diff options
Diffstat (limited to 'tools')
673 files changed, 34028 insertions, 4861 deletions
diff --git a/tools/Makefile b/tools/Makefile index 00caacd3ed92..c8a90d01dd8e 100644 --- a/tools/Makefile +++ b/tools/Makefile @@ -86,10 +86,13 @@ tmon: FORCE freefall: FORCE $(call descend,laptop/$@) +kvm_stat: FORCE + $(call descend,kvm/$@) + all: acpi cgroup cpupower gpio hv firewire lguest \ perf selftests turbostat usb \ virtio vm net x86_energy_perf_policy \ - tmon freefall objtool + tmon freefall objtool kvm_stat acpi_install: $(call descend,power/$(@:_install=),install) diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h index a2b3eb313a25..6ebd3e6a1fd1 100644 --- a/tools/arch/arm/include/uapi/asm/kvm.h +++ b/tools/arch/arm/include/uapi/asm/kvm.h @@ -84,6 +84,15 @@ struct kvm_regs { #define KVM_VGIC_V2_DIST_SIZE 0x1000 #define KVM_VGIC_V2_CPU_SIZE 0x2000 +/* Supported VGICv3 address types */ +#define KVM_VGIC_V3_ADDR_TYPE_DIST 2 +#define KVM_VGIC_V3_ADDR_TYPE_REDIST 3 +#define KVM_VGIC_ITS_ADDR_TYPE 4 + +#define KVM_VGIC_V3_DIST_SIZE SZ_64K +#define KVM_VGIC_V3_REDIST_SIZE (2 * SZ_64K) +#define KVM_VGIC_V3_ITS_SIZE (2 * SZ_64K) + #define KVM_ARM_VCPU_POWER_OFF 0 /* CPU is started in OFF state */ #define KVM_ARM_VCPU_PSCI_0_2 1 /* CPU uses PSCI v0.2 */ @@ -172,10 +181,23 @@ struct kvm_arch_memory_slot { #define KVM_DEV_ARM_VGIC_GRP_CPU_REGS 2 #define KVM_DEV_ARM_VGIC_CPUID_SHIFT 32 #define KVM_DEV_ARM_VGIC_CPUID_MASK (0xffULL << KVM_DEV_ARM_VGIC_CPUID_SHIFT) +#define KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT 32 +#define KVM_DEV_ARM_VGIC_V3_MPIDR_MASK \ + (0xffffffffULL << KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT) #define KVM_DEV_ARM_VGIC_OFFSET_SHIFT 0 #define KVM_DEV_ARM_VGIC_OFFSET_MASK (0xffffffffULL << KVM_DEV_ARM_VGIC_OFFSET_SHIFT) +#define KVM_DEV_ARM_VGIC_SYSREG_INSTR_MASK (0xffff) #define KVM_DEV_ARM_VGIC_GRP_NR_IRQS 3 #define KVM_DEV_ARM_VGIC_GRP_CTRL 4 +#define KVM_DEV_ARM_VGIC_GRP_REDIST_REGS 5 +#define KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS 6 +#define KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO 7 +#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT 10 +#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK \ + (0x3fffffULL << KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT) +#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INTID_MASK 0x3ff +#define VGIC_LEVEL_INFO_LINE_LEVEL 0 + #define KVM_DEV_ARM_VGIC_CTRL_INIT 0 /* KVM_IRQ_LINE irq field index values */ diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index 3051f86a9b5f..c2860358ae3e 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -201,10 +201,23 @@ struct kvm_arch_memory_slot { #define KVM_DEV_ARM_VGIC_GRP_CPU_REGS 2 #define KVM_DEV_ARM_VGIC_CPUID_SHIFT 32 #define KVM_DEV_ARM_VGIC_CPUID_MASK (0xffULL << KVM_DEV_ARM_VGIC_CPUID_SHIFT) +#define KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT 32 +#define KVM_DEV_ARM_VGIC_V3_MPIDR_MASK \ + (0xffffffffULL << KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT) #define KVM_DEV_ARM_VGIC_OFFSET_SHIFT 0 #define KVM_DEV_ARM_VGIC_OFFSET_MASK (0xffffffffULL << KVM_DEV_ARM_VGIC_OFFSET_SHIFT) +#define KVM_DEV_ARM_VGIC_SYSREG_INSTR_MASK (0xffff) #define KVM_DEV_ARM_VGIC_GRP_NR_IRQS 3 #define KVM_DEV_ARM_VGIC_GRP_CTRL 4 +#define KVM_DEV_ARM_VGIC_GRP_REDIST_REGS 5 +#define KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS 6 +#define KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO 7 +#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT 10 +#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK \ + (0x3fffffULL << KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT) +#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INTID_MASK 0x3ff +#define VGIC_LEVEL_INFO_LINE_LEVEL 0 + #define KVM_DEV_ARM_VGIC_CTRL_INIT 0 /* Device Control API on vcpu fd */ diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h index c93cf35ce379..4edbe4bb0e8b 100644 --- a/tools/arch/powerpc/include/uapi/asm/kvm.h +++ b/tools/arch/powerpc/include/uapi/asm/kvm.h @@ -413,6 +413,26 @@ struct kvm_get_htab_header { __u16 n_invalid; }; +/* For KVM_PPC_CONFIGURE_V3_MMU */ +struct kvm_ppc_mmuv3_cfg { + __u64 flags; + __u64 process_table; /* second doubleword of partition table entry */ +}; + +/* Flag values for KVM_PPC_CONFIGURE_V3_MMU */ +#define KVM_PPC_MMUV3_RADIX 1 /* 1 = radix mode, 0 = HPT */ +#define KVM_PPC_MMUV3_GTSE 2 /* global translation shootdown enb. */ + +/* For KVM_PPC_GET_RMMU_INFO */ +struct kvm_ppc_rmmu_info { + struct kvm_ppc_radix_geom { + __u8 page_shift; + __u8 level_bits[4]; + __u8 pad[3]; + } geometries[8]; + __u32 ap_encodings[8]; +}; + /* Per-vcpu XICS interrupt controller state */ #define KVM_REG_PPC_ICP_STATE (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8c) @@ -573,6 +593,10 @@ struct kvm_get_htab_header { #define KVM_REG_PPC_SPRG9 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xba) #define KVM_REG_PPC_DBSR (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xbb) +/* POWER9 registers */ +#define KVM_REG_PPC_TIDR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbc) +#define KVM_REG_PPC_PSSCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbd) + /* Transactional Memory checkpointed state: * This is all GPRs, all VSX regs and a subset of SPRs */ @@ -596,6 +620,7 @@ struct kvm_get_htab_header { #define KVM_REG_PPC_TM_VSCR (KVM_REG_PPC_TM | KVM_REG_SIZE_U32 | 0x67) #define KVM_REG_PPC_TM_DSCR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x68) #define KVM_REG_PPC_TM_TAR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x69) +#define KVM_REG_PPC_TM_XER (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x6a) /* PPC64 eXternal Interrupt Controller Specification */ #define KVM_DEV_XICS_GRP_SOURCES 1 /* 64-bit source attributes */ @@ -608,5 +633,7 @@ struct kvm_get_htab_header { #define KVM_XICS_LEVEL_SENSITIVE (1ULL << 40) #define KVM_XICS_MASKED (1ULL << 41) #define KVM_XICS_PENDING (1ULL << 42) +#define KVM_XICS_PRESENTED (1ULL << 43) +#define KVM_XICS_QUEUED (1ULL << 44) #endif /* __LINUX_KVM_POWERPC_H */ diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h index a2ffec4139ad..7f4fd65e9208 100644 --- a/tools/arch/s390/include/uapi/asm/kvm.h +++ b/tools/arch/s390/include/uapi/asm/kvm.h @@ -131,7 +131,8 @@ struct kvm_s390_vm_cpu_subfunc { __u8 kmo[16]; /* with MSA4 */ __u8 pcc[16]; /* with MSA4 */ __u8 ppno[16]; /* with MSA5 */ - __u8 reserved[1824]; + __u8 kma[16]; /* with MSA8 */ + __u8 reserved[1808]; }; /* kvm attributes for crypto */ diff --git a/tools/arch/x86/include/asm/atomic.h b/tools/arch/x86/include/asm/atomic.h index 059e33e94260..328eeceec709 100644 --- a/tools/arch/x86/include/asm/atomic.h +++ b/tools/arch/x86/include/asm/atomic.h @@ -7,6 +7,8 @@ #define LOCK_PREFIX "\n\tlock; " +#include <asm/cmpxchg.h> + /* * Atomic operations that C can't guarantee us. Useful for * resource counting etc.. @@ -62,4 +64,9 @@ static inline int atomic_dec_and_test(atomic_t *v) GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", "e"); } +static __always_inline int atomic_cmpxchg(atomic_t *v, int old, int new) +{ + return cmpxchg(&v->counter, old, new); +} + #endif /* _TOOLS_LINUX_ASM_X86_ATOMIC_H */ diff --git a/tools/arch/x86/include/asm/cmpxchg.h b/tools/arch/x86/include/asm/cmpxchg.h new file mode 100644 index 000000000000..f5253260f3cc --- /dev/null +++ b/tools/arch/x86/include/asm/cmpxchg.h @@ -0,0 +1,89 @@ +#ifndef TOOLS_ASM_X86_CMPXCHG_H +#define TOOLS_ASM_X86_CMPXCHG_H + +#include <linux/compiler.h> + +/* + * Non-existant functions to indicate usage errors at link time + * (or compile-time if the compiler implements __compiletime_error(). + */ +extern void __cmpxchg_wrong_size(void) + __compiletime_error("Bad argument size for cmpxchg"); + +/* + * Constants for operation sizes. On 32-bit, the 64-bit size it set to + * -1 because sizeof will never return -1, thereby making those switch + * case statements guaranteeed dead code which the compiler will + * eliminate, and allowing the "missing symbol in the default case" to + * indicate a usage error. + */ +#define __X86_CASE_B 1 +#define __X86_CASE_W 2 +#define __X86_CASE_L 4 +#ifdef __x86_64__ +#define __X86_CASE_Q 8 +#else +#define __X86_CASE_Q -1 /* sizeof will never return -1 */ +#endif + +/* + * Atomic compare and exchange. Compare OLD with MEM, if identical, + * store NEW in MEM. Return the initial value in MEM. Success is + * indicated by comparing RETURN with OLD. + */ +#define __raw_cmpxchg(ptr, old, new, size, lock) \ +({ \ + __typeof__(*(ptr)) __ret; \ + __typeof__(*(ptr)) __old = (old); \ + __typeof__(*(ptr)) __new = (new); \ + switch (size) { \ + case __X86_CASE_B: \ + { \ + volatile u8 *__ptr = (volatile u8 *)(ptr); \ + asm volatile(lock "cmpxchgb %2,%1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "q" (__new), "0" (__old) \ + : "memory"); \ + break; \ + } \ + case __X86_CASE_W: \ + { \ + volatile u16 *__ptr = (volatile u16 *)(ptr); \ + asm volatile(lock "cmpxchgw %2,%1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "r" (__new), "0" (__old) \ + : "memory"); \ + break; \ + } \ + case __X86_CASE_L: \ + { \ + volatile u32 *__ptr = (volatile u32 *)(ptr); \ + asm volatile(lock "cmpxchgl %2,%1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "r" (__new), "0" (__old) \ + : "memory"); \ + break; \ + } \ + case __X86_CASE_Q: \ + { \ + volatile u64 *__ptr = (volatile u64 *)(ptr); \ + asm volatile(lock "cmpxchgq %2,%1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "r" (__new), "0" (__old) \ + : "memory"); \ + break; \ + } \ + default: \ + __cmpxchg_wrong_size(); \ + } \ + __ret; \ +}) + +#define __cmpxchg(ptr, old, new, size) \ + __raw_cmpxchg((ptr), (old), (new), (size), LOCK_PREFIX) + +#define cmpxchg(ptr, old, new) \ + __cmpxchg(ptr, old, new, sizeof(*(ptr))) + + +#endif /* TOOLS_ASM_X86_CMPXCHG_H */ diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index cddd5d06e1cb..0fe00446f9ca 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -100,11 +100,12 @@ #define X86_FEATURE_XTOPOLOGY ( 3*32+22) /* cpu topology enum extensions */ #define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* TSC is known to be reliable */ #define X86_FEATURE_NONSTOP_TSC ( 3*32+24) /* TSC does not stop in C states */ -/* free, was #define X86_FEATURE_CLFLUSH_MONITOR ( 3*32+25) * "" clflush reqd with monitor */ +#define X86_FEATURE_CPUID ( 3*32+25) /* CPU has CPUID instruction itself */ #define X86_FEATURE_EXTD_APICID ( 3*32+26) /* has extended APICID (8 bits) */ #define X86_FEATURE_AMD_DCM ( 3*32+27) /* multi-node processor */ #define X86_FEATURE_APERFMPERF ( 3*32+28) /* APERFMPERF */ #define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */ +#define X86_FEATURE_TSC_KNOWN_FREQ ( 3*32+31) /* TSC has known frequency */ /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */ #define X86_FEATURE_XMM3 ( 4*32+ 0) /* "pni" SSE-3 */ @@ -185,13 +186,18 @@ * * Reuse free bits when adding new feature flags! */ - +#define X86_FEATURE_RING3MWAIT ( 7*32+ 0) /* Ring 3 MONITOR/MWAIT */ +#define X86_FEATURE_CPUID_FAULT ( 7*32+ 1) /* Intel CPUID faulting */ #define X86_FEATURE_CPB ( 7*32+ 2) /* AMD Core Performance Boost */ #define X86_FEATURE_EPB ( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */ +#define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* Cache Allocation Technology L3 */ +#define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* Cache Allocation Technology L2 */ +#define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* Code and Data Prioritization L3 */ #define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ +#define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ #define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */ #define X86_FEATURE_AVX512_4VNNIW (7*32+16) /* AVX-512 Neural Network Instructions */ #define X86_FEATURE_AVX512_4FMAPS (7*32+17) /* AVX-512 Multiply Accumulation Single precision */ @@ -220,11 +226,13 @@ #define X86_FEATURE_RTM ( 9*32+11) /* Restricted Transactional Memory */ #define X86_FEATURE_CQM ( 9*32+12) /* Cache QoS Monitoring */ #define X86_FEATURE_MPX ( 9*32+14) /* Memory Protection Extension */ +#define X86_FEATURE_RDT_A ( 9*32+15) /* Resource Director Technology Allocation */ #define X86_FEATURE_AVX512F ( 9*32+16) /* AVX-512 Foundation */ #define X86_FEATURE_AVX512DQ ( 9*32+17) /* AVX-512 DQ (Double/Quad granular) Instructions */ #define X86_FEATURE_RDSEED ( 9*32+18) /* The RDSEED instruction */ #define X86_FEATURE_ADX ( 9*32+19) /* The ADCX and ADOX instructions */ #define X86_FEATURE_SMAP ( 9*32+20) /* Supervisor Mode Access Prevention */ +#define X86_FEATURE_AVX512IFMA ( 9*32+21) /* AVX-512 Integer Fused Multiply-Add instructions */ #define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* CLFLUSHOPT instruction */ #define X86_FEATURE_CLWB ( 9*32+24) /* CLWB instruction */ #define X86_FEATURE_AVX512PF ( 9*32+26) /* AVX-512 Prefetch */ @@ -278,8 +286,12 @@ #define X86_FEATURE_AVIC (15*32+13) /* Virtual Interrupt Controller */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */ +#define X86_FEATURE_AVX512VBMI (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/ #define X86_FEATURE_PKU (16*32+ 3) /* Protection Keys for Userspace */ #define X86_FEATURE_OSPKE (16*32+ 4) /* OS Protection Keys Enable */ +#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */ +#define X86_FEATURE_LA57 (16*32+16) /* 5-level page tables */ +#define X86_FEATURE_RDPID (16*32+22) /* RDPID instruction */ /* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */ #define X86_FEATURE_OVERFLOW_RECOV (17*32+0) /* MCA overflow recovery support */ @@ -310,4 +322,5 @@ #define X86_BUG_NULL_SEG X86_BUG(10) /* Nulling a selector preserves the base */ #define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */ #define X86_BUG_MONITOR X86_BUG(12) /* IPI required to wake up remote CPU */ +#define X86_BUG_AMD_E400 X86_BUG(13) /* CPU is among the affected by Erratum 400 */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h index 37fee272618f..14458658e988 100644 --- a/tools/arch/x86/include/uapi/asm/vmx.h +++ b/tools/arch/x86/include/uapi/asm/vmx.h @@ -65,6 +65,8 @@ #define EXIT_REASON_TPR_BELOW_THRESHOLD 43 #define EXIT_REASON_APIC_ACCESS 44 #define EXIT_REASON_EOI_INDUCED 45 +#define EXIT_REASON_GDTR_IDTR 46 +#define EXIT_REASON_LDTR_TR 47 #define EXIT_REASON_EPT_VIOLATION 48 #define EXIT_REASON_EPT_MISCONFIG 49 #define EXIT_REASON_INVEPT 50 @@ -113,6 +115,8 @@ { EXIT_REASON_MCE_DURING_VMENTRY, "MCE_DURING_VMENTRY" }, \ { EXIT_REASON_TPR_BELOW_THRESHOLD, "TPR_BELOW_THRESHOLD" }, \ { EXIT_REASON_APIC_ACCESS, "APIC_ACCESS" }, \ + { EXIT_REASON_GDTR_IDTR, "GDTR_IDTR" }, \ + { EXIT_REASON_LDTR_TR, "LDTR_TR" }, \ { EXIT_REASON_EPT_VIOLATION, "EPT_VIOLATION" }, \ { EXIT_REASON_EPT_MISCONFIG, "EPT_MISCONFIG" }, \ { EXIT_REASON_INVEPT, "INVEPT" }, \ @@ -129,6 +133,7 @@ { EXIT_REASON_XRSTORS, "XRSTORS" } #define VMX_ABORT_SAVE_GUEST_MSR_FAIL 1 +#define VMX_ABORT_LOAD_HOST_PDPTE_FAIL 2 #define VMX_ABORT_LOAD_HOST_MSR_FAIL 4 #endif /* _UAPIVMX_H */ diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S index 49e6ebac7e73..98dcc112b363 100644 --- a/tools/arch/x86/lib/memcpy_64.S +++ b/tools/arch/x86/lib/memcpy_64.S @@ -286,7 +286,7 @@ ENDPROC(memcpy_mcsafe_unrolled) _ASM_EXTABLE_FAULT(.L_copy_leading_bytes, .L_memcpy_mcsafe_fail) _ASM_EXTABLE_FAULT(.L_cache_w0, .L_memcpy_mcsafe_fail) _ASM_EXTABLE_FAULT(.L_cache_w1, .L_memcpy_mcsafe_fail) - _ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_cache_w2, .L_memcpy_mcsafe_fail) _ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail) _ASM_EXTABLE_FAULT(.L_cache_w4, .L_memcpy_mcsafe_fail) _ASM_EXTABLE_FAULT(.L_cache_w5, .L_memcpy_mcsafe_fail) diff --git a/tools/build/Makefile b/tools/build/Makefile index aaf7ed329a45..477f00eda591 100644 --- a/tools/build/Makefile +++ b/tools/build/Makefile @@ -35,8 +35,8 @@ all: $(OUTPUT)fixdep clean: $(call QUIET_CLEAN, fixdep) - $(Q)find . -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete - $(Q)rm -f fixdep + $(Q)find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete + $(Q)rm -f $(OUTPUT)fixdep $(OUTPUT)fixdep-in.o: FORCE $(Q)$(MAKE) $(build)=fixdep diff --git a/tools/build/Makefile.build b/tools/build/Makefile.build index 99c0ccd2f176..e279a71c650d 100644 --- a/tools/build/Makefile.build +++ b/tools/build/Makefile.build @@ -19,6 +19,16 @@ else Q=@ endif +ifneq ($(filter 4.%,$(MAKE_VERSION)),) # make-4 +ifneq ($(filter %s ,$(firstword x$(MAKEFLAGS))),) + quiet=silent_ +endif +else # make-3.8x +ifneq ($(filter s% -s%,$(MAKEFLAGS)),) + quiet=silent_ +endif +endif + build-dir := $(srctree)/tools/build # Define $(fixdep) for dep-cmd function diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature index e3fb5ecbdcb6..523911f316ce 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -63,6 +63,7 @@ FEATURE_TESTS_BASIC := \ lzma \ get_cpuid \ bpf \ + sched_getcpu \ sdt # FEATURE_TESTS_BASIC + FEATURE_TESTS_EXTRA is the complete list diff --git a/tools/build/Makefile.include b/tools/build/Makefile.include index ad22e4e7bc59..d360f39a445b 100644 --- a/tools/build/Makefile.include +++ b/tools/build/Makefile.include @@ -3,4 +3,7 @@ build := -f $(srctree)/tools/build/Makefile.build dir=. obj fixdep: $(Q)$(MAKE) -C $(srctree)/tools/build CFLAGS= LDFLAGS= $(OUTPUT)fixdep +fixdep-clean: + $(Q)$(MAKE) -C $(srctree)/tools/build clean + .PHONY: fixdep diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index b564a2eea039..e35e4e5ad192 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -48,21 +48,22 @@ FILES= \ test-get_cpuid.bin \ test-sdt.bin \ test-cxx.bin \ - test-jvmti.bin + test-jvmti.bin \ + test-sched_getcpu.bin FILES := $(addprefix $(OUTPUT),$(FILES)) -CC := $(CROSS_COMPILE)gcc -MD -CXX := $(CROSS_COMPILE)g++ -MD -PKG_CONFIG := $(CROSS_COMPILE)pkg-config +CC ?= $(CROSS_COMPILE)gcc +CXX ?= $(CROSS_COMPILE)g++ +PKG_CONFIG ?= $(CROSS_COMPILE)pkg-config LLVM_CONFIG ?= llvm-config all: $(FILES) -__BUILD = $(CC) $(CFLAGS) -Wall -Werror -o $@ $(patsubst %.bin,%.c,$(@F)) $(LDFLAGS) +__BUILD = $(CC) $(CFLAGS) -MD -Wall -Werror -o $@ $(patsubst %.bin,%.c,$(@F)) $(LDFLAGS) BUILD = $(__BUILD) > $(@:.bin=.make.output) 2>&1 -__BUILDXX = $(CXX) $(CXXFLAGS) -Wall -Werror -o $@ $(patsubst %.bin,%.cpp,$(@F)) $(LDFLAGS) +__BUILDXX = $(CXX) $(CXXFLAGS) -MD -Wall -Werror -o $@ $(patsubst %.bin,%.cpp,$(@F)) $(LDFLAGS) BUILDXX = $(__BUILDXX) > $(@:.bin=.make.output) 2>&1 ############################### @@ -91,6 +92,9 @@ $(OUTPUT)test-libelf.bin: $(OUTPUT)test-glibc.bin: $(BUILD) +$(OUTPUT)test-sched_getcpu.bin: + $(BUILD) + DWARFLIBS := -ldw ifeq ($(findstring -static,${LDFLAGS}),-static) DWARFLIBS += -lelf -lebl -lz -llzma -lbz2 @@ -171,7 +175,7 @@ $(OUTPUT)test-libperl.bin: $(BUILD) $(FLAGS_PERL_EMBED) $(OUTPUT)test-libpython.bin: - $(BUILD) + $(BUILD) $(FLAGS_PYTHON_EMBED) $(OUTPUT)test-libpython-version.bin: $(BUILD) diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c index 699e43627397..cc6c7c01f4ca 100644 --- a/tools/build/feature/test-all.c +++ b/tools/build/feature/test-all.c @@ -117,6 +117,10 @@ # include "test-pthread-attr-setaffinity-np.c" #undef main +#define main main_test_sched_getcpu +# include "test-sched_getcpu.c" +#undef main + # if 0 /* * Disable libbabeltrace check for test-all, because the requested @@ -182,6 +186,7 @@ int main(int argc, char *argv[]) main_test_get_cpuid(); main_test_bpf(); main_test_libcrypto(); + main_test_sched_getcpu(); main_test_sdt(); return 0; diff --git a/tools/build/feature/test-bpf.c b/tools/build/feature/test-bpf.c index e04ab89a1013..ebc6dceddb58 100644 --- a/tools/build/feature/test-bpf.c +++ b/tools/build/feature/test-bpf.c @@ -9,6 +9,9 @@ # define __NR_bpf 321 # elif defined(__aarch64__) # define __NR_bpf 280 +# elif defined(__sparc__) +# define __NR_bpf 349 +# else # error __NR_bpf not defined. libbpf does not support your arch. # endif #endif diff --git a/tools/build/feature/test-sched_getcpu.c b/tools/build/feature/test-sched_getcpu.c new file mode 100644 index 000000000000..9c6b4cbffb1c --- /dev/null +++ b/tools/build/feature/test-sched_getcpu.c @@ -0,0 +1,9 @@ +#ifndef _GNU_SOURCE +#define _GNU_SOURCE +#endif +#include <sched.h> + +int main(void) +{ + return sched_getcpu(); +} diff --git a/tools/gpio/.gitignore b/tools/gpio/.gitignore new file mode 100644 index 000000000000..9e9dd4b681b2 --- /dev/null +++ b/tools/gpio/.gitignore @@ -0,0 +1,4 @@ +gpio-event-mon +gpio-hammer +lsgpio + diff --git a/tools/gpio/gpio-hammer.c b/tools/gpio/gpio-hammer.c index f1eab587dfea..4bcb234c0fca 100644 --- a/tools/gpio/gpio-hammer.c +++ b/tools/gpio/gpio-hammer.c @@ -38,7 +38,7 @@ int hammer_device(const char *device_name, unsigned int *lines, int nlines, memset(&data.values, 0, sizeof(data.values)); ret = gpiotools_request_linehandle(device_name, lines, nlines, GPIOHANDLE_REQUEST_OUTPUT, &data, - "gpio-hammler"); + "gpio-hammer"); if (ret < 0) goto exit_error; else diff --git a/tools/hv/bondvf.sh b/tools/hv/bondvf.sh index 4aa5369ffa4e..d85968cb1bf2 100755 --- a/tools/hv/bondvf.sh +++ b/tools/hv/bondvf.sh @@ -101,9 +101,25 @@ function create_bond_cfg_redhat { echo BONDING_OPTS=\"mode=active-backup miimon=100 primary=$2\" >>$fn } +function del_eth_cfg_ubuntu { + local fn=$cfgdir/interfaces + local tmpfl=$(mktemp) + + local nic_start='^[ \t]*(auto|iface|mapping|allow-.*)[ \t]+'$1 + local nic_end='^[ \t]*(auto|iface|mapping|allow-.*|source)' + + awk "/$nic_end/{x=0} x{next} /$nic_start/{x=1;next} 1" $fn >$tmpfl + + cp $tmpfl $fn + + rm $tmpfl +} + function create_eth_cfg_ubuntu { local fn=$cfgdir/interfaces + del_eth_cfg_ubuntu $1 + echo $'\n'auto $1 >>$fn echo iface $1 inet manual >>$fn echo bond-master $2 >>$fn @@ -119,6 +135,8 @@ function create_eth_cfg_pri_ubuntu { function create_bond_cfg_ubuntu { local fn=$cfgdir/interfaces + del_eth_cfg_ubuntu $1 + echo $'\n'auto $1 >>$fn echo iface $1 inet dhcp >>$fn echo bond-mode active-backup >>$fn diff --git a/tools/iio/iio_event_monitor.c b/tools/iio/iio_event_monitor.c index d9b7e0f306c6..b61245e1181d 100644 --- a/tools/iio/iio_event_monitor.c +++ b/tools/iio/iio_event_monitor.c @@ -57,6 +57,7 @@ static const char * const iio_chan_type_name_spec[] = { [IIO_RESISTANCE] = "resistance", [IIO_PH] = "ph", [IIO_UVINDEX] = "uvindex", + [IIO_GRAVITY] = "gravity", }; static const char * const iio_ev_type_text[] = { @@ -149,6 +150,7 @@ static bool event_is_known(struct iio_event_data *event) case IIO_RESISTANCE: case IIO_PH: case IIO_UVINDEX: + case IIO_GRAVITY: break; default: return false; diff --git a/tools/include/asm-generic/atomic-gcc.h b/tools/include/asm-generic/atomic-gcc.h index 2ba78c9f5701..5e9738f97bf3 100644 --- a/tools/include/asm-generic/atomic-gcc.h +++ b/tools/include/asm-generic/atomic-gcc.h @@ -60,4 +60,12 @@ static inline int atomic_dec_and_test(atomic_t *v) return __sync_sub_and_fetch(&v->counter, 1) == 0; } +#define cmpxchg(ptr, oldval, newval) \ + __sync_val_compare_and_swap(ptr, oldval, newval) + +static inline int atomic_cmpxchg(atomic_t *v, int oldval, int newval) +{ + return cmpxchg(&(v)->counter, oldval, newval); +} + #endif /* __TOOLS_ASM_GENERIC_ATOMIC_H */ diff --git a/tools/include/asm-generic/bitops/atomic.h b/tools/include/asm-generic/bitops/atomic.h index 18663f59d72f..68b8c1516c5a 100644 --- a/tools/include/asm-generic/bitops/atomic.h +++ b/tools/include/asm-generic/bitops/atomic.h @@ -20,4 +20,7 @@ static __always_inline int test_bit(unsigned int nr, const unsigned long *addr) (((unsigned long *)addr)[nr / __BITS_PER_LONG])) != 0; } +#define __set_bit(nr, addr) set_bit(nr, addr) +#define __clear_bit(nr, addr) clear_bit(nr, addr) + #endif /* _TOOLS_LINUX_ASM_GENERIC_BITOPS_ATOMIC_H_ */ diff --git a/tools/include/asm/bug.h b/tools/include/asm/bug.h index beda1a884b50..4790f047a89c 100644 --- a/tools/include/asm/bug.h +++ b/tools/include/asm/bug.h @@ -12,6 +12,14 @@ unlikely(__ret_warn_on); \ }) +#define WARN_ON(condition) ({ \ + int __ret_warn_on = !!(condition); \ + if (unlikely(__ret_warn_on)) \ + __WARN_printf("assertion failed at %s:%d\n", \ + __FILE__, __LINE__); \ + unlikely(__ret_warn_on); \ +}) + #define WARN_ON_ONCE(condition) ({ \ static int __warned; \ int __ret_warn_once = !!(condition); \ diff --git a/tools/include/linux/atomic.h b/tools/include/linux/atomic.h index 4e3d3d18ebab..9f21fc2b092b 100644 --- a/tools/include/linux/atomic.h +++ b/tools/include/linux/atomic.h @@ -3,4 +3,10 @@ #include <asm/atomic.h> +/* atomic_cmpxchg_relaxed */ +#ifndef atomic_cmpxchg_relaxed +#define atomic_cmpxchg_relaxed atomic_cmpxchg +#define atomic_cmpxchg_release atomic_cmpxchg +#endif /* atomic_cmpxchg_relaxed */ + #endif /* __TOOLS_LINUX_ATOMIC_H */ diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h index eef41d500e9e..e8b9f518e36b 100644 --- a/tools/include/linux/bitmap.h +++ b/tools/include/linux/bitmap.h @@ -4,6 +4,7 @@ #include <string.h> #include <linux/bitops.h> #include <stdlib.h> +#include <linux/kernel.h> #define DECLARE_BITMAP(name,bits) \ unsigned long name[BITS_TO_LONGS(bits)] diff --git a/tools/include/linux/bitops.h b/tools/include/linux/bitops.h index fc446343ff41..1aecad369af5 100644 --- a/tools/include/linux/bitops.h +++ b/tools/include/linux/bitops.h @@ -2,7 +2,6 @@ #define _TOOLS_LINUX_BITOPS_H_ #include <asm/types.h> -#include <linux/kernel.h> #include <linux/compiler.h> #ifndef __WORDSIZE diff --git a/tools/include/linux/bug.h b/tools/include/linux/bug.h new file mode 100644 index 000000000000..8e4a4f49135d --- /dev/null +++ b/tools/include/linux/bug.h @@ -0,0 +1,10 @@ +#ifndef _TOOLS_PERF_LINUX_BUG_H +#define _TOOLS_PERF_LINUX_BUG_H + +/* Force a compilation error if condition is true, but also produce a + result (of value 0 and type size_t), so the expression can be used + e.g. in a structure initializer (or where-ever else comma expressions + aren't permitted). */ +#define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:-!!(e); })) + +#endif /* _TOOLS_PERF_LINUX_BUG_H */ diff --git a/tools/include/linux/compiler-gcc.h b/tools/include/linux/compiler-gcc.h new file mode 100644 index 000000000000..825d44f89a29 --- /dev/null +++ b/tools/include/linux/compiler-gcc.h @@ -0,0 +1,21 @@ +#ifndef _TOOLS_LINUX_COMPILER_H_ +#error "Please don't include <linux/compiler-gcc.h> directly, include <linux/compiler.h> instead." +#endif + +/* + * Common definitions for all gcc versions go here. + */ +#define GCC_VERSION (__GNUC__ * 10000 \ + + __GNUC_MINOR__ * 100 \ + + __GNUC_PATCHLEVEL__) + +#if GCC_VERSION >= 70000 && !defined(__CHECKER__) +# define __fallthrough __attribute__ ((fallthrough)) +#endif + +#if GCC_VERSION >= 40300 +# define __compiletime_error(message) __attribute__((error(message))) +#endif /* GCC_VERSION >= 40300 */ + +/* &a[0] degrades to a pointer: a different type from an array */ +#define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h index e33fc1df3935..23299d7e7160 100644 --- a/tools/include/linux/compiler.h +++ b/tools/include/linux/compiler.h @@ -1,6 +1,14 @@ #ifndef _TOOLS_LINUX_COMPILER_H_ #define _TOOLS_LINUX_COMPILER_H_ +#ifdef __GNUC__ +#include <linux/compiler-gcc.h> +#endif + +#ifndef __compiletime_error +# define __compiletime_error(message) +#endif + /* Optimization barrier */ /* The "volatile" is due to gcc bugs */ #define barrier() __asm__ __volatile__("": : :"memory") @@ -9,6 +17,11 @@ # define __always_inline inline __attribute__((always_inline)) #endif +/* Are two types/vars the same type (ignoring qualifiers)? */ +#ifndef __same_type +# define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b)) +#endif + #ifdef __ANDROID__ /* * FIXME: Big hammer to get rid of tons of: @@ -21,6 +34,8 @@ #endif #define __user +#define __rcu +#define __read_mostly #ifndef __attribute_const__ # define __attribute_const__ @@ -50,6 +65,8 @@ # define unlikely(x) __builtin_expect(!!(x), 0) #endif +#define uninitialized_var(x) x = *(&(x)) + #define ACCESS_ONCE(x) (*(volatile typeof(x) *)&(x)) #include <linux/types.h> @@ -126,4 +143,9 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s #define WRITE_ONCE(x, val) \ ({ union { typeof(x) __val; char __c[1]; } __u = { .__val = (val) }; __write_once_size(&(x), __u.__c, sizeof(x)); __u.__val; }) + +#ifndef __fallthrough +# define __fallthrough +#endif + #endif /* _TOOLS_LINUX_COMPILER_H */ diff --git a/tools/include/linux/filter.h b/tools/include/linux/filter.h index 122153b16ea4..390d7c9685fd 100644 --- a/tools/include/linux/filter.h +++ b/tools/include/linux/filter.h @@ -168,6 +168,16 @@ .off = OFF, \ .imm = 0 }) +/* Atomic memory add, *(uint *)(dst_reg + off16) += src_reg */ + +#define BPF_STX_XADD(SIZE, DST, SRC, OFF) \ + ((struct bpf_insn) { \ + .code = BPF_STX | BPF_SIZE(SIZE) | BPF_XADD, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = OFF, \ + .imm = 0 }) + /* Memory store, *(uint *) (dst_reg + off16) = imm32 */ #define BPF_ST_MEM(SIZE, DST, OFF, IMM) \ diff --git a/tools/include/linux/hashtable.h b/tools/include/linux/hashtable.h index c65cc0aa2659..251eabf2a05e 100644 --- a/tools/include/linux/hashtable.h +++ b/tools/include/linux/hashtable.h @@ -13,10 +13,6 @@ #include <linux/hash.h> #include <linux/log2.h> -#ifndef ARRAY_SIZE -#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) -#endif - #define DEFINE_HASHTABLE(name, bits) \ struct hlist_head name[1 << (bits)] = \ { [0 ... ((1 << (bits)) - 1)] = HLIST_HEAD_INIT } diff --git a/tools/include/linux/kernel.h b/tools/include/linux/kernel.h index 28607db02bd3..73ccc48126bb 100644 --- a/tools/include/linux/kernel.h +++ b/tools/include/linux/kernel.h @@ -4,6 +4,11 @@ #include <stdarg.h> #include <stddef.h> #include <assert.h> +#include <linux/compiler.h> + +#ifndef UINT_MAX +#define UINT_MAX (~0U) +#endif #define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d)) @@ -72,6 +77,8 @@ int vscnprintf(char *buf, size_t size, const char *fmt, va_list args); int scnprintf(char * buf, size_t size, const char * fmt, ...); +#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]) + __must_be_array(arr)) + /* * This looks more complex than it should be. But we need to * get the type for the ~ right in round_down (it needs to be diff --git a/tools/include/linux/log2.h b/tools/include/linux/log2.h index 41446668ccce..0325cefc2220 100644 --- a/tools/include/linux/log2.h +++ b/tools/include/linux/log2.h @@ -12,11 +12,8 @@ #ifndef _TOOLS_LINUX_LOG2_H #define _TOOLS_LINUX_LOG2_H -/* - * deal with unrepresentable constant logarithms - */ -extern __attribute__((const, noreturn)) -int ____ilog2_NaN(void); +#include <linux/bitops.h> +#include <linux/types.h> /* * non-constant log of base 2 calculators @@ -78,7 +75,7 @@ unsigned long __rounddown_pow_of_two(unsigned long n) #define ilog2(n) \ ( \ __builtin_constant_p(n) ? ( \ - (n) < 1 ? ____ilog2_NaN() : \ + (n) < 2 ? 0 : \ (n) & (1ULL << 63) ? 63 : \ (n) & (1ULL << 62) ? 62 : \ (n) & (1ULL << 61) ? 61 : \ @@ -141,10 +138,7 @@ unsigned long __rounddown_pow_of_two(unsigned long n) (n) & (1ULL << 4) ? 4 : \ (n) & (1ULL << 3) ? 3 : \ (n) & (1ULL << 2) ? 2 : \ - (n) & (1ULL << 1) ? 1 : \ - (n) & (1ULL << 0) ? 0 : \ - ____ilog2_NaN() \ - ) : \ + 1 ) : \ (sizeof(n) <= 4) ? \ __ilog2_u32(n) : \ __ilog2_u64(n) \ diff --git a/tools/include/linux/refcount.h b/tools/include/linux/refcount.h new file mode 100644 index 000000000000..a0177c1f55b1 --- /dev/null +++ b/tools/include/linux/refcount.h @@ -0,0 +1,151 @@ +#ifndef _TOOLS_LINUX_REFCOUNT_H +#define _TOOLS_LINUX_REFCOUNT_H + +/* + * Variant of atomic_t specialized for reference counts. + * + * The interface matches the atomic_t interface (to aid in porting) but only + * provides the few functions one should use for reference counting. + * + * It differs in that the counter saturates at UINT_MAX and will not move once + * there. This avoids wrapping the counter and causing 'spurious' + * use-after-free issues. + * + * Memory ordering rules are slightly relaxed wrt regular atomic_t functions + * and provide only what is strictly required for refcounts. + * + * The increments are fully relaxed; these will not provide ordering. The + * rationale is that whatever is used to obtain the object we're increasing the + * reference count on will provide the ordering. For locked data structures, + * its the lock acquire, for RCU/lockless data structures its the dependent + * load. + * + * Do note that inc_not_zero() provides a control dependency which will order + * future stores against the inc, this ensures we'll never modify the object + * if we did not in fact acquire a reference. + * + * The decrements will provide release order, such that all the prior loads and + * stores will be issued before, it also provides a control dependency, which + * will order us against the subsequent free(). + * + * The control dependency is against the load of the cmpxchg (ll/sc) that + * succeeded. This means the stores aren't fully ordered, but this is fine + * because the 1->0 transition indicates no concurrency. + * + * Note that the allocator is responsible for ordering things between free() + * and alloc(). + * + */ + +#include <linux/atomic.h> +#include <linux/kernel.h> + +#ifdef NDEBUG +#define REFCOUNT_WARN(cond, str) (void)(cond) +#define __refcount_check +#else +#define REFCOUNT_WARN(cond, str) BUG_ON(cond) +#define __refcount_check __must_check +#endif + +typedef struct refcount_struct { + atomic_t refs; +} refcount_t; + +#define REFCOUNT_INIT(n) { .refs = ATOMIC_INIT(n), } + +static inline void refcount_set(refcount_t *r, unsigned int n) +{ + atomic_set(&r->refs, n); +} + +static inline unsigned int refcount_read(const refcount_t *r) +{ + return atomic_read(&r->refs); +} + +/* + * Similar to atomic_inc_not_zero(), will saturate at UINT_MAX and WARN. + * + * Provides no memory ordering, it is assumed the caller has guaranteed the + * object memory to be stable (RCU, etc.). It does provide a control dependency + * and thereby orders future stores. See the comment on top. + */ +static inline __refcount_check +bool refcount_inc_not_zero(refcount_t *r) +{ + unsigned int old, new, val = atomic_read(&r->refs); + + for (;;) { + new = val + 1; + + if (!val) + return false; + + if (unlikely(!new)) + return true; + + old = atomic_cmpxchg_relaxed(&r->refs, val, new); + if (old == val) + break; + + val = old; + } + + REFCOUNT_WARN(new == UINT_MAX, "refcount_t: saturated; leaking memory.\n"); + + return true; +} + +/* + * Similar to atomic_inc(), will saturate at UINT_MAX and WARN. + * + * Provides no memory ordering, it is assumed the caller already has a + * reference on the object, will WARN when this is not so. + */ +static inline void refcount_inc(refcount_t *r) +{ + REFCOUNT_WARN(!refcount_inc_not_zero(r), "refcount_t: increment on 0; use-after-free.\n"); +} + +/* + * Similar to atomic_dec_and_test(), it will WARN on underflow and fail to + * decrement when saturated at UINT_MAX. + * + * Provides release memory ordering, such that prior loads and stores are done + * before, and provides a control dependency such that free() must come after. + * See the comment on top. + */ +static inline __refcount_check +bool refcount_sub_and_test(unsigned int i, refcount_t *r) +{ + unsigned int old, new, val = atomic_read(&r->refs); + + for (;;) { + if (unlikely(val == UINT_MAX)) + return false; + + new = val - i; + if (new > val) { + REFCOUNT_WARN(new > val, "refcount_t: underflow; use-after-free.\n"); + return false; + } + + old = atomic_cmpxchg_release(&r->refs, val, new); + if (old == val) + break; + + val = old; + } + + return !new; +} + +static inline __refcount_check +bool refcount_dec_and_test(refcount_t *r) +{ + return refcount_sub_and_test(1, r); +} + + +#endif /* _ATOMIC_LINUX_REFCOUNT_H */ diff --git a/tools/include/linux/spinlock.h b/tools/include/linux/spinlock.h new file mode 100644 index 000000000000..58397dcb19d6 --- /dev/null +++ b/tools/include/linux/spinlock.h @@ -0,0 +1,5 @@ +#define spinlock_t pthread_mutex_t +#define DEFINE_SPINLOCK(x) pthread_mutex_t x = PTHREAD_MUTEX_INITIALIZER; + +#define spin_lock_irqsave(x, f) (void)f, pthread_mutex_lock(x) +#define spin_unlock_irqrestore(x, f) (void)f, pthread_mutex_unlock(x) diff --git a/tools/include/linux/string.h b/tools/include/linux/string.h index f436d2420a18..d62b56cf8c12 100644 --- a/tools/include/linux/string.h +++ b/tools/include/linux/string.h @@ -18,4 +18,6 @@ extern size_t strlcpy(char *dest, const char *src, size_t size); char *str_error_r(int errnum, char *buf, size_t buflen); +int prefixcmp(const char *str, const char *prefix); + #endif /* _LINUX_STRING_H_ */ diff --git a/tools/include/linux/types.h b/tools/include/linux/types.h index c24b3e3ae296..77a28a26a670 100644 --- a/tools/include/linux/types.h +++ b/tools/include/linux/types.h @@ -7,6 +7,7 @@ #define __SANE_USERSPACE_TYPES__ /* For PPC64, to get LL64 types */ #include <asm/types.h> +#include <asm/posix_types.h> struct page; struct kmem_cache; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index d2b0ac799d03..e553529929f6 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -63,6 +63,12 @@ struct bpf_insn { __s32 imm; /* signed immediate constant */ }; +/* Key of an a BPF_MAP_TYPE_LPM_TRIE entry */ +struct bpf_lpm_trie_key { + __u32 prefixlen; /* up to 32 for AF_INET, 128 for AF_INET6 */ + __u8 data[0]; /* Arbitrary size */ +}; + /* BPF syscall commands, see bpf(2) man-page for details. */ enum bpf_cmd { BPF_MAP_CREATE, @@ -75,6 +81,7 @@ enum bpf_cmd { BPF_OBJ_GET, BPF_PROG_ATTACH, BPF_PROG_DETACH, + BPF_PROG_TEST_RUN, }; enum bpf_map_type { @@ -89,6 +96,9 @@ enum bpf_map_type { BPF_MAP_TYPE_CGROUP_ARRAY, BPF_MAP_TYPE_LRU_HASH, BPF_MAP_TYPE_LRU_PERCPU_HASH, + BPF_MAP_TYPE_LPM_TRIE, + BPF_MAP_TYPE_ARRAY_OF_MAPS, + BPF_MAP_TYPE_HASH_OF_MAPS, }; enum bpf_prog_type { @@ -145,6 +155,7 @@ union bpf_attr { __u32 value_size; /* size of value in bytes */ __u32 max_entries; /* max number of entries in a map */ __u32 map_flags; /* prealloc or not */ + __u32 inner_map_fd; /* fd pointing to the inner map */ }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -179,6 +190,17 @@ union bpf_attr { __u32 attach_type; __u32 attach_flags; }; + + struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */ + __u32 prog_fd; + __u32 retval; + __u32 data_size_in; + __u32 data_size_out; + __aligned_u64 data_in; + __aligned_u64 data_out; + __u32 repeat; + __u32 duration; + } test; } __attribute__((aligned(8))); /* BPF helper function descriptions: @@ -437,6 +459,30 @@ union bpf_attr { * @xdp_md: pointer to xdp_md * @delta: An positive/negative integer to be added to xdp_md.data * Return: 0 on success or negative on error + * + * int bpf_probe_read_str(void *dst, int size, const void *unsafe_ptr) + * Copy a NUL terminated string from unsafe address. In case the string + * length is smaller than size, the target is not padded with further NUL + * bytes. In case the string length is larger than size, just count-1 + * bytes are copied and the last byte is set to NUL. + * @dst: destination address + * @size: maximum number of bytes to copy, including the trailing NUL + * @unsafe_ptr: unsafe address + * Return: + * > 0 length of the string including the trailing NUL on success + * < 0 error + * + * u64 bpf_get_socket_cookie(skb) + * Get the cookie for the socket stored inside sk_buff. + * @skb: pointer to skb + * Return: 8 Bytes non-decreasing number on success or 0 if the socket + * field is missing inside sk_buff + * + * u32 bpf_get_socket_uid(skb) + * Get the owner uid of the socket stored inside sk_buff. + * @skb: pointer to skb + * Return: uid of the socket owner on success or 0 if the socket pointer + * inside sk_buff is NULL */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -483,7 +529,10 @@ union bpf_attr { FN(set_hash_invalid), \ FN(get_numa_node_id), \ FN(skb_change_head), \ - FN(xdp_adjust_head), + FN(xdp_adjust_head), \ + FN(probe_read_str), \ + FN(get_socket_cookie), \ + FN(get_socket_uid), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -509,6 +558,7 @@ enum bpf_func_id { /* BPF_FUNC_l4_csum_replace flags. */ #define BPF_F_PSEUDO_HDR (1ULL << 4) #define BPF_F_MARK_MANGLED_0 (1ULL << 5) +#define BPF_F_MARK_ENFORCE (1ULL << 6) /* BPF_FUNC_clone_redirect and BPF_FUNC_redirect flags. */ #define BPF_F_INGRESS (1ULL << 0) @@ -553,6 +603,7 @@ struct __sk_buff { __u32 tc_classid; __u32 data; __u32 data_end; + __u32 napi_id; }; struct bpf_tunnel_key { diff --git a/tools/include/uapi/linux/bpf_perf_event.h b/tools/include/uapi/linux/bpf_perf_event.h new file mode 100644 index 000000000000..067427259820 --- /dev/null +++ b/tools/include/uapi/linux/bpf_perf_event.h @@ -0,0 +1,18 @@ +/* Copyright (c) 2016 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#ifndef _UAPI__LINUX_BPF_PERF_EVENT_H__ +#define _UAPI__LINUX_BPF_PERF_EVENT_H__ + +#include <linux/types.h> +#include <linux/ptrace.h> + +struct bpf_perf_event_data { + struct pt_regs regs; + __u64 sample_period; +}; + +#endif /* _UAPI__LINUX_BPF_PERF_EVENT_H__ */ diff --git a/tools/include/uapi/linux/fcntl.h b/tools/include/uapi/linux/fcntl.h new file mode 100644 index 000000000000..813afd6eee71 --- /dev/null +++ b/tools/include/uapi/linux/fcntl.h @@ -0,0 +1,72 @@ +#ifndef _UAPI_LINUX_FCNTL_H +#define _UAPI_LINUX_FCNTL_H + +#include <asm/fcntl.h> + +#define F_SETLEASE (F_LINUX_SPECIFIC_BASE + 0) +#define F_GETLEASE (F_LINUX_SPECIFIC_BASE + 1) + +/* + * Cancel a blocking posix lock; internal use only until we expose an + * asynchronous lock api to userspace: + */ +#define F_CANCELLK (F_LINUX_SPECIFIC_BASE + 5) + +/* Create a file descriptor with FD_CLOEXEC set. */ +#define F_DUPFD_CLOEXEC (F_LINUX_SPECIFIC_BASE + 6) + +/* + * Request nofications on a directory. + * See below for events that may be notified. + */ +#define F_NOTIFY (F_LINUX_SPECIFIC_BASE+2) + +/* + * Set and get of pipe page size array + */ +#define F_SETPIPE_SZ (F_LINUX_SPECIFIC_BASE + 7) +#define F_GETPIPE_SZ (F_LINUX_SPECIFIC_BASE + 8) + +/* + * Set/Get seals + */ +#define F_ADD_SEALS (F_LINUX_SPECIFIC_BASE + 9) +#define F_GET_SEALS (F_LINUX_SPECIFIC_BASE + 10) + +/* + * Types of seals + */ +#define F_SEAL_SEAL 0x0001 /* prevent further seals from being set */ +#define F_SEAL_SHRINK 0x0002 /* prevent file from shrinking */ +#define F_SEAL_GROW 0x0004 /* prevent file from growing */ +#define F_SEAL_WRITE 0x0008 /* prevent writes */ +/* (1U << 31) is reserved for signed error codes */ + +/* + * Types of directory notifications that may be requested. + */ +#define DN_ACCESS 0x00000001 /* File accessed */ +#define DN_MODIFY 0x00000002 /* File modified */ +#define DN_CREATE 0x00000004 /* File created */ +#define DN_DELETE 0x00000008 /* File removed */ +#define DN_RENAME 0x00000010 /* File renamed */ +#define DN_ATTRIB 0x00000020 /* File changed attibutes */ +#define DN_MULTISHOT 0x80000000 /* Don't remove notifier */ + +#define AT_FDCWD -100 /* Special value used to indicate + openat should use the current + working directory. */ +#define AT_SYMLINK_NOFOLLOW 0x100 /* Do not follow symbolic links. */ +#define AT_REMOVEDIR 0x200 /* Remove directory instead of + unlinking file. */ +#define AT_SYMLINK_FOLLOW 0x400 /* Follow symbolic links. */ +#define AT_NO_AUTOMOUNT 0x800 /* Suppress terminal automount traversal */ +#define AT_EMPTY_PATH 0x1000 /* Allow empty relative pathname */ + +#define AT_STATX_SYNC_TYPE 0x6000 /* Type of synchronisation required from statx() */ +#define AT_STATX_SYNC_AS_STAT 0x0000 /* - Do whatever stat() does */ +#define AT_STATX_FORCE_SYNC 0x2000 /* - Force the attributes to be sync'd with the server */ +#define AT_STATX_DONT_SYNC 0x4000 /* - Don't sync attributes with the server */ + + +#endif /* _UAPI_LINUX_FCNTL_H */ diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index c66a485a24ac..b1c0b187acfe 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -344,7 +344,8 @@ struct perf_event_attr { use_clockid : 1, /* use @clockid for time fields */ context_switch : 1, /* context switch data */ write_backward : 1, /* Write ring buffer from end to beginning */ - __reserved_1 : 36; + namespaces : 1, /* include namespaces data */ + __reserved_1 : 35; union { __u32 wakeup_events; /* wakeup every n events */ @@ -610,6 +611,23 @@ struct perf_event_header { __u16 size; }; +struct perf_ns_link_info { + __u64 dev; + __u64 ino; +}; + +enum { + NET_NS_INDEX = 0, + UTS_NS_INDEX = 1, + IPC_NS_INDEX = 2, + PID_NS_INDEX = 3, + USER_NS_INDEX = 4, + MNT_NS_INDEX = 5, + CGROUP_NS_INDEX = 6, + + NR_NAMESPACES, /* number of available namespaces */ +}; + enum perf_event_type { /* @@ -862,6 +880,18 @@ enum perf_event_type { */ PERF_RECORD_SWITCH_CPU_WIDE = 15, + /* + * struct { + * struct perf_event_header header; + * u32 pid; + * u32 tid; + * u64 nr_namespaces; + * { u64 dev, inode; } [nr_namespaces]; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_NAMESPACES = 16, + PERF_RECORD_MAX, /* non-ABI */ }; @@ -885,12 +915,14 @@ enum perf_callchain_context { */ #define PERF_AUX_FLAG_TRUNCATED 0x01 /* record was truncated to fit */ #define PERF_AUX_FLAG_OVERWRITE 0x02 /* snapshot from overwrite mode */ +#define PERF_AUX_FLAG_PARTIAL 0x04 /* record contains gaps */ #define PERF_FLAG_FD_NO_GROUP (1UL << 0) #define PERF_FLAG_FD_OUTPUT (1UL << 1) #define PERF_FLAG_PID_CGROUP (1UL << 2) /* pid=cgroup id, per-cpu mode only */ #define PERF_FLAG_FD_CLOEXEC (1UL << 3) /* O_CLOEXEC */ +#if defined(__LITTLE_ENDIAN_BITFIELD) union perf_mem_data_src { __u64 val; struct { @@ -902,6 +934,21 @@ union perf_mem_data_src { mem_rsvd:31; }; }; +#elif defined(__BIG_ENDIAN_BITFIELD) +union perf_mem_data_src { + __u64 val; + struct { + __u64 mem_rsvd:31, + mem_dtlb:7, /* tlb access */ + mem_lock:2, /* lock instr */ + mem_snoop:5, /* snoop mode */ + mem_lvl:14, /* memory hierarchy level */ + mem_op:5; /* type of opcode */ + }; +}; +#else +#error "Unknown endianness" +#endif /* type of opcode (load/store/prefetch,code) */ #define PERF_MEM_OP_NA 0x01 /* not available */ diff --git a/tools/include/uapi/linux/stat.h b/tools/include/uapi/linux/stat.h new file mode 100644 index 000000000000..d538897b8e08 --- /dev/null +++ b/tools/include/uapi/linux/stat.h @@ -0,0 +1,177 @@ +#ifndef _UAPI_LINUX_STAT_H +#define _UAPI_LINUX_STAT_H + +#include <linux/types.h> + +#if defined(__KERNEL__) || !defined(__GLIBC__) || (__GLIBC__ < 2) + +#define S_IFMT 00170000 +#define S_IFSOCK 0140000 +#define S_IFLNK 0120000 +#define S_IFREG 0100000 +#define S_IFBLK 0060000 +#define S_IFDIR 0040000 +#define S_IFCHR 0020000 +#define S_IFIFO 0010000 +#define S_ISUID 0004000 +#define S_ISGID 0002000 +#define S_ISVTX 0001000 + +#define S_ISLNK(m) (((m) & S_IFMT) == S_IFLNK) +#define S_ISREG(m) (((m) & S_IFMT) == S_IFREG) +#define S_ISDIR(m) (((m) & S_IFMT) == S_IFDIR) +#define S_ISCHR(m) (((m) & S_IFMT) == S_IFCHR) +#define S_ISBLK(m) (((m) & S_IFMT) == S_IFBLK) +#define S_ISFIFO(m) (((m) & S_IFMT) == S_IFIFO) +#define S_ISSOCK(m) (((m) & S_IFMT) == S_IFSOCK) + +#define S_IRWXU 00700 +#define S_IRUSR 00400 +#define S_IWUSR 00200 +#define S_IXUSR 00100 + +#define S_IRWXG 00070 +#define S_IRGRP 00040 +#define S_IWGRP 00020 +#define S_IXGRP 00010 + +#define S_IRWXO 00007 +#define S_IROTH 00004 +#define S_IWOTH 00002 +#define S_IXOTH 00001 + +#endif + +/* + * Timestamp structure for the timestamps in struct statx. + * + * tv_sec holds the number of seconds before (negative) or after (positive) + * 00:00:00 1st January 1970 UTC. + * + * tv_nsec holds a number of nanoseconds before (0..-999,999,999 if tv_sec is + * negative) or after (0..999,999,999 if tv_sec is positive) the tv_sec time. + * + * Note that if both tv_sec and tv_nsec are non-zero, then the two values must + * either be both positive or both negative. + * + * __reserved is held in case we need a yet finer resolution. + */ +struct statx_timestamp { + __s64 tv_sec; + __s32 tv_nsec; + __s32 __reserved; +}; + +/* + * Structures for the extended file attribute retrieval system call + * (statx()). + * + * The caller passes a mask of what they're specifically interested in as a + * parameter to statx(). What statx() actually got will be indicated in + * st_mask upon return. + * + * For each bit in the mask argument: + * + * - if the datum is not supported: + * + * - the bit will be cleared, and + * + * - the datum will be set to an appropriate fabricated value if one is + * available (eg. CIFS can take a default uid and gid), otherwise + * + * - the field will be cleared; + * + * - otherwise, if explicitly requested: + * + * - the datum will be synchronised to the server if AT_STATX_FORCE_SYNC is + * set or if the datum is considered out of date, and + * + * - the field will be filled in and the bit will be set; + * + * - otherwise, if not requested, but available in approximate form without any + * effort, it will be filled in anyway, and the bit will be set upon return + * (it might not be up to date, however, and no attempt will be made to + * synchronise the internal state first); + * + * - otherwise the field and the bit will be cleared before returning. + * + * Items in STATX_BASIC_STATS may be marked unavailable on return, but they + * will have values installed for compatibility purposes so that stat() and + * co. can be emulated in userspace. + */ +struct statx { + /* 0x00 */ + __u32 stx_mask; /* What results were written [uncond] */ + __u32 stx_blksize; /* Preferred general I/O size [uncond] */ + __u64 stx_attributes; /* Flags conveying information about the file [uncond] */ + /* 0x10 */ + __u32 stx_nlink; /* Number of hard links */ + __u32 stx_uid; /* User ID of owner */ + __u32 stx_gid; /* Group ID of owner */ + __u16 stx_mode; /* File mode */ + __u16 __spare0[1]; + /* 0x20 */ + __u64 stx_ino; /* Inode number */ + __u64 stx_size; /* File size */ + __u64 stx_blocks; /* Number of 512-byte blocks allocated */ + __u64 stx_attributes_mask; /* Mask to show what's supported in stx_attributes */ + /* 0x40 */ + struct statx_timestamp stx_atime; /* Last access time */ + struct statx_timestamp stx_btime; /* File creation time */ + struct statx_timestamp stx_ctime; /* Last attribute change time */ + struct statx_timestamp stx_mtime; /* Last data modification time */ + /* 0x80 */ + __u32 stx_rdev_major; /* Device ID of special file [if bdev/cdev] */ + __u32 stx_rdev_minor; + __u32 stx_dev_major; /* ID of device containing file [uncond] */ + __u32 stx_dev_minor; + /* 0x90 */ + __u64 __spare2[14]; /* Spare space for future expansion */ + /* 0x100 */ +}; + +/* + * Flags to be stx_mask + * + * Query request/result mask for statx() and struct statx::stx_mask. + * + * These bits should be set in the mask argument of statx() to request + * particular items when calling statx(). + */ +#define STATX_TYPE 0x00000001U /* Want/got stx_mode & S_IFMT */ +#define STATX_MODE 0x00000002U /* Want/got stx_mode & ~S_IFMT */ +#define STATX_NLINK 0x00000004U /* Want/got stx_nlink */ +#define STATX_UID 0x00000008U /* Want/got stx_uid */ +#define STATX_GID 0x00000010U /* Want/got stx_gid */ +#define STATX_ATIME 0x00000020U /* Want/got stx_atime */ +#define STATX_MTIME 0x00000040U /* Want/got stx_mtime */ +#define STATX_CTIME 0x00000080U /* Want/got stx_ctime */ +#define STATX_INO 0x00000100U /* Want/got stx_ino */ +#define STATX_SIZE 0x00000200U /* Want/got stx_size */ +#define STATX_BLOCKS 0x00000400U /* Want/got stx_blocks */ +#define STATX_BASIC_STATS 0x000007ffU /* The stuff in the normal stat struct */ +#define STATX_BTIME 0x00000800U /* Want/got stx_btime */ +#define STATX_ALL 0x00000fffU /* All currently supported flags */ +#define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */ + +/* + * Attributes to be found in stx_attributes and masked in stx_attributes_mask. + * + * These give information about the features or the state of a file that might + * be of use to ordinary userspace programs such as GUIs or ls rather than + * specialised tools. + * + * Note that the flags marked [I] correspond to generic FS_IOC_FLAGS + * semantically. Where possible, the numerical value is picked to correspond + * also. + */ +#define STATX_ATTR_COMPRESSED 0x00000004 /* [I] File is compressed by the fs */ +#define STATX_ATTR_IMMUTABLE 0x00000010 /* [I] File is marked immutable */ +#define STATX_ATTR_APPEND 0x00000020 /* [I] File is append-only */ +#define STATX_ATTR_NODUMP 0x00000040 /* [I] File is not to be dumped */ +#define STATX_ATTR_ENCRYPTED 0x00000800 /* [I] File requires key to decrypt in fs */ + +#define STATX_ATTR_AUTOMOUNT 0x00001000 /* Dir: Automount trigger */ + + +#endif /* _UAPI_LINUX_STAT_H */ diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat index 581278c58488..8f74ed8e7237 100755 --- a/tools/kvm/kvm_stat/kvm_stat +++ b/tools/kvm/kvm_stat/kvm_stat @@ -30,8 +30,8 @@ import fcntl import resource import struct import re +import subprocess from collections import defaultdict -from time import sleep VMX_EXIT_REASONS = { 'EXCEPTION_NMI': 0, @@ -225,6 +225,7 @@ IOCTL_NUMBERS = { 'RESET': 0x00002403, } + class Arch(object): """Encapsulates global architecture specific data. @@ -255,12 +256,14 @@ class Arch(object): return ArchX86(SVM_EXIT_REASONS) return + class ArchX86(Arch): def __init__(self, exit_reasons): self.sc_perf_evt_open = 298 self.ioctl_numbers = IOCTL_NUMBERS self.exit_reasons = exit_reasons + class ArchPPC(Arch): def __init__(self): self.sc_perf_evt_open = 319 @@ -275,12 +278,14 @@ class ArchPPC(Arch): self.ioctl_numbers['SET_FILTER'] = 0x80002406 | char_ptr_size << 16 self.exit_reasons = {} + class ArchA64(Arch): def __init__(self): self.sc_perf_evt_open = 241 self.ioctl_numbers = IOCTL_NUMBERS self.exit_reasons = AARCH64_EXIT_REASONS + class ArchS390(Arch): def __init__(self): self.sc_perf_evt_open = 331 @@ -316,6 +321,61 @@ def parse_int_list(list_string): return integers +def get_pid_from_gname(gname): + """Fuzzy function to convert guest name to QEMU process pid. + + Returns a list of potential pids, can be empty if no match found. + Throws an exception on processing errors. + + """ + pids = [] + try: + child = subprocess.Popen(['ps', '-A', '--format', 'pid,args'], + stdout=subprocess.PIPE) + except: + raise Exception + for line in child.stdout: + line = line.lstrip().split(' ', 1) + # perform a sanity check before calling the more expensive + # function to possibly extract the guest name + if ' -name ' in line[1] and gname == get_gname_from_pid(line[0]): + pids.append(int(line[0])) + child.stdout.close() + + return pids + + +def get_gname_from_pid(pid): + """Returns the guest name for a QEMU process pid. + + Extracts the guest name from the QEMU comma line by processing the '-name' + option. Will also handle names specified out of sequence. + + """ + name = '' + try: + line = open('/proc/{}/cmdline'.format(pid), 'rb').read().split('\0') + parms = line[line.index('-name') + 1].split(',') + while '' in parms: + # commas are escaped (i.e. ',,'), hence e.g. 'foo,bar' results in + # ['foo', '', 'bar'], which we revert here + idx = parms.index('') + parms[idx - 1] += ',' + parms[idx + 1] + del parms[idx:idx+2] + # the '-name' switch allows for two ways to specify the guest name, + # where the plain name overrides the name specified via 'guest=' + for arg in parms: + if '=' not in arg: + name = arg + break + if arg[:6] == 'guest=': + name = arg[6:] + except (ValueError, IOError, IndexError): + pass + + return name + + def get_online_cpus(): """Returns a list of cpu id integers.""" with open('/sys/devices/system/cpu/online') as cpu_list: @@ -342,6 +402,7 @@ def get_filters(): libc = ctypes.CDLL('libc.so.6', use_errno=True) syscall = libc.syscall + class perf_event_attr(ctypes.Structure): """Struct that holds the necessary data to set up a trace event. @@ -370,6 +431,7 @@ class perf_event_attr(ctypes.Structure): self.size = ctypes.sizeof(self) self.read_format = PERF_FORMAT_GROUP + def perf_event_open(attr, pid, cpu, group_fd, flags): """Wrapper for the sys_perf_evt_open() syscall. @@ -395,6 +457,7 @@ PERF_FORMAT_GROUP = 1 << 3 PATH_DEBUGFS_TRACING = '/sys/kernel/debug/tracing' PATH_DEBUGFS_KVM = '/sys/kernel/debug/kvm' + class Group(object): """Represents a perf event group.""" @@ -427,6 +490,7 @@ class Group(object): struct.unpack(read_format, os.read(self.events[0].fd, length)))) + class Event(object): """Represents a performance event and manages its life cycle.""" def __init__(self, name, group, trace_cpu, trace_pid, trace_point, @@ -510,6 +574,7 @@ class Event(object): """Resets the count of the trace event in the kernel.""" fcntl.ioctl(self.fd, ARCH.ioctl_numbers['RESET'], 0) + class TracepointProvider(object): """Data provider for the stats class. @@ -551,6 +616,7 @@ class TracepointProvider(object): def setup_traces(self): """Creates all event and group objects needed to be able to retrieve data.""" + fields = self.get_available_fields() if self._pid > 0: # Fetch list of all threads of the monitored pid, as qemu # starts a thread for each vcpu. @@ -561,7 +627,7 @@ class TracepointProvider(object): # The constant is needed as a buffer for python libs, std # streams and other files that the script opens. - newlim = len(groupids) * len(self._fields) + 50 + newlim = len(groupids) * len(fields) + 50 try: softlim_, hardlim = resource.getrlimit(resource.RLIMIT_NOFILE) @@ -577,7 +643,7 @@ class TracepointProvider(object): for groupid in groupids: group = Group() - for name in self._fields: + for name in fields: tracepoint = name tracefilter = None match = re.match(r'(.