diff options
Diffstat (limited to 'tools')
263 files changed, 6717 insertions, 2596 deletions
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index f8129c624b07..f7ddd73a8c0f 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -198,6 +198,15 @@ struct kvm_arm_copy_mte_tags { __u64 reserved[2]; }; +/* + * Counter/Timer offset structure. Describe the virtual/physical offset. + * To be used with KVM_ARM_SET_COUNTER_OFFSET. + */ +struct kvm_arm_counter_offset { + __u64 counter_offset; + __u64 reserved; +}; + #define KVM_ARM_TAGS_TO_GUEST 0 #define KVM_ARM_TAGS_FROM_GUEST 1 @@ -372,6 +381,10 @@ enum { #endif }; +/* Device Control API on vm fd */ +#define KVM_ARM_VM_SMCCC_CTRL 0 +#define KVM_ARM_VM_SMCCC_FILTER 0 + /* Device Control API: ARM VGIC */ #define KVM_DEV_ARM_VGIC_GRP_ADDR 0 #define KVM_DEV_ARM_VGIC_GRP_DIST_REGS 1 @@ -411,6 +424,8 @@ enum { #define KVM_ARM_VCPU_TIMER_CTRL 1 #define KVM_ARM_VCPU_TIMER_IRQ_VTIMER 0 #define KVM_ARM_VCPU_TIMER_IRQ_PTIMER 1 +#define KVM_ARM_VCPU_TIMER_IRQ_HVTIMER 2 +#define KVM_ARM_VCPU_TIMER_IRQ_HPTIMER 3 #define KVM_ARM_VCPU_PVTIME_CTRL 2 #define KVM_ARM_VCPU_PVTIME_IPA 0 @@ -469,6 +484,27 @@ enum { /* run->fail_entry.hardware_entry_failure_reason codes. */ #define KVM_EXIT_FAIL_ENTRY_CPU_UNSUPPORTED (1ULL << 0) +enum kvm_smccc_filter_action { + KVM_SMCCC_FILTER_HANDLE = 0, + KVM_SMCCC_FILTER_DENY, + KVM_SMCCC_FILTER_FWD_TO_USER, + +#ifdef __KERNEL__ + NR_SMCCC_FILTER_ACTIONS +#endif +}; + +struct kvm_smccc_filter { + __u32 base; + __u32 nr_functions; + __u8 action; + __u8 pad[15]; +}; + +/* arm64-specific KVM_EXIT_HYPERCALL flags */ +#define KVM_HYPERCALL_EXIT_SMC (1U << 0) +#define KVM_HYPERCALL_EXIT_16BIT (1U << 1) + #endif #endif /* __ARM_KVM_H__ */ diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index b89005819cd5..cb8ca46213be 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -97,7 +97,7 @@ #define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in IA32 userspace */ #define X86_FEATURE_REP_GOOD ( 3*32+16) /* REP microcode works well */ #define X86_FEATURE_AMD_LBR_V2 ( 3*32+17) /* AMD Last Branch Record Extension Version 2 */ -#define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" LFENCE synchronizes RDTSC */ +/* FREE, was #define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) "" LFENCE synchronizes RDTSC */ #define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */ #define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */ #define X86_FEATURE_ALWAYS ( 3*32+21) /* "" Always-present feature */ @@ -226,10 +226,9 @@ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ -#define X86_FEATURE_VNMI ( 8*32+ 1) /* Intel Virtual NMI */ -#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 2) /* Intel FlexPriority */ -#define X86_FEATURE_EPT ( 8*32+ 3) /* Intel Extended Page Table */ -#define X86_FEATURE_VPID ( 8*32+ 4) /* Intel Virtual Processor ID */ +#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 1) /* Intel FlexPriority */ +#define X86_FEATURE_EPT ( 8*32+ 2) /* Intel Extended Page Table */ +#define X86_FEATURE_VPID ( 8*32+ 3) /* Intel Virtual Processor ID */ #define X86_FEATURE_VMMCALL ( 8*32+15) /* Prefer VMMCALL to VMCALL */ #define X86_FEATURE_XENPV ( 8*32+16) /* "" Xen paravirtual guest */ @@ -307,14 +306,21 @@ #define X86_FEATURE_SGX_EDECCSSA (11*32+18) /* "" SGX EDECCSSA user leaf function */ #define X86_FEATURE_CALL_DEPTH (11*32+19) /* "" Call depth tracking for RSB stuffing */ #define X86_FEATURE_MSR_TSX_CTRL (11*32+20) /* "" MSR IA32_TSX_CTRL (Intel) implemented */ +#define X86_FEATURE_SMBA (11*32+21) /* "" Slow Memory Bandwidth Allocation */ +#define X86_FEATURE_BMEC (11*32+22) /* "" Bandwidth Monitoring Event Configuration */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ #define X86_FEATURE_CMPCCXADD (12*32+ 7) /* "" CMPccXADD instructions */ +#define X86_FEATURE_ARCH_PERFMON_EXT (12*32+ 8) /* "" Intel Architectural PerfMon Extension */ +#define X86_FEATURE_FZRM (12*32+10) /* "" Fast zero-length REP MOVSB */ +#define X86_FEATURE_FSRS (12*32+11) /* "" Fast short REP STOSB */ +#define X86_FEATURE_FSRC (12*32+12) /* "" Fast short REP {CMPSB,SCASB} */ #define X86_FEATURE_LKGS (12*32+18) /* "" Load "kernel" (userspace) GS */ #define X86_FEATURE_AMX_FP16 (12*32+21) /* "" AMX fp16 Support */ #define X86_FEATURE_AVX_IFMA (12*32+23) /* "" Support for VPMADD52[H,L]UQ */ +#define X86_FEATURE_LAM (12*32+26) /* Linear Address Masking */ /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */ #define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */ @@ -331,6 +337,7 @@ #define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */ #define X86_FEATURE_AMD_SSB_NO (13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */ #define X86_FEATURE_CPPC (13*32+27) /* Collaborative Processor Performance Control */ +#define X86_FEATURE_AMD_PSFD (13*32+28) /* "" Predictive Store Forwarding Disable */ #define X86_FEATURE_BTC_NO (13*32+29) /* "" Not vulnerable to Branch Type Confusion */ #define X86_FEATURE_BRS (13*32+31) /* Branch Sampling available */ @@ -363,6 +370,7 @@ #define X86_FEATURE_VGIF (15*32+16) /* Virtual GIF */ #define X86_FEATURE_X2AVIC (15*32+18) /* Virtual x2apic */ #define X86_FEATURE_V_SPEC_CTRL (15*32+20) /* Virtual SPEC_CTRL */ +#define X86_FEATURE_VNMI (15*32+25) /* Virtual NMI */ #define X86_FEATURE_SVME_ADDR_CHK (15*32+28) /* "" SVME addr check */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */ @@ -427,6 +435,13 @@ #define X86_FEATURE_V_TSC_AUX (19*32+ 9) /* "" Virtual TSC_AUX */ #define X86_FEATURE_SME_COHERENT (19*32+10) /* "" AMD hardware-enforced cache coherency */ +/* AMD-defined Extended Feature 2 EAX, CPUID level 0x80000021 (EAX), word 20 */ +#define X86_FEATURE_NO_NESTED_DATA_BP (20*32+ 0) /* "" No Nested Data Breakpoints */ +#define X86_FEATURE_LFENCE_RDTSC (20*32+ 2) /* "" LFENCE always serializing / synchronizes RDTSC */ +#define X86_FEATURE_NULL_SEL_CLR_BASE (20*32+ 6) /* "" Null Selector Clears Base */ +#define X86_FEATURE_AUTOIBRS (20*32+ 8) /* "" Automatic IBRS */ +#define X86_FEATURE_NO_SMM_CTL_MSR (20*32+ 9) /* "" SMM_CTL MSR is not present */ + /* * BUG word(s) */ @@ -467,5 +482,6 @@ #define X86_BUG_MMIO_UNKNOWN X86_BUG(26) /* CPU is too old and its MMIO Stale Data status is unknown */ #define X86_BUG_RETBLEED X86_BUG(27) /* CPU is affected by RETBleed */ #define X86_BUG_EIBRS_PBRSB X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */ +#define X86_BUG_SMT_RSB X86_BUG(29) /* CPU is vulnerable to Cross-Thread Return Address Predictions */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index 5dfa4fb76f4b..fafe9be7a6f4 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -75,6 +75,12 @@ # define DISABLE_CALL_DEPTH_TRACKING (1 << (X86_FEATURE_CALL_DEPTH & 31)) #endif +#ifdef CONFIG_ADDRESS_MASKING +# define DISABLE_LAM 0 +#else +# define DISABLE_LAM (1 << (X86_FEATURE_LAM & 31)) +#endif + #ifdef CONFIG_INTEL_IOMMU_SVM # define DISABLE_ENQCMD 0 #else @@ -115,7 +121,7 @@ #define DISABLED_MASK10 0 #define DISABLED_MASK11 (DISABLE_RETPOLINE|DISABLE_RETHUNK|DISABLE_UNRET| \ DISABLE_CALL_DEPTH_TRACKING) -#define DISABLED_MASK12 0 +#define DISABLED_MASK12 (DISABLE_LAM) #define DISABLED_MASK13 0 #define DISABLED_MASK14 0 #define DISABLED_MASK15 0 diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index ad35355ee43e..3aedae61af4f 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -206,6 +206,8 @@ /* Abbreviated from Intel SDM name IA32_INTEGRITY_CAPABILITIES */ #define MSR_INTEGRITY_CAPS 0x000002d9 +#define MSR_INTEGRITY_CAPS_ARRAY_BIST_BIT 2 +#define MSR_INTEGRITY_CAPS_ARRAY_BIST BIT(MSR_INTEGRITY_CAPS_ARRAY_BIST_BIT) #define MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT 4 #define MSR_INTEGRITY_CAPS_PERIODIC_BIST BIT(MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT) diff --git a/tools/arch/x86/include/asm/nops.h b/tools/arch/x86/include/asm/nops.h index c5573eaa5bb9..1c1b7550fa55 100644 --- a/tools/arch/x86/include/asm/nops.h +++ b/tools/arch/x86/include/asm/nops.h @@ -34,6 +34,8 @@ #define BYTES_NOP7 0x8d,0xb4,0x26,0x00,0x00,0x00,0x00 #define BYTES_NOP8 0x3e,BYTES_NOP7 +#define ASM_NOP_MAX 8 + #else /* @@ -47,6 +49,9 @@ * 6: osp nopl 0x00(%eax,%eax,1) * 7: nopl 0x00000000(%eax) * 8: nopl 0x00000000(%eax,%eax,1) + * 9: cs nopl 0x00000000(%eax,%eax,1) + * 10: osp cs nopl 0x00000000(%eax,%eax,1) + * 11: osp osp cs nopl 0x00000000(%eax,%eax,1) */ #define BYTES_NOP1 0x90 #define BYTES_NOP2 0x66,BYTES_NOP1 @@ -56,6 +61,15 @@ #define BYTES_NOP6 0x66,BYTES_NOP5 #define BYTES_NOP7 0x0f,0x1f,0x80,0x00,0x00,0x00,0x00 #define BYTES_NOP8 0x0f,0x1f,0x84,0x00,0x00,0x00,0x00,0x00 +#define BYTES_NOP9 0x2e,BYTES_NOP8 +#define BYTES_NOP10 0x66,BYTES_NOP9 +#define BYTES_NOP11 0x66,BYTES_NOP10 + +#define ASM_NOP9 _ASM_BYTES(BYTES_NOP9) +#define ASM_NOP10 _ASM_BYTES(BYTES_NOP10) +#define ASM_NOP11 _ASM_BYTES(BYTES_NOP11) + +#define ASM_NOP_MAX 11 #endif /* CONFIG_64BIT */ @@ -68,8 +82,6 @@ #define ASM_NOP7 _ASM_BYTES(BYTES_NOP7) #define ASM_NOP8 _ASM_BYTES(BYTES_NOP8) -#define ASM_NOP_MAX 8 - #ifndef __ASSEMBLY__ extern const unsigned char * const x86_nops[]; #endif diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index 7f467fe05d42..1a6a1f987949 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -559,4 +559,7 @@ struct kvm_pmu_event_filter { #define KVM_VCPU_TSC_CTRL 0 /* control group for the timestamp counter (TSC) */ #define KVM_VCPU_TSC_OFFSET 0 /* attribute for the TSC offset */ +/* x86-specific KVM_EXIT_HYPERCALL flags. */ +#define KVM_EXIT_HYPERCALL_LONG_MODE BIT(0) + #endif /* _ASM_X86_KVM_H */ diff --git a/tools/arch/x86/include/uapi/asm/prctl.h b/tools/arch/x86/include/uapi/asm/prctl.h index 500b96e71f18..e8d7ebbca1a4 100644 --- a/tools/arch/x86/include/uapi/asm/prctl.h +++ b/tools/arch/x86/include/uapi/asm/prctl.h @@ -16,8 +16,16 @@ #define ARCH_GET_XCOMP_GUEST_PERM 0x1024 #define ARCH_REQ_XCOMP_GUEST_PERM 0x1025 +#define ARCH_XCOMP_TILECFG 17 +#define ARCH_XCOMP_TILEDATA 18 + #define ARCH_MAP_VDSO_X32 0x2001 #define ARCH_MAP_VDSO_32 0x2002 #define ARCH_MAP_VDSO_64 0x2003 +#define ARCH_GET_UNTAG_MASK 0x4001 +#define ARCH_ENABLE_TAGGED_ADDR 0x4002 +#define ARCH_GET_MAX_TAG_BITS 0x4003 +#define ARCH_FORCE_TAGGED_SVA 0x4004 + #endif /* _ASM_X86_PRCTL_H */ diff --git a/tools/arch/x86/include/uapi/asm/unistd_32.h b/tools/arch/x86/include/uapi/asm/unistd_32.h index b8ddfc4c4ab0..bc48a4dabe5d 100644 --- a/tools/arch/x86/include/uapi/asm/unistd_32.h +++ b/tools/arch/x86/include/uapi/asm/unistd_32.h @@ -2,6 +2,9 @@ #ifndef __NR_fork #define __NR_fork 2 #endif +#ifndef __NR_execve +#define __NR_execve 11 +#endif #ifndef __NR_getppid #define __NR_getppid 64 #endif diff --git a/tools/arch/x86/kcpuid/.gitignore b/tools/arch/x86/kcpuid/.gitignore new file mode 100644 index 000000000000..1b8541bc8dd0 --- /dev/null +++ b/tools/arch/x86/kcpuid/.gitignore @@ -0,0 +1 @@ +kcpuid diff --git a/tools/arch/x86/kcpuid/kcpuid.c b/tools/arch/x86/kcpuid/kcpuid.c index 416f5b35dd8f..24b7d017ec2c 100644 --- a/tools/arch/x86/kcpuid/kcpuid.c +++ b/tools/arch/x86/kcpuid/kcpuid.c @@ -517,15 +517,16 @@ static void show_range(struct cpuid_range *range) static inline struct cpuid_func *index_to_func(u32 index) { struct cpuid_range *range; + u32 func_idx; range = (index & 0x80000000) ? leafs_ext : leafs_basic; - index &= 0x7FFFFFFF; + func_idx = index & 0xffff; - if (((index & 0xFFFF) + 1) > (u32)range->nr) { + if ((func_idx + 1) > (u32)range->nr) { printf("ERR: invalid input index (0x%x)\n", index); return NULL; } - return &range->funcs[index]; + return &range->funcs[func_idx]; } static void show_info(void) diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S index a91ac666f758..d055b82d22cc 100644 --- a/tools/arch/x86/lib/memcpy_64.S +++ b/tools/arch/x86/lib/memcpy_64.S @@ -10,13 +10,6 @@ .section .noinstr.text, "ax" /* - * We build a jump to memcpy_orig by default which gets NOPped out on - * the majority of x86 CPUs which set REP_GOOD. In addition, CPUs which - * have the enhanced REP MOVSB/STOSB feature (ERMS), change those NOPs - * to a jmp to memcpy_erms which does the REP; MOVSB mem copy. - */ - -/* * memcpy - Copy a memory block. * * Input: @@ -26,17 +19,21 @@ * * Output: * rax original destination + * + * The FSRM alternative should be done inline (avoiding the call and + * the disgusting return handling), but that would require some help + * from the compiler for better calling conventions. + * + * The 'rep movsb' itself is small enough to replace the call, but the + * two register moves blow up the code. And one of them is "needed" + * only for the return value that is the same as the source input, + * which the compiler could/should do much better anyway. */ SYM_TYPED_FUNC_START(__memcpy) - ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \ - "jmp memcpy_erms", X86_FEATURE_ERMS + ALTERNATIVE "jmp memcpy_orig", "", X86_FEATURE_FSRM movq %rdi, %rax movq %rdx, %rcx - shrq $3, %rcx - andl $7, %edx - rep movsq - movl %edx, %ecx rep movsb RET SYM_FUNC_END(__memcpy) @@ -45,17 +42,6 @@ EXPORT_SYMBOL(__memcpy) SYM_FUNC_ALIAS(memcpy, __memcpy) EXPORT_SYMBOL(memcpy) -/* - * memcpy_erms() - enhanced fast string memcpy. This is faster and - * simpler than memcpy. Use memcpy_erms when possible. - */ -SYM_FUNC_START_LOCAL(memcpy_erms) - movq %rdi, %rax - movq %rdx, %rcx - rep movsb - RET -SYM_FUNC_END(memcpy_erms) - SYM_FUNC_START_LOCAL(memcpy_orig) movq %rdi, %rax diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S index 6143b1a6fa2c..7c59a704c458 100644 --- a/tools/arch/x86/lib/memset_64.S +++ b/tools/arch/x86/lib/memset_64.S @@ -18,27 +18,22 @@ * rdx count (bytes) * * rax original destination + * + * The FSRS alternative should be done inline (avoiding the call and + * the disgusting return handling), but that would require some help + * from the compiler for better calling conventions. + * + * The 'rep stosb' itself is small enough to replace the call, but all + * the register moves blow up the code. And two of them are "needed" + * only for the return value that is the same as the source input, + * which the compiler could/should do much better anyway. */ SYM_FUNC_START(__memset) - /* - * Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended - * to use it when possible. If not available, use fast string instructions. - * - * Otherwise, use original memset function. - */ - ALTERNATIVE_2 "jmp memset_orig", "", X86_FEATURE_REP_GOOD, \ - "jmp memset_erms", X86_FEATURE_ERMS + ALTERNATIVE "jmp memset_orig", "", X86_FEATURE_FSRS movq %rdi,%r9 + movb %sil,%al movq %rdx,%rcx - andl $7,%edx - shrq $3,%rcx - /* expand byte value */ - movzbl %sil,%esi - movabs $0x0101010101010101,%rax - imulq %rsi,%rax - rep stosq - movl %edx,%ecx rep stosb movq %r9,%rax RET @@ -48,26 +43,6 @@ EXPORT_SYMBOL(__memset) SYM_FUNC_ALIAS(memset, __memset) EXPORT_SYMBOL(memset) -/* - * ISO C memset - set a memory block to a byte value. This function uses - * enhanced rep stosb to override the fast string function. - * The code is simpler and shorter than the fast string function as well. - * - * rdi destination - * rsi value (char) - * rdx count (bytes) - * - * rax original destination - */ -SYM_FUNC_START_LOCAL(memset_erms) - movq %rdi,%r9 - movb %sil,%al - movq %rdx,%rcx - rep stosb - movq %r9,%rax - RET -SYM_FUNC_END(memset_erms) - SYM_FUNC_START_LOCAL(memset_orig) movq %rdi,%r10 diff --git a/tools/gpio/lsgpio.c b/tools/gpio/lsgpio.c index c61d061247e1..52a0be45410c 100644 --- a/tools/gpio/lsgpio.c +++ b/tools/gpio/lsgpio.c @@ -94,7 +94,7 @@ static void print_attributes(struct gpio_v2_line_info *info) for (i = 0; i < info->num_attrs; i++) { if (info->attrs[i].id == GPIO_V2_LINE_ATTR_ID_DEBOUNCE) fprintf(stdout, ", debounce_period=%dusec", - info->attrs[0].debounce_period_us); + info->attrs[i].debounce_period_us); } } diff --git a/tools/include/asm/alternative.h b/tools/include/asm/alternative.h index b54bd860dff6..7ce02a223732 100644 --- a/tools/include/asm/alternative.h +++ b/tools/include/asm/alternative.h @@ -4,7 +4,6 @@ /* Just disable it so we can build arch/x86/lib/memcpy_64.S for perf bench: */ -#define altinstruction_entry # -#define ALTERNATIVE_2 # +#define ALTERNATIVE # #endif diff --git a/tools/include/linux/coresight-pmu.h b/tools/include/linux/coresight-pmu.h index cef3b1c25335..51ac441a37c3 100644 --- a/tools/include/linux/coresight-pmu.h +++ b/tools/include/linux/coresight-pmu.h @@ -21,19 +21,6 @@ */ #define CORESIGHT_LEGACY_CPU_TRACE_ID(cpu) (0x10 + (cpu * 2)) -/* CoreSight trace ID is currently the bottom 7 bits of the value */ -#define CORESIGHT_TRACE_ID_VAL_MASK GENMASK(6, 0) - -/* - * perf record will set the legacy meta data values as unused initially. - * This allows perf report to manage the decoders created when dynamic - * allocation in operation. - */ -#define CORESIGHT_TRACE_ID_UNUSED_FLAG BIT(31) - -/* Value to set for unused trace ID values */ -#define CORESIGHT_TRACE_ID_UNUSED_VAL 0x7F - /* * Below are the definition of bit offsets for perf option, and works as * arbitrary values for all ETM versions. diff --git a/tools/include/nolibc/Makefile b/tools/include/nolibc/Makefile index 9839feafd38a..64d67b080744 100644 --- a/tools/include/nolibc/Makefile +++ b/tools/include/nolibc/Makefile @@ -25,8 +25,23 @@ endif nolibc_arch := $(patsubst arm64,aarch64,$(ARCH)) arch_file := arch-$(nolibc_arch).h -all_files := ctype.h errno.h nolibc.h signal.h stackprotector.h std.h stdint.h \ - stdio.h stdlib.h string.h sys.h time.h types.h unistd.h +all_files := \ + compiler.h \ + ctype.h \ + errno.h \ + nolibc.h \ + signal.h \ + stackprotector.h \ + std.h \ + stdint.h \ + stdlib.h \ + string.h \ + sys.h \ + time.h \ + types.h \ + unistd.h \ + stdio.h \ + # install all headers needed to support a bare-metal compiler all: headers diff --git a/tools/include/nolibc/arch-aarch64.h b/tools/include/nolibc/arch-aarch64.h index 383baddef701..11f294a406b7 100644 --- a/tools/include/nolibc/arch-aarch64.h +++ b/tools/include/nolibc/arch-aarch64.h @@ -7,6 +7,8 @@ #ifndef _NOLIBC_ARCH_AARCH64_H #define _NOLIBC_ARCH_AARCH64_H +#include "compiler.h" + /* The struct returned by the newfstatat() syscall. Differs slightly from the * x86_64's stat one by field ordering, so be careful. */ @@ -173,27 +175,30 @@ char **environ __attribute__((weak)); const unsigned long *_auxv __attribute__((weak)); /* startup code */ -void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) _start(void) +void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) __no_stack_protector _start(void) { __asm__ volatile ( - "ldr x0, [sp]\n" // argc (x0) was in the stack - "add x1, sp, 8\n" // argv (x1) = sp - "lsl x2, x0, 3\n" // envp (x2) = 8*argc ... - "add x2, x2, 8\n" // + 8 (skip null) - "add x2, x2, x1\n" // + argv - "adrp x3, environ\n" // x3 = &environ (high bits) - "str x2, [x3, #:lo12:environ]\n" // store envp into environ - "mov x4, x2\n" // search for auxv (follows NULL after last env) +#ifdef _NOLIBC_STACKPROTECTOR + "bl __stack_chk_init\n" /* initialize stack protector */ +#endif + "ldr x0, [sp]\n" /* argc (x0) was in the stack */ + "add x1, sp, 8\n" /* argv (x1) = sp */ + "lsl x2, x0, 3\n" /* envp (x2) = 8*argc ... */ + "add x2, x2, 8\n" /* + 8 (skip null) */ + "add x2, x2, x1\n" /* + argv */ + "adrp x3, environ\n" /* x3 = &environ (high bits) */ + "str x2, [x3, #:lo12:environ]\n" /* store envp into environ */ + "mov x4, x2\n" /* search for auxv (follows NULL after last env) */ "0:\n" - "ldr x5, [x4], 8\n" // x5 = *x4; x4 += 8 - "cbnz x5, 0b\n" // and stop at NULL after last env - "adrp x3, _auxv\n" // x3 = &_auxv (high bits) - "str x4, [x3, #:lo12:_auxv]\n" // store x4 into _auxv - "and sp, x1, -16\n" // sp must be 16-byte aligned in the callee - "bl main\n" // main() returns the status code, we'll exit with it. - "mov x8, 93\n" // NR_exit == 93 + "ldr x5, [x4], 8\n" /* x5 = *x4; x4 += 8 */ + "cbnz x5, 0b\n" /* and stop at NULL after last env */ + "adrp x3, _auxv\n" /* x3 = &_auxv (high bits) */ + "str x4, [x3, #:lo12:_auxv]\n" /* store x4 into _auxv */ + "and sp, x1, -16\n" /* sp must be 16-byte aligned in the callee */ + "bl main\n" /* main() returns the status code, we'll exit with it. */ + "mov x8, 93\n" /* NR_exit == 93 */ "svc #0\n" ); __builtin_unreachable(); } -#endif // _NOLIBC_ARCH_AARCH64_H +#endif /* _NOLIBC_ARCH_AARCH64_H */ diff --git a/tools/include/nolibc/arch-arm.h b/tools/include/nolibc/arch-arm.h index 42499f23e73c..ca4c66987497 100644 --- a/tools/include/nolibc/arch-arm.h +++ b/tools/include/nolibc/arch-arm.h @@ -7,6 +7,8 @@ #ifndef _NOLIBC_ARCH_ARM_H #define _NOLIBC_ARCH_ARM_H +#include "compiler.h" + /* The struct returned by the stat() syscall, 32-bit only, the syscall returns * exactly 56 bytes (stops before the unused array). In big endian, the format * differs as devices are returned as short only. @@ -196,41 +198,67 @@ struct sys_stat_struct { _arg1; \ }) +#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \ +({ \ + register long _num __asm__(_NOLIBC_SYSCALL_REG) = (num); \ + register long _arg1 __asm__ ("r0") = (long)(arg1); \ + register long _arg2 __asm__ ("r1") = (long)(arg2); \ + register long _arg3 __asm__ ("r2") = (long)(arg3); \ + register long _arg4 __asm__ ("r3") = (long)(arg4); \ + register long _arg5 __asm__ ("r4") = (long)(arg5); \ + register long _arg6 __asm__ ("r5") = (long)(arg6); \ + \ + __asm__ volatile ( \ + _NOLIBC_THUMB_SET_R7 \ + "svc #0\n" \ + _NOLIBC_THUMB_RESTORE_R7 \ + : "=r"(_arg1), "=r" (_num) \ + : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \ + "r"(_arg6), "r"(_num) \ + : "memory", "cc", "lr" \ + ); \ + _arg1; \ +}) + + char **environ __attribute__((weak)); const unsigned long *_auxv __attribute__((weak)); /* startup code */ -void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) _start(void) +void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) __no_stack_protector _start(void) { __asm__ volatile ( - "pop {%r0}\n" // argc was in the stack - "mov %r1, %sp\n" // argv = sp +#ifdef _NOLIBC_STACKPROTECTOR + "bl __stack_chk_init\n" /* initialize stack protector */ +#endif + "pop {%r0}\n" /* argc was in the stack */ + "mov %r1, %sp\n" /* argv = sp */ - "add %r2, %r0, $1\n" // envp = (argc + 1) ... - "lsl %r2, %r2, $2\n" // * 4 ... - "add %r2, %r2, %r1\n" // + argv - "ldr %r3, 1f\n" // r3 = &environ (see below) - "str %r2, [r3]\n" // store envp into environ + "add %r2, %r0, $1\n" /* envp = (argc + 1) ... */ + "lsl %r2, %r2, $2\n" /* * 4 ... */ + "add %r2, %r2, %r1\n" /* + argv */ + "ldr %r3, 1f\n" /* r3 = &environ (see below) */ + "str %r2, [r3]\n" /* store envp into environ */ - "mov r4, r2\n" // search for auxv (follows NULL after last env) + "mov r4, r2\n" /* search for auxv (follows NULL after last env) */ "0:\n" - "mov r5, r4\n" // r5 = r4 - "add r4, r4, #4\n" // r4 += 4 - "ldr r5,[r5]\n" // r5 = *r5 = *(r4-4) - "cmp r5, #0\n" // and stop at NULL after last env + "mov r5, r4\n" /* r5 = r4 */ + "add r4, r4, #4\n" /* r4 += 4 */ + "ldr r5,[r5]\n" /* r5 = *r5 = *(r4-4) */ + "cmp r5, #0\n" /* and stop at NULL after last env */ "bne 0b\n" - "ldr %r3, 2f\n" // r3 = &_auxv (low bits) - "str r4, [r3]\n" // store r4 into _auxv + "ldr %r3, 2f\n" /* r3 = &_auxv (low bits) */ + "str r4, [r3]\n" /* store r4 into _auxv */ - "mov %r3, $8\n" // AAPCS : sp must be 8-byte aligned in the - "neg %r3, %r3\n" // callee, and bl doesn't push (lr=pc) - "and %r3, %r3, %r1\n" // so we do sp = r1(=sp) & r3(=-8); - "mov %sp, %r3\n" // + "mov %r3, $8\n" /* AAPCS : sp must be 8-byte aligned in the */ + "neg %r3, %r3\n" /* callee, and bl doesn't push (lr=pc) */ + "and %r3, %r3, %r1\n" /* so we do sp = r1(=sp) & r3(=-8); */ + "mov %sp, %r3\n" - "bl main\n" // main() returns the status code, we'll exit with it. - "movs r7, $1\n" // NR_exit == 1 + "bl main\n" /* main() returns the status code, we'll exit with it. */ + "movs r7, $1\n" /* NR_exit == 1 */ "svc $0x00\n" - ".align 2\n" // below are the pointers to a few variables + ".align 2\n" /* below are the pointers to a few variables */ "1:\n" ".word environ\n" "2:\n" @@ -239,4 +267,4 @@ void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) _start(void) __builtin_unreachable(); } -#endif // _NOLIBC_ARCH_ARM_H +#endif /* _NOLIBC_ARCH_ARM_H */ diff --git a/tools/include/nolibc/arch-i386.h b/tools/include/nolibc/arch-i386.h index 2d98d78fd3f3..3d672d925e9e 100644 --- a/tools/include/nolibc/arch-i386.h +++ b/tools/include/nolibc/arch-i386.h @@ -7,6 +7,8 @@ #ifndef _NOLIBC_ARCH_I386_H #define _NOLIBC_ARCH_I386_H +#include "compiler.h" + /* The struct returned by the stat() syscall, 32-bit only, the syscall returns * exactly 56 bytes (stops before the unused array). */ @@ -181,8 +183,6 @@ struct sys_stat_struct { char **environ __attribute__((weak)); const unsigned long *_auxv __attribute__((weak)); -#define __ARCH_SUPPORTS_STACK_PROTECTOR - /* startup code */ /* * i386 System V ABI mandates: @@ -190,35 +190,35 @@ const unsigned long *_auxv __attribute__((weak)); * 2) The deepest stack frame should be set to zero * */ -void __attribute__((weak,noreturn,optimize("omit-frame-pointer"),no_stack_protector)) _start(void) +void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) __no_stack_protector _start(void) { __asm__ volatile ( -#ifdef NOLIBC_STACKPROTECTOR - "call __stack_chk_init\n" // initialize stack protector +#ifdef _NOLIBC_STACKPROTECTOR + "call __stack_chk_init\n" /* initialize stack protector */ #endif - "pop %eax\n" // argc (first arg, %eax) - "mov %esp, %ebx\n" // argv[] (second arg, %ebx) - "lea 4(%ebx,%eax,4),%ecx\n" // then a NULL then envp (third arg, %ecx) - "mov %ecx, environ\n" // save environ - "xor %ebp, %ebp\n" // zero the stack frame - "mov %ecx, %edx\n" // search for auxv (follows NULL after last env) + "pop %eax\n" /* argc (first arg, %eax) */ + "mov %esp, %ebx\n" /* argv[] (second arg, %ebx) */ + "lea 4(%ebx,%eax,4),%ecx\n" /* then a NULL then envp (third arg, %ecx) */ + "mov %ecx, environ\n" /* save environ */ + "xor %ebp, %ebp\n" /* zero the stack frame */ + "mov %ecx, %edx\n" /* search for auxv (follows NULL after last env) */ "0:\n" - "add $4, %edx\n" // search for auxv using edx, it follows the - "cmp -4(%edx), %ebp\n" // ... NULL after last env (ebp is zero here) + "add $4, %edx\n" /* search for auxv using edx, it follows the */ + "cmp -4(%edx), %ebp\n" /* ... NULL after last env (ebp is zero here) */ "jnz 0b\n" - "mov %edx, _auxv\n" // save it into _auxv - "and $-16, %esp\n" // x86 ABI : esp must be 16-byte aligned before - "sub $4, %esp\n" // the call instruction (args are aligned) - "push %ecx\n" // push all registers on the stack so that we - "push %ebx\n" // support both regparm and plain stack modes + "mov %edx, _auxv\n" /* save it into _auxv */ + "and $-16, %esp\n" /* x86 ABI : esp must be 16-byte aligned before */ + "sub $4, %esp\n" /* the call instruction (args are aligned) */ + "push %ecx\n" /* push all registers on the stack so that we */ + "push %ebx\n" /* support both regparm and plain stack modes */ "push %eax\n" - "call main\n" // main() returns the status code in %eax - "mov %eax, %ebx\n" // retrieve exit code (32-bit int) - "movl $1, %eax\n" // NR_exit == 1 - "int $0x80\n" // exit now - "hlt\n" // ensure it does not + "call main\n" /* main() returns the status code in %eax */ + "mov %eax, %ebx\n" /* retrieve exit code (32-bit int) */ + "movl $1, %eax\n" /* NR_exit == 1 */ + "int $0x80\n" /* exit now */ + "hlt\n" /* ensure it does not */ ); __builtin_unreachable(); } -#endif // _NOLIBC_ARCH_I386_H +#endif /* _NOLIBC_ARCH_I386_H */ diff --git a/tools/include/nolibc/arch-loongarch.h b/tools/include/nolibc/arch-loongarch.h index 029ee3cd6baf..ad3f266e7093 100644 --- a/tools/include/nolibc/arch-loongarch.h +++ b/tools/include/nolibc/arch-loongarch.h @@ -7,6 +7,8 @@ #ifndef _NOLIBC_ARCH_LOONGARCH_H #define _NOLIBC_ARCH_LOONGARCH_H +#include "compiler.h" + /* Syscalls for LoongArch : * - stack is 16-byte aligned * - syscall number is passed in a7 @@ -158,7 +160,7 @@ const unsigned long *_auxv __attribute__((weak)); #define LONG_ADDI "addi.w" #define LONG_SLL "slli.w" #define LONG_BSTRINS "bstrins.w" -#else // __loongarch_grlen == 64 +#else /* __loongarch_grlen == 64 */ #define LONGLOG "3" #define SZREG "8" #define REG_L "ld.d" @@ -170,31 +172,34 @@ const unsigned long *_auxv __attribute__((weak)); #endif /* startup code */ -void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) _start(void) +void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) __no_stack_protector _start(void) { __asm__ volatile ( - REG_L " $a0, $sp, 0\n" // argc (a0) was in the stack - LONG_ADDI " $a1, $sp, "SZREG"\n" // argv (a1) = sp + SZREG - LONG_SLL " $a2, $a0, "LONGLOG"\n" // envp (a2) = SZREG*argc ... - LONG_ADDI " $a2, $a2, "SZREG"\n" // + SZREG (skip null) - LONG_ADD " $a2, $a2, $a1\n" // + argv - - "move $a3, $a2\n" // iterate a3 over envp to find auxv (after NULL) - "0:\n" // do { - REG_L " $a4, $a3, 0\n" // a4 = *a3; - LONG_ADDI " $a3, $a3, "SZREG"\n" // a3 += sizeof(void*); - "bne $a4, $zero, 0b\n" // } while (a4); - "la.pcrel $a4, _auxv\n" // a4 = &_auxv - LONG_S " $a3, $a4, 0\n" // store a3 into _auxv - - "la.pcrel $a3, environ\n" // a3 = &environ - LONG_S " $a2, $a3, 0\n" // store envp(a2) into environ - LONG_BSTRINS " $sp, $zero, 3, 0\n" // sp must be 16-byte aligned - "bl main\n" // main() returns the status code, we'll exit with it. - "li.w $a7, 93\n" // NR_exit == 93 +#ifdef _NOLIBC_STACKPROTECTOR + "bl __stack_chk_init\n" /* initialize stack protector */ +#endif + REG_L " $a0, $sp, 0\n" /* argc (a0) was in the stack */ + LONG_ADDI " $a1, $sp, "SZREG"\n" /* argv (a1) = sp + SZREG */ + LONG_SLL " $a2, $a0, "LONGLOG"\n" /* envp (a2) = SZREG*argc ... */ + LONG_ADDI " $a2, $a2, "SZREG"\n" /* + SZREG (skip null) */ + LONG_ADD " $a2, $a2, $a1\n" /* + argv */ + + "move $a3, $a2\n" /* iterate a3 over envp to find auxv (after NULL) */ + "0:\n" /* do { */ + REG_L " $a4, $a3, 0\n" /* a4 = *a3; */ + LONG_ADDI " $a3, $a3, "SZREG"\n" /* a3 += sizeof(void*); */ + "bne $a4, $zero, 0b\n" /* } while (a4); */ + "la.pcrel $a4, _auxv\n" /* a4 = &_auxv */ + LONG_S " $a3, $a4, 0\n" /* store a3 into _auxv */ + + "la.pcrel $a3, environ\n" /* a3 = &environ */ + LONG_S " $a2, $a3, 0\n" /* store envp(a2) into environ */ + LONG_BSTRINS " $sp, $zero, 3, 0\n" /* sp must be 16-byte aligned */ + "bl main\n" /* main() returns the status code, we'll exit with it. */ + "li.w $a7, 93\n" /* NR_exit == 93 */ "syscall 0\n" ); __builtin_unreachable(); } -#endif // _NOLIBC_ARCH_LOONGARCH_H +#endif /* _NOLIBC_ARCH_LOONGARCH_H */ diff --git a/tools/include/nolibc/arch-mips.h b/tools/include/nolibc/arch-mips.h index bf83432d23ed..db24e0837a39 100644 --- a/tools/include/nolibc/arch-mips.h +++ b/tools/include/nolibc/arch-mips.h @@ -7,6 +7,8 @@ #ifndef _NOLIBC_ARCH_MIPS_H #define _NOLIBC_ARCH_MIPS_H +#include "compiler.h" + /* The struct returned by the stat() syscall. 88 bytes are returned by the * syscall. */ @@ -180,45 +182,49 @@ char **environ __attribute__((weak)); const unsigned long *_auxv __attribute__((weak)); /* startup code, note that it's called __start on MIPS */ -void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) __start(void) +void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) __no_stack_protector __start(void) { __asm__ volatile ( - //".set nomips16\n" + /*".set nomips16\n"*/ ".set push\n" ".set noreorder\n" ".option pic0\n" - //".ent __start\n" - //"__start:\n" - "lw $a0,($sp)\n" // argc was in the stack - "addiu $a1, $sp, 4\n" // argv = sp + 4 - "sll $a2, $a0, 2\n" // a2 = argc * 4 - "add $a2, $a2, $a1\n" // envp = argv + 4*argc ... - "addiu $a2, $a2, 4\n" // ... + 4 - "lui $a3, %hi(environ)\n" // load environ into a3 (hi) - "addiu $a3, %lo(environ)\n" // load environ into a3 (lo) - "sw $a2,($a3)\n" // store envp(a2) into environ - - "move $t0, $a2\n" // iterate t0 over envp, look for NULL - "0:" // do { - "lw $a3, ($t0)\n" // a3=*(t0); - "bne $a3, $0, 0b\n" // } while (a3); - "addiu $t0, $t0, 4\n" // delayed slot: t0+=4; - "lui $a3, %hi(_auxv)\n" // load _auxv into a3 (hi) - "addiu $a3, %lo(_auxv)\n" // load _auxv into a3 (lo) - "sw $t0, ($a3)\n" // store t0 into _auxv +#ifdef _NOLIBC_STACKPROTECTOR + "jal __stack_chk_init\n" /* initialize stack protector */ + "nop\n" /* delayed slot */ +#endif + /*".ent __start\n"*/ + /*"__start:\n"*/ + "lw $a0,($sp)\n" /* argc was in the stack */ + "addiu $a1, $sp, 4\n" /* argv = sp + 4 */ + "sll $a2, $a0, 2\n" /* a2 = argc * 4 */ + "add $a2, $a2, $a1\n" /* envp = argv + 4*argc ... */ + "addiu $a2, $a2, 4\n" /* ... + 4 */ + "lui $a3, %hi(environ)\n" /* load environ into a3 (hi) */ + "addiu $a3, %lo(environ)\n" /* load environ into a3 (lo) */ + "sw $a2,($a3)\n" /* store envp(a2) into environ */ + + "move $t0, $a2\n" /* iterate t0 over envp, look for NULL */ + "0:" /* do { */ + "lw $a3, ($t0)\n" /* a3=*(t0); */ + "bne $a3, $0, 0b\n" /* } while (a3); */ + "addiu $t0, $t0, 4\n" /* delayed slot: t0+=4; */ + "lui $a3, %hi(_auxv)\n" /* load _auxv into a3 (hi) */ + "addiu $a3, %lo(_auxv)\n" /* load _auxv into a3 (lo) */ + "sw $t0, ($a3)\n" /* store t0 into _auxv */ "li $t0, -8\n" - "and $sp, $sp, $t0\n" // sp must be 8-byte aligned - "addiu $sp,$sp,-16\n" // the callee expects to save a0..a3 there! - "jal main\n" // main() returns the status code, we'll exit with it. - "nop\n" // delayed slot - "move $a0, $v0\n" // retrieve 32-bit exit code from v0 - "li $v0, 4001\n" // NR_exit == 4001 + "and $sp, $sp, $t0\n" /* sp must be 8-byte aligned */ + "addiu $sp,$sp,-16\n" /* the callee expects to save a0..a3 there! */ + "jal main\n" /* main() returns the status code, we'll exit with it. */ + "nop\n" /* delayed slot */ + "move $a0, $v0\n" /* retrieve 32-bit exit code from v0 */ + "li $v0, 4001\n" /* NR_exit == 4001 */ "syscall\n" - //".end __start\n" + /*".end __start\n"*/ ".set pop\n" ); __builtin_unreachable(); } -#endif // _NOLIBC_ARCH_MIPS_H +#endif /* _NOLIBC_ARCH_MIPS_H */ diff --git a/tools/include/nolibc/arch-riscv.h b/tools/include/nolibc/arch-riscv.h index e197fcb10ac0..a2e8564e66d6 100644 --- a/tools/include/nolibc/arch-riscv.h +++ b/tools/include/nolibc/arch-riscv.h @@ -7,6 +7,8 @@ #ifndef _NOLIBC_ARCH_RISCV_H #define _NOLIBC_ARCH_RISCV_H +#include "compiler.h" + struct sys_stat_struct { unsigned long st_dev; /* Device. */ unsigned long st_ino; /* File serial number. */ @@ -33,9 +35,13 @@ struct sys_stat_struct { #if __riscv_xlen == 64 #define PTRLOG "3" #define SZREG "8" +#define REG_L "ld" +#define REG_S "sd" #elif __riscv_xlen == 32 #define PTRLOG "2" #define SZREG "4" +#define REG_L "lw" +#define REG_S "sw" #endif /* Syscalls for RISCV : @@ -174,35 +180,38 @@ char **environ __attribute__((weak)); const unsigned long *_auxv __attribute__((weak)); /* startup code */ -void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) _start(void) +void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) __no_stack_protector _start(void) { __asm__ volatile ( ".option push\n" ".option norelax\n" "lla gp, __global_pointer$\n" ".option pop\n" - "lw a0, 0(sp)\n" // argc (a0) was in the stack - "add a1, sp, "SZREG"\n" // argv (a1) = sp - "slli a2, a0, "PTRLOG"\n" // envp (a2) = SZREG*argc ... - "add a2, a2, "SZREG"\n" // + SZREG (skip null) - "add a2,a2,a1\n" // + argv - - "add a3, a2, zero\n" // iterate a3 over envp to find auxv (after NULL) - "0:\n" // do { - "ld a4, 0(a3)\n" // a4 = *a3; - "add a3, a3, "SZREG"\n" // a3 += sizeof(void*); - "bne a4, zero, 0b\n" // } while (a4); - "lui a4, %hi(_auxv)\n" // a4 = &_auxv (high bits) - "sd a3, %lo(_auxv)(a4)\n" // store a3 into _auxv - - "lui a3, %hi(environ)\n" // a3 = &environ (high bits) - "sd a2,%lo(environ)(a3)\n" // store envp(a2) into environ - "andi sp,a1,-16\n" // sp must be 16-byte aligned - "call main\n" // main() returns the status code, we'll exit with it. - "li a7, 93\n" // NR_exit == 93 +#ifdef _NOLIBC_STACKPROTECTOR + "call __stack_chk_init\n" /* initialize stack protector */ +#endif + REG_L" a0, 0(sp)\n" /* argc (a0) was in the stack */ + "add a1, sp, "SZREG"\n" /* argv (a1) = sp */ + "slli a2, a0, "PTRLOG"\n" /* envp (a2) = SZREG*argc ... */ + "add a2, a2, "SZREG"\n" /* + SZREG (skip null) */ + "add a2,a2,a1\n" /* + argv */ + + "add a3, a2, zero\n" /* iterate a3 over envp to find auxv (after NULL) */ + "0:\n" /* do { */ + REG_L" a4, 0(a3)\n" /* a4 = *a3; */ + "add a3, a3, "SZREG"\n" /* a3 += sizeof(void*); */ + "bne a4, zero, 0b\n" /* } while (a4); */ + "lui a4, %hi(_auxv)\n" /* a4 = &_auxv (high bits) */ + REG_S" a3, %lo(_auxv)(a4)\n" /* store a3 into _auxv */ + + "lui a3, %hi(environ)\n" /* a3 = &environ (high bits) */ + REG_S" a2,%lo(environ)(a3)\n"/* store envp(a2) into environ */ + "andi sp,a1,-16\n" /* sp must be 16-byte aligned */ + "call main\n" /* main() returns the status code, we'll exit with it. */ + "li a7, 93\n" /* NR_exit == 93 */ "ecall\n" ); __builtin_unreachable(); } -#endif // _NOLIBC_ARCH_RISCV_H +#endif /* _NOLIBC_ARCH_RISCV_H */ diff --git a/tools/include/nolibc/arch-s390.h b/tools/include/nolibc/arch-s390.h index 6b0e54ed543d..516dff5bff8b 100644 --- a/tools/include/nolibc/arch-s390.h +++ b/tools/include/nolibc/arch-s390.h @@ -5,8 +5,11 @@ #ifndef _NOLIBC_ARCH_S390_H #define _NOLIBC_ARCH_S390_H +#include <asm/signal.h> #include <asm/unistd.h> +#include "compiler.h" + /* The struct returned by the stat() syscall, equivalent to stat64(). The * syscall returns 116 bytes and stops in the middle of __unused. */ @@ -163,7 +166,7 @@ char **environ __attribute__((weak)); const unsigned long *_auxv __attribute__((weak)); /* startup code */ -void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) _start(void) +void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) __no_stack_protector _start(void) { __asm__ volatile ( "lg %r2,0(%r15)\n" /* argument count */ @@ -223,4 +226,12 @@ void *sys_mmap(void *addr, size_t length, int prot, int flags, int fd, return (void *)my_syscall1(__NR_mmap, &args); } #define sys_mmap sys_mmap -#endif // _NOLIBC_ARCH_S390_H + +static __attribute__((unused)) +pid_t sys_fork(void) +{ + return my_syscall5(__NR_clone, 0, SIGCHLD, 0, 0, 0); +} +#define sys_fork sys_fork + +#endif /* _NOLIBC_ARCH_S390_H */ diff --git a/tools/include/nolibc/arch-x86_64.h b/tools/include/nolibc/arch-x86_64.h index f7f2a11d4c3b..6fc4d8392742 100644 --- a/tools/include/nolibc/arch-x86_64.h +++ b/tools/include/nolibc/arch-x86_64.h @@ -7,6 +7,8 @@ #ifndef _NOLIBC_ARCH_X86_64_H #define _NOLIBC_ARCH_X86_64_H +#include "compiler.h" + /* The struct returned by the stat() syscall, equivalent to stat64(). The * syscall returns 116 bytes and stops in the middle of __unused. */ @@ -181,8 +183,6 @@ struct sys_stat_struct { char **environ __attribute__((weak)); const unsigned long *_auxv __attribute__((weak)); -#define __ARCH_SUPPORTS_STACK_PROTECTOR - /* startup code */ /* * x86-64 System V ABI mandates: @@ -190,31 +190,31 @@ const unsigned long *_auxv __attribute__((weak)); * 2) The deepest stack frame should be zero (the %rbp). * */ -void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) _start(void) +void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) __no_stack_protector _start(void) { __asm__ volatile ( -#ifdef NOLIBC_STACKPROTECTOR - "call __stack_chk_init\n" // initialize stack protector +#ifdef _NOLIBC_STACKPROTECTOR + "call __stack_chk_init\n" /* initialize stack protector */ #endif - "pop %rdi\n" // argc (first arg, %rdi) - "mov %rsp, %rsi\n" // argv[] (second arg, %rsi) - "lea 8(%rsi,%rdi,8),%rdx\n" // then a NULL then envp (third arg, %rdx) - "mov %rdx, environ\n" // save environ - "xor %ebp, %ebp\n" // zero the stack frame - "mov %rdx, %rax\n" // search for auxv (follows NULL after last env) + "pop %rdi\n" /* argc (first arg, %rdi) */ + "mov %rsp, %rsi\n" /* argv[] (second arg, %rsi) */ + "lea 8(%rsi,%rdi,8),%rdx\n" /* then a NULL then envp (third arg, %rdx) */ + "mov %rdx, environ\n" /* save environ */ + "xor %ebp, %ebp\n" /* zero the stack frame */ + "mov %rdx, %rax\n" /* search for auxv (follows NULL after last env) */ "0:\n" - "add $8, %rax\n" // search for auxv using rax, it follows the - "cmp -8(%rax), %rbp\n" // ... NULL after last env (rbp is zero here) + "add $8, %rax\n" /* search for auxv using rax, it follows the */ + "cmp -8(%rax), %rbp\n" /* ... NULL after last env (rbp is zero here) */ "jnz 0b\n" - "mov %rax, _auxv\n" // save it into _auxv - "and $-16, %rsp\n" // x86 ABI : esp must be 16-byte aligned before call - "call main\n" // main() returns the status code, we'll exit with it. - "mov %eax, %edi\n" // retrieve exit code (32 bit) - "mov $60, %eax\n" // NR_exit == 60 - "syscall\n" // really exit - "hlt\n" // ensure it does not return + "mov %rax, _auxv\n" /* save it into _auxv */ + "and $-16, %rsp\n" /* x86 ABI : esp must be 16-byte aligned before call */ + "call main\n" /* main() returns the status code, we'll exit with it. */ + "mov %eax, %edi\n" /* retrieve exit code (32 bit) */ + "mov $60, %eax\n" /* NR_exit == 60 */ + "syscall\n" /* really exit */ + "hlt\n" /* ensure it does not return */ ); __builtin_unreachable(); } -#endif // _NOLIBC_ARCH_X86_64_H +#endif /* _NOLIBC_ARCH_X86_64_H */ diff --git a/tools/include/nolibc/arch.h b/tools/include/nolibc/arch.h index 2d5386a8d6aa..82b43935650f 100644 --- a/tools/include/nolibc/arch.h +++ b/tools/include/nolibc/arch.h @@ -7,7 +7,7 @@ * the syscall declarations and the _start code definition. This is the only * global part. On all architectures the kernel puts everything in the stack * before jumping to _start just above us, without any return address (_start - * is not a function but an entry pint). So at the stack pointer we find argc. + * is not a function but an entry point). So at the stack pointer we find argc. * Then argv[] begins, and ends at the first NULL. Then we have envp which * starts and ends with a NULL as well. So envp=argv+argc+1. */ diff --git a/tools/include/nolibc/compiler.h b/tools/include/nolibc/compiler.h new file mode 100644 index 000000000000..beddc3665d69 --- /dev/null +++ b/tools/include/nolibc/compiler.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * NOLIBC compiler support header + * Copyright (C) 2023 Thomas Weißschuh <linux@weissschuh.net> + */ +#ifndef _NOLIBC_COMPILER_H +#define _NOLIBC_COMPILER_H + +#if defined(__SSP__) || defined(__SSP_STRONG__) || defined(__SSP_ALL__) || defined(__SSP_EXPLICIT__) + +#define _NOLIBC_STACKPROTECTOR + +#endif /* defined(__SSP__) ... */ + +#if defined(__has_attribute) +# if __has_attribute(no_stack_protector) +# define __no_stack_protector __attribute__((no_stack_protector)) +# else +# define __no_stack_protector __attribute__((__optimize__("-fno-stack-protector"))) +# endif +#else +# define __no_stack_protector __attribute__((__optimize__("-fno-stack-protector"))) +#endif /* defined(__has_attribute) */ + +#endif /* _NOLIBC_COMPILER_H */ diff --git a/tools/include/nolibc/nolibc.h b/tools/include/nolibc/nolibc.h index 04739a6293c4..05a228a6ee78 100644 --- a/tools/include/nolibc/nolibc.h +++ b/tools/include/nolibc/nolibc.h @@ -99,11 +99,11 @@ #include "sys.h" #include "ctype.h" #include "signal.h" +#include "unistd.h" #include "stdio.h" #include "stdlib.h" #include "string.h" #include "time.h" -#include "unistd.h" #include "stackprotector.h" /* Used by programs to avoid std includes */ diff --git a/tools/include/nolibc/stackprotector.h b/tools/include/nolibc/stackprotector.h index d119cbbbc256..88f7b2d098ff 100644 --- a/tools/include/nolibc/stackprotector.h +++ b/tools/include/nolibc/stackprotector.h @@ -7,13 +7,9 @@ #ifndef _NOLIBC_STACKPROTECTOR_H #define _NOLIBC_STACKPROTECTOR_H -#include "arch.h" +#include "compiler.h" -#if defined(NOLIBC_STACKPROTECTOR) - -#if !defined(__ARCH_SUPPORTS_STACK_PROTECTOR) -#error "nolibc does not support stack protectors on this arch" -#endif +#if defined(_NOLIBC_STACKPROTECTOR) #include "sys.h" #include "stdlib.h" @@ -41,13 +37,14 @@ void __stack_chk_fail_local(void) __attribute__((weak,section(".data.nolibc_stack_chk"))) uintptr_t __stack_chk_guard; -__attribute__((weak,no_stack_protector,section(".text.nolibc_stack_chk"))) +__attribute__((weak,section(".text.nolibc_stack_chk"))) __no_stack_protector void __stack_chk_init(void) { my_syscall3(__NR_getrandom, &__stack_chk_guard, sizeof(__stack_chk_guard), 0); - /* a bit more randomness in case getrandom() fails */ - __stack_chk_guard ^= (uintptr_t) &__stack_chk_guard; + /* a bit more randomness in case getrandom() fails, ensure the guard is never 0 */ + if (__stack_chk_guard != (uintptr_t) &__stack_chk_guard) + __stack_chk_guard ^= (uintptr_t) &__stack_chk_guard; } -#endif // defined(NOLIBC_STACKPROTECTOR) +#endif /* defined(_NOLIBC_STACKPROTECTOR) */ -#endif // _NOLIBC_STACKPROTECTOR_H +#endif /* _NOLIBC_STACKPROTECTOR_H */ diff --git a/tools/include/nolibc/stdint.h b/tools/include/nolibc/stdint.h index c1ce4f5e0603..4b282435a59a 100644 --- a/tools/include/nolibc/stdint.h +++ b/tools/include/nolibc/stdint.h @@ -36,8 +36,8 @@ typedef ssize_t int_fast16_t; typedef size_t uint_fast16_t; typedef ssize_t int_fast32_t; typedef size_t uint_fast32_t; -typedef ssize_t int_fast64_t; -typedef size_t uint_fast64_t; +typedef int64_t int_fast64_t; +typedef uint64_t uint_fast64_t; typedef int64_t intmax_t; typedef uint64_t uintmax_t; @@ -84,16 +84,30 @@ typedef uint64_t uintmax_t; #define INT_FAST8_MIN INT8_MIN #define INT_FAST16_MIN INTPTR_MIN #define INT_FAST32_MIN INTPTR_MIN -#define INT_FAST64_MIN INTPTR_MIN +#define INT_FAST64_MIN INT64_MIN #define INT_FAST8_MAX INT8_MAX #define INT_FAST16_MAX INTPTR_MAX #define INT_FAST32_MAX INTPTR_MAX -#define INT_FAST64_MAX INTPTR_MAX +#define INT_FAST64_MAX INT64_MAX #define UINT_FAST8_MAX UINT8_MAX #define UINT_FAST16_MAX SIZE_MAX #define UINT_FAST32_MAX SIZE_MAX -#define UINT_FAST64_MAX SIZE_MAX +#define UINT_FAST64_MAX UINT64_MAX + +#ifndef INT_MIN +#define INT_MIN (-__INT_MAX__ - 1) +#endif +#ifndef INT_MAX +#define INT_MAX __INT_MAX__ +#endif + +#ifndef LONG_MIN +#define LONG_MIN (-__LONG_MAX__ - 1) +#endif +#ifndef LONG_MAX +#define LONG_MAX __LONG_MAX__ +#endif #endif /* _NOLIBC_STDINT_H */ diff --git a/tools/include/nolibc/stdio.h b/tools/include/nolibc/stdio.h index 6cbbb52836a0..0eef91daf289 100644 --- a/tools/include/nolibc/stdio.h +++ b/tools/include/nolibc/stdio.h @@ -21,17 +21,75 @@ #define EOF (-1) #endif -/* just define FILE as a non-empty type */ +/* just define FILE as a non-empty type. The value of the pointer gives + * the FD: FILE=~fd for fd>=0 or NULL for fd<0. This way positive FILE + * are immediately identified as abnormal entries (i.e. possible copies + * of valid pointers to something else). + */ typedef struct FILE { char dummy[1]; } FILE; -/* We define the 3 common stdio files as constant invalid pointers that - * are easily recognized. - */ -static __attribute__((unused)) FILE* const stdin = (FILE*)-3; -static __attribute__((unused)) FILE* const stdout = (FILE*)-2; -static __attribute__((unused)) FILE* const stderr = (FILE*)-1; +static __attribute__((unused)) FILE* const stdin = (FILE*)(intptr_t)~STDIN_FILENO; +static __attribute__((unused)) FILE* const stdout = (FILE*)(intptr_t)~STDOUT_FILENO; +static __attribute__((unused)) FILE* const stderr = (FILE*)(intptr_t)~STDERR_FILENO; + +/* provides a FILE* equivalent of fd. The mode is ignored. */ +static __attribute__((unused)) +FILE *fdopen(int fd, const char *mode __attribute__((unused))) +{ + if (fd < 0) { + SET_ERRNO(EBADF); + return NULL; + } + return (FILE*)(intptr_t)~fd; +} + +/* provides the fd of stream. */ +static __attribute__((unused)) +int fileno(FILE *stream) +{ + intptr_t i = (intptr_t)stream; + + if (i >= 0) { + SET_ERRNO(EBADF); + return -1; + } + return ~i; +} + +/* flush a stream. */ +static __attribute__((unused)) +int fflush(FILE *stream) +{ + intptr_t i = (intptr_t)stream; + + /* NULL is valid here. */ + if (i > 0) { + SET_ERRNO(EBADF); + return -1; + } + + /* Don't do anything, nolibc does not support buffering. */ + return 0; +} + +/* flush a stream. */ +static __attribute__((unused)) +int fclose(FILE *stream) +{ + intptr_t i = (intptr_t)stream; + + if (i >= 0) { + SET_ERRNO(EBADF); + return -1; + } + + if (close(~i)) + return EOF; + + return 0; +} /* getc(), fgetc(), getchar() */ @@ -41,14 +99,8 @@ static __attribute__((unused)) int fgetc(FILE* stream) { unsigned char ch; - int fd; - if (stream < stdin || stream > stderr) - return EOF; - - fd = 3 + (long)stream; - - if (read(fd, &ch, 1) <= 0) + if (read(fileno(stream), &ch, 1) <= 0) return EOF; return ch; } @@ -68,14 +120,8 @@ static __attribute__((unused)) int fputc(int c, FILE* stream) { unsigned char ch = c; - int fd; - - if (stream < stdin || stream > stderr) - return EOF; - - fd = 3 + (long)stream; - if (write(fd, &ch, 1) <= 0) + if (write(fileno(stream), &ch, 1) <= 0) return EOF; return ch; } @@ -96,12 +142,7 @@ static __attribute__((unused)) int _fwrite(const void *buf, size_t size, FILE *stream) { ssize_t ret; - int fd; - - if (stream < stdin || stream > stderr) - return EOF; - - fd = 3 + (long)stream; + int fd = fileno(stream); while (size) { ret = write(fd, buf, size); diff --git a/tools/include/nolibc/stdlib.h b/tools/include/nolibc/stdlib.h index 894c955d027e..902162f80337 100644 --- a/tools/include/nolibc/stdlib.h +++ b/tools/include/nolibc/stdlib.h @@ -102,7 +102,7 @@ char *_getenv(const char *name, char **environ) return NULL; } -static inline __attribute__((unused,always_inline)) +static __inline__ __attribute__((unused,always_inline)) char *getenv(const char *name) { extern char **environ; @@ -231,7 +231,7 @@ int utoh_r(unsigned long in, char *buffer) /* converts unsigned long <in> to an hex string using the static itoa_buffer * and returns the pointer to that string. */ -static inline __attribute__((unused)) +static __inline__ __attribute__((unused)) char *utoh(unsigned long in) { utoh_r(in, itoa_buffer); @@ -293,7 +293,7 @@ int itoa_r(long in, char *buffer) /* for historical compatibility, same as above but returns the pointer to the * buffer. */ -static inline __attribute__((unused)) +static __inline__ __attribute__((unused)) char *ltoa_r(long in, char *buffer) { itoa_r(in, buffer); @@ -303,7 +303,7 @@ char *ltoa_r(long in, char *buffer) /* converts long integer <in> to a string using the static itoa_buffer and * returns the pointer to that string. */ -static inline __attribute__((unused)) +static __inline__ __attribute__((unused)) char *itoa(long in) { itoa_r(in, itoa_buffer); @@ -313,7 +313,7 @@ char *itoa(long in) /* converts long integer <in> to a string using the static itoa_buffer and * returns the pointer to that string. Same as above, for compatibility. */ -static inline __attribute__((unused)) +static __inline__ __attribute__((unused)) char *ltoa(long in) { itoa_r(in, itoa_buffer); @@ -323,7 +323,7 @@ char *ltoa(long in) /* converts unsigned long integer <in> to a string using the static itoa_buffer * and returns the pointer to that string. */ -static inline __attribute__((unused)) +static __inline__ __attribute__((unused)) char *utoa(unsigned long in) { utoa_r(in, itoa_buffer); @@ -367,7 +367,7 @@ int u64toh_r(uint64_t in, char *buffer) /* converts uint64_t <in> to an hex string using the static itoa_buffer and * returns the pointer to that string. */ -static inline __attribute__((unused)) +static __inline__ __attribute__((unused)) char *u64toh(uint64_t in) { u64toh_r(in, itoa_buffer); @@ -429,7 +429,7 @@ int i64toa_r(int64_t in, char *buffer) /* converts int64_t <in> to a string using the static itoa_buffer and returns * the pointer to that string. */ -static inline __attribute__((unused)) +static __inline__ __attribute__((unused)) char *i64toa(int64_t in) { i64toa_r(in, itoa_buffer); @@ -439,7 +439,7 @@ char *i64toa(int64_t in) /* converts uint64_t <in> to a string using the static itoa_buffer and returns * the pointer to that string. */ -static inline __attribute__((unused)) +static __inline__ __attribute__((unused)) char *u64toa(uint64_t in) { u64toa_r(in, itoa_buffer); diff --git a/tools/include/nolibc/string.h b/tools/include/nolibc/string.h index fffdaf6ff467..0c2e06c7c477 100644 --- a/tools/include/nolibc/string.h +++ b/tools/include/nolibc/string.h @@ -90,7 +90,7 @@ void *memset(void *dst, int b, size_t len) while (len--) { /* prevent gcc from recognizing memset() here */ - asm volatile(""); + __asm__ volatile(""); *(p++) = b; } return dst; @@ -139,7 +139,7 @@ size_t strlen(const char *str) size_t len; for (len = 0; str[len]; len++) - asm(""); + __asm__(""); return len; } diff --git a/tools/include/nolibc/sys.h b/tools/include/nolibc/sys.h index 5d624dc63a42..856249a11890 100644 --- a/tools/include/nolibc/sys.h +++ b/tools/include/nolibc/sys.h @@ -12,15 +12,17 @@ /* system includes */ #include <asm/unistd.h> -#include <asm/signal.h> // for SIGCHLD +#include <asm/signal.h> /* for SIGCHLD */ #include <asm/ioctls.h> #include <asm/mman.h> #include <linux/fs.h> #include <linux/loop.h> #include <linux/time.h> #include <linux/auxvec.h> -#include <linux/fcntl.h> // for O_* and AT_* -#include <linux/stat.h> // for statx() +#include <linux/fcntl.h> /* for O_* and AT_* */ +#include <linux/stat.h> /* for statx() */ +#include <linux/reboot.h> /* for LINUX_REBOOT_* */ +#include <linux/prctl.h> #include "arch.h" #include "errno.h" @@ -322,7 +324,7 @@ static __attribute__((noreturn,unused)) void sys_exit(int status) { my_syscall1(__NR_exit, status & 255); - while(1); // shut the "noreturn" warnings. + while(1); /* shut the "noreturn" warnings. */ } static __attribute__((noreturn,unused)) @@ -336,6 +338,7 @@ void exit(int status) * pid_t fork(void); */ +#ifndef sys_fork static __attribute__((unused)) pid_t sys_fork(void) { @@ -351,6 +354,7 @@ pid_t sys_fork(void) #error Neither __NR_clone nor __NR_fork defined, cannot implement sys_fork() #endif } +#endif static __attribute__((unused)) pid_t fork(void) @@ -858,7 +862,7 @@ int open(const char *path, int flags, ...) va_list args; va_start(args, flags); - mode = va_arg(args, mode_t); + mode = va_arg(args, int); va_end(args); } @@ -873,6 +877,32 @@ int open(const char *path, int flags, ...) /* + * int prctl(int option, unsigned long arg2, unsigned long arg3, + * unsigned long arg4, unsigned long arg5); + */ + +static __attribute__((unused)) +int sys_prctl(int option, unsigned long arg2, unsigned long arg3, + unsigned long arg4, unsigned long arg5) +{ + return my_syscall5(__NR_prctl, option, arg2, arg3, arg4, arg5); +} + +static __attribute__((unused)) +int prctl(int option, unsigned long arg2, unsigned long arg3, + unsigned long arg4, unsigned long arg5) +{ + int ret = sys_prctl(option, arg2, arg3, arg4, arg5); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + + +/* * int pivot_root(const char *new, const char *old); */ @@ -909,7 +939,7 @@ int sys_poll(struct pollfd *fds, int nfds, int timeout) t.tv_sec = timeout / 1000; t.tv_nsec = (timeout % 1000) * 1000000; } - return my_syscall4(__NR_ppoll, fds, nfds, (timeout >= 0) ? &t : NULL, NULL); + return my_syscall5(__NR_ppoll, fds, nfds, (timeout >= 0) ? &t : NULL, NULL, 0); #elif defined(__NR_poll) return my_syscall3(__NR_poll, fds, nfds, timeout); #else @@ -1131,23 +1161,26 @@ int sys_stat(const char *path, struct stat *buf) long ret; ret = sys_statx(AT_FDCWD, path, AT_NO_AUTOMOUNT, STATX_BASIC_STATS, &statx); - buf->st_dev = ((statx.stx_dev_minor & 0xff) - | (statx.stx_dev_major << 8) - | ((statx.stx_dev_minor & ~0xff) << 12)); - buf->st_ino = statx.stx_ino; - buf->st_mode = statx.stx_mode; - buf->st_nlink = statx.stx_nlink; - buf->st_uid = statx.stx_uid; - buf->st_gid = statx.stx_gid; - buf->st_rdev = ((statx.stx_rdev_minor & 0xff) - | (statx.stx_rdev_major << 8) - | ((statx.stx_rdev_minor & ~0xff) << 12)); - buf->st_size = statx.stx_size; - buf->st_blksize = statx.stx_blksize; - buf->st_blocks = statx.stx_blocks; - buf->st_atime = statx.stx_atime.tv_sec; - buf->st_mtime = statx.stx_mtime.tv_sec; - buf->st_ctime = statx.stx_ctime.tv_sec; + buf->st_dev = ((statx.stx_dev_minor & 0xff) + | (statx.stx_dev_major << 8) + | ((statx.stx_dev_minor & ~0xff) << 12)); + buf->st_ino = statx.stx_ino; + buf->st_mode = statx.stx_mode; + buf->st_nlink = statx.stx_nlink; + buf->st_uid = statx.stx_uid; + buf->st_gid = statx.stx_gid; + buf->st_rdev = ((statx.stx_rdev_minor & 0xff) + | (statx.stx_rdev_major << 8) + | ((statx.stx_rdev_minor & ~0xff) << 12)); + buf->st_size = statx.stx_size; + buf->st_blksize = statx.stx_blksize; + buf->st_blocks = statx.stx_blocks; + buf->st_atim.tv_sec = statx.stx_atime.tv_sec; + buf->st_atim.tv_nsec = statx.stx_atime.tv_nsec; + buf->st_mtim.tv_sec = statx.stx_mtime.tv_sec; + buf->st_mtim.tv_nsec = statx.stx_mtime.tv_nsec; + buf->st_ctim.tv_sec = statx.stx_ctime.tv_sec; + buf->st_ctim.tv_nsec = statx.stx_ctime.tv_nsec; return ret; } #else @@ -1165,19 +1198,22 @@ int sys_stat(const char *path, struct stat *buf) #else #error Neither __NR_newfstatat nor __NR_stat defined, cannot implement sys_stat() #endif - buf->st_dev = stat.st_dev; - buf->st_ino = stat.st_ino; - buf->st_mode = stat.st_mode; - buf->st_nlink = stat.st_nlink; - buf->st_uid = stat.st_uid; - buf->st_gid = stat.st_gid; - buf->st_rdev = stat.st_rdev; - buf->st_size = stat.st_size; - buf->st_blksize = stat.st_blksize; - buf->st_blocks = stat.st_blocks; - buf->st_atime = stat.st_atime; - buf->st_mtime = stat.st_mtime; - buf->st_ctime = stat.st_ctime; + buf->st_dev = stat.st_dev; + buf->st_ino = stat.st_ino; + buf->st_mode = stat.st_mode; + buf->st_nlink = stat.st_nlink; + buf->st_uid = stat.st_uid; + buf->st_gid = stat.st_gid; + buf->st_rdev = stat.st_rdev; + buf->st_size = stat.st_size; + buf->st_blksize = stat.st_blksize; + buf->st_blocks = stat.st_blocks; + buf->st_atim.tv_sec = stat.st_atime; + buf->st_atim.tv_nsec = stat.st_atime_nsec; + buf->st_mtim.tv_sec = stat.st_mtime; + buf->st_mtim.tv_nsec = stat.st_mtime_nsec; + buf->st_ctim.tv_sec = stat.st_ctime; + buf->st_ctim.tv_nsec = stat.st_ctime_nsec; return ret; } #endif @@ -1365,6 +1401,29 @@ ssize_t write(int fd, const void *buf, size_t count) return ret; } + +/* + * int memfd_create(const char *name, unsigned int flags); + */ + +static __attribute__((unused)) +int sys_memfd_create(const char *name, unsigned int flags) +{ + return my_syscall2(__NR_memfd_create, name, flags); +} + +static __attribute__((unused)) +int memfd_create(const char *name, unsigned int flags) +{ + ssize_t ret = sys_memfd_create(name, flags); + + if (ret < 0) { + SET_ERRNO(-ret); + ret = -1; + } + return ret; +} + /* make sure to include all global symbols */ #include "nolibc.h" diff --git a/tools/include/nolibc/types.h b/tools/include/nolibc/types.h index aedd7d9e3f64..f96e28bff4ba 100644 --- a/tools/include/nolibc/types.h +++ b/tools/include/nolibc/types.h @@ -86,14 +86,6 @@ #define SEEK_CUR 1 #define SEEK_END 2 -/* cmd for reboot() */ -#define LINUX_REBOOT_MAGIC1 0xfee1dead -#define LINUX_REBOOT_MAGIC2 0x28121969 -#define LINUX_REBOOT_CMD_HALT 0xcdef0123 -#define LINUX_REBOOT_CMD_POWER_OFF 0x4321fedc -#define LINUX_REBOOT_CMD_RESTART 0x01234567 -#define LINUX_REBOOT_CMD_SW_SUSPEND 0xd000fce2 - /* Macros used on waitpid()'s return status */ #define WEXITSTATUS(status) (((status) & 0xff00) >> 8) #define WIFEXITED(status) (((status) & 0x7f) == 0) @@ -206,9 +198,9 @@ struct stat { off_t st_size; /* total size, in bytes */ blksize_t st_blksize; /* blocksize for file system I/O */ blkcnt_t st_blocks; /* number of 512B blocks allocated */ - time_t st_atime; /* time of last access */ - time_t st_mtime; /* time of last modification */ - time_t st_ctime; /* time of last status change */ + union { time_t st_atime; struct timespec st_atim; }; /* time of last access */ + union { time_t st_mtime; struct timespec st_mtim; }; /* time of last modification */ + union { time_t st_ctime; struct timespec st_ctim; }; /* time of last status change */ }; /* WARNING, it only deals with the 4096 first majors and 256 first minors */ diff --git a/tools/include/nolibc/unistd.h b/tools/include/nolibc/unistd.h index ac7d53d986cd..0e832e10a0b2 100644 --- a/tools/include/nolibc/unistd.h +++ b/tools/include/nolibc/unistd.h @@ -56,6 +56,21 @@ int tcsetpgrp(int fd, pid_t pid) return ioctl(fd, TIOCSPGRP, &pid); } +#define _syscall(N, ...) \ +({ \ + long _ret = my_syscall##N(__VA_ARGS__); \ + if (_ret < 0) { \ + SET_ERRNO(-_ret); \ + _ret = -1; \ + } \ + _ret; \ +}) + +#define _syscall_narg(...) __syscall_narg(__VA_ARGS__, 6, 5, 4, 3, 2, 1, 0) +#define __syscall_narg(_0, _1, _2, _3, _4, _5, _6, N, ...) N +#define _syscall_n(N, ...) _syscall(N, __VA_ARGS__) +#define syscall(...) _syscall_n(_syscall_narg(__VA_ARGS__), ##__VA_ARGS__) + /* make sure to include all global symbols */ #include "nolibc.h" diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h index 642808520d92..a87bbbbca2d4 100644 --- a/tools/include/uapi/drm/drm.h +++ b/tools/include/uapi/drm/drm.h @@ -972,6 +972,19 @@ extern "C" { #define DRM_IOCTL_GET_STATS DRM_IOR( 0x06, struct drm_stats) #define DRM_IOCTL_SET_VERSION DRM_IOWR(0x07, struct drm_set_version) #define DRM_IOCTL_MODESET_CTL DRM_IOW(0x08, struct drm_modeset_ctl) +/** + * DRM_IOCTL_GEM_CLOSE - Close a GEM handle. + * + * GEM handles are not reference-counted by the kernel. User-space is + * responsible for managing their lifetime. For example, if user-space imports + * the same memory object twice on the same DRM file description, the same GEM + * handle is returned by both imports, and user-space needs to ensure + * &DRM_IOCTL_GEM_CLOSE is performed once only. The same situation can happen + * when a memory object is allocated, then exported and imported again on the + * same DRM file description. The &DRM_IOCTL_MODE_GETFB2 IOCTL is an exception + * and always returns fresh new GEM handles even if an existing GEM handle + * already refers to the same memory object before the IOCTL is performed. + */ #define DRM_IOCTL_GEM_CLOSE DRM_IOW (0x09, struct drm_gem_close) #define DRM_IOCTL_GEM_FLINK DRM_IOWR(0x0a, struct drm_gem_flink) #define DRM_IOCTL_GEM_OPEN DRM_IOWR(0x0b, struct