define X86_BUG_SMT_RSB X86_BUG(29) /* "smt_rsb" CPU is vulnerable to Cross-Thread Return Address Predictions */ +#define X86_BUG_GDS X86_BUG(30) /* "gds" CPU is affected by Gather Data Sampling */ +#define X86_BUG_TDX_PW_MCE X86_BUG(31) /* "tdx_pw_mce" CPU may incur #MC if non-TD software does partial write to TDX private memory */ /* BUG word 2 */ -#define X86_BUG_SRSO X86_BUG(1*32 + 0) /* AMD SRSO bug */ -#define X86_BUG_DIV0 X86_BUG(1*32 + 1) /* AMD DIV0 speculation bug */ -#define X86_BUG_RFDS X86_BUG(1*32 + 2) /* CPU is vulnerable to Register File Data Sampling */ -#define X86_BUG_BHI X86_BUG(1*32 + 3) /* CPU is affected by Branch History Injection */ +#define X86_BUG_SRSO X86_BUG(1*32 + 0) /* "srso" AMD SRSO bug */ +#define X86_BUG_DIV0 X86_BUG(1*32 + 1) /* "div0" AMD DIV0 speculation bug */ +#define X86_BUG_RFDS X86_BUG(1*32 + 2) /* "rfds" CPU is vulnerable to Register File Data Sampling */ +#define X86_BUG_BHI X86_BUG(1*32 + 3) /* "bhi" CPU is affected by Branch History Injection */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index e022e6eb766c..82c6a4d350e0 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -566,6 +566,12 @@ #define MSR_RELOAD_PMC0 0x000014c1 #define MSR_RELOAD_FIXED_CTR0 0x00001309 +/* V6 PMON MSR range */ +#define MSR_IA32_PMC_V6_GP0_CTR 0x1900 +#define MSR_IA32_PMC_V6_GP0_CFG_A 0x1901 +#define MSR_IA32_PMC_V6_FX0_CTR 0x1980 +#define MSR_IA32_PMC_V6_STEP 4 + /* KeyID partitioning between MKTME and TDX */ #define MSR_IA32_MKTME_KEYID_PARTITIONING 0x00000087 @@ -660,6 +666,8 @@ #define MSR_AMD64_RMP_BASE 0xc0010132 #define MSR_AMD64_RMP_END 0xc0010133 +#define MSR_SVSM_CAA 0xc001f000 + /* AMD Collaborative Processor Performance Control MSRs */ #define MSR_AMD_CPPC_CAP1 0xc00102b0 #define MSR_AMD_CPPC_ENABLE 0xc00102b1 @@ -781,6 +789,8 @@ #define MSR_K7_HWCR_IRPERF_EN BIT_ULL(MSR_K7_HWCR_IRPERF_EN_BIT) #define MSR_K7_FID_VID_CTL 0xc0010041 #define MSR_K7_FID_VID_STATUS 0xc0010042 +#define MSR_K7_HWCR_CPB_DIS_BIT 25 +#define MSR_K7_HWCR_CPB_DIS BIT_ULL(MSR_K7_HWCR_CPB_DIS_BIT) /* K6 MSRs */ #define MSR_K6_WHCR 0xc0000082 @@ -1164,6 +1174,7 @@ #define MSR_IA32_QM_CTR 0xc8e #define MSR_IA32_PQR_ASSOC 0xc8f #define MSR_IA32_L3_CBM_BASE 0xc90 +#define MSR_RMID_SNC_CONFIG 0xca0 #define MSR_IA32_L2_CBM_BASE 0xd10 #define MSR_IA32_MBA_THRTL_BASE 0xd50 diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index 9fae1b73b529..bf57a824f722 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -106,6 +106,7 @@ struct kvm_ioapic_state { #define KVM_RUN_X86_SMM (1 << 0) #define KVM_RUN_X86_BUS_LOCK (1 << 1) +#define KVM_RUN_X86_GUEST_MODE (1 << 2) /* for KVM_GET_REGS and KVM_SET_REGS */ struct kvm_regs { @@ -697,6 +698,11 @@ enum sev_cmd_id { /* Second time is the charm; improved versions of the above ioctls. */ KVM_SEV_INIT2, + /* SNP-specific commands */ + KVM_SEV_SNP_LAUNCH_START = 100, + KVM_SEV_SNP_LAUNCH_UPDATE, + KVM_SEV_SNP_LAUNCH_FINISH, + KVM_SEV_NR_MAX, }; @@ -824,6 +830,48 @@ struct kvm_sev_receive_update_data { __u32 pad2; }; +struct kvm_sev_snp_launch_start { + __u64 policy; + __u8 gosvw[16]; + __u16 flags; + __u8 pad0[6]; + __u64 pad1[4]; +}; + +/* Kept in sync with firmware values for simplicity. */ +#define KVM_SEV_SNP_PAGE_TYPE_NORMAL 0x1 +#define KVM_SEV_SNP_PAGE_TYPE_ZERO 0x3 +#define KVM_SEV_SNP_PAGE_TYPE_UNMEASURED 0x4 +#define KVM_SEV_SNP_PAGE_TYPE_SECRETS 0x5 +#define KVM_SEV_SNP_PAGE_TYPE_CPUID 0x6 + +struct kvm_sev_snp_launch_update { + __u64 gfn_start; + __u64 uaddr; + __u64 len; + __u8 type; + __u8 pad0; + __u16 flags; + __u32 pad1; + __u64 pad2[4]; +}; + +#define KVM_SEV_SNP_ID_BLOCK_SIZE 96 +#define KVM_SEV_SNP_ID_AUTH_SIZE 4096 +#define KVM_SEV_SNP_FINISH_DATA_SIZE 32 + +struct kvm_sev_snp_launch_finish { + __u64 id_block_uaddr; + __u64 id_auth_uaddr; + __u8 id_block_en; + __u8 auth_key_en; + __u8 vcek_disabled; + __u8 host_data[KVM_SEV_SNP_FINISH_DATA_SIZE]; + __u8 pad0[3]; + __u16 flags; + __u64 pad1[4]; +}; + #define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0) #define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1) @@ -874,5 +922,6 @@ struct kvm_hyperv_eventfd { #define KVM_X86_SW_PROTECTED_VM 1 #define KVM_X86_SEV_VM 2 #define KVM_X86_SEV_ES_VM 3 +#define KVM_X86_SNP_VM 4 #endif /* _ASM_X86_KVM_H */ diff --git a/tools/arch/x86/include/uapi/asm/svm.h b/tools/arch/x86/include/uapi/asm/svm.h index 80e1df482337..1814b413fd57 100644 --- a/tools/arch/x86/include/uapi/asm/svm.h +++ b/tools/arch/x86/include/uapi/asm/svm.h @@ -115,6 +115,7 @@ #define SVM_VMGEXIT_AP_CREATE_ON_INIT 0 #define SVM_VMGEXIT_AP_CREATE 1 #define SVM_VMGEXIT_AP_DESTROY 2 +#define SVM_VMGEXIT_SNP_RUN_VMPL 0x80000018 #define SVM_VMGEXIT_HV_FEATURES 0x8000fffd #define SVM_VMGEXIT_TERM_REQUEST 0x8000fffe #define SVM_VMGEXIT_TERM_REASON(reason_set, reason_code) \ diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index 489cbed7e82a..12796808f07a 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -82,7 +82,30 @@ FILES= \ FILES := $(addprefix $(OUTPUT),$(FILES)) -PKG_CONFIG ?= $(CROSS_COMPILE)pkg-config +# Some distros provide the command $(CROSS_COMPILE)pkg-config for +# searching packges installed with Multiarch. Use it for cross +# compilation if it is existed. +ifneq (, $(shell which $(CROSS_COMPILE)pkg-config)) + PKG_CONFIG ?= $(CROSS_COMPILE)pkg-config +else + PKG_CONFIG ?= pkg-config + + # PKG_CONFIG_PATH or PKG_CONFIG_LIBDIR, alongside PKG_CONFIG_SYSROOT_DIR + # for modified system root, are required for the cross compilation. + # If these PKG_CONFIG environment variables are not set, Multiarch library + # paths are used instead. + ifdef CROSS_COMPILE + ifeq ($(PKG_CONFIG_LIBDIR)$(PKG_CONFIG_PATH)$(PKG_CONFIG_SYSROOT_DIR),) + CROSS_ARCH = $(shell $(CC) -dumpmachine) + PKG_CONFIG_LIBDIR := /usr/local/$(CROSS_ARCH)/lib/pkgconfig/ + PKG_CONFIG_LIBDIR := $(PKG_CONFIG_LIBDIR):/usr/local/lib/$(CROSS_ARCH)/pkgconfig/ + PKG_CONFIG_LIBDIR := $(PKG_CONFIG_LIBDIR):/usr/lib/$(CROSS_ARCH)/pkgconfig/ + PKG_CONFIG_LIBDIR := $(PKG_CONFIG_LIBDIR):/usr/local/share/pkgconfig/ + PKG_CONFIG_LIBDIR := $(PKG_CONFIG_LIBDIR):/usr/share/pkgconfig/ + export PKG_CONFIG_LIBDIR + endif + endif +endif all: $(FILES) @@ -147,7 +170,17 @@ $(OUTPUT)test-libopencsd.bin: DWARFLIBS := -ldw ifeq ($(findstring -static,${LDFLAGS}),-static) -DWARFLIBS += -lelf -lebl -lz -llzma -lbz2 + DWARFLIBS += -lelf -lz -llzma -lbz2 -lzstd + + LIBDW_VERSION := $(shell $(PKG_CONFIG) --modversion libdw) + LIBDW_VERSION_1 := $(word 1, $(subst ., ,$(LIBDW_VERSION))) + LIBDW_VERSION_2 := $(word 2, $(subst ., ,$(LIBDW_VERSION))) + + # Elfutils merged libebl.a into libdw.a starting from version 0.177, + # Link libebl.a only if libdw is older than this version. + ifeq ($(shell test $(LIBDW_VERSION_2) -lt 177; echo $$?),0) + DWARFLIBS += -lebl + endif endif $(OUTPUT)test-dwarf.bin: @@ -178,27 +211,27 @@ $(OUTPUT)test-numa_num_possible_cpus.bin: $(BUILD) -lnuma $(OUTPUT)test-libunwind.bin: - $(BUILD) -lelf + $(BUILD) -lelf -llzma $(OUTPUT)test-libunwind-debug-frame.bin: - $(BUILD) -lelf + $(BUILD) -lelf -llzma $(OUTPUT)test-libunwind-x86.bin: - $(BUILD) -lelf -lunwind-x86 + $(BUILD) -lelf -llzma -lunwind-x86 $(OUTPUT)test-libunwind-x86_64.bin: - $(BUILD) -lelf -lunwind-x86_64 + $(BUILD) -lelf -llzma -lunwind-x86_64 $(OUTPUT)test-libunwind-arm.bin: - $(BUILD) -lelf -lunwind-arm + $(BUILD) -lelf -llzma -lunwind-arm $(OUTPUT)test-libunwind-aarch64.bin: - $(BUILD) -lelf -lunwind-aarch64 + $(BUILD) -lelf -llzma -lunwind-aarch64 $(OUTPUT)test-libunwind-debug-frame-arm.bin: - $(BUILD) -lelf -lunwind-arm + $(BUILD) -lelf -llzma -lunwind-arm $(OUTPUT)test-libunwind-debug-frame-aarch64.bin: - $(BUILD) -lelf -lunwind-aarch64 + $(BUILD) -lelf -llzma -lunwind-aarch64 $(OUTPUT)test-libaudit.bin: $(BUILD) -laudit diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h index 210c13b1b857..2a7f260ef9dc 100644 --- a/tools/include/linux/bitmap.h +++ b/tools/include/linux/bitmap.h @@ -19,7 +19,7 @@ bool __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits); bool __bitmap_equal(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits); -void bitmap_clear(unsigned long *map, unsigned int start, int len); +void __bitmap_clear(unsigned long *map, unsigned int start, int len); bool __bitmap_intersects(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits); @@ -150,4 +150,19 @@ static inline bool bitmap_intersects(const unsigned long *src1, return __bitmap_intersects(src1, src2, nbits); } +static inline void bitmap_clear(unsigned long *map, unsigned int start, + unsigned int nbits) +{ + if (__builtin_constant_p(nbits) && nbits == 1) + __clear_bit(start, map); + else if (small_const_nbits(start + nbits)) + *map &= ~GENMASK(start + nbits - 1, start); + else if (__builtin_constant_p(start & BITMAP_MEM_MASK) && + IS_ALIGNED(start, BITMAP_MEM_ALIGNMENT) && + __builtin_constant_p(nbits & BITMAP_MEM_MASK) && + IS_ALIGNED(nbits, BITMAP_MEM_ALIGNMENT)) + memset((char *)map + start / 8, 0, nbits / 8); + else + __bitmap_clear(map, start, nbits); +} #endif /* _TOOLS_LINUX_BITMAP_H */ diff --git a/tools/include/uapi/README b/tools/include/uapi/README new file mode 100644 index 000000000000..7147b1b2cb28 --- /dev/null +++ b/tools/include/uapi/README @@ -0,0 +1,73 @@ +Why we want a copy of kernel headers in tools? +============================================== + +There used to be no copies, with tools/ code using kernel headers +directly. From time to time tools/perf/ broke due to legitimate kernel +hacking. At some point Linus complained about such direct usage. Then we +adopted the current model. + +The way these headers are used in perf are not restricted to just +including them to compile something. + +There are sometimes used in scripts that convert defines into string +tables, etc, so some change may break one of these scripts, or new MSRs +may use some different #define pattern, etc. + +E.g.: + + $ ls -1 tools/perf/trace/beauty/*.sh | head -5 + tools/perf/trace/beauty/arch_errno_names.sh + tools/perf/trace/beauty/drm_ioctl.sh + tools/perf/trace/beauty/fadvise.sh + tools/perf/trace/beauty/fsconfig.sh + tools/perf/trace/beauty/fsmount.sh + $ + $ tools/perf/trace/beauty/fadvise.sh + static const char *fadvise_advices[] = { + [0] = "NORMAL", + [1] = "RANDOM", + [2] = "SEQUENTIAL", + [3] = "WILLNEED", + [4] = "DONTNEED", + [5] = "NOREUSE", + }; + $ + +The tools/perf/check-headers.sh script, part of the tools/ build +process, points out changes in the original files. + +So its important not to touch the copies in tools/ when doing changes in +the original kernel headers, that will be done later, when +check-headers.sh inform about the change to the perf tools hackers. + +Another explanation from Ingo Molnar: +It's better than all the alternatives we tried so far: + + - Symbolic links and direct #includes: this was the original approach but + was pushed back on from the kernel side, when tooling modified the + headers and broke them accidentally for kernel builds. + + - Duplicate self-defined ABI headers like glibc: double the maintenance + burden, double the chance for mistakes, plus there's no tech-driven + notification mechanism to look at new kernel side changes. + +What we are doing now is a third option: + + - A software-enforced copy-on-write mechanism of kernel headers to + tooling, driven by non-fatal warnings on the tooling side build when + kernel headers get modified: + + Warning: Kernel ABI header differences: + diff -u tools/include/uapi/drm/i915_drm.h include/uapi/drm/i915_drm.h + diff -u tools/include/uapi/linux/fs.h include/uapi/linux/fs.h + diff -u tools/include/uapi/linux/kvm.h include/uapi/linux/kvm.h + ... + + The tooling policy is to always pick up the kernel side headers as-is, + and integate them into the tooling build. The warnings above serve as a + notification to tooling maintainers that there's changes on the kernel + side. + +We've been using this for many years now, and it might seem hacky, but +works surprisingly well. + diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index a00d53d02723..5bf6148cac2b 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -737,7 +737,7 @@ __SC_COMP(__NR_pselect6_time64, sys_pselect6, compat_sys_pselect6_time64) #define __NR_ppoll_time64 414 __SC_COMP(__NR_ppoll_time64, sys_ppoll, compat_sys_ppoll_time64) #define __NR_io_pgetevents_time64 416 -__SYSCALL(__NR_io_pgetevents_time64, sys_io_pgetevents) +__SC_COMP(__NR_io_pgetevents_time64, sys_io_pgetevents, compat_sys_io_pgetevents_time64) #define __NR_recvmmsg_time64 417 __SC_COMP(__NR_recvmmsg_time64, sys_recvmmsg, compat_sys_recvmmsg_time64) #define __NR_mq_timedsend_time64 418 diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index d4d86e566e07..535cb68fdb5c 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -2163,6 +2163,15 @@ struct drm_i915_gem_context_param { * supports this per context flag. */ #define I915_CONTEXT_PARAM_LOW_LATENCY 0xe + +/* + * I915_CONTEXT_PARAM_CONTEXT_IMAGE: + * + * Allows userspace to provide own context images. + * + * Note that this is a debug API not available on production kernel builds. + */ +#define I915_CONTEXT_PARAM_CONTEXT_IMAGE 0xf /* Must be kept compact -- no holes and well documented */ /** @value: Context parameter value to be set or queried */ @@ -2564,6 +2573,24 @@ struct i915_context_param_engines { struct i915_engine_class_instance engines[N__]; \ } __attribute__((packed)) name__ +struct i915_gem_context_param_context_image { + /** @engine: Engine class & instance to be configured. */ + struct i915_engine_class_instance engine; + + /** @flags: One of the supported flags or zero. */ + __u32 flags; +#define I915_CONTEXT_IMAGE_FLAG_ENGINE_INDEX (1u << 0) + + /** @size: Size of the image blob pointed to by @image. */ + __u32 size; + + /** @mbz: Must be zero. */ + __u32 mbz; + + /** @image: Userspace memory containing the context image. */ + __u64 image; +} __attribute__((packed)); + /** * struct drm_i915_gem_context_create_ext_setparam - Context parameter * to set or query during context creation. diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h index e682ab628dfa..d358add1611c 100644 --- a/tools/include/uapi/linux/in.h +++ b/tools/include/uapi/linux/in.h @@ -81,6 +81,8 @@ enum { #define IPPROTO_ETHERNET IPPROTO_ETHERNET IPPROTO_RAW = 255, /* Raw IP packets */ #define IPPROTO_RAW IPPROTO_RAW + IPPROTO_SMC = 256, /* Shared Memory Communications */ +#define IPPROTO_SMC IPPROTO_SMC IPPROTO_MPTCP = 262, /* Multipath TCP connection */ #define IPPROTO_MPTCP IPPROTO_MPTCP IPPROTO_MAX diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index e5af8c692dc0..637efc055145 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -192,11 +192,24 @@ struct kvm_xen_exit { /* Flags that describe what fields in emulation_failure hold valid data. */ #define KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES (1ULL << 0) +/* + * struct kvm_run can be modified by userspace at any time, so KVM must be + * careful to avoid TOCTOU bugs. In order to protect KVM, HINT_UNSAFE_IN_KVM() + * renames fields in struct kvm_run from <symbol> to <symbol>__unsafe when + * compiled into the kernel, ensuring that any use within KVM is obvious and + * gets extra scrutiny. + */ +#ifdef __KERNEL__ +#define HINT_UNSAFE_IN_KVM(_symbol) _symbol##__unsafe +#else +#define HINT_UNSAFE_IN_KVM(_symbol) _symbol +#endif + /* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */ struct kvm_run { /* in */ __u8 request_interrupt_window; - __u8 immediate_exit; + __u8 HINT_UNSAFE_IN_KVM(immediate_exit); __u8 padding1[6]; /* out */ @@ -918,6 +931,8 @@ struct kvm_enable_cap { #define KVM_CAP_GUEST_MEMFD 234 #define KVM_CAP_VM_TYPES 235 #define KVM_CAP_PRE_FAULT_MEMORY 236 +#define KVM_CAP_X86_APIC_BUS_CYCLES_NS 237 +#define KVM_CAP_X86_GUEST_MODE 238 struct kvm_irq_routing_irqchip { __u32 irqchip; diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index 3a64499b0f5d..4842c36fdf80 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -1349,12 +1349,14 @@ union perf_mem_data_src { #define PERF_MEM_LVLNUM_L2 0x02 /* L2 */ #define PERF_MEM_LVLNUM_L3 0x03 /* L3 */ #define PERF_MEM_LVLNUM_L4 0x04 /* L4 */ -/* 5-0x7 available */ +#define PERF_MEM_LVLNUM_L2_MHB 0x05 /* L2 Miss Handling Buffer */ +#define PERF_MEM_LVLNUM_MSC 0x06 /* Memory-side Cache */ +/* 0x7 available */ #define PERF_MEM_LVLNUM_UNC 0x08 /* Uncached */ #define PERF_MEM_LVLNUM_CXL 0x09 /* CXL */ #define PERF_MEM_LVLNUM_IO 0x0a /* I/O */ #define PERF_MEM_LVLNUM_ANY_CACHE 0x0b /* Any cache */ -#define PERF_MEM_LVLNUM_LFB 0x0c /* LFB */ +#define PERF_MEM_LVLNUM_LFB 0x0c /* LFB / L1 Miss Handling Buffer */ #define PERF_MEM_LVLNUM_RAM 0x0d /* RAM */ #define PERF_MEM_LVLNUM_PMEM 0x0e /* PMEM */ #define PERF_MEM_LVLNUM_NA 0x0f /* N/A */ diff --git a/tools/include/uapi/linux/stat.h b/tools/include/uapi/linux/stat.h index 67626d535316..887a25286441 100644 --- a/tools/include/uapi/linux/stat.h +++ b/tools/include/uapi/linux/stat.h @@ -126,9 +126,15 @@ struct statx { __u64 stx_mnt_id; __u32 stx_dio_mem_align; /* Memory buffer alignment for direct I/O */ __u32 stx_dio_offset_align; /* File offset alignment for direct I/O */ - __u64 stx_subvol; /* Subvolume identifier */ /* 0xa0 */ - __u64 __spare3[11]; /* Spare space for future expansion */ + __u64 stx_subvol; /* Subvolume identifier */ + __u32 stx_atomic_write_unit_min; /* Min atomic write unit in bytes */ + __u32 stx_atomic_write_unit_max; /* Max atomic write unit in bytes */ + /* 0xb0 */ + __u32 stx_atomic_write_segments_max; /* Max atomic write segment count */ + __u32 __spare1[1]; + /* 0xb8 */ + __u64 __spare3[9]; /* Spare space for future expansion */ /* 0x100 */ }; @@ -157,6 +163,7 @@ struct statx { #define STATX_DIOALIGN 0x00002000U /* Want/got direct I/O alignment info */ #define STATX_MNT_ID_UNIQUE 0x00004000U /* Want/got extended stx_mount_id */ #define STATX_SUBVOL 0x00008000U /* Want/got stx_subvol */ +#define STATX_WRITE_ATOMIC 0x00010000U /* Want/got atomic_write_* fields */ #define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */ @@ -192,6 +199,7 @@ struct statx { #define STATX_ATTR_MOUNT_ROOT 0x00002000 /* Root of a mount */ #define STATX_ATTR_VERITY 0x00100000 /* [I] Verity protected file */ #define STATX_ATTR_DAX 0x00200000 /* File is currently in DAX state */ +#define STATX_ATTR_WRITE_ATOMIC 0x00400000 /* File supports atomic write operations */ #endif /* _UAPI_LINUX_STAT_H */ diff --git a/tools/lib/bitmap.c b/tools/lib/bitmap.c index c3e4871967bc..2178862bb114 100644 --- a/tools/lib/bitmap.c +++ b/tools/lib/bitmap.c @@ -100,3 +100,23 @@ bool __bitmap_intersects(const unsigned long *bitmap1, return true; return false; } + +void __bitmap_clear(unsigned long *map, unsigned int start, int len) +{ + unsigned long *p = map + BIT_WORD(start); + const unsigned int size = start + len; + int bits_to_clear = BITS_PER_LONG - (start % BITS_PER_LONG); + unsigned long mask_to_clear = BITMAP_FIRST_WORD_MASK(start); + + while (len - bits_to_clear >= 0) { + *p &= ~mask_to_clear; + len -= bits_to_clear; + bits_to_clear = BITS_PER_LONG; + mask_to_clear = ~0UL; + p++; + } + if (len) { + mask_to_clear &= BITMAP_LAST_WORD_MASK(size); + *p &= ~mask_to_clear; + } +} diff --git a/tools/perf/Documentation/Build.txt b/tools/perf/Documentation/Build.txt index 3766886c4bca..83dc87c662b6 100644 --- a/tools/perf/Documentation/Build.txt +++ b/tools/perf/Documentation/Build.txt @@ -71,3 +71,31 @@ supported by GCC. UBSan detects undefined behaviors of programs at runtime. $ UBSAN_OPTIONS=print_stacktrace=1 ./perf record -a If UBSan detects any problem at runtime, it outputs a “runtime error:” message. + +4) Cross compilation +==================== +As Multiarch is commonly supported in Linux distributions, we can install +libraries for multiple architectures on the same system and then cross-compile +Linux perf. For example, Aarch64 libraries and toolchains can be installed on +an x86_64 machine, allowing us to compile perf for an Aarch64 target. + +Below is the command for building the perf with dynamic linking. + + $ cd /path/to/Linux + $ make ARCH=arm64 CROSS_COMPILE=aarch64-linux-gnu- -C tools/perf + +For static linking, the option `LDFLAGS="-static"` is required. + + $ make ARCH=arm64 CROSS_COMPILE=aarch64-linux-gnu- \ + LDFLAGS="-static" -C tools/perf + +In the embedded system world, a use case is to explicitly specify the package +configuration paths for cross building: + + $ PKG_CONFIG_SYSROOT_DIR="/path/to/cross/build/sysroot" \ + PKG_CONFIG_LIBDIR="/usr/lib/:/usr/local/lib" \ + make ARCH=arm64 CROSS_COMPILE=aarch64-linux-gnu- -C tools/perf + +In this case, the variable PKG_CONFIG_SYSROOT_DIR can be used alongside the +variable PKG_CONFIG_LIBDIR or PKG_CONFIG_PATH to prepend the sysroot path to +the library paths for cross compilation. diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index c896babf7a74..fa679db61f62 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -152,7 +152,17 @@ ifdef LIBDW_DIR endif DWARFLIBS := -ldw ifeq ($(findstring -static,${LDFLAGS}),-static) - DWARFLIBS += -lelf -lebl -ldl -lz -llzma -lbz2 + DWARFLIBS += -lelf -ldl -lz -llzma -lbz2 -lzstd + + LIBDW_VERSION := $(shell $(PKG_CONFIG) --modversion libdw) + LIBDW_VERSION_1 := $(word 1, $(subst ., ,$(LIBDW_VERSION))) + LIBDW_VERSION_2 := $(word 2, $(subst ., ,$(LIBDW_VERSION))) + + # Elfutils merged libebl.a into libdw.a starting from version 0.177, + # Link libebl.a only if libdw is older than this version. + ifeq ($(shell test $(LIBDW_VERSION_2) -lt 177; echo $$?),0) + DWARFLIBS += -lebl + endif endif FEATURE_CHECK_CFLAGS-libdw-dwarf-unwind := $(LIBDW_CFLAGS) FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind := $(LIBDW_LDFLAGS) $(DWARFLIBS) @@ -296,6 +306,11 @@ endif ifdef PYTHON_CONFIG PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) $(PYTHON_CONFIG_LDFLAGS) 2>/dev/null) + # Update the python flags for cross compilation + ifdef CROSS_COMPILE + PYTHON_NATIVE := $(shell echo $(PYTHON_EMBED_LDOPTS) | sed 's/\(-L.*\/\)\(.*-linux-gnu\).*/\2/') + PYTHON_EMBED_LDOPTS := $(subst $(PYTHON_NATIVE),$(shell $(CC) -dumpmachine),$(PYTHON_EMBED_LDOPTS)) + endif PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS)) PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --includes 2>/dev/null) @@ -897,6 +912,9 @@ else PYTHON_SETUPTOOLS_INSTALLED := $(shell $(PYTHON) -c 'import setuptools;' 2> /dev/null && echo "yes" || echo "no") ifeq ($(PYTHON_SETUPTOOLS_INSTALLED), yes) PYTHON_EXTENSION_SUFFIX := $(shell $(PYTHON) -c 'from importlib import machinery; print(machinery.EXTENSION_SUFFIXES[0])') + ifdef CROSS_COMPILE + PYTHON_EXTENSION_SUFFIX := $(subst $(PYTHON_NATIVE),$(shell $(CC) -dumpmachine),$(PYTHON_EXTENSION_SUFFIX)) + endif LANG_BINDINGS += $(obj-perf)python/perf$(PYTHON_EXTENSION_SUFFIX) else $(warning Missing python setuptools, the python binding won't be built, please install python3-setuptools or equivalent) diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 175e4c7898f0..f8148db5fc38 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -193,7 +193,32 @@ HOSTLD ?= ld HOSTAR ?= ar CLANG ?= clang -PKG_CONFIG = $(CROSS_COMPILE)pkg-config +# Some distros provide the command $(CROSS_COMPILE)pkg-config for +# searching packges installed with Multiarch. Use it for cross +# compilation if it is existed. +ifneq (, $(shell which $(CROSS_COMPILE)pkg-config)) + PKG_CONFIG ?= $(CROSS_COMPILE)pkg-config +else + PKG_CONFIG ?