*)\((.*)\)', name) @@ -650,13 +716,23 @@ class TracepointProvider(object): ret[name] += val return ret + def reset(self): + """Reset all field counters""" + for group in self.group_leaders: + for event in group.events: + event.reset() + + class DebugfsProvider(object): """Provides data from the files that KVM creates in the kvm debugfs folder.""" def __init__(self): self._fields = self.get_available_fields() + self._baseline = {} self._pid = 0 self.do_read = True + self.paths = [] + self.reset() def get_available_fields(self): """"Returns a list of available fields. @@ -673,6 +749,7 @@ class DebugfsProvider(object): @fields.setter def fields(self, fields): self._fields = fields + self.reset() @property def pid(self): @@ -690,10 +767,11 @@ class DebugfsProvider(object): self.paths = filter(lambda x: "{}-".format(pid) in x, vms) else: - self.paths = [''] + self.paths = [] self.do_read = True + self.reset() - def read(self): + def read(self, reset=0): """Returns a dict with format:'file name / field -> current value'.""" results = {} @@ -701,10 +779,22 @@ class DebugfsProvider(object): if not self.do_read: return results - for path in self.paths: + paths = self.paths + if self._pid == 0: + paths = [] + for entry in os.walk(PATH_DEBUGFS_KVM): + for dir in entry[1]: + paths.append(dir) + for path in paths: for field in self._fields: - results[field] = results.get(field, 0) \ - + self.read_field(field, path) + value = self.read_field(field, path) + key = path + field + if reset: + self._baseline[key] = value + if self._baseline.get(key, -1) == -1: + self._baseline[key] = value + results[field] = (results.get(field, 0) + value - + self._baseline.get(key, 0)) return results @@ -718,6 +808,12 @@ class DebugfsProvider(object): except IOError: return 0 + def reset(self): + """Reset field counters""" + self._baseline = {} + self.read(1) + + class Stats(object): """Manages the data providers and the data they provide. @@ -753,14 +849,20 @@ class Stats(object): for provider in self.providers: provider.pid = self._pid_filter + def reset(self): + self.values = {} + for provider in self.providers: + provider.reset() + @property def fields_filter(self): return self._fields_filter @fields_filter.setter def fields_filter(self, fields_filter): - self._fields_filter = fields_filter - self.update_provider_filters() + if fields_filter != self._fields_filter: + self._fields_filter = fields_filter + self.update_provider_filters() @property def pid_filter(self): @@ -768,9 +870,10 @@ class Stats(object): @pid_filter.setter def pid_filter(self, pid): - self._pid_filter = pid - self.values = {} - self.update_provider_pid() + if pid != self._pid_filter: + self._pid_filter = pid + self.values = {} + self.update_provider_pid() def get(self): """Returns a dict with field -> (value, delta to last value) of all @@ -778,23 +881,26 @@ class Stats(object): for provider in self.providers: new = provider.read() for key in provider.fields: - oldval = self.values.get(key, (0, 0)) + oldval = self.values.get(key, (0, 0))[0] newval = new.get(key, 0) - newdelta = None - if oldval is not None: - newdelta = newval - oldval[0] + newdelta = newval - oldval self.values[key] = (newval, newdelta) return self.values LABEL_WIDTH = 40 NUMBER_WIDTH = 10 +DELAY_INITIAL = 0.25 +DELAY_REGULAR = 3.0 +MAX_GUEST_NAME_LEN = 48 +MAX_REGEX_LEN = 44 +DEFAULT_REGEX = r'^[^\(]*$' + class Tui(object): """Instruments curses to draw a nice text ui.""" def __init__(self, stats): self.stats = stats self.screen = None - self.drilldown = False self.update_drilldown() def __enter__(self): @@ -809,7 +915,14 @@ class Tui(object): # return from C start_color() is ignorable. try: curses.start_color() - except: + except curses.error: + pass + + # Hide cursor in extra statement as some monochrome terminals + # might support hiding but not colors. + try: + curses.curs_set(0) + except curses.error: pass curses.use_default_colors() @@ -827,36 +940,60 @@ class Tui(object): def update_drilldown(self): """Sets or removes a filter that only allows fields without braces.""" if not self.stats.fields_filter: - self.stats.fields_filter = r'^[^\(]*$' + self.stats.fields_filter = DEFAULT_REGEX - elif self.stats.fields_filter == r'^[^\(]*$': + elif self.stats.fields_filter == DEFAULT_REGEX: self.stats.fields_filter = None def update_pid(self, pid): """Propagates pid selection to stats object.""" self.stats.pid_filter = pid - def refresh(self, sleeptime): - """Refreshes on-screen data.""" + def refresh_header(self, pid=None): + """Refreshes the header.""" + if pid is None: + pid = self.stats.pid_filter self.screen.erase() - if self.stats.pid_filter > 0: - self.screen.addstr(0, 0, 'kvm statistics - pid {0}' - .format(self.stats.pid_filter), - curses.A_BOLD) + gname = get_gname_from_pid(pid) + if gname: + gname = ('({})'.format(gname[:MAX_GUEST_NAME_LEN] + '...' + if len(gname) > MAX_GUEST_NAME_LEN + else gname)) + if pid > 0: + self.screen.addstr(0, 0, 'kvm statistics - pid {0} {1}' + .format(pid, gname), curses.A_BOLD) else: self.screen.addstr(0, 0, 'kvm statistics - summary', curses.A_BOLD) + if self.stats.fields_filter and self.stats.fields_filter \ + != DEFAULT_REGEX: + regex = self.stats.fields_filter + if len(regex) > MAX_REGEX_LEN: + regex = regex[:MAX_REGEX_LEN] + '...' + self.screen.addstr(1, 17, 'regex filter: {0}'.format(regex)) self.screen.addstr(2, 1, 'Event') self.screen.addstr(2, 1 + LABEL_WIDTH + NUMBER_WIDTH - len('Total'), 'Total') - self.screen.addstr(2, 1 + LABEL_WIDTH + NUMBER_WIDTH + 8 - + self.screen.addstr(2, 1 + LABEL_WIDTH + NUMBER_WIDTH + 7 - + len('%Total'), '%Total') + self.screen.addstr(2, 1 + LABEL_WIDTH + NUMBER_WIDTH + 7 + 8 - len('Current'), 'Current') + self.screen.addstr(4, 1, 'Collecting data...') + self.screen.refresh() + + def refresh_body(self, sleeptime): row = 3 + self.screen.move(row, 0) + self.screen.clrtobot() stats = self.stats.get() + def sortkey(x): if stats[x][1]: return (-stats[x][1], -stats[x][0]) else: return (0, -stats[x][0]) + total = 0. + for val in stats.values(): + total += val[0] for key in sorted(stats.keys(), key=sortkey): if row >= self.screen.getmaxyx()[0]: @@ -869,6 +1006,8 @@ class Tui(object): col += LABEL_WIDTH self.screen.addstr(row, col, '%10d' % (values[0],)) col += NUMBER_WIDTH + self.screen.addstr(row, col, '%7.1f' % (values[0] * 100 / total,)) + col += 7 if values[1] is not None: self.screen.addstr(row, col, '%8d' % (values[1] / sleeptime,)) row += 1 @@ -893,20 +1032,24 @@ class Tui(object): regex = self.screen.getstr() curses.noecho() if len(regex) == 0: + self.stats.fields_filter = DEFAULT_REGEX + self.refresh_header() return try: re.compile(regex) self.stats.fields_filter = regex + self.refresh_header() return except re.error: continue - def show_vm_selection(self): + def show_vm_selection_by_pid(self): """Draws PID selection mask. Asks for a pid until a valid pid or 0 has been entered. """ + msg = '' while True: self.screen.erase() self.screen.addstr(0, 0, @@ -915,6 +1058,7 @@ class Tui(object): self.screen.addstr(1, 0, 'This might limit the shown data to the trace ' 'statistics.') + self.screen.addstr(5, 0, msg) curses.echo() self.screen.addstr(3, 0, "Pid [0 or pid]: ") @@ -922,60 +1066,128 @@ class Tui(object): curses.noecho() try: - pid = int(pid) - - if pid == 0: - self.update_pid(pid) - break - else: - if not os.path.isdir(os.path.join('/proc/', str(pid))): + if len(pid) > 0: + pid = int(pid) + if pid != 0 and not os.path.isdir(os.path.join('/proc/', + str(pid))): + msg = '"' + str(pid) + '": Not a running process' continue - else: - self.update_pid(pid) - break + else: + pid = 0 + self.refresh_header(pid) + self.update_pid(pid) + break except ValueError: + msg = '"' + str(pid) + '": Not a valid pid' continue + def show_vm_selection_by_guest_name(self): + """Draws guest selection mask. + + Asks for a guest name until a valid guest name or '' is entered. + + """ + msg = '' + while True: + self.screen.erase() + self.screen.addstr(0, 0, + 'Show statistics for specific guest.', + curses.A_BOLD) + self.screen.addstr(1, 0, + 'This might limit the shown data to the trace ' + 'statistics.') + self.screen.addstr(5, 0, msg) + curses.echo() + self.screen.addstr(3, 0, "Guest [ENTER or guest]: ") + gname = self.screen.getstr() + curses.noecho() + + if not gname: + self.refresh_header(0) + self.update_pid(0) + break + else: + pids = [] + try: + pids = get_pid_from_gname(gname) + except: + msg = '"' + gname + '": Internal error while searching, ' \ + 'use pid filter instead' + continue + if len(pids) == 0: + msg = '"' + gname + '": Not an active guest' + continue + if len(pids) > 1: + msg = '"' + gname + '": Multiple matches found, use pid ' \ + 'filter instead' + continue + self.refresh_header(pids[0]) + self.update_pid(pids[0]) + break + def show_stats(self): """Refreshes the screen and processes user input.""" - sleeptime = 0.25 + sleeptime = DELAY_INITIAL + self.refresh_header() while True: - self.refresh(sleeptime) + self.refresh_body(sleeptime) curses.halfdelay(int(sleeptime * 10)) - sleeptime = 3 + sleeptime = DELAY_REGULAR try: char = self.screen.getkey() if char == 'x': - self.drilldown = not self.drilldown + self.refresh_header() self.update_drilldown() + sleeptime = DELAY_INITIAL if char == 'q': break + if char == 'c': + self.stats.fields_filter = DEFAULT_REGEX + self.refresh_header(0) + self.update_pid(0) + sleeptime = DELAY_INITIAL if char == 'f': self.show_filter_selection() + sleeptime = DELAY_INITIAL + if char == 'g': + self.show_vm_selection_by_guest_name() + sleeptime = DELAY_INITIAL if char == 'p': - self.show_vm_selection() + self.show_vm_selection_by_pid() + sleeptime = DELAY_INITIAL + if char == 'r': + self.refresh_header() + self.stats.reset() + sleeptime = DELAY_INITIAL except KeyboardInterrupt: break except curses.error: continue + def batch(stats): """Prints statistics in a key, value format.""" - s = stats.get() - time.sleep(1) - s = stats.get() - for key in sorted(s.keys()): - values = s[key] - print '%-42s%10d%10d' % (key, values[0], values[1]) + try: + s = stats.get() + time.sleep(1) + s = stats.get() + for key in sorted(s.keys()): + values = s[key] + print '%-42s%10d%10d' % (key, values[0], values[1]) + except KeyboardInterrupt: + pass + def log(stats): """Prints statistics as reiterating key block, multiple value blocks.""" keys = sorted(stats.get().iterkeys()) + def banner(): for k in keys: print '%s' % k, print + def statline(): s = stats.get() for k in keys: @@ -984,11 +1196,15 @@ def log(stats): line = 0 banner_repeat = 20 while True: - time.sleep(1) - if line % banner_repeat == 0: - banner() - statline() - line += 1 + try: + time.sleep(1) + if line % banner_repeat == 0: + banner() + statline() + line += 1 + except KeyboardInterrupt: + break + def get_options(): """Returns processed program arguments.""" @@ -1009,6 +1225,16 @@ Requirements: CAP_SYS_ADMIN and perf events are used. - CAP_SYS_RESOURCE if the hard limit is not high enough to allow the large number of files that are possibly opened. + +Interactive Commands: + c clear filter + f filter by regular expression + g filter by guest name + p filter by PID + q quit + x toggle reporting of stats for individual child trace events + r reset stats +Press any other key to refresh statistics immediately. """ class PlainHelpFormatter(optparse.IndentedHelpFormatter): @@ -1018,6 +1244,22 @@ Requirements: else: return "" + def cb_guest_to_pid(option, opt, val, parser): + try: + pids = get_pid_from_gname(val) + except: + raise optparse.OptionValueError('Error while searching for guest ' + '"{}", use "-p" to specify a pid ' + 'instead'.format(val)) + if len(pids) == 0: + raise optparse.OptionValueError('No guest by the name "{}" ' + 'found'.format(val)) + if len(pids) > 1: + raise optparse.OptionValueError('Multiple processes found (pids: ' + '{}) - use "-p" to specify a pid ' + 'instead'.format(" ".join(pids))) + parser.values.pid = pids[0] + optparser = optparse.OptionParser(description=description_text, formatter=PlainHelpFormatter()) optparser.add_option('-1', '--once', '--batch', @@ -1051,15 +1293,24 @@ Requirements: help='fields to display (regex)', ) optparser.add_option('-p', '--pid', - action='store', - default=0, - type=int, - dest='pid', - help='restrict statistics to pid', - ) + action='store', + default=0, + type='int', + dest='pid', + help='restrict statistics to pid', + ) + optparser.add_option('-g', '--guest', + action='callback', + type='string', + dest='pid', + metavar='GUEST', + help='restrict statistics to guest by name', + callback=cb_guest_to_pid, + ) (options, _) = optparser.parse_args(sys.argv) return options + def get_providers(options): """Returns a list of data providers depending on the passed options.""" providers = [] @@ -1073,6 +1324,7 @@ def get_providers(options): return providers + def check_access(options): """Exits if the current user can't access all needed directories.""" if not os.path.exists('/sys/kernel/debug'): @@ -1086,8 +1338,8 @@ def check_access(options): "Also ensure, that the kvm modules are loaded.\n") sys.exit(1) - if not os.path.exists(PATH_DEBUGFS_TRACING) and (options.tracepoints - or not options.debugfs): + if not os.path.exists(PATH_DEBUGFS_TRACING) and (options.tracepoints or + not options.debugfs): sys.stderr.write("Please enable CONFIG_TRACING in your kernel " "when using the option -t (default).\n" "If it is enabled, make {0} readable by the " @@ -1098,10 +1350,11 @@ def check_access(options): sys.stderr.write("Falling back to debugfs statistics!\n") options.debugfs = True - sleep(5) + time.sleep(5) return options + def main(): options = get_options() options = check_access(options) diff --git a/tools/kvm/kvm_stat/kvm_stat.txt b/tools/kvm/kvm_stat/kvm_stat.txt index b92a153d7115..109431bdc63c 100644 --- a/tools/kvm/kvm_stat/kvm_stat.txt +++ b/tools/kvm/kvm_stat/kvm_stat.txt @@ -18,11 +18,33 @@ state transitions such as guest mode entry and exit. This tool is useful for observing guest behavior from the host perspective. Often conclusions about performance or buggy behavior can be drawn from the output. +While running in regular mode, use any of the keys listed in section +'Interactive Commands' below. +Use batch and logging modes for scripting purposes. The set of KVM kernel module trace events may be specific to the kernel version or architecture. It is best to check the KVM kernel module source code for the meaning of events. +INTERACTIVE COMMANDS +-------------------- +[horizontal] +*c*:: clear filter + +*f*:: filter by regular expression + +*g*:: filter by guest name + +*p*:: filter by PID + +*q*:: quit + +*r*:: reset stats + +*x*:: toggle reporting of stats for child trace events + +Press any other key to refresh statistics immediately. + OPTIONS ------- -1:: @@ -46,6 +68,10 @@ OPTIONS --pid=<pid>:: limit statistics to one virtual machine (pid) +-g<guest>:: +--guest=<guest_name>:: + limit statistics to one virtual machine (guest name) + -f<fields>:: --fields=<fields>:: fields to display (regex) diff --git a/tools/leds/Makefile b/tools/leds/Makefile index c03a79ebf9c8..078b666fd78b 100644 --- a/tools/leds/Makefile +++ b/tools/leds/Makefile @@ -3,11 +3,11 @@ CC = $(CROSS_COMPILE)gcc CFLAGS = -Wall -Wextra -g -I../../include/uapi -all: uledmon +all: uledmon led_hw_brightness_mon %: %.c $(CC) $(CFLAGS) -o $@ $^ clean: - $(RM) uledmon + $(RM) uledmon led_hw_brightness_mon .PHONY: all clean diff --git a/tools/leds/led_hw_brightness_mon.c b/tools/leds/led_hw_brightness_mon.c new file mode 100644 index 000000000000..64642ccfe442 --- /dev/null +++ b/tools/leds/led_hw_brightness_mon.c @@ -0,0 +1,84 @@ +/* + * led_hw_brightness_mon.c + * + * This program monitors LED brightness level changes having its origin + * in hardware/firmware, i.e. outside of kernel control. + * A timestamp and brightness value is printed each time the brightness changes. + * + * Usage: led_hw_brightness_mon <device-name> + * + * <device-name> is the name of the LED class device to be monitored. Pressing + * CTRL+C will exit. + */ + +#include <errno.h> +#include <fcntl.h> +#include <poll.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <time.h> +#include <unistd.h> + +#include <linux/uleds.h> + +int main(int argc, char const *argv[]) +{ + int fd, ret; + char brightness_file_path[LED_MAX_NAME_SIZE + 11]; + struct pollfd pollfd; + struct timespec ts; + char buf[11]; + + if (argc != 2) { + fprintf(stderr, "Requires <device-name> argument\n"); + return 1; + } + + snprintf(brightness_file_path, LED_MAX_NAME_SIZE, + "/sys/class/leds/%s/brightness_hw_changed", argv[1]); + + fd = open(brightness_file_path, O_RDONLY); + if (fd == -1) { + printf("Failed to open %s file\n", brightness_file_path); + return 1; + } + + /* + * read may fail if no hw brightness change has occurred so far, + * but it is required to avoid spurious poll notifications in + * the opposite case. + */ + read(fd, buf, sizeof(buf)); + + pollfd.fd = fd; + pollfd.events = POLLPRI; + + while (1) { + ret = poll(&pollfd, 1, -1); + if (ret == -1) { + printf("Failed to poll %s file (%d)\n", + brightness_file_path, ret); + ret = 1; + break; + } + + clock_gettime(CLOCK_MONOTONIC, &ts); + + ret = read(fd, buf, sizeof(buf)); + if (ret < 0) + break; + + ret = lseek(pollfd.fd, 0, SEEK_SET); + if (ret < 0) { + printf("lseek failed (%d)\n", ret); + break; + } + + printf("[%ld.%09ld] %d\n", ts.tv_sec, ts.tv_nsec, atoi(buf)); + } + + close(fd); + + return ret; +} diff --git a/tools/lguest/lguest.c b/tools/lguest/lguest.c index 11c8d9bc762e..897cd6f3f687 100644 --- a/tools/lguest/lguest.c +++ b/tools/lguest/lguest.c @@ -1387,7 +1387,7 @@ static bool pci_data_iowrite(u16 port, u32 mask, u32 val) /* Allow writing to any other BAR, or expansion ROM */ iowrite(portoff, val, mask, &d->config_words[reg]); return true; - /* We let them overide latency timer and cacheline size */ + /* We let them override latency timer and cacheline size */ } else if (&d->config_words[reg] == (void *)&d->config.cacheline_size) { /* Only let them change the first two fields. */ if (mask == 0xFFFFFFFF) @@ -3339,7 +3339,7 @@ int main(int argc, char *argv[]) * simple, single region. */ boot->e820_entries = 1; - boot->e820_map[0] = ((struct e820entry) { 0, mem, E820_RAM }); + boot->e820_table[0] = ((struct e820_entry) { 0, mem, E820_TYPE_RAM }); /* * The boot header contains a command line pointer: we put the command * line after the boot header. diff --git a/tools/lib/api/Makefile b/tools/lib/api/Makefile index adba83b325d5..eb6e0b36bfc1 100644 --- a/tools/lib/api/Makefile +++ b/tools/lib/api/Makefile @@ -17,7 +17,13 @@ MAKEFLAGS += --no-print-directory LIBFILE = $(OUTPUT)libapi.a CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) -CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -O6 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC +CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC + +ifeq ($(CC), clang) + CFLAGS += -O3 +else + CFLAGS += -O6 +endif # Treat warnings as errors unless directed not to ifneq ($(WERROR),0) diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c index f99f49e4a31e..809c7721cd24 100644 --- a/tools/lib/api/fs/fs.c +++ b/tools/lib/api/fs/fs.c @@ -38,6 +38,10 @@ #define HUGETLBFS_MAGIC 0x958458f6 #endif +#ifndef BPF_FS_MAGIC +#define BPF_FS_MAGIC 0xcafe4a11 +#endif + static const char * const sysfs__fs_known_mountpoints[] = { "/sys", 0, @@ -75,6 +79,11 @@ static const char * const hugetlbfs__known_mountpoints[] = { 0, }; +static const char * const bpf_fs__known_mountpoints[] = { + "/sys/fs/bpf", + 0, +}; + struct fs { const char *name; const char * const *mounts; @@ -89,6 +98,7 @@ enum { FS__DEBUGFS = 2, FS__TRACEFS = 3, FS__HUGETLBFS = 4, + FS__BPF_FS = 5, }; #ifndef TRACEFS_MAGIC @@ -121,6 +131,11 @@ static struct fs fs__entries[] = { .mounts = hugetlbfs__known_mountpoints, .magic = HUGETLBFS_MAGIC, }, + [FS__BPF_FS] = { + .name = "bpf", + .mounts = bpf_fs__known_mountpoints, + .magic = BPF_FS_MAGIC, + }, }; static bool fs__read_mounts(struct fs *fs) @@ -280,6 +295,7 @@ FS(procfs, FS__PROCFS); FS(debugfs, FS__DEBUGFS); FS(tracefs, FS__TRACEFS); FS(hugetlbfs, FS__HUGETLBFS); +FS(bpf_fs, FS__BPF_FS); int filename__read_int(const char *filename, int *value) { @@ -423,6 +439,35 @@ int sysfs__read_str(const char *entry, char **buf, size_t *sizep) return filename__read_str(path, buf, sizep); } +int sysfs__read_bool(const char *entry, bool *value) +{ + char *buf; + size_t size; + int ret; + + ret = sysfs__read_str(entry, &buf, &size); + if (ret < 0) + return ret; + + switch (buf[0]) { + case '1': + case 'y': + case 'Y': + *value = true; + break; + case '0': + case 'n': + case 'N': + *value = false; + break; + default: + ret = -1; + } + + free(buf); + + return ret; +} int sysctl__read_int(const char *sysctl, int *value) { char path[PATH_MAX]; diff --git a/tools/lib/api/fs/fs.h b/tools/lib/api/fs/fs.h index a63269f5d20c..956c21127d1e 100644 --- a/tools/lib/api/fs/fs.h +++ b/tools/lib/api/fs/fs.h @@ -22,6 +22,7 @@ FS(procfs) FS(debugfs) FS(tracefs) FS(hugetlbfs) +FS(bpf_fs) #undef FS @@ -36,4 +37,5 @@ int sysctl__read_int(const char *sysctl, int *value); int sysfs__read_int(const char *entry, int *value); int sysfs__read_ull(const char *entry, unsigned long long *value); int sysfs__read_str(const char *entry, char **buf, size_t *sizep); +int sysfs__read_bool(const char *entry, bool *value); #endif /* __API_FS__ */ diff --git a/tools/lib/api/fs/tracing_path.c b/tools/lib/api/fs/tracing_path.c index 251b7c342a87..3e606b9c443e 100644 --- a/tools/lib/api/fs/tracing_path.c +++ b/tools/lib/api/fs/tracing_path.c @@ -86,9 +86,13 @@ void put_tracing_file(char *file) free(file); } -static int strerror_open(int err, char *buf, size_t size, const char *filename) +int tracing_path__strerror_open_tp(int err, char *buf, size_t size, + const char *sys, const char *name) { char sbuf[128]; + char filename[PATH_MAX]; + + snprintf(filename, PATH_MAX, "%s/%s", sys, name ?: "*"); switch (err) { case ENOENT: @@ -99,10 +103,19 @@ static int strerror_open(int err, char *buf, size_t size, const char *filename) * - jirka */ if (debugfs__configured() || tracefs__configured()) { - snprintf(buf, size, - "Error:\tFile %s/%s not found.\n" - "Hint:\tPerhaps this kernel misses some CONFIG_ setting to enable this feature?.\n", - tracing_events_path, filename); + /* sdt markers */ + if (!strncmp(filename, "sdt_", 4)) { + snprintf(buf, size, + "Error:\tFile %s/%s not found.\n" + "Hint:\tSDT event cannot be directly recorded on.\n" + "\tPlease first use 'perf probe %s:%s' before recording it.\n", + tracing_events_path, filename, sys, name); + } else { + snprintf(buf, size, + "Error:\tFile %s/%s not found.\n" + "Hint:\tPerhaps this kernel misses some CONFIG_ setting to enable this feature?.\n", + tracing_events_path, filename); + } break; } snprintf(buf, size, "%s", @@ -125,12 +138,3 @@ static int strerror_open(int err, char *buf, size_t size, const char *filename) return 0; } - -int tracing_path__strerror_open_tp(int err, char *buf, size_t size, const char *sys, const char *name) -{ - char path[PATH_MAX]; - - snprintf(path, PATH_MAX, "%s/%s", sys, name ?: "*"); - - return strerror_open(err, buf, size, path); -} diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index e2efddf10231..1f5300e56b44 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -132,7 +132,7 @@ else Q = @ endif -# Disable command line variables (CFLAGS) overide from top +# Disable command line variables (CFLAGS) override from top # level Makefile (perf), otherwise build Makefile will get # the same command line setup. MAKEOVERRIDES= diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index ae752fa4eaa7..4fe444b8092e 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -27,7 +27,7 @@ #include "bpf.h" /* - * When building perf, unistd.h is overrided. __NR_bpf is + * When building perf, unistd.h is overridden. __NR_bpf is * required to be defined explicitly. */ #ifndef __NR_bpf @@ -37,18 +37,20 @@ # define __NR_bpf 321 # elif defined(__aarch64__) # define __NR_bpf 280 +# elif defined(__sparc__) +# define __NR_bpf 349 # else # error __NR_bpf not defined. libbpf does not support your arch. # endif #endif -static __u64 ptr_to_u64(void *ptr) +static inline __u64 ptr_to_u64(const void *ptr) { return (__u64) (unsigned long) ptr; } -static int sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr, - unsigned int size) +static inline int sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr, + unsigned int size) { return syscall(__NR_bpf, cmd, attr, size); } @@ -69,8 +71,25 @@ int bpf_create_map(enum bpf_map_type map_type, int key_size, return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr)); } -int bpf_load_program(enum bpf_prog_type type, struct bpf_insn *insns, - size_t insns_cnt, char *license, +int bpf_create_map_in_map(enum bpf_map_type map_type, int key_size, + int inner_map_fd, int max_entries, __u32 map_flags) +{ + union bpf_attr attr; + + memset(&attr, '\0', sizeof(attr)); + + attr.map_type = map_type; + attr.key_size = key_size; + attr.value_size = 4; + attr.inner_map_fd = inner_map_fd; + attr.max_entries = max_entries; + attr.map_flags = map_flags; + + return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr)); +} + +int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns, + size_t insns_cnt, const char *license, __u32 kern_version, char *log_buf, size_t log_buf_sz) { int fd; @@ -98,7 +117,7 @@ int bpf_load_program(enum bpf_prog_type type, struct bpf_insn *insns, return sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr)); } -int bpf_map_update_elem(int fd, void *key, void *value, +int bpf_map_update_elem(int fd, const void *key, const void *value, __u64 flags) { union bpf_attr attr; @@ -112,7 +131,7 @@ int bpf_map_update_elem(int fd, void *key, void *value, return sys_bpf(BPF_MAP_UPDATE_ELEM, &attr, sizeof(attr)); } -int bpf_map_lookup_elem(int fd, void *key, void *value) +int bpf_map_lookup_elem(int fd, const void *key, void *value) { union bpf_attr attr; @@ -124,7 +143,7 @@ int bpf_map_lookup_elem(int fd, void *key, void *value) return sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr)); } -int bpf_map_delete_elem(int fd, void *key) +int bpf_map_delete_elem(int fd, const void *key) { union bpf_attr attr; @@ -135,7 +154,7 @@ int bpf_map_delete_elem(int fd, void *key) return sys_bpf(BPF_MAP_DELETE_ELEM, &attr, sizeof(attr)); } -int bpf_map_get_next_key(int fd, void *key, void *next_key) +int bpf_map_get_next_key(int fd, const void *key, void *next_key) { union bpf_attr attr; @@ -192,3 +211,27 @@ int bpf_prog_detach(int target_fd, enum bpf_attach_type type) return sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr)); } + +int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size, + void *data_out, __u32 *size_out, __u32 *retval, + __u32 *duration) +{ + union bpf_attr attr; + int ret; + + bzero(&attr, sizeof(attr)); + attr.test.prog_fd = prog_fd; + attr.test.data_in = ptr_to_u64(data); + attr.test.data_out = ptr_to_u64(data_out); + attr.test.data_size_in = size; + attr.test.repeat = repeat; + + ret = sys_bpf(BPF_PROG_TEST_RUN, &attr, sizeof(attr)); + if (size_out) + *size_out = attr.test.data_size_out; + if (retval) + *retval = attr.test.retval; + if (duration) + *duration = attr.test.duration; + return ret; +} diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 4ac6c4b84100..edb4daeff7a5 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -22,28 +22,33 @@ #define __BPF_BPF_H #include <linux/bpf.h> +#include <stddef.h> int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size, int max_entries, __u32 map_flags); +int bpf_create_map_in_map(enum bpf_map_type map_type, int key_size, + int inner_map_fd, int max_entries, __u32 map_flags); /* Recommend log buffer size */ #define BPF_LOG_BUF_SIZE 65536 -int bpf_load_program(enum bpf_prog_type type, struct bpf_insn *insns, - size_t insns_cnt, char *license, +int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns, + size_t insns_cnt, const char *license, __u32 kern_version, char *log_buf, size_t log_buf_sz); -int bpf_map_update_elem(int fd, void *key, void *value, +int bpf_map_update_elem(int fd, const void *key, const void *value, __u64 flags); -int bpf_map_lookup_elem(int fd, void *key, void *value); -int bpf_map_delete_elem(int fd, void *key); -int bpf_map_get_next_key(int fd, void *key, void *next_key); +int bpf_map_lookup_elem(int fd, const void *key, void *value); +int bpf_map_delete_elem(int fd, const void *key); +int bpf_map_get_next_key(int fd, const void *key, void *next_key); int bpf_obj_pin(int fd, const char *pathname); int bpf_obj_get(const char *pathname); int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type, unsigned int flags); int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type); - +int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size, + void *data_out, __u32 *size_out, __u32 *retval, + __u32 *duration); #endif diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 84e6b35da4bd..1a2c07eb7795 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -4,6 +4,7 @@ * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org> * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com> * Copyright (C) 2015 Huawei Inc. + * Copyright (C) 2017 Nicira, Inc. * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU Lesser General Public @@ -22,15 +23,21 @@ #include <stdlib.h> #include <stdio.h> #include <stdarg.h> +#include <libgen.h> #include <inttypes.h> #include <string.h> #include <unistd.h> #include <fcntl.h> #include <errno.h> #include <asm/unistd.h> +#include <linux/err.h> #include <linux/kernel.h> #include <linux/bpf.h> #include <linux/list.h> +#include <linux/limits.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <sys/vfs.h> #include <libelf.h> #include <gelf.h> @@ -41,6 +48,10 @@ #define EM_BPF 247 #endif +#ifndef BPF_FS_MAGIC +#define BPF_FS_MAGIC 0xcafe4a11 +#endif + #define __printf(a, b) __attribute__((format(printf, a, b))) __printf(1, 2) @@ -779,7 +790,7 @@ static int bpf_program__collect_reloc(struct bpf_program *prog, size_t nr_maps, GElf_Shdr *shdr, Elf_Data *data, Elf_Data *symbols, - int maps_shndx) + int maps_shndx, struct bpf_map *maps) { int i, nrels; @@ -829,7 +840,15 @@ bpf_program__collect_reloc(struct bpf_program *prog, return -LIBBPF_ERRNO__RELOC; } - map_idx = sym.st_value / sizeof(struct bpf_map_def); + /* TODO: 'maps' is sorted. We can use bsearch to make it faster. */ + for (map_idx = 0; map_idx < nr_maps; map_idx++) { + if (maps[map_idx].offset == sym.st_value) { + pr_debug("relocation: find map %zd (%s) for insn %u\n", + map_idx, maps[map_idx].name, insn_idx); + break; + } + } + if (map_idx >= nr_maps) { pr_warning("bpf relocation: map_idx %d large than %d\n", (int)map_idx, (int)nr_maps - 1); @@ -953,7 +972,8 @@ static int bpf_object__collect_reloc(struct bpf_object *obj) err = bpf_program__collect_reloc(prog, nr_maps, shdr, data, obj->efile.symbols, - obj->efile.maps_shndx); + obj->efile.maps_shndx, + obj->maps); if (err) return err; } @@ -1227,6 +1247,191 @@ out: return err; } +static int check_path(const char *path) +{ + struct statfs st_fs; + char *dname, *dir; + int err = 0; + + if (path == NULL) + return -EINVAL; + + dname = strdup(path); + if (dname == NULL) + return -ENOMEM; + + dir = dirname(dname); + if (statfs(dir, &st_fs)) { + pr_warning("failed to statfs %s: %s\n", dir, strerror(errno)); + err = -errno; + } + free(dname); + + if (!err && st_fs.f_type != BPF_FS_MAGIC) { + pr_warning("specified path %s is not on BPF FS\n", path); + err = -EINVAL; + } + + return err; +} + +int bpf_program__pin_instance(struct bpf_program *prog, const char *path, + int instance) +{ + int err; + + err = check_path(path); + if (err) + return err; + + if (prog == NULL) { + pr_warning("invalid program pointer\n"); + return -EINVAL; + } + + if (instance < 0 || instance >= prog->instances.nr) { + pr_warning("invalid prog instance %d of prog %s (max %d)\n", + instance, prog->section_name, prog->instances.nr); + return -EINVAL; + } + + if (bpf_obj_pin(prog->instances.fds[instance], path)) { + pr_warning("failed to pin program: %s\n", strerror(errno)); + return -errno; + } + pr_debug("pinned program '%s'\n", path); + + return 0; +} + +static int make_dir(const char *path) +{ + int err = 0; + + if (mkdir(path, 0700) && errno != EEXIST) + err = -errno; + + if (err) + pr_warning("failed to mkdir %s: %s\n", path, strerror(-err)); + return err; +} + +int bpf_program__pin(struct bpf_program *prog, const char *path) +{ + int i, err; + + err = check_path(path); + if (err) + return err; + + if (prog == NULL) { + pr_warning("invalid program pointer\n"); + return -EINVAL; + } + + if (prog->instances.nr <= 0) { + pr_warning("no instances of prog %s to pin\n", + prog->section_name); + return -EINVAL; + } + + err = make_dir(path); + if (err) + return err; + + for (i = 0; i < prog->instances.nr; i++) { + char buf[PATH_MAX]; + int len; + + len = snprintf(buf, PATH_MAX, "%s/%d", path, i); + if (len < 0) + return -EINVAL; + else if (len >= PATH_MAX) + return -ENAMETOOLONG; + + err = bpf_program__pin_instance(prog, buf, i); + if (err) + return err; + } + + return 0; +} + +int bpf_map__pin(struct bpf_map *map, const char *path) +{ + int err; + + err = check_path(path); + if (err) + return err; + + if (map == NULL) { + pr_warning("invalid map pointer\n"); + return -EINVAL; + } + + if (bpf_obj_pin(map->fd, path)) { + pr_warning("failed to pin map: %s\n", strerror(errno)); + return -errno; + } + + pr_debug("pinned map '%s'\n", path); + return 0; +} + +int bpf_object__pin(struct bpf_object *obj, const char *path) +{ + struct bpf_program *prog; + struct bpf_map *map; + int err; + + if (!obj) + return -ENOENT; + + if (!obj->loaded) { + pr_warning("object not yet loaded; load it first\n"); + return -ENOENT; + } + + err = make_dir(path); + if (err) + return err; + + bpf_map__for_each(map, obj) { + char buf[PATH_MAX]; + int len; + + len = snprintf(buf, PATH_MAX, "%s/%s", path, + bpf_map__name(map)); + if (len < 0) + return -EINVAL; + else if (len >= PATH_MAX) + return -ENAMETOOLONG; + + err = bpf_map__pin(map, buf); + if (err) + return err; + } + + bpf_object__for_each_program(prog, obj) { + char buf[PATH_MAX]; + int len; + + len = snprintf(buf, PATH_MAX, "%s/%s", path, + prog->section_name); + if (len < 0) + return -EINVAL; + else if (len >= PATH_MAX) + return -ENAMETOOLONG; + + err = bpf_program__pin(prog, buf); + if (err) + return err; + } + + return 0; +} + void bpf_object__close(struct bpf_object *obj) { size_t i; @@ -1413,43 +1618,38 @@ int bpf_program__nth_fd(struct bpf_program *prog, int n) return fd; } -static void bpf_program__set_type(struct bpf_program *prog, - enum bpf_prog_type type) +void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type) { prog->type = type; } -int bpf_program__set_tracepoint(struct bpf_program *prog) -{ - if (!prog) - return -EINVAL; - bpf_program__set_type(prog, BPF_PROG_TYPE_TRACEPOINT); - return 0; -} - -int bpf_program__set_kprobe(struct bpf_program *prog) -{ - if (!prog) - return -EINVAL; - bpf_program__set_type(prog, BPF_PROG_TYPE_KPROBE); - return 0; -} - static bool bpf_program__is_type(struct bpf_program *prog, enum bpf_prog_type type) { return prog ? (prog->type == type) : false; } -bool bpf_program__is_tracepoint(struct bpf_program *prog) -{ - return bpf_program__is_type(prog, BPF_PROG_TYPE_TRACEPOINT); -} - -bool bpf_program__is_kprobe(struct bpf_program *prog) -{ - return bpf_program__is_type(prog, BPF_PROG_TYPE_KPROBE); -} +#define BPF_PROG_TYPE_FNS(NAME, TYPE) \ +int bpf_program__set_##NAME(struct bpf_program *prog) \ +{ \ + if (!prog) \ + return -EINVAL; \ + bpf_program__set_type(prog, TYPE); \ + return 0; \ +} \ + \ +bool bpf_program__is_##NAME(struct bpf_program *prog) \ +{ \ + return bpf_program__is_type(prog, TYPE); \ +} \ + +BPF_PROG_TYPE_FNS(socket_filter, BPF_PROG_TYPE_SOCKET_FILTER); +BPF_PROG_TYPE_FNS(kprobe, BPF_PROG_TYPE_KPROBE); +BPF_PROG_TYPE_FNS(sched_cls, BPF_PROG_TYPE_SCHED_CLS); +BPF_PROG_TYPE_FNS(sched_act, BPF_PROG_TYPE_SCHED_ACT); +BPF_PROG_TYPE_FNS(tracepoint, BPF_PROG_TYPE_TRACEPOINT); +BPF_PROG_TYPE_FNS(xdp, BPF_PROG_TYPE_XDP); +BPF_PROG_TYPE_FNS(perf_event, BPF_PROG_TYPE_PERF_EVENT); int bpf_map__fd(struct bpf_map *map) { @@ -1537,3 +1737,10 @@ bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset) } return ERR_PTR(-ENOENT); } + +long libbpf_get_error(const void *ptr) +{ + if (IS_ERR(ptr)) + return PTR_ERR(ptr); + return 0; +} diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index a5a8b86a06fe..32c7252f734e 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -22,9 +22,10 @@ #define __BPF_LIBBPF_H #include <stdio.h> +#include <stdint.h> #include <stdbool.h> -#include <linux/err.h> #include <sys/types.h> // for size_t +#include <linux/bpf.h> enum libbpf_errno { __LIBBPF_ERRNO__START = 4000, @@ -65,6 +66,7 @@ struct bpf_object *bpf_object__open(const char *path); struct bpf_object *bpf_object__open_buffer(void *obj_buf, size_t obj_buf_sz, const char *name); +int bpf_object__pin(struct bpf_object *object, const char *path); void bpf_object__close(struct bpf_object *object); /* Load/unload object into/from kernel */ @@ -106,6 +108,9 @@ void *bpf_program__priv(struct bpf_program *prog); const char *bpf_program__title(struct bpf_program *prog, bool needs_copy); int bpf_program__fd(struct bpf_program *prog); +int bpf_program__pin_instance(struct bpf_program *prog, const char *path, + int instance); +int bpf_program__pin(struct bpf_program *prog, const char *path); struct bpf_insn; @@ -174,11 +179,22 @@ int bpf_program__nth_fd(struct bpf_program *prog, int n); /* * Adjust type of bpf program. Default is kprobe. */ +int bpf_program__set_socket_filter(struct bpf_program *prog); int bpf_program__set_tracepoint(struct bpf_program *prog); int bpf_program__set_kprobe(struct bpf_program *prog); +int bpf_program__set_sched_cls(struct bpf_program *prog); +int bpf_program__set_sched_act(struct bpf_program *prog); +int bpf_program__set_xdp(struct bpf_program *prog); +int bpf_program__set_perf_event(struct bpf_program *prog); +void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type); +bool bpf_program__is_socket_filter(struct bpf_program *prog); bool bpf_program__is_tracepoint(struct bpf_program *prog); bool bpf_program__is_kprobe(struct bpf_program *prog); +bool bpf_program__is_sched_cls(struct bpf_program *prog); +bool bpf_program__is_sched_act(struct bpf_program *prog); +bool bpf_program__is_xdp(struct bpf_program *prog); +bool bpf_program__is_perf_event(struct bpf_program *prog); /* * We don't need __attribute__((packed)) now since it is @@ -223,5 +239,8 @@ typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *); int bpf_map__set_priv(struct bpf_map *map, void *priv, bpf_map_clear_priv_t clear_priv); void *bpf_map__priv(struct bpf_map *map); +int bpf_map__pin(struct bpf_map *map, const char *path); + +long libbpf_get_error(const void *ptr); #endif diff --git a/tools/lib/find_bit.c b/tools/lib/find_bit.c index 6d8b8f22cf55..42c15f906aac 100644 --- a/tools/lib/find_bit.c +++ b/tools/lib/find_bit.c @@ -34,7 +34,7 @@ static unsigned long _find_next_bit(const unsigned long *addr, { unsigned long tmp; - if (!nbits || start >= nbits) + if (unlikely(start >= nbits)) return nbits; tmp = addr[start / BITS_PER_LONG] ^ invert; diff --git a/tools/lib/string.c b/tools/lib/string.c index bd239bc1d557..8e678af1c6ee 100644 --- a/tools/lib/string.c +++ b/tools/lib/string.c @@ -87,3 +87,12 @@ size_t __weak strlcpy(char *dest, const char *src, size_t size) } return ret; } + +int prefixcmp(const char *str, const char *prefix) +{ + for (; ; str++, prefix++) + if (!*prefix) + return 0; + else if (*str != *prefix) + return (unsigned char)*prefix - (unsigned char)*str; +} diff --git a/tools/lib/subcmd/Makefile b/tools/lib/subcmd/Makefile index 3f8cc44a0dbd..3d1c3b5b5150 100644 --- a/tools/lib/subcmd/Makefile +++ b/tools/lib/subcmd/Makefile @@ -19,7 +19,13 @@ MAKEFLAGS += --no-print-directory LIBFILE = $(OUTPUT)libsubcmd.a CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) -CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -O6 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC +CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC + +ifeq ($(CC), clang) + CFLAGS += -O3 +else + CFLAGS += -O6 +endif # Treat warnings as errors unless directed not to ifneq ($(WERROR),0) diff --git a/tools/lib/subcmd/help.c b/tools/lib/subcmd/help.c index e228c3cb3716..ba970a73d053 100644 --- a/tools/lib/subcmd/help.c +++ b/tools/lib/subcmd/help.c @@ -1,6 +1,7 @@ #include <stdio.h> #include <stdlib.h> #include <string.h> +#include <linux/string.h> #include <termios.h> #include <sys/ioctl.h> #include <sys/types.h> diff --git a/tools/lib/subcmd/help.h b/tools/lib/subcmd/help.h index e145a020780c..9bd4223dc722 100644 --- a/tools/lib/subcmd/help.h +++ b/tools/lib/subcmd/help.h @@ -2,6 +2,7 @@ #define __SUBCMD_HELP_H #include <sys/types.h> +#include <stdio.h> struct cmdnames { size_t alloc; diff --git a/tools/lib/subcmd/parse-options.c b/tools/lib/subcmd/parse-options.c index 8aad81151d50..359bfa77f39c 100644 --- a/tools/lib/subcmd/parse-options.c +++ b/tools/lib/subcmd/parse-options.c @@ -1,4 +1,5 @@ #include <linux/compiler.h> +#include <linux/string.h> #include <linux/types.h> #include <stdio.h> #include <stdlib.h> @@ -270,6 +271,8 @@ static int get_value(struct parse_opt_ctx_t *p, } if (get_arg(p, opt, flags, &arg)) return -1; + if (arg[0] == '-') + return opterror(opt, "expects an unsigned numerical value", flags); *(unsigned int *)opt->value = strtol(arg, (char **)&s, 10); if (*s) return opterror(opt, "expects a numerical value", flags); @@ -302,6 +305,8 @@ static int get_value(struct parse_opt_ctx_t *p, } if (get_arg(p, opt, flags, &arg)) return -1; + if (arg[0] == '-') + return opterror(opt, "expects an unsigned numerical value", flags); *(u64 *)opt->value = strtoull(arg, (char **)&s, 10); if (*s) return opterror(opt, "expects a numerical value", flags); diff --git a/tools/lib/subcmd/parse-options.h b/tools/lib/subcmd/parse-options.h index 11c3be3bcce7..f054ca1b899d 100644 --- a/tools/lib/subcmd/parse-options.h +++ b/tools/lib/subcmd/parse-options.h @@ -1,6 +1,7 @@ #ifndef __SUBCMD_PARSE_OPTIONS_H #define __SUBCMD_PARSE_OPTIONS_H +#include <linux/kernel.h> #include <stdbool.h> #include <stdint.h> @@ -132,32 +133,32 @@ struct option { #define OPT_UINTEGER(s, l, v, h) { .type = OPTION_UINTEGER, .short_name = (s), .long_name = (l), .value = check_vtype(v, unsigned int *), .help = (h) } #define OPT_LONG(s, l, v, h) { .type = OPTION_LONG, .short_name = (s), .long_name = (l), .value = check_vtype(v, long *), .help = (h) } #define OPT_U64(s, l, v, h) { .type = OPTION_U64, .short_name = (s), .long_name = (l), .value = check_vtype(v, u64 *), .help = (h) } -#define OPT_STRING(s, l, v, a, h) { .type = OPTION_STRING, .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h) } +#define OPT_STRING(s, l, v, a, h) { .type = OPTION_STRING, .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), .argh = (a), .help = (h) } #define OPT_STRING_OPTARG(s, l, v, a, h, d) \ { .type = OPTION_STRING, .short_name = (s), .long_name = (l), \ - .value = check_vtype(v, const char **), (a), .help = (h), \ + .value = check_vtype(v, const char **), .argh =(a), .help = (h), \ .flags = PARSE_OPT_OPTARG, .defval = (intptr_t)(d) } #define OPT_STRING_OPTARG_SET(s, l, v, os, a, h, d) \ { .type = OPTION_STRING, .short_name = (s), .long_name = (l), \ - .value = check_vtype(v, const char **), (a), .help = (h), \ + .value = check_vtype(v, const char **), .argh = (a), .help = (h), \ .flags = PARSE_OPT_OPTARG, .defval = (intptr_t)(d), \ .set = check_vtype(os, bool *)} -#define OPT_STRING_NOEMPTY(s, l, v, a, h) { .type = OPTION_STRING, .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h), .flags = PARSE_OPT_NOEMPTY} +#define OPT_STRING_NOEMPTY(s, l, v, a, h) { .type = OPTION_STRING, .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), .argh = (a), .help = (h), .flags = PARSE_OPT_NOEMPTY} #define OPT_DATE(s, l, v, h) \ { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = "time", .help = (h), .callback = parse_opt_approxidate_cb } #define OPT_CALLBACK(s, l, v, a, h, f) \ - { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h), .callback = (f) } + { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = (a), .help = (h), .callback = (f) } #define OPT_CALLBACK_NOOPT(s, l, v, a, h, f) \ - { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h), .callback = (f), .flags = PARSE_OPT_NOARG } + { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = (a), .help = (h), .callback = (f), .flags = PARSE_OPT_NOARG } #define OPT_CALLBACK_DEFAULT(s, l, v, a, h, f, d) \ - { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h), .callback = (f), .defval = (intptr_t)d, .flags = PARSE_OPT_LASTARG_DEFAULT } + { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = (a), .help = (h), .callback = (f), .defval = (intptr_t)d, .flags = PARSE_OPT_LASTARG_DEFAULT } #define OPT_CALLBACK_DEFAULT_NOOPT(s, l, v, a, h, f, d) \ { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l),\ - .value = (v), (a), .help = (h), .callback = (f), .defval = (intptr_t)d,\ + .value = (v), .arg = (a), .help = (h), .callback = (f), .defval = (intptr_t)d,\ .flags = PARSE_OPT_LASTARG_DEFAULT | PARSE_OPT_NOARG} #define OPT_CALLBACK_OPTARG(s, l, v, d, a, h, f) \ { .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), \ - .value = (v), (a), .help = (h), .callback = (f), \ + .value = (v), .argh = (a), .help = (h), .callback = (f), \ .flags = PARSE_OPT_OPTARG, .data = (d) } /* parse_options() will filter out the processed options and leave the diff --git a/tools/lib/subcmd/subcmd-util.h b/tools/lib/subcmd/subcmd-util.h index fc2e45d8aaf1..8fa5f036eff0 100644 --- a/tools/lib/subcmd/subcmd-util.h +++ b/tools/lib/subcmd/subcmd-util.h @@ -79,13 +79,4 @@ static inline void astrcat(char **out, const char *add) free(tmp); } -static inline int prefixcmp(const char *str, const char *prefix) -{ - for (; ; str++, prefix++) - if (!*prefix) - return 0; - else if (*str != *prefix) - return (unsigned char)*prefix - (unsigned char)*str; -} - #endif /* __SUBCMD_UTIL_H */ diff --git a/tools/lib/symbol/kallsyms.c b/tools/lib/symbol/kallsyms.c index 5e431077fcd6..d270ac00613d 100644 --- a/tools/lib/symbol/kallsyms.c +++ b/tools/lib/symbol/kallsyms.c @@ -1,3 +1,4 @@ +#include <ctype.h> #include "symbol/kallsyms.h" #include <stdio.h> #include <stdlib.h> diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile index 2616c66e10c1..9b8555ea3459 100644 --- a/tools/lib/traceevent/Makefile +++ b/tools/lib/traceevent/Makefile @@ -135,7 +135,7 @@ else Q = @ endif -# Disable command line variables (CFLAGS) overide from top +# Disable command line variables (CFLAGS) override from top # level Makefile (perf), otherwise build Makefile will get # the same command line setup. MAKEOVERRIDES= @@ -257,10 +257,16 @@ define do_install_plugins endef define do_generate_dynamic_list_file - (echo '{'; \ - $(NM) -u -D $1 | awk 'NF>1 {print "\t"$$2";"}' | sort -u; \ - echo '};'; \ - ) > $2 + symbol_type=`$(NM) -u -D $1 | awk 'NF>1 {print $$1}' | \ + xargs echo "U W w" | tr ' ' '\n' | sort -u | xargs echo`;\ + if [ "$$symbol_type" = "U W w" ];then \ + (echo '{'; \ + $(NM) -u -D $1 | awk 'NF>1 {print "\t"$$2";"}' | sort -u;\ + echo '};'; \ + ) > $2; \ + else \ + (echo Either missing one of [$1] or bad version of $(NM)) 1>&2;\ + fi endef install_lib: all_cmd install_plugins diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index 14a4f623c1a5..7ce724fc0544 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -831,6 +831,7 @@ static void free_arg(struct print_arg *arg) free_flag_sym(arg->symbol.symbols); break; case PRINT_HEX: + case PRINT_HEX_STR: free_arg(arg->hex.field); free_arg(arg->hex.size); break; @@ -2629,10 +2630,11 @@ out_free: } static enum event_type -process_hex(struct event_format *event, struct print_arg *arg, char **tok) +process_hex_common(struct event_format *event, struct print_arg *arg, + char **tok, enum print_arg_type type) { memset(arg, 0, sizeof(*arg)); - arg->type = PRINT_HEX; + arg->type = type; if (alloc_and_process_delim(event, ",", &arg->hex.field)) goto out; @@ -2651,6 +2653,19 @@ out: } static enum event_type +process_hex(struct event_format *event, struct print_arg *arg, char **tok) +{ + return process_hex_common(event, arg, tok, PRINT_HEX); +} + +static enum event_type +process_hex_str(struct event_format *event, struct print_arg *arg, + char **tok) +{ + return process_hex_common(event, arg, tok, PRINT_HEX_STR); +} + +static enum event_type process_int_array(struct event_format *event, struct print_arg *arg, char **tok) { memset(arg, 0, sizeof(*arg)); @@ -3009,6 +3024,10 @@ process_function(struct event_format *event, struct print_arg *arg, free_token(token); return process_hex(event, arg, tok); } + if (strcmp(token, "__print_hex_str") == 0) { + free_token(token); + return process_hex_str(event, arg, tok); + } if (strcmp(token, "__print_array") == 0) { free_token(token); return process_int_array(event, arg, tok); @@ -3547,6 +3566,7 @@ eval_num_arg(void *data, int size, struct event_format *event, struct print_arg case PRINT_SYMBOL: case PRINT_INT_ARRAY: case PRINT_HEX: + case PRINT_HEX_STR: break; case PRINT_TYPE: val = eval_num_arg(data, size, event, arg->typecast.item); @@ -3962,6 +3982,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size, } break; case PRINT_HEX: + case PRINT_HEX_STR: if (arg->hex.field->type == PRINT_DYNAMIC_ARRAY) { unsigned long offset; offset = pevent_read_number(pevent, @@ -3981,7 +4002,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size, } len = eval_num_arg(data, size, event, arg->hex.size); for (i = 0; i < len; i++) { - if (i) + if (i && arg->type == PRINT_HEX) trace_seq_putc(s, ' '); trace_seq_printf(s, "%02x", hex[i]); } @@ -5204,13 +5225,13 @@ int pevent_data_pid(struct pevent *pevent, struct pevent_record *rec) } /** - * pevent_data_prempt_count - parse the preempt count from the record + * pevent_data_preempt_count - parse the preempt count from the record * @pevent: a handle to the pevent * @rec: the record to parse * * This returns the preempt count from a record. */ -int pevent_data_prempt_count(struct pevent *pevent, struct pevent_record *rec) +int pevent_data_preempt_count(struct pevent *pevent, struct pevent_record *rec) { return parse_common_pc(pevent, rec->data); } @@ -5727,6 +5748,13 @@ static void print_args(struct print_arg *args) print_args(args->hex.size); printf(")"); break; + case PRINT_HEX_STR: + printf("__print_hex_str("); + print_args(args->hex.field); + printf(", "); + print_args(args->hex.size); + printf(")"); + break; case PRINT_INT_ARRAY: printf("__print_array("); print_args(args->int_array.field); diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h index 7aae746ec2fe..0c03538df74c 100644 --- a/tools/lib/traceevent/event-parse.h +++ b/tools/lib/traceevent/event-parse.h @@ -140,7 +140,7 @@ struct pevent_plugin_option { * struct pevent_plugin_option PEVENT_PLUGIN_OPTIONS[] = { * { * .name = "option-name", - * .plugin_alias = "overide-file-name", (optional) + * .plugin_alias = "override-file-name", (optional) * .description = "description of option to show users", * }, * { @@ -292,6 +292,7 @@ enum print_arg_type { PRINT_FUNC, PRINT_BITMASK, PRINT_DYNAMIC_ARRAY_LEN, + PRINT_HEX_STR, }; struct print_arg { @@ -709,7 +710,7 @@ void pevent_data_lat_fmt(struct pevent *pevent, int pevent_data_type(struct pevent *pevent, struct pevent_record *rec); struct event_format *pevent_data_event_from_type(struct pevent *pevent, int type); int pevent_data_pid(struct pevent *pevent, struct pevent_record *rec); -int pevent_data_prempt_count(struct pevent *pevent, struct pevent_record *rec); +int pevent_data_preempt_count(struct pevent *pevent, struct pevent_record *rec); int pevent_data_flags(struct pevent *pevent, struct pevent_record *rec); const char *pevent_data_comm_from_pid(struct pevent *pevent, int pid); struct cmdline; diff --git a/tools/lib/traceevent/kbuffer-parse.c b/tools/lib/traceevent/kbuffer-parse.c index 65984f1c2974..c94e3641b046 100644 --- a/tools/lib/traceevent/kbuffer-parse.c +++ b/tools/lib/traceevent/kbuffer-parse.c @@ -315,6 +315,7 @@ static unsigned int old_update_pointers(struct kbuffer *kbuf) extend += delta; delta = extend; ptr += 4; + length = 0; break; case OLD_RINGBUF_TYPE_TIME_STAMP: diff --git a/tools/lib/traceevent/plugin_function.c b/tools/lib/traceevent/plugin_function.c index a00ec190821a..42dbf73758f3 100644 --- a/tools/lib/traceevent/plugin_function.c +++ b/tools/lib/traceevent/plugin_function.c @@ -130,7 +130,7 @@ static int function_handler(struct trace_seq *s, struct pevent_record *record, unsigned long long pfunction; const char *func; const char *parent; - int index; + int index = 0; if (pevent_get_field_val(s, event, "ip", record, &function, 1)) return trace_seq_putc(s, '!'); diff --git a/tools/net/bpf_jit_disasm.c b/tools/net/bpf_jit_disasm.c index 544b05a53b70..ad572e6cdbd0 100644 --- a/tools/net/bpf_jit_disasm.c +++ b/tools/net/bpf_jit_disasm.c @@ -229,6 +229,7 @@ static void usage(void) { printf("Usage: bpf_jit_disasm [...]\n"); printf(" -o Also display related opcodes (default: off).\n"); + printf(" -O <file> Write binary image of code to file, don't disassemble to stdout.\n"); printf(" -f <file> Read last image dump from file or stdin (default: klog).\n"); printf(" -h Display this help.\n"); } @@ -238,12 +239,19 @@ int main(int argc, char **argv) unsigned int len, klen, opt, opcodes = 0; static uint8_t image[32768]; char *kbuff, *file = NULL; + char *ofile = NULL; + int ofd; + ssize_t nr; + uint8_t *pos; - while ((opt = getopt(argc, argv, "of:")) != -1) { + while ((opt = getopt(argc, argv, "of:O:")) != -1) { switch (opt) { case 'o': opcodes = 1; break; + case 'O': + ofile = optarg; + break; case 'f': file = optarg; break; @@ -263,11 +271,35 @@ int main(int argc, char **argv) } len = get_last_jit_image(kbuff, klen, image, sizeof(image)); - if (len > 0) - get_asm_insns(image, len, opcodes); - else + if (len <= 0) { fprintf(stderr, "No JIT image found!