drm_gem_open) @@ -1012,7 +1025,37 @@ extern "C" { #define DRM_IOCTL_UNLOCK DRM_IOW( 0x2b, struct drm_lock) #define DRM_IOCTL_FINISH DRM_IOW( 0x2c, struct drm_lock) +/** + * DRM_IOCTL_PRIME_HANDLE_TO_FD - Convert a GEM handle to a DMA-BUF FD. + * + * User-space sets &drm_prime_handle.handle with the GEM handle to export and + * &drm_prime_handle.flags, and gets back a DMA-BUF file descriptor in + * &drm_prime_handle.fd. + * + * The export can fail for any driver-specific reason, e.g. because export is + * not supported for this specific GEM handle (but might be for others). + * + * Support for exporting DMA-BUFs is advertised via &DRM_PRIME_CAP_EXPORT. + */ #define DRM_IOCTL_PRIME_HANDLE_TO_FD DRM_IOWR(0x2d, struct drm_prime_handle) +/** + * DRM_IOCTL_PRIME_FD_TO_HANDLE - Convert a DMA-BUF FD to a GEM handle. + * + * User-space sets &drm_prime_handle.fd with a DMA-BUF file descriptor to + * import, and gets back a GEM handle in &drm_prime_handle.handle. + * &drm_prime_handle.flags is unused. + * + * If an existing GEM handle refers to the memory object backing the DMA-BUF, + * that GEM handle is returned. Therefore user-space which needs to handle + * arbitrary DMA-BUFs must have a user-space lookup data structure to manually + * reference-count duplicated GEM handles. For more information see + * &DRM_IOCTL_GEM_CLOSE. + * + * The import can fail for any driver-specific reason, e.g. because import is + * only supported for DMA-BUFs allocated on this DRM device. + * + * Support for importing DMA-BUFs is advertised via &DRM_PRIME_CAP_IMPORT. + */ #define DRM_IOCTL_PRIME_FD_TO_HANDLE DRM_IOWR(0x2e, struct drm_prime_handle) #define DRM_IOCTL_AGP_ACQUIRE DRM_IO( 0x30) @@ -1104,8 +1147,13 @@ extern "C" { * struct as the output. * * If the client is DRM master or has &CAP_SYS_ADMIN, &drm_mode_fb_cmd2.handles - * will be filled with GEM buffer handles. Planes are valid until one has a - * zero handle -- this can be used to compute the number of planes. + * will be filled with GEM buffer handles. Fresh new GEM handles are always + * returned, even if another GEM handle referring to the same memory object + * already exists on the DRM file description. The caller is responsible for + * removing the new handles, e.g. via the &DRM_IOCTL_GEM_CLOSE IOCTL. The same + * new handle will be returned for multiple planes in case they use the same + * memory object. Planes are valid until one has a zero handle -- this can be + * used to compute the number of planes. * * Otherwise, &drm_mode_fb_cmd2.handles will be zeroed and planes are valid * until one has a zero &drm_mode_fb_cmd2.pitches. @@ -1113,6 +1161,11 @@ extern "C" { * If the framebuffer has a format modifier, &DRM_MODE_FB_MODIFIERS will be set * in &drm_mode_fb_cmd2.flags and &drm_mode_fb_cmd2.modifier will contain the * modifier. Otherwise, user-space must ignore &drm_mode_fb_cmd2.modifier. + * + * To obtain DMA-BUF FDs for each plane without leaking GEM handles, user-space + * can export each handle via &DRM_IOCTL_PRIME_HANDLE_TO_FD, then immediately + * close each unique handle via &DRM_IOCTL_GEM_CLOSE, making sure to not + * double-close handles which are specified multiple times in the array. */ #define DRM_IOCTL_MODE_GETFB2 DRM_IOWR(0xCE, struct drm_mode_fb_cmd2) diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index 8df261c5ab9b..dba7c5a5b25e 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -2491,7 +2491,7 @@ struct i915_context_param_engines { #define I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE 0 /* see i915_context_engines_load_balance */ #define I915_CONTEXT_ENGINES_EXT_BOND 1 /* see i915_context_engines_bond */ #define I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT 2 /* see i915_context_engines_parallel_submit */ - struct i915_engine_class_instance engines[0]; + struct i915_engine_class_instance engines[]; } __attribute__((packed)); #define I915_DEFINE_CONTEXT_PARAM_ENGINES(name__, N__) struct { \ @@ -2676,6 +2676,10 @@ enum drm_i915_oa_format { I915_OAR_FORMAT_A32u40_A4u32_B8_C8, I915_OA_FORMAT_A24u40_A14u32_B8_C8, + /* MTL OAM */ + I915_OAM_FORMAT_MPEC8u64_B8_C8, + I915_OAM_FORMAT_MPEC8u32_B8_C8, + I915_OA_FORMAT_MAX /* non-ABI */ }; @@ -2758,6 +2762,25 @@ enum drm_i915_perf_property_id { */ DRM_I915_PERF_PROP_POLL_OA_PERIOD, + /** + * Multiple engines may be mapped to the same OA unit. The OA unit is + * identified by class:instance of any engine mapped to it. + * + * This parameter specifies the engine class and must be passed along + * with DRM_I915_PERF_PROP_OA_ENGINE_INSTANCE. + * + * This property is available in perf revision 6. + */ + DRM_I915_PERF_PROP_OA_ENGINE_CLASS, + + /** + * This parameter specifies the engine instance and must be passed along + * with DRM_I915_PERF_PROP_OA_ENGINE_CLASS. + * + * This property is available in perf revision 6. + */ + DRM_I915_PERF_PROP_OA_ENGINE_INSTANCE, + DRM_I915_PERF_PROP_MAX /* non-ABI */ }; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 1bb11a6ee667..c994ff5b157c 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1035,6 +1035,7 @@ enum bpf_attach_type { BPF_TRACE_KPROBE_MULTI, BPF_LSM_CGROUP, BPF_STRUCT_OPS, + BPF_NETFILTER, __MAX_BPF_ATTACH_TYPE }; diff --git a/tools/include/uapi/linux/const.h b/tools/include/uapi/linux/const.h index af2a44c08683..a429381e7ca5 100644 --- a/tools/include/uapi/linux/const.h +++ b/tools/include/uapi/linux/const.h @@ -28,7 +28,7 @@ #define _BITUL(x) (_UL(1) << (x)) #define _BITULL(x) (_ULL(1) << (x)) -#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1) +#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (__typeof__(x))(a) - 1) #define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask)) #define __KERNEL_DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d)) diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h index 07a4cb149305..e682ab628dfa 100644 --- a/tools/include/uapi/linux/in.h +++ b/tools/include/uapi/linux/in.h @@ -162,6 +162,8 @@ struct in_addr { #define MCAST_MSFILTER 48 #define IP_MULTICAST_ALL 49 #define IP_UNICAST_IF 50 +#define IP_LOCAL_PORT_RANGE 51 +#define IP_PROTOCOL 52 #define MCAST_EXCLUDE 0 #define MCAST_INCLUDE 1 diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 4003a166328c..737318b1c1d9 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -341,8 +341,13 @@ struct kvm_run { __u64 nr; __u64 args[6]; __u64 ret; - __u32 longmode; - __u32 pad; + + union { +#ifndef __KERNEL__ + __u32 longmode; +#endif + __u64 flags; + }; } hypercall; /* KVM_EXIT_TPR_ACCESS */ struct { @@ -1184,6 +1189,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_S390_PROTECTED_ASYNC_DISABLE 224 #define KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP 225 #define KVM_CAP_PMU_EVENT_MASKED_EVENTS 226 +#define KVM_CAP_COUNTER_OFFSET 227 #ifdef KVM_CAP_IRQ_ROUTING @@ -1543,6 +1549,8 @@ struct kvm_s390_ucas_mapping { #define KVM_SET_PMU_EVENT_FILTER _IOW(KVMIO, 0xb2, struct kvm_pmu_event_filter) #define KVM_PPC_SVM_OFF _IO(KVMIO, 0xb3) #define KVM_ARM_MTE_COPY_TAGS _IOR(KVMIO, 0xb4, struct kvm_arm_copy_mte_tags) +/* Available with KVM_CAP_COUNTER_OFFSET */ +#define KVM_ARM_SET_COUNTER_OFFSET _IOW(KVMIO, 0xb5, struct kvm_arm_counter_offset) /* ioctl for vm fd */ #define KVM_CREATE_DEVICE _IOWR(KVMIO, 0xe0, struct kvm_create_device) diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index 759b3f53e53f..f23d9a16507f 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -290,6 +290,8 @@ struct prctl_mm_map { #define PR_SET_VMA 0x53564d41 # define PR_SET_VMA_ANON_NAME 0 +#define PR_GET_AUXV 0x41555856 + #define PR_SET_MEMORY_MERGE 67 #define PR_GET_MEMORY_MERGE 68 #endif /* _LINUX_PRCTL_H */ diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h index de6810e94abe..0aa955aa8246 100644 --- a/tools/include/uapi/sound/asound.h +++ b/tools/include/uapi/sound/asound.h @@ -429,9 +429,14 @@ struct snd_pcm_sw_params { snd_pcm_uframes_t avail_min; /* min avail frames for wakeup */ snd_pcm_uframes_t xfer_align; /* obsolete: xfer size need to be a multiple */ snd_pcm_uframes_t start_threshold; /* min hw_avail frames for automatic start */ - snd_pcm_uframes_t stop_threshold; /* min avail frames for automatic stop */ - snd_pcm_uframes_t silence_threshold; /* min distance from noise for silence filling */ - snd_pcm_uframes_t silence_size; /* silence block size */ + /* + * The following two thresholds alleviate playback buffer underruns; when + * hw_avail drops below the threshold, the respective action is triggered: + */ + snd_pcm_uframes_t stop_threshold; /* - stop playback */ + snd_pcm_uframes_t silence_threshold; /* - pre-fill buffer with silence */ + snd_pcm_uframes_t silence_size; /* max size of silence pre-fill; when >= boundary, + * fill played area with silence immediately */ snd_pcm_uframes_t boundary; /* pointers wrap point */ unsigned int proto; /* protocol version */ unsigned int tstamp_type; /* timestamp type (req. proto >= 2.0.12) */ @@ -570,7 +575,8 @@ struct __snd_pcm_mmap_status64 { struct __snd_pcm_mmap_control64 { __pad_before_uframe __pad1; snd_pcm_uframes_t appl_ptr; /* RW: appl ptr (0...boundary-1) */ - __pad_before_uframe __pad2; + __pad_before_uframe __pad2; // This should be __pad_after_uframe, but binary + // backwards compatibility constraints prevent a fix. __pad_before_uframe __pad3; snd_pcm_uframes_t avail_min; /* RW: min available frames for wakeup */ diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index ad1ec893b41b..a27f6e9ccce7 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -117,6 +117,7 @@ static const char * const attach_type_name[] = { [BPF_PERF_EVENT] = "perf_event", [BPF_TRACE_KPROBE_MULTI] = "trace_kprobe_multi", [BPF_STRUCT_OPS] = "struct_ops", + [BPF_NETFILTER] = "netfilter", }; static const char * const link_type_name[] = { @@ -8712,7 +8713,7 @@ static const struct bpf_sec_def section_defs[] = { SEC_DEF("struct_ops+", STRUCT_OPS, 0, SEC_NONE), SEC_DEF("struct_ops.s+", STRUCT_OPS, 0, SEC_SLEEPABLE), SEC_DEF("sk_lookup", SK_LOOKUP, BPF_SK_LOOKUP, SEC_ATTACHABLE), - SEC_DEF("netfilter", NETFILTER, 0, SEC_NONE), + SEC_DEF("netfilter", NETFILTER, BPF_NETFILTER, SEC_NONE), }; static size_t custom_sec_def_cnt; diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index 6065f408a59c..b7d443129f1c 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -180,7 +180,9 @@ static int probe_prog_load(enum bpf_prog_type prog_type, case BPF_PROG_TYPE_SK_REUSEPORT: case BPF_PROG_TYPE_FLOW_DISSECTOR: case BPF_PROG_TYPE_CGROUP_SYSCTL: + break; case BPF_PROG_TYPE_NETFILTER: + opts.expected_attach_type = BPF_NETFILTER; break; default: return -EOPNOTSUPP; diff --git a/tools/lib/subcmd/parse-options.h b/tools/lib/subcmd/parse-options.h index 41b9b942504d..8e9147358a28 100644 --- a/tools/lib/subcmd/parse-options.h +++ b/tools/lib/subcmd/parse-options.h @@ -6,10 +6,6 @@ #include <stdbool.h> #include <stdint.h> -#ifndef NORETURN -#define NORETURN __attribute__((__noreturn__)) -#endif - enum parse_opt_type { /* special types */ OPTION_END, @@ -183,9 +179,9 @@ extern int parse_options_subcommand(int argc, const char **argv, const char *const subcommands[], const char *usagestr[], int flags); -extern NORETURN void usage_with_options(const char * const *usagestr, +extern __noreturn void usage_with_options(const char * const *usagestr, const struct option *options); -extern NORETURN __attribute__((format(printf,3,4))) +extern __noreturn __attribute__((format(printf,3,4))) void usage_with_options_msg(const char * const *usagestr, const struct option *options, const char *fmt, ...); diff --git a/tools/lib/subcmd/subcmd-util.h b/tools/lib/subcmd/subcmd-util.h index b2aec04fce8f..dfac76e35ac7 100644 --- a/tools/lib/subcmd/subcmd-util.h +++ b/tools/lib/subcmd/subcmd-util.h @@ -5,8 +5,7 @@ #include <stdarg.h> #include <stdlib.h> #include <stdio.h> - -#define NORETURN __attribute__((__noreturn__)) +#include <linux/compiler.h> static inline void report(const char *prefix, const char *err, va_list params) { @@ -15,7 +14,7 @@ static inline void report(const char *prefix, const char *err, va_list params) fprintf(stderr, " %s%s\n", prefix, msg); } -static NORETURN inline void die(const char *err, ...) +static __noreturn inline void die(const char *err, ...) { va_list params; diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py index aa77bcae4807..3144f33196be 100644 --- a/tools/net/ynl/lib/ynl.py +++ b/tools/net/ynl/lib/ynl.py @@ -591,8 +591,9 @@ class YnlFamily(SpecFamily): print('Unexpected message: ' + repr(gm)) continue - rsp.append(self._decode(gm.raw_attrs, op.attr_set.name) - | gm.fixed_header_attrs) + rsp_msg = self._decode(gm.raw_attrs, op.attr_set.name) + rsp_msg.update(gm.fixed_header_attrs) + rsp.append(rsp_msg) if not rsp: return None diff --git a/tools/objtool/Documentation/objtool.txt b/tools/objtool/Documentation/objtool.txt index 744db4218e7a..fe39c2a8ef0d 100644 --- a/tools/objtool/Documentation/objtool.txt +++ b/tools/objtool/Documentation/objtool.txt @@ -244,6 +244,11 @@ To achieve the validation, objtool enforces the following rules: Objtool warnings ---------------- +NOTE: When requesting help with an objtool warning, please recreate with +OBJTOOL_VERBOSE=1 (e.g., "make OBJTOOL_VERBOSE=1") and send the full +output, including any disassembly or backtrace below the warning, to the +objtool maintainers. + For asm files, if you're getting an error which doesn't make sense, first make sure that the affected code follows the above rules. @@ -298,6 +303,11 @@ the objtool maintainers. If it's not actually in a callable function (e.g. kernel entry code), change ENDPROC to END. +3. file.o: warning: objtool: foo+0x48c: bar() is missing a __noreturn annotation + + The call from foo() to bar() doesn't return, but bar() is missing the + __noreturn annotation. NOTE: In addition to annotating the function + with __noreturn, please also add it to tools/objtool/noreturns.h. 4. file.o: warning: objtool: func(): can't find starting instruction or diff --git a/tools/objtool/arch/powerpc/include/arch/elf.h b/tools/objtool/arch/powerpc/include/arch/elf.h index 73f9ae172fe5..66814fa28024 100644 --- a/tools/objtool/arch/powerpc/include/arch/elf.h +++ b/tools/objtool/arch/powerpc/include/arch/elf.h @@ -1,10 +1,13 @@ /* SPDX-License-Identifier: GPL-2.0-or-later */ - #ifndef _OBJTOOL_ARCH_ELF #define _OBJTOOL_ARCH_ELF -#define R_NONE R_PPC_NONE -#define R_ABS64 R_PPC64_ADDR64 -#define R_ABS32 R_PPC_ADDR32 +#define R_NONE R_PPC_NONE +#define R_ABS64 R_PPC64_ADDR64 +#define R_ABS32 R_PPC_ADDR32 +#define R_DATA32 R_PPC_REL32 +#define R_DATA64 R_PPC64_REL64 +#define R_TEXT32 R_PPC_REL32 +#define R_TEXT64 R_PPC64_REL32 #endif /* _OBJTOOL_ARCH_ELF */ diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index 9ef024fd648c..2e1caabecb18 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -84,7 +84,7 @@ bool arch_pc_relative_reloc(struct reloc *reloc) * All relocation types where P (the address of the target) * is included in the computation. */ - switch (reloc->type) { + switch (reloc_type(reloc)) { case R_X86_64_PC8: case R_X86_64_PC16: case R_X86_64_PC32: @@ -623,11 +623,11 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec if (!immr || strcmp(immr->sym->name, "pv_ops")) break; - idx = (immr->addend + 8) / sizeof(void *); + idx = (reloc_addend(immr) + 8) / sizeof(void *); func = disp->sym; if (disp->sym->type == STT_SECTION) - func = find_symbol_by_offset(disp->sym->sec, disp->addend); + func = find_symbol_by_offset(disp->sym->sec, reloc_addend(disp)); if (!func) { WARN("no func for pv_ops[]"); return -1; diff --git a/tools/objtool/arch/x86/include/arch/elf.h b/tools/objtool/arch/x86/include/arch/elf.h index ac14987cf687..7131f7f51a4e 100644 --- a/tools/objtool/arch/x86/include/arch/elf.h +++ b/tools/objtool/arch/x86/include/arch/elf.h @@ -1,8 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ #ifndef _OBJTOOL_ARCH_ELF #define _OBJTOOL_ARCH_ELF -#define R_NONE R_X86_64_NONE -#define R_ABS64 R_X86_64_64 -#define R_ABS32 R_X86_64_32 +#define R_NONE R_X86_64_NONE +#define R_ABS32 R_X86_64_32 +#define R_ABS64 R_X86_64_64 +#define R_DATA32 R_X86_64_PC32 +#define R_DATA64 R_X86_64_PC32 +#define R_TEXT32 R_X86_64_PC32 +#define R_TEXT64 R_X86_64_PC32 #endif /* _OBJTOOL_ARCH_ELF */ diff --git a/tools/objtool/arch/x86/special.c b/tools/objtool/arch/x86/special.c index 7c97b7391279..29e949579ede 100644 --- a/tools/objtool/arch/x86/special.c +++ b/tools/objtool/arch/x86/special.c @@ -42,13 +42,7 @@ bool arch_support_alt_relocation(struct special_alt *special_alt, struct instruction *insn, struct reloc *reloc) { - /* - * The x86 alternatives code adjusts the offsets only when it - * encounters a branch instruction at the very beginning of the - * replacement group. - */ - return insn->offset == special_alt->new_off && - (insn->type == INSN_CALL || is_jump(insn)); + return true; } /* @@ -105,10 +99,10 @@ struct reloc *arch_find_switch_table(struct objtool_file *file, !text_reloc->sym->sec->rodata) return NULL; - table_offset = text_reloc->addend; + table_offset = reloc_addend(text_reloc); table_sec = text_reloc->sym->sec; - if (text_reloc->type == R_X86_64_PC32) + if (reloc_type(text_reloc) == R_X86_64_PC32) table_offset += 4; /* @@ -138,7 +132,7 @@ struct reloc *arch_find_switch_table(struct objtool_file *file, * indicates a rare GCC quirk/bug which can leave dead * code behind. */ - if (text_reloc->type == R_X86_64_PC32) + if (reloc_type(text_reloc) == R_X86_64_PC32) file->ignore_unreachables = true; return rodata_reloc; diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c index 7c175198d09f..5e21cfb7661d 100644 --- a/tools/objtool/builtin-check.c +++ b/tools/objtool/builtin-check.c @@ -93,6 +93,7 @@ static const struct option check_options[] = { OPT_BOOLEAN(0, "no-unreachable", &opts.no_unreachable, "skip 'unreachable instruction' warnings"), OPT_BOOLEAN(0, "sec-address", &opts.sec_address, "print section addresses in warnings"), OPT_BOOLEAN(0, "stats", &opts.stats, "print statistics"), + OPT_BOOLEAN('v', "verbose", &opts.verbose, "verbose warnings"), OPT_END(), }; @@ -118,6 +119,10 @@ int cmd_parse_options(int argc, const char **argv, const char * const usage[]) parse_options(envc, envv, check_options, env_usage, 0); } + env = getenv("OBJTOOL_VERBOSE"); + if (env && !strcmp(env, "1")) + opts.verbose = true; + argc = parse_options(argc, argv, check_options, usage, 0); if (argc != 1) usage_with_options(usage, check_options); diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 0fcf99c91400..8936a05f0e5a 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -8,7 +8,6 @@ #include <inttypes.h> #include <sys/mman.h> -#include <arch/elf.h> #include <objtool/builtin.h> #include <objtool/cfi.h> #include <objtool/arch.h> @@ -33,6 +32,7 @@ static unsigned long nr_cfi, nr_cfi_reused, nr_cfi_cache; static struct cfi_init_state initial_func_cfi; static struct cfi_state init_cfi; static struct cfi_state func_cfi; +static struct cfi_state force_undefined_cfi; struct instruction *find_insn(struct objtool_file *file, struct section *sec, unsigned long offset) @@ -192,51 +192,11 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, struct instruction *insn; bool empty = true; - /* - * Unfortunately these have to be hard coded because the noreturn - * attribute isn't provided in ELF data. Keep 'em sorted. - */ +#define NORETURN(func) __stringify(func), static const char * const global_noreturns[] = { - "__invalid_creds", - "__module_put_and_kthread_exit", - "__reiserfs_panic", - "__stack_chk_fail", - "__ubsan_handle_builtin_unreachable", - "arch_call_rest_init", - "arch_cpu_idle_dead", - "btrfs_assertfail", - "cpu_bringup_and_idle", - "cpu_startup_entry", - "do_exit", - "do_group_exit", - "do_task_dead", - "ex_handler_msr_mce", - "fortify_panic", - "hlt_play_dead", - "hv_ghcb_terminate", - "kthread_complete_and_exit", - "kthread_exit", - "kunit_try_catch_throw", - "lbug_with_loc", - "machine_real_restart", - "make_task_dead", - "mpt_halt_firmware", - "nmi_panic_self_stop", - "panic", - "panic_smp_self_stop", - "rest_init", - "resume_play_dead", - "rewind_stack_and_make_dead", - "sev_es_terminate", - "snp_abort", - "start_kernel", - "stop_this_cpu", - "usercopy_abort", - "x86_64_start_kernel", - "x86_64_start_reservations", - "xen_cpu_bringup_again", - "xen_start_kernel", +#include "noreturns.h" }; +#undef NORETURN if (!func) return false; @@ -533,7 +493,7 @@ static int add_pv_ops(struct objtool_file *file, const char *symname) { struct symbol *sym, *func; unsigned long off, end; - struct reloc *rel; + struct reloc *reloc; int idx; sym = find_symbol_by_name(file->elf, symname); @@ -543,19 +503,20 @@ static int add_pv_ops(struct objtool_file *file, const char *symname) off = sym->offset; end = off + sym->len; for (;;) { - rel = find_reloc_by_dest_range(file->elf, sym->sec, off, end - off); - if (!rel) + reloc = find_reloc_by_dest_range(file->elf, sym->sec, off, end - off); + if (!reloc) break; - func = rel->sym; + func = reloc->sym; if (func->type == STT_SECTION) - func = find_symbol_by_offset(rel->sym->sec, rel->addend); + func = find_symbol_by_offset(reloc->sym->sec, + reloc_addend(reloc)); - idx = (rel->offset - sym->offset) / sizeof(unsigned long); + idx = (reloc_offset(reloc) - sym->offset) / sizeof(unsigned long); objtool_pv_add(file, idx, func); - off = rel->offset + 1; + off = reloc_offset(reloc) + 1; if (off > end) break; } @@ -620,35 +581,40 @@ static struct instruction *find_last_insn(struct objtool_file *file, */ static int add_dead_ends(struct objtool_file *file) { - struct section *sec; + struct section *rsec; struct reloc *reloc; struct instruction *insn; + s64 addend; /* * Check for manually annotated dead ends. */ - sec = find_section_by_name(file->elf, ".rela.discard.unreachable"); - if (!sec) + rsec = find_section_by_name(file->elf, ".rela.discard.unreachable"); + if (!rsec) goto reachable; - list_for_each_entry(reloc, &sec->reloc_list, list) { + for_each_reloc(rsec, reloc) { + if (reloc->sym->type != STT_SECTION) { - WARN("unexpected relocation symbol type in %s", sec->name); + WARN("unexpected relocation symbol type in %s", rsec->name); return -1; } - insn = find_insn(file, reloc->sym->sec, reloc->addend); + + addend = reloc_addend(reloc); + + insn = find_insn(file, reloc->sym->sec, addend); if (insn) insn = prev_insn_same_sec(file, insn); - else if (reloc->addend == reloc->sym->sec->sh.sh_size) { + else if (addend == reloc->sym->sec->sh.sh_size) { insn = find_last_insn(file, reloc->sym->sec); if (!insn) { WARN("can't find unreachable insn at %s+0x%" PRIx64, - reloc->sym->sec->name, reloc->addend); + reloc->sym->sec->name, addend); return -1; } } else { WARN("can't find unreachable insn at %s+0x%" PRIx64, - reloc->sym->sec->name, reloc->addend); + reloc->sym->sec->name, addend); return -1; } @@ -662,28 +628,32 @@ reachable: * GCC doesn't know the "ud2" is fatal, so it generates code as if it's * not a dead end. */ - sec = find_section_by_name(file->elf, ".rela.discard.reachable"); - if (!sec) + rsec = find_section_by_name(file->elf, ".rela.discard.reachable"); + if (!rsec) return 0; - list_for_each_entry(reloc, &sec->reloc_list, list) { + for_each_reloc(rsec, reloc) { + if (reloc->sym->type != STT_SECTION) { - WARN("unexpected relocation symbol type in %s", sec->name); + WARN("unexpected relocation symbol type in %s", rsec->name); return -1; } - insn = find_insn(file, reloc->sym->sec, reloc->addend); + + addend = reloc_addend(reloc); + + insn = find_insn(file, reloc->sym->sec, addend); if (insn) insn = prev_insn_same_sec(file, insn); - else if (reloc->addend == reloc->sym->sec->sh.sh_size) { + else if (addend == reloc->sym->sec->sh.sh_size) { insn = find_last_insn(file, reloc->sym->sec); if (!insn) { WARN("can't find reachable insn at %s+0x%" PRIx64, - reloc->sym->sec->name, reloc->addend); + reloc->sym->sec->name, addend); return -1; } } else { WARN("can't find reachable insn at %s+0x%" PRIx64, - reloc->sym->sec->name, reloc->addend); + reloc->sym->sec->name, addend); return -1; } @@ -695,8 +665,8 @@ reachable: static int create_static_call_sections(struct objtool_file *file) { - struct section *sec; struct static_call_site *site; + struct section *sec; struct instruction *insn; struct symbol *key_sym; char *key_name, *tmp; @@ -716,22 +686,21 @@ static int create_static_call_sections(struct objtool_file *file) list_for_each_entry(insn, &file->static_call_list, call_node) idx++; - sec = elf_create_section(file->elf, ".static_call_sites", SHF_WRITE, - sizeof(struct static_call_site), idx); + sec = elf_create_section_pair(file->elf, ".static_call_sites", + sizeof(*site), idx, idx * 2); if (!sec) return -1; + /* Allow modules to modify the low bits of static_call_site::key */ + sec->sh.sh_flags |= SHF_WRITE; + idx = 0; list_for_each_entry(insn, &file->static_call_list, call_node) { - site = (struct static_call_site *)sec->data->d_buf + idx; - memset(site, 0, sizeof(struct static_call_site)); - /* populate reloc for 'addr' */ - if (elf_add_reloc_to_insn(file->elf, sec, - idx * sizeof(struct static_call_site), - R_X86_64_PC32, - insn->sec, insn->offset)) + if (!elf_init_reloc_text_sym(file->elf, sec, + idx * sizeof(*site), idx * 2, + insn->sec, insn->offset)) return -1; /* find key symbol */ @@ -771,10 +740,10 @@ static int create_static_call_sections(struct objtool_file *file) free(key_name); /* populate reloc for 'key' */ - if (elf_add_reloc(file->elf, sec, - idx * sizeof(struct static_call_site) + 4, - R_X86_64_PC32, key_sym, - is_sibling_call(insn) * STATIC_CALL_SITE_TAIL)) + if (!elf_init_reloc_data_sym(file->elf, sec, + idx * sizeof(*site) + 4, + (idx * 2) + 1, key_sym, + is_sibling_call(insn) * STATIC_CALL_SITE_TAIL)) return -1; idx++; @@ -802,26 +771,18 @@ static int create_retpoline_sites_sections(struct objtool_file *file) if (!idx) return 0; - sec = elf_create_section(file->elf, ".retpoline_sites", 0, - sizeof(int), idx); - if (!sec) { - WARN("elf_create_section: .retpoline_sites"); + sec = elf_create_section_pair(file->elf, ".retpoline_sites", + sizeof(int), idx, idx); + if (!sec) return -1; - } idx = 0; list_for_each_entry(insn, &file->retpoline_call_list, call_node) { - int *site = (int *)sec->data->d_buf + idx; - *site = 0; - - if (elf_add_reloc_to_insn(file->elf, sec, - idx * sizeof(int), - R_X86_64_PC32, - insn->sec, insn->offset)) { - WARN("elf_add_reloc_to_insn: .retpoline_sites"); + if (!elf_init_reloc_text_sym(file->elf, sec, + idx * sizeof(int), idx, + insn->sec, insn->offset)) return -1; - } idx++; } @@ -848,26 +809,18 @@ static int create_return_sites_sections(struct objtool_file *file) if (!idx) return 0; - sec = elf_create_section(file->elf, ".return_sites", 0, - sizeof(int), idx); - if (!sec) { - WARN("elf_create_section: .return_sites"); + sec = elf_create_section_pair(file->elf, ".return_sites", + sizeof(int), idx, idx); + if (!sec) return -1; - } idx = 0; list_for_each_entry(insn, &file->return_thunk_list, call_node) { - int *site = (int *)sec->data->d_buf + idx; - *site = 0; - - if (elf_add_reloc_to_insn(file->elf, sec, - idx * sizeof(int), - R_X86_64_PC32, - insn->sec, insn->offset)) { - WARN("elf_add_reloc_to_insn: .return_sites"); + if (!elf_init_reloc_text_sym(file->elf, sec, + idx * sizeof(int), idx, + insn->sec, insn->offset)) return -1; - } idx++; } @@ -900,12 +853,10 @@ static int create_ibt_endbr_seal_sections(struct objtool_file *file) if (!idx) return 0; - sec = elf_create_section(file->elf, ".ibt_endbr_seal", 0, - sizeof(int), idx); - if (!sec) { - WARN("elf_create_section: .ibt_endbr_seal"); + sec = elf_create_section_pair(file->elf, ".ibt_endbr_seal", + sizeof(int), idx, idx); + if (!sec) return -1; - } idx = 0; list_for_each_entry(insn, &file->endbr_list, call_node) { @@ -920,13 +871,10 @@ static int create_ibt_endbr_seal_sections(struct objtool_file *file) !strcmp(sym->name, "cleanup_module"))) WARN("%s(): not an indirect call target", sym->name); - if (elf_add_reloc_to_insn(file->elf, sec, - idx * sizeof(int), - R_X86_64_PC32, - insn->sec, insn->offset)) { - WARN("elf_add_reloc_to_insn: .ibt_endbr_seal"); + if (!elf_init_reloc_text_sym(file->elf, sec, + idx * sizeof(int), idx, + insn->sec, insn->offset)) return -1; - } idx++; } @@ -938,7 +886,6 @@ static int create_cfi_sections(struct objtool_file *file) { struct section *sec; struct symbol *sym; - unsigned int *loc; int idx; sec = find_section_by_name(file->elf, ".cfi_sites"); @@ -959,7 +906,8 @@ static int create_cfi_sections(struct objtool_file *file) idx++; } - sec = elf_create_section(file->elf, ".cfi_sites", 0, sizeof(unsigned int), idx); + sec = elf_create_section_pair(file->elf, ".cfi_sites", + sizeof(unsigned int), idx, idx); if (!sec) return -1; @@ -971,13 +919,9 @@ static int create_cfi_sections(struct objtool_file *file) if (strncmp(sym->name, "__cfi_", 6)) continue; - loc = (unsigned int *)sec->data->d_buf + idx; - memset(loc, 0, sizeof(unsigned int)); - - if (elf_add_reloc_to_insn(file->elf, sec, - idx * sizeof(unsigned int), - R_X86_64_PC32, - sym->sec, sym->offset)) + if (!elf_init_reloc_text_sym(file->elf, sec, + idx * sizeof(unsigned int), idx, + sym->sec, sym->offset)) return -1; idx++; @@ -988,7 +932,7 @@ static int create_cfi_sections(struct objtool_file *file) static int create_mcount_loc_sections(struct objtool_file *file) { - int addrsize = elf_class_addrsize(file->elf); + size_t addr_size = elf_addr_size(file->elf); struct instruction *insn; struct section *sec; int idx; @@ -1007,25 +951,26 @@ static int create_mcount_loc_sections(struct objtool_file *file) list_for_each_entry(insn, &file->mcount_loc_list, call_node) idx++; - sec = elf_create_section(file->elf, "__mcount_loc", 0, addrsize, idx); + sec = elf_create_section_pair(file->elf, "__mcount_loc", addr_size, + idx, idx); if (!sec) return -1; - sec->sh.sh_addralign = addrsize; + sec->sh.sh_addralign = addr_size; idx = 0; list_for_each_entry(insn, &file->mcount_loc_list, call_node) { - void *loc; - loc = sec->data->d_buf + idx; - memset(loc, 0, addrsize); + struct reloc *reloc; - if (elf_add_reloc_to_insn(file->elf, sec, idx, - addrsize == sizeof(u64) ? R_ABS64 : R_ABS32, - insn->sec, insn->offset)) + reloc = elf_init_reloc_text_sym(file->elf, sec, idx * addr_size, idx, + insn->sec, insn->offset); + if (!reloc) return -1; - idx += addrsize; + set_reloc_type(file->elf, reloc, addr_size == 8 ? R_ABS64 : R_ABS32); + + idx++; } return 0; @@ -1035,7 +980,6 @@ static int create_direct_call_sections(struct objtool_file *file) { struct instruction *insn; struct section *sec; - unsigned int *loc; int idx; sec = find_section_by_name(file->elf, ".call_sites"); @@ -1052,20 +996,17 @@ static int create_direct_call_sections(struct objtool_file *file) list_for_each_entry(insn, &file->call_list, call_node) idx++; - sec = elf_create_section(file->elf, ".call_sites", 0, sizeof(unsigned int), idx); + sec = elf_create_section_pair(file->elf, ".call_sites", + sizeof(unsigned int), idx, idx); if (!sec) return -1; idx = 0; list_for_each_entry(insn, &file->call_list, call_node) { - loc = (unsigned int *)sec->data->d_buf + idx; - memset(loc, 0, sizeof(unsigned int)); - - if (elf_add_reloc_to_insn(file->elf, sec, - idx * sizeof(unsigned int), - R_X86_64_PC32, - insn->sec, insn->offset)) + if (!elf_init_reloc_text_sym(file->elf, sec, + idx * sizeof(unsigned int), idx, + insn->sec, insn->offset)) return -1; idx++; @@ -1080,28 +1021,29 @@ static int create_direct_call_sections(struct objtool_file *file) static void add_ignores(struct objtool_file *file) { struct instruction *insn; - struct section *sec; + struct section *rsec; struct symbol *func; struct reloc *reloc; - sec = find_section_by_name(file->elf, ".rela.discard.func_stack_frame_non_standard"); - if (!sec) + rsec = find_section_by_name(file->elf, ".rela.discard.func_stack_frame_non_standard"); + if (!rsec) return; - list_for_each_entry(reloc, &sec->reloc_list, list) { + for_each_reloc(rsec, reloc) { switch (reloc->sym->type) { case STT_FUNC: func = reloc->sym; break; case STT_SECTION: - func = find_func_by_offset(reloc->sym->sec, reloc->addend); + func = find_func_by_offset(reloc->sym->sec, reloc_addend(reloc)); if (!func) continue; break; default: - WARN("unexpected relocation symbol type in %s: %d", sec->name, reloc->sym->type); + WARN("unexpected relocation symbol type in %s: %d", + rsec->name, reloc->sym->type); continue; } @@ -1320,21 +1262,21 @@ static void add_uaccess_safe(struct objtool_file *file) */ static int add_ignore_alternatives(struct objtool_file *file) { - struct section *sec; + struct section *rsec; struct reloc *reloc; struct instruction *insn; - sec = find_section_by_name(file->elf, ".rela.discard.ignore_alts"); - if (!sec) + rsec = find_section_by_name(file->elf, ".rela.discard.ignore_alts"); + if (!rsec) return 0; - list_for_each_entry(reloc, &sec->reloc_list, list) { + for_each_reloc(rsec, reloc) { if (reloc->sym->type != STT_SECTION) { - WARN("unexpected relocation symbol type in %s", sec->name); + WARN("unexpected relocation symbol type in %s", rsec->name); return -1; } - insn = find_insn(file, reloc->sym->sec, reloc->addend); + insn = find_insn(file, reloc->sym->sec, reloc_addend(reloc)); if (!insn) { WARN("bad .discard.ignore_alts entry"); return -1; @@ -1421,10 +1363,8 @@ static void annotate_call_site(struct objtool_file *file, * noinstr text. */ if (opts.hack_noinstr && insn->sec->noinstr && sym->profiling_func) { - if (reloc) { - reloc->type = R_NONE; - elf_write_reloc(file->elf, reloc); - } + if (reloc) + set_reloc_type(file->elf, reloc, R_NONE); elf_write_insn(file->elf, insn->sec, insn->offset, insn->len, @@ -1450,10 +1390,8 @@ static void annotate_call_site(struct objtool_file *file, if (sibling) WARN_INSN(insn, "tail call to __fentry__ !?!?"); if (opts.mnop) { - if (reloc) { - reloc->type = R_NONE; - elf_write_reloc(file->elf, reloc); - } + if (reloc) + set_reloc_type(file->elf, reloc, R_NONE); elf_write_insn(file->elf, insn->sec, insn->offset, insn->len, @@ -1610,7 +1548,7 @@ static int add_jump_destinations(struct objtool_file *file) dest_off = arch_jump_destination(insn); } else if (reloc->sym->type == STT_SECTION) { dest_sec = reloc->sym->sec; - dest_off = arch_dest_reloc_offset(reloc->addend); + dest_off = arch_dest_reloc_offset(reloc_addend(reloc)); } else if (reloc->sym->retpoline_thunk) { add_retpoline_call(file, insn); continue; @@ -1627,7 +1565,7 @@ static int add_jump_destinations(struct objtool_file *file) } else if (reloc->sym->sec->idx) { dest_sec = reloc->sym->sec; dest_off = reloc->sym->sym.st_value + - arch_dest_reloc_offset(reloc->addend); + arch_dest_reloc_offset(reloc_addend(reloc)); } else { /* non-func asm code jumping to another file */ continue; @@ -1744,7 +1682,7 @@ static int add_call_destinations(struct objtool_file *file) } } else if (reloc->sym->type == STT_SECTION) { - dest_off = arch_dest_reloc_offset(reloc->addend); + dest_off = arch_dest_reloc_offset(reloc_addend(reloc)); dest = find_call_destination(reloc->sym->sec, dest_off); if (!dest) { WARN_INSN(insn, "can't find call dest symbol at %s+0x%lx", @@ -1932,10 +1870,8 @@ static int handle_jump_alt(struct objtool_file *file, if (opts.hack_jump_label && special_alt->key_addend & 2) { struct reloc *reloc = insn_reloc(file, orig_insn); - if (reloc) { - reloc->type = R_NONE; - elf_write_reloc(file->elf, reloc); - } + if (reloc) + set_reloc_type(file->elf, reloc, R_NONE); elf_write_insn(file->elf, orig_insn->sec, orig_insn->offset, orig_insn->len, arch_nop_insn(orig_insn->len)); @@ -2047,34 +1983,35 @@ out: } static int add_jump_table(struct objtool_file *file, struct instruction *insn, - struct reloc *table) + struct reloc *next_table) { - struct reloc *reloc = table; - struct instruction *dest_insn; - struct alternative *alt; struct symbol *pfunc = insn_func(insn)->pfunc; + struct reloc *table = insn_jump_table(insn); + struct instruction *dest_insn; unsigned int prev_offset = 0; + struct reloc *reloc = table; + struct alternative *alt; /* * Each @reloc is a switch table relocation which points to the target * instruction. */ - list_for_each_entry_from(reloc, &table->sec->reloc_list, list) { + for_each_reloc_from(table->sec, reloc) { /* Check for the end of the table: */ - if (reloc != table && reloc->jump_table_start) + if (reloc != table && reloc == next_table) break; /* Make sure the table entries are consecutive: */ - if (prev_offset && reloc->offset != prev_offset + 8) + if (prev_offset && reloc_offset(reloc) != prev_offset + 8) break; /* Detect function pointers from contiguous objects: */ if (reloc->sym->sec == pfunc->sec && - reloc->addend == pfunc->offset) + reloc_addend(reloc) == pfunc->offset) break; - dest_insn = find_insn(file, reloc->sym->sec, reloc->addend); + dest_insn = find_insn(file, reloc->sym->sec, reloc_addend(reloc)); if (!dest_insn) break; @@ -2091,7 +2028,7 @@ static int add_jump_table(struct objtool_file *file, struct instruction *insn, alt->insn = dest_insn; alt->next = insn->alts; insn->alts = alt; - prev_offset = reloc->offset; + prev_offset = reloc_offset(reloc); } if (!prev_offset) { @@ -2135,7 +2072,7 @@ static struct reloc *find_jump_table(struct objtool_file *file, table_reloc = arch_find_switch_table(file, insn); if (!table_reloc) continue; - dest_insn = find_insn(file, table_reloc->sym->sec, table_reloc->addend); + dest_insn = find_insn(file, table_reloc->sym->sec, reloc_addend(table_reloc)); if (!dest_insn || !insn_func(dest_insn) || insn_func(dest_insn)->pfunc != func) continue; @@ -2177,29 +2114,39 @@ static void mark_func_jump_tables(struct objtool_file *file, continue; reloc = find_jump_table(file, func, insn); - if (reloc) { - reloc->jump_table_start = true; + if (reloc) insn->_jump_table = reloc; - } } } static int add_func_jump_tables(struct objtool_file *file, struct symbol *func) { - struct instruction *insn; - int ret; + struct instruction *insn, *insn_t1 = NULL, *insn_t2; + int ret = 0; func_for_each_insn(file, func, insn) { if (!insn_jump_table(insn)) continue; - ret = add_jump_table(file, insn, insn_jump_table(insn)); + if (!insn_t1) { + insn_t1 = insn; + continue; + } + + insn_t2 = insn; + + ret = add_jump_table(file, insn_t1, insn_jump_table(insn_t2)); if (ret) return ret; + + insn_t1 = insn_t2; } - return 0; + if (insn_t1) + ret = add_jump_table(file, insn_t1, NULL); + + return ret; } /* @@ -2240,7 +2187,7 @@ static void set_func_state(struct cfi_state *state) static int read_unwind_hints(struct objtool_file *file) { struct cfi_state cfi = init_cfi; - struct section *sec, *relocsec; + struct section *sec; struct unwind_hint *hint; struct instruction *insn; struct reloc *reloc; @@ -2250,8 +2197,7 @@ static int read_unwind_hints(struct objtool_file *file) if (!sec) return 0; - relocsec = sec->reloc; - if (!relocsec) { + if (!sec->rsec) { WARN("missing .rela.discard.unwind_hints section"); return -1; } @@ -2272,7 +2218,7 @@ static int read_unwind_hints(struct objtool_file *file) return -1; } - insn = find_insn(file, reloc->sym->sec, reloc->addend); + insn = find_insn(file, reloc->sym->sec, reloc_addend(reloc)); if (!insn) { WARN("can't find insn for unwind_hints[%d]", i); return -1; @@ -2280,6 +2226,11 @@ static int read_unwind_hints(struct objtool_file *file) insn->hint = true; + if (hint->type == UNWIND_HINT_TYPE_UNDEFINED) { + insn->cfi = &force_undefined_cfi; + continue; + } + if (hint->type == UNWIND_HINT_TYPE_SAVE) { insn->hint = false; insn->save = true; @@ -2326,16 +2277,17 @@ static int read_unwind_hints(struct objtool_file *file) static int read_noendbr_hints(struct objtool_file *file) { - struct section *sec; struct instruction *insn; + struct section *rsec; struct reloc *reloc; - sec = find_section_by_name(file->elf, ".rela.discard.noendbr"); - if (!sec) + rsec = find_section_by_name(file->elf, ".rela.discard.noendbr"); + if (!rsec) return 0; - list_for_each_entry(reloc, &sec->reloc_list, list) { - insn = find_insn(file, reloc->sym->sec, reloc->sym->offset + reloc->addend); + for_each_reloc(rsec, reloc) { + insn = find_insn(file, reloc->sym->sec, + reloc->sym->offset + reloc_addend(reloc)); if (!insn) { WARN("bad .discard.noendbr entry"); return -1; @@ -2349,21 +2301,21 @@ static int read_noendbr_hints(struct objtool_file *file) static int read_retpoline_hints(struct objtool_file *file) { - struct section *sec; + struct section *rsec; struct instruction *insn; struct reloc *reloc; - sec = find_section_by_name(file->elf, ".rela.discard.retpoline_safe"); - if (!sec) + rsec = find_section_by_name(file->elf, ".rela.discard.retpoline_safe"); + if (!rsec) return 0; - list_for_each_entry(reloc, &sec->reloc_list, list) { + for_each_reloc(rsec, reloc) { if (reloc->sym->type != STT_SECTION) { - WARN("unexpected relocation symbol type in %s", sec->name); + WARN("unexpected relocation symbol type in %s", rsec->name); return -1; } - insn = find_insn(file, reloc->sym->sec, reloc->addend); + insn = find_insn(file, reloc->sym->sec, reloc_addend(reloc)); if (!insn) { WARN("bad .discard.retpoline_safe entry"); return -1; @@ -2385,21 +2337,21 @@ static int read_retpoline_hints(struct objtool_file *file) static int read_instr_hints(struct objtool_file *file) { - struct section *sec; + struct section *rsec; struct instruction *insn; struct reloc *reloc; - sec = find_section_by_name(file->elf, ".rela.discard.instr_end"); - if (!sec) + rsec = find_section_by_name(file->elf, ".rela.discard.instr_end"); + if (!rsec) return 0; - list_for_each_entry(reloc, &sec->reloc_list, list) { + for_each_reloc(rsec, reloc) { if (reloc->sym->type != STT_SECTION) { - WARN("unexpected relocation symbol type in %s", sec->name); + WARN("unexpected relocation symbol type in %s", rsec->name); return -1; } - insn = find_insn(file, reloc->sym->sec, reloc->addend); + insn = find_insn(file, reloc->sym->sec, reloc_addend(reloc)); if (!insn) { WARN("bad .discard.instr_end entry"); return -1; @@ -2408,17 +2360,17 @@ static int read_instr_hints(struct objtool_file *file) insn->instr--; } - sec = find_section_by_name(file->elf, ".rela.discard.instr_begin"); - if (!sec) + rsec = find_section_by_name(file->elf, ".rela.discard.instr_begin"); + if (!rsec) return 0; - list_for_each_entry(reloc, &sec->reloc_list, list) { + for_each_reloc(rsec, reloc) { if (reloc->sym->type != STT_SECTION) { - WARN("unexpected relocation symbol type in %s", sec->name); + WARN("unexpected relocation symbol type in %s", rsec->name); return -1; } - insn = find_insn(file, reloc->sym->sec, reloc->addend); + insn = find_insn(file, reloc->sym->sec, reloc_addend(reloc)); if (!insn) { WARN("bad .discard.instr_begin entry"); return -1; @@ -2432,21 +2384,21 @@ static int read_instr_hints(struct objtool_file *file) static int read_validate_unret_hints(struct objtool_file *file) { - struct section *sec; + struct section *rsec; struct instruction *insn; struct reloc *reloc; - sec = find_section_by_name(file->elf, ".rela.discard.validate_unret"); - if (!sec) + rsec = find_section_by_name(file->elf, ".rela.discard.validate_unret"); + if (!rsec) return 0; - list_for_each_entry(reloc, &sec->reloc_list, list) { + for_each_reloc(rsec, reloc) { if (reloc->sym->type != STT_SECTION) { - WARN("unexpected relocation symbol type in %s", sec->name); + WARN("unexpected relocation symbol type in %s", rsec->name); return -1; } - insn = find_insn(file, reloc->sym->sec, reloc->addend); + insn = find_insn(file, reloc->sym->sec, reloc_addend(reloc)); if (!insn) { WARN("bad .discard.instr_end entry"); return -1; @@ -2461,23 +2413,23 @@ static int read_validate_unret_hints(struct objtool_file *file) static int read_intra_function_calls(struct objtool_file *file) { struct instruction *insn; - struct section *sec; + struct section *rsec; struct reloc *reloc; - sec = find_section_by_name(file->elf, ".rela.discard.intra_function_calls"); - if (!sec) + rsec = find_section_by_name(file->elf, ".rela.discard.intra_function_calls"); + if (!rsec) return 0; - list_for_each_entry(reloc, &sec->reloc_list, list) { + for_each_reloc(rsec, reloc) { unsigned long dest_off; if (reloc->sym->type != STT_SECTION) { WARN("unexpected relocation symbol type in %s", - sec->name); + rsec->name); return -1; } - insn = find_insn(file, reloc->sym->sec, reloc->addend); + insn = find_insn(file, reloc->sym->sec, reloc_addend(reloc)); if (!insn) { WARN("bad .discard.intra_function_call entry"); return -1; @@ -2833,6 +2785,10 @@ static int update_cfi_state(struct instruction *insn, struct cfi_reg *cfa = &cfi->cfa; struct cfi_reg *regs = cfi->regs; + /* ignore UNWIND_HINT_UNDEFINED regions */ + if (cfi->force_undefined) + return 0; + /* stack operations don't make sense with an undefined CFA */ if (cfa->base == CFI_UNDEFINED) { if (insn_func(insn)) { @@ -3369,15 +3325,15 @@ static inline bool func_uaccess_safe(struct symbol *func) static inline const char *call_dest_name(struct instruction *insn) { static char pvname[19]; - struct reloc *rel; + struct reloc *reloc; int idx; if (insn_call_dest(insn)) return insn_call_dest(insn)->name; - rel = insn_reloc(NULL, insn); - if (rel && !strcmp(rel->sym->name, "pv_ops")) { - idx = (rel->addend / sizeof(void *)); + reloc = insn_reloc(NULL, insn); + if (reloc && !strcmp(reloc->sym->name, "pv_ops")) { + idx = (reloc_addend(reloc) / sizeof(void *)); snprintf(pvname, sizeof(pvname), "pv_ops[%d]", idx); return pvname; } @@ -3388,14 +3344,14 @@ static inline const char *call_dest_name(struct instruction *insn) static bool pv_call_dest(struct objtool_file *file, struct instruction *insn) { struct symbol *target; - struct reloc *rel; + struct reloc *reloc; int idx; - rel = insn_reloc(file, insn); - if (!rel || strcmp(rel->sym->name, "pv_ops")) + reloc = insn_reloc(file, insn); + if (!reloc || strcmp(reloc->sym->name, "pv_ops")) return false; - idx = (arch_dest_reloc_offset(rel->addend) / sizeof(void *)); + idx = (arch_dest_reloc_offset(reloc_addend(reloc)) / sizeof(void *)); if (file->pv_ops[idx].clean) return true; @@ -3657,8 +3613,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, ret = validate_branch(file, func, alt->insn, state); if (ret) { - if (opts.backtrace) - BT_FUNC("(alt)", insn); + BT_INSN(insn, "(alt)"); return ret; } } @@ -3703,8 +3658,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, ret = validate_branch(file, func, insn->jump_dest, state); if (ret) { - if (opts.backtrace) - BT_FUNC("(branch)", insn); + BT_INSN(insn, "(branch)"); return ret; } } @@ -3802,8 +3756,8 @@ static int validate_unwind_hint(struct objtool_file *file, { if (insn->hint && !insn->visited && !insn->ignore) { int ret = validate_branch(file, insn_func(insn), insn, *state); - if (ret && opts.backtrace) - BT_FUNC("<=== (hint)", insn); + if (ret) + BT_INSN(insn, "<=== (hint)"); return ret; } @@ -3841,7 +3795,7 @@ static int validate_unwind_hints(struct objtool_file *file, struct section *sec) static int validate_unret(struct objtool_file *file, struct instruction *insn) { struct instruction *next, *dest; - int ret, warnings = 0; + int ret; for (;;) { next = next_insn_to_validate(file, insn); @@ -3861,8 +3815,7 @@ static int validate_unret(struct objtool_file *file, struct instruction *insn) ret = validate_unret(file, alt->insn); if (ret) { - if (opts.backtrace) - BT_FUNC("(alt)", insn); + BT_INSN(insn, "(alt)"); return ret; } } @@ -3888,10 +3841,8 @@ static int validate_unret(struct objtool_file *file, struct instruction *insn) } ret = validate_unret(file, insn->jump_dest); if (ret) { - if (opts.backtrace) { - BT_FUNC("(branch%s)", insn, - insn->type == INSN_JUMP_CONDITIONAL ? "-cond" : ""); - } + BT_INSN(insn, "(branch%s)", + insn->type == INSN_JUMP_CONDITIONAL ? "-cond" : ""); return ret; } @@ -3913,8 +3864,7 @@ static int validate_unret(struct objtool_file *file, struct instruction *insn) ret = validate_unret(file, dest); if (ret) { - if (opts.backtrace) - BT_FUNC("(call)", insn); + BT_INSN(insn, "(call)"); return ret; } /* @@ -3943,7 +3893,7 @@ static int validate_unret(struct objtool_file *file, struct instruction *insn) insn = next; } - return warnings; + return 0; } /* @@ -4178,7 +4128,6 @@ static int add_prefix_symbols(struct objtool_file *file) { struct section *sec; struct symbol *func; - int warnings = 0; for_each_sec(file, sec) { if (!(sec->sh.sh_flags & SHF_EXECINSTR)) @@ -4192,7 +4141,7 @@ static int add_prefix_symbols(struct objtool_file *file) } } - return warnings; + return 0; } static int validate_symbol(struct objtool_file *file, struct section *sec, @@ -4216,8 +4165,8 @@ static int validate_symbol(struct objtool_file *file, struct section *sec, state->uaccess = sym->uaccess_safe; ret = validate_branch(file, insn_func(insn), insn, *state); - if (ret && opts.backtrace) - BT_FUNC("<=== (sym)", insn); + if (ret) + BT_INSN(insn, "<=== (sym)"); return ret; } @@ -4333,8 +4282,8 @@ static int validate_ibt_insn(struct objtool_file *file, struct instruction *insn for (reloc = insn_reloc(file, insn); reloc; reloc = find_reloc_by_dest_range(file->elf, insn->sec, - reloc->offset + 1, - (insn->offset + insn->len) - (reloc->offset + 1))) { + reloc_offset(reloc) + 1, + (insn->offset + insn->len) - (reloc_offset(reloc) + 1))) { /* * static_call_update() references the trampoline, which @@ -4344,10 +4293,11 @@ static int validate_ibt_insn(struct objtool_file *file, struct instruction *insn continue; off = reloc->sym->offset; - if (reloc->type == R_X86_64_PC32 || reloc->type == R_X86_64_PLT32) - off += arch_dest_reloc_offset(reloc->addend); + if (reloc_type(reloc) == R_X86_64_PC32 || + reloc_type(reloc) == R_X86_64_PLT32) + off += arch_dest_reloc_offset(reloc_addend(reloc)); else - off += reloc->addend; + off += reloc_addend(reloc); dest = find_insn(file, reloc->sym->sec, off); if (!dest) @@ -4404,7 +4354,7 @@ static int validate_ibt_data_reloc(struct objtool_file *file, struct instruction *dest; dest = find_insn(file, reloc->sym->sec, - reloc->sym->offset + reloc->addend); + reloc->sym->offset + reloc_addend(reloc)); if (!dest) return 0; @@ -4417,7 +4367,7 @@ static int validate_ibt_data_reloc(struct objtool_file *file, return 0; WARN_FUNC("data relocation to !ENDBR: %s", - reloc->sec->base, reloc->offset, + reloc->sec->base, reloc_offset(reloc), offstr(dest->sec, dest->offset)); return 1; @@ -4444,7 +4394,7 @@ static int validate_ibt(struct objtool_file *file) if (sec->sh.sh_flags & SHF_EXECINSTR) continue; - if (!sec->reloc) + if (!sec->rsec) continue; /* @@ -4471,7 +4421,7 @@ static int validate_ibt(struct objtool_file *file) strstr(sec->name, "__patchable_function_entries")) continue; - list_for_each_entry(reloc, &sec->reloc->reloc_list, list) + for_each_reloc(sec->rsec, reloc) warnings += validate_ibt_data_reloc(file, reloc); } @@ -4511,9 +4461,40 @@ static int validate_sls(struct objtool_file *file) return warnings; } +static bool ignore_noreturn_call(struct instruction *insn) +{ + struct symbol *call_dest = insn_call_dest(insn); + + /* + * FIXME: hack, we need a real noreturn solution + * + * Problem is, exc_double_fault() may or may not return, depending on + * whether CONFIG_X86_ESPFIX64 is set. But objtool has no visibility + * to the kernel config. + * + * Other potential ways to fix it: + * + * - have compiler communicate __noreturn functions somehow + * - remove CONFIG_X86_ESPFIX64 + * - read the .config file + * - add a cmdline option + * - create a generic objtool annotation format (vs a bunch of custom + * formats) and annotate it + */ + if (!strcmp(call_dest->name, "exc_double_fault")) { + /* prevent further unreachable warnings for the caller */ + insn->sym->warned = 1; + return true; + } + + return false; +} + static int validate_reachable_instructions(struct objtool_file *file) { - struct instruction *insn; + struct instruction *insn, *prev_insn; + struct symbol *call_dest; + int warnings = 0; if (file->ignore_unreachables) return 0; @@ -4522,13 +4503,127 @@ static int validate_reachable_instructions(struct objtool_file *file) if (insn->visited || ignore_unreachable_insn(file, insn)) continue; + prev_insn = prev_insn_same_sec(file, insn); + if (prev_insn && prev_insn->dead_end) { + call_dest = insn_call_dest(prev_insn); + if (call_dest && !ignore_noreturn_call(prev_insn)) { + WARN_INSN(insn, "%s() is missing a __noreturn annotation", + call_dest->name); + warnings++; + continue; + } + } + WARN_INSN(insn, "unreachable instruction"); - return 1; + warnings++; + } + + return warnings; +} + +/* 'funcs' is a space-separated list of function names */ +static int disas_funcs(const char *funcs) +{ + const char *objdump_str, *cross_compile; + int size, ret; + char *cmd; + + cross_compile = getenv("CROSS_COMPILE"); + + objdump_str = "%sobjdump -wdr %s | gawk -M -v _funcs='%s' '" + "BEGIN { split(_funcs, funcs); }" + "/^$/ { func_match = 0; }" + "/<.*>:/ { " + "f = gensub(/.*<(.*)>:/, \"\\\\1\", 1);" + "for (i in funcs) {" + "if (funcs[i] == f) {" + "func_match = 1;" + "base = strtonum(\"0x\" $1);" + "break;" + "}" + "}" + "}" + "{" + "if (func_match) {" + "addr = strtonum(\"0x\" $1);" + "printf(\"%%04x \", addr - base);" + "print;" + "}" + "}' 1>&2"; + + /* fake snprintf() to calculate the size */ + size = snprintf(NULL, 0, objdump_str, cross_compile, objname, funcs) + 1; + if (size <= 0) { + WARN("objdump string size calculation failed"); + return -1; + } + + cmd = malloc(size); + + /* real snprintf() */ + snprintf(cmd, size, objdump_str, cross_compile, objname, funcs); + ret = system(cmd); + if (ret) { + WARN("disassembly failed: %d", ret); + return -1; } return 0; } +static int disas_warned_funcs(struct objtool_file *file) +{ + struct symbol *sym; + char *funcs = NULL, *tmp; + + for_each_sym(file, sym) { + if (sym->warned) { + if (!funcs) { + funcs = malloc(strlen(sym->name) + 1); + strcpy(funcs, sym->name); + } else { + tmp = malloc(strlen(funcs) + strlen(sym->name) + 2); + sprintf(tmp, "%s %s", funcs, sym->name); + free(funcs); + funcs = tmp; + } + } + } + + if (funcs) + disas_funcs(funcs); + + return 0; +} + +struct insn_chunk { + void *addr; + struct insn_chunk *next; +}; + +/* + * Reduce peak RSS usage by freeing insns memory before writing the ELF file, + * which can trigger more allocations for .debug_* sections whose data hasn't + * been read yet. + */ +static void free_insns(struct objtool_file *file) +{ + struct instruction *insn; + struct insn_chunk *chunks = NULL, *chunk; + + for_each_insn(file, insn) { + if (!insn->idx) { + chunk = malloc(sizeof(*chunk)); + chunk->addr = insn; + chunk->next = chunks; + chunks = chunk; + } + } + + for (chunk = chunks; chunk; chunk = chunk->next) + free(chunk->addr); +} + int check(struct objtool_file *file) { int ret, warnings = 0; @@ -4537,6 +4632,8 @@ int check(struct objtool_file *file) init_cfi_state(&init_cfi); init_cfi_state(&func_cfi); set_func_state(&func_cfi); + init_cfi_state(&force_undefined_cfi); + force_undefined_cfi.force_undefined = true; if (!cfi_hash_alloc(1UL << (file->elf->symbol_bits - 3))) goto out; @@ -4673,6 +4770,10 @@ int check(struct objtool_file *file) warnings += ret; } + free_insns(file); + + if (opts.verbose) + disas_warned_funcs(file); if (opts.stats) { printf("nr_insns_visited: %ld\n", nr_insns_visited); diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index 500e92979a31..d420b5d2e2b6 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -32,16 +32,52 @@ static inline u32 str_hash(const char *str) #define __elf_table(name) (elf->name##_hash) #define __elf_bits(name) (elf->name##_bits) -#define elf_hash_add(name, node, key) \ - hlist_add_head(node, &__elf_table(name)[hash_min(key, __elf_bits(name))]) +#define __elf_table_entry(name, key) \ + __elf_table(name)[hash_min(key, __elf_bits(name))] + +#define elf_hash_add(name, node, key) \ +({ \ + struct elf_hash_node *__node = node; \ + __node->next = __elf_table_entry(name, key); \ + __elf_table_entry(name, key) = __node; \ +}) + +static inline void __elf_hash_del(struct elf_hash_node *node, + struct elf_hash_node **head) +{ + struct elf_hash_node *cur, *prev; + + if (node == *head) { + *head = node->next; + return; + } + + for (prev = NULL, cur = *head; cur; prev = cur, cur = cur->next) { + if (cur == node) { + prev->next = cur->next; + break; + } + } +} -#define elf_hash_for_each_possible(name, obj, member, key) \ - hlist_for_each_entry(obj, &__elf_table(name)[hash_min(key, __elf_bits(name))], member) +#define elf_hash_del(name, node, key) \ + __elf_hash_del(node, &__elf_table_entry(name, key)) + +#define elf_list_entry(ptr, type, member) \ +({ \ + typeof(ptr) __ptr = (ptr); \ + __ptr ? container_of(__ptr, type, member) : NULL; \ +}) + +#define elf_hash_for_each_possible(name, obj, member, key) \ + for (obj = elf_list_entry(__elf_table_entry(name, key), typeof(*obj), member); \ + obj; \ + obj = elf_list_entry(obj->member.next, typeof(*(obj)), member)) #define elf_alloc_hash(name, size) \ ({ \ __elf_bits(name) = max(10, ilog2(size)); \ - __elf_table(name) = mmap(NULL, sizeof(struct hlist_head) << __elf_bits(name), \ + __elf_table(name) = mmap(NULL, sizeof(struct elf_hash_node *) << __elf_bits(name), \ PROT_READ|PROT_WRITE, \ MAP_PRIVATE|MAP_ANON, -1, 0); \ if (__elf_table(name) == (void *)-1L) { \ @@ -233,21 +269,22 @@ struct reloc *find_reloc_by_dest_range(const struct elf *elf, struct section *se unsigned long offset, unsigned int len) { struct reloc *reloc, *r = NULL; + struct section *rsec; unsigned long o; - if (!sec->reloc) + rsec = sec->rsec; + if (!rsec) return NULL; - sec = sec->reloc; - for_offset_range(o, offset, offset + len) { elf_hash_for_each_possible(reloc, reloc, hash, - sec_offset_hash(sec, o)) { - if (reloc->sec != sec) + sec_offset_hash(rsec, o)) { + if (reloc->sec != rsec) continue; - if (reloc->offset >= offset && reloc->offset < offset + len) { - if (!r || reloc->offset < r->offset) + if (reloc_offset(reloc) >= offset && + reloc_offset(reloc) < offset + len) { + if (!r || reloc_offset(reloc) < reloc_offset(r)) r = reloc; } } @@ -263,6 +300,11 @@ struct reloc *find_reloc_by_dest(const struct elf *elf, struct section *sec, uns return find_reloc_by_dest_range(elf, sec, offset, 1); } +static bool is_dwarf_section(struct section *sec) +{ + return !strncmp(sec->name, ".debug_", 7); +} + static int read_sections(struct elf *elf) { Elf_Scn *s = NULL; @@ -293,7 +335,6 @@ static int read_sections(struct elf *elf) sec = &elf->section_data[i]; INIT_LIST_HEAD(&sec->symbol_list); - INIT_LIST_HEAD(&sec->reloc_list); s = elf_getscn(elf->elf, i); if (!s) { @@ -314,7 +355,7 @@ static int read_sections(struct elf *elf) return -1; } - if (sec->sh.sh_size != 0) { + if (sec->sh.sh_size != 0 && !is_dwarf_section(sec)) { sec->data = elf_getdata(s, NULL); if (!sec->data) { WARN_ELF("elf_getdata"); @@ -328,12 +369,12 @@ static int read_sections(struct elf *elf) } } - if (sec->sh.sh_flags & SHF_EXECINSTR) - elf->text_size += sec->sh.sh_size; - list_add_tail(&sec->list, &elf->sections); elf_hash_add(section, &sec->hash, sec->idx); elf_hash_add(section_name, &sec->name_hash, str_hash(sec->name)); + + if (is_reloc_sec(sec)) + elf->num_relocs += sec_num_entries(sec); } if (opts.stats) { @@ -356,7 +397,6 @@ static void elf_add_symbol(struct elf *elf, struct symbol *sym) struct rb_node *pnode; struct symbol *iter; - INIT_LIST_HEAD(&sym->reloc_list); INIT_LIST_HEAD(&sym->pv_target); sym->alias = sym; @@ -407,7 +447,7 @@ static int read_symbols(struct elf *elf) if (symtab_shndx) shndx_data = symtab_shndx->data; - symbols_nr = symtab->sh.sh_size / symtab->sh.sh_entsize; + symbols_nr = sec_num_entries(symtab); } else { /* * A missing symbol table is actually possible if it's an empty @@ -533,52 +573,17 @@ err: return -1; } -static struct section *elf_create_reloc_section(struct elf *elf, - struct section *base, - int reltype); - -int elf_add_reloc(struct elf *elf, struct section *sec, unsigned long offset, - unsigned int type, struct symbol *sym, s64 addend) -{ - struct reloc *reloc; - - if (!sec->reloc && !elf_create_reloc_section(elf, sec, SHT_RELA)) - return -1; - - reloc = malloc(sizeof(*reloc)); - if (!reloc) { - perror("malloc"); - return -1; - } - memset(reloc, 0, sizeof(*reloc)); - - reloc->sec = sec->reloc; - reloc->offset = offset; - reloc->type = type; - reloc->sym = sym; - reloc->addend = addend; - - list_add_tail(&reloc->sym_reloc_entry, &sym->reloc_list); - list_add_tail(&reloc->list, &sec->reloc->reloc_list); - elf_hash_add(reloc, &reloc->hash, reloc_hash(reloc)); - - sec->reloc->sh.sh_size += sec->reloc->sh.sh_entsize; - sec->reloc->changed = true; - - return 0; -} - /* - * Ensure that any reloc section containing references to @sym is marked - * changed such that it will get re-generated in elf_rebuild_reloc_sections() - * with the new symbol index. + * @sym's idx has changed. Update the relocs which reference it. */ -static void elf_dirty_reloc_sym(struct elf *elf, struct symbol *sym) +static int elf_update_sym_relocs(struct elf *elf, struct symbol *sym) { struct reloc *reloc; - list_for_each_entry(reloc, &sym->reloc_list, sym_reloc_entry) - reloc->sec->changed = true; + for (reloc = sym->relocs; reloc; reloc = reloc->sym_next_reloc) + set_reloc_sym(elf, reloc, reloc->sym->idx); + + return 0; } /* @@ -655,7 +660,7 @@ static int elf_update_symbol(struct elf *elf, struct section *symtab, symtab_data->d_align = 1; symtab_data->d_type = ELF_T_SYM; - symtab->changed = true; + mark_sec_changed(elf, symtab, true); symtab->truncate = true; if (t) { @@ -670,7 +675,7 @@ static int elf_update_symbol(struct elf *elf, struct section *symtab, shndx_data->d_align = sizeof(Elf32_Word); shndx_data->d_type = ELF_T_WORD; - symtab_shndx->changed = true; + mark_sec_changed(elf, symtab_shndx, true); symtab_shndx->truncate = true; } @@ -734,7 +739,7 @@ __elf_create_symbol(struct elf *elf, struct symbol *sym) return NULL; } - new_idx = symtab->sh.sh_size / symtab->sh.sh_entsize; + new_idx = sec_num_entries(symtab); if (GELF_ST_BIND(sym->sym.st_info) != STB_LOCAL) goto non_local; @@ -746,18 +751,19 @@ __elf_create_symbol(struct elf *elf, struct symbol *sym) first_non_local = symtab->sh.sh_info; old = find_symbol_by_index(elf, first_non_local); if (old) { - old->idx = new_idx; - hlist_del(&old->hash); - elf_hash_add(symbol, &old->hash, old->idx); - - elf_dirty_reloc_sym(elf, old); + elf_hash_del(symbol, &old->hash, old->idx); + elf_hash_add(symbol, &old->hash, new_idx); + old->idx = new_idx; if (elf_update_symbol(elf, symtab, symtab_shndx, old)) { WARN("elf_update_symbol move"); return NULL; } + if (elf_update_sym_relocs(elf, old)) + return NULL; + new_idx = first_non_local; } @@ -774,11 +780,11 @@ non_local: } symtab->sh.sh_size += symtab->sh.sh_entsize; - symtab->changed = true; + mark_sec_changed(elf, symtab, true); if (symtab_shndx) { symtab_shndx->sh.sh_size += sizeof(Elf32_Word); - symtab_shndx->changed = true; + mark_sec_changed(elf, symtab_shndx, true); } return sym; @@ -841,13 +847,57 @@ elf_create_prefix_symbol(struct elf *elf, struct symbol *orig, long size) return sym; } -int elf_add_reloc_to_insn(struct elf *elf, struct section *sec, - unsigned long offset, unsigned int type, - struct section *insn_sec, unsigned long insn_off) +static struct reloc *elf_init_reloc(struct elf *elf, struct section *rsec, + unsigned int reloc_idx, + unsigned long offset, struct symbol *sym, + s64 addend, unsigned int type) +{ + struct reloc *reloc, empty = { 0 }; + + if (reloc_idx >= sec_num_entries(rsec)) { + WARN("%s: bad reloc_idx %u for %s with %d relocs", + __func__, reloc_idx, rsec->name, sec_num_entries(rsec)); + return NULL; + } + + reloc = &rsec->relocs[reloc_idx]; + + if (memcmp(reloc, &empty, sizeof(empty))) { + WARN("%s: %s: reloc %d already initialized!", + __func__, rsec->name, reloc_idx); + return NULL; + } + + reloc->sec = rsec; + reloc->sym = sym; + + set_reloc_offset(elf, reloc, offset); + set_reloc_sym(elf, reloc, sym->idx); + set_reloc_type(elf, reloc, type); + set_reloc_addend(elf, reloc, addend); + + elf_hash_add(reloc, &reloc->hash, reloc_hash(reloc)); + reloc->sym_next_reloc = sym->relocs; + sym->relocs = reloc; + + return reloc; +} + +struct reloc *elf_init_reloc_text_sym(struct elf *elf, struct section *sec, + unsigned long offset, + unsigned int reloc_idx, + struct section *insn_sec, + unsigned long insn_off) { struct symbol *sym = insn_sec->sym; int addend = insn_off; + if (!