= pkg-config + + # PKG_CONFIG_PATH or PKG_CONFIG_LIBDIR, alongside PKG_CONFIG_SYSROOT_DIR + # for modified system root, is required for the cross compilation. + # If these PKG_CONFIG environment variables are not set, Multiarch library + # paths are used instead. + ifdef CROSS_COMPILE + ifeq ($(PKG_CONFIG_LIBDIR)$(PKG_CONFIG_PATH)$(PKG_CONFIG_SYSROOT_DIR),) + CROSS_ARCH = $(shell $(CC) -dumpmachine) + PKG_CONFIG_LIBDIR := /usr/local/$(CROSS_ARCH)/lib/pkgconfig/ + PKG_CONFIG_LIBDIR := $(PKG_CONFIG_LIBDIR):/usr/local/lib/$(CROSS_ARCH)/pkgconfig/ + PKG_CONFIG_LIBDIR := $(PKG_CONFIG_LIBDIR):/usr/lib/$(CROSS_ARCH)/pkgconfig/ + PKG_CONFIG_LIBDIR := $(PKG_CONFIG_LIBDIR):/usr/local/share/pkgconfig/ + PKG_CONFIG_LIBDIR := $(PKG_CONFIG_LIBDIR):/usr/share/pkgconfig/ + export PKG_CONFIG_LIBDIR + $(warning Missing PKG_CONFIG_LIBDIR, PKG_CONFIG_PATH and PKG_CONFIG_SYSROOT_DIR for cross compilation,) + $(warning set PKG_CONFIG_LIBDIR for using Multiarch libs.) + endif + endif +endif RM = rm -f LN = ln -f diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl index 3656f1ca7a21..ebae8415dfbb 100644 --- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl @@ -230,8 +230,10 @@ 178 nospu rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend 179 32 pread64 sys_ppc_pread64 compat_sys_ppc_pread64 179 64 pread64 sys_pread64 +179 spu pread64 sys_pread64 180 32 pwrite64 sys_ppc_pwrite64 compat_sys_ppc_pwrite64 180 64 pwrite64 sys_pwrite64 +180 spu pwrite64 sys_pwrite64 181 common chown sys_chown 182 common getcwd sys_getcwd 183 common capget sys_capget @@ -246,6 +248,7 @@ 190 common ugetrlimit sys_getrlimit compat_sys_getrlimit 191 32 readahead sys_ppc_readahead compat_sys_ppc_readahead 191 64 readahead sys_readahead +191 spu readahead sys_readahead 192 32 mmap2 sys_mmap2 compat_sys_mmap2 193 32 truncate64 sys_ppc_truncate64 compat_sys_ppc_truncate64 194 32 ftruncate64 sys_ppc_ftruncate64 compat_sys_ppc_ftruncate64 @@ -293,6 +296,7 @@ 232 nospu set_tid_address sys_set_tid_address 233 32 fadvise64 sys_ppc32_fadvise64 compat_sys_ppc32_fadvise64 233 64 fadvise64 sys_fadvise64 +233 spu fadvise64 sys_fadvise64 234 nospu exit_group sys_exit_group 235 nospu lookup_dcookie sys_ni_syscall 236 common epoll_create sys_epoll_create @@ -502,7 +506,7 @@ 412 32 utimensat_time64 sys_utimensat sys_utimensat 413 32 pselect6_time64 sys_pselect6 compat_sys_pselect6_time64 414 32 ppoll_time64 sys_ppoll compat_sys_ppoll_time64 -416 32 io_pgetevents_time64 sys_io_pgetevents sys_io_pgetevents +416 32 io_pgetevents_time64 sys_io_pgetevents compat_sys_io_pgetevents_time64 417 32 recvmmsg_time64 sys_recvmmsg compat_sys_recvmmsg_time64 418 32 mq_timedsend_time64 sys_mq_timedsend sys_mq_timedsend 419 32 mq_timedreceive_time64 sys_mq_timedreceive sys_mq_timedreceive diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl index bd0fee24ad10..01071182763e 100644 --- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -418,7 +418,7 @@ 412 32 utimensat_time64 - sys_utimensat 413 32 pselect6_time64 - compat_sys_pselect6_time64 414 32 ppoll_time64 - compat_sys_ppoll_time64 -416 32 io_pgetevents_time64 - sys_io_pgetevents +416 32 io_pgetevents_time64 - compat_sys_io_pgetevents_time64 417 32 recvmmsg_time64 - compat_sys_recvmmsg_time64 418 32 mq_timedsend_time64 - sys_mq_timedsend 419 32 mq_timedreceive_time64 - sys_mq_timedreceive diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index a396f6e6ab5b..7093ee21c0d1 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -1,8 +1,9 @@ +# SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note # # 64-bit system call numbers and entry vectors # # The format is: -# <number> <abi> <name> <entry point> +# <number> <abi> <name> <entry point> [<compat entry point> [noreturn]] # # The __x64_sys_*() stubs are created on-the-fly for sys_*() system calls # @@ -68,7 +69,7 @@ 57 common fork sys_fork 58 common vfork sys_vfork 59 64 execve sys_execve -60 common exit sys_exit +60 common exit sys_exit - noreturn 61 common wait4 sys_wait4 62 common kill sys_kill 63 common uname sys_newuname @@ -239,7 +240,7 @@ 228 common clock_gettime sys_clock_gettime 229 common clock_getres sys_clock_getres 230 common clock_nanosleep sys_clock_nanosleep -231 common exit_group sys_exit_group +231 common exit_group sys_exit_group - noreturn 232 common epoll_wait sys_epoll_wait 233 common epoll_ctl sys_epoll_ctl 234 common tgkill sys_tgkill @@ -343,6 +344,7 @@ 332 common statx sys_statx 333 common io_pgetevents sys_io_pgetevents 334 common rseq sys_rseq +335 common uretprobe sys_uretprobe # don't use numbers 387 through 423, add new calls after the last # 'common' entry 424 common pidfd_send_signal sys_pidfd_send_signal diff --git a/tools/perf/builtin-daemon.c b/tools/perf/builtin-daemon.c index de76bbc50bfb..5c9335fff2d3 100644 --- a/tools/perf/builtin-daemon.c +++ b/tools/perf/builtin-daemon.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <internal/lib.h> +#include <inttypes.h> #include <subcmd/parse-options.h> #include <api/fd/array.h> #include <api/fs/fs.h> @@ -688,7 +689,7 @@ static int cmd_session_list(struct daemon *daemon, union cmd *cmd, FILE *out) /* lock */ csv_sep, daemon->base, "lock"); - fprintf(out, "%c%lu", + fprintf(out, "%c%" PRIu64, /* session up time */ csv_sep, (curr - daemon->start) / 60); @@ -700,7 +701,7 @@ static int cmd_session_list(struct daemon *daemon, union cmd *cmd, FILE *out) daemon->base, SESSION_OUTPUT); fprintf(out, " lock: %s/lock\n", daemon->base); - fprintf(out, " up: %lu minutes\n", + fprintf(out, " up: %" PRIu64 " minutes\n", (curr - daemon->start) / 60); } } @@ -727,7 +728,7 @@ static int cmd_session_list(struct daemon *daemon, union cmd *cmd, FILE *out) /* session ack */ csv_sep, session->base, SESSION_ACK); - fprintf(out, "%c%lu", + fprintf(out, "%c%" PRIu64, /* session up time */ csv_sep, (curr - session->start) / 60); @@ -745,7 +746,7 @@ static int cmd_session_list(struct daemon *daemon, union cmd *cmd, FILE *out) session->base, SESSION_CONTROL); fprintf(out, " ack: %s/%s\n", session->base, SESSION_ACK); - fprintf(out, " up: %lu minutes\n", + fprintf(out, " up: %" PRIu64 " minutes\n", (curr - session->start) / 60); } } diff --git a/tools/perf/pmu-events/arch/riscv/andes/ax45/firmware.json b/tools/perf/pmu-events/arch/riscv/andes/ax45/firmware.json index 9b4a032186a7..7149caec4f80 100644 --- a/tools/perf/pmu-events/arch/riscv/andes/ax45/firmware.json +++ b/tools/perf/pmu-events/arch/riscv/andes/ax45/firmware.json @@ -36,7 +36,7 @@ "ArchStdEvent": "FW_SFENCE_VMA_RECEIVED" }, { - "ArchStdEvent": "FW_SFENCE_VMA_RECEIVED" + "ArchStdEvent": "FW_SFENCE_VMA_ASID_SENT" }, { "ArchStdEvent": "FW_SFENCE_VMA_ASID_RECEIVED" diff --git a/tools/perf/pmu-events/arch/riscv/riscv-sbi-firmware.json b/tools/perf/pmu-events/arch/riscv/riscv-sbi-firmware.json index a9939823b14b..0c9b9a2d2958 100644 --- a/tools/perf/pmu-events/arch/riscv/riscv-sbi-firmware.json +++ b/tools/perf/pmu-events/arch/riscv/riscv-sbi-firmware.json @@ -74,7 +74,7 @@ { "PublicDescription": "Sent SFENCE.VMA with ASID request to other HART event", "ConfigCode": "0x800000000000000c", - "EventName": "FW_SFENCE_VMA_RECEIVED", + "EventName": "FW_SFENCE_VMA_ASID_SENT", "BriefDescription": "Sent SFENCE.VMA with ASID request to other HART event" }, { diff --git a/tools/perf/pmu-events/arch/riscv/sifive/u74/firmware.json b/tools/perf/pmu-events/arch/riscv/sifive/u74/firmware.json index 9b4a032186a7..7149caec4f80 100644 --- a/tools/perf/pmu-events/arch/riscv/sifive/u74/firmware.json +++ b/tools/perf/pmu-events/arch/riscv/sifive/u74/firmware.json @@ -36,7 +36,7 @@ "ArchStdEvent": "FW_SFENCE_VMA_RECEIVED" }, { - "ArchStdEvent": "FW_SFENCE_VMA_RECEIVED" + "ArchStdEvent": "FW_SFENCE_VMA_ASID_SENT" }, { "ArchStdEvent": "FW_SFENCE_VMA_ASID_RECEIVED" diff --git a/tools/perf/pmu-events/arch/riscv/starfive/dubhe-80/firmware.json b/tools/perf/pmu-events/arch/riscv/starfive/dubhe-80/firmware.json index 9b4a032186a7..7149caec4f80 100644 --- a/tools/perf/pmu-events/arch/riscv/starfive/dubhe-80/firmware.json +++ b/tools/perf/pmu-events/arch/riscv/starfive/dubhe-80/firmware.json @@ -36,7 +36,7 @@ "ArchStdEvent": "FW_SFENCE_VMA_RECEIVED" }, { - "ArchStdEvent": "FW_SFENCE_VMA_RECEIVED" + "ArchStdEvent": "FW_SFENCE_VMA_ASID_SENT" }, { "ArchStdEvent": "FW_SFENCE_VMA_ASID_RECEIVED" diff --git a/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/firmware.json b/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/firmware.json index 9b4a032186a7..7149caec4f80 100644 --- a/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/firmware.json +++ b/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/firmware.json @@ -36,7 +36,7 @@ "ArchStdEvent": "FW_SFENCE_VMA_RECEIVED" }, { - "ArchStdEvent": "FW_SFENCE_VMA_RECEIVED" + "ArchStdEvent": "FW_SFENCE_VMA_ASID_SENT" }, { "ArchStdEvent": "FW_SFENCE_VMA_ASID_RECEIVED" diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h index 89d16b90370b..df9cdb8bbfb8 100644 --- a/tools/perf/trace/beauty/include/linux/socket.h +++ b/tools/perf/trace/beauty/include/linux/socket.h @@ -76,7 +76,7 @@ struct msghdr { __kernel_size_t msg_controllen; /* ancillary data buffer length */ struct kiocb *msg_iocb; /* ptr to iocb for async requests */ struct ubuf_info *msg_ubuf; - int (*sg_from_iter)(struct sock *sk, struct sk_buff *skb, + int (*sg_from_iter)(struct sk_buff *skb, struct iov_iter *from, size_t length); }; @@ -442,11 +442,14 @@ extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, extern int __sys_socket(int family, int type, int protocol); extern struct file *__sys_socket_file(int family, int type, int protocol); extern int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen); +extern int __sys_bind_socket(struct socket *sock, struct sockaddr_storage *address, + int addrlen); extern int __sys_connect_file(struct file *file, struct sockaddr_storage *addr, int addrlen, int file_flags); extern int __sys_connect(int fd, struct sockaddr __user *uservaddr, int addrlen); extern int __sys_listen(int fd, int backlog); +extern int __sys_listen_socket(struct socket *sock, int backlog); extern int __sys_getsockname(int fd, struct sockaddr __user *usockaddr, int __user *usockaddr_len); extern int __sys_getpeername(int fd, struct sockaddr __user *usockaddr, diff --git a/tools/perf/trace/beauty/include/uapi/linux/fs.h b/tools/perf/trace/beauty/include/uapi/linux/fs.h index 45e4e64fd664..753971770733 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/fs.h +++ b/tools/perf/trace/beauty/include/uapi/linux/fs.h @@ -329,12 +329,17 @@ typedef int __bitwise __kernel_rwf_t; /* per-IO negation of O_APPEND */ #define RWF_NOAPPEND ((__force __kernel_rwf_t)0x00000020) +/* Atomic Write */ +#define RWF_ATOMIC ((__force __kernel_rwf_t)0x00000040) + /* mask of flags supported by the kernel */ #define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\ - RWF_APPEND | RWF_NOAPPEND) + RWF_APPEND | RWF_NOAPPEND | RWF_ATOMIC) + +#define PROCFS_IOCTL_MAGIC 'f' /* Pagemap ioctl */ -#define PAGEMAP_SCAN _IOWR('f', 16, struct pm_scan_arg) +#define PAGEMAP_SCAN _IOWR(PROCFS_IOCTL_MAGIC, 16, struct pm_scan_arg) /* Bitmasks provided in pm_scan_args masks and reported in page_region.categories. */ #define PAGE_IS_WPALLOWED (1 << 0) @@ -393,4 +398,158 @@ struct pm_scan_arg { __u64 return_mask; }; +/* /proc/<pid>/maps ioctl */ +#define PROCMAP_QUERY _IOWR(PROCFS_IOCTL_MAGIC, 17, struct procmap_query) + +enum procmap_query_flags { + /* + * VMA permission flags. + * + * Can be used as part of procmap_query.query_flags field to look up + * only VMAs satisfying specified subset of permissions. E.g., specifying + * PROCMAP_QUERY_VMA_READABLE only will return both readable and read/write VMAs, + * while having PROCMAP_QUERY_VMA_READABLE | PROCMAP_QUERY_VMA_WRITABLE will only + * return read/write VMAs, though both executable/non-executable and + * private/shared will be ignored. + * + * PROCMAP_QUERY_VMA_* flags are also returned in procmap_query.vma_flags + * field to specify actual VMA permissions. + */ + PROCMAP_QUERY_VMA_READABLE = 0x01, + PROCMAP_QUERY_VMA_WRITABLE = 0x02, + PROCMAP_QUERY_VMA_EXECUTABLE = 0x04, + PROCMAP_QUERY_VMA_SHARED = 0x08, + /* + * Query modifier flags. + * + * By default VMA that covers provided address is returned, or -ENOENT + * is returned. With PROCMAP_QUERY_COVERING_OR_NEXT_VMA flag set, closest + * VMA with vma_start > addr will be returned if no covering VMA is + * found. + * + * PROCMAP_QUERY_FILE_BACKED_VMA instructs query to consider only VMAs that + * have file backing. Can be combined with PROCMAP_QUERY_COVERING_OR_NEXT_VMA + * to iterate all VMAs with file backing. + */ + PROCMAP_QUERY_COVERING_OR_NEXT_VMA = 0x10, + PROCMAP_QUERY_FILE_BACKED_VMA = 0x20, +}; + +/* + * Input/output argument structured passed into ioctl() call. It can be used + * to query a set of VMAs (Virtual Memory Areas) of a process. + * + * Each field can be one of three kinds, marked in a short comment to the + * right of the field: + * - "in", input argument, user has to provide this value, kernel doesn't modify it; + * - "out", output argument, kernel sets this field with VMA data; + * - "in/out", input and output argument; user provides initial value (used + * to specify maximum allowable buffer size), and kernel sets it to actual + * amount of data written (or zero, if there is no data). + * + * If matching VMA is found (according to criterias specified by + * query_addr/query_flags, all the out fields are filled out, and ioctl() + * returns 0. If there is no matching VMA, -ENOENT will be returned. + * In case of any other error, negative error code other than -ENOENT is + * returned. + * + * Most of the data is similar to the one returned as text in /proc/<pid>/maps + * file, but procmap_query provides more querying flexibility. There are no + * consistency guarantees between subsequent ioctl() calls, but data returned + * for matched VMA is self-consistent. + */ +struct procmap_query { + /* Query struct size, for backwards/forward compatibility */ + __u64 size; + /* + * Query flags, a combination of enum procmap_query_flags values. + * Defines query filtering and behavior, see enum procmap_query_flags. + * + * Input argument, provided by user. Kernel doesn't modify it. + */ + __u64 query_flags; /* in */ + /* + * Query address. By default, VMA that covers this address will + * be looked up. PROCMAP_QUERY_* flags above modify this default + * behavior further. + * + * Input argument, provided by user. Kernel doesn't modify it. + */ + __u64 query_addr; /* in */ + /* VMA starting (inclusive) and ending (exclusive) address, if VMA is found. */ + __u64 vma_start; /* out */ + __u64 vma_end; /* out */ + /* VMA permissions flags. A combination of PROCMAP_QUERY_VMA_* flags. */ + __u64 vma_flags; /* out */ + /* VMA backing page size granularity. */ + __u64 vma_page_size; /* out */ + /* + * VMA file offset. If VMA has file backing, this specifies offset + * within the file that VMA's start address corresponds to. + * Is set to zero if VMA has no backing file. + */ + __u64 vma_offset; /* out */ + /* Backing file's inode number, or zero, if VMA has no backing file. */ + __u64 inode; /* out */ + /* Backing file's device major/minor number, or zero, if VMA has no backing file. */ + __u32 dev_major; /* out */ + __u32 dev_minor; /* out */ + /* + * If set to non-zero value, signals the request to return VMA name + * (i.e., VMA's backing file's absolute path, with " (deleted)" suffix + * appended, if file was unlinked from FS) for matched VMA. VMA name + * can also be some special name (e.g., "[heap]", "[stack]") or could + * be even user-supplied with prctl(PR_SET_VMA, PR_SET_VMA_ANON_NAME). + * + * Kernel will set this field to zero, if VMA has no associated name. + * Otherwise kernel will return actual amount of bytes filled in + * user-supplied buffer (see vma_name_addr field below), including the + * terminating zero. + * + * If VMA name is longer that user-supplied maximum buffer size, + * -E2BIG error is returned. + * + * If this field is set to non-zero value, vma_name_addr should point + * to valid user space memory buffer of at least vma_name_size bytes. + * If set to zero, vma_name_addr should be set to zero as well + */ + __u32 vma_name_size; /* in/out */ + /* + * If set to non-zero value, signals the request to extract and return + * VMA's backing file's build ID, if the backing file is an ELF file + * and it contains embedded build ID. + * + * Kernel will set this field to zero, if VMA has no backing file, + * backing file is not an ELF file, or ELF file has no build ID + * embedded. + * + * Build ID is a binary value (not a string). Kernel will set + * build_id_size field to exact number of bytes used for build ID. + * If build ID is requested and present, but needs more bytes than + * user-supplied maximum buffer size (see build_id_addr field below), + * -E2BIG error will be returned. + * + * If this field is set to non-zero value, build_id_addr should point + * to valid user space memory buffer of at least build_id_size bytes. + * If set to zero, build_id_addr should be set to zero as well + */ + __u32 build_id_size; /* in/out */ + /* + * User-supplied address of a buffer of at least vma_name_size bytes + * for kernel to fill with matched VMA's name (see vma_name_size field + * description above for details). + * + * Should be set to zero if VMA name should not be returned. + */ + __u64 vma_name_addr; /* in */ + /* + * User-supplied address of a buffer of at least build_id_size bytes + * for kernel to fill with matched VMA's ELF build ID, if available + * (see build_id_size field description above for details). + * + * Should be set to zero if build ID should not be returned. + */ + __u64 build_id_addr; /* in */ +}; + #endif /* _UAPI_LINUX_FS_H */ diff --git a/tools/perf/trace/beauty/include/uapi/linux/mount.h b/tools/perf/trace/beauty/include/uapi/linux/mount.h index ad5478dbad00..225bc366ffcb 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/mount.h +++ b/tools/perf/trace/beauty/include/uapi/linux/mount.h @@ -154,7 +154,7 @@ struct mount_attr { */ struct statmount { __u32 size; /* Total size, including strings */ - __u32 __spare1; + __u32 mnt_opts; /* [str] Mount options of the mount */ __u64 mask; /* What results were written */ __u32 sb_dev_major; /* Device ID */ __u32 sb_dev_minor; @@ -172,7 +172,8 @@ struct statmount { __u64 propagate_from; /* Propagation from in current namespace */ __u32 mnt_root; /* [str] Root of mount relative to root of fs */ __u32 mnt_point; /* [str] Mountpoint relative to current root */ - __u64 __spare2[50]; + __u64 mnt_ns_id; /* ID of the mount namespace */ + __u64 __spare2[49]; char str[]; /* Variable size part containing strings */ }; @@ -188,10 +189,12 @@ struct mnt_id_req { __u32 spare; __u64 mnt_id; __u64 param; + __u64 mnt_ns_id; }; /* List of all mnt_id_req versions. */ #define MNT_ID_REQ_SIZE_VER0 24 /* sizeof first published struct */ +#define MNT_ID_REQ_SIZE_VER1 32 /* sizeof second published struct */ /* * @mask bits for statmount(2) @@ -202,10 +205,13 @@ struct mnt_id_req { #define STATMOUNT_MNT_ROOT 0x00000008U /* Want/got mnt_root */ #define STATMOUNT_MNT_POINT 0x00000010U /* Want/got mnt_point */ #define STATMOUNT_FS_TYPE 0x00000020U /* Want/got fs_type */ +#define STATMOUNT_MNT_NS_ID 0x00000040U /* Want/got mnt_ns_id */ +#define STATMOUNT_MNT_OPTS 0x00000080U /* Want/got mnt_opts */ /* * Special @mnt_id values that can be passed to listmount */ #define LSMT_ROOT 0xffffffffffffffff /* root mount */ +#define LISTMOUNT_REVERSE (1 << 0) /* List later mounts first */ #endif /* _UAPI_LINUX_MOUNT_H */ diff --git a/tools/perf/trace/beauty/include/uapi/linux/stat.h b/tools/perf/trace/beauty/include/uapi/linux/stat.h index 67626d535316..887a25286441 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/stat.h +++ b/tools/perf/trace/beauty/include/uapi/linux/stat.h @@ -126,9 +126,15 @@ struct statx { __u64 stx_mnt_id; __u32 stx_dio_mem_align; /* Memory buffer alignment for direct I/O */ __u32 stx_dio_offset_align; /* File offset alignment for direct I/O */ - __u64 stx_subvol; /* Subvolume identifier */ /* 0xa0 */ - __u64 __spare3[11]; /* Spare space for future expansion */ + __u64 stx_subvol; /* Subvolume identifier */ + __u32 stx_atomic_write_unit_min; /* Min atomic write unit in bytes */ + __u32 stx_atomic_write_unit_max; /* Max atomic write unit in bytes */ + /* 0xb0 */ + __u32 stx_atomic_write_segments_max; /* Max atomic write segment count */ + __u32 __spare1[1]; + /* 0xb8 */ + __u64 __spare3[9]; /* Spare space for future expansion */ /* 0x100 */ }; @@ -157,6 +163,7 @@ struct statx { #define STATX_DIOALIGN 0x00002000U /* Want/got direct I/O alignment info */ #define STATX_MNT_ID_UNIQUE 0x00004000U /* Want/got extended stx_mount_id */ #define STATX_SUBVOL 0x00008000U /* Want/got stx_subvol */ +#define STATX_WRITE_ATOMIC 0x00010000U /* Want/got atomic_write_* fields */ #define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */ @@ -192,6 +199,7 @@ struct statx { #define STATX_ATTR_MOUNT_ROOT 0x00002000 /* Root of a mount */ #define STATX_ATTR_VERITY 0x00100000 /* [I] Verity protected file */ #define STATX_ATTR_DAX 0x00200000 /* File is currently in DAX state */ +#define STATX_ATTR_WRITE_ATOMIC 0x00400000 /* File supports atomic write operations */ #endif /* _UAPI_LINUX_STAT_H */ diff --git a/tools/perf/trace/beauty/include/uapi/sound/asound.h b/tools/perf/trace/beauty/include/uapi/sound/asound.h index 628d46a0da92..8bf7e8a0eb6f 100644 --- a/tools/perf/trace/beauty/include/uapi/sound/asound.h +++ b/tools/perf/trace/beauty/include/uapi/sound/asound.h @@ -142,7 +142,7 @@ struct snd_hwdep_dsp_image { * * *****************************************************************************/ -#define SNDRV_PCM_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 17) +#define SNDRV_PCM_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 18) typedef unsigned long snd_pcm_uframes_t; typedef signed long snd_pcm_sframes_t; @@ -334,7 +334,7 @@ union snd_pcm_sync_id { unsigned char id[16]; unsigned short id16[8]; unsigned int id32[4]; -}; +} __attribute__((deprecated)); struct snd_pcm_info { unsigned int device; /* RO/WR (control): device number */ @@ -348,7 +348,7 @@ struct snd_pcm_info { int dev_subclass; /* SNDRV_PCM_SUBCLASS_* */ unsigned int subdevices_count; unsigned int subdevices_avail; - union snd_pcm_sync_id sync; /* hardware synchronization ID */ + unsigned char pad1[16]; /* was: hardware synchronization ID */ unsigned char reserved[64]; /* reserved for future... */ }; @@ -420,7 +420,8 @@ struct snd_pcm_hw_params { unsigned int rate_num; /* R: rate numerator */ unsigned int rate_den; /* R: rate denominator */ snd_pcm_uframes_t fifo_size; /* R: chip FIFO size in frames */ - unsigned char reserved[64]; /* reserved for future */ + unsigned char sync[16]; /* R: synchronization ID (perfect sync - one clock source) */ + unsigned char reserved[48]; /* reserved for future */ }; enum { diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 1730b852a947..6d075648d2cc 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -1141,7 +1141,7 @@ int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *samp int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *node, bool hide_unresolved) { - struct machine *machine = maps__machine(node->ms.maps); + struct machine *machine = node->ms.maps ? maps__machine(node->ms.maps) : NULL; maps__put(al->maps); al->maps = maps__get(node->ms.maps); diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile index b1e6817f1e54..3946d5254a1f 100644 --- a/tools/power/x86/turbostat/Makefile +++ b/tools/power/x86/turbostat/Makefile @@ -46,6 +46,7 @@ snapshot: turbostat @echo "#define GENMASK_ULL(h, l) (((~0ULL) << (l)) & (~0ULL >> (sizeof(long long) * 8 - 1 - (h))))" >> $(SNAPSHOT)/bits.h @echo '#define BUILD_BUG_ON(cond) do { enum { compile_time_check ## __COUNTER__ = 1/(!(cond)) }; } while (0)' > $(SNAPSHOT)/build_bug.h + @echo '#define __must_be_array(arr) 0' >> $(SNAPSHOT)/build_bug.h @echo PWD=. > $(SNAPSHOT)/Makefile @echo "CFLAGS += -DMSRHEADER='\"msr-index.h\"'" >> $(SNAPSHOT)/Makefile diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8 index 8d37acd39201..067717bce1d4 100644 --- a/tools/power/x86/turbostat/turbostat.8 +++ b/tools/power/x86/turbostat/turbostat.8 @@ -28,10 +28,13 @@ name as necessary to disambiguate it from others is necessary. Note that option .PP \fB--add attributes\fP add column with counter having specified 'attributes'. The 'location' attribute is required, all others are optional. .nf - location: {\fBmsrDDD\fP | \fBmsr0xXXX\fP | \fB/sys/path...\fP} + location: {\fBmsrDDD\fP | \fBmsr0xXXX\fP | \fB/sys/path...\fP | \fBperf/<device>/<event>\fP} msrDDD is a decimal offset, eg. msr16 msr0xXXX is a hex offset, eg. msr0x10 /sys/path... is an absolute path to a sysfs attribute + <device> is a perf device from /sys/bus/event_source/devices/<device> eg. cstate_core + <event> is a perf event for given device from /sys/bus/event_source/devices/<device>/events/<event> eg. c1-residency + perf/cstate_core/c1-residency would then use /sys/bus/event_source/devices/cstate_core/events/c1-residency scope: {\fBcpu\fP | \fBcore\fP | \fBpackage\fP} sample and print the counter for every cpu, core, or package. @@ -52,6 +55,39 @@ name as necessary to disambiguate it from others is necessary. Note that option as the column header. .fi .PP +\fB--add pmt,[attr_name=attr_value, ...]