\n"); + goto done; + } + if (!ofile) { + get_asm_insns(image, len, opcodes); + goto done; + } + + ofd = open(ofile, O_WRONLY | O_CREAT | O_TRUNC, DEFFILEMODE); + if (ofd < 0) { + fprintf(stderr, "Could not open file %s for writing: ", ofile); + perror(NULL); + goto done; + } + pos = image; + do { + nr = write(ofd, pos, len); + if (nr < 0) { + fprintf(stderr, "Could not write data to %s: ", ofile); + perror(NULL); + goto done; + } + len -= nr; + pos += nr; + } while (len); + close(ofd); +done: put_log_buff(kbuff); return 0; } diff --git a/tools/objtool/arch.h b/tools/objtool/arch.h index f7350fcedc70..a59e061c0b4a 100644 --- a/tools/objtool/arch.h +++ b/tools/objtool/arch.h @@ -31,9 +31,8 @@ #define INSN_CALL_DYNAMIC 8 #define INSN_RETURN 9 #define INSN_CONTEXT_SWITCH 10 -#define INSN_BUG 11 -#define INSN_NOP 12 -#define INSN_OTHER 13 +#define INSN_NOP 11 +#define INSN_OTHER 12 #define INSN_LAST INSN_OTHER int arch_decode_instruction(struct elf *elf, struct section *sec, diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index 039636ffb6c8..6ac99e3266eb 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -118,9 +118,6 @@ int arch_decode_instruction(struct elf *elf, struct section *sec, op2 == 0x35) /* sysenter, sysret */ *type = INSN_CONTEXT_SWITCH; - else if (op2 == 0x0b || op2 == 0xb9) - /* ud2 */ - *type = INSN_BUG; else if (op2 == 0x0d || op2 == 0x1f) /* nopl/nopw */ *type = INSN_NOP; diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c index e8a1f699058a..282a60368b14 100644 --- a/tools/objtool/builtin-check.c +++ b/tools/objtool/builtin-check.c @@ -36,8 +36,7 @@ #include "warn.h" #include <linux/hashtable.h> - -#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) +#include <linux/kernel.h> #define STATE_FP_SAVED 0x1 #define STATE_FP_SETUP 0x2 @@ -51,7 +50,7 @@ struct instruction { unsigned int len, state; unsigned char type; unsigned long immediate; - bool alt_group, visited; + bool alt_group, visited, dead_end; struct symbol *call_dest; struct instruction *jump_dest; struct list_head alts; @@ -330,6 +329,54 @@ static int decode_instructions(struct objtool_file *file) } /* + * Find all uses of the unreachable() macro, which are code path dead ends. + */ +static int add_dead_ends(struct objtool_file *file) +{ + struct section *sec; + struct rela *rela; + struct instruction *insn; + bool found; + + sec = find_section_by_name(file->elf, ".rela.discard.unreachable"); + if (!sec) + return 0; + + list_for_each_entry(rela, &sec->rela_list, list) { + if (rela->sym->type != STT_SECTION) { + WARN("unexpected relocation symbol type in %s", sec->name); + return -1; + } + insn = find_insn(file, rela->sym->sec, rela->addend); + if (insn) + insn = list_prev_entry(insn, list); + else if (rela->addend == rela->sym->sec->len) { + found = false; + list_for_each_entry_reverse(insn, &file->insn_list, list) { + if (insn->sec == rela->sym->sec) { + found = true; + break; + } + } + + if (!found) { + WARN("can't find unreachable insn at %s+0x%x", + rela->sym->sec->name, rela->addend); + return -1; + } + } else { + WARN("can't find unreachable insn at %s+0x%x", + rela->sym->sec->name, rela->addend); + return -1; + } + + insn->dead_end = true; + } + + return 0; +} + +/* * Warnings shouldn't be reported for ignored functions. */ static void add_ignores(struct objtool_file *file) @@ -757,11 +804,20 @@ static struct rela *find_switch_table(struct objtool_file *file, insn->jump_dest->offset > orig_insn->offset)) break; + /* look for a relocation which references .rodata */ text_rela = find_rela_by_dest_range(insn->sec, insn->offset, insn->len); - if (text_rela && text_rela->sym == file->rodata->sym) - return find_rela_by_dest(file->rodata, - text_rela->addend); + if (!text_rela || text_rela->sym != file->rodata->sym) + continue; + + /* + * Make sure the .rodata address isn't associated with a + * symbol. gcc jump tables are anonymous data. + */ + if (find_symbol_containing(file->rodata, text_rela->addend)) + continue; + + return find_rela_by_dest(file->rodata, text_rela->addend); } return NULL; @@ -843,6 +899,10 @@ static int decode_sections(struct objtool_file *file) if (ret) return ret; + ret = add_dead_ends(file); + if (ret) + return ret; + add_ignores(file); ret = add_jump_destinations(file); @@ -1037,13 +1097,13 @@ static int validate_branch(struct objtool_file *file, return 0; - case INSN_BUG: - return 0; - default: break; } + if (insn->dead_end) + return 0; + insn = next_insn_same_sec(file, insn); if (!insn) { WARN("%s: unexpected end of section", sec->name); @@ -1220,7 +1280,7 @@ int cmd_check(int argc, const char **argv) INIT_LIST_HEAD(&file.insn_list); hash_init(file.insn_hash); - file.whitelist = find_section_by_name(file.elf, "__func_stack_frame_non_standard"); + file.whitelist = find_section_by_name(file.elf, ".discard.func_stack_frame_non_standard"); file.rodata = find_section_by_name(file.elf, ".rodata"); file.ignore_unreachables = false; file.c_file = find_section_by_name(file.elf, ".comment"); diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index 0d7983ac63ef..d897702ce742 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -85,6 +85,18 @@ struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset) return NULL; } +struct symbol *find_symbol_containing(struct section *sec, unsigned long offset) +{ + struct symbol *sym; + + list_for_each_entry(sym, &sec->symbol_list, list) + if (sym->type != STT_SECTION && + offset >= sym->offset && offset < sym->offset + sym->len) + return sym; + + return NULL; +} + struct rela *find_rela_by_dest_range(struct section *sec, unsigned long offset, unsigned int len) { diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h index aa1ff6596684..731973e1a3f5 100644 --- a/tools/objtool/elf.h +++ b/tools/objtool/elf.h @@ -79,6 +79,7 @@ struct elf { struct elf *elf_open(const char *name); struct section *find_section_by_name(struct elf *elf, const char *name); struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset); +struct symbol *find_symbol_containing(struct section *sec, unsigned long offset); struct rela *find_rela_by_dest(struct section *sec, unsigned long offset); struct rela *find_rela_by_dest_range(struct section *sec, unsigned long offset, unsigned int len); diff --git a/tools/objtool/objtool.c b/tools/objtool/objtool.c index 46c326db4f46..ecc5b1b5d15d 100644 --- a/tools/objtool/objtool.c +++ b/tools/objtool/objtool.c @@ -31,11 +31,10 @@ #include <stdlib.h> #include <subcmd/exec-cmd.h> #include <subcmd/pager.h> +#include <linux/kernel.h> #include "builtin.h" -#define ARRAY_SIZE(x) (sizeof(x)/sizeof(x[0])) - struct cmd_struct { const char *name; int (*fn)(int, const char **); diff --git a/tools/pci/pcitest.c b/tools/pci/pcitest.c new file mode 100644 index 000000000000..ad54a58d7dda --- /dev/null +++ b/tools/pci/pcitest.c @@ -0,0 +1,186 @@ +/** + * Userspace PCI Endpoint Test Module + * + * Copyright (C) 2017 Texas Instruments + * Author: Kishon Vijay Abraham I <kishon@ti.com> + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 of + * the License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include <errno.h> +#include <fcntl.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <sys/ioctl.h> +#include <time.h> +#include <unistd.h> + +#include <linux/pcitest.h> + +#define BILLION 1E9 + +static char *result[] = { "NOT OKAY", "OKAY" }; + +struct pci_test { + char *device; + char barnum; + bool legacyirq; + unsigned int msinum; + bool read; + bool write; + bool copy; + unsigned long size; +}; + +static int run_test(struct pci_test *test) +{ + long ret; + int fd; + struct timespec start, end; + double time; + + fd = open(test->device, O_RDWR); + if (fd < 0) { + perror("can't open PCI Endpoint Test device"); + return fd; + } + + if (test->barnum >= 0 && test->barnum <= 5) { + ret = ioctl(fd, PCITEST_BAR, test->barnum); + fprintf(stdout, "BAR%d:\t\t", test->barnum); + if (ret < 0) + fprintf(stdout, "TEST FAILED\n"); + else + fprintf(stdout, "%s\n", result[ret]); + } + + if (test->legacyirq) { + ret = ioctl(fd, PCITEST_LEGACY_IRQ, 0); + fprintf(stdout, "LEGACY IRQ:\t"); + if (ret < 0) + fprintf(stdout, "TEST FAILED\n"); + else + fprintf(stdout, "%s\n", result[ret]); + } + + if (test->msinum > 0 && test->msinum <= 32) { + ret = ioctl(fd, PCITEST_MSI, test->msinum); + fprintf(stdout, "MSI%d:\t\t", test->msinum); + if (ret < 0) + fprintf(stdout, "TEST FAILED\n"); + else + fprintf(stdout, "%s\n", result[ret]); + } + + if (test->write) { + ret = ioctl(fd, PCITEST_WRITE, test->size); + fprintf(stdout, "WRITE (%7ld bytes):\t\t", test->size); + if (ret < 0) + fprintf(stdout, "TEST FAILED\n"); + else + fprintf(stdout, "%s\n", result[ret]); + } + + if (test->read) { + ret = ioctl(fd, PCITEST_READ, test->size); + fprintf(stdout, "READ (%7ld bytes):\t\t", test->size); + if (ret < 0) + fprintf(stdout, "TEST FAILED\n"); + else + fprintf(stdout, "%s\n", result[ret]); + } + + if (test->copy) { + ret = ioctl(fd, PCITEST_COPY, test->size); + fprintf(stdout, "COPY (%7ld bytes):\t\t", test->size); + if (ret < 0) + fprintf(stdout, "TEST FAILED\n"); + else + fprintf(stdout, "%s\n", result[ret]); + } + + fflush(stdout); +} + +int main(int argc, char **argv) +{ + int c; + struct pci_test *test; + + test = calloc(1, sizeof(*test)); + if (!test) { + perror("Fail to allocate memory for pci_test\n"); + return -ENOMEM; + } + + /* since '0' is a valid BAR number, initialize it to -1 */ + test->barnum = -1; + + /* set default size as 100KB */ + test->size = 0x19000; + + /* set default endpoint device */ + test->device = "/dev/pci-endpoint-test.0"; + + while ((c = getopt(argc, argv, "D:b:m:lrwcs:")) != EOF) + switch (c) { + case 'D': + test->device = optarg; + continue; + case 'b': + test->barnum = atoi(optarg); + if (test->barnum < 0 || test->barnum > 5) + goto usage; + continue; + case 'l': + test->legacyirq = true; + continue; + case 'm': + test->msinum = atoi(optarg); + if (test->msinum < 1 || test->msinum > 32) + goto usage; + continue; + case 'r': + test->read = true; + continue; + case 'w': + test->write = true; + continue; + case 'c': + test->copy = true; + continue; + case 's': + test->size = strtoul(optarg, NULL, 0); + continue; + case '?': + case 'h': + default: +usage: + fprintf(stderr, + "usage: %s [options]\n" + "Options:\n" + "\t-D <dev> PCI endpoint test device {default: /dev/pci-endpoint-test.0}\n" + "\t-b <bar num> BAR test (bar number between 0..5)\n" + "\t-m <msi num> MSI test (msi number between 1..32)\n" + "\t-r Read buffer test\n" + "\t-w Write buffer test\n" + "\t-c Copy buffer test\n" + "\t-s <size> Size of buffer {default: 100KB}\n", + argv[0]); + return -EINVAL; + } + + run_test(test); + return 0; +} diff --git a/tools/pci/pcitest.sh b/tools/pci/pcitest.sh new file mode 100644 index 000000000000..5442bbea4c22 --- /dev/null +++ b/tools/pci/pcitest.sh @@ -0,0 +1,56 @@ +#!/bin/sh + +echo "BAR tests" +echo + +bar=0 + +while [ $bar -lt 6 ] +do + pcitest -b $bar + bar=`expr $bar + 1` +done +echo + +echo "Interrupt tests" +echo + +pcitest -l +msi=1 + +while [ $msi -lt 33 ] +do + pcitest -m $msi + msi=`expr $msi + 1` +done +echo + +echo "Read Tests" +echo + +pcitest -r -s 1 +pcitest -r -s 1024 +pcitest -r -s 1025 +pcitest -r -s 1024000 +pcitest -r -s 1024001 +echo + +echo "Write Tests" +echo + +pcitest -w -s 1 +pcitest -w -s 1024 +pcitest -w -s 1025 +pcitest -w -s 1024000 +pcitest -w -s 1024001 +echo + +echo "Copy Tests" +echo + +pcitest -c -s 1 +pcitest -c -s 1024 +pcitest -c -s 1025 +pcitest -c -s 1024000 +pcitest -c -s 1024001 +echo diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore index 3db3db9278be..643cc4ba6872 100644 --- a/tools/perf/.gitignore +++ b/tools/perf/.gitignore @@ -31,3 +31,5 @@ config.mak.autogen .config-detected util/intel-pt-decoder/inat-tables.c arch/*/include/generated/ +pmu-events/pmu-events.c +pmu-events/jevents diff --git a/tools/perf/Build b/tools/perf/Build index b12d5d1666e3..bd8eeb60533c 100644 --- a/tools/perf/Build +++ b/tools/perf/Build @@ -3,10 +3,12 @@ perf-y += builtin-annotate.o perf-y += builtin-config.o perf-y += builtin-diff.o perf-y += builtin-evlist.o +perf-y += builtin-ftrace.o perf-y += builtin-help.o perf-y += builtin-sched.o perf-y += builtin-buildid-list.o perf-y += builtin-buildid-cache.o +perf-y += builtin-kallsyms.o perf-y += builtin-list.o perf-y += builtin-record.o perf-y += builtin-report.o @@ -39,8 +41,7 @@ CFLAGS_builtin-help.o += $(paths) CFLAGS_builtin-timechart.o += $(paths) CFLAGS_perf.o += -DPERF_HTML_PATH="BUILD_STR($(htmldir_SQ))" \ -DPERF_EXEC_PATH="BUILD_STR($(perfexecdir_SQ))" \ - -DPREFIX="BUILD_STR($(prefix_SQ))" \ - -include $(OUTPUT)PERF-VERSION-FILE + -DPREFIX="BUILD_STR($(prefix_SQ))" CFLAGS_builtin-trace.o += -DSTRACE_GROUPS_DIR="BUILD_STR($(STRACE_GROUPS_DIR_SQ))" CFLAGS_builtin-report.o += -DTIPDIR="BUILD_STR($(tipdir_SQ))" CFLAGS_builtin-report.o += -DDOCDIR="BUILD_STR($(srcdir_SQ)/Documentation)" @@ -49,5 +50,6 @@ libperf-y += util/ libperf-y += arch/ libperf-y += ui/ libperf-y += scripts/ +libperf-y += trace/beauty/ gtk-y += ui/gtk/ diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt index 8ffbd272952d..a89273d8e744 100644 --- a/tools/perf/Documentation/perf-annotate.txt +++ b/tools/perf/Documentation/perf-annotate.txt @@ -39,6 +39,10 @@ OPTIONS --verbose:: Be more verbose. (Show symbol address, etc) +-q:: +--quiet:: + Do not show any message. (Suppress -v) + -D:: --dump-raw-trace:: Dump raw trace in ASCII. diff --git a/tools/perf/Documentation/perf-c2c.txt b/tools/perf/Documentation/perf-c2c.txt index 3f06730c7f47..822414235170 100644 --- a/tools/perf/Documentation/perf-c2c.txt +++ b/tools/perf/Documentation/perf-c2c.txt @@ -76,7 +76,7 @@ REPORT OPTIONS -c:: --coalesce:: - Specify sorintg fields for single cacheline display. + Specify sorting fields for single cacheline display. Following fields are available: tid,pid,iaddr,dso (see COALESCE) @@ -106,7 +106,7 @@ REPORT OPTIONS -d:: --display:: - Siwtch to HITM type (rmt, lcl) to display and sort on. Total HITMs as default. + Switch to HITM type (rmt, lcl) to display and sort on. Total HITMs as default. C2C RECORD ---------- @@ -248,7 +248,7 @@ output fields set for caheline offsets output: Code address, Code symbol, Shared Object, Source line dso - coalesced by shared object -By default the coalescing is setup with 'pid,tid,iaddr'. +By default the coalescing is setup with 'pid,iaddr'. STDIO OUTPUT ------------ diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt index 9365b75fd04f..5b4fff3adc4b 100644 --- a/tools/perf/Documentation/perf-config.txt +++ b/tools/perf/Documentation/perf-config.txt @@ -498,6 +498,18 @@ record.*:: But if this option is 'no-cache', it will not update the build-id cache. 'skip' skips post-processing and does not update the cache. +diff.*:: + diff.order:: + This option sets the number of columns to sort the result. + The default is 0, which means sorting by baseline. + Setting it to 1 will sort the result by delta (or other + compute method selected). + + diff.compute:: + This options sets the method for computing the diff result. + Possible values are 'delta', 'delta-abs', 'ratio' and + 'wdiff'. Default is 'delta'. + SEE ALSO -------- linkperf:perf[1] diff --git a/tools/perf/Documentation/perf-diff.txt b/tools/perf/Documentation/perf-diff.txt index 3e9490b9c533..a79c84ae61aa 100644 --- a/tools/perf/Documentation/perf-diff.txt +++ b/tools/perf/Documentation/perf-diff.txt @@ -73,6 +73,10 @@ OPTIONS Be verbose, for instance, show the raw counts in addition to the diff. +-q:: +--quiet:: + Do not show any message. (Suppress -v) + -f:: --force:: Don't do ownership validation. @@ -86,8 +90,9 @@ OPTIONS -c:: --compute:: - Differential computation selection - delta,ratio,wdiff (default is delta). - See COMPARISON METHODS section for more info. + Differential computation selection - delta, ratio, wdiff, delta-abs + (default is delta-abs). Default can be changed using diff.compute + config option. See COMPARISON METHODS section for more info. -p:: --period:: @@ -99,7 +104,11 @@ OPTIONS -o:: --order:: - Specify compute sorting column number. + Specify compute sorting column number. 0 means sorting by baseline + overhead and 1 (default) means sorting by computed value of column 1 + (data from the first file other base baseline). Values more than 1 + can be used only if enough data files are provided. + The default value can be set using the diff.order config option. --percentage:: Determine how to display the overhead percentage of filtered entries. @@ -181,6 +190,10 @@ with: relative to how entries are filtered. Use --percentage=absolute to prevent such fluctuation. +delta-abs +~~~~~~~~~ +Same as 'delta` method, but sort the result with the absolute values. + ratio ~~~~~ If specified the 'Ratio' column is displayed with value 'r' computed as: diff --git a/tools/perf/Documentation/perf-ftrace.txt b/tools/perf/Documentation/perf-ftrace.txt new file mode 100644 index 000000000000..6e6a8b22c859 --- /dev/null +++ b/tools/perf/Documentation/perf-ftrace.txt @@ -0,0 +1,54 @@ +perf-ftrace(1) +============= + +NAME +---- +perf-ftrace - simple wrapper for kernel's ftrace functionality + + +SYNOPSIS +-------- +[verse] +'perf ftrace' <command> + +DESCRIPTION +----------- +The 'perf ftrace' command is a simple wrapper of kernel's ftrace +functionality. It only supports single thread tracing currently and +just reads trace_pipe in text and then write it to stdout. + +The following options apply to perf ftrace. + +OPTIONS +------- + +-t:: +--tracer=:: + Tracer to use: function_graph or function. + +-v:: +--verbose=:: + Verbosity level. + +-p:: +--pid=:: + Trace on existing process id (comma separated list). + +-a:: +--all-cpus:: + Force system-wide collection. Scripts run without a <command> + normally use -a by default, while scripts run with a <command> + normally don't - this option allows the latter to be run in + system-wide mode. + +-C:: +--cpu=:: + Only trace for the list of CPUs provided. Multiple CPUs can + be provided as a comma separated list with no space like: 0,1. + Ranges of CPUs are specified with -: 0-2. + Default is to trace on all online CPUs. + + +SEE ALSO +-------- +linkperf:perf-record[1], linkperf:perf-trace[1] diff --git a/tools/perf/Documentation/perf-kallsyms.txt b/tools/perf/Documentation/perf-kallsyms.txt new file mode 100644 index 000000000000..954ea9e21236 --- /dev/null +++ b/tools/perf/Documentation/perf-kallsyms.txt @@ -0,0 +1,24 @@ +perf-kallsyms(1) +============== + +NAME +---- +perf-kallsyms - Searches running kernel for symbols + +SYNOPSIS +-------- +[verse] +'perf kallsyms <options> symbol_name[,symbol_name...]' + +DESCRIPTION +----------- +This command searches the running kernel kallsyms file for the given symbol(s) +and prints information about it, including the DSO, the kallsyms begin/end +addresses and the addresses in the ELF kallsyms symbol table (for symbols in +modules). + +OPTIONS +------- +-v:: +--verbose=:: + Increase verbosity level, showing details about symbol table loading, etc. diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt index 41857cce5e86..f709de54707b 100644 --- a/tools/perf/Documentation/perf-list.txt +++ b/tools/perf/Documentation/perf-list.txt @@ -8,7 +8,7 @@ perf-list - List all symbolic event types SYNOPSIS -------- [verse] -'perf list' [--no-desc] [--long-desc] [hw|sw|cache|tracepoint|pmu|event_glob] +'perf list' [--no-desc] [--long-desc] [hw|sw|cache|tracepoint|pmu|sdt|event_glob] DESCRIPTION ----------- @@ -24,6 +24,10 @@ Don't print descriptions. --long-desc:: Print longer event descriptions. +--details:: +Print how named events are resolved internally into perf events, and also +any extra expressions computed by perf stat. + [[EVENT_MODIFIERS]] EVENT MODIFIERS @@ -240,6 +244,8 @@ To limit the list use: . 'pmu' to print the kernel supplied PMU events. +. 'sdt' to list all Statically Defined Tracepoint events. + . If none of the above is matched, it will apply the supplied glob to all events, printing the ones that match. diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 5054d9147f0f..b0e9e921d534 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -157,7 +157,7 @@ OPTIONS -a:: --all-cpus:: - System-wide collection from all CPUs. + System-wide collection from all CPUs (default if no target is specified). -p:: --pid=:: @@ -225,7 +225,7 @@ OPTIONS the libunwind or libdw library) should be used instead. Using the "lbr" method doesn't require any compiler options. It will produce call graphs from the hardware LBR registers. The - main limition is that it is only available on new Intel + main limitation is that it is only available on new Intel platforms, such as Haswell. It can only get user call chain. It doesn't work with branch stack sampling at the same time. @@ -347,6 +347,9 @@ Enable weightened sampling. An additional weight is recorded per sample and can displayed with the weight and local_weight sort keys. This currently works for TSX abort events and some memory events in precise mode on modern Intel CPUs. +--namespaces:: +Record events of type PERF_RECORD_NAMESPACES. + --transaction:: Record transaction flags for transaction related events. @@ -421,9 +424,19 @@ Configure all used events to run in user space. --timestamp-filename Append timestamp to output file name. ---switch-output:: +--switch-output[=mode]:: Generate multiple perf.data files, timestamp prefixed, switching to a new one -when receiving a SIGUSR2. +based on 'mode' value: + "signal" - when receiving a SIGUSR2 (default value) or + <size> - when reaching the size threshold, size is expected to + be a number with appended unit character - B/K/M/G + <time> - when reaching the time threshold, size is expected to + be a number with appended unit character - s/m/h/d + + Note: the precision of the size threshold hugely depends + on your configuration - the number and size of your ring + buffers (-m). It is generally more precise for higher sizes + (like >5M), for lower values expect different sizes. A possible use case is to, given an external event, slice the perf.data file that gets then processed, possibly via a perf script, to decide if that diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index f2914f03ae7b..9fa84617181e 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -25,6 +25,10 @@ OPTIONS --verbose:: Be more verbose. (show symbol address, etc) +-q:: +--quiet:: + Do not show any message. (Suppress -v) + -n:: --show-nr-samples:: Show the number of samples for each symbol @@ -68,7 +72,8 @@ OPTIONS --sort=:: Sort histogram entries by given key(s) - multiple keys can be specified in CSV format. Following sort keys are available: - pid, comm, dso, symbol, parent, cpu, socket, srcline, weight, local_weight. + pid, comm, dso, symbol, parent, cpu, socket, srcline, weight, + local_weight, cgroup_id. Each key has following meaning: @@ -76,6 +81,7 @@ OPTIONS - pid: command and tid of the task - dso: name of library or module executed at the time of sample - symbol: name of function executed at the time of sample + - symbol_size: size of function executed at the time of sample - parent: name of function matched to the parent regex filter. Unmatched entries are displayed as "[other]". - cpu: cpu number the task ran at the time of sample @@ -87,6 +93,7 @@ OPTIONS - weight: Event specific weight, e.g. memory latency or transaction abort cost. This is the global weight. - local_weight: Local weight version of the weight above. + - cgroup_id: ID derived from cgroup namespace device and inode numbers. - transaction: Transaction abort flags. - overhead: Overhead percentage of sample - overhead_sys: Overhead percentage of sample running in system mode @@ -168,11 +175,14 @@ OPTIONS By default, every sort keys not specified in -F will be appended automatically. + If the keys starts with a prefix '+', then it will append the specified + field(s) to the default field order. For example: perf report -F +period,sample. + -p:: --parent=<regex>:: A regex filter to identify parent. The parent is a caller of this function and searched through the callchain, thus it requires callchain - information recorded. The pattern is in the exteneded regex format and + information recorded. The pattern is in the extended regex format and defaults to "\^sys_|^do_page_fault", see '--sort parent'. -x:: @@ -197,8 +207,8 @@ OPTIONS -g:: --call-graph=<print_type,threshold[,print_limit],order,sort_key[,branch],value>:: Display call chains using type, min percent threshold, print limit, - call order, sort key, optional branch and value. Note that ordering of - parameters is not fixed so any parement can be given in an arbitraty order. + call order, sort key, optional branch and value. Note that ordering + is not fixed so any parameter can be given in an arbitrary order. One exception is the print_limit which should be preceded by threshold. print_type can be either: @@ -225,6 +235,7 @@ OPTIONS sort_key can be: - function: compare on functions (default) - address: compare on individual code addresses + - srcline: compare on source filename and line number branch can be: - branch: include last branch information in callgraph when available. @@ -420,6 +431,10 @@ include::itrace.txt[] --hierarchy:: Enable hierarchical output. +--inline:: + If a callgraph address belongs to an inlined function, the inline stack + will be printed. Each entry is function name or file/line. + include::callchain-overhead-calculation.txt[] SEE ALSO diff --git a/tools/perf/Documentation/perf-sched.txt b/tools/perf/Documentation/perf-sched.txt index 76173969ab80..a092a2499e8f 100644 --- a/tools/perf/Documentation/perf-sched.txt +++ b/tools/perf/Documentation/perf-sched.txt @@ -132,6 +132,10 @@ OPTIONS for 'perf sched timehist' --migrations:: Show migration events. +-n:: +--next:: + Show next task. + -I:: --idle-hist:: Show idle-related events only. @@ -143,6 +147,8 @@ OPTIONS for 'perf sched timehist' stop time is not given (i.e, time string is 'x.y,') then analysis goes to end of file. +--state:: + Show task state when it switched out. SEE ALSO -------- diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index 5dc5c6a09ac4..cb0eda3925e6 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -36,7 +36,7 @@ There are several variants of perf script: 'perf script report <script> [args]' to run and display the results of <script>. <script> is the name displayed in the output of 'perf - trace --list' i.e. the actual script name minus any language + script --list' i.e. the actual script name minus any language extension. The perf.data output from a previous run of 'perf script record <script>' is used and should be present for this command to succeed. [args] refers to the (mainly optional) args expected by @@ -76,7 +76,7 @@ OPTIONS Any command you can specify in a shell. -D:: ---dump-raw-script=:: +--dump-raw-trace=:: Display verbose dump of the trace data. -L:: @@ -116,7 +116,7 @@ OPTIONS --fields:: Comma separated list of fields to print. Options are: comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff, - srcline, period, iregs, brstack, brstacksym, flags, bpf-output, + srcline, period, iregs, brstack, brstacksym, flags, bpf-output, brstackinsn, callindent, insn, insnlen. Field list can be prepended with the type, trace, sw or hw, to indicate to which event type the field list applies. e.g., -F sw:comm,tid,time,ip,sym and -F trace:time,cpu,trace @@ -189,15 +189,20 @@ OPTIONS i.e., -F "" is not allowed. The brstack output includes branch related information with raw addresses using the - /v/v/v/v/ syntax in the following order: + /v/v/v/v/cycles syntax in the following order: FROM: branch source instruction TO : branch target instruction M/P/-: M=branch target mispredicted or branch direction was mispredicted, P=target predicted or direction predicted, -=not supported X/- : X=branch inside a transactional region, -=not in transaction region or not supported A/- : A=TSX abort entry, -=not aborted region or not supported + cycles The brstacksym is identical to brstack, except that the FROM and TO addresses are printed in a symbolic form if possible. + When brstackinsn is specified the full assembler sequences of branch sequences for each sample + is printed. This is the full execution path leading to the sample. This is only supported when the + sample was recorded with perf record -b or -j any. + -k:: --vmlinux=<file>:: vmlinux pathname @@ -248,6 +253,9 @@ OPTIONS --show-mmap-events Display mmap related events (e.g. MMAP, MMAP2). +--show-namespace-events + Display namespace events i.e. events of type PERF_RECORD_NAMESPACES. + --show-switch-events Display context switch events i.e. events of type PERF_RECORD_SWITCH or PERF_RECORD_SWITCH_CPU_WIDE. @@ -299,6 +307,10 @@ include::itrace.txt[] stop time is not given (i.e, time string is 'x.y,') then analysis goes to end of file. +--max-blocks:: + Set the maximum number of program blocks to print with brstackasm for + each sample. + SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-script-perl[1], diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index d96ccd4844df..bd0e4417f2be 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -63,7 +63,7 @@ report:: -a:: --all-cpus:: - system-wide collection from all CPUs + system-wide collection from all CPUs (default if no target is specified) -c:: --scale:: @@ -94,8 +94,7 @@ to activate system-wide monitoring. Default is to count on all CPUs. -A:: --no-aggr:: -Do not aggregate counts across all monitored CPUs in system-wide mode (-a). -This option is only valid in system-wide mode. +Do not aggregate counts across all monitored CPUs. -n:: --null:: @@ -237,6 +236,9 @@ To interpret the results it is usually needed to know on which CPUs the workload runs on. If needed the CPUs can be forced using taskset. +--no-merge:: +Do not merge results from same PMUs. + EXAMPLES -------- diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt index 781b019751a4..c1e3288a2dfb 100644 --- a/tools/perf/Documentation/perf-trace.txt +++ b/tools/perf/Documentation/perf-trace.txt @@ -35,7 +35,10 @@ OPTIONS -e:: --expr:: - List of syscalls to show, currently only syscall names. +--event:: + List of syscalls and other perf events (tracepoints, HW cache events, + etc) to show. + See 'perf list' for a complete list of events. Prefixing with ! shows all syscalls but the ones specified. You may need to escape it. @@ -120,7 +123,8 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs. major or all pagefaults. Default value is maj. --syscalls:: - Trace system calls. This options is enabled by default. + Trace system calls. This options is enabled by default, disable with + --no-syscalls. --call-graph [mode,type,min[,limit],order[,key][,branch]]:: Setup and enable call-graph (stack chain/backtrace) recording. @@ -135,9 +139,6 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs. --kernel-syscall-graph:: Show the kernel callchains on the syscall exit path. ---event:: - Trace other events, see 'perf list' for a complete list. - --max-stack:: Set the stack depth limit when parsing the callchain, anything beyond the specified depth will be ignored. Note that at this point diff --git a/tools/perf/Documentation/perf.data-file-format.txt b/tools/perf/Documentation/perf.data-file-format.txt index b664b18d3991..de8b39dda7b8 100644 --- a/tools/perf/Documentation/perf.data-file-format.txt +++ b/tools/perf/Documentation/perf.data-file-format.txt @@ -11,8 +11,8 @@ All fields are in native-endian of the machine that generated the perf.data. When perf is writing to a pipe it uses a special version of the file format that does not rely on seeking to adjust data offsets. This -format is not described here. The pipe version can be converted to -normal perf.data with perf inject. +format is described in "Pipe-mode data" section. The pipe data version can be +augmented with additional events using perf inject. The file starts with a perf_header: @@ -270,7 +270,7 @@ When the event stream contains multiple events each event is identified by an ID. This can be either through the PERF_SAMPLE_ID or the PERF_SAMPLE_IDENTIFIER header. The PERF_SAMPLE_IDENTIFIER header is at a fixed offset from the event header, which allows reliable -parsing of the header. Relying on ID may be ambigious. +parsing of the header. Relying on ID may be ambiguous. IDENTIFIER is only supported by newer Linux kernels. Perf record specific events: @@ -288,7 +288,7 @@ struct attr_event { uint64_t id[]; }; - PERF_RECORD_HEADER_EVENT_TYPE = 65, /* depreceated */ + PERF_RECORD_HEADER_EVENT_TYPE = 65, /* deprecated */ #define MAX_EVENT_NAME 64 @@ -411,6 +411,21 @@ An array bound by the perf_file_section size. ids points to a array of uint64_t defining the ids for event attr attr. +Pipe-mode data + +Pipe-mode avoid seeks in the file by removing the perf_file_section and flags +from the struct perf_header. The trimmed header is: + +struct perf_pipe_file_header { + u64 magic; + u64 size; +}; + +The information about attrs, data, and event_types is instead in the +synthesized events PERF_RECORD_ATTR, PERF_RECORD_HEADER_TRACING_DATA and +PERF_RECORD_HEADER_EVENT_TYPE that are generated by perf record in pipe-mode. + + References: include/uapi/linux/perf_event.h diff --git a/tools/perf/Documentation/tips.txt b/tools/perf/Documentation/tips.txt index 8a6479c0eac9..db0ca3063eae 100644 --- a/tools/perf/Documentation/tips.txt +++ b/tools/perf/Documentation/tips.txt @@ -22,8 +22,8 @@ If you have debuginfo enabled, try: perf report -s sym,srcline For memory address profiling, try: perf mem record / perf mem report For tracepoint events, try: perf report -s trace_fields To record callchains for each sample: perf record -g -To record every process run by an user: perf record -u <user> -Skip collecing build-id when recording: perf record -B +To record every process run by a user: perf record -u <user> +Skip collecting build-id when recording: perf record -B To change sampling frequency to 100 Hz: perf record -F 100 See assembly instructions with percentage: perf annotate <symbol> If you prefer Intel style assembly, try: perf annotate -M intel diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index a511e5f31e36..a29da46d180f 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -12,6 +12,7 @@ tools/arch/sparc/include/asm/barrier_32.h tools/arch/sparc/include/asm/barrier_64.h tools/arch/tile/include/asm/barrier.h tools/arch/x86/include/asm/barrier.h +tools/arch/x86/include/asm/cmpxchg.h tools/arch/x86/include/asm/cpufeatures.h tools/arch/x86/include/asm/disabled-features.h tools/arch/x86/include/asm/required-features.h @@ -61,7 +62,9 @@ tools/include/asm-generic/bitops.h tools/include/linux/atomic.h tools/include/linux/bitops.h tools/include/linux/compiler.h +tools/include/linux/compiler-gcc.h tools/include/linux/coresight-pmu.h +tools/include/linux/bug.h tools/include/linux/filter.h tools/include/linux/hash.h tools/include/linux/kernel.h @@ -71,12 +74,15 @@ tools/include/uapi/asm-generic/mman-common.h tools/include/uapi/asm-generic/mman.h tools/include/uapi/linux/bpf.h tools/include/uapi/linux/bpf_common.h +tools/include/uapi/linux/fcntl.h tools/include/uapi/linux/hw_breakpoint.h tools/include/uapi/linux/mman.h tools/include/uapi/linux/perf_event.h +tools/include/uapi/linux/stat.h tools/include/linux/poison.h tools/include/linux/rbtree.h tools/include/linux/rbtree_augmented.h +tools/include/linux/refcount.h tools/include/linux/string.h tools/include/linux/stringify.h tools/include/linux/types.h diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 76c84f0eec52..8354d04b392f 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -144,8 +144,12 @@ ifndef DEBUG endif ifeq ($(DEBUG),0) +ifeq ($(CC), clang) + CFLAGS += -O3 +else CFLAGS += -O6 endif +endif ifdef PARSER_DEBUG PARSER_DEBUG_BISON := -t @@ -166,10 +170,21 @@ PYTHON2_CONFIG := \ override PYTHON_CONFIG := \ $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON2_CONFIG)) +grep-libs = $(filter -l%,$(1)) +strip-libs = $(filter-out -l%,$(1)) + PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG)) -PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null) -PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null) +ifdef PYTHON_CONFIG + PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null) + PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS)) + PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil + PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null) + ifeq ($(CC), clang) + PYTHON_EMBED_CCOPTS := $(filter-out -specs=%,$(PYTHON_EMBED_CCOPTS)) + endif + FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS) +endif FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS) FEATURE_CHECK_LDFLAGS-libpython := $(PYTHON_EMBED_LDOPTS) @@ -259,6 +274,7 @@ ifdef NO_LIBELF NO_LIBUNWIND := 1 NO_LIBDW_DWARF_UNWIND := 1 NO_LIBBPF := 1 + NO_JVMTI := 1 else ifeq ($(feature-libelf), 0) ifeq ($(feature-glibc), 1) @@ -268,7 +284,7 @@ else LIBC_SUPPORT := 1 endif ifeq ($(LIBC_SUPPORT),1) - msg := $(warning No libelf found, disables 'probe' tool and BPF support in 'perf record', please install libelf-dev, libelf-devel or elfutils-libelf-devel); + msg := $(warning No libelf found. Disables 'probe' tool, jvmti and BPF support in 'perf record'. Please install libelf-dev, libelf-devel or elfutils-libelf-devel); NO_LIBELF := 1 NO_DWARF := 1 @@ -276,6 +292,7 @@ else NO_LIBUNWIND := 1 NO_LIBDW_DWARF_UNWIND := 1 NO_LIBBPF := 1 + NO_JVMTI := 1 else ifneq ($(filter s% -static%,$(LDFLAGS),),) msg := $(error No static glibc found, please install glibc-static); @@ -291,8 +308,10 @@ else endif endif ifneq ($(feature-dwarf), 1) - msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev); - NO_DWARF := 1 + ifndef NO_DWARF + msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev); + NO_DWARF := 1 + endif else ifneq ($(feature-dwarf_getlocations), 1) msg := $(warning Old libdw.h, finding variables at given 'perf probe' point will not work, install elfutils-devel/libdw-dev >= 0.157); @@ -307,6 +326,10 @@ ifdef NO_DWARF NO_LIBDW_DWARF_UNWIND := 1 endif +ifeq ($(feature-sched_getcpu), 1) + CFLAGS += -DHAVE_SCHED_GETCPU_SUPPORT +endif + ifndef NO_LIBELF CFLAGS += -DHAVE_LIBELF_SUPPORT EXTLIBS += -lelf @@ -540,8 +563,6 @@ ifndef NO_GTK2 endif endif -grep-libs = $(filter -l%,$(1)) -strip-libs = $(filter-out -l%,$(1)) ifdef NO_LIBPERL CFLAGS += -DNO_LIBPERL @@ -589,18 +610,9 @@ else $(call disable-python,No 'python-config' tool was found: disables Python support - please install python-devel/python-dev) else - PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG)) - - PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null) - PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS)) - PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil - PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null) - FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS) - ifneq ($(feature-libpython), 1) $(call disable-python,No 'Python.h' (for Python 2.x support) was found: disables Python support - please install python-devel/python-dev) else - ifneq ($(feature-libpython-version), 1) $(warning Python 3 is not yet supported; please set) $(warning PYTHON and/or PYTHON_CONFIG appropriately.) diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 8bb16aa9d661..79fe31f20a17 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -661,6 +661,7 @@ ifndef NO_PERF_READ_VDSOX32 endif ifndef NO_JVMTI $(call QUIET_INSTALL, $(LIBJVMTI)) \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(libdir_SQ)'; \ $(INSTALL) $(OUTPUT)$(LIBJVMTI) '$(DESTDIR_SQ)$(libdir_SQ)'; endif $(call QUIET_INSTALL, libexec) \ @@ -725,13 +726,13 @@ config-clean: $(call QUIET_CLEAN, config) $(Q)$(MAKE) -C $(srctree)/tools/build/feature/ $(if $(OUTPUT),OUTPUT=$(OUTPUT)feature/,) clean >/dev/null -clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean config-clean +clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean config-clean fixdep-clean $(call QUIET_CLEAN, core-objs) $(RM) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(LANG_BINDINGS) $(Q)find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete $(Q)$(RM) $(OUTPUT).config-detected $(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32 $(OUTPUT)pmu-events/jevents $(OUTPUT)$(LIBJVMTI).so $(call QUIET_CLEAN, core-gen) $(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)FEATURE-DUMP $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex* \ - $(OUTPUT)util/intel-pt-decoder/inat-tables.c $(OUTPUT)fixdep \ + $(OUTPUT)util/intel-pt-decoder/inat-tables.c \ $(OUTPUT)tests/llvm-src-{base,kbuild,prologue,relocation}.c \ $(OUTPUT)pmu-events/pmu-events.c $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index dfea6b635525..29361d9b635a 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -33,6 +33,7 @@ #include "../../util/cs-etm.h" #include <stdlib.h> +#include <sys/stat.h> #define ENABLE_SINK_MAX 128 #define CS_BUS_DEVICE_PATH "/bus/coresight/devices/" diff --git a/tools/perf/arch/arm/util/dwarf-regs.c b/tools/perf/arch/arm/util/dwarf-regs.c index 33ec5b339da8..8bb176a37990 100644 --- a/tools/perf/arch/arm/util/dwarf-regs.c +++ b/tools/perf/arch/arm/util/dwarf-regs.c @@ -9,6 +9,7 @@ */ #include <stddef.h> +#include <linux/stringify.h> #include <dwarf-regs.h> struct pt_regs_dwarfnum { @@ -16,10 +17,9 @@ struct pt_regs_dwarfnum { unsigned int dwarfnum; }; -#define STR(s) #s #define REG_DWARFNUM_NAME(r, num) {.name = r, .dwarfnum = num} #define GPR_DWARFNUM_NAME(num) \ - {.name = STR(%r##num), .dwarfnum = num} + {.name = __stringify(%r##num), .dwarfnum = num} #define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0} /* diff --git a/tools/perf/arch/arm/util/unwind-libdw.c b/tools/perf/arch/arm/util/unwind-libdw.c index b4176c60117a..bacfa00fca39 100644 --- a/tools/perf/arch/arm/util/unwind-libdw.c +++ b/tools/perf/arch/arm/util/unwind-libdw.c @@ -1,6 +1,7 @@ #include <elfutils/libdwfl.h> #include "../../util/unwind-libdw.h" #include "../../util/perf_regs.h" +#include "../../util/event.h" bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg) { diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile index 18b13518d8d8..eebe1ec9d2ee 100644 --- a/tools/perf/arch/arm64/Makefile +++ b/tools/perf/arch/arm64/Makefile @@ -2,3 +2,4 @@ ifndef NO_DWARF PERF_HAVE_DWARF_REGS := 1 endif PERF_HAVE_JITDUMP := 1 +PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1 diff --git a/tools/perf/arch/arm64/annotate/instructions.c b/tools/perf/arch/arm64/annotate/instructions.c index 44eafd6f2d50..8f1908756cb6 100644 --- a/tools/perf/arch/arm64/annotate/instructions.c +++ b/tools/perf/arch/arm64/annotate/instructions.c @@ -50,7 +50,7 @@ static int arm64__annotate_init(struct arch *arch) arch->initialized = true; arch->priv = arm; arch->associate_instruction_ops = arm64__associate_instruction_ops; - arch->objdump.comment_char = ';'; + arch->objdump.comment_char = '/'; arch->objdump.skip_functions_char = '+'; return 0; diff --git a/tools/perf/arch/arm64/include/dwarf-regs-table.h b/tools/perf/arch/arm64/include/dwarf-regs-table.h index 26759363f921..36e375f5a211 100644 --- a/tools/perf/arch/arm64/include/dwarf-regs-table.h +++ b/tools/perf/arch/arm64/include/dwarf-regs-table.h @@ -2,12 +2,12 @@ /* This is included in perf/util/dwarf-regs.c */ static const char * const aarch64_regstr_tbl[] = { - "%r0", "%r1", "%r2", "%r3", "%r4", - "%r5", "%r6", "%r7", "%r8", "%r9", - "%r10", "%r11", "%r12", "%r13", "%r14", - "%r15", "%r16", "%r17", "%r18", "%r19", - "%r20", "%r21", "%r22", "%r23", "%r24", - "%r25", "%r26", "%r27", "%r28", "%r29", + "%x0", "%x1", "%x2", "%x3", "%x4", + "%x5", "%x6", "%x7", "%x8", "%x9", + "%x10", "%x11", "%x12", "%x13", "%x14", + "%x15", "%x16", "%x17", "%x18", "%x19", + "%x20", "%x21", "%x22", "%x23", "%x24", + "%x25", "%x26", "%x27", "%x28", "%x29", "%lr", "%sp", }; #endif diff --git a/tools/perf/arch/arm64/util/dwarf-regs.c b/tools/perf/arch/arm64/util/dwarf-regs.c index d49efeb8172e..cd764a9fd098 100644 --- a/tools/perf/arch/arm64/util/dwarf-regs.c +++ b/tools/perf/arch/arm64/util/dwarf-regs.c @@ -8,19 +8,25 @@ * published by the Free Software Foundation. */ +#include <errno.h> #include <stddef.h> +#include <string.h> #include <dwarf-regs.h> +#include <linux/ptrace.h> /* for struct user_pt_regs */ +#include <linux/stringify.h> +#include "util.h" struct pt_regs_dwarfnum { const char *name; unsigned int dwarfnum; }; -#define STR(s) #s #define REG_DWARFNUM_NAME(r, num) {.name = r, .dwarfnum = num} #define GPR_DWARFNUM_NAME(num) \ - {.name = STR(%x##num), .dwarfnum = num} + {.name = __stringify(%x##num), .dwarfnum = num} #define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0} +#define DWARFNUM2OFFSET(index) \ + (index * sizeof((struct user_pt_regs *)0)->regs[0]) /* * Reference: @@ -78,3 +84,13 @@ const char *get_arch_regstr(unsigned int n) return roff->name; return NULL; } + +int regs_query_register_offset(const char *name) +{ + const struct pt_regs_dwarfnum *roff; + + for (roff = regdwarfnum_table; roff->name != NULL; roff++) + if (!strcmp(roff->name, name)) + return DWARFNUM2OFFSET(roff->dwarfnum); + return -EINVAL; +} diff --git a/tools/perf/arch/arm64/util/unwind-libunwind.c b/tools/perf/arch/arm64/util/unwind-libunwind.c index c116b713f7f7..b415dfdbccca 100644 --- a/tools/perf/arch/arm64/util/unwind-libunwind.c +++ b/tools/perf/arch/arm64/util/unwind-libunwind.c @@ -1,6 +1,6 @@ +#include <errno.h> #ifndef REMOTE_UNWIND_LIBUNWIND -#include <errno.h> #include <libunwind.h> #include "perf_regs.h" #include "../../util/unwind.h" diff --git a/tools/perf/arch/common.c b/tools/perf/arch/common.c index 886dd2aaff0d..837067f48a4c 100644 --- a/tools/perf/arch/common.c +++ b/tools/perf/arch/common.c @@ -4,6 +4,8 @@ #include "../util/util.h" #include "../util/debug.h" +#include "sane_ctype.h" + const char *const arm_triplets[] = { "arm-eabi-", "arm-linux-androideabi-", diff --git a/tools/perf/arch/powerpc/util/dwarf-regs.c b/tools/perf/arch/powerpc/util/dwarf-regs.c index 41bdf9530d82..98ac87052a74 100644 --- a/tools/perf/arch/powerpc/util/dwarf-regs.c +++ b/tools/perf/arch/powerpc/util/dwarf-regs.c @@ -15,6 +15,7 @@ #include <dwarf-regs.h> #include <linux/ptrace.h> #include <linux/kernel.h> +#include <linux/stringify.h> #include "util.h" struct pt_regs_dwarfnum { @@ -24,10 +25,10 @@ struct pt_regs_dwarfnum { }; #define REG_DWARFNUM_NAME(r, num) \ - {.name = STR(%)STR(r), .dwarfnum = num, \ + {.name = __stringify(%)__stringify(r), .dwarfnum = num, \ .ptregs_offset = offsetof(struct pt_regs, r)} #define GPR_DWARFNUM_NAME(num) \ - {.name = STR(%gpr##num), .dwarfnum = num, \ + {.name = __stringify(%gpr##num), .dwarfnum = num, \ .ptregs_offset = offsetof(struct pt_regs, gpr[num])} #define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0, .ptregs_offset = 0} diff --git a/tools/perf/arch/powerpc/util/kvm-stat.c b/tools/perf/arch/powerpc/util/kvm-stat.c index 74eee30398f8..249723f0e6a9 100644 --- a/tools/perf/arch/powerpc/util/kvm-stat.c +++ b/tools/perf/arch/powerpc/util/kvm-stat.c @@ -1,3 +1,4 @@ +#include <errno.h> #include "util/kvm-stat.h" #include "util/parse-events.h" #include "util/debug.h" diff --git a/tools/perf/arch/powerpc/util/perf_regs.c b/tools/perf/arch/powerpc/util/perf_regs.c index a3c3e1ce6807..f860dc411f69 100644 --- a/tools/perf/arch/powerpc/util/perf_regs.c +++ b/tools/perf/arch/powerpc/util/perf_regs.c @@ -1,5 +1,11 @@ +#include <errno.h> +#include <string.h> +#include <regex.h> + #include "../../perf.h" +#include "../../util/util.h" #include "../../util/perf_regs.h" +#include "../../util/debug.h" const struct sample_reg sample_reg_masks[] = { SMPL_REG(r0, PERF_REG_POWERPC_R0), @@ -47,3 +53,109 @@ const struct sample_reg sample_reg_masks[] = { SMPL_REG(dsisr, PERF_REG_POWERPC_DSISR), SMPL_REG_END }; + +/* REG or %rREG */ +#define SDT_OP_REGEX1 "^(%r)?([1-2]?[0-9]|3[0-1])$" + +/* -NUM(REG) or NUM(REG) or -NUM(%rREG) or NUM(%rREG) */ +#define SDT_OP_REGEX2 "^(\\-)?([0-9]+)\\((%r)?([1-2]?[0-9]|3[0-1])\\)$" + +static regex_t sdt_op_regex1, sdt_op_regex2; + +static int sdt_init_op_regex(void) +{ + static int initialized; + int ret = 0; + + if (initialized) + return 0; + + ret = regcomp(&sdt_op_regex1, SDT_OP_REGEX1, REG_EXTENDED); + if (ret) + goto error; + + ret = regcomp(&sdt_op_regex2, SDT_OP_REGEX2, REG_EXTENDED); + if (ret) + goto free_regex1; + + initialized = 1; + return 0; + +free_regex1: + regfree(&sdt_op_regex1); +error: + pr_debug4("Regex compilation error.\n"); + return ret; +} + +/* + * Parse OP and convert it into uprobe format, which is, +/-NUM(%gprREG). + * Possible variants of OP are: + * Format Example + * ------------------------- + * NUM(REG) 48(18) + * -NUM(REG) -48(18) + * NUM(%rREG) 48(%r18) + * -NUM(%rREG) -48(%r18) + * REG 18 + * %rREG %r18 + * iNUM i0 + * i-NUM i-1 + * + * SDT marker arguments on Powerpc uses %rREG form with -mregnames flag + * and REG form with -mno-regnames. Here REG is general purpose register, + * which is in 0 to 31 range. + */ +int arch_sdt_arg_parse_op(char *old_op, char **new_op) +{ + int ret, new_len; + regmatch_t rm[5]; + char prefix; + + /* Constant argument. Uprobe does not support it */ + if (old_op[0] == 'i') { + pr_debug4("Skipping unsupported SDT argument: %s\n", old_op); + return SDT_ARG_SKIP; + } + + ret = sdt_init_op_regex(); + if (ret < 0) + return ret; + + if (!regexec(&sdt_op_regex1, old_op, 3, rm, 0)) { + /* REG or %rREG --> %gprREG */ + + new_len = 5; /* % g p r NULL */ + new_len += (int)(rm[2].rm_eo - rm[2].rm_so); + + *new_op = zalloc(new_len); + if (!*new_op) + return -ENOMEM; + + scnprintf(*new_op, new_len, "%%gpr%.*s", + (int)(rm[2].rm_eo - rm[2].rm_so), old_op + rm[2].rm_so); + } else if (!regexec(&sdt_op_regex2, old_op, 5, rm, 0)) { + /* + * -NUM(REG) or NUM(REG) or -NUM(%rREG) or NUM(%rREG) --> + * +/-NUM(%gprREG) + */ + prefix = (rm[1].rm_so == -1) ? '+' : '-'; + + new_len = 8; /* +/- ( % g p r ) NULL */ + new_len += (int)(rm[2].rm_eo - rm[2].rm_so); + new_len += (int)(rm[4].rm_eo - rm[4].rm_so); + + *new_op = zalloc(new_len); + if (!*new_op) + return -ENOMEM; + + scnprintf(*new_op, new_len, "%c%.*s(%%gpr%.*s)", prefix, + (int)(rm[2].rm_eo - rm[2].rm_so), old_op + rm[2].rm_so, + (int)(rm[4].rm_eo - rm[4].rm_so), old_op + rm[4].rm_so); + } else { + pr_debug4("Skipping unsupported SDT argument: %s\n", old_op); + return SDT_ARG_SKIP; + } + + return SDT_ARG_VALID; +} diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c index 1030a6e504bb..bf9a2594572c 100644 --- a/tools/perf/arch/powerpc/util/sym-handling.c +++ b/tools/perf/arch/powerpc/util/sym-handling.c @@ -10,6 +10,7 @@ #include "symbol.h" #include "map.h" #include "probe-event.h" +#include "probe-file.h" #ifdef HAVE_LIBELF_SUPPORT bool elf__needs_adjust_symbols(GElf_Ehdr ehdr) @@ -51,6 +52,18 @@ int arch__compare_symbol_names(const char *namea, const char *nameb) return strcmp(namea, nameb); } + +int arch__compare_symbol_names_n(const char *namea, const char *nameb, + unsigned int n) +{ + /* Skip over initial dot */ + if (*namea == '.') + namea++; + if (*nameb == '.') + nameb++; + + return strncmp(namea, nameb, n); +} #endif #if defined(_CALL_ELF) && _CALL_ELF == 2 @@ -79,13 +92,18 @@ void arch__fix_tev_from_maps(struct perf_probe_event *pev, * However, if the user specifies an offset, we fall back to using the * GEP since all userspace applications (objdump/readelf) show function * disassembly with offsets from the GEP. - * - * In addition, we shouldn't specify an offset for kretprobes. */ - if (pev->point.offset || (!pev->uprobes && pev->point.retprobe) || - !map || !sym) + if (pev->point.offset || !map || !sym) return; + /* For kretprobes, add an offset only if the kernel supports it */ + if (!pev->uprobes && pev->point.retprobe) { +#ifdef HAVE_LIBELF_SUPPORT + if (!kretprobe_offset_is_supported()) +#endif + return; + } + lep_offset = PPC64_LOCAL_ENTRY_OFFSET(sym->arch_sym); if (map->dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS) diff --git a/tools/perf/arch/s390/annotate/instructions.c b/tools/perf/arch/s390/annotate/instructions.c new file mode 100644 index 000000000000..745b4b1b8b21 --- /dev/null +++ b/tools/perf/arch/s390/annotate/instructions.c @@ -0,0 +1,30 @@ +static struct ins_ops *s390__associate_ins_ops(struct arch *arch, const char *name) +{ + struct ins_ops *ops = NULL; + + /* catch all kind of jumps */ + if (strchr(name, 'j') || + !strncmp(name, "bct", 3) || + !strncmp(name, "br", 2)) + ops = &jump_ops; + /* override call/returns */ + if (!strcmp(name, "bras") || + !strcmp(name, "brasl") || + !strcmp(name, "basr")) + ops = &call_ops; + if (!strcmp(name, "br")) + ops = &ret_ops; + + arch__associate_ins_ops(arch, name, ops); + return ops; +} + +static int s390__annotate_init(struct arch *arch) +{ + if (!arch->initialized) { + arch->initialized = true; + arch->associate_instruction_ops = s390__associate_ins_ops; + } + + return 0; +} diff --git a/tools/perf/arch/s390/util/kvm-stat.c b/tools/perf/arch/s390/util/kvm-stat.c index ed57df2e6d68..d233e2eb9592 100644 --- a/tools/perf/arch/s390/util/kvm-stat.c +++ b/tools/perf/arch/s390/util/kvm-stat.c @@ -9,6 +9,7 @@ * as published by the Free Software Foundation. */ +#include <errno.h> #include "../../util/kvm-stat.h" #include <asm/sie.h> diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index e93ef0b38db8..5aef183e2f85 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -338,6 +338,7 @@ 329 common pkey_mprotect sys_pkey_mprotect 330 common pkey_alloc sys_pkey_alloc 331 common pkey_free sys_pkey_free +332 common statx sys_statx # # x32-specific system call numbers start at 512 to avoid cache impact diff --git a/tools/perf/arch/x86/tests/intel-cqm.c b/tools/perf/arch/x86/tests/intel-cqm.c index 7f064eb37158..f9713a71d77e 100644 --- a/tools/perf/arch/x86/tests/intel-cqm.c +++ b/tools/perf/arch/x86/tests/intel-cqm.c @@ -6,7 +6,10 @@ #include "evsel.h" #include "arch-tests.h" +#include <signal.h> #include <sys/mman.h> +#include <sys/wait.h> +#include <errno.h> #include <string.h> static pid_t spawn(void) diff --git a/tools/perf/arch/x86/tests/perf-time-to-tsc.c b/tools/perf/arch/x86/tests/perf-time-to-tsc.c index 5c76cc83186a..e3ae9cff2b67 100644 --- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c +++ b/tools/perf/arch/x86/tests/perf-time-to-tsc.c @@ -1,3 +1,5 @@ +#include <errno.h> +#include <inttypes.h> #include <stdio.h> #include <unistd.h> #include <linux/types.h> diff --git a/tools/perf/arch/x86/util/auxtrace.c b/tools/perf/arch/x86/util/auxtrace.c index cc1d865e31f1..6aa3f2a38321 100644 --- a/tools/perf/arch/x86/util/auxtrace.c +++ b/tools/perf/arch/x86/util/auxtrace.c @@ -13,6 +13,7 @@ * */ +#include <errno.h> #include <stdbool.h> #include "../../util/header.h" diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c index 5132775a044f..af2bce7a2cd6 100644 --- a/tools/perf/arch/x86/util/intel-bts.c +++ b/tools/perf/arch/x86/util/intel-bts.c @@ -13,6 +13,7 @@ * */ +#include <errno.h> #include <linux/kernel.h> #include <linux/types.h> #include <linux/bitops.h> diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c index 90fa2286edcf..f630de0206a1 100644 --- a/tools/perf/arch/x86/util/intel-pt.c +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -13,6 +13,7 @@ * */ +#include <errno.h> #include <stdbool.h> #include <linux/kernel.h> #include <linux/types.h> diff --git a/tools/perf/arch/x86/util/kvm-stat.c b/tools/perf/arch/x86/util/kvm-stat.c index b63d4be655a2..bf817beca0a8 100644 --- a/tools/perf/arch/x86/util/kvm-stat.c +++ b/tools/perf/arch/x86/util/kvm-stat.c @@ -1,3 +1,4 @@ +#include <errno.h> #include "../../util/kvm-stat.h" #include <asm/svm.h> #include <asm/vmx.h> diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c index c5db14f36cc7..f95edebfb716 100644 --- a/tools/perf/arch/x86/util/perf_regs.c +++ b/tools/perf/arch/x86/util/perf_regs.c @@ -1,5 +1,11 @@ +#include <errno.h> +#include <string.h> +#include <regex.h> + #include "../../perf.h" +#include "../../util/util.h" #include "../../util/perf_regs.h" +#include "../../util/debug.h" const struct sample_reg sample_reg_masks[] = { SMPL_REG(AX, PERF_REG_X86_AX), @@ -26,3 +32,224 @@ const struct sample_reg sample_reg_masks[] = { #endif SMPL_REG_END }; + +struct sdt_name_reg { + const char *sdt_name; + const char *uprobe_name; +}; +#define SDT_NAME_REG(n, m) {.sdt_name = "%" #n, .uprobe_name = "%" #m} +#define SDT_NAME_REG_END {.sdt_name = NULL, .uprobe_name = NULL} + +static const struct sdt_name_reg sdt_reg_tbl[] = { + SDT_NAME_REG(eax, ax), + SDT_NAME_REG(rax, ax), + SDT_NAME_REG(al, ax), + SDT_NAME_REG(ah, ax), + SDT_NAME_REG(ebx, bx), + SDT_NAME_REG(rbx, bx), + SDT_NAME_REG(bl, bx), + SDT_NAME_REG(bh, bx), + SDT_NAME_REG(ecx, cx), + SDT_NAME_REG(rcx, cx), + SDT_NAME_REG(cl, cx), + SDT_NAME_REG(ch, cx), + SDT_NAME_REG(edx, dx), + SDT_NAME_REG(rdx, dx), + SDT_NAME_REG(dl, dx), + SDT_NAME_REG(dh, dx), + SDT_NAME_REG(esi, si), + SDT_NAME_REG(rsi, si), + SDT_NAME_REG(sil, si), + SDT_NAME_REG(edi, di), + SDT_NAME_REG(rdi, di), + SDT_NAME_REG(dil, di), + SDT_NAME_REG(ebp, bp), + SDT_NAME_REG(rbp, bp), + SDT_NAME_REG(bpl, bp), + SDT_NAME_REG(rsp, sp), + SDT_NAME_REG(esp, sp), + SDT_NAME_REG(spl, sp), + + /* rNN registers */ + SDT_NAME_REG(r8b, r8), + SDT_NAME_REG(r8w, r8), + SDT_NAME_REG(r8d, r8), + SDT_NAME_REG(r9b, r9), + SDT_NAME_REG(r9w, r9), + SDT_NAME_REG(r9d, r9), + SDT_NAME_REG(r10b, r10), + SDT_NAME_REG(r10w, r10), + SDT_NAME_REG(r10d, r10), + SDT_NAME_REG(r11b, r11), + SDT_NAME_REG(r11w, r11), + SDT_NAME_REG(r11d, r11), + SDT_NAME_REG(r12b, r12), + SDT_NAME_REG(r12w, r12), + SDT_NAME_REG(r12d, r12), + SDT_NAME_REG(r13b, r13), + SDT_NAME_REG(r13w, r13), + SDT_NAME_REG(r13d, r13), + SDT_NAME_REG(r14b, r14), + SDT_NAME_REG(r14w, r14), + SDT_NAME_REG(r14d, r14), + SDT_NAME_REG(r15b, r15), + SDT_NAME_REG(r15w, r15), + SDT_NAME_REG(r15d, r15), + SDT_NAME_REG_END, +}; + +/* + * Perf only supports OP which is in +/-NUM(REG) form. + * Here plus-minus sign, NUM and parenthesis are optional, + * only REG is mandatory. + * + * SDT events also supports indirect addressing mode with a + * symbol as offset, scaled mode and constants in OP. But + * perf does not support them yet. Below are few examples. + * + * OP with scaled mode: + * (%rax,%rsi,8) + * 10(%ras,%rsi,8) + * + * OP with indirect addressing mode: + * check_action(%rip) + * mp_+52(%rip) + * 44+mp_(%rip) + * + * OP with constant values: + * $0 + * $123 + * $-1 + */ +#define SDT_OP_REGEX "^([+\\-]?)