(insn_sec->sh.sh_flags & SHF_EXECINSTR)) { + WARN("bad call to %s() for data symbol %s", + __func__, sym->name); + return NULL; + } + if (!sym) { /* * Due to how weak functions work, we must use section based @@ -857,108 +907,86 @@ int elf_add_reloc_to_insn(struct elf *elf, struct section *sec, */ sym = elf_create_section_symbol(elf, insn_sec); if (!sym) - return -1; + return NULL; insn_sec->sym = sym; } - return elf_add_reloc(elf, sec, offset, type, sym, addend); + return elf_init_reloc(elf, sec->rsec, reloc_idx, offset, sym, addend, + elf_text_rela_type(elf)); } -static int read_rel_reloc(struct section *sec, int i, struct reloc *reloc, unsigned int *symndx) +struct reloc *elf_init_reloc_data_sym(struct elf *elf, struct section *sec, + unsigned long offset, + unsigned int reloc_idx, + struct symbol *sym, + s64 addend) { - if (!gelf_getrel(sec->data, i, &reloc->rel)) { - WARN_ELF("gelf_getrel"); - return -1; + if (sym->sec && (sec->sh.sh_flags & SHF_EXECINSTR)) { + WARN("bad call to %s() for text symbol %s", + __func__, sym->name); + return NULL; } - reloc->type = GELF_R_TYPE(reloc->rel.r_info); - reloc->addend = 0; - reloc->offset = reloc->rel.r_offset; - *symndx = GELF_R_SYM(reloc->rel.r_info); - return 0; -} -static int read_rela_reloc(struct section *sec, int i, struct reloc *reloc, unsigned int *symndx) -{ - if (!gelf_getrela(sec->data, i, &reloc->rela)) { - WARN_ELF("gelf_getrela"); - return -1; - } - reloc->type = GELF_R_TYPE(reloc->rela.r_info); - reloc->addend = reloc->rela.r_addend; - reloc->offset = reloc->rela.r_offset; - *symndx = GELF_R_SYM(reloc->rela.r_info); - return 0; + return elf_init_reloc(elf, sec->rsec, reloc_idx, offset, sym, addend, + elf_data_rela_type(elf)); } static int read_relocs(struct elf *elf) { - unsigned long nr_reloc, max_reloc = 0, tot_reloc = 0; - struct section *sec; + unsigned long nr_reloc, max_reloc = 0; + struct section *rsec; struct reloc *reloc; unsigned int symndx; struct symbol *sym; int i; - if (!elf_alloc_hash(reloc, elf->text_size / 16)) + if (!elf_alloc_hash(reloc, elf->num_relocs)) return -1; - list_for_each_entry(sec, &elf->sections, list) { - if ((sec->sh.sh_type != SHT_RELA) && - (sec->sh.sh_type != SHT_REL)) + list_for_each_entry(rsec, &elf->sections, list) { + if (!is_reloc_sec(rsec)) continue; - sec->base = find_section_by_index(elf, sec->sh.sh_info); - if (!sec->base) { + rsec->base = find_section_by_index(elf, rsec->sh.sh_info); + if (!rsec->base) { WARN("can't find base section for reloc section %s", - sec->name); + rsec->name); return -1; } - sec->base->reloc = sec; + rsec->base->rsec = rsec; nr_reloc = 0; - sec->reloc_data = calloc(sec->sh.sh_size / sec->sh.sh_entsize, sizeof(*reloc)); - if (!sec->reloc_data) { + rsec->relocs = calloc(sec_num_entries(rsec), sizeof(*reloc)); + if (!rsec->relocs) { perror("calloc"); return -1; } - for (i = 0; i < sec->sh.sh_size / sec->sh.sh_entsize; i++) { - reloc = &sec->reloc_data[i]; - switch (sec->sh.sh_type) { - case SHT_REL: - if (read_rel_reloc(sec, i, reloc, &symndx)) - return -1; - break; - case SHT_RELA: - if (read_rela_reloc(sec, i, reloc, &symndx)) - return -1; - break; - default: return -1; - } + for (i = 0; i < sec_num_entries(rsec); i++) { + reloc = &rsec->relocs[i]; - reloc->sec = sec; - reloc->idx = i; + reloc->sec = rsec; + symndx = reloc_sym(reloc); reloc->sym = sym = find_symbol_by_index(elf, symndx); if (!reloc->sym) { WARN("can't find reloc entry symbol %d for %s", - symndx, sec->name); + symndx, rsec->name); return -1; } - list_add_tail(&reloc->sym_reloc_entry, &sym->reloc_list); - list_add_tail(&reloc->list, &sec->reloc_list); elf_hash_add(reloc, &reloc->hash, reloc_hash(reloc)); + reloc->sym_next_reloc = sym->relocs; + sym->relocs = reloc; nr_reloc++; } max_reloc = max(max_reloc, nr_reloc); - tot_reloc += nr_reloc; } if (opts.stats) { printf("max_reloc: %lu\n", max_reloc); - printf("tot_reloc: %lu\n", tot_reloc); + printf("num_relocs: %lu\n", elf->num_relocs); printf("reloc_bits: %d\n", elf->reloc_bits); } @@ -1053,13 +1081,14 @@ static int elf_add_string(struct elf *elf, struct section *strtab, char *str) len = strtab->sh.sh_size; strtab->sh.sh_size += data->d_size; - strtab->changed = true; + + mark_sec_changed(elf, strtab, true); return len; } struct section *elf_create_section(struct elf *elf, const char *name, - unsigned int sh_flags, size_t entsize, int nr) + size_t entsize, unsigned int nr) { struct section *sec, *shstrtab; size_t size = entsize * nr; @@ -1073,7 +1102,6 @@ struct section *elf_create_section(struct elf *elf, const char *name, memset(sec, 0, sizeof(*sec)); INIT_LIST_HEAD(&sec->symbol_list); - INIT_LIST_HEAD(&sec->reloc_list); s = elf_newscn(elf->elf); if (!s) { @@ -1088,7 +1116,6 @@ struct section *elf_create_section(struct elf *elf, const char *name, } sec->idx = elf_ndxscn(s); - sec->changed = true; sec->data = elf_newdata(s); if (!sec->data) { @@ -1117,7 +1144,7 @@ struct section *elf_create_section(struct elf *elf, const char *name, sec->sh.sh_entsize = entsize; sec->sh.sh_type = SHT_PROGBITS; sec->sh.sh_addralign = 1; - sec->sh.sh_flags = SHF_ALLOC | sh_flags; + sec->sh.sh_flags = SHF_ALLOC; /* Add section name to .shstrtab (or .strtab for Clang) */ shstrtab = find_section_by_name(elf, ".shstrtab"); @@ -1135,158 +1162,66 @@ struct section *elf_create_section(struct elf *elf, const char *name, elf_hash_add(section, &sec->hash, sec->idx); elf_hash_add(section_name, &sec->name_hash, str_hash(sec->name)); - elf->changed = true; + mark_sec_changed(elf, sec, true); return sec; } -static struct section *elf_create_rel_reloc_section(struct elf *elf, struct section *base) +static struct section *elf_create_rela_section(struct elf *elf, + struct section *sec, + unsigned int reloc_nr) { - char *relocname; - struct section *sec; + struct section *rsec; + char *rsec_name; - relocname = malloc(strlen(base->name) + strlen(".rel") + 1); - if (!relocname) { + rsec_name = malloc(strlen(sec->name) + strlen(".rela") + 1); + if (!rsec_name) { perror("malloc"); return NULL; } - strcpy(relocname, ".rel"); - strcat(relocname, base->name); + strcpy(rsec_name, ".rela"); + strcat(rsec_name, sec->name); - sec = elf_create_section(elf, relocname, 0, sizeof(GElf_Rel), 0); - free(relocname); - if (!sec) + rsec = elf_create_section(elf, rsec_name, elf_rela_size(elf), reloc_nr); + free(rsec_name); + if (!rsec) return NULL; - base->reloc = sec; - sec->base = base; + rsec->data->d_type = ELF_T_RELA; + rsec->sh.sh_type = SHT_RELA; + rsec->sh.sh_addralign = elf_addr_size(elf); + rsec->sh.sh_link = find_section_by_name(elf, ".symtab")->idx; + rsec->sh.sh_info = sec->idx; + rsec->sh.sh_flags = SHF_INFO_LINK; + + rsec->relocs = calloc(sec_num_entries(rsec), sizeof(struct reloc)); + if (!rsec->relocs) { + perror("calloc"); + return NULL; + } - sec->sh.sh_type = SHT_REL; - sec->sh.sh_addralign = 8; - sec->sh.sh_link = find_section_by_name(elf, ".symtab")->idx; - sec->sh.sh_info = base->idx; - sec->sh.sh_flags = SHF_INFO_LINK; + sec->rsec = rsec; + rsec->base = sec; - return sec; + return rsec; } -static struct section *elf_create_rela_reloc_section(struct elf *elf, struct section *base) +struct section *elf_create_section_pair(struct elf *elf, const char *name, + size_t entsize, unsigned int nr, + unsigned int reloc_nr) { - char *relocname; struct section *sec; - int addrsize = elf_class_addrsize(elf); - - relocname = malloc(strlen(base->name) + strlen(".rela") + 1); - if (!relocname) { - perror("malloc"); - return NULL; - } - strcpy(relocname, ".rela"); - strcat(relocname, base->name); - if (addrsize == sizeof(u32)) - sec = elf_create_section(elf, relocname, 0, sizeof(Elf32_Rela), 0); - else - sec = elf_create_section(elf, relocname, 0, sizeof(GElf_Rela), 0); - free(relocname); + sec = elf_create_section(elf, name, entsize, nr); if (!sec) return NULL; - base->reloc = sec; - sec->base = base; - - sec->sh.sh_type = SHT_RELA; - sec->sh.sh_addralign = addrsize; - sec->sh.sh_link = find_section_by_name(elf, ".symtab")->idx; - sec->sh.sh_info = base->idx; - sec->sh.sh_flags = SHF_INFO_LINK; + if (!elf_create_rela_section(elf, sec, reloc_nr)) + return NULL; return sec; } -static struct section *elf_create_reloc_section(struct elf *elf, - struct section *base, - int reltype) -{ - switch (reltype) { - case SHT_REL: return elf_create_rel_reloc_section(elf, base); - case SHT_RELA: return elf_create_rela_reloc_section(elf, base); - default: return NULL; - } -} - -static int elf_rebuild_rel_reloc_section(struct section *sec) -{ - struct reloc *reloc; - int idx = 0; - void *buf; - - /* Allocate a buffer for relocations */ - buf = malloc(sec->sh.sh_size); - if (!buf) { - perror("malloc"); - return -1; - } - - sec->data->d_buf = buf; - sec->data->d_size = sec->sh.sh_size; - sec->data->d_type = ELF_T_REL; - - idx = 0; - list_for_each_entry(reloc, &sec->reloc_list, list) { - reloc->rel.r_offset = reloc->offset; - reloc->rel.r_info = GELF_R_INFO(reloc->sym->idx, reloc->type); - if (!gelf_update_rel(sec->data, idx, &reloc->rel)) { - WARN_ELF("gelf_update_rel"); - return -1; - } - idx++; - } - - return 0; -} - -static int elf_rebuild_rela_reloc_section(struct section *sec) -{ - struct reloc *reloc; - int idx = 0; - void *buf; - - /* Allocate a buffer for relocations with addends */ - buf = malloc(sec->sh.sh_size); - if (!buf) { - perror("malloc"); - return -1; - } - - sec->data->d_buf = buf; - sec->data->d_size = sec->sh.sh_size; - sec->data->d_type = ELF_T_RELA; - - idx = 0; - list_for_each_entry(reloc, &sec->reloc_list, list) { - reloc->rela.r_offset = reloc->offset; - reloc->rela.r_addend = reloc->addend; - reloc->rela.r_info = GELF_R_INFO(reloc->sym->idx, reloc->type); - if (!gelf_update_rela(sec->data, idx, &reloc->rela)) { - WARN_ELF("gelf_update_rela"); - return -1; - } - idx++; - } - - return 0; -} - -static int elf_rebuild_reloc_section(struct elf *elf, struct section *sec) -{ - switch (sec->sh.sh_type) { - case SHT_REL: return elf_rebuild_rel_reloc_section(sec); - case SHT_RELA: return elf_rebuild_rela_reloc_section(sec); - default: return -1; - } -} - int elf_write_insn(struct elf *elf, struct section *sec, unsigned long offset, unsigned int len, const char *insn) @@ -1299,37 +1234,8 @@ int elf_write_insn(struct elf *elf, struct section *sec, } memcpy(data->d_buf + offset, insn, len); - elf_flagdata(data, ELF_C_SET, ELF_F_DIRTY); - elf->changed = true; - - return 0; -} - -int elf_write_reloc(struct elf *elf, struct reloc *reloc) -{ - struct section *sec = reloc->sec; - - if (sec->sh.sh_type == SHT_REL) { - reloc->rel.r_info = GELF_R_INFO(reloc->sym->idx, reloc->type); - reloc->rel.r_offset = reloc->offset; - - if (!gelf_update_rel(sec->data, reloc->idx, &reloc->rel)) { - WARN_ELF("gelf_update_rel"); - return -1; - } - } else { - reloc->rela.r_info = GELF_R_INFO(reloc->sym->idx, reloc->type); - reloc->rela.r_addend = reloc->addend; - reloc->rela.r_offset = reloc->offset; - - if (!gelf_update_rela(sec->data, reloc->idx, &reloc->rela)) { - WARN_ELF("gelf_update_rela"); - return -1; - } - } - - elf->changed = true; + mark_sec_changed(elf, sec, true); return 0; } @@ -1401,25 +1307,20 @@ int elf_write(struct elf *elf) if (sec->truncate) elf_truncate_section(elf, sec); - if (sec->changed) { + if (sec_changed(sec)) { s = elf_getscn(elf->elf, sec->idx); if (!s) { WARN_ELF("elf_getscn"); return -1; } + + /* Note this also flags the section dirty */ if (!gelf_update_shdr(s, &sec->sh)) { WARN_ELF("gelf_update_shdr"); return -1; } - if (sec->base && - elf_rebuild_reloc_section(elf, sec)) { - WARN("elf_rebuild_reloc_section"); - return -1; - } - - sec->changed = false; - elf->changed = true; + mark_sec_changed(elf, sec, false); } } @@ -1439,30 +1340,14 @@ int elf_write(struct elf *elf) void elf_close(struct elf *elf) { - struct section *sec, *tmpsec; - struct symbol *sym, *tmpsym; - struct reloc *reloc, *tmpreloc; - if (elf->elf) elf_end(elf->elf); if (elf->fd > 0) close(elf->fd); - list_for_each_entry_safe(sec, tmpsec, &elf->sections, list) { - list_for_each_entry_safe(sym, tmpsym, &sec->symbol_list, list) { - list_del(&sym->list); - hash_del(&sym->hash); - } - list_for_each_entry_safe(reloc, tmpreloc, &sec->reloc_list, list) { - list_del(&reloc->list); - hash_del(&reloc->hash); - } - list_del(&sec->list); - free(sec->reloc_data); - } - - free(elf->symbol_data); - free(elf->section_data); - free(elf); + /* + * NOTE: All remaining allocations are leaked on purpose. Objtool is + * about to exit anyway. + */ } diff --git a/tools/objtool/include/objtool/builtin.h b/tools/objtool/include/objtool/builtin.h index 2a108e648b7a..fcca6662c8b4 100644 --- a/tools/objtool/include/objtool/builtin.h +++ b/tools/objtool/include/objtool/builtin.h @@ -37,6 +37,7 @@ struct opts { bool no_unreachable; bool sec_address; bool stats; + bool verbose; }; extern struct opts opts; diff --git a/tools/objtool/include/objtool/cfi.h b/tools/objtool/include/objtool/cfi.h index b1258e79a1b7..c8a6bec4f6b9 100644 --- a/tools/objtool/include/objtool/cfi.h +++ b/tools/objtool/include/objtool/cfi.h @@ -36,6 +36,7 @@ struct cfi_state { bool drap; bool signal; bool end; + bool force_undefined; }; #endif /* _OBJTOOL_CFI_H */ diff --git a/tools/objtool/include/objtool/elf.h b/tools/objtool/include/objtool/elf.h index e1ca588eb69d..c532d70864dc 100644 --- a/tools/objtool/include/objtool/elf.h +++ b/tools/objtool/include/objtool/elf.h @@ -12,6 +12,7 @@ #include <linux/hashtable.h> #include <linux/rbtree.h> #include <linux/jhash.h> +#include <arch/elf.h> #ifdef LIBELF_USE_DEPRECATED # define elf_getshdrnum elf_getshnum @@ -25,28 +26,31 @@ #define ELF_C_READ_MMAP ELF_C_READ #endif +struct elf_hash_node { + struct elf_hash_node *next; +}; + struct section { struct list_head list; - struct hlist_node hash; - struct hlist_node name_hash; + struct elf_hash_node hash; + struct elf_hash_node name_hash; GElf_Shdr sh; struct rb_root_cached symbol_tree; struct list_head symbol_list; - struct list_head reloc_list; - struct section *base, *reloc; + struct section *base, *rsec; struct symbol *sym; Elf_Data *data; char *name; int idx; - bool changed, text, rodata, noinstr, init, truncate; - struct reloc *reloc_data; + bool _changed, text, rodata, noinstr, init, truncate; + struct reloc *relocs; }; struct symbol { struct list_head list; struct rb_node node; - struct hlist_node hash; - struct hlist_node name_hash; + struct elf_hash_node hash; + struct elf_hash_node name_hash; GElf_Sym sym; struct section *sec; char *name; @@ -61,37 +65,27 @@ struct symbol { u8 return_thunk : 1; u8 fentry : 1; u8 profiling_func : 1; + u8 warned : 1; struct list_head pv_target; - struct list_head reloc_list; + struct reloc *relocs; }; struct reloc { - struct list_head list; - struct hlist_node hash; - union { - GElf_Rela rela; - GElf_Rel rel; - }; + struct elf_hash_node hash; struct section *sec; struct symbol *sym; - struct list_head sym_reloc_entry; - unsigned long offset; - unsigned int type; - s64 addend; - int idx; - bool jump_table_start; + struct reloc *sym_next_reloc; }; -#define ELF_HASH_BITS 20 - struct elf { Elf *elf; GElf_Ehdr ehdr; int fd; bool changed; char *name; - unsigned int text_size, num_files; + unsigned int num_files; struct list_head sections; + unsigned long num_relocs; int symbol_bits; int symbol_name_bits; @@ -99,44 +93,54 @@ struct elf { int section_name_bits; int reloc_bits; - struct hlist_head *symbol_hash; - struct hlist_head *symbol_name_hash; - struct hlist_head *section_hash; - struct hlist_head *section_name_hash; - struct hlist_head *reloc_hash; + struct elf_hash_node **symbol_hash; + struct elf_hash_node **symbol_name_hash; + struct elf_hash_node **section_hash; + struct elf_hash_node **section_name_hash; + struct elf_hash_node **reloc_hash; struct section *section_data; struct symbol *symbol_data; }; -#define OFFSET_STRIDE_BITS 4 -#define OFFSET_STRIDE (1UL << OFFSET_STRIDE_BITS) -#define OFFSET_STRIDE_MASK (~(OFFSET_STRIDE - 1)) - -#define for_offset_range(_offset, _start, _end) \ - for (_offset = ((_start) & OFFSET_STRIDE_MASK); \ - _offset >= ((_start) & OFFSET_STRIDE_MASK) && \ - _offset <= ((_end) & OFFSET_STRIDE_MASK); \ - _offset += OFFSET_STRIDE) +struct elf *elf_open_read(const char *name, int flags); -static inline u32 sec_offset_hash(struct section *sec, unsigned long offset) -{ - u32 ol, oh, idx = sec->idx; +struct section *elf_create_section(struct elf *elf, const char *name, + size_t entsize, unsigned int nr); +struct section *elf_create_section_pair(struct elf *elf, const char *name, + size_t entsize, unsigned int nr, + unsigned int reloc_nr); - offset &= OFFSET_STRIDE_MASK; +struct symbol *elf_create_prefix_symbol(struct elf *elf, struct symbol *orig, long size); - ol = offset; - oh = (offset >> 16) >> 16; +struct reloc *elf_init_reloc_text_sym(struct elf *elf, struct section *sec, + unsigned long offset, + unsigned int reloc_idx, + struct section *insn_sec, + unsigned long insn_off); - __jhash_mix(ol, oh, idx); +struct reloc *elf_init_reloc_data_sym(struct elf *elf, struct section *sec, + unsigned long offset, + unsigned int reloc_idx, + struct symbol *sym, + s64 addend); - return ol; -} +int elf_write_insn(struct elf *elf, struct section *sec, + unsigned long offset, unsigned int len, + const char *insn); +int elf_write(struct elf *elf); +void elf_close(struct elf *elf); -static inline u32 reloc_hash(struct reloc *reloc) -{ - return sec_offset_hash(reloc->sec, reloc->offset); -} +struct section *find_section_by_name(const struct elf *elf, const char *name); +struct symbol *find_func_by_offset(struct section *sec, unsigned long offset); +struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset); +struct symbol *find_symbol_by_name(const struct elf *elf, const char *name); +struct symbol *find_symbol_containing(const struct section *sec, unsigned long offset); +int find_symbol_hole_containing(const struct section *sec, unsigned long offset); +struct reloc *find_reloc_by_dest(const struct elf *elf, struct section *sec, unsigned long offset); +struct reloc *find_reloc_by_dest_range(const struct elf *elf, struct section *sec, + unsigned long offset, unsigned int len); +struct symbol *find_func_containing(struct section *sec, unsigned long offset); /* * Try to see if it's a whole archive (vmlinux.o or module). @@ -148,42 +152,147 @@ static inline bool has_multiple_files(struct elf *elf) return elf->num_files > 1; } -static inline int elf_class_addrsize(struct elf *elf) +static inline size_t elf_addr_size(struct elf *elf) { - if (elf->ehdr.e_ident[EI_CLASS] == ELFCLASS32) - return sizeof(u32); - else - return sizeof(u64); + return elf->ehdr.e_ident[EI_CLASS] == ELFCLASS32 ? 4 : 8; } -struct elf *elf_open_read(const char *name, int flags); -struct section *elf_create_section(struct elf *elf, const char *name, unsigned int sh_flags, size_t entsize, int nr); +static inline size_t elf_rela_size(struct elf *elf) +{ + return elf_addr_size(elf) == 4 ? sizeof(Elf32_Rela) : sizeof(Elf64_Rela); +} -struct symbol *elf_create_prefix_symbol(struct elf *elf, struct symbol *orig, long size); +static inline unsigned int elf_data_rela_type(struct elf *elf) +{ + return elf_addr_size(elf) == 4 ? R_DATA32 : R_DATA64; +} -int elf_add_reloc(struct elf *elf, struct section *sec, unsigned long offset, - unsigned int type, struct symbol *sym, s64 addend); -int elf_add_reloc_to_insn(struct elf *elf, struct section *sec, - unsigned long offset, unsigned int type, - struct section *insn_sec, unsigned long insn_off); +static inline unsigned int elf_text_rela_type(struct elf *elf) +{ + return elf_addr_size(elf) == 4 ? R_TEXT32 : R_TEXT64; +} -int elf_write_insn(struct elf *elf, struct section *sec, - unsigned long offset, unsigned int len, - const char *insn); -int elf_write_reloc(struct elf *elf, struct reloc *reloc); -int elf_write(struct elf *elf); -void elf_close(struct elf *elf); +static inline bool is_reloc_sec(struct section *sec) +{ + return sec->sh.sh_type == SHT_RELA || sec->sh.sh_type == SHT_REL; +} -struct section *find_section_by_name(const struct elf *elf, const char *name); -struct symbol *find_func_by_offset(struct section *sec, unsigned long offset); -struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset); -struct symbol *find_symbol_by_name(const struct elf *elf, const char *name); -struct symbol *find_symbol_containing(const struct section *sec, unsigned long offset); -int find_symbol_hole_containing(const struct section *sec, unsigned long offset); -struct reloc *find_reloc_by_dest(const struct elf *elf, struct section *sec, unsigned long offset); -struct reloc *find_reloc_by_dest_range(const struct elf *elf, struct section *sec, - unsigned long offset, unsigned int len); -struct symbol *find_func_containing(struct section *sec, unsigned long offset); +static inline bool sec_changed(struct section *sec) +{ + return sec->_changed; +} + +static inline void mark_sec_changed(struct elf *elf, struct section *sec, + bool changed) +{ + sec->_changed = changed; + elf->changed |= changed; +} + +static inline unsigned int sec_num_entries(struct section *sec) +{ + return sec->sh.sh_size / sec->sh.sh_entsize; +} + +static inline unsigned int reloc_idx(struct reloc *reloc) +{ + return reloc - reloc->sec->relocs; +} + +static inline void *reloc_rel(struct reloc *reloc) +{ + struct section *rsec = reloc->sec; + + return rsec->data->d_buf + (reloc_idx(reloc) * rsec->sh.sh_entsize); +} + +static inline bool is_32bit_reloc(struct reloc *reloc) +{ + /* + * Elf32_Rel: 8 bytes + * Elf32_Rela: 12 bytes + * Elf64_Rel: 16 bytes + * Elf64_Rela: 24 bytes + */ + return reloc->sec->sh.sh_entsize < 16; +} + +#define __get_reloc_field(reloc, field) \ +({ \ + is_32bit_reloc(reloc) ? \ + ((Elf32_Rela *)reloc_rel(reloc))->field : \ + ((Elf64_Rela *)reloc_rel(reloc))->field; \ +}) + +#define __set_reloc_field(reloc, field, val) \ +({ \ + if (is_32bit_reloc(reloc)) \ + ((Elf32_Rela *)reloc_rel(reloc))->field = val; \ + else \ + ((Elf64_Rela *)reloc_rel(reloc))->field = val; \ +}) + +static inline u64 reloc_offset(struct reloc *reloc) +{ + return __get_reloc_field(reloc, r_offset); +} + +static inline void set_reloc_offset(struct elf *elf, struct reloc *reloc, u64 offset) +{ + __set_reloc_field(reloc, r_offset, offset); + mark_sec_changed(elf, reloc->sec, true); +} + +static inline s64 reloc_addend(struct reloc *reloc) +{ + return __get_reloc_field(reloc, r_addend); +} + +static inline void set_reloc_addend(struct elf *elf, struct reloc *reloc, s64 addend) +{ + __set_reloc_field(reloc, r_addend, addend); + mark_sec_changed(elf, reloc->sec, true); +} + + +static inline unsigned int reloc_sym(struct reloc *reloc) +{ + u64 info = __get_reloc_field(reloc, r_info); + + return is_32bit_reloc(reloc) ? + ELF32_R_SYM(info) : + ELF64_R_SYM(info); +} + +static inline unsigned int reloc_type(struct reloc *reloc) +{ + u64 info = __get_reloc_field(reloc, r_info); + + return is_32bit_reloc(reloc) ? + ELF32_R_TYPE(info) : + ELF64_R_TYPE(info); +} + +static inline void set_reloc_sym(struct elf *elf, struct reloc *reloc, unsigned int sym) +{ + u64 info = is_32bit_reloc(reloc) ? + ELF32_R_INFO(sym, reloc_type(reloc)) : + ELF64_R_INFO(sym, reloc_type(reloc)); + + __set_reloc_field(reloc, r_info, info); + + mark_sec_changed(elf, reloc->sec, true); +} +static inline void set_reloc_type(struct elf *elf, struct reloc *reloc, unsigned int type) +{ + u64 info = is_32bit_reloc(reloc) ? + ELF32_R_INFO(reloc_sym(reloc), type) : + ELF64_R_INFO(reloc_sym(reloc), type); + + __set_reloc_field(reloc, r_info, info); + + mark_sec_changed(elf, reloc->sec, true); +} #define for_each_sec(file, sec) \ list_for_each_entry(sec, &file->elf->sections, list) @@ -197,4 +306,44 @@ struct symbol *find_func_containing(struct section *sec, unsigned long offset); for_each_sec(file, __sec) \ sec_for_each_sym(__sec, sym) +#define for_each_reloc(rsec, reloc) \ + for (int __i = 0, __fake = 1; __fake; __fake = 0) \ + for (reloc = rsec->relocs; \ + __i < sec_num_entries(rsec); \ + __i++, reloc++) + +#define for_each_reloc_from(rsec, reloc) \ + for (int __i = reloc_idx(reloc); \ + __i < sec_num_entries(rsec); \ + __i++, reloc++) + +#define OFFSET_STRIDE_BITS 4 +#define OFFSET_STRIDE (1UL << OFFSET_STRIDE_BITS) +#define OFFSET_STRIDE_MASK (~(OFFSET_STRIDE - 1)) + +#define for_offset_range(_offset, _start, _end) \ + for (_offset = ((_start) & OFFSET_STRIDE_MASK); \ + _offset >= ((_start) & OFFSET_STRIDE_MASK) && \ + _offset <= ((_end) & OFFSET_STRIDE_MASK); \ + _offset += OFFSET_STRIDE) + +static inline u32 sec_offset_hash(struct section *sec, unsigned long offset) +{ + u32 ol, oh, idx = sec->idx; + + offset &= OFFSET_STRIDE_MASK; + + ol = offset; + oh = (offset >> 16) >> 16; + + __jhash_mix(ol, oh, idx); + + return ol; +} + +static inline u32 reloc_hash(struct reloc *reloc) +{ + return sec_offset_hash(reloc->sec, reloc_offset(reloc)); +} + #endif /* _OBJTOOL_ELF_H */ diff --git a/tools/objtool/include/objtool/warn.h b/tools/objtool/include/objtool/warn.h index b1c920dc9516..ac04d3fe4dd9 100644 --- a/tools/objtool/include/objtool/warn.h +++ b/tools/objtool/include/objtool/warn.h @@ -55,15 +55,22 @@ static inline char *offstr(struct section *sec, unsigned long offset) #define WARN_INSN(insn, format, ...) \ ({ \ - WARN_FUNC(format, insn->sec, insn->offset, ##__VA_ARGS__); \ + struct instruction *_insn = (insn); \ + if (!_insn->sym || !_insn->sym->warned) \ + WARN_FUNC(format, _insn->sec, _insn->offset, \ + ##__VA_ARGS__); \ + if (_insn->sym) \ + _insn->sym->warned = 1; \ }) -#define BT_FUNC(format, insn, ...) \ -({ \ - struct instruction *_insn = (insn); \ - char *_str = offstr(_insn->sec, _insn->offset); \ - WARN(" %s: " format, _str, ##__VA_ARGS__); \ - free(_str); \ +#define BT_INSN(insn, format, ...) \ +({ \ + if (opts.verbose || opts.backtrace) { \ + struct instruction *_insn = (insn); \ + char *_str = offstr(_insn->sec, _insn->offset); \ + WARN(" %s: " format, _str, ##__VA_ARGS__); \ + free(_str); \ + } \ }) #define WARN_ELF(format, ...) \ diff --git a/tools/objtool/noreturns.h b/tools/objtool/noreturns.h new file mode 100644 index 000000000000..1514e84d5cc4 --- /dev/null +++ b/tools/objtool/noreturns.h @@ -0,0 +1,46 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * This is a (sorted!) list of all known __noreturn functions in the kernel. + * It's needed for objtool to properly reverse-engineer the control flow graph. + * + * Yes, this is unfortunate. A better solution is in the works. + */ +NORETURN(__invalid_creds) +NORETURN(__kunit_abort) +NORETURN(__module_put_and_kthread_exit) +NORETURN(__reiserfs_panic) +NORETURN(__stack_chk_fail) +NORETURN(__ubsan_handle_builtin_unreachable) +NORETURN(arch_call_rest_init) +NORETURN(arch_cpu_idle_dead) +NORETURN(btrfs_assertfail) +NORETURN(cpu_bringup_and_idle) +NORETURN(cpu_startup_entry) +NORETURN(do_exit) +NORETURN(do_group_exit) +NORETURN(do_task_dead) +NORETURN(ex_handler_msr_mce) +NORETURN(fortify_panic) +NORETURN(hlt_play_dead) +NORETURN(hv_ghcb_terminate) +NORETURN(kthread_complete_and_exit) +NORETURN(kthread_exit) +NORETURN(kunit_try_catch_throw) +NORETURN(machine_real_restart) +NORETURN(make_task_dead) +NORETURN(mpt_halt_firmware) +NORETURN(nmi_panic_self_stop) +NORETURN(panic) +NORETURN(panic_smp_self_stop) +NORETURN(rest_init) +NORETURN(rewind_stack_and_make_dead) +NORETURN(sev_es_terminate) +NORETURN(snp_abort) +NORETURN(start_kernel) +NORETURN(stop_this_cpu) +NORETURN(usercopy_abort) +NORETURN(x86_64_start_kernel) +NORETURN(x86_64_start_reservations) +NORETURN(xen_cpu_bringup_again) +NORETURN(xen_start_kernel) diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c index 48efd1e2f00d..bae343908867 100644 --- a/tools/objtool/orc_gen.c +++ b/tools/objtool/orc_gen.c @@ -118,8 +118,8 @@ static int write_orc_entry(struct elf *elf, struct section *orc_sec, orc->bp_offset = bswap_if_needed(elf, orc->bp_offset); /* populate reloc for ip */ - if (elf_add_reloc_to_insn(elf, ip_sec, idx * sizeof(int), R_X86_64_PC32, - insn_sec, insn_off)) + if (!elf_init_reloc_text_sym(elf, ip_sec, idx * sizeof(int), idx, + insn_sec, insn_off)) return -1; return 0; @@ -237,12 +237,12 @@ int orc_create(struct objtool_file *file) WARN("file already has .orc_unwind section, skipping"); return -1; } - orc_sec = elf_create_section(file->elf, ".orc_unwind", 0, + orc_sec = elf_create_section(file->elf, ".orc_unwind", sizeof(struct orc_entry), nr); if (!orc_sec) return -1; - sec = elf_create_section(file->elf, ".orc_unwind_ip", 0, sizeof(int), nr); + sec = elf_create_section_pair(file->elf, ".orc_unwind_ip", sizeof(int), nr, nr); if (!sec) return -1; diff --git a/tools/objtool/special.c b/tools/objtool/special.c index baa85c31526b..91b1950f5bd8 100644 --- a/tools/objtool/special.c +++ b/tools/objtool/special.c @@ -62,7 +62,7 @@ static void reloc_to_sec_off(struct reloc *reloc, struct section **sec, unsigned long *off) { *sec = reloc->sym->sec; - *off = reloc->sym->offset + reloc->addend; + *off = reloc->sym->offset + reloc_addend(reloc); } static int get_alt_entry(struct elf *elf, const struct special_entry *entry, @@ -126,7 +126,7 @@ static int get_alt_entry(struct elf *elf, const struct special_entry *entry, sec, offset + entry->key); return -1; } - alt->key_addend = key_reloc->addend; + alt->key_addend = reloc_addend(key_reloc); } return 0; diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 4884520f954f..a794d9eca93d 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -216,6 +216,12 @@ ifeq ($(call get-executable,$(BISON)),) dummy := $(error Error: $(BISON) is missing on this system, please install it) endif +ifeq ($(BUILD_BPF_SKEL),1) + ifeq ($(call get-executable,$(CLANG)),) + dummy := $(error $(CLANG) is missing on this system, please install it to be able to build with BUILD_BPF_SKEL=1) + endif +endif + ifneq ($(OUTPUT),) ifeq ($(shell expr $(shell $(BISON) --version | grep bison | sed -e 's/.\+ \([0-9]\+\).\([0-9]\+\).\([0-9]\+\)/\1\2\3/g') \>\= 371), 1) BISON_FILE_PREFIX_MAP := --file-prefix-map=$(OUTPUT)= @@ -921,6 +927,7 @@ ifndef NO_DEMANGLE EXTLIBS += -lstdc++ CFLAGS += -DHAVE_CXA_DEMANGLE_SUPPORT CXXFLAGS += -DHAVE_CXA_DEMANGLE_SUPPORT + $(call detected,CONFIG_CXX_DEMANGLE) endif ifdef BUILD_NONDISTRO ifeq ($(filter -liberty,$(EXTLIBS)),) diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index a42a6a99c2bc..f48794816d82 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -181,7 +181,6 @@ HOSTCC ?= gcc HOSTLD ?= ld HOSTAR ?= ar CLANG ?= clang -LLVM_STRIP ?= llvm-strip PKG_CONFIG = $(CROSS_COMPILE)pkg-config @@ -1057,15 +1056,33 @@ $(SKEL_TMP_OUT) $(LIBAPI_OUTPUT) $(LIBBPF_OUTPUT) $(LIBPERF_OUTPUT) $(LIBSUBCMD_ ifdef BUILD_BPF_SKEL BPFTOOL := $(SKEL_TMP_OUT)/bootstrap/bpftool -BPF_INCLUDE := -I$(SKEL_TMP_OUT)/.. -I$(LIBBPF_INCLUDE) +# Get Clang's default includes on this system, as opposed to those seen by +# '-target bpf'. This fixes "missing" files on some architectures/distros, +# such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc. +# +# Use '-idirafter': Don't interfere with include mechanics except where the +# build would have failed anyways. +define get_sys_includes +$(shell $(1) $(2) -v -E - </dev/null 2>&1 \ + | sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') \ +$(shell $(1) $(2) -dM -E - </dev/null | grep '__riscv_xlen ' | awk '{printf("-D__riscv_xlen=%d -D__BITS_PER_LONG=%d", $$3, $$3)}') +endef + +ifneq ($(CROSS_COMPILE),) +CLANG_TARGET_ARCH = --target=$(notdir $(CROSS_COMPILE:%-=%)) +endif + +CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG),$(CLANG_TARGET_ARCH)) +BPF_INCLUDE := -I$(SKEL_TMP_OUT)/.. -I$(LIBBPF_INCLUDE) $(CLANG_SYS_INCLUDES) +TOOLS_UAPI_INCLUDE := -I$(srctree)/tools/include/uapi $(BPFTOOL): | $(SKEL_TMP_OUT) $(Q)CFLAGS= $(MAKE) -C ../bpf/bpftool \ OUTPUT=$(SKEL_TMP_OUT)/ bootstrap $(SKEL_TMP_OUT)/%.bpf.o: util/bpf_skel/%.bpf.c $(LIBBPF) | $(SKEL_TMP_OUT) - $(QUIET_CLANG)$(CLANG) -g -O2 -target bpf -Wall -Werror $(BPF_INCLUDE) \ - -c $(filter util/bpf_skel/%.bpf.c,$^) -o $@ && $(LLVM_STRIP) -g $@ + $(QUIET_CLANG)$(CLANG) -g -O2 -target bpf -Wall -Werror $(BPF_INCLUDE) $(TOOLS_UAPI_INCLUDE) \ + -c $(filter util/bpf_skel/%.bpf.c,$^) -o $@ $(SKEL_OUT)/%.skel.h: $(SKEL_TMP_OUT)/%.bpf.o | $(BPFTOOL) $(QUIET_GENSKEL)$(BPFTOOL) gen skeleton $< > $@ diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index 77cb03e6ff87..9ca040bfb1aa 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -78,9 +78,9 @@ static int cs_etm_validate_context_id(struct auxtrace_record *itr, char path[PATH_MAX]; int err; u32 val; - u64 contextid = - evsel->core.attr.config & - (perf_pmu__format_bits(&cs_etm_pmu->format, "contextid1") | + u64 contextid = evsel->core.attr.config & + (perf_pmu__format_bits(&cs_etm_pmu->format, "contextid") | + perf_pmu__format_bits(&cs_etm_pmu->format, "contextid1") | perf_pmu__format_bits(&cs_etm_pmu->format, "contextid2")); if (!contextid) @@ -114,8 +114,7 @@ static int cs_etm_validate_context_id(struct auxtrace_record *itr, * 0b00100 Maximum of 32-bit Context ID size. * All other values are reserved. */ - val = BMVAL(val, 5, 9); - if (!val || val != 0x4) { + if (BMVAL(val, 5, 9) != 0x4) { pr_err("%s: CONTEXTIDR_EL1 isn't supported, disable with %s/contextid1=0/\n", CORESIGHT_ETM_PMU_NAME, CORESIGHT_ETM_PMU_NAME); return -EINVAL; diff --git a/tools/perf/arch/arm/util/pmu.c b/tools/perf/arch/arm/util/pmu.c index 860a8b42b4b5..a9623b128ece 100644 --- a/tools/perf/arch/arm/util/pmu.c +++ b/tools/perf/arch/arm/util/pmu.c @@ -12,7 +12,7 @@ #include "arm-spe.h" #include "hisi-ptt.h" #include "../../../util/pmu.h" -#include "../cs-etm.h" +#include "../../../util/cs-etm.h" struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused) diff --git a/tools/perf/arch/arm64/util/header.c b/tools/perf/arch/arm64/util/header.c index d730666ab95d..80b9f6287fe2 100644 --- a/tools/perf/arch/arm64/util/header.c +++ b/tools/perf/arch/arm64/util/header.c @@ -29,8 +29,8 @@ static int _get_cpuid(char *buf, size_t sz, struct perf_cpu_map *cpus) char path[PATH_MAX]; FILE *file; - scnprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d"MIDR, - sysfs, cpus->map[cpu]); + scnprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d" MIDR, + sysfs, RC_CHK_ACCESS(cpus)->map[cpu].cpu); file = fopen(path, "r"); if (!file) { diff --git a/tools/perf/arch/arm64/util/pmu.c b/tools/perf/arch/arm64/util/pmu.c index fa143acb4c8d..ef1ed645097c 100644 --- a/tools/perf/arch/arm64/util/pmu.c +++ b/tools/perf/arch/arm64/util/pmu.c @@ -18,7 +18,7 @@ static struct perf_pmu *pmu__find_core_pmu(void) * The cpumap should cover all CPUs. Otherwise, some CPUs may * not support some events or have different event IDs. */ - if (pmu->cpus->nr != cpu__max_cpu().cpu) + if (RC_CHK_ACCESS(pmu->cpus)->nr != cpu__max_cpu().cpu) return NULL; return pmu; diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl index 799147658dee..b68f47541169 100644 --- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -449,7 +449,7 @@ 444 common landlock_create_ruleset sys_landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self sys_landlock_restrict_self -# 447 reserved for memfd_secret +447 common memfd_secret sys_memfd_secret sys_memfd_secret 448 common process_mrelease sys_process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/tools/perf/arch/x86/include/arch-tests.h b/tools/perf/arch/x86/include/arch-tests.h index 902e9ea9b99e..93d3b8877baa 100644 --- a/tools/perf/arch/x86/include/arch-tests.h +++ b/tools/perf/arch/x86/include/arch-tests.h @@ -11,6 +11,7 @@ int test__intel_pt_pkt_decoder(struct test_suite *test, int subtest); int test__intel_pt_hybrid_compat(struct test_suite *test, int subtest); int test__bp_modify(struct test_suite *test, int subtest); int test__x86_sample_parsing(struct test_suite *test, int subtest); +int test__amd_ibs_via_core_pmu(struct test_suite *test, int subtest); extern struct test_suite *arch_tests[]; diff --git a/tools/perf/arch/x86/tests/Build b/tools/perf/arch/x86/tests/Build index 6f4e8636c3bf..fd02d8181718 100644 --- a/tools/perf/arch/x86/tests/Build +++ b/tools/perf/arch/x86/tests/Build @@ -5,3 +5,4 @@ perf-y += arch-tests.o perf-y += sample-parsing.o perf-$(CONFIG_AUXTRACE) += insn-x86.o intel-pt-test.o perf-$(CONFIG_X86_64) += bp-modify.o +perf-y += amd-ibs-via-core-pmu.o diff --git a/tools/perf/arch/x86/tests/amd-ibs-via-core-pmu.c b/tools/perf/arch/x86/tests/amd-ibs-via-core-pmu.c new file mode 100644 index 000000000000..2902798ca5c1 --- /dev/null +++ b/tools/perf/arch/x86/tests/amd-ibs-via-core-pmu.c @@ -0,0 +1,71 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "arch-tests.h" +#include "linux/perf_event.h" +#include "tests/tests.h" +#include "pmu.h" +#include "pmus.h" +#include "../perf-sys.h" +#include "debug.h" + +#define NR_SUB_TESTS 5 + +static struct sub_tests { + int type; + unsigned long config; + bool valid; +} sub_tests[NR_SUB_TESTS] = { + { PERF_TYPE_HARDWARE, PERF_COUNT_HW_CPU_CYCLES, true }, + { PERF_TYPE_HARDWARE, PERF_COUNT_HW_INSTRUCTIONS, false }, + { PERF_TYPE_RAW, 0x076, true }, + { PERF_TYPE_RAW, 0x0C1, true }, + { PERF_TYPE_RAW, 0x012, false }, +}; + +static int event_open(int type, unsigned long config) +{ + struct perf_event_attr attr; + + memset(&attr, 0, sizeof(struct perf_event_attr)); + attr.type = type; + attr.size = sizeof(struct perf_event_attr); + attr.config = config; + attr.disabled = 1; + attr.precise_ip = 1; + attr.sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_TID; + attr.sample_period = 100000; + + return sys_perf_event_open(&attr, -1, 0, -1, 0); +} + +int test__amd_ibs_via_core_pmu(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) +{ + struct perf_pmu *ibs_pmu; + int ret = TEST_OK; + int fd, i; + + if (list_empty(&pmus)) + perf_pmu__scan(NULL); + + ibs_pmu = perf_pmu__find("ibs_op"); + if (!ibs_pmu) + return TEST_SKIP; + + for (i = 0; i < NR_SUB_TESTS; i++) { + fd = event_open(sub_tests[i].type, sub_tests[i].config); + pr_debug("type: 0x%x, config: 0x%lx, fd: %d - ", sub_tests[i].type, + sub_tests[i].config, fd); + if ((sub_tests[i].valid && fd == -1) || + (!sub_tests[i].valid && fd > 0)) { + pr_debug("Fail\n"); + ret = TEST_FAIL; + } else { + pr_debug("Pass\n"); + } + + if (fd > 0) + close(fd); + } + + return ret; +} diff --git a/tools/perf/arch/x86/tests/arch-tests.c b/tools/perf/arch/x86/tests/arch-tests.c index aae6ea0fe52b..b5c85ab8d92e 100644 --- a/tools/perf/arch/x86/tests/arch-tests.c +++ b/tools/perf/arch/x86/tests/arch-tests.c @@ -22,6 +22,7 @@ struct test_suite suite__intel_pt = { DEFINE_SUITE("x86 bp modify", bp_modify); #endif DEFINE_SUITE("x86 Sample parsing", x86_sample_parsing); +DEFINE_SUITE("AMD IBS via core pmu", amd_ibs_via_core_pmu); struct test_suite *arch_tests[] = { #ifdef HAVE_DWARF_UNWIND_SUPPORT @@ -35,5 +36,6 @@ struct test_suite *arch_tests[] = { &suite__bp_modify, #endif &suite__x86_sample_parsing, + &suite__amd_ibs_via_core_pmu, NULL, }; diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm-def.h b/tools/perf/bench/mem-memcpy-x86-64-asm-def.h index 50ae8bd58296..6188e19d3129 100644 --- a/tools/perf/bench/mem-memcpy-x86-64-asm-def.h +++ b/tools/perf/bench/mem-memcpy-x86-64-asm-def.h @@ -7,7 +7,3 @@ MEMCPY_FN(memcpy_orig, MEMCPY_FN(__memcpy, "x86-64-movsq", "movsq-based memcpy() in arch/x86/lib/memcpy_64.S") - -MEMCPY_FN(memcpy_erms, - "x86-64-movsb", - "movsb-based memcpy() in arch/x86/lib/memcpy_64.S") diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S index 6eb45a2aa8db..1b9fef7efcdc 100644 --- a/tools/perf/bench/mem-memcpy-x86-64-asm.S +++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S @@ -2,7 +2,7 @@ /* Various wrappers to make the kernel .S file build in user-space: */ -// memcpy_orig and memcpy_erms are being defined as SYM_L_LOCAL but we need it +// memcpy_orig is being defined as SYM_L_LOCAL but we need it #define SYM_FUNC_START_LOCAL(name) \ SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) #define memcpy MEMCPY /* don't hide glibc's memcpy() */ diff --git a/tools/perf/bench/mem-memset-x86-64-asm-def.h b/tools/perf/bench/mem-memset-x86-64-asm-def.h index dac6d2b7c39b..247c72fdfb9d 100644 --- a/tools/perf/bench/mem-memset-x86-64-asm-def.h +++ b/tools/perf/bench/mem-memset-x86-64-asm-def.h @@ -7,7 +7,3 @@ MEMSET_FN(memset_orig, MEMSET_FN(__memset, "x86-64-stosq", "movsq-based memset() in arch/x86/lib/memset_64.S") - -MEMSET_FN(memset_erms, - "x86-64-stosb", - "movsb-based memset() in arch/x86/lib/memset_64.S") diff --git a/tools/perf/bench/mem-memset-x86-64-asm.S b/tools/perf/bench/mem-memset-x86-64-asm.S index 6f093c483842..abd26c95f1aa 100644 --- a/tools/perf/bench/mem-memset-x86-64-asm.S +++ b/tools/perf/bench/mem-memset-x86-64-asm.S @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -// memset_orig and memset_erms are being defined as SYM_L_LOCAL but we need it +// memset_orig is being defined as SYM_L_LOCAL but we need it #define SYM_FUNC_START_LOCAL(name) \ SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) #define memset MEMSET /* don't hide glibc's memset() */ diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c index 810e3376c7d6..f9906f52e4fa 100644 --- a/tools/perf/builtin-ftrace.c +++ b/tools/perf/builtin-ftrace.c @@ -1175,7 +1175,7 @@ int cmd_ftrace(int argc, const char **argv) OPT_BOOLEAN('b', "use-bpf", &ftrace.target.use_bpf, "Use BPF to measure function latency"), #endif - OPT_BOOLEAN('n', "--use-nsec", &ftrace.use_nsec, + OPT_BOOLEAN('n', "use-nsec", &ftrace.use_nsec, "Use nano-second histogram"), OPT_PARENT(common_options), }; diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 006f522d0e7f..c57be48d65bb 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -3647,6 +3647,13 @@ static int process_stat_config_event(struct perf_session *session __maybe_unused union perf_event *event) { perf_event__read_stat_config(&stat_config, &event->stat_config); + + /* + * Aggregation modes are not used since post-processing scripts are + * supposed to take care of such requirements + */ + stat_config.aggr_mode = AGGR_NONE; + return 0; } diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index cc9fa48d636f..b9ad32f21e57 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -667,6 +667,13 @@ static enum counter_recovery stat_handle_error(struct evsel *counter) evsel_list->core.threads->err_thread = -1; return COUNTER_RETRY; } + } else if (counter->skippable) { + if (verbose > 0) + ui__warning("skipping event %s that kernel failed to open .\n", + evsel__name(counter)); + counter->supported = false; + counter->errored = true; + return COUNTER_SKIP; } evsel__open_strerror(counter, &target, errno, msg, sizeof(msg)); @@ -1890,15 +1897,28 @@ static int add_default_attributes(void) * caused by exposing latent bugs. This is fixed properly in: * https://lore.kernel.org/lkml/bff481ba-e60a-763f-0aa0-3ee53302c480@linux.intel.com/ */ - if (metricgroup__has_metric("TopdownL1") && !perf_pmu__has_hybrid() && - metricgroup__parse_groups(evsel_list, "TopdownL1", - /*metric_no_group=*/false, - /*metric_no_merge=*/false, - /*metric_no_threshold=*/true, - stat_config.user_requested_cpu_list, - stat_config.system_wide, - &stat_config.metric_events) < 0) - return -1; + if (metricgroup__has_metric("TopdownL1") && !perf_pmu__has_hybrid()) { + struct evlist *metric_evlist = evlist__new(); + struct evsel *metric_evsel; + + if (!metric_evlist) + return -1; + + if (metricgroup__parse_groups(metric_evlist, "TopdownL1", + /*metric_no_group=*/false, + /*metric_no_merge=*/false, + /*metric_no_threshold=*/true, + stat_config.user_requested_cpu_list, + stat_config.system_wide, + &stat_config.metric_events) < 0) + return -1; + + evlist__for_each_entry(metric_evlist, metric_evsel) { + metric_evsel->skippable = true; + } + evlist__splice_list_tail(evsel_list, &metric_evlist->core.entries); + evlist__delete(metric_evlist); + } /* Platform specific attrs */ if (evlist__add_default_attrs(evsel_list, default_null_attrs) < 0) diff --git a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json index 75d80e70e5cd..1f9047553942 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json @@ -133,6 +133,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count. The rest of these subevents count backend stalls, in cycles, due to an outstanding request which is memory bound vs core bound. The subevents are not slot based events and therefore can not be precisely added or subtracted from the Backend_Bound_Aux subevents which are slot based.", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -143,6 +144,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound_aux", "MetricThreshold": "tma_backend_bound_aux > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that UOPS must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count. All of these subevents count backend stalls, in slots, due to a resource limitation. These are not cycle based events and therefore can not be precisely added or subtracted from the Backend_Bound subevents which are cycle based. These subevents are supplementary to Backend_Bound and can be used to analyze results from a resource perspective at allocation.", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -153,6 +155,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -163,6 +166,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_base", "MetricThreshold": "tma_base > 0.6", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -182,6 +186,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.05", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -209,6 +214,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -255,6 +261,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -264,6 +271,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.15", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -291,6 +299,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -593,6 +602,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.05", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -611,6 +621,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -629,6 +640,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_ms_uops", "MetricThreshold": "tma_ms_uops > 0.05", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "Counts the number of uops that are from the complex flows issued by the micro-sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows.", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -729,6 +741,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_aux_group", "MetricName": "tma_resource_bound", "MetricThreshold": "tma_resource_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count.", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -739,6 +752,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.75", + "MetricgroupNoGroup": "TopdownL1", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -848,6 +862,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -858,6 +873,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -868,6 +884,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -919,6 +936,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -1031,6 +1049,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 6 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -1041,6 +1060,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -1121,6 +1141,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -1141,6 +1162,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. Sample with: UOPS_RETIRED.HEAVY", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2023,6 +2045,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2082,6 +2105,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2112,6 +2136,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2310,6 +2335,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json index 1a85d935c733..0402adbf7d92 100644 --- a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json +++ b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json @@ -98,6 +98,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count. The rest of these subevents count backend stalls, in cycles, due to an outstanding request which is memory bound vs core bound. The subevents are not slot based events and therefore can not be precisely added or subtracted from the Backend_Bound_Aux subevents which are slot based.", "ScaleUnit": "100%" }, @@ -107,6 +108,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound_aux", "MetricThreshold": "tma_backend_bound_aux > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that UOPS must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count. All of these subevents count backend stalls, in slots, due to a resource limitation. These are not cycle based events and therefore can not be precisely added or subtracted from the Backend_Bound subevents which are cycle based. These subevents are supplementary to Backend_Bound and can be used to analyze results from a resource perspective at allocation.", "ScaleUnit": "100%" }, @@ -116,6 +118,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.", "ScaleUnit": "100%" }, @@ -125,6 +128,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_base", "MetricThreshold": "tma_base > 0.6", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -142,6 +146,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.05", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -166,6 +171,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -207,6 +213,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -215,6 +222,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.15", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -239,6 +247,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "ScaleUnit": "100%" }, { @@ -499,6 +508,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.05", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -515,6 +525,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -531,6 +542,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_ms_uops", "MetricThreshold": "tma_ms_uops > 0.05", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "Counts the number of uops that are from the complex flows issued by the micro-sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows.", "ScaleUnit": "100%" }, @@ -620,6 +632,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_aux_group", "MetricName": "tma_resource_bound", "MetricThreshold": "tma_resource_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count.", "ScaleUnit": "100%" }, @@ -629,6 +642,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.75", + "MetricgroupNoGroup": "TopdownL1", "ScaleUnit": "100%" }, { diff --git a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json index 51cf8560a8d3..f9e2316601e1 100644 --- a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json @@ -103,6 +103,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -112,6 +113,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -122,6 +124,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -170,6 +173,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -263,6 +267,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -272,6 +277,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -326,6 +332,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -335,6 +342,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -828,6 +836,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -858,6 +867,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -886,6 +896,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1048,6 +1059,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json index fb57c7382408..e9c46d336a8e 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json @@ -97,6 +97,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%" }, @@ -106,6 +107,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -116,6 +118,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -164,6 +167,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -248,6 +252,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -257,6 +262,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -311,6 +317,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -320,6 +327,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -795,6 +803,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -825,6 +834,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -853,6 +863,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1013,6 +1024,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json index 65ec0c9e55d1..437b9867acb9 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json @@ -103,6 +103,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -112,6 +113,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -122,6 +124,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -170,6 +173,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -263,6 +267,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -272,6 +277,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -326,6 +332,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -335,6 +342,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -829,6 +837,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -869,6 +878,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -897,6 +907,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1079,6 +1090,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json index 8f7dc72accd0..875c766222e3 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json @@ -101,6 +101,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -110,6 +111,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -120,6 +122,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -167,6 +170,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -271,6 +275,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -280,6 +285,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -354,6 +360,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -372,6 +379,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -1142,6 +1150,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1196,6 +1205,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1224,6 +1234,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1458,6 +1469,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json index 2528418200bb..9570a88d6d1c 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json +++ b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json @@ -103,6 +103,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -112,6 +113,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -122,6 +124,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -161,6 +164,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -254,6 +258,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -263,6 +268,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -272,6 +278,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -281,6 +288,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -663,6 +671,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -693,6 +702,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -721,6 +731,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -874,6 +885,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json index 11f152c346eb..a522202cf684 100644 --- a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json @@ -103,6 +103,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -112,6 +113,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -122,6 +124,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -161,6 +164,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -254,6 +258,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -263,6 +268,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -272,6 +278,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -281,6 +288,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -664,6 +672,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -704,6 +713,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -732,6 +742,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -905,6 +916,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json b/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json index f45ae3483df4..1a2154f28b7b 100644 --- a/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json @@ -115,6 +115,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%" }, @@ -124,6 +125,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -141,6 +143,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -187,6 +190,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -288,6 +292,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -297,6 +302,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -369,6 +375,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -378,6 +385,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -1111,6 +1119,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1164,6 +1173,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1191,6 +1201,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1360,6 +1371,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json index 0f9b174dfc22..1ef772b40e04 100644 --- a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json @@ -80,6 +80,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%" }, @@ -89,6 +90,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -106,6 +108,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -152,6 +155,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -253,6 +257,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -262,6 +267,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -334,6 +340,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -343,6 +350,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -1134,6 +1142,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1187,6 +1196,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1214,6 +1224,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1410,6 +1421,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json index 5247f69c13b6..11080ccffd51 100644 --- a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json +++ b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json @@ -103,6 +103,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -112,6 +113,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -122,6 +124,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -161,6 +164,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -254,6 +258,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -263,6 +268,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -299,6 +305,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -308,6 +315,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -724,6 +732,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -754,6 +763,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -782,6 +792,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -917,6 +928,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json index 89469b10fa30..65a46d659c0a 100644 --- a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json +++ b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json @@ -103,6 +103,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -112,6 +113,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -122,6 +124,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -161,6 +164,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -254,6 +258,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -263,6 +268,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -299,6 +305,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -308,6 +315,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -725,6 +733,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -765,6 +774,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -793,6 +803,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -948,6 +959,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json index e8f4e5c01c9f..66a6f657bd6f 100644 --- a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json +++ b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json @@ -76,6 +76,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -85,6 +86,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -95,6 +97,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -114,6 +117,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -160,6 +164,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_lcp", "ScaleUnit": "100%" }, @@ -169,6 +174,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -205,6 +211,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -214,6 +221,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -412,6 +420,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -422,6 +431,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -450,6 +460,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -487,6 +498,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json index 4a99fe515f4b..4b8bc19392a4 100644 --- a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json +++ b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json @@ -76,6 +76,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -85,6 +86,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -95,6 +97,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -114,6 +117,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -160,6 +164,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_lcp", "ScaleUnit": "100%" }, @@ -169,6 +174,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -205,6 +211,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -214,6 +221,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -411,6 +419,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -421,6 +430,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -449,6 +459,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -486,6 +497,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json index 126300b7ae77..620fc5bd2217 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json @@ -87,6 +87,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%" }, @@ -96,6 +97,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -105,6 +107,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -151,6 +154,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -252,6 +256,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 6 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -261,6 +266,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -351,6 +357,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -369,6 +376,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. Sample with: UOPS_RETIRED.HEAVY", "ScaleUnit": "100%" }, @@ -1216,6 +1224,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1269,6 +1278,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1304,6 +1314,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1509,6 +1520,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json index a6d212b349f5..21ef6c9be816 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json @@ -101,6 +101,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -110,6 +111,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -120,6 +122,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -167,6 +170,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -271,6 +275,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -280,6 +285,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -345,6 +351,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -363,6 +370,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -1065,6 +1073,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1110,6 +1119,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1138,6 +1148,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1343,6 +1354,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json index fa2f7f126a30..eb6f12c0343d 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json @@ -101,6 +101,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -110,6 +111,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -120,6 +122,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -167,6 +170,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -271,6 +275,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -280,6 +285,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -354,6 +360,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -372,6 +379,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -1123,6 +1131,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1177,6 +1186,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1205,6 +1215,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1429,6 +1440,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json b/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json index 4c80d6be6cf1..b442ed4acfbb 100644 --- a/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json @@ -109,6 +109,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%" }, @@ -118,6 +119,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -135,6 +137,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -181,6 +184,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -282,6 +286,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -291,6 +296,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -363,6 +369,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -372,6 +379,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -1125,6 +1133,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1178,6 +1187,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1205,6 +1215,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1374,6 +1385,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py index ca99b9cfe4ad..f57a8f274025 100755 --- a/tools/perf/pmu-events/jevents.py +++ b/tools/perf/pmu-events/jevents.py @@ -52,7 +52,8 @@ _json_event_attributes = [ # Attributes that are in pmu_metric rather than pmu_event. _json_metric_attributes = [ 'metric_name', 'metric_group', 'metric_expr', 'metric_threshold', 'desc', - 'long_desc', 'unit', 'compat', 'aggr_mode', 'event_grouping' + 'long_desc', 'unit', 'compat', 'metricgroup_no_group', 'aggr_mode', + 'event_grouping' ] # Attributes that are bools or enum int values, encoded as '0', '1',... _json_enum_attributes = ['aggr_mode', 'deprecated', 'event_grouping', 'perpkg'] @@ -303,6 +304,7 @@ class JsonEvent: self.deprecated = jd.get('Deprecated') self.metric_name = jd.get('MetricName') self.metric_group = jd.get('MetricGroup') + self.metricgroup_no_group = jd.get('MetricgroupNoGroup') self.event_grouping = convert_metric_constraint(jd.get('MetricConstraint')) self.metric_expr = None if 'MetricExpr' in jd: diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h index b7dff8f1021f..80349685cf4d 100644 --- a/tools/perf/pmu-events/pmu-events.h +++ b/tools/perf/pmu-events/pmu-events.h @@ -59,6 +59,7 @@ struct pmu_metric { const char *compat; const char *desc; const char *long_desc; + const char *metricgroup_no_group; enum aggr_mode_class aggr_mode; enum metric_event_groups event_grouping; }; diff --git a/tools/perf/tests/attr.py b/tools/perf/tests/attr.py index ccfef861e931..e890c261ad26 100644 --- a/tools/perf/tests/attr.py +++ b/tools/perf/tests/attr.py @@ -152,7 +152,7 @@ def parse_version(version): # - expected values assignments class Test(object): def __init__(self, path, options): - parser = configparser.SafeConfigParser() + parser = configparser.ConfigParser() parser.read(path) log.warning("running '%s'" % path) @@ -247,7 +247,7 @@ class Test(object): return True def load_events(self, path, events): - parser_event = configparser.SafeConfigParser() + parser_event = configparser.ConfigParser() parser_event.read(path) # The event record section header contains 'event' word, @@ -261,7 +261,7 @@ class Test(object): # Read parent event if there's any if (':' in section): base = section[section.index(':') + 1:] - parser_base = configparser.SafeConfigParser() + parser_base = configparser.ConfigParser() parser_base.read(self.test_dir + '/' + base) base_items = parser_base.items('event') diff --git a/tools/perf/tests/attr/base-stat b/tools/perf/tests/attr/base-stat index a21fb65bc012..fccd8ec4d1b0 100644 --- a/tools/perf/tests/attr/base-stat +++ b/tools/perf/tests/attr/base-stat @@ -16,7 +16,7 @@ pinned=0 exclusive=0 exclude_user=0 exclude_kernel=0|1 -exclude_hv=0 +exclude_hv=0|1 exclude_idle=0 mmap=0 comm=0 diff --git a/tools/perf/tests/attr/test-stat-default b/tools/perf/tests/attr/test-stat-default index d8ea6a88163f..a1e2da0a9a6d 100644 --- a/tools/perf/tests/attr/test-stat-default +++ b/tools/perf/tests/attr/test-stat-default @@ -40,7 +40,6 @@ fd=6 type=0 config=7 optional=1 - # PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_BACKEND [event7:base-stat] fd=7 @@ -89,79 +88,98 @@ enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) [event13:base-stat] fd=13 group_fd=11 type=4 -config=33024 +config=33280 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-fe-bound (0x8200) +# PERF_TYPE_RAW / topdown-be-bound (0x8300) [event14:base-stat] fd=14 group_fd=11 type=4 -config=33280 +config=33536 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-be-bound (0x8300) +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) [event15:base-stat] fd=15 group_fd=11 type=4 -config=33536 +config=33024 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +# PERF_TYPE_RAW / INT_MISC.UOP_DROPPING [event16:base-stat] fd=16 -group_fd=11 type=4 -config=33792 -disabled=0 -enable_on_exec=0 -read_format=15 +config=4109 optional=1 -# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +# PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/ [event17:base-stat] fd=17 -group_fd=11 type=4 -config=34048 -disabled=0 -enable_on_exec=0 -read_format=15 +config=17039629 optional=1 -# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD [event18:base-stat] fd=18 -group_fd=11 type=4 -config=34304 -disabled=0 -enable_on_exec=0 -read_format=15 +config=60 optional=1 -# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +# PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY [event19:base-stat] fd=19 -group_fd=11 type=4 -config=34560 -disabled=0 -enable_on_exec=0 -read_format=15 +config=2097421 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK +[event20:base-stat] +fd=20 +type=4 +config=316 +optional=1 + +# PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE +[event21:base-stat] +fd=21 +type=4 +config=412 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE +[event22:base-stat] +fd=22 +type=4 +config=572 +optional=1 + +# PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS +[event23:base-stat] +fd=23 +type=4 +config=706 +optional=1 + +# PERF_TYPE_RAW / UOPS_ISSUED.ANY +[event24:base-stat] +fd=24 +type=4 +config=270 optional=1 diff --git a/tools/perf/tests/attr/test-stat-detailed-1 b/tools/perf/tests/attr/test-stat-detailed-1 index b656ab93c5bf..1c52cb05c900 100644 --- a/tools/perf/tests/attr/test-stat-detailed-1 +++ b/tools/perf/tests/attr/test-stat-detailed-1 @@ -90,89 +90,108 @@ enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) [event13:base-stat] fd=13 group_fd=11 type=4 -config=33024 +config=33280 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-fe-bound (0x8200) +# PERF_TYPE_RAW / topdown-be-bound (0x8300) [event14:base-stat] fd=14 group_fd=11 type=4 -config=33280 +config=33536 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-be-bound (0x8300) +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) [event15:base-stat] fd=15 group_fd=11 type=4 -config=33536 +config=33024 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +# PERF_TYPE_RAW / INT_MISC.UOP_DROPPING [event16:base-stat] fd=16 -group_fd=11 type=4 -config=33792 -disabled=0 -enable_on_exec=0 -read_format=15 +config=4109 optional=1 -# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +# PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/ [event17:base-stat] fd=17 -group_fd=11 type=4 -config=34048 -disabled=0 -enable_on_exec=0 -read_format=15 +config=17039629 optional=1 -# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD [event18:base-stat] fd=18 -group_fd=11 type=4 -config=34304 -disabled=0 -enable_on_exec=0 -read_format=15 +config=60 optional=1 -# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +# PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY [event19:base-stat] fd=19 -group_fd=11 type=4 -config=34560 -disabled=0 -enable_on_exec=0 -read_format=15 +config=2097421 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK +[event20:base-stat] +fd=20 +type=4 +config=316 +optional=1 + +# PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE +[event21:base-stat] +fd=21 +type=4 +config=412 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE +[event22:base-stat] +fd=22 +type=4 +config=572 +optional=1 + +# PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS +[event23:base-stat] +fd=23 +type=4 +config=706 +optional=1 + +# PERF_TYPE_RAW / UOPS_ISSUED.ANY +[event24:base-stat] +fd=24 +type=4 +config=270 optional=1 # PERF_TYPE_HW_CACHE / # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event20:base-stat] -fd=20 +[event25:base-stat] +fd=25 type=3 config=0 optional=1 @@ -181,8 +200,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event21:base-stat] -fd=21 +[event26:base-stat] +fd=26 type=3 config=65536 optional=1 @@ -191,8 +210,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event22:base-stat] -fd=22 +[event27:base-stat] +fd=27 type=3 config=2 optional=1 @@ -201,8 +220,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event23:base-stat] -fd=23 +[event28:base-stat] +fd=28 type=3 config=65538 optional=1 diff --git a/tools/perf/tests/attr/test-stat-detailed-2 b/tools/perf/tests/attr/test-stat-detailed-2 index 97625090a1c4..7e961d24a885 100644 --- a/tools/perf/tests/attr/test-stat-detailed-2 +++ b/tools/perf/tests/attr/test-stat-detailed-2 @@ -90,89 +90,108 @@ enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) [event13:base-stat] fd=13 group_fd=11 type=4 -config=33024 +config=33280 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-fe-bound (0x8200) +# PERF_TYPE_RAW / topdown-be-bound (0x8300) [event14:base-stat] fd=14 group_fd=11 type=4 -config=33280 +config=33536 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-be-bound (0x8300) +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) [event15:base-stat] fd=15 group_fd=11 type=4 -config=33536 +config=33024 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +# PERF_TYPE_RAW / INT_MISC.UOP_DROPPING [event16:base-stat] fd=16 -group_fd=11 type=4 -config=33792 -disabled=0 -enable_on_exec=0 -read_format=15 +config=4109 optional=1 -# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +# PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/ [event17:base-stat] fd=17 -group_fd=11 type=4 -config=34048 -disabled=0 -enable_on_exec=0 -read_format=15 +config=17039629 optional=1 -# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD [event18:base-stat] fd=18 -group_fd=11 type=4 -config=34304 -disabled=0 -enable_on_exec=0 -read_format=15 +config=60 optional=1 -# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +# PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY [event19:base-stat] fd=19 -group_fd=11 type=4 -config=34560 -disabled=0 -enable_on_exec=0 -read_format=15 +config=2097421 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK +[event20:base-stat] +fd=20 +type=4 +config=316 +optional=1 + +# PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE +[event21:base-stat] +fd=21 +type=4 +config=412 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE +[event22:base-stat] +fd=22 +type=4 +config=572 +optional=1 + +# PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS +[event23:base-stat] +fd=23 +type=4 +config=706 +optional=1 + +# PERF_TYPE_RAW / UOPS_ISSUED.ANY +[event24:base-stat] +fd=24 +type=4 +config=270 optional=1 # PERF_TYPE_HW_CACHE / # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event20:base-stat] -fd=20 +[event25:base-stat] +fd=25 type=3 config=0 optional=1 @@ -181,8 +200,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event21:base-stat] -fd=21 +[event26:base-stat] +fd=26 type=3 config=65536 optional=1 @@ -191,8 +210,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event22:base-stat] -fd=22 +[event27:base-stat] +fd=27 type=3 config=2 optional=1 @@ -201,8 +220,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event23:base-stat] -fd=23 +[event28:base-stat] +fd=28 type=3 config=65538 optional=1 @@ -211,8 +230,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event24:base-stat] -fd=24 +[event29:base-stat] +fd=29 type=3 config=1 optional=1 @@ -221,8 +240,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event25:base-stat] -fd=25 +[event30:base-stat] +fd=30 type=3 config=65537 optional=1 @@ -231,8 +250,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event26:base-stat] -fd=26 +[event31:base-stat] +fd=31 type=3 config=3 optional=1 @@ -241,8 +260,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event27:base-stat] -fd=27 +[event32:base-stat] +fd=32 type=3 config=65539 optional=1 @@ -251,8 +270,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event28:base-stat] -fd=28 +[event33:base-stat] +fd=33 type=3 config=4 optional=1 @@ -261,8 +280,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event29:base-stat] -fd=29 +[event34:base-stat] +fd=34 type=3 config=65540 optional=1 diff --git a/tools/perf/tests/attr/test-stat-detailed-3 b/tools/perf/tests/attr/test-stat-detailed-3 index d555042e3fbf..e50535f45977 100644 --- a/tools/perf/tests/attr/test-stat-detailed-3 +++ b/tools/perf/tests/attr/test-stat-detailed-3 @@ -90,89 +90,108 @@ enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) [event13:base-stat] fd=13 group_fd=11 type=4 -config=33024 +config=33280 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-fe-bound (0x8200) +# PERF_TYPE_RAW / topdown-be-bound (0x8300) [event14:base-stat] fd=14 group_fd=11 type=4 -config=33280 +config=33536 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-be-bound (0x8300) +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) [event15:base-stat] fd=15 group_fd=11 type=4 -config=33536 +config=33024 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +# PERF_TYPE_RAW / INT_MISC.UOP_DROPPING [event16:base-stat] fd=16 -group_fd=11 type=4 -config=33792 -disabled=0 -enable_on_exec=0 -read_format=15 +config=4109 optional=1 -# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +# PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/ [event17:base-stat] fd=17 -group_fd=11 type=4 -config=34048 -disabled=0 -enable_on_exec=0 -read_format=15 +config=17039629 optional=1 -# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD [event18:base-stat] fd=18 -group_fd=11 type=4 -config=34304 -disabled=0 -enable_on_exec=0 -read_format=15 +config=60 optional=1 -# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +# PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY [event19:base-stat] fd=19 -group_fd=11 type=4 -config=34560 -disabled=0 -enable_on_exec=0 -read_format=15 +config=2097421 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK +[event20:base-stat] +fd=20 +type=4 +config=316 +optional=1 + +# PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE +[event21:base-stat] +fd=21 +type=4 +config=412 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE +[event22:base-stat] +fd=22 +type=4 +config=572 +optional=1 + +# PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS +[event23:base-stat] +fd=23 +type=4 +config=706 +optional=1 + +# PERF_TYPE_RAW / UOPS_ISSUED.ANY +[event24:base-stat] +fd=24 +type=4 +config=270 optional=1 # PERF_TYPE_HW_CACHE / # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event20:base-stat] -fd=20 +[event25:base-stat] +fd=25 type=3 config=0 optional=1 @@ -181,8 +200,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event21:base-stat] -fd=21 +[event26:base-stat] +fd=26 type=3 config=65536 optional=1 @@ -191,8 +210,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event22:base-stat] -fd=22 +[event27:base-stat] +fd=27 type=3 config=2 optional=1 @@ -201,8 +220,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event23:base-stat] -fd=23 +[event28:base-stat] +fd=28 type=3 config=65538 optional=1 @@ -211,8 +230,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event24:base-stat] -fd=24 +[event29:base-stat] +fd=29 type=3 config=1 optional=1 @@ -221,8 +240,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event25:base-stat] -fd=25 +[event30:base-stat] +fd=30 type=3 config=65537 optional=1 @@ -231,8 +250,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event26:base-stat] -fd=26 +[event31:base-stat] +fd=31 type=3 config=3 optional=1 @@ -241,8 +260,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event27:base-stat] -fd=27 +[event32:base-stat] +fd=32 type=3 config=65539 optional=1 @@ -251,8 +270,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event28:base-stat] -fd=28 +[event33:base-stat] +fd=33 type=3 config=4 optional=1 @@ -261,8 +280,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event29:base-stat] -fd=29 +[event34:base-stat] +fd=34 type=3 config=65540 optional=1 @@ -271,8 +290,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_PREFETCH << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event30:base-stat] -fd=30 +[event35:base-stat] +fd=35 type=3 config=512 optional=1 @@ -281,8 +300,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_PREFETCH << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event31:base-stat] -fd=31 +[event36:base-stat] +fd=36 type=3 config=66048 optional=1 diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c index cbf0e0c74906..733ead151c63 100644 --- a/tools/perf/tests/expr.c +++ b/tools/perf/tests/expr.c @@ -120,7 +120,8 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u p = "FOO/0"; ret = expr__parse(&val, ctx, p); - TEST_ASSERT_VAL("division by zero", ret == -1); + TEST_ASSERT_VAL("division by zero", ret == 0); + TEST_ASSERT_VAL("division by zero", isnan(val)); p = "BAR/"; ret = expr__parse(&val, ctx, p); diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c index 1185b79e6274..c05148ea400c 100644 --- a/tools/perf/tests/parse-metric.c +++ b/tools/perf/tests/parse-metric.c @@ -38,6 +38,7 @@ static void load_runtime_stat(struct evlist *evlist, struct value *vals) evlist__alloc_aggr_stats(evlist, 1); evlist__for_each_entry(evlist, evsel) { count = find_value(evsel->name, vals); + evsel->supported = true; evsel->stats->aggr->counts.val = count; if (evsel__name_is(evsel, "duration_time")) update_stats(&walltime_nsecs_stats, count); diff --git a/tools/perf/tests/shell/stat.sh b/tools/perf/tests/shell/stat.sh index 2c1d3f704995..b154fbb15d54 100755 --- a/tools/perf/tests/shell/stat.sh +++ b/tools/perf/tests/shell/stat.sh @@ -28,6 +28,18 @@ test_stat_record_report() { echo "stat record and report test [Success]" } +test_stat_record_script() { + echo "stat record and script test" + if ! perf stat record -o - true | perf script -i - 2>&1 | \ + grep -E -q "CPU[[:space:]]+THREAD[[:space:]]+VAL[[:space:]]+ENA[[:space:]]+RUN[[:space:]]+TIME[[:space:]]+EVENT" + then + echo "stat record and script test [Failed]" + err=1 + return + fi + echo "stat record and script test [Success]" +} + test_stat_repeat_weak_groups() { echo "stat repeat weak groups test" if ! perf stat -e '{cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles}' \ @@ -93,6 +105,7 @@ test_topdown_weak_groups() { test_default_stat test_stat_record_report +test_stat_record_script test_stat_repeat_weak_groups test_topdown_groups test_topdown_weak_groups diff --git a/tools/perf/tests/shell/test_intel_pt.sh b/tools/perf/tests/shell/test_intel_pt.sh index 4ddb17cb83c5..3a8b9bffa022 100755 --- a/tools/perf/tests/shell/test_intel_pt.sh +++ b/tools/perf/tests/shell/test_intel_pt.sh @@ -506,6 +506,13 @@ test_sample() echo "perf record failed with --aux-sample" return 1 fi + # Check with event with PMU name + if perf_record_no_decode -o "${perfdatafile}" -e br_misp_retired.all_branches:u uname ; then + if ! perf_record_no_decode -o "${perfdatafile}" -e '{intel_pt//,br_misp_retired.all_branches/aux-sample-size=8192/}:u' uname ; then + echo "perf record failed with --aux-sample-size" + return 1 + fi + fi echo OK return 0 } diff --git a/tools/perf/tests/shell/test_java_symbol.sh b/tools/perf/tests/shell/test_java_symbol.sh index 90cea8811926..499539d1c479 100755 --- a/tools/perf/tests/shell/test_java_symbol.sh +++ b/tools/perf/tests/shell/test_java_symbol.sh @@ -56,7 +56,7 @@ if [ $? -ne 0 ]; then exit 1 fi -if ! perf inject -i $PERF_DATA -o $PERF_INJ_DATA -j; then +if ! DEBUGINFOD_URLS='' perf inject -i $PERF_DATA -o $PERF_INJ_DATA -j; then echo "Fail to inject samples" exit 1 fi diff --git a/tools/perf/trace/beauty/arch_prctl.c b/tools/perf/trace/beauty/arch_prctl.c index fe022ca67e60..a211348d3204 100644 --- a/tools/perf/trace/beauty/arch_prctl.c +++ b/tools/perf/trace/beauty/arch_prctl.c @@ -12,10 +12,12 @@ static DEFINE_STRARRAY_OFFSET(x86_arch_prctl_codes_1, "ARCH_", x86_arch_prctl_codes_1_offset); static DEFINE_STRARRAY_OFFSET(x86_arch_prctl_codes_2, "ARCH_", x86_arch_prctl_codes_2_offset); +static DEFINE_STRARRAY_OFFSET(x86_arch_prctl_codes_3, "ARCH_", x86_arch_prctl_codes_3_offset); static struct strarray *x86_arch_prctl_codes[] = { &strarray__x86_arch_prctl_codes_1, &strarray__x86_arch_prctl_codes_2, + &strarray__x86_arch_prctl_codes_3, }; static DEFINE_STRARRAYS(x86_arch_prctl_codes); diff --git a/tools/perf/trace/beauty/x86_arch_prctl.sh b/tools/perf/trace/beauty/x86_arch_prctl.sh index 57fa6aaffe70..fd5c740512c5 100755 --- a/tools/perf/trace/beauty/x86_arch_prctl.sh +++ b/tools/perf/trace/beauty/x86_arch_prctl.sh @@ -24,3 +24,4 @@ print_range () { print_range 1 0x1 0x1001 print_range 2 0x2 0x2001 +print_range 3 0x4 0x4001 diff --git a/tools/perf/util/Build b/tools/perf/util/Build index bd18fe5f2719..f9df1df1eec0 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -214,7 +214,7 @@ perf-$(CONFIG_ZSTD) += zstd.o perf-$(CONFIG_LIBCAP) += cap.o -perf-y += demangle-cxx.o +perf-$(CONFIG_CXX_DEMANGLE) += demangle-cxx.o perf-y += demangle-ocaml.o perf-y += demangle-java.o perf-y += demangle-rust.o diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c index f3918f290df5..ba807071d3c1 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c +++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c @@ -51,7 +51,7 @@ static u64 arm_spe_calc_ip(int index, u64 payload) * (bits [63:56]) is assigned as top-byte tag; so we only can * retrieve address value from bits [55:0]. * - * According to Documentation/arm64/memory.rst, if detects the + * According to Documentation/arch/arm64/memory.rst, if detects the * specific pattern in bits [55:52] of payload which falls in * the kernel space, should fixup the top byte and this allows * perf tool to parse DSO symbol for data address correctly. diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c index 8d3cfbb3cc65..1d48226ae75d 100644 --- a/tools/perf/util/bpf_skel/lock_contention.bpf.c +++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c @@ -416,6 +416,8 @@ int contention_end(u64 *ctx) return 0; } +struct rq {}; + extern struct rq runqueues __ksym; struct rq___old { diff --git a/tools/perf/util/bpf_skel/sample_filter.bpf.c b/tools/perf/util/bpf_skel/sample_filter.bpf.c index cffe493af1ed..fb94f5280626 100644 --- a/tools/perf/util/bpf_skel/sample_filter.bpf.c +++ b/tools/perf/util/bpf_skel/sample_filter.bpf.c @@ -25,7 +25,7 @@ struct perf_sample_data___new { } __attribute__((preserve_access_index)); /* new kernel perf_mem_data_src definition */ -union perf_mem_data_src__new { +union perf_mem_data_src___new { __u64 val; struct { __u64 mem_op:5, /* type of opcode */ @@ -108,7 +108,7 @@ static inline __u64 perf_get_sample(struct bpf_perf_event_data_kern *kctx, if (entry->part == 7) return kctx->data->data_src.mem_blk; if (entry->part == 8) { - union perf_mem_data_src__new *data = (void *)&kctx->data->data_src; + union perf_mem_data_src___new *data = (void *)&kctx->data->data_src; if (bpf_core_field_exists(data->mem_hops)) return data->mem_hops; diff --git a/tools/perf/util/bpf_skel/vmlinux.h b/tools/perf/util/bpf_skel/vmlinux.h index 449b1ea91fc4..c7ed51b0c1ef 100644 --- a/tools/perf/util/bpf_skel/vmlinux.h +++ b/tools/perf/util/bpf_skel/vmlinux.h @@ -1,6 +1,7 @@ #ifndef __VMLINUX_H #define __VMLINUX_H +#include <linux/stddef.h> // for define __always_inline #include <linux/bpf.h> #include <linux/types.h> #include <linux/perf_event.h> diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h index 70cac0375b34..ecca40787ac9 100644 --- a/tools/perf/util/cs-etm.h +++ b/tools/perf/util/cs-etm.h @@ -227,6 +227,19 @@ struct cs_etm_packet_queue { #define INFO_HEADER_SIZE (sizeof(((struct perf_record_auxtrace_info *)0)->type) + \ sizeof(((struct perf_record_auxtrace_info *)0)->reserved__)) +/* CoreSight trace ID is currently the bottom 7 bits of the value */ +#define CORESIGHT_TRACE_ID_VAL_MASK GENMASK(6, 0) + +/* + * perf record will set the legacy meta data values as unused initially. + * This allows perf report to manage the decoders created when dynamic + * allocation in operation. + */ +#define CORESIGHT_TRACE_ID_UNUSED_FLAG BIT(31) + +/* Value to set for unused trace ID values */ +#define CORESIGHT_TRACE_ID_UNUSED_VAL 0x7F + int cs_etm__process_auxtrace_info(union perf_event *event, struct perf_session *session); struct perf_event_attr *cs_etm_get_default_config(struct perf_pmu *pmu); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 356c07f03be6..c2dbb5647e75 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -282,6 +282,7 @@ void evsel__init(struct evsel *evsel, evsel->bpf_fd = -1; INIT_LIST_HEAD(&evsel->config_terms); INIT_LIST_HEAD(&evsel->bpf_counter_list); + INIT_LIST_HEAD(&evsel->bpf_filters); perf_evsel__object.init(evsel); evsel->sample_size = __evsel__sample_size(attr->sample_type); evsel__calc_id_pos(evsel); @@ -290,6 +291,7 @@ void evsel__init(struct evsel *evsel, evsel->per_pkg_mask = NULL; evsel->collect_stat = false; evsel->pmu_name = NULL; + evsel->skippable = false; } struct evsel *evsel__new_idx(struct perf_event_attr *attr, int idx) @@ -828,26 +830,26 @@ bool evsel__name_is(struct evsel *evsel, const char *name) const char *evsel__group_pmu_name(const struct evsel *evsel) { - const struct evsel *leader; + struct evsel *leader = evsel__leader(evsel); + struct evsel *pos; - /* If the pmu_name is set use it. pmu_name isn't set for CPU and software events. */ - if (evsel->pmu_name) - return evsel->pmu_name; /* * Software events may be in a group with other uncore PMU events. Use - * the pmu_name of the group leader to avoid breaking the software event - * out of the group. + * the pmu_name of the first non-software event to avoid breaking the + * software event out of the group. * * Aux event leaders, like intel_pt, expect a group with events from * other PMUs, so substitute the AUX event's PMU in this case. */ - leader = evsel__leader(evsel); - if ((evsel->core.attr.type == PERF_TYPE_SOFTWARE || evsel__is_aux_event(leader)) && - leader->pmu_name) { - return leader->pmu_name; + if (evsel->core.attr.type == PERF_TYPE_SOFTWARE || evsel__is_aux_event(leader)) { + /* Starting with the leader, find the first event with a named PMU. */ + for_each_group_evsel(pos, leader) { + if (pos->pmu_name) + return pos->pmu_name; + } } - return "cpu"; + return evsel->pmu_name ?: "cpu"; } const char *evsel__metric_id(const struct evsel *evsel) @@ -1725,9 +1727,13 @@ static int get_group_fd(struct evsel *evsel, int cpu_map_idx, int thread) return -1; fd = FD(leader, cpu_map_idx, thread); - BUG_ON(fd == -1); + BUG_ON(fd == -1 && !leader->skippable); - return fd; + /* + * When the leader has been skipped, return -2 to distinguish from no + * group leader case. + */ + return fd == -1 ? -2 : fd; } static void evsel__remove_fd(struct evsel *pos, int nr_cpus, int nr_threads, int thread_idx) @@ -2109,6 +2115,12 @@ retry_open: group_fd = get_group_fd(evsel, idx, thread); + if (group_fd == -2) { + pr_debug("broken group leader for %s\n", evsel->name); + err = -EINVAL; + goto out_close; + } + test_attr__ready(); /* Debug message used by test scripts */ diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index d575390d80bc..0f54f28a69c2 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -95,6 +95,7 @@ struct evsel { bool weak_group; bool bpf_counter; bool use_config_name; + bool skippable; int bpf_fd; struct bpf_object *bpf_obj; struct list_head config_terms; @@ -150,10 +151,8 @@ struct evsel { */ struct bpf_counter_ops *bpf_counter_ops; - union { - struct list_head bpf_counter_list; /* for perf-stat -b */ - struct list_head bpf_filters; /* for perf-record --filter */ - }; + struct list_head bpf_counter_list; /* for perf-stat -b */ + struct list_head bpf_filters; /* for perf-record --filter */ /* for perf-stat --use-bpf */ int bperf_leader_prog_fd; diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y index 250e444bf032..4ce931cccb63 100644 --- a/tools/perf/util/expr.y +++ b/tools/perf/util/expr.y @@ -225,7 +225,11 @@ expr: NUMBER { if (fpclassify($3.val) == FP_ZERO) { pr_debug("division by zero\n"); - YYABORT; + assert($3.ids == NULL); + if (compute_ids) + ids__free($1.ids); + $$.val = NAN; + $$.ids = NULL; } else if (!compute_ids || (is_const($1.val) && is_const($3.val))) { assert($1.ids == NULL); assert($3.ids == NULL); diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index c566c6859302..5e9c657dd3f7 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -1144,12 +1144,12 @@ static int metricgroup__add_metric_callback(const struct pmu_metric *pm, struct metricgroup__add_metric_data *data = vdata; int ret = 0; - if (pm->metric_expr && - (match_metric(pm->metric_group, data->metric_name) || - match_metric(pm->metric_name, data->metric_name))) { + if (pm->metric_expr && match_pm_metric(pm, data->metric_name)) { + bool metric_no_group = data->metric_no_group || + match_metric(data->metric_name, pm->metricgroup_no_group); data->has_match = true; - ret = add_metric(data->list, pm, data->modifier, data->metric_no_group, + ret = add_metric(data->list, pm, data->modifier, metric_no_group, data->metric_no_threshold, data->user_requested_cpu_list, data->system_wide, /*root_metric=*/NULL, /*visited_metrics=*/NULL, table); @@ -1672,7 +1672,7 @@ static int metricgroup__topdown_max_level_callback(const struct pmu_metric *pm, { unsigned int *max_level = data; unsigned int level; - const char *p = strstr(pm->metric_group, "TopdownL"); + const char *p = strstr(pm->metric_group ?: "", "TopdownL"); if (!p || p[8] == '\0') return 0; diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index d71019dcd614..34ba840ae19a 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -2140,25 +2140,32 @@ static int evlist__cmp(void *state, const struct list_head *l, const struct list int *leader_idx = state; int lhs_leader_idx = *leader_idx, rhs_leader_idx = *leader_idx, ret; const char *lhs_pmu_name, *rhs_pmu_name; + bool lhs_has_group = false, rhs_has_group = false; /* * First sort by grouping/leader. Read the leader idx only if the evsel * is part of a group, as -1 indicates no group. */ - if (lhs_core->leader != lhs_core || lhs_core->nr_members > 1) + if (lhs_core->leader != lhs_core || lhs_core->nr_members > 1) { + lhs_has_group = true; lhs_leader_idx = lhs_core->leader->idx; - if (rhs_core->leader != rhs_core || rhs_core->nr_members > 1) + } + if (rhs_core->leader != rhs_core || rhs_core->nr_members > 1) { + rhs_has_group = true; rhs_leader_idx = rhs_core->leader->idx; + } if (lhs_leader_idx != rhs_leader_idx) return lhs_leader_idx - rhs_leader_idx; - /* Group by PMU. Groups can't span PMUs. */ - lhs_pmu_name = evsel__group_pmu_name(lhs); - rhs_pmu_name = evsel__group_pmu_name(rhs); - ret = strcmp(lhs_pmu_name, rhs_pmu_name); - if (ret) - return ret; + /* Group by PMU if there is a group. Groups can't span PMUs. */ + if (lhs_has_group && rhs_has_group) { + lhs_pmu_name = evsel__group_pmu_name(lhs); + rhs_pmu_name = evsel__group_pmu_name(rhs); + ret = strcmp(lhs_pmu_name, rhs_pmu_name); + if (ret) + return ret; + } /* Architecture specific sorting. */ return arch_evlist__cmp(lhs, rhs); diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 73b2ff2ddf29..bf5a6c14dfcd 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -431,7 +431,7 @@ static void print_metric_json(struct perf_stat_config *config __maybe_unused, struct outstate *os = ctx; FILE *out = os->fh; - fprintf(out, "\"metric-value\" : %f, ", val); + fprintf(out, "\"metric-value\" : \"%f\", ", val); fprintf(out, "\"metric-unit\" : \"%s\"", unit); if (!config->metric_only) fprintf(out, "}"); diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index eeccab6751d7..1566a206ba42 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -403,12 +403,25 @@ static int prepare_metric(struct evsel **metric_events, if (!aggr) break; - /* - * If an event was scaled during stat gathering, reverse - * the scale before computing the metric. - */ - val = aggr->counts.val * (1.0 / metric_events[i]->scale); - source_count = evsel__source_count(metric_events[i]); + if (!metric_events[i]->supported) { + /* + * Not supported events will have a count of 0, + * which can be confusing in a + * metric. Explicitly set the value to NAN. Not + * counted events (enable time of 0) are read as + * 0. + */ + val = NAN; + source_count = 0; + } else { + /* + * If an event was scaled during stat gathering, + * reverse the scale before computing the + * metric. + */ + val = aggr->counts.val * (1.0 / metric_events[i]->scale); + source_count = evsel__source_count(metric_events[i]); + } } n = strdup(evsel__metric_id(metric_events[i])); if (!n) diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index b2ed9cc52265..63882a4db5c7 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -31,6 +31,13 @@ #include <bfd.h> #endif +#if defined(HAVE_LIBBFD_SUPPORT) || defined(HAVE_CPLUS_DEMANGLE_SUPPORT) +#ifndef DMGL_PARAMS +#define DMGL_PARAMS (1 << 0) /* Include function args */ +#define DMGL_ANSI (1 << 1) /* Include const, volatile, etc */ +#endif +#endif + #ifndef EM_AARCH64 #define EM_AARCH64 183 /* ARM 64 bit */ #endif @@ -271,6 +278,26 @@ static bool want_demangle(bool is_kernel_sym) return is_kernel_sym ? symbol_conf.demangle_kernel : symbol_conf.demangle; } +/* + * Demangle C++ function signature, typically replaced by demangle-cxx.cpp + * version. + */ +__weak char *cxx_demangle_sym(const char *str __maybe_unused, bool params __maybe_unused, + bool modifiers __maybe_unused) +{ +#ifdef HAVE_LIBBFD_SUPPORT + int flags = (params ? DMGL_PARAMS : 0) | (modifiers ? DMGL_ANSI : 0); + + return bfd_demangle(NULL, str, flags); +#elif defined(HAVE_CPLUS_DEMANGLE_SUPPORT) + int flags = (params ? DMGL_PARAMS : 0) | (modifiers ? DMGL_ANSI : 0); + + return cplus_demangle(str, flags); +#else + return NULL; +#endif +} + static char *demangle_sym(struct dso *dso, int kmodule, const char *elf_name) { char *demangled = NULL; diff --git a/tools/power/cpupower/lib/powercap.c b/tools/power/cpupower/lib/powercap.c index 0ce29ee4c2e4..a7a59c6bacda 100644 --- a/tools/power/cpupower/lib/powercap.c +++ b/tools/power/cpupower/lib/powercap.c @@ -40,25 +40,34 @@ static int sysfs_get_enabled(char *path, int *mode) { int fd; char yes_no; + int ret = 0; *mode = 0; fd = open(path, O_RDONLY); - if (fd == -1) - return -1; + if (fd == -1) { + ret = -1; + goto out; + } if (read(fd, &yes_no, 1) != 1) { - close(fd); - return -1; + ret = -1; + goto out_close; } if (yes_no == '1') { *mode = 1; - return 0; + goto out_close; } else if (yes_no == '0') { - return 0; + goto out_close; + } else { + ret = -1; + goto out_close; } - return -1; +out_close: + close(fd); +out: + return ret; } int powercap_get_enabled(int *mode) diff --git a/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c b/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c index e7d48cb563c0..ae6af354a81d 100644 --- a/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c +++ b/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c @@ -70,8 +70,8 @@ static int max_freq_mode; */ static unsigned long max_frequency; -static unsigned long long tsc_at_measure_start; -static unsigned long long tsc_at_measure_end; +static unsigned long long *tsc_at_measure_start; +static unsigned long long *tsc_at_measure_end; static unsigned long long *mperf_previous_count; static unsigned long long *aperf_previous_count; static unsigned long long *mperf_current_count; @@ -169,7 +169,7 @@ static int mperf_get_count_percent(unsigned int id, double *percent, aperf_diff = aperf_current_count[cpu] - aperf_previous_count[cpu]; if (max_freq_mode == MAX_FREQ_TSC_REF) { - tsc_diff = tsc_at_measure_end - tsc_at_measure_start; + tsc_diff = tsc_at_measure_end[cpu] - tsc_at_measure_start[cpu]; *percent = 100.0 * mperf_diff / tsc_diff; dprint("%s: TSC Ref - mperf_diff: %llu, tsc_diff: %llu\n", mperf_cstates[id].name, mperf_diff, tsc_diff); @@ -206,7 +206,7 @@ static int mperf_get_count_freq(unsigned int id, unsigned long long *count, if (max_freq_mode == MAX_FREQ_TSC_REF) { /* Calculate max_freq from TSC count */ - tsc_diff = tsc_at_measure_end - tsc_at_measure_start; + tsc_diff = tsc_at_measure_end[cpu] - tsc_at_measure_start[cpu]; time_diff = timespec_diff_us(time_start, time_end); max_frequency = tsc_diff / time_diff; } @@ -225,33 +225,27 @@ static int mperf_get_count_freq(unsigned int id, unsigned long long *count, static int mperf_start(void) { int cpu; - unsigned long long dbg; clock_gettime(CLOCK_REALTIME, &time_start); - mperf_get_tsc(&tsc_at_measure_start); - for (cpu = 0; cpu < cpu_count; cpu++) + for (cpu = 0; cpu < cpu_count; cpu++) { + mperf_get_tsc(&tsc_at_measure_start[cpu]); mperf_init_stats(cpu); + } - mperf_get_tsc(&dbg); - dprint("TSC diff: %llu\n", dbg - tsc_at_measure_start); return 0; } static int mperf_stop(void) { - unsigned long long dbg; int cpu; - for (cpu = 0; cpu < cpu_count; cpu++) + for (cpu = 0; cpu < cpu_count; cpu++) { mperf_measure_stats(cpu); + mperf_get_tsc(&tsc_at_measure_end[cpu]); + } - mperf_get_tsc(&tsc_at_measure_end); clock_gettime(CLOCK_REALTIME, &time_end); - - mperf_get_tsc(&dbg); - dprint("TSC diff: %llu\n", dbg - tsc_at_measure_end); - return 0; } @@ -353,7 +347,8 @@ struct cpuidle_monitor *mperf_register(void) aperf_previous_count = calloc(cpu_count, sizeof(unsigned long long)); mperf_current_count = calloc(cpu_count, sizeof(unsigned long long)); aperf_current_count = calloc(cpu_count, sizeof(unsigned long long)); - + tsc_at_measure_start = calloc(cpu_count, sizeof(unsigned long long)); + tsc_at_measure_end = calloc(cpu_count, sizeof(unsigned long long)); mperf_monitor.name_len = strlen(mperf_monitor.name); return &mperf_monitor; } @@ -364,6 +359,8 @@ void mperf_unregister(void) free(aperf_previous_count); free(mperf_current_count); free(aperf_current_count); + free(tsc_at_measure_start); + free(tsc_at_measure_end); free(is_valid); } diff --git a/tools/spi/spidev_test.c b/tools/spi/spidev_test.c index b0ca44c70e83..9179942d7f15 100644 --- a/tools/spi/spidev_test.c +++ b/tools/spi/spidev_test.c @@ -172,28 +172,37 @@ static void transfer(int fd, uint8_t const *tx, uint8_t const *rx, size_t len) static void print_usage(const char *prog) { - printf("Usage: %s [-DsbdlHOLC3vpNR24SI]\n", prog); - puts(" -D --device device to use (default /dev/spidev1.1)\n" - " -s --speed max speed (Hz)\n" - " -d --delay delay (usec)\n" - " -b --bpw bits per word\n" - " -i --input input data from a file (e.g. \"test.bin\")\n" - " -o --output output data to a file (e.g. \"results.bin\")\n" - " -l --loop loopback\n" - " -H --cpha clock phase\n" - " -O --cpol clock polarity\n" - " -L --lsb least significant bit first\n" - " -C --cs-high chip select active high\n" - " -3 --3wire SI/SO signals shared\n" - " -v --verbose Verbose (show tx buffer)\n" - " -p Send data (e.g. \"1234\\xde\\xad\")\n" - " -N --no-cs no chip select\n" - " -R --ready slave pulls low to pause\n" - " -2 --dual dual transfer\n" - " -4 --quad quad transfer\n" - " -8 --octal octal transfer\n" - " -S --size transfer size\n" - " -I --iter iterations\n"); + printf("Usage: %s [-2348CDFHILMNORSZbdilopsv]\n", prog); + puts("general device settings:\n" + " -D --device device to use (default /dev/spidev1.1)\n" + " -s --speed max speed (Hz)\n" + " -d --delay delay (usec)\n" + " -l --loop loopback\n" + "spi mode:\n" + " -H --cpha clock phase\n" + " -O --cpol clock polarity\n" + " -F --rx-cpha-flip flip CPHA on Rx only xfer\n" + "number of wires for transmission:\n" + " -2 --dual dual transfer\n" + " -4 --quad quad transfer\n" + " -8 --octal octal transfer\n" + " -3 --3wire SI/SO signals shared\n" + " -Z --3wire-hiz high impedance turnaround\n" + "data:\n" + " -i --input input data from a file (e.g. \"test.bin\")\n" + " -o --output output data to a file (e.g. \"results.bin\")\n" + " -p Send data (e.g. \"1234\\xde\\xad\")\n" + " -S --size transfer size\n" + " -I --iter iterations\n" + "additional parameters:\n" + " -b --bpw bits per word\n" + " -L --lsb least significant bit first\n" + " -C --cs-high chip select active high\n" + " -N --no-cs no chip select\n" + " -R --ready slave pulls low to pause\n" + " -M --mosi-idle-low leave mosi line low when idle\n" + "misc:\n" + " -v --verbose Verbose (show tx buffer)\n"); exit(1); } @@ -201,31 +210,34 @@ static void parse_opts(int argc, char *argv[]) { while (1) { static const struct option lopts[] = { - { "device", 1, 0, 'D' }, - { "speed", 1, 0, 's' }, - { "delay", 1, 0, 'd' }, - { "bpw", 1, 0, 'b' }, - { "input", 1, 0, 'i' }, - { "output", 1, 0, 'o' }, - { "loop", 0, 0, 'l' }, - { "cpha", 0, 0, 'H' }, - { "cpol", 0, 0, 'O' }, - { "lsb", 0, 0, 'L' }, - { "cs-high", 0, 0, 'C' }, - { "3wire", 0, 0, '3' }, - { "no-cs", 0, 0, 'N' }, - { "ready", 0, 0, 'R' }, - { "dual", 0, 0, '2' }, - { "verbose", 0, 0, 'v' }, - { "quad", 0, 0, '4' }, - { "octal", 0, 0, '8' }, - { "size", 1, 0, 'S' }, - { "iter", 1, 0, 'I' }, + { "device", 1, 0, 'D' }, + { "speed", 1, 0, 's' }, + { "delay", 1, 0, 'd' }, + { "loop", 0, 0, 'l' }, + { "cpha", 0, 0, 'H' }, + { "cpol", 0, 0, 'O' }, + { "rx-cpha-flip", 0, 0, 'F' }, + { "dual", 0, 0, '2' }, + { "quad", 0, 0, '4' }, + { "octal", 0, 0, '8' }, + { "3wire", 0, 0, '3' }, + { "3wire-hiz", 0, 0, 'Z' }, + { "input", 1, 0, 'i' }, + { "output", 1, 0, 'o' }, + { "size", 1, 0, 'S' }, + { "iter", 1, 0, 'I' }, + { "bpw", 1, 0, 'b' }, + { "lsb", 0, 0, 'L' }, + { "cs-high", 0, 0, 'C' }, + { "no-cs", 0, 0, 'N' }, + { "ready", 0, 0, 'R' }, + { "mosi-idle-low", 0, 0, 'M' }, + { "verbose", 0, 0, 'v' }, { NULL, 0, 0, 0 }, }; int c; - c = getopt_long(argc, argv, "D:s:d:b:i:o:lHOLC3NR248p:vS:I:", + c = getopt_long(argc, argv, "D:s:d:b:i:o:lHOLC3ZFMNR248p:vS:I:", lopts, NULL); if (c == -1) @@ -268,6 +280,15 @@ static void parse_opts(int argc, char *argv[]) case '3': mode |= SPI_3WIRE; break; + case 'Z': + mode |= SPI_3WIRE_HIZ; + break; + case 'F': + mode |= SPI_RX_CPHA_FLIP; + break; + case 'M': + mode |= SPI_MOSI_IDLE_LOW; + break; case 'N': mode |= SPI_NO_CS; break; diff --git a/tools/testing/cxl/Kbuild b/tools/testing/cxl/Kbuild index fba7bec96acd..6f9347ade82c 100644 --- a/tools/testing/cxl/Kbuild +++ b/tools/testing/cxl/Kbuild @@ -6,6 +6,7 @@ ldflags-y += --wrap=acpi_pci_find_root ldflags-y += --wrap=nvdimm_bus_register ldflags-y += --wrap=devm_cxl_port_enumerate_dports ldflags-y += --wrap=devm_cxl_setup_hdm +ldflags-y += --wrap=devm_cxl_enable_hdm ldflags-y += --wrap=devm_cxl_add_passthrough_decoder ldflags-y += --wrap=devm_cxl_enumerate_decoders ldflags-y += --wrap=cxl_await_media_ready diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c index ba572d03c687..34b48027b3de 100644 --- a/tools/testing/cxl/test/mem.c +++ b/tools/testing/cxl/test/mem.c @@ -1256,6 +1256,7 @@ static int cxl_mock_mem_probe(struct platform_device *pdev) if (rc) return rc; + cxlds->media_ready = true; rc = cxl_dev_state_identify(cxlds); if (rc) return rc; diff --git a/tools/testing/cxl/test/mock.c b/tools/testing/cxl/test/mock.c index de3933a776fd..284416527644 100644 --- a/tools/testing/cxl/test/mock.c +++ b/tools/testing/cxl/test/mock.c @@ -149,6 +149,21 @@ struct cxl_hdm *__wrap_devm_cxl_setup_hdm(struct cxl_port *port, } EXPORT_SYMBOL_NS_GPL(__wrap_devm_cxl_setup_hdm, CXL); +int __wrap_devm_cxl_enable_hdm(struct cxl_port *port, struct cxl_hdm *cxlhdm) +{ + int index, rc; + struct cxl_mock_ops *ops = get_cxl_mock_ops(&index); + + if (ops && ops->is_mock_port(port->uport)) + rc = 0; + else + rc = devm_cxl_enable_hdm(port, cxlhdm); + put_cxl_mock_ops(index); + + return rc; +} +EXPORT_SYMBOL_NS_GPL(__wrap_devm_cxl_enable_hdm, CXL); + int __wrap_devm_cxl_add_passthrough_decoder(struct cxl_port *port) { int rc, index; diff --git a/tools/testing/kunit/configs/all_tests.config b/tools/testing/kunit/configs/all_tests.config index f990cbb73250..0393940c706a 100644 --- a/tools/testing/kunit/configs/all_tests.config +++ b/tools/testing/kunit/configs/all_tests.config @@ -9,6 +9,8 @@ CONFIG_KUNIT=y CONFIG_KUNIT_EXAMPLE_TEST=y CONFIG_KUNIT_ALL_TESTS=y +CONFIG_FORTIFY_SOURCE=y + CONFIG_IIO=y CONFIG_EXT4_FS=y diff --git a/tools/testing/kunit/configs/arch_uml.config b/tools/testing/kunit/configs/arch_uml.config index e824ce43b05a..54ad8972681a 100644 --- a/tools/testing/kunit/configs/arch_uml.config +++ b/tools/testing/kunit/configs/arch_uml.config @@ -3,3 +3,6 @@ # Enable virtio/pci, as a lot of tests require it. CONFIG_VIRTIO_UML=y CONFIG_UML_PCI_OVER_VIRTIO=y + +# Enable FORTIFY_SOURCE for wider checking. +CONFIG_FORTIFY_SOURCE=y diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py index f01f94106129..7f648802caf6 100644 --- a/tools/testing/kunit/kunit_kernel.py +++ b/tools/testing/kunit/kunit_kernel.py @@ -92,7 +92,7 @@ class LinuxSourceTreeOperations: if stderr: # likely only due to build warnings print(stderr.decode()) - def start(self, params: List[str], build_dir: str) -> subprocess.Popen[str]: + def start(self, params: List[str], build_dir: str) -> subprocess.Popen: raise RuntimeError('not implemented!') @@ -113,7 +113,7 @@ class LinuxSourceTreeOperationsQemu(LinuxSourceTreeOperations): kconfig.merge_in_entries(base_kunitconfig) return kconfig - def start(self, params: List[str], build_dir: str) -> subprocess.Popen[str]: + def start(self, params: List[str], build_dir: str) -> subprocess.Popen: kernel_path = os.path.join(build_dir, self._kernel_path) qemu_command = ['qemu-system-' + self._qemu_arch, '-nodefaults', @@ -142,7 +142,7 @@ class LinuxSourceTreeOperationsUml(LinuxSourceTreeOperations): kconfig.merge_in_entries(base_kunitconfig) return kconfig - def start(self, params: List[str], build_dir: str) -> subprocess.Popen[str]: + def start(self, params: List[str], build_dir: str) -> subprocess.Popen: """Runs the Linux UML binary. Must be named 'linux'.""" linux_bin = os.path.join(build_dir, 'linux') params.extend(['mem=1G', 'console=tty', 'kunit_shutdown=halt']) diff --git a/tools/testing/kunit/mypy.ini b/tools/testing/kunit/mypy.ini new file mode 100644 index 000000000000..ddd288309efa --- /dev/null +++ b/tools/testing/kunit/mypy.ini @@ -0,0 +1,6 @@ +[mypy] +strict = True + +# E.g. we can't write subprocess.Popen[str] until Python 3.9+. +# But kunit.py tries to support Python 3.7+, so let's disable it. +disable_error_code = type-arg diff --git a/tools/testing/kunit/run_checks.py b/tools/testing/kunit/run_checks.py index 8208c3b3135e..c6d494ea3373 100755 --- a/tools/testing/kunit/run_checks.py +++ b/tools/testing/kunit/run_checks.py @@ -23,7 +23,7 @@ commands: Dict[str, Sequence[str]] = { 'kunit_tool_test.py': ['./kunit_tool_test.py'], 'kunit smoke test': ['./kunit.py', 'run', '--kunitconfig=lib/kunit', '--build_dir=kunit_run_checks'], 'pytype': ['/bin/sh', '-c', 'pytype *.py'], - 'mypy': ['mypy', '--strict', '--exclude', '_test.py$', '--exclude', 'qemu_configs/', '.'], + 'mypy': ['mypy', '--config-file', 'mypy.ini', '--exclude', '_test.py$', '--exclude', 'qemu_configs/', '.'], } # The user might not have mypy or pytype installed, skip them if so. diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile index caf32a9b9608..7527f738b4a1 100644 --- a/tools/testing/radix-tree/Makefile +++ b/tools/testing/radix-tree/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 -CFLAGS += -I. -I../../include -g -Og -Wall -D_LGPL_SOURCE -fsanitize=address \ - -fsanitize=undefined +CFLAGS += -I. -I../../include -I../../../lib -g -Og -Wall \ + -D_LGPL_SOURCE -fsanitize=address -fsanitize=undefined LDFLAGS += -fsanitize=address -fsanitize=undefined LDLIBS+= -lpthread -lurcu TARGETS = main idr-test multiorder xarray maple @@ -49,6 +49,7 @@ $(OFILES): Makefile *.h */*.h generated/map-shift.h generated/bit-length.h \ ../../../include/linux/xarray.h \ ../../../include/linux/maple_tree.h \ ../../../include/linux/radix-tree.h \ + ../../../lib/radix-tree.h \ ../../../include/linux/idr.h radix-tree.c: ../../../lib/radix-tree.c diff --git a/tools/testing/radix-tree/linux/init.h b/tools/testing/radix-tree/linux/init.h index 1bb0afc21309..81563c3dfce7 100644 --- a/tools/testing/radix-tree/linux/init.h +++ b/tools/testing/radix-tree/linux/init.h @@ -1 +1,2 @@ #define __init +#define __exit diff --git a/tools/testing/radix-tree/maple.c b/tools/testing/radix-tree/maple.c index 9286d3baa12d..03539d86cdf0 100644 --- a/tools/testing/radix-tree/maple.c +++ b/tools/testing/radix-tree/maple.c @@ -14,6 +14,7 @@ #include "test.h" #include <stdlib.h> #include <time.h> +#include "linux/init.h" #define module_init(x) #define module_exit(x) @@ -22,7 +23,6 @@ #define dump_stack() assert(0) #include "../../../lib/maple_tree.c" -#undef CONFIG_DEBUG_MAPLE_TREE #include "../../../lib/test_maple_tree.c" #define RCU_RANGE_COUNT 1000 @@ -81,7 +81,7 @@ static void check_mas_alloc_node_count(struct ma_state *mas) * check_new_node() - Check the creation of new nodes and error path * verification. */ -static noinline void check_new_node(struct maple_tree *mt) +static noinline void __init check_new_node(struct maple_tree *mt) { struct maple_node *mn, *mn2, *mn3; @@ -455,7 +455,7 @@ static noinline void check_new_node(struct maple_tree *mt) /* * Check erasing including RCU. */ -static noinline void check_erase(struct maple_tree *mt, unsigned long index, +static noinline void __init check_erase(struct maple_tree *mt, unsigned long index, void *ptr) { MT_BUG_ON(mt, mtree_test_erase(mt, index) != ptr); @@ -465,24 +465,24 @@ static noinline void check_erase(struct maple_tree *mt, unsigned long index, #define erase_check_insert(mt, i) check_insert(mt, set[i], entry[i%2]) #define erase_check_erase(mt, i) check_erase(mt, set[i], entry[i%2]) -static noinline void check_erase_testset(struct maple_tree *mt) +static noinline void __init check_erase_testset(struct maple_tree *mt) { - unsigned long set[] = { 5015, 5014, 5017, 25, 1000, - 1001, 1002, 1003, 1005, 0, - 6003, 6002, 6008, 6012, 6015, - 7003, 7002, 7008, 7012, 7015, - 8003, 8002, 8008, 8012, 8015, - 9003, 9002, 9008, 9012, 9015, - 10003, 10002, 10008, 10012, 10015, - 11003, 11002, 11008, 11012, 11015, - 12003, 12002, 12008, 12012, 12015, - 13003, 13002, 13008, 13012, 13015, - 14003, 14002, 14008, 14012, 14015, - 15003, 15002, 15008, 15012, 15015, - }; - - - void *ptr = &set; + static const unsigned long set[] = { 5015, 5014, 5017, 25, 1000, + 1001, 1002, 1003, 1005, 0, + 6003, 6002, 6008, 6012, 6015, + 7003, 7002, 7008, 7012, 7015, + 8003, 8002, 8008, 8012, 8015, + 9003, 9002, 9008, 9012, 9015, + 10003, 10002, 10008, 10012, 10015, + 11003, 11002, 11008, 11012, 11015, + 12003, 12002, 12008, 12012, 12015, + 13003, 13002, 13008, 13012, 13015, + 14003, 14002, 14008, 14012, 14015, + 15003, 15002, 15008, 15012, 15015, + }; + + + void *ptr = &check_erase_testset; void *entry[2] = { ptr, mt }; void *root_node; @@ -739,7 +739,7 @@ static noinline void check_erase_testset(struct maple_tree *mt) int mas_ce2_over_count(struct ma_state *mas_start, struct ma_state *mas_end, void *s_entry, unsigned long s_min, void *e_entry, unsigned long e_max, - unsigned long *set, int i, bool null_entry) + const unsigned long *set, int i, bool null_entry) { int count = 0, span = 0; unsigned long retry = 0; @@ -969,8 +969,8 @@ retry: } #if defined(CONFIG_64BIT) -static noinline void check_erase2_testset(struct maple_tree *mt, - unsigned long *set, unsigned long size) +static noinline void __init check_erase2_testset(struct maple_tree *mt, + const unsigned long *set, unsigned long size) { int entry_count = 0; int check = 0; @@ -1054,7 +1054,7 @@ static noinline void check_erase2_testset(struct maple_tree *mt, if (entry_count) MT_BUG_ON(mt, !mt_height(mt)); #if check_erase2_debug > 1 - mt_dump(mt); + mt_dump(mt, mt_dump_hex); #endif #if check_erase2_debug pr_err("Done\n"); @@ -1085,7 +1085,7 @@ static noinline void check_erase2_testset(struct maple_tree *mt, mas_for_each(&mas, foo, ULONG_MAX) { if (xa_is_zero(foo)) { if (addr == mas.index) { - mt_dump(mas.tree); + mt_dump(mas.tree, mt_dump_hex); pr_err("retry failed %lu - %lu\n", mas.index, mas.last); MT_BUG_ON(mt, 1); @@ -1114,11 +1114,11 @@ static noinline void check_erase2_testset(struct maple_tree *mt, /* These tests were pulled from KVM tree modifications which failed. */ -static noinline void check_erase2_sets(struct maple_tree *mt) +static noinline void __init check_erase2_sets(struct maple_tree *mt) { void *entry; unsigned long start = 0; - unsigned long set[] = { + static const unsigned long set[] = { STORE, 140737488347136, 140737488351231, STORE, 140721266458624, 140737488351231, ERASE, 140721266458624, 140737488351231, @@ -1136,7 +1136,7 @@ ERASE, 140253902692352, 140253902864383, STORE, 140253902692352, 140253902696447, STORE, 140253902696448, 140253902864383, }; - unsigned long set2[] = { + static const unsigned long set2[] = { STORE, 140737488347136, 140737488351231, STORE, 140735933583360, 140737488351231, ERASE, 140735933583360, 140737488351231, @@ -1160,7 +1160,7 @@ STORE, 140277094813696, 140277094821887, STORE, 140277094821888, 140277094825983, STORE, 140735933906944, 140735933911039, }; - unsigned long set3[] = { + static const unsigned long set3[] = { STORE, 140737488347136, 140737488351231, STORE, 140735790264320, 140737488351231, ERASE, 140735790264320, 140737488351231, @@ -1203,7 +1203,7 @@ STORE, 47135835840512, 47135835885567, STORE, 47135835885568, 47135835893759, }; - unsigned long set4[] = { + static const unsigned long set4[] = { STORE, 140737488347136, 140737488351231, STORE, 140728251703296, 140737488351231, ERASE, 140728251703296, 140737488351231, @@ -1224,7 +1224,7 @@ ERASE, 47646523277312, 47646523445247, STORE, 47646523277312, 47646523400191, }; - unsigned long set5[] = { + static const unsigned long set5[] = { STORE, 140737488347136, 140737488351231, STORE, 140726874062848, 140737488351231, ERASE, 140726874062848, 140737488351231, @@ -1357,7 +1357,7 @@ STORE, 47884791619584, 47884791623679, STORE, 47884791623680, 47884791627775, }; - unsigned long set6[] = { + static const unsigned long set6[] = { STORE, 140737488347136, 140737488351231, STORE, 140722999021568, 140737488351231, ERASE, 140722999021568, 140737488351231, @@ -1489,7 +1489,7 @@ ERASE, 47430432014336, 47430432022527, STORE, 47430432014336, 47430432018431, STORE, 47430432018432, 47430432022527, }; - unsigned long set7[] = { + static const unsigned long set7[] = { STORE, 140737488347136, 140737488351231, STORE, 140729808330752, 140737488351231, ERASE, 140729808330752, 140737488351231, @@ -1621,7 +1621,7 @@ ERASE, 47439987130368, 47439987138559, STORE, 47439987130368, 47439987134463, STORE, 47439987134464, 47439987138559, }; - unsigned long set8[] = { + static const unsigned long set8[] = { STORE, 140737488347136, 140737488351231, STORE, 140722482974720, 140737488351231, ERASE, 140722482974720, 140737488351231, @@ -1754,7 +1754,7 @@ STORE, 47708488638464, 47708488642559, STORE, 47708488642560, 47708488646655, }; - unsigned long set9[] = { + static const unsigned long set9[] = { STORE, 140737488347136, 140737488351231, STORE, 140736427839488, 140737488351231, ERASE, 140736427839488, 140736427839488, @@ -5620,7 +5620,7 @@ ERASE, 47906195480576, 47906195480576, STORE, 94641242615808, 94641242750975, }; - unsigned long set10[] = { + static const unsigned long set10[] = { STORE, 140737488347136, 140737488351231, STORE, 140736427839488, 140737488351231, ERASE, 140736427839488, 140736427839488, @@ -9484,7 +9484,7 @@ STORE, 139726599680000, 139726599684095, ERASE, 47906195480576, 47906195480576, STORE, 94641242615808, 94641242750975, }; - unsigned long set11[] = { + static const unsigned long set11[] = { STORE, 140737488347136, 140737488351231, STORE, 140732658499584, 140737488351231, ERASE, 140732658499584, 140732658499584, @@ -9510,7 +9510,7 @@ STORE, 140732658565120, 140732658569215, STORE, 140732658552832, 140732658565119, }; - unsigned long set12[] = { /* contains 12 values. */ + static const unsigned long set12[] = { /* contains 12 values. */ STORE, 140737488347136, 140737488351231, STORE, 140732658499584, 140737488351231, ERASE, 140732658499584, 140732658499584, @@ -9537,7 +9537,7 @@ STORE, 140732658552832, 140732658565119, STORE, 140014592741375, 140014592741375, /* contrived */ STORE, 140014592733184, 140014592741376, /* creates first entry retry. */ }; - unsigned long set13[] = { + static const unsigned long set13[] = { STORE, 140373516247040, 140373516251135,/*: ffffa2e7b0e10d80 */ STORE, 140373516251136, 140373516255231,/*: ffffa2e7b1195d80 */ STORE, 140373516255232, 140373516443647,/*: ffffa2e7b0e109c0 */ @@ -9550,7 +9550,7 @@ STORE, 140373518684160, 140373518688254,/*: ffffa2e7b05fec00 */ STORE, 140373518688256, 140373518692351,/*: ffffa2e7bfbdcd80 */ STORE, 140373518692352, 