\fP add column with a PMT (Intel Platform Monitoring Technology) counter in a similar way to --add option above, but require PMT metadata to be supplied to correctly read and display the counter. The metadata can be found in the Intel PMT XML files, hosted at https://github.com/intel/Intel-PMT. For a complete example see "ADD PMT COUNTER EXAMPLE". +.nf + name="name_string" + For column header. + + type={\fBraw\fP} + 'raw' shows the counter contents in hex. + default: raw + + format={\fBraw\fP | \fBdelta\fP} + 'raw' shows the counter contents in hex. + 'delta' shows the difference in values during the measurement interval. + default: raw + + domain={\fBcpu%u\fP | \fBcore%u\fP | \fBpackage%u\fP} + 'cpu' per cpu/thread counter. + 'core' per core counter. + 'package' per package counter. + '%u' denotes id of the domain that the counter is associated with. For example core4 would mean that the counter is associated with core number 4. + + offset=\fB%u\fP + '%u' offset within the PMT MMIO region. + + lsb=\fB%u\fP + '%u' least significant bit within the 64 bit value read from 'offset'. Together with 'msb', used to form a read mask. + + msb=\fB%u\fP + '%u' most significant bit within the 64 bit value read from 'offset'. Together with 'lsb', used to form a read mask. + + guid=\fB%x\fP + '%x' hex identifier of the PMT MMIO region. +.fi +.PP \fB--cpu cpu-set\fP limit output to system summary plus the specified cpu-set. If cpu-set is the string "core", then the system summary plus the first CPU in each core are printed -- eg. subsequent HT siblings are not printed. Or if cpu-set is the string "package", then the system summary plus the first CPU in each package is printed. Otherwise, the system summary plus the specified set of CPUs are printed. The cpu-set is ordered from low to high, comma delimited with ".." and "-" permitted to denote a range. eg. 1,2,8,14..17,21-44 .PP \fB--hide column\fP do not show the specified built-in columns. May be invoked multiple times, or with a comma-separated list of column names. @@ -67,10 +103,10 @@ The column name "all" can be used to enable all disabled-by-default built-in cou .PP \fB--quiet\fP Do not decode and print the system configuration header information. .PP -+\fB--no-msr\fP Disable all the uses of the MSR driver. -+.PP -+\fB--no-perf\fP Disable all the uses of the perf API. -+.PP +\fB--no-msr\fP Disable all the uses of the MSR driver. +.PP +\fB--no-perf\fP Disable all the uses of the perf API. +.PP \fB--interval seconds\fP overrides the default 5.0 second measurement interval. .PP \fB--num_iterations num\fP number of the measurement iterations. @@ -320,7 +356,7 @@ available on all processors. Here we limit turbostat to showing just the CPU number for cpu0 - cpu3. We add a counter showing the 32-bit raw value of MSR 0x199 (MSR_IA32_PERF_CTL), labeling it with the column header, "PRF_CTRL", and display it only once, -afte the conclusion of a 0.1 second sleep. +after the conclusion of a 0.1 second sleep. .nf sudo ./turbostat --quiet --cpu 0-3 --show CPU --add msr0x199,u32,raw,PRF_CTRL sleep .1 0.101604 sec @@ -333,6 +369,56 @@ CPU PRF_CTRL .fi +.SH ADD PERF COUNTER EXAMPLE +Here we limit turbostat to showing just the CPU number for cpu0 - cpu3. +We add a counter showing time spent in C1 core cstate, +labeling it with the column header, "pCPU%c1", and display it only once, +after the conclusion of 0.1 second sleep. +We also show CPU%c1 built-in counter that should show similar values. +.nf +sudo ./turbostat --quiet --cpu 0-3 --show CPU,CPU%c1 --add perf/cstate_core/c1-residency,cpu,delta,percent,pCPU%c1 sleep .1 +0.102448 sec +CPU pCPU%c1 CPU%c1 +- 34.89 34.89 +0 45.99 45.99 +1 45.94 45.94 +2 23.83 23.83 +3 23.84 23.84 + +.fi + +.SH ADD PMT COUNTER EXAMPLE +Here we limit turbostat to showing just the CPU number 0. +We add two counters, showing crystal clock count and the DC6 residency. +All the parameters passed are based on the metadata found in the PMT XML files. + +For the crystal clock count, we +label it with the column header, "XTAL", +we set the type to 'raw', to read the number of clock ticks in hex, +we set the format to 'delta', to display the difference in ticks during the measurement interval, +we set the domain to 'package0', to collect it and associate it with the whole package number 0, +we set the offset to '0', which is a offset of the counter within the PMT MMIO region, +we set the lsb and msb to cover all 64 bits of the read 64 bit value, +and finally we set the guid to '0x1a067102', that identifies the PMT MMIO region to which the 'offset' is applied to read the counter value. + +For the DC6 residency counter, we +label it with the column header, "Die%c6", +we set the type to 'txtal_time', to obtain the percent residency value +we set the format to 'delta', to display the difference in ticks during the measurement interval, +we set the domain to 'package0', to collect it and associate it with the whole package number 0, +we set the offset to '0', which is a offset of the counter within the PMT MMIO region, +we set the lsb and msb to cover all 64 bits of the read 64 bit value, +and finally we set the guid to '0x1a067102', that identifies the PMT MMIO region to which the 'offset' is applied to read the counter value. + +.nf +sudo ./turbostat --quiet --cpu 0 --show CPU --add pmt,name=XTAL,type=raw,format=delta,domain=package0,offset=0,lsb=0,msb=63,guid=0x1a067102 --add pmt,name=Die%c6,type=txtal_time,format=delta,domain=package0,offset=120,lsb=0,msb=63,guid=0x1a067102 +0.104352 sec +CPU XTAL Die%c6 +- 0x0000006d4d957ca7 0.00 +0 0x0000006d4d957ca7 0.00 +0.102448 sec +.fi + .SH INPUT For interval-mode, turbostat will immediately end the current interval diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 9f5d053d4bc6..089220aaa5c9 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -9,6 +9,30 @@ #define _GNU_SOURCE #include MSRHEADER + +// copied from arch/x86/include/asm/cpu_device_id.h +#define VFM_MODEL_BIT 0 +#define VFM_FAMILY_BIT 8 +#define VFM_VENDOR_BIT 16 +#define VFM_RSVD_BIT 24 + +#define VFM_MODEL_MASK GENMASK(VFM_FAMILY_BIT - 1, VFM_MODEL_BIT) +#define VFM_FAMILY_MASK GENMASK(VFM_VENDOR_BIT - 1, VFM_FAMILY_BIT) +#define VFM_VENDOR_MASK GENMASK(VFM_RSVD_BIT - 1, VFM_VENDOR_BIT) + +#define VFM_MODEL(vfm) (((vfm) & VFM_MODEL_MASK) >> VFM_MODEL_BIT) +#define VFM_FAMILY(vfm) (((vfm) & VFM_FAMILY_MASK) >> VFM_FAMILY_BIT) +#define VFM_VENDOR(vfm) (((vfm) & VFM_VENDOR_MASK) >> VFM_VENDOR_BIT) + +#define VFM_MAKE(_vendor, _family, _model) ( \ + ((_model) << VFM_MODEL_BIT) | \ + ((_family) << VFM_FAMILY_BIT) | \ + ((_vendor) << VFM_VENDOR_BIT) \ +) +// end copied section + +#define X86_VENDOR_INTEL 0 + #include INTEL_FAMILY_HEADER #include BUILD_BUG_HEADER #include <stdarg.h> @@ -20,6 +44,7 @@ #include <sys/stat.h> #include <sys/select.h> #include <sys/resource.h> +#include <sys/mman.h> #include <fcntl.h> #include <signal.h> #include <sys/time.h> @@ -55,15 +80,39 @@ */ #define NAME_BYTES 20 #define PATH_BYTES 128 +#define PERF_NAME_BYTES 128 #define MAX_NOFILE 0x8000 +#define COUNTER_KIND_PERF_PREFIX "perf/" +#define COUNTER_KIND_PERF_PREFIX_LEN strlen(COUNTER_KIND_PERF_PREFIX) +#define PERF_DEV_NAME_BYTES 32 +#define PERF_EVT_NAME_BYTES 32 + enum counter_scope { SCOPE_CPU, SCOPE_CORE, SCOPE_PACKAGE }; enum counter_type { COUNTER_ITEMS, COUNTER_CYCLES, COUNTER_SECONDS, COUNTER_USEC, COUNTER_K2M }; enum counter_format { FORMAT_RAW, FORMAT_DELTA, FORMAT_PERCENT, FORMAT_AVERAGE }; -enum amperf_source { AMPERF_SOURCE_PERF, AMPERF_SOURCE_MSR }; -enum rapl_source { RAPL_SOURCE_NONE, RAPL_SOURCE_PERF, RAPL_SOURCE_MSR }; -enum cstate_source { CSTATE_SOURCE_NONE, CSTATE_SOURCE_PERF, CSTATE_SOURCE_MSR }; +enum counter_source { COUNTER_SOURCE_NONE, COUNTER_SOURCE_PERF, COUNTER_SOURCE_MSR }; + +struct perf_counter_info { + struct perf_counter_info *next; + + /* How to open the counter / What counter it is. */ + char device[PERF_DEV_NAME_BYTES]; + char event[PERF_EVT_NAME_BYTES]; + + /* How to show/format the counter. */ + char name[PERF_NAME_BYTES]; + unsigned int width; + enum counter_scope scope; + enum counter_type type; + enum counter_format format; + double scale; + + /* For reading the counter. */ + int *fd_perf_per_domain; + size_t num_domains; +}; struct sysfs_path { char path[PATH_BYTES]; @@ -144,6 +193,7 @@ struct msr_counter bic[] = { { 0x0, "SAM%mc6", NULL, 0, 0, 0, NULL, 0 }, { 0x0, "SAMMHz", NULL, 0, 0, 0, NULL, 0 }, { 0x0, "SAMAMHz", NULL, 0, 0, 0, NULL, 0 }, + { 0x0, "Die%c6", NULL, 0, 0, 0, NULL, 0 }, }; #define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter)) @@ -205,11 +255,12 @@ struct msr_counter bic[] = { #define BIC_SAM_mc6 (1ULL << 55) #define BIC_SAMMHz (1ULL << 56) #define BIC_SAMACTMHz (1ULL << 57) +#define BIC_Diec6 (1ULL << 58) #define BIC_TOPOLOGY (BIC_Package | BIC_Node | BIC_CoreCnt | BIC_PkgCnt | BIC_Core | BIC_CPU | BIC_Die ) #define BIC_THERMAL_PWR ( BIC_CoreTmp | BIC_PkgTmp | BIC_PkgWatt | BIC_CorWatt | BIC_GFXWatt | BIC_RAMWatt | BIC_PKG__ | BIC_RAM__) #define BIC_FREQUENCY (BIC_Avg_MHz | BIC_Busy | BIC_Bzy_MHz | BIC_TSC_MHz | BIC_GFXMHz | BIC_GFXACTMHz | BIC_SAMMHz | BIC_SAMACTMHz | BIC_UNCORE_MHZ) -#define BIC_IDLE (BIC_sysfs | BIC_CPU_c1 | BIC_CPU_c3 | BIC_CPU_c6 | BIC_CPU_c7 | BIC_GFX_rc6 | BIC_Pkgpc2 | BIC_Pkgpc3 | BIC_Pkgpc6 | BIC_Pkgpc7 | BIC_Pkgpc8 | BIC_Pkgpc9 | BIC_Pkgpc10 | BIC_CPU_LPI | BIC_SYS_LPI | BIC_Mod_c6 | BIC_Totl_c0 | BIC_Any_c0 | BIC_GFX_c0 | BIC_CPUGFX | BIC_SAM_mc6) +#define BIC_IDLE (BIC_sysfs | BIC_CPU_c1 | BIC_CPU_c3 | BIC_CPU_c6 | BIC_CPU_c7 | BIC_GFX_rc6 | BIC_Pkgpc2 | BIC_Pkgpc3 | BIC_Pkgpc6 | BIC_Pkgpc7 | BIC_Pkgpc8 | BIC_Pkgpc9 | BIC_Pkgpc10 | BIC_CPU_LPI | BIC_SYS_LPI | BIC_Mod_c6 | BIC_Totl_c0 | BIC_Any_c0 | BIC_GFX_c0 | BIC_CPUGFX | BIC_SAM_mc6 | BIC_Diec6) #define BIC_OTHER ( BIC_IRQ | BIC_SMI | BIC_ThreadC | BIC_CoreTmp | BIC_IPC) #define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC) @@ -252,7 +303,6 @@ char *proc_stat = "/proc/stat"; FILE *outf; int *fd_percpu; int *fd_instr_count_percpu; -struct amperf_group_fd *fd_amperf_percpu; /* File descriptors for perf group with APERF and MPERF counters. */ struct timeval interval_tv = { 5, 0 }; struct timespec interval_ts = { 5, 0 }; @@ -267,6 +317,7 @@ unsigned int summary_only; unsigned int list_header_only; unsigned int dump_only; unsigned int has_aperf; +unsigned int has_aperf_access; unsigned int has_epb; unsigned int has_turbo; unsigned int is_hybrid; @@ -307,7 +358,6 @@ unsigned int first_counter_read = 1; int ignore_stdin; bool no_msr; bool no_perf; -enum amperf_source amperf_source; enum gfx_sysfs_idx { GFX_rc6, @@ -367,7 +417,7 @@ struct platform_features { }; struct platform_data { - unsigned int model; + unsigned int vfm; const struct platform_features *features; }; @@ -910,75 +960,75 @@ static const struct platform_features amd_features_with_rapl = { }; static const struct platform_data turbostat_pdata[] = { - { INTEL_FAM6_NEHALEM, &nhm_features }, - { INTEL_FAM6_NEHALEM_G, &nhm_features }, - { INTEL_FAM6_NEHALEM_EP, &nhm_features }, - { INTEL_FAM6_NEHALEM_EX, &nhx_features }, - { INTEL_FAM6_WESTMERE, &nhm_features }, - { INTEL_FAM6_WESTMERE_EP, &nhm_features }, - { INTEL_FAM6_WESTMERE_EX, &nhx_features }, - { INTEL_FAM6_SANDYBRIDGE, &snb_features }, - { INTEL_FAM6_SANDYBRIDGE_X, &snx_features }, - { INTEL_FAM6_IVYBRIDGE, &ivb_features }, - { INTEL_FAM6_IVYBRIDGE_X, &ivx_features }, - { INTEL_FAM6_HASWELL, &hsw_features }, - { INTEL_FAM6_HASWELL_X, &hsx_features }, - { INTEL_FAM6_HASWELL_L, &hswl_features }, - { INTEL_FAM6_HASWELL_G, &hswg_features }, - { INTEL_FAM6_BROADWELL, &bdw_features }, - { INTEL_FAM6_BROADWELL_G, &bdwg_features }, - { INTEL_FAM6_BROADWELL_X, &bdx_features }, - { INTEL_FAM6_BROADWELL_D, &bdx_features }, - { INTEL_FAM6_SKYLAKE_L, &skl_features }, - { INTEL_FAM6_SKYLAKE, &skl_features }, - { INTEL_FAM6_SKYLAKE_X, &skx_features }, - { INTEL_FAM6_KABYLAKE_L, &skl_features }, - { INTEL_FAM6_KABYLAKE, &skl_features }, - { INTEL_FAM6_COMETLAKE, &skl_features }, - { INTEL_FAM6_COMETLAKE_L, &skl_features }, - { INTEL_FAM6_CANNONLAKE_L, &cnl_features }, - { INTEL_FAM6_ICELAKE_X, &icx_features }, - { INTEL_FAM6_ICELAKE_D, &icx_features }, - { INTEL_FAM6_ICELAKE_L, &cnl_features }, - { INTEL_FAM6_ICELAKE_NNPI, &cnl_features }, - { INTEL_FAM6_ROCKETLAKE, &cnl_features }, - { INTEL_FAM6_TIGERLAKE_L, &cnl_features }, - { INTEL_FAM6_TIGERLAKE, &cnl_features }, - { INTEL_FAM6_SAPPHIRERAPIDS_X, &spr_features }, - { INTEL_FAM6_EMERALDRAPIDS_X, &spr_features }, - { INTEL_FAM6_GRANITERAPIDS_X, &spr_features }, - { INTEL_FAM6_LAKEFIELD, &cnl_features }, - { INTEL_FAM6_ALDERLAKE, &adl_features }, - { INTEL_FAM6_ALDERLAKE_L, &adl_features }, - { INTEL_FAM6_RAPTORLAKE, &adl_features }, - { INTEL_FAM6_RAPTORLAKE_P, &adl_features }, - { INTEL_FAM6_RAPTORLAKE_S, &adl_features }, - { INTEL_FAM6_METEORLAKE, &cnl_features }, - { INTEL_FAM6_METEORLAKE_L, &cnl_features }, - { INTEL_FAM6_ARROWLAKE_H, &arl_features }, - { INTEL_FAM6_ARROWLAKE_U, &arl_features }, - { INTEL_FAM6_ARROWLAKE, &arl_features }, - { INTEL_FAM6_LUNARLAKE_M, &arl_features }, - { INTEL_FAM6_ATOM_SILVERMONT, &slv_features }, - { INTEL_FAM6_ATOM_SILVERMONT_D, &slvd_features }, - { INTEL_FAM6_ATOM_AIRMONT, &amt_features }, - { INTEL_FAM6_ATOM_GOLDMONT, &gmt_features }, - { INTEL_FAM6_ATOM_GOLDMONT_D, &gmtd_features }, - { INTEL_FAM6_ATOM_GOLDMONT_PLUS, &gmtp_features }, - { INTEL_FAM6_ATOM_TREMONT_D, &tmtd_features }, - { INTEL_FAM6_ATOM_TREMONT, &tmt_features }, - { INTEL_FAM6_ATOM_TREMONT_L, &tmt_features }, - { INTEL_FAM6_ATOM_GRACEMONT, &adl_features }, - { INTEL_FAM6_ATOM_CRESTMONT_X, &srf_features }, - { INTEL_FAM6_ATOM_CRESTMONT, &grr_features }, - { INTEL_FAM6_XEON_PHI_KNL, &knl_features }, - { INTEL_FAM6_XEON_PHI_KNM, &knl_features }, + { INTEL_NEHALEM, &nhm_features }, + { INTEL_NEHALEM_G, &nhm_features }, + { INTEL_NEHALEM_EP, &nhm_features }, + { INTEL_NEHALEM_EX, &nhx_features }, + { INTEL_WESTMERE, &nhm_features }, + { INTEL_WESTMERE_EP, &nhm_features }, + { INTEL_WESTMERE_EX, &nhx_features }, + { INTEL_SANDYBRIDGE, &snb_features }, + { INTEL_SANDYBRIDGE_X, &snx_features }, + { INTEL_IVYBRIDGE, &ivb_features }, + { INTEL_IVYBRIDGE_X, &ivx_features }, + { INTEL_HASWELL, &hsw_features }, + { INTEL_HASWELL_X, &hsx_features }, + { INTEL_HASWELL_L, &hswl_features }, + { INTEL_HASWELL_G, &hswg_features }, + { INTEL_BROADWELL, &bdw_features }, + { INTEL_BROADWELL_G, &bdwg_features }, + { INTEL_BROADWELL_X, &bdx_features }, + { INTEL_BROADWELL_D, &bdx_features }, + { INTEL_SKYLAKE_L, &skl_features }, + { INTEL_SKYLAKE, &skl_features }, + { INTEL_SKYLAKE_X, &skx_features }, + { INTEL_KABYLAKE_L, &skl_features }, + { INTEL_KABYLAKE, &skl_features }, + { INTEL_COMETLAKE, &skl_features }, + { INTEL_COMETLAKE_L, &skl_features }, + { INTEL_CANNONLAKE_L, &cnl_features }, + { INTEL_ICELAKE_X, &icx_features }, + { INTEL_ICELAKE_D, &icx_features }, + { INTEL_ICELAKE_L, &cnl_features }, + { INTEL_ICELAKE_NNPI, &cnl_features }, + { INTEL_ROCKETLAKE, &cnl_features }, + { INTEL_TIGERLAKE_L, &cnl_features }, + { INTEL_TIGERLAKE, &cnl_features }, + { INTEL_SAPPHIRERAPIDS_X, &spr_features }, + { INTEL_EMERALDRAPIDS_X, &spr_features }, + { INTEL_GRANITERAPIDS_X, &spr_features }, + { INTEL_LAKEFIELD, &cnl_features }, + { INTEL_ALDERLAKE, &adl_features }, + { INTEL_ALDERLAKE_L, &adl_features }, + { INTEL_RAPTORLAKE, &adl_features }, + { INTEL_RAPTORLAKE_P, &adl_features }, + { INTEL_RAPTORLAKE_S, &adl_features }, + { INTEL_METEORLAKE, &cnl_features }, + { INTEL_METEORLAKE_L, &cnl_features }, + { INTEL_ARROWLAKE_H, &arl_features }, + { INTEL_ARROWLAKE_U, &arl_features }, + { INTEL_ARROWLAKE, &arl_features }, + { INTEL_LUNARLAKE_M, &arl_features }, + { INTEL_ATOM_SILVERMONT, &slv_features }, + { INTEL_ATOM_SILVERMONT_D, &slvd_features }, + { INTEL_ATOM_AIRMONT, &amt_features }, + { INTEL_ATOM_GOLDMONT, &gmt_features }, + { INTEL_ATOM_GOLDMONT_D, &gmtd_features }, + { INTEL_ATOM_GOLDMONT_PLUS, &gmtp_features }, + { INTEL_ATOM_TREMONT_D, &tmtd_features }, + { INTEL_ATOM_TREMONT, &tmt_features }, + { INTEL_ATOM_TREMONT_L, &tmt_features }, + { INTEL_ATOM_GRACEMONT, &adl_features }, + { INTEL_ATOM_CRESTMONT_X, &srf_features }, + { INTEL_ATOM_CRESTMONT, &grr_features }, + { INTEL_XEON_PHI_KNL, &knl_features }, + { INTEL_XEON_PHI_KNM, &knl_features }, /* * Missing support for - * INTEL_FAM6_ICELAKE - * INTEL_FAM6_ATOM_SILVERMONT_MID - * INTEL_FAM6_ATOM_AIRMONT_MID - * INTEL_FAM6_ATOM_AIRMONT_NP + * INTEL_ICELAKE + * INTEL_ATOM_SILVERMONT_MID + * INTEL_ATOM_AIRMONT_MID + * INTEL_ATOM_AIRMONT_NP */ { 0, NULL }, }; @@ -1003,11 +1053,11 @@ void probe_platform_features(unsigned int family, unsigned int model) return; } - if (!genuine_intel || family != 6) + if (!genuine_intel) return; for (i = 0; turbostat_pdata[i].features; i++) { - if (turbostat_pdata[i].model == model) { + if (VFM_FAMILY(turbostat_pdata[i].vfm) == family && VFM_MODEL(turbostat_pdata[i].vfm) == model) { platform = turbostat_pdata[i].features; return; } @@ -1034,8 +1084,13 @@ size_t cpu_present_setsize, cpu_effective_setsize, cpu_allowed_setsize, cpu_affi #define MAX_ADDED_THREAD_COUNTERS 24 #define MAX_ADDED_CORE_COUNTERS 8 #define MAX_ADDED_PACKAGE_COUNTERS 16 +#define PMT_MAX_ADDED_THREAD_COUNTERS 24 +#define PMT_MAX_ADDED_CORE_COUNTERS 8 +#define PMT_MAX_ADDED_PACKAGE_COUNTERS 16 #define BITMASK_SIZE 32 +#define ZERO_ARRAY(arr) (memset(arr, 0, sizeof(arr)) + __must_be_array(arr)) + /* Indexes used to map data read from perf and MSRs into global variables */ enum rapl_rci_index { RAPL_RCI_INDEX_ENERGY_PKG = 0, @@ -1056,19 +1111,13 @@ enum rapl_unit { struct rapl_counter_info_t { unsigned long long data[NUM_RAPL_COUNTERS]; - enum rapl_source source[NUM_RAPL_COUNTERS]; + enum counter_source source[NUM_RAPL_COUNTERS]; unsigned long long flags[NUM_RAPL_COUNTERS]; double scale[NUM_RAPL_COUNTERS]; enum rapl_unit unit[NUM_RAPL_COUNTERS]; - - union { - /* Active when source == RAPL_SOURCE_MSR */ - struct { - unsigned long long msr[NUM_RAPL_COUNTERS]; - unsigned long long msr_mask[NUM_RAPL_COUNTERS]; - int msr_shift[NUM_RAPL_COUNTERS]; - }; - }; + unsigned long long msr[NUM_RAPL_COUNTERS]; + unsigned long long msr_mask[NUM_RAPL_COUNTERS]; + int msr_shift[NUM_RAPL_COUNTERS]; int fd_perf; }; @@ -1224,7 +1273,7 @@ enum ccstate_rci_index { struct cstate_counter_info_t { unsigned long long data[NUM_CSTATE_COUNTERS]; - enum cstate_source source[NUM_CSTATE_COUNTERS]; + enum counter_source source[NUM_CSTATE_COUNTERS]; unsigned long long msr[NUM_CSTATE_COUNTERS]; int fd_perf_core; int fd_perf_pkg; @@ -1361,6 +1410,167 @@ static struct cstate_counter_arch_info ccstate_counter_arch_infos[] = { }, }; +/* Indexes used to map data read from perf and MSRs into global variables */ +enum msr_rci_index { + MSR_RCI_INDEX_APERF = 0, + MSR_RCI_INDEX_MPERF = 1, + MSR_RCI_INDEX_SMI = 2, + NUM_MSR_COUNTERS, +}; + +struct msr_counter_info_t { + unsigned long long data[NUM_MSR_COUNTERS]; + enum counter_source source[NUM_MSR_COUNTERS]; + unsigned long long msr[NUM_MSR_COUNTERS]; + unsigned long long msr_mask[NUM_MSR_COUNTERS]; + int fd_perf; +}; + +struct msr_counter_info_t *msr_counter_info; +unsigned int msr_counter_info_size; + +struct msr_counter_arch_info { + const char *perf_subsys; + const char *perf_name; + unsigned long long msr; + unsigned long long msr_mask; + unsigned int rci_index; /* Maps data from perf counters to global variables */ + bool needed; + bool present; +}; + +enum msr_arch_info_index { + MSR_ARCH_INFO_APERF_INDEX = 0, + MSR_ARCH_INFO_MPERF_INDEX = 1, + MSR_ARCH_INFO_SMI_INDEX = 2, +}; + +static struct msr_counter_arch_info msr_counter_arch_infos[] = { + [MSR_ARCH_INFO_APERF_INDEX] = { + .perf_subsys = "msr", + .perf_name = "aperf", + .msr = MSR_IA32_APERF, + .msr_mask = 0xFFFFFFFFFFFFFFFF, + .rci_index = MSR_RCI_INDEX_APERF, + }, + + [MSR_ARCH_INFO_MPERF_INDEX] = { + .perf_subsys = "msr", + .perf_name = "mperf", + .msr = MSR_IA32_MPERF, + .msr_mask = 0xFFFFFFFFFFFFFFFF, + .rci_index = MSR_RCI_INDEX_MPERF, + }, + + [MSR_ARCH_INFO_SMI_INDEX] = { + .perf_subsys = "msr", + .perf_name = "smi", + .msr = MSR_SMI_COUNT, + .msr_mask = 0xFFFFFFFF, + .rci_index = MSR_RCI_INDEX_SMI, + }, +}; + +/* Can be redefined when compiling, useful for testing. */ +#ifndef SYSFS_TELEM_PATH +#define SYSFS_TELEM_PATH "/sys/class/intel_pmt" +#endif + +#define PMT_COUNTER_MTL_DC6_OFFSET 120 +#define PMT_COUNTER_MTL_DC6_LSB 0 +#define PMT_COUNTER_MTL_DC6_MSB 63 +#define PMT_MTL_DC6_GUID 0x1a067102 + +#define PMT_COUNTER_NAME_SIZE_BYTES 16 +#define PMT_COUNTER_TYPE_NAME_SIZE_BYTES 32 + +struct pmt_mmio { + struct pmt_mmio *next; + + unsigned int guid; + unsigned int size; + + /* Base pointer to the mmaped memory. */ + void *mmio_base; + + /* + * Offset to be applied to the mmio_base + * to get the beginning of the PMT counters for given GUID. + */ + unsigned long pmt_offset; +} *pmt_mmios; + +enum pmt_datatype { + PMT_TYPE_RAW, + PMT_TYPE_XTAL_TIME, +}; + +struct pmt_domain_info { + /* + * Pointer to the MMIO obtained by applying a counter offset + * to the mmio_base of the mmaped region for the given GUID. + * + * This is where to read the raw value of the counter from. + */ + unsigned long *pcounter; +}; + +struct pmt_counter { + struct pmt_counter *next; + + /* PMT metadata */ + char name[PMT_COUNTER_NAME_SIZE_BYTES]; + enum pmt_datatype type; + enum counter_scope scope; + unsigned int lsb; + unsigned int msb; + + /* BIC-like metadata */ + enum counter_format format; + + unsigned int num_domains; + struct pmt_domain_info *domains; +}; + +unsigned int pmt_counter_get_width(const struct pmt_counter *p) +{ + return (p->msb - p->lsb) + 1; +} + +void pmt_counter_resize_(struct pmt_counter *pcounter, unsigned int new_size) +{ + struct pmt_domain_info *new_mem; + + new_mem = (struct pmt_domain_info *)reallocarray(pcounter->domains, new_size, sizeof(*pcounter->domains)); + if (!new_mem) { + fprintf(stderr, "%s: failed to allocate memory for PMT counters\n", __func__); + exit(1); + } + + /* Zero initialize just allocated memory. */ + const size_t num_new_domains = new_size - pcounter->num_domains; + + memset(&new_mem[pcounter->num_domains], 0, num_new_domains * sizeof(*pcounter->domains)); + + pcounter->num_domains = new_size; + pcounter->domains = new_mem; +} + +void pmt_counter_resize(struct pmt_counter *pcounter, unsigned int new_size) +{ + /* + * Allocate more memory ahead of time. + * + * Always allocate space for at least 8 elements + * and double the size when growing. + */ + if (new_size < 8) + new_size = 8; + new_size = MAX(new_size, pcounter->num_domains * 2); + + pmt_counter_resize_(pcounter, new_size); +} + struct thread_data { struct timeval tv_begin; struct timeval tv_end; @@ -1378,6 +1588,8 @@ struct thread_data { unsigned int flags; bool is_atom; unsigned long long counter[MAX_ADDED_THREAD_COUNTERS]; + unsigned long long perf_counter[MAX_ADDED_THREAD_COUNTERS]; + unsigned long long pmt_counter[PMT_MAX_ADDED_THREAD_COUNTERS]; } *thread_even, *thread_odd; struct core_data { @@ -1391,6 +1603,8 @@ struct core_data { unsigned int core_id; unsigned long long core_throt_cnt; unsigned long long counter[MAX_ADDED_CORE_COUNTERS]; + unsigned long long perf_counter[MAX_ADDED_CORE_COUNTERS]; + unsigned long long pmt_counter[PMT_MAX_ADDED_CORE_COUNTERS]; } *core_even, *core_odd; struct pkg_data { @@ -1423,7 +1637,10 @@ struct pkg_data { struct rapl_counter rapl_dram_perf_status; /* MSR_DRAM_PERF_STATUS */ unsigned int pkg_temp_c; unsigned int uncore_mhz; + unsigned long long die_c6; unsigned long long counter[MAX_ADDED_PACKAGE_COUNTERS]; + unsigned long long perf_counter[MAX_ADDED_PACKAGE_COUNTERS]; + unsigned long long pmt_counter[PMT_MAX_ADDED_PACKAGE_COUNTERS]; } *package_even, *package_odd; #define ODD_COUNTERS thread_odd, core_odd, package_odd @@ -1558,12 +1775,25 @@ int idx_valid(int idx) } struct sys_counters { + /* MSR added counters */ unsigned int added_thread_counters; unsigned int added_core_counters; unsigned int added_package_counters; struct msr_counter *tp; struct msr_counter *cp; struct msr_counter *pp; + + /* perf added counters */ + unsigned int added_thread_perf_counters; + unsigned int added_core_perf_counters; + unsigned int added_package_perf_counters; + struct perf_counter_info *perf_tp; + struct perf_counter_info *perf_cp; + struct perf_counter_info *perf_pp; + + struct pmt_counter *pmt_tp; + struct pmt_counter *pmt_cp; + struct pmt_counter *pmt_pp; } sys; static size_t free_msr_counters_(struct msr_counter **pp) @@ -1747,7 +1977,7 @@ int get_msr_fd(int cpu) static void bic_disable_msr_access(void) { - const unsigned long bic_msrs = BIC_SMI | BIC_Mod_c6 | BIC_CoreTmp | + const unsigned long bic_msrs = BIC_Mod_c6 | BIC_CoreTmp | BIC_Totl_c0 | BIC_Any_c0 | BIC_GFX_c0 | BIC_CPUGFX | BIC_PkgTmp; bic_enabled &= ~bic_msrs; @@ -1823,6 +2053,23 @@ int probe_msr(int cpu, off_t offset) return 0; } +/* Convert CPU ID to domain ID for given added perf counter. */ +unsigned int cpu_to_domain(const struct perf_counter_info *pc, int cpu) +{ + switch (pc->scope) { + case SCOPE_CPU: + return cpu; + + case SCOPE_CORE: + return cpus[cpu].physical_core_id; + + case SCOPE_PACKAGE: + return cpus[cpu].physical_package_id; + } + + __builtin_unreachable(); +} + #define MAX_DEFERRED 16 char *deferred_add_names[MAX_DEFERRED]; char *deferred_skip_names[MAX_DEFERRED]; @@ -1846,9 +2093,12 @@ void help(void) "to print statistics, until interrupted.