([0-9]*)(\\(?)(%[a-z][a-z0-9]+)(\\)?)$" + +static regex_t sdt_op_regex; + +static int sdt_init_op_regex(void) +{ + static int initialized; + int ret = 0; + + if (initialized) + return 0; + + ret = regcomp(&sdt_op_regex, SDT_OP_REGEX, REG_EXTENDED); + if (ret < 0) { + pr_debug4("Regex compilation error.\n"); + return ret; + } + + initialized = 1; + return 0; +} + +/* + * Max x86 register name length is 5(ex: %r15d). So, 6th char + * should always contain NULL. This helps to find register name + * length using strlen, insted of maintaing one more variable. + */ +#define SDT_REG_NAME_SIZE 6 + +/* + * The uprobe parser does not support all gas register names; + * so, we have to replace them (ex. for x86_64: %rax -> %ax). + * Note: If register does not require renaming, just copy + * paste as it is, but don't leave it empty. + */ +static void sdt_rename_register(char *sdt_reg, int sdt_len, char *uprobe_reg) +{ + int i = 0; + + for (i = 0; sdt_reg_tbl[i].sdt_name != NULL; i++) { + if (!strncmp(sdt_reg_tbl[i].sdt_name, sdt_reg, sdt_len)) { + strcpy(uprobe_reg, sdt_reg_tbl[i].uprobe_name); + return; + } + } + + strncpy(uprobe_reg, sdt_reg, sdt_len); +} + +int arch_sdt_arg_parse_op(char *old_op, char **new_op) +{ + char new_reg[SDT_REG_NAME_SIZE] = {0}; + int new_len = 0, ret; + /* + * rm[0]: +/-NUM(REG) + * rm[1]: +/- + * rm[2]: NUM + * rm[3]: ( + * rm[4]: REG + * rm[5]: ) + */ + regmatch_t rm[6]; + /* + * Max prefix length is 2 as it may contains sign(+/-) + * and displacement 0 (Both sign and displacement 0 are + * optional so it may be empty). Use one more character + * to hold last NULL so that strlen can be used to find + * prefix length, instead of maintaing one more variable. + */ + char prefix[3] = {0}; + + ret = sdt_init_op_regex(); + if (ret < 0) + return ret; + + /* + * If unsupported OR does not match with regex OR + * register name too long, skip it. + */ + if (strchr(old_op, ',') || strchr(old_op, '$') || + regexec(&sdt_op_regex, old_op, 6, rm, 0) || + rm[4].rm_eo - rm[4].rm_so > SDT_REG_NAME_SIZE) { + pr_debug4("Skipping unsupported SDT argument: %s\n", old_op); + return SDT_ARG_SKIP; + } + + /* + * Prepare prefix. + * If SDT OP has parenthesis but does not provide + * displacement, add 0 for displacement. + * SDT Uprobe Prefix + * ----------------------------- + * +24(%rdi) +24(%di) + + * 24(%rdi) +24(%di) + + * %rdi %di + * (%rdi) +0(%di) +0 + * -80(%rbx) -80(%bx) - + */ + if (rm[3].rm_so != rm[3].rm_eo) { + if (rm[1].rm_so != rm[1].rm_eo) + prefix[0] = *(old_op + rm[1].rm_so); + else if (rm[2].rm_so != rm[2].rm_eo) + prefix[0] = '+'; + else + strncpy(prefix, "+0", 2); + } + + /* Rename register */ + sdt_rename_register(old_op + rm[4].rm_so, rm[4].rm_eo - rm[4].rm_so, + new_reg); + + /* Prepare final OP which should be valid for uprobe_events */ + new_len = strlen(prefix) + + (rm[2].rm_eo - rm[2].rm_so) + + (rm[3].rm_eo - rm[3].rm_so) + + strlen(new_reg) + + (rm[5].rm_eo - rm[5].rm_so) + + 1; /* NULL */ + + *new_op = zalloc(new_len); + if (!*new_op) + return -ENOMEM; + + scnprintf(*new_op, new_len, "%.*s%.*s%.*s%.*s%.*s", + strlen(prefix), prefix, + (int)(rm[2].rm_eo - rm[2].rm_so), old_op + rm[2].rm_so, + (int)(rm[3].rm_eo - rm[3].rm_so), old_op + rm[3].rm_so, + strlen(new_reg), new_reg, + (int)(rm[5].rm_eo - rm[5].rm_so), old_op + rm[5].rm_so); + + return SDT_ARG_VALID; +} diff --git a/tools/perf/arch/x86/util/unwind-libdw.c b/tools/perf/arch/x86/util/unwind-libdw.c index c4b72176ca83..38dc9bb2a7c9 100644 --- a/tools/perf/arch/x86/util/unwind-libdw.c +++ b/tools/perf/arch/x86/util/unwind-libdw.c @@ -1,6 +1,7 @@ #include <elfutils/libdwfl.h> #include "../../util/unwind-libdw.h" #include "../../util/perf_regs.h" +#include "../../util/event.h" bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg) { diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h index 579a592990dd..842ab2781cdc 100644 --- a/tools/perf/bench/bench.h +++ b/tools/perf/bench/bench.h @@ -25,17 +25,17 @@ # endif #endif -int bench_numa(int argc, const char **argv, const char *prefix); -int bench_sched_messaging(int argc, const char **argv, const char *prefix); -int bench_sched_pipe(int argc, const char **argv, const char *prefix); -int bench_mem_memcpy(int argc, const char **argv, const char *prefix); -int bench_mem_memset(int argc, const char **argv, const char *prefix); -int bench_futex_hash(int argc, const char **argv, const char *prefix); -int bench_futex_wake(int argc, const char **argv, const char *prefix); -int bench_futex_wake_parallel(int argc, const char **argv, const char *prefix); -int bench_futex_requeue(int argc, const char **argv, const char *prefix); +int bench_numa(int argc, const char **argv); +int bench_sched_messaging(int argc, const char **argv); +int bench_sched_pipe(int argc, const char **argv); +int bench_mem_memcpy(int argc, const char **argv); +int bench_mem_memset(int argc, const char **argv); +int bench_futex_hash(int argc, const char **argv); +int bench_futex_wake(int argc, const char **argv); +int bench_futex_wake_parallel(int argc, const char **argv); +int bench_futex_requeue(int argc, const char **argv); /* pi futexes */ -int bench_futex_lock_pi(int argc, const char **argv, const char *prefix); +int bench_futex_lock_pi(int argc, const char **argv); #define BENCH_FORMAT_DEFAULT_STR "default" #define BENCH_FORMAT_DEFAULT 0 diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c index bfbb6b5f609c..fe16b310097f 100644 --- a/tools/perf/bench/futex-hash.c +++ b/tools/perf/bench/futex-hash.c @@ -9,6 +9,7 @@ */ /* For the CLR_() macros */ +#include <string.h> #include <pthread.h> #include <errno.h> @@ -113,8 +114,7 @@ static void print_summary(void) (int) runtime.tv_sec); } -int bench_futex_hash(int argc, const char **argv, - const char *prefix __maybe_unused) +int bench_futex_hash(int argc, const char **argv) { int ret = 0; cpu_set_t cpu; @@ -130,8 +130,6 @@ int bench_futex_hash(int argc, const char **argv, } ncpus = sysconf(_SC_NPROCESSORS_ONLN); - nsecs = futexbench_sanitize_numeric(nsecs); - nfutexes = futexbench_sanitize_numeric(nfutexes); sigfillset(&act.sa_mask); act.sa_sigaction = toggle_done; @@ -139,8 +137,6 @@ int bench_futex_hash(int argc, const char **argv, if (!nthreads) /* default to the number of CPUs */ nthreads = ncpus; - else - nthreads = futexbench_sanitize_numeric(nthreads); worker = calloc(nthreads, sizeof(*worker)); if (!worker) diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c index 6d9d6c40a916..73a1c44ea63c 100644 --- a/tools/perf/bench/futex-lock-pi.c +++ b/tools/perf/bench/futex-lock-pi.c @@ -3,6 +3,7 @@ */ /* For the CLR_() macros */ +#include <string.h> #include <pthread.h> #include <signal.h> @@ -139,8 +140,7 @@ static void create_threads(struct worker *w, pthread_attr_t thread_attr) } } -int bench_futex_lock_pi(int argc, const char **argv, - const char *prefix __maybe_unused) +int bench_futex_lock_pi(int argc, const char **argv) { int ret = 0; unsigned int i; @@ -152,7 +152,6 @@ int bench_futex_lock_pi(int argc, const char **argv, goto err; ncpus = sysconf(_SC_NPROCESSORS_ONLN); - nsecs = futexbench_sanitize_numeric(nsecs); sigfillset(&act.sa_mask); act.sa_sigaction = toggle_done; @@ -160,8 +159,6 @@ int bench_futex_lock_pi(int argc, const char **argv, if (!nthreads) nthreads = ncpus; - else - nthreads = futexbench_sanitize_numeric(nthreads); worker = calloc(nthreads, sizeof(*worker)); if (!worker) diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c index fd4ee95b689a..41786cbea24c 100644 --- a/tools/perf/bench/futex-requeue.c +++ b/tools/perf/bench/futex-requeue.c @@ -9,6 +9,7 @@ */ /* For the CLR_() macros */ +#include <string.h> #include <pthread.h> #include <signal.h> @@ -108,8 +109,7 @@ static void toggle_done(int sig __maybe_unused, done = true; } -int bench_futex_requeue(int argc, const char **argv, - const char *prefix __maybe_unused) +int bench_futex_requeue(int argc, const char **argv) { int ret = 0; unsigned int i, j; @@ -128,8 +128,6 @@ int bench_futex_requeue(int argc, const char **argv, if (!nthreads) nthreads = ncpus; - else - nthreads = futexbench_sanitize_numeric(nthreads); worker = calloc(nthreads, sizeof(*worker)); if (!worker) diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c index beaa6c142477..4ab12c8e016a 100644 --- a/tools/perf/bench/futex-wake-parallel.c +++ b/tools/perf/bench/futex-wake-parallel.c @@ -8,6 +8,7 @@ */ /* For the CLR_() macros */ +#include <string.h> #include <pthread.h> #include <signal.h> @@ -196,8 +197,7 @@ static void toggle_done(int sig __maybe_unused, done = true; } -int bench_futex_wake_parallel(int argc, const char **argv, - const char *prefix __maybe_unused) +int bench_futex_wake_parallel(int argc, const char **argv) { int ret = 0; unsigned int i, j; @@ -217,12 +217,8 @@ int bench_futex_wake_parallel(int argc, const char **argv, sigaction(SIGINT, &act, NULL); ncpus = sysconf(_SC_NPROCESSORS_ONLN); - nwaking_threads = futexbench_sanitize_numeric(nwaking_threads); - if (!nblocked_threads) nblocked_threads = ncpus; - else - nblocked_threads = futexbench_sanitize_numeric(nblocked_threads); /* some sanity checks */ if (nwaking_threads > nblocked_threads || !nwaking_threads) diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c index 46efcb98b5a4..2fa49222ef8d 100644 --- a/tools/perf/bench/futex-wake.c +++ b/tools/perf/bench/futex-wake.c @@ -9,6 +9,7 @@ */ /* For the CLR_() macros */ +#include <string.h> #include <pthread.h> #include <signal.h> @@ -114,8 +115,7 @@ static void toggle_done(int sig __maybe_unused, done = true; } -int bench_futex_wake(int argc, const char **argv, - const char *prefix __maybe_unused) +int bench_futex_wake(int argc, const char **argv) { int ret = 0; unsigned int i, j; @@ -129,7 +129,6 @@ int bench_futex_wake(int argc, const char **argv, } ncpus = sysconf(_SC_NPROCESSORS_ONLN); - nwakes = futexbench_sanitize_numeric(nwakes); sigfillset(&act.sa_mask); act.sa_sigaction = toggle_done; @@ -137,8 +136,6 @@ int bench_futex_wake(int argc, const char **argv, if (!nthreads) nthreads = ncpus; - else - nthreads = futexbench_sanitize_numeric(nthreads); worker = calloc(nthreads, sizeof(*worker)); if (!worker) diff --git a/tools/perf/bench/futex.h b/tools/perf/bench/futex.h index ba7c735c0c62..e44fd3239530 100644 --- a/tools/perf/bench/futex.h +++ b/tools/perf/bench/futex.h @@ -7,7 +7,6 @@ #ifndef _FUTEX_H #define _FUTEX_H -#include <stdlib.h> #include <unistd.h> #include <sys/syscall.h> #include <sys/types.h> @@ -89,18 +88,13 @@ futex_cmp_requeue(u_int32_t *uaddr, u_int32_t val, u_int32_t *uaddr2, int nr_wak #ifndef HAVE_PTHREAD_ATTR_SETAFFINITY_NP #include <pthread.h> -static inline int pthread_attr_setaffinity_np(pthread_attr_t *attr, - size_t cpusetsize, - cpu_set_t *cpuset) +#include <linux/compiler.h> +static inline int pthread_attr_setaffinity_np(pthread_attr_t *attr __maybe_unused, + size_t cpusetsize __maybe_unused, + cpu_set_t *cpuset __maybe_unused) { - attr = attr; - cpusetsize = cpusetsize; - cpuset = cpuset; return 0; } #endif -/* User input sanitation */ -#define futexbench_sanitize_numeric(__n) abs((__n)) - #endif /* _FUTEX_H */ diff --git a/tools/perf/bench/mem-functions.c b/tools/perf/bench/mem-functions.c index 52504a83b5a1..fbd732b54047 100644 --- a/tools/perf/bench/mem-functions.c +++ b/tools/perf/bench/mem-functions.c @@ -12,6 +12,7 @@ #include <subcmd/parse-options.h> #include "../util/header.h" #include "../util/cloexec.h" +#include "../util/string2.h" #include "bench.h" #include "mem-memcpy-arch.h" #include "mem-memset-arch.h" @@ -284,7 +285,7 @@ static const char * const bench_mem_memcpy_usage[] = { NULL }; -int bench_mem_memcpy(int argc, const char **argv, const char *prefix __maybe_unused) +int bench_mem_memcpy(int argc, const char **argv) { struct bench_mem_info info = { .functions = memcpy_functions, @@ -358,7 +359,7 @@ static const struct function memset_functions[] = { { .name = NULL, } }; -int bench_mem_memset(int argc, const char **argv, const char *prefix __maybe_unused) +int bench_mem_memset(int argc, const char **argv) { struct bench_mem_info info = { .functions = memset_functions, diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c index 8efe904e486b..27de0c8c5c19 100644 --- a/tools/perf/bench/numa.c +++ b/tools/perf/bench/numa.c @@ -4,6 +4,7 @@ * numa: Simulate NUMA-sensitive workload and measure their NUMA performance */ +#include <inttypes.h> /* For the CLR_() macros */ #include <pthread.h> @@ -30,6 +31,7 @@ #include <sys/wait.h> #include <sys/prctl.h> #include <sys/types.h> +#include <linux/kernel.h> #include <linux/time64.h> #include <numa.h> @@ -43,6 +45,7 @@ /* * Debug printf: */ +#undef dprintf #define dprintf(x...) do { if (g && g->p.show_details >= 1) printf(x); } while (0) struct thread_data { @@ -186,7 +189,8 @@ static const struct option options[] = { OPT_INCR ('d', "show_details" , &p0.show_details, "Show details"), OPT_INCR ('a', "all" , &p0.run_all, "Run all tests in the suite"), OPT_INTEGER('H', "thp" , &p0.thp, "MADV_NOHUGEPAGE < 0 < MADV_HUGEPAGE"), - OPT_BOOLEAN('c', "show_convergence", &p0.show_convergence, "show convergence details"), + OPT_BOOLEAN('c', "show_convergence", &p0.show_convergence, "show convergence details, " + "convergence is reached when each process (all its threads) is running on a single NUMA node."), OPT_BOOLEAN('m', "measure_convergence", &p0.measure_convergence, "measure convergence latency"), OPT_BOOLEAN('q', "quiet" , &p0.show_quiet, "quiet mode"), OPT_BOOLEAN('S', "serialize-startup", &p0.serialize_startup,"serialize thread startup"), @@ -1573,13 +1577,13 @@ static int __bench_numa(const char *name) "GB/sec,", "total-speed", "GB/sec total speed"); if (g->p.show_details >= 2) { - char tname[32]; + char tname[14 + 2 * 10 + 1]; struct thread_data *td; for (p = 0; p < g->p.nr_proc; p++) { for (t = 0; t < g->p.nr_threads; t++) { - memset(tname, 0, 32); + memset(tname, 0, sizeof(tname)); td = g->threads + p*g->p.nr_threads + t; - snprintf(tname, 32, "process%d:thread%d", p, t); + snprintf(tname, sizeof(tname), "process%d:thread%d", p, t); print_res(tname, td->speed_gbs, "GB/sec", "thread-speed", "GB/sec/thread speed"); print_res(tname, td->system_time_ns / NSEC_PER_SEC, @@ -1765,7 +1769,7 @@ static int bench_all(void) return 0; } -int bench_numa(int argc, const char **argv, const char *prefix __maybe_unused) +int bench_numa(int argc, const char **argv) { init_params(&p0, "main,", argc, argv); argc = parse_options(argc, argv, options, bench_numa_usage, 0); diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c index 6a111e775210..4f961e74535b 100644 --- a/tools/perf/bench/sched-messaging.c +++ b/tools/perf/bench/sched-messaging.c @@ -260,8 +260,7 @@ static const char * const bench_sched_message_usage[] = { NULL }; -int bench_sched_messaging(int argc, const char **argv, - const char *prefix __maybe_unused) +int bench_sched_messaging(int argc, const char **argv) { unsigned int i, total_children; struct timeval start, stop, diff; diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c index 2243f0150d76..a152737370c5 100644 --- a/tools/perf/bench/sched-pipe.c +++ b/tools/perf/bench/sched-pipe.c @@ -76,7 +76,7 @@ static void *worker_thread(void *__tdata) return NULL; } -int bench_sched_pipe(int argc, const char **argv, const char *prefix __maybe_unused) +int bench_sched_pipe(int argc, const char **argv) { struct thread_data threads[2], *td; int pipe_1[2], pipe_2[2]; diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index ebb628332a6e..7a5dc7e5c577 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -33,6 +33,7 @@ #include "util/block-range.h" #include <dlfcn.h> +#include <errno.h> #include <linux/bitmap.h> struct perf_annotate { @@ -383,7 +384,7 @@ static const char * const annotate_usage[] = { NULL }; -int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused) +int cmd_annotate(int argc, const char **argv) { struct perf_annotate annotate = { .tool = { @@ -393,6 +394,9 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused) .comm = perf_event__process_comm, .exit = perf_event__process_exit, .fork = perf_event__process_fork, + .namespaces = perf_event__process_namespaces, + .attr = perf_event__process_attr, + .build_id = perf_event__process_build_id, .ordered_events = true, .ordering_requires_timestamps = true, }, @@ -410,6 +414,7 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused) OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"), OPT_INCR('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"), + OPT_BOOLEAN('q', "quiet", &quiet, "do now show any message"), OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, "dump raw trace in ASCII"), OPT_BOOLEAN(0, "gtk", &annotate.use_gtk, "Use the GTK interface"), @@ -463,6 +468,9 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused) annotate.sym_hist_filter = argv[0]; } + if (quiet) + perf_quiet_option(); + file.path = input_name; annotate.session = perf_session__new(&file, false, &annotate.tool); diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c index a1cddc6bbf0f..445e62881254 100644 --- a/tools/perf/builtin-bench.c +++ b/tools/perf/builtin-bench.c @@ -25,7 +25,7 @@ #include <string.h> #include <sys/prctl.h> -typedef int (*bench_fn_t)(int argc, const char **argv, const char *prefix); +typedef int (*bench_fn_t)(int argc, const char **argv); struct bench { const char *name; @@ -155,7 +155,7 @@ static int bench_str2int(const char *str) * to something meaningful: */ static int run_bench(const char *coll_name, const char *bench_name, bench_fn_t fn, - int argc, const char **argv, const char *prefix) + int argc, const char **argv) { int size; char *name; @@ -171,7 +171,7 @@ static int run_bench(const char *coll_name, const char *bench_name, bench_fn_t f prctl(PR_SET_NAME, name); argv[0] = name; - ret = fn(argc, argv, prefix); + ret = fn(argc, argv); free(name); @@ -198,7 +198,7 @@ static void run_collection(struct collection *coll) fflush(stdout); argv[1] = bench->name; - run_bench(coll->name, bench->name, bench->fn, 1, argv, NULL); + run_bench(coll->name, bench->name, bench->fn, 1, argv); printf("\n"); } } @@ -211,7 +211,7 @@ static void run_all_collections(void) run_collection(coll); } -int cmd_bench(int argc, const char **argv, const char *prefix __maybe_unused) +int cmd_bench(int argc, const char **argv) { struct collection *coll; int ret = 0; @@ -270,7 +270,7 @@ int cmd_bench(int argc, const char **argv, const char *prefix __maybe_unused) if (bench_format == BENCH_FORMAT_DEFAULT) printf("# Running '%s/%s' benchmark:\n", coll->name, bench->name); fflush(stdout); - ret = run_bench(coll->name, bench->name, bench->fn, argc-1, argv+1, prefix); + ret = run_bench(coll->name, bench->name, bench->fn, argc-1, argv+1); goto end; } diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c index 30e2b2cb2421..9eba7f1add1f 100644 --- a/tools/perf/builtin-buildid-cache.c +++ b/tools/perf/builtin-buildid-cache.c @@ -10,6 +10,7 @@ #include <sys/time.h> #include <time.h> #include <dirent.h> +#include <errno.h> #include <unistd.h> #include "builtin.h" #include "perf.h" @@ -21,6 +22,7 @@ #include "util/build-id.h" #include "util/session.h" #include "util/symbol.h" +#include "util/time-utils.h" static int build_id_cache__kcore_buildid(const char *proc_dir, char *sbuildid) { @@ -47,19 +49,22 @@ static bool same_kallsyms_reloc(const char *from_dir, char *to_dir) char to[PATH_MAX]; const char *name; u64 addr1 = 0, addr2 = 0; - int i; + int i, err = -1; scnprintf(from, sizeof(from), "%s/kallsyms", from_dir); scnprintf(to, sizeof(to), "%s/kallsyms", to_dir); for (i = 0; (name = ref_reloc_sym_names[i]) != NULL; i++) { - addr1 = kallsyms__get_function_start(from, name); - if (addr1) + err = kallsyms__get_function_start(from, name, &addr1); + if (!err) break; } - if (name) - addr2 = kallsyms__get_function_start(to, name); + if (err) + return false; + + if (kallsyms__get_function_start(to, name, &addr2)) + return false; return addr1 == addr2; } @@ -276,8 +281,7 @@ static int build_id_cache__update_file(const char *filename) return err; } -int cmd_buildid_cache(int argc, const char **argv, - const char *prefix __maybe_unused) +int cmd_buildid_cache(int argc, const char **argv) { struct strlist *list; struct str_node *pos; diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c index 5e914ee79eb3..fdaca16e0c74 100644 --- a/tools/perf/builtin-buildid-list.c +++ b/tools/perf/builtin-buildid-list.c @@ -16,6 +16,7 @@ #include "util/session.h" #include "util/symbol.h" #include "util/data.h" +#include <errno.h> static int sysfs__fprintf_build_id(FILE *fp) { @@ -87,8 +88,7 @@ out: return 0; } -int cmd_buildid_list(int argc, const char **argv, - const char *prefix __maybe_unused) +int cmd_buildid_list(int argc, const char **argv) { bool show_kernel = false; bool with_hits = false; diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index f8ca7a4ebabc..620a467ee304 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -9,10 +9,13 @@ * Dick Fowles <fowles@inreach.com> * Joe Mario <jmario@redhat.com> */ +#include <errno.h> +#include <inttypes.h> #include <linux/compiler.h> #include <linux/kernel.h> #include <linux/stringify.h> #include <asm/bug.h> +#include <sys/param.h> #include "util.h" #include "debug.h" #include "builtin.h" @@ -24,11 +27,13 @@ #include "tool.h" #include "data.h" #include "sort.h" +#include "event.h" #include "evlist.h" #include "evsel.h" #include <asm/bug.h> #include "ui/browsers/hists.h" #include "evlist.h" +#include "thread.h" struct c2c_hists { struct hists hists; @@ -58,7 +63,7 @@ struct c2c_hist_entry { struct hist_entry he; }; -static char const *coalesce_default = "pid,tid,iaddr"; +static char const *coalesce_default = "pid,iaddr"; struct perf_c2c { struct perf_tool tool; @@ -2334,7 +2339,7 @@ out: static void perf_c2c_display(struct perf_session *session) { - if (c2c.use_stdio) + if (use_browser == 0) perf_c2c__hists_fprintf(stdout, session); else perf_c2c__hists_browse(&c2c.hists.hists); @@ -2476,6 +2481,7 @@ static int build_cl_output(char *cl_sort, bool no_source) "mean_rmt," "mean_lcl," "mean_load," + "tot_recs," "cpucnt,", add_sym ? "symbol," : "", add_dso ? "dso," : "", @@ -2535,7 +2541,7 @@ static int perf_c2c__report(int argc, const char **argv) OPT_BOOLEAN(0, "stdio", &c2c.use_stdio, "Use the stdio interface"), #endif OPT_BOOLEAN(0, "stats", &c2c.stats_only, - "Use the stdio interface"), + "Display only statistic tables (implies --stdio)"), OPT_BOOLEAN(0, "full-symbols", &c2c.symbol_full, "Display full length of symbols"), OPT_BOOLEAN(0, "no-source", &no_source, @@ -2754,12 +2760,12 @@ static int perf_c2c__record(int argc, const char **argv) pr_debug("\n"); } - ret = cmd_record(i, rec_argv, NULL); + ret = cmd_record(i, rec_argv); free(rec_argv); return ret; } -int cmd_c2c(int argc, const char **argv, const char *prefix __maybe_unused) +int cmd_c2c(int argc, const char **argv) { argc = parse_options(argc, argv, c2c_options, c2c_usage, PARSE_OPT_STOP_AT_NON_OPTION); diff --git a/tools/perf/builtin-config.c b/tools/perf/builtin-config.c index 8c0d93b7c2f0..80668fa7556e 100644 --- a/tools/perf/builtin-config.c +++ b/tools/perf/builtin-config.c @@ -154,11 +154,12 @@ static int parse_config_arg(char *arg, char **var, char **value) return 0; } -int cmd_config(int argc, const char **argv, const char *prefix __maybe_unused) +int cmd_config(int argc, const char **argv) { int i, ret = 0; struct perf_config_set *set; char *user_config = mkpath("%s/.perfconfig", getenv("HOME")); + const char *config_filename; argc = parse_options(argc, argv, config_options, config_usage, PARSE_OPT_STOP_AT_NON_OPTION); @@ -175,6 +176,11 @@ int cmd_config(int argc, const char **argv, const char *prefix __maybe_unused) else if (use_user_config) config_exclusive_filename = user_config; + if (!config_exclusive_filename) + config_filename = user_config; + else + config_filename = config_exclusive_filename; + /* * At only 'config' sub-command, individually use the config set * because of reinitializing with options config file location. @@ -192,13 +198,9 @@ int cmd_config(int argc, const char **argv, const char *prefix __maybe_unused) parse_options_usage(config_usage, config_options, "l", 1); } else { ret = show_config(set); - if (ret < 0) { - const char * config_filename = config_exclusive_filename; - if (!config_exclusive_filename) - config_filename = user_config; + if (ret < 0) pr_err("Nothing configured, " "please check your %s \n", config_filename); - } } break; default: @@ -221,13 +223,8 @@ int cmd_config(int argc, const char **argv, const char *prefix __maybe_unused) if (value == NULL) ret = show_spec_config(set, var); - else { - const char *config_filename = config_exclusive_filename; - - if (!config_exclusive_filename) - config_filename = user_config; + else ret = set_config(set, config_filename, var, value); - } free(arg); } } else diff --git a/tools/perf/builtin-data.c b/tools/perf/builtin-data.c index 7ad6e17ac6b3..0adb5f82335a 100644 --- a/tools/perf/builtin-data.c +++ b/tools/perf/builtin-data.c @@ -6,7 +6,7 @@ #include "data-convert.h" #include "data-convert-bt.h" -typedef int (*data_cmd_fn_t)(int argc, const char **argv, const char *prefix); +typedef int (*data_cmd_fn_t)(int argc, const char **argv); struct data_cmd { const char *name; @@ -50,8 +50,7 @@ static const char * const data_convert_usage[] = { NULL }; -static int cmd_data_convert(int argc, const char **argv, - const char *prefix __maybe_unused) +static int cmd_data_convert(int argc, const char **argv) { const char *to_ctf = NULL; struct perf_data_convert_opts opts = { @@ -98,7 +97,7 @@ static struct data_cmd data_cmds[] = { { .name = NULL, }, }; -int cmd_data(int argc, const char **argv, const char *prefix) +int cmd_data(int argc, const char **argv) { struct data_cmd *cmd; const char *cmdstr; @@ -118,7 +117,7 @@ int cmd_data(int argc, const char **argv, const char *prefix) if (strcmp(cmd->name, cmdstr)) continue; - return cmd->fn(argc, argv, prefix); + return cmd->fn(argc, argv); } pr_err("Unknown command: %s\n", cmdstr); diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 933aeec46f4a..eec5df80f5a3 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -17,7 +17,10 @@ #include "util/symbol.h" #include "util/util.h" #include "util/data.h" +#include "util/config.h" +#include <errno.h> +#include <inttypes.h> #include <stdlib.h> #include <math.h> @@ -30,6 +33,7 @@ enum { PERF_HPP_DIFF__RATIO, PERF_HPP_DIFF__WEIGHTED_DIFF, PERF_HPP_DIFF__FORMULA, + PERF_HPP_DIFF__DELTA_ABS, PERF_HPP_DIFF__MAX_INDEX }; @@ -64,7 +68,7 @@ static bool force; static bool show_period; static bool show_formula; static bool show_baseline_only; -static unsigned int sort_compute; +static unsigned int sort_compute = 1; static s64 compute_wdiff_w1; static s64 compute_wdiff_w2; @@ -73,19 +77,22 @@ enum { COMPUTE_DELTA, COMPUTE_RATIO, COMPUTE_WEIGHTED_DIFF, + COMPUTE_DELTA_ABS, COMPUTE_MAX, }; const char *compute_names[COMPUTE_MAX] = { [COMPUTE_DELTA] = "delta", + [COMPUTE_DELTA_ABS] = "delta-abs", [COMPUTE_RATIO] = "ratio", [COMPUTE_WEIGHTED_DIFF] = "wdiff", }; -static int compute; +static int compute = COMPUTE_DELTA_ABS; static int compute_2_hpp[COMPUTE_MAX] = { [COMPUTE_DELTA] = PERF_HPP_DIFF__DELTA, + [COMPUTE_DELTA_ABS] = PERF_HPP_DIFF__DELTA_ABS, [COMPUTE_RATIO] = PERF_HPP_DIFF__RATIO, [COMPUTE_WEIGHTED_DIFF] = PERF_HPP_DIFF__WEIGHTED_DIFF, }; @@ -111,6 +118,10 @@ static struct header_column { .name = "Delta", .width = 7, }, + [PERF_HPP_DIFF__DELTA_ABS] = { + .name = "Delta Abs", + .width = 7, + }, [PERF_HPP_DIFF__RATIO] = { .name = "Ratio", .width = 14, @@ -298,6 +309,7 @@ static int formula_fprintf(struct hist_entry *he, struct hist_entry *pair, { switch (compute) { case COMPUTE_DELTA: + case COMPUTE_DELTA_ABS: return formula_delta(he, pair, buf, size); case COMPUTE_RATIO: return formula_ratio(he, pair, buf, size); @@ -354,6 +366,7 @@ static struct perf_tool tool = { .exit = perf_event__process_exit, .fork = perf_event__process_fork, .lost = perf_event__process_lost, + .namespaces = perf_event__process_namespaces, .ordered_events = true, .ordering_requires_timestamps = true, }; @@ -461,6 +474,7 @@ static void hists__precompute(struct hists *hists) switch (compute) { case COMPUTE_DELTA: + case COMPUTE_DELTA_ABS: compute_delta(he, pair); break; case COMPUTE_RATIO: @@ -498,6 +512,13 @@ __hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right, return cmp_doubles(l, r); } + case COMPUTE_DELTA_ABS: + { + double l = fabs(left->diff.period_ratio_delta); + double r = fabs(right->diff.period_ratio_delta); + + return cmp_doubles(l, r); + } case COMPUTE_RATIO: { double l = left->diff.period_ratio; @@ -564,7 +585,7 @@ hist_entry__cmp_compute_idx(struct hist_entry *left, struct hist_entry *right, if (!p_left || !p_right) return p_left ? -1 : 1; - if (c != COMPUTE_DELTA) { + if (c != COMPUTE_DELTA && c != COMPUTE_DELTA_ABS) { /* * The delta can be computed without the baseline, but * others are not. Put those entries which have no @@ -607,6 +628,15 @@ hist_entry__cmp_delta(struct perf_hpp_fmt *fmt, } static int64_t +hist_entry__cmp_delta_abs(struct perf_hpp_fmt *fmt, + struct hist_entry *left, struct hist_entry *right) +{ + struct data__file *d = fmt_to_data_file(fmt); + + return hist_entry__cmp_compute(right, left, COMPUTE_DELTA_ABS, d->idx); +} + +static int64_t hist_entry__cmp_ratio(struct perf_hpp_fmt *fmt, struct hist_entry *left, struct hist_entry *right) { @@ -633,6 +663,14 @@ hist_entry__cmp_delta_idx(struct perf_hpp_fmt *fmt __maybe_unused, } static int64_t +hist_entry__cmp_delta_abs_idx(struct perf_hpp_fmt *fmt __maybe_unused, + struct hist_entry *left, struct hist_entry *right) +{ + return hist_entry__cmp_compute_idx(right, left, COMPUTE_DELTA_ABS, + sort_compute); +} + +static int64_t hist_entry__cmp_ratio_idx(struct perf_hpp_fmt *fmt __maybe_unused, struct hist_entry *left, struct hist_entry *right) { @@ -656,7 +694,7 @@ static void hists__process(struct hists *hists) hists__precompute(hists); hists__output_resort(hists, NULL); - hists__fprintf(hists, true, 0, 0, 0, stdout, + hists__fprintf(hists, !quiet, 0, 0, 0, stdout, symbol_conf.use_callchain); } @@ -704,12 +742,14 @@ static void data_process(void) hists__link(hists_base, hists); } - fprintf(stdout, "%s# Event '%s'\n#\n", first ? "" : "\n", - perf_evsel__name(evsel_base)); + if (!quiet) { + fprintf(stdout, "%s# Event '%s'\n#\n", first ? "" : "\n", + perf_evsel__name(evsel_base)); + } first = false; - if (verbose || data__files_cnt > 2) + if (verbose > 0 || ((data__files_cnt > 2) && !quiet)) data__fprintf(); /* Don't sort callchain for perf diff */ @@ -772,10 +812,11 @@ static const char * const diff_usage[] = { static const struct option options[] = { OPT_INCR('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"), + OPT_BOOLEAN('q', "quiet", &quiet, "Do not show any message"), OPT_BOOLEAN('b', "baseline-only", &show_baseline_only, "Show only items with match in baseline"), OPT_CALLBACK('c', "compute", &compute, - "delta,ratio,wdiff:w1,w2 (default delta)", + "delta,delta-abs,ratio,wdiff:w1,w2 (default delta-abs)", "Entries differential computation selection", setup_compute), OPT_BOOLEAN('p', "period", &show_period, @@ -945,6 +986,7 @@ hpp__entry_pair(struct hist_entry *he, struct hist_entry *pair, switch (idx) { case PERF_HPP_DIFF__DELTA: + case PERF_HPP_DIFF__DELTA_ABS: if (pair->diff.computed) diff = pair->diff.period_ratio_delta; else @@ -1118,6 +1160,10 @@ static void data__hpp_register(struct data__file *d, int idx) fmt->color = hpp__color_wdiff; fmt->sort = hist_entry__cmp_wdiff; break; + case PERF_HPP_DIFF__DELTA_ABS: + fmt->color = hpp__color_delta; + fmt->sort = hist_entry__cmp_delta_abs; + break; default: fmt->sort = hist_entry__cmp_nop; break; @@ -1195,6 +1241,9 @@ static int ui_init(void) case COMPUTE_WEIGHTED_DIFF: fmt->sort = hist_entry__cmp_wdiff_idx; break; + case COMPUTE_DELTA_ABS: + fmt->sort = hist_entry__cmp_delta_abs_idx; + break; default: BUG_ON(1); } @@ -1249,15 +1298,45 @@ static int data_init(int argc, const char **argv) return 0; } -int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused) +static int diff__config(const char *var, const char *value, + void *cb __maybe_unused) +{ + if (!strcmp(var, "diff.order")) { + sort_compute = perf_config_int(var, value); + return 0; + } + if (!strcmp(var, "diff.compute")) { + if (!strcmp(value, "delta")) { + compute = COMPUTE_DELTA; + } else if (!strcmp(value, "delta-abs")) { + compute = COMPUTE_DELTA_ABS; + } else if (!strcmp(value, "ratio")) { + compute = COMPUTE_RATIO; + } else if (!strcmp(value, "wdiff")) { + compute = COMPUTE_WEIGHTED_DIFF; + } else { + pr_err("Invalid compute method: %s\n", value); + return -1; + } + } + + return 0; +} + +int cmd_diff(int argc, const char **argv) { int ret = hists__init(); if (ret < 0) return ret; + perf_config(diff__config, NULL); + argc = parse_options(argc, argv, options, diff_usage, 0); + if (quiet) + perf_quiet_option(); + if (symbol__init(NULL) < 0) return -1; diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c index e09c4287fe87..6d210e40d611 100644 --- a/tools/perf/builtin-evlist.c +++ b/tools/perf/builtin-evlist.c @@ -46,7 +46,7 @@ static int __cmd_evlist(const char *file_name, struct perf_attr_details *details return 0; } -int cmd_evlist(int argc, const char **argv, const char *prefix __maybe_unused) +int cmd_evlist(int argc, const char **argv) { struct perf_attr_details details = { .verbose = false, }; const struct option options[] = { diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c new file mode 100644 index 000000000000..9e0b35cd0eea --- /dev/null +++ b/tools/perf/builtin-ftrace.c @@ -0,0 +1,368 @@ +/* + * builtin-ftrace.c + * + * Copyright (c) 2013 LG Electronics, Namhyung Kim <namhyung@kernel.org> + * + * Released under the GPL v2. + */ + +#include "builtin.h" +#include "perf.h" + +#include <errno.h> +#include <unistd.h> +#include <signal.h> +#include <fcntl.h> +#include <poll.h> + +#include "debug.h" +#include <subcmd/parse-options.h> +#include <api/fs/tracing_path.h> +#include "evlist.h" +#include "target.h" +#include "cpumap.h" +#include "thread_map.h" +#include "util/config.h" + + +#define DEFAULT_TRACER "function_graph" + +struct perf_ftrace { + struct perf_evlist *evlist; + struct target target; + const char *tracer; +}; + +static bool done; + +static void sig_handler(int sig __maybe_unused) +{ + done = true; +} + +/* + * perf_evlist__prepare_workload will send a SIGUSR1 if the fork fails, since + * we asked by setting its exec_error to the function below, + * ftrace__workload_exec_failed_signal. + * + * XXX We need to handle this more appropriately, emitting an error, etc. + */ +static void ftrace__workload_exec_failed_signal(int signo __maybe_unused, + siginfo_t *info __maybe_unused, + void *ucontext __maybe_unused) +{ + /* workload_exec_errno = info->si_value.sival_int; */ + done = true; +} + +static int __write_tracing_file(const char *name, const char *val, bool append) +{ + char *file; + int fd, ret = -1; + ssize_t size = strlen(val); + int flags = O_WRONLY; + + file = get_tracing_file(name); + if (!file) { + pr_debug("cannot get tracing file: %s\n", name); + return -1; + } + + if (append) + flags |= O_APPEND; + else + flags |= O_TRUNC; + + fd = open(file, flags); + if (fd < 0) { + pr_debug("cannot open tracing file: %s\n", name); + goto out; + } + + if (write(fd, val, size) == size) + ret = 0; + else + pr_debug("write '%s' to tracing/%s failed\n", val, name); + + close(fd); +out: + put_tracing_file(file); + return ret; +} + +static int write_tracing_file(const char *name, const char *val) +{ + return __write_tracing_file(name, val, false); +} + +static int append_tracing_file(const char *name, const char *val) +{ + return __write_tracing_file(name, val, true); +} + +static int reset_tracing_cpu(void); + +static int reset_tracing_files(struct perf_ftrace *ftrace __maybe_unused) +{ + if (write_tracing_file("tracing_on", "0") < 0) + return -1; + + if (write_tracing_file("current_tracer", "nop") < 0) + return -1; + + if (write_tracing_file("set_ftrace_pid", " ") < 0) + return -1; + + if (reset_tracing_cpu() < 0) + return -1; + + return 0; +} + +static int set_tracing_pid(struct perf_ftrace *ftrace) +{ + int i; + char buf[16]; + + if (target__has_cpu(&ftrace->target)) + return 0; + + for (i = 0; i < thread_map__nr(ftrace->evlist->threads); i++) { + scnprintf(buf, sizeof(buf), "%d", + ftrace->evlist->threads->map[i]); + if (append_tracing_file("set_ftrace_pid", buf) < 0) + return -1; + } + return 0; +} + +static int set_tracing_cpumask(struct cpu_map *cpumap) +{ + char *cpumask; + size_t mask_size; + int ret; + int last_cpu; + + last_cpu = cpu_map__cpu(cpumap, cpumap->nr - 1); + mask_size = (last_cpu + 3) / 4 + 1; + mask_size += last_cpu / 32; /* ',' is needed for every 32th cpus */ + + cpumask = malloc(mask_size); + if (cpumask == NULL) { + pr_debug("failed to allocate cpu mask\n"); + return -1; + } + + cpu_map__snprint_mask(cpumap, cpumask, mask_size); + + ret = write_tracing_file("tracing_cpumask", cpumask); + + free(cpumask); + return ret; +} + +static int set_tracing_cpu(struct perf_ftrace *ftrace) +{ + struct cpu_map *cpumap = ftrace->evlist->cpus; + + if (!target__has_cpu(&ftrace->target)) + return 0; + + return set_tracing_cpumask(cpumap); +} + +static int reset_tracing_cpu(void) +{ + struct cpu_map *cpumap = cpu_map__new(NULL); + int ret; + + ret = set_tracing_cpumask(cpumap); + cpu_map__put(cpumap); + return ret; +} + +static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv) +{ + char *trace_file; + int trace_fd; + char buf[4096]; + struct pollfd pollfd = { + .events = POLLIN, + }; + + if (geteuid() != 0) { + pr_err("ftrace only works for root!\n"); + return -1; + } + + signal(SIGINT, sig_handler); + signal(SIGUSR1, sig_handler); + signal(SIGCHLD, sig_handler); + signal(SIGPIPE, sig_handler); + + if (reset_tracing_files(ftrace) < 0) + goto out; + + /* reset ftrace buffer */ + if (write_tracing_file("trace", "0") < 0) + goto out; + + if (argc && perf_evlist__prepare_workload(ftrace->evlist, + &ftrace->target, argv, false, + ftrace__workload_exec_failed_signal) < 0) { + goto out; + } + + if (set_tracing_pid(ftrace) < 0) { + pr_err("failed to set ftrace pid\n"); + goto out_reset; + } + + if (set_tracing_cpu(ftrace) < 0) { + pr_err("failed to set tracing cpumask\n"); + goto out_reset; + } + + if (write_tracing_file("current_tracer", ftrace->tracer) < 0) { + pr_err("failed to set current_tracer to %s\n", ftrace->tracer); + goto out_reset; + } + + trace_file = get_tracing_file("trace_pipe"); + if (!trace_file) { + pr_err("failed to open trace_pipe\n"); + goto out_reset; + } + + trace_fd = open(trace_file, O_RDONLY); + + put_tracing_file(trace_file); + + if (trace_fd < 0) { + pr_err("failed to open trace_pipe\n"); + goto out_reset; + } + + fcntl(trace_fd, F_SETFL, O_NONBLOCK); + pollfd.fd = trace_fd; + + if (write_tracing_file("tracing_on", "1") < 0) { + pr_err("can't enable tracing\n"); + goto out_close_fd; + } + + setup_pager(); + + perf_evlist__start_workload(ftrace->evlist); + + while (!done) { + if (poll(&pollfd, 1, -1) < 0) + break; + + if (pollfd.revents & POLLIN) { + int n = read(trace_fd, buf, sizeof(buf)); + if (n < 0) + break; + if (fwrite(buf, n, 1, stdout) != 1) + break; + } + } + + write_tracing_file("tracing_on", "0"); + + /* read remaining buffer contents */ + while (true) { + int n = read(trace_fd, buf, sizeof(buf)); + if (n <= 0) + break; + if (fwrite(buf, n, 1, stdout) != 1) + break; + } + +out_close_fd: + close(trace_fd); +out_reset: + reset_tracing_files(ftrace); +out: + return done ? 0 : -1; +} + +static int perf_ftrace_config(const char *var, const char *value, void *cb) +{ + struct perf_ftrace *ftrace = cb; + + if (prefixcmp(var, "ftrace.")) + return 0; + + if (strcmp(var, "ftrace.tracer")) + return -1; + + if (!strcmp(value, "function_graph") || + !strcmp(value, "function")) { + ftrace->tracer = value; + return 0; + } + + pr_err("Please select \"function_graph\" (default) or \"function\"\n"); + return -1; +} + +int cmd_ftrace(int argc, const char **argv) +{ + int ret; + struct perf_ftrace ftrace = { + .tracer = DEFAULT_TRACER, + .target = { .uid = UINT_MAX, }, + }; + const char * const ftrace_usage[] = { + "perf ftrace [<options>] [<command>]", + "perf ftrace [<options>] -- <command> [<options>]", + NULL + }; + const struct option ftrace_options[] = { + OPT_STRING('t', "tracer", &ftrace.tracer, "tracer", + "tracer to use: function_graph(default) or function"), + OPT_STRING('p', "pid", &ftrace.target.pid, "pid", + "trace on existing process id"), + OPT_INCR('v', "verbose", &verbose, + "be more verbose"), + OPT_BOOLEAN('a', "all-cpus", &ftrace.target.system_wide, + "system-wide collection from all CPUs"), + OPT_STRING('C', "cpu", &ftrace.target.cpu_list, "cpu", + "list of cpus to monitor"), + OPT_END() + }; + + ret = perf_config(perf_ftrace_config, &ftrace); + if (ret < 0) + return -1; + + argc = parse_options(argc, argv, ftrace_options, ftrace_usage, + PARSE_OPT_STOP_AT_NON_OPTION); + if (!argc && target__none(&ftrace.target)) + usage_with_options(ftrace_usage, ftrace_options); + + ret = target__validate(&ftrace.target); + if (ret) { + char errbuf[512]; + + target__strerror(&ftrace.target, ret, errbuf, 512); + pr_err("%s\n", errbuf); + return -EINVAL; + } + + ftrace.evlist = perf_evlist__new(); + if (ftrace.evlist == NULL) + return -ENOMEM; + + ret = perf_evlist__create_maps(ftrace.evlist, &ftrace.target); + if (ret < 0) + goto out_delete_evlist; + + ret = __cmd_ftrace(&ftrace, argc, argv); + +out_delete_evlist: + perf_evlist__delete(ftrace.evlist); + + return ret; +} diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c index 3bdb2c78a21b..492f8e14ab09 100644 --- a/tools/perf/builtin-help.c +++ b/tools/perf/builtin-help.c @@ -12,16 +12,22 @@ #include <subcmd/run-command.h> #include <subcmd/help.h> #include "util/debug.h" +#include <linux/kernel.h> +#include <errno.h> +#include <stdio.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> static struct man_viewer_list { struct man_viewer_list *next; - char name[FLEX_ARRAY]; + char name[0]; } *man_viewer_list; static struct man_viewer_info_list { struct man_viewer_info_list *next; const char *info; - char name[FLEX_ARRAY]; + char name[0]; } *man_viewer_info_list; enum help_format { @@ -301,12 +307,6 @@ void list_common_cmds_help(void) } } -static int is_perf_command(const char *s) -{ - return is_in_cmdlist(&main_cmds, s) || - is_in_cmdlist(&other_cmds, s); -} - static const char *cmd_to_page(const char *perf_cmd) { char *s; @@ -418,7 +418,7 @@ static int show_html_page(const char *perf_cmd) return 0; } -int cmd_help(int argc, const char **argv, const char *prefix __maybe_unused) +int cmd_help(int argc, const char **argv) { bool show_all = false; enum help_format help_format = HELP_FORMAT_MAN; @@ -434,7 +434,7 @@ int cmd_help(int argc, const char **argv, const char *prefix __maybe_unused) const char * const builtin_help_subcommands[] = { "buildid-cache", "buildid-list", "diff", "evlist", "help", "list", "record", "report", "bench", "stat", "timechart", "top", "annotate", - "script", "sched", "kmem", "lock", "kvm", "test", "inject", "mem", "data", + "script", "sched", "kallsyms", "kmem", "lock", "kvm", "test", "inject", "mem", "data", #ifdef HAVE_LIBELF_SUPPORT "probe", #endif @@ -446,12 +446,13 @@ int cmd_help(int argc, const char **argv, const char *prefix __maybe_unused) "perf help [--all] [--man|--web|--info] [command]", NULL }; - const char *alias; - int rc = 0; + int rc; load_command_list("perf-", &main_cmds, &other_cmds); - perf_config(perf_help_config, &help_format); + rc = perf_config(perf_help_config, &help_format); + if (rc) + return rc; argc = parse_options_subcommand(argc, argv, builtin_help_options, builtin_help_subcommands, builtin_help_usage, 0); @@ -470,12 +471,6 @@ int cmd_help(int argc, const char **argv, const char *prefix __maybe_unused) return 0; } - alias = alias_lookup(argv[0]); - if (alias && !is_perf_command(argv[0])) { - printf("`perf %s' is aliased to `%s'\n", argv[0], alias); - return 0; - } - switch (help_format) { case HELP_FORMAT_MAN: rc = show_man_page(argv[0]); diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index b9bc7e39833a..ea8db38eedd1 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -18,10 +18,13 @@ #include "util/data.h" #include "util/auxtrace.h" #include "util/jit.h" +#include "util/thread.h" #include <subcmd/parse-options.h> #include <linux/list.h> +#include <errno.h> +#include <signal.h> struct perf_inject { struct perf_tool tool; @@ -333,6 +336,18 @@ static int perf_event__repipe_comm(struct perf_tool *tool, return err; } +static int perf_event__repipe_namespaces(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + int err = perf_event__process_namespaces(tool, event, sample, machine); + + perf_event__repipe(tool, event, sample, machine); + + return err; +} + static int perf_event__repipe_exit(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -660,6 +675,7 @@ static int __cmd_inject(struct perf_inject *inject) session->itrace_synth_opts = &inject->itrace_synth_opts; inject->itrace_synth_opts.inject = true; inject->tool.comm = perf_event__repipe_comm; + inject->tool.namespaces = perf_event__repipe_namespaces; inject->tool.exit = perf_event__repipe_exit; inject->tool.id_index = perf_event__repipe_id_index; inject->tool.auxtrace_info = perf_event__process_auxtrace_info; @@ -681,6 +697,8 @@ static int __cmd_inject(struct perf_inject *inject) lseek(fd, output_data_offset, SEEK_SET); ret = perf_session__process_events(session); + if (ret) + return ret; if (!file_out->is_pipe) { if (inject->build_ids) @@ -725,7 +743,7 @@ static int __cmd_inject(struct perf_inject *inject) return ret; } -int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused) +int cmd_inject(int argc, const char **argv) { struct perf_inject inject = { .tool = { diff --git a/tools/perf/builtin-kallsyms.c b/tools/perf/builtin-kallsyms.c new file mode 100644 index 000000000000..bcfb363112d3 --- /dev/null +++ b/tools/perf/builtin-kallsyms.c @@ -0,0 +1,68 @@ +/* + * builtin-kallsyms.c + * + * Builtin command: Look for a symbol in the running kernel and its modules + * + * Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com> + * + * Released under the GPL v2. (and only v2, not any later version) + */ +#include <inttypes.h> +#include "builtin.h" +#include <linux/compiler.h> +#include <subcmd/parse-options.h> +#include "debug.h" +#include "machine.h" +#include "symbol.h" + +static int __cmd_kallsyms(int argc, const char **argv) +{ + int i; + struct machine *machine = machine__new_kallsyms(); + + if (machine == NULL) { + pr_err("Couldn't read /proc/kallsyms\n"); + return -1; + } + + for (i = 0; i < argc; ++i) { + struct map *map; + struct symbol *symbol = machine__find_kernel_function_by_name(machine, argv[i], &map); + + if (symbol == NULL) { + printf("%s: not found\n", argv[i]); + continue; + } + + printf("%s: %s %s %#" PRIx64 "-%#" PRIx64 " (%#" PRIx64 "-%#" PRIx64")\n", + symbol->name, map->dso->short_name, map->dso->long_name, + map->unmap_ip(map, symbol->start), map->unmap_ip(map, symbol->end), + symbol->start, symbol->end); + } + + machine__delete(machine); + return 0; +} + +int cmd_kallsyms(int argc, const char **argv) +{ + const struct option options[] = { + OPT_INCR('v', "verbose", &verbose, "be more verbose (show counter open errors, etc)"), + OPT_END() + }; + const char * const kallsyms_usage[] = { + "perf kallsyms [<options>] symbol_name", + NULL + }; + + argc = parse_options(argc, argv, options, kallsyms_usage, 0); + if (argc < 1) + usage_with_options(kallsyms_usage, options); + + symbol_conf.sort_by_name = true; + symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL); + if (symbol__init(NULL) < 0) + return -1; + + return __cmd_kallsyms(argc, argv); +} diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index 915869e00d86..9409c9464667 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -20,11 +20,16 @@ #include "util/debug.h" +#include <linux/kernel.h> #include <linux/rbtree.h> #include <linux/string.h> +#include <errno.h> +#include <inttypes.h> #include <locale.h> #include <regex.h> +#include "sane_ctype.h" + static int kmem_slab; static int kmem_page; @@ -964,6 +969,7 @@ static struct perf_tool perf_kmem = { .comm = perf_event__process_comm, .mmap = perf_event__process_mmap, .mmap2 = perf_event__process_mmap2, + .namespaces = perf_event__process_namespaces, .ordered_events = true, }; @@ -1065,7 +1071,7 @@ static void __print_page_alloc_result(struct perf_session *session, int n_lines) data = rb_entry(next, struct page_stat, node); sym = machine__find_kernel_function(machine, data->callsite, &map); - if (sym && sym->name) + if (sym) caller = sym->name; else scnprintf(buf, sizeof(buf), "%"PRIx64, data->callsite); @@ -1107,7 +1113,7 @@ static void __print_page_caller_result(struct perf_session *session, int n_lines data = rb_entry(next, struct page_stat, node); sym = machine__find_kernel_function(machine, data->callsite, &map); - if (sym && sym->name) + if (sym) caller = sym->name; else scnprintf(buf, sizeof(buf), "%"PRIx64, data->callsite); @@ -1865,7 +1871,7 @@ static int __cmd_record(int argc, const char **argv) for (j = 1; j < (unsigned int)argc; j++, i++) rec_argv[i] = argv[j]; - return cmd_record(i, rec_argv, NULL); + return cmd_record(i, rec_argv); } static int kmem_config(const char *var, const char *value, void *cb __maybe_unused) @@ -1884,7 +1890,7 @@ static int kmem_config(const char *var, const char *value, void *cb __maybe_unus return 0; } -int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused) +int cmd_kmem(int argc, const char **argv) { const char * const default_slab_sort = "frag,hit,bytes"; const char * const default_page_sort = "bytes,hit"; @@ -1920,10 +1926,12 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused) NULL }; struct perf_session *session; - int ret = -1; const char errmsg[] = "No %s allocation events found. Have you run 'perf kmem record --%s'?\n"; + int ret = perf_config(kmem_config, NULL); + + if (ret) + return ret; - perf_config(kmem_config, NULL); argc = parse_options_subcommand(argc, argv, kmem_options, kmem_subcommands, kmem_usage, 0); @@ -1948,6 +1956,8 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused) if (session == NULL) return -1; + ret = -1; + if (kmem_slab) { if (!perf_evlist__find_tracepoint_by_name(session->evlist, "kmem:kmalloc")) { diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index 08fa88f62a24..f309c3773522 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -3,6 +3,7 @@ #include "util/evsel.h" #include "util/evlist.h" +#include "util/term.h" #include "util/util.h" #include "util/cache.h" #include "util/symbol.h" @@ -23,13 +24,33 @@ #ifdef HAVE_TIMERFD_SUPPORT #include <sys/timerfd.h> #endif +#include <sys/time.h> +#include <linux/kernel.h> #include <linux/time64.h> +#include <errno.h> +#include <inttypes.h> +#include <poll.h> #include <termios.h> #include <semaphore.h> +#include <signal.h> #include <pthread.h> #include <math.h> +static const char *get_filename_for_perf_kvm(void) +{ + const char *filename; + + if (perf_host && !perf_guest) + filename = strdup("perf.data.host"); + else if (!perf_host && perf_guest) + filename = strdup("perf.data.guest"); + else + filename = strdup("perf.data.kvm"); + + return filename; +} + #ifdef HAVE_KVM_STAT_SUPPORT #include "util/kvm-stat.h" @@ -1044,6 +1065,7 @@ static int read_events(struct perf_kvm_stat *kvm) struct perf_tool eops = { .sample = process_sample_event, .comm = perf_event__process_comm, + .namespaces = perf_event__process_namespaces, .ordered_events = true, }; struct perf_data_file file = { @@ -1208,7 +1230,7 @@ kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv) set_option_flag(record_options, 0, "transaction", PARSE_OPT_DISABLED); record_usage = kvm_stat_record_usage; - return cmd_record(i, rec_argv, NULL); + return cmd_record(i, rec_argv); } static int @@ -1348,6 +1370,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm, kvm->tool.exit = perf_event__process_exit; kvm->tool.fork = perf_event__process_fork; kvm->tool.lost = process_lost_event; + kvm->tool.namespaces = perf_event__process_namespaces; kvm->tool.ordered_events = true; perf_tool__fill_defaults(&kvm->tool); @@ -1475,7 +1498,7 @@ static int kvm_cmd_stat(const char *file_name, int argc, const char **argv) #endif perf_stat: - return cmd_stat(argc, argv, NULL); + return cmd_stat(argc, argv); } #endif /* HAVE_KVM_STAT_SUPPORT */ @@ -1494,7 +1517,7 @@ static int __cmd_record(const char *file_name, int argc, const char **argv) BUG_ON(i != rec_argc); - return cmd_record(i, rec_argv, NULL); + return cmd_record(i, rec_argv); } static int __cmd_report(const char *file_name, int argc, const char **argv) @@ -1512,7 +1535,7 @@ static int __cmd_report(const char *file_name, int argc, const char **argv) BUG_ON(i != rec_argc); - return cmd_report(i, rec_argv, NULL); + return cmd_report(i, rec_argv); } static int @@ -1531,10 +1554,10 @@ __cmd_buildid_list(const char *file_name, int argc, const char **argv) BUG_ON(i != rec_argc); - return cmd_buildid_list(i, rec_argv, NULL); + return cmd_buildid_list(i, rec_argv); } -int cmd_kvm(int argc, const char **argv, const char *prefix __maybe_unused) +int cmd_kvm(int argc, const char **argv) { const char *file_name = NULL; const struct option kvm_options[] = { @@ -1589,9 +1612,9 @@ int cmd_kvm(int argc, const char **argv, const char *prefix __maybe_unused) else if (!strncmp(argv[0], "rep", 3)) return __cmd_report(file_name, argc, argv); else if (!strncmp(argv[0], "diff", 4)) - return cmd_diff(argc, argv, NULL); + return cmd_diff(argc, argv); else if (!strncmp(argv[0], "top", 3)) - return cmd_top(argc, argv, NULL); + return cmd_top(argc, argv); else if (!strncmp(argv[0], "buildid-list", 12)) return __cmd_buildid_list(file_name, argc, argv); #ifdef HAVE_KVM_STAT_SUPPORT diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c index ba9322ff858b..4bf2cb4d25aa 100644 --- a/tools/perf/builtin-list.c +++ b/tools/perf/builtin-list.c @@ -14,11 +14,13 @@ #include "util/parse-events.h" #include "util/cache.h" #include "util/pmu.h" +#include "util/debug.h" #include <subcmd/parse-options.h> static bool desc_flag = true; +static bool details_flag; -int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused) +int cmd_list(int argc, const char **argv) { int i; bool raw_dump = false; @@ -29,6 +31,10 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused) "Print extra event descriptions. --no-desc to not print."), OPT_BOOLEAN('v', "long-desc", &long_desc_flag, "Print longer event descriptions."), + OPT_BOOLEAN(0, "details", &details_flag, + "Print information on the perf event names and expressions used internally by events."), + OPT_INCR(0, "debug", &verbose, + "Enable debugging output"), OPT_END() }; const char * const list_usage[] = { @@ -47,7 +53,8 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused) printf("\nList of pre-defined events (to be used in -e):\n\n"); if (argc == 0) { - print_events(NULL, raw_dump, !desc_flag, long_desc_flag); + print_events(NULL, raw_dump, !desc_flag, long_desc_flag, + details_flag); return 0; } @@ -69,7 +76,7 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused) print_hwcache_events(NULL, raw_dump); else if (strcmp(argv[i], "pmu") == 0) print_pmu_events(NULL, raw_dump, !desc_flag, - long_desc_flag); + long_desc_flag, details_flag); else if (strcmp(argv[i], "sdt") == 0) print_sdt_events(NULL, NULL, raw_dump); else if ((sep = strchr(argv[i], ':')) != NULL) { @@ -77,7 +84,8 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused) if (sep == NULL) { print_events(argv[i], raw_dump, !desc_flag, - long_desc_flag); + long_desc_flag, + details_flag); continue; } sep_idx = sep - argv[i]; @@ -100,7 +108,8 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused) event_symbols_sw, PERF_COUNT_SW_MAX, raw_dump); print_hwcache_events(s, raw_dump); print_pmu_events(s, raw_dump, !desc_flag, - long_desc_flag); + long_desc_flag, + details_flag); print_tracepoint_events(NULL, s, raw_dump); print_sdt_events(NULL, s, raw_dump); free(s); diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index ce3bfb48b26f..ff98652484a7 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -1,3 +1,5 @@ +#include <errno.h> +#include <inttypes.h> #include "builtin.h" #include "perf.h" @@ -26,6 +28,7 @@ #include <linux/list.h> #include <linux/hash.h> +#include <linux/kernel.h> static struct perf_session *session; @@ -858,6 +861,7 @@ static int __cmd_report(bool display_info) struct perf_tool eops = { .sample = process_sample_event, .comm = perf_event__process_comm, + .namespaces = perf_event__process_namespaces, .ordered_events = true, }; struct perf_data_file file = { @@ -940,34 +944,36 @@ static int __cmd_record(int argc, const char **argv) BUG_ON(i != rec_argc); - ret = cmd_record(i, rec_argv, NULL); + ret = cmd_record(i, rec_argv); free(rec_argv); return ret; } -int cmd_lock(int argc, const char **argv, const char *prefix __maybe_unused) +int cmd_lock(int argc, const char **argv) { - const struct option info_options[] = { - OPT_BOOLEAN('t', "threads", &info_threads, - "dump thread list in perf.data"), - OPT_BOOLEAN('m', "map", &info_map, - "map of lock instances (address:name table)"), - OPT_BOOLEAN('f', "force", &force, "don't complain, do it"), - OPT_END() - }; const struct option lock_options[] = { OPT_STRING('i', "input", &input_name, "file", "input file name"), OPT_INCR('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"), OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, "dump raw trace in ASCII"), + OPT_BOOLEAN('f', "force", &force, "don't complain, do it"), OPT_END() }; + + const struct option info_options[] = { + OPT_BOOLEAN('t', "threads", &info_threads, + "dump thread list in perf.data"), + OPT_BOOLEAN('m', "map", &info_map, + "map of lock instances (address:name table)"), + OPT_PARENT(lock_options) + }; + const struct option report_options[] = { OPT_STRING('k', "key", &sort_key, "acquired", "key for sorting (acquired / contended / avg_wait / wait_total / wait_max / wait_min)"), - OPT_BOOLEAN('f', "force", &force, "don't complain, do it"), /* TODO: type */ - OPT_END() + OPT_PARENT(lock_options) }; + const char * const info_usage[] = { "perf lock info [<options>]", NULL @@ -1006,7 +1012,7 @@ int cmd_lock(int argc, const char **argv, const char *prefix __maybe_unused) rc = __cmd_report(false); } else if (!strcmp(argv[0], "script")) { /* Aliased to 'perf script' */ - return cmd_script(argc, argv, prefix); + return cmd_script(argc, argv); } else if (!strcmp(argv[0], "info")) { if (argc) { argc = parse_options(argc, argv, diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c index cd7bc4d104e2..e001c0290793 100644 --- a/tools/perf/builtin-mem.c +++ b/tools/perf/builtin-mem.c @@ -1,3 +1,7 @@ +#include <inttypes.