140373518696447,/*: ffffa2e7b0749e40 */ }; - unsigned long set14[] = { + static const unsigned long set14[] = { STORE, 140737488347136, 140737488351231, STORE, 140731667996672, 140737488351231, SNULL, 140731668000767, 140737488351231, @@ -9834,7 +9834,7 @@ SNULL, 139826136543232, 139826136809471, STORE, 139826136809472, 139826136842239, STORE, 139826136543232, 139826136809471, }; - unsigned long set15[] = { + static const unsigned long set15[] = { STORE, 140737488347136, 140737488351231, STORE, 140722061451264, 140737488351231, SNULL, 140722061455359, 140737488351231, @@ -10119,7 +10119,7 @@ STORE, 139906808958976, 139906808991743, STORE, 139906808692736, 139906808958975, }; - unsigned long set16[] = { + static const unsigned long set16[] = { STORE, 94174808662016, 94174809321471, STORE, 94174811414528, 94174811426815, STORE, 94174811426816, 94174811430911, @@ -10330,7 +10330,7 @@ STORE, 139921865613312, 139921865617407, STORE, 139921865547776, 139921865564159, }; - unsigned long set17[] = { + static const unsigned long set17[] = { STORE, 94397057224704, 94397057646591, STORE, 94397057650688, 94397057691647, STORE, 94397057691648, 94397057695743, @@ -10392,7 +10392,7 @@ STORE, 140720477511680, 140720477646847, STORE, 140720478302208, 140720478314495, STORE, 140720478314496, 140720478318591, }; - unsigned long set18[] = { + static const unsigned long set18[] = { STORE, 140737488347136, 140737488351231, STORE, 140724953673728, 140737488351231, SNULL, 140724953677823, 140737488351231, @@ -10425,7 +10425,7 @@ STORE, 140222970597376, 140222970605567, ERASE, 140222970597376, 140222970605567, STORE, 140222970597376, 140222970605567, }; - unsigned long set19[] = { + static const unsigned long set19[] = { STORE, 140737488347136, 140737488351231, STORE, 140725182459904, 140737488351231, SNULL, 140725182463999, 140737488351231, @@ -10694,7 +10694,7 @@ STORE, 140656836775936, 140656836780031, STORE, 140656787476480, 140656791920639, ERASE, 140656774639616, 140656779083775, }; - unsigned long set20[] = { + static const unsigned long set20[] = { STORE, 140737488347136, 140737488351231, STORE, 140735952392192, 140737488351231, SNULL, 140735952396287, 140737488351231, @@ -10850,7 +10850,7 @@ STORE, 140590386819072, 140590386823167, STORE, 140590386823168, 140590386827263, SNULL, 140590376591359, 140590376595455, }; - unsigned long set21[] = { + static const unsigned long set21[] = { STORE, 93874710941696, 93874711363583, STORE, 93874711367680, 93874711408639, STORE, 93874711408640, 93874711412735, @@ -10920,7 +10920,7 @@ ERASE, 140708393312256, 140708393316351, ERASE, 140708393308160, 140708393312255, ERASE, 140708393291776, 140708393308159, }; - unsigned long set22[] = { + static const unsigned long set22[] = { STORE, 93951397134336, 93951397183487, STORE, 93951397183488, 93951397728255, STORE, 93951397728256, 93951397826559, @@ -11047,7 +11047,7 @@ STORE, 140551361253376, 140551361519615, ERASE, 140551361253376, 140551361519615, }; - unsigned long set23[] = { + static const unsigned long set23[] = { STORE, 94014447943680, 94014448156671, STORE, 94014450253824, 94014450257919, STORE, 94014450257920, 94014450266111, @@ -14371,7 +14371,7 @@ SNULL, 140175956627455, 140175985139711, STORE, 140175927242752, 140175956627455, STORE, 140175956627456, 140175985139711, }; - unsigned long set24[] = { + static const unsigned long set24[] = { STORE, 140737488347136, 140737488351231, STORE, 140735281639424, 140737488351231, SNULL, 140735281643519, 140737488351231, @@ -15533,7 +15533,7 @@ ERASE, 139635393024000, 139635401412607, ERASE, 139635384627200, 139635384631295, ERASE, 139635384631296, 139635393019903, }; - unsigned long set25[] = { + static const unsigned long set25[] = { STORE, 140737488347136, 140737488351231, STORE, 140737488343040, 140737488351231, STORE, 140722547441664, 140737488351231, @@ -22321,7 +22321,7 @@ STORE, 140249652703232, 140249682087935, STORE, 140249682087936, 140249710600191, }; - unsigned long set26[] = { + static const unsigned long set26[] = { STORE, 140737488347136, 140737488351231, STORE, 140729464770560, 140737488351231, SNULL, 140729464774655, 140737488351231, @@ -22345,7 +22345,7 @@ ERASE, 140109040951296, 140109040959487, STORE, 140109040955392, 140109040959487, ERASE, 140109040955392, 140109040959487, }; - unsigned long set27[] = { + static const unsigned long set27[] = { STORE, 140737488347136, 140737488351231, STORE, 140726128070656, 140737488351231, SNULL, 140726128074751, 140737488351231, @@ -22741,7 +22741,7 @@ STORE, 140415509696512, 140415535910911, ERASE, 140415537422336, 140415562588159, STORE, 140415482433536, 140415509696511, }; - unsigned long set28[] = { + static const unsigned long set28[] = { STORE, 140737488347136, 140737488351231, STORE, 140722475622400, 140737488351231, SNULL, 140722475626495, 140737488351231, @@ -22809,7 +22809,7 @@ STORE, 139918413348864, 139918413352959, ERASE, 139918413316096, 139918413344767, STORE, 93865848528896, 93865848664063, }; - unsigned long set29[] = { + static const unsigned long set29[] = { STORE, 140737488347136, 140737488351231, STORE, 140734467944448, 140737488351231, SNULL, 140734467948543, 140737488351231, @@ -23684,7 +23684,7 @@ ERASE, 140143079972864, 140143088361471, ERASE, 140143205793792, 140143205797887, ERASE, 140143205797888, 140143214186495, }; - unsigned long set30[] = { + static const unsigned long set30[] = { STORE, 140737488347136, 140737488351231, STORE, 140733436743680, 140737488351231, SNULL, 140733436747775, 140737488351231, @@ -24566,7 +24566,7 @@ ERASE, 140165225893888, 140165225897983, ERASE, 140165225897984, 140165234286591, ERASE, 140165058105344, 140165058109439, }; - unsigned long set31[] = { + static const unsigned long set31[] = { STORE, 140737488347136, 140737488351231, STORE, 140730890784768, 140737488351231, SNULL, 140730890788863, 140737488351231, @@ -25379,7 +25379,7 @@ ERASE, 140623906590720, 140623914979327, ERASE, 140622950277120, 140622950281215, ERASE, 140622950281216, 140622958669823, }; - unsigned long set32[] = { + static const unsigned long set32[] = { STORE, 140737488347136, 140737488351231, STORE, 140731244212224, 140737488351231, SNULL, 140731244216319, 140737488351231, @@ -26175,7 +26175,7 @@ ERASE, 140400417288192, 140400425676799, ERASE, 140400283066368, 140400283070463, ERASE, 140400283070464, 140400291459071, }; - unsigned long set33[] = { + static const unsigned long set33[] = { STORE, 140737488347136, 140737488351231, STORE, 140734562918400, 140737488351231, SNULL, 140734562922495, 140737488351231, @@ -26317,7 +26317,7 @@ STORE, 140582961786880, 140583003750399, ERASE, 140582961786880, 140583003750399, }; - unsigned long set34[] = { + static const unsigned long set34[] = { STORE, 140737488347136, 140737488351231, STORE, 140731327180800, 140737488351231, SNULL, 140731327184895, 140737488351231, @@ -27198,7 +27198,7 @@ ERASE, 140012522094592, 140012530483199, ERASE, 140012033142784, 140012033146879, ERASE, 140012033146880, 140012041535487, }; - unsigned long set35[] = { + static const unsigned long set35[] = { STORE, 140737488347136, 140737488351231, STORE, 140730536939520, 140737488351231, SNULL, 140730536943615, 140737488351231, @@ -27955,7 +27955,7 @@ ERASE, 140474471936000, 140474480324607, ERASE, 140474396430336, 140474396434431, ERASE, 140474396434432, 140474404823039, }; - unsigned long set36[] = { + static const unsigned long set36[] = { STORE, 140737488347136, 140737488351231, STORE, 140723893125120, 140737488351231, SNULL, 140723893129215, 140737488351231, @@ -28816,7 +28816,7 @@ ERASE, 140121890357248, 140121898745855, ERASE, 140121269587968, 140121269592063, ERASE, 140121269592064, 140121277980671, }; - unsigned long set37[] = { + static const unsigned long set37[] = { STORE, 140737488347136, 140737488351231, STORE, 140722404016128, 140737488351231, SNULL, 140722404020223, 140737488351231, @@ -28942,7 +28942,7 @@ STORE, 139759821246464, 139759888355327, ERASE, 139759821246464, 139759888355327, ERASE, 139759888355328, 139759955464191, }; - unsigned long set38[] = { + static const unsigned long set38[] = { STORE, 140737488347136, 140737488351231, STORE, 140730666221568, 140737488351231, SNULL, 140730666225663, 140737488351231, @@ -29752,7 +29752,7 @@ ERASE, 140613504712704, 140613504716799, ERASE, 140613504716800, 140613513105407, }; - unsigned long set39[] = { + static const unsigned long set39[] = { STORE, 140737488347136, 140737488351231, STORE, 140736271417344, 140737488351231, SNULL, 140736271421439, 140737488351231, @@ -30124,7 +30124,7 @@ STORE, 140325364428800, 140325372821503, STORE, 140325356036096, 140325364428799, SNULL, 140325364432895, 140325372821503, }; - unsigned long set40[] = { + static const unsigned long set40[] = { STORE, 140737488347136, 140737488351231, STORE, 140734309167104, 140737488351231, SNULL, 140734309171199, 140737488351231, @@ -30875,7 +30875,7 @@ ERASE, 140320289300480, 140320289304575, ERASE, 140320289304576, 140320297693183, ERASE, 140320163409920, 140320163414015, }; - unsigned long set41[] = { + static const unsigned long set41[] = { STORE, 140737488347136, 140737488351231, STORE, 140728157171712, 140737488351231, SNULL, 140728157175807, 140737488351231, @@ -31185,7 +31185,7 @@ STORE, 94376135090176, 94376135094271, STORE, 94376135094272, 94376135098367, SNULL, 94376135094272, 94377208836095, }; - unsigned long set42[] = { + static const unsigned long set42[] = { STORE, 314572800, 1388314623, STORE, 1462157312, 1462169599, STORE, 1462169600, 1462185983, @@ -33862,7 +33862,7 @@ SNULL, 3798999040, 3799101439, */ }; - unsigned long set43[] = { + static const unsigned long set43[] = { STORE, 140737488347136, 140737488351231, STORE, 140734187720704, 140737488351231, SNULL, 140734187724800, 140737488351231, @@ -34513,7 +34513,7 @@ static void *rcu_reader_rev(void *ptr) if (mas.index != r_start) { alt = xa_mk_value(index + i * 2 + 1 + RCU_RANGE_COUNT); - mt_dump(test->mt); + mt_dump(test->mt, mt_dump_dec); printk("Error: %lu-%lu %p != %lu-%lu %p %p line %d i %d\n", mas.index, mas.last, entry, r_start, r_end, expected, alt, @@ -34996,7 +34996,7 @@ void run_check_rcu_slowread(struct maple_tree *mt, struct rcu_test_struct *vals) MT_BUG_ON(mt, !vals->seen_entry3); MT_BUG_ON(mt, !vals->seen_both); } -static noinline void check_rcu_simulated(struct maple_tree *mt) +static noinline void __init check_rcu_simulated(struct maple_tree *mt) { unsigned long i, nr_entries = 1000; unsigned long target = 4320; @@ -35157,7 +35157,7 @@ static noinline void check_rcu_simulated(struct maple_tree *mt) rcu_unregister_thread(); } -static noinline void check_rcu_threaded(struct maple_tree *mt) +static noinline void __init check_rcu_threaded(struct maple_tree *mt) { unsigned long i, nr_entries = 1000; struct rcu_test_struct vals; @@ -35259,6 +35259,7 @@ static void mas_dfs_preorder(struct ma_state *mas) struct maple_enode *prev; unsigned char end, slot = 0; + unsigned long *pivots; if (mas->node == MAS_START) { mas_start(mas); @@ -35291,6 +35292,9 @@ walk_up: mas_ascend(mas); goto walk_up; } + pivots = ma_pivots(mte_to_node(prev), mte_node_type(prev)); + mas->max = mas_safe_pivot(mas, pivots, slot, mte_node_type(prev)); + mas->min = mas_safe_min(mas, pivots, slot); return; done: @@ -35366,7 +35370,7 @@ static void check_dfs_preorder(struct maple_tree *mt) /* End of depth first search tests */ /* Preallocation testing */ -static noinline void check_prealloc(struct maple_tree *mt) +static noinline void __init check_prealloc(struct maple_tree *mt) { unsigned long i, max = 100; unsigned long allocated; @@ -35494,7 +35498,7 @@ static noinline void check_prealloc(struct maple_tree *mt) /* End of preallocation testing */ /* Spanning writes, writes that span nodes and layers of the tree */ -static noinline void check_spanning_write(struct maple_tree *mt) +static noinline void __init check_spanning_write(struct maple_tree *mt) { unsigned long i, max = 5000; MA_STATE(mas, mt, 1200, 2380); @@ -35662,7 +35666,7 @@ static noinline void check_spanning_write(struct maple_tree *mt) /* End of spanning write testing */ /* Writes to a NULL area that are adjacent to other NULLs */ -static noinline void check_null_expand(struct maple_tree *mt) +static noinline void __init check_null_expand(struct maple_tree *mt) { unsigned long i, max = 100; unsigned char data_end; @@ -35723,7 +35727,7 @@ static noinline void check_null_expand(struct maple_tree *mt) /* End of NULL area expansions */ /* Checking for no memory is best done outside the kernel */ -static noinline void check_nomem(struct maple_tree *mt) +static noinline void __init check_nomem(struct maple_tree *mt) { MA_STATE(ms, mt, 1, 1); @@ -35758,7 +35762,7 @@ static noinline void check_nomem(struct maple_tree *mt) mtree_destroy(mt); } -static noinline void check_locky(struct maple_tree *mt) +static noinline void __init check_locky(struct maple_tree *mt) { MA_STATE(ms, mt, 2, 2); MA_STATE(reader, mt, 2, 2); @@ -35780,10 +35784,10 @@ void farmer_tests(void) struct maple_node *node; DEFINE_MTREE(tree); - mt_dump(&tree); + mt_dump(&tree, mt_dump_dec); tree.ma_root = xa_mk_value(0); - mt_dump(&tree); + mt_dump(&tree, mt_dump_dec); node = mt_alloc_one(GFP_KERNEL); node->parent = (void *)((unsigned long)(&tree) | 1); @@ -35793,7 +35797,7 @@ void farmer_tests(void) node->mr64.pivot[1] = 1; node->mr64.pivot[2] = 0; tree.ma_root = mt_mk_node(node, maple_leaf_64); - mt_dump(&tree); + mt_dump(&tree, mt_dump_dec); node->parent = ma_parent_ptr(node); ma_free_rcu(node); diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 90a62cf75008..6b456c5ecec1 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -4,6 +4,7 @@ TARGETS += amd-pstate TARGETS += arm64 TARGETS += bpf TARGETS += breakpoints +TARGETS += cachestat TARGETS += capabilities TARGETS += cgroup TARGETS += clone3 @@ -144,10 +145,12 @@ ifneq ($(KBUILD_OUTPUT),) abs_objtree := $(realpath $(abs_objtree)) BUILD := $(abs_objtree)/kselftest KHDR_INCLUDES := -isystem ${abs_objtree}/usr/include + KHDR_DIR := ${abs_objtree}/usr/include else BUILD := $(CURDIR) abs_srctree := $(shell cd $(top_srcdir) && pwd) KHDR_INCLUDES := -isystem ${abs_srctree}/usr/include + KHDR_DIR := ${abs_srctree}/usr/include DEFAULT_INSTALL_HDR_PATH := 1 endif @@ -161,7 +164,7 @@ export KHDR_INCLUDES # all isn't the first target in the file. .DEFAULT_GOAL := all -all: +all: kernel_header_files @ret=1; \ for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ @@ -172,6 +175,23 @@ all: ret=$$((ret * $$?)); \ done; exit $$ret; +kernel_header_files: + @ls $(KHDR_DIR)/linux/*.h >/dev/null 2>/dev/null; \ + if [ $$? -ne 0 ]; then \ + RED='\033[1;31m'; \ + NOCOLOR='\033[0m'; \ + echo; \ + echo -e "$${RED}error$${NOCOLOR}: missing kernel header files."; \ + echo "Please run this and try again:"; \ + echo; \ + echo " cd $(top_srcdir)"; \ + echo " make headers"; \ + echo; \ + exit 1; \ + fi + +.PHONY: kernel_header_files + run_tests: all @for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ diff --git a/tools/testing/selftests/alsa/pcm-test.c b/tools/testing/selftests/alsa/pcm-test.c index 3e390fe67eb9..b7eef32addb4 100644 --- a/tools/testing/selftests/alsa/pcm-test.c +++ b/tools/testing/selftests/alsa/pcm-test.c @@ -381,7 +381,7 @@ __format: goto __close; } if (rrate != rate) { - snprintf(msg, sizeof(msg), "rate mismatch %ld != %ld", rate, rrate); + snprintf(msg, sizeof(msg), "rate mismatch %ld != %d", rate, rrate); goto __close; } rperiod_size = period_size; @@ -447,24 +447,24 @@ __format: frames = snd_pcm_writei(handle, samples, rate); if (frames < 0) { snprintf(msg, sizeof(msg), - "Write failed: expected %d, wrote %li", rate, frames); + "Write failed: expected %ld, wrote %li", rate, frames); goto __close; } if (frames < rate) { snprintf(msg, sizeof(msg), - "expected %d, wrote %li", rate, frames); + "expected %ld, wrote %li", rate, frames); goto __close; } } else { frames = snd_pcm_readi(handle, samples, rate); if (frames < 0) { snprintf(msg, sizeof(msg), - "expected %d, wrote %li", rate, frames); + "expected %ld, wrote %li", rate, frames); goto __close; } if (frames < rate) { snprintf(msg, sizeof(msg), - "expected %d, wrote %li", rate, frames); + "expected %ld, wrote %li", rate, frames); goto __close; } } diff --git a/tools/testing/selftests/arm64/abi/hwcap.c b/tools/testing/selftests/arm64/abi/hwcap.c index 93333a90bf3a..d4ad813fed10 100644 --- a/tools/testing/selftests/arm64/abi/hwcap.c +++ b/tools/testing/selftests/arm64/abi/hwcap.c @@ -39,6 +39,20 @@ static void cssc_sigill(void) asm volatile(".inst 0xdac01c00" : : : "x0"); } +static void mops_sigill(void) +{ + char dst[1], src[1]; + register char *dstp asm ("x0") = dst; + register char *srcp asm ("x1") = src; + register long size asm ("x2") = 1; + + /* CPYP [x0]!, [x1]!, x2! */ + asm volatile(".inst 0x1d010440" + : "+r" (dstp), "+r" (srcp), "+r" (size) + : + : "cc", "memory"); +} + static void rng_sigill(void) { asm volatile("mrs x0, S3_3_C2_C4_0" : : : "x0"); @@ -210,6 +224,14 @@ static const struct hwcap_data { .sigill_fn = cssc_sigill, }, { + .name = "MOPS", + .at_hwcap = AT_HWCAP2, + .hwcap_bit = HWCAP2_MOPS, + .cpuinfo = "mops", + .sigill_fn = mops_sigill, + .sigill_reliable = true, + }, + { .name = "RNG", .at_hwcap = AT_HWCAP2, .hwcap_bit = HWCAP2_RNG, diff --git a/tools/testing/selftests/arm64/abi/ptrace.c b/tools/testing/selftests/arm64/abi/ptrace.c index be952511af22..abe4d58d731d 100644 --- a/tools/testing/selftests/arm64/abi/ptrace.c +++ b/tools/testing/selftests/arm64/abi/ptrace.c @@ -20,7 +20,7 @@ #include "../../kselftest.h" -#define EXPECTED_TESTS 7 +#define EXPECTED_TESTS 11 #define MAX_TPIDRS 2 @@ -132,6 +132,34 @@ static void test_tpidr(pid_t child) } } +static void test_hw_debug(pid_t child, int type, const char *type_name) +{ + struct user_hwdebug_state state; + struct iovec iov; + int slots, arch, ret; + + iov.iov_len = sizeof(state); + iov.iov_base = &state; + + /* Should be able to read the values */ + ret = ptrace(PTRACE_GETREGSET, child, type, &iov); + ksft_test_result(ret == 0, "read_%s\n", type_name); + + if (ret == 0) { + /* Low 8 bits is the number of slots, next 4 bits the arch */ + slots = state.dbg_info & 0xff; + arch = (state.dbg_info >> 8) & 0xf; + + ksft_print_msg("%s version %d with %d slots\n", type_name, + arch, slots); + + /* 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"); + } +} + static int do_child(void) { if (ptrace(PTRACE_TRACEME, -1, NULL, NULL)) @@ -207,6 +235,8 @@ static int do_parent(pid_t child) ksft_print_msg("Parent is %d, child is %d\n", getpid(), child); test_tpidr(child); + test_hw_debug(child, NT_ARM_HW_WATCH, "NT_ARM_HW_WATCH"); + test_hw_debug(child, NT_ARM_HW_BREAK, "NT_ARM_HW_BREAK"); ret = EXIT_SUCCESS; diff --git a/tools/testing/selftests/arm64/signal/.gitignore b/tools/testing/selftests/arm64/signal/.gitignore index 8ab4c86837fd..839e3a252629 100644 --- a/tools/testing/selftests/arm64/signal/.gitignore +++ b/tools/testing/selftests/arm64/signal/.gitignore @@ -4,7 +4,7 @@ fake_sigreturn_* sme_* ssve_* sve_* -tpidr2_siginfo +tpidr2_* za_* zt_* !*.[ch] diff --git a/tools/testing/selftests/arm64/signal/test_signals_utils.c b/tools/testing/selftests/arm64/signal/test_signals_utils.c index 40be8443949d..0dc948db3a4a 100644 --- a/tools/testing/selftests/arm64/signal/test_signals_utils.c +++ b/tools/testing/selftests/arm64/signal/test_signals_utils.c @@ -249,7 +249,8 @@ static void default_handler(int signum, siginfo_t *si, void *uc) fprintf(stderr, "-- Timeout !\n"); } else { fprintf(stderr, - "-- RX UNEXPECTED SIGNAL: %d\n", signum); + "-- RX UNEXPECTED SIGNAL: %d code %d address %p\n", + signum, si->si_code, si->si_addr); } default_result(current, 1); } diff --git a/tools/testing/selftests/arm64/signal/testcases/tpidr2_restore.c b/tools/testing/selftests/arm64/signal/testcases/tpidr2_restore.c new file mode 100644 index 000000000000..f9a86c00c28c --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/tpidr2_restore.c @@ -0,0 +1,86 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2023 ARM Limited + * + * Verify that the TPIDR2 register context in signal frames is restored. + */ + +#include <signal.h> +#include <ucontext.h> +#include <sys/auxv.h> +#include <sys/prctl.h> +#include <unistd.h> +#include <asm/sigcontext.h> + +#include "test_signals_utils.h" +#include "testcases.h" + +#define SYS_TPIDR2 "S3_3_C13_C0_5" + +static uint64_t get_tpidr2(void) +{ + uint64_t val; + + asm volatile ( + "mrs %0, " SYS_TPIDR2 "\n" + : "=r"(val) + : + : "cc"); + + return val; +} + +static void set_tpidr2(uint64_t val) +{ + asm volatile ( + "msr " SYS_TPIDR2 ", %0\n" + : + : "r"(val) + : "cc"); +} + + +static uint64_t initial_tpidr2; + +static bool save_tpidr2(struct tdescr *td) +{ + initial_tpidr2 = get_tpidr2(); + fprintf(stderr, "Initial TPIDR2: %lx\n", initial_tpidr2); + + return true; +} + +static int modify_tpidr2(struct tdescr *td, siginfo_t *si, ucontext_t *uc) +{ + uint64_t my_tpidr2 = get_tpidr2(); + + my_tpidr2++; + fprintf(stderr, "Setting TPIDR2 to %lx\n", my_tpidr2); + set_tpidr2(my_tpidr2); + + return 0; +} + +static void check_tpidr2(struct tdescr *td) +{ + uint64_t tpidr2 = get_tpidr2(); + + td->pass = tpidr2 == initial_tpidr2; + + if (td->pass) + fprintf(stderr, "TPIDR2 restored\n"); + else + fprintf(stderr, "TPIDR2 was %lx but is now %lx\n", + initial_tpidr2, tpidr2); +} + +struct tdescr tde = { + .name = "TPIDR2 restore", + .descr = "Validate that TPIDR2 is restored from the sigframe", + .feats_required = FEAT_SME, + .timeout = 3, + .sig_trig = SIGUSR1, + .init = save_tpidr2, + .run = modify_tpidr2, + .check_result = check_tpidr2, +}; diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index c49e5403ad0e..28d2c77262be 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -197,7 +197,7 @@ $(OUTPUT)/urandom_read: urandom_read.c urandom_read_aux.c $(OUTPUT)/liburandom_r $(OUTPUT)/sign-file: ../../../../scripts/sign-file.c $(call msg,SIGN-FILE,,$@) - $(Q)$(CC) $(shell $(HOSTPKG_CONFIG)--cflags libcrypto 2> /dev/null) \ + $(Q)$(CC) $(shell $(HOSTPKG_CONFIG) --cflags libcrypto 2> /dev/null) \ $< -o $@ \ $(shell $(HOSTPKG_CONFIG) --libs libcrypto 2> /dev/null || echo -lcrypto) diff --git a/tools/testing/selftests/bpf/prog_tests/inner_array_lookup.c b/tools/testing/selftests/bpf/prog_tests/inner_array_lookup.c new file mode 100644 index 000000000000..9ab4cd195108 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/inner_array_lookup.c @@ -0,0 +1,31 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <test_progs.h> + +#include "inner_array_lookup.skel.h" + +void test_inner_array_lookup(void) +{ + int map1_fd, err; + int key = 3; + int val = 1; + struct inner_array_lookup *skel; + + skel = inner_array_lookup__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_load_skeleton")) + return; + + err = inner_array_lookup__attach(skel); + if (!ASSERT_OK(err, "skeleton_attach")) + goto cleanup; + + map1_fd = bpf_map__fd(skel->maps.inner_map1); + bpf_map_update_elem(map1_fd, &key, &val, 0); + + /* Probe should have set the element at index 3 to 2 */ + bpf_map_lookup_elem(map1_fd, &key, &val); + ASSERT_EQ(val, 2, "value_is_2"); + +cleanup: + inner_array_lookup__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index 0ce25a967481..064cc5e8d9ad 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -2,6 +2,7 @@ // Copyright (c) 2020 Cloudflare #include <error.h> #include <netinet/tcp.h> +#include <sys/epoll.h> #include "test_progs.h" #include "test_skmsg_load_helpers.skel.h" @@ -9,8 +10,12 @@ #include "test_sockmap_invalid_update.skel.h" #include "test_sockmap_skb_verdict_attach.skel.h" #include "test_sockmap_progs_query.skel.h" +#include "test_sockmap_pass_prog.skel.h" +#include "test_sockmap_drop_prog.skel.h" #include "bpf_iter_sockmap.skel.h" +#include "sockmap_helpers.h" + #define TCP_REPAIR 19 /* TCP sock is under repair right now */ #define TCP_REPAIR_ON 1 @@ -350,6 +355,126 @@ out: test_sockmap_progs_query__destroy(skel); } +#define MAX_EVENTS 10 +static void test_sockmap_skb_verdict_shutdown(void) +{ + struct epoll_event ev, events[MAX_EVENTS]; + int n, err, map, verdict, s, c1, p1; + struct test_sockmap_pass_prog *skel; + int epollfd; + int zero = 0; + char b; + + skel = test_sockmap_pass_prog__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + return; + + verdict = bpf_program__fd(skel->progs.prog_skb_verdict); + map = bpf_map__fd(skel->maps.sock_map_rx); + + err = bpf_prog_attach(verdict, map, BPF_SK_SKB_STREAM_VERDICT, 0); + if (!ASSERT_OK(err, "bpf_prog_attach")) + goto out; + + s = socket_loopback(AF_INET, SOCK_STREAM); + if (s < 0) + goto out; + err = create_pair(s, AF_INET, SOCK_STREAM, &c1, &p1); + if (err < 0) + goto out; + + err = bpf_map_update_elem(map, &zero, &c1, BPF_NOEXIST); + if (err < 0) + goto out_close; + + shutdown(p1, SHUT_WR); + + ev.events = EPOLLIN; + ev.data.fd = c1; + + epollfd = epoll_create1(0); + if (!ASSERT_GT(epollfd, -1, "epoll_create(0)")) + goto out_close; + err = epoll_ctl(epollfd, EPOLL_CTL_ADD, c1, &ev); + if (!ASSERT_OK(err, "epoll_ctl(EPOLL_CTL_ADD)")) + goto out_close; + err = epoll_wait(epollfd, events, MAX_EVENTS, -1); + if (!ASSERT_EQ(err, 1, "epoll_wait(fd)")) + goto out_close; + + n = recv(c1, &b, 1, SOCK_NONBLOCK); + ASSERT_EQ(n, 0, "recv_timeout(fin)"); +out_close: + close(c1); + close(p1); +out: + test_sockmap_pass_prog__destroy(skel); +} + +static void test_sockmap_skb_verdict_fionread(bool pass_prog) +{ + int expected, zero = 0, sent, recvd, avail; + int err, map, verdict, s, c0, c1, p0, p1; + struct test_sockmap_pass_prog *pass; + struct test_sockmap_drop_prog *drop; + char buf[256] = "0123456789"; + + if (pass_prog) { + pass = test_sockmap_pass_prog__open_and_load(); + if (!ASSERT_OK_PTR(pass, "open_and_load")) + return; + verdict = bpf_program__fd(pass->progs.prog_skb_verdict); + map = bpf_map__fd(pass->maps.sock_map_rx); + expected = sizeof(buf); + } else { + drop = test_sockmap_drop_prog__open_and_load(); + if (!ASSERT_OK_PTR(drop, "open_and_load")) + return; + verdict = bpf_program__fd(drop->progs.prog_skb_verdict); + map = bpf_map__fd(drop->maps.sock_map_rx); + /* On drop data is consumed immediately and copied_seq inc'd */ + expected = 0; + } + + + err = bpf_prog_attach(verdict, map, BPF_SK_SKB_STREAM_VERDICT, 0); + if (!ASSERT_OK(err, "bpf_prog_attach")) + goto out; + + s = socket_loopback(AF_INET, SOCK_STREAM); + if (!ASSERT_GT(s, -1, "socket_loopback(s)")) + goto out; + err = create_socket_pairs(s, AF_INET, SOCK_STREAM, &c0, &c1, &p0, &p1); + if (!ASSERT_OK(err, "create_socket_pairs(s)")) + goto out; + + err = bpf_map_update_elem(map, &zero, &c1, BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem(c1)")) + goto out_close; + + sent = xsend(p1, &buf, sizeof(buf), 0); + ASSERT_EQ(sent, sizeof(buf), "xsend(p0)"); + err = ioctl(c1, FIONREAD, &avail); + ASSERT_OK(err, "ioctl(FIONREAD) error"); + ASSERT_EQ(avail, expected, "ioctl(FIONREAD)"); + /* On DROP test there will be no data to read */ + if (pass_prog) { + recvd = recv_timeout(c1, &buf, sizeof(buf), SOCK_NONBLOCK, IO_TIMEOUT_SEC); + ASSERT_EQ(recvd, sizeof(buf), "recv_timeout(c0)"); + } + +out_close: + close(c0); + close(p0); + close(c1); + close(p1); +out: + if (pass_prog) + test_sockmap_pass_prog__destroy(pass); + else + test_sockmap_drop_prog__destroy(drop); +} + void test_sockmap_basic(void) { if (test__start_subtest("sockmap create_update_free")) @@ -384,4 +509,10 @@ void test_sockmap_basic(void) test_sockmap_progs_query(BPF_SK_SKB_STREAM_VERDICT); if (test__start_subtest("sockmap skb_verdict progs query")) test_sockmap_progs_query(BPF_SK_SKB_VERDICT); + if (test__start_subtest("sockmap skb_verdict shutdown")) + test_sockmap_skb_verdict_shutdown(); + if (test__start_subtest("sockmap skb_verdict fionread")) + test_sockmap_skb_verdict_fionread(true); + if (test__start_subtest("sockmap skb_verdict fionread on drop")) + test_sockmap_skb_verdict_fionread(false); } diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h new file mode 100644 index 000000000000..d12665490a90 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h @@ -0,0 +1,390 @@ +#ifndef __SOCKMAP_HELPERS__ +#define __SOCKMAP_HELPERS__ + +#include <linux/vm_sockets.h> + +#define IO_TIMEOUT_SEC 30 +#define MAX_STRERR_LEN 256 +#define MAX_TEST_NAME 80 + +/* workaround for older vm_sockets.h */ +#ifndef VMADDR_CID_LOCAL +#define VMADDR_CID_LOCAL 1 +#endif + +#define __always_unused __attribute__((__unused__)) + +#define _FAIL(errnum, fmt...) \ + ({ \ + error_at_line(0, (errnum), __func__, __LINE__, fmt); \ + CHECK_FAIL(true); \ + }) +#define FAIL(fmt...) _FAIL(0, fmt) +#define FAIL_ERRNO(fmt...) _FAIL(errno, fmt) +#define FAIL_LIBBPF(err, msg) \ + ({ \ + char __buf[MAX_STRERR_LEN]; \ + libbpf_strerror((err), __buf, sizeof(__buf)); \ + FAIL("%s: %s", (msg), __buf); \ + }) + +/* Wrappers that fail the test on error and report it. */ + +#define xaccept_nonblock(fd, addr, len) \ + ({ \ + int __ret = \ + accept_timeout((fd), (addr), (len), IO_TIMEOUT_SEC); \ + if (__ret == -1) \ + FAIL_ERRNO("accept"); \ + __ret; \ + }) + +#define xbind(fd, addr, len) \ + ({ \ + int __ret = bind((fd), (addr), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("bind"); \ + __ret; \ + }) + +#define xclose(fd) \ + ({ \ + int __ret = close((fd)); \ + if (__ret == -1) \ + FAIL_ERRNO("close"); \ + __ret; \ + }) + +#define xconnect(fd, addr, len) \ + ({ \ + int __ret = connect((fd), (addr), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("connect"); \ + __ret; \ + }) + +#define xgetsockname(fd, addr, len) \ + ({ \ + int __ret = getsockname((fd), (addr), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("getsockname"); \ + __ret; \ + }) + +#define xgetsockopt(fd, level, name, val, len) \ + ({ \ + int __ret = getsockopt((fd), (level), (name), (val), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("getsockopt(" #name ")"); \ + __ret; \ + }) + +#define xlisten(fd, backlog) \ + ({ \ + int __ret = listen((fd), (backlog)); \ + if (__ret == -1) \ + FAIL_ERRNO("listen"); \ + __ret; \ + }) + +#define xsetsockopt(fd, level, name, val, len) \ + ({ \ + int __ret = setsockopt((fd), (level), (name), (val), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("setsockopt(" #name ")"); \ + __ret; \ + }) + +#define xsend(fd, buf, len, flags) \ + ({ \ + ssize_t __ret = send((fd), (buf), (len), (flags)); \ + if (__ret == -1) \ + FAIL_ERRNO("send"); \ + __ret; \ + }) + +#define xrecv_nonblock(fd, buf, len, flags) \ + ({ \ + ssize_t __ret = recv_timeout((fd), (buf), (len), (flags), \ + IO_TIMEOUT_SEC); \ + if (__ret == -1) \ + FAIL_ERRNO("recv"); \ + __ret; \ + }) + +#define xsocket(family, sotype, flags) \ + ({ \ + int __ret = socket(family, sotype, flags); \ + if (__ret == -1) \ + FAIL_ERRNO("socket"); \ + __ret; \ + }) + +#define xbpf_map_delete_elem(fd, key) \ + ({ \ + int __ret = bpf_map_delete_elem((fd), (key)); \ + if (__ret < 0) \ + FAIL_ERRNO("map_delete"); \ + __ret; \ + }) + +#define xbpf_map_lookup_elem(fd, key, val) \ + ({ \ + int __ret = bpf_map_lookup_elem((fd), (key), (val)); \ + if (__ret < 0) \ + FAIL_ERRNO("map_lookup"); \ + __ret; \ + }) + +#define xbpf_map_update_elem(fd, key, val, flags) \ + ({ \ + int __ret = bpf_map_update_elem((fd), (key), (val), (flags)); \ + if (__ret < 0) \ + FAIL_ERRNO("map_update"); \ + __ret; \ + }) + +#define xbpf_prog_attach(prog, target, type, flags) \ + ({ \ + int __ret = \ + bpf_prog_attach((prog), (target), (type), (flags)); \ + if (__ret < 0) \ + FAIL_ERRNO("prog_attach(" #type ")"); \ + __ret; \ + }) + +#define xbpf_prog_detach2(prog, target, type) \ + ({ \ + int __ret = bpf_prog_detach2((prog), (target), (type)); \ + if (__ret < 0) \ + FAIL_ERRNO("prog_detach2(" #type ")"); \ + __ret; \ + }) + +#define xpthread_create(thread, attr, func, arg) \ + ({ \ + int __ret = pthread_create((thread), (attr), (func), (arg)); \ + errno = __ret; \ + if (__ret) \ + FAIL_ERRNO("pthread_create"); \ + __ret; \ + }) + +#define xpthread_join(thread, retval) \ + ({ \ + int __ret = pthread_join((thread), (retval)); \ + errno = __ret; \ + if (__ret) \ + FAIL_ERRNO("pthread_join"); \ + __ret; \ + }) + +static inline int poll_read(int fd, unsigned int timeout_sec) +{ + struct timeval timeout = { .tv_sec = timeout_sec }; + fd_set rfds; + int r; + + FD_ZERO(&rfds); + FD_SET(fd, &rfds); + + r = select(fd + 1, &rfds, NULL, NULL, &timeout); + if (r == 0) + errno = ETIME; + + return r == 1 ? 0 : -1; +} + +static inline int accept_timeout(int fd, struct sockaddr *addr, socklen_t *len, + unsigned int timeout_sec) +{ + if (poll_read(fd, timeout_sec)) + return -1; + + return accept(fd, addr, len); +} + +static inline int recv_timeout(int fd, void *buf, size_t len, int flags, + unsigned int timeout_sec) +{ + if (poll_read(fd, timeout_sec)) + return -1; + + return recv(fd, buf, len, flags); +} + +static inline void init_addr_loopback4(struct sockaddr_storage *ss, + socklen_t *len) +{ + struct sockaddr_in *addr4 = memset(ss, 0, sizeof(*ss)); + + addr4->sin_family = AF_INET; + addr4->sin_port = 0; + addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK); + *len = sizeof(*addr4); +} + +static inline void init_addr_loopback6(struct sockaddr_storage *ss, + socklen_t *len) +{ + struct sockaddr_in6 *addr6 = memset(ss, 0, sizeof(*ss)); + + addr6->sin6_family = AF_INET6; + addr6->sin6_port = 0; + addr6->sin6_addr = in6addr_loopback; + *len = sizeof(*addr6); +} + +static inline void init_addr_loopback_vsock(struct sockaddr_storage *ss, + socklen_t *len) +{ + struct sockaddr_vm *addr = memset(ss, 0, sizeof(*ss)); + + addr->svm_family = AF_VSOCK; + addr->svm_port = VMADDR_PORT_ANY; + addr->svm_cid = VMADDR_CID_LOCAL; + *len = sizeof(*addr); +} + +static inline void init_addr_loopback(int family, struct sockaddr_storage *ss, + socklen_t *len) +{ + switch (family) { + case AF_INET: + init_addr_loopback4(ss, len); + return; + case AF_INET6: + init_addr_loopback6(ss, len); + return; + case AF_VSOCK: + init_addr_loopback_vsock(ss, len); + return; + default: + FAIL("unsupported address family %d", family); + } +} + +static inline struct sockaddr *sockaddr(struct sockaddr_storage *ss) +{ + return (struct sockaddr *)ss; +} + +static inline int add_to_sockmap(int sock_mapfd, int fd1, int fd2) +{ + u64 value; + u32 key; + int err; + + key = 0; + value = fd1; + err = xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST); + if (err) + return err; + + key = 1; + value = fd2; + return xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST); +} + +static inline int create_pair(int s, int family, int sotype, int *c, int *p) +{ + struct sockaddr_storage addr; + socklen_t len; + int err = 0; + + len = sizeof(addr); + err = xgetsockname(s, sockaddr(&addr), &len); + if (err) + return err; + + *c = xsocket(family, sotype, 0); + if (*c < 0) + return errno; + err = xconnect(*c, sockaddr(&addr), len); + if (err) { + err = errno; + goto close_cli0; + } + + *p = xaccept_nonblock(s, NULL, NULL); + if (*p < 0) { + err = errno; + goto close_cli0; + } + return err; +close_cli0: + close(*c); + return err; +} + +static inline int create_socket_pairs(int s, int family, int sotype, + int *c0, int *c1, int *p0, int *p1) +{ + int err; + + err = create_pair(s, family, sotype, c0, p0); + if (err) + return err; + + err = create_pair(s, family, sotype, c1, p1); + if (err) { + close(*c0); + close(*p0); + } + return err; +} + +static inline int enable_reuseport(int s, int progfd) +{ + int err, one = 1; + + err = xsetsockopt(s, SOL_SOCKET, SO_REUSEPORT, &one, sizeof(one)); + if (err) + return -1; + err = xsetsockopt(s, SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF, &progfd, + sizeof(progfd)); + if (err) + return -1; + + return 0; +} + +static inline int socket_loopback_reuseport(int family, int sotype, int progfd) +{ + struct sockaddr_storage addr; + socklen_t len; + int err, s; + + init_addr_loopback(family, &addr, &len); + + s = xsocket(family, sotype, 0); + if (s == -1) + return -1; + + if (progfd >= 0) + enable_reuseport(s, progfd); + + err = xbind(s, sockaddr(&addr), len); + if (err) + goto close; + + if (sotype & SOCK_DGRAM) + return s; + + err = xlisten(s, SOMAXCONN); + if (err) + goto close; + + return s; +close: + xclose(s); + return -1; +} + +static inline int socket_loopback(int family, int sotype) +{ + return socket_loopback_reuseport(family, sotype, -1); +} + + +#endif // __SOCKMAP_HELPERS__ diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c index 141c1e5944ee..b4f6f3a50ae5 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c @@ -20,11 +20,6 @@ #include <unistd.h> #include <linux/vm_sockets.h> -/* workaround for older vm_sockets.h */ -#ifndef VMADDR_CID_LOCAL -#define VMADDR_CID_LOCAL 1 -#endif - #include <bpf/bpf.h> #include <bpf/libbpf.h> @@ -32,315 +27,7 @@ #include "test_progs.h" #include "test_sockmap_listen.skel.h" -#define IO_TIMEOUT_SEC 30 -#define MAX_STRERR_LEN 256 -#define MAX_TEST_NAME 80 - -#define __always_unused __attribute__((__unused__)) - -#define _FAIL(errnum, fmt...) \ - ({ \ - error_at_line(0, (errnum), __func__, __LINE__, fmt); \ - CHECK_FAIL(true); \ - }) -#define FAIL(fmt...) _FAIL(0, fmt) -#define FAIL_ERRNO(fmt...) _FAIL(errno, fmt) -#define FAIL_LIBBPF(err, msg) \ - ({ \ - char __buf[MAX_STRERR_LEN]; \ - libbpf_strerror((err), __buf, sizeof(__buf)); \ - FAIL("%s: %s", (msg), __buf); \ - }) - -/* Wrappers that fail the test on error and report it. */ - -#define xaccept_nonblock(fd, addr, len) \ - ({ \ - int __ret = \ - accept_timeout((fd), (addr), (len), IO_TIMEOUT_SEC); \ - if (__ret == -1) \ - FAIL_ERRNO("accept"); \ - __ret; \ - }) - -#define xbind(fd, addr, len) \ - ({ \ - int __ret = bind((fd), (addr), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("bind"); \ - __ret; \ - }) - -#define xclose(fd) \ - ({ \ - int __ret = close((fd)); \ - if (__ret == -1) \ - FAIL_ERRNO("close"); \ - __ret; \ - }) - -#define xconnect(fd, addr, len) \ - ({ \ - int __ret = connect((fd), (addr), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("connect"); \ - __ret; \ - }) - -#define xgetsockname(fd, addr, len) \ - ({ \ - int __ret = getsockname((fd), (addr), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("getsockname"); \ - __ret; \ - }) - -#define xgetsockopt(fd, level, name, val, len) \ - ({ \ - int __ret = getsockopt((fd), (level), (name), (val), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("getsockopt(" #name ")"); \ - __ret; \ - }) - -#define xlisten(fd, backlog) \ - ({ \ - int __ret = listen((fd), (backlog)); \ - if (__ret == -1) \ - FAIL_ERRNO("listen"); \ - __ret; \ - }) - -#define xsetsockopt(fd, level, name, val, len) \ - ({ \ - int __ret = setsockopt((fd), (level), (name), (val), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("setsockopt(" #name ")"); \ - __ret; \ - }) - -#define xsend(fd, buf, len, flags) \ - ({ \ - ssize_t __ret = send((fd), (buf), (len), (flags)); \ - if (__ret == -1) \ - FAIL_ERRNO("send"); \ - __ret; \ - }) - -#define xrecv_nonblock(fd, buf, len, flags) \ - ({ \ - ssize_t __ret = recv_timeout((fd), (buf), (len), (flags), \ - IO_TIMEOUT_SEC); \ - if (__ret == -1) \ - FAIL_ERRNO("recv"); \ - __ret; \ - }) - -#define xsocket(family, sotype, flags) \ - ({ \ - int __ret = socket(family, sotype, flags); \ - if (__ret == -1) \ - FAIL_ERRNO("socket"); \ - __ret; \ - }) - -#define xbpf_map_delete_elem(fd, key) \ - ({ \ - int __ret = bpf_map_delete_elem((fd), (key)); \ - if (__ret < 0) \ - FAIL_ERRNO("map_delete"); \ - __ret; \ - }) - -#define xbpf_map_lookup_elem(fd, key, val) \ - ({ \ - int __ret = bpf_map_lookup_elem((fd), (key), (val)); \ - if (__ret < 0) \ - FAIL_ERRNO("map_lookup"); \ - __ret; \ - }) - -#define xbpf_map_update_elem(fd, key, val, flags) \ - ({ \ - int __ret = bpf_map_update_elem((fd), (key), (val), (flags)); \ - if (__ret < 0) \ - FAIL_ERRNO("map_update"); \ - __ret; \ - }) - -#define xbpf_prog_attach(prog, target, type, flags) \ - ({ \ - int __ret = \ - bpf_prog_attach((prog), (target), (type), (flags)); \ - if (__ret < 0) \ - FAIL_ERRNO("prog_attach(" #type ")"); \ - __ret; \ - }) - -#define xbpf_prog_detach2(prog, target, type) \ - ({ \ - int __ret = bpf_prog_detach2((prog), (target), (type)); \ - if (__ret < 0) \ - FAIL_ERRNO("prog_detach2(" #type ")"); \ - __ret; \ - }) - -#define xpthread_create(thread, attr, func, arg) \ - ({ \ - int __ret = pthread_create((thread), (attr), (func), (arg)); \ - errno = __ret; \ - if (__ret) \ - FAIL_ERRNO("pthread_create"); \ - __ret; \ - }) - -#define xpthread_join(thread, retval) \ - ({ \ - int __ret = pthread_join((thread), (retval)); \ - errno = __ret; \ - if (__ret) \ - FAIL_ERRNO("pthread_join"); \ - __ret; \ - }) - -static int poll_read(int fd, unsigned int timeout_sec) -{ - struct timeval timeout = { .tv_sec = timeout_sec }; - fd_set rfds; - int r; - - FD_ZERO(&rfds); - FD_SET(fd, &rfds); - - r = select(fd + 1, &rfds, NULL, NULL, &timeout); - if (r == 0) - errno = ETIME; - - return r == 1 ? 0 : -1; -} - -static int accept_timeout(int fd, struct sockaddr *addr, socklen_t *len, - unsigned int timeout_sec) -{ - if (poll_read(fd, timeout_sec)) - return -1; - - return accept(fd, addr, len); -} - -static int recv_timeout(int fd, void *buf, size_t len, int flags, - unsigned int timeout_sec) -{ - if (poll_read(fd, timeout_sec)) - return -1; - - return recv(fd, buf, len, flags); -} - -static void init_addr_loopback4(struct sockaddr_storage *ss, socklen_t *len) -{ - struct sockaddr_in *addr4 = memset(ss, 0, sizeof(*ss)); - - addr4->sin_family = AF_INET; - addr4->sin_port = 0; - addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK); - *len = sizeof(*addr4); -} - -static void init_addr_loopback6(struct sockaddr_storage *ss, socklen_t *len) -{ - struct sockaddr_in6 *addr6 = memset(ss, 0, sizeof(*ss)); - - addr6->sin6_family = AF_INET6; - addr6->sin6_port = 0; - addr6->sin6_addr = in6addr_loopback; - *len = sizeof(*addr6); -} - -static void init_addr_loopback_vsock(struct sockaddr_storage *ss, socklen_t *len) -{ - struct sockaddr_vm *addr = memset(ss, 0, sizeof(*ss)); - - addr->svm_family = AF_VSOCK; - addr->svm_port = VMADDR_PORT_ANY; - addr->svm_cid = VMADDR_CID_LOCAL; - *len = sizeof(*addr); -} - -static void init_addr_loopback(int family, struct sockaddr_storage *ss, - socklen_t *len) -{ - switch (family) { - case AF_INET: - init_addr_loopback4(ss, len); - return; - case AF_INET6: - init_addr_loopback6(ss, len); - return; - case AF_VSOCK: - init_addr_loopback_vsock(ss, len); - return; - default: - FAIL("unsupported address family %d", family); - } -} - -static inline struct sockaddr *sockaddr(struct sockaddr_storage *ss) -{ - return (struct sockaddr *)ss; -} - -static int enable_reuseport(int s, int progfd) -{ - int err, one = 1; - - err = xsetsockopt(s, SOL_SOCKET, SO_REUSEPORT, &one, sizeof(one)); - if (err) - return -1; - err = xsetsockopt(s, SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF, &progfd, - sizeof(progfd)); - if (err) - return -1; - - return 0; -} - -static int socket_loopback_reuseport(int family, int sotype, int progfd) -{ - struct sockaddr_storage addr; - socklen_t len; - int err, s; - - init_addr_loopback(family, &addr, &len); - - s = xsocket(family, sotype, 0); - if (s == -1) - return -1; - - if (progfd >= 0) - enable_reuseport(s, progfd); - - err = xbind(s, sockaddr(&addr), len); - if (err) - goto close; - - if (sotype & SOCK_DGRAM) - return s; - - err = xlisten(s, SOMAXCONN); - if (err) - goto close; - - return s; -close: - xclose(s); - return -1; -} - -static int socket_loopback(int family, int sotype) -{ - return socket_loopback_reuseport(family, sotype, -1); -} +#include "sockmap_helpers.h" static void test_insert_invalid(struct test_sockmap_listen *skel __always_unused, int family, int sotype, int mapfd) @@ -984,31 +671,12 @@ static const char *redir_mode_str(enum redir_mode mode) } } -static int add_to_sockmap(int sock_mapfd, int fd1, int fd2) -{ - u64 value; - u32 key; - int err; - - key = 0; - value = fd1; - err = xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST); - if (err) - return err; - - key = 1; - value = fd2; - return xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST); -} - static void redir_to_connected(int family, int sotype, int sock_mapfd, int verd_mapfd, enum redir_mode mode) { const char *log_prefix = redir_mode_str(mode); - struct sockaddr_storage addr; int s, c0, c1, p0, p1; unsigned int pass; - socklen_t len; int err, n; u32 key; char b; @@ -1019,36 +687,13 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd, if (s < 0) return; - len = sizeof(addr); - err = xgetsockname(s, sockaddr(&addr), &len); + err = create_socket_pairs(s, family, sotype, &c0, &c1, &p0, &p1); if (err) goto close_srv; - c0 = xsocket(family, sotype, 0); - if (c0 < 0) - goto close_srv; - err = xconnect(c0, sockaddr(&addr), len); - if (err) - goto close_cli0; - - p0 = xaccept_nonblock(s, NULL, NULL); - if (p0 < 0) - goto close_cli0; - - c1 = xsocket(family, sotype, 0); - if (c1 < 0) - goto close_peer0; - err = xconnect(c1, sockaddr(&addr), len); - if (err) - goto close_cli1; - - p1 = xaccept_nonblock(s, NULL, NULL); - if (p1 < 0) - goto close_cli1; - err = add_to_sockmap(sock_mapfd, p0, p1); if (err) - goto close_peer1; + goto close; n = write(mode == REDIR_INGRESS ? c1 : p1, "a", 1); if (n < 0) @@ -1056,12 +701,12 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd, if (n == 0) FAIL("%s: incomplete write", log_prefix); if (n < 1) - goto close_peer1; + goto close; key = SK_PASS; err = xbpf_map_lookup_elem(verd_mapfd, &key, &pass); if (err) - goto close_peer1; + goto close; if (pass != 1) FAIL("%s: want pass count 1, have %d", log_prefix, pass); n = recv_timeout(c0, &b, 1, 0, IO_TIMEOUT_SEC); @@ -1070,13 +715,10 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd, if (n == 0) FAIL("%s: incomplete recv", log_prefix); -close_peer1: +close: xclose(p1); -close_cli1: xclose(c1); -close_peer0: xclose(p0); -close_cli0: xclose(c0); close_srv: xclose(s); diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c index 4512dd808c33..05d0e07da394 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c @@ -209,7 +209,7 @@ static int getsetsockopt(void) err, errno); goto err; } - ASSERT_EQ(optlen, 4, "Unexpected NETLINK_LIST_MEMBERSHIPS value"); + ASSERT_EQ(optlen, 8, "Unexpected NETLINK_LIST_MEMBERSHIPS value"); free(big_buf); close(fd); diff --git a/tools/testing/selftests/bpf/prog_tests/subprogs_extable.c b/tools/testing/selftests/bpf/prog_tests/subprogs_extable.c new file mode 100644 index 000000000000..3afd9f775f68 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/subprogs_extable.c @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <test_progs.h> +#include "test_subprogs_extable.skel.h" + +void test_subprogs_extable(void) +{ + const int read_sz = 456; + struct test_subprogs_extable *skel; + int err; + + skel = test_subprogs_extable__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_open_and_load")) + return; + + err = test_subprogs_extable__attach(skel); + if (!ASSERT_OK(err, "skel_attach")) + goto cleanup; + + /* trigger tracepoint */ + ASSERT_OK(trigger_module_test_read(read_sz), "trigger_read"); + + ASSERT_NEQ(skel->bss->triggered, 0, "verify at least one program ran"); + + test_subprogs_extable__detach(skel); + +cleanup: + test_subprogs_extable__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_ksym.c b/tools/testing/selftests/bpf/progs/bpf_iter_ksym.c index 5ddcc46fd886..521267818f4d 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_ksym.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_ksym.c @@ -59,9 +59,7 @@ int dump_ksym(struct bpf_iter__ksym *ctx) } else { BPF_SEQ_PRINTF(seq, "0x%llx %c %s ", value, type, iter->name); } - if (!iter->pos_arch_end || iter->pos_arch_end > iter->pos) - BPF_SEQ_PRINTF(seq, "CORE "); - else if (!iter->pos_mod_end || iter->pos_mod_end > iter->pos) + if (!iter->pos_mod_end || iter->pos_mod_end > iter->pos) BPF_SEQ_PRINTF(seq, "MOD "); else if (!iter->pos_ftrace_mod_end || iter->pos_ftrace_mod_end > iter->pos) BPF_SEQ_PRINTF(seq, "FTRACE_MOD "); diff --git a/tools/testing/selftests/bpf/progs/inner_array_lookup.c b/tools/testing/selftests/bpf/progs/inner_array_lookup.c new file mode 100644 index 000000000000..c2c8f2fa451d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/inner_array_lookup.c @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +struct inner_map { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 5); + __type(key, int); + __type(value, int); +} inner_map1 SEC(".maps"); + +struct outer_map { + __uint(type, BPF_MAP_TYPE_HASH_OF_MAPS); + __uint(max_entries, 3); + __type(key, int); + __array(values, struct inner_map); +} outer_map1 SEC(".maps") = { + .values = { + [2] = &inner_map1, + }, +}; + +SEC("raw_tp/sys_enter") +int handle__sys_enter(void *ctx) +{ + int outer_key = 2, inner_key = 3; + int *val; + void *map; + + map = bpf_map_lookup_elem(&outer_map1, &outer_key); + if (!map) + return 1; + + val = bpf_map_lookup_elem(map, &inner_key); + if (!val) + return 1; + + if (*val == 1) + *val = 2; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_drop_prog.c b/tools/testing/selftests/bpf/progs/test_sockmap_drop_prog.c new file mode 100644 index 000000000000..29314805ce42 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sockmap_drop_prog.c @@ -0,0 +1,32 @@ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map_rx SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map_tx SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map_msg SEC(".maps"); + +SEC("sk_skb") +int prog_skb_verdict(struct __sk_buff *skb) +{ + return SK_DROP; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h index baf9ebc6d903..99d2ea9fb658 100644 --- a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h +++ b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h @@ -191,7 +191,7 @@ SEC("sockops") int bpf_sockmap(struct bpf_sock_ops *skops) { __u32 lport, rport; - int op, err, ret; + int op, ret; op = (int) skops->op; @@ -203,10 +203,10 @@ int bpf_sockmap(struct bpf_sock_ops *skops) if (lport == 10000) { ret = 1; #ifdef SOCKMAP - err = bpf_sock_map_update(skops, &sock_map, &ret, + bpf_sock_map_update(skops, &sock_map, &ret, BPF_NOEXIST); #else - err = bpf_sock_hash_update(skops, &sock_map, &ret, + bpf_sock_hash_update(skops, &sock_map, &ret, BPF_NOEXIST); #endif } @@ -218,10 +218,10 @@ int bpf_sockmap(struct bpf_sock_ops *skops) if (bpf_ntohl(rport) == 10001) { ret = 10; #ifdef SOCKMAP - err = bpf_sock_map_update(skops, &sock_map, &ret, + bpf_sock_map_update(skops, &sock_map, &ret, BPF_NOEXIST); #else - err = bpf_sock_hash_update(skops, &sock_map, &ret, + bpf_sock_hash_update(skops, &sock_map, &ret, BPF_NOEXIST); #endif } @@ -230,8 +230,6 @@ int bpf_sockmap(struct bpf_sock_ops *skops) break; } - __sink(err); - return 0; } diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_pass_prog.c b/tools/testing/selftests/bpf/progs/test_sockmap_pass_prog.c new file mode 100644 index 000000000000..1d86a717a290 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sockmap_pass_prog.c @@ -0,0 +1,32 @@ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map_rx SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map_tx SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map_msg SEC(".maps"); + +SEC("sk_skb") +int prog_skb_verdict(struct __sk_buff *skb) +{ + return SK_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_subprogs_extable.c b/tools/testing/selftests/bpf/progs/test_subprogs_extable.c new file mode 100644 index 000000000000..e2a21fbd4e44 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_subprogs_extable.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 8); + __type(key, __u32); + __type(value, __u64); +} test_array SEC(".maps"); + +unsigned int triggered; + +static __u64 test_cb(struct bpf_map *map, __u32 *key, __u64 *val, void *data) +{ + return 1; +} + +SEC("fexit/bpf_testmod_return_ptr") +int BPF_PROG(handle_fexit_ret_subprogs, int arg, struct file *ret) +{ + *(volatile long *)ret; + *(volatile int *)&ret->f_mode; + bpf_for_each_map_elem(&test_array, test_cb, NULL, 0); + triggered++; + return 0; +} + +SEC("fexit/bpf_testmod_return_ptr") +int BPF_PROG(handle_fexit_ret_subprogs2, int arg, struct file *ret) +{ + *(volatile long *)ret; + *(volatile int *)&ret->f_mode; + bpf_for_each_map_elem(&test_array, test_cb, NULL, 0); + triggered++; + return 0; +} + +SEC("fexit/bpf_testmod_return_ptr") +int BPF_PROG(handle_fexit_ret_subprogs3, int arg, struct file *ret) +{ + *(volatile long *)ret; + *(volatile int *)&ret->f_mode; + bpf_for_each_map_elem(&test_array, test_cb, NULL, 0); + triggered++; + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c index 136e5530b72c..6115520154e3 100644 --- a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c +++ b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c @@ -371,4 +371,83 @@ __naked void and_then_at_fp_8(void) " ::: __clobber_all); } +SEC("xdp") +__description("32-bit spill of 64-bit reg should clear ID") +__failure __msg("math between ctx pointer and 4294967295 is not allowed") +__naked void spill_32bit_of_64bit_fail(void) +{ + asm volatile (" \ + r6 = r1; \ + /* Roll one bit to force the verifier to track both branches. */\ + call %[bpf_get_prandom_u32]; \ + r0 &= 0x8; \ + /* Put a large number into r1. */ \ + r1 = 0xffffffff; \ + r1 <<= 32; \ + r1 += r0; \ + /* Assign an ID to r1. */ \ + r2 = r1; \ + /* 32-bit spill r1 to stack - should clear the ID! */\ + *(u32*)(r10 - 8) = r1; \ + /* 32-bit fill r2 from stack. */ \ + r2 = *(u32*)(r10 - 8); \ + /* Compare r2 with another register to trigger find_equal_scalars.\ + * Having one random bit is important here, otherwise the verifier cuts\ + * the corners. If the ID was mistakenly preserved on spill, this would\ + * cause the verifier to think that r1 is also equal to zero in one of\ + * the branches, and equal to eight on the other branch.\ + */ \ + r3 = 0; \ + if r2 != r3 goto l0_%=; \ +l0_%=: r1 >>= 32; \ + /* At this point, if the verifier thinks that r1 is 0, an out-of-bounds\ + * read will happen, because it actually contains 0xffffffff.\ + */ \ + r6 += r1; \ + r0 = *(u32*)(r6 + 0); \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("xdp") +__description("16-bit spill of 32-bit reg should clear ID") +__failure __msg("dereference of modified ctx ptr R6 off=65535 disallowed") +__naked void spill_16bit_of_32bit_fail(void) +{ + asm volatile (" \ + r6 = r1; \ + /* Roll one bit to force the verifier to track both branches. */\ + call %[bpf_get_prandom_u32]; \ + r0 &= 0x8; \ + /* Put a large number into r1. */ \ + w1 = 0xffff0000; \ + r1 += r0; \ + /* Assign an ID to r1. */ \ + r2 = r1; \ + /* 16-bit spill r1 to stack - should clear the ID! */\ + *(u16*)(r10 - 8) = r1; \ + /* 16-bit fill r2 from stack. */ \ + r2 = *(u16*)(r10 - 8); \ + /* Compare r2 with another register to trigger find_equal_scalars.\ + * Having one random bit is important here, otherwise the verifier cuts\ + * the corners. If the ID was mistakenly preserved on spill, this would\ + * cause the verifier to think that r1 is also equal to zero in one of\ + * the branches, and equal to eight on the other branch.\ + */ \ + r3 = 0; \ + if r2 != r3 goto l0_%=; \ +l0_%=: r1 >>= 16; \ + /* At this point, if the verifier thinks that r1 is 0, an out-of-bounds\ + * read will happen, because it actually contains 0xffff.\ + */ \ + r6 += r1; \ + r0 = *(u32*)(r6 + 0); \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/cachestat/.gitignore b/tools/testing/selftests/cachestat/.gitignore new file mode 100644 index 000000000000..d6c30b43a4bb --- /dev/null +++ b/tools/testing/selftests/cachestat/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +test_cachestat diff --git a/tools/testing/selftests/cachestat/Makefile b/tools/testing/selftests/cachestat/Makefile new file mode 100644 index 000000000000..fca73aaa7d14 --- /dev/null +++ b/tools/testing/selftests/cachestat/Makefile @@ -0,0 +1,8 @@ +# SPDX-License-Identifier: GPL-2.0 +TEST_GEN_PROGS := test_cachestat + +CFLAGS += $(KHDR_INCLUDES) +CFLAGS += -Wall +CFLAGS += -lrt + +include ../lib.mk diff --git a/tools/testing/selftests/cachestat/test_cachestat.c b/tools/testing/selftests/cachestat/test_cachestat.c new file mode 100644 index 000000000000..54d09b820ed4 --- /dev/null +++ b/tools/testing/selftests/cachestat/test_cachestat.c @@ -0,0 +1,269 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE + +#include <stdio.h> +#include <stdbool.h> +#include <linux/kernel.h> +#include <linux/mman.h> +#include <sys/mman.h> +#include <sys/shm.h> +#include <sys/syscall.h> +#include <unistd.h> +#include <string.h> +#include <fcntl.h> +#include <errno.h> + +#include "../kselftest.h" + +static const char * const dev_files[] = { + "/dev/zero", "/dev/null", "/dev/urandom", + "/proc/version", "/proc" +}; +static const int cachestat_nr = 451; + +void print_cachestat(struct cachestat *cs) +{ + ksft_print_msg( + "Using cachestat: Cached: %lu, Dirty: %lu, Writeback: %lu, Evicted: %lu, Recently Evicted: %lu\n", + cs->nr_cache, cs->nr_dirty, cs->nr_writeback, + cs->nr_evicted, cs->nr_recently_evicted); +} + +bool write_exactly(int fd, size_t filesize) +{ + int random_fd = open("/dev/urandom", O_RDONLY); + char *cursor, *data; + int remained; + bool ret; + + if (random_fd < 0) { + ksft_print_msg("Unable to access urandom.\n"); + ret = false; + goto out; + } + + data = malloc(filesize); + if (!data) { + ksft_print_msg("Unable to allocate data.\n"); + ret = false; + goto close_random_fd; + } + + remained = filesize; + cursor = data; + + while (remained) { + ssize_t read_len = read(random_fd, cursor, remained); + + if (read_len <= 0) { + ksft_print_msg("Unable to read from urandom.\n"); + ret = false; + goto out_free_data; + } + + remained -= read_len; + cursor += read_len; + } + + /* write random data to fd */ + remained = filesize; + cursor = data; + while (remained) { + ssize_t write_len = write(fd, cursor, remained); + + if (write_len <= 0) { + ksft_print_msg("Unable write random data to file.\n"); + ret = false; + goto out_free_data; + } + + remained -= write_len; + cursor += write_len; + } + + ret = true; +out_free_data: + free(data); +close_random_fd: + close(random_fd); +out: + return ret; +} + +/* + * Open/create the file at filename, (optionally) write random data to it + * (exactly num_pages), then test the cachestat syscall on this file. + * + * If test_fsync == true, fsync the file, then check the number of dirty + * pages. + */ +bool test_cachestat(const char *filename, bool write_random, bool create, + bool test_fsync, unsigned long num_pages, int open_flags, + mode_t open_mode) +{ + size_t PS = sysconf(_SC_PAGESIZE); + int filesize = num_pages * PS; + bool ret = true; + long syscall_ret; + struct cachestat cs; + struct cachestat_range cs_range = { 0, filesize }; + + int fd = open(filename, open_flags, open_mode); + + if (fd == -1) { + ksft_print_msg("Unable to create/open file.\n"); + ret = false; + goto out; + } else { + ksft_print_msg("Create/open %s\n", filename); + } + + if (write_random) { + if (!write_exactly(fd, filesize)) { + ksft_print_msg("Unable to access urandom.\n"); + ret = false; + goto out1; + } + } + + syscall_ret = syscall(cachestat_nr, fd, &cs_range, &cs, 0); + + ksft_print_msg("Cachestat call returned %ld\n", syscall_ret); + + if (syscall_ret) { + ksft_print_msg("Cachestat returned non-zero.\n"); + ret = false; + goto out1; + + } else { + print_cachestat(&cs); + + if (write_random) { + if (cs.nr_cache + cs.nr_evicted != num_pages) { + ksft_print_msg( + "Total number of cached and evicted pages is off.\n"); + ret = false; + } + } + } + + if (test_fsync) { + if (fsync(fd)) { + ksft_print_msg("fsync fails.\n"); + ret = false; + } else { + syscall_ret = syscall(cachestat_nr, fd, &cs_range, &cs, 0); + + ksft_print_msg("Cachestat call (after fsync) returned %ld\n", + syscall_ret); + + if (!syscall_ret) { + print_cachestat(&cs); + + if (cs.nr_dirty) { + ret = false; + ksft_print_msg( + "Number of dirty should be zero after fsync.\n"); + } + } else { + ksft_print_msg("Cachestat (after fsync) returned non-zero.\n"); + ret = false; + goto out1; + } + } + } + +out1: + close(fd); + + if (create) + remove(filename); +out: + return ret; +} + +bool test_cachestat_shmem(void) +{ + size_t PS = sysconf(_SC_PAGESIZE); + size_t filesize = PS * 512 * 2; /* 2 2MB huge pages */ + int syscall_ret; + size_t compute_len = PS * 512; + struct cachestat_range cs_range = { PS, compute_len }; + char *filename = "tmpshmcstat"; + struct cachestat cs; + bool ret = true; + unsigned long num_pages = compute_len / PS; + int fd = shm_open(filename, O_CREAT | O_RDWR, 0600); + + if (fd < 0) { + ksft_print_msg("Unable to create shmem file.\n"); + ret = false; + goto out; + } + + if (ftruncate(fd, filesize)) { + ksft_print_msg("Unable to truncate shmem file.\n"); + ret = false; + goto close_fd; + } + + if (!write_exactly(fd, filesize)) { + ksft_print_msg("Unable to write to shmem file.\n"); + ret = false; + goto close_fd; + } + + syscall_ret = syscall(cachestat_nr, fd, &cs_range, &cs, 0); + + if (syscall_ret) { + ksft_print_msg("Cachestat returned non-zero.\n"); + ret = false; + goto close_fd; + } else { + print_cachestat(&cs); + if (cs.nr_cache + cs.nr_evicted != num_pages) { + ksft_print_msg( + "Total number of cached and evicted pages is off.