\n" " -a, --add add a counter\n" " eg. --add msr0x10,u64,cpu,delta,MY_TSC\n" + " eg. --add perf/cstate_pkg/c2-residency,package,delta,percent,perfPC2\n" + " eg. --add pmt,name=XTAL,type=raw,domain=package0,offset=0,lsb=0,msb=63,guid=0x1a067102\n" " -c, --cpu cpu-set limit output to summary plus cpu-set:\n" " {core | package | j,k,l..m,n-p }\n" " -d, --debug displays usec, Time_Of_Day_Seconds and more debugging\n" + " debug messages are printed to stderr\n" " -D, --Dump displays the raw counter values\n" " -e, --enable [all | column]\n" " shows all or the specified disabled column\n" @@ -1955,6 +2205,8 @@ unsigned long long bic_lookup(char *name_list, enum show_hide_mode mode) void print_header(char *delim) { struct msr_counter *mp; + struct perf_counter_info *pp; + struct pmt_counter *ppmt; int printed = 0; if (DO_BIC(BIC_USEC)) @@ -2012,6 +2264,40 @@ void print_header(char *delim) } } + for (pp = sys.perf_tp; pp; pp = pp->next) { + + if (pp->format == FORMAT_RAW) { + if (pp->width == 64) + outp += sprintf(outp, "%s%18.18s", (printed++ ? delim : ""), pp->name); + else + outp += sprintf(outp, "%s%10.10s", (printed++ ? delim : ""), pp->name); + } else { + if ((pp->type == COUNTER_ITEMS) && sums_need_wide_columns) + outp += sprintf(outp, "%s%8s", (printed++ ? delim : ""), pp->name); + else + outp += sprintf(outp, "%s%s", (printed++ ? delim : ""), pp->name); + } + } + + ppmt = sys.pmt_tp; + while (ppmt) { + switch (ppmt->type) { + case PMT_TYPE_RAW: + if (pmt_counter_get_width(ppmt) <= 32) + outp += sprintf(outp, "%s%10.10s", (printed++ ? delim : ""), ppmt->name); + else + outp += sprintf(outp, "%s%18.18s", (printed++ ? delim : ""), ppmt->name); + + break; + + case PMT_TYPE_XTAL_TIME: + outp += sprintf(outp, "%s%s", delim, ppmt->name); + break; + } + + ppmt = ppmt->next; + } + if (DO_BIC(BIC_CPU_c1)) outp += sprintf(outp, "%sCPU%%c1", (printed++ ? delim : "")); if (DO_BIC(BIC_CPU_c3)) @@ -2052,6 +2338,40 @@ void print_header(char *delim) } } + for (pp = sys.perf_cp; pp; pp = pp->next) { + + if (pp->format == FORMAT_RAW) { + if (pp->width == 64) + outp += sprintf(outp, "%s%18.18s", (printed++ ? delim : ""), pp->name); + else + outp += sprintf(outp, "%s%10.10s", (printed++ ? delim : ""), pp->name); + } else { + if ((pp->type == COUNTER_ITEMS) && sums_need_wide_columns) + outp += sprintf(outp, "%s%8s", (printed++ ? delim : ""), pp->name); + else + outp += sprintf(outp, "%s%s", (printed++ ? delim : ""), pp->name); + } + } + + ppmt = sys.pmt_cp; + while (ppmt) { + switch (ppmt->type) { + case PMT_TYPE_RAW: + if (pmt_counter_get_width(ppmt) <= 32) + outp += sprintf(outp, "%s%10.10s", (printed++ ? delim : ""), ppmt->name); + else + outp += sprintf(outp, "%s%18.18s", (printed++ ? delim : ""), ppmt->name); + + break; + + case PMT_TYPE_XTAL_TIME: + outp += sprintf(outp, "%s%s", delim, ppmt->name); + break; + } + + ppmt = ppmt->next; + } + if (DO_BIC(BIC_PkgTmp)) outp += sprintf(outp, "%sPkgTmp", (printed++ ? delim : "")); @@ -2096,6 +2416,8 @@ void print_header(char *delim) outp += sprintf(outp, "%sPkg%%pc9", (printed++ ? delim : "")); if (DO_BIC(BIC_Pkgpc10)) outp += sprintf(outp, "%sPk%%pc10", (printed++ ? delim : "")); + if (DO_BIC(BIC_Diec6)) + outp += sprintf(outp, "%sDie%%c6", (printed++ ? delim : "")); if (DO_BIC(BIC_CPU_LPI)) outp += sprintf(outp, "%sCPU%%LPI", (printed++ ? delim : "")); if (DO_BIC(BIC_SYS_LPI)) @@ -2147,6 +2469,40 @@ void print_header(char *delim) } } + for (pp = sys.perf_pp; pp; pp = pp->next) { + + if (pp->format == FORMAT_RAW) { + if (pp->width == 64) + outp += sprintf(outp, "%s%18.18s", (printed++ ? delim : ""), pp->name); + else + outp += sprintf(outp, "%s%10.10s", (printed++ ? delim : ""), pp->name); + } else { + if ((pp->type == COUNTER_ITEMS) && sums_need_wide_columns) + outp += sprintf(outp, "%s%8s", (printed++ ? delim : ""), pp->name); + else + outp += sprintf(outp, "%s%s", (printed++ ? delim : ""), pp->name); + } + } + + ppmt = sys.pmt_pp; + while (ppmt) { + switch (ppmt->type) { + case PMT_TYPE_RAW: + if (pmt_counter_get_width(ppmt) <= 32) + outp += sprintf(outp, "%s%10.10s", (printed++ ? delim : ""), ppmt->name); + else + outp += sprintf(outp, "%s%18.18s", (printed++ ? delim : ""), ppmt->name); + + break; + + case PMT_TYPE_XTAL_TIME: + outp += sprintf(outp, "%s%s", delim, ppmt->name); + break; + } + + ppmt = ppmt->next; + } + outp += sprintf(outp, "\n"); } @@ -2267,6 +2623,8 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data char *fmt8; int i; struct msr_counter *mp; + struct perf_counter_info *pp; + struct pmt_counter *ppmt; char *delim = "\t"; int printed = 0; @@ -2404,6 +2762,51 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data } } + /* Added perf counters */ + for (i = 0, pp = sys.perf_tp; pp; ++i, pp = pp->next) { + if (pp->format == FORMAT_RAW) { + if (pp->width == 32) + outp += + sprintf(outp, "%s0x%08x", (printed++ ? delim : ""), + (unsigned int)t->perf_counter[i]); + else + outp += sprintf(outp, "%s0x%016llx", (printed++ ? delim : ""), t->perf_counter[i]); + } else if (pp->format == FORMAT_DELTA) { + if ((pp->type == COUNTER_ITEMS) && sums_need_wide_columns) + outp += sprintf(outp, "%s%8lld", (printed++ ? delim : ""), t->perf_counter[i]); + else + outp += sprintf(outp, "%s%lld", (printed++ ? delim : ""), t->perf_counter[i]); + } else if (pp->format == FORMAT_PERCENT) { + if (pp->type == COUNTER_USEC) + outp += + sprintf(outp, "%s%.2f", (printed++ ? delim : ""), + t->perf_counter[i] / interval_float / 10000); + else + outp += + sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * t->perf_counter[i] / tsc); + } + } + + for (i = 0, ppmt = sys.pmt_tp; ppmt; i++, ppmt = ppmt->next) { + switch (ppmt->type) { + case PMT_TYPE_RAW: + if (pmt_counter_get_width(ppmt) <= 32) + outp += sprintf(outp, "%s0x%08x", (printed++ ? delim : ""), + (unsigned int)t->pmt_counter[i]); + else + outp += sprintf(outp, "%s0x%016llx", (printed++ ? delim : ""), t->pmt_counter[i]); + + break; + + case PMT_TYPE_XTAL_TIME: + const unsigned long value_raw = t->pmt_counter[i]; + const double value_converted = 100.0 * value_raw / crystal_hz / interval_float; + + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted); + break; + } + } + /* C1 */ if (DO_BIC(BIC_CPU_c1)) outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * t->c1 / tsc); @@ -2447,6 +2850,44 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data } } + for (i = 0, pp = sys.perf_cp; pp; i++, pp = pp->next) { + if (pp->format == FORMAT_RAW) { + if (pp->width == 32) + outp += + sprintf(outp, "%s0x%08x", (printed++ ? delim : ""), + (unsigned int)c->perf_counter[i]); + else + outp += sprintf(outp, "%s0x%016llx", (printed++ ? delim : ""), c->perf_counter[i]); + } else if (pp->format == FORMAT_DELTA) { + if ((pp->type == COUNTER_ITEMS) && sums_need_wide_columns) + outp += sprintf(outp, "%s%8lld", (printed++ ? delim : ""), c->perf_counter[i]); + else + outp += sprintf(outp, "%s%lld", (printed++ ? delim : ""), c->perf_counter[i]); + } else if (pp->format == FORMAT_PERCENT) { + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->perf_counter[i] / tsc); + } + } + + for (i = 0, ppmt = sys.pmt_cp; ppmt; i++, ppmt = ppmt->next) { + switch (ppmt->type) { + case PMT_TYPE_RAW: + if (pmt_counter_get_width(ppmt) <= 32) + outp += sprintf(outp, "%s0x%08x", (printed++ ? delim : ""), + (unsigned int)c->pmt_counter[i]); + else + outp += sprintf(outp, "%s0x%016llx", (printed++ ? delim : ""), c->pmt_counter[i]); + + break; + + case PMT_TYPE_XTAL_TIME: + const unsigned long value_raw = c->pmt_counter[i]; + const double value_converted = 100.0 * value_raw / crystal_hz / interval_float; + + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted); + break; + } + } + fmt8 = "%s%.2f"; if (DO_BIC(BIC_CorWatt) && platform->has_per_core_rapl) @@ -2526,6 +2967,10 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data if (DO_BIC(BIC_Pkgpc10)) outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pc10 / tsc); + if (DO_BIC(BIC_Diec6)) + outp += + sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->die_c6 / crystal_hz / interval_float); + if (DO_BIC(BIC_CPU_LPI)) { if (p->cpu_lpi >= 0) outp += @@ -2601,6 +3046,47 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), (unsigned int)p->counter[i] / 1000); } + for (i = 0, pp = sys.perf_pp; pp; i++, pp = pp->next) { + if (pp->format == FORMAT_RAW) { + if (pp->width == 32) + outp += + sprintf(outp, "%s0x%08x", (printed++ ? delim : ""), + (unsigned int)p->perf_counter[i]); + else + outp += sprintf(outp, "%s0x%016llx", (printed++ ? delim : ""), p->perf_counter[i]); + } else if (pp->format == FORMAT_DELTA) { + if ((pp->type == COUNTER_ITEMS) && sums_need_wide_columns) + outp += sprintf(outp, "%s%8lld", (printed++ ? delim : ""), p->perf_counter[i]); + else + outp += sprintf(outp, "%s%lld", (printed++ ? delim : ""), p->perf_counter[i]); + } else if (pp->format == FORMAT_PERCENT) { + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->perf_counter[i] / tsc); + } else if (pp->type == COUNTER_K2M) { + outp += + sprintf(outp, "%s%d", (printed++ ? delim : ""), (unsigned int)p->perf_counter[i] / 1000); + } + } + + for (i = 0, ppmt = sys.pmt_pp; ppmt; i++, ppmt = ppmt->next) { + switch (ppmt->type) { + case PMT_TYPE_RAW: + if (pmt_counter_get_width(ppmt) <= 32) + outp += sprintf(outp, "%s0x%08x", (printed++ ? delim : ""), + (unsigned int)p->pmt_counter[i]); + else + outp += sprintf(outp, "%s0x%016llx", (printed++ ? delim : ""), p->pmt_counter[i]); + + break; + + case PMT_TYPE_XTAL_TIME: + const unsigned long value_raw = p->pmt_counter[i]; + const double value_converted = 100.0 * value_raw / crystal_hz / interval_float; + + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted); + break; + } + } + done: if (*(outp - 1) != '\n') outp += sprintf(outp, "\n"); @@ -2654,6 +3140,8 @@ int delta_package(struct pkg_data *new, struct pkg_data *old) { int i; struct msr_counter *mp; + struct perf_counter_info *pp; + struct pmt_counter *ppmt; if (DO_BIC(BIC_Totl_c0)) old->pkg_wtd_core_c0 = new->pkg_wtd_core_c0 - old->pkg_wtd_core_c0; @@ -2674,6 +3162,7 @@ int delta_package(struct pkg_data *new, struct pkg_data *old) old->pc8 = new->pc8 - old->pc8; old->pc9 = new->pc9 - old->pc9; old->pc10 = new->pc10 - old->pc10; + old->die_c6 = new->die_c6 - old->die_c6; old->cpu_lpi = new->cpu_lpi - old->cpu_lpi; old->sys_lpi = new->sys_lpi - old->sys_lpi; old->pkg_temp_c = new->pkg_temp_c; @@ -2714,6 +3203,22 @@ int delta_package(struct pkg_data *new, struct pkg_data *old) old->counter[i] = new->counter[i] - old->counter[i]; } + for (i = 0, pp = sys.perf_pp; pp; i++, pp = pp->next) { + if (pp->format == FORMAT_RAW) + old->perf_counter[i] = new->perf_counter[i]; + else if (pp->format == FORMAT_AVERAGE) + old->perf_counter[i] = new->perf_counter[i]; + else + old->perf_counter[i] = new->perf_counter[i] - old->perf_counter[i]; + } + + for (i = 0, ppmt = sys.pmt_pp; ppmt; i++, ppmt = ppmt->next) { + if (ppmt->format == FORMAT_RAW) + old->pmt_counter[i] = new->pmt_counter[i]; + else + old->pmt_counter[i] = new->pmt_counter[i] - old->pmt_counter[i]; + } + return 0; } @@ -2721,6 +3226,8 @@ void delta_core(struct core_data *new, struct core_data *old) { int i; struct msr_counter *mp; + struct perf_counter_info *pp; + struct pmt_counter *ppmt; old->c3 = new->c3 - old->c3; old->c6 = new->c6 - old->c6; @@ -2737,6 +3244,20 @@ void delta_core(struct core_data *new, struct core_data *old) else old->counter[i] = new->counter[i] - old->counter[i]; } + + for (i = 0, pp = sys.perf_cp; pp; i++, pp = pp->next) { + if (pp->format == FORMAT_RAW) + old->perf_counter[i] = new->perf_counter[i]; + else + old->perf_counter[i] = new->perf_counter[i] - old->perf_counter[i]; + } + + for (i = 0, ppmt = sys.pmt_cp; ppmt; i++, ppmt = ppmt->next) { + if (ppmt->format == FORMAT_RAW) + old->pmt_counter[i] = new->pmt_counter[i]; + else + old->pmt_counter[i] = new->pmt_counter[i] - old->pmt_counter[i]; + } } int soft_c1_residency_display(int bic) @@ -2754,6 +3275,8 @@ int delta_thread(struct thread_data *new, struct thread_data *old, struct core_d { int i; struct msr_counter *mp; + struct perf_counter_info *pp; + struct pmt_counter *ppmt; /* we run cpuid just the 1st time, copy the results */ if (DO_BIC(BIC_APIC)) @@ -2832,6 +3355,21 @@ int delta_thread(struct thread_data *new, struct thread_data *old, struct core_d else old->counter[i] = new->counter[i] - old->counter[i]; } + + for (i = 0, pp = sys.perf_tp; pp; i++, pp = pp->next) { + if (pp->format == FORMAT_RAW) + old->perf_counter[i] = new->perf_counter[i]; + else + old->perf_counter[i] = new->perf_counter[i] - old->perf_counter[i]; + } + + for (i = 0, ppmt = sys.pmt_tp; ppmt; i++, ppmt = ppmt->next) { + if (ppmt->format == FORMAT_RAW) + old->pmt_counter[i] = new->pmt_counter[i]; + else + old->pmt_counter[i] = new->pmt_counter[i] - old->pmt_counter[i]; + } + return 0; } @@ -2908,6 +3446,7 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data p->pc8 = 0; p->pc9 = 0; p->pc10 = 0; + p->die_c6 = 0; p->cpu_lpi = 0; p->sys_lpi = 0; @@ -2934,6 +3473,14 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) p->counter[i] = 0; + + memset(&t->perf_counter[0], 0, sizeof(t->perf_counter)); + memset(&c->perf_counter[0], 0, sizeof(c->perf_counter)); + memset(&p->perf_counter[0], 0, sizeof(p->perf_counter)); + + memset(&t->pmt_counter[0], 0, ARRAY_SIZE(t->pmt_counter)); + memset(&c->pmt_counter[0], 0, ARRAY_SIZE(c->pmt_counter)); + memset(&p->pmt_counter[0], 0, ARRAY_SIZE(p->pmt_counter)); } void rapl_counter_accumulate(struct rapl_counter *dst, const struct rapl_counter *src) @@ -2954,6 +3501,8 @@ int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) { int i; struct msr_counter *mp; + struct perf_counter_info *pp; + struct pmt_counter *ppmt; /* copy un-changing apic_id's */ if (DO_BIC(BIC_APIC)) @@ -2984,6 +3533,16 @@ int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) average.threads.counter[i] += t->counter[i]; } + for (i = 0, pp = sys.perf_tp; pp; i++, pp = pp->next) { + if (pp->format == FORMAT_RAW) + continue; + average.threads.perf_counter[i] += t->perf_counter[i]; + } + + for (i = 0, ppmt = sys.pmt_tp; ppmt; i++, ppmt = ppmt->next) { + average.threads.pmt_counter[i] += t->pmt_counter[i]; + } + /* sum per-core values only for 1st thread in core */ if (!is_cpu_first_thread_in_core(t, c, p)) return 0; @@ -3004,6 +3563,16 @@ int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) average.cores.counter[i] += c->counter[i]; } + for (i = 0, pp = sys.perf_cp; pp; i++, pp = pp->next) { + if (pp->format == FORMAT_RAW) + continue; + average.cores.perf_counter[i] += c->perf_counter[i]; + } + + for (i = 0, ppmt = sys.pmt_cp; ppmt; i++, ppmt = ppmt->next) { + average.cores.pmt_counter[i] += c->pmt_counter[i]; + } + /* sum per-pkg values only for 1st core in pkg */ if (!is_cpu_first_core_in_package(t, c, p)) return 0; @@ -3027,6 +3596,7 @@ int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) average.packages.pc8 += p->pc8; average.packages.pc9 += p->pc9; average.packages.pc10 += p->pc10; + average.packages.die_c6 += p->die_c6; average.packages.cpu_lpi = p->cpu_lpi; average.packages.sys_lpi = p->sys_lpi; @@ -3055,6 +3625,18 @@ int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) else average.packages.counter[i] += p->counter[i]; } + + for (i = 0, pp = sys.perf_pp; pp; i++, pp = pp->next) { + if ((pp->format == FORMAT_RAW) && (topo.num_packages == 0)) + average.packages.perf_counter[i] = p->perf_counter[i]; + else + average.packages.perf_counter[i] += p->perf_counter[i]; + } + + for (i = 0, ppmt = sys.pmt_pp; ppmt; i++, ppmt = ppmt->next) { + average.packages.pmt_counter[i] += p->pmt_counter[i]; + } + return 0; } @@ -3066,6 +3648,8 @@ void compute_average(struct thread_data *t, struct core_data *c, struct pkg_data { int i; struct msr_counter *mp; + struct perf_counter_info *pp; + struct pmt_counter *ppmt; clear_counters(&average.threads, &average.cores, &average.packages); @@ -3108,6 +3692,7 @@ void compute_average(struct thread_data *t, struct core_data *c, struct pkg_data average.packages.pc8 /= topo.allowed_packages; average.packages.pc9 /= topo.allowed_packages; average.packages.pc10 /= topo.allowed_packages; + average.packages.die_c6 /= topo.allowed_packages; for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) { if (mp->format == FORMAT_RAW) @@ -3137,6 +3722,45 @@ void compute_average(struct thread_data *t, struct core_data *c, struct pkg_data } average.packages.counter[i] /= topo.allowed_packages; } + + for (i = 0, pp = sys.perf_tp; pp; i++, pp = pp->next) { + if (pp->format == FORMAT_RAW) + continue; + if (pp->type == COUNTER_ITEMS) { + if (average.threads.perf_counter[i] > 9999999) + sums_need_wide_columns = 1; + continue; + } + average.threads.perf_counter[i] /= topo.allowed_cpus; + } + for (i = 0, pp = sys.perf_cp; pp; i++, pp = pp->next) { + if (pp->format == FORMAT_RAW) + continue; + if (pp->type == COUNTER_ITEMS) { + if (average.cores.perf_counter[i] > 9999999) + sums_need_wide_columns = 1; + } + average.cores.perf_counter[i] /= topo.allowed_cores; + } + for (i = 0, pp = sys.perf_pp; pp; i++, pp = pp->next) { + if (pp->format == FORMAT_RAW) + continue; + if (pp->type == COUNTER_ITEMS) { + if (average.packages.perf_counter[i] > 9999999) + sums_need_wide_columns = 1; + } + average.packages.perf_counter[i] /= topo.allowed_packages; + } + + for (i = 0, ppmt = sys.pmt_tp; ppmt; i++, ppmt = ppmt->next) { + average.threads.pmt_counter[i] /= topo.allowed_cpus; + } + for (i = 0, ppmt = sys.pmt_cp; ppmt; i++, ppmt = ppmt->next) { + average.cores.pmt_counter[i] /= topo.allowed_cores; + } + for (i = 0, ppmt = sys.pmt_pp; ppmt; i++, ppmt = ppmt->next) { + average.packages.pmt_counter[i] /= topo.allowed_packages; + } } static unsigned long long rdtsc(void) @@ -3382,30 +4006,6 @@ static unsigned int read_perf_counter_info_n(const char *const path, const char return v; } -static unsigned int read_msr_type(void) -{ - const char *const path = "/sys/bus/event_source/devices/msr/type"; - const char *const format = "%u"; - - return read_perf_counter_info_n(path, format); -} - -static unsigned int read_aperf_config(void) -{ - const char *const path = "/sys/bus/event_source/devices/msr/events/aperf"; - const char *const format = "event=%x"; - - return read_perf_counter_info_n(path, format); -} - -static unsigned int read_mperf_config(void) -{ - const char *const path = "/sys/bus/event_source/devices/msr/events/mperf"; - const char *const format = "event=%x"; - - return read_perf_counter_info_n(path, format); -} - static unsigned int read_perf_type(const char *subsys) { const char *const path_format = "/sys/bus/event_source/devices/%s/type"; @@ -3417,15 +4017,55 @@ static unsigned int read_perf_type(const char *subsys) return read_perf_counter_info_n(path, format); } -static unsigned int read_rapl_config(const char *subsys, const char *event_name) +static unsigned int read_perf_config(const char *subsys, const char *event_name) { const char *const path_format = "/sys/bus/event_source/devices/%s/events/%s"; - const char *const format = "event=%x"; + FILE *fconfig = NULL; char path[128]; + char config_str[64]; + unsigned int config; + unsigned int umask; + bool has_config = false; + bool has_umask = false; + unsigned int ret = -1; snprintf(path, sizeof(path), path_format, subsys, event_name); - return read_perf_counter_info_n(path, format); + fconfig = fopen(path, "r"); + if (!fconfig) + return -1; + + if (fgets(config_str, ARRAY_SIZE(config_str), fconfig) != config_str) + goto cleanup_and_exit; + + for (char *pconfig_str = &config_str[0]; pconfig_str;) { + if (sscanf(pconfig_str, "event=%x", &config) == 1) { + has_config = true; + goto next; + } + + if (sscanf(pconfig_str, "umask=%x", &umask) == 1) { + has_umask = true; + goto next; + } + +next: + pconfig_str = strchr(pconfig_str, ','); + if (pconfig_str) { + *pconfig_str = '\0'; + ++pconfig_str; + } + } + + if (!has_umask) + umask = 0; + + if (has_config) + ret = (umask << 8) | config; + +cleanup_and_exit: + fclose(fconfig); + return ret; } static unsigned int read_perf_rapl_unit(const char *subsys, const char *event_name) @@ -3444,7 +4084,7 @@ static unsigned int read_perf_rapl_unit(const char *subsys, const char *event_na return RAPL_UNIT_INVALID; } -static double read_perf_rapl_scale(const char *subsys, const char *event_name) +static double read_perf_scale(const char *subsys, const char *event_name) { const char *const path_format = "/sys/bus/event_source/devices/%s/events/%s.scale"; const char *const format = "%lf"; @@ -3459,130 +4099,12 @@ static double read_perf_rapl_scale(const char *subsys, const char *event_name) return scale; } -static struct amperf_group_fd open_amperf_fd(int cpu) -{ - const unsigned int msr_type = read_msr_type(); - const unsigned int aperf_config = read_aperf_config(); - const unsigned int mperf_config = read_mperf_config(); - struct amperf_group_fd fds = {.aperf = -1, .mperf = -1 }; - - fds.aperf = open_perf_counter(cpu, msr_type, aperf_config, -1, PERF_FORMAT_GROUP); - fds.mperf = open_perf_counter(cpu, msr_type, mperf_config, fds.aperf, PERF_FORMAT_GROUP); - - return fds; -} - -static int get_amperf_fd(int cpu) -{ - assert(fd_amperf_percpu); - - if (fd_amperf_percpu[cpu].aperf) - return fd_amperf_percpu[cpu].aperf; - - fd_amperf_percpu[cpu] = open_amperf_fd(cpu); - - return fd_amperf_percpu[cpu].aperf; -} - -/* Read APERF, MPERF and TSC using the perf API. */ -static int read_aperf_mperf_tsc_perf(struct thread_data *t, int cpu) -{ - union { - struct { - unsigned long nr_entries; - unsigned long aperf; - unsigned long mperf; - }; - - unsigned long as_array[3]; - } cnt; - - const int fd_amperf = get_amperf_fd(cpu); - - /* - * Read the TSC with rdtsc, because we want the absolute value and not - * the offset from the start of the counter. - */ - t->tsc = rdtsc(); - - const int n = read(fd_amperf, &cnt.as_array[0], sizeof(cnt.as_array)); - - if (n != sizeof(cnt.as_array)) - return -2; - - t->aperf = cnt.aperf * aperf_mperf_multiplier; - t->mperf = cnt.mperf * aperf_mperf_multiplier; - - return 0; -} - -/* Read APERF, MPERF and TSC using the MSR driver and rdtsc instruction. */ -static int read_aperf_mperf_tsc_msr(struct thread_data *t, int cpu) -{ - unsigned long long tsc_before, tsc_between, tsc_after, aperf_time, mperf_time; - int aperf_mperf_retry_count = 0; - - /* - * The TSC, APERF and MPERF must be read together for - * APERF/MPERF and MPERF/TSC to give accurate results. - * - * Unfortunately, APERF and MPERF are read by - * individual system call, so delays may occur - * between them. If the time to read them - * varies by a large amount, we re-read them. - */ - - /* - * This initial dummy APERF read has been seen to - * reduce jitter in the subsequent reads. - */ - - if (get_msr(cpu, MSR_IA32_APERF, &t->aperf)) - return -3; - -retry: - t->tsc = rdtsc(); /* re-read close to APERF */ - - tsc_before = t->tsc; - - if (get_msr(cpu, MSR_IA32_APERF, &t->aperf)) - return -3; - - tsc_between = rdtsc(); - - if (get_msr(cpu, MSR_IA32_MPERF, &t->mperf)) - return -4; - - tsc_after = rdtsc(); - - aperf_time = tsc_between - tsc_before; - mperf_time = tsc_after - tsc_between; - - /* - * If the system call latency to read APERF and MPERF - * differ by more than 2x, then try again. - */ - if ((aperf_time > (2 * mperf_time)) || (mperf_time > (2 * aperf_time))) { - aperf_mperf_retry_count++; - if (aperf_mperf_retry_count < 5) - goto retry; - else - warnx("cpu%d jitter %lld %lld", cpu, aperf_time, mperf_time); - } - aperf_mperf_retry_count = 0; - - t->aperf = t->aperf * aperf_mperf_multiplier; - t->mperf = t->mperf * aperf_mperf_multiplier; - - return 0; -} - size_t rapl_counter_info_count_perf(const struct rapl_counter_info_t *rci) { size_t ret = 0; for (int i = 0; i < NUM_RAPL_COUNTERS; ++i) - if (rci->source[i] == RAPL_SOURCE_PERF) + if (rci->source[i] == COUNTER_SOURCE_PERF) ++ret; return ret; @@ -3593,7 +4115,7 @@ static size_t cstate_counter_info_count_perf(const struct cstate_counter_info_t size_t ret = 0; for (int i = 0; i < NUM_CSTATE_COUNTERS; ++i) - if (cci->source[i] == CSTATE_SOURCE_PERF) + if (cci->source[i] == COUNTER_SOURCE_PERF) ++ret; return ret; @@ -3611,7 +4133,7 @@ int get_rapl_counters(int cpu, unsigned int domain, struct core_data *c, struct unsigned long long perf_data[NUM_RAPL_COUNTERS + 1]; struct rapl_counter_info_t *rci; - if (debug) + if (debug >= 2) fprintf(stderr, "%s: cpu%d domain%d\n", __func__, cpu, domain); assert(rapl_counter_info_perdomain); @@ -3634,14 +4156,14 @@ int get_rapl_counters(int cpu, unsigned int domain, struct core_data *c, struct for (unsigned int i = 0, pi = 1; i < NUM_RAPL_COUNTERS; ++i) { switch (rci->source[i]) { - case RAPL_SOURCE_NONE: + case COUNTER_SOURCE_NONE: break; - case RAPL_SOURCE_PERF: + case COUNTER_SOURCE_PERF: assert(pi < ARRAY_SIZE(perf_data)); assert(rci->fd_perf != -1); - if (debug) + if (debug >= 2) fprintf(stderr, "Reading rapl counter via perf at %u (%llu %e %lf)\n", i, perf_data[pi], rci->scale[i], perf_data[pi] * rci->scale[i]); @@ -3650,8 +4172,8 @@ int get_rapl_counters(int cpu, unsigned int domain, struct core_data *c, struct ++pi; break; - case RAPL_SOURCE_MSR: - if (debug) + case COUNTER_SOURCE_MSR: + if (debug >= 2) fprintf(stderr, "Reading rapl counter via msr at %u\n", i); assert(!no_msr); @@ -3709,15 +4231,15 @@ int get_cstate_counters(unsigned int cpu, struct thread_data *t, struct core_dat struct cstate_counter_info_t *cci; - if (debug) + if (debug >= 2) fprintf(stderr, "%s: cpu%d\n", __func__, cpu); assert(ccstate_counter_info); assert(cpu <= ccstate_counter_info_size); - memset(perf_data, 0, sizeof(perf_data)); - memset(perf_data_core, 0, sizeof(perf_data_core)); - memset(perf_data_pkg, 0, sizeof(perf_data_pkg)); + ZERO_ARRAY(perf_data); + ZERO_ARRAY(perf_data_core); + ZERO_ARRAY(perf_data_pkg); cci = &ccstate_counter_info[cpu]; @@ -3772,30 +4294,28 @@ int get_cstate_counters(unsigned int cpu, struct thread_data *t, struct core_dat for (unsigned int i = 0, pi = 0; i < NUM_CSTATE_COUNTERS; ++i) { switch (cci->source[i]) { - case CSTATE_SOURCE_NONE: + case COUNTER_SOURCE_NONE: break; - case CSTATE_SOURCE_PERF: + case COUNTER_SOURCE_PERF: assert(pi < ARRAY_SIZE(perf_data)); assert(cci->fd_perf_core != -1 || cci->fd_perf_pkg != -1); - if (debug) { + if (debug >= 2) fprintf(stderr, "cstate via %s %u: %llu\n", "perf", i, perf_data[pi]); - } cci->data[i] = perf_data[pi]; ++pi; break; - case CSTATE_SOURCE_MSR: + case COUNTER_SOURCE_MSR: assert(!no_msr); if (get_msr(cpu, cci->msr[i], &cci->data[i])) return -13 - i; - if (debug) { + if (debug >= 2) fprintf(stderr, "cstate via %s0x%llx %u: %llu\n", "msr", cci->msr[i], i, cci->data[i]); - } break; } @@ -3809,7 +4329,7 @@ int get_cstate_counters(unsigned int cpu, struct thread_data *t, struct core_dat * when invoked for the thread sibling. */ #define PERF_COUNTER_WRITE_DATA(out_counter, index) do { \ - if (cci->source[index] != CSTATE_SOURCE_NONE) \ + if (cci->source[index] != COUNTER_SOURCE_NONE) \ out_counter = cci->data[index]; \ } while (0) @@ -3833,6 +4353,135 @@ int get_cstate_counters(unsigned int cpu, struct thread_data *t, struct core_dat return 0; } +size_t msr_counter_info_count_perf(const struct msr_counter_info_t *mci) +{ + size_t ret = 0; + + for (int i = 0; i < NUM_MSR_COUNTERS; ++i) + if (mci->source[i] == COUNTER_SOURCE_PERF) + ++ret; + + return ret; +} + +int get_smi_aperf_mperf(unsigned int cpu, struct thread_data *t) +{ + unsigned long long perf_data[NUM_MSR_COUNTERS + 1]; + + struct msr_counter_info_t *mci; + + if (debug >= 2) + fprintf(stderr, "%s: cpu%d\n", __func__, cpu); + + assert(msr_counter_info); + assert(cpu <= msr_counter_info_size); + + mci = &msr_counter_info[cpu]; + + ZERO_ARRAY(perf_data); + ZERO_ARRAY(mci->data); + + if (mci->fd_perf != -1) { + const size_t num_perf_counters = msr_counter_info_count_perf(mci); + const ssize_t expected_read_size = (num_perf_counters + 1) * sizeof(unsigned long long); + const ssize_t actual_read_size = read(mci->fd_perf, &perf_data[0], sizeof(perf_data)); + + if (actual_read_size != expected_read_size) + err(-1, "%s: failed to read perf_data (%zu %zu)", __func__, expected_read_size, + actual_read_size); + } + + for (unsigned int i = 0, pi = 1; i < NUM_MSR_COUNTERS; ++i) { + switch (mci->source[i]) { + case COUNTER_SOURCE_NONE: + break; + + case COUNTER_SOURCE_PERF: + assert(pi < ARRAY_SIZE(perf_data)); + assert(mci->fd_perf != -1); + + if (debug >= 2) + fprintf(stderr, "Reading msr counter via perf at %u: %llu\n", i, perf_data[pi]); + + mci->data[i] = perf_data[pi]; + + ++pi; + break; + + case COUNTER_SOURCE_MSR: + assert(!no_msr); + + if (get_msr(cpu, mci->msr[i], &mci->data[i])) + return -2 - i; + + mci->data[i] &= mci->msr_mask[i]; + + if (debug >= 2) + fprintf(stderr, "Reading msr counter via msr at %u: %llu\n", i, mci->data[i]); + + break; + } + } + + BUILD_BUG_ON(NUM_MSR_COUNTERS != 3); + t->aperf = mci->data[MSR_RCI_INDEX_APERF]; + t->mperf = mci->data[MSR_RCI_INDEX_MPERF]; + t->smi_count = mci->data[MSR_RCI_INDEX_SMI]; + + return 0; +} + +int perf_counter_info_read_values(struct perf_counter_info *pp, int cpu, unsigned long long *out, size_t out_size) +{ + unsigned int domain; + unsigned long long value; + int fd_counter; + + for (size_t i = 0; pp; ++i, pp = pp->next) { + domain = cpu_to_domain(pp, cpu); + assert(domain < pp->num_domains); + + fd_counter = pp->fd_perf_per_domain[domain]; + + if (fd_counter == -1) + continue; + + if (read(fd_counter, &value, sizeof(value)) != sizeof(value)) + return 1; + + assert(i < out_size); + out[i] = value * pp->scale; + } + + return 0; +} + +unsigned long pmt_gen_value_mask(unsigned int lsb, unsigned int msb) +{ + unsigned long mask; + + if (msb == 63) + mask = 0xffffffffffffffff; + else + mask = ((1 << (msb + 1)) - 1); + + mask -= (1 << lsb) - 1; + + return mask; +} + +unsigned long pmt_read_counter(struct pmt_counter *ppmt, unsigned int domain_id) +{ + assert(domain_id < ppmt->num_domains); + + const unsigned long *pmmio = ppmt->domains[domain_id].pcounter; + const unsigned long value = pmmio ? *pmmio : 0; + const unsigned long value_mask = pmt_gen_value_mask(ppmt->lsb, ppmt->msb); + const unsigned long value_shift = ppmt->lsb; + + return (value & value_mask) >> value_shift; +} + /* * get_counters(...) * migrate to cpu @@ -3843,6 +4492,7 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) int cpu = t->cpu_id; unsigned long long msr; struct msr_counter *mp; + struct pmt_counter *pp; int i; int status; @@ -3858,24 +4508,7 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) t->tsc = rdtsc(); /* we are running on local CPU of interest */ - if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz) || DO_BIC(BIC_IPC) - || soft_c1_residency_display(BIC_Avg_MHz)) { - int status = -1; - - assert(!no_perf || !no_msr); - - switch (amperf_source) { - case AMPERF_SOURCE_PERF: - status = read_aperf_mperf_tsc_perf(t, cpu); - break; - case AMPERF_SOURCE_MSR: - status = read_aperf_mperf_tsc_msr(t, cpu); - break; - } - - if (status != 0) - return status; - } + get_smi_aperf_mperf(cpu, t); if (DO_BIC(BIC_IPC)) if (read(get_instr_count_fd(cpu), &t->instr_count, sizeof(long long)) != sizeof(long long)) @@ -3883,11 +4516,6 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) if (DO_BIC(BIC_IRQ)) t->irq_count = irqs_per_cpu[cpu]; - if (DO_BIC(BIC_SMI)) { - if (get_msr(cpu, MSR_SMI_COUNT, &msr)) - return -5; - t->smi_count = msr & 0xFFFFFFFF; - } get_cstate_counters(cpu, t, c, p); @@ -3896,6 +4524,12 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) return -10; } + if (perf_counter_info_read_values(sys.perf_tp, cpu, t->perf_counter, MAX_ADDED_THREAD_COUNTERS)) + return -10; + + for (i = 0, pp = sys.pmt_tp; pp; i++, pp = pp->next) + t->pmt_counter[i] = pmt_read_counter(pp, t->cpu_id); + /* collect core counters only for 1st thread in core */ if (!is_cpu_first_thread_in_core(t, c, p)) goto done; @@ -3934,6 +4568,12 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) return -10; } + if (perf_counter_info_read_values(sys.perf_cp, cpu, c->perf_counter, MAX_ADDED_CORE_COUNTERS)) + return -10; + + for (i = 0, pp = sys.pmt_cp; pp; i++, pp = pp->next) + c->pmt_counter[i] = pmt_read_counter(pp, c->core_id); + /* collect package counters only for 1st core in package */ if (!is_cpu_first_core_in_package(t, c, p)) goto done; @@ -4006,6 +4646,13 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) if (get_mp(cpu, mp, &p->counter[i], path)) return -10; } + + if (perf_counter_info_read_values(sys.perf_pp, cpu, p->perf_counter, MAX_ADDED_PACKAGE_COUNTERS)) + return -10; + + for (i = 0, pp = sys.pmt_pp; pp; i++, pp = pp->next) + p->pmt_counter[i] = pmt_read_counter(pp, p->package_id); + done: gettimeofday(&t->tv_end, (struct timezone *)NULL); @@ -4469,25 +5116,6 @@ void free_fd_percpu(void) fd_percpu = NULL; } -void free_fd_amperf_percpu(void) -{ - int i; - - if (!fd_amperf_percpu) - return; - - for (i = 0; i < topo.max_cpu_num + 1; ++i) { - if (fd_amperf_percpu[i].mperf != 0) - close(fd_amperf_percpu[i].mperf); - - if (fd_amperf_percpu[i].aperf != 0) - close(fd_amperf_percpu[i].aperf); - } - - free(fd_amperf_percpu); - fd_amperf_percpu = NULL; -} - void free_fd_instr_count_percpu(void) { if (!fd_instr_count_percpu) @@ -4522,6 +5150,21 @@ void free_fd_cstate(void) ccstate_counter_info_size = 0; } +void free_fd_msr(void) +{ + if (!msr_counter_info) + return; + + for (int cpu = 0; cpu < topo.max_cpu_num; ++cpu) { + if (msr_counter_info[cpu].fd_perf != -1) + close(msr_counter_info[cpu].fd_perf); + } + + free(msr_counter_info); + msr_counter_info = NULL; + msr_counter_info_size = 0; +} + void free_fd_rapl_percpu(void) { if (!rapl_counter_info_perdomain) @@ -4539,6 +5182,36 @@ void free_fd_rapl_percpu(void) rapl_counter_info_perdomain_size = 0; } +void free_fd_added_perf_counters_(struct perf_counter_info *pp) +{ + if (!pp) + return; + + if (!pp->fd_perf_per_domain) + return; + + while (pp) { + for (size_t domain = 0; domain < pp->num_domains; ++domain) { + if (pp->fd_perf_per_domain[domain] != -1) { + close(pp->fd_perf_per_domain[domain]); + pp->fd_perf_per_domain[domain] = -1; + } + } + + free(pp->fd_perf_per_domain); + pp->fd_perf_per_domain = NULL; + + pp = pp->next; + } +} + +void free_fd_added_perf_counters(void) +{ + free_fd_added_perf_counters_(sys.perf_tp); + free_fd_added_perf_counters_(sys.perf_cp); + free_fd_added_perf_counters_(sys.perf_pp); +} + void free_all_buffers(void) { int i; @@ -4581,9 +5254,10 @@ void free_all_buffers(void) free_fd_percpu(); free_fd_instr_count_percpu(); - free_fd_amperf_percpu(); + free_fd_msr(); free_fd_rapl_percpu(); free_fd_cstate(); + free_fd_added_perf_counters(); free(irq_column_2_cpu); free(irqs_per_cpu); @@ -4918,16 +5592,22 @@ static void update_effective_set(bool startup) } void linux_perf_init(void); +void msr_perf_init(void); void rapl_perf_init(void); void cstate_perf_init(void); +void added_perf_counters_init(void); +void pmt_init(void); void re_initialize(void) { free_all_buffers(); setup_all_buffers(false); linux_perf_init(); + msr_perf_init(); rapl_perf_init(); cstate_perf_init(); + added_perf_counters_init(); + pmt_init(); fprintf(outf, "turbostat: re-initialized with num_cpus %d, allowed_cpus %d\n", topo.num_cpus, topo.allowed_cpus); } @@ -6779,22 +7459,13 @@ static int has_instr_count_access(void) return has_access; } -bool is_aperf_access_required(void) -{ - return BIC_IS_ENABLED(BIC_Avg_MHz) - || BIC_IS_ENABLED(BIC_Busy) - || BIC_IS_ENABLED(BIC_Bzy_MHz) - || BIC_IS_ENABLED(BIC_IPC) - || BIC_IS_ENABLED(BIC_CPU_c1); -} - int add_rapl_perf_counter_(int cpu, struct rapl_counter_info_t *rci, const struct rapl_counter_arch_info *cai, double *scale_, enum rapl_unit *unit_) { if (no_perf) return -1; - const double scale = read_perf_rapl_scale(cai->perf_subsys, cai->perf_name); + const double scale = read_perf_scale(cai->perf_subsys, cai->perf_name); if (scale == 0.0) return -1; @@ -6805,7 +7476,7 @@ int add_rapl_perf_counter_(int cpu, struct rapl_counter_info_t *rci, const struc return -1; const unsigned int rapl_type = read_perf_type(cai->perf_subsys); - const unsigned int rapl_energy_pkg_config = read_rapl_config(cai->perf_subsys, cai->perf_name); + const unsigned int rapl_energy_pkg_config = read_perf_config(cai->perf_subsys, cai->perf_name); const int fd_counter = open_perf_counter(cpu, rapl_type, rapl_energy_pkg_config, rci->fd_perf, PERF_FORMAT_GROUP); @@ -6826,7 +7497,7 @@ int add_rapl_perf_counter(int cpu, struct rapl_counter_info_t *rci, const struct { int ret = add_rapl_perf_counter_(cpu, rci, cai, scale, unit); - if (debug) + if (debug >= 2) fprintf(stderr, "%s: %d (cpu: %d)\n", __func__, ret, cpu); return ret; @@ -6846,14 +7517,6 @@ void linux_perf_init(void) if (fd_instr_count_percpu == NULL) err(-1, "calloc fd_instr_count_percpu"); } - - const bool aperf_required = is_aperf_access_required(); - - if (aperf_required && has_aperf && amperf_source == AMPERF_SOURCE_PERF) { - fd_amperf_percpu = calloc(topo.max_cpu_num + 1, sizeof(*fd_amperf_percpu)); - if (fd_amperf_percpu == NULL) - err(-1, "calloc fd_amperf_percpu"); - } } void rapl_perf_init(void) @@ -6875,7 +7538,7 @@ void rapl_perf_init(void) rci->fd_perf = -1; for (size_t i = 0; i < NUM_RAPL_COUNTERS; ++i) { rci->data[i] = 0; - rci->source[i] = RAPL_SOURCE_NONE; + rci->source[i] = COUNTER_SOURCE_NONE; } } @@ -6917,14 +7580,14 @@ void rapl_perf_init(void) /* Use perf API for this counter */ if (!no_perf && cai->perf_name && add_rapl_perf_counter(cpu, rci, cai, &scale, &unit) != -1) { - rci->source[cai->rci_index] = RAPL_SOURCE_PERF; + rci->source[cai->rci_index] = COUNTER_SOURCE_PERF; rci->scale[cai->rci_index] = scale * cai->compat_scale; rci->unit[cai->rci_index] = unit; rci->flags[cai->rci_index] = cai->flags; /* Use MSR for this counter */ } else if (!no_msr && cai->msr && probe_msr(cpu, cai->msr) == 0) { - rci->source[cai->rci_index] = RAPL_SOURCE_MSR; + rci->source[cai->rci_index] = COUNTER_SOURCE_MSR; rci->msr[cai->rci_index] = cai->msr; rci->msr_mask[cai->rci_index] = cai->msr_mask; rci->msr_shift[cai->rci_index] = cai->msr_shift; @@ -6934,7 +7597,7 @@ void rapl_perf_init(void) } } - if (rci->source[cai->rci_index] != RAPL_SOURCE_NONE) + if (rci->source[cai->rci_index] != COUNTER_SOURCE_NONE) has_counter = 1; } @@ -6946,75 +7609,11 @@ void rapl_perf_init(void) free(domain_visited); } -static int has_amperf_access_via_msr(void) -{ - if (no_msr) - return 0; - - if (probe_msr(base_cpu, MSR_IA32_APERF)) - return 0; - - if (probe_msr(base_cpu, MSR_IA32_MPERF)) - return 0; - - return 1; -} - -static int has_amperf_access_via_perf(void) -{ - struct amperf_group_fd fds; - - /* - * Cache the last result, so we don't warn the user multiple times - * - * Negative means cached, no access - * Zero means not cached - * Positive means cached, has access - */ - static int has_access_cached; - - if (no_perf) - return 0; - - if (has_access_cached != 0) - return has_access_cached > 0; - - fds = open_amperf_fd(base_cpu); - has_access_cached = (fds.aperf != -1) && (fds.mperf != -1); - - if (fds.aperf == -1) - warnx("Failed to access %s. Some of the counters may not be available\n" - "\tRun as root to enable them or use %s to disable the access explicitly", - "APERF perf counter", "--no-perf"); - else - close(fds.aperf); - - if (fds.mperf == -1) - warnx("Failed to access %s. Some of the counters may not be available\n" - "\tRun as root to enable them or use %s to disable the access explicitly", - "MPERF perf counter", "--no-perf"); - else - close(fds.mperf); - - if (has_access_cached == 0) - has_access_cached = -1; - - return has_access_cached > 0; -} - -/* Check if we can access APERF and MPERF */ +/* Assumes msr_counter_info is populated */ static int has_amperf_access(void) { - if (!is_aperf_access_required()) - return 0; - - if (!no_msr && has_amperf_access_via_msr()) - return 1; - - if (!no_perf && has_amperf_access_via_perf()) - return 1; - - return 0; + return msr_counter_arch_infos[MSR_ARCH_INFO_APERF_INDEX].present && + msr_counter_arch_infos[MSR_ARCH_INFO_MPERF_INDEX].present; } int *get_cstate_perf_group_fd(struct cstate_counter_info_t *cci, const char *group_name) @@ -7039,7 +7638,7 @@ int add_cstate_perf_counter_(int cpu, struct cstate_counter_info_t *cci, const s return -1; const unsigned int type = read_perf_type(cai->perf_subsys); - const unsigned int config = read_rapl_config(cai->perf_subsys, cai->perf_name); + const unsigned int config = read_perf_config(cai->perf_subsys, cai->perf_name); const int fd_counter = open_perf_counter(cpu, type, config, *pfd_group, PERF_FORMAT_GROUP); @@ -7057,12 +7656,120 @@ int add_cstate_perf_counter(int cpu, struct cstate_counter_info_t *cci, const st { int ret = add_cstate_perf_counter_(cpu, cci, cai); - if (debug) + if (debug >= 2) fprintf(stderr, "%s: %d (cpu: %d)\n", __func__, ret, cpu); return ret; } +int add_msr_perf_counter_(int cpu, struct msr_counter_info_t *cci, const struct msr_counter_arch_info *cai) +{ + if (no_perf) + return -1; + + const unsigned int type = read_perf_type(cai->perf_subsys); + const unsigned int config = read_perf_config(cai->perf_subsys, cai->perf_name); + + const int fd_counter = open_perf_counter(cpu, type, config, cci->fd_perf, PERF_FORMAT_GROUP); + + if (fd_counter == -1) + return -1; + + /* If it's the first counter opened, make it a group descriptor */ + if (cci->fd_perf == -1) + cci->fd_perf = fd_counter; + + return fd_counter; +} + +int add_msr_perf_counter(int cpu, struct msr_counter_info_t *cci, const struct msr_counter_arch_info *cai) +{ + int ret = add_msr_perf_counter_(cpu, cci, cai); + + if (debug) + fprintf(stderr, "%s: %s/%s: %d (cpu: %d)\n", __func__, cai->perf_subsys, cai->perf_name, ret, cpu); + + return ret; +} + +void msr_perf_init_(void) +{ + const int mci_num = topo.max_cpu_num + 1; + + msr_counter_info = calloc(mci_num, sizeof(*msr_counter_info)); + if (!msr_counter_info) + err(1, "calloc msr_counter_info"); + msr_counter_info_size = mci_num; + + for (int cpu = 0; cpu < mci_num; ++cpu) + msr_counter_info[cpu].fd_perf = -1; + + for (int cidx = 0; cidx < NUM_MSR_COUNTERS; ++cidx) { + + struct msr_counter_arch_info *cai = &msr_counter_arch_infos[cidx]; + + cai->present = false; + + for (int cpu = 0; cpu < mci_num; ++cpu) { + + struct msr_counter_info_t *const cci = &msr_counter_info[cpu]; + + if (cpu_is_not_allowed(cpu)) + continue; + + if (cai->needed) { + /* Use perf API for this counter */ + if (!no_perf && cai->perf_name && add_msr_perf_counter(cpu, cci, cai) != -1) { + cci->source[cai->rci_index] = COUNTER_SOURCE_PERF; + cai->present = true; + + /* User MSR for this counter */ + } else if (!no_msr && cai->msr && probe_msr(cpu, cai->msr) == 0) { + cci->source[cai->rci_index] = COUNTER_SOURCE_MSR; + cci->msr[cai->rci_index] = cai->msr; + cci->msr_mask[cai->rci_index] = cai->msr_mask; + cai->present = true; + } + } + } + } +} + +/* Initialize data for reading perf counters from the MSR group. */ +void msr_perf_init(void) +{ + bool need_amperf = false, need_smi = false; + const bool need_soft_c1 = (!platform->has_msr_core_c1_res) && (platform->supported_cstates & CC1); + + need_amperf = BIC_IS_ENABLED(BIC_Avg_MHz) || BIC_IS_ENABLED(BIC_Busy) || BIC_IS_ENABLED(BIC_Bzy_MHz) + || BIC_IS_ENABLED(BIC_IPC) || need_soft_c1; + + if (BIC_IS_ENABLED(BIC_SMI)) + need_smi = true; + + /* Enable needed counters */ + msr_counter_arch_infos[MSR_ARCH_INFO_APERF_INDEX].needed = need_amperf; + msr_counter_arch_infos[MSR_ARCH_INFO_MPERF_INDEX].needed = need_amperf; + msr_counter_arch_infos[MSR_ARCH_INFO_SMI_INDEX].needed = need_smi; + + msr_perf_init_(); + + const bool has_amperf = has_amperf_access(); + const bool has_smi = msr_counter_arch_infos[MSR_ARCH_INFO_SMI_INDEX].present; + + has_aperf_access = has_amperf; + + if (has_amperf) { + BIC_PRESENT(BIC_Avg_MHz); + BIC_PRESENT(BIC_Busy); + BIC_PRESENT(BIC_Bzy_MHz); + BIC_PRESENT(BIC_SMI); + } + + if (has_smi) + BIC_PRESENT(BIC_SMI); +} + void cstate_perf_init_(bool soft_c1) { bool has_counter; @@ -7127,17 +7834,17 @@ void cstate_perf_init_(bool soft_c1) /* Use perf API for this counter */ if (!no_perf && cai->perf_name && add_cstate_perf_counter(cpu, cci, cai) != -1) { - cci->source[cai->rci_index] = CSTATE_SOURCE_PERF; + cci->source[cai->rci_index] = COUNTER_SOURCE_PERF; /* User MSR for this counter */ } else if (!no_msr && cai->msr && pkg_cstate_limit >= cai->pkg_cstate_limit && probe_msr(cpu, cai->msr) == 0) { - cci->source[cai->rci_index] = CSTATE_SOURCE_MSR; + cci->source[cai->rci_index] = COUNTER_SOURCE_MSR; cci->msr[cai->rci_index] = cai->msr; } } - if (cci->source[cai->rci_index] != CSTATE_SOURCE_NONE) { + if (cci->source[cai->rci_index] != COUNTER_SOURCE_NONE) { has_counter = true; cores_visited[core_id] = true; pkg_visited[pkg_id] = true; @@ -7320,12 +8027,6 @@ void process_cpuid() __cpuid(0x6, eax, ebx, ecx, edx); has_aperf = ecx & (1 << 0); - if (has_aperf && has_amperf_access()) { - BIC_PRESENT(BIC_Avg_MHz); - BIC_PRESENT(BIC_Busy); - BIC_PRESENT(BIC_Bzy_MHz); - BIC_PRESENT(BIC_IPC); - } do_dts = eax & (1 << 0); if (do_dts) BIC_PRESENT(BIC_CoreTmp); @@ -7442,6 +8143,11 @@ static void counter_info_init(void) if (platform->has_msr_atom_pkg_c6_residency && cai->msr == MSR_PKG_C6_RESIDENCY) cai->msr = MSR_ATOM_PKG_C6_RESIDENCY; } + + for (int i = 0; i < NUM_MSR_COUNTERS; ++i) { + msr_counter_arch_infos[i].present = false; + msr_counter_arch_infos[i].needed = false; + } } void probe_pm_features(void) @@ -7817,100 +8523,446 @@ void set_base_cpu(void) err(-ENODEV, "No valid cpus found"); } -static void set_amperf_source(void) +bool has_added_counters(void) { - amperf_source = AMPERF_SOURCE_PERF; + /* + * It only makes sense to call this after the command line is parsed, + * otherwise sys structure is not populated. + */ - const bool aperf_required = is_aperf_access_required(); + return sys.added_core_counters | sys.added_thread_counters | sys.added_package_counters; +} - if (no_perf || !aperf_required || !has_amperf_access_via_perf()) - amperf_source = AMPERF_SOURCE_MSR; +void check_msr_access(void) +{ + check_dev_msr(); + check_msr_permission(); - if (quiet || !debug) - return; + if (no_msr) + bic_disable_msr_access(); +} - fprintf(outf, "aperf/mperf source preference: %s\n", amperf_source == AMPERF_SOURCE_MSR ? "msr" : "perf"); +void check_perf_access(void) +{ + if (no_perf || !BIC_IS_ENABLED(BIC_IPC) || !has_instr_count_access()) + bic_enabled &= ~BIC_IPC; } -bool has_added_counters(void) +int added_perf_counters_init_(struct perf_counter_info *pinfo) +{ + size_t num_domains = 0; + unsigned int next_domain; + bool *domain_visited; + unsigned int perf_type, perf_config; + double perf_scale; + int fd_perf; + + if (!pinfo) + return 0; + + const size_t max_num_domains = MAX(topo.max_cpu_num + 1, MAX(topo.max_core_id + 1, topo.max_package_id + 1)); + + domain_visited = calloc(max_num_domains, sizeof(*domain_visited)); + + while (pinfo) { + switch (pinfo->scope) { + case SCOPE_CPU: + num_domains = topo.max_cpu_num + 1; + break; + + case SCOPE_CORE: + num_domains = topo.max_core_id + 1; + break; + + case SCOPE_PACKAGE: + num_domains = topo.max_package_id + 1; + break; + } + + /* Allocate buffer for file descriptor for each domain. */ + pinfo->fd_perf_per_domain = calloc(num_domains, sizeof(*pinfo->fd_perf_per_domain)); + if (!pinfo->fd_perf_per_domain) + errx(1, "%s: alloc %s", __func__, "fd_perf_per_domain"); + + for (size_t i = 0; i < num_domains; ++i) + pinfo->fd_perf_per_domain[i] = -1; + + pinfo->num_domains = num_domains; + pinfo->scale = 1.0; + + memset(domain_visited, 0, max_num_domains * sizeof(*domain_visited)); + + for (int cpu = 0; cpu < topo.max_cpu_num + 1; ++cpu) { + + next_domain = cpu_to_domain(pinfo, cpu); + + assert(next_domain < num_domains); + + if (cpu_is_not_allowed(cpu)) + continue; + + if (domain_visited[next_domain]) + continue; + + perf_type = read_perf_type(pinfo->device); + if (perf_type == (unsigned int)-1) { + warnx("%s: perf/%s/%s: failed to read %s", + __func__, pinfo->device, pinfo->event, "type"); + continue; + } + + perf_config = read_perf_config(pinfo->device, pinfo->event); + if (perf_config == (unsigned int)-1) { + warnx("%s: perf/%s/%s: failed to read %s", + __func__, pinfo->device, pinfo->event, "config"); + continue; + } + + /* Scale is not required, some counters just don't have it. */ + perf_scale = read_perf_scale(pinfo->device, pinfo->event); + if (perf_scale == 0.0) + perf_scale = 1.0; + + fd_perf = open_perf_counter(cpu, perf_type, perf_config, -1, 0); + if (fd_perf == -1) { + warnx("%s: perf/%s/%s: failed to open counter on cpu%d", + __func__, pinfo->device, pinfo->event, cpu); + continue; + } + + domain_visited[next_domain] = 1; + pinfo->fd_perf_per_domain[next_domain] = fd_perf; + pinfo->scale = perf_scale; + + if (debug) + fprintf(stderr, "Add perf/%s/%s cpu%d: %d\n", + pinfo->device, pinfo->event, cpu, pinfo->fd_perf_per_domain[next_domain]); + } + + pinfo = pinfo->next; + } + + free(domain_visited); + + return 0; +} + +void added_perf_counters_init(void) +{ + if (added_perf_counters_init_(sys.perf_tp)) + errx(1, "%s: %s", __func__, "thread"); + + if (added_perf_counters_init_(sys.perf_cp)) + errx(1, "%s: %s", __func__, "core"); + + if (added_perf_counters_init_(sys.perf_pp)) + errx(1, "%s: %s", __func__, "package"); +} + +int parse_telem_info_file(int fd_dir, const char *info_filename, const char *format, unsigned long *output) +{ + int