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> #include "builtin.h" #include "perf.h" @@ -8,6 +12,7 @@ #include "util/data.h" #include "util/mem-events.h" #include "util/debug.h" +#include "util/symbol.h" #define MEM_OPERATION_LOAD 0x1 #define MEM_OPERATION_STORE 0x2 @@ -42,8 +47,8 @@ static int parse_record_events(const struct option *opt, fprintf(stderr, "%-13s%-*s%s\n", e->tag, - verbose ? 25 : 0, - verbose ? perf_mem_events__name(j) : "", + verbose > 0 ? 25 : 0, + verbose > 0 ? perf_mem_events__name(j) : "", e->supported ? ": available" : ""); } exit(0); @@ -129,7 +134,7 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem) pr_debug("\n"); } - ret = cmd_record(i, rec_argv, NULL); + ret = cmd_record(i, rec_argv); free(rec_argv); return ret; } @@ -256,7 +261,7 @@ static int report_events(int argc, const char **argv, struct perf_mem *mem) for (j = 1; j < argc; j++, i++) rep_argv[i] = argv[j]; - ret = cmd_report(i, rep_argv, NULL); + ret = cmd_report(i, rep_argv); free(rep_argv); return ret; } @@ -330,7 +335,7 @@ error: return ret; } -int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused) +int cmd_mem(int argc, const char **argv) { struct stat st; struct perf_mem mem = { @@ -342,6 +347,7 @@ int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused) .lost = perf_event__process_lost, .fork = perf_event__process_fork, .build_id = perf_event__process_build_id, + .namespaces = perf_event__process_namespaces, .ordered_events = true, }, .input_name = "perf.data", diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c index f87996b0cb29..cf9f9e9c2fc0 100644 --- a/tools/perf/builtin-probe.c +++ b/tools/perf/builtin-probe.c @@ -442,9 +442,9 @@ static int perf_del_probe_events(struct strfilter *filter) } if (ret == -ENOENT && ret2 == -ENOENT) - pr_debug("\"%s\" does not hit any event.\n", str); - /* Note that this is silently ignored */ - ret = 0; + pr_warning("\"%s\" does not hit any event.\n", str); + else + ret = 0; error: if (kfd >= 0) @@ -468,7 +468,7 @@ out: static int -__cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused) +__cmd_probe(int argc, const char **argv) { const char * const probe_usage[] = { "perf probe [<options>] 'PROBEDEF' ['PROBEDEF' ...]", @@ -486,7 +486,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused) OPT_INCR('v', "verbose", &verbose, "be more verbose (show parsed arguments, etc)"), OPT_BOOLEAN('q', "quiet", ¶ms.quiet, - "be quiet (do not show any mesages)"), + "be quiet (do not show any messages)"), OPT_CALLBACK_DEFAULT('l', "list", NULL, "[GROUP:]EVENT", "list up probe events", opt_set_filter_with_command, DEFAULT_LIST_FILTER), @@ -552,6 +552,8 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused) OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel, "Enable kernel symbol demangling"), OPT_BOOLEAN(0, "cache", &probe_conf.cache, "Manipulate probe cache"), + OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory", + "Look for files with symbols relative to this directory"), OPT_END() }; int ret; @@ -685,13 +687,13 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused) return 0; } -int cmd_probe(int argc, const char **argv, const char *prefix) +int cmd_probe(int argc, const char **argv) { int ret; ret = init_params(); if (!ret) { - ret = __cmd_probe(argc, argv, prefix); + ret = __cmd_probe(argc, argv); cleanup_params(); } diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 4ec10e9427d9..ee7d0a82ccd0 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -38,14 +38,30 @@ #include "util/bpf-loader.h" #include "util/trigger.h" #include "util/perf-hooks.h" +#include "util/time-utils.h" +#include "util/units.h" #include "asm/bug.h" +#include <errno.h> +#include <inttypes.h> +#include <poll.h> #include <unistd.h> #include <sched.h> +#include <signal.h> #include <sys/mman.h> +#include <sys/wait.h> #include <asm/bug.h> #include <linux/time64.h> +struct switch_output { + bool enabled; + bool signal; + unsigned long size; + unsigned long time; + const char *str; + bool set; +}; + struct record { struct perf_tool tool; struct record_opts opts; @@ -62,10 +78,33 @@ struct record { bool no_buildid_cache_set; bool buildid_all; bool timestamp_filename; - bool switch_output; + struct switch_output switch_output; unsigned long long samples; }; +static volatile int auxtrace_record__snapshot_started; +static DEFINE_TRIGGER(auxtrace_snapshot_trigger); +static DEFINE_TRIGGER(switch_output_trigger); + +static bool switch_output_signal(struct record *rec) +{ + return rec->switch_output.signal && + trigger_is_ready(&switch_output_trigger); +} + +static bool switch_output_size(struct record *rec) +{ + return rec->switch_output.size && + trigger_is_ready(&switch_output_trigger) && + (rec->bytes_written >= rec->switch_output.size); +} + +static bool switch_output_time(struct record *rec) +{ + return rec->switch_output.time && + trigger_is_ready(&switch_output_trigger); +} + static int record__write(struct record *rec, void *bf, size_t size) { if (perf_data_file__write(rec->session->file, bf, size) < 0) { @@ -74,6 +113,10 @@ static int record__write(struct record *rec, void *bf, size_t size) } rec->bytes_written += size; + + if (switch_output_size(rec)) + trigger_hit(&switch_output_trigger); + return 0; } @@ -193,10 +236,6 @@ static volatile int done; static volatile int signr = -1; static volatile int child_finished; -static volatile int auxtrace_record__snapshot_started; -static DEFINE_TRIGGER(auxtrace_snapshot_trigger); -static DEFINE_TRIGGER(switch_output_trigger); - static void sig_handler(int sig) { if (sig == SIGCHLD) @@ -386,7 +425,7 @@ static int record__mmap(struct record *rec) static int record__open(struct record *rec) { - char msg[512]; + char msg[BUFSIZ]; struct perf_evsel *pos; struct perf_evlist *evlist = rec->evlist; struct perf_session *session = rec->session; @@ -400,7 +439,7 @@ static int record__open(struct record *rec) try_again: if (perf_evsel__open(pos, pos->cpus, pos->threads) < 0) { if (perf_evsel__fallback(pos, errno, msg, sizeof(msg))) { - if (verbose) + if (verbose > 0) ui__warning("%s\n", msg); goto try_again; } @@ -623,22 +662,23 @@ record__finish_output(struct record *rec) static int record__synthesize_workload(struct record *rec, bool tail) { - struct { - struct thread_map map; - struct thread_map_data map_data; - } thread_map; + int err; + struct thread_map *thread_map; if (rec->opts.tail_synthesize != tail) return 0; - thread_map.map.nr = 1; - thread_map.map.map[0].pid = rec->evlist->workload.pid; - thread_map.map.map[0].comm = NULL; - return perf_event__synthesize_thread_map(&rec->tool, &thread_map.map, + thread_map = thread_map__new_by_tid(rec->evlist->workload.pid); + if (thread_map == NULL) + return -1; + + err = perf_event__synthesize_thread_map(&rec->tool, thread_map, process_synthesized_event, &rec->session->machines.host, rec->opts.sample_address, rec->opts.proc_map_timeout); + thread_map__put(thread_map); + return err; } static int record__synthesize(struct record *rec, bool tail); @@ -712,6 +752,7 @@ static void workload_exec_failed_signal(int signo __maybe_unused, } static void snapshot_sig_handler(int sig); +static void alarm_sig_handler(int sig); int __weak perf_event__synth_time_conv(const struct perf_event_mmap_page *pc __maybe_unused, @@ -842,11 +883,14 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) signal(SIGTERM, sig_handler); signal(SIGSEGV, sigsegv_handler); - if (rec->opts.auxtrace_snapshot_mode || rec->switch_output) { + if (rec->opts.record_namespaces) + tool->namespace_events = true; + + if (rec->opts.auxtrace_snapshot_mode || rec->switch_output.enabled) { signal(SIGUSR2, snapshot_sig_handler); if (rec->opts.auxtrace_snapshot_mode) trigger_on(&auxtrace_snapshot_trigger); - if (rec->switch_output) + if (rec->switch_output.enabled) trigger_on(&switch_output_trigger); } else { signal(SIGUSR2, SIG_IGN); @@ -949,6 +993,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) */ if (forks) { union perf_event *event; + pid_t tgid; event = malloc(sizeof(event->comm) + machine->id_hdr_size); if (event == NULL) { @@ -962,10 +1007,30 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) * cannot see a correct process name for those events. * Synthesize COMM event to prevent it. */ - perf_event__synthesize_comm(tool, event, - rec->evlist->workload.pid, - process_synthesized_event, - machine); + tgid = perf_event__synthesize_comm(tool, event, + rec->evlist->workload.pid, + process_synthesized_event, + machine); + free(event); + + if (tgid == -1) + goto out_child; + + event = malloc(sizeof(event->namespaces) + + (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) + + machine->id_hdr_size); + if (event == NULL) { + err = -ENOMEM; + goto out_child; + } + + /* + * Synthesize NAMESPACES event for the command specified. + */ + perf_event__synthesize_namespaces(tool, event, + rec->evlist->workload.pid, + tgid, process_synthesized_event, + machine); free(event); perf_evlist__start_workload(rec->evlist); @@ -1043,6 +1108,10 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) err = fd; goto out_child; } + + /* re-arm the alarm */ + if (rec->switch_output.time) + alarm(rec->switch_output.time); } if (hits == rec->samples) { @@ -1352,6 +1421,78 @@ out_free: return ret; } +static void switch_output_size_warn(struct record *rec) +{ + u64 wakeup_size = perf_evlist__mmap_size(rec->opts.mmap_pages); + struct switch_output *s = &rec->switch_output; + + wakeup_size /= 2; + + if (s->size < wakeup_size) { + char buf[100]; + + unit_number__scnprintf(buf, sizeof(buf), wakeup_size); + pr_warning("WARNING: switch-output data size lower than " + "wakeup kernel buffer size (%s) " + "expect bigger perf.data sizes\n", buf); + } +} + +static int switch_output_setup(struct record *rec) +{ + struct switch_output *s = &rec->switch_output; + static struct parse_tag tags_size[] = { + { .tag = 'B', .mult = 1 }, + { .tag = 'K', .mult = 1 << 10 }, + { .tag = 'M', .mult = 1 << 20 }, + { .tag = 'G', .mult = 1 << 30 }, + { .tag = 0 }, + }; + static struct parse_tag tags_time[] = { + { .tag = 's', .mult = 1 }, + { .tag = 'm', .mult = 60 }, + { .tag = 'h', .mult = 60*60 }, + { .tag = 'd', .mult = 60*60*24 }, + { .tag = 0 }, + }; + unsigned long val; + + if (!s->set) + return 0; + + if (!strcmp(s->str, "signal")) { + s->signal = true; + pr_debug("switch-output with SIGUSR2 signal\n"); + goto enabled; + } + + val = parse_tag_value(s->str, tags_size); + if (val != (unsigned long) -1) { + s->size = val; + pr_debug("switch-output with %s size threshold\n", s->str); + goto enabled; + } + + val = parse_tag_value(s->str, tags_time); + if (val != (unsigned long) -1) { + s->time = val; + pr_debug("switch-output with %s time threshold (%lu seconds)\n", + s->str, s->time); + goto enabled; + } + + return -1; + +enabled: + rec->timestamp_filename = true; + s->enabled = true; + + if (s->size && !rec->opts.no_buffering) + switch_output_size_warn(rec); + + return 0; +} + static const char * const __record_usage[] = { "perf record [<options>] [<command>]", "perf record [<options>] -- <command> [<options>]", @@ -1387,6 +1528,7 @@ static struct record record = { .fork = perf_event__process_fork, .exit = perf_event__process_exit, .comm = perf_event__process_comm, + .namespaces = perf_event__process_namespaces, .mmap = perf_event__process_mmap, .mmap2 = perf_event__process_mmap2, .ordered_events = true, @@ -1501,6 +1643,8 @@ static struct option __record_options[] = { "opts", "AUX area tracing Snapshot Mode", ""), OPT_UINTEGER(0, "proc-map-timeout", &record.opts.proc_map_timeout, "per thread proc mmap processing timeout in ms"), + OPT_BOOLEAN(0, "namespaces", &record.opts.record_namespaces, + "Record namespaces events"), OPT_BOOLEAN(0, "switch-events", &record.opts.record_switch_events, "Record context switch events"), OPT_BOOLEAN_FLAG(0, "all-kernel", &record.opts.all_kernel, @@ -1519,8 +1663,10 @@ static struct option __record_options[] = { "Record build-id of all DSOs regardless of hits"), OPT_BOOLEAN(0, "timestamp-filename", &record.timestamp_filename, "append timestamp to output filename"), - OPT_BOOLEAN(0, "switch-output", &record.switch_output, - "Switch output when receive SIGUSR2"), + OPT_STRING_OPTARG_SET(0, "switch-output", &record.switch_output.str, + &record.switch_output.set, "signal,size,time", + "Switch output when receive SIGUSR2 or cross size,time threshold", + "signal"), OPT_BOOLEAN(0, "dry-run", &dry_run, "Parse options then exit"), OPT_END() @@ -1528,7 +1674,7 @@ static struct option __record_options[] = { struct option *record_options = __record_options; -int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused) +int cmd_record(int argc, const char **argv) { int err; struct record *rec = &record; @@ -1559,12 +1705,18 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused) if (rec->evlist == NULL) return -ENOMEM; - perf_config(perf_record_config, rec); + err = perf_config(perf_record_config, rec); + if (err) + return err; argc = parse_options(argc, argv, record_options, record_usage, PARSE_OPT_STOP_AT_NON_OPTION); + if (quiet) + perf_quiet_option(); + + /* Make system wide (-a) the default target. */ if (!argc && target__none(&rec->opts.target)) - usage_with_options(record_usage, record_options); + rec->opts.target.system_wide = true; if (nr_cgroups && !rec->opts.target.system_wide) { usage_with_options_msg(record_usage, record_options, @@ -1578,8 +1730,15 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused) return -EINVAL; } - if (rec->switch_output) - rec->timestamp_filename = true; + if (switch_output_setup(rec)) { + parse_options_usage(record_usage, record_options, "switch-output", 0); + return -EINVAL; + } + + if (rec->switch_output.time) { + signal(SIGALRM, alarm_sig_handler); + alarm(rec->switch_output.time); + } if (!rec->itr) { rec->itr = auxtrace_record__init(rec->evlist, &err); @@ -1629,7 +1788,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused) if (rec->no_buildid_cache || rec->no_buildid) { disable_buildid_cache(); - } else if (rec->switch_output) { + } else if (rec->switch_output.enabled) { /* * In 'perf record --switch-output', disable buildid * generation by default to reduce data file switching @@ -1721,6 +1880,8 @@ out: static void snapshot_sig_handler(int sig __maybe_unused) { + struct record *rec = &record; + if (trigger_is_ready(&auxtrace_snapshot_trigger)) { trigger_hit(&auxtrace_snapshot_trigger); auxtrace_record__snapshot_started = 1; @@ -1728,6 +1889,14 @@ static void snapshot_sig_handler(int sig __maybe_unused) trigger_error(&auxtrace_snapshot_trigger); } - if (trigger_is_ready(&switch_output_trigger)) + if (switch_output_signal(rec)) + trigger_hit(&switch_output_trigger); +} + +static void alarm_sig_handler(int sig __maybe_unused) +{ + struct record *rec = &record; + + if (switch_output_time(rec)) trigger_hit(&switch_output_trigger); } diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 06cc759a4597..22478ff2b706 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -16,7 +16,6 @@ #include <linux/rbtree.h> #include "util/symbol.h" #include "util/callchain.h" -#include "util/strlist.h" #include "util/values.h" #include "perf.h" @@ -38,10 +37,18 @@ #include "arch/common.h" #include "util/time-utils.h" #include "util/auxtrace.h" +#include "util/units.h" #include <dlfcn.h> +#include <errno.h> +#include <inttypes.h> +#include <regex.h> +#include <signal.h> #include <linux/bitmap.h> #include <linux/stringify.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> struct report { struct perf_tool tool; @@ -320,6 +327,9 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report size_t size = sizeof(buf); int socked_id = hists->socket_filter; + if (quiet) + return 0; + if (symbol_conf.filter_relative) { nr_samples = hists->stats.nr_non_filtered_samples; nr_events = hists->stats.total_non_filtered_period; @@ -372,7 +382,11 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist, { struct perf_evsel *pos; - fprintf(stdout, "#\n# Total Lost Samples: %" PRIu64 "\n#\n", evlist->stats.total_lost_samples); + if (!quiet) { + fprintf(stdout, "#\n# Total Lost Samples: %" PRIu64 "\n#\n", + evlist->stats.total_lost_samples); + } + evlist__for_each_entry(evlist, pos) { struct hists *hists = evsel__hists(pos); const char *evname = perf_evsel__name(pos); @@ -382,13 +396,12 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist, continue; hists__fprintf_nr_sample_events(hists, rep, evname, stdout); - hists__fprintf(hists, true, 0, 0, rep->min_percent, stdout, + hists__fprintf(hists, !quiet, 0, 0, rep->min_percent, stdout, symbol_conf.use_callchain); fprintf(stdout, "\n\n"); } - if (sort_order == NULL && - parent_pattern == default_parent_pattern) + if (!quiet) fprintf(stdout, "#\n# (%s)\n#\n", help); if (rep->show_threads) { @@ -675,7 +688,7 @@ const char report_callchain_help[] = "Display call graph (stack chain/backtrace) CALLCHAIN_REPORT_HELP "\n\t\t\t\tDefault: " CALLCHAIN_DEFAULT_OPT; -int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) +int cmd_report(int argc, const char **argv) { struct perf_session *session; struct itrace_synth_opts itrace_synth_opts = { .set = 0, }; @@ -694,6 +707,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) .mmap = perf_event__process_mmap, .mmap2 = perf_event__process_mmap2, .comm = perf_event__process_comm, + .namespaces = perf_event__process_namespaces, .exit = perf_event__process_exit, .fork = perf_event__process_fork, .lost = perf_event__process_lost, @@ -716,6 +730,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) "input file name"), OPT_INCR('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"), + OPT_BOOLEAN('q', "quiet", &quiet, "Do not show any message"), OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, "dump raw trace in ASCII"), OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name, @@ -837,6 +852,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) stdio__config_color, "always"), OPT_STRING(0, "time", &report.time_str, "str", "Time span of interest (start,stop)"), + OPT_BOOLEAN(0, "inline", &symbol_conf.inline_name, + "Show inline function"), OPT_END() }; struct perf_data_file file = { @@ -847,7 +864,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) if (ret < 0) return ret; - perf_config(report__config, &report); + ret = perf_config(report__config, &report); + if (ret) + return ret; argc = parse_options(argc, argv, options, report_usage, 0); if (argc) { @@ -861,6 +880,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) report.symbol_filter_str = argv[0]; } + if (quiet) + perf_quiet_option(); + if (symbol_conf.vmlinux_name && access(symbol_conf.vmlinux_name, R_OK)) { pr_err("Invalid file: %s\n", symbol_conf.vmlinux_name); @@ -981,14 +1003,14 @@ repeat: goto error; } - if (report.header || report.header_only) { + if ((report.header || report.header_only) && !quiet) { perf_session__fprintf_info(session, stdout, report.show_full_info); if (report.header_only) { ret = 0; goto error; } - } else if (use_browser == 0) { + } else if (use_browser == 0 && !quiet) { fputs("# To display the perf.data header info, please use --header/--header-only options.\n#\n", stdout); } @@ -1007,7 +1029,7 @@ repeat: * providing it only in verbose mode not to bloat too * much struct symbol. */ - if (verbose) { + if (verbose > 0) { /* * XXX: Need to provide a less kludgy way to ask for * more space per symbol, the u32 is for the index on diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 5b134b0d1ff3..39996c53995a 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -22,16 +22,21 @@ #include "util/debug.h" +#include <linux/kernel.h> #include <linux/log2.h> #include <sys/prctl.h> #include <sys/resource.h> +#include <inttypes.h> +#include <errno.h> #include <semaphore.h> #include <pthread.h> #include <math.h> #include <api/fs/fs.h> #include <linux/time64.h> +#include "sane_ctype.h" + #define PR_SET_NAME 15 /* Set process name */ #define MAX_CPUS 4096 #define COMM_LEN 20 @@ -77,6 +82,22 @@ struct sched_atom { #define TASK_STATE_TO_CHAR_STR "RSDTtZXxKWP" +/* task state bitmask, copied from include/linux/sched.h */ +#define TASK_RUNNING 0 +#define TASK_INTERRUPTIBLE 1 +#define TASK_UNINTERRUPTIBLE 2 +#define __TASK_STOPPED 4 +#define __TASK_TRACED 8 +/* in tsk->exit_state */ +#define EXIT_DEAD 16 +#define EXIT_ZOMBIE 32 +#define EXIT_TRACE (EXIT_ZOMBIE | EXIT_DEAD) +/* in tsk->state again */ +#define TASK_DEAD 64 +#define TASK_WAKEKILL 128 +#define TASK_WAKING 256 +#define TASK_PARKED 512 + enum thread_state { THREAD_SLEEPING = 0, THREAD_WAIT_CPU, @@ -205,7 +226,9 @@ struct perf_sched { unsigned int max_stack; bool show_cpu_visual; bool show_wakeups; + bool show_next; bool show_migrations; + bool show_state; u64 skipped_samples; const char *time_str; struct perf_time_interval ptime; @@ -216,13 +239,20 @@ struct perf_sched { struct thread_runtime { u64 last_time; /* time of previous sched in/out event */ u64 dt_run; /* run time */ - u64 dt_wait; /* time between CPU access (off cpu) */ + u64 dt_sleep; /* time between CPU access by sleep (off cpu) */ + u64 dt_iowait; /* time between CPU access by iowait (off cpu) */ + u64 dt_preempt; /* time between CPU access by preempt (off cpu) */ u64 dt_delay; /* time between wakeup and sched-in */ u64 ready_to_run; /* time of wakeup */ struct stats run_stats; u64 total_run_time; + u64 total_sleep_time; + u64 total_iowait_time; + u64 total_preempt_time; + u64 total_delay_time; + int last_state; u64 migrations; }; @@ -436,7 +466,7 @@ static struct task_desc *register_pid(struct perf_sched *sched, BUG_ON(!sched->tasks); sched->tasks[task->nr] = task; - if (verbose) + if (verbose > 0) printf("registered task #%ld, PID %ld (%s)\n", sched->nr_tasks, pid, comm); return task; @@ -770,7 +800,7 @@ replay_wakeup_event(struct perf_sched *sched, const u32 pid = perf_evsel__intval(evsel, sample, "pid"); struct task_desc *waker, *wakee; - if (verbose) { + if (verbose > 0) { printf("sched_wakeup event %p\n", evsel); printf(" ... pid %d woke up %s/%d\n", sample->tid, comm, pid); @@ -798,7 +828,7 @@ static int replay_switch_event(struct perf_sched *sched, int cpu = sample->cpu; s64 delta; - if (verbose) + if (verbose > 0) printf("sched_switch event %p\n", evsel); if (cpu >= MAX_CPUS || cpu < 0) @@ -846,7 +876,7 @@ static int replay_fork_event(struct perf_sched *sched, goto out_put; } - if (verbose) { + if (verbose > 0) { printf("fork event\n"); printf("... parent: %s/%d\n", thread__comm_str(parent), parent->tid); printf("... child: %s/%d\n", thread__comm_str(child), child->tid); @@ -1549,7 +1579,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel, timestamp__scnprintf_usec(timestamp, stimestamp, sizeof(stimestamp)); color_fprintf(stdout, color, " %12s secs ", stimestamp); - if (new_shortname || (verbose && sched_in->tid)) { + if (new_shortname || (verbose > 0 && sched_in->tid)) { const char *pid_color = color; if (thread__has_color(sched_in)) @@ -1821,6 +1851,9 @@ static void timehist_header(struct perf_sched *sched) printf(" %-*s %9s %9s %9s", comm_width, "task name", "wait time", "sch delay", "run time"); + if (sched->show_state) + printf(" %s", "state"); + printf("\n"); /* @@ -1831,9 +1864,14 @@ static void timehist_header(struct perf_sched *sched) if (sched->show_cpu_visual) printf(" %*s ", ncpus, ""); - printf(" %-*s %9s %9s %9s\n", comm_width, + printf(" %-*s %9s %9s %9s", comm_width, "[tid/pid]", "(msec)", "(msec)", "(msec)"); + if (sched->show_state) + printf(" %5s", ""); + + printf("\n"); + /* * separator */ @@ -1846,18 +1884,38 @@ static void timehist_header(struct perf_sched *sched) graph_dotted_line, graph_dotted_line, graph_dotted_line, graph_dotted_line); + if (sched->show_state) + printf(" %.5s", graph_dotted_line); + printf("\n"); } +static char task_state_char(struct thread *thread, int state) +{ + static const char state_to_char[] = TASK_STATE_TO_CHAR_STR; + unsigned bit = state ? ffs(state) : 0; + + /* 'I' for idle */ + if (thread->tid == 0) + return 'I'; + + return bit < sizeof(state_to_char) - 1 ? state_to_char[bit] : '?'; +} + static void timehist_print_sample(struct perf_sched *sched, + struct perf_evsel *evsel, struct perf_sample *sample, struct addr_location *al, struct thread *thread, - u64 t) + u64 t, int state) { struct thread_runtime *tr = thread__priv(thread); + const char *next_comm = perf_evsel__strval(evsel, sample, "next_comm"); + const u32 next_pid = perf_evsel__intval(evsel, sample, "next_pid"); u32 max_cpus = sched->max_cpu + 1; char tstr[64]; + char nstr[30]; + u64 wait_time; timestamp__scnprintf_usec(t, tstr, sizeof(tstr)); printf("%15s [%04d] ", tstr, sample->cpu); @@ -1880,11 +1938,21 @@ static void timehist_print_sample(struct perf_sched *sched, printf(" %-*s ", comm_width, timehist_get_commstr(thread)); - print_sched_time(tr->dt_wait, 6); + wait_time = tr->dt_sleep + tr->dt_iowait + tr->dt_preempt; + print_sched_time(wait_time, 6); + print_sched_time(tr->dt_delay, 6); print_sched_time(tr->dt_run, 6); - if (sched->show_wakeups) + if (sched->show_state) + printf(" %5c ", task_state_char(thread, state)); + + if (sched->show_next) { + snprintf(nstr, sizeof(nstr), "next: %s[%d]", next_comm, next_pid); + printf(" %-*s", comm_width, nstr); + } + + if (sched->show_wakeups && !sched->show_next) printf(" %-*s", comm_width, ""); if (thread->tid == 0) @@ -1930,8 +1998,11 @@ static void timehist_update_runtime_stats(struct thread_runtime *r, u64 t, u64 tprev) { r->dt_delay = 0; - r->dt_wait = 0; + r->dt_sleep = 0; + r->dt_iowait = 0; + r->dt_preempt = 0; r->dt_run = 0; + if (tprev) { r->dt_run = t - tprev; if (r->ready_to_run) { @@ -1943,12 +2014,25 @@ static void timehist_update_runtime_stats(struct thread_runtime *r, if (r->last_time > tprev) pr_debug("time travel: last sched out time for task > previous sched_switch event\n"); - else if (r->last_time) - r->dt_wait = tprev - r->last_time; + else if (r->last_time) { + u64 dt_wait = tprev - r->last_time; + + if (r->last_state == TASK_RUNNING) + r->dt_preempt = dt_wait; + else if (r->last_state == TASK_UNINTERRUPTIBLE) + r->dt_iowait = dt_wait; + else + r->dt_sleep = dt_wait; + } } update_stats(&r->run_stats, r->dt_run); - r->total_run_time += r->dt_run; + + r->total_run_time += r->dt_run; + r->total_delay_time += r->dt_delay; + r->total_sleep_time += r->dt_sleep; + r->total_iowait_time += r->dt_iowait; + r->total_preempt_time += r->dt_preempt; } static bool is_idle_sample(struct perf_sample *sample, @@ -1981,7 +2065,7 @@ static void save_task_callchain(struct perf_sched *sched, if (thread__resolve_callchain(thread, cursor, evsel, sample, NULL, NULL, sched->max_stack + 2) != 0) { - if (verbose) + if (verbose > 0) error("Failed to resolve callchain. Skipping\n"); return; @@ -1998,7 +2082,7 @@ static void save_task_callchain(struct perf_sched *sched, break; sym = node->sym; - if (sym && sym->name) { + if (sym) { if (!strcmp(sym->name, "schedule") || !strcmp(sym->name, "__schedule") || !strcmp(sym->name, "preempt_schedule")) @@ -2373,6 +2457,8 @@ static int timehist_sched_change_event(struct perf_tool *tool, struct thread_runtime *tr = NULL; u64 tprev, t = sample->time; int rc = 0; + int state = perf_evsel__intval(evsel, sample, "prev_state"); + if (machine__resolve(machine, &al, sample) < 0) { pr_err("problem processing %d event. skipping it\n", @@ -2447,8 +2533,10 @@ static int timehist_sched_change_event(struct perf_tool *tool, * time. we only care total run time and run stat. */ last_tr->dt_run = 0; - last_tr->dt_wait = 0; last_tr->dt_delay = 0; + last_tr->dt_sleep = 0; + last_tr->dt_iowait = 0; + last_tr->dt_preempt = 0; if (itr->cursor.nr) callchain_append(&itr->callchain, &itr->cursor, t - tprev); @@ -2458,7 +2546,7 @@ static int timehist_sched_change_event(struct perf_tool *tool, } if (!sched->summary_only) - timehist_print_sample(sched, sample, &al, thread, t); + timehist_print_sample(sched, evsel, sample, &al, thread, t, state); out: if (sched->hist_time.start == 0 && t >= ptime->start) @@ -2470,6 +2558,9 @@ out: /* time of this sched_switch event becomes last time task seen */ tr->last_time = sample->time; + /* last state is used to determine where to account wait time */ + tr->last_state = state; + /* sched out event for task so reset ready to run time */ tr->ready_to_run = 0; } @@ -2526,7 +2617,26 @@ static void print_thread_runtime(struct thread *t, printf("\n"); } +static void print_thread_waittime(struct thread *t, + struct thread_runtime *r) +{ + printf("%*s %5d %9" PRIu64 " ", + comm_width, timehist_get_commstr(t), t->ppid, + (u64) r->run_stats.n); + + print_sched_time(r->total_run_time, 8); + print_sched_time(r->total_sleep_time, 6); + printf(" "); + print_sched_time(r->total_iowait_time, 6); + printf(" "); + print_sched_time(r->total_preempt_time, 6); + printf(" "); + print_sched_time(r->total_delay_time, 6); + printf("\n"); +} + struct total_run_stats { + struct perf_sched *sched; u64 sched_count; u64 task_count; u64 total_run_time; @@ -2545,7 +2655,11 @@ static int __show_thread_runtime(struct thread *t, void *priv) stats->task_count++; stats->sched_count += r->run_stats.n; stats->total_run_time += r->total_run_time; - print_thread_runtime(t, r); + + if (stats->sched->show_state) + print_thread_waittime(t, r); + else + print_thread_runtime(t, r); } return 0; @@ -2633,18 +2747,24 @@ static void timehist_print_summary(struct perf_sched *sched, u64 hist_time = sched->hist_time.end - sched->hist_time.start; memset(&totals, 0, sizeof(totals)); + totals.sched = sched; if (sched->idle_hist) { printf("\nIdle-time summary\n"); printf("%*s parent sched-out ", comm_width, "comm"); printf(" idle-time min-idle avg-idle max-idle stddev migrations\n"); + } else if (sched->show_state) { + printf("\nWait-time summary\n"); + printf("%*s parent sched-in ", comm_width, "comm"); + printf(" run-time sleep iowait preempt delay\n"); } else { printf("\nRuntime summary\n"); printf("%*s parent sched-in ", comm_width, "comm"); printf(" run-time min-run avg-run max-run stddev migrations\n"); } printf("%*s (count) ", comm_width, ""); - printf(" (msec) (msec) (msec) (msec) %%\n"); + printf(" (msec) (msec) (msec) (msec) %s\n", + sched->show_state ? "(msec)" : "%"); printf("%.117s\n", graph_dotted_line); machine__for_each_thread(m, show_thread_runtime, &totals); @@ -3157,16 +3277,17 @@ static int __cmd_record(int argc, const char **argv) BUG_ON(i != rec_argc); - return cmd_record(i, rec_argv, NULL); + return cmd_record(i, rec_argv); } -int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused) +int cmd_sched(int argc, const char **argv) { const char default_sort_order[] = "avg, max, switch, runtime"; struct perf_sched sched = { .tool = { .sample = perf_sched__process_tracepoint_sample, .comm = perf_event__process_comm, + .namespaces = perf_event__process_namespaces, .lost = perf_event__process_lost, .fork = perf_sched__process_fork_event, .ordered_events = true, @@ -3235,11 +3356,13 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused) OPT_BOOLEAN('S', "with-summary", &sched.summary, "Show all syscalls and summary with statistics"), OPT_BOOLEAN('w', "wakeups", &sched.show_wakeups, "Show wakeup events"), + OPT_BOOLEAN('n', "next", &sched.show_next, "Show next task"), OPT_BOOLEAN('M', "migrations", &sched.show_migrations, "Show migration events"), OPT_BOOLEAN('V', "cpu-visual", &sched.show_cpu_visual, "Add CPU visual"), OPT_BOOLEAN('I', "idle-hist", &sched.idle_hist, "Show idle events only"), OPT_STRING(0, "time", &sched.time_str, "str", "Time span for analysis (start,stop)"), + OPT_BOOLEAN(0, "state", &sched.show_state, "Show task state when sched-out"), OPT_PARENT(sched_options) }; @@ -3294,7 +3417,7 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused) * Aliased to 'perf script' for now: */ if (!strcmp(argv[0], "script")) - return cmd_script(argc, argv, prefix); + return cmd_script(argc, argv); if (!strncmp(argv[0], "rec", 3)) { return __cmd_record(argc, argv); @@ -3331,10 +3454,14 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused) if (argc) usage_with_options(timehist_usage, timehist_options); } - if (sched.show_wakeups && sched.summary_only) { - pr_err(" Error: -s and -w are mutually exclusive.\n"); + if ((sched.show_wakeups || sched.show_next) && + sched.summary_only) { + pr_err(" Error: -s and -[n|w] are mutually exclusive.\n"); parse_options_usage(timehist_usage, timehist_options, "s", true); - parse_options_usage(NULL, timehist_options, "w", true); + if (sched.show_wakeups) + parse_options_usage(NULL, timehist_options, "w", true); + if (sched.show_next) + parse_options_usage(NULL, timehist_options, "n", true); return -EINVAL; } diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 2f3ff69fc4e7..d05aec491cff 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -21,13 +21,27 @@ #include "util/cpumap.h" #include "util/thread_map.h" #include "util/stat.h" +#include "util/string2.h" #include "util/thread-stack.h" #include "util/time-utils.h" +#include "print_binary.h" #include <linux/bitmap.h> +#include <linux/kernel.h> #include <linux/stringify.h> #include <linux/time64.h> #include "asm/bug.h" #include "util/mem-events.h" +#include "util/dump-insn.h" +#include <dirent.h> +#include <errno.h> +#include <inttypes.h> +#include <signal.h> +#include <sys/param.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> + +#include "sane_ctype.h" static char const *script_name; static char const *generate_script_lang; @@ -42,6 +56,7 @@ static bool nanosecs; static const char *cpu_list; static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); static struct perf_stat_config stat_config; +static int max_blocks; unsigned int scripting_max_stack = PERF_MAX_STACK_DEPTH; @@ -69,6 +84,7 @@ enum perf_output_field { PERF_OUTPUT_CALLINDENT = 1U << 20, PERF_OUTPUT_INSN = 1U << 21, PERF_OUTPUT_INSNLEN = 1U << 22, + PERF_OUTPUT_BRSTACKINSN = 1U << 23, }; struct output_option { @@ -98,6 +114,7 @@ struct output_option { {.str = "callindent", .field = PERF_OUTPUT_CALLINDENT}, {.str = "insn", .field = PERF_OUTPUT_INSN}, {.str = "insnlen", .field = PERF_OUTPUT_INSNLEN}, + {.str = "brstackinsn", .field = PERF_OUTPUT_BRSTACKINSN}, }; /* default set to maintain compatibility with current format */ @@ -292,7 +309,13 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel, "selected. Hence, no address to lookup the source line number.\n"); return -EINVAL; } - + if (PRINT_FIELD(BRSTACKINSN) && + !(perf_evlist__combined_branch_type(session->evlist) & + PERF_SAMPLE_BRANCH_ANY)) { + pr_err("Display of branch stack assembler requested, but non all-branch filter set\n" + "Hint: run 'perf record -b ...'\n"); + return -EINVAL; + } if ((PRINT_FIELD(PID) || PRINT_FIELD(TID)) && perf_evsel__check_stype(evsel, PERF_SAMPLE_TID, "TID", PERF_OUTPUT_TID|PERF_OUTPUT_PID)) @@ -546,6 +569,233 @@ static void print_sample_brstacksym(struct perf_sample *sample, } } +#define MAXBB 16384UL + +static int grab_bb(u8 *buffer, u64 start, u64 end, + struct machine *machine, struct thread *thread, + bool *is64bit, u8 *cpumode, bool last) +{ + long offset, len; + struct addr_location al; + bool kernel; + + if (!start || !end) + return 0; + + kernel = machine__kernel_ip(machine, start); + if (kernel) + *cpumode = PERF_RECORD_MISC_KERNEL; + else + *cpumode = PERF_RECORD_MISC_USER; + + /* + * Block overlaps between kernel and user. + * This can happen due to ring filtering + * On Intel CPUs the entry into the kernel is filtered, + * but the exit is not. Let the caller patch it up. + */ + if (kernel != machine__kernel_ip(machine, end)) { + printf("\tblock %" PRIx64 "-%" PRIx64 " transfers between kernel and user\n", + start, end); + return -ENXIO; + } + + memset(&al, 0, sizeof(al)); + if (end - start > MAXBB - MAXINSN) { + if (last) + printf("\tbrstack does not reach to final jump (%" PRIx64 "-%" PRIx64 ")\n", start, end); + else + printf("\tblock %" PRIx64 "-%" PRIx64 " (%" PRIu64 ") too long to dump\n", start, end, end - start); + return 0; + } + + thread__find_addr_map(thread, *cpumode, MAP__FUNCTION, start, &al); + if (!al.map || !al.map->dso) { + printf("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n", start, end); + return 0; + } + if (al.map->dso->data.status == DSO_DATA_STATUS_ERROR) { + printf("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n", start, end); + return 0; + } + + /* Load maps to ensure dso->is_64_bit has been updated */ + map__load(al.map); + + offset = al.map->map_ip(al.map, start); + len = dso__data_read_offset(al.map->dso, machine, offset, (u8 *)buffer, + end - start + MAXINSN); + + *is64bit = al.map->dso->is_64_bit; + if (len <= 0) + printf("\tcannot fetch code for block at %" PRIx64 "-%" PRIx64 "\n", + start, end); + return len; +} + +static void print_jump(uint64_t ip, struct branch_entry *en, + struct perf_insn *x, u8 *inbuf, int len, + int insn) +{ + printf("\t%016" PRIx64 "\t%-30s\t#%s%s%s%s", + ip, + dump_insn(x, ip, inbuf, len, NULL), + en->flags.predicted ? " PRED" : "", + en->flags.mispred ? " MISPRED" : "", + en->flags.in_tx ? " INTX" : "", + en->flags.abort ? " ABORT" : ""); + if (en->flags.cycles) { + printf(" %d cycles", en->flags.cycles); + if (insn) + printf(" %.2f IPC", (float)insn / en->flags.cycles); + } + putchar('\n'); +} + +static void print_ip_sym(struct thread *thread, u8 cpumode, int cpu, + uint64_t addr, struct symbol **lastsym, + struct perf_event_attr *attr) +{ + struct addr_location al; + int off; + + memset(&al, 0, sizeof(al)); + + thread__find_addr_map(thread, cpumode, MAP__FUNCTION, addr, &al); + if (!al.map) + thread__find_addr_map(thread, cpumode, MAP__VARIABLE, + addr, &al); + if ((*lastsym) && al.addr >= (*lastsym)->start && al.addr < (*lastsym)->end) + return; + + al.cpu = cpu; + al.sym = NULL; + if (al.map) + al.sym = map__find_symbol(al.map, al.addr); + + if (!al.sym) + return; + + if (al.addr < al.sym->end) + off = al.addr - al.sym->start; + else + off = al.addr - al.map->start - al.sym->start; + printf("\t%s", al.sym->name); + if (off) + printf("%+d", off); + putchar(':'); + if (PRINT_FIELD(SRCLINE)) + map__fprintf_srcline(al.map, al.addr, "\t", stdout); + putchar('\n'); + *lastsym = al.sym; +} + +static void print_sample_brstackinsn(struct perf_sample *sample, + struct thread *thread, + struct perf_event_attr *attr, + struct machine *machine) +{ + struct branch_stack *br = sample->branch_stack; + u64 start, end; + int i, insn, len, nr, ilen; + struct perf_insn x; + u8 buffer[MAXBB]; + unsigned off; + struct symbol *lastsym = NULL; + + if (!(br && br->nr)) + return; + nr = br->nr; + if (max_blocks && nr > max_blocks + 1) + nr = max_blocks + 1; + + x.thread = thread; + x.cpu = sample->cpu; + + putchar('\n'); + + /* Handle first from jump, of which we don't know the entry. */ + len = grab_bb(buffer, br->entries[nr-1].from, + br->entries[nr-1].from, + machine, thread, &x.is64bit, &x.cpumode, false); + if (len > 0) { + print_ip_sym(thread, x.cpumode, x.cpu, + br->entries[nr - 1].from, &lastsym, attr); + print_jump(br->entries[nr - 1].from, &br->entries[nr - 1], + &x, buffer, len, 0); + } + + /* Print all blocks */ + for (i = nr - 2; i >= 0; i--) { + if (br->entries[i].from || br->entries[i].to) + pr_debug("%d: %" PRIx64 "-%" PRIx64 "\n", i, + br->entries[i].from, + br->entries[i].to); + start = br->entries[i + 1].to; + end = br->entries[i].from; + + len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, false); + /* Patch up missing kernel transfers due to ring filters */ + if (len == -ENXIO && i > 0) { + end = br->entries[--i].from; + pr_debug("\tpatching up to %" PRIx64 "-%" PRIx64 "\n", start, end); + len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, false); + } + if (len <= 0) + continue; + + insn = 0; + for (off = 0;; off += ilen) { + uint64_t ip = start + off; + + print_ip_sym(thread, x.cpumode, x.cpu, ip, &lastsym, attr); + if (ip == end) { + print_jump(ip, &br->entries[i], &x, buffer + off, len - off, insn); + break; + } else { + printf("\t%016" PRIx64 "\t%s\n", ip, + dump_insn(&x, ip, buffer + off, len - off, &ilen)); + if (ilen == 0) + break; + insn++; + } + } + } + + /* + * Hit the branch? In this case we are already done, and the target + * has not been executed yet. + */ + if (br->entries[0].from == sample->ip) + return; + if (br->entries[0].flags.abort) + return; + + /* + * Print final block upto sample + */ + start = br->entries[0].to; + end = sample->ip; + len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, true); + print_ip_sym(thread, x.cpumode, x.cpu, start, &lastsym, attr); + if (len <= 0) { + /* Print at least last IP if basic block did not work */ + len = grab_bb(buffer, sample->ip, sample->ip, + machine, thread, &x.is64bit, &x.cpumode, false); + if (len <= 0) + return; + + printf("\t%016" PRIx64 "\t%s\n", sample->ip, + dump_insn(&x, sample->ip, buffer, len, NULL)); + return; + } + for (off = 0; off <= end - start; off += ilen) { + printf("\t%016" PRIx64 "\t%s\n", start + off, + dump_insn(&x, start + off, buffer + off, len - off, &ilen)); + if (ilen == 0) + break; + } +} static void print_sample_addr(struct perf_sample *sample, struct thread *thread, @@ -632,7 +882,9 @@ static void print_sample_callindent(struct perf_sample *sample, } static void print_insn(struct perf_sample *sample, - struct perf_event_attr *attr) + struct perf_event_attr *attr, + struct thread *thread, + struct machine *machine) { if (PRINT_FIELD(INSNLEN)) printf(" ilen: %d", sample->insn_len); @@ -643,12 +895,15 @@ static void print_insn(struct perf_sample *sample, for (i = 0; i < sample->insn_len; i++) printf(" %02x", (unsigned char)sample->insn[i]); } + if (PRINT_FIELD(BRSTACKINSN)) + print_sample_brstackinsn(sample, thread, attr, machine); } static void print_sample_bts(struct perf_sample *sample, struct perf_evsel *evsel, struct thread *thread, - struct addr_location *al) + struct addr_location *al, + struct machine *machine) { struct perf_event_attr *attr = &evsel->attr; bool print_srcline_last = false; @@ -689,7 +944,7 @@ static void print_sample_bts(struct perf_sample *sample, if (print_srcline_last) map__fprintf_srcline(al->map, al->addr, "\n ", stdout); - print_insn(sample, attr); + print_insn(sample, attr, thread, machine); printf("\n"); } @@ -830,6 +1085,7 @@ struct perf_script { bool show_task_events; bool show_mmap_events; bool show_switch_events; + bool show_namespace_events; bool allocated; struct cpu_map *cpus; struct thread_map *threads; @@ -871,7 +1127,8 @@ static size_t data_src__printf(u64 data_src) static void process_event(struct perf_script *script, struct perf_sample *sample, struct perf_evsel *evsel, - struct addr_location *al) + struct addr_location *al, + struct machine *machine) { struct thread *thread = al->thread; struct perf_event_attr *attr = &evsel->attr; @@ -898,7 +1155,7 @@ static void process_event(struct perf_script *script, print_sample_flags(sample->flags); if (is_bts_event(attr)) { - print_sample_bts(sample, evsel, thread, al); + print_sample_bts(sample, evsel, thread, al, machine); return; } @@ -936,7 +1193,7 @@ static void process_event(struct perf_script *script, if (perf_evsel__is_bpf_output(evsel) && PRINT_FIELD(BPF_OUTPUT)) print_sample_bpf_output(sample); - print_insn(sample, attr); + print_insn(sample, attr, thread, machine); printf("\n"); } @@ -1046,7 +1303,7 @@ static int process_sample_event(struct perf_tool *tool, if (scripting_ops) scripting_ops->process_event(event, sample, evsel, &al); else - process_event(scr, sample, evsel, &al); + process_event(scr, sample, evsel, &al, machine); out_put: addr_location__put(&al); @@ -1118,6 +1375,41 @@ out: return ret; } +static int process_namespaces_event(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + struct thread *thread; + struct perf_script *script = container_of(tool, struct perf_script, tool); + struct perf_session *session = script->session; + struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); + int ret = -1; + + thread = machine__findnew_thread(machine, event->namespaces.pid, + event->namespaces.tid); + if (thread == NULL) { + pr_debug("problem processing NAMESPACES event, skipping it.\n"); + return -1; + } + + if (perf_event__process_namespaces(tool, event, sample, machine) < 0) + goto out; + + if (!evsel->attr.sample_id_all) { + sample->cpu = 0; + sample->time = 0; + sample->tid = event->namespaces.tid; + sample->pid = event->namespaces.pid; + } + print_sample_start(sample, thread, evsel); + perf_event__fprintf(event, stdout); + ret = 0; +out: + thread__put(thread); + return ret; +} + static int process_fork_event(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -1293,6 +1585,8 @@ static int __cmd_script(struct perf_script *script) } if (script->show_switch_events) script->tool.context_switch = process_switch_event; + if (script->show_namespace_events) + script->tool.namespaces = process_namespaces_event; ret = perf_session__process_events(script->session); @@ -1427,7 +1721,7 @@ static int parse_scriptname(const struct option *opt __maybe_unused, static int parse_output_fields(const struct option *opt __maybe_unused, const char *arg, int unset __maybe_unused) { - char *tok; + char *tok, *strtok_saveptr = NULL; int i, imax = ARRAY_SIZE(all_output_options); int j; int rc = 0; @@ -1488,7 +1782,7 @@ static int parse_output_fields(const struct option *opt __maybe_unused, } } - for (tok = strtok(tok, ","); tok; tok = strtok(NULL, ",")) { + for (tok = strtok_r(tok, ",", &strtok_saveptr); tok; tok = strtok_r(NULL, ",", &strtok_saveptr)) { for (i = 0; i < imax; ++i) { if (strcmp(tok, all_output_options[i].str) == 0) break; @@ -2078,7 +2372,7 @@ int process_cpu_map_event(struct perf_tool *tool __maybe_unused, return set_maps(script); } -int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) +int cmd_script(int argc, const char **argv) { bool show_full_info = false; bool header = false; @@ -2097,6 +2391,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) .mmap = perf_event__process_mmap, .mmap2 = perf_event__process_mmap2, .comm = perf_event__process_comm, + .namespaces = perf_event__process_namespaces, .exit = perf_event__process_exit, .fork = perf_event__process_fork, .attr = process_attr, @@ -2152,7 +2447,8 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) "Valid types: hw,sw,trace,raw. " "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso," "addr,symoff,period,iregs,brstack,brstacksym,flags," - "bpf-output,callindent,insn,insnlen", parse_output_fields), + "bpf-output,callindent,insn,insnlen,brstackinsn", + parse_output_fields), OPT_BOOLEAN('a', "all-cpus", &system_wide, "system-wide collection from all CPUs"), OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]", @@ -2180,7 +2476,11 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) "Show the mmap events"), OPT_BOOLEAN('\0', "show-switch-events", &script.show_switch_events, "Show context switch events (if recorded)"), - OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"), + OPT_BOOLEAN('\0', "show-namespace-events", &script.show_namespace_events, + "Show namespace events (if recorded)"), + OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"), + OPT_INTEGER(0, "max-blocks", &max_blocks, + "Maximum number of code blocks to dump with brstackinsn"), OPT_BOOLEAN(0, "ns", &nanosecs, "Use 9 decimal places when displaying time"), OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts", @@ -2212,11 +2512,12 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) PARSE_OPT_STOP_AT_NON_OPTION); file.path = input_name; + file.force = symbol_conf.force; if (argc > 1 && !strncmp(argv[0], "rec", strlen("rec"))) { rec_script_path = get_script_path(argv[1], RECORD_SUFFIX); if (!rec_script_path) - return cmd_record(argc, argv, NULL); + return cmd_record(argc, argv); } if (argc > 1 && !strncmp(argv[0], "rep", strlen("rep"))) { diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index a02f2e965628..a935b5023732 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -64,14 +64,24 @@ #include "util/session.h" #include "util/tool.h" #include "util/group.h" +#include "util/string2.h" #include "asm/bug.h" #include <linux/time64.h> #include <api/fs/fs.h> +#include <errno.h> +#include <signal.h> #include <stdlib.h> #include <sys/prctl.h> +#include <inttypes.h> #include <locale.h> #include <math.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <sys/wait.h> +#include <unistd.h> + +#include "sane_ctype.h" #define DEFAULT_SEPARATOR " " #define CNTR_NOT_SUPPORTED "<not supported>" @@ -140,12 +150,14 @@ static unsigned int unit_width = 4; /* strlen("unit") */ static bool forever = false; static bool metric_only = false; static bool force_metric_only = false; +static bool no_merge = false; static struct timespec ref_time; static struct cpu_map *aggr_map; static aggr_get_id_t aggr_get_id; static bool append_file; static const char *output_name; static int output_fd; +static int print_free_counters_hint; struct perf_stat { bool record; @@ -310,8 +322,12 @@ static int read_counter(struct perf_evsel *counter) struct perf_counts_values *count; count = perf_counts(counter->counts, cpu, thread); - if (perf_evsel__read(counter, cpu, thread, count)) + if (perf_evsel__read(counter, cpu, thread, count)) { + counter->counts->scaled = -1; + perf_counts(counter->counts, cpu, thread)->ena = 0; + perf_counts(counter->counts, cpu, thread)->run = 0; return -1; + } if (STAT_RECORD) { if (perf_evsel__write_stat_event(counter, cpu, thread, count)) { @@ -336,12 +352,14 @@ static int read_counter(struct perf_evsel *counter) static void read_counters(void) { struct perf_evsel *counter; + int ret; evlist__for_each_entry(evsel_list, counter) { - if (read_counter(counter)) + ret = read_counter(counter); + if (ret) pr_debug("failed to read counter %s\n", counter->name); - if (perf_stat_process_counter(&stat_config, counter)) + if (ret == 0 && perf_stat_process_counter(&stat_config, counter)) pr_warning("failed to process counter %s\n", counter->name); } } @@ -533,7 +551,7 @@ static int store_counter_ids(struct perf_evsel *counter) static int __run_perf_stat(int argc, const char **argv) { int interval = stat_config.interval; - char msg[512]; + char msg[BUFSIZ]; unsigned long long t0, t1; struct perf_evsel *counter; struct timespec ts; @@ -573,7 +591,7 @@ try_again: if (errno == EINVAL || errno == ENOSYS || errno == ENOENT || errno == EOPNOTSUPP || errno == ENXIO) { - if (verbose) + if (verbose > 0) ui__warning("%s event is not supported by the kernel.\n", perf_evsel__name(counter)); counter->supported = false; @@ -582,7 +600,7 @@ try_again: !(counter->leader->nr_members > 1)) continue; } else if (perf_evsel__fallback(counter, errno, msg, sizeof(msg))) { - if (verbose) + if (verbose > 0) ui__warning("%s\n", msg); goto try_again; } @@ -873,10 +891,7 @@ static void print_metric_csv(void *ctx, return; } snprintf(buf, sizeof(buf), fmt, val); - vals = buf; - while (isspace(*vals)) - vals++; - ends = vals; + ends = vals = ltrim(buf); while (isdigit(*ends) || *ends == '.') ends++; *ends = 0; @@ -948,10 +963,7 @@ static void print_metric_only_csv(void *ctx, const char *color __maybe_unused, return; unit = fixunit(tbuf, os->evsel, unit); snprintf(buf, sizeof buf, fmt, val); - vals = buf; - while (isspace(*vals)) - vals++; - ends = vals; + ends = vals = ltrim(buf); while (isdigit(*ends) || *ends == '.') ends++; *ends = 0; @@ -1109,6 +1121,9 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval, counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED, csv_sep); + if (counter->supported) + print_free_counters_hint = 1; + fprintf(stat_config.output, "%-*s%s", csv_output ? 