\n"); + ret = false; + } + } + +close_fd: + shm_unlink(filename); +out: + return ret; +} + +int main(void) +{ + int ret = 0; + + for (int i = 0; i < 5; i++) { + const char *dev_filename = dev_files[i]; + + if (test_cachestat(dev_filename, false, false, false, + 4, O_RDONLY, 0400)) + ksft_test_result_pass("cachestat works with %s\n", dev_filename); + else { + ksft_test_result_fail("cachestat fails with %s\n", dev_filename); + ret = 1; + } + } + + if (test_cachestat("tmpfilecachestat", true, true, + true, 4, O_CREAT | O_RDWR, 0400 | 0600)) + ksft_test_result_pass("cachestat works with a normal file\n"); + else { + ksft_test_result_fail("cachestat fails with normal file\n"); + ret = 1; + } + + if (test_cachestat_shmem()) + ksft_test_result_pass("cachestat works with a shmem file\n"); + else { + ksft_test_result_fail("cachestat fails with a shmem file\n"); + ret = 1; + } + + return ret; +} diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c index f4f7c0aef702..c7c9572003a8 100644 --- a/tools/testing/selftests/cgroup/test_memcontrol.c +++ b/tools/testing/selftests/cgroup/test_memcontrol.c @@ -292,6 +292,7 @@ static int test_memcg_protection(const char *root, bool min) char *children[4] = {NULL}; const char *attribute = min ? "memory.min" : "memory.low"; long c[4]; + long current; int i, attempts; int fd; @@ -400,7 +401,8 @@ static int test_memcg_protection(const char *root, bool min) goto cleanup; } - if (!values_close(cg_read_long(parent[1], "memory.current"), MB(50), 3)) + current = min ? MB(50) : MB(30); + if (!values_close(cg_read_long(parent[1], "memory.current"), current, 3)) goto cleanup; if (!reclaim_until(children[0], MB(10))) @@ -987,7 +989,9 @@ static int tcp_client(const char *cgroup, unsigned short port) char servport[6]; int retries = 0x10; /* nice round number */ int sk, ret; + long allocated; + allocated = cg_read_long(cgroup, "memory.current"); snprintf(servport, sizeof(servport), "%hd", port); ret = getaddrinfo(server, servport, NULL, &ai); if (ret) @@ -1015,7 +1019,8 @@ static int tcp_client(const char *cgroup, unsigned short port) if (current < 0 || sock < 0) goto close_sk; - if (values_close(current, sock, 10)) { + /* exclude the memory not related to socket connection */ + if (values_close(current - allocated, sock, 10)) { ret = KSFT_PASS; break; } diff --git a/tools/testing/selftests/clone3/clone3.c b/tools/testing/selftests/clone3/clone3.c index e495f895a2cd..e60cf4da8fb0 100644 --- a/tools/testing/selftests/clone3/clone3.c +++ b/tools/testing/selftests/clone3/clone3.c @@ -129,7 +129,7 @@ int main(int argc, char *argv[]) uid_t uid = getuid(); ksft_print_header(); - ksft_set_plan(18); + ksft_set_plan(19); test_clone3_supported(); /* Just a simple clone3() should return 0.*/ @@ -198,5 +198,8 @@ int main(int argc, char *argv[]) /* Do a clone3() in a new time namespace */ test_clone3(CLONE_NEWTIME, 0, 0, CLONE3_ARGS_NO_TEST); + /* Do a clone3() with exit signal (SIGCHLD) in flags */ + test_clone3(SIGCHLD, 0, -EINVAL, CLONE3_ARGS_NO_TEST); + ksft_finished(); } diff --git a/tools/testing/selftests/cpufreq/config b/tools/testing/selftests/cpufreq/config index 75e900793e8a..ce5068f5a6a2 100644 --- a/tools/testing/selftests/cpufreq/config +++ b/tools/testing/selftests/cpufreq/config @@ -5,11 +5,3 @@ CONFIG_CPU_FREQ_GOV_USERSPACE=y CONFIG_CPU_FREQ_GOV_ONDEMAND=y CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y CONFIG_CPU_FREQ_GOV_SCHEDUTIL=y -CONFIG_DEBUG_RT_MUTEXES=y -CONFIG_DEBUG_PLIST=y -CONFIG_DEBUG_SPINLOCK=y -CONFIG_DEBUG_MUTEXES=y -CONFIG_DEBUG_LOCK_ALLOC=y -CONFIG_PROVE_LOCKING=y -CONFIG_LOCKDEP=y -CONFIG_DEBUG_ATOMIC_SLEEP=y diff --git a/tools/testing/selftests/damon/config b/tools/testing/selftests/damon/config new file mode 100644 index 000000000000..0daf38974eb0 --- /dev/null +++ b/tools/testing/selftests/damon/config @@ -0,0 +1,7 @@ +CONFIG_DAMON=y +CONFIG_DAMON_SYSFS=y +CONFIG_DAMON_DBGFS=y +CONFIG_DAMON_PADDR=y +CONFIG_DAMON_VADDR=y +CONFIG_DAMON_RECLAIM=y +CONFIG_DAMON_LRU_SORT=y diff --git a/tools/testing/selftests/ftrace/Makefile b/tools/testing/selftests/ftrace/Makefile index d6e106fbce11..a1e955d2de4c 100644 --- a/tools/testing/selftests/ftrace/Makefile +++ b/tools/testing/selftests/ftrace/Makefile @@ -1,7 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 all: -TEST_PROGS := ftracetest +TEST_PROGS_EXTENDED := ftracetest +TEST_PROGS := ftracetest-ktap TEST_FILES := test.d settings EXTRA_CLEAN := $(OUTPUT)/logs/* diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest index c3311c8c4089..cb5f18c06593 100755 --- a/tools/testing/selftests/ftrace/ftracetest +++ b/tools/testing/selftests/ftrace/ftracetest @@ -13,6 +13,7 @@ echo "Usage: ftracetest [options] [testcase(s)] [testcase-directory(s)]" echo " Options:" echo " -h|--help Show help message" echo " -k|--keep Keep passed test logs" +echo " -K|--ktap Output in KTAP format" echo " -v|--verbose Increase verbosity of test messages" echo " -vv Alias of -v -v (Show all results in stdout)" echo " -vvv Alias of -v -v -v (Show all commands immediately)" @@ -85,6 +86,10 @@ parse_opts() { # opts KEEP_LOG=1 shift 1 ;; + --ktap|-K) + KTAP=1 + shift 1 + ;; --verbose|-v|-vv|-vvv) if [ $VERBOSE -eq -1 ]; then usage "--console can not use with --verbose" @@ -178,6 +183,7 @@ TEST_DIR=$TOP_DIR/test.d TEST_CASES=`find_testcases $TEST_DIR` LOG_DIR=$TOP_DIR/logs/`date +%Y%m%d-%H%M%S`/ KEEP_LOG=0 +KTAP=0 DEBUG=0 VERBOSE=0 UNSUPPORTED_RESULT=0 @@ -229,7 +235,7 @@ prlog() { # messages newline= shift fi - printf "$*$newline" + [ "$KTAP" != "1" ] && printf "$*$newline" [ "$LOG_FILE" ] && printf "$*$newline" | strip_esc >> $LOG_FILE } catlog() { #file @@ -260,11 +266,11 @@ TOTAL_RESULT=0 INSTANCE= CASENO=0 +CASENAME= testcase() { # testfile CASENO=$((CASENO+1)) - desc=`grep "^#[ \t]*description:" $1 | cut -f2- -d:` - prlog -n "[$CASENO]$INSTANCE$desc" + CASENAME=`grep "^#[ \t]*description:" $1 | cut -f2- -d:` } checkreq() { # testfile @@ -277,40 +283,68 @@ test_on_instance() { # testfile grep -q "^#[ \t]*flags:.*instance" $1 } +ktaptest() { # result comment + if [ "$KTAP" != "1" ]; then + return + fi + + local result= + if [ "$1" = "1" ]; then + result="ok" + else + result="not ok" + fi + shift + + local comment=$* + if [ "$comment" != "" ]; then + comment="# $comment" + fi + + echo $result $CASENO $INSTANCE$CASENAME $comment +} + eval_result() { # sigval case $1 in $PASS) prlog " [${color_green}PASS${color_reset}]" + ktaptest 1 PASSED_CASES="$PASSED_CASES $CASENO" return 0 ;; $FAIL) prlog " [${color_red}FAIL${color_reset}]" + ktaptest 0 FAILED_CASES="$FAILED_CASES $CASENO" return 1 # this is a bug. ;; $UNRESOLVED) prlog " [${color_blue}UNRESOLVED${color_reset}]" + ktaptest 0 UNRESOLVED UNRESOLVED_CASES="$UNRESOLVED_CASES $CASENO" return $UNRESOLVED_RESULT # depends on use case ;; $UNTESTED) prlog " [${color_blue}UNTESTED${color_reset}]" + ktaptest 1 SKIP UNTESTED_CASES="$UNTESTED_CASES $CASENO" return 0 ;; $UNSUPPORTED) prlog " [${color_blue}UNSUPPORTED${color_reset}]" + ktaptest 1 SKIP UNSUPPORTED_CASES="$UNSUPPORTED_CASES $CASENO" return $UNSUPPORTED_RESULT # depends on use case ;; $XFAIL) prlog " [${color_green}XFAIL${color_reset}]" + ktaptest 1 XFAIL XFAILED_CASES="$XFAILED_CASES $CASENO" return 0 ;; *) prlog " [${color_blue}UNDEFINED${color_reset}]" + ktaptest 0 error UNDEFINED_CASES="$UNDEFINED_CASES $CASENO" return 1 # this must be a test bug ;; @@ -371,6 +405,7 @@ __run_test() { # testfile run_test() { # testfile local testname=`basename $1` testcase $1 + prlog -n "[$CASENO]$INSTANCE$CASENAME" if [ ! -z "$LOG_FILE" ] ; then local testlog=`mktemp $LOG_DIR/${CASENO}-${testname}-log.XXXXXX` else @@ -405,6 +440,17 @@ run_test() { # testfile # load in the helper functions . $TEST_DIR/functions +if [ "$KTAP" = "1" ]; then + echo "TAP version 13" + + casecount=`echo $TEST_CASES | wc -w` + for t in $TEST_CASES; do + test_on_instance $t || continue + casecount=$((casecount+1)) + done + echo "1..${casecount}" +fi + # Main loop for t in $TEST_CASES; do run_test $t @@ -439,6 +485,17 @@ prlog "# of unsupported: " `echo $UNSUPPORTED_CASES | wc -w` prlog "# of xfailed: " `echo $XFAILED_CASES | wc -w` prlog "# of undefined(test bug): " `echo $UNDEFINED_CASES | wc -w` +if [ "$KTAP" = "1" ]; then + echo -n "# Totals:" + echo -n " pass:"`echo $PASSED_CASES | wc -w` + echo -n " faii:"`echo $FAILED_CASES | wc -w` + echo -n " xfail:"`echo $XFAILED_CASES | wc -w` + echo -n " xpass:0" + echo -n " skip:"`echo $UNTESTED_CASES $UNSUPPORTED_CASES | wc -w` + echo -n " error:"`echo $UNRESOLVED_CASES $UNDEFINED_CASES | wc -w` + echo +fi + cleanup # if no error, return 0 diff --git a/tools/testing/selftests/ftrace/ftracetest-ktap b/tools/testing/selftests/ftrace/ftracetest-ktap new file mode 100755 index 000000000000..b3284679ef3a --- /dev/null +++ b/tools/testing/selftests/ftrace/ftracetest-ktap @@ -0,0 +1,8 @@ +#!/bin/sh -e +# SPDX-License-Identifier: GPL-2.0-only +# +# ftracetest-ktap: Wrapper to integrate ftracetest with the kselftest runner +# +# Copyright (C) Arm Ltd., 2023 + +./ftracetest -K diff --git a/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc b/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc index e2ff3bf4df80..2de7c61d1ae3 100644 --- a/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc +++ b/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc @@ -9,18 +9,33 @@ fail() { #msg exit_fail } -echo "Test event filter function name" +sample_events() { + echo > trace + echo 1 > events/kmem/kmem_cache_free/enable + echo 1 > tracing_on + ls > /dev/null + echo 0 > tracing_on + echo 0 > events/kmem/kmem_cache_free/enable +} + echo 0 > tracing_on echo 0 > events/enable + +echo "Get the most frequently calling function" +sample_events + +target_func=`cut -d: -f3 trace | sed 's/call_site=\([^+]*\)+0x.*/\1/' | sort | uniq -c | sort | tail -n 1 | sed 's/^[ 0-9]*//'` +if [ -z "$target_func" ]; then + exit_fail +fi echo > trace -echo 'call_site.function == exit_mmap' > events/kmem/kmem_cache_free/filter -echo 1 > events/kmem/kmem_cache_free/enable -echo 1 > tracing_on -ls > /dev/null -echo 0 > events/kmem/kmem_cache_free/enable -hitcnt=`grep kmem_cache_free trace| grep exit_mmap | wc -l` -misscnt=`grep kmem_cache_free trace| grep -v exit_mmap | wc -l` +echo "Test event filter function name" +echo "call_site.function == $target_func" > events/kmem/kmem_cache_free/filter +sample_events + +hitcnt=`grep kmem_cache_free trace| grep $target_func | wc -l` +misscnt=`grep kmem_cache_free trace| grep -v $target_func | wc -l` if [ $hitcnt -eq 0 ]; then exit_fail @@ -30,20 +45,14 @@ if [ $misscnt -gt 0 ]; then exit_fail fi -address=`grep ' exit_mmap$' /proc/kallsyms | cut -d' ' -f1` +address=`grep " ${target_func}\$" /proc/kallsyms | cut -d' ' -f1` echo "Test event filter function address" -echo 0 > tracing_on -echo 0 > events/enable -echo > trace echo "call_site.function == 0x$address" > events/kmem/kmem_cache_free/filter -echo 1 > events/kmem/kmem_cache_free/enable -echo 1 > tracing_on -sleep 1 -echo 0 > events/kmem/kmem_cache_free/enable +sample_events -hitcnt=`grep kmem_cache_free trace| grep exit_mmap | wc -l` -misscnt=`grep kmem_cache_free trace| grep -v exit_mmap | wc -l` +hitcnt=`grep kmem_cache_free trace| grep $target_func | wc -l` +misscnt=`grep kmem_cache_free trace| grep -v $target_func | wc -l` if [ $hitcnt -eq 0 ]; then exit_fail diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_opt_types.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_opt_types.tc new file mode 100644 index 000000000000..9f5d99328086 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_opt_types.tc @@ -0,0 +1,34 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0-or-later +# Copyright (C) 2023 Akanksha J N, IBM corporation +# description: Register/unregister optimized probe +# requires: kprobe_events + +case `uname -m` in +x86_64) +;; +arm*) +;; +ppc*) +;; +*) + echo "Please implement other architecture here" + exit_unsupported +esac + +DEFAULT=$(cat /proc/sys/debug/kprobes-optimization) +echo 1 > /proc/sys/debug/kprobes-optimization +for i in `seq 0 255`; do + echo "p:testprobe $FUNCTION_FORK+${i}" > kprobe_events || continue + echo 1 > events/kprobes/enable || continue + (echo "forked") + PROBE=$(grep $FUNCTION_FORK /sys/kernel/debug/kprobes/list) + echo 0 > events/kprobes/enable + echo > kprobe_events + if echo $PROBE | grep -q OPTIMIZED; then + echo "$DEFAULT" > /proc/sys/debug/kprobes-optimization + exit_pass + fi +done +echo "$DEFAULT" > /proc/sys/debug/kprobes-optimization +exit_unresolved diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack-legacy.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack-legacy.tc new file mode 100644 index 000000000000..d0cd91a93069 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack-legacy.tc @@ -0,0 +1,24 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: event trigger - test inter-event histogram trigger trace action with dynamic string param (legacy stack) +# requires: set_event synthetic_events events/sched/sched_process_exec/hist "long[] stack' >> synthetic_events":README + +fail() { #msg + echo $1 + exit_fail +} + +echo "Test create synthetic event with stack" + +# Test the old stacktrace keyword (for backward compatibility) +echo 's:wake_lat pid_t pid; u64 delta; unsigned long[] stack;' > dynamic_events +echo 'hist:keys=next_pid:ts=common_timestamp.usecs,st=stacktrace if prev_state == 1||prev_state == 2' >> events/sched/sched_switch/trigger +echo 'hist:keys=prev_pid:delta=common_timestamp.usecs-$ts,s=$st:onmax($delta).trace(wake_lat,prev_pid,$delta,$s)' >> events/sched/sched_switch/trigger +echo 1 > events/synthetic/wake_lat/enable +sleep 1 + +if ! grep -q "=>.*sched" trace; then + fail "Failed to create synthetic event with stack" +fi + +exit 0 diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack.tc index 755dbe94ccf4..8f1cc9a86a06 100644 --- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack.tc +++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack.tc @@ -1,7 +1,7 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 # description: event trigger - test inter-event histogram trigger trace action with dynamic string param -# requires: set_event synthetic_events events/sched/sched_process_exec/hist "long[]' >> synthetic_events":README +# requires: set_event synthetic_events events/sched/sched_process_exec/hist "can be any field, or the special string 'common_stacktrace'":README fail() { #msg echo $1 @@ -10,9 +10,8 @@ fail() { #msg echo "Test create synthetic event with stack" - echo 's:wake_lat pid_t pid; u64 delta; unsigned long[] stack;' > dynamic_events -echo 'hist:keys=next_pid:ts=common_timestamp.usecs,st=stacktrace if prev_state == 1||prev_state == 2' >> events/sched/sched_switch/trigger +echo 'hist:keys=next_pid:ts=common_timestamp.usecs,st=common_stacktrace if prev_state == 1||prev_state == 2' >> events/sched/sched_switch/trigger echo 'hist:keys=prev_pid:delta=common_timestamp.usecs-$ts,s=$st:onmax($delta).trace(wake_lat,prev_pid,$delta,$s)' >> events/sched/sched_switch/trigger echo 1 > events/synthetic/wake_lat/enable sleep 1 diff --git a/tools/testing/selftests/gpio/gpio-sim.sh b/tools/testing/selftests/gpio/gpio-sim.sh index 9f539d454ee4..fa2ce2b9dd5f 100755 --- a/tools/testing/selftests/gpio/gpio-sim.sh +++ b/tools/testing/selftests/gpio/gpio-sim.sh @@ -389,6 +389,9 @@ create_chip chip create_bank chip bank set_num_lines chip bank 8 enable_chip chip +DEVNAME=`configfs_dev_name chip` +CHIPNAME=`configfs_chip_name chip bank` +SYSFS_PATH="/sys/devices/platform/$DEVNAME/$CHIPNAME/sim_gpio0/value" $BASE_DIR/gpio-mockup-cdev -b pull-up /dev/`configfs_chip_name chip bank` 0 test `cat $SYSFS_PATH` = "1" || fail "bias setting does not work" remove_chip chip diff --git a/tools/testing/selftests/kselftest/runner.sh b/tools/testing/selftests/kselftest/runner.sh index 294619ade49f..1c952d1401d4 100644 --- a/tools/testing/selftests/kselftest/runner.sh +++ b/tools/testing/selftests/kselftest/runner.sh @@ -8,7 +8,8 @@ export logfile=/dev/stdout export per_test_logging= # Defaults for "settings" file fields: -# "timeout" how many seconds to let each test run before failing. +# "timeout" how many seconds to let each test run before running +# over our soft timeout limit. export kselftest_default_timeout=45 # There isn't a shell-agnostic way to find the path of a sourced file, @@ -90,6 +91,14 @@ run_one() done < "$settings" fi + # Command line timeout overrides the settings file + if [ -n "$kselftest_override_timeout" ]; then + kselftest_timeout="$kselftest_override_timeout" + echo "# overriding timeout to $kselftest_timeout" >> "$logfile" + else + echo "# timeout set to $kselftest_timeout" >> "$logfile" + fi + TEST_HDR_MSG="selftests: $DIR: $BASENAME_TEST" echo "# $TEST_HDR_MSG" if [ ! -e "$TEST" ]; then diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index d8bff2005dfc..5fd49ad0c696 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -249,7 +249,7 @@ /** * FIXTURE_SETUP() - Prepares the setup function for the fixture. - * *_metadata* is included so that EXPECT_* and ASSERT_* work correctly. + * *_metadata* is included so that EXPECT_*, ASSERT_* etc. work correctly. * * @fixture_name: fixture name * @@ -275,7 +275,7 @@ /** * FIXTURE_TEARDOWN() - * *_metadata* is included so that EXPECT_* and ASSERT_* work correctly. + * *_metadata* is included so that EXPECT_*, ASSERT_* etc. work correctly. * * @fixture_name: fixture name * @@ -388,7 +388,7 @@ if (setjmp(_metadata->env) == 0) { \ fixture_name##_setup(_metadata, &self, variant->data); \ /* Let setup failure terminate early. */ \ - if (!_metadata->passed) \ + if (!_metadata->passed || _metadata->skip) \ return; \ _metadata->setup_completed = true; \ fixture_name##_##test_name(_metadata, &self, variant->data); \ diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 7a5ff646e7e7..4761b768b773 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -116,6 +116,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/sev_migrate_tests TEST_GEN_PROGS_x86_64 += x86_64/amx_test TEST_GEN_PROGS_x86_64 += x86_64/max_vcpuid_cap_test TEST_GEN_PROGS_x86_64 += x86_64/triple_fault_event_test +TEST_GEN_PROGS_x86_64 += x86_64/recalc_apic_map_test TEST_GEN_PROGS_x86_64 += access_tracking_perf_test TEST_GEN_PROGS_x86_64 += demand_paging_test TEST_GEN_PROGS_x86_64 += dirty_log_test diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c index d4e1f4af29d6..4f10055af2aa 100644 --- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c +++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c @@ -48,6 +48,34 @@ struct reg_sublist { __u64 rejects_set_n; }; +struct feature_id_reg { + __u64 reg; + __u64 id_reg; + __u64 feat_shift; + __u64 feat_min; +}; + +static struct feature_id_reg feat_id_regs[] = { + { + ARM64_SYS_REG(3, 0, 2, 0, 3), /* TCR2_EL1 */ + ARM64_SYS_REG(3, 0, 0, 7, 3), /* ID_AA64MMFR3_EL1 */ + 0, + 1 + }, + { + ARM64_SYS_REG(3, 0, 10, 2, 2), /* PIRE0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 7, 3), /* ID_AA64MMFR3_EL1 */ + 4, + 1 + }, + { + ARM64_SYS_REG(3, 0, 10, 2, 3), /* PIR_EL1 */ + ARM64_SYS_REG(3, 0, 0, 7, 3), /* ID_AA64MMFR3_EL1 */ + 4, + 1 + } +}; + struct vcpu_config { char *name; struct reg_sublist sublists[]; @@ -68,7 +96,8 @@ static int vcpu_configs_n; #define for_each_missing_reg(i) \ for ((i) = 0; (i) < blessed_n; ++(i)) \ - if (!find_reg(reg_list->reg, reg_list->n, blessed_reg[i])) + if (!find_reg(reg_list->reg, reg_list->n, blessed_reg[i])) \ + if (check_supported_feat_reg(vcpu, blessed_reg[i])) #define for_each_new_reg(i) \ for_each_reg_filtered(i) \ @@ -132,6 +161,25 @@ static bool find_reg(__u64 regs[], __u64 nr_regs, __u64 reg) return false; } +static bool check_supported_feat_reg(struct kvm_vcpu *vcpu, __u64 reg) +{ + int i, ret; + __u64 data, feat_val; + + for (i = 0; i < ARRAY_SIZE(feat_id_regs); i++) { + if (feat_id_regs[i].reg == reg) { + ret = __vcpu_get_reg(vcpu, feat_id_regs[i].id_reg, &data); + if (ret < 0) + return false; + + feat_val = ((data >> feat_id_regs[i].feat_shift) & 0xf); + return feat_val >= feat_id_regs[i].feat_min; + } + } + + return true; +} + static const char *str_with_index(const char *template, __u64 index) { char *str, *p; @@ -843,12 +891,15 @@ static __u64 base_regs[] = { ARM64_SYS_REG(3, 0, 2, 0, 0), /* TTBR0_EL1 */ ARM64_SYS_REG(3, 0, 2, 0, 1), /* TTBR1_EL1 */ ARM64_SYS_REG(3, 0, 2, 0, 2), /* TCR_EL1 */ + ARM64_SYS_REG(3, 0, 2, 0, 3), /* TCR2_EL1 */ ARM64_SYS_REG(3, 0, 5, 1, 0), /* AFSR0_EL1 */ ARM64_SYS_REG(3, 0, 5, 1, 1), /* AFSR1_EL1 */ ARM64_SYS_REG(3, 0, 5, 2, 0), /* ESR_EL1 */ ARM64_SYS_REG(3, 0, 6, 0, 0), /* FAR_EL1 */ ARM64_SYS_REG(3, 0, 7, 4, 0), /* PAR_EL1 */ ARM64_SYS_REG(3, 0, 10, 2, 0), /* MAIR_EL1 */ + ARM64_SYS_REG(3, 0, 10, 2, 2), /* PIRE0_EL1 */ + ARM64_SYS_REG(3, 0, 10, 2, 3), /* PIR_EL1 */ ARM64_SYS_REG(3, 0, 10, 3, 0), /* AMAIR_EL1 */ ARM64_SYS_REG(3, 0, 12, 0, 0), /* VBAR_EL1 */ ARM64_SYS_REG(3, 0, 12, 1, 1), /* DISR_EL1 */ diff --git a/tools/testing/selftests/kvm/x86_64/recalc_apic_map_test.c b/tools/testing/selftests/kvm/x86_64/recalc_apic_map_test.c new file mode 100644 index 000000000000..4c416ebe7d66 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/recalc_apic_map_test.c @@ -0,0 +1,74 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Test edge cases and race conditions in kvm_recalculate_apic_map(). + */ + +#include <sys/ioctl.h> +#include <pthread.h> +#include <time.h> + +#include "processor.h" +#include "test_util.h" +#include "kvm_util.h" +#include "apic.h" + +#define TIMEOUT 5 /* seconds */ + +#define LAPIC_DISABLED 0 +#define LAPIC_X2APIC (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE) +#define MAX_XAPIC_ID 0xff + +static void *race(void *arg) +{ + struct kvm_lapic_state lapic = {}; + struct kvm_vcpu *vcpu = arg; + + while (1) { + /* Trigger kvm_recalculate_apic_map(). */ + vcpu_ioctl(vcpu, KVM_SET_LAPIC, &lapic); + pthread_testcancel(); + } + + return NULL; +} + +int main(void) +{ + struct kvm_vcpu *vcpus[KVM_MAX_VCPUS]; + struct kvm_vcpu *vcpuN; + struct kvm_vm *vm; + pthread_t thread; + time_t t; + int i; + + kvm_static_assert(KVM_MAX_VCPUS > MAX_XAPIC_ID); + + /* + * Create the max number of vCPUs supported by selftests so that KVM + * has decent amount of work to do when recalculating the map, i.e. to + * make the problematic window large enough to hit. + */ + vm = vm_create_with_vcpus(KVM_MAX_VCPUS, NULL, vcpus); + + /* + * Enable x2APIC on all vCPUs so that KVM doesn't bail from the recalc + * due to vCPUs having aliased xAPIC IDs (truncated to 8 bits). + */ + for (i = 0; i < KVM_MAX_VCPUS; i++) + vcpu_set_msr(vcpus[i], MSR_IA32_APICBASE, LAPIC_X2APIC); + + ASSERT_EQ(pthread_create(&thread, NULL, race, vcpus[0]), 0); + + vcpuN = vcpus[KVM_MAX_VCPUS - 1]; + for (t = time(NULL) + TIMEOUT; time(NULL) < t;) { + vcpu_set_msr(vcpuN, MSR_IA32_APICBASE, LAPIC_X2APIC); + vcpu_set_msr(vcpuN, MSR_IA32_APICBASE, LAPIC_DISABLED); + } + + ASSERT_EQ(pthread_cancel(thread), 0); + ASSERT_EQ(pthread_join(thread, NULL), 0); + + kvm_vm_free(vm); + + return 0; +} diff --git a/tools/testing/selftests/landlock/config b/tools/testing/selftests/landlock/config index 0f0a65287bac..3dc9e438eab1 100644 --- a/tools/testing/selftests/landlock/config +++ b/tools/testing/selftests/landlock/config @@ -1,7 +1,10 @@ +CONFIG_CGROUPS=y +CONFIG_CGROUP_SCHED=y CONFIG_OVERLAY_FS=y -CONFIG_SECURITY_LANDLOCK=y -CONFIG_SECURITY_PATH=y +CONFIG_PROC_FS=y CONFIG_SECURITY=y +CONFIG_SECURITY_LANDLOCK=y CONFIG_SHMEM=y -CONFIG_TMPFS_XATTR=y +CONFIG_SYSFS=y CONFIG_TMPFS=y +CONFIG_TMPFS_XATTR=y diff --git a/tools/testing/selftests/landlock/config.um b/tools/testing/selftests/landlock/config.um new file mode 100644 index 000000000000..40937c0395d6 --- /dev/null +++ b/tools/testing/selftests/landlock/config.um @@ -0,0 +1 @@ +CONFIG_HOSTFS=y diff --git a/tools/testing/selftests/landlock/fs_test.c b/tools/testing/selftests/landlock/fs_test.c index b6c4be3faf7a..83d565569512 100644 --- a/tools/testing/selftests/landlock/fs_test.c +++ b/tools/testing/selftests/landlock/fs_test.c @@ -10,6 +10,7 @@ #define _GNU_SOURCE #include <fcntl.h> #include <linux/landlock.h> +#include <linux/magic.h> #include <sched.h> #include <stdio.h> #include <string.h> @@ -19,6 +20,7 @@ #include <sys/sendfile.h> #include <sys/stat.h> #include <sys/sysmacros.h> +#include <sys/vfs.h> #include <unistd.h> #include "common.h" @@ -107,8 +109,10 @@ static bool fgrep(FILE *const inf, const char *const str) return false; } -static bool supports_overlayfs(void) +static bool supports_filesystem(const char *const filesystem) { + char str[32]; + int len; bool res; FILE *const inf = fopen("/proc/filesystems", "r"); @@ -119,11 +123,33 @@ static bool supports_overlayfs(void) if (!inf) return true; - res = fgrep(inf, "nodev\toverlay\n"); + /* filesystem can be null for bind mounts. */ + if (!filesystem) + return true; + + len = snprintf(str, sizeof(str), "nodev\t%s\n", filesystem); + if (len >= sizeof(str)) + /* Ignores too-long filesystem names. */ + return true; + + res = fgrep(inf, str); fclose(inf); return res; } +static bool cwd_matches_fs(unsigned int fs_magic) +{ + struct statfs statfs_buf; + + if (!fs_magic) + return true; + + if (statfs(".", &statfs_buf)) + return true; + + return statfs_buf.f_type == fs_magic; +} + static void mkdir_parents(struct __test_metadata *const _metadata, const char *const path) { @@ -206,7 +232,26 @@ out: return err; } -static void prepare_layout(struct __test_metadata *const _metadata) +struct mnt_opt { + const char *const source; + const char *const type; + const unsigned long flags; + const char *const data; +}; + +const struct mnt_opt mnt_tmp = { + .type = "tmpfs", + .data = "size=4m,mode=700", +}; + +static int mount_opt(const struct mnt_opt *const mnt, const char *const target) +{ + return mount(mnt->source ?: mnt->type, target, mnt->type, mnt->flags, + mnt->data); +} + +static void prepare_layout_opt(struct __test_metadata *const _metadata, + const struct mnt_opt *const mnt) { disable_caps(_metadata); umask(0077); @@ -217,12 +262,28 @@ static void prepare_layout(struct __test_metadata *const _metadata) * for tests relying on pivot_root(2) and move_mount(2). */ set_cap(_metadata, CAP_SYS_ADMIN); - ASSERT_EQ(0, unshare(CLONE_NEWNS)); - ASSERT_EQ(0, mount("tmp", TMP_DIR, "tmpfs", 0, "size=4m,mode=700")); + ASSERT_EQ(0, unshare(CLONE_NEWNS | CLONE_NEWCGROUP)); + ASSERT_EQ(0, mount_opt(mnt, TMP_DIR)) + { + TH_LOG("Failed to mount the %s filesystem: %s", mnt->type, + strerror(errno)); + /* + * FIXTURE_TEARDOWN() is not called when FIXTURE_SETUP() + * failed, so we need to explicitly do a minimal cleanup to + * avoid cascading errors with other tests that don't depend on + * the same filesystem. + */ + remove_path(TMP_DIR); + } ASSERT_EQ(0, mount(NULL, TMP_DIR, NULL, MS_PRIVATE | MS_REC, NULL)); clear_cap(_metadata, CAP_SYS_ADMIN); } +static void prepare_layout(struct __test_metadata *const _metadata) +{ + prepare_layout_opt(_metadata, &mnt_tmp); +} + static void cleanup_layout(struct __test_metadata *const _metadata) { set_cap(_metadata, CAP_SYS_ADMIN); @@ -231,6 +292,20 @@ static void cleanup_layout(struct __test_metadata *const _metadata) EXPECT_EQ(0, remove_path(TMP_DIR)); } +/* clang-format off */ +FIXTURE(layout0) {}; +/* clang-format on */ + +FIXTURE_SETUP(layout0) +{ + prepare_layout(_metadata); +} + +FIXTURE_TEARDOWN(layout0) +{ + cleanup_layout(_metadata); +} + static void create_layout1(struct __test_metadata *const _metadata) { create_file(_metadata, file1_s1d1); @@ -248,7 +323,7 @@ static void create_layout1(struct __test_metadata *const _metadata) create_file(_metadata, file1_s3d1); create_directory(_metadata, dir_s3d2); set_cap(_metadata, CAP_SYS_ADMIN); - ASSERT_EQ(0, mount("tmp", dir_s3d2, "tmpfs", 0, "size=4m,mode=700")); + ASSERT_EQ(0, mount_opt(&mnt_tmp, dir_s3d2)); clear_cap(_metadata, CAP_SYS_ADMIN); ASSERT_EQ(0, mkdir(dir_s3d3, 0700)); @@ -262,11 +337,13 @@ static void remove_layout1(struct __test_metadata *const _metadata) EXPECT_EQ(0, remove_path(file1_s1d3)); EXPECT_EQ(0, remove_path(file1_s1d2)); EXPECT_EQ(0, remove_path(file1_s1d1)); + EXPECT_EQ(0, remove_path(dir_s1d3)); EXPECT_EQ(0, remove_path(file2_s2d3)); EXPECT_EQ(0, remove_path(file1_s2d3)); EXPECT_EQ(0, remove_path(file1_s2d2)); EXPECT_EQ(0, remove_path(file1_s2d1)); + EXPECT_EQ(0, remove_path(dir_s2d2)); EXPECT_EQ(0, remove_path(file1_s3d1)); EXPECT_EQ(0, remove_path(dir_s3d3)); @@ -510,7 +587,7 @@ TEST_F_FORK(layout1, file_and_dir_access_rights) ASSERT_EQ(0, close(ruleset_fd)); } -TEST_F_FORK(layout1, unknown_access_rights) +TEST_F_FORK(layout0, unknown_access_rights) { __u64 access_mask; @@ -608,7 +685,7 @@ static void enforce_ruleset(struct __test_metadata *const _metadata, } } -TEST_F_FORK(layout1, proc_nsfs) +TEST_F_FORK(layout0, proc_nsfs) { const struct rule rules[] = { { @@ -657,11 +734,11 @@ TEST_F_FORK(layout1, proc_nsfs) ASSERT_EQ(0, close(path_beneath.parent_fd)); } -TEST_F_FORK(layout1, unpriv) +TEST_F_FORK(layout0, unpriv) { const struct rule rules[] = { { - .path = dir_s1d2, + .path = TMP_DIR, .access = ACCESS_RO, }, {}, @@ -1301,12 +1378,12 @@ TEST_F_FORK(layout1, inherit_superset) ASSERT_EQ(0, test_open(file1_s1d3, O_RDONLY)); } -TEST_F_FORK(layout1, max_layers) +TEST_F_FORK(layout0, max_layers) { int i, err; const struct rule rules[] = { { - .path = dir_s1d2, + .path = TMP_DIR, .access = ACCESS_RO, }, {}, @@ -4030,21 +4107,24 @@ static const char (*merge_sub_files[])[] = { * └── work */ -/* clang-format off */ -FIXTURE(layout2_overlay) {}; -/* clang-format on */ +FIXTURE(layout2_overlay) +{ + bool skip_test; +}; FIXTURE_SETUP(layout2_overlay) { - if (!supports_overlayfs()) - SKIP(return, "overlayfs is not supported"); + if (!supports_filesystem("overlay")) { + self->skip_test = true; + SKIP(return, "overlayfs is not supported (setup)"); + } prepare_layout(_metadata); create_directory(_metadata, LOWER_BASE); set_cap(_metadata, CAP_SYS_ADMIN); /* Creates tmpfs mount points to get deterministic overlayfs. */ - ASSERT_EQ(0, mount("tmp", LOWER_BASE, "tmpfs", 0, "size=4m,mode=700")); + ASSERT_EQ(0, mount_opt(&mnt_tmp, LOWER_BASE)); clear_cap(_metadata, CAP_SYS_ADMIN); create_file(_metadata, lower_fl1); create_file(_metadata, lower_dl1_fl2); @@ -4054,7 +4134,7 @@ FIXTURE_SETUP(layout2_overlay) create_directory(_metadata, UPPER_BASE); set_cap(_metadata, CAP_SYS_ADMIN); - ASSERT_EQ(0, mount("tmp", UPPER_BASE, "tmpfs", 0, "size=4m,mode=700")); + ASSERT_EQ(0, mount_opt(&mnt_tmp, UPPER_BASE)); clear_cap(_metadata, CAP_SYS_ADMIN); create_file(_metadata, upper_fu1); create_file(_metadata, upper_du1_fu2); @@ -4075,8 +4155,8 @@ FIXTURE_SETUP(layout2_overlay) FIXTURE_TEARDOWN(layout2_overlay) { - if (!supports_overlayfs()) - SKIP(return, "overlayfs is not supported"); + if (self->skip_test) + SKIP(return, "overlayfs is not supported (teardown)"); EXPECT_EQ(0, remove_path(lower_do1_fl3)); EXPECT_EQ(0, remove_path(lower_dl1_fl2)); @@ -4109,8 +4189,8 @@ FIXTURE_TEARDOWN(layout2_overlay) TEST_F_FORK(layout2_overlay, no_restriction) { - if (!supports_overlayfs()) - SKIP(return, "overlayfs is not supported"); + if (self->skip_test) + SKIP(return, "overlayfs is not supported (test)"); ASSERT_EQ(0, test_open(lower_fl1, O_RDONLY)); ASSERT_EQ(0, test_open(lower_dl1, O_RDONLY)); @@ -4275,8 +4355,8 @@ TEST_F_FORK(layout2_overlay, same_content_different_file) size_t i; const char *path_entry; - if (!supports_overlayfs()) - SKIP(return, "overlayfs is not supported"); + if (self->skip_test) + SKIP(return, "overlayfs is not supported (test)"); /* Sets rules on base directories (i.e. outside overlay scope). */ ruleset_fd = create_ruleset(_metadata, ACCESS_RW, layer1_base); @@ -4423,4 +4503,261 @@ TEST_F_FORK(layout2_overlay, same_content_different_file) } } +FIXTURE(layout3_fs) +{ + bool has_created_dir; + bool has_created_file; + char *dir_path; + bool skip_test; +}; + +FIXTURE_VARIANT(layout3_fs) +{ + const struct mnt_opt mnt; + const char *const file_path; + unsigned int cwd_fs_magic; +}; + +/* clang-format off */ +FIXTURE_VARIANT_ADD(layout3_fs, tmpfs) { + /* clang-format on */ + .mnt = mnt_tmp, + .file_path = file1_s1d1, +}; + +FIXTURE_VARIANT_ADD(layout3_fs, ramfs) { + .mnt = { + .type = "ramfs", + .data = "mode=700", + }, + .file_path = TMP_DIR "/dir/file", +}; + +FIXTURE_VARIANT_ADD(layout3_fs, cgroup2) { + .mnt = { + .type = "cgroup2", + }, + .file_path = TMP_DIR "/test/cgroup.procs", +}; + +FIXTURE_VARIANT_ADD(layout3_fs, proc) { + .mnt = { + .type = "proc", + }, + .file_path = TMP_DIR "/self/status", +}; + +FIXTURE_VARIANT_ADD(layout3_fs, sysfs) { + .mnt = { + .type = "sysfs", + }, + .file_path = TMP_DIR "/kernel/notes", +}; + +FIXTURE_VARIANT_ADD(layout3_fs, hostfs) { + .mnt = { + .source = TMP_DIR, + .flags = MS_BIND, + }, + .file_path = TMP_DIR "/dir/file", + .cwd_fs_magic = HOSTFS_SUPER_MAGIC, +}; + +FIXTURE_SETUP(layout3_fs) +{ + struct stat statbuf; + const char *slash; + size_t dir_len; + + if (!supports_filesystem(variant->mnt.type) || + !cwd_matches_fs(variant->cwd_fs_magic)) { + self->skip_test = true; + SKIP(return, "this filesystem is not supported (setup)"); + } + + slash = strrchr(variant->file_path, '/'); + ASSERT_NE(slash, NULL); + dir_len = (size_t)slash - (size_t)variant->file_path; + ASSERT_LT(0, dir_len); + self->dir_path = malloc(dir_len + 1); + self->dir_path[dir_len] = '\0'; + strncpy(self->dir_path, variant->file_path, dir_len); + + prepare_layout_opt(_metadata, &variant->mnt); + + /* Creates directory when required. */ + if (stat(self->dir_path, &statbuf)) { + set_cap(_metadata, CAP_DAC_OVERRIDE); + EXPECT_EQ(0, mkdir(self->dir_path, 0700)) + { + TH_LOG("Failed to create directory \"%s\": %s", + self->dir_path, strerror(errno)); + free(self->dir_path); + self->dir_path = NULL; + } + self->has_created_dir = true; + clear_cap(_metadata, CAP_DAC_OVERRIDE); + } + + /* Creates file when required. */ + if (stat(variant->file_path, &statbuf)) { + int fd; + + set_cap(_metadata, CAP_DAC_OVERRIDE); + fd = creat(variant->file_path, 0600); + EXPECT_LE(0, fd) + { + TH_LOG("Failed to create file \"%s\": %s", + variant->file_path, strerror(errno)); + } + EXPECT_EQ(0, close(fd)); + self->has_created_file = true; + clear_cap(_metadata, CAP_DAC_OVERRIDE); + } +} + +FIXTURE_TEARDOWN(layout3_fs) +{ + if (self->skip_test) + SKIP(return, "this filesystem is not supported (teardown)"); + + if (self->has_created_file) { + set_cap(_metadata, CAP_DAC_OVERRIDE); + /* + * Don't check for error because the file might already + * have been removed (cf. release_inode test). + */ + unlink(variant->file_path); + clear_cap(_metadata, CAP_DAC_OVERRIDE); + } + + if (self->has_created_dir) { + set_cap(_metadata, CAP_DAC_OVERRIDE); + /* + * Don't check for error because the directory might already + * have been removed (cf. release_inode test). + */ + rmdir(self->dir_path); + clear_cap(_metadata, CAP_DAC_OVERRIDE); + } + free(self->dir_path); + self->dir_path = NULL; + + cleanup_layout(_metadata); +} + +static void layer3_fs_tag_inode(struct __test_metadata *const _metadata, + FIXTURE_DATA(layout3_fs) * self, + const FIXTURE_VARIANT(layout3_fs) * variant, + const char *const rule_path) +{ + const struct rule layer1_allow_read_file[] = { + { + .path = rule_path, + .access = LANDLOCK_ACCESS_FS_READ_FILE, + }, + {}, + }; + const struct landlock_ruleset_attr layer2_deny_everything_attr = { + .handled_access_fs = LANDLOCK_ACCESS_FS_READ_FILE, + }; + const char *const dev_null_path = "/dev/null"; + int ruleset_fd; + + if (self->skip_test) + SKIP(return, "this filesystem is not supported (test)"); + + /* Checks without Landlock. */ + EXPECT_EQ(0, test_open(dev_null_path, O_RDONLY | O_CLOEXEC)); + EXPECT_EQ(0, test_open(variant->file_path, O_RDONLY | O_CLOEXEC)); + + ruleset_fd = create_ruleset(_metadata, LANDLOCK_ACCESS_FS_READ_FILE, + layer1_allow_read_file); + EXPECT_LE(0, ruleset_fd); + enforce_ruleset(_metadata, ruleset_fd); + EXPECT_EQ(0, close(ruleset_fd)); + + EXPECT_EQ(EACCES, test_open(dev_null_path, O_RDONLY | O_CLOEXEC)); + EXPECT_EQ(0, test_open(variant->file_path, O_RDONLY | O_CLOEXEC)); + + /* Forbids directory reading. */ + ruleset_fd = + landlock_create_ruleset(&layer2_deny_everything_attr, + sizeof(layer2_deny_everything_attr), 0); + EXPECT_LE(0, ruleset_fd); + enforce_ruleset(_metadata, ruleset_fd); + EXPECT_EQ(0, close(ruleset_fd)); + + /* Checks with Landlock and forbidden access. */ + EXPECT_EQ(EACCES, test_open(dev_null_path, O_RDONLY | O_CLOEXEC)); + EXPECT_EQ(EACCES, test_open(variant->file_path, O_RDONLY | O_CLOEXEC)); +} + +/* Matrix of tests to check file hierarchy evaluation. */ + +TEST_F_FORK(layout3_fs, tag_inode_dir_parent) +{ + /* The current directory must not be the root for this test. */ + layer3_fs_tag_inode(_metadata, self, variant, "."); +} + +TEST_F_FORK(layout3_fs, tag_inode_dir_mnt) +{ + layer3_fs_tag_inode(_metadata, self, variant, TMP_DIR); +} + +TEST_F_FORK(layout3_fs, tag_inode_dir_child) +{ + layer3_fs_tag_inode(_metadata, self, variant, self->dir_path); +} + +TEST_F_FORK(layout3_fs, tag_inode_file) +{ + layer3_fs_tag_inode(_metadata, self, variant, variant->file_path); +} + +/* Light version of layout1.release_inodes */ +TEST_F_FORK(layout3_fs, release_inodes) +{ + const struct rule layer1[] = { + { + .path = TMP_DIR, + .access = LANDLOCK_ACCESS_FS_READ_DIR, + }, + {}, + }; + int ruleset_fd; + + if (self->skip_test) + SKIP(return, "this filesystem is not supported (test)"); + + /* Clean up for the teardown to not fail. */ + if (self->has_created_file) + EXPECT_EQ(0, remove_path(variant->file_path)); + + if (self->has_created_dir) + /* Don't check for error because of cgroup specificities. */ + remove_path(self->dir_path); + + ruleset_fd = + create_ruleset(_metadata, LANDLOCK_ACCESS_FS_READ_DIR, layer1); + ASSERT_LE(0, ruleset_fd); + + /* Unmount the filesystem while it is being used by a ruleset. */ + set_cap(_metadata, CAP_SYS_ADMIN); + ASSERT_EQ(0, umount(TMP_DIR)); + clear_cap(_metadata, CAP_SYS_ADMIN); + + /* Replaces with a new mount point to simplify FIXTURE_TEARDOWN. */ + set_cap(_metadata, CAP_SYS_ADMIN); + ASSERT_EQ(0, mount_opt(&mnt_tmp, TMP_DIR)); + clear_cap(_metadata, CAP_SYS_ADMIN); + + enforce_ruleset(_metadata, ruleset_fd); + ASSERT_EQ(0, close(ruleset_fd)); + + /* Checks that access to the new mount point is denied. */ + ASSERT_EQ(EACCES, test_open(TMP_DIR, O_RDONLY)); +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index 05400462c779..d17854285f2b 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -44,10 +44,26 @@ endif selfdir = $(realpath $(dir $(filter %/lib.mk,$(MAKEFILE_LIST)))) top_srcdir = $(selfdir)/../../.. -ifeq ($(KHDR_INCLUDES),) -KHDR_INCLUDES := -isystem $(top_srcdir)/usr/include +ifeq ("$(origin O)", "command line") + KBUILD_OUTPUT := $(O) endif +ifneq ($(KBUILD_OUTPUT),) + # Make's built-in functions such as $(abspath ...), $(realpath ...) cannot + # expand a shell special character '~'. We use a somewhat tedious way here. + abs_objtree := $(shell cd $(top_srcdir) && mkdir -p $(KBUILD_OUTPUT) && cd $(KBUILD_OUTPUT) && pwd) + $(if $(abs_objtree),, \ + $(error failed to create output directory "$(KBUILD_OUTPUT)")) + # $(realpath ...) resolves symlinks + abs_objtree := $(realpath $(abs_objtree)) + KHDR_DIR := ${abs_objtree}/usr/include +else + abs_srctree := $(shell cd $(top_srcdir) && pwd) + KHDR_DIR := ${abs_srctree}/usr/include +endif + +KHDR_INCLUDES := -isystem $(KHDR_DIR) + # The following are built by lib.mk common compile rules. # TEST_CUSTOM_PROGS should be used by tests that require # custom build rule and prevent common build rule use. @@ -58,7 +74,25 @@ TEST_GEN_PROGS := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS)) TEST_GEN_PROGS_EXTENDED := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS_EXTENDED)) TEST_GEN_FILES := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_FILES)) -all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) +all: kernel_header_files $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) \ + $(TEST_GEN_FILES) + +kernel_header_files: + @ls $(KHDR_DIR)/linux/*.h >/dev/null 2>/dev/null; \ + if [ $$? -ne 0 ]; then \ + RED='\033[1;31m'; \ + NOCOLOR='\033[0m'; \ + echo; \ + echo -e "$${RED}error$${NOCOLOR}: missing kernel header files."; \ + echo "Please run this and try again:"; \ + echo; \ + echo " cd $(top_srcdir)"; \ + echo " make headers"; \ + echo; \ + exit 1; \ + fi + +.PHONY: kernel_header_files define RUN_TESTS BASE_DIR="$(selfdir)"; \ diff --git a/tools/testing/selftests/media_tests/video_device_test.c b/tools/testing/selftests/media_tests/video_device_test.c index 0f6aef2e2593..2c44e115f2f0 100644 --- a/tools/testing/selftests/media_tests/video_device_test.c +++ b/tools/testing/selftests/media_tests/video_device_test.c @@ -37,45 +37,58 @@ #include <time.h> #include <linux/videodev2.h> -int main(int argc, char **argv) +#define PRIORITY_MAX 4 + +int priority_test(int fd) { - int opt; - char video_dev[256]; - int count; - struct v4l2_tuner vtuner; - struct v4l2_capability vcap; + /* This test will try to update the priority associated with a file descriptor */ + + enum v4l2_priority old_priority, new_priority, priority_to_compare; int ret; - int fd; + int result = 0; - if (argc < 2) { - printf("Usage: %s [-d </dev/videoX>]\n", argv[0]); - exit(-1); + ret = ioctl(fd, VIDIOC_G_PRIORITY, &old_priority); + if (ret < 0) { + printf("Failed to get priority: %s\n", strerror(errno)); + return -1; + } + new_priority = (old_priority + 1) % PRIORITY_MAX; + ret = ioctl(fd, VIDIOC_S_PRIORITY, &new_priority); + if (ret < 0) { + printf("Failed to set priority: %s\n", strerror(errno)); + return -1; + } + ret = ioctl(fd, VIDIOC_G_PRIORITY, &priority_to_compare); + if (ret < 0) { + printf("Failed to get new priority: %s\n", strerror(errno)); + result = -1; + goto cleanup; + } + if (priority_to_compare != new_priority) { + printf("Priority wasn't set - test failed\n"); + result = -1; } - /* Process arguments */ - while ((opt = getopt(argc, argv, "d:")) != -1) { - switch (opt) { - case 'd': - strncpy(video_dev, optarg, sizeof(video_dev) - 1); - video_dev[sizeof(video_dev)-1] = '\0'; - break; - default: - printf("Usage: %s [-d </dev/videoX>]\n", argv[0]); - exit(-1); - } +cleanup: + ret = ioctl(fd, VIDIOC_S_PRIORITY, &old_priority); + if (ret < 0) { + printf("Failed to restore priority: %s\n", strerror(errno)); + return -1; } + return result; +} + +int loop_test(int fd) +{ + int count; + struct v4l2_tuner vtuner; + struct v4l2_capability vcap; + int ret; /* Generate random number of interations */ srand((unsigned int) time(NULL)); count = rand(); - /* Open Video device and keep it open */ - fd = open(video_dev, O_RDWR); - if (fd == -1) { - printf("Video Device open errno %s\n", strerror(errno)); - exit(-1); - } - printf("\nNote:\n" "While test is running, remove the device or unbind\n" "driver and ensure there are no use after free errors\n" @@ -98,4 +111,46 @@ int main(int argc, char **argv) sleep(10); count--; } + return 0; +} + +int main(int argc, char **argv) +{ + int opt; + char video_dev[256]; + int fd; + int test_result; + + if (argc < 2) { + printf("Usage: %s [-d </dev/videoX>]\n", argv[0]); + exit(-1); + } + + /* Process arguments */ + while ((opt = getopt(argc, argv, "d:")) != -1) { + switch (opt) { + case 'd': + strncpy(video_dev, optarg, sizeof(video_dev) - 1); + video_dev[sizeof(video_dev)-1] = '\0'; + break; + default: + printf("Usage: %s [-d </dev/videoX>]\n", argv[0]); + exit(-1); + } + } + + /* Open Video device and keep it open */ + fd = open(video_dev, O_RDWR); + if (fd == -1) { + printf("Video Device open errno %s\n", strerror(errno)); + exit(-1); + } + + test_result = priority_test(fd); + if (!test_result) + printf("Priority test - PASSED\n"); + else + printf("Priority test - FAILED\n"); + + loop_test(fd); } diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore index 8917455f4f51..7e2a982383c0 100644 --- a/tools/testing/selftests/mm/.gitignore +++ b/tools/testing/selftests/mm/.gitignore @@ -39,3 +39,6 @@ local_config.h local_config.mk ksm_functional_tests mdwe_test +gup_longterm +mkdirty +va_high_addr_switch diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index 23af4633f0f4..66d7c07dc177 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -5,12 +5,15 @@ LOCAL_HDRS += $(selfdir)/mm/local_config.h $(top_srcdir)/mm/gup_test.h include local_config.mk +ifeq ($(ARCH),) + ifeq ($(CROSS_COMPILE),) uname_M := $(shell uname -m 2>/dev/null || echo not) else uname_M := $(shell echo $(CROSS_COMPILE) | grep -o '^[a-z0-9]\+') endif -MACHINE ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/' -e 's/ppc64.*/ppc64/') +ARCH ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/' -e 's/ppc64.*/ppc64/') +endif # Without this, failed build products remain, with up-to-date timestamps, # thus tricking Make (and you!) into believing that All Is Well, in subsequent @@ -29,11 +32,12 @@ MACHINE ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/' -e 's/ppc64.*/p # LDLIBS. MAKEFLAGS += --no-builtin-rules -CFLAGS = -Wall -I $(top_srcdir) -I $(top_srcdir)/tools/include/uapi $(EXTRA_CFLAGS) $(KHDR_INCLUDES) +CFLAGS = -Wall -I $(top_srcdir) $(EXTRA_CFLAGS) $(KHDR_INCLUDES) LDLIBS = -lrt -lpthread TEST_GEN_PROGS = cow TEST_GEN_PROGS += compaction_test +TEST_GEN_PROGS += gup_longterm TEST_GEN_PROGS += gup_test TEST_GEN_PROGS += hmm-tests TEST_GEN_PROGS += hugetlb-madvise @@ -65,7 +69,7 @@ TEST_GEN_PROGS += ksm_tests TEST_GEN_PROGS += ksm_functional_tests TEST_GEN_PROGS += mdwe_test -ifeq ($(MACHINE),x86_64) +ifeq ($(ARCH),x86_64) CAN_BUILD_I386 := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_32bit_program.c -m32) CAN_BUILD_X86_64 := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_64bit_program.c) CAN_BUILD_WITH_NOPIE := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_program.c -no-pie) @@ -87,13 +91,13 @@ TEST_GEN_PROGS += $(BINARIES_64) endif else -ifneq (,$(findstring $(MACHINE),ppc64)) +ifneq (,$(findstring $(ARCH),ppc64)) TEST_GEN_PROGS += protection_keys endif endif -ifneq (,$(filter $(MACHINE),arm64 ia64 mips64 parisc64 ppc64 riscv64 s390x sparc64 x86_64)) +ifneq (,$(filter $(ARCH),arm64 ia64 mips64 parisc64 ppc64 riscv64 s390x sparc64 x86_64)) TEST_GEN_PROGS += va_high_addr_switch TEST_GEN_PROGS += virtual_address_range TEST_GEN_PROGS += write_to_hugetlbfs @@ -112,7 +116,7 @@ $(TEST_GEN_PROGS): vm_util.c $(OUTPUT)/uffd-stress: uffd-common.c $(OUTPUT)/uffd-unit-tests: uffd-common.c -ifeq ($(MACHINE),x86_64) +ifeq ($(ARCH),x86_64) BINARIES_32 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_32)) BINARIES_64 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_64)) @@ -164,6 +168,8 @@ endif # IOURING_EXTRA_LIBS may get set in local_config.mk, or it may be left empty. $(OUTPUT)/cow: LDLIBS += $(IOURING_EXTRA_LIBS) +$(OUTPUT)/gup_longterm: LDLIBS += $(IOURING_EXTRA_LIBS) + $(OUTPUT)/mlock-random-test $(OUTPUT)/memfd_secret: LDLIBS += -lcap $(OUTPUT)/ksm_tests: LDLIBS += -lnuma diff --git a/tools/testing/selftests/mm/cow.c b/tools/testing/selftests/mm/cow.c index dc9d6fe86028..7324ce5363c0 100644 --- a/tools/testing/selftests/mm/cow.c +++ b/tools/testing/selftests/mm/cow.c @@ -14,8 +14,8 @@ #include <unistd.h> #include <errno.h> #include <fcntl.h> -#include <dirent.h> #include <assert.h> +#include <linux/mman.h> #include <sys/mman.h> #include <sys/ioctl.h> #include <sys/wait.h> @@ -30,13 +30,6 @@ #include "../kselftest.h" #include "vm_util.h" -#ifndef MADV_PAGEOUT -#define MADV_PAGEOUT 21 -#endif -#ifndef MADV_COLLAPSE -#define MADV_COLLAPSE 25 -#endif - static size_t pagesize; static int pagemap_fd; static size_t thpsize; @@ -70,31 +63,6 @@ static void detect_huge_zeropage(void) close(fd); } -static void detect_hugetlbsizes(void) -{ - DIR *dir = opendir("/sys/kernel/mm/hugepages/"); - - if (!dir) - return; - - while (nr_hugetlbsizes < ARRAY_SIZE(hugetlbsizes)) { - struct dirent *entry = readdir(dir); - size_t kb; - - if (!entry) - break; - if (entry->d_type != DT_DIR) - continue; - if (sscanf(entry->d_name, "hugepages-%zukB", &kb) != 1) - continue; - hugetlbsizes[nr_hugetlbsizes] = kb * 1024; - nr_hugetlbsizes++; - ksft_print_msg("[INFO] detected hugetlb size: %zu KiB\n", - kb); - } - closedir(dir); -} - static bool range_is_swapped(void *addr, size_t size) { for (; size; addr += pagesize, size -= pagesize) @@ -1717,7 +1685,8 @@ int main(int argc, char **argv) if (thpsize) ksft_print_msg("[INFO] detected THP size: %zu KiB\n", thpsize / 1024); - detect_hugetlbsizes(); + nr_hugetlbsizes = detect_hugetlb_page_sizes(hugetlbsizes, + ARRAY_SIZE(hugetlbsizes)); detect_huge_zeropage(); ksft_print_header(); diff --git a/tools/testing/selftests/mm/gup_longterm.c b/tools/testing/selftests/mm/gup_longterm.c new file mode 100644 index 000000000000..d33d3e68ffab --- /dev/null +++ b/tools/testing/selftests/mm/gup_longterm.c @@ -0,0 +1,459 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * GUP long-term page pinning tests. + * + * Copyright 2023, Red Hat, Inc. + * + * Author(s): David Hildenbrand <david@redhat.com> + */ +#define _GNU_SOURCE +#include <stdlib.h> +#include <string.h> +#include <stdbool.h> +#include <stdint.h> +#include <unistd.h> +#include <errno.h> +#include <fcntl.h> +#include <assert.h> +#include <sys/mman.h> +#include <sys/ioctl.h> +#include <sys/vfs.h> +#include <linux/magic.h> +#include <linux/memfd.h> + +#include "local_config.h" +#ifdef LOCAL_CONFIG_HAVE_LIBURING +#include <liburing.h> +#endif /* LOCAL_CONFIG_HAVE_LIBURING */ + +#include "../../../../mm/gup_test.h" +#include "../kselftest.h" +#include "vm_util.h" + +static size_t pagesize; +static int nr_hugetlbsizes; +static size_t hugetlbsizes[10]; +static int gup_fd; + +static __fsword_t get_fs_type(int fd) +{ + struct statfs fs; + int ret; + + do { + ret = fstatfs(fd, &fs); + } while (ret && errno == EINTR); + + return ret ? 0 : fs.f_type; +} + +static bool fs_is_unknown(__fsword_t fs_type) +{ + /* + * We only support some filesystems in our tests when dealing with + * R/W long-term pinning. For these filesystems, we can be fairly sure + * whether they support it or not. + */ + switch (fs_type) { + case TMPFS_MAGIC: + case HUGETLBFS_MAGIC: + case BTRFS_SUPER_MAGIC: + case EXT4_SUPER_MAGIC: + case XFS_SUPER_MAGIC: + return false; + default: + return true; + } +} + +static bool fs_supports_writable_longterm_pinning(__fsword_t fs_type) +{ + assert(!fs_is_unknown(fs_type)); + switch (fs_type) { + case TMPFS_MAGIC: + case HUGETLBFS_MAGIC: + return true; + default: + return false; + } +} + +enum test_type { + TEST_TYPE_RO, + TEST_TYPE_RO_FAST, + TEST_TYPE_RW, + TEST_TYPE_RW_FAST, +#ifdef LOCAL_CONFIG_HAVE_LIBURING + TEST_TYPE_IOURING, +#endif /* LOCAL_CONFIG_HAVE_LIBURING */ +}; + +static void do_test(int fd, size_t size, enum test_type type, bool shared) +{ + __fsword_t fs_type = get_fs_type(fd); + bool should_work; + char *mem; + int ret; + + if (ftruncate(fd, size)) { + ksft_test_result_fail("ftruncate() failed\n"); + return; + } + + if (fallocate(fd, 0, 0, size)) { + if (size == pagesize) + ksft_test_result_fail("fallocate() failed\n"); + else + ksft_test_result_skip("need more free huge pages\n"); + return; + } + + mem = mmap(NULL, size, PROT_READ | PROT_WRITE, + shared ? MAP_SHARED : MAP_PRIVATE, fd, 0); + if (mem == MAP_FAILED) { + if (size == pagesize || shared) + ksft_test_result_fail("mmap() failed\n"); + else + ksft_test_result_skip("need more free huge pages\n"); + return; + } + + /* + * Fault in the page writable such that GUP-fast can eventually pin + * it immediately. + */ + memset(mem, 0, size); + + switch (type) { + case TEST_TYPE_RO: + case TEST_TYPE_RO_FAST: + case TEST_TYPE_RW: + case TEST_TYPE_RW_FAST: { + struct pin_longterm_test args; + const bool fast = type == TEST_TYPE_RO_FAST || + type == TEST_TYPE_RW_FAST; + const bool rw = type == TEST_TYPE_RW || + type == TEST_TYPE_RW_FAST; + + if (gup_fd < 0) { + ksft_test_result_skip("gup_test not available\n"); + break; + } + + if (rw && shared && fs_is_unknown(fs_type)) { + ksft_test_result_skip("Unknown filesystem\n"); + return; + } + /* + * R/O pinning or pinning in a private mapping is always + * expected to work. Otherwise, we expect long-term R/W pinning + * to only succeed for special fielesystems. + */ + should_work = !shared || !rw || + fs_supports_writable_longterm_pinning(fs_type); + + args.addr = (__u64)(uintptr_t)mem; + args.size = size; + args.flags = fast ? PIN_LONGTERM_TEST_FLAG_USE_FAST : 0; + args.flags |= rw ? PIN_LONGTERM_TEST_FLAG_USE_WRITE : 0; + ret = ioctl(gup_fd, PIN_LONGTERM_TEST_START, &args); + if (ret && errno == EINVAL) { + ksft_test_result_skip("PIN_LONGTERM_TEST_START failed\n"); + break; + } else if (ret && errno == EFAULT) { + ksft_test_result(!should_work, "Should have failed\n"); + break; + } else if (ret) { + ksft_test_result_fail("PIN_LONGTERM_TEST_START failed\n"); + break; + } + + if (ioctl(gup_fd, PIN_LONGTERM_TEST_STOP)) + ksft_print_msg("[INFO] PIN_LONGTERM_TEST_STOP failed\n"); + + /* + * TODO: if the kernel ever supports long-term R/W pinning on + * some previously unsupported filesystems, we might want to + * perform some additional tests for possible data corruptions. + */ + ksft_test_result(should_work, "Should have worked\n"); + break; + } +#ifdef LOCAL_CONFIG_HAVE_LIBURING + case TEST_TYPE_IOURING: { + struct io_uring ring; + struct iovec iov; + + /* io_uring always pins pages writable. */ + if (shared && fs_is_unknown(fs_type)) { + ksft_test_result_skip("Unknown filesystem\n"); + return; + } + should_work = !shared || + fs_supports_writable_longterm_pinning(fs_type); + + /* Skip on errors, as we might just lack kernel support. */ + ret = io_uring_queue_init(1, &ring, 0); + if (ret < 0) { + ksft_test_result_skip("io_uring_queue_init() failed\n"); + break; + } + /* + * Register the range as a fixed buffer. This will FOLL_WRITE | + * FOLL_PIN | FOLL_LONGTERM the range. + */ + iov.iov_base = mem; + iov.iov_len = size; + ret = io_uring_register_buffers(&ring, &iov, 1); + /* Only new kernels return EFAULT. */ + if (ret && (errno == ENOSPC || errno == EOPNOTSUPP || + errno == EFAULT)) { + ksft_test_result(!should_work, "Should have failed\n"); + } else if (ret) { + /* + * We might just lack support or have insufficient + * MEMLOCK limits. + */ + ksft_test_result_skip("io_uring_register_buffers() failed\n"); + } else { + ksft_test_result(should_work, "Should have worked\n"); + io_uring_unregister_buffers(&ring); + } + + io_uring_queue_exit(&ring); + break; + } +#endif /* LOCAL_CONFIG_HAVE_LIBURING */ + default: + assert(false); + } + + munmap(mem, size); +} + +typedef void (*test_fn)(int fd, size_t size); + +static void run_with_memfd(test_fn fn, const char *desc) +{ + int fd; + + ksft_print_msg("[RUN] %s ... with memfd\n", desc); + + fd = memfd_create("test", 0); + if (fd < 0) { + ksft_test_result_fail("memfd_create() failed\n"); + return; + } + + fn(fd, pagesize); + close(fd); +} + +static void run_with_tmpfile(test_fn fn, const char *desc) +{ + FILE *file; + int fd; + + ksft_print_msg("[RUN] %s ... with tmpfile\n", desc); + + file = tmpfile(); + if (!file) { + ksft_test_result_fail("tmpfile() failed\n"); + return; + } + + fd = fileno(file); + if (fd < 0) { + ksft_test_result_fail("fileno() failed\n"); + return; + } + + fn(fd, pagesize); + fclose(file); +} + +static void run_with_local_tmpfile(test_fn fn, const char *desc) +{ + char filename[] = __FILE__"_tmpfile_XXXXXX"; + int fd; + + ksft_print_msg("[RUN] %s ... with local tmpfile\n", desc); + + fd = mkstemp(filename); + if (fd < 0) { + ksft_test_result_fail("mkstemp() failed\n"); + return; + } + + if (unlink(filename)) { + ksft_test_result_fail("unlink() failed\n"); + goto close; + } + + fn(fd, pagesize); +close: + close(fd); +} + +static void run_with_memfd_hugetlb(test_fn fn, const char *desc, + size_t hugetlbsize) +{ + int flags = MFD_HUGETLB; + int fd; + + ksft_print_msg("[RUN] %s ... with memfd hugetlb (%zu kB)\n", desc, + hugetlbsize / 1024); + + flags |= __builtin_ctzll(hugetlbsize) << MFD_HUGE_SHIFT; + + fd = memfd_create("test", flags); + if (fd < 0) { + ksft_test_result_skip("memfd_create() failed\n"); + return; + } + + fn(fd, hugetlbsize); + close(fd); +} + +struct test_case { + const char *desc; + test_fn fn; +}; + +static void test_shared_rw_pin(int fd, size_t size) +{ + do_test(fd, size, TEST_TYPE_RW, true); +} + +static void test_shared_rw_fast_pin(int fd, size_t size) +{ + do_test(fd, size, TEST_TYPE_RW_FAST, true); +} + +static void test_shared_ro_pin(int fd, size_t size) +{ + do_test(fd, size, TEST_TYPE_RO, true); +} + +static void test_shared_ro_fast_pin(int fd, size_t size) +{ + do_test(fd, size, TEST_TYPE_RO_FAST, true); +} + +static void test_private_rw_pin(int fd, size_t size) +{ + do_test(fd, size, TEST_TYPE_RW, false); +} + +static void test_private_rw_fast_pin(int fd, size_t size) +{ + do_test(fd, size, TEST_TYPE_RW_FAST, false); +} + +static void test_private_ro_pin(int fd, size_t size) +{ + do_test(fd, size, TEST_TYPE_RO, false); +} + +static void test_private_ro_fast_pin(int fd, size_t size) +{ + do_test(fd, size, TEST_TYPE_RO_FAST, false); +} + +#ifdef LOCAL_CONFIG_HAVE_LIBURING +static void test_shared_iouring(int fd, size_t size) +{ + do_test(fd, size, TEST_TYPE_IOURING, true); +} + +static void test_private_iouring(int fd, size_t size) +{ + do_test(fd, size, TEST_TYPE_IOURING, false); +} +#endif /* LOCAL_CONFIG_HAVE_LIBURING */ + +static const struct test_case test_cases[] = { + { + "R/W longterm GUP pin in MAP_SHARED file mapping", + test_shared_rw_pin, + }, + { + "R/W longterm GUP-fast pin in MAP_SHARED file mapping", + test_shared_rw_fast_pin, + }, + { + "R/O longterm GUP pin in MAP_SHARED file mapping", + test_shared_ro_pin, + }, + { + "R/O longterm GUP-fast pin in MAP_SHARED file mapping", + test_shared_ro_fast_pin, + }, + { + "R/W longterm GUP pin in MAP_PRIVATE file mapping", + test_private_rw_pin, + }, + { + "R/W longterm GUP-fast pin in MAP_PRIVATE file mapping", + test_private_rw_fast_pin, + }, + { + "R/O longterm GUP pin in MAP_PRIVATE file mapping", + test_private_ro_pin, + }, + { + "R/O longterm GUP-fast pin in MAP_PRIVATE file mapping", + test_private_ro_fast_pin, + }, +#ifdef LOCAL_CONFIG_HAVE_LIBURING + { + "io_uring fixed buffer with MAP_SHARED file mapping", + test_shared_iouring, + }, + { + "io_uring fixed buffer with MAP_PRIVATE file mapping", + test_private_iouring, + }, +#endif /* LOCAL_CONFIG_HAVE_LIBURING */ +}; + +static void run_test_case(struct test_case const *test_case) +{ + int i; + + run_with_memfd(test_case->fn, test_case->desc); + run_with_tmpfile(test_case->fn, test_case->desc); + run_with_local_tmpfile(test_case->fn, test_case->desc); + for (i = 0; i < nr_hugetlbsizes; i++) + run_with_memfd_hugetlb(test_case->fn, test_case->desc, + hugetlbsizes[i]); +} + +static int tests_per_test_case(void) +{ + return 3 + nr_hugetlbsizes; +} + +int main(int argc, char **argv) +{ + int i, err; + + pagesize = getpagesize(); + nr_hugetlbsizes = detect_hugetlb_page_sizes(hugetlbsizes, + ARRAY_SIZE(hugetlbsizes)); + + ksft_print_header(); + ksft_set_plan(ARRAY_SIZE(test_cases) * tests_per_test_case()); + + gup_fd = open("/sys/kernel/debug/gup_test", O_RDWR); + + for (i = 0; i < ARRAY_SIZE(test_cases); i++) + run_test_case(&test_cases[i]); + + err = ksft_get_fail_cnt(); + if (err) + ksft_exit_fail_msg("%d out of %d tests failed\n", + err, ksft_test_num()); + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/mm/hugepage-shm.c b/tools/testing/selftests/mm/hugepage-shm.c index e2527f32005b..478bb1e989e9 100644 --- a/tools/testing/selftests/mm/hugepage-shm.c +++ b/tools/testing/selftests/mm/hugepage-shm.c @@ -35,10 +35,6 @@ #include <sys/shm.h> #include <sys/mman.h> -#ifndef SHM_HUGETLB -#define SHM_HUGETLB 04000 -#endif - #define LENGTH (256UL*1024*1024) #define dprintf(x) printf(x) diff --git a/tools/testing/selftests/mm/hugepage-vmemmap.c b/tools/testing/selftests/mm/hugepage-vmemmap.c index 557bdbd4f87e..5b354c209e93 100644 --- a/tools/testing/selftests/mm/hugepage-vmemmap.c +++ b/tools/testing/selftests/mm/hugepage-vmemmap.c @@ -13,10 +13,6 @@ #define MAP_LENGTH (2UL * 1024 * 1024) -#ifndef MAP_HUGETLB -#define MAP_HUGETLB 0x40000 /* arch specific */ -#endif - #define PAGE_SIZE 4096 #define PAGE_COMPOUND_HEAD (1UL << 15) diff --git a/tools/testing/selftests/mm/hugetlb-madvise.c b/tools/testing/selftests/mm/hugetlb-madvise.c index 28426e30d9bc..d55322df4b73 100644 --- a/tools/testing/selftests/mm/hugetlb-madvise.c +++ b/tools/testing/selftests/mm/hugetlb-madvise.c @@ -65,11 +65,15 @@ void write_fault_pages(void *addr, unsigned long nr_pages) void read_fault_pages(void *addr, unsigned long nr_pages) { - unsigned long dummy = 0; + volatile unsigned long dummy = 0; unsigned long i; - for (i = 0; i < nr_pages; i++) + for (i = 0; i < nr_pages; i++) { dummy += *((unsigned long *)(addr + (i * huge_page_size))); + + /* Prevent the compiler from optimizing out the entire loop: */ + asm volatile("" : "+r" (dummy)); + } } int main(int argc, char **argv) diff --git a/tools/testing/selftests/mm/khugepaged.c b/tools/testing/selftests/mm/khugepaged.c index 97adc0f34f9c..030667cb5533 100644 --- a/tools/testing/selftests/mm/khugepaged.c +++ b/tools/testing/selftests/mm/khugepaged.c @@ -11,6 +11,7 @@ #include <string.h> #include <unistd.h> +#include <linux/mman.h> #include <sys/mman.h> #include <sys/wait.h> #include <sys/types.h> @@ -22,16 +23,6 @@ #include "vm_util.h" -#ifndef MADV_PAGEOUT -#define MADV_PAGEOUT 21 -#endif -#ifndef MADV_POPULATE_READ -#define MADV_POPULATE_READ 22 -#endif -#ifndef MADV_COLLAPSE -#define MADV_COLLAPSE 25 -#endif - #define BASE_ADDR ((void *)(1UL << 30)) static unsigned long hpage_pmd_size; static unsigned long page_size; diff --git a/tools/testing/selftests/mm/madv_populate.c b/tools/testing/selftests/mm/madv_populate.c index 262eae6b58f2..60547245e479 100644 --- a/tools/testing/selftests/mm/madv_populate.c +++ b/tools/testing/selftests/mm/madv_populate.c @@ -20,13 +20,6 @@ #include "../kselftest.h" #include "vm_util.h" -#ifndef MADV_POPULATE_READ -#define MADV_POPULATE_READ 22 -#endif /* MADV_POPULATE_READ */ -#ifndef MADV_POPULATE_WRITE -#define MADV_POPULATE_WRITE 23 -#endif /* MADV_POPULATE_WRITE */ - /* * For now, we're using 2 MiB of private anonymous memory for all tests. */ diff --git a/tools/testing/selftests/mm/map_fixed_noreplace.c b/tools/testing/selftests/mm/map_fixed_noreplace.c index eed44322d1a6..598159f3df1f 100644 --- a/tools/testing/selftests/mm/map_fixed_noreplace.c +++ b/tools/testing/selftests/mm/map_fixed_noreplace.c @@ -13,10 +13,6 @@ #include <stdlib.h> #include <unistd.h> -#ifndef MAP_FIXED_NOREPLACE -#define MAP_FIXED_NOREPLACE 0x100000 -#endif - static void dump_maps(void) { char cmd[32]; diff --git a/tools/testing/selftests/mm/map_hugetlb.c b/tools/testing/selftests/mm/map_hugetlb.c index 312889edb84a..193281560b61 100644 --- a/tools/testing/selftests/mm/map_hugetlb.c +++ b/tools/testing/selftests/mm/map_hugetlb.c @@ -19,18 +19,6 @@ #define LENGTH (256UL*1024*1024) #define PROTECTION (PROT_READ | PROT_WRITE) -#ifndef MAP_HUGETLB -#define MAP_HUGETLB 0x40000 /* arch specific */ -#endif - -#ifndef MAP_HUGE_SHIFT -#define MAP_HUGE_SHIFT 26 -#endif - -#ifndef MAP_HUGE_MASK -#define MAP_HUGE_MASK 0x3f -#endif - /* Only ia64 requires this */ #ifdef __ia64__ #define ADDR (void *)(0x8000000000000000UL) diff --git a/tools/testing/selftests/mm/map_populate.c b/tools/testing/selftests/mm/map_populate.c index 6b8aeaa0bf7a..240f2d9dae7a 100644 --- a/tools/testing/selftests/mm/map_populate.c +++ b/tools/testing/selftests/mm/map_populate.c @@ -17,9 +17,7 @@ #include <string.h> #include <unistd.h> -#ifndef MMAP_SZ #define MMAP_SZ 4096 -#endif #define BUG_ON(condition, description) \ do { \ diff --git a/tools/testing/selftests/mm/migration.c b/tools/testing/selftests/mm/migration.c index 1cec8425e3ca..379581567f27 100644 --- a/tools/testing/selftests/mm/migration.c +++ b/tools/testing/selftests/mm/migration.c @@ -95,12 +95,15 @@ int migrate(uint64_t *ptr, int n1, int n2) void *access_mem(void *ptr) { - uint64_t y = 0; + volatile uint64_t y = 0; volatile uint64_t *x = ptr; while (1) { pthread_testcancel(); y += *x; + + /* Prevent the compiler from optimizing out the writes to y: */ + asm volatile("" : "+r" (y)); } return NULL; diff --git a/tools/testing/selftests/mm/mlock-random-test.c b/tools/testing/selftests/mm/mlock-random-test.c index 782ea94dee2f..1fba77df7f62 100644 --- a/tools/testing/selftests/mm/mlock-random-test.c +++ b/tools/testing/selftests/mm/mlock-random-test.c @@ -7,6 +7,7 @@ #include <sys/resource.h> #include <sys/capability.h> #include <sys/mman.h> +#include <linux/mman.h> #include <fcntl.h> #include <string.h> #include <sys/ipc.h> diff --git a/tools/testing/selftests/mm/mlock2-tests.c b/tools/testing/selftests/mm/mlock2-tests.c index 11b2301f3aa3..80cddc0de206 100644 --- a/tools/testing/selftests/mm/mlock2-tests.c +++ b/tools/testing/selftests/mm/mlock2-tests.c @@ -50,7 +50,6 @@ static int get_vm_area(unsigned long addr, struct vm_boundaries *area) printf("cannot parse /proc/self/maps\n"); goto out; } - stop = '\0'; sscanf(line, "%lx", &start); sscanf(end_addr, "%lx", &end); diff --git a/tools/testing/selftests/mm/mlock2.h b/tools/testing/selftests/mm/mlock2.h index 2a6e76c226bc..8e02991b313c 100644 --- a/tools/testing/selftests/mm/mlock2.h +++ b/tools/testing/selftests/mm/mlock2.h @@ -4,14 +4,6 @@ #include <stdio.h> #include <stdlib.h> -#ifndef MLOCK_ONFAULT -#define MLOCK_ONFAULT 1 -#endif - -#ifndef MCL_ONFAULT -#define MCL_ONFAULT (MCL_FUTURE << 1) -#endif - static int mlock2_(void *start, size_t len, int flags) { #ifdef __NR_mlock2 diff --git a/tools/testing/selftests/mm/mrelease_test.c b/tools/testing/selftests/mm/mrelease_test.c index 37b6d33b9e84..dca21042b679 100644 --- a/tools/testing/selftests/mm/mrelease_test.c +++ b/tools/testing/selftests/mm/mrelease_test.c @@ -9,18 +9,10 @@ #include <stdlib.h> #include <sys/wait.h> #include <unistd.h> +#include <asm-generic/unistd.h> #include "vm_util.h" - #include "../kselftest.h" -#ifndef __NR_pidfd_open -#define __NR_pidfd_open -1 -#endif - -#ifndef __NR_process_mrelease -#define __NR_process_mrelease -1 -#endif - #define MB(x) (x << 20) #define MAX_SIZE_MB 1024 diff --git a/tools/testing/selftests/mm/mremap_dontunmap.c b/tools/testing/selftests/mm/mremap_dontunmap.c index f01dc4a85b0b..ca2359835e75 100644 --- a/tools/testing/selftests/mm/mremap_dontunmap.c +++ b/tools/testing/selftests/mm/mremap_dontunmap.c @@ -15,10 +15,6 @@ #include "../kselftest.h" -#ifndef MREMAP_DONTUNMAP -#define MREMAP_DONTUNMAP 4 -#endif - unsigned long page_size; char *page_buffer; diff --git a/tools/testing/selftests/mm/on-fault-limit.c b/tools/testing/selftests/mm/on-fault-limit.c index 634d87dfb2a4..b5888d613f34 100644 --- a/tools/testing/selftests/mm/on-fault-limit.c +++ b/tools/testing/selftests/mm/on-fault-limit.c @@ -6,10 +6,6 @@ #include <sys/time.h> #include <sys/resource.h> -#ifndef MCL_ONFAULT -#define MCL_ONFAULT (MCL_FUTURE << 1) -#endif - static int test_limit(void) { int ret = 1; diff --git a/tools/testing/selftests/mm/pkey-powerpc.h b/tools/testing/selftests/mm/pkey-powerpc.h index 1ebb586b2fbc..ae5df26104e5 100644 --- a/tools/testing/selftests/mm/pkey-powerpc.h +++ b/tools/testing/selftests/mm/pkey-powerpc.h @@ -3,9 +3,6 @@ #ifndef _PKEYS_POWERPC_H #define _PKEYS_POWERPC_H -#ifndef SYS_mprotect_key -# define SYS_mprotect_key 386 -#endif #ifndef SYS_pkey_alloc # define SYS_pkey_alloc 384 # define SYS_pkey_free 385 diff --git a/tools/testing/selftests/mm/pkey-x86.h b/tools/testing/selftests/mm/pkey-x86.h index 72c14cd3ddc7..814758e109c0 100644 --- a/tools/testing/selftests/mm/pkey-x86.h +++ b/tools/testing/selftests/mm/pkey-x86.h @@ -5,29 +5,11 @@ #ifdef __i386__ -#ifndef SYS_mprotect_key -# define SYS_mprotect_key 380 -#endif - -#ifndef SYS_pkey_alloc -# define SYS_pkey_alloc 381 -# define SYS_pkey_free 382 -#endif - #define REG_IP_IDX REG_EIP #define si_pkey_offset 0x14 #else -#ifndef SYS_mprotect_key -# define SYS_mprotect_key 329 -#endif - -#ifndef SYS_pkey_alloc -# define SYS_pkey_alloc 330 -# define SYS_pkey_free 331 -#endif - #define REG_IP_IDX REG_RIP #define si_pkey_offset 0x20 @@ -132,7 +114,7 @@ int pkey_reg_xstate_offset(void) unsigned int ecx; unsigned int edx; int xstate_offset; - int xstate_size; + int xstate_size = 0; unsigned long XSTATE_CPUID = 0xd; int leaf; diff --git a/tools/testing/selftests/mm/protection_keys.c b/tools/testing/selftests/mm/protection_keys.c index 0381c34fdd56..48dc151f8fca 100644 --- a/tools/testing/selftests/mm/protection_keys.c +++ b/tools/testing/selftests/mm/protection_keys.c @@ -294,15 +294,6 @@ void pkey_access_deny(int pkey) pkey_disable_set(pkey, PKEY_DISABLE_ACCESS); } -/* Failed address bound checks: */ -#ifndef SEGV_BNDERR -# define SEGV_BNDERR 3 -#endif - -#ifndef SEGV_PKUERR -# define SEGV_PKUERR 4 -#endif - static char *si_code_str(int si_code) { if (si_code == SEGV_MAPERR) @@ -476,7 +467,7 @@ int sys_mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot, ptr, size, orig_prot, pkey); errno = 0; - sret = syscall(SYS_mprotect_key, ptr, size, orig_prot, pkey); + sret = syscall(__NR_pkey_mprotect, ptr, size, orig_prot, pkey); if (errno) { dprintf2("SYS_mprotect_key sret: %d\n", sret); dprintf2("SYS_mprotect_key prot: 0x%lx\n", orig_prot); @@ -1684,7 +1675,7 @@ void test_mprotect_pkey_on_unsupported_cpu(int *ptr, u16 pkey) return; } - sret = syscall(SYS_mprotect_key, ptr, size, PROT_READ, pkey); + sret = syscall(__NR_pkey_mprotect, ptr, size, PROT_READ, pkey); pkey_assert(sret < 0); } diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index 4893eb60d96d..3f26f6e15b2a 100644 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -24,7 +24,7 @@ separated by spaces: - mmap tests for mmap(2) - gup_test - tests for gup using gup_test interface + tests for gup - userfaultfd tests for userfaultfd(2) - compaction @@ -196,6 +196,8 @@ CATEGORY="gup_test" run_test ./gup_test -a # Dump pages 0, 19, and 4096, using pin_user_pages: CATEGORY="gup_test" run_test ./gup_test -ct -F 0x1 0 19 0x1000 +CATEGORY="gup_test" run_test ./gup_longterm + CATEGORY="userfaultfd" run_test ./uffd-unit-tests uffd_stress_bin=./uffd-stress CATEGORY="userfaultfd" run_test ${uffd_stress_bin} anon 20 16 @@ -242,18 +244,18 @@ if [ $VADDR64 -ne 0 ]; then if [ "$ARCH" == "$ARCH_ARM64" ]; then echo 6 > /proc/sys/vm/nr_hugepages fi - CATEGORY="hugevm" run_test ./va_high_addr_switch.sh + CATEGORY="hugevm" run_test bash ./va_high_addr_switch.sh if [ "$ARCH" == "$ARCH_ARM64" ]; then echo $prev_nr_hugepages > /proc/sys/vm/nr_hugepages fi fi # VADDR64 # vmalloc stability smoke test -CATEGORY="vmalloc" run_test ./test_vmalloc.sh smoke +CATEGORY="vmalloc" run_test bash ./test_vmalloc.sh smoke CATEGORY="mremap" run_test ./mremap_dontunmap -CATEGORY="hmm" run_test ./test_hmm.sh smoke +CATEGORY="hmm" run_test bash ./test_hmm.sh smoke # MADV_POPULATE_READ and MADV_POPULATE_WRITE tests CATEGORY="madv_populate" run_test ./madv_populate diff --git a/tools/testing/selftests/mm/uffd-common.c b/tools/testing/selftests/mm/uffd-common.c index 61c6250adf93..ba20d7504022 100644 --- a/tools/testing/selftests/mm/uffd-common.c +++ b/tools/testing/selftests/mm/uffd-common.c @@ -616,3 +616,62 @@ int copy_page(int ufd, unsigned long offset, bool wp) { return __copy_page(ufd, offset, false, wp); } + +int uffd_open_dev(unsigned int flags) +{ + int fd, uffd; + + fd = open("/dev/userfaultfd", O_RDWR | O_CLOEXEC); + if (fd < 0) + return fd; + uffd = ioctl(fd, USERFAULTFD_IOC_NEW, flags); + close(fd); + + return uffd; +} + +int uffd_open_sys(unsigned int flags) +{ +#ifdef __NR_userfaultfd + return syscall(__NR_userfaultfd, flags); +#else + return -1; +#endif +} + +int uffd_open(unsigned int flags) +{ + int uffd = uffd_open_sys(flags); + + if (uffd < 0) + uffd = uffd_open_dev(flags); + + return uffd; +} + +int uffd_get_features(uint64_t *features) +{ + struct uffdio_api uffdio_api = { .api = UFFD_API, .features = 0 }; + /* + * This should by default work in most kernels; the feature list + * will be the same no matter what we pass in here. + */ + int fd = uffd_open(UFFD_USER_MODE_ONLY); + + if (fd < 0) + /* Maybe the kernel is older than user-only mode? */ + fd = uffd_open(0); + + if (fd < 0) + return fd; + + if (ioctl(fd, UFFDIO_API, &uffdio_api)) { + close(fd); + return -errno; + } + + *features = uffdio_api.features; + close(fd); + + return 0; +} diff --git a/tools/testing/selftests/mm/uffd-common.h b/tools/testing/selftests/mm/uffd-common.h index 6068f2346b86..197f5262fe0d 100644 --- a/tools/testing/selftests/mm/uffd-common.h +++ b/tools/testing/selftests/mm/uffd-common.h @@ -110,6 +110,11 @@ int __copy_page(int ufd, unsigned long offset, bool retry, bool wp); int copy_page(int ufd, unsigned long offset, bool wp); void *uffd_poll_thread(void *arg); +int uffd_open_dev(unsigned int flags); +int uffd_open_sys(unsigned int flags); +int uffd_open(unsigned int flags); +int uffd_get_features(uint64_t *features); + #define TEST_ANON 1 #define TEST_HUGETLB 2 #define TEST_SHMEM 3 diff --git a/tools/testing/selftests/mm/uffd-stress.c b/tools/testing/selftests/mm/uffd-stress.c index f1ad9eef1c3a..995ff13e74c7 100644 --- a/tools/testing/selftests/mm/uffd-stress.c +++ b/tools/testing/selftests/mm/uffd-stress.c @@ -88,16 +88,6 @@ static void uffd_stats_reset(struct uffd_args *args, unsigned long n_cpus) } } -static inline uint64_t uffd_minor_feature(void) -{ - if (test_type == TEST_HUGETLB && map_shared) - return UFFD_FEATURE_MINOR_HUGETLBFS; - else if (test_type == TEST_SHMEM) - return UFFD_FEATURE_MINOR_SHMEM; - else - return 0; -} - static void *locking_thread(void *arg) { unsigned long cpu = (unsigned long) arg; diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c index 269c86768a02..04d91f144d1c 100644 --- a/tools/testing/selftests/mm/uffd-unit-tests.c +++ b/tools/testing/selftests/mm/uffd-unit-tests.c @@ -109,12 +109,11 @@ static void uffd_test_pass(void) ksft_inc_fail_cnt(); \ } while (0) -#define uffd_test_skip(...) do { \ - printf("skipped [reason: "); \ - printf(__VA_ARGS__); \ - printf("]\n"); \ - ksft_inc_xskip_cnt(); \ - } while (0) +static void uffd_test_skip(const char *message) +{ + printf("skipped [reason: %s]\n", message); + ksft_inc_xskip_cnt(); +} /* * Returns 1 if specific userfaultfd supported, 0 otherwise. Note, we'll @@ -1149,7 +1148,6 @@ int main(int argc, char *argv[]) uffd_test_case_t *test; mem_type_t *mem_type; uffd_test_args_t args; - char test_name[128]; const char *errmsg; int has_uffd, opt; int i, j; @@ -1192,10 +1190,8 @@ int main(int argc, char *argv[]) mem_type = &mem_types[j]; if (!(test->mem_targets & mem_type->mem_flag)) continue; - snprintf(test_name, sizeof(test_name), - "%s on %s", test->name, mem_type->name); - uffd_test_start(test_name); + uffd_test_start("%s on %s", test->name, mem_type->name); if (!uffd_feature_supported(test)) { uffd_test_skip("feature missing"); continue; diff --git a/tools/testing/selftests/mm/vm_util.c b/tools/testing/selftests/mm/vm_util.c index 9b06a5034808..558c9cd8901c 100644 --- a/tools/testing/selftests/mm/vm_util.c +++ b/tools/testing/selftests/mm/vm_util.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <string.h> #include <fcntl.h> +#include <dirent.h> #include <sys/ioctl.h> #include <linux/userfaultfd.h> #include <sys/syscall.h> @@ -198,6 +199,32 @@ unsigned long default_huge_page_size(void) return hps; } +int detect_hugetlb_page_sizes(size_t sizes[], int max) +{ + DIR *dir = opendir("/sys/kernel/mm/hugepages/"); + int count = 0; + + if (!dir) + return 0; + + while (count < max) { + struct dirent *entry = readdir(dir); + size_t kb; + + if (!entry) + break; + if (entry->d_type != DT_DIR) + continue; + if (sscanf(entry->d_name, "hugepages-%zukB", &kb) != 1) + continue; + sizes[count++] = kb * 1024; + ksft_print_msg("[INFO] detected hugetlb page size: %zu KiB\n", + kb); + } + closedir(dir); + return count; +} + /* If `ioctls' non-NULL, the allowed ioctls will be returned into the var */ int uffd_register_with_ioctls(int uffd, void *addr, uint64_t len, bool miss, bool wp, bool minor, uint64_t *ioctls) @@ -242,62 +269,3 @@ int uffd_unregister(int uffd, void *addr, uint64_t len) return ret; } - -int uffd_open_dev(unsigned int flags) -{ - int fd, uffd; - - fd = open("/dev/userfaultfd", O_RDWR | O_CLOEXEC); - if (fd < 0) - return fd; - uffd = ioctl(fd, USERFAULTFD_IOC_NEW, flags); - close(fd); - - return uffd; -} - -int uffd_open_sys(unsigned int flags) -{ -#ifdef __NR_userfaultfd - return syscall(__NR_userfaultfd, flags); -#else - return -1; -#endif -} - -int uffd_open(unsigned int flags) -{ - int uffd = uffd_open_sys(flags); - - if (uffd < 0) - uffd = uffd_open_dev(flags); - - return uffd; -} - -int uffd_get_features(uint64_t *features) -{ - struct uffdio_api uffdio_api = { .api = UFFD_API, .features = 0 }; - /* - * This should by default work in most kernels; the feature list - * will be the same no matter what we pass in here. - */ - int fd = uffd_open(UFFD_USER_MODE_ONLY); - - if (fd < 0) - /* Maybe the kernel is older than user-only mode? */ - fd = uffd_open(0); - - if (fd < 0) - return fd; - - if (ioctl(fd, UFFDIO_API, &uffdio_api)) { - close(fd); - return -errno; - } - - *features = uffdio_api.features; - close(fd); - - return 0; -} diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h index b950bd16083a..c7fa61f0dff8 100644 --- a/tools/testing/selftests/mm/vm_util.h +++ b/tools/testing/selftests/mm/vm_util.h @@ -44,14 +44,11 @@ bool check_huge_file(void *addr, int nr_hpages, uint64_t hpage_size); bool check_huge_shmem(void *addr, int nr_hpages, uint64_t hpage_size); int64_t allocate_transhuge(void *ptr, int pagemap_fd); unsigned long default_huge_page_size(void); +int detect_hugetlb_page_sizes(size_t sizes[], int max); int uffd_register(int uffd, void *addr, uint64_t len, bool miss, bool wp, bool minor); int uffd_unregister(int uffd, void *addr, uint64_t len); -int uffd_open_dev(unsigned int flags); -int uffd_open_sys(unsigned int flags); -int uffd_open(unsigned int flags); -int uffd_get_features(uint64_t *features); int uffd_register_with_ioctls(int uffd, void *addr, uint64_t len, bool miss, bool wp, bool minor, uint64_t *ioctls); diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 80f06aa62034..f27a7338b60e 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -8,8 +8,10 @@ diag_uid fin_ack_lat gro hwtstamp_config +io_uring_zerocopy_tx ioam6_parser ip_defrag +ip_local_port_range ipsec ipv6_flowlabel ipv6_flowlabel_mgr @@ -26,6 +28,7 @@ reuseport_bpf_cpu reuseport_bpf_numa reuseport_dualstack rxtimestamp +sctp_hello sk_bind_sendto_listen sk_connect_zero_addr socket diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index 21ca91473c09..ee6880ac3e5e 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -92,6 +92,13 @@ NSC_CMD="ip netns exec ${NSC}" which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping) +# Check if FIPS mode is enabled +if [ -f /proc/sys/crypto/fips_enabled ]; then + fips_enabled=`cat /proc/sys/crypto/fips_enabled` +else + fips_enabled=0 +fi + ################################################################################ # utilities @@ -1216,7 +1223,7 @@ ipv4_tcp_novrf() run_cmd nettest -d ${NSA_DEV} -r ${a} log_test_addr ${a} $? 1 "No server, device client, local conn" - ipv4_tcp_md5_novrf + [ "$fips_enabled" = "1" ] || ipv4_tcp_md5_novrf } ipv4_tcp_vrf() @@ -1270,9 +1277,11 @@ ipv4_tcp_vrf() log_test_addr ${a} $? 1 "Global server, local connection" # run MD5 tests - setup_vrf_dup - ipv4_tcp_md5 - cleanup_vrf_dup + if [ "$fips_enabled" = "0" ]; then + setup_vrf_dup + ipv4_tcp_md5 + cleanup_vrf_dup + fi # # enable VRF global server @@ -2772,7 +2781,7 @@ ipv6_tcp_novrf() log_test_addr ${a} $? 1 "No server, device client, local conn" done - ipv6_tcp_md5_novrf + [ "$fips_enabled" = "1" ] || ipv6_tcp_md5_novrf } ipv6_tcp_vrf() @@ -2842,9 +2851,11 @@ ipv6_tcp_vrf() log_test_addr ${a} $? 1 "Global server, local connection" # run MD5 tests - setup_vrf_dup - ipv6_tcp_md5 - cleanup_vrf_dup + if [ "$fips_enabled" = "0" ]; then + setup_vrf_dup + ipv6_tcp_md5 + cleanup_vrf_dup + fi # # enable VRF global server diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index a47b26ab48f2..0f5e88c8f4ff 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -2283,7 +2283,7 @@ EOF ################################################################################ # main -while getopts :t:pP46hv:w: o +while getopts :t:pP46hvw: o do case $o in t) TESTS=$OPTARG;; diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 7da8ec838c63..35d89dfa6f11 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -68,7 +68,7 @@ setup() cleanup() { $IP link del dev dummy0 &> /dev/null - ip netns del ns1 + ip netns del ns1 &> /dev/null ip netns del ns2 &> /dev/null } diff --git a/tools/testing/selftests/net/forwarding/hw_stats_l3.sh b/tools/testing/selftests/net/forwarding/hw_stats_l3.sh index 432fe8469851..48584a51388f 100755 --- a/tools/testing/selftests/net/forwarding/hw_stats_l3.sh +++ b/tools/testing/selftests/net/forwarding/hw_stats_l3.sh @@ -84,8 +84,9 @@ h2_destroy() router_rp1_200_create() { - ip link add name $rp1.200 up \ - link $rp1 addrgenmode eui64 type vlan id 200 + ip link add name $rp1.200 link $rp1 type vlan id 200 + ip link set dev $rp1.200 addrgenmode eui64 + ip link set dev $rp1.200 up ip address add dev $rp1.200 192.0.2.2/28 ip address add dev $rp1.200 2001:db8:1::2/64 ip stats set dev $rp1.200 l3_stats on @@ -256,9 +257,11 @@ reapply_config() router_rp1_200_destroy - ip link add name $rp1.200 link $rp1 addrgenmode none type vlan id 200 + ip link add name $rp1.200 link $rp1 type vlan id 200 + ip link set dev $rp1.200 addrgenmode none ip stats set dev $rp1.200 l3_stats on - ip link set dev $rp1.200 up addrgenmode eui64 + ip link set dev $rp1.200 addrgenmode eui64 + ip link set dev $rp1.200 up ip address add dev $rp1.200 192.0.2.2/28 ip address add dev $rp1.200 2001:db8:1::2/64 } diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d.sh index c5095da7f6bf..aec752a22e9e 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d.sh @@ -93,12 +93,16 @@ cleanup() test_gretap() { + ip neigh replace 192.0.2.130 lladdr $(mac_get $h3) \ + nud permanent dev br2 full_test_span_gre_dir gt4 ingress 8 0 "mirror to gretap" full_test_span_gre_dir gt4 egress 0 8 "mirror to gretap" } test_ip6gretap() { + ip neigh replace 2001:db8:2::2 lladdr $(mac_get $h3) \ + nud permanent dev br2 full_test_span_gre_dir gt6 ingress 8 0 "mirror to ip6gretap" full_test_span_gre_dir gt6 egress 0 8 "mirror to ip6gretap" } diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q.sh index 9ff22f28032d..0cf4c47a46f9 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q.sh @@ -90,12 +90,16 @@ cleanup() test_gretap() { + ip neigh replace 192.0.2.130 lladdr $(mac_get $h3) \ + nud permanent dev br1 full_test_span_gre_dir gt4 ingress 8 0 "mirror to gretap" full_test_span_gre_dir gt4 egress 0 8 "mirror to gretap" } test_ip6gretap() { + ip neigh replace 2001:db8:2::2 lladdr $(mac_get $h3) \ + nud permanent dev br1 full_test_span_gre_dir gt6 ingress 8 0 "mirror to ip6gretap" full_test_span_gre_dir gt6 egress 0 8 "mirror to ip6gretap" } diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile index 43a723626126..7b936a926859 100644 --- a/tools/testing/selftests/net/mptcp/Makefile +++ b/tools/testing/selftests/net/mptcp/Makefile @@ -9,7 +9,7 @@ TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh \ TEST_GEN_FILES = mptcp_connect pm_nl_ctl mptcp_sockopt mptcp_inq -TEST_FILES := settings +TEST_FILES := mptcp_lib.sh settings EXTRA_CLEAN := *.pcap diff --git a/tools/testing/selftests/net/mptcp/config b/tools/testing/selftests/net/mptcp/config index 38021a0dd527..6032f9b23c4c 100644 --- a/tools/testing/selftests/net/mptcp/config +++ b/tools/testing/selftests/net/mptcp/config @@ -1,3 +1,4 @@ +CONFIG_KALLSYMS=y CONFIG_MPTCP=y CONFIG_IPV6=y CONFIG_MPTCP_IPV6=y diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh index ef628b16fe9b..fa9e09ad97d9 100755 --- a/tools/testing/selftests/net/mptcp/diag.sh +++ b/tools/testing/selftests/net/mptcp/diag.sh @@ -1,6 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/mptcp_lib.sh" + sec=$(date +%s) rndh=$(printf %x $sec)-$(mktemp -u XXXXXX) ns="ns1-$rndh" @@ -31,6 +33,8 @@ cleanup() ip netns del $ns } +mptcp_lib_check_mptcp + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Could not run test without ip tool" @@ -51,16 +55,20 @@ __chk_nr() { local command="$1" local expected=$2 - local msg nr + local msg="$3" + local skip="${4:-SKIP}" + local nr - shift 2 - msg=$* nr=$(eval $command) printf "%-50s" "$msg" if [ $nr != $expected ]; then - echo "[ fail ] expected $expected found $nr" - ret=$test_cnt + if [ $nr = "$skip" ] && ! mptcp_lib_expect_all_features; then + echo "[ skip ] Feature probably not supported" + else + echo "[ fail ] expected $expected found $nr" + ret=$test_cnt + fi else echo "[ ok ]" fi @@ -72,12 +80,12 @@ __chk_msk_nr() local condition=$1 shift 1 - __chk_nr "ss -inmHMN $ns | $condition" $* + __chk_nr "ss -inmHMN $ns | $condition" "$@" } chk_msk_nr() { - __chk_msk_nr "grep -c token:" $* + __chk_msk_nr "grep -c token:" "$@" } wait_msk_nr() @@ -115,37 +123,26 @@ wait_msk_nr() chk_msk_fallback_nr() { - __chk_msk_nr "grep -c fallback" $* + __chk_msk_nr "grep -c fallback" "$@" } chk_msk_remote_key_nr() { - __chk_msk_nr "grep -c remote_key" $* + __chk_msk_nr "grep -c remote_key" "$@" } __chk_listen() { local filter="$1" local expected=$2 + local msg="$3" - shift 2 - msg=$* - - nr=$(ss -N $ns -Ml "$filter" | grep -c LISTEN) - printf "%-50s" "$msg" - - if [ $nr != $expected ]; then - echo "[ fail ] expected $expected found $nr" - ret=$test_cnt - else - echo "[ ok ]" - fi + __chk_nr "ss -N $ns -Ml '$filter' | grep -c LISTEN" "$expected" "$msg" 0 } chk_msk_listen() { lport=$1 - local msg="check for listen socket" # destination port search should always return empty list __chk_listen "dport $lport" 0 "listen match for dport $lport" @@ -163,10 +160,9 @@ chk_msk_listen() chk_msk_inuse() { local expected=$1 + local msg="$2" local listen_nr - shift 1 - listen_nr=$(ss -N "${ns}" -Ml | grep -c LISTEN) expected=$((expected + listen_nr)) @@ -177,7 +173,7 @@ chk_msk_inuse() sleep 0.1 done - __chk_nr get_msk_inuse $expected $* + __chk_nr get_msk_inuse $expected "$msg" 0 } # $1: ns, $2: port diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index a43d3e2f59bb..773dd770a567 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -1,6 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/mptcp_lib.sh" + time_start=$(date +%s) optstring="S:R:d:e:l:r:h4cm:f:tC" @@ -141,6 +143,9 @@ cleanup() done } +mptcp_lib_check_mptcp +mptcp_lib_check_kallsyms + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Could not run test without ip tool" @@ -691,6 +696,15 @@ run_test_transparent() return 0 fi + # IP(V6)_TRANSPARENT has been added after TOS support which came with + # the required infrastructure in MPTCP sockopt code. To support TOS, the + # following function has been exported (T). Not great but better than + # checking for a specific kernel version. + if ! mptcp_lib_kallsyms_has "T __ip_sock_set_tos$"; then + echo "INFO: ${msg} not supported by the kernel: SKIP" + return + fi + ip netns exec "$listener_ns" nft -f /dev/stdin <<"EOF" flush ruleset table inet mangle { @@ -763,6 +777,11 @@ run_tests_peekmode() run_tests_mptfo() { + if ! mptcp_lib_kallsyms_has "mptcp_fastopen_"; then + echo "INFO: TFO not supported by the kernel: SKIP" + return + fi + echo "INFO: with MPTFO start" ip netns exec "$ns1" sysctl -q net.ipv4.tcp_fastopen=2 ip netns exec "$ns2" sysctl -q net.ipv4.tcp_fastopen=1 @@ -783,6 +802,11 @@ run_tests_disconnect() local old_cin=$cin local old_sin=$sin + if ! mptcp_lib_kallsyms_has "mptcp_pm_data_reset$"; then + echo "INFO: Full disconnect not supported: SKIP" + return + fi + cat $cin $cin $cin > "$cin".disconnect # force do_transfer to cope with the multiple tranmissions diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 26310c17b4c6..0ae8cafde439 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -10,6 +10,8 @@ # because it's invoked by variable name, see how the "tests" array is used #shellcheck disable=SC2317 +. "$(dirname "${0}")/mptcp_lib.sh" + ret=0 sin="" sinfail="" @@ -17,11 +19,14 @@ sout="" cin="" cinfail="" cinsent="" +tmpfile="" cout="" capout="" ns1="" ns2="" ksft_skip=4 +iptables="iptables" +ip6tables="ip6tables" timeout_poll=30 timeout_test=$((timeout_poll * 2 + 1)) capture=0 @@ -79,7 +84,7 @@ init_partial() ip netns add $netns || exit $ksft_skip ip -net $netns link set lo up ip netns exec $netns sysctl -q net.mptcp.enabled=1 - ip netns exec $netns sysctl -q net.mptcp.pm_type=0 + ip netns exec $netns sysctl -q net.mptcp.pm_type=0 2>/dev/null || true ip netns exec $netns sysctl -q net.ipv4.conf.all.rp_filter=0 ip netns exec $netns sysctl -q net.ipv4.conf.default.rp_filter=0 if [ $checksum -eq 1 ]; then @@ -136,12 +141,19 @@ cleanup_partial() check_tools() { + mptcp_lib_check_mptcp + mptcp_lib_check_kallsyms + if ! ip -Version &> /dev/null; then echo "SKIP: Could not run test without ip tool" exit $ksft_skip fi - if ! iptables -V &> /dev/null; then + # Use the legacy version if available to support old kernel versions + if iptables-legacy -V &> /dev/null; then + iptables="iptables-legacy" + ip6tables="ip6tables-legacy" + elif ! iptables -V &> /dev/null; then echo "SKIP: Could not run all tests without iptables tool" exit $ksft_skip fi @@ -175,10 +187,37 @@ cleanup() { rm -f "$cin" "$cout" "$sinfail" rm -f "$sin" "$sout" "$cinsent" "$cinfail" + rm -f "$tmpfile" rm -rf $evts_ns1 $evts_ns2 cleanup_partial } +# $1: msg +print_title() +{ + printf "%03u %-36s %s" "${TEST_COUNT}" "${TEST_NAME}" "${1}" +} + +# [ $1: fail msg ] +mark_as_skipped() +{ + local msg="${1:-"Feature not supported"}" + + mptcp_lib_fail_if_expected_feature "${msg}" + + print_title "[ skip ] ${msg}" + printf "\n" +} + +# $@: condition +continue_if() +{ + if ! "${@}"; then + mark_as_skipped + return 1 + fi +} + skip_test() { if [ "${#only_tests_ids[@]}" -eq 0 ] && [ "${#only_tests_names[@]}" -eq 0 ]; then @@ -222,6 +261,19 @@ reset() return 0 } +# $1: test name ; $2: counter to check +reset_check_counter() +{ + reset "${1}" || return 1 + + local counter="${2}" + + if ! nstat -asz "${counter}" | grep -wq "${counter}"; then + mark_as_skipped "counter '${counter}' is not available" + return 1 + fi +} + # $1: test name reset_with_cookies() { @@ -241,17 +293,21 @@ reset_with_add_addr_timeout() reset "${1}" || return 1 - tables="iptables" + tables="${iptables}" if [ $ip -eq 6 ]; then - tables="ip6tables" + tables="${ip6tables}" fi ip netns exec $ns1 sysctl -q net.mptcp.add_addr_timeout=1 - ip netns exec $ns2 $tables -A OUTPUT -p tcp \ - -m tcp --tcp-option 30 \ - -m bpf --bytecode \ - "$CBPF_MPTCP_SUBOPTION_ADD_ADDR" \ - -j DROP + + if ! ip netns exec $ns2 $tables -A OUTPUT -p tcp \ + -m tcp --tcp-option 30 \ + -m bpf --bytecode \ + "$CBPF_MPTCP_SUBOPTION_ADD_ADDR" \ + -j DROP; then + mark_as_skipped "unable to set the 'add addr' rule" + return 1 + fi } # $1: test name @@ -295,22 +351,17 @@ reset_with_allow_join_id0() # tc action pedit offset 162 out of bounds # # Netfilter is used to mark packets with enough data. -reset_with_fail() +setup_fail_rules() { - reset "${1}" || return 1 - - ip netns exec $ns1 sysctl -q net.mptcp.checksum_enabled=1 - ip netns exec $ns2 sysctl -q net.mptcp.checksum_enabled=1 - check_invert=1 validate_checksum=1 - local i="$2" - local ip="${3:-4}" + local i="$1" + local ip="${2:-4}" local tables - tables="iptables" + tables="${iptables}" if [ $ip -eq 6 ]; then - tables="ip6tables" + tables="${ip6tables}" fi ip netns exec $ns2 $tables \ @@ -320,15 +371,32 @@ reset_with_fail() -p tcp \ -m length --length 150:9999 \ -m statistic --mode nth --packet 1 --every 99999 \ - -j MARK --set-mark 42 || exit 1 + -j MARK --set-mark 42 || return ${ksft_skip} - tc -n $ns2 qdisc add dev ns2eth$i clsact || exit 1 + tc -n $ns2 qdisc add dev ns2eth$i clsact || return ${ksft_skip} tc -n $ns2 filter add dev ns2eth$i egress \ protocol ip prio 1000 \ handle 42 fw \ action pedit munge offset 148 u8 invert \ pipe csum tcp \ - index 100 || exit 1 + index 100 || return ${ksft_skip} +} + +reset_with_fail() +{ + reset_check_counter "${1}" "MPTcpExtInfiniteMapTx" || return 1 + shift + + ip netns exec $ns1 sysctl -q net.mptcp.checksum_enabled=1 + ip netns exec $ns2 sysctl -q net.mptcp.checksum_enabled=1 + + local rc=0 + setup_fail_rules "${@}" || rc=$? + + if [ ${rc} -eq ${ksft_skip} ]; then + mark_as_skipped "unable to set the 'fail' rules" + return 1 + fi } reset_with_events() @@ -343,6 +411,25 @@ reset_with_events() evts_ns2_pid=$! } +reset_with_tcp_filter() +{ + reset "${1}" || return 1 + shift + + local ns="${!1}" + local src="${2}" + local target="${3}" + + if ! ip netns exec "${ns}" ${iptables} \ + -A INPUT \ + -s "${src}" \ + -p tcp \ + -j "${target}"; then + mark_as_skipped "unable to set the filter rules" + return 1 + fi +} + fail_test() { ret=1 @@ -383,9 +470,16 @@ check_transfer() fail_test return 1 fi - bytes="--bytes=${bytes}" + + # note: BusyBox's "cmp" command doesn't support --bytes + tmpfile=$(mktemp) + head --bytes="$bytes" "$in" > "$tmpfile" + mv "$tmpfile" "$in" + head --bytes="$bytes" "$out" > "$tmpfile" + mv "$tmpfile" "$out" + tmpfile="" fi - cmp -l "$in" "$out" ${bytes} | while read -r i a b; do + cmp -l "$in" "$out" | while read -r i a b; do local sum=$((0${a} + 0${b})) if [ $check_invert -eq 0 ] || [ $sum -ne $((0xff)) ]; then echo "[ FAIL ] $what does not match (in, out):" @@ -454,11 +548,25 @@ wait_local_port_listen() done } -rm_addr_count() +# $1: ns ; $2: counter +get_counter() { - local ns=${1} + local ns="${1}" + local counter="${2}" + local count - ip netns exec ${ns} nstat -as | grep MPTcpExtRmAddr | awk '{print $2}' + count=$(ip netns exec ${ns} nstat -asz "${counter}" | awk 'NR==1 {next} {print $2}') + if [ -z "${count}" ]; then + mptcp_lib_fail_if_expected_feature "${counter} counter" + return 1 + fi + + echo "${count}" +} + +rm_addr_count() +{ + get_counter "${1}" "MPTcpExtRmAddr" } # $1: ns, $2: old rm_addr counter in $ns @@ -481,11 +589,11 @@ wait_mpj() local ns="${1}" local cnt old_cnt - old_cnt=$(ip netns exec ${ns} nstat -as | grep MPJoinAckRx | awk '{print $2}') + old_cnt=$(get_counter ${ns} "MPTcpExtMPJoinAckRx") local i for i in $(seq 10); do - cnt=$(ip netns exec ${ns} nstat -as | grep MPJoinAckRx | awk '{print $2}') + cnt=$(get_counter ${ns} "MPTcpExtMPJoinAckRx") [ "$cnt" = "${old_cnt}" ] || break sleep 0.1 done @@ -685,15 +793,6 @@ pm_nl_check_endpoint() fi } -filter_tcp_from() -{ - local ns="${1}" - local src="${2}" - local target="${3}" - - ip netns exec "${ns}" iptables -A INPUT -s "${src}" -p tcp -j "${target}" -} - do_transfer() { local listener_ns="$1" @@ -849,7 +948,15 @@ do_transfer() sed -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q') ip netns exec ${listener_ns} ./pm_nl_ctl ann $addr token $tk id $id sleep 1 + sp=$(grep "type:10" "$evts_ns1" | + sed -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q') + da=$(grep "type:10" "$evts_ns1" | + sed -n 's/.*\(daddr6:\)\([0-9a-f:.]*\).*$/\2/p;q') + dp=$(grep "type:10" "$evts_ns1" | + sed -n 's/.*\(dport:\)\([[:digit:]]*\).*$/\2/p;q') ip netns exec ${listener_ns} ./pm_nl_ctl rem token $tk id $id + ip netns exec ${listener_ns} ./pm_nl_ctl dsf lip "::ffff:$addr" \ + lport $sp rip $da rport $dp token $tk fi counter=$((counter + 1)) @@ -915,6 +1022,7 @@ do_transfer() sleep 1 sp=$(grep "type:10" "$evts_ns2" | sed -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q') + ip netns exec ${connector_ns} ./pm_nl_ctl rem token $tk id $id ip netns exec ${connector_ns} ./pm_nl_ctl dsf lip $addr lport $sp \ rip $da rport $dp token $tk fi @@ -1135,12 +1243,13 @@ chk_csum_nr() fi printf "%-${nr_blank}s %s" " " "sum" - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtDataCsumErr | awk '{print $2}') - [ -z "$count" ] && count=0 + count=$(get_counter ${ns1} "MPTcpExtDataCsumErr") if [ "$count" != "$csum_ns1" ]; then extra_msg="$extra_msg ns1=$count" fi - if { [ "$count" != $csum_ns1 ] && [ $allow_multi_errors_ns1 -eq 0 ]; } || + if [ -z "$count" ]; then + echo -n "[skip]" + elif { [ "$count" != $csum_ns1 ] && [ $allow_multi_errors_ns1 -eq 0 ]; } || { [ "$count" -lt $csum_ns1 ] && [ $allow_multi_errors_ns1 -eq 1 ]; }; then echo "[fail] got $count data checksum error[s] expected $csum_ns1" fail_test @@ -1149,12 +1258,13 @@ chk_csum_nr() echo -n "[ ok ]" fi echo -n " - csum " - count=$(ip netns exec $ns2 nstat -as | grep MPTcpExtDataCsumErr | awk '{print $2}') - [ -z "$count" ] && count=0 + count=$(get_counter ${ns2} "MPTcpExtDataCsumErr") if [ "$count" != "$csum_ns2" ]; then extra_msg="$extra_msg ns2=$count" fi - if { [ "$count" != $csum_ns2 ] && [ $allow_multi_errors_ns2 -eq 0 ]; } || + if [ -z "$count" ]; then + echo -n "[skip]" + elif { [ "$count" != $csum_ns2 ] && [ $allow_multi_errors_ns2 -eq 0 ]; } || { [ "$count" -lt $csum_ns2 ] && [ $allow_multi_errors_ns2 -eq 1 ]; }; then echo "[fail] got $count data checksum error[s] expected $csum_ns2" fail_test @@ -1196,12 +1306,13 @@ chk_fail_nr() fi printf "%-${nr_blank}s %s" " " "ftx" - count=$(ip netns exec $ns_tx nstat -as | grep MPTcpExtMPFailTx | awk '{print $2}') - [ -z "$count" ] && count=0 + count=$(get_counter ${ns_tx} "MPTcpExtMPFailTx") if [ "$count" != "$fail_tx" ]; then extra_msg="$extra_msg,tx=$count" fi - if { [ "$count" != "$fail_tx" ] && [ $allow_tx_lost -eq 0 ]; } || + if [ -z "$count" ]; then + echo -n "[skip]" + elif { [ "$count" != "$fail_tx" ] && [ $allow_tx_lost -eq 0 ]; } || { [ "$count" -gt "$fail_tx" ] && [ $allow_tx_lost -eq 1 ]; }; then echo "[fail] got $count MP_FAIL[s] TX expected $fail_tx" fail_test @@ -1211,12 +1322,13 @@ chk_fail_nr() fi echo -n " - failrx" - count=$(ip netns exec $ns_rx nstat -as | grep MPTcpExtMPFailRx | awk '{print $2}') - [ -z "$count" ] && count=0 + count=$(get_counter ${ns_rx} "MPTcpExtMPFailRx") if [ "$count" != "$fail_rx" ]; then extra_msg="$extra_msg,rx=$count" fi - if { [ "$count" != "$fail_rx" ] && [ $allow_rx_lost -eq 0 ]; } || + if [ -z "$count" ]; then + echo -n "[skip]" + elif { [ "$count" != "$fail_rx" ] && [ $allow_rx_lost -eq 0 ]; } || { [ "$count" -gt "$fail_rx" ] && [ $allow_rx_lost -eq 1 ]; }; then echo "[fail] got $count MP_FAIL[s] RX expected $fail_rx" fail_test @@ -1248,10 +1360,11 @@ chk_fclose_nr() fi printf "%-${nr_blank}s %s" " " "ctx" - count=$(ip netns exec $ns_tx nstat -as | grep MPTcpExtMPFastcloseTx | awk '{print $2}') - [ -z "$count" ] && count=0 - [ "$count" != "$fclose_tx" ] && extra_msg="$extra_msg,tx=$count" - if [ "$count" != "$fclose_tx" ]; then + count=$(get_counter ${ns_tx} "MPTcpExtMPFastcloseTx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$fclose_tx" ]; then + extra_msg="$extra_msg,tx=$count" echo "[fail] got $count MP_FASTCLOSE[s] TX expected $fclose_tx" fail_test dump_stats=1 @@ -1260,10 +1373,11 @@ chk_fclose_nr() fi echo -n " - fclzrx" - count=$(ip netns exec $ns_rx nstat -as | grep MPTcpExtMPFastcloseRx | awk '{print $2}') - [ -z "$count" ] && count=0 - [ "$count" != "$fclose_rx" ] && extra_msg="$extra_msg,rx=$count" - if [ "$count" != "$fclose_rx" ]; then + count=$(get_counter ${ns_rx} "MPTcpExtMPFastcloseRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$fclose_rx" ]; then + extra_msg="$extra_msg,rx=$count" echo "[fail] got $count MP_FASTCLOSE[s] RX expected $fclose_rx" fail_test dump_stats=1 @@ -1294,9 +1408,10 @@ chk_rst_nr() fi printf "%-${nr_blank}s %s" " " "rtx" - count=$(ip netns exec $ns_tx nstat -as | grep MPTcpExtMPRstTx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ $count -lt $rst_tx ]; then + count=$(get_counter ${ns_tx} "MPTcpExtMPRstTx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ $count -lt $rst_tx ]; then echo "[fail] got $count MP_RST[s] TX expected $rst_tx" fail_test dump_stats=1 @@ -1305,9 +1420,10 @@ chk_rst_nr() fi echo -n " - rstrx " - count=$(ip netns exec $ns_rx nstat -as | grep MPTcpExtMPRstRx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" -lt "$rst_rx" ]; then + count=$(get_counter ${ns_rx} "MPTcpExtMPRstRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" -lt "$rst_rx" ]; then echo "[fail] got $count MP_RST[s] RX expected $rst_rx" fail_test dump_stats=1 @@ -1328,9 +1444,10 @@ chk_infi_nr() local dump_stats printf "%-${nr_blank}s %s" " " "itx" - count=$(ip netns exec $ns2 nstat -as | grep InfiniteMapTx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$infi_tx" ]; then + count=$(get_counter ${ns2} "MPTcpExtInfiniteMapTx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$infi_tx" ]; then echo "[fail] got $count infinite map[s] TX expected $infi_tx" fail_test dump_stats=1 @@ -1339,9 +1456,10 @@ chk_infi_nr() fi echo -n " - infirx" - count=$(ip netns exec $ns1 nstat -as | grep InfiniteMapRx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$infi_rx" ]; then + count=$(get_counter ${ns1} "MPTcpExtInfiniteMapRx") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$infi_rx" ]; then echo "[fail] got $count infinite map[s] RX expected $infi_rx" fail_test dump_stats=1 @@ -1373,9 +1491,10 @@ chk_join_nr() fi printf "%03u %-36s %s" "${TEST_COUNT}" "${title}" "syn" - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinSynRx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$syn_nr" ]; then + count=$(get_counter ${ns1} "MPTcpExtMPJoinSynRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$syn_nr" ]; then echo "[fail] got $count JOIN[s] syn expected $syn_nr" fail_test dump_stats=1 @@ -1385,9 +1504,10 @@ chk_join_nr() echo -n " - synack" with_cookie=$(ip netns exec $ns2 sysctl -n net.ipv4.tcp_syncookies) - count=$(ip netns exec $ns2 nstat -as | grep MPTcpExtMPJoinSynAckRx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$syn_ack_nr" ]; then + count=$(get_counter ${ns2} "MPTcpExtMPJoinSynAckRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$syn_ack_nr" ]; then # simult connections exceeding the limit with cookie enabled could go up to # synack validation as the conn limit can be enforced reliably only after # the subflow creation @@ -1403,9 +1523,10 @@ chk_join_nr() fi echo -n " - ack" - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinAckRx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$ack_nr" ]; then + count=$(get_counter ${ns1} "MPTcpExtMPJoinAckRx") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$ack_nr" ]; then echo "[fail] got $count JOIN[s] ack expected $ack_nr" fail_test dump_stats=1 @@ -1437,12 +1558,12 @@ chk_stale_nr() local recover_nr printf "%-${nr_blank}s %-18s" " " "stale" - stale_nr=$(ip netns exec $ns nstat -as | grep MPTcpExtSubflowStale | awk '{print $2}') - [ -z "$stale_nr" ] && stale_nr=0 - recover_nr=$(ip netns exec $ns nstat -as | grep MPTcpExtSubflowRecover | awk '{print $2}') - [ -z "$recover_nr" ] && recover_nr=0 - if [ $stale_nr -lt $stale_min ] || + stale_nr=$(get_counter ${ns} "MPTcpExtSubflowStale") + recover_nr=$(get_counter ${ns} "MPTcpExtSubflowRecover") + if [ -z "$stale_nr" ] || [ -z "$recover_nr" ]; then + echo "[skip]" + elif [ $stale_nr -lt $stale_min ] || { [ $stale_max -gt 0 ] && [ $stale_nr -gt $stale_max ]; } || [ $((stale_nr - recover_nr)) -ne $stale_delta ]; then echo "[fail] got $stale_nr stale[s] $recover_nr recover[s], " \ @@ -1478,12 +1599,12 @@ chk_add_nr() timeout=$(ip netns exec $ns1 sysctl -n net.mptcp.add_addr_timeout) printf "%-${nr_blank}s %s" " " "add" - count=$(ip netns exec $ns2 nstat -as MPTcpExtAddAddr | grep MPTcpExtAddAddr | awk '{print $2}') - [ -z "$count" ] && count=0 - + count=$(get_counter ${ns2} "MPTcpExtAddAddr") + if [ -z "$count" ]; then + echo -n "[skip]" # if the test configured a short timeout tolerate greater then expected # add addrs options, due to retransmissions - if [ "$count" != "$add_nr" ] && { [ "$timeout" -gt 1 ] || [ "$count" -lt "$add_nr" ]; }; then + elif [ "$count" != "$add_nr" ] && { [ "$timeout" -gt 1 ] || [ "$count" -lt "$add_nr" ]; }; then echo "[fail] got $count ADD_ADDR[s] expected $add_nr" fail_test dump_stats=1 @@ -1492,9 +1613,10 @@ chk_add_nr() fi echo -n " - echo " - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtEchoAdd | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$echo_nr" ]; then + count=$(get_counter ${ns1} "MPTcpExtEchoAdd") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$echo_nr" ]; then echo "[fail] got $count ADD_ADDR echo[s] expected $echo_nr" fail_test dump_stats=1 @@ -1504,9 +1626,10 @@ chk_add_nr() if [ $port_nr -gt 0 ]; then echo -n " - pt " - count=$(ip netns exec $ns2 nstat -as | grep MPTcpExtPortAdd | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$port_nr" ]; then + count=$(get_counter ${ns2} "MPTcpExtPortAdd") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$port_nr" ]; then echo "[fail] got $count ADD_ADDR[s] with a port-number expected $port_nr" fail_test dump_stats=1 @@ -1515,10 +1638,10 @@ chk_add_nr() fi printf "%-${nr_blank}s %s" " " "syn" - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinPortSynRx | - awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$syn_nr" ]; then + count=$(get_counter ${ns1} "MPTcpExtMPJoinPortSynRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$syn_nr" ]; then echo "[fail] got $count JOIN[s] syn with a different \ port-number expected $syn_nr" fail_test @@ -1528,10 +1651,10 @@ chk_add_nr() fi echo -n " - synack" - count=$(ip netns exec $ns2 nstat -as | grep MPTcpExtMPJoinPortSynAckRx | - awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$syn_ack_nr" ]; then + count=$(get_counter ${ns2} "MPTcpExtMPJoinPortSynAckRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$syn_ack_nr" ]; then echo "[fail] got $count JOIN[s] synack with a different \ port-number expected $syn_ack_nr" fail_test @@ -1541,10 +1664,10 @@ chk_add_nr() fi echo -n " - ack" - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinPortAckRx | - awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$ack_nr" ]; then + count=$(get_counter ${ns1} "MPTcpExtMPJoinPortAckRx") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$ack_nr" ]; then echo "[fail] got $count JOIN[s] ack with a different \ port-number expected $ack_nr" fail_test @@ -1554,10 +1677,10 @@ chk_add_nr() fi printf "%-${nr_blank}s %s" " " "syn" - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMismatchPortSynRx | - awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$mis_syn_nr" ]; then + count=$(get_counter ${ns1} "MPTcpExtMismatchPortSynRx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$mis_syn_nr" ]; then echo "[fail] got $count JOIN[s] syn with a mismatched \ port-number expected $mis_syn_nr" fail_test @@ -1567,10 +1690,10 @@ chk_add_nr() fi echo -n " - ack " - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMismatchPortAckRx | - awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$mis_ack_nr" ]; then + count=$(get_counter ${ns1} "MPTcpExtMismatchPortAckRx") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$mis_ack_nr" ]; then echo "[fail] got $count JOIN[s] ack with a mismatched \ port-number expected $mis_ack_nr" fail_test @@ -1614,9 +1737,10 @@ chk_rm_nr() fi printf "%-${nr_blank}s %s" " " "rm " - count=$(ip netns exec $addr_ns nstat -as | grep MPTcpExtRmAddr | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$rm_addr_nr" ]; then + count=$(get_counter ${addr_ns} "MPTcpExtRmAddr") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$rm_addr_nr" ]; then echo "[fail] got $count RM_ADDR[s] expected $rm_addr_nr" fail_test dump_stats=1 @@ -1625,29 +1749,27 @@ chk_rm_nr() fi echo -n " - rmsf " - count=$(ip netns exec $subflow_ns nstat -as | grep MPTcpExtRmSubflow | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ -n "$simult" ]; then + count=$(get_counter ${subflow_ns} "MPTcpExtRmSubflow") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ -n "$simult" ]; then local cnt suffix - cnt=$(ip netns exec $addr_ns nstat -as | grep MPTcpExtRmSubflow | awk '{print $2}') + cnt=$(get_counter ${addr_ns} "MPTcpExtRmSubflow") # in case of simult flush, the subflow removal count on each side is # unreliable - [ -z "$cnt" ] && cnt=0 count=$((count + cnt)) [ "$count" != "$rm_subflow_nr" ] && suffix="$count in [$rm_subflow_nr:$((rm_subflow_nr*2))]" if [ $count -ge "$rm_subflow_nr" ] && \ [ "$count" -le "$((rm_subflow_nr *2 ))" ]; then - echo "[ ok ] $suffix" + echo -n "[ ok ] $suffix" else echo "[fail] got $count RM_SUBFLOW[s] expected in range [$rm_subflow_nr:$((rm_subflow_nr*2))]" fail_test dump_stats=1 fi - return - fi - if [ "$count" != "$rm_subflow_nr" ]; then + elif [ "$count" != "$rm_subflow_nr" ]; then echo "[fail] got $count RM_SUBFLOW[s] expected $rm_subflow_nr" fail_test dump_stats=1 @@ -1668,9 +1790,10 @@ chk_prio_nr() local dump_stats printf "%-${nr_blank}s %s" " " "ptx" - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPPrioTx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$mp_prio_nr_tx" ]; then + count=$(get_counter ${ns1} "MPTcpExtMPPrioTx") + if [ -z "$count" ]; then + echo -n "[skip]" + elif [ "$count" != "$mp_prio_nr_tx" ]; then echo "[fail] got $count MP_PRIO[s] TX expected $mp_prio_nr_tx" fail_test dump_stats=1 @@ -1679,9 +1802,10 @@ chk_prio_nr() fi echo -n " - prx " - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPPrioRx | awk '{print $2}') - [ -z "$count" ] && count=0 - if [ "$count" != "$mp_prio_nr_rx" ]; then + count=$(get_counter ${ns1} "MPTcpExtMPPrioRx") + if [ -z "$count" ]; then + echo "[skip]" + elif [ "$count" != "$mp_prio_nr_rx" ]; then echo "[fail] got $count MP_PRIO[s] RX expected $mp_prio_nr_rx" fail_test dump_stats=1 @@ -1797,7 +1921,7 @@ wait_attempt_fail() while [ $time -lt $timeout_ms ]; do local cnt - cnt=$(ip netns exec $ns nstat -as TcpAttemptFails | grep TcpAttemptFails | awk '{print $2}') + cnt=$(get_counter ${ns} "TcpAttemptFails") [ "$cnt" = 1 ] && return 1 time=$((time + 100)) @@ -1890,23 +2014,23 @@ subflows_error_tests() fi # multiple subflows, with subflow creation error - if reset "multi subflows, with failing subflow"; then + if reset_with_tcp_filter "multi subflows, with failing subflow" ns1 10.0.3.2 REJECT && + continue_if mptcp_lib_kallsyms_has "mptcp_pm_subflow_check_next$"; 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 subflow pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow - filter_tcp_from $ns1 10.0.3.2 REJECT run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow chk_join_nr 1 1 1 fi # multiple subflows, with subflow timeout on MPJ - if reset "multi subflows, with subflow timeout"; then + if reset_with_tcp_filter "multi subflows, with subflow timeout" ns1 10.0.3.2 DROP && + continue_if mptcp_lib_kallsyms_has "mptcp_pm_subflow_check_next$"; 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 subflow pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow - filter_tcp_from $ns1 10.0.3.2 DROP run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow chk_join_nr 1 1 1 fi @@ -1914,11 +2038,11 @@ subflows_error_tests() # multiple subflows, check that the endpoint corresponding to # closed subflow (due to reset) is not reused if additional # subflows are added later - if reset "multi subflows, fair usage on close"; then + if reset_with_tcp_filter "multi subflows, fair usage on close" ns1 10.0.3.2 REJECT && + continue_if mptcp_lib_kallsyms_has "mptcp_pm_subflow_check_next$"; then pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 0 1 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - filter_tcp_from $ns1 10.0.3.2 REJECT run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow & # mpj subflow will be in TW after the reset @@ -2018,11 +2142,18 @@ signal_address_tests() # the peer could possibly miss some addr notification, allow retransmission ip netns exec $ns1 sysctl -q net.mptcp.add_addr_timeout=1 run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow - chk_join_nr 3 3 3 - # the server will not signal the address terminating - # the MPC subflow - chk_add_nr 3 3 + # It is not directly linked to the commit introducing this + # symbol but for the parent one which is linked anyway. + if ! mptcp_lib_kallsyms_has "mptcp_pm_subflow_check_next$"; then + chk_join_nr 3 3 2 + chk_add_nr 4 4 + else + chk_join_nr 3 3 3 + # the server will not signal the address terminating + # the MPC subflow + chk_add_nr 3 3 + fi fi } @@ -2263,7 +2394,12 @@ remove_tests() pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow chk_join_nr 3 3 3 - chk_rm_nr 0 3 simult + + if mptcp_lib_kversion_ge 5.18; then + chk_rm_nr 0 3 simult + else + chk_rm_nr 3 3 + fi fi # addresses flush @@ -2501,7 +2637,8 @@ v4mapped_tests() mixed_tests() { - if reset "IPv4 sockets do not use IPv6 addresses"; then + if reset "IPv4 sockets do not use IPv6 addresses" && + continue_if mptcp_lib_kversion_ge 6.3; then pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 1 1 pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal @@ -2510,7 +2647,8 @@ mixed_tests() fi # Need an IPv6 mptcp socket to allow subflows of both families - if reset "simult IPv4 and IPv6 subflows"; then + if reset "simult IPv4 and IPv6 subflows" && + continue_if mptcp_lib_kversion_ge 6.3; then pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 1 1 pm_nl_add_endpoint $ns1 10.0.1.1 flags signal @@ -2519,7 +2657,8 @@ mixed_tests() fi # cross families subflows will not be created even in fullmesh mode - if reset "simult IPv4 and IPv6 subflows, fullmesh 1x1"; then + if reset "simult IPv4 and IPv6 subflows, fullmesh 1x1" && + continue_if mptcp_lib_kversion_ge 6.3; then pm_nl_set_limits $ns1 0 4 pm_nl_set_limits $ns2 1 4 pm_nl_add_endpoint $ns2 dead:beef:2::2 flags subflow,fullmesh @@ -2530,7 +2669,8 @@ mixed_tests() # fullmesh still tries to create all the possibly subflows with # matching family - if reset "simult IPv4 and IPv6 subflows, fullmesh 2x2"; then + if reset "simult IPv4 and IPv6 subflows, fullmesh 2x2" && + continue_if mptcp_lib_kversion_ge 6.3; then pm_nl_set_limits $ns1 0 4 pm_nl_set_limits $ns2 2 4 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal @@ -2543,7 +2683,8 @@ mixed_tests() backup_tests() { # single subflow, backup - if reset "single subflow, backup"; then + if reset "single subflow, backup" && + continue_if mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 0 1 pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow,backup @@ -2553,7 +2694,8 @@ backup_tests() fi # single address, backup - if reset "single address, backup"; then + if reset "single address, backup" && + continue_if mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then pm_nl_set_limits $ns1 0 1 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal pm_nl_set_limits $ns2 1 1 @@ -2564,7 +2706,8 @@ backup_tests() fi # single address with port, backup - if reset "single address with port, backup"; then + if reset "single address with port, backup" && + continue_if mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then pm_nl_set_limits $ns1 0 1 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 pm_nl_set_limits $ns2 1 1 @@ -2574,14 +2717,16 @@ backup_tests() chk_prio_nr 1 1 fi - if reset "mpc backup"; then + if reset "mpc backup" && + continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,backup run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow chk_join_nr 0 0 0 chk_prio_nr 0 1 fi - if reset "mpc backup both sides"; then + if reset "mpc backup both sides" && + continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then pm_nl_add_endpoint $ns1 10.0.1.1 flags subflow,backup pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,backup run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow @@ -2589,14 +2734,16 @@ backup_tests() chk_prio_nr 1 1 fi - if reset "mpc switch to backup"; then + if reset "mpc switch to backup" && + continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow backup chk_join_nr 0 0 0 chk_prio_nr 0 1 fi - if reset "mpc switch to backup both sides"; then + if reset "mpc switch to backup both sides" && + continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then pm_nl_add_endpoint $ns1 10.0.1.1 flags subflow pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow backup @@ -2622,38 +2769,41 @@ verify_listener_events() local family local saddr local sport + local name if [ $e_type = $LISTENER_CREATED ]; then - stdbuf -o0 -e0 printf "\t\t\t\t\t CREATE_LISTENER %s:%s"\ - $e_saddr $e_sport + name="LISTENER_CREATED" elif [ $e_type = $LISTENER_CLOSED ]; then - stdbuf -o0 -e0 printf "\t\t\t\t\t CLOSE_LISTENER %s:%s "\ - $e_saddr $e_sport + name="LISTENER_CLOSED" + else + name="$e_type" fi - type=$(grep "type:$e_type," $evt | - sed --unbuffered -n 's/.*\(type:\)\([[:digit:]]*\).*$/\2/p;q') - family=$(grep "type:$e_type," $evt | - sed --unbuffered -n 's/.*\(family:\)\([[:digit:]]*\).*$/\2/p;q') - sport=$(grep "type:$e_type," $evt | - sed --unbuffered -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q') + printf "%-${nr_blank}s %s %s:%s " " " "$name" "$e_saddr" "$e_sport" + + if ! mptcp_lib_kallsyms_has "mptcp_event_pm_listener$"; then + printf "[skip]: event not supported\n" + return + fi + + type=$(grep "type:$e_type," $evt | sed -n 's/.*\(type:\)\([[:digit:]]*\).*$/\2/p;q') + family=$(grep "type:$e_type," $evt | sed -n 's/.*\(family:\)\([[:digit:]]*\).*$/\2/p;q') + sport=$(grep "type:$e_type," $evt | sed -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q') if [ $family ] && [ $family = $AF_INET6 ]; then - saddr=$(grep "type:$e_type," $evt | - sed --unbuffered -n 's/.*\(saddr6:\)\([0-9a-f:.]*\).*$/\2/p;q') + saddr=$(grep "type:$e_type," $evt | sed -n 's/.*\(saddr6:\)\([0-9a-f:.]*\).*$/\2/p;q') else - saddr=$(grep "type:$e_type," $evt | - sed --unbuffered -n 's/.*\(saddr4:\)\([0-9.]*\).*$/\2/p;q') + saddr=$(grep "type:$e_type," $evt | sed -n 's/.*\(saddr4:\)\([0-9.]*\).*$/\2/p;q') fi if [ $type ] && [ $type = $e_type ] && [ $family ] && [ $family = $e_family ] && [ $saddr ] && [ $saddr = $e_saddr ] && [ $sport ] && [ $sport = $e_sport ]; then - stdbuf -o0 -e0 printf "[ ok ]\n" + echo "[ ok ]" return 0 fi fail_test - stdbuf -o0 -e0 printf "[fail]\n" + echo "[fail]" } add_addr_ports_tests() @@ -2959,7 +3109,8 @@ fullmesh_tests() fi # set fullmesh flag - if reset "set fullmesh flag test"; then + if reset "set fullmesh flag test" && + continue_if mptcp_lib_kversion_ge 5.18; then pm_nl_set_limits $ns1 4 4 pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow pm_nl_set_limits $ns2 4 4 @@ -2969,7 +3120,8 @@ fullmesh_tests() fi # set nofullmesh flag - if reset "set nofullmesh flag test"; then + if reset "set nofullmesh flag test" && + continue_if mptcp_lib_kversion_ge 5.18; then pm_nl_set_limits $ns1 4 4 pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow,fullmesh pm_nl_set_limits $ns2 4 4 @@ -2979,7 +3131,8 @@ fullmesh_tests() fi # set backup,fullmesh flags - if reset "set backup,fullmesh flags test"; then + if reset "set backup,fullmesh flags test" && + continue_if mptcp_lib_kversion_ge 5.18; then pm_nl_set_limits $ns1 4 4 pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow pm_nl_set_limits $ns2 4 4 @@ -2990,7 +3143,8 @@ fullmesh_tests() fi # set nobackup,nofullmesh flags - if reset "set nobackup,nofullmesh flags test"; then + if reset "set nobackup,nofullmesh flags test" && + continue_if mptcp_lib_kversion_ge 5.18; then pm_nl_set_limits $ns1 4 4 pm_nl_set_limits $ns2 4 4 pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow,backup,fullmesh @@ -3003,14 +3157,14 @@ fullmesh_tests() fastclose_tests() { - if reset "fastclose test"; then + if reset_check_counter "fastclose test" "MPTcpExtMPFastcloseTx"; then run_tests $ns1 $ns2 10.0.1.1 1024 0 fastclose_client chk_join_nr 0 0 0 chk_fclose_nr 1 1 chk_rst_nr 1 1 invert fi - if reset "fastclose server test"; then + if reset_check_counter "fastclose server test" "MPTcpExtMPFastcloseRx"; then run_tests $ns1 $ns2 10.0.1.1 1024 0 fastclose_server chk_join_nr 0 0 0 chk_fclose_nr 1 1 invert @@ -3048,7 +3202,8 @@ fail_tests() userspace_tests() { # userspace pm type prevents add_addr - if reset "userspace pm type prevents add_addr"; then + if reset "userspace pm type prevents add_addr" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns1 pm_nl_set_limits $ns1 0 2 pm_nl_set_limits $ns2 0 2 @@ -3059,7 +3214,8 @@ userspace_tests() fi # userspace pm type does not echo add_addr without daemon - if reset "userspace pm no echo w/o daemon"; then + if reset "userspace pm no echo w/o daemon" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns2 pm_nl_set_limits $ns1 0 2 pm_nl_set_limits $ns2 0 2 @@ -3070,7 +3226,8 @@ userspace_tests() fi # userspace pm type rejects join - if reset "userspace pm type rejects join"; then + if reset "userspace pm type rejects join" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns1 pm_nl_set_limits $ns1 1 1 pm_nl_set_limits $ns2 1 1 @@ -3080,7 +3237,8 @@ userspace_tests() fi # userspace pm type does not send join - if reset "userspace pm type does not send join"; then + if reset "userspace pm type does not send join" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns2 pm_nl_set_limits $ns1 1 1 pm_nl_set_limits $ns2 1 1 @@ -3090,7 +3248,8 @@ userspace_tests() fi # userspace pm type prevents mp_prio - if reset "userspace pm type prevents mp_prio"; then + if reset "userspace pm type prevents mp_prio" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns1 pm_nl_set_limits $ns1 1 1 pm_nl_set_limits $ns2 1 1 @@ -3101,7 +3260,8 @@ userspace_tests() fi # userspace pm type prevents rm_addr - if reset "userspace pm type prevents rm_addr"; then + if reset "userspace pm type prevents rm_addr" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns1 set_userspace_pm $ns2 pm_nl_set_limits $ns1 0 1 @@ -3113,7 +3273,8 @@ userspace_tests() fi # userspace pm add & remove address - if reset_with_events "userspace pm add & remove address"; then + if reset_with_events "userspace pm add & remove address" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns1 pm_nl_set_limits $ns2 1 1 run_tests $ns1 $ns2 10.0.1.1 0 userspace_1 0 slow @@ -3124,20 +3285,23 @@ userspace_tests() fi # userspace pm create destroy subflow - if reset_with_events "userspace pm create destroy subflow"; then + if reset_with_events "userspace pm create destroy subflow" && + continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns2 pm_nl_set_limits $ns1 0 1 run_tests $ns1 $ns2 10.0.1.1 0 0 userspace_1 slow chk_join_nr 1 1 1 - chk_rm_nr 0 1 + chk_rm_nr 1 1 kill_events_pids fi } endpoint_tests() { + # subflow_rebuild_header is needed to support the implicit flag # userspace pm type prevents add_addr - if reset "implicit EP"; then + if reset "implicit EP" && + mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then pm_nl_set_limits $ns1 2 2 pm_nl_set_limits $ns2 2 2 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal @@ -3157,7 +3321,8 @@ endpoint_tests() kill_tests_wait fi - if reset "delete and re-add"; then + if reset "delete and re-add" && + mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then pm_nl_set_limits $ns1 1 1 pm_nl_set_limits $ns2 1 1 pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh new file mode 100644 index 000000000000..f32045b23b89 --- /dev/null +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -0,0 +1,104 @@ +#! /bin/bash +# SPDX-License-Identifier: GPL-2.0 + +readonly KSFT_FAIL=1 +readonly KSFT_SKIP=4 + +# SELFTESTS_MPTCP_LIB_EXPECT_ALL_FEATURES env var can be set when validating all +# features using the last version of the kernel and the selftests to make sure +# a test is not being skipped by mistake. +mptcp_lib_expect_all_features() { + [ "${SELFTESTS_MPTCP_LIB_EXPECT_ALL_FEATURES:-}" = "1" ] +} + +# $1: msg +mptcp_lib_fail_if_expected_feature() { + if mptcp_lib_expect_all_features; then + echo "ERROR: missing feature: ${*}" + exit ${KSFT_FAIL} + fi + + return 1 +} + +# $1: file +mptcp_lib_has_file() { + local f="${1}" + + if [ -f "${f}" ]; then + return 0 + fi + + mptcp_lib_fail_if_expected_feature "${f} file not found" +} + +mptcp_lib_check_mptcp() { + if ! mptcp_lib_has_file "/proc/sys/net/mptcp/enabled"; then + echo "SKIP: MPTCP support is not available" + exit ${KSFT_SKIP} + fi +} + +mptcp_lib_check_kallsyms() { + if ! mptcp_lib_has_file "/proc/kallsyms"; then + echo "SKIP: CONFIG_KALLSYMS is missing" + exit ${KSFT_SKIP} + fi +} + +# Internal: use mptcp_lib_kallsyms_has() instead +__mptcp_lib_kallsyms_has() { + local sym="${1}" + + mptcp_lib_check_kallsyms + + grep -q " ${sym}" /proc/kallsyms +} + +# $1: part of a symbol to look at, add '$' at the end for full name +mptcp_lib_kallsyms_has() { + local sym="${1}" + + if __mptcp_lib_kallsyms_has "${sym}"; then + return 0 + fi + + mptcp_lib_fail_if_expected_feature "${sym} symbol not found" +} + +# $1: part of a symbol to look at, add '$' at the end for full name +mptcp_lib_kallsyms_doesnt_have() { + local sym="${1}" + + if ! __mptcp_lib_kallsyms_has "${sym}"; then + return 0 + fi + + mptcp_lib_fail_if_expected_feature "${sym} symbol has been found" +} + +# !!!AVOID USING THIS!!! +# Features might not land in the expected version and features can be backported +# +# $1: kernel version, e.g. 6.3 +mptcp_lib_kversion_ge() { + local exp_maj="${1%.