fd_telem_info; + FILE *file_telem_info; + unsigned long value; + + fd_telem_info = openat(fd_dir, info_filename, O_RDONLY); + if (fd_telem_info == -1) + return -1; + + file_telem_info = fdopen(fd_telem_info, "r"); + if (file_telem_info == NULL) { + close(fd_telem_info); + return -1; + } + + if (fscanf(file_telem_info, format, &value) != 1) { + fclose(file_telem_info); + return -1; + } + + fclose(file_telem_info); + + *output = value; + + return 0; +} + +struct pmt_mmio *pmt_mmio_open(unsigned int target_guid) { + DIR *dirp; + struct dirent *entry; + struct stat st; + unsigned int telem_idx; + int fd_telem_dir, fd_pmt; + unsigned long guid, size, offset; + size_t mmap_size; + void *mmio; + struct pmt_mmio *ret = NULL; + + if (stat(SYSFS_TELEM_PATH, &st) == -1) + return NULL; + + dirp = opendir(SYSFS_TELEM_PATH); + if (dirp == NULL) + return NULL; + + for (;;) { + entry = readdir(dirp); + + if (entry == NULL) + break; + + if (strcmp(entry->d_name, ".") == 0) + continue; + + if (strcmp(entry->d_name, "..") == 0) + continue; + + if (sscanf(entry->d_name, "telem%u", &telem_idx) != 1) + continue; + + if (fstatat(dirfd(dirp), entry->d_name, &st, 0) == -1) { + break; + } + + if (!S_ISDIR(st.st_mode)) + continue; + + fd_telem_dir = openat(dirfd(dirp), entry->d_name, O_RDONLY); + if (fd_telem_dir == -1) { + break; + } + + if (parse_telem_info_file(fd_telem_dir, "guid", "%lx", &guid)) { + close(fd_telem_dir); + break; + } + + if (parse_telem_info_file(fd_telem_dir, "size", "%lu", &size)) { + close(fd_telem_dir); + break; + } + + if (guid != target_guid) { + close(fd_telem_dir); + continue; + } + + if (parse_telem_info_file(fd_telem_dir, "offset", "%lu", &offset)) { + close(fd_telem_dir); + break; + } + + assert(offset == 0); + + fd_pmt = openat(fd_telem_dir, "telem", O_RDONLY); + if (fd_pmt == -1) + goto loop_cleanup_and_break; + + mmap_size = (size + 0x1000UL) & (~0x1000UL); + mmio = mmap(0, mmap_size, PROT_READ, MAP_SHARED, fd_pmt, 0); + if (mmio != MAP_FAILED) { + + if (debug) + fprintf(stderr, "%s: 0x%lx mmaped at: %p\n", __func__, guid, mmio); + + ret = calloc(1, sizeof(*ret)); + + if (!ret) { + fprintf(stderr, "%s: Failed to allocate pmt_mmio\n", __func__); + exit(1); + } + + ret->guid = guid; + ret->mmio_base = mmio; + ret->pmt_offset = offset; + ret->size = size; + + ret->next = pmt_mmios; + pmt_mmios = ret; + } + +loop_cleanup_and_break: + close(fd_pmt); + close(fd_telem_dir); + break; + } + + closedir(dirp); + + return ret; +} + +struct pmt_mmio *pmt_mmio_find(unsigned int guid) +{ + struct pmt_mmio *pmmio = pmt_mmios; + + while (pmmio) { + if (pmmio->guid == guid) + return pmmio; + + pmmio = pmmio->next; + } + + return NULL; +} + +void *pmt_get_counter_pointer(struct pmt_mmio *pmmio, unsigned long counter_offset) +{ + char *ret; + + /* Get base of mmaped PMT file. */ + ret = (char *)pmmio->mmio_base; + /* - * It only makes sense to call this after the command line is parsed, - * otherwise sys structure is not populated. + * Apply PMT MMIO offset to obtain beginning of the mmaped telemetry data. + * It's not guaranteed that the mmaped memory begins with the telemetry data + * - we might have to apply the offset first. */ + ret += pmmio->pmt_offset; - return sys.added_core_counters | sys.added_thread_counters | sys.added_package_counters; + /* Apply the counter offset to get the address to the mmaped counter. */ + ret += counter_offset; + + return ret; } -bool is_msr_access_required(void) +struct pmt_mmio *pmt_add_guid(unsigned int guid) { - if (no_msr) - return false; - - if (has_added_counters()) - return true; - - return BIC_IS_ENABLED(BIC_SMI) - || BIC_IS_ENABLED(BIC_CPU_c1) - || BIC_IS_ENABLED(BIC_CPU_c3) - || BIC_IS_ENABLED(BIC_CPU_c6) - || BIC_IS_ENABLED(BIC_CPU_c7) - || BIC_IS_ENABLED(BIC_Mod_c6) - || BIC_IS_ENABLED(BIC_CoreTmp) - || BIC_IS_ENABLED(BIC_Totl_c0) - || BIC_IS_ENABLED(BIC_Any_c0) - || BIC_IS_ENABLED(BIC_GFX_c0) - || BIC_IS_ENABLED(BIC_CPUGFX) - || BIC_IS_ENABLED(BIC_Pkgpc3) - || BIC_IS_ENABLED(BIC_Pkgpc6) - || BIC_IS_ENABLED(BIC_Pkgpc2) - || BIC_IS_ENABLED(BIC_Pkgpc7) - || BIC_IS_ENABLED(BIC_Pkgpc8) - || BIC_IS_ENABLED(BIC_Pkgpc9) - || BIC_IS_ENABLED(BIC_Pkgpc10) - /* TODO: Multiplex access with perf */ - || BIC_IS_ENABLED(BIC_CorWatt) - || BIC_IS_ENABLED(BIC_Cor_J) - || BIC_IS_ENABLED(BIC_PkgWatt) - || BIC_IS_ENABLED(BIC_CorWatt) - || BIC_IS_ENABLED(BIC_GFXWatt) - || BIC_IS_ENABLED(BIC_RAMWatt) - || BIC_IS_ENABLED(BIC_Pkg_J) - || BIC_IS_ENABLED(BIC_Cor_J) - || BIC_IS_ENABLED(BIC_GFX_J) - || BIC_IS_ENABLED(BIC_RAM_J) - || BIC_IS_ENABLED(BIC_PKG__) - || BIC_IS_ENABLED(BIC_RAM__) - || BIC_IS_ENABLED(BIC_PkgTmp) - || (is_aperf_access_required() && !has_amperf_access_via_perf()); + struct pmt_mmio *ret; + + ret = pmt_mmio_find(guid); + if (!ret) + ret = pmt_mmio_open(guid); + + return ret; } -void check_msr_access(void) +enum pmt_open_mode { + PMT_OPEN_TRY, /* Open failure is not an error. */ + PMT_OPEN_REQUIRED, /* Open failure is a fatal error. */ +}; + +struct pmt_counter *pmt_find_counter(struct pmt_counter *pcounter, const char *name) { - if (!is_msr_access_required()) - no_msr = 1; + while (pcounter) { + if (strcmp(pcounter->name, name) == 0) + break; - check_dev_msr(); - check_msr_permission(); + pcounter = pcounter->next; + } - if (no_msr) - bic_disable_msr_access(); + return pcounter; } -void check_perf_access(void) +struct pmt_counter **pmt_get_scope_root(enum counter_scope scope) { - const bool intrcount_required = BIC_IS_ENABLED(BIC_IPC); + switch (scope) { + case SCOPE_CPU: + return &sys.pmt_tp; + case SCOPE_CORE: + return &sys.pmt_cp; + case SCOPE_PACKAGE: + return &sys.pmt_pp; + } - if (no_perf || !intrcount_required || !has_instr_count_access()) - bic_enabled &= ~BIC_IPC; + __builtin_unreachable(); +} - const bool aperf_required = is_aperf_access_required(); +void pmt_counter_add_domain(struct pmt_counter *pcounter, unsigned long *pmmio, unsigned int domain_id) +{ + /* Make sure the new domain fits. */ + if (domain_id >= pcounter->num_domains) + pmt_counter_resize(pcounter, domain_id + 1); - if (!aperf_required || !has_amperf_access()) { - bic_enabled &= ~BIC_Avg_MHz; - bic_enabled &= ~BIC_Busy; - bic_enabled &= ~BIC_Bzy_MHz; - bic_enabled &= ~BIC_IPC; + assert(pcounter->domains); + assert(domain_id < pcounter->num_domains); + + pcounter->domains[domain_id].pcounter = pmmio; +} + +int pmt_add_counter(unsigned int guid, const char *name, enum pmt_datatype type, + unsigned int lsb, unsigned int msb, unsigned int offset, enum counter_scope scope, + enum counter_format format, unsigned int domain_id, enum pmt_open_mode mode) +{ + struct pmt_mmio *mmio; + struct pmt_counter *pcounter; + struct pmt_counter **const pmt_root = pmt_get_scope_root(scope); + bool new_counter = false; + int conflict = 0; + + if (lsb > msb) { + fprintf(stderr, "%s: %s: `%s` must be satisfied\n", __func__, "lsb <= msb", name); + exit(1); + } + + if (msb >= 64) { + fprintf(stderr, "%s: %s: `%s` must be satisfied\n", __func__, "msb < 64", name); + exit(1); + } + + mmio = pmt_add_guid(guid); + if (!mmio) { + if (mode != PMT_OPEN_TRY) { + fprintf(stderr, "%s: failed to map PMT MMIO for guid %x\n", __func__, guid); + exit(1); + } + + return 1; + } + + if (offset >= mmio->size) { + if (mode != PMT_OPEN_TRY) { + fprintf(stderr, "%s: offset %u outside of PMT MMIO size %u\n", __func__, offset, mmio->size); + exit(1); + } + + return 1; + } + + pcounter = pmt_find_counter(*pmt_root, name); + if (!pcounter) { + pcounter = calloc(1, sizeof(*pcounter)); + new_counter = true; + } + + if (new_counter) { + strncpy(pcounter->name, name, ARRAY_SIZE(pcounter->name) - 1); + pcounter->type = type; + pcounter->scope = scope; + pcounter->lsb = lsb; + pcounter->msb = msb; + pcounter->format = format; + } else { + conflict += pcounter->type != type; + conflict += pcounter->scope != scope; + conflict += pcounter->lsb != lsb; + conflict += pcounter->msb != msb; + conflict += pcounter->format != format; + } + + if (conflict) { + fprintf(stderr, "%s: conflicting parameters for the PMT counter with the same name %s\n", + __func__, name); + exit(1); + } + + pmt_counter_add_domain(pcounter, pmt_get_counter_pointer(mmio, offset), domain_id); + + if (new_counter) { + pcounter->next = *pmt_root; + *pmt_root = pcounter; + } + + return 0; +} + +void pmt_init(void) +{ + if (BIC_IS_ENABLED(BIC_Diec6)) { + pmt_add_counter(PMT_MTL_DC6_GUID, "Die%c6", PMT_TYPE_XTAL_TIME, PMT_COUNTER_MTL_DC6_LSB, + PMT_COUNTER_MTL_DC6_MSB, PMT_COUNTER_MTL_DC6_OFFSET, SCOPE_PACKAGE, FORMAT_DELTA, + 0, PMT_OPEN_TRY); } } @@ -7923,16 +8975,18 @@ void turbostat_init() process_cpuid(); counter_info_init(); probe_pm_features(); - set_amperf_source(); + msr_perf_init(); linux_perf_init(); rapl_perf_init(); cstate_perf_init(); + added_perf_counters_init(); + pmt_init(); for_all_cpus(get_cpu_type, ODD_COUNTERS); for_all_cpus(get_cpu_type, EVEN_COUNTERS); - if (DO_BIC(BIC_IPC)) - (void)get_instr_count_fd(base_cpu); + if (BIC_IS_ENABLED(BIC_IPC) && has_aperf_access && get_instr_count_fd(base_cpu) != -1) + BIC_PRESENT(BIC_IPC); /* * If TSC tweak is needed, but couldn't get it, @@ -8017,7 +9071,7 @@ int get_and_dump_counters(void) void print_version() { - fprintf(outf, "turbostat version 2024.05.10 - Len Brown <lenb@kernel.org>\n"); + fprintf(outf, "turbostat version 2024.07.26 - Len Brown <lenb@kernel.org>\n"); } #define COMMAND_LINE_SIZE 2048 @@ -8049,7 +9103,7 @@ struct msr_counter *find_msrp_by_name(struct msr_counter *head, char *name) for (mp = head; mp; mp = mp->next) { if (debug) - printf("%s: %s %s\n", __func__, name, mp->name); + fprintf(stderr, "%s: %s %s\n", __func__, name, mp->name); if (!strncmp(name, mp->name, strlen(mp->name))) return mp; } @@ -8066,8 +9120,8 @@ int add_counter(unsigned int msr_num, char *path, char *name, errx(1, "Requested MSR counter 0x%x, but in --no-msr mode", msr_num); if (debug) - printf("%s(msr%d, %s, %s, width%d, scope%d, type%d, format%d, flags%x, id%d)\n", __func__, msr_num, - path, name, width, scope, type, format, flags, id); + fprintf(stderr, "%s(msr%d, %s, %s, width%d, scope%d, type%d, format%d, flags%x, id%d)\n", + __func__, msr_num, path, name, width, scope, type, format, flags, id); switch (scope) { @@ -8075,7 +9129,7 @@ int add_counter(unsigned int msr_num, char *path, char *name, msrp = find_msrp_by_name(sys.tp, name); if (msrp) { if (debug) - printf("%s: %s FOUND\n", __func__, name); + fprintf(stderr, "%s: %s FOUND\n", __func__, name); break; } if (sys.added_thread_counters++ >= MAX_ADDED_THREAD_COUNTERS) { @@ -8087,7 +9141,7 @@ int add_counter(unsigned int msr_num, char *path, char *name, msrp = find_msrp_by_name(sys.cp, name); if (msrp) { if (debug) - printf("%s: %s FOUND\n", __func__, name); + fprintf(stderr, "%s: %s FOUND\n", __func__, name); break; } if (sys.added_core_counters++ >= MAX_ADDED_CORE_COUNTERS) { @@ -8099,7 +9153,7 @@ int add_counter(unsigned int msr_num, char *path, char *name, msrp = find_msrp_by_name(sys.pp, name); if (msrp) { if (debug) - printf("%s: %s FOUND\n", __func__, name); + fprintf(stderr, "%s: %s FOUND\n", __func__, name); break; } if (sys.added_package_counters++ >= MAX_ADDED_PACKAGE_COUNTERS) { @@ -8116,6 +9170,7 @@ int add_counter(unsigned int msr_num, char *path, char *name, msrp = calloc(1, sizeof(struct msr_counter)); if (msrp == NULL) err(-1, "calloc msr_counter"); + msrp->msr_num = msr_num; strncpy(msrp->name, name, NAME_BYTES - 1); msrp->width = width; @@ -8156,11 +9211,106 @@ int add_counter(unsigned int msr_num, char *path, char *name, return 0; } -void parse_add_command(char *add_command) +/* + * Initialize the fields used for identifying and opening the counter. + * + * Defer the initialization of any runtime buffers for actually reading + * the counters for when we initialize all perf counters, so we can later + * easily call re_initialize(). + */ +struct perf_counter_info *make_perf_counter_info(const char *perf_device, + const char *perf_event, + const char *name, + unsigned int width, + enum counter_scope scope, + enum counter_type type, enum counter_format format) +{ + struct perf_counter_info *pinfo; + + pinfo = calloc(1, sizeof(*pinfo)); + if (!pinfo) + errx(1, "%s: Failed to allocate %s/%s\n", __func__, perf_device, perf_event); + + strncpy(pinfo->device, perf_device, ARRAY_SIZE(pinfo->device) - 1); + strncpy(pinfo->event, perf_event, ARRAY_SIZE(pinfo->event) - 1); + + strncpy(pinfo->name, name, ARRAY_SIZE(pinfo->name) - 1); + pinfo->width = width; + pinfo->scope = scope; + pinfo->type = type; + pinfo->format = format; + + return pinfo; +} + +int add_perf_counter(const char *perf_device, const char *perf_event, const char *name_buffer, unsigned int width, + enum counter_scope scope, enum counter_type type, enum counter_format format) +{ + struct perf_counter_info *pinfo; + + switch (scope) { + case SCOPE_CPU: + if (sys.added_thread_perf_counters >= MAX_ADDED_THREAD_COUNTERS) { + warnx("ignoring thread counter perf/%s/%s", perf_device, perf_event); + return -1; + } + break; + + case SCOPE_CORE: + if (sys.added_core_perf_counters >= MAX_ADDED_CORE_COUNTERS) { + warnx("ignoring core counter perf/%s/%s", perf_device, perf_event); + return -1; + } + break; + + case SCOPE_PACKAGE: + if (sys.added_package_perf_counters >= MAX_ADDED_PACKAGE_COUNTERS) { + warnx("ignoring package counter perf/%s/%s", perf_device, perf_event); + return -1; + } + break; + } + + pinfo = make_perf_counter_info(perf_device, perf_event, name_buffer, width, scope, type, format); + + if (!pinfo) + return -1; + + switch (scope) { + case SCOPE_CPU: + pinfo->next = sys.perf_tp; + sys.perf_tp = pinfo; + ++sys.added_thread_perf_counters; + break; + + case SCOPE_CORE: + pinfo->next = sys.perf_cp; + sys.perf_cp = pinfo; + ++sys.added_core_perf_counters; + break; + + case SCOPE_PACKAGE: + pinfo->next = sys.perf_pp; + sys.perf_pp = pinfo; + ++sys.added_package_perf_counters; + break; + } + + // FIXME: we might not have debug here yet + if (debug) + fprintf(stderr, "%s: %s/%s, name: %s, scope%d\n", + __func__, pinfo->device, pinfo->event, pinfo->name, pinfo->scope); + + return 0; +} + +void parse_add_command_msr(char *add_command) { int msr_num = 0; char *path = NULL; - char name_buffer[NAME_BYTES] = ""; + char perf_device[PERF_DEV_NAME_BYTES] = ""; + char perf_event[PERF_EVT_NAME_BYTES] = ""; + char name_buffer[PERF_NAME_BYTES] = ""; int width = 64; int fail = 0; enum counter_scope scope = SCOPE_CPU; @@ -8175,6 +9325,11 @@ void parse_add_command(char *add_command) if (sscanf(add_command, "msr%d", &msr_num) == 1) goto next; + BUILD_BUG_ON(ARRAY_SIZE(perf_device) <= 31); + BUILD_BUG_ON(ARRAY_SIZE(perf_event) <= 31); + if (sscanf(add_command, "perf/%31[^/]/%31[^,]", &perf_device[0], &perf_event[0]) == 2) + goto next; + if (*add_command == '/') { path = add_command; goto next; @@ -8222,7 +9377,8 @@ void parse_add_command(char *add_command) goto next; } - if (sscanf(add_command, "%18s,%*s", name_buffer) == 1) { /* 18 < NAME_BYTES */ + BUILD_BUG_ON(ARRAY_SIZE(name_buffer) <= 18); + if (sscanf(add_command, "%18s,%*s", name_buffer) == 1) { char *eos; eos = strchr(name_buffer, ','); @@ -8239,21 +9395,33 @@ next: } } - if ((msr_num == 0) && (path == NULL)) { - fprintf(stderr, "--add: (msrDDD | msr0xXXX | /path_to_counter ) required\n"); + if ((msr_num == 0) && (path == NULL) && (perf_device[0] == '\0' || perf_event[0] == '\0')) { + fprintf(stderr, "--add: (msrDDD | msr0xXXX | /path_to_counter | perf/device/event ) required\n"); fail++; } + /* Test for non-empty perf_device and perf_event */ + const bool is_perf_counter = perf_device[0] && perf_event[0]; + /* generate default column header */ if (*name_buffer == '\0') { - if (width == 32) - sprintf(name_buffer, "M0x%x%s", msr_num, format == FORMAT_PERCENT ? "%" : ""); - else - sprintf(name_buffer, "M0X%x%s", msr_num, format == FORMAT_PERCENT ? "%" : ""); + if (is_perf_counter) { + snprintf(name_buffer, ARRAY_SIZE(name_buffer), "perf/%s", perf_event); + } else { + if (width == 32) + sprintf(name_buffer, "M0x%x%s", msr_num, format == FORMAT_PERCENT ? "%" : ""); + else + sprintf(name_buffer, "M0X%x%s", msr_num, format == FORMAT_PERCENT ? "%" : ""); + } } - if (add_counter(msr_num, path, name_buffer, width, scope, type, format, 0, 0)) - fail++; + if (is_perf_counter) { + if (add_perf_counter(perf_device, perf_event, name_buffer, width, scope, type, format)) + fail++; + } else { + if (add_counter(msr_num, path, name_buffer, width, scope, type, format, 0, 0)) + fail++; + } if (fail) { help(); @@ -8261,6 +9429,195 @@ next: } } +bool starts_with(const char *str, const char *prefix) +{ + return strncmp(prefix, str, strlen(prefix)) == 0; +} + +void parse_add_command_pmt(char *add_command) +{ + char *name = NULL; + char *type_name = NULL; + char *format_name = NULL; + unsigned int offset; + unsigned int lsb; + unsigned int msb; + unsigned int guid; + unsigned int domain_id; + enum counter_scope scope = 0; + enum pmt_datatype type = PMT_TYPE_RAW; + enum counter_format format = FORMAT_RAW; + bool has_offset = false; + bool has_lsb = false; + bool has_msb = false; + bool has_format = true; /* Format has a default value. */ + bool has_guid = false; + bool has_scope = false; + bool has_type = true; /* Type has a default value. */ + + /* Consume the "pmt," prefix. */ + add_command = strchr(add_command, ','); + if (!add_command) { + help(); + exit(1); + } + ++add_command; + + while (add_command) { + if (starts_with(add_command, "name=")) { + name = add_command + strlen("name="); + goto next; + } + + if (starts_with(add_command, "type=")) { + type_name = add_command + strlen("type="); + goto next; + } + + if (starts_with(add_command, "domain=")) { + const size_t prefix_len = strlen("domain="); + + if (sscanf(add_command + prefix_len, "cpu%u", &domain_id) == 1) { + scope = SCOPE_CPU; + has_scope = true; + } else if (sscanf(add_command + prefix_len, "core%u", &domain_id) == 1) { + scope = SCOPE_CORE; + has_scope = true; + } else if (sscanf(add_command + prefix_len, "package%u", &domain_id) == 1) { + scope = SCOPE_PACKAGE; + has_scope = true; + } + + if (!has_scope) { + printf("%s: invalid value for scope. Expected cpu%%u, core%%u or package%%u.\n", + __func__); + exit(1); + } + + goto next; + } + + if (starts_with(add_command, "format=")) { + format_name = add_command + strlen("format="); + goto next; + } + + if (sscanf(add_command, "offset=%u", &offset) == 1) { + has_offset = true; + goto next; + } + + if (sscanf(add_command, "lsb=%u", &lsb) == 1) { + has_lsb = true; + goto next; + } + + if (sscanf(add_command, "msb=%u", &msb) == 1) { + has_msb = true; + goto next; + } + + if (sscanf(add_command, "guid=%x", &guid) == 1) { + has_guid = true; + goto next; + } + +next: + add_command = strchr(add_command, ','); + if (add_command) { + *add_command = '\0'; + add_command++; + } + } + + if (!name) { + printf("%s: missing %s\n", __func__, "name"); + exit(1); + } + + if (strlen(name) >= PMT_COUNTER_NAME_SIZE_BYTES) { + printf("%s: name has to be at most %d characters long\n", __func__, PMT_COUNTER_NAME_SIZE_BYTES); + exit(1); + } + + if (format_name) { + has_format = false; + + if (strcmp("raw", format_name) == 0) { + format = FORMAT_RAW; + has_format = true; + } + + if (strcmp("delta", format_name) == 0) { + format = FORMAT_DELTA; + has_format = true; + } + + if (!has_format) { + fprintf(stderr, "%s: Invalid format %s. Expected raw or delta\n", __func__, format_name); + exit(1); + } + } + + if (type_name) { + has_type = false; + + if (strcmp("raw", type_name) == 0) { + type = PMT_TYPE_RAW; + has_type = true; + } + + if (strcmp("txtal_time", type_name) == 0) { + type = PMT_TYPE_XTAL_TIME; + has_type = true; + } + + if (!has_type) { + printf("%s: invalid %s: %s\n", __func__, "type", type_name); + exit(1); + } + } + + if (!has_offset) { + printf("%s : missing %s\n", __func__, "offset"); + exit(1); + } + + if (!has_lsb) { + printf("%s: missing %s\n", __func__, "lsb"); + exit(1); + } + + if (!has_msb) { + printf("%s: missing %s\n", __func__, "msb"); + exit(1); + } + + if (!has_guid) { + printf("%s: missing %s\n", __func__, "guid"); + exit(1); + } + + if (!has_scope) { + printf("%s: missing %s\n", __func__, "scope"); + exit(1); + } + + if (lsb > msb) { + printf("%s: lsb > msb doesn't make sense\n", __func__); + exit(1); + } + + pmt_add_counter(guid, name, type, lsb, msb, offset, scope, format, domain_id, PMT_OPEN_REQUIRED); +} + +void parse_add_command(char *add_command) +{ + if (strncmp(add_command, "pmt", strlen("pmt")) == 0) + return parse_add_command_pmt(add_command); + return parse_add_command_msr(add_command); +} + int is_deferred_add(char *name) { int i; diff --git a/tools/testing/cxl/Kbuild b/tools/testing/cxl/Kbuild index 030b388800f0..3d1ca9e38b1f 100644 --- a/tools/testing/cxl/Kbuild +++ b/tools/testing/cxl/Kbuild @@ -14,6 +14,7 @@ ldflags-y += --wrap=cxl_dvsec_rr_decode ldflags-y += --wrap=devm_cxl_add_rch_dport ldflags-y += --wrap=cxl_rcd_component_reg_phys ldflags-y += --wrap=cxl_endpoint_parse_cdat +ldflags-y += --wrap=cxl_setup_parent_dport DRIVERS := ../../../drivers CXL_SRC := $(DRIVERS)/cxl diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c index eaf091a3d331..129f179b0ac5 100644 --- a/tools/testing/cxl/test/mem.c +++ b/tools/testing/cxl/test/mem.c @@ -385,19 +385,21 @@ struct cxl_test_gen_media { struct cxl_test_gen_media gen_media = { .id = CXL_EVENT_GEN_MEDIA_UUID, .rec = { - .hdr = { - .length = sizeof(struct cxl_test_gen_media), - .flags[0] = CXL_EVENT_RECORD_FLAG_PERMANENT, - /* .handle = Set dynamically */ - .related_handle = cpu_to_le16(0), + .media_hdr = { + .hdr = { + .length = sizeof(struct cxl_test_gen_media), + .flags[0] = CXL_EVENT_RECORD_FLAG_PERMANENT, + /* .handle = Set dynamically */ + .related_handle = cpu_to_le16(0), + }, + .phys_addr = cpu_to_le64(0x2000), + .descriptor = CXL_GMER_EVT_DESC_UNCORECTABLE_EVENT, + .type = CXL_GMER_MEM_EVT_TYPE_DATA_PATH_ERROR, + .transaction_type = CXL_GMER_TRANS_HOST_WRITE, + /* .validity_flags = <set below> */ + .channel = 1, + .rank = 30, }, - .phys_addr = cpu_to_le64(0x2000), - .descriptor = CXL_GMER_EVT_DESC_UNCORECTABLE_EVENT, - .type = CXL_GMER_MEM_EVT_TYPE_DATA_PATH_ERROR, - .transaction_type = CXL_GMER_TRANS_HOST_WRITE, - /* .validity_flags = <set below> */ - .channel = 1, - .rank = 30 }, }; @@ -409,18 +411,20 @@ struct cxl_test_dram { struct cxl_test_dram dram = { .id = CXL_EVENT_DRAM_UUID, .rec = { - .hdr = { - .length = sizeof(struct cxl_test_dram), - .flags[0] = CXL_EVENT_RECORD_FLAG_PERF_DEGRADED, - /* .handle = Set dynamically */ - .related_handle = cpu_to_le16(0), + .media_hdr = { + .hdr = { + .length = sizeof(struct cxl_test_dram), + .flags[0] = CXL_EVENT_RECORD_FLAG_PERF_DEGRADED, + /* .handle = Set dynamically */ + .related_handle = cpu_to_le16(0), + }, + .phys_addr = cpu_to_le64(0x8000), + .descriptor = CXL_GMER_EVT_DESC_THRESHOLD_EVENT, + .type = CXL_GMER_MEM_EVT_TYPE_INV_ADDR, + .transaction_type = CXL_GMER_TRANS_INTERNAL_MEDIA_SCRUB, + /* .validity_flags = <set below> */ + .channel = 1, }, - .phys_addr = cpu_to_le64(0x8000), - .descriptor = CXL_GMER_EVT_DESC_THRESHOLD_EVENT, - .type = CXL_GMER_MEM_EVT_TYPE_INV_ADDR, - .transaction_type = CXL_GMER_TRANS_INTERNAL_MEDIA_SCRUB, - /* .validity_flags = <set below> */ - .channel = 1, .bank_group = 5, .bank = 2, .column = {0xDE, 0xAD}, @@ -474,11 +478,11 @@ static int mock_set_timestamp(struct cxl_dev_state *cxlds, static void cxl_mock_add_event_logs(struct mock_event_store *mes) { put_unaligned_le16(CXL_GMER_VALID_CHANNEL | CXL_GMER_VALID_RANK, - &gen_media.rec.validity_flags); + &gen_media.rec.media_hdr.validity_flags); put_unaligned_le16(CXL_DER_VALID_CHANNEL | CXL_DER_VALID_BANK_GROUP | CXL_DER_VALID_BANK | CXL_DER_VALID_COLUMN, - &dram.rec.validity_flags); + &dram.rec.media_hdr.validity_flags); mes_add_event(mes, CXL_EVENT_TYPE_INFO, &maint_needed); mes_add_event(mes, CXL_EVENT_TYPE_INFO, @@ -1131,27 +1135,28 @@ static bool mock_poison_dev_max_injected(struct cxl_dev_state *cxlds) return (count >= poison_inject_dev_max); } -static bool mock_poison_add(struct cxl_dev_state *cxlds, u64 dpa) +static int mock_poison_add(struct cxl_dev_state *cxlds, u64 dpa) { + /* Return EBUSY to match the CXL driver handling */ if (mock_poison_dev_max_injected(cxlds)) { dev_dbg(cxlds->dev, "Device poison injection limit has been reached: %d\n", - MOCK_INJECT_DEV_MAX); - return false; + poison_inject_dev_max); + return -EBUSY; } for (int i = 0; i < MOCK_INJECT_TEST_MAX; i++) { if (!mock_poison_list[i].cxlds) { mock_poison_list[i].cxlds = cxlds; mock_poison_list[i].dpa = dpa; - return true; + return 0; } } dev_dbg(cxlds->dev, "Mock test poison injection limit has been reached: %d\n", MOCK_INJECT_TEST_MAX); - return false; + return -ENXIO; } static bool mock_poison_found(struct cxl_dev_state *cxlds, u64 dpa) @@ -1175,10 +1180,8 @@ static int mock_inject_poison(struct cxl_dev_state *cxlds, dev_dbg(cxlds->dev, "DPA: 0x%llx already poisoned\n", dpa); return 0; } - if (!mock_poison_add(cxlds, dpa)) - return -ENXIO; - return 0; + return mock_poison_add(cxlds, dpa); } static bool mock_poison_del(struct cxl_dev_state *cxlds, u64 dpa) diff --git a/tools/testing/cxl/test/mock.c b/tools/testing/cxl/test/mock.c index 6f737941dc0e..d619672faa49 100644 --- a/tools/testing/cxl/test/mock.c +++ b/tools/testing/cxl/test/mock.c @@ -299,6 +299,18 @@ void __wrap_cxl_endpoint_parse_cdat(struct cxl_port *port) } EXPORT_SYMBOL_NS_GPL(__wrap_cxl_endpoint_parse_cdat, CXL); +void __wrap_cxl_setup_parent_dport(struct device *host, struct cxl_dport *dport) +{ + int index; + struct cxl_mock_ops *ops = get_cxl_mock_ops(&index); + + if (!ops || !ops->is_mock_port(dport->dport_dev)) + cxl_setup_parent_dport(host, dport); + + put_cxl_mock_ops(index); +} +EXPORT_SYMBOL_NS_GPL(__wrap_cxl_setup_parent_dport, CXL); + MODULE_LICENSE("GPL v2"); MODULE_IMPORT_NS(ACPI); MODULE_IMPORT_NS(CXL); diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile index 7527f738b4a1..d1acd7d58850 100644 --- a/tools/testing/radix-tree/Makefile +++ b/tools/testing/radix-tree/Makefile @@ -5,8 +5,8 @@ CFLAGS += -I. -I../../include -I../../../lib -g -Og -Wall \ LDFLAGS += -fsanitize=address -fsanitize=undefined LDLIBS+= -lpthread -lurcu TARGETS = main idr-test multiorder xarray maple -CORE_OFILES := xarray.o radix-tree.o idr.o linux.o test.o find_bit.o bitmap.o \ - slab.o maple.o +LIBS := slab.o find_bit.o bitmap.o hweight.o vsprintf.o +CORE_OFILES := xarray.o radix-tree.o idr.o linux.o test.o maple.o $(LIBS) OFILES = main.o $(CORE_OFILES) regression1.o regression2.o regression3.o \ regression4.o tag_check.o multiorder.o idr-test.o iteration_check.o \ iteration_check_2.o benchmark.o diff --git a/tools/testing/radix-tree/bitmap.c b/tools/testing/radix-tree/bitmap.c deleted file mode 100644 index 66ec4a24a203..000000000000 --- a/tools/testing/radix-tree/bitmap.c +++ /dev/null @@ -1,23 +0,0 @@ -/* lib/bitmap.c pulls in at least two other files. */ - -#include <linux/bitmap.h> - -void bitmap_clear(unsigned long *map, unsigned int start, int len) -{ - unsigned long *p = map + BIT_WORD(start); - const unsigned int size = start + len; - int bits_to_clear = BITS_PER_LONG - (start % BITS_PER_LONG); - unsigned long mask_to_clear = BITMAP_FIRST_WORD_MASK(start); - - while (len - bits_to_clear >= 0) { - *p &= ~mask_to_clear; - len -= bits_to_clear; - bits_to_clear = BITS_PER_LONG; - mask_to_clear = ~0UL; - p++; - } - if (len) { - mask_to_clear &= BITMAP_LAST_WORD_MASK(size); - *p &= ~mask_to_clear; - } -} diff --git a/tools/testing/selftests/arm64/abi/ptrace.c b/tools/testing/selftests/arm64/abi/ptrace.c index 4c941270d8de..e4fa507cbdd0 100644 --- a/tools/testing/selftests/arm64/abi/ptrace.c +++ b/tools/testing/selftests/arm64/abi/ptrace.c @@ -156,7 +156,7 @@ static void test_hw_debug(pid_t child, int type, const char *type_name) /* Zero is not currently architecturally valid */ ksft_test_result(arch, "%s_arch_set\n", type_name); } else { - ksft_test_result_skip("%s_arch_set\n"); + ksft_test_result_skip("%s_arch_set\n", type_name); } } diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 6d6d0c29db47..ec7d425c4022 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -780,7 +780,7 @@ $(OUTPUT)/xdp_features: xdp_features.c $(OUTPUT)/network_helpers.o $(OUTPUT)/xdp # Make sure we are able to include and link libbpf against c++. $(OUTPUT)/test_cpp: test_cpp.cpp $(OUTPUT)/test_core_extern.skel.h $(BPFOBJ) $(call msg,CXX,,$@) - $(Q)$(CXX) $(CFLAGS) $(filter %.a %.o %.cpp,$^) $(LDLIBS) -o $@ + $(Q)$(CXX) $(subst -D_GNU_SOURCE=,,$(CFLAGS)) $(filter %.a %.o %.cpp,$^) $(LDLIBS) -o $@ # Benchmark runner $(OUTPUT)/bench_%.o: benchs/bench_%.c bench.h $(BPFOBJ) diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c index bd8c75b620c2..c397336fe1ed 100644 --- a/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c +++ b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c @@ -216,7 +216,7 @@ static void test_uretprobe_regs_change(void) } #ifndef __NR_uretprobe -#define __NR_uretprobe 467 +#define __NR_uretprobe 335 #endif __naked unsigned long uretprobe_syscall_call_1(void) @@ -253,7 +253,7 @@ static void test_uretprobe_syscall_call(void) struct uprobe_syscall_executed *skel; int pid, status, err, go[2], c; - if (ASSERT_OK(pipe(go), "pipe")) + if (!ASSERT_OK(pipe(go), "pipe")) return; skel = uprobe_syscall_executed__open_and_load(); diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c index 16bdc3e25591..ef70b88bccb2 100644 --- a/tools/testing/selftests/bpf/progs/iters.c +++ b/tools/testing/selftests/bpf/progs/iters.c @@ -1432,4 +1432,58 @@ int iter_arr_with_actual_elem_count(const void *ctx) return sum; } +__u32 upper, select_n, result; +__u64 global; + +static __noinline bool nest_2(char *str) +{ + /* some insns (including branch insns) to ensure stacksafe() is triggered + * in nest_2(). This way, stacksafe() can compare frame associated with nest_1(). + */ + if (str[0] == 't') + return true; + if (str[1] == 'e') + return true; + if (str[2] == 's') + return true; + if (str[3] == 't') + return true; + return false; +} + +static __noinline bool nest_1(int n) +{ + /* case 0: allocate stack, case 1: no allocate stack */ + switch (n) { + case 0: { + char comm[16]; + + if (bpf_get_current_comm(comm, 16)) + return false; + return nest_2(comm); + } + case 1: + return nest_2((char *)&global); + default: + return false; + } +} + +SEC("raw_tp") +__success +int iter_subprog_check_stacksafe(const void *ctx) +{ + long i; + + bpf_for(i, 0, upper) { + if (!nest_1(select_n)) { + result = 1; + return 0; + } + } + + result = 2; + return 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/core/close_range_test.c b/tools/testing/selftests/core/close_range_test.c index 991c473e3859..12b4eb9d0434 100644 --- a/tools/testing/selftests/core/close_range_test.c +++ b/tools/testing/selftests/core/close_range_test.c @@ -589,4 +589,39 @@ TEST(close_range_cloexec_unshare_syzbot) EXPECT_EQ(close(fd3), 0); } +TEST(close_range_bitmap_corruption) +{ + pid_t pid; + int status; + struct __clone_args args = { + .flags = CLONE_FILES, + .exit_signal = SIGCHLD, + }; + + /* get the first 128 descriptors open */ + for (int i = 2; i < 128; i++) + EXPECT_GE(dup2(0, i), 0); + + /* get descriptor table shared */ + pid = sys_clone3(&args, sizeof(args)); + ASSERT_GE(pid, 0); + + if (pid == 0) { + /* unshare and truncate descriptor table down to 64 */ + if (sys_close_range(64, ~0U, CLOSE_RANGE_UNSHARE)) + exit(EXIT_FAILURE); + + ASSERT_EQ(fcntl(64, F_GETFD), -1); + /* ... and verify that the range 64..127 is not + stuck "fully used" according to secondary bitmap */ + EXPECT_EQ(dup(0), 64) + exit(EXIT_FAILURE); + exit(EXIT_SUCCESS); + } + + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c b/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c index 5f541522364f..5d0a809dc2df 100644 --- a/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c +++ b/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c @@ -29,9 +29,11 @@ static int check_vgem(int fd) version.name = name; ret = ioctl(fd, DRM_IOCTL_VERSION, &version); - if (ret) + if (ret || version.name_len != 4) return 0; + name[4] = '\0'; + return !strcmp(name, "vgem"); } diff --git a/tools/testing/selftests/drivers/net/hw/rss_ctx.py b/tools/testing/selftests/drivers/net/hw/rss_ctx.py index 931dbc36ca43..011508ca604b 100755 --- a/tools/testing/selftests/drivers/net/hw/rss_ctx.py +++ b/tools/testing/selftests/drivers/net/hw/rss_ctx.py @@ -19,6 +19,15 @@ def _rss_key_rand(length): return [random.randint(0, 255) for _ in range(length)] +def _rss_key_check(cfg, data=None, context=0): + if data is None: + data = get_rss(cfg, context=context) + if 'rss-hash-key' not in data: + return + non_zero = [x for x in data['rss-hash-key'] if x != 0] + ksft_eq(bool(non_zero), True, comment=f"RSS key is all zero {data['rss-hash-key']}") + + def get_rss(cfg, context=0): return ethtool(f"-x {cfg.ifname} context {context}", json=True)[0] @@ -90,8 +99,9 @@ def _send_traffic_check(cfg, port, name, params): def test_rss_key_indir(cfg): """Test basics like updating the main RSS key and indirection table.""" - if len(_get_rx_cnts(cfg)) < 2: - KsftSkipEx("Device has only one queue (or doesn't support queue stats)") + qcnt = len(_get_rx_cnts(cfg)) + if qcnt < 3: + KsftSkipEx("Device has fewer than 3 queues (or doesn't support queue stats)") data = get_rss(cfg) want_keys = ['rss-hash-key', 'rss-hash-function', 'rss-indirection-table'] @@ -101,6 +111,7 @@ def test_rss_key_indir(cfg): if not data[k]: raise KsftFailEx(f"ethtool results empty for '{k}': {data[k]}") + _rss_key_check(cfg, data=data) key_len = len(data['rss-hash-key']) # Set the key @@ -110,9 +121,26 @@ def test_rss_key_indir(cfg): data = get_rss(cfg) ksft_eq(key, data['rss-hash-key']) + # Set the indirection table and the key together + key = _rss_key_rand(key_len) + ethtool(f"-X {cfg.ifname} equal 3 hkey " + _rss_key_str(key)) + reset_indir = defer(ethtool, f"-X {cfg.ifname} default") + + data = get_rss(cfg) + _rss_key_check(cfg, data=data) + ksft_eq(0, min(data['rss-indirection-table'])) + ksft_eq(2, max(data['rss-indirection-table'])) + + # Reset indirection table and set the key + key = _rss_key_rand(key_len) + ethtool(f"-X {cfg.ifname} default hkey " + _rss_key_str(key)) + data = get_rss(cfg) + _rss_key_check(cfg, data=data) + ksft_eq(0, min(data['rss-indirection-table'])) + ksft_eq(qcnt - 1, max(data['rss-indirection-table'])) + # Set the indirection table ethtool(f"-X {cfg.ifname} equal 2") - reset_indir = defer(ethtool, f"-X {cfg.ifname} default") data = get_rss(cfg) ksft_eq(0, min(data['rss-indirection-table'])) ksft_eq(1, max(data['rss-indirection-table'])) @@ -317,8 +345,11 @@ def test_rss_context(cfg, ctx_cnt=1, create_with_cfg=None): ctx_cnt = i break + _rss_key_check(cfg, context=ctx_id) + if not create_with_cfg: ethtool(f"-X {cfg.ifname} context {ctx_id} {want_cfg}") + _rss_key_check(cfg, context=ctx_id) # Sanity check the context we just created data = get_rss(cfg, ctx_id) diff --git a/tools/testing/selftests/hid/hid_bpf.c b/tools/testing/selftests/hid/hid_bpf.c index dc0408a831d0..75b7b4ef6cfa 100644 --- a/tools/testing/selftests/hid/hid_bpf.c +++ b/tools/testing/selftests/hid/hid_bpf.c @@ -532,6 +532,7 @@ static void load_programs(const struct test_program programs[], FIXTURE_DATA(hid_bpf) * self, const FIXTURE_VARIANT(hid_bpf) * variant) { + struct bpf_map *iter_map; int err = -EINVAL; ASSERT_LE(progs_count, ARRAY_SIZE(self->hid_links)) @@ -564,6 +565,13 @@ static void load_programs(const struct test_program programs[], *ops_hid_id = self->hid_id; } + /* we disable the auto-attach feature of all maps because we + * only want the tested one to be manually attached in the next + * call to bpf_map__attach_struct_ops() + */ + bpf_object__for_each_map(iter_map, *self->skel->skeleton->obj) + bpf_map__set_autoattach(iter_map, false); + err = hid__load(self->skel); ASSERT_OK(err) TH_LOG("hid_skel_load failed: %d", err); @@ -687,6 +695,24 @@ TEST_F(hid_bpf, subprog_raw_event) } /* + * Attach hid_first_event to the given uhid device, + * attempt at re-attaching it, we should not lock and + * return an invalid struct bpf_link + */ +TEST_F(hid_bpf, multiple_attach) +{ + const struct test_program progs[] = { + { .name = "hid_first_event" }, + }; + struct bpf_link *link; + + LOAD_PROGRAMS(progs); + + link = bpf_map__attach_struct_ops(self->skel->maps.first_event); + ASSERT_NULL(link) TH_LOG("unexpected return value when re-attaching the struct_ops"); +} + +/* * Ensures that we can attach/detach programs */ TEST_F(hid_bpf, test_attach_detach) diff --git a/tools/testing/selftests/hid/progs/hid.c b/tools/testing/selftests/hid/progs/hid.c index ee9bbbcf751b..5ecc845ef792 100644 --- a/tools/testing/selftests/hid/progs/hid.c +++ b/tools/testing/selftests/hid/progs/hid.c @@ -455,7 +455,7 @@ struct { __type(value, struct elem); } hmap SEC(".maps"); -static int wq_cb_sleepable(void *map, int *key, struct bpf_wq *work) +static int wq_cb_sleepable(void *map, int *key, void *work) { __u8 buf[9] = {2, 3, 4, 5, 6, 7, 8, 9, 10}; struct hid_bpf_ctx *hid_ctx; diff --git a/tools/testing/selftests/hid/progs/hid_bpf_helpers.h b/tools/testing/selftests/hid/progs/hid_bpf_helpers.h index cfe37f491906..e5db897586bb 100644 --- a/tools/testing/selftests/hid/progs/hid_bpf_helpers.h +++ b/tools/testing/selftests/hid/progs/hid_bpf_helpers.h @@ -114,7 +114,7 @@ extern int hid_bpf_try_input_report(struct hid_bpf_ctx *ctx, extern int bpf_wq_init(struct bpf_wq *wq, void *p__map, unsigned int flags) __weak __ksym; extern int bpf_wq_start(struct bpf_wq *wq, unsigned int flags) __weak __ksym; extern int bpf_wq_set_callback_impl(struct bpf_wq *wq, - int (callback_fn)(void *map, int *key, struct bpf_wq *wq), + int (callback_fn)(void *map, int *key, void *wq), unsigned int flags__k, void *aux__ign) __ksym; #define bpf_wq_set_callback(timer, cb, flags) \ bpf_wq_set_callback_impl(timer, cb, flags, NULL) diff --git a/tools/testing/selftests/kselftest/ksft.py b/tools/testing/selftests/kselftest/ksft.py index cd89fb2bc10e..bf215790a89d 100644 --- a/tools/testing/selftests/kselftest/ksft.py +++ b/tools/testing/selftests/kselftest/ksft.py @@ -70,7 +70,7 @@ def test_result(condition, description=""): def finished(): - if ksft_cnt["pass"] == ksft_num_tests: + if ksft_cnt["pass"] + ksft_cnt["skip"] == ksft_num_tests: exit_code = KSFT_PASS else: exit_code = KSFT_FAIL diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c index 709d7d721760..4abebde78187 100644 --- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c +++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c @@ -32,13 +32,13 @@ static struct feature_id_reg feat_id_regs[] = { { ARM64_SYS_REG(3, 0, 10, 2, 2), /* PIRE0_EL1 */ ARM64_SYS_REG(3, 0, 0, 7, 3), /* ID_AA64MMFR3_EL1 */ - 4, + 8, 1 }, { ARM64_SYS_REG(3, 0, 10, 2, 3), /* PIR_EL1 */ ARM64_SYS_REG(3, 0, 0, 7, 3), /* ID_AA64MMFR3_EL1 */ - 4, + 8, 1 } }; diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c index f92c2fb23fcd..8e34f7fa44e9 100644 --- a/tools/testing/selftests/kvm/riscv/get-reg-list.c +++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c @@ -961,10 +961,10 @@ KVM_ISA_EXT_SIMPLE_CONFIG(zbkb, ZBKB); KVM_ISA_EXT_SIMPLE_CONFIG(zbkc, ZBKC); KVM_ISA_EXT_SIMPLE_CONFIG(zbkx, ZBKX); KVM_ISA_EXT_SIMPLE_CONFIG(zbs, ZBS); -KVM_ISA_EXT_SIMPLE_CONFIG(zca, ZCA), -KVM_ISA_EXT_SIMPLE_CONFIG(zcb, ZCB), -KVM_ISA_EXT_SIMPLE_CONFIG(zcd, ZCD), -KVM_ISA_EXT_SIMPLE_CONFIG(zcf, ZCF), +KVM_ISA_EXT_SIMPLE_CONFIG(zca, ZCA); +KVM_ISA_EXT_SIMPLE_CONFIG(zcb, ZCB); +KVM_ISA_EXT_SIMPLE_CONFIG(zcd, ZCD); +KVM_ISA_EXT_SIMPLE_CONFIG(zcf, ZCF); KVM_ISA_EXT_SIMPLE_CONFIG(zcmop, ZCMOP); KVM_ISA_EXT_SIMPLE_CONFIG(zfa, ZFA); KVM_ISA_EXT_SIMPLE_CONFIG(zfh, ZFH); diff --git a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c b/tools/testing/selftests/kvm/x86_64/xapic_state_test.c index 69849acd95b0..618cd2442390 100644 --- a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c +++ b/tools/testing/selftests/kvm/x86_64/xapic_state_test.c @@ -184,6 +184,33 @@ static void test_apic_id(void) kvm_vm_free(vm); } +static void test_x2apic_id(void) +{ + struct kvm_lapic_state lapic = {}; + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + int i; + + vm = vm_create_with_one_vcpu(&vcpu, NULL); + vcpu_set_msr(vcpu, MSR_IA32_APICBASE, MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE); + + /* + * Try stuffing a modified x2APIC ID, KVM should ignore the value and + * always return the vCPU's default/readonly x2APIC ID. + */ + for (i = 0; i <= 0xff; i++) { + *(u32 *)(lapic.regs + APIC_ID) = i << 24; + *(u32 *)(lapic.regs + APIC_SPIV) = APIC_SPIV_APIC_ENABLED; + vcpu_ioctl(vcpu, KVM_SET_LAPIC, &lapic); + + vcpu_ioctl(vcpu, KVM_GET_LAPIC, &lapic); + TEST_ASSERT(*((u32 *)&lapic.regs[APIC_ID]) == vcpu->id << 24, + "x2APIC ID should be fully readonly"); + } + + kvm_vm_free(vm); +} + int main(int argc, char *argv[]) { struct xapic_vcpu x = { @@ -211,4 +238,5 @@ int main(int argc, char *argv[]) kvm_vm_free(vm); test_apic_id(); + test_x2apic_id(); } diff --git a/tools/testing/selftests/landlock/base_test.c b/tools/testing/selftests/landlock/base_test.c index 3c1e9f35b531..3b26bf3cf5b9 100644 --- a/tools/testing/selftests/landlock/base_test.c +++ b/tools/testing/selftests/landlock/base_test.c @@ -9,6 +9,7 @@ #define _GNU_SOURCE #include <errno.h> #include <fcntl.h> +#include <linux/keyctl.h> #include <linux/landlock.h> #include <string.h> #include <sys/prctl.h> @@ -326,4 +327,77 @@ TEST(ruleset_fd_transfer) ASSERT_EQ(EXIT_SUCCESS, WEXITSTATUS(status)); } +TEST(cred_transfer) +{ + struct landlock_ruleset_attr ruleset_attr = { + .handled_access_fs = LANDLOCK_ACCESS_FS_READ_DIR, + }; + int ruleset_fd, dir_fd; + pid_t child; + int status; + + drop_caps(_metadata); + + dir_fd = open("/", O_RDONLY | O_DIRECTORY | O_CLOEXEC); + EXPECT_LE(0, dir_fd); + EXPECT_EQ(0, close(dir_fd)); + + /* Denies opening directories. */ + ruleset_fd = + landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0); + ASSERT_LE(0, ruleset_fd); + EXPECT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0)); + ASSERT_EQ(0, landlock_restrict_self(ruleset_fd, 0)); + EXPECT_EQ(0, close(ruleset_fd)); + + /* Checks ruleset enforcement. */ + EXPECT_EQ(-1, open("/", O_RDONLY | O_DIRECTORY | O_CLOEXEC)); + EXPECT_EQ(EACCES, errno); + + /* Needed for KEYCTL_SESSION_TO_PARENT permission checks */ + EXPECT_NE(-1, syscall(__NR_keyctl, KEYCTL_JOIN_SESSION_KEYRING, NULL, 0, + 0, 0)) + { + TH_LOG("Failed to join session keyring: %s", strerror(errno)); + } + + child = fork(); + ASSERT_LE(0, child); + if (child == 0) { + /* Checks ruleset enforcement. */ + EXPECT_EQ(-1, open("/", O_RDONLY | O_DIRECTORY | O_CLOEXEC)); + EXPECT_EQ(EACCES, errno); + + /* + * KEYCTL_SESSION_TO_PARENT is a no-op unless we have a + * different session keyring in the child, so make that happen. + */ + EXPECT_NE(-1, syscall(__NR_keyctl, KEYCTL_JOIN_SESSION_KEYRING, + NULL, 0, 0, 0)); + + /* + * KEYCTL_SESSION_TO_PARENT installs credentials on the parent + * that never go through the cred_prepare hook, this path uses + * cred_transfer instead. + */ + EXPECT_EQ(0, syscall(__NR_keyctl, KEYCTL_SESSION_TO_PARENT, 0, + 0, 0, 0)); + + /* Re-checks ruleset enforcement. */ + EXPECT_EQ(-1, open("/", O_RDONLY | O_DIRECTORY | O_CLOEXEC)); + EXPECT_EQ(EACCES, errno); + + _exit(_metadata->exit_code); + return; + } + + EXPECT_EQ(child, waitpid(child, &status, 0)); + EXPECT_EQ(1, WIFEXITED(status)); + EXPECT_EQ(EXIT_SUCCESS, WEXITSTATUS(status)); + + /* Re-checks ruleset enforcement. */ + EXPECT_EQ(-1, open("/", O_RDONLY | O_DIRECTORY | O_CLOEXEC)); + EXPECT_EQ(EACCES, errno); +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/landlock/config b/tools/testing/selftests/landlock/config index 0086efaa7b68..29af19c4e9f9 100644 --- a/tools/testing/selftests/landlock/config +++ b/tools/testing/selftests/landlock/config @@ -2,6 +2,7 @@ CONFIG_CGROUPS=y CONFIG_CGROUP_SCHED=y CONFIG_INET=y CONFIG_IPV6=y +CONFIG_KEYS=y CONFIG_NET=y CONFIG_NET_NS=y CONFIG_OVERLAY_FS=y diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index 901e0d07765b..cfad627e8d94 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -53,7 +53,9 @@ TEST_GEN_FILES += madv_populate TEST_GEN_FILES += map_fixed_noreplace TEST_GEN_FILES += map_hugetlb TEST_GEN_FILES += map_populate +ifneq (,$(filter $(ARCH),arm64 riscv riscv64 x86 x86_64)) TEST_GEN_FILES += memfd_secret +endif TEST_GEN_FILES += migration TEST_GEN_FILES += mkdirty TEST_GEN_FILES += mlock-random-test @@ -110,7 +112,7 @@ endif endif -ifneq (,$(filter $(ARCH),arm64 ia64 mips64 parisc64 powerpc riscv64 s390x sparc64 x86_64)) +ifneq (,$(filter $(ARCH),arm64 ia64 mips64 parisc64 powerpc riscv64 s390x sparc64 x86_64 s390)) TEST_GEN_FILES += va_high_addr_switch TEST_GEN_FILES += virtual_address_range TEST_GEN_FILES += write_to_hugetlbfs diff --git a/tools/testing/selftests/mm/compaction_test.c b/tools/testing/selftests/mm/compaction_test.c index e140558e6f53..2c3a0eb6b22d 100644 --- a/tools/testing/selftests/mm/compaction_test.c +++ b/tools/testing/selftests/mm/compaction_test.c @@ -89,9 +89,10 @@ int check_compaction(unsigned long mem_free, unsigned long hugepage_size, int fd, ret = -1; int compaction_index = 0; char nr_hugepages[20] = {0}; - char init_nr_hugepages[20] = {0}; + char init_nr_hugepages[24] = {0}; - sprintf(init_nr_hugepages, "%lu", initial_nr_hugepages); + snprintf(init_nr_hugepages, sizeof(init_nr_hugepages), + "%lu", initial_nr_hugepages); /* We want to test with 80% of available memory. Else, OOM killer comes in to play */ diff --git a/tools/testing/selftests/mm/mremap_test.c b/tools/testing/selftests/mm/mremap_test.c index 1b03bcfaefdf..5a3a9bcba640 100644 --- a/tools/testing/selftests/mm/mremap_test.c +++ b/tools/testing/selftests/mm/mremap_test.c @@ -22,8 +22,10 @@ #define VALIDATION_DEFAULT_THRESHOLD 4 /* 4MB */ #define VALIDATION_NO_THRESHOLD 0 /* Verify the entire region */ +#ifndef MIN #define MIN(X, Y) ((X) < (Y) ? (X) : (Y)) #define MAX(X, Y) ((X) > (Y) ? (X) : (Y)) +#endif #define SIZE_MB(m) ((size_t)m * (1024 * 1024)) #define SIZE_KB(k) ((size_t)k * 1024) diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index 03ac4f2e1cce..36045edb10de 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -374,8 +374,11 @@ CATEGORY="hmm" run_test bash ./test_hmm.sh smoke # MADV_POPULATE_READ and MADV_POPULATE_WRITE tests CATEGORY="madv_populate" run_test ./madv_populate +if [ -x ./memfd_secret ] +then (echo 0 | sudo tee /proc/sys/kernel/yama/ptrace_scope 2>&1) | tap_prefix CATEGORY="memfd_secret" run_test ./memfd_secret +fi # KSM KSM_MERGE_TIME_HUGE_PAGES test with size of 100 CATEGORY="ksm" run_test ./ksm_tests -H -s 100 diff --git a/tools/testing/selftests/mm/va_high_addr_switch.c b/tools/testing/selftests/mm/va_high_addr_switch.c index fa7eabfaf841..896b3f73fc53 100644 --- a/tools/testing/selftests/mm/va_high_addr_switch.c +++ b/tools/testing/selftests/mm/va_high_addr_switch.c @@ -293,6 +293,20 @@ static int run_test(struct testcase *test, int count) return ret; } +#ifdef __aarch64__ +/* Check if userspace VA > 48 bits */ +static int high_address_present(void) +{ + void *ptr = mmap((void *)(1UL << 50), 1, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED, -1, 0); + if (ptr == MAP_FAILED) + return 0; + + munmap(ptr, 1); + return 1; +} +#endif + static int supported_arch(void) { #if defined(__powerpc64__) @@ -300,7 +314,7 @@ static int supported_arch(void) #elif defined(__x86_64__) return 1; #elif defined(__aarch64__) - return 1; + return high_address_present(); #else return 0; #endif diff --git a/tools/testing/selftests/net/af_unix/msg_oob.c b/tools/testing/selftests/net/af_unix/msg_oob.c index 16d0c172eaeb..535eb2c3d7d1 100644 --- a/tools/testing/selftests/net/af_unix/msg_oob.c +++ b/tools/testing/selftests/net/af_unix/msg_oob.c @@ -209,7 +209,7 @@ static void __sendpair(struct __test_metadata *_metadata, static void __recvpair(struct __test_metadata *_metadata, FIXTURE_DATA(msg_oob) *self, - const void *expected_buf, int expected_len, + const char *expected_buf, int expected_len, int buf_len, int flags) { int i, ret[2], recv_errno[2], expected_errno = 0; diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index d0219032f773..8ee4489238ca 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -146,6 +146,7 @@ cleanup_ns() for ns in "$@"; do [ -z "${ns}" ] && continue + ip netns pids "${ns}" 2> /dev/null | xargs -r kill || true ip netns delete "${ns}" &> /dev/null || true if ! busywait $BUSYWAIT_TIMEOUT ip netns list \| grep -vq "^$ns$" &> /dev/null; then echo "Warn: Failed to remove namespace $ns" diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c index d2043ec3bf6d..4209b9569039 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.c +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -1115,11 +1115,11 @@ again: return 1; } - if (--cfg_repeat > 0) { - if (cfg_input) - close(fd); + if (cfg_input) + close(fd); + + if (--cfg_repeat > 0) goto again; - } return 0; } diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 108aeeb84ef1..9ea6d698e9d3 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -661,7 +661,7 @@ pm_nl_check_endpoint() done if [ -z "${id}" ]; then - test_fail "bad test - missing endpoint id" + fail_test "bad test - missing endpoint id" return fi @@ -1415,18 +1415,28 @@ chk_add_nr() local add_nr=$1 local echo_nr=$2 local port_nr=${3:-0} - local syn_nr=${4:-$port_nr} - local syn_ack_nr=${5:-$port_nr} - local ack_nr=${6:-$port_nr} - local mis_syn_nr=${7:-0} - local