*}" + local exp_min="${1#*.}" + local v maj min + + # If the kernel has backported features, set this env var to 1: + if [ "${SELFTESTS_MPTCP_LIB_NO_KVERSION_CHECK:-}" = "1" ]; then + return 0 + fi + + v=$(uname -r | cut -d'.' -f1,2) + maj=${v%.*} + min=${v#*.} + + if [ "${maj}" -gt "${exp_maj}" ] || + { [ "${maj}" -eq "${exp_maj}" ] && [ "${min}" -ge "${exp_min}" ]; }; then + return 0 + fi + + mptcp_lib_fail_if_expected_feature "kernel version ${1} lower than ${v}" +} diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c index ae61f39556ca..b35148edbf02 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c @@ -87,6 +87,10 @@ struct so_state { uint64_t tcpi_rcv_delta; }; +#ifndef MIN +#define MIN(a, b) ((a) < (b) ? (a) : (b)) +#endif + static void die_perror(const char *msg) { perror(msg); @@ -349,13 +353,14 @@ static void do_getsockopt_tcp_info(struct so_state *s, int fd, size_t r, size_t xerror("getsockopt MPTCP_TCPINFO (tries %d, %m)"); assert(olen <= sizeof(ti)); - assert(ti.d.size_user == ti.d.size_kernel); - assert(ti.d.size_user == sizeof(struct tcp_info)); + assert(ti.d.size_kernel > 0); + assert(ti.d.size_user == + MIN(ti.d.size_kernel, sizeof(struct tcp_info))); assert(ti.d.num_subflows == 1); assert(olen > (socklen_t)sizeof(struct mptcp_subflow_data)); olen -= sizeof(struct mptcp_subflow_data); - assert(olen == sizeof(struct tcp_info)); + assert(olen == ti.d.size_user); if (ti.ti[0].tcpi_bytes_sent == w && ti.ti[0].tcpi_bytes_received == r) @@ -401,13 +406,14 @@ static void do_getsockopt_subflow_addrs(int fd) die_perror("getsockopt MPTCP_SUBFLOW_ADDRS"); assert(olen <= sizeof(addrs)); - assert(addrs.d.size_user == addrs.d.size_kernel); - assert(addrs.d.size_user == sizeof(struct mptcp_subflow_addrs)); + assert(addrs.d.size_kernel > 0); + assert(addrs.d.size_user == + MIN(addrs.d.size_kernel, sizeof(struct mptcp_subflow_addrs))); assert(addrs.d.num_subflows == 1); assert(olen > (socklen_t)sizeof(struct mptcp_subflow_data)); olen -= sizeof(struct mptcp_subflow_data); - assert(olen == sizeof(struct mptcp_subflow_addrs)); + assert(olen == addrs.d.size_user); llen = sizeof(local); ret = getsockname(fd, (struct sockaddr *)&local, &llen); diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh index 1b70c0a304ce..f295a371ff14 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh @@ -1,6 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/mptcp_lib.sh" + ret=0 sin="" sout="" @@ -84,6 +86,9 @@ cleanup() rm -f "$sin" "$sout" } +mptcp_lib_check_mptcp +mptcp_lib_check_kallsyms + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Could not run test without ip tool" @@ -182,9 +187,14 @@ do_transfer() local_addr="0.0.0.0" fi + cmsg="TIMESTAMPNS" + if mptcp_lib_kallsyms_has "mptcp_ioctl$"; then + cmsg+=",TCPINQ" + fi + timeout ${timeout_test} \ ip netns exec ${listener_ns} \ - $mptcp_connect -t ${timeout_poll} -l -M 1 -p $port -s ${srv_proto} -c TIMESTAMPNS,TCPINQ \ + $mptcp_connect -t ${timeout_poll} -l -M 1 -p $port -s ${srv_proto} -c "${cmsg}" \ ${local_addr} < "$sin" > "$sout" & local spid=$! @@ -192,7 +202,7 @@ do_transfer() timeout ${timeout_test} \ ip netns exec ${connector_ns} \ - $mptcp_connect -t ${timeout_poll} -M 2 -p $port -s ${cl_proto} -c TIMESTAMPNS,TCPINQ \ + $mptcp_connect -t ${timeout_poll} -M 2 -p $port -s ${cl_proto} -c "${cmsg}" \ $connect_addr < "$cin" > "$cout" & local cpid=$! @@ -249,6 +259,11 @@ do_mptcp_sockopt_tests() { local lret=0 + if ! mptcp_lib_kallsyms_has "mptcp_diag_fill_info$"; then + echo "INFO: MPTCP sockopt not supported: SKIP" + return + fi + ip netns exec "$ns_sbox" ./mptcp_sockopt lret=$? @@ -303,6 +318,11 @@ do_tcpinq_tests() { local lret=0 + if ! mptcp_lib_kallsyms_has "mptcp_ioctl$"; then + echo "INFO: TCP_INQ not supported: SKIP" + return + fi + local args for args in "-t tcp" "-r tcp"; do do_tcpinq_test $args diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh index 89839d1ff9d8..d02e0d63a8f9 100755 --- a/tools/testing/selftests/net/mptcp/pm_netlink.sh +++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh @@ -1,6 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/mptcp_lib.sh" + ksft_skip=4 ret=0 @@ -34,6 +36,8 @@ cleanup() ip netns del $ns1 } +mptcp_lib_check_mptcp + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Could not run test without ip tool" @@ -69,8 +73,12 @@ check() } check "ip netns exec $ns1 ./pm_nl_ctl dump" "" "defaults addr list" -check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 0 + +default_limits="$(ip netns exec $ns1 ./pm_nl_ctl limits)" +if mptcp_lib_expect_all_features; then + check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 0 subflows 2" "defaults limits" +fi ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.1 ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.2 flags subflow dev lo @@ -117,12 +125,10 @@ ip netns exec $ns1 ./pm_nl_ctl flush check "ip netns exec $ns1 ./pm_nl_ctl dump" "" "flush addrs" ip netns exec $ns1 ./pm_nl_ctl limits 9 1 -check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 0 -subflows 2" "rcv addrs above hard limit" +check "ip netns exec $ns1 ./pm_nl_ctl limits" "$default_limits" "rcv addrs above hard limit" ip netns exec $ns1 ./pm_nl_ctl limits 1 9 -check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 0 -subflows 2" "subflows above hard limit" +check "ip netns exec $ns1 ./pm_nl_ctl limits" "$default_limits" "subflows above hard limit" ip netns exec $ns1 ./pm_nl_ctl limits 8 8 check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 8 @@ -172,14 +178,19 @@ subflow,backup 10.0.1.1" "set flags (backup)" ip netns exec $ns1 ./pm_nl_ctl set 10.0.1.1 flags nobackup check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ subflow 10.0.1.1" " (nobackup)" + +# fullmesh support has been added later ip netns exec $ns1 ./pm_nl_ctl set id 1 flags fullmesh -check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ +if ip netns exec $ns1 ./pm_nl_ctl dump | grep -q "fullmesh" || + mptcp_lib_expect_all_features; then + check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ subflow,fullmesh 10.0.1.1" " (fullmesh)" -ip netns exec $ns1 ./pm_nl_ctl set id 1 flags nofullmesh -check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ + ip netns exec $ns1 ./pm_nl_ctl set id 1 flags nofullmesh + check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ subflow 10.0.1.1" " (nofullmesh)" -ip netns exec $ns1 ./pm_nl_ctl set id 1 flags backup,fullmesh -check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ + ip netns exec $ns1 ./pm_nl_ctl set id 1 flags backup,fullmesh + check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ subflow,backup,fullmesh 10.0.1.1" " (backup,fullmesh)" +fi exit $ret diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh index 9f22f7e5027d..36a3c9d92e20 100755 --- a/tools/testing/selftests/net/mptcp/simult_flows.sh +++ b/tools/testing/selftests/net/mptcp/simult_flows.sh @@ -1,6 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/mptcp_lib.sh" + sec=$(date +%s) rndh=$(printf %x $sec)-$(mktemp -u XXXXXX) ns1="ns1-$rndh" @@ -34,6 +36,8 @@ cleanup() done } +mptcp_lib_check_mptcp + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Could not run test without ip tool" diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh index b1eb7bce599d..98d9e4d2d3fc 100755 --- a/tools/testing/selftests/net/mptcp/userspace_pm.sh +++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh @@ -1,10 +1,20 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/mptcp_lib.sh" + +mptcp_lib_check_mptcp +mptcp_lib_check_kallsyms + +if ! mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then + echo "userspace pm tests are not supported by the kernel: SKIP" + exit ${KSFT_SKIP} +fi + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Cannot not run test without ip tool" - exit 1 + exit ${KSFT_SKIP} fi ANNOUNCED=6 # MPTCP_EVENT_ANNOUNCED @@ -905,6 +915,11 @@ test_listener() { print_title "Listener tests" + if ! mptcp_lib_kallsyms_has "mptcp_event_pm_listener$"; then + stdbuf -o0 -e0 printf "LISTENER events \t[SKIP] Not supported\n" + return + fi + # Capture events on the network namespace running the client :>$client_evts diff --git a/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh index 1003119773e5..f96282362811 100755 --- a/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh +++ b/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh @@ -232,10 +232,14 @@ setup_rt_networking() local nsname=rt-${rt} ip netns add ${nsname} + + ip netns exec ${nsname} sysctl -wq net.ipv6.conf.all.accept_dad=0 + ip netns exec ${nsname} sysctl -wq net.ipv6.conf.default.accept_dad=0 + ip link set veth-rt-${rt} netns ${nsname} ip -netns ${nsname} link set veth-rt-${rt} name veth0 - ip -netns ${nsname} addr add ${IPv6_RT_NETWORK}::${rt}/64 dev veth0 + ip -netns ${nsname} addr add ${IPv6_RT_NETWORK}::${rt}/64 dev veth0 nodad ip -netns ${nsname} link set veth0 up ip -netns ${nsname} link set lo up @@ -254,6 +258,12 @@ setup_hs() # set the networking for the host ip netns add ${hsname} + + # disable the rp_filter otherwise the kernel gets confused about how + # to route decap ipv4 packets. + ip netns exec ${rtname} sysctl -wq net.ipv4.conf.all.rp_filter=0 + ip netns exec ${rtname} sysctl -wq net.ipv4.conf.default.rp_filter=0 + ip -netns ${hsname} link add veth0 type veth peer name ${rtveth} ip -netns ${hsname} link set ${rtveth} netns ${rtname} ip -netns ${hsname} addr add ${IPv4_HS_NETWORK}.${hs}/24 dev veth0 @@ -272,11 +282,6 @@ setup_hs() ip netns exec ${rtname} sysctl -wq net.ipv4.conf.${rtveth}.proxy_arp=1 - # disable the rp_filter otherwise the kernel gets confused about how - # to route decap ipv4 packets. - ip netns exec ${rtname} sysctl -wq net.ipv4.conf.all.rp_filter=0 - ip netns exec ${rtname} sysctl -wq net.ipv4.conf.${rtveth}.rp_filter=0 - ip netns exec ${rtname} sh -c "echo 1 > /proc/sys/net/vrf/strict_mode" } diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index e699548d4247..ff36844d14b4 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -25,6 +25,8 @@ #define TLS_PAYLOAD_MAX_LEN 16384 #define SOL_TLS 282 +static int fips_enabled; + struct tls_crypto_info_keys { union { struct tls12_crypto_info_aes_gcm_128 aes128; @@ -235,7 +237,7 @@ FIXTURE_VARIANT(tls) { uint16_t tls_version; uint16_t cipher_type; - bool nopad; + bool nopad, fips_non_compliant; }; FIXTURE_VARIANT_ADD(tls, 12_aes_gcm) @@ -254,24 +256,28 @@ FIXTURE_VARIANT_ADD(tls, 12_chacha) { .tls_version = TLS_1_2_VERSION, .cipher_type = TLS_CIPHER_CHACHA20_POLY1305, + .fips_non_compliant = true, }; FIXTURE_VARIANT_ADD(tls, 13_chacha) { .tls_version = TLS_1_3_VERSION, .cipher_type = TLS_CIPHER_CHACHA20_POLY1305, + .fips_non_compliant = true, }; FIXTURE_VARIANT_ADD(tls, 13_sm4_gcm) { .tls_version = TLS_1_3_VERSION, .cipher_type = TLS_CIPHER_SM4_GCM, + .fips_non_compliant = true, }; FIXTURE_VARIANT_ADD(tls, 13_sm4_ccm) { .tls_version = TLS_1_3_VERSION, .cipher_type = TLS_CIPHER_SM4_CCM, + .fips_non_compliant = true, }; FIXTURE_VARIANT_ADD(tls, 12_aes_ccm) @@ -311,6 +317,9 @@ FIXTURE_SETUP(tls) int one = 1; int ret; + if (fips_enabled && variant->fips_non_compliant) + SKIP(return, "Unsupported cipher in FIPS mode"); + tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12); @@ -1865,4 +1874,17 @@ TEST(prequeue) { close(cfd); } +static void __attribute__((constructor)) fips_check(void) { + int res; + FILE *f; + + f = fopen("/proc/sys/crypto/fips_enabled", "r"); + if (f) { + res = fscanf(f, "%d", &fips_enabled); + if (res != 1) + ksft_print_msg("ERROR: Couldn't read /proc/sys/crypto/fips_enabled\n"); + fclose(f); + } +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/net/vrf-xfrm-tests.sh b/tools/testing/selftests/net/vrf-xfrm-tests.sh index 184da81f554f..452638ae8aed 100755 --- a/tools/testing/selftests/net/vrf-xfrm-tests.sh +++ b/tools/testing/selftests/net/vrf-xfrm-tests.sh @@ -264,60 +264,60 @@ setup_xfrm() ip -netns host1 xfrm state add src ${HOST1_4} dst ${HOST2_4} \ proto esp spi ${SPI_1} reqid 0 mode tunnel \ replay-window 4 replay-oseq 0x4 \ - auth-trunc 'hmac(md5)' ${AUTH_1} 96 \ - enc 'cbc(des3_ede)' ${ENC_1} \ + auth-trunc 'hmac(sha1)' ${AUTH_1} 96 \ + enc 'cbc(aes)' ${ENC_1} \ sel src ${h1_4} dst ${h2_4} ${devarg} ip -netns host2 xfrm state add src ${HOST1_4} dst ${HOST2_4} \ proto esp spi ${SPI_1} reqid 0 mode tunnel \ replay-window 4 replay-oseq 0x4 \ - auth-trunc 'hmac(md5)' ${AUTH_1} 96 \ - enc 'cbc(des3_ede)' ${ENC_1} \ + auth-trunc 'hmac(sha1)' ${AUTH_1} 96 \ + enc 'cbc(aes)' ${ENC_1} \ sel src ${h1_4} dst ${h2_4} ip -netns host1 xfrm state add src ${HOST2_4} dst ${HOST1_4} \ proto esp spi ${SPI_2} reqid 0 mode tunnel \ replay-window 4 replay-oseq 0x4 \ - auth-trunc 'hmac(md5)' ${AUTH_2} 96 \ - enc 'cbc(des3_ede)' ${ENC_2} \ + auth-trunc 'hmac(sha1)' ${AUTH_2} 96 \ + enc 'cbc(aes)' ${ENC_2} \ sel src ${h2_4} dst ${h1_4} ${devarg} ip -netns host2 xfrm state add src ${HOST2_4} dst ${HOST1_4} \ proto esp spi ${SPI_2} reqid 0 mode tunnel \ replay-window 4 replay-oseq 0x4 \ - auth-trunc 'hmac(md5)' ${AUTH_2} 96 \ - enc 'cbc(des3_ede)' ${ENC_2} \ + auth-trunc 'hmac(sha1)' ${AUTH_2} 96 \ + enc 'cbc(aes)' ${ENC_2} \ sel src ${h2_4} dst ${h1_4} ip -6 -netns host1 xfrm state add src ${HOST1_6} dst ${HOST2_6} \ proto esp spi ${SPI_1} reqid 0 mode tunnel \ replay-window 4 replay-oseq 0x4 \ - auth-trunc 'hmac(md5)' ${AUTH_1} 96 \ - enc 'cbc(des3_ede)' ${ENC_1} \ + auth-trunc 'hmac(sha1)' ${AUTH_1} 96 \ + enc 'cbc(aes)' ${ENC_1} \ sel src ${h1_6} dst ${h2_6} ${devarg} ip -6 -netns host2 xfrm state add src ${HOST1_6} dst ${HOST2_6} \ proto esp spi ${SPI_1} reqid 0 mode tunnel \ replay-window 4 replay-oseq 0x4 \ - auth-trunc 'hmac(md5)' ${AUTH_1} 96 \ - enc 'cbc(des3_ede)' ${ENC_1} \ + auth-trunc 'hmac(sha1)' ${AUTH_1} 96 \ + enc 'cbc(aes)' ${ENC_1} \ sel src ${h1_6} dst ${h2_6} ip -6 -netns host1 xfrm state add src ${HOST2_6} dst ${HOST1_6} \ proto esp spi ${SPI_2} reqid 0 mode tunnel \ replay-window 4 replay-oseq 0x4 \ - auth-trunc 'hmac(md5)' ${AUTH_2} 96 \ - enc 'cbc(des3_ede)' ${ENC_2} \ + auth-trunc 'hmac(sha1)' ${AUTH_2} 96 \ + enc 'cbc(aes)' ${ENC_2} \ sel src ${h2_6} dst ${h1_6} ${devarg} ip -6 -netns host2 xfrm state add src ${HOST2_6} dst ${HOST1_6} \ proto esp spi ${SPI_2} reqid 0 mode tunnel \ replay-window 4 replay-oseq 0x4 \ - auth-trunc 'hmac(md5)' ${AUTH_2} 96 \ - enc 'cbc(des3_ede)' ${ENC_2} \ + auth-trunc 'hmac(sha1)' ${AUTH_2} 96 \ + enc 'cbc(aes)' ${ENC_2} \ sel src ${h2_6} dst ${h1_6} } diff --git a/tools/testing/selftests/nolibc/.gitignore b/tools/testing/selftests/nolibc/.gitignore index 4696df589d68..52f613cdad54 100644 --- a/tools/testing/selftests/nolibc/.gitignore +++ b/tools/testing/selftests/nolibc/.gitignore @@ -1,4 +1,5 @@ /initramfs/ +/libc-test /nolibc-test /run.out /sysroot/ diff --git a/tools/testing/selftests/nolibc/Makefile b/tools/testing/selftests/nolibc/Makefile index bbce57420465..1b7b3c82f8ad 100644 --- a/tools/testing/selftests/nolibc/Makefile +++ b/tools/testing/selftests/nolibc/Makefile @@ -64,7 +64,7 @@ QEMU_ARGS_mips = -M malta -append "panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS_riscv = -M virt -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS_s390 = -M s390-ccw-virtio -m 1G -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS_loongarch = -M virt -append "console=ttyS0,115200 panic=-1 $(TEST:%=NOLIBC_TEST=%)" -QEMU_ARGS = $(QEMU_ARGS_$(ARCH)) +QEMU_ARGS = $(QEMU_ARGS_$(ARCH)) $(QEMU_ARGS_EXTRA) # OUTPUT is only set when run from the main makefile, otherwise # it defaults to this nolibc directory. @@ -76,16 +76,12 @@ else Q=@ endif -CFLAGS_STACKPROTECTOR = -DNOLIBC_STACKPROTECTOR \ - $(call cc-option,-mstack-protector-guard=global) \ - $(call cc-option,-fstack-protector-all) -CFLAGS_STKP_i386 = $(CFLAGS_STACKPROTECTOR) -CFLAGS_STKP_x86_64 = $(CFLAGS_STACKPROTECTOR) -CFLAGS_STKP_x86 = $(CFLAGS_STACKPROTECTOR) CFLAGS_s390 = -m64 -CFLAGS ?= -Os -fno-ident -fno-asynchronous-unwind-tables \ +CFLAGS_mips = -EL +CFLAGS_STACKPROTECTOR ?= $(call cc-option,-mstack-protector-guard=global $(call cc-option,-fstack-protector-all)) +CFLAGS ?= -Os -fno-ident -fno-asynchronous-unwind-tables -std=c89 \ $(call cc-option,-fno-stack-protector) \ - $(CFLAGS_STKP_$(ARCH)) $(CFLAGS_$(ARCH)) + $(CFLAGS_$(ARCH)) $(CFLAGS_STACKPROTECTOR) LDFLAGS := -s help: @@ -94,6 +90,7 @@ help: @echo " help this help" @echo " sysroot create the nolibc sysroot here (uses \$$ARCH)" @echo " nolibc-test build the executable (uses \$$CC and \$$CROSS_COMPILE)" + @echo " libc-test build an executable using the compiler's default libc instead" @echo " run-user runs the executable under QEMU (uses \$$ARCH, \$$TEST)" @echo " initramfs prepare the initramfs with nolibc-test" @echo " defconfig create a fresh new default config (uses \$$ARCH)" @@ -128,10 +125,16 @@ nolibc-test: nolibc-test.c sysroot/$(ARCH)/include $(QUIET_CC)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ \ -nostdlib -static -Isysroot/$(ARCH)/include $< -lgcc +libc-test: nolibc-test.c + $(QUIET_CC)$(CC) -o $@ $< + # qemu user-land test run-user: nolibc-test $(Q)qemu-$(QEMU_ARCH) ./nolibc-test > "$(CURDIR)/run.out" || : - $(Q)grep -w FAIL "$(CURDIR)/run.out" && echo "See all results in $(CURDIR)/run.out" || echo "$$(grep -c ^[0-9].*OK $(CURDIR)/run.out) test(s) passed." + $(Q)awk '/\[OK\][\r]*$$/{p++} /\[FAIL\][\r]*$$/{f++} /\[SKIPPED\][\r]*$$/{s++} \ + END{ printf("%d test(s) passed, %d skipped, %d failed.", p, s, f); \ + if (s+f > 0) printf(" See all results in %s\n", ARGV[1]); else print; }' \ + $(CURDIR)/run.out initramfs: nolibc-test $(QUIET_MKDIR)mkdir -p initramfs @@ -147,18 +150,26 @@ kernel: initramfs # run the tests after building the kernel run: kernel $(Q)qemu-system-$(QEMU_ARCH) -display none -no-reboot -kernel "$(srctree)/$(IMAGE)" -serial stdio $(QEMU_ARGS) > "$(CURDIR)/run.out" - $(Q)grep -w FAIL "$(CURDIR)/run.out" && echo "See all results in $(CURDIR)/run.out" || echo "$$(grep -c ^[0-9].*OK $(CURDIR)/run.out) test(s) passed." + $(Q)awk '/\[OK\][\r]*$$/{p++} /\[FAIL\][\r]*$$/{f++} /\[SKIPPED\][\r]*$$/{s++} \ + END{ printf("%d test(s) passed, %d skipped, %d failed.", p, s, f); \ + if (s+f > 0) printf(" See all results in %s\n", ARGV[1]); else print; }' \ + $(CURDIR)/run.out # re-run the tests from an existing kernel rerun: $(Q)qemu-system-$(QEMU_ARCH) -display none -no-reboot -kernel "$(srctree)/$(IMAGE)" -serial stdio $(QEMU_ARGS) > "$(CURDIR)/run.out" - $(Q)grep -w FAIL "$(CURDIR)/run.out" && echo "See all results in $(CURDIR)/run.out" || echo "$$(grep -c ^[0-9].*OK $(CURDIR)/run.out) test(s) passed." + $(Q)awk '/\[OK\][\r]*$$/{p++} /\[FAIL\][\r]*$$/{f++} /\[SKIPPED\][\r]*$$/{s++} \ + END{ printf("%d test(s) passed, %d skipped, %d failed.", p, s, f); \ + if (s+f > 0) printf(" See all results in %s\n", ARGV[1]); else print; }' \ + $(CURDIR)/run.out clean: $(call QUIET_CLEAN, sysroot) $(Q)rm -rf sysroot $(call QUIET_CLEAN, nolibc-test) $(Q)rm -f nolibc-test + $(call QUIET_CLEAN, libc-test) + $(Q)rm -f libc-test $(call QUIET_CLEAN, initramfs) $(Q)rm -rf initramfs $(call QUIET_CLEAN, run.out) diff --git a/tools/testing/selftests/nolibc/nolibc-test.c b/tools/testing/selftests/nolibc/nolibc-test.c index 21bacc928bf7..486334981e60 100644 --- a/tools/testing/selftests/nolibc/nolibc-test.c +++ b/tools/testing/selftests/nolibc/nolibc-test.c @@ -1,10 +1,7 @@ -// SPDX-License-Identifier: GPL-2.0 +/* SPDX-License-Identifier: GPL-2.0 */ #define _GNU_SOURCE -/* platform-specific include files coming from the compiler */ -#include <limits.h> - /* libc-specific include files * The program may be built in 3 ways: * $(CC) -nostdlib -include /path/to/nolibc.h => NOLIBC already defined @@ -20,7 +17,9 @@ #include <linux/reboot.h> #include <sys/io.h> #include <sys/ioctl.h> +#include <sys/mman.h> #include <sys/mount.h> +#include <sys/prctl.h> #include <sys/reboot.h> #include <sys/stat.h> #include <sys/syscall.h> @@ -34,7 +33,10 @@ #include <sched.h> #include <signal.h> #include <stdarg.h> +#include <stddef.h> +#include <stdint.h> #include <unistd.h> +#include <limits.h> #endif #endif @@ -43,8 +45,8 @@ char **environ; /* definition of a series of tests */ struct test { - const char *name; // test name - int (*func)(int min, int max); // handler + const char *name; /* test name */ + int (*func)(int min, int max); /* handler */ }; #ifndef _NOLIBC_STDLIB_H @@ -103,24 +105,32 @@ const char *errorname(int err) CASE_ERR(EDOM); CASE_ERR(ERANGE); CASE_ERR(ENOSYS); + CASE_ERR(EOVERFLOW); default: return itoa(err); } } +static void putcharn(char c, size_t n) +{ + char buf[64]; + + memset(buf, c, n); + buf[n] = '\0'; + fputs(buf, stdout); +} + static int pad_spc(int llen, int cnt, const char *fmt, ...) { va_list args; - int len; int ret; - for (len = 0; len < cnt - llen; len++) - putchar(' '); + putcharn(' ', cnt - llen); va_start(args, fmt); ret = vfprintf(stdout, fmt, args); va_end(args); - return ret < 0 ? ret : ret + len; + return ret < 0 ? ret : ret + cnt - llen; } /* The tests below are intended to be used by the macroes, which evaluate @@ -162,7 +172,7 @@ static int expect_eq(uint64_t expr, int llen, uint64_t val) { int ret = !(expr == val); - llen += printf(" = %lld ", expr); + llen += printf(" = %lld ", (long long)expr); pad_spc(llen, 64, ret ? "[FAIL]\n" : " [OK]\n"); return ret; } @@ -290,18 +300,24 @@ static int expect_sysne(int expr, int llen, int val) } +#define EXPECT_SYSER2(cond, expr, expret, experr1, experr2) \ + do { if (!cond) pad_spc(llen, 64, "[SKIPPED]\n"); else ret += expect_syserr2(expr, expret, experr1, experr2, llen); } while (0) + #define EXPECT_SYSER(cond, expr, expret, experr) \ - do { if (!cond) pad_spc(llen, 64, "[SKIPPED]\n"); else ret += expect_syserr(expr, expret, experr, llen); } while (0) + EXPECT_SYSER2(cond, expr, expret, experr, 0) -static int expect_syserr(int expr, int expret, int experr, int llen) +static int expect_syserr2(int expr, int expret, int experr1, int experr2, int llen) { int ret = 0; int _errno = errno; llen += printf(" = %d %s ", expr, errorname(_errno)); - if (expr != expret || _errno != experr) { + if (expr != expret || (_errno != experr1 && _errno != experr2)) { ret = 1; - llen += printf(" != (%d %s) ", expret, errorname(experr)); + if (experr2 == 0) + llen += printf(" != (%d %s) ", expret, errorname(experr1)); + else + llen += printf(" != (%d %s %s) ", expret, errorname(experr1), errorname(experr2)); llen += pad_spc(llen, 64, "[FAIL]\n"); } else { llen += pad_spc(llen, 64, " [OK]\n"); @@ -471,11 +487,60 @@ static int test_getpagesize(void) return !c; } +static int test_fork(void) +{ + int status; + pid_t pid; + + /* flush the printf buffer to avoid child flush it */ + fflush(stdout); + fflush(stderr); + + pid = fork(); + + switch (pid) { + case -1: + return 1; + + case 0: + exit(123); + + default: + pid = waitpid(pid, &status, 0); + + return pid == -1 || !WIFEXITED(status) || WEXITSTATUS(status) != 123; + } +} + +static int test_stat_timestamps(void) +{ + struct stat st; + + if (sizeof(st.st_atim.tv_sec) != sizeof(st.st_atime)) + return 1; + + if (stat("/proc/self/", &st)) + return 1; + + if (st.st_atim.tv_sec != st.st_atime || st.st_atim.tv_nsec > 1000000000) + return 1; + + if (st.st_mtim.tv_sec != st.st_mtime || st.st_mtim.tv_nsec > 1000000000) + return 1; + + if (st.st_ctim.tv_sec != st.st_ctime || st.st_ctim.tv_nsec > 1000000000) + return 1; + + return 0; +} + /* Run syscall tests between IDs <min> and <max>. * Return 0 on success, non-zero on failure. */ int run_syscall(int min, int max) { + struct timeval tv; + struct timezone tz; struct stat stat_buf; int euid0; int proc; @@ -491,7 +556,7 @@ int run_syscall(int min, int max) euid0 = geteuid() == 0; for (test = min; test >= 0 && test <= max; test++) { - int llen = 0; // line length + int llen = 0; /* line length */ /* avoid leaving empty lines below, this will insert holes into * test numbers. @@ -527,14 +592,11 @@ int run_syscall(int min, int max) CASE_TEST(dup3_0); tmp = dup3(0, 100, 0); EXPECT_SYSNE(1, tmp, -1); close(tmp); break; CASE_TEST(dup3_m1); tmp = dup3(-1, 100, 0); EXPECT_SYSER(1, tmp, -1, EBADF); if (tmp != -1) close(tmp); break; CASE_TEST(execve_root); EXPECT_SYSER(1, execve("/", (char*[]){ [0] = "/", [1] = NULL }, NULL), -1, EACCES); break; + CASE_TEST(fork); EXPECT_SYSZR(1, test_fork()); break; CASE_TEST(getdents64_root); EXPECT_SYSNE(1, test_getdents64("/"), -1); break; CASE_TEST(getdents64_null); EXPECT_SYSER(1, test_getdents64("/dev/null"), -1, ENOTDIR); break; - CASE_TEST(gettimeofday_null); EXPECT_SYSZR(1, gettimeofday(NULL, NULL)); break; -#ifdef NOLIBC - CASE_TEST(gettimeofday_bad1); EXPECT_SYSER(1, gettimeofday((void *)1, NULL), -1, EFAULT); break; - CASE_TEST(gettimeofday_bad2); EXPECT_SYSER(1, gettimeofday(NULL, (void *)1), -1, EFAULT); break; - CASE_TEST(gettimeofday_bad2); EXPECT_SYSER(1, gettimeofday(NULL, (void *)1), -1, EFAULT); break; -#endif + CASE_TEST(gettimeofday_tv); EXPECT_SYSZR(1, gettimeofday(&tv, NULL)); break; + CASE_TEST(gettimeofday_tv_tz);EXPECT_SYSZR(1, gettimeofday(&tv, &tz)); break; CASE_TEST(getpagesize); EXPECT_SYSZR(1, test_getpagesize()); break; CASE_TEST(ioctl_tiocinq); EXPECT_SYSZR(1, ioctl(0, TIOCINQ, &tmp)); break; CASE_TEST(ioctl_tiocinq); EXPECT_SYSZR(1, ioctl(0, TIOCINQ, &tmp)); break; @@ -550,6 +612,7 @@ int run_syscall(int min, int max) CASE_TEST(poll_null); EXPECT_SYSZR(1, poll(NULL, 0, 0)); break; CASE_TEST(poll_stdout); EXPECT_SYSNE(1, ({ struct pollfd fds = { 1, POLLOUT, 0}; poll(&fds, 1, 0); }), -1); break; CASE_TEST(poll_fault); EXPECT_SYSER(1, poll((void *)1, 1, 0), -1, EFAULT); break; + CASE_TEST(prctl); EXPECT_SYSER(1, prctl(PR_SET_NAME, (unsigned long)NULL, 0, 0, 0), -1, EFAULT); break; CASE_TEST(read_badf); EXPECT_SYSER(1, read(-1, &tmp, 1), -1, EBADF); break; CASE_TEST(sched_yield); EXPECT_SYSZR(1, sched_yield()); break; CASE_TEST(select_null); EXPECT_SYSZR(1, ({ struct timeval tv = { 0 }; select(0, NULL, NULL, NULL, &tv); })); break; @@ -557,6 +620,7 @@ int run_syscall(int min, int max) CASE_TEST(select_fault); EXPECT_SYSER(1, select(1, (void *)1, NULL, NULL, 0), -1, EFAULT); break; CASE_TEST(stat_blah); EXPECT_SYSER(1, stat("/proc/self/blah", &stat_buf), -1, ENOENT); break; CASE_TEST(stat_fault); EXPECT_SYSER(1, stat(NULL, &stat_buf), -1, EFAULT); break; + CASE_TEST(stat_timestamps); EXPECT_SYSZR(1, test_stat_timestamps()); break; CASE_TEST(symlink_root); EXPECT_SYSER(1, symlink("/", "/"), -1, EEXIST); break; CASE_TEST(unlink_root); EXPECT_SYSER(1, unlink("/"), -1, EISDIR); break; CASE_TEST(unlink_blah); EXPECT_SYSER(1, unlink("/proc/self/blah"), -1, ENOENT); break; @@ -565,6 +629,8 @@ int run_syscall(int min, int max) CASE_TEST(waitpid_child); EXPECT_SYSER(1, waitpid(getpid(), &tmp, WNOHANG), -1, ECHILD); break; CASE_TEST(write_badf); EXPECT_SYSER(1, write(-1, &tmp, 1), -1, EBADF); break; CASE_TEST(write_zero); EXPECT_SYSZR(1, write(1, &tmp, 0)); break; + CASE_TEST(syscall_noargs); EXPECT_SYSEQ(1, syscall(__NR_getpid), getpid()); break; + CASE_TEST(syscall_args); EXPECT_SYSER(1, syscall(__NR_statx, 0, NULL, 0, 0, NULL), -1, EFAULT); break; case __LINE__: return ret; /* must be last */ /* note: do not set any defaults so as to permit holes above */ @@ -581,7 +647,7 @@ int run_stdlib(int min, int max) void *p1, *p2; for (test = min; test >= 0 && test <= max; test++) { - int llen = 0; // line length + int llen = 0; /* line length */ /* avoid leaving empty lines below, this will insert holes into * test numbers. @@ -639,9 +705,9 @@ int run_stdlib(int min, int max) CASE_TEST(limit_int_fast32_min); EXPECT_EQ(1, INT_FAST32_MIN, (int_fast32_t) INTPTR_MIN); break; CASE_TEST(limit_int_fast32_max); EXPECT_EQ(1, INT_FAST32_MAX, (int_fast32_t) INTPTR_MAX); break; CASE_TEST(limit_uint_fast32_max); EXPECT_EQ(1, UINT_FAST32_MAX, (uint_fast32_t) UINTPTR_MAX); break; - CASE_TEST(limit_int_fast64_min); EXPECT_EQ(1, INT_FAST64_MIN, (int_fast64_t) INTPTR_MIN); break; - CASE_TEST(limit_int_fast64_max); EXPECT_EQ(1, INT_FAST64_MAX, (int_fast64_t) INTPTR_MAX); break; - CASE_TEST(limit_uint_fast64_max); EXPECT_EQ(1, UINT_FAST64_MAX, (uint_fast64_t) UINTPTR_MAX); break; + CASE_TEST(limit_int_fast64_min); EXPECT_EQ(1, INT_FAST64_MIN, (int_fast64_t) INT64_MIN); break; + CASE_TEST(limit_int_fast64_max); EXPECT_EQ(1, INT_FAST64_MAX, (int_fast64_t) INT64_MAX); break; + CASE_TEST(limit_uint_fast64_max); EXPECT_EQ(1, UINT_FAST64_MAX, (uint_fast64_t) UINT64_MAX); break; #if __SIZEOF_LONG__ == 8 CASE_TEST(limit_intptr_min); EXPECT_EQ(1, INTPTR_MIN, (intptr_t) 0x8000000000000000LL); break; CASE_TEST(limit_intptr_max); EXPECT_EQ(1, INTPTR_MAX, (intptr_t) 0x7fffffffffffffffLL); break; @@ -667,17 +733,98 @@ int run_stdlib(int min, int max) return ret; } -#if defined(__clang__) -__attribute__((optnone)) -#elif defined(__GNUC__) -__attribute__((optimize("O0"))) -#endif +#define EXPECT_VFPRINTF(c, expected, fmt, ...) \ + ret += expect_vfprintf(llen, c, expected, fmt, ##__VA_ARGS__) + +static int expect_vfprintf(int llen, size_t c, const char *expected, const char *fmt, ...) +{ + int ret, fd, w, r; + char buf[100]; + FILE *memfile; + va_list args; + + fd = memfd_create("vfprintf", 0); + if (fd == -1) { + pad_spc(llen, 64, "[FAIL]\n"); + return 1; + } + + memfile = fdopen(fd, "w+"); + if (!memfile) { + pad_spc(llen, 64, "[FAIL]\n"); + return 1; + } + + va_start(args, fmt); + w = vfprintf(memfile, fmt, args); + va_end(args); + + if (w != c) { + llen += printf(" written(%d) != %d", w, (int) c); + pad_spc(llen, 64, "[FAIL]\n"); + return 1; + } + + fflush(memfile); + lseek(fd, 0, SEEK_SET); + + r = read(fd, buf, sizeof(buf) - 1); + buf[r] = '\0'; + + fclose(memfile); + + if (r != w) { + llen += printf(" written(%d) != read(%d)", w, r); + pad_spc(llen, 64, "[FAIL]\n"); + return 1; + } + + llen += printf(" \"%s\" = \"%s\"", expected, buf); + ret = strncmp(expected, buf, c); + + pad_spc(llen, 64, ret ? "[FAIL]\n" : " [OK]\n"); + return ret; +} + +static int run_vfprintf(int min, int max) +{ + int test; + int tmp; + int ret = 0; + void *p1, *p2; + + for (test = min; test >= 0 && test <= max; test++) { + int llen = 0; /* line length */ + + /* avoid leaving empty lines below, this will insert holes into + * test numbers. + */ + switch (test + __LINE__ + 1) { + CASE_TEST(empty); EXPECT_VFPRINTF(0, "", ""); break; + CASE_TEST(simple); EXPECT_VFPRINTF(3, "foo", "foo"); break; + CASE_TEST(string); EXPECT_VFPRINTF(3, "foo", "%s", "foo"); break; + CASE_TEST(number); EXPECT_VFPRINTF(4, "1234", "%d", 1234); break; + CASE_TEST(negnumber); EXPECT_VFPRINTF(5, "-1234", "%d", -1234); break; + CASE_TEST(unsigned); EXPECT_VFPRINTF(5, "12345", "%u", 12345); break; + CASE_TEST(char); EXPECT_VFPRINTF(1, "c", "%c", 'c'); break; + CASE_TEST(hex); EXPECT_VFPRINTF(1, "f", "%x", 0xf); break; + CASE_TEST(pointer); EXPECT_VFPRINTF(3, "0x1", "%p", (void *) 0x1); break; + case __LINE__: + return ret; /* must be last */ + /* note: do not set any defaults so as to permit holes above */ + } + } + return ret; +} + static int smash_stack(void) { char buf[100]; + volatile char *ptr = buf; + size_t i; - for (size_t i = 0; i < 200; i++) - buf[i] = 'P'; + for (i = 0; i < 200; i++) + ptr[i] = 'P'; return 1; } @@ -689,12 +836,20 @@ static int run_protection(int min, int max) llen += printf("0 -fstackprotector "); -#if !defined(NOLIBC_STACKPROTECTOR) +#if !defined(_NOLIBC_STACKPROTECTOR) llen += printf("not supported"); pad_spc(llen, 64, "[SKIPPED]\n"); return 0; #endif +#if defined(_NOLIBC_STACKPROTECTOR) + if (!__stack_chk_guard) { + llen += printf("__stack_chk_guard not initialized"); + pad_spc(llen, 64, "[FAIL]\n"); + return 1; + } +#endif + pid = -1; pid = fork(); @@ -708,6 +863,7 @@ static int run_protection(int min, int max) close(STDOUT_FILENO); close(STDERR_FILENO); + prctl(PR_SET_DUMPABLE, 0, 0, 0, 0); smash_stack(); return 1; @@ -778,6 +934,7 @@ static const struct test test_names[] = { /* add new tests here */ { .name = "syscall", .func = run_syscall }, { .name = "stdlib", .func = run_stdlib }, + { .name = "vfprintf", .func = run_vfprintf }, { .name = "protection", .func = run_protection }, { 0 } }; @@ -785,7 +942,7 @@ static const struct test test_names[] = { int main(int argc, char **argv, char **envp) { int min = 0; - int max = __INT_MAX__; + int max = INT_MAX; int ret = 0; int err; int idx; @@ -833,7 +990,7 @@ int main(int argc, char **argv, char **envp) * here, which defaults to the full range. */ do { - min = 0; max = __INT_MAX__; + min = 0; max = INT_MAX; value = colon; if (value && *value) { colon = strchr(value, ':'); @@ -899,7 +1056,7 @@ int main(int argc, char **argv, char **envp) #else else if (ioperm(0x501, 1, 1) == 0) #endif - asm volatile ("outb %%al, %%dx" :: "d"(0x501), "a"(0)); + __asm__ volatile ("outb %%al, %%dx" :: "d"(0x501), "a"(0)); /* if it does nothing, fall back to the regular panic */ #endif } diff --git a/tools/testing/selftests/pidfd/pidfd.h b/tools/testing/selftests/pidfd/pidfd.h index 6922d6417e1c..88d6830ee004 100644 --- a/tools/testing/selftests/pidfd/pidfd.h +++ b/tools/testing/selftests/pidfd/pidfd.h @@ -90,7 +90,6 @@ again: } ret = WEXITSTATUS(status); - ksft_print_msg("waitpid WEXITSTATUS=%d\n", ret); return ret; } diff --git a/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c b/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c index 3fd8e903118f..4e86f927880c 100644 --- a/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c +++ b/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c @@ -143,6 +143,7 @@ static inline int child_join(struct child *child, struct error *err) r = -1; } + ksft_print_msg("waitpid WEXITSTATUS=%d\n", r); return r; } diff --git a/tools/testing/selftests/pidfd/pidfd_test.c b/tools/testing/selftests/pidfd/pidfd_test.c index e2dd4ed84984..00a07e7c571c 100644 --- a/tools/testing/selftests/pidfd/pidfd_test.c +++ b/tools/testing/selftests/pidfd/pidfd_test.c @@ -115,7 +115,8 @@ static int test_pidfd_send_signal_exited_fail(void) pidfd = open(buf, O_DIRECTORY | O_CLOEXEC); - (void)wait_for_pid(pid); + ret = wait_for_pid(pid); + ksft_print_msg("waitpid WEXITSTATUS=%d\n", ret); if (pidfd < 0) ksft_exit_fail_msg( diff --git a/tools/testing/selftests/prctl/set-anon-vma-name-test.c b/tools/testing/selftests/prctl/set-anon-vma-name-test.c index 26d853c5a0c1..4275cb256dce 100644 --- a/tools/testing/selftests/prctl/set-anon-vma-name-test.c +++ b/tools/testing/selftests/prctl/set-anon-vma-name-test.c @@ -97,7 +97,7 @@ TEST_F(vma, renaming) { TH_LOG("Try to pass invalid name (with non-printable character \\1) to rename the VMA"); EXPECT_EQ(rename_vma((unsigned long)self->ptr_anon, AREA_SIZE, BAD_NAME), -EINVAL); - TH_LOG("Try to rename non-anonynous VMA"); + TH_LOG("Try to rename non-anonymous VMA"); EXPECT_EQ(rename_vma((unsigned long) self->ptr_not_anon, AREA_SIZE, GOOD_NAME), -EINVAL); } diff --git a/tools/testing/selftests/ptp/testptp.c b/tools/testing/selftests/ptp/testptp.c index 198ad5f32187..cfa9562f3cd8 100644 --- a/tools/testing/selftests/ptp/testptp.c +++ b/tools/testing/selftests/ptp/testptp.c @@ -502,11 +502,11 @@ int main(int argc, char *argv[]) interval = t2 - t1; offset = (t2 + t1) / 2 - tp; - printf("system time: %lld.%u\n", + printf("system time: %lld.%09u\n", (pct+2*i)->sec, (pct+2*i)->nsec); - printf("phc time: %lld.%u\n", + printf("phc time: %lld.%09u\n", (pct+2*i+1)->sec, (pct+2*i+1)->nsec); - printf("system time: %lld.%u\n", + printf("system time: %lld.%09u\n", (pct+2*i+2)->sec, (pct+2*i+2)->nsec); printf("system/phc clock time offset is %" PRId64 " ns\n" "system clock time delay is %" PRId64 " ns\n", diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh index b52d5069563c..48b9147e8c91 100644 --- a/tools/testing/selftests/rcutorture/bin/functions.sh +++ b/tools/testing/selftests/rcutorture/bin/functions.sh @@ -250,7 +250,7 @@ identify_qemu_args () { echo -machine virt,gic-version=host -cpu host ;; qemu-system-ppc64) - echo -enable-kvm -M pseries -nodefaults + echo -M pseries -nodefaults echo -device spapr-vscsi if test -n "$TORTURE_QEMU_INTERACTIVE" -a -n "$TORTURE_QEMU_MAC" then diff --git a/tools/testing/selftests/rcutorture/configs/rcu/BUSTED-BOOST.boot b/tools/testing/selftests/rcutorture/configs/rcu/BUSTED-BOOST.boot index f57720c52c0f..84f6bb98ce99 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/BUSTED-BOOST.boot +++ b/tools/testing/selftests/rcutorture/configs/rcu/BUSTED-BOOST.boot @@ -5,4 +5,4 @@ rcutree.gp_init_delay=3 rcutree.gp_cleanup_delay=3 rcutree.kthread_prio=2 threadirqs -tree.use_softirq=0 +rcutree.use_softirq=0 diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot index 64f864f1f361..8e50bfd4b710 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot @@ -4,4 +4,4 @@ rcutree.gp_init_delay=3 rcutree.gp_cleanup_delay=3 rcutree.kthread_prio=2 threadirqs -tree.use_softirq=0 +rcutree.use_softirq=0 diff --git a/tools/testing/selftests/run_kselftest.sh b/tools/testing/selftests/run_kselftest.sh index 97165a83df63..92743980e553 100755 --- a/tools/testing/selftests/run_kselftest.sh +++ b/tools/testing/selftests/run_kselftest.sh @@ -26,6 +26,7 @@ Usage: $0 [OPTIONS] -l | --list List the available collection:test entries -d | --dry-run Don't actually run any tests -h | --help Show this usage info + -o | --override-timeout Number of seconds after which we timeout EOF exit $1 } @@ -33,6 +34,7 @@ EOF COLLECTIONS="" TESTS="" dryrun="" +kselftest_override_timeout="" while true; do case "$1" in -s | --summary) @@ -51,6 +53,9 @@ while true; do -d | --dry-run) dryrun="echo" shift ;; + -o | --override-timeout) + kselftest_override_timeout="$2" + shift 2 ;; -h | --help) usage 0 ;; "") @@ -85,7 +90,7 @@ if [ -n "$TESTS" ]; then available="$(echo "$valid" | sed -e 's/ /\n/g')" fi -collections=$(echo "$available" | cut -d: -f1 | uniq) +collections=$(echo "$available" | cut -d: -f1 | sort | uniq) for collection in $collections ; do [ -w /dev/kmsg ] && echo "kselftest: Running tests in $collection" >> /dev/kmsg tests=$(echo "$available" | grep "^$collection:" | cut -d: -f2) diff --git a/tools/testing/selftests/sgx/Makefile b/tools/testing/selftests/sgx/Makefile index 75af864e07b6..50aab6b57da3 100644 --- a/tools/testing/selftests/sgx/Makefile +++ b/tools/testing/selftests/sgx/Makefile @@ -17,6 +17,7 @@ ENCL_CFLAGS := -Wall -Werror -static -nostdlib -nostartfiles -fPIC \ -fno-stack-protector -mrdrnd $(INCLUDES) TEST_CUSTOM_PROGS := $(OUTPUT)/test_sgx +TEST_FILES := $(OUTPUT)/test_encl.elf ifeq ($(CAN_BUILD_X86_64), 1) all: $(TEST_CUSTOM_PROGS) $(OUTPUT)/test_encl.elf diff --git a/tools/testing/selftests/tc-testing/config b/tools/testing/selftests/tc-testing/config index 4638c63a339f..6e73b09c20c8 100644 --- a/tools/testing/selftests/tc-testing/config +++ b/tools/testing/selftests/tc-testing/config @@ -6,20 +6,18 @@ CONFIG_NF_CONNTRACK_MARK=y CONFIG_NF_CONNTRACK_ZONES=y CONFIG_NF_CONNTRACK_LABELS=y CONFIG_NF_NAT=m +CONFIG_NETFILTER_XT_TARGET_LOG=m CONFIG_NET_SCHED=y # # Queueing/Scheduling # -CONFIG_NET_SCH_ATM=m CONFIG_NET_SCH_CAKE=m -CONFIG_NET_SCH_CBQ=m CONFIG_NET_SCH_CBS=m CONFIG_NET_SCH_CHOKE=m CONFIG_NET_SCH_CODEL=m CONFIG_NET_SCH_DRR=m -CONFIG_NET_SCH_DSMARK=m CONFIG_NET_SCH_ETF=m CONFIG_NET_SCH_FQ=m CONFIG_NET_SCH_FQ_CODEL=m @@ -57,8 +55,6 @@ CONFIG_NET_CLS_FLOW=m CONFIG_NET_CLS_FLOWER=m CONFIG_NET_CLS_MATCHALL=m CONFIG_NET_CLS_ROUTE4=m -CONFIG_NET_CLS_RSVP=m -CONFIG_NET_CLS_TCINDEX=m CONFIG_NET_EMATCH=y CONFIG_NET_EMATCH_STACK=32 CONFIG_NET_EMATCH_CMP=m diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfb.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfb.json index ba2f5e79cdbf..e21c7f22c6d4 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfb.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfb.json @@ -58,10 +58,10 @@ "setup": [ "$IP link add dev $DUMMY type dummy || /bin/true" ], - "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root sfb db 10", + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root sfb db 100", "expExitCode": "0", "verifyCmd": "$TC qdisc show dev $DUMMY", - "matchPattern": "qdisc sfb 1: root refcnt [0-9]+ rehash 600s db 10ms", + "matchPattern": "qdisc sfb 1: root refcnt [0-9]+ rehash 600s db 100ms", "matchCount": "1", "teardown": [ "$TC qdisc del dev $DUMMY handle 1: root", diff --git a/tools/testing/selftests/tc-testing/tdc.sh b/tools/testing/selftests/tc-testing/tdc.sh index afb0cd86fa3d..eb357bd7923c 100755 --- a/tools/testing/selftests/tc-testing/tdc.sh +++ b/tools/testing/selftests/tc-testing/tdc.sh @@ -2,5 +2,6 @@ # SPDX-License-Identifier: GPL-2.0 modprobe netdevsim +modprobe sch_teql ./tdc.py -c actions --nobuildebpf ./tdc.py -c qdisc diff --git a/tools/testing/selftests/user_events/dyn_test.c b/tools/testing/selftests/user_events/dyn_test.c index 8879a7b04c6a..d6979a48478f 100644 --- a/tools/testing/selftests/user_events/dyn_test.c +++ b/tools/testing/selftests/user_events/dyn_test.c @@ -16,42 +16,140 @@ #include "../kselftest_harness.h" -const char *dyn_file = "/sys/kernel/tracing/dynamic_events"; -const char *clear = "!u:__test_event"; +const char *abi_file = "/sys/kernel/tracing/user_events_data"; +const char *enable_file = "/sys/kernel/tracing/events/user_events/__test_event/enable"; -static int Append(const char *value) +static bool wait_for_delete(void) { - int fd = open(dyn_file, O_RDWR | O_APPEND); - int ret = write(fd, value, strlen(value)); + int i; + + for (i = 0; i < 1000; ++i) { + int fd = open(enable_file, O_RDONLY); + + if (fd == -1) + return true; + + close(fd); + usleep(1000); + } + + return false; +} + +static int reg_event(int fd, int *check, int bit, const char *value) +{ + struct user_reg reg = {0}; + + reg.size = sizeof(reg); + reg.name_args = (__u64)value; + reg.enable_bit = bit; + reg.enable_addr = (__u64)check; + reg.enable_size = sizeof(*check); + + if (ioctl(fd, DIAG_IOCSREG, ®) == -1) + return -1; + + return 0; +} + +static int unreg_event(int fd, int *check, int bit) +{ + struct user_unreg unreg = {0}; + + unreg.size = sizeof(unreg); + unreg.disable_bit = bit; + unreg.disable_addr = (__u64)check; + + return ioctl(fd, DIAG_IOCSUNREG, &unreg); +} + +static int parse(int *check, const char *value) +{ + int fd = open(abi_file, O_RDWR); + int ret; + + if (fd == -1) + return -1; + + /* Until we have persist flags via dynamic events, use the base name */ + if (value[0] != 'u' || value[1] != ':') { + close(fd); + return -1; + } + + ret = reg_event(fd, check, 31, value + 2); + + if (ret != -1) { + if (unreg_event(fd, check, 31) == -1) + printf("WARN: Couldn't unreg event\n"); + } close(fd); + return ret; } -#define CLEAR() \ +static int check_match(int *check, const char *first, const char *second, bool *match) +{ + int fd = open(abi_file, O_RDWR); + int ret = -1; + + if (fd == -1) + return -1; + + if (reg_event(fd, check, 31, first) == -1) + goto cleanup; + + if (reg_event(fd, check, 30, second) == -1) { + if (errno == EADDRINUSE) { + /* Name is in use, with different fields */ + *match = false; + ret = 0; + } + + goto cleanup; + } + + *match = true; + ret = 0; +cleanup: + unreg_event(fd, check, 31); + unreg_event(fd, check, 30); + + close(fd); + + wait_for_delete(); + + return ret; +} + +#define TEST_MATCH(x, y) \ do { \ - int ret = Append(clear); \ - if (ret == -1) \ - ASSERT_EQ(ENOENT, errno); \ + bool match; \ + ASSERT_NE(-1, check_match(&self->check, x, y, &match)); \ + ASSERT_EQ(true, match); \ } while (0) -#define TEST_PARSE(x) \ +#define TEST_NMATCH(x, y) \ do { \ - ASSERT_NE(-1, Append(x)); \ - CLEAR(); \ + bool match; \ + ASSERT_NE(-1, check_match(&self->check, x, y, &match)); \ + ASSERT_EQ(false, match); \ } while (0) -#define TEST_NPARSE(x) ASSERT_EQ(-1, Append(x)) +#define TEST_PARSE(x) ASSERT_NE(-1, parse(&self->check, x)) + +#define TEST_NPARSE(x) ASSERT_EQ(-1, parse(&self->check, x)) FIXTURE(user) { + int check; }; FIXTURE_SETUP(user) { - CLEAR(); } FIXTURE_TEARDOWN(user) { - CLEAR(); + wait_for_delete(); } TEST_F(user, basic_types) { @@ -95,33 +193,30 @@ TEST_F(user, size_types) { TEST_NPARSE("u:__test_event char a 20"); } -TEST_F(user, flags) { - /* Should work */ - TEST_PARSE("u:__test_event:BPF_ITER u32 a"); - /* Forward compat */ - TEST_PARSE("u:__test_event:BPF_ITER,FLAG_FUTURE u32 a"); -} - TEST_F(user, matching) { - /* Register */ - ASSERT_NE(-1, Append("u:__test_event struct custom a 20")); - /* Should not match */ - TEST_NPARSE("!u:__test_event struct custom b"); - /* Should match */ - TEST_PARSE("!u:__test_event struct custom a"); - /* Multi field reg */ - ASSERT_NE(-1, Append("u:__test_event u32 a; u32 b")); - /* Non matching cases */ - TEST_NPARSE("!u:__test_event u32 a"); - TEST_NPARSE("!u:__test_event u32 b"); - TEST_NPARSE("!u:__test_event u32 a; u32 "); - TEST_NPARSE("!u:__test_event u32 a; u32 a"); - /* Matching case */ - TEST_PARSE("!u:__test_event u32 a; u32 b"); - /* Register */ - ASSERT_NE(-1, Append("u:__test_event u32 a; u32 b")); - /* Ensure trailing semi-colon case */ - TEST_PARSE("!u:__test_event u32 a; u32 b;"); + /* Single name matches */ + TEST_MATCH("__test_event u32 a", + "__test_event u32 a"); + + /* Multiple names match */ + TEST_MATCH("__test_event u32 a; u32 b", + "__test_event u32 a; u32 b"); + + /* Multiple names match with dangling ; */ + TEST_MATCH("__test_event u32 a; u32 b", + "__test_event u32 a; u32 b;"); + + /* Single name doesn't match */ + TEST_NMATCH("__test_event u32 a", + "__test_event u32 b"); + + /* Multiple names don't match */ + TEST_NMATCH("__test_event u32 a; u32 b", + "__test_event u32 b; u32 a"); + + /* Types don't match */ + TEST_NMATCH("__test_event u64 a; u64 b", + "__test_event u32 a; u32 b"); } int main(int argc, char **argv) diff --git a/tools/testing/selftests/user_events/ftrace_test.c b/tools/testing/selftests/user_events/ftrace_test.c index 7c99cef94a65..eb6904d89f14 100644 --- a/tools/testing/selftests/user_events/ftrace_test.c +++ b/tools/testing/selftests/user_events/ftrace_test.c @@ -102,30 +102,56 @@ err: return -1; } +static bool wait_for_delete(void) +{ + int i; + + for (i = 0; i < 1000; ++i) { + int fd = open(enable_file, O_RDONLY); + + if (fd == -1) + return true; + + close(fd); + usleep(1000); + } + + return false; +} + static int clear(int *check) { struct user_unreg unreg = {0}; + int fd; unreg.size = sizeof(unreg); unreg.disable_bit = 31; unreg.disable_addr = (__u64)check; - int fd = open(data_file, O_RDWR); + fd = open(data_file, O_RDWR); if (fd == -1) return -1; if (ioctl(fd, DIAG_IOCSUNREG, &unreg) == -1) if (errno != ENOENT) - return -1; - - if (ioctl(fd, DIAG_IOCSDEL, "__test_event") == -1) - if (errno != ENOENT) - return -1; + goto fail; + + if (ioctl(fd, DIAG_IOCSDEL, "__test_event") == -1) { + if (errno == EBUSY) { + if (!wait_for_delete()) + goto fail; + } else if (errno != ENOENT) + goto fail; + } close(fd); return 0; +fail: + close(fd); + + return -1; } static int check_print_fmt(const char *event, const char *expected, int *check) @@ -155,9 +181,8 @@ static int check_print_fmt(const char *event, const char *expected, int *check) /* Register should work */ ret = ioctl(fd, DIAG_IOCSREG, ®); - close(fd); - if (ret != 0) { + close(fd); printf("Reg failed in fmt\n"); return ret; } @@ -165,6 +190,8 @@ static int check_print_fmt(const char *event, const char *expected, int *check) /* Ensure correct print_fmt */ ret = get_print_fmt(print_fmt, sizeof(print_fmt)); + close(fd); + if (ret != 0) return ret; @@ -228,6 +255,12 @@ TEST_F(user, register_events) { ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); ASSERT_EQ(0, reg.write_index); + /* Multiple registers to same name but different args should fail */ + reg.enable_bit = 29; + reg.name_args = (__u64)"__test_event u32 field1;"; + ASSERT_EQ(-1, ioctl(self->data_fd, DIAG_IOCSREG, ®)); + ASSERT_EQ(EADDRINUSE, errno); + /* Ensure disabled */ self->enable_fd = open(enable_file, O_RDWR); ASSERT_NE(-1, self->enable_fd); @@ -250,10 +283,10 @@ TEST_F(user, register_events) { unreg.disable_bit = 30; ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSUNREG, &unreg)); - /* Delete should work only after close and unregister */ + /* Delete should have been auto-done after close and unregister */ close(self->data_fd); - self->data_fd = open(data_file, O_RDWR); - ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSDEL, "__test_event")); + + ASSERT_EQ(true, wait_for_delete()); } TEST_F(user, write_events) { @@ -310,6 +343,39 @@ TEST_F(user, write_events) { ASSERT_EQ(EINVAL, errno); } +TEST_F(user, write_empty_events) { + struct user_reg reg = {0}; + struct iovec io[1]; + int before = 0, after = 0; + + reg.size = sizeof(reg); + reg.name_args = (__u64)"__test_event"; + reg.enable_bit = 31; + reg.enable_addr = (__u64)&self->check; + reg.enable_size = sizeof(self->check); + + io[0].iov_base = ®.write_index; + io[0].iov_len = sizeof(reg.write_index); + + /* Register should work */ + ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); + ASSERT_EQ(0, reg.write_index); + ASSERT_EQ(0, self->check); + + /* Enable event */ + self->enable_fd = open(enable_file, O_RDWR); + ASSERT_NE(-1, write(self->enable_fd, "1", sizeof("1"))) + + /* Event should now be enabled */ + ASSERT_EQ(1 << reg.enable_bit, self->check); + + /* Write should make it out to ftrace buffers */ + before = trace_bytes(); + ASSERT_NE(-1, writev(self->data_fd, (const struct iovec *)io, 1)); + after = trace_bytes(); + ASSERT_GT(after, before); +} + TEST_F(user, write_fault) { struct user_reg reg = {0}; struct iovec io[2]; diff --git a/tools/testing/selftests/user_events/perf_test.c b/tools/testing/selftests/user_events/perf_test.c index a070258d4449..8b09be566fa2 100644 --- a/tools/testing/selftests/user_events/perf_test.c +++ b/tools/testing/selftests/user_events/perf_test.c @@ -81,6 +81,32 @@ static int get_offset(void) return offset; } +static int clear(int *check) +{ + struct user_unreg unreg = {0}; + + unreg.size = sizeof(unreg); + unreg.disable_bit = 31; + unreg.disable_addr = (__u64)check; + + int fd = open(data_file, O_RDWR); + + if (fd == -1) + return -1; + + if (ioctl(fd, DIAG_IOCSUNREG, &unreg) == -1) + if (errno != ENOENT) + return -1; + + if (ioctl(fd, DIAG_IOCSDEL, "__test_event") == -1) + if (errno != ENOENT) + return -1; + + close(fd); + + return 0; +} + FIXTURE(user) { int data_fd; int check; @@ -93,6 +119,9 @@ FIXTURE_SETUP(user) { FIXTURE_TEARDOWN(user) { close(self->data_fd); + + if (clear(&self->check) != 0) + printf("WARNING: Clear didn't work!\n"); } TEST_F(user, perf_write) { @@ -160,6 +189,59 @@ TEST_F(user, perf_write) { ASSERT_EQ(0, self->check); } +TEST_F(user, perf_empty_events) { + struct perf_event_attr pe = {0}; + struct user_reg reg = {0}; + struct perf_event_mmap_page *perf_page; + int page_size = sysconf(_SC_PAGESIZE); + int id, fd; + __u32 *val; + + reg.size = sizeof(reg); + reg.name_args = (__u64)"__test_event"; + reg.enable_bit = 31; + reg.enable_addr = (__u64)&self->check; + reg.enable_size = sizeof(self->check); + + /* Register should work */ + ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); + ASSERT_EQ(0, reg.write_index); + ASSERT_EQ(0, self->check); + + /* Id should be there */ + id = get_id(); + ASSERT_NE(-1, id); + + pe.type = PERF_TYPE_TRACEPOINT; + pe.size = sizeof(pe); + pe.config = id; + pe.sample_type = PERF_SAMPLE_RAW; + pe.sample_period = 1; + pe.wakeup_events = 1; + + /* Tracepoint attach should work */ + fd = perf_event_open(&pe, 0, -1, -1, 0); + ASSERT_NE(-1, fd); + + perf_page = mmap(NULL, page_size * 2, PROT_READ, MAP_SHARED, fd, 0); + ASSERT_NE(MAP_FAILED, perf_page); + + /* Status should be updated */ + ASSERT_EQ(1 << reg.enable_bit, self->check); + + /* Ensure write shows up at correct offset */ + ASSERT_NE(-1, write(self->data_fd, ®.write_index, + sizeof(reg.write_index))); + val = (void *)(((char *)perf_page) + perf_page->data_offset); + ASSERT_EQ(PERF_RECORD_SAMPLE, *val); + + munmap(perf_page, page_size * 2); + close(fd); + + /* Status should be updated */ + ASSERT_EQ(0, self->check); +} + int main(int argc, char **argv) { return test_harness_run(argc, argv); diff --git a/tools/testing/selftests/vDSO/vdso_test_clock_getres.c b/tools/testing/selftests/vDSO/vdso_test_clock_getres.c index 15dcee16ff72..38d46a8bf7cb 100644 --- a/tools/testing/selftests/vDSO/vdso_test_clock_getres.c +++ b/tools/testing/selftests/vDSO/vdso_test_clock_getres.c @@ -84,12 +84,12 @@ static inline int vdso_test_clock(unsigned int clock_id) int main(int argc, char **argv) { - int ret; + int ret = 0; #if _POSIX_TIMERS > 0 #ifdef CLOCK_REALTIME - ret = vdso_test_clock(CLOCK_REALTIME); + ret += vdso_test_clock(CLOCK_REALTIME); #endif #ifdef CLOCK_BOOTTIME diff --git a/tools/virtio/ringtest/.gitignore b/tools/virtio/ringtest/.gitignore new file mode 100644 index 000000000000..100b9e30c0f4 --- /dev/null +++ b/tools/virtio/ringtest/.gitignore @@ -0,0 +1,7 @@ +# SPDX-License-Identifier: GPL-2.0-only +/noring +/ptr_ring +/ring +/virtio_ring_0_9 +/virtio_ring_inorder +/virtio_ring_poll diff --git a/tools/virtio/ringtest/main.h b/tools/virtio/ringtest/main.h index b68920d52750..d18dd317e27f 100644 --- a/tools/virtio/ringtest/main.h +++ b/tools/virtio/ringtest/main.h @@ -8,6 +8,7 @@ #ifndef MAIN_H #define MAIN_H +#include <assert.h> #include <stdbool.h> extern int param; @@ -95,6 +96,8 @@ extern unsigned ring_size; #define cpu_relax() asm ("rep; nop" ::: "memory") #elif defined(__s390x__) #define cpu_relax() barrier() +#elif defined(__aarch64__) +#define cpu_relax() asm ("yield" ::: "memory") #else #define cpu_relax() assert(0) #endif @@ -112,6 +115,8 @@ static inline void busy_wait(void) #if defined(__x86_64__) || defined(__i386__) #define smp_mb() asm volatile("lock; addl $0,-132(%%rsp)" ::: "memory", "cc") +#elif defined(__aarch64__) +#define smp_mb() asm volatile("dmb ish" ::: "memory") #else /* * Not using __ATOMIC_SEQ_CST since gcc docs say they are only synchronized @@ -136,10 +141,16 @@ static inline void busy_wait(void) #if defined(__i386__) || defined(__x86_64__) || defined(__s390x__) #define smp_wmb() barrier() +#elif defined(__aarch64__) +#define smp_wmb() asm volatile("dmb ishst" ::: "memory") #else #define smp_wmb() smp_release() #endif +#ifndef __always_inline +#define __always_inline inline __attribute__((always_inline)) +#endif + static __always_inline void __read_once_size(const volatile void *p, void *res, int size) { diff --git a/tools/virtio/virtio-trace/README b/tools/virtio/virtio-trace/README index 4fb9368bf751..0127ff0c54b0 100644 --- a/tools/virtio/virtio-trace/README +++ b/tools/virtio/virtio-trace/README @@ -95,7 +95,7 @@ Run 1) Enable ftrace in the guest <Example> - # echo 1 > /sys/kernel/debug/tracing/events/sched/enable + # echo 1 > /sys/kernel/tracing/events/sched/enable 2) Run trace agent in the guest This agent must be operated as root. diff --git a/tools/virtio/virtio-trace/trace-agent.c b/tools/virtio/virtio-trace/trace-agent.c index cdfe77c2b4c8..7e2d9bbf0b84 100644 --- a/tools/virtio/virtio-trace/trace-agent.c +++ b/tools/virtio/virtio-trace/trace-agent.c @@ -18,8 +18,9 @@ #define PIPE_DEF_BUFS 16 #define PIPE_MIN_SIZE (PAGE_SIZE*PIPE_DEF_BUFS) #define PIPE_MAX_SIZE (1024*1024) -#define READ_PATH_FMT \ - "/sys/kernel/debug/tracing/per_cpu/cpu%d/trace_pipe_raw" +#define TRACEFS "/sys/kernel/tracing" +#define DEBUGFS "/sys/kernel/debug/tracing" +#define READ_PATH_FMT "%s/per_cpu/cpu%d/trace_pipe_raw" #define WRITE_PATH_FMT "/dev/virtio-ports/trace-path-cpu%d" #define CTL_PATH "/dev/virtio-ports/agent-ctl-path" @@ -120,9 +121,12 @@ static const char *make_path(int cpu_num, bool this_is_write_path) if (this_is_write_path) /* write(output) path */ ret = snprintf(buf, PATH_MAX, WRITE_PATH_FMT, cpu_num); - else + else { /* read(input) path */ - ret = snprintf(buf, PATH_MAX, READ_PATH_FMT, cpu_num); + ret = snprintf(buf, PATH_MAX, READ_PATH_FMT, TRACEFS, cpu_num); + if (ret > 0 && access(buf, F_OK) != 0) + ret = snprintf(buf, PATH_MAX, READ_PATH_FMT, DEBUGFS, cpu_num); + } if (ret <= 0) { pr_err("Failed to generate %s path(CPU#%d):%d\n", diff --git a/tools/workqueue/wq_monitor.py b/tools/workqueue/wq_monitor.py new file mode 100644 index 000000000000..6e258d123e8c --- /dev/null +++ b/tools/workqueue/wq_monitor.py @@ -0,0 +1,168 @@ +#!/usr/bin/env drgn +# +# Copyright (C) 2023 Tejun Heo <tj@kernel.org> +# Copyright (C) 2023 Meta Platforms, Inc. and affiliates. + +desc = """ +This is a drgn script to monitor workqueues. For more info on drgn, visit +https://github.com/osandov/drgn. + + total Total number of work items executed by the workqueue. + + infl The number of currently in-flight work items. + + CPUtime Total CPU time consumed by the workqueue in seconds. This is + sampled from scheduler ticks and only provides ballpark + measurement. "nohz_full=" CPUs are excluded from measurement. + + CPUitsv The number of times a concurrency-managed work item hogged CPU + longer than the threshold (workqueue.cpu_intensive_thresh_us) + and got excluded from concurrency management to avoid stalling + other work items. + + CMwake The number of concurrency-management wake-ups while executing a + work item of the workqueue. + + mayday The number of times the rescuer was requested while waiting for + new worker creation. + + rescued The number of work items executed by the rescuer. +""" + +import sys +import signal +import os +import re +import time +import json + +import drgn +from drgn.helpers.linux.list import list_for_each_entry,list_empty +from drgn.helpers.linux.cpumask import for_each_possible_cpu + +import argparse +parser = argparse.ArgumentParser(description=desc, + formatter_class=argparse.RawTextHelpFormatter) +parser.add_argument('workqueue', metavar='REGEX', nargs='*', + help='Target workqueue name patterns (all if empty)') +parser.add_argument('-i', '--interval', metavar='SECS', type=float, default=1, + help='Monitoring interval (0 to print once and exit)') +parser.add_argument('-j', '--json', action='store_true', + help='Output in json') +args = parser.parse_args() + +def err(s): + print(s, file=sys.stderr, flush=True) + sys.exit(1) + +workqueues = prog['workqueues'] + +WQ_UNBOUND = prog['WQ_UNBOUND'] +WQ_MEM_RECLAIM = prog['WQ_MEM_RECLAIM'] + +PWQ_STAT_STARTED = prog['PWQ_STAT_STARTED'] # work items started execution +PWQ_STAT_COMPLETED = prog['PWQ_STAT_COMPLETED'] # work items completed execution +PWQ_STAT_CPU_TIME = prog['PWQ_STAT_CPU_TIME'] # total CPU time consumed +PWQ_STAT_CPU_INTENSIVE = prog['PWQ_STAT_CPU_INTENSIVE'] # wq_cpu_intensive_thresh_us violations +PWQ_STAT_CM_WAKEUP = prog['PWQ_STAT_CM_WAKEUP'] # concurrency-management worker wakeups +PWQ_STAT_MAYDAY = prog['PWQ_STAT_MAYDAY'] # maydays to rescuer +PWQ_STAT_RESCUED = prog['PWQ_STAT_RESCUED'] # linked work items executed by rescuer +PWQ_NR_STATS = prog['PWQ_NR_STATS'] + +class WqStats: + def __init__(self, wq): + self.name = wq.name.string_().decode() + self.unbound = wq.flags & WQ_UNBOUND != 0 + self.mem_reclaim = wq.flags & WQ_MEM_RECLAIM != 0 + self.stats = [0] * PWQ_NR_STATS + for pwq in list_for_each_entry('struct pool_workqueue', wq.pwqs.address_of_(), 'pwqs_node'): + for i in range(PWQ_NR_STATS): + self.stats[i] += int(pwq.stats[i]) + + def dict(self, now): + return { 'timestamp' : now, + 'name' : self.name, + 'unbound' : self.unbound, + 'mem_reclaim' : self.mem_reclaim, + 'started' : self.stats[PWQ_STAT_STARTED], + 'completed' : self.stats[PWQ_STAT_COMPLETED], + 'cpu_time' : self.stats[PWQ_STAT_CPU_TIME], + 'cpu_intensive' : self.stats[PWQ_STAT_CPU_INTENSIVE], + 'cm_wakeup' : self.stats[PWQ_STAT_CM_WAKEUP], + 'mayday' : self.stats[PWQ_STAT_MAYDAY], + 'rescued' : self.stats[PWQ_STAT_RESCUED], } + + def table_header_str(): + return f'{"":>24} {"total":>8} {"infl":>5} {"CPUtime":>8} '\ + f'{"CPUitsv":>7} {"CMwake":>7} {"mayday":>7} {"rescued":>7}' + + def table_row_str(self): + cpu_intensive = '-' + cm_wakeup = '-' + mayday = '-' + rescued = '-' + + if not self.unbound: + cpu_intensive = str(self.stats[PWQ_STAT_CPU_INTENSIVE]) + cm_wakeup = str(self.stats[PWQ_STAT_CM_WAKEUP]) + + if self.mem_reclaim: + mayday = str(self.stats[PWQ_STAT_MAYDAY]) + rescued = str(self.stats[PWQ_STAT_RESCUED]) + + out = f'{self.name[-24:]:24} ' \ + f'{self.stats[PWQ_STAT_STARTED]:8} ' \ + f'{max(self.stats[PWQ_STAT_STARTED] - self.stats[PWQ_STAT_COMPLETED], 0):5} ' \ + f'{self.stats[PWQ_STAT_CPU_TIME] / 1000000:8.1f} ' \ + f'{cpu_intensive:>7} ' \ + f'{cm_wakeup:>7} ' \ + f'{mayday:>7} ' \ + f'{rescued:>7} ' + return out.rstrip(':') + +exit_req = False + +def sigint_handler(signr, frame): + global exit_req + exit_req = True + +def main(): + # handle args + table_fmt = not args.json + interval = args.interval + + re_str = None + if args.workqueue: + for r in args.workqueue: + if re_str is None: + re_str = r + else: + re_str += '|' + r + + filter_re = re.compile(re_str) if re_str else None + + # monitoring loop + signal.signal(signal.SIGINT, sigint_handler) + + while not exit_req: + now = time.time() + + if table_fmt: + print() + print(WqStats.table_header_str()) + + for wq in list_for_each_entry('struct workqueue_struct', workqueues.address_of_(), 'list'): + stats = WqStats(wq) + if filter_re and not filter_re.search(stats.name): + continue + if table_fmt: + print(stats.table_row_str()) + else: + print(stats.dict(now)) + + if interval == 0: + break + time.sleep(interval) + +if __name__ == "__main__": + main() |