mis_ack_nr=${8:-0} + local ns_invert=${4:-""} + local syn_nr=$port_nr + local syn_ack_nr=$port_nr + local ack_nr=$port_nr + local mis_syn_nr=0 + local mis_ack_nr=0 + local ns_tx=$ns1 + local ns_rx=$ns2 + local extra_msg="" local count local timeout - timeout=$(ip netns exec $ns1 sysctl -n net.mptcp.add_addr_timeout) + if [[ $ns_invert = "invert" ]]; then + ns_tx=$ns2 + ns_rx=$ns1 + extra_msg="invert" + fi + + timeout=$(ip netns exec ${ns_tx} sysctl -n net.mptcp.add_addr_timeout) print_check "add" - count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtAddAddr") + count=$(mptcp_lib_get_counter ${ns_rx} "MPTcpExtAddAddr") if [ -z "$count" ]; then print_skip # if the test configured a short timeout tolerate greater then expected @@ -1438,7 +1448,7 @@ chk_add_nr() fi print_check "echo" - count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtEchoAdd") + count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtEchoAdd") if [ -z "$count" ]; then print_skip elif [ "$count" != "$echo_nr" ]; then @@ -1449,7 +1459,7 @@ chk_add_nr() if [ $port_nr -gt 0 ]; then print_check "pt" - count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtPortAdd") + count=$(mptcp_lib_get_counter ${ns_rx} "MPTcpExtPortAdd") if [ -z "$count" ]; then print_skip elif [ "$count" != "$port_nr" ]; then @@ -1459,7 +1469,7 @@ chk_add_nr() fi print_check "syn" - count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPJoinPortSynRx") + count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMPJoinPortSynRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$syn_nr" ]; then @@ -1470,7 +1480,7 @@ chk_add_nr() fi print_check "synack" - count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtMPJoinPortSynAckRx") + count=$(mptcp_lib_get_counter ${ns_rx} "MPTcpExtMPJoinPortSynAckRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$syn_ack_nr" ]; then @@ -1481,7 +1491,7 @@ chk_add_nr() fi print_check "ack" - count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPJoinPortAckRx") + count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMPJoinPortAckRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$ack_nr" ]; then @@ -1492,7 +1502,7 @@ chk_add_nr() fi print_check "syn" - count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMismatchPortSynRx") + count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMismatchPortSynRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$mis_syn_nr" ]; then @@ -1503,7 +1513,7 @@ chk_add_nr() fi print_check "ack" - count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMismatchPortAckRx") + count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMismatchPortAckRx") if [ -z "$count" ]; then print_skip elif [ "$count" != "$mis_ack_nr" ]; then @@ -1513,6 +1523,8 @@ chk_add_nr() print_ok fi fi + + print_info "$extra_msg" } chk_add_tx_nr() @@ -1634,6 +1646,8 @@ chk_prio_nr() { local mp_prio_nr_tx=$1 local mp_prio_nr_rx=$2 + local mpj_syn=$3 + local mpj_syn_ack=$4 local count print_check "ptx" @@ -1655,6 +1669,26 @@ chk_prio_nr() else print_ok fi + + print_check "syn backup" + count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPJoinSynBackupRx") + if [ -z "$count" ]; then + print_skip + elif [ "$count" != "$mpj_syn" ]; then + fail_test "got $count JOIN[s] syn with Backup expected $mpj_syn" + else + print_ok + fi + + print_check "synack backup" + count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtMPJoinSynAckBackupRx") + if [ -z "$count" ]; then + print_skip + elif [ "$count" != "$mpj_syn_ack" ]; then + fail_test "got $count JOIN[s] synack with Backup expected $mpj_syn_ack" + else + print_ok + fi } chk_subflow_nr() @@ -1955,6 +1989,21 @@ signal_address_tests() chk_add_nr 1 1 fi + # uncommon: subflow and signal flags on the same endpoint + # or because the user wrongly picked both, but still expects the client + # to create additional subflows + if reset "subflow and signal together"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags signal,subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + chk_add_nr 1 1 0 invert # only initiated by ns2 + chk_add_nr 0 0 0 # none initiated by ns1 + chk_rst_nr 0 0 invert # no RST sent by the client + chk_rst_nr 0 0 # no RST sent by the server + fi + # accept and use add_addr with additional subflows if reset "multiple subflows and signal"; then pm_nl_set_limits $ns1 0 3 @@ -2612,33 +2661,46 @@ backup_tests() sflags=nobackup speed=slow \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 1 1 1 - chk_prio_nr 0 1 + chk_prio_nr 0 1 1 0 fi # single address, backup if reset "single address, backup" && continue_if mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal,backup + pm_nl_set_limits $ns2 1 1 + sflags=nobackup speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + chk_add_nr 1 1 + chk_prio_nr 1 0 0 1 + fi + + # single address, switch to backup + if reset "single address, switch to backup" && + continue_if mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then + pm_nl_set_limits $ns1 0 1 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal pm_nl_set_limits $ns2 1 1 sflags=backup speed=slow \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 1 1 1 chk_add_nr 1 1 - chk_prio_nr 1 1 + chk_prio_nr 1 1 0 0 fi # single address with port, backup if reset "single address with port, backup" && continue_if mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then pm_nl_set_limits $ns1 0 1 - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal,backup port 10100 pm_nl_set_limits $ns2 1 1 - sflags=backup speed=slow \ + sflags=nobackup speed=slow \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 1 1 1 chk_add_nr 1 1 - chk_prio_nr 1 1 + chk_prio_nr 1 0 0 1 fi if reset "mpc backup" && @@ -2647,17 +2709,26 @@ backup_tests() speed=slow \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 0 0 0 - chk_prio_nr 0 1 + chk_prio_nr 0 1 0 0 fi if reset "mpc backup both sides" && continue_if mptcp_lib_kallsyms_doesnt_have "T mptcp_subflow_send_ack$"; then - pm_nl_add_endpoint $ns1 10.0.1.1 flags subflow,backup + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns1 10.0.1.1 flags signal,backup pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,backup + + # 10.0.2.2 (non-backup) -> 10.0.1.1 (backup) + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow + # 10.0.1.2 (backup) -> 10.0.2.1 (non-backup) + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + ip -net "$ns2" route add 10.0.2.1 via 10.0.1.1 dev ns2eth1 # force this path + speed=slow \ run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr 0 0 0 - chk_prio_nr 1 1 + chk_join_nr 2 2 2 + chk_prio_nr 1 1 1 1 fi if reset "mpc switch to backup" && @@ -2666,7 +2737,7 @@ backup_tests() sflags=backup speed=slow \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 0 0 0 - chk_prio_nr 0 1 + chk_prio_nr 0 1 0 0 fi if reset "mpc switch to backup both sides" && @@ -2676,7 +2747,7 @@ backup_tests() sflags=backup speed=slow \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 0 0 0 - chk_prio_nr 1 1 + chk_prio_nr 1 1 0 0 fi } @@ -3053,7 +3124,7 @@ fullmesh_tests() addr_nr_ns2=1 sflags=backup,fullmesh speed=slow \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 2 2 2 - chk_prio_nr 0 1 + chk_prio_nr 0 1 1 0 chk_rm_nr 0 1 fi @@ -3066,7 +3137,7 @@ fullmesh_tests() sflags=nobackup,nofullmesh speed=slow \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 2 2 2 - chk_prio_nr 0 1 + chk_prio_nr 0 1 1 0 chk_rm_nr 0 1 fi } @@ -3318,7 +3389,7 @@ userspace_tests() sflags=backup speed=slow \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 1 1 0 - chk_prio_nr 0 0 + chk_prio_nr 0 0 0 0 fi # userspace pm type prevents rm_addr @@ -3526,6 +3597,35 @@ endpoint_tests() chk_mptcp_info subflows 1 subflows 1 mptcp_lib_kill_wait $tests_pid fi + + # remove and re-add + if reset "delete re-add signal" && + mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then + pm_nl_set_limits $ns1 1 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 id 1 flags signal + test_linkfail=4 speed=20 \ + run_tests $ns1 $ns2 10.0.1.1 & + local tests_pid=$! + + wait_mpj $ns2 + pm_nl_check_endpoint "creation" \ + $ns1 10.0.2.1 id 1 flags signal + chk_subflow_nr "before delete" 2 + chk_mptcp_info subflows 1 subflows 1 + + pm_nl_del_endpoint $ns1 1 10.0.2.1 + sleep 0.5 + chk_subflow_nr "after delete" 1 + chk_mptcp_info subflows 0 subflows 0 + + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + wait_mpj $ns2 + chk_subflow_nr "after re-add" 2 + chk_mptcp_info subflows 1 subflows 1 + mptcp_lib_kill_wait $tests_pid + fi + } # [$1: error message] diff --git a/tools/testing/selftests/net/netfilter/Makefile b/tools/testing/selftests/net/netfilter/Makefile index 47945b2b3f92..d13fb5ea3e89 100644 --- a/tools/testing/selftests/net/netfilter/Makefile +++ b/tools/testing/selftests/net/netfilter/Makefile @@ -7,6 +7,7 @@ MNL_CFLAGS := $(shell $(HOSTPKG_CONFIG) --cflags libmnl 2>/dev/null) MNL_LDLIBS := $(shell $(HOSTPKG_CONFIG) --libs libmnl 2>/dev/null || echo -lmnl) TEST_PROGS := br_netfilter.sh bridge_brouter.sh +TEST_PROGS += br_netfilter_queue.sh TEST_PROGS += conntrack_icmp_related.sh TEST_PROGS += conntrack_ipip_mtu.sh TEST_PROGS += conntrack_tcp_unreplied.sh diff --git a/tools/testing/selftests/net/netfilter/br_netfilter_queue.sh b/tools/testing/selftests/net/netfilter/br_netfilter_queue.sh new file mode 100755 index 000000000000..6a764d70ab06 --- /dev/null +++ b/tools/testing/selftests/net/netfilter/br_netfilter_queue.sh @@ -0,0 +1,78 @@ +#!/bin/bash + +source lib.sh + +checktool "nft --version" "run test without nft tool" + +cleanup() { + cleanup_all_ns +} + +setup_ns c1 c2 c3 sender + +trap cleanup EXIT + +nf_queue_wait() +{ + grep -q "^ *$1 " "/proc/self/net/netfilter/nfnetlink_queue" +} + +port_add() { + ns="$1" + dev="$2" + a="$3" + + ip link add name "$dev" type veth peer name "$dev" netns "$ns" + + ip -net "$ns" addr add 192.168.1."$a"/24 dev "$dev" + ip -net "$ns" link set "$dev" up + + ip link set "$dev" master br0 + ip link set "$dev" up +} + +[ "${1}" != "run" ] && { unshare -n "${0}" run; exit $?; } + +ip link add br0 type bridge +ip addr add 192.168.1.254/24 dev br0 + +port_add "$c1" "c1" 1 +port_add "$c2" "c2" 2 +port_add "$c3" "c3" 3 +port_add "$sender" "sender" 253 + +ip link set br0 up + +modprobe -q br_netfilter + +sysctl net.bridge.bridge-nf-call-iptables=1 || exit 1 + +ip netns exec "$sender" ping -I sender -c1 192.168.1.1 || exit 1 +ip netns exec "$sender" ping -I sender -c1 192.168.1.2 || exit 2 +ip netns exec "$sender" ping -I sender -c1 192.168.1.3 || exit 3 + +nft -f /dev/stdin <<EOF +table ip filter { + chain forward { + type filter hook forward priority 0; policy accept; + ct state new counter + ip protocol icmp counter queue num 0 bypass + } +} +EOF +./nf_queue -t 5 > /dev/null & + +busywait 5000 nf_queue_wait + +for i in $(seq 1 5); do conntrack -F > /dev/null 2> /dev/null; sleep 0.1 ; done & +ip netns exec "$sender" ping -I sender -f -c 50 -b 192.168.1.255 + +read t < /proc/sys/kernel/tainted +if [ "$t" -eq 0 ];then + echo PASS: kernel not tainted +else + echo ERROR: kernel is tainted + exit 1 +fi + +exit 0 diff --git a/tools/testing/selftests/net/udpgso.c b/tools/testing/selftests/net/udpgso.c index 3e74cfa1a2bf..3f2fca02fec5 100644 --- a/tools/testing/selftests/net/udpgso.c +++ b/tools/testing/selftests/net/udpgso.c @@ -67,6 +67,7 @@ struct testcase { int gso_len; /* mss after applying gso */ int r_num_mss; /* recv(): number of calls of full mss */ int r_len_last; /* recv(): size of last non-mss dgram, if any */ + bool v6_ext_hdr; /* send() dgrams with IPv6 extension headers */ }; const struct in6_addr addr6 = { @@ -77,6 +78,8 @@ const struct in_addr addr4 = { __constant_htonl(0x0a000001), /* 10.0.0.1 */ }; +static const char ipv6_hopopts_pad1[8] = { 0 }; + struct testcase testcases_v4[] = { { /* no GSO: send a single byte */ @@ -256,6 +259,13 @@ struct testcase testcases_v6[] = { .r_num_mss = 2, }, { + /* send 2 1B segments with extension headers */ + .tlen = 2, + .gso_len = 1, + .r_num_mss = 2, + .v6_ext_hdr = true, + }, + { /* send 2B + 2B + 1B segments */ .tlen = 5, .gso_len = 2, @@ -396,11 +406,18 @@ static void run_one(struct testcase *test, int fdt, int fdr, int i, ret, val, mss; bool sent; - fprintf(stderr, "ipv%d tx:%d gso:%d %s\n", + fprintf(stderr, "ipv%d tx:%d gso:%d %s%s\n", addr->sa_family == AF_INET ? 4 : 6, test->tlen, test->gso_len, + test->v6_ext_hdr ? "ext-hdr " : "", test->tfail ? "(fail)" : ""); + if (test->v6_ext_hdr) { + if (setsockopt(fdt, IPPROTO_IPV6, IPV6_HOPOPTS, + ipv6_hopopts_pad1, sizeof(ipv6_hopopts_pad1))) + error(1, errno, "setsockopt ipv6 hopopts"); + } + val = test->gso_len; if (cfg_do_setsockopt) { if (setsockopt(fdt, SOL_UDP, UDP_SEGMENT, &val, sizeof(val))) @@ -412,6 +429,12 @@ static void run_one(struct testcase *test, int fdt, int fdr, error(1, 0, "send succeeded while expecting failure"); if (!sent && !test->tfail) error(1, 0, "send failed while expecting success"); + + if (test->v6_ext_hdr) { + if (setsockopt(fdt, IPPROTO_IPV6, IPV6_HOPOPTS, NULL, 0)) + error(1, errno, "setsockopt ipv6 hopopts clear"); + } + if (!sent) return; diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index e3f97f90d8db..8c3a73461475 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -60,7 +60,9 @@ #define SKIP(s, ...) XFAIL(s, ##__VA_ARGS__) #endif +#ifndef MIN #define MIN(X, Y) ((X) < (Y) ? (X) : (Y)) +#endif #ifndef PR_SET_PTRACER # define PR_SET_PTRACER 0x59616d61 diff --git a/tools/testing/selftests/turbostat/added_perf_counters.py b/tools/testing/selftests/turbostat/added_perf_counters.py new file mode 100755 index 000000000000..9ab4aaf45fb8 --- /dev/null +++ b/tools/testing/selftests/turbostat/added_perf_counters.py @@ -0,0 +1,178 @@ +#!/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +import subprocess +from shutil import which +from os import pread + +class PerfCounterInfo: + def __init__(self, subsys, event): + self.subsys = subsys + self.event = event + + def get_perf_event_name(self): + return f'{self.subsys}/{self.event}/' + + def get_turbostat_perf_id(self, counter_scope, counter_type, column_name): + return f'perf/{self.subsys}/{self.event},{counter_scope},{counter_type},{column_name}' + +PERF_COUNTERS_CANDIDATES = [ + PerfCounterInfo('msr', 'mperf'), + PerfCounterInfo('msr', 'aperf'), + PerfCounterInfo('msr', 'tsc'), + PerfCounterInfo('cstate_core', 'c1-residency'), + PerfCounterInfo('cstate_core', 'c6-residency'), + PerfCounterInfo('cstate_core', 'c7-residency'), + PerfCounterInfo('cstate_pkg', 'c2-residency'), + PerfCounterInfo('cstate_pkg', 'c3-residency'), + PerfCounterInfo('cstate_pkg', 'c6-residency'), + PerfCounterInfo('cstate_pkg', 'c7-residency'), + PerfCounterInfo('cstate_pkg', 'c8-residency'), + PerfCounterInfo('cstate_pkg', 'c9-residency'), + PerfCounterInfo('cstate_pkg', 'c10-residency'), +] +present_perf_counters = [] + +def check_perf_access(): + perf = which('perf') + if perf is None: + print('SKIP: Could not find perf binary, thus could not determine perf access.') + return False + + def has_perf_counter_access(counter_name): + proc_perf = subprocess.run([perf, 'stat', '-e', counter_name, '--timeout', '10'], + capture_output = True) + + if proc_perf.returncode != 0: + print(f'SKIP: Could not read {counter_name} perf counter.') + return False + + if b'<not supported>' in proc_perf.stderr: + print(f'SKIP: Could not read {counter_name} perf counter.') + return False + + return True + + for counter in PERF_COUNTERS_CANDIDATES: + if has_perf_counter_access(counter.get_perf_event_name()): + present_perf_counters.append(counter) + + if len(present_perf_counters) == 0: + print('SKIP: Could not read any perf counter.') + return False + + if len(present_perf_counters) != len(PERF_COUNTERS_CANDIDATES): + print(f'WARN: Could not access all of the counters - some will be left untested') + + return True + +if not check_perf_access(): + exit(0) + +turbostat_counter_source_opts = [''] + +turbostat = which('turbostat') +if turbostat is None: + print('Could not find turbostat binary') + exit(1) + +timeout = which('timeout') +if timeout is None: + print('Could not find timeout binary') + exit(1) + +proc_turbostat = subprocess.run([turbostat, '--list'], capture_output = True) +if proc_turbostat.returncode != 0: + print(f'turbostat failed with {proc_turbostat.returncode}') + exit(1) + +EXPECTED_COLUMNS_DEBUG_DEFAULT = [b'usec', b'Time_Of_Day_Seconds', b'APIC', b'X2APIC'] + +expected_columns = [b'CPU'] +counters_argv = [] +for counter in present_perf_counters: + if counter.subsys == 'cstate_core': + counter_scope = 'core' + elif counter.subsys == 'cstate_pkg': + counter_scope = 'package' + else: + counter_scope = 'cpu' + + counter_type = 'delta' + column_name = counter.event + + cparams = counter.get_turbostat_perf_id( + counter_scope = counter_scope, + counter_type = counter_type, + column_name = column_name + ) + expected_columns.append(column_name.encode()) + counters_argv.extend(['--add', cparams]) + +expected_columns_debug = EXPECTED_COLUMNS_DEBUG_DEFAULT + expected_columns + +def gen_user_friendly_cmdline(argv_): + argv = argv_[:] + ret = '' + + while len(argv) != 0: + arg = argv.pop(0) + arg_next = '' + + if arg in ('-i', '--show', '--add'): + arg_next = argv.pop(0) if len(argv) > 0 else '' + + ret += f'{arg} {arg_next} \\\n\t' + + # Remove the last separator and return + return ret[:-4] + +# +# Run turbostat for some time and send SIGINT +# +timeout_argv = [timeout, '--preserve-status', '-s', 'SIGINT', '-k', '3', '0.2s'] +turbostat_argv = [turbostat, '-i', '0.50', '--show', 'CPU'] + counters_argv + +def check_columns_or_fail(expected_columns: list, actual_columns: list): + if len(actual_columns) != len(expected_columns): + print(f'turbostat column check failed\n{expected_columns=}\n{actual_columns=}') + exit(1) + + failed = False + for expected_column in expected_columns: + if expected_column not in actual_columns: + print(f'turbostat column check failed: missing column {expected_column.decode()}') + failed = True + + if failed: + exit(1) + +cmdline = gen_user_friendly_cmdline(turbostat_argv) +print(f'Running turbostat with:\n\t{cmdline}\n... ', end = '', flush = True) +proc_turbostat = subprocess.run(timeout_argv + turbostat_argv, capture_output = True) +if proc_turbostat.returncode != 0: + print(f'turbostat failed with {proc_turbostat.returncode}') + exit(1) + +actual_columns = proc_turbostat.stdout.split(b'\n')[0].split(b'\t') +check_columns_or_fail(expected_columns, actual_columns) +print('OK') + +# +# Same, but with --debug +# +# We explicitly specify '--show CPU' to make sure turbostat +# don't show a bunch of default counters instead. +# +turbostat_argv.append('--debug') + +cmdline = gen_user_friendly_cmdline(turbostat_argv) +print(f'Running turbostat (in debug mode) with:\n\t{cmdline}\n... ', end = '', flush = True) +proc_turbostat = subprocess.run(timeout_argv + turbostat_argv, capture_output = True) +if proc_turbostat.returncode != 0: + print(f'turbostat failed with {proc_turbostat.returncode}') + exit(1) + +actual_columns = proc_turbostat.stdout.split(b'\n')[0].split(b'\t') +check_columns_or_fail(expected_columns_debug, actual_columns) +print('OK') diff --git a/tools/testing/selftests/turbostat/smi_aperf_mperf.py b/tools/testing/selftests/turbostat/smi_aperf_mperf.py new file mode 100755 index 000000000000..6289cc47d5f0 --- /dev/null +++ b/tools/testing/selftests/turbostat/smi_aperf_mperf.py @@ -0,0 +1,157 @@ +#!/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +import subprocess +from shutil import which +from os import pread + +# CDLL calls dlopen underneath. +# Calling it with None (null), we get handle to the our own image (python interpreter). +# We hope to find sched_getcpu() inside ;] +# This is a bit ugly, but helps shipping working software, so.. +try: + import ctypes + + this_image = ctypes.CDLL(None) + BASE_CPU = this_image.sched_getcpu() +except: + BASE_CPU = 0 # If we fail, set to 0 and pray it's not offline. + +MSR_IA32_MPERF = 0x000000e7 +MSR_IA32_APERF = 0x000000e8 + +def check_perf_access(): + perf = which('perf') + if perf is None: + print('SKIP: Could not find perf binary, thus could not determine perf access.') + return False + + def has_perf_counter_access(counter_name): + proc_perf = subprocess.run([perf, 'stat', '-e', counter_name, '--timeout', '10'], + capture_output = True) + + if proc_perf.returncode != 0: + print(f'SKIP: Could not read {counter_name} perf counter, assuming no access.') + return False + + if b'<not supported>' in proc_perf.stderr: + print(f'SKIP: Could not read {counter_name} perf counter, assuming no access.') + return False + + return True + + if not has_perf_counter_access('msr/mperf/'): + return False + if not has_perf_counter_access('msr/aperf/'): + return False + if not has_perf_counter_access('msr/smi/'): + return False + + return True + +def check_msr_access(): + try: + file_msr = open(f'/dev/cpu/{BASE_CPU}/msr', 'rb') + except: + return False + + if len(pread(file_msr.fileno(), 8, MSR_IA32_MPERF)) != 8: + return False + + if len(pread(file_msr.fileno(), 8, MSR_IA32_APERF)) != 8: + return False + + return True + +has_perf_access = check_perf_access() +has_msr_access = check_msr_access() + +turbostat_counter_source_opts = [''] + +if has_msr_access: + turbostat_counter_source_opts.append('--no-perf') +else: + print('SKIP: doesn\'t have MSR access, skipping run with --no-perf') + +if has_perf_access: + turbostat_counter_source_opts.append('--no-msr') +else: + print('SKIP: doesn\'t have perf access, skipping run with --no-msr') + +if not has_msr_access and not has_perf_access: + print('SKIP: No MSR nor perf access detected. Skipping the tests entirely') + exit(0) + +turbostat = which('turbostat') +if turbostat is None: + print('Could not find turbostat binary') + exit(1) + +timeout = which('timeout') +if timeout is None: + print('Could not find timeout binary') + exit(1) + +proc_turbostat = subprocess.run([turbostat, '--list'], capture_output = True) +if proc_turbostat.returncode != 0: + print(f'turbostat failed with {proc_turbostat.returncode}') + exit(1) + +EXPECTED_COLUMNS_DEBUG_DEFAULT = b'usec\tTime_Of_Day_Seconds\tAPIC\tX2APIC' + +SMI_APERF_MPERF_DEPENDENT_BICS = [ + 'SMI', + 'Avg_MHz', + 'Busy%', + 'Bzy_MHz', +] +if has_perf_access: + SMI_APERF_MPERF_DEPENDENT_BICS.append('IPC') + +for bic in SMI_APERF_MPERF_DEPENDENT_BICS: + for counter_source_opt in turbostat_counter_source_opts: + + # Ugly special case, but it is what it is.. + if counter_source_opt == '--no-perf' and bic == 'IPC': + continue + + expected_columns = bic.encode() + expected_columns_debug = EXPECTED_COLUMNS_DEBUG_DEFAULT + f'\t{bic}'.encode() + + # + # Run turbostat for some time and send SIGINT + # + timeout_argv = [timeout, '--preserve-status', '-s', 'SIGINT', '-k', '3', '0.2s'] + turbostat_argv = [turbostat, '-i', '0.50', '--show', bic] + + if counter_source_opt: + turbostat_argv.append(counter_source_opt) + + print(f'Running turbostat with {turbostat_argv=}... ', end = '', flush = True) + proc_turbostat = subprocess.run(timeout_argv + turbostat_argv, capture_output = True) + if proc_turbostat.returncode != 0: + print(f'turbostat failed with {proc_turbostat.returncode}') + exit(1) + + actual_columns = proc_turbostat.stdout.split(b'\n')[0] + if expected_columns != actual_columns: + print(f'turbostat column check failed\n{expected_columns=}\n{actual_columns=}') + exit(1) + print('OK') + + # + # Same, but with --debug + # + turbostat_argv.append('--debug') + + print(f'Running turbostat with {turbostat_argv=}... ', end = '', flush = True) + proc_turbostat = subprocess.run(timeout_argv + turbostat_argv, capture_output = True) + if proc_turbostat.returncode != 0: + print(f'turbostat failed with {proc_turbostat.returncode}') + exit(1) + + actual_columns = proc_turbostat.stdout.split(b'\n')[0] + if expected_columns_debug != actual_columns: + print(f'turbostat column check failed\n{expected_columns_debug=}\n{actual_columns=}') + exit(1) + print('OK') diff --git a/tools/tracing/rtla/src/osnoise_top.c b/tools/tracing/rtla/src/osnoise_top.c index f594a44df840..2f756628613d 100644 --- a/tools/tracing/rtla/src/osnoise_top.c +++ b/tools/tracing/rtla/src/osnoise_top.c @@ -651,8 +651,10 @@ struct osnoise_tool *osnoise_init_top(struct osnoise_top_params *params) return NULL; tool->data = osnoise_alloc_top(nr_cpus); - if (!tool->data) - goto out_err; + if (!tool->data) { + osnoise_destroy_tool(tool); + return NULL; + } tool->params = params; @@ -660,11 +662,6 @@ struct osnoise_tool *osnoise_init_top(struct osnoise_top_params *params) osnoise_top_handler, NULL); return tool; - -out_err: - osnoise_free_top(tool->data); - osnoise_destroy_tool(tool); - return NULL; } static int stop_tracing; |