0 : unit_width, counter->unit, csv_sep); @@ -1140,6 +1155,7 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval, out.print_metric = pm; out.new_line = nl; out.ctx = &os; + out.force_header = false; if (csv_output && !metric_only) { print_noise(counter, noise); @@ -1178,11 +1194,81 @@ static void aggr_update_shadow(void) } } +static void collect_all_aliases(struct perf_evsel *counter, + void (*cb)(struct perf_evsel *counter, void *data, + bool first), + void *data) +{ + struct perf_evsel *alias; + + alias = list_prepare_entry(counter, &(evsel_list->entries), node); + list_for_each_entry_continue (alias, &evsel_list->entries, node) { + if (strcmp(perf_evsel__name(alias), perf_evsel__name(counter)) || + alias->scale != counter->scale || + alias->cgrp != counter->cgrp || + strcmp(alias->unit, counter->unit) || + nsec_counter(alias) != nsec_counter(counter)) + break; + alias->merged_stat = true; + cb(alias, data, false); + } +} + +static bool collect_data(struct perf_evsel *counter, + void (*cb)(struct perf_evsel *counter, void *data, + bool first), + void *data) +{ + if (counter->merged_stat) + return false; + cb(counter, data, true); + if (!no_merge) + collect_all_aliases(counter, cb, data); + return true; +} + +struct aggr_data { + u64 ena, run, val; + int id; + int nr; + int cpu; +}; + +static void aggr_cb(struct perf_evsel *counter, void *data, bool first) +{ + struct aggr_data *ad = data; + int cpu, s2; + + for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) { + struct perf_counts_values *counts; + + s2 = aggr_get_id(perf_evsel__cpus(counter), cpu); + if (s2 != ad->id) + continue; + if (first) + ad->nr++; + counts = perf_counts(counter->counts, cpu, 0); + /* + * When any result is bad, make them all to give + * consistent output in interval mode. + */ + if (counts->ena == 0 || counts->run == 0 || + counter->counts->scaled == -1) { + ad->ena = 0; + ad->run = 0; + break; + } + ad->val += counts->val; + ad->ena += counts->ena; + ad->run += counts->run; + } +} + static void print_aggr(char *prefix) { FILE *output = stat_config.output; struct perf_evsel *counter; - int cpu, s, s2, id, nr; + int s, id, nr; double uval; u64 ena, run, val; bool first; @@ -1197,23 +1283,21 @@ static void print_aggr(char *prefix) * Without each counter has its own line. */ for (s = 0; s < aggr_map->nr; s++) { + struct aggr_data ad; if (prefix && metric_only) fprintf(output, "%s", prefix); - id = aggr_map->map[s]; + ad.id = id = aggr_map->map[s]; first = true; evlist__for_each_entry(evsel_list, counter) { - val = ena = run = 0; - nr = 0; - for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) { - s2 = aggr_get_id(perf_evsel__cpus(counter), cpu); - if (s2 != id) - continue; - val += perf_counts(counter->counts, cpu, 0)->val; - ena += perf_counts(counter->counts, cpu, 0)->ena; - run += perf_counts(counter->counts, cpu, 0)->run; - nr++; - } + ad.val = ad.ena = ad.run = 0; + ad.nr = 0; + if (!collect_data(counter, aggr_cb, &ad)) + continue; + nr = ad.nr; + ena = ad.ena; + run = ad.run; + val = ad.val; if (first && metric_only) { first = false; aggr_printout(counter, id, nr); @@ -1257,6 +1341,21 @@ static void print_aggr_thread(struct perf_evsel *counter, char *prefix) } } +struct caggr_data { + double avg, avg_enabled, avg_running; +}; + +static void counter_aggr_cb(struct perf_evsel *counter, void *data, + bool first __maybe_unused) +{ + struct caggr_data *cd = data; + struct perf_stat_evsel *ps = counter->priv; + + cd->avg += avg_stats(&ps->res_stats[0]); + cd->avg_enabled += avg_stats(&ps->res_stats[1]); + cd->avg_running += avg_stats(&ps->res_stats[2]); +} + /* * Print out the results of a single counter: * aggregated counts in system-wide mode @@ -1264,23 +1363,31 @@ static void print_aggr_thread(struct perf_evsel *counter, char *prefix) static void print_counter_aggr(struct perf_evsel *counter, char *prefix) { FILE *output = stat_config.output; - struct perf_stat_evsel *ps = counter->priv; - double avg = avg_stats(&ps->res_stats[0]); double uval; - double avg_enabled, avg_running; + struct caggr_data cd = { .avg = 0.0 }; - avg_enabled = avg_stats(&ps->res_stats[1]); - avg_running = avg_stats(&ps->res_stats[2]); + if (!collect_data(counter, counter_aggr_cb, &cd)) + return; if (prefix && !metric_only) fprintf(output, "%s", prefix); - uval = avg * counter->scale; - printout(-1, 0, counter, uval, prefix, avg_running, avg_enabled, avg); + uval = cd.avg * counter->scale; + printout(-1, 0, counter, uval, prefix, cd.avg_running, cd.avg_enabled, cd.avg); if (!metric_only) fprintf(output, "\n"); } +static void counter_cb(struct perf_evsel *counter, void *data, + bool first __maybe_unused) +{ + struct aggr_data *ad = data; + + ad->val += perf_counts(counter->counts, ad->cpu, 0)->val; + ad->ena += perf_counts(counter->counts, ad->cpu, 0)->ena; + ad->run += perf_counts(counter->counts, ad->cpu, 0)->run; +} + /* * Print out the results of a single counter: * does not use aggregated count in system-wide @@ -1293,9 +1400,13 @@ static void print_counter(struct perf_evsel *counter, char *prefix) int cpu; for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) { - val = perf_counts(counter->counts, cpu, 0)->val; - ena = perf_counts(counter->counts, cpu, 0)->ena; - run = perf_counts(counter->counts, cpu, 0)->run; + struct aggr_data ad = { .cpu = cpu }; + + if (!collect_data(counter, counter_cb, &ad)) + return; + val = ad.val; + ena = ad.ena; + run = ad.run; if (prefix) fprintf(output, "%s", prefix); @@ -1380,6 +1491,7 @@ static void print_metric_headers(const char *prefix, bool no_indent) out.ctx = &os; out.print_metric = print_metric_header; out.new_line = new_line_metric; + out.force_header = true; os.evsel = counter; perf_stat__print_shadow_stats(counter, 0, 0, @@ -1477,6 +1589,13 @@ static void print_footer(void) avg_stats(&walltime_nsecs_stats)); } fprintf(output, "\n\n"); + + if (print_free_counters_hint) + fprintf(output, +"Some events weren't counted. Try disabling the NMI watchdog:\n" +" echo 0 > /proc/sys/kernel/nmi_watchdog\n" +" perf stat ...\n" +" echo 1 > /proc/sys/kernel/nmi_watchdog\n"); } static void print_counters(struct timespec *ts, int argc, const char **argv) @@ -1633,6 +1752,7 @@ static const struct option stat_options[] = { "list of cpus to monitor in system-wide"), OPT_SET_UINT('A', "no-aggr", &stat_config.aggr_mode, "disable CPU count aggregation", AGGR_NONE), + OPT_BOOLEAN(0, "no-merge", &no_merge, "Do not merge identical named events"), OPT_STRING('x', "field-separator", &csv_sep, "separator", "print counts with custom separator"), OPT_CALLBACK('G', "cgroup", &evsel_list, "name", @@ -1765,7 +1885,7 @@ static inline int perf_env__get_cpu(struct perf_env *env, struct cpu_map *map, i cpu = map->map[idx]; - if (cpu >= env->nr_cpus_online) + if (cpu >= env->nr_cpus_avail) return -1; return cpu; @@ -2339,7 +2459,36 @@ static int __cmd_report(int argc, const char **argv) return 0; } -int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) +static void setup_system_wide(int forks) +{ + /* + * Make system wide (-a) the default target if + * no target was specified and one of following + * conditions is met: + * + * - there's no workload specified + * - there is workload specified but all requested + * events are system wide events + */ + if (!target__none(&target)) + return; + + if (!forks) + target.system_wide = true; + else { + struct perf_evsel *counter; + + evlist__for_each_entry(evsel_list, counter) { + if (!counter->system_wide) + return; + } + + if (evsel_list->nr_entries) + target.system_wide = true; + } +} + +int cmd_stat(int argc, const char **argv) { const char * const stat_usage[] = { "perf stat [<options>] [<command>]", @@ -2361,6 +2510,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) argc = parse_options_subcommand(argc, argv, stat_options, stat_subcommands, (const char **) stat_usage, PARSE_OPT_STOP_AT_NON_OPTION); + perf_stat__collect_metric_expr(evsel_list); perf_stat__init_shadow_stats(); if (csv_sep) { @@ -2445,8 +2595,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) } else if (big_num_opt == 0) /* User passed --no-big-num */ big_num = false; - if (!argc && target__none(&target)) - usage_with_options(stat_usage, stat_options); + setup_system_wide(argc); if (run_count < 0) { pr_err("Run count must be a positive number\n"); @@ -2538,7 +2687,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) status = 0; for (run_idx = 0; forever || run_idx < run_count; run_idx++) { - if (run_count != 1 && verbose) + if (run_count != 1 && verbose > 0) fprintf(output, "[ perf stat: executing run #%d ... ]\n", run_idx + 1); diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c index e7eaa298d34a..4e2e61695986 100644 --- a/tools/perf/builtin-timechart.c +++ b/tools/perf/builtin-timechart.c @@ -12,6 +12,8 @@ * of the License. */ +#include <errno.h> +#include <inttypes.h> #include <traceevent/event-parse.h> #include "builtin.h" @@ -23,11 +25,12 @@ #include "util/cache.h" #include "util/evlist.h" #include "util/evsel.h" +#include <linux/kernel.h> #include <linux/rbtree.h> #include <linux/time64.h> #include "util/symbol.h" +#include "util/thread.h" #include "util/callchain.h" -#include "util/strlist.h" #include "perf.h" #include "util/header.h" @@ -1773,7 +1776,7 @@ static int timechart__io_record(int argc, const char **argv) for (i = 0; i < (unsigned int)argc; i++) *p++ = argv[i]; - return cmd_record(rec_argc, rec_argv, NULL); + return cmd_record(rec_argc, rec_argv); } @@ -1864,7 +1867,7 @@ static int timechart__record(struct timechart *tchart, int argc, const char **ar for (j = 0; j < (unsigned int)argc; j++) *p++ = argv[j]; - return cmd_record(rec_argc, rec_argv, NULL); + return cmd_record(rec_argc, rec_argv); } static int @@ -1917,8 +1920,7 @@ parse_time(const struct option *opt, const char *arg, int __maybe_unused unset) return 0; } -int cmd_timechart(int argc, const char **argv, - const char *prefix __maybe_unused) +int cmd_timechart(int argc, const char **argv) { struct timechart tchart = { .tool = { @@ -1933,6 +1935,11 @@ int cmd_timechart(int argc, const char **argv, .merge_dist = 1000, }; const char *output_name = "output.svg"; + const struct option timechart_common_options[] = { + OPT_BOOLEAN('P', "power-only", &tchart.power_only, "output power data only"), + OPT_BOOLEAN('T', "tasks-only", &tchart.tasks_only, "output processes data only"), + OPT_END() + }; const struct option timechart_options[] = { OPT_STRING('i', "input", &input_name, "file", "input file name"), OPT_STRING('o', "output", &output_name, "file", "output file name"), @@ -1940,9 +1947,6 @@ int cmd_timechart(int argc, const char **argv, OPT_CALLBACK(0, "highlight", NULL, "duration or task name", "highlight tasks. Pass duration in ns or process name.", parse_highlight), - OPT_BOOLEAN('P', "power-only", &tchart.power_only, "output power data only"), - OPT_BOOLEAN('T', "tasks-only", &tchart.tasks_only, - "output processes data only"), OPT_CALLBACK('p', "process", NULL, "process", "process selector. Pass a pid or process name.", parse_process), @@ -1962,22 +1966,18 @@ int cmd_timechart(int argc, const char **argv, "merge events that are merge-dist us apart", parse_time), OPT_BOOLEAN('f', "force", &tchart.force, "don't complain, do it"), - OPT_END() + OPT_PARENT(timechart_common_options), }; const char * const timechart_subcommands[] = { "record", NULL }; const char *timechart_usage[] = { "perf timechart [<options>] {record}", NULL }; - const struct option timechart_record_options[] = { - OPT_BOOLEAN('P', "power-only", &tchart.power_only, "output power data only"), - OPT_BOOLEAN('T', "tasks-only", &tchart.tasks_only, - "output processes data only"), OPT_BOOLEAN('I', "io-only", &tchart.io_only, "record only IO data"), OPT_BOOLEAN('g', "callchain", &tchart.with_backtrace, "record callchain"), - OPT_END() + OPT_PARENT(timechart_common_options), }; const char * const timechart_record_usage[] = { "perf timechart record [<options>]", diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 3df4178ba378..10b6362ca0bf 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -27,19 +27,20 @@ #include "util/drv_configs.h" #include "util/evlist.h" #include "util/evsel.h" +#include "util/event.h" #include "util/machine.h" #include "util/session.h" #include "util/symbol.h" #include "util/thread.h" #include "util/thread_map.h" #include "util/top.h" -#include "util/util.h" #include <linux/rbtree.h> #include <subcmd/parse-options.h> #include "util/parse-events.h" #include "util/cpumap.h" #include "util/xyarray.h" #include "util/sort.h" +#include "util/term.h" #include "util/intlist.h" #include "util/parse-branch-options.h" #include "arch/common.h" @@ -58,6 +59,7 @@ #include <errno.h> #include <time.h> #include <sched.h> +#include <signal.h> #include <sys/syscall.h> #include <sys/ioctl.h> @@ -72,6 +74,8 @@ #include <linux/time64.h> #include <linux/types.h> +#include "sane_ctype.h" + static volatile int done; #define HEADER_LINE_NR 5 @@ -643,7 +647,7 @@ repeat: case -1: if (errno == EINTR) continue; - /* Fall trhu */ + __fallthrough; default: c = getc(stdin); tcsetattr(0, TCSAFLUSH, &save); @@ -859,7 +863,7 @@ static void perf_top__mmap_read(struct perf_top *top) static int perf_top__start_counters(struct perf_top *top) { - char msg[512]; + char msg[BUFSIZ]; struct perf_evsel *counter; struct perf_evlist *evlist = top->evlist; struct record_opts *opts = &top->record_opts; @@ -871,7 +875,7 @@ try_again: if (perf_evsel__open(counter, top->evlist->cpus, top->evlist->threads) < 0) { if (perf_evsel__fallback(counter, errno, msg, sizeof(msg))) { - if (verbose) + if (verbose > 0) ui__warning("%s\n", msg); goto try_again; } @@ -1075,7 +1079,7 @@ parse_percent_limit(const struct option *opt, const char *arg, const char top_callchain_help[] = CALLCHAIN_RECORD_HELP CALLCHAIN_REPORT_HELP "\n\t\t\t\tDefault: fp,graph,0.5,caller,function"; -int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) +int cmd_top(int argc, const char **argv) { char errbuf[BUFSIZ]; struct perf_top top = { @@ -1216,7 +1220,9 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) if (top.evlist == NULL) return -ENOMEM; - perf_config(perf_top_config, &top); + status = perf_config(perf_top_config, &top); + if (status) + return status; argc = parse_options(argc, argv, options, top_usage, 0); if (argc) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 206bf72b77fc..d014350adc52 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -21,9 +21,11 @@ #include "builtin.h" #include "util/color.h" #include "util/debug.h" +#include "util/event.h" #include "util/evlist.h" #include <subcmd/exec-cmd.h> #include "util/machine.h" +#include "util/path.h" #include "util/session.h" #include "util/thread.h" #include <subcmd/parse-options.h> @@ -31,22 +33,33 @@ #include "util/intlist.h" #include "util/thread_map.h" #include "util/stat.h" +#include "trace/beauty/beauty.h" #include "trace-event.h" #include "util/parse-events.h" #include "util/bpf-loader.h" #include "callchain.h" +#include "print_binary.h" +#include "string2.h" #include "syscalltbl.h" #include "rb_resort.h" +#include <errno.h> +#include <inttypes.h> #include <libaudit.h> /* FIXME: Still needed for audit_errno_to_name */ +#include <poll.h> +#include <signal.h> #include <stdlib.h> +#include <string.h> #include <linux/err.h> #include <linux/filter.h> #include <linux/audit.h> +#include <linux/kernel.h> #include <linux/random.h> #include <linux/stringify.h> #include <linux/time64.h> +#include "sane_ctype.h" + #ifndef O_CLOEXEC # define O_CLOEXEC 02000000 #endif @@ -266,15 +279,6 @@ out_delete: ({ struct syscall_tp *fields = evsel->priv; \ fields->name.pointer(&fields->name, sample); }) -struct syscall_arg { - unsigned long val; - struct thread *thread; - struct trace *trace; - void *parm; - u8 idx; - u8 mask; -}; - struct strarray { int offset; int nr_entries; @@ -770,6 +774,10 @@ static struct syscall_fmt { .arg_parm = { [0] = &strarray__socket_families, /* family */ }, }, { .name = "stat", .errmsg = true, .alias = "newstat", }, { .name = "statfs", .errmsg = true, }, + { .name = "statx", .errmsg = true, + .arg_scnprintf = { [0] = SCA_FDAT, /* flags */ + [2] = SCA_STATX_FLAGS, /* flags */ + [3] = SCA_STATX_MASK, /* mask */ }, }, { .name = "swapoff", .errmsg = true, .arg_scnprintf = { [0] = SCA_FILENAME, /* specialfile */ }, }, { .name = "swapon", .errmsg = true, @@ -820,12 +828,21 @@ struct syscall { void **arg_parm; }; -static size_t fprintf_duration(unsigned long t, FILE *fp) +/* + * We need to have this 'calculated' boolean because in some cases we really + * don't know what is the duration of a syscall, for instance, when we start + * a session and some threads are waiting for a syscall to finish, say 'poll', + * in which case all we can do is to print "( ? ) for duration and for the + * start timestamp. + */ +static size_t fprintf_duration(unsigned long t, bool calculated, FILE *fp) { double duration = (double)t / NSEC_PER_MSEC; size_t printed = fprintf(fp, "("); - if (duration >= 1.0) + if (!calculated) + printed += fprintf(fp, " ? "); + else if (duration >= 1.0) printed += color_fprintf(fp, PERF_COLOR_RED, "%6.3f ms", duration); else if (duration >= 0.01) printed += color_fprintf(fp, PERF_COLOR_YELLOW, "%6.3f ms", duration); @@ -1027,13 +1044,27 @@ static bool trace__filter_duration(struct trace *trace, double t) return t < (trace->duration_filter * NSEC_PER_MSEC); } -static size_t trace__fprintf_tstamp(struct trace *trace, u64 tstamp, FILE *fp) +static size_t __trace__fprintf_tstamp(struct trace *trace, u64 tstamp, FILE *fp) { double ts = (double)(tstamp - trace->base_time) / NSEC_PER_MSEC; return fprintf(fp, "%10.3f ", ts); } +/* + * We're handling tstamp=0 as an undefined tstamp, i.e. like when we are + * using ttrace->entry_time for a thread that receives a sys_exit without + * first having received a sys_enter ("poll" issued before tracing session + * starts, lost sys_enter exit due to ring buffer overflow). + */ +static size_t trace__fprintf_tstamp(struct trace *trace, u64 tstamp, FILE *fp) +{ + if (tstamp > 0) + return __trace__fprintf_tstamp(trace, tstamp, fp); + + return fprintf(fp, " ? "); +} + static bool done = false; static bool interrupted = false; @@ -1044,10 +1075,10 @@ static void sig_handler(int sig) } static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thread, - u64 duration, u64 tstamp, FILE *fp) + u64 duration, bool duration_calculated, u64 tstamp, FILE *fp) { size_t printed = trace__fprintf_tstamp(trace, tstamp, fp); - printed += fprintf_duration(duration, fp); + printed += fprintf_duration(duration, duration_calculated, fp); if (trace->multiple_threads) { if (trace->show_comm) @@ -1398,7 +1429,7 @@ static struct syscall *trace__syscall_info(struct trace *trace, return &trace->syscalls.table[id]; out_cant_read: - if (verbose) { + if (verbose > 0) { fprintf(trace->output, "Problems reading syscall %d", id); if (id <= trace->syscalls.max && trace->syscalls.table[id].name != NULL) fprintf(trace->output, "(%s)", trace->syscalls.table[id].name); @@ -1449,7 +1480,7 @@ static int trace__printf_interrupted_entry(struct trace *trace, struct perf_samp duration = sample->time - ttrace->entry_time; - printed = trace__fprintf_entry_head(trace, trace->current, duration, ttrace->entry_time, trace->output); + printed = trace__fprintf_entry_head(trace, trace->current, duration, true, ttrace->entry_time, trace->output); printed += fprintf(trace->output, "%-70s) ...\n", ttrace->entry_str); ttrace->entry_pending = false; @@ -1496,7 +1527,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel, if (sc->is_exit) { if (!(trace->duration_filter || trace->summary_only || trace->min_stack)) { - trace__fprintf_entry_head(trace, thread, 1, ttrace->entry_time, trace->output); + trace__fprintf_entry_head(trace, thread, 0, false, ttrace->entry_time, trace->output); fprintf(trace->output, "%-70s)\n", ttrace->entry_str); } } else { @@ -1544,6 +1575,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel, { long ret; u64 duration = 0; + bool duration_calculated = false; struct thread *thread; int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1, callchain_ret = 0; struct syscall *sc = trace__syscall_info(trace, evsel, id); @@ -1572,6 +1604,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel, duration = sample->time - ttrace->entry_time; if (trace__filter_duration(trace, duration)) goto out; + duration_calculated = true; } else if (trace->duration_filter) goto out; @@ -1587,7 +1620,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel, if (trace->summary_only) goto out; - trace__fprintf_entry_head(trace, thread, duration, ttrace->entry_time, trace->output); + trace__fprintf_entry_head(trace, thread, duration, duration_calculated, ttrace->entry_time, trace->output); if (ttrace->entry_pending) { fprintf(trace->output, "%-70s", ttrace->entry_str); @@ -1652,15 +1685,17 @@ static int trace__vfs_getname(struct trace *trace, struct perf_evsel *evsel, ttrace = thread__priv(thread); if (!ttrace) - goto out; + goto out_put; filename_len = strlen(filename); + if (filename_len == 0) + goto out_put; if (ttrace->filename.namelen < filename_len) { char *f = realloc(ttrace->filename.name, filename_len + 1); if (f == NULL) - goto out; + goto out_put; ttrace->filename.namelen = filename_len; ttrace->filename.name = f; @@ -1670,12 +1705,12 @@ static int trace__vfs_getname(struct trace *trace, struct perf_evsel *evsel, ttrace->filename.pending_open = true; if (!ttrace->filename.ptr) - goto out; + goto out_put; entry_str_len = strlen(ttrace->entry_str); remaining_space = trace__entry_str_size - entry_str_len - 1; /* \0 */ if (remaining_space <= 0) - goto out; + goto out_put; if (filename_len > (size_t)remaining_space) { filename += filename_len - remaining_space; @@ -1689,6 +1724,8 @@ static int trace__vfs_getname(struct trace *trace, struct perf_evsel *evsel, ttrace->filename.ptr = 0; ttrace->filename.entry_str_pos = 0; +out_put: + thread__put(thread); out: return 0; } @@ -1709,6 +1746,7 @@ static int trace__sched_stat_runtime(struct trace *trace, struct perf_evsel *evs ttrace->runtime_ms += runtime_ms; trace->runtime_ms += runtime_ms; +out_put: thread__put(thread); return 0; @@ -1719,8 +1757,7 @@ out_dump: (pid_t)perf_evsel__intval(evsel, sample, "pid"), runtime, perf_evsel__intval(evsel, sample, "vruntime")); - thread__put(thread); - return 0; + goto out_put; } static void bpf_output__printer(enum binary_printer_ops op, @@ -1800,10 +1837,10 @@ static void print_location(FILE *f, struct perf_sample *sample, bool print_dso, bool print_sym) { - if ((verbose || print_dso) && al->map) + if ((verbose > 0 || print_dso) && al->map) fprintf(f, "%s@", al->map->dso->long_name); - if ((verbose || print_sym) && al->sym) + if ((verbose > 0 || print_sym) && al->sym) fprintf(f, "%s+0x%" PRIx64, al->sym->name, al->addr - al->sym->start); else if (al->map) @@ -1850,7 +1887,7 @@ static int trace__pgfault(struct trace *trace, thread__find_addr_location(thread, sample->cpumode, MAP__FUNCTION, sample->ip, &al); - trace__fprintf_entry_head(trace, thread, 0, sample->time, trace->output); + trace__fprintf_entry_head(trace, thread, 0, true, sample->time, trace->output); fprintf(trace->output, "%sfault [", evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ ? @@ -1919,7 +1956,7 @@ static int trace__process_sample(struct perf_tool *tool, thread = machine__findnew_thread(trace->host, sample->pid, sample->tid); if (thread && thread__is_filtered(thread)) - return 0; + goto out; trace__set_base_time(trace, evsel, sample); @@ -1927,7 +1964,8 @@ static int trace__process_sample(struct perf_tool *tool, ++trace->nr_events; handler(trace, evsel, event, sample); } - +out: + thread__put(thread); return err; } @@ -1987,7 +2025,7 @@ static int trace__record(struct trace *trace, int argc, const char **argv) for (i = 0; i < (unsigned int)argc; i++) rec_argv[j++] = argv[i]; - return cmd_record(j, rec_argv, NULL); + return cmd_record(j, rec_argv); } static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp); @@ -2414,8 +2452,9 @@ static int trace__replay(struct trace *trace) trace->tool.exit = perf_event__process_exit; trace->tool.fork = perf_event__process_fork; trace->tool.attr = perf_event__process_attr; - trace->tool.tracing_data = perf_event__process_tracing_data; + trace->tool.tracing_data = perf_event__process_tracing_data; trace->tool.build_id = perf_event__process_build_id; + trace->tool.namespaces = perf_event__process_namespaces; trace->tool.ordered_events = true; trace->tool.ordering_requires_timestamps = true; @@ -2699,7 +2738,92 @@ static void evlist__set_evsel_handler(struct perf_evlist *evlist, void *handler) evsel->handler = handler; } -int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) +/* + * XXX: Hackish, just splitting the combined -e+--event (syscalls + * (raw_syscalls:{sys_{enter,exit}} + events (tracepoints, HW, SW, etc) to use + * existing facilities unchanged (trace->ev_qualifier + parse_options()). + * + * It'd be better to introduce a parse_options() variant that would return a + * list with the terms it didn't match to an event... + */ +static int trace__parse_events_option(const struct option *opt, const char *str, + int unset __maybe_unused) +{ + struct trace *trace = (struct trace *)opt->value; + const char *s = str; + char *sep = NULL, *lists[2] = { NULL, NULL, }; + int len = strlen(str), err = -1, list; + char *strace_groups_dir = system_path(STRACE_GROUPS_DIR); + char group_name[PATH_MAX]; + + if (strace_groups_dir == NULL) + return -1; + + if (*s == '!') { + ++s; + trace->not_ev_qualifier = true; + } + + while (1) { + if ((sep = strchr(s, ',')) != NULL) + *sep = '\0'; + + list = 0; + if (syscalltbl__id(trace->sctbl, s) >= 0) { + list = 1; + } else { + path__join(group_name, sizeof(group_name), strace_groups_dir, s); + if (access(group_name, R_OK) == 0) + list = 1; + } + + if (lists[list]) { + sprintf(lists[list] + strlen(lists[list]), ",%s", s); + } else { + lists[list] = malloc(len); + if (lists[list] == NULL) + goto out; + strcpy(lists[list], s); + } + + if (!sep) + break; + + *sep = ','; + s = sep + 1; + } + + if (lists[1] != NULL) { + struct strlist_config slist_config = { + .dirname = strace_groups_dir, + }; + + trace->ev_qualifier = strlist__new(lists[1], &slist_config); + if (trace->ev_qualifier == NULL) { + fputs("Not enough memory to parse event qualifier", trace->output); + goto out; + } + + if (trace__validate_ev_qualifier(trace)) + goto out; + } + + err = 0; + + if (lists[0]) { + struct option o = OPT_CALLBACK('e', "event", &trace->evlist, "event", + "event selector. use 'perf list' to list available events", + parse_events_option); + err = parse_events_option(&o, lists[0], 0); + } +out: + if (sep) + *sep = ','; + + return err; +} + +int cmd_trace(int argc, const char **argv) { const char *trace_usage[] = { "perf trace [<options>] [<command>]", @@ -2730,15 +2854,15 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) .max_stack = UINT_MAX, }; const char *output_name = NULL; - const char *ev_qualifier_str = NULL; const struct option trace_options[] = { - OPT_CALLBACK(0, "event", &trace.evlist, "event", - "event selector. use 'perf list' to list available events", - parse_events_option), + OPT_CALLBACK('e', "event", &trace, "event", + "event/syscall selector. use 'perf list' to list available events", + trace__parse_events_option), OPT_BOOLEAN(0, "comm", &trace.show_comm, "show the thread COMM next to its id"), OPT_BOOLEAN(0, "tool_stats", &trace.show_tool_stats, "show tool stats"), - OPT_STRING('e', "expr", &ev_qualifier_str, "expr", "list of syscalls to trace"), + OPT_CALLBACK(0, "expr", &trace, "expr", "list of syscalls/events to trace", + trace__parse_events_option), OPT_STRING('o', "output", &output_name, "file", "output file name"), OPT_STRING('i', "input", &input_name, "file", "Analyze events in file"), OPT_STRING('p', "pid", &trace.opts.target.pid, "pid", @@ -2863,7 +2987,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) return -1; } - if (!trace.trace_syscalls && ev_qualifier_str) { + if (!trace.trace_syscalls && trace.ev_qualifier) { pr_err("The -e option can't be used with --no-syscalls.\n"); goto out; } @@ -2878,28 +3002,6 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused) trace.open_id = syscalltbl__id(trace.sctbl, "open"); - if (ev_qualifier_str != NULL) { - const char *s = ev_qualifier_str; - struct strlist_config slist_config = { - .dirname = system_path(STRACE_GROUPS_DIR), - }; - - trace.not_ev_qualifier = *s == '!'; - if (trace.not_ev_qualifier) - ++s; - trace.ev_qualifier = strlist__new(s, &slist_config); - if (trace.ev_qualifier == NULL) { - fputs("Not enough memory to parse event qualifier", - trace.output); - err = -ENOMEM; - goto out_close; - } - - err = trace__validate_ev_qualifier(&trace); - if (err) - goto out_close; - } - err = target__validate(&trace.opts.target); if (err) { target__strerror(&trace.opts.target, err, bf, sizeof(bf)); diff --git a/tools/perf/builtin-version.c b/tools/perf/builtin-version.c index 9b10cda6b6dc..d25149456a2f 100644 --- a/tools/perf/builtin-version.c +++ b/tools/perf/builtin-version.c @@ -1,9 +1,9 @@ -#include "util/util.h" #include "builtin.h" #include "perf.h" +#include <linux/compiler.h> +#include <stdio.h> -int cmd_version(int argc __maybe_unused, const char **argv __maybe_unused, - const char *prefix __maybe_unused) +int cmd_version(int argc __maybe_unused, const char **argv __maybe_unused) { printf("perf version %s\n", perf_version_string); return 0; diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h index 0bcf68e98ccc..d4d19fe3d050 100644 --- a/tools/perf/builtin.h +++ b/tools/perf/builtin.h @@ -2,44 +2,42 @@ #define BUILTIN_H #include "util/util.h" -#include "util/strbuf.h" extern const char perf_usage_string[]; extern const char perf_more_info_string[]; void list_common_cmds_help(void); const char *help_unknown_cmd(const char *cmd); -void prune_packed_objects(int); -int read_line_with_nul(char *buf, int size, FILE *file); -int check_pager_config(const char *cmd); -int cmd_annotate(int argc, const char **argv, const char *prefix); -int cmd_bench(int argc, const char **argv, const char *prefix); -int cmd_buildid_cache(int argc, const char **argv, const char *prefix); -int cmd_buildid_list(int argc, const char **argv, const char *prefix); -int cmd_config(int argc, const char **argv, const char *prefix); -int cmd_c2c(int argc, const char **argv, const char *prefix); -int cmd_diff(int argc, const char **argv, const char *prefix); -int cmd_evlist(int argc, const char **argv, const char *prefix); -int cmd_help(int argc, const char **argv, const char *prefix); -int cmd_sched(int argc, const char **argv, const char *prefix); -int cmd_list(int argc, const char **argv, const char *prefix); -int cmd_record(int argc, const char **argv, const char *prefix); -int cmd_report(int argc, const char **argv, const char *prefix); -int cmd_stat(int argc, const char **argv, const char *prefix); -int cmd_timechart(int argc, const char **argv, const char *prefix); -int cmd_top(int argc, const char **argv, const char *prefix); -int cmd_script(int argc, const char **argv, const char *prefix); -int cmd_version(int argc, const char **argv, const char *prefix); -int cmd_probe(int argc, const char **argv, const char *prefix); -int cmd_kmem(int argc, const char **argv, const char *prefix); -int cmd_lock(int argc, const char **argv, const char *prefix); -int cmd_kvm(int argc, const char **argv, const char *prefix); -int cmd_test(int argc, const char **argv, const char *prefix); -int cmd_trace(int argc, const char **argv, const char *prefix); -int cmd_inject(int argc, const char **argv, const char *prefix); -int cmd_mem(int argc, const char **argv, const char *prefix); -int cmd_data(int argc, const char **argv, const char *prefix); +int cmd_annotate(int argc, const char **argv); +int cmd_bench(int argc, const char **argv); +int cmd_buildid_cache(int argc, const char **argv); +int cmd_buildid_list(int argc, const char **argv); +int cmd_config(int argc, const char **argv); +int cmd_c2c(int argc, const char **argv); +int cmd_diff(int argc, const char **argv); +int cmd_evlist(int argc, const char **argv); +int cmd_help(int argc, const char **argv); +int cmd_sched(int argc, const char **argv); +int cmd_kallsyms(int argc, const char **argv); +int cmd_list(int argc, const char **argv); +int cmd_record(int argc, const char **argv); +int cmd_report(int argc, const char **argv); +int cmd_stat(int argc, const char **argv); +int cmd_timechart(int argc, const char **argv); +int cmd_top(int argc, const char **argv); +int cmd_script(int argc, const char **argv); +int cmd_version(int argc, const char **argv); +int cmd_probe(int argc, const char **argv); +int cmd_kmem(int argc, const char **argv); +int cmd_lock(int argc, const char **argv); +int cmd_kvm(int argc, const char **argv); +int cmd_test(int argc, const char **argv); +int cmd_trace(int argc, const char **argv); +int cmd_inject(int argc, const char **argv); +int cmd_mem(int argc, const char **argv); +int cmd_data(int argc, const char **argv); +int cmd_ftrace(int argc, const char **argv); int find_scripts(char **scripts_array, char **scripts_path_array); #endif diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index c747bfd7f14d..83fe2202382e 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -1,7 +1,9 @@ #!/bin/sh HEADERS=' +include/uapi/linux/fcntl.h include/uapi/linux/perf_event.h +include/uapi/linux/stat.h include/linux/hash.h include/uapi/linux/hw_breakpoint.h arch/x86/include/asm/disabled-features.h diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt index ab5cbaa170d0..2d0caf20ff3a 100644 --- a/tools/perf/command-list.txt +++ b/tools/perf/command-list.txt @@ -9,9 +9,12 @@ perf-buildid-cache mainporcelain common perf-buildid-list mainporcelain common perf-data mainporcelain common perf-diff mainporcelain common +perf-c2c mainporcelain common perf-config mainporcelain common perf-evlist mainporcelain common +perf-ftrace mainporcelain common perf-inject mainporcelain common +perf-kallsyms mainporcelain common perf-kmem mainporcelain common perf-kvm mainporcelain common perf-list mainporcelain common diff --git a/tools/perf/perf.c b/tools/perf/perf.c index aa23b3347d6b..628a5e412cb1 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -17,11 +17,18 @@ #include <subcmd/parse-options.h> #include "util/bpf-loader.h" #include "util/debug.h" +#include "util/event.h" #include <api/fs/fs.h> #include <api/fs/tracing_path.h> +#include <errno.h> #include <pthread.h> +#include <signal.h> #include <stdlib.h> #include <time.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> +#include <linux/kernel.h> const char perf_usage_string[] = "perf [--version] [--help] [OPTIONS] COMMAND [ARGS]"; @@ -29,13 +36,12 @@ const char perf_usage_string[] = const char perf_more_info_string[] = "See 'perf help COMMAND' for more information on a specific command."; -int use_browser = -1; static int use_pager = -1; const char *input_name; struct cmd_struct { const char *cmd; - int (*fn)(int, const char **, const char *); + int (*fn)(int, const char **); int option; }; @@ -47,6 +53,7 @@ static struct cmd_struct commands[] = { { "diff", cmd_diff, 0 }, { "evlist", cmd_evlist, 0 }, { "help", cmd_help, 0 }, + { "kallsyms", cmd_kallsyms, 0 }, { "list", cmd_list, 0 }, { "record", cmd_record, 0 }, { "report", cmd_report, 0 }, @@ -71,6 +78,7 @@ static struct cmd_struct commands[] = { { "inject", cmd_inject, 0 }, { "mem", cmd_mem, 0 }, { "data", cmd_data, 0 }, + { "ftrace", cmd_ftrace, 0 }, }; struct pager_config { @@ -87,13 +95,14 @@ static int pager_command_config(const char *var, const char *value, void *data) } /* returns 0 for "no pager", 1 for "use pager", and -1 for "not specified" */ -int check_pager_config(const char *cmd) +static int check_pager_config(const char *cmd) { + int err; struct pager_config c; c.cmd = cmd; c.val = -1; - perf_config(pager_command_config, &c); - return c.val; + err = perf_config(pager_command_config, &c); + return err ?: c.val; } static int browser_command_config(const char *var, const char *value, void *data) @@ -112,11 +121,12 @@ static int browser_command_config(const char *var, const char *value, void *data */ static int check_browser_config(const char *cmd) { + int err; struct pager_config c; c.cmd = cmd; c.val = -1; - perf_config(browser_command_config, &c); - return c.val; + err = perf_config(browser_command_config, &c); + return err ?: c.val; } static void commit_pager_choice(void) @@ -264,73 +274,6 @@ static int handle_options(const char ***argv, int *argc, int *envchanged) return handled; } -static int handle_alias(int *argcp, const char ***argv) -{ - int envchanged = 0, ret = 0, saved_errno = errno; - int count, option_count; - const char **new_argv; - const char *alias_command; - char *alias_string; - - alias_command = (*argv)[0]; - alias_string = alias_lookup(alias_command); - if (alias_string) { - if (alias_string[0] == '!') { - if (*argcp > 1) { - struct strbuf buf; - - if (strbuf_init(&buf, PATH_MAX) < 0 || - strbuf_addstr(&buf, alias_string) < 0 || - sq_quote_argv(&buf, (*argv) + 1, - PATH_MAX) < 0) - die("Failed to allocate memory."); - free(alias_string); - alias_string = buf.buf; - } - ret = system(alias_string + 1); - if (ret >= 0 && WIFEXITED(ret) && - WEXITSTATUS(ret) != 127) - exit(WEXITSTATUS(ret)); - die("Failed to run '%s' when expanding alias '%s'", - alias_string + 1, alias_command); - } - count = split_cmdline(alias_string, &new_argv); - if (count < 0) - die("Bad alias.%s string", alias_command); - option_count = handle_options(&new_argv, &count, &envchanged); - if (envchanged) - die("alias '%s' changes environment variables\n" - "You can use '!perf' in the alias to do this.", - alias_command); - memmove(new_argv - option_count, new_argv, - count * sizeof(char *)); - new_argv -= option_count; - - if (count < 1) - die("empty alias for %s", alias_command); - - if (!strcmp(alias_command, new_argv[0])) - die("recursive alias: %s", alias_command); - - new_argv = realloc(new_argv, sizeof(char *) * - (count + *argcp + 1)); - /* insert after command name */ - memcpy(new_argv + count, *argv + 1, sizeof(char *) * *argcp); - new_argv[count + *argcp] = NULL; - - *argv = new_argv; - *argcp += count - 1; - - ret = 1; - } - - errno = saved_errno; - - return ret; -} - -const char perf_version_string[] = PERF_VERSION; - #define RUN_SETUP (1<<0) #define USE_PAGER (1<<1) @@ -338,13 +281,8 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv) { int status; struct stat st; - const char *prefix; char sbuf[STRERR_BUFSIZE]; - prefix = NULL; - if (p->option & RUN_SETUP) - prefix = NULL; /* setup_perf_directory(); */ - if (use_browser == -1) use_browser = check_browser_config(p->cmd); @@ -355,7 +293,7 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv) commit_pager_choice(); perf_env__set_cmdline(&perf_env, argc, argv); - status = p->fn(argc, argv, prefix); + status = p->fn(argc, argv); perf_config__exit(); exit_browser(status); perf_env__exit(&perf_env); @@ -396,16 +334,6 @@ static void handle_internal_command(int argc, const char **argv) { const char *cmd = argv[0]; unsigned int i; - static const char ext[] = STRIP_EXTENSION; - - if (sizeof(ext) > 1) { - i = strlen(argv[0]) - strlen(ext); - if (i > 0 && !strcmp(argv[0] + i, ext)) { - char *argv0 = strdup(argv[0]); - argv[0] = cmd = argv0; - argv0[i] = '\0'; - } - } /* Turn "perf cmd --help" into "perf help cmd" */ if (argc > 1 && !strcmp(argv[1], "--help")) { @@ -447,7 +375,8 @@ static void execv_dashed_external(const char **argv) if (status != -ERR_RUN_COMMAND_EXEC) { if (IS_RUN_COMMAND_ERR(status)) { do_die: - die("unable to run '%s'", argv[0]); + pr_err("FATAL: unable to run '%s'", argv[0]); + status = -128; } exit(-status); } @@ -459,25 +388,12 @@ do_die: static int run_argv(int *argcp, const char ***argv) { - int done_alias = 0; - - while (1) { - /* See if it's an internal command */ - handle_internal_command(*argcp, *argv); + /* See if it's an internal command */ + handle_internal_command(*argcp, *argv); - /* .. then try the external ones */ - execv_dashed_external(*argv); - - /* It could be an alias -- this works around the insanity - * of overriding "perf log" with "perf show" by having - * alias.log = show - */ - if (done_alias || !handle_alias(argcp, argv)) - break; - done_alias = 1; - } - - return done_alias; + /* .. then try the external ones */ + execv_dashed_external(*argv); + return 0; } static void pthread__block_sigwinch(void) @@ -510,6 +426,7 @@ static void cache_line_size(int *cacheline_sizep) int main(int argc, const char **argv) { + int err; const char *cmd; char sbuf[STRERR_BUFSIZE]; int value; @@ -535,7 +452,9 @@ int main(int argc, const char **argv) srandom(time(NULL)); perf_config__init(); - perf_config(perf_default_config, NULL); + err = perf_config(perf_default_config, NULL); + if (err) + return err; set_buildid_dir(NULL); /* get debugfs/tracefs mount point from /proc/mounts */ @@ -562,7 +481,7 @@ int main(int argc, const char **argv) #ifdef HAVE_LIBAUDIT_SUPPORT setup_path(); argv[0] = "trace"; - return cmd_trace(argc, argv, NULL); + return cmd_trace(argc, argv); #else fprintf(stderr, "trace command not available: missing audit-libs devel package at build time.\n"); @@ -607,17 +526,12 @@ int main(int argc, const char **argv) while (1) { static int done_help; - int was_alias = run_argv(&argc, &argv); + + run_argv(&argc, &argv); if (errno != ENOENT) break; - if (was_alias) { - fprintf(stderr, "Expansion of alias '%s' failed; " - "'%s' is not a perf-command\n", - cmd, argv[0]); - goto out; - } if (!done_help) { cmd = argv[0] = help_unknown_cmd(cmd); done_help = 1; diff --git a/tools/perf/perf.h b/tools/perf/perf.h index 1c27d947c2fe..806c216a1078 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -50,6 +50,7 @@ struct record_opts { bool running_time; bool full_auxtrace; bool auxtrace_snapshot_mode; + bool record_namespaces; bool record_switch_events; bool all_kernel; bool all_user; diff --git a/tools/perf/pmu-events/arch/x86/broadwell/uncore.json b/tools/perf/pmu-events/arch/x86/broadwell/uncore.json new file mode 100644 index 000000000000..28e1e159a3cb --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/broadwell/uncore.json @@ -0,0 +1,278 @@ +[ + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x41", + "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_XCORE", + "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.", + "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x81", + "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_EVICTION", + "BriefDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.", + "PublicDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x44", + "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_XCORE", + "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.", + "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x48", + "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_XCORE", + "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.", + "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x11", + "EventName": "UNC_CBO_CACHE_LOOKUP.READ_M", + "BriefDescription": "L3 Lookup read request that access cache and found line in M-state", + "PublicDescription": "L3 Lookup read request that access cache and found line in M-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x21", + "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_M", + "BriefDescription": "L3 Lookup write request that access cache and found line in M-state", + "PublicDescription": "L3 Lookup write request that access cache and found line in M-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x81", + "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_M", + "BriefDescription": "L3 Lookup any request that access cache and found line in M-state", + "PublicDescription": "L3 Lookup any request that access cache and found line in M-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x18", + "EventName": "UNC_CBO_CACHE_LOOKUP.READ_I", + "BriefDescription": "L3 Lookup read request that access cache and found line in I-state", + "PublicDescription": "L3 Lookup read request that access cache and found line in I-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x88", + "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_I", + "BriefDescription": "L3 Lookup any request that access cache and found line in I-state", + "PublicDescription": "L3 Lookup any request that access cache and found line in I-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x1f", + "EventName": "UNC_CBO_CACHE_LOOKUP.READ_MESI", + "BriefDescription": "L3 Lookup read request that access cache and found line in any MESI-state", + "PublicDescription": "L3 Lookup read request that access cache and found line in any MESI-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x2f", + "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_MESI", + "BriefDescription": "L3 Lookup write request that access cache and found line in MESI-state", + "PublicDescription": "L3 Lookup write request that access cache and found line in MESI-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x8f", + "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_MESI", + "BriefDescription": "L3 Lookup any request that access cache and found line in MESI-state", + "PublicDescription": "L3 Lookup any request that access cache and found line in MESI-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x86", + "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_ES", + "BriefDescription": "L3 Lookup any request that access cache and found line in E or S-state", + "PublicDescription": "L3 Lookup any request that access cache and found line in E or S-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x16", + "EventName": "UNC_CBO_CACHE_LOOKUP.READ_ES", + "BriefDescription": "L3 Lookup read request that access cache and found line in E or S-state", + "PublicDescription": "L3 Lookup read request that access cache and found line in E or S-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x26", + "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_ES", + "BriefDescription": "L3 Lookup write request that access cache and found line in E or S-state", + "PublicDescription": "L3 Lookup write request that access cache and found line in E or S-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "iMPH-U", + "EventCode": "0x80", + "UMask": "0x01", + "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL", + "BriefDescription": "Each cycle count number of all Core outgoing valid entries. Such entry is defined as valid from it's allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.", + "PublicDescription": "Each cycle count number of all Core outgoing valid entries. Such entry is defined as valid from it's allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.", + "Counter": "0,", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "iMPH-U", + "EventCode": "0x80", + "UMask": "0x02", + "EventName": "UNC_ARB_TRK_OCCUPANCY.DRD_DIRECT", + "BriefDescription": "Each cycle count number of 'valid' coherent Data Read entries that are in DirectData mode. Such entry is defined as valid when it is allocated till data sent to Core (first chunk, IDI0). Applicable for IA Cores' requests in normal case.", + "PublicDescription": "Each cycle count number of 'valid' coherent Data Read entries that are in DirectData mode. Such entry is defined as valid when it is allocated till data sent to Core (first chunk, IDI0). Applicable for IA Cores' requests in normal case.", + "Counter": "0,", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "iMPH-U", + "EventCode": "0x81", + "UMask": "0x01", + "EventName": "UNC_ARB_TRK_REQUESTS.ALL", + "BriefDescription": "Total number of Core outgoing entries allocated. Accounts for Coherent and non-coherent traffic.", + "PublicDescription": "Total number of Core outgoing entries allocated. Accounts for Coherent and non-coherent traffic.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "iMPH-U", + "EventCode": "0x81", + "UMask": "0x02", + "EventName": "UNC_ARB_TRK_REQUESTS.DRD_DIRECT", + "BriefDescription": "Number of Core coherent Data Read entries allocated in DirectData mode", + "PublicDescription": "Number of Core coherent Data Read entries allocated in DirectData mode.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "iMPH-U", + "EventCode": "0x81", + "UMask": "0x20", + "EventName": "UNC_ARB_TRK_REQUESTS.WRITES", + "BriefDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.", + "PublicDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "iMPH-U", + "EventCode": "0x84", + "UMask": "0x01", + "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL", + "BriefDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.", + "PublicDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "iMPH-U", + "EventCode": "0x80", + "UMask": "0x01", + "EventName": "UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST", + "BriefDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.;", + "PublicDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.", + "Counter": "0,", + "CounterMask": "1", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "NCU", + "EventCode": "0x0", + "UMask": "0x01", + "EventName": "UNC_CLOCK.SOCKET", + "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles", + "PublicDescription": "This 48-bit fixed counter counts the UCLK cycles.", + "Counter": "FIXED", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json new file mode 100644 index 000000000000..58ed6d33d1f4 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json @@ -0,0 +1,317 @@ +[ + { + "BriefDescription": "Uncore cache clock ticks", + "Counter": "0,1,2,3", + "EventName": "UNC_C_CLOCKTICKS", + "PerPkg": "1", + "Unit": "CBO" + }, + { + "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch)", + "Counter": "0,1,2,3", + "EventCode": "0x34", + "EventName": "UNC_C_LLC_LOOKUP.ANY", + "Filter": "filter_state=0x1", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x11", + "Unit": "CBO" + }, + { + "BriefDescription": "M line evictions from LLC (writebacks to memory)", + "Counter": "0,1,2,3", + "EventCode": "0x37", + "EventName": "UNC_C_LLC_VICTIMS.M_STATE", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses - demand and prefetch data reads - excludes LLC prefetches. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.DATA_READ", + "Filter": "filter_opc=0x182", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses - Uncacheable reads (from cpu) . Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.UNCACHEABLE", + "Filter": "filter_opc=0x187", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "MMIO reads. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.MMIO_READ", + "Filter": "filter_opc=0x187,filter_nc=1", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "MMIO writes. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.MMIO_WRITE", + "Filter": "filter_opc=0x18f,filter_nc=1", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC prefetch misses for RFO. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.RFO_LLC_PREFETCH", + "Filter": "filter_opc=0x190", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC prefetch misses for code reads. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.CODE_LLC_PREFETCH", + "Filter": "filter_opc=0x191", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC prefetch misses for data reads. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.DATA_LLC_PREFETCH", + "Filter": "filter_opc=0x192", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses for PCIe read current. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_READ", + "Filter": "filter_opc=0x19e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "ItoM write misses (as part of fast string memcpy stores) + PCIe full line writes. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_WRITE", + "Filter": "filter_opc=0x1c8", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe write misses (full cache line). Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_NON_SNOOP_WRITE", + "Filter": "filter_opc=0x1c8,filter_tid=0x3e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe writes (partial cache line). Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_NS_PARTIAL_WRITE", + "Filter": "filter_opc=0x180,filter_tid=0x3e", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "L2 demand and L2 prefetch code references to LLC. Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.CODE_LLC_PREFETCH", + "Filter": "filter_opc=0x181", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Streaming stores (full cache line). Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_FULL", + "Filter": "filter_opc=0x18c", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Streaming stores (partial cache line). Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_PARTIAL", + "Filter": "filter_opc=0x18d", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe read current. Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_READ", + "Filter": "filter_opc=0x19e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe write references (full cache line). Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_WRITE", + "Filter": "filter_opc=0x1c8,filter_tid=0x3e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Occupancy counter for LLC data reads (demand and L2 prefetch). Derived from unc_c_tor_occupancy.miss_opcode", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.LLC_DATA_READ", + "Filter": "filter_opc=0x182", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "read requests to home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.READS", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "HA" + }, + { + "BriefDescription": "read requests to local home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.READS_LOCAL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "read requests to remote home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.READS_REMOTE", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "write requests to home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.WRITES", + "PerPkg": "1", + "UMask": "0xC", + "Unit": "HA" + }, + { + "BriefDescription": "write requests to local home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.WRITES_LOCAL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "write requests to remote home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.WRITES_REMOTE", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "HA" + }, + { + "BriefDescription": "Conflict requests (requests for same address from multiple agents simultaneously)", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPCNFLCT", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "HA" + }, + { + "BriefDescription": "M line forwarded from remote cache along with writeback to memory", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x20", + "Unit": "HA" + }, + { + "BriefDescription": "M line forwarded from remote cache with no writeback to memory", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPIFWD", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "Shared line response from remote cache", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPS", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "Shared line forwarded from remote cache", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPSFWD", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x8", + "Unit": "HA" + } +] diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-memory.json b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-memory.json new file mode 100644 index 000000000000..f4b0745cdbbf --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-memory.json @@ -0,0 +1,86 @@ +[ + { + "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "LLC_MISSES.MEM_READ", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "iMC" + }, + { + "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "LLC_MISSES.MEM_WRITE", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0xC", + "Unit": "iMC" + }, + { + "BriefDescription": "Memory controller clock ticks", + "Counter": "0,1,2,3", + "EventName": "UNC_M_DCLOCKTICKS", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode", + "Counter": "0,1,2,3", + "EventCode": "0x85", + "EventName": "UNC_M_POWER_CHANNEL_PPD", + "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_DCLOCKTICKS) * 100.", + "MetricName": "power_channel_ppd %", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles all ranks are in critical thermal throttle", + "Counter": "0,1,2,3", + "EventCode": "0x86", + "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES", + "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_DCLOCKTICKS) * 100.", + "MetricName": "power_critical_throttle_cycles %", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles Memory is in self refresh power mode", + "Counter": "0,1,2,3", + "EventCode": "0x43", + "EventName": "UNC_M_POWER_SELF_REFRESH", + "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_DCLOCKTICKS) * 100.", + "MetricName": "power_self_refresh %", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Pre-charges due to page misses", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.PAGE_MISS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "Pre-charge for reads", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.RD", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "Pre-charge for writes", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.WR", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "iMC" + } +] diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-power.json b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-power.json new file mode 100644 index 000000000000..dd1b95655d1d --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-power.json @@ -0,0 +1,92 @@ +[ + { + "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events", + "Counter": "0,1,2,3", + "EventName": "UNC_P_CLOCKTICKS", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C0. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0", + "Filter": "occ_sel=1", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "power_state_occupancy.cores_c0 %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C3. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3", + "Filter": "occ_sel=2", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "power_state_occupancy.cores_c3 %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C6. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events ", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6", + "Filter": "occ_sel=3", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "power_state_occupancy.cores_c6 %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode. This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip", + "Counter": "0,1,2,3", + "EventCode": "0xA", + "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES", + "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "prochot_external_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when temperature is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_max_limit_thermal_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x6", + "EventName": "UNC_P_FREQ_MAX_OS_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_max_os_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when power is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x5", + "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_max_power_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when current is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x74", + "EventName": "UNC_P_FREQ_TRANS_CYCLES", + "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_trans_cycles %", + "PerPkg": "1", + "Unit": "PCU" + } +] diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json new file mode 100644 index 000000000000..58ed6d33d1f4 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json @@ -0,0 +1,317 @@ +[ + { + "BriefDescription": "Uncore cache clock ticks", + "Counter": "0,1,2,3", + "EventName": "UNC_C_CLOCKTICKS", + "PerPkg": "1", + "Unit": "CBO" + }, + { + "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch)", + "Counter": "0,1,2,3", + "EventCode": "0x34", + "EventName": "UNC_C_LLC_LOOKUP.ANY", + "Filter": "filter_state=0x1", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x11", + "Unit": "CBO" + }, + { + "BriefDescription": "M line evictions from LLC (writebacks to memory)", + "Counter": "0,1,2,3", + "EventCode": "0x37", + "EventName": "UNC_C_LLC_VICTIMS.M_STATE", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses - demand and prefetch data reads - excludes LLC prefetches. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.DATA_READ", + "Filter": "filter_opc=0x182", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses - Uncacheable reads (from cpu) . Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.UNCACHEABLE", + "Filter": "filter_opc=0x187", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "MMIO reads. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.MMIO_READ", + "Filter": "filter_opc=0x187,filter_nc=1", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "MMIO writes. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.MMIO_WRITE", + "Filter": "filter_opc=0x18f,filter_nc=1", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC prefetch misses for RFO. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.RFO_LLC_PREFETCH", + "Filter": "filter_opc=0x190", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC prefetch misses for code reads. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.CODE_LLC_PREFETCH", + "Filter": "filter_opc=0x191", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC prefetch misses for data reads. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.DATA_LLC_PREFETCH", + "Filter": "filter_opc=0x192", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses for PCIe read current. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_READ", + "Filter": "filter_opc=0x19e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "ItoM write misses (as part of fast string memcpy stores) + PCIe full line writes. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_WRITE", + "Filter": "filter_opc=0x1c8", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe write misses (full cache line). Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_NON_SNOOP_WRITE", + "Filter": "filter_opc=0x1c8,filter_tid=0x3e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe writes (partial cache line). Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_NS_PARTIAL_WRITE", + "Filter": "filter_opc=0x180,filter_tid=0x3e", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "L2 demand and L2 prefetch code references to LLC. Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.CODE_LLC_PREFETCH", + "Filter": "filter_opc=0x181", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Streaming stores (full cache line). Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_FULL", + "Filter": "filter_opc=0x18c", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Streaming stores (partial cache line). Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_PARTIAL", + "Filter": "filter_opc=0x18d", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe read current. Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_READ", + "Filter": "filter_opc=0x19e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe write references (full cache line). Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_WRITE", + "Filter": "filter_opc=0x1c8,filter_tid=0x3e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Occupancy counter for LLC data reads (demand and L2 prefetch). Derived from unc_c_tor_occupancy.miss_opcode", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.LLC_DATA_READ", + "Filter": "filter_opc=0x182", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "read requests to home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.READS", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "HA" + }, + { + "BriefDescription": "read requests to local home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.READS_LOCAL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "read requests to remote home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.READS_REMOTE", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "write requests to home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.WRITES", + "PerPkg": "1", + "UMask": "0xC", + "Unit": "HA" + }, + { + "BriefDescription": "write requests to local home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.WRITES_LOCAL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "write requests to remote home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.WRITES_REMOTE", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "HA" + }, + { + "BriefDescription": "Conflict requests (requests for same address from multiple agents simultaneously)", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPCNFLCT", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "HA" + }, + { + "BriefDescription": "M line forwarded from remote cache along with writeback to memory", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x20", + "Unit": "HA" + }, + { + "BriefDescription": "M line forwarded from remote cache with no writeback to memory", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPIFWD", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "Shared line response from remote cache", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPS", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "Shared line forwarded from remote cache", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPSFWD", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x8", + "Unit": "HA" + } +] diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json new file mode 100644 index 000000000000..824961318c1e --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json @@ -0,0 +1,28 @@ +[ + { + "BriefDescription": "QPI clock ticks", + "Counter": "0,1,2,3", + "EventCode": "0x14", + "EventName": "UNC_Q_CLOCKTICKS", + "PerPkg": "1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data", + "Counter": "0,1,2,3", + "EventName": "QPI_DATA_BANDWIDTH_TX", + "PerPkg": "1", + "ScaleUnit": "8Bytes", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data", + "Counter": "0,1,2,3", + "EventName": "QPI_CTL_BANDWIDTH_TX", + "PerPkg": "1", + "ScaleUnit": "8Bytes", + "UMask": "0x4", + "Unit": "QPI LL" + } +] diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-memory.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-memory.json new file mode 100644 index 000000000000..66eed399724c --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-memory.json @@ -0,0 +1,86 @@ +[ + { + "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "LLC_MISSES.MEM_READ", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "iMC" + }, + { + "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "LLC_MISSES.MEM_WRITE", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0xC", + "Unit": "iMC" + }, + { + "BriefDescription": "Memory controller clock ticks", + "Counter": "0,1,2,3", + "EventName": "UNC_M_CLOCKTICKS", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode", + "Counter": "0,1,2,3", + "EventCode": "0x85", + "EventName": "UNC_M_POWER_CHANNEL_PPD", + "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.", + "MetricName": "power_channel_ppd %", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles all ranks are in critical thermal throttle", + "Counter": "0,1,2,3", + "EventCode": "0x86", + "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES", + "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.", + "MetricName": "power_critical_throttle_cycles %", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles Memory is in self refresh power mode", + "Counter": "0,1,2,3", + "EventCode": "0x43", + "EventName": "UNC_M_POWER_SELF_REFRESH", + "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.", + "MetricName": "power_self_refresh %", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Pre-charges due to page misses", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.PAGE_MISS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "Pre-charge for reads", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.RD", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "Pre-charge for writes", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.WR", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "iMC" + } +] diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-power.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-power.json new file mode 100644 index 000000000000..dd1b95655d1d --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-power.json @@ -0,0 +1,92 @@ +[ + { + "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events", + "Counter": "0,1,2,3", + "EventName": "UNC_P_CLOCKTICKS", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C0. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0", + "Filter": "occ_sel=1", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "power_state_occupancy.cores_c0 %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C3. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3", + "Filter": "occ_sel=2", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "power_state_occupancy.cores_c3 %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C6. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events ", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6", + "Filter": "occ_sel=3", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "power_state_occupancy.cores_c6 %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode. This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip", + "Counter": "0,1,2,3", + "EventCode": "0xA", + "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES", + "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "prochot_external_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when temperature is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_max_limit_thermal_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x6", + "EventName": "UNC_P_FREQ_MAX_OS_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_max_os_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when power is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x5", + "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_max_power_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when current is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x74", + "EventName": "UNC_P_FREQ_TRANS_CYCLES", + "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_trans_cycles %", + "PerPkg": "1", + "Unit": "PCU" + } +] diff --git a/tools/perf/pmu-events/arch/x86/haswell/uncore.json b/tools/perf/pmu-events/arch/x86/haswell/uncore.json new file mode 100644 index 000000000000..3ef5c21fef56 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/haswell/uncore.json @@ -0,0 +1,374 @@ +[ + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x21", + "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_EXTERNAL", + "BriefDescription": "An external snoop misses in some processor core.", + "PublicDescription": "An external snoop misses in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x41", + "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_XCORE", + "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.", + "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x81", + "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_EVICTION", + "BriefDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.", + "PublicDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x24", + "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_EXTERNAL", + "BriefDescription": "An external snoop hits a non-modified line in some processor core.", + "PublicDescription": "An external snoop hits a non-modified line in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x44", + "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_XCORE", + "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.", + "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x84", + "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_EVICTION", + "BriefDescription": "A cross-core snoop resulted from L3 Eviction which hits a non-modified line in some processor core.", + "PublicDescription": "A cross-core snoop resulted from L3 Eviction which hits a non-modified line in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x28", + "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_EXTERNAL", + "BriefDescription": "An external snoop hits a modified line in some processor core.", + "PublicDescription": "An external snoop hits a modified line in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x48", + "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_XCORE", + "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.", + "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x88", + "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_EVICTION", + "BriefDescription": "A cross-core snoop resulted from L3 Eviction which hits a modified line in some processor core.", + "PublicDescription": "A cross-core snoop resulted from L3 Eviction which hits a modified line in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x11", + "EventName": "UNC_CBO_CACHE_LOOKUP.READ_M", + "BriefDescription": "L3 Lookup read request that access cache and found line in M-state.", + "PublicDescription": "L3 Lookup read request that access cache and found line in M-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x21", + "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_M", + "BriefDescription": "L3 Lookup write request that access cache and found line in M-state.", + "PublicDescription": "L3 Lookup write request that access cache and found line in M-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x41", + "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_M", + "BriefDescription": "L3 Lookup external snoop request that access cache and found line in M-state.", + "PublicDescription": "L3 Lookup external snoop request that access cache and found line in M-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x81", + "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_M", + "BriefDescription": "L3 Lookup any request that access cache and found line in M-state.", + "PublicDescription": "L3 Lookup any request that access cache and found line in M-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x18", + "EventName": "UNC_CBO_CACHE_LOOKUP.READ_I", + "BriefDescription": "L3 Lookup read request that access cache and found line in I-state.", + "PublicDescription": "L3 Lookup read request that access cache and found line in I-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x28", + "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_I", + "BriefDescription": "L3 Lookup write request that access cache and found line in I-state.", + "PublicDescription": "L3 Lookup write request that access cache and found line in I-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x48", + "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_I", + "BriefDescription": "L3 Lookup external snoop request that access cache and found line in I-state.", + "PublicDescription": "L3 Lookup external snoop request that access cache and found line in I-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x88", + "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_I", + "BriefDescription": "L3 Lookup any request that access cache and found line in I-state.", + "PublicDescription": "L3 Lookup any request that access cache and found line in I-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x1f", + "EventName": "UNC_CBO_CACHE_LOOKUP.READ_MESI", + "BriefDescription": "L3 Lookup read request that access cache and found line in any MESI-state.", + "PublicDescription": "L3 Lookup read request that access cache and found line in any MESI-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x2f", + "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_MESI", + "BriefDescription": "L3 Lookup write request that access cache and found line in MESI-state.", + "PublicDescription": "L3 Lookup write request that access cache and found line in MESI-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x4f", + "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_MESI", + "BriefDescription": "L3 Lookup external snoop request that access cache and found line in MESI-state.", + "PublicDescription": "L3 Lookup external snoop request that access cache and found line in MESI-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x8f", + "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_MESI", + "BriefDescription": "L3 Lookup any request that access cache and found line in MESI-state.", + "PublicDescription": "L3 Lookup any request that access cache and found line in MESI-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x86", + "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_ES", + "BriefDescription": "L3 Lookup any request that access cache and found line in E or S-state.", + "PublicDescription": "L3 Lookup any request that access cache and found line in E or S-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x46", + "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_ES", + "BriefDescription": "L3 Lookup external snoop request that access cache and found line in E or S-state.", + "PublicDescription": "L3 Lookup external snoop request that access cache and found line in E or S-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x16", + "EventName": "UNC_CBO_CACHE_LOOKUP.READ_ES", + "BriefDescription": "L3 Lookup read request that access cache and found line in E or S-state.", + "PublicDescription": "L3 Lookup read request that access cache and found line in E or S-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x26", + "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_ES", + "BriefDescription": "L3 Lookup write request that access cache and found line in E or S-state.", + "PublicDescription": "L3 Lookup write request that access cache and found line in E or S-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "iMPH-U", + "EventCode": "0x80", + "UMask": "0x01", + "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL", + "BriefDescription": "Each cycle count number of all Core outgoing valid entries. Such entry is defined as valid from it's allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.", + "PublicDescription": "Each cycle count number of all Core outgoing valid entries. Such entry is defined as valid from it's allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.", + "Counter": "0", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "iMPH-U", + "EventCode": "0x81", + "UMask": "0x01", + "EventName": "UNC_ARB_TRK_REQUESTS.ALL", + "BriefDescription": "Total number of Core outgoing entries allocated. Accounts for Coherent and non-coherent traffic.", + "PublicDescription": "Total number of Core outgoing entries allocated. Accounts for Coherent and non-coherent traffic.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "iMPH-U", + "EventCode": "0x81", + "UMask": "0x20", + "EventName": "UNC_ARB_TRK_REQUESTS.WRITES", + "BriefDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.", + "PublicDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "iMPH-U", + "EventCode": "0x83", + "UMask": "0x01", + "EventName": "UNC_ARB_COH_TRK_OCCUPANCY.All", + "BriefDescription": "Each cycle count number of valid entries in Coherency Tracker queue from allocation till deallocation. Aperture requests (snoops) appear as NC decoded internally and become coherent (snoop L3, access memory)", + "PublicDescription": "Each cycle count number of valid entries in Coherency Tracker queue from allocation till deallocation. Aperture requests (snoops) appear as NC decoded internally and become coherent (snoop L3, access memory).", + "Counter": "0", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "iMPH-U", + "EventCode": "0x84", + "UMask": "0x01", + "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL", + "BriefDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.", + "PublicDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "NCU", + "EventCode": "0x0", + "UMask": "0x01", + "EventName": "UNC_CLOCK.SOCKET", + "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles.", + "PublicDescription": "This 48-bit fixed counter counts the UCLK cycles.", + "Counter": "FIXED", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/haswellx/uncore-cache.json b/tools/perf/pmu-events/arch/x86/haswellx/uncore-cache.json new file mode 100644 index 000000000000..58ed6d33d1f4 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/haswellx/uncore-cache.json @@ -0,0 +1,317 @@ +[ + { + "BriefDescription": "Uncore cache clock ticks", + "Counter": "0,1,2,3", + "EventName": "UNC_C_CLOCKTICKS", + "PerPkg": "1", + "Unit": "CBO" + }, + { + "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch)", + "Counter": "0,1,2,3", + "EventCode": "0x34", + "EventName": "UNC_C_LLC_LOOKUP.ANY", + "Filter": "filter_state=0x1", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x11", + "Unit": "CBO" + }, + { + "BriefDescription": "M line evictions from LLC (writebacks to memory)", + "Counter": "0,1,2,3", + "EventCode": "0x37", + "EventName": "UNC_C_LLC_VICTIMS.M_STATE", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses - demand and prefetch data reads - excludes LLC prefetches. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.DATA_READ", + "Filter": "filter_opc=0x182", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses - Uncacheable reads (from cpu) . Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.UNCACHEABLE", + "Filter": "filter_opc=0x187", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "MMIO reads. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.MMIO_READ", + "Filter": "filter_opc=0x187,filter_nc=1", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "MMIO writes. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.MMIO_WRITE", + "Filter": "filter_opc=0x18f,filter_nc=1", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC prefetch misses for RFO. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.RFO_LLC_PREFETCH", + "Filter": "filter_opc=0x190", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC prefetch misses for code reads. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.CODE_LLC_PREFETCH", + "Filter": "filter_opc=0x191", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC prefetch misses for data reads. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.DATA_LLC_PREFETCH", + "Filter": "filter_opc=0x192", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses for PCIe read current. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_READ", + "Filter": "filter_opc=0x19e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "ItoM write misses (as part of fast string memcpy stores) + PCIe full line writes. Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_WRITE", + "Filter": "filter_opc=0x1c8", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe write misses (full cache line). Derived from unc_c_tor_inserts.miss_opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_NON_SNOOP_WRITE", + "Filter": "filter_opc=0x1c8,filter_tid=0x3e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe writes (partial cache line). Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_NS_PARTIAL_WRITE", + "Filter": "filter_opc=0x180,filter_tid=0x3e", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "L2 demand and L2 prefetch code references to LLC. Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.CODE_LLC_PREFETCH", + "Filter": "filter_opc=0x181", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Streaming stores (full cache line). Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_FULL", + "Filter": "filter_opc=0x18c", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Streaming stores (partial cache line). Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_PARTIAL", + "Filter": "filter_opc=0x18d", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe read current. Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_READ", + "Filter": "filter_opc=0x19e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe write references (full cache line). Derived from unc_c_tor_inserts.opcode", + "Counter": "0,1,2,3", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_WRITE", + "Filter": "filter_opc=0x1c8,filter_tid=0x3e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Occupancy counter for LLC data reads (demand and L2 prefetch). Derived from unc_c_tor_occupancy.miss_opcode", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.LLC_DATA_READ", + "Filter": "filter_opc=0x182", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "read requests to home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.READS", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "HA" + }, + { + "BriefDescription": "read requests to local home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.READS_LOCAL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "HA" + }, + { + "BriefDescription": "read requests to remote home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.READS_REMOTE", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "write requests to home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.WRITES", + "PerPkg": "1", + "UMask": "0xC", + "Unit": "HA" + }, + { + "BriefDescription": "write requests to local home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.WRITES_LOCAL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "write requests to remote home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.WRITES_REMOTE", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "HA" + }, + { + "BriefDescription": "Conflict requests (requests for same address from multiple agents simultaneously)", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPCNFLCT", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "HA" + }, + { + "BriefDescription": "M line forwarded from remote cache along with writeback to memory", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x20", + "Unit": "HA" + }, + { + "BriefDescription": "M line forwarded from remote cache with no writeback to memory", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPIFWD", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "Shared line response from remote cache", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPS", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "Shared line forwarded from remote cache", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPSFWD", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x8", + "Unit": "HA" + } +] diff --git a/tools/perf/pmu-events/arch/x86/haswellx/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/haswellx/uncore-interconnect.json new file mode 100644 index 000000000000..824961318c1e --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/haswellx/uncore-interconnect.json @@ -0,0 +1,28 @@ +[ + { + "BriefDescription": "QPI clock ticks", + "Counter": "0,1,2,3", + "EventCode": "0x14", + "EventName": "UNC_Q_CLOCKTICKS", + "PerPkg": "1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data", + "Counter": "0,1,2,3", + "EventName": "QPI_DATA_BANDWIDTH_TX", + "PerPkg": "1", + "ScaleUnit": "8Bytes", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data", + "Counter": "0,1,2,3", + "EventName": "QPI_CTL_BANDWIDTH_TX", + "PerPkg": "1", + "ScaleUnit": "8Bytes", + "UMask": "0x4", + "Unit": "QPI LL" + } +] diff --git a/tools/perf/pmu-events/arch/x86/haswellx/uncore-memory.json b/tools/perf/pmu-events/arch/x86/haswellx/uncore-memory.json new file mode 100644 index 000000000000..66eed399724c --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/haswellx/uncore-memory.json @@ -0,0 +1,86 @@ +[ + { + "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "LLC_MISSES.MEM_READ", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "iMC" + }, + { + "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "LLC_MISSES.MEM_WRITE", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0xC", + "Unit": "iMC" + }, + { + "BriefDescription": "Memory controller clock ticks", + "Counter": "0,1,2,3", + "EventName": "UNC_M_CLOCKTICKS", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode", + "Counter": "0,1,2,3", + "EventCode": "0x85", + "EventName": "UNC_M_POWER_CHANNEL_PPD", + "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.", + "MetricName": "power_channel_ppd %", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles all ranks are in critical thermal throttle", + "Counter": "0,1,2,3", + "EventCode": "0x86", + "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES", + "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.", + "MetricName": "power_critical_throttle_cycles %", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles Memory is in self refresh power mode", + "Counter": "0,1,2,3", + "EventCode": "0x43", + "EventName": "UNC_M_POWER_SELF_REFRESH", + "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.", + "MetricName": "power_self_refresh %", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Pre-charges due to page misses", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.PAGE_MISS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "Pre-charge for reads", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.RD", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "Pre-charge for writes", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.WR", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "iMC" + } +] diff --git a/tools/perf/pmu-events/arch/x86/haswellx/uncore-power.json b/tools/perf/pmu-events/arch/x86/haswellx/uncore-power.json new file mode 100644 index 000000000000..dd1b95655d1d --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/haswellx/uncore-power.json @@ -0,0 +1,92 @@ +[ + { + "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events", + "Counter": "0,1,2,3", + "EventName": "UNC_P_CLOCKTICKS", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C0. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0", + "Filter": "occ_sel=1", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "power_state_occupancy.cores_c0 %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C3. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3", + "Filter": "occ_sel=2", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "power_state_occupancy.cores_c3 %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C6. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events ", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6", + "Filter": "occ_sel=3", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "power_state_occupancy.cores_c6 %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode. This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip", + "Counter": "0,1,2,3", + "EventCode": "0xA", + "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES", + "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "prochot_external_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when temperature is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_max_limit_thermal_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x6", + "EventName": "UNC_P_FREQ_MAX_OS_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_max_os_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when power is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x5", + "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_max_power_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when current is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x74", + "EventName": "UNC_P_FREQ_TRANS_CYCLES", + "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_trans_cycles %", + "PerPkg": "1", + "Unit": "PCU" + } +] diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/uncore.json b/tools/perf/pmu-events/arch/x86/ivybridge/uncore.json new file mode 100644 index 000000000000..42c70eed05a2 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/ivybridge/uncore.json @@ -0,0 +1,314 @@ +[ + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x01", + "EventName": "UNC_CBO_XSNP_RESPONSE.MISS", + "BriefDescription": "A snoop misses in some processor core.", + "PublicDescription": "A snoop misses in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x02", + "EventName": "UNC_CBO_XSNP_RESPONSE.INVAL", + "BriefDescription": "A snoop invalidates a non-modified line in some processor core.", + "PublicDescription": "A snoop invalidates a non-modified line in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x04", + "EventName": "UNC_CBO_XSNP_RESPONSE.HIT", + "BriefDescription": "A snoop hits a non-modified line in some processor core.", + "PublicDescription": "A snoop hits a non-modified line in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x08", + "EventName": "UNC_CBO_XSNP_RESPONSE.HITM", + "BriefDescription": "A snoop hits a modified line in some processor core.", + "PublicDescription": "A snoop hits a modified line in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x10", + "EventName": "UNC_CBO_XSNP_RESPONSE.INVAL_M", + "BriefDescription": "A snoop invalidates a modified line in some processor core.", + "PublicDescription": "A snoop invalidates a modified line in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x20", + "EventName": "UNC_CBO_XSNP_RESPONSE.EXTERNAL_FILTER", + "BriefDescription": "Filter on cross-core snoops initiated by this Cbox due to external snoop request.", + "PublicDescription": "Filter on cross-core snoops initiated by this Cbox due to external snoop request.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x40", + "EventName": "UNC_CBO_XSNP_RESPONSE.XCORE_FILTER", + "BriefDescription": "Filter on cross-core snoops initiated by this Cbox due to processor core memory request.", + "PublicDescription": "Filter on cross-core snoops initiated by this Cbox due to processor core memory request.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x80", + "EventName": "UNC_CBO_XSNP_RESPONSE.EVICTION_FILTER", + "BriefDescription": "Filter on cross-core snoops initiated by this Cbox due to LLC eviction.", + "PublicDescription": "Filter on cross-core snoops initiated by this Cbox due to LLC eviction.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x01", + "EventName": "UNC_CBO_CACHE_LOOKUP.M", + "BriefDescription": "LLC lookup request that access cache and found line in M-state.", + "PublicDescription": "LLC lookup request that access cache and found line in M-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x02", + "EventName": "UNC_CBO_CACHE_LOOKUP.E", + "BriefDescription": "LLC lookup request that access cache and found line in E-state.", + "PublicDescription": "LLC lookup request that access cache and found line in E-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x04", + "EventName": "UNC_CBO_CACHE_LOOKUP.S", + "BriefDescription": "LLC lookup request that access cache and found line in S-state.", + "PublicDescription": "LLC lookup request that access cache and found line in S-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x08", + "EventName": "UNC_CBO_CACHE_LOOKUP.I", + "BriefDescription": "LLC lookup request that access cache and found line in I-state.", + "PublicDescription": "LLC lookup request that access cache and found line in I-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x10", + "EventName": "UNC_CBO_CACHE_LOOKUP.READ_FILTER", + "BriefDescription": "Filter on processor core initiated cacheable read requests.", + "PublicDescription": "Filter on processor core initiated cacheable read requests.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x20", + "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_FILTER", + "BriefDescription": "Filter on processor core initiated cacheable write requests.", + "PublicDescription": "Filter on processor core initiated cacheable write requests.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x40", + "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_FILTER", + "BriefDescription": "Filter on external snoop requests.", + "PublicDescription": "Filter on external snoop requests.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x80", + "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_REQUEST_FILTER", + "BriefDescription": "Filter on any IRQ or IPQ initiated requests including uncacheable, non-coherent requests.", + "PublicDescription": "Filter on any IRQ or IPQ initiated requests including uncacheable, non-coherent requests.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "ARB", + "EventCode": "0x80", + "UMask": "0x01", + "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL", + "BriefDescription": "Counts cycles weighted by the number of requests waiting for data returning from the memory controller. Accounts for coherent and non-coherent requests initiated by IA cores, processor graphic units, or LLC.", + "PublicDescription": "Counts cycles weighted by the number of requests waiting for data returning from the memory controller. Accounts for coherent and non-coherent requests initiated by IA cores, processor graphic units, or LLC.", + "Counter": "0", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "ARB", + "EventCode": "0x81", + "UMask": "0x01", + "EventName": "UNC_ARB_TRK_REQUESTS.ALL", + "BriefDescription": "Counts the number of coherent and in-coherent requests initiated by IA cores, processor graphic units, or LLC.", + "PublicDescription": "Counts the number of coherent and in-coherent requests initiated by IA cores, processor graphic units, or LLC.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "ARB", + "EventCode": "0x81", + "UMask": "0x20", + "EventName": "UNC_ARB_TRK_REQUESTS.WRITES", + "BriefDescription": "Counts the number of allocated write entries, include full, partial, and LLC evictions.", + "PublicDescription": "Counts the number of allocated write entries, include full, partial, and LLC evictions.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "ARB", + "EventCode": "0x81", + "UMask": "0x80", + "EventName": "UNC_ARB_TRK_REQUESTS.EVICTIONS", + "BriefDescription": "Counts the number of LLC evictions allocated.", + "PublicDescription": "Counts the number of LLC evictions allocated.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "ARB", + "EventCode": "0x83", + "UMask": "0x01", + "EventName": "UNC_ARB_COH_TRK_OCCUPANCY.ALL", + "BriefDescription": "Cycles weighted by number of requests pending in Coherency Tracker.", + "PublicDescription": "Cycles weighted by number of requests pending in Coherency Tracker.", + "Counter": "0", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "ARB", + "EventCode": "0x84", + "UMask": "0x01", + "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL", + "BriefDescription": "Number of requests allocated in Coherency Tracker.", + "PublicDescription": "Number of requests allocated in Coherency Tracker.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "ARB", + "EventCode": "0x80", + "UMask": "0x01", + "EventName": "UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST", + "BriefDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.", + "PublicDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.", + "Counter": "0,1", + "CounterMask": "1", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "ARB", + "EventCode": "0x80", + "UMask": "0x01", + "EventName": "UNC_ARB_TRK_OCCUPANCY.CYCLES_OVER_HALF_FULL", + "BriefDescription": "Cycles with at least half of the requests outstanding are waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.", + "PublicDescription": "Cycles with at least half of the requests outstanding are waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.", + "Counter": "0,1", + "CounterMask": "10", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "ARB", + "EventCode": "0x0", + "UMask": "0x01", + "EventName": "UNC_CLOCK.SOCKET", + "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles.", + "PublicDescription": "This 48-bit fixed counter counts the UCLK cycles.", + "Counter": "Fixed", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x06", + "EventName": "UNC_CBO_CACHE_LOOKUP.ES", + "BriefDescription": "LLC lookup request that access cache and found line in E-state or S-state.", + "PublicDescription": "LLC lookup request that access cache and found line in E-state or S-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-cache.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-cache.json new file mode 100644 index 000000000000..267410594833 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-cache.json @@ -0,0 +1,322 @@ +[ + { + "BriefDescription": "Uncore cache clock ticks", + "Counter": "0,1,2,3", + "EventName": "UNC_C_CLOCKTICKS", + "PerPkg": "1", + "Unit": "CBO" + }, + { + "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch)", + "Counter": "0,1", + "EventCode": "0x34", + "EventName": "UNC_C_LLC_LOOKUP.ANY", + "Filter": "filter_state=0x1", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x11", + "Unit": "CBO" + }, + { + "BriefDescription": "M line evictions from LLC (writebacks to memory)", + "Counter": "0,1", + "EventCode": "0x37", + "EventName": "UNC_C_LLC_VICTIMS.M_STATE", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses - demand and prefetch data reads - excludes LLC prefetches. Derived from unc_c_tor_inserts.miss_opcode.demand", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.DATA_READ", + "Filter": "filter_opc=0x182", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses - Uncacheable reads. Derived from unc_c_tor_inserts.miss_opcode.uncacheable", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.UNCACHEABLE", + "Filter": "filter_opc=0x187", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC prefetch misses for RFO. Derived from unc_c_tor_inserts.miss_opcode.rfo_prefetch", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.RFO_LLC_PREFETCH", + "Filter": "filter_opc=0x190", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC prefetch misses for code reads. Derived from unc_c_tor_inserts.miss_opcode.code", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.CODE_LLC_PREFETCH", + "Filter": "filter_opc=0x191", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC prefetch misses for data reads. Derived from unc_c_tor_inserts.miss_opcode.data_read", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.DATA_LLC_PREFETCH", + "Filter": "filter_opc=0x192", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe allocating writes that miss LLC - DDIO misses. Derived from unc_c_tor_inserts.miss_opcode.ddio_miss", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_WRITE", + "Filter": "filter_opc=0x19c", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses for PCIe read current. Derived from unc_c_tor_inserts.miss_opcode.pcie_read", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_READ", + "Filter": "filter_opc=0x19e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses for ItoM writes (as part of fast string memcpy stores). Derived from unc_c_tor_inserts.miss_opcode.itom_write", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.ITOM_WRITE", + "Filter": "filter_opc=0x1c8", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses for PCIe non-snoop reads. Derived from unc_c_tor_inserts.miss_opcode.pcie_read", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_NON_SNOOP_READ", + "Filter": "filter_opc=0x1e4", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses for PCIe non-snoop writes (full line). Derived from unc_c_tor_inserts.miss_opcode.pcie_write", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_NON_SNOOP_WRITE", + "Filter": "filter_opc=0x1e6", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "Streaming stores (full cache line). Derived from unc_c_tor_inserts.opcode.streaming_full", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_FULL", + "Filter": "filter_opc=0x18c", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Streaming stores (partial cache line). Derived from unc_c_tor_inserts.opcode.streaming_partial", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_PARTIAL", + "Filter": "filter_opc=0x18d", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Partial PCIe reads. Derived from unc_c_tor_inserts.opcode.pcie_partial", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_PARTIAL_READ", + "Filter": "filter_opc=0x195", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe allocating writes that hit in LLC (DDIO hits). Derived from unc_c_tor_inserts.opcode.ddio_hit", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_WRITE", + "Filter": "filter_opc=0x19c", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe read current. Derived from unc_c_tor_inserts.opcode.pcie_read_current", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_READ", + "Filter": "filter_opc=0x19e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "ItoM write hits (as part of fast string memcpy stores). Derived from unc_c_tor_inserts.opcode.itom_write_hit", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.ITOM_WRITE", + "Filter": "filter_opc=0x1c8", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe non-snoop reads. Derived from unc_c_tor_inserts.opcode.pcie_read", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_NS_READ", + "Filter": "filter_opc=0x1e4", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe non-snoop writes (partial). Derived from unc_c_tor_inserts.opcode.pcie_partial_write", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_NS_PARTIAL_WRITE", + "Filter": "filter_opc=0x1e5", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe non-snoop writes (full line). Derived from unc_c_tor_inserts.opcode.pcie_full_write", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_NS_WRITE", + "Filter": "filter_opc=0x1e6", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Occupancy for all LLC misses that are addressed to local memory", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.MISS_LOCAL", + "PerPkg": "1", + "UMask": "0x2A", + "Unit": "CBO" + }, + { + "BriefDescription": "Occupancy counter for LLC data reads (demand and L2 prefetch). Derived from unc_c_tor_occupancy.miss_opcode.llc_data_read", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.LLC_DATA_READ", + "Filter": "filter_opc=0x182", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "Occupancy for all LLC misses that are addressed to remote memory", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.MISS_REMOTE", + "PerPkg": "1", + "UMask": "0x8A", + "Unit": "CBO" + }, + { + "BriefDescription": "Read requests to home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.READS", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "HA" + }, + { + "BriefDescription": "Write requests to home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.WRITES", + "PerPkg": "1", + "UMask": "0xC", + "Unit": "HA" + }, + { + "BriefDescription": "M line forwarded from remote cache along with writeback to memory", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x20", + "Unit": "HA" + }, + { + "BriefDescription": "M line forwarded from remote cache with no writeback to memory", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPIFWD", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x4", + "Unit": "HA" + }, + { + "BriefDescription": "Shared line response from remote cache", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPS", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x2", + "Unit": "HA" + }, + { + "BriefDescription": "Shared line forwarded from remote cache", + "Counter": "0,1,2,3", + "EventCode": "0x21", + "EventName": "UNC_H_SNOOP_RESP.RSPSFWD", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x8", + "Unit": "HA" + } +] diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json new file mode 100644 index 000000000000..b798a860bc81 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json @@ -0,0 +1,48 @@ +[ + { + "BriefDescription": "QPI clock ticks. Use to get percentages for QPI cycles events", + "Counter": "0,1,2,3", + "EventCode": "0x14", + "EventName": "UNC_Q_CLOCKTICKS", + "PerPkg": "1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Cycles where receiving QPI link is in half-width mode", + "Counter": "0,1,2,3", + "EventCode": "0x10", + "EventName": "UNC_Q_RxL0P_POWER_CYCLES", + "MetricExpr": "(UNC_Q_RxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.", + "MetricName": "rxl0p_power_cycles %", + "PerPkg": "1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Cycles where transmitting QPI link is in half-width mode", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_Q_TxL0P_POWER_CYCLES", + "MetricExpr": "(UNC_Q_TxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.", + "MetricName": "txl0p_power_cycles %", + "PerPkg": "1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Number of data flits transmitted ", + "Counter": "0,1,2,3", + "EventName": "UNC_Q_TxL_FLITS_G0.DATA", + "PerPkg": "1", + "ScaleUnit": "8Bytes", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Number of non data (control) flits transmitted ", + "Counter": "0,1,2,3", + "EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA", + "PerPkg": "1", + "ScaleUnit": "8Bytes", + "UMask": "0x4", + "Unit": "QPI LL" + } +] diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-memory.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-memory.json new file mode 100644 index 000000000000..df4b43294fa0 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-memory.json @@ -0,0 +1,78 @@ +[ + { + "BriefDescription": "Memory page activates for reads and writes", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_M_ACT_COUNT.RD", + "PerPkg": "1", + "UMask": "0x1", + "Umask": "0x3", + "Unit": "iMC" + }, + { + "BriefDescription": "Read requests to memory controller. Derived from unc_m_cas_count.rd", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "LLC_MISSES.MEM_READ", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "iMC" + }, + { + "BriefDescription": "Write requests to memory controller. Derived from unc_m_cas_count.wr", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "LLC_MISSES.MEM_WRITE", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0xC", + "Unit": "iMC" + }, + { + "BriefDescription": "Memory controller clock ticks. Use to generate percentages for memory controller CYCLES events", + "Counter": "0,1,2,3", + "EventName": "UNC_M_CLOCKTICKS", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode", + "Counter": "0,1,2,3", + "EventCode": "0x85", + "EventName": "UNC_M_POWER_CHANNEL_PPD", + "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.", + "MetricName": "power_channel_ppd %", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles all ranks are in critical thermal throttle", + "Counter": "0,1,2,3", + "EventCode": "0x86", + "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES", + "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.", + "MetricName": "power_critical_throttle_cycles %", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles Memory is in self refresh power mode", + "Counter": "0,1,2,3", + "EventCode": "0x43", + "EventName": "UNC_M_POWER_SELF_REFRESH", + "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.", + "MetricName": "power_self_refresh %", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Memory page conflicts", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.PAGE_MISS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + } +] diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json new file mode 100644 index 000000000000..d40498f2cb1e --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json @@ -0,0 +1,274 @@ +[ + { + "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events", + "Counter": "0,1,2,3", + "EventName": "UNC_P_CLOCKTICKS", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band0=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency", + "Counter": "0,1,2,3", + "EventCode": "0xb", + "EventName": "UNC_P_FREQ_BAND0_CYCLES", + "MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_band0_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band1=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency", + "Counter": "0,1,2,3", + "EventCode": "0xc", + "EventName": "UNC_P_FREQ_BAND1_CYCLES", + "MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_band1_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band2=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_P_FREQ_BAND2_CYCLES", + "MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_band2_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency", + "Counter": "0,1,2,3", + "EventCode": "0xe", + "EventName": "UNC_P_FREQ_BAND3_CYCLES", + "MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_band3_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of times that the uncore transitioned a frequency greater than or equal to the frequency that is configured in the filter. (filter_band0=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band0_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xb", + "EventName": "UNC_P_FREQ_BAND0_TRANSITIONS", + "Filter": "edge=1", + "MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_band0_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of times that the uncore transitioned to a frequency greater than or equal to the frequency that is configured in the filter. (filter_band1=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band1_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xc", + "EventName": "UNC_P_FREQ_BAND1_TRANSITIONS", + "Filter": "edge=1", + "MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_band1_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to the frequency that is configured in the filter. (filter_band2=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band2_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_P_FREQ_BAND2_TRANSITIONS", + "Filter": "edge=1", + "MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_band2_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to the frequency that is configured in the filter. (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band3_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xe", + "EventName": "UNC_P_FREQ_BAND3_TRANSITIONS", + "Filter": "edge=1", + "MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_band3_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C0. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0", + "Filter": "occ_sel=1", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "power_state_occupancy.cores_c0 %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C3. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3", + "Filter": "occ_sel=2", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "power_state_occupancy.cores_c3 %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C6. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events ", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6", + "Filter": "occ_sel=3", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "power_state_occupancy.cores_c6 %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode. This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip", + "Counter": "0,1,2,3", + "EventCode": "0xa", + "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES", + "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "prochot_external_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when temperature is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_max_limit_thermal_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x6", + "EventName": "UNC_P_FREQ_MAX_OS_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_max_os_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when power is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x5", + "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_max_power_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when current is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x7", + "EventName": "UNC_P_FREQ_MAX_CURRENT_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_CURRENT_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_max_current_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Cycles spent changing Frequency", + "Counter": "0,1,2,3", + "EventCode": "0x60", + "EventName": "UNC_P_FREQ_TRANS_CYCLES", + "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_trans_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 1.2Ghz. Derived from unc_p_freq_band0_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xb", + "EventName": "UNC_P_FREQ_GE_1200MHZ_CYCLES", + "Filter": "filter_band0=1200", + "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_ge_1200mhz_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 2Ghz. Derived from unc_p_freq_band1_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xc", + "EventName": "UNC_P_FREQ_GE_2000MHZ_CYCLES", + "Filter": "filter_band1=2000", + "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_ge_2000mhz_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 3Ghz. Derived from unc_p_freq_band2_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_P_FREQ_GE_3000MHZ_CYCLES", + "Filter": "filter_band2=3000", + "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_ge_3000mhz_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 4Ghz. Derived from unc_p_freq_band3_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xe", + "EventName": "UNC_P_FREQ_GE_4000MHZ_CYCLES", + "Filter": "filter_band3=4000", + "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_ge_4000mhz_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of times that the uncore transitioned to a frequency greater than or equal to 1.2Ghz. Derived from unc_p_freq_band0_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xb", + "EventName": "UNC_P_FREQ_GE_1200MHZ_TRANSITIONS", + "Filter": "edge=1,filter_band0=1200", + "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_ge_1200mhz_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of times that the uncore transitioned to a frequency greater than or equal to 2Ghz. Derived from unc_p_freq_band1_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xc", + "EventName": "UNC_P_FREQ_GE_2000MHZ_TRANSITIONS", + "Filter": "edge=1,filter_band1=2000", + "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_ge_2000mhz_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to 3Ghz. Derived from unc_p_freq_band2_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_P_FREQ_GE_3000MHZ_TRANSITIONS", + "Filter": "edge=1,filter_band2=4000", + "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_ge_3000mhz_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to 4Ghz. Derived from unc_p_freq_band3_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xe", + "EventName": "UNC_P_FREQ_GE_4000MHZ_TRANSITIONS", + "Filter": "edge=1,filter_band3=4000", + "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_ge_4000mhz_cycles %", + "PerPkg": "1", + "Unit": "PCU" + } +] diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json new file mode 100644 index 000000000000..3fa61d962607 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json @@ -0,0 +1,210 @@ +[ + { + "BriefDescription": "Uncore cache clock ticks", + "Counter": "0,1,2,3", + "EventName": "UNC_C_CLOCKTICKS", + "PerPkg": "1", + "Unit": "CBO" + }, + { + "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch)", + "Counter": "0,1", + "EventCode": "0x34", + "EventName": "UNC_C_LLC_LOOKUP.ANY", + "Filter": "filter_state=0x1", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x11", + "Unit": "CBO" + }, + { + "BriefDescription": "M line evictions from LLC (writebacks to memory)", + "Counter": "0,1", + "EventCode": "0x37", + "EventName": "UNC_C_LLC_VICTIMS.M_STATE", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses - demand and prefetch data reads - excludes LLC prefetches. Derived from unc_c_tor_inserts.miss_opcode.demand", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.DATA_READ", + "Filter": "filter_opc=0x182", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses - Uncacheable reads. Derived from unc_c_tor_inserts.miss_opcode.uncacheable", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.UNCACHEABLE", + "Filter": "filter_opc=0x187", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe allocating writes that miss LLC - DDIO misses. Derived from unc_c_tor_inserts.miss_opcode.ddio_miss", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.PCIE_WRITE", + "Filter": "filter_opc=0x19c", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "LLC misses for ItoM writes (as part of fast string memcpy stores). Derived from unc_c_tor_inserts.miss_opcode.itom_write", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_MISSES.ITOM_WRITE", + "Filter": "filter_opc=0x1c8", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "Streaming stores (full cache line). Derived from unc_c_tor_inserts.opcode.streaming_full", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_FULL", + "Filter": "filter_opc=0x18c", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Streaming stores (partial cache line). Derived from unc_c_tor_inserts.opcode.streaming_partial", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_PARTIAL", + "Filter": "filter_opc=0x18d", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Partial PCIe reads. Derived from unc_c_tor_inserts.opcode.pcie_partial", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_PARTIAL_READ", + "Filter": "filter_opc=0x195", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe allocating writes that hit in LLC (DDIO hits). Derived from unc_c_tor_inserts.opcode.ddio_hit", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_WRITE", + "Filter": "filter_opc=0x19c", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe read current. Derived from unc_c_tor_inserts.opcode.pcie_read_current", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_READ", + "Filter": "filter_opc=0x19e", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "ItoM write hits (as part of fast string memcpy stores). Derived from unc_c_tor_inserts.opcode.itom_write_hit", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.ITOM_WRITE", + "Filter": "filter_opc=0x1c8", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe non-snoop reads. Derived from unc_c_tor_inserts.opcode.pcie_read", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_NS_READ", + "Filter": "filter_opc=0x1e4", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe non-snoop writes (partial). Derived from unc_c_tor_inserts.opcode.pcie_partial_write", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_NS_PARTIAL_WRITE", + "Filter": "filter_opc=0x1e5", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "PCIe non-snoop writes (full line). Derived from unc_c_tor_inserts.opcode.pcie_full_write", + "Counter": "0,1", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.PCIE_NS_WRITE", + "Filter": "filter_opc=0x1e6", + "PerPkg": "1", + "ScaleUnit": "64Bytes", + "UMask": "0x1", + "Unit": "CBO" + }, + { + "BriefDescription": "Occupancy counter for all LLC misses; we divide this by UNC_C_CLOCKTICKS to get average Q depth", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.MISS_ALL", + "Filter": "filter_opc=0x182", + "MetricExpr": "(UNC_C_TOR_OCCUPANCY.MISS_ALL / UNC_C_CLOCKTICKS) * 100.", + "MetricName": "tor_occupancy.miss_all %", + "PerPkg": "1", + "UMask": "0xa", + "Unit": "CBO" + }, + { + "BriefDescription": "Occupancy counter for LLC data reads (demand and L2 prefetch). Derived from unc_c_tor_occupancy.miss_opcode.llc_data_read", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.LLC_DATA_READ", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "CBO" + }, + { + "BriefDescription": "read requests to home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.READS", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "HA" + }, + { + "BriefDescription": "write requests to home agent", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_H_REQUESTS.WRITES", + "PerPkg": "1", + "UMask": "0xc", + "Unit": "HA" + } +] diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json new file mode 100644 index 000000000000..1b53c0e609e3 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json @@ -0,0 +1,48 @@ +[ + { + "BriefDescription": "QPI clock ticks. Used to get percentages of QPI cycles events", + "Counter": "0,1,2,3", + "EventCode": "0x14", + "EventName": "UNC_Q_CLOCKTICKS", + "PerPkg": "1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Cycles where receiving QPI link is in half-width mode", + "Counter": "0,1,2,3", + "EventCode": "0x10", + "EventName": "UNC_Q_RxL0P_POWER_CYCLES", + "MetricExpr": "(UNC_Q_RxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.", + "MetricName": "rxl0p_power_cycles %", + "PerPkg": "1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Cycles where transmitting QPI link is in half-width mode", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_Q_TxL0P_POWER_CYCLES", + "MetricExpr": "(UNC_Q_TxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.", + "MetricName": "txl0p_power_cycles %", + "PerPkg": "1", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Number of data flits transmitted ", + "Counter": "0,1,2,3", + "EventName": "UNC_Q_TxL_FLITS_G0.DATA", + "PerPkg": "1", + "ScaleUnit": "8Bytes", + "UMask": "0x2", + "Unit": "QPI LL" + }, + { + "BriefDescription": "Number of non data (control) flits transmitted ", + "Counter": "0,1,2,3", + "EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA", + "PerPkg": "1", + "ScaleUnit": "8Bytes", + "UMask": "0x4", + "Unit": "QPI LL" + } +] diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-memory.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-memory.json new file mode 100644 index 000000000000..8551cebeba23 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-memory.json @@ -0,0 +1,82 @@ +[ + { + "BriefDescription": "Memory page activates", + "Counter": "0,1,2,3", + "EventCode": "0x1", + "EventName": "UNC_M_ACT_COUNT", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "LLC_MISSES.MEM_READ", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "iMC" + }, + { + "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "LLC_MISSES.MEM_WRITE", + "PerPkg": "1", + "UMask": "0xc", + "Unit": "iMC" + }, + { + "BriefDescription": "Memory controller clock ticks. Used to get percentages of memory controller cycles events", + "Counter": "0,1,2,3", + "EventName": "UNC_M_CLOCKTICKS", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode", + "Counter": "0,1,2,3", + "EventCode": "0x85", + "EventName": "UNC_M_POWER_CHANNEL_PPD", + "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.", + "MetricName": "power_channel_ppd %", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles all ranks are in critical thermal throttle", + "Counter": "0,1,2,3", + "EventCode": "0x86", + "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES", + "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.", + "MetricName": "power_critical_throttle_cycles %", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Cycles Memory is in self refresh power mode", + "Counter": "0,1,2,3", + "EventCode": "0x43", + "EventName": "UNC_M_POWER_SELF_REFRESH", + "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.", + "MetricName": "power_self_refresh %", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Memory page conflicts", + "Counter": "0,1,2,3", + "EventCode": "0x2", + "EventName": "UNC_M_PRE_COUNT.PAGE_MISS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "Occupancy counter for memory read queue", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_M_RPQ_OCCUPANCY", + "PerPkg": "1", + "Unit": "iMC" + } +] diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json new file mode 100644 index 000000000000..16034bfd06dd --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json @@ -0,0 +1,273 @@ +[ + { + "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events", + "Counter": "0,1,2,3", + "EventName": "UNC_P_CLOCKTICKS", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band0=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency", + "Counter": "0,1,2,3", + "EventCode": "0xb", + "EventName": "UNC_P_FREQ_BAND0_CYCLES", + "MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_band0_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band1=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency", + "Counter": "0,1,2,3", + "EventCode": "0xc", + "EventName": "UNC_P_FREQ_BAND1_CYCLES", + "MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_band1_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band2=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_P_FREQ_BAND2_CYCLES", + "MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_band2_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency", + "Counter": "0,1,2,3", + "EventCode": "0xe", + "EventName": "UNC_P_FREQ_BAND3_CYCLES", + "MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_band3_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of times that the uncore transitioned a frequency greater than or equal to the frequency that is configured in the filter. (filter_band0=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band0_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xb", + "EventName": "UNC_P_FREQ_BAND0_TRANSITIONS", + "Filter": "edge=1", + "MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_band0_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of times that the uncore transistioned to a frequency greater than or equal to the frequency that is configured in the filter. (filter_band1=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band1_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xc", + "EventName": "UNC_P_FREQ_BAND1_TRANSITIONS", + "Filter": "edge=1", + "MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_band1_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to the frequency that is configured in the filter. (filter_band2=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band2_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_P_FREQ_BAND2_TRANSITIONS", + "Filter": "edge=1", + "MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_band2_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to the frequency that is configured in the filter. (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band3_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xe", + "EventName": "UNC_P_FREQ_BAND3_TRANSITIONS", + "Filter": "edge=1", + "MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_band3_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C0. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0", + "Filter": "occ_sel=1", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "power_state_occupancy.cores_c0 %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C3. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3", + "Filter": "occ_sel=2", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "power_state_occupancy.cores_c3 %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C6. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events ", + "Counter": "0,1,2,3", + "EventCode": "0x80", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6", + "Filter": "occ_sel=3", + "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "power_state_occupancy.cores_c6 %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode. This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip", + "Counter": "0,1,2,3", + "EventCode": "0xa", + "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES", + "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "prochot_external_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when temperature is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x4", + "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_max_limit_thermal_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x6", + "EventName": "UNC_P_FREQ_MAX_OS_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_max_os_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when power is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x5", + "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_max_power_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles when current is the upper limit on frequency", + "Counter": "0,1,2,3", + "EventCode": "0x7", + "EventName": "UNC_P_FREQ_MAX_CURRENT_CYCLES", + "MetricExpr": "(UNC_P_FREQ_MAX_CURRENT_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_max_current_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Cycles spent changing Frequency", + "Counter": "0,1,2,3", + "EventName": "UNC_P_FREQ_TRANS_CYCLES", + "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_trans_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 1.2Ghz. Derived from unc_p_freq_band0_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xb", + "EventName": "UNC_P_FREQ_GE_1200MHZ_CYCLES", + "Filter": "filter_band0=1200", + "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_ge_1200mhz_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 2Ghz. Derived from unc_p_freq_band1_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xc", + "EventName": "UNC_P_FREQ_GE_2000MHZ_CYCLES", + "Filter": "filter_band1=2000", + "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_ge_2000mhz_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 3Ghz. Derived from unc_p_freq_band2_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_P_FREQ_GE_3000MHZ_CYCLES", + "Filter": "filter_band2=3000", + "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_ge_3000mhz_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 4Ghz. Derived from unc_p_freq_band3_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xe", + "EventName": "UNC_P_FREQ_GE_4000MHZ_CYCLES", + "Filter": "filter_band3=4000", + "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_ge_4000mhz_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of times that the uncore transitioned to a frequency greater than or equal to 1.2Ghz. Derived from unc_p_freq_band0_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xb", + "EventName": "UNC_P_FREQ_GE_1200MHZ_TRANSITIONS", + "Filter": "edge=1,filter_band0=1200", + "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_ge_1200mhz_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of times that the uncore transitioned to a frequency greater than or equal to 2Ghz. Derived from unc_p_freq_band1_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xc", + "EventName": "UNC_P_FREQ_GE_2000MHZ_TRANSITIONS", + "Filter": "edge=1,filter_band1=2000", + "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_ge_2000mhz_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to 3Ghz. Derived from unc_p_freq_band2_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xd", + "EventName": "UNC_P_FREQ_GE_3000MHZ_TRANSITIONS", + "Filter": "edge=1,filter_band2=4000", + "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_ge_3000mhz_cycles %", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to 4Ghz. Derived from unc_p_freq_band3_cycles", + "Counter": "0,1,2,3", + "EventCode": "0xe", + "EventName": "UNC_P_FREQ_GE_4000MHZ_TRANSITIONS", + "Filter": "edge=1,filter_band3=4000", + "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.", + "MetricName": "freq_ge_4000mhz_cycles %", + "PerPkg": "1", + "Unit": "PCU" + } +] diff --git a/tools/perf/pmu-events/arch/x86/knightslanding/uncore-memory.json b/tools/perf/pmu-events/arch/x86/knightslanding/uncore-memory.json new file mode 100644 index 000000000000..e3bcd86c4f56 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/knightslanding/uncore-memory.json @@ -0,0 +1,42 @@ +[ + { + "BriefDescription": "ddr bandwidth read (CPU traffic only) (MB/sec). ", + "Counter": "0,1,2,3", + "EventCode": "0x03", + "EventName": "UNC_M_CAS_COUNT.RD", + "PerPkg": "1", + "ScaleUnit": "6.4e-05MiB", + "UMask": "0x01", + "Unit": "imc" + }, + { + "BriefDescription": "ddr bandwidth write (CPU traffic only) (MB/sec). ", + "Counter": "0,1,2,3", + "EventCode": "0x03", + "EventName": "UNC_M_CAS_COUNT.WR", + "PerPkg": "1", + "ScaleUnit": "6.4e-05MiB", + "UMask": "0x02", + "Unit": "imc" + }, + { + "BriefDescription": "mcdram bandwidth read (CPU traffic only) (MB/sec). ", + "Counter": "0,1,2,3", + "EventCode": "0x01", + "EventName": "UNC_E_RPQ_INSERTS", + "PerPkg": "1", + "ScaleUnit": "6.4e-05MiB", + "UMask": "0x01", + "Unit": "edc_eclk" + }, + { + "BriefDescription": "mcdram bandwidth write (CPU traffic only) (MB/sec). ", + "Counter": "0,1,2,3", + "EventCode": "0x02", + "EventName": "UNC_E_WPQ_INSERTS", + "PerPkg": "1", + "ScaleUnit": "6.4e-05MiB", + "UMask": "0x01", + "Unit": "edc_eclk" + } +] diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index 12181bb1da2a..d1a12e584c1b 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -17,6 +17,7 @@ GenuineIntel-6-3A,v18,ivybridge,core GenuineIntel-6-3E,v19,ivytown,core GenuineIntel-6-2D,v20,jaketown,core GenuineIntel-6-57,v9,knightslanding,core +GenuineIntel-6-85,v9,knightslanding,core GenuineIntel-6-1E,v2,nehalemep,core GenuineIntel-6-1F,v2,nehalemep,core GenuineIntel-6-1A,v2,nehalemep,core diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/uncore.json b/tools/perf/pmu-events/arch/x86/sandybridge/uncore.json new file mode 100644 index 000000000000..42c70eed05a2 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/sandybridge/uncore.json @@ -0,0 +1,314 @@ +[ + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x01", + "EventName": "UNC_CBO_XSNP_RESPONSE.MISS", + "BriefDescription": "A snoop misses in some processor core.", + "PublicDescription": "A snoop misses in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x02", + "EventName": "UNC_CBO_XSNP_RESPONSE.INVAL", + "BriefDescription": "A snoop invalidates a non-modified line in some processor core.", + "PublicDescription": "A snoop invalidates a non-modified line in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x04", + "EventName": "UNC_CBO_XSNP_RESPONSE.HIT", + "BriefDescription": "A snoop hits a non-modified line in some processor core.", + "PublicDescription": "A snoop hits a non-modified line in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x08", + "EventName": "UNC_CBO_XSNP_RESPONSE.HITM", + "BriefDescription": "A snoop hits a modified line in some processor core.", + "PublicDescription": "A snoop hits a modified line in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x10", + "EventName": "UNC_CBO_XSNP_RESPONSE.INVAL_M", + "BriefDescription": "A snoop invalidates a modified line in some processor core.", + "PublicDescription": "A snoop invalidates a modified line in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x20", + "EventName": "UNC_CBO_XSNP_RESPONSE.EXTERNAL_FILTER", + "BriefDescription": "Filter on cross-core snoops initiated by this Cbox due to external snoop request.", + "PublicDescription": "Filter on cross-core snoops initiated by this Cbox due to external snoop request.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x40", + "EventName": "UNC_CBO_XSNP_RESPONSE.XCORE_FILTER", + "BriefDescription": "Filter on cross-core snoops initiated by this Cbox due to processor core memory request.", + "PublicDescription": "Filter on cross-core snoops initiated by this Cbox due to processor core memory request.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x80", + "EventName": "UNC_CBO_XSNP_RESPONSE.EVICTION_FILTER", + "BriefDescription": "Filter on cross-core snoops initiated by this Cbox due to LLC eviction.", + "PublicDescription": "Filter on cross-core snoops initiated by this Cbox due to LLC eviction.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x01", + "EventName": "UNC_CBO_CACHE_LOOKUP.M", + "BriefDescription": "LLC lookup request that access cache and found line in M-state.", + "PublicDescription": "LLC lookup request that access cache and found line in M-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x02", + "EventName": "UNC_CBO_CACHE_LOOKUP.E", + "BriefDescription": "LLC lookup request that access cache and found line in E-state.", + "PublicDescription": "LLC lookup request that access cache and found line in E-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x04", + "EventName": "UNC_CBO_CACHE_LOOKUP.S", + "BriefDescription": "LLC lookup request that access cache and found line in S-state.", + "PublicDescription": "LLC lookup request that access cache and found line in S-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x08", + "EventName": "UNC_CBO_CACHE_LOOKUP.I", + "BriefDescription": "LLC lookup request that access cache and found line in I-state.", + "PublicDescription": "LLC lookup request that access cache and found line in I-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x10", + "EventName": "UNC_CBO_CACHE_LOOKUP.READ_FILTER", + "BriefDescription": "Filter on processor core initiated cacheable read requests.", + "PublicDescription": "Filter on processor core initiated cacheable read requests.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x20", + "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_FILTER", + "BriefDescription": "Filter on processor core initiated cacheable write requests.", + "PublicDescription": "Filter on processor core initiated cacheable write requests.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x40", + "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_FILTER", + "BriefDescription": "Filter on external snoop requests.", + "PublicDescription": "Filter on external snoop requests.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x80", + "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_REQUEST_FILTER", + "BriefDescription": "Filter on any IRQ or IPQ initiated requests including uncacheable, non-coherent requests.", + "PublicDescription": "Filter on any IRQ or IPQ initiated requests including uncacheable, non-coherent requests.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "ARB", + "EventCode": "0x80", + "UMask": "0x01", + "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL", + "BriefDescription": "Counts cycles weighted by the number of requests waiting for data returning from the memory controller. Accounts for coherent and non-coherent requests initiated by IA cores, processor graphic units, or LLC.", + "PublicDescription": "Counts cycles weighted by the number of requests waiting for data returning from the memory controller. Accounts for coherent and non-coherent requests initiated by IA cores, processor graphic units, or LLC.", + "Counter": "0", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "ARB", + "EventCode": "0x81", + "UMask": "0x01", + "EventName": "UNC_ARB_TRK_REQUESTS.ALL", + "BriefDescription": "Counts the number of coherent and in-coherent requests initiated by IA cores, processor graphic units, or LLC.", + "PublicDescription": "Counts the number of coherent and in-coherent requests initiated by IA cores, processor graphic units, or LLC.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "ARB", + "EventCode": "0x81", + "UMask": "0x20", + "EventName": "UNC_ARB_TRK_REQUESTS.WRITES", + "BriefDescription": "Counts the number of allocated write entries, include full, partial, and LLC evictions.", + "PublicDescription": "Counts the number of allocated write entries, include full, partial, and LLC evictions.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "ARB", + "EventCode": "0x81", + "UMask": "0x80", + "EventName": "UNC_ARB_TRK_REQUESTS.EVICTIONS", + "BriefDescription": "Counts the number of LLC evictions allocated.", + "PublicDescription": "Counts the number of LLC evictions allocated.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "ARB", + "EventCode": "0x83", + "UMask": "0x01", + "EventName": "UNC_ARB_COH_TRK_OCCUPANCY.ALL", + "BriefDescription": "Cycles weighted by number of requests pending in Coherency Tracker.", + "PublicDescription": "Cycles weighted by number of requests pending in Coherency Tracker.", + "Counter": "0", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "ARB", + "EventCode": "0x84", + "UMask": "0x01", + "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL", + "BriefDescription": "Number of requests allocated in Coherency Tracker.", + "PublicDescription": "Number of requests allocated in Coherency Tracker.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "ARB", + "EventCode": "0x80", + "UMask": "0x01", + "EventName": "UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST", + "BriefDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.", + "PublicDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.", + "Counter": "0,1", + "CounterMask": "1", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "ARB", + "EventCode": "0x80", + "UMask": "0x01", + "EventName": "UNC_ARB_TRK_OCCUPANCY.CYCLES_OVER_HALF_FULL", + "BriefDescription": "Cycles with at least half of the requests outstanding are waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.", + "PublicDescription": "Cycles with at least half of the requests outstanding are waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.", + "Counter": "0,1", + "CounterMask": "10", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "ARB", + "EventCode": "0x0", + "UMask": "0x01", + "EventName": "UNC_CLOCK.SOCKET", + "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles.", + "PublicDescription": "This 48-bit fixed counter counts the UCLK cycles.", + "Counter": "Fixed", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x06", + "EventName": "UNC_CBO_CACHE_LOOKUP.ES", + "BriefDescription": "LLC lookup request that access cache and found line in E-state or S-state.", + "PublicDescription": "LLC lookup request that access cache and found line in E-state or S-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/skylake/uncore.json b/tools/perf/pmu-events/arch/x86/skylake/uncore.json new file mode 100644 index 000000000000..dbc193252fb3 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/skylake/uncore.json @@ -0,0 +1,254 @@ +[ + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x41", + "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_XCORE", + "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.", + "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x81", + "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_EVICTION", + "BriefDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.", + "PublicDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x44", + "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_XCORE", + "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.", + "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x22", + "UMask": "0x48", + "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_XCORE", + "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.", + "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x21", + "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_M", + "BriefDescription": "L3 Lookup write request that access cache and found line in M-state", + "PublicDescription": "L3 Lookup write request that access cache and found line in M-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x81", + "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_M", + "BriefDescription": "L3 Lookup any request that access cache and found line in M-state", + "PublicDescription": "L3 Lookup any request that access cache and found line in M-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x18", + "EventName": "UNC_CBO_CACHE_LOOKUP.READ_I", + "BriefDescription": "L3 Lookup read request that access cache and found line in I-state", + "PublicDescription": "L3 Lookup read request that access cache and found line in I-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x88", + "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_I", + "BriefDescription": "L3 Lookup any request that access cache and found line in I-state", + "PublicDescription": "L3 Lookup any request that access cache and found line in I-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x1f", + "EventName": "UNC_CBO_CACHE_LOOKUP.READ_MESI", + "BriefDescription": "L3 Lookup read request that access cache and found line in any MESI-state", + "PublicDescription": "L3 Lookup read request that access cache and found line in any MESI-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x2f", + "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_MESI", + "BriefDescription": "L3 Lookup write request that access cache and found line in MESI-state", + "PublicDescription": "L3 Lookup write request that access cache and found line in MESI-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x8f", + "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_MESI", + "BriefDescription": "L3 Lookup any request that access cache and found line in MESI-state", + "PublicDescription": "L3 Lookup any request that access cache and found line in MESI-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x86", + "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_ES", + "BriefDescription": "L3 Lookup any request that access cache and found line in E or S-state", + "PublicDescription": "L3 Lookup any request that access cache and found line in E or S-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x16", + "EventName": "UNC_CBO_CACHE_LOOKUP.READ_ES", + "BriefDescription": "L3 Lookup read request that access cache and found line in E or S-state", + "PublicDescription": "L3 Lookup read request that access cache and found line in E or S-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "CBO", + "EventCode": "0x34", + "UMask": "0x26", + "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_ES", + "BriefDescription": "L3 Lookup write request that access cache and found line in E or S-state", + "PublicDescription": "L3 Lookup write request that access cache and found line in E or S-state.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "iMPH-U", + "EventCode": "0x80", + "UMask": "0x01", + "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL", + "BriefDescription": "Each cycle count number of all Core outgoing valid entries. Such entry is defined as valid from its allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.", + "PublicDescription": "Each cycle count number of all Core outgoing valid entries. Such entry is defined as valid from its allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.", + "Counter": "0", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "iMPH-U", + "EventCode": "0x81", + "UMask": "0x01", + "EventName": "UNC_ARB_TRK_REQUESTS.ALL", + "BriefDescription": "Total number of Core outgoing entries allocated. Accounts for Coherent and non-coherent traffic.", + "PublicDescription": "Total number of Core outgoing entries allocated. Accounts for Coherent and non-coherent traffic.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "iMPH-U", + "EventCode": "0x81", + "UMask": "0x02", + "EventName": "UNC_ARB_TRK_REQUESTS.DRD_DIRECT", + "BriefDescription": "Number of Core coherent Data Read entries allocated in DirectData mode", + "PublicDescription": "Number of Core coherent Data Read entries allocated in DirectData mode.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "iMPH-U", + "EventCode": "0x81", + "UMask": "0x20", + "EventName": "UNC_ARB_TRK_REQUESTS.WRITES", + "BriefDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.", + "PublicDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "iMPH-U", + "EventCode": "0x84", + "UMask": "0x01", + "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL", + "BriefDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.", + "PublicDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.", + "Counter": "0,1", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "iMPH-U", + "EventCode": "0x80", + "UMask": "0x01", + "EventName": "UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST", + "BriefDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.;", + "PublicDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.", + "Counter": "0", + "CounterMask": "1", + "Invert": "0", + "EdgeDetect": "0" + }, + { + "Unit": "NCU", + "EventCode": "0x0", + "UMask": "0x01", + "EventName": "UNC_CLOCK.SOCKET", + "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles", + "PublicDescription": "This 48-bit fixed counter counts the UCLK cycles.", + "Counter": "FIXED", + "CounterMask": "0", + "Invert": "0", + "EdgeDetect": "0" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index 41611d7f9873..baa073f38334 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -135,7 +135,6 @@ static struct field { const char *field; const char *kernel; } fields[] = { - { "EventCode", "event=" }, { "UMask", "umask=" }, { "CounterMask", "cmask=" }, { "Invert", "inv=" }, @@ -189,6 +188,28 @@ static struct msrmap *lookup_msr(char *map, jsmntok_t *val) return NULL; } +static struct map { + const char *json; + const char *perf; +} unit_to_pmu[] = { + { "CBO", "uncore_cbox" }, + { "QPI LL", "uncore_qpi" }, + { "SBO", "uncore_sbox" }, + { "iMPH-U", "uncore_arb" }, + {} +}; + +static const char *field_to_perf(struct map *table, char *map, jsmntok_t *val) +{ + int i; + + for (i = 0; table[i].json; i++) { + if (json_streq(map, val, table[i].json)) + return table[i].perf; + } + return NULL; +} + #define EXPECT(e, t, m) do { if (!(e)) { \ jsmntok_t *loc = (t); \ if (!(t)->start && (t) > tokens) \ @@ -270,7 +291,10 @@ static void print_events_table_prefix(FILE *fp, const char *tblname) } static int print_events_table_entry(void *data, char *name, char *event, - char *desc, char *long_desc) + char *desc, char *long_desc, + char *pmu, char *unit, char *perpkg, + char *metric_expr, + char *metric_name) { struct perf_entry_data *pd = data; FILE *outfp = pd->outfp; @@ -288,7 +312,16 @@ static int print_events_table_entry(void *data, char *name, char *event, fprintf(outfp, "\t.topic = \"%s\",\n", topic); if (long_desc && long_desc[0]) fprintf(outfp, "\t.long_desc = \"%s\",\n", long_desc); - + if (pmu) + fprintf(outfp, "\t.pmu = \"%s\",\n", pmu); + if (unit) + fprintf(outfp, "\t.unit = \"%s\",\n", unit); + if (perpkg) + fprintf(outfp, "\t.perpkg = \"%s\",\n", perpkg); + if (metric_expr) + fprintf(outfp, "\t.metric_expr = \"%s\",\n", metric_expr); + if (metric_name) + fprintf(outfp, "\t.metric_name = \"%s\",\n", metric_name); fprintf(outfp, "},\n"); return 0; @@ -335,7 +368,10 @@ static char *real_event(const char *name, char *event) /* Call func with each event in the json file */ int json_events(const char *fn, int (*func)(void *data, char *name, char *event, char *desc, - char *long_desc), + char *long_desc, + char *pmu, char *unit, char *perpkg, + char *metric_expr, + char *metric_name), void *data) { int err = -EIO; @@ -343,6 +379,7 @@ int json_events(const char *fn, jsmntok_t *tokens, *tok; int i, j, len; char *map; + char buf[128]; if (!fn) return -ENOENT; @@ -356,6 +393,13 @@ int json_events(const char *fn, char *event = NULL, *desc = NULL, *name = NULL; char *long_desc = NULL; char *extra_desc = NULL; + char *pmu = NULL; + char *filter = NULL; + char *perpkg = NULL; + char *unit = NULL; + char *metric_expr = NULL; + char *metric_name = NULL; + unsigned long long eventcode = 0; struct msrmap *msr = NULL; jsmntok_t *msrval = NULL; jsmntok_t *precise = NULL; @@ -365,6 +409,7 @@ int json_events(const char *fn, for (j = 0; j < obj->size; j += 2) { jsmntok_t *field, *val; int nz; + char *s; field = tok + j; EXPECT(field->type == JSMN_STRING, tok + j, @@ -376,6 +421,16 @@ int json_events(const char *fn, nz = !json_streq(map, val, "0"); if (match_field(map, field, nz, &event, val)) { /* ok */ + } else if (json_streq(map, field, "EventCode")) { + char *code = NULL; + addfield(map, &code, "", "", val); + eventcode |= strtoul(code, NULL, 0); + free(code); + } else if (json_streq(map, field, "ExtSel")) { + char *code = NULL; + addfield(map, &code, "", "", val); + eventcode |= strtoul(code, NULL, 0) << 21; + free(code); } else if (json_streq(map, field, "EventName")) { addfield(map, &name, "", "", val); } else if (json_streq(map, field, "BriefDescription")) { @@ -399,6 +454,34 @@ int json_events(const char *fn, addfield(map, &extra_desc, ". ", " Supports address when precise", NULL); + } else if (json_streq(map, field, "Unit")) { + const char *ppmu; + + ppmu = field_to_perf(unit_to_pmu, map, val); + if (ppmu) { + pmu = strdup(ppmu); + } else { + if (!pmu) + pmu = strdup("uncore_"); + addfield(map, &pmu, "", "", val); + for (s = pmu; *s; s++) + *s = tolower(*s); + } + addfield(map, &desc, ". ", "Unit: ", NULL); + addfield(map, &desc, "", pmu, NULL); + addfield(map, &desc, "", " ", NULL); + } else if (json_streq(map, field, "Filter")) { + addfield(map, &filter, "", "", val); + } else if (json_streq(map, field, "ScaleUnit")) { + addfield(map, &unit, "", "", val); + } else if (json_streq(map, field, "PerPkg")) { + addfield(map, &perpkg, "", "", val); + } else if (json_streq(map, field, "MetricName")) { + addfield(map, &metric_name, "", "", val); + } else if (json_streq(map, field, "MetricExpr")) { + addfield(map, &metric_expr, "", "", val); + for (s = metric_expr; *s; s++) + *s = tolower(*s); } /* ignore unknown fields */ } @@ -410,20 +493,31 @@ int json_events(const char *fn, addfield(map, &extra_desc, " ", "(Precise event)", NULL); } + snprintf(buf, sizeof buf, "event=%#llx", eventcode); + addfield(map, &event, ",", buf, NULL); if (desc && extra_desc) addfield(map, &desc, " ", extra_desc, NULL); if (long_desc && extra_desc) addfield(map, &long_desc, " ", extra_desc, NULL); + if (filter) + addfield(map, &event, ",", filter, NULL); if (msr != NULL) addfield(map, &event, ",", msr->pname, msrval); fixname(name); - err = func(data, name, real_event(name, event), desc, long_desc); + err = func(data, name, real_event(name, event), desc, long_desc, + pmu, unit, perpkg, metric_expr, metric_name); free(event); free(desc); free(name); free(long_desc); free(extra_desc); + free(pmu); + free(filter); + free(perpkg); + free(unit); + free(metric_expr); + free(metric_name); if (err) break; tok += j; diff --git a/tools/perf/pmu-events/jevents.h b/tools/perf/pmu-events/jevents.h index b0eb2744b498..611fac01913d 100644 --- a/tools/perf/pmu-events/jevents.h +++ b/tools/perf/pmu-events/jevents.h @@ -3,7 +3,10 @@ int json_events(const char *fn, int (*func)(void *data, char *name, char *event, char *desc, - char *long_desc), + char *long_desc, + char *pmu, + char *unit, char *perpkg, char *metric_expr, + char *metric_name), void *data); char *get_cpu_str(void); diff --git a/tools/perf/pmu-events/json.c b/tools/perf/pmu-events/json.c index f67bbb0aa36e..0544398d6e2d 100644 --- a/tools/perf/pmu-events/json.c +++ b/tools/perf/pmu-events/json.c @@ -49,7 +49,7 @@ static char *mapfile(const char *fn, size_t *size) int err; int fd = open(fn, O_RDONLY); - if (fd < 0 && verbose && fn) { + if (fd < 0 && verbose > 0 && fn) { pr_err("Error opening events file '%s': %s\n", fn, strerror(errno)); } diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h index 2eaef595d8a0..569eab3688dd 100644 --- a/tools/perf/pmu-events/pmu-events.h +++ b/tools/perf/pmu-events/pmu-events.h @@ -10,6 +10,11 @@ struct pmu_event { const char *desc; const char *topic; const char *long_desc; + const char *pmu; + const char *unit; + const char *perpkg; + const char *metric_expr; + const char *metric_name; }; /* diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build index 6676c2dd6dcb..af58ebc243ef 100644 --- a/tools/perf/tests/Build +++ b/tools/perf/tests/Build @@ -38,12 +38,14 @@ perf-y += cpumap.o perf-y += stat.o perf-y += event_update.o perf-y += event-times.o +perf-y += expr.o perf-y += backward-ring-buffer.o perf-y += sdt.o perf-y += is_printable_array.o perf-y += bitmap.o perf-y += perf-hooks.o perf-y += clang.o +perf-y += unit_number__scnprintf.o $(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build $(call rule_mkdir) diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c index 28d1605b0338..0dd77494bb58 100644 --- a/tools/perf/tests/attr.c +++ b/tools/perf/tests/attr.c @@ -18,10 +18,16 @@ * permissions. All the event text files are stored there. */ +#include <errno.h> +#include <inttypes.h> #include <stdlib.h> #include <stdio.h> #include <linux/types.h> #include <linux/kernel.h> +#include <sys/param.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> #include "../perf.h" #include "util.h" #include <subcmd/exec-cmd.h> @@ -144,7 +150,7 @@ static int run_dir(const char *d, const char *perf) int vcnt = min(verbose, (int) sizeof(v) - 1); char cmd[3*PATH_MAX]; - if (verbose) + if (verbose > 0) vcnt++; snprintf(cmd, 3*PATH_MAX, PYTHON " %s/attr.py -d %s/attr/ -p %s %.*s", diff --git a/tools/perf/tests/backward-ring-buffer.c b/tools/perf/tests/backward-ring-buffer.c index 42e892b1e979..50f6d7afee58 100644 --- a/tools/perf/tests/backward-ring-buffer.c +++ b/tools/perf/tests/backward-ring-buffer.c @@ -8,6 +8,7 @@ #include <sys/prctl.h> #include "tests.h" #include "debug.h" +#include <errno.h> #define NR_ITERS 111 diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c index 92343f43e44a..5876da126b58 100644 --- a/tools/perf/tests/bpf.c +++ b/tools/perf/tests/bpf.c @@ -1,15 +1,21 @@ +#include <errno.h> #include <stdio.h> #include <sys/epoll.h> +#include <sys/types.h> +#include <sys/stat.h> #include <util/util.h> #include <util/bpf-loader.h> #include <util/evlist.h> #include <linux/bpf.h> #include <linux/filter.h> +#include <linux/kernel.h> +#include <api/fs/fs.h> #include <bpf/bpf.h> #include "tests.h" #include "llvm.h" #include "debug.h" #define NR_ITERS 111 +#define PERF_TEST_BPF_PATH "/sys/fs/bpf/perf_test" #ifdef HAVE_LIBBPF_SUPPORT @@ -54,6 +60,7 @@ static struct { const char *msg_load_fail; int (*target_func)(void); int expect_result; + bool pin; } bpf_testcase_table[] = { { LLVM_TESTCASE_BASE, @@ -63,6 +70,17 @@ static struct { "load bpf object failed", &epoll_wait_loop, (NR_ITERS + 1) / 2, + false, + }, + { + LLVM_TESTCASE_BASE, + "BPF pinning", + "[bpf_pinning]", + "fix kbuild first", + "check your vmlinux setting?", + &epoll_wait_loop, + (NR_ITERS + 1) / 2, + true, }, #ifdef HAVE_BPF_PROLOGUE { @@ -73,6 +91,7 @@ static struct { "check your vmlinux setting?", &llseek_loop, (NR_ITERS + 1) / 4, + false, }, #endif { @@ -83,6 +102,7 @@ static struct { "libbpf error when dealing with relocation", NULL, 0, + false, }, }; @@ -226,10 +246,34 @@ static int __test__bpf(int idx) goto out; } - if (obj) + if (obj) { ret = do_test(obj, bpf_testcase_table[idx].target_func, bpf_testcase_table[idx].expect_result); + if (ret != TEST_OK) + goto out; + if (bpf_testcase_table[idx].pin) { + int err; + + if (!bpf_fs__mount()) { + pr_debug("BPF filesystem not mounted\n"); + ret = TEST_FAIL; + goto out; + } + err = mkdir(PERF_TEST_BPF_PATH, 0777); + if (err && errno != EEXIST) { + pr_debug("Failed to make perf_test dir: %s\n", + strerror(errno)); + ret = TEST_FAIL; + goto out; + } + if (bpf_object__pin(obj, PERF_TEST_BPF_PATH)) + ret = TEST_FAIL; + if (rm_rf(PERF_TEST_BPF_PATH)) + ret = TEST_FAIL; + } + } + out: bpf__clear(); return ret; diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index a77dcc0d24e3..9e08d297f1a9 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -3,8 +3,10 @@ * * Builtin regression testing command: ever growing number of sanity tests */ +#include <errno.h> #include <unistd.h> #include <string.h> +#include <sys/wait.h> #include "builtin.h" #include "hist.h" #include "intlist.h" @@ -13,6 +15,7 @@ #include "color.h" #include <subcmd/parse-options.h> #include "symbol.h" +#include <linux/kernel.h> static bool dont_fork; @@ -44,6 +47,10 @@ static struct test generic_tests[] = { .func = test__parse_events, }, { + .desc = "Simple expression parser", + .func = test__expr, + }, + { .desc = "PERF_RECORD_* events & perf_sample fields", .func = test__PERF_RECORD, }, @@ -247,6 +254,10 @@ static struct test generic_tests[] = { } }, { + .desc = "unit_number__scnprintf", + .func = test__unit_number__scnprint, + }, + { .func = NULL, }, }; @@ -295,7 +306,7 @@ static int run_test(struct test *test, int subtest) if (!dont_fork) { pr_debug("test child forked, pid %d\n", getpid()); - if (!verbose) { + if (verbose <= 0) { int nullfd = open("/dev/null", O_WRONLY); if (nullfd >= 0) { @@ -456,7 +467,7 @@ static int perf_test__list(int argc, const char **argv) return 0; } -int cmd_test(int argc, const char **argv, const char *prefix __maybe_unused) +int cmd_test(int argc, const char **argv) { const char *test_usage[] = { "perf test [<options>] [{list <test-name-fragment>|[<test-name-fragments>|<test-numbers>]}]", diff --git a/tools/perf/tests/clang.c b/tools/perf/tests/clang.c index f853e242a86c..c5bb2203f5a9 100644 --- a/tools/perf/tests/clang.c +++ b/tools/perf/tests/clang.c @@ -2,6 +2,7 @@ #include "debug.h" #include "util.h" #include "c++/clang-c.h" +#include <linux/kernel.h> static struct { int (*func)(void); diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index ff5bc6363a79..1f14e7612cbb 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -1,9 +1,12 @@ +#include <errno.h> +#include <linux/kernel.h> #include <linux/types.h> +#include <inttypes.h> #include <stdlib.h> #include <unistd.h> #include <stdio.h> -#include <ctype.h> #include <string.h> +#include <sys/param.h> #include "parse-events.h" #include "evlist.h" @@ -16,6 +19,8 @@ #include "tests.h" +#include "sane_ctype.h" + #define BUFSZ 1024 #define READLEN 128 @@ -599,7 +604,7 @@ static int do_test_code_reading(bool try_kcore) continue; } - if (verbose) { + if (verbose > 0) { char errbuf[512]; perf_evlist__strerror_open(evlist, errno, errbuf, sizeof(errbuf)); pr_debug("perf_evlist__open() failed!\n%s\n", errbuf); diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c index f168a85992d0..4478773cdb97 100644 --- a/tools/perf/tests/cpumap.c +++ b/tools/perf/tests/cpumap.c @@ -66,7 +66,7 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused, TEST_ASSERT_VAL("wrong nr", map->nr == 2); TEST_ASSERT_VAL("wrong cpu", map->map[0] == 1); TEST_ASSERT_VAL("wrong cpu", map->map[1] == 256); - TEST_ASSERT_VAL("wrong refcnt", atomic_read(&map->refcnt) == 1); + TEST_ASSERT_VAL("wrong refcnt", refcount_read(&map->refcnt) == 1); cpu_map__put(map); return 0; } diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c index 13725e09ba22..8f08df5861cb 100644 --- a/tools/perf/tests/dso-data.c +++ b/tools/perf/tests/dso-data.c @@ -1,4 +1,6 @@ +#include <dirent.h> #include <stdlib.h> +#include <linux/kernel.h> #include <linux/types.h> #include <sys/stat.h> #include <fcntl.h> diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c index 1046491de4b2..dfe5c89e2049 100644 --- a/tools/perf/tests/dwarf-unwind.c +++ b/tools/perf/tests/dwarf-unwind.c @@ -1,5 +1,6 @@ #include <linux/compiler.h> #include <linux/types.h> +#include <inttypes.h> #include <unistd.h> #include "tests.h" #include "debug.h" diff --git a/tools/perf/tests/event-times.c b/tools/perf/tests/event-times.c index 19ef77bd6eb4..634f20c631d8 100644 --- a/tools/perf/tests/event-times.c +++ b/tools/perf/tests/event-times.c @@ -1,5 +1,8 @@ #include <linux/compiler.h> +#include <errno.h> +#include <inttypes.h> #include <string.h> +#include <sys/wait.h> #include "tests.h" #include "evlist.h" #include "evsel.h" diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c index 60926a1f6fd7..d2bea6f780f8 100644 --- a/tools/perf/tests/evsel-roundtrip-name.c +++ b/tools/perf/tests/evsel-roundtrip-name.c @@ -3,6 +3,8 @@ #include "parse-events.h" #include "tests.h" #include "debug.h" +#include <errno.h> +#include <linux/kernel.h> static int perf_evsel__roundtrip_cache_name_test(void) { diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c new file mode 100644 index 000000000000..6c6a3749aaf6 --- /dev/null +++ b/tools/perf/tests/expr.c @@ -0,0 +1,56 @@ +#include "util/debug.h" +#include "util/expr.h" +#include "tests.h" +#include <stdlib.h> + +static int test(struct parse_ctx *ctx, const char *e, double val2) +{ + double val; + + if (expr__parse(&val, ctx, &e)) + TEST_ASSERT_VAL("parse test failed", 0); + TEST_ASSERT_VAL("unexpected value", val == val2); + return 0; +} + +int test__expr(int subtest __maybe_unused) +{ + const char *p; + const char **other; + double val; + int ret; + struct parse_ctx ctx; + int num_other; + + expr__ctx_init(&ctx); + expr__add_id(&ctx, "FOO", 1); + expr__add_id(&ctx, "BAR", 2); + + ret = test(&ctx, "1+1", 2); + ret |= test(&ctx, "FOO+BAR", 3); + ret |= test(&ctx, "(BAR/2)%2", 1); + ret |= test(&ctx, "1 - -4", 5); + ret |= test(&ctx, "(FOO-1)*2 + (BAR/2)%2 - -4", 5); + + if (ret) + return ret; + + p = "FOO/0"; + ret = expr__parse(&val, &ctx, &p); + TEST_ASSERT_VAL("division by zero", ret == 1); + + p = "BAR/"; + ret = expr__parse(&val, &ctx, &p); + TEST_ASSERT_VAL("missing operand", ret == 1); + + TEST_ASSERT_VAL("find other", + expr__find_other("FOO + BAR + BAZ + BOZO", "FOO", &other, &num_other) == 0); + TEST_ASSERT_VAL("find other", num_other == 3); + TEST_ASSERT_VAL("find other", !strcmp(other[0], "BAR")); + TEST_ASSERT_VAL("find other", !strcmp(other[1], "BAZ")); + TEST_ASSERT_VAL("find other", !strcmp(other[2], "BOZO")); + TEST_ASSERT_VAL("find other", other[3] == NULL); + free((void *)other); + + return 0; +} diff --git a/tools/perf/tests/fdarray.c b/tools/perf/tests/fdarray.c index a2b5ff9bf83d..bc5982f42dc3 100644 --- a/tools/perf/tests/fdarray.c +++ b/tools/perf/tests/fdarray.c @@ -19,7 +19,7 @@ static int fdarray__fprintf_prefix(struct fdarray *fda, const char *prefix, FILE { int printed = 0; - if (!verbose) + if (verbose <= 0) return 0; printed += fprintf(fp, "\n%s: ", prefix); diff --git a/tools/perf/tests/hists_common.c b/tools/perf/tests/hists_common.c index 6b21746d6eec..00b8dc50f3db 100644 --- a/tools/perf/tests/hists_common.c +++ b/tools/perf/tests/hists_common.c @@ -1,3 +1,4 @@ +#include <inttypes.h> #include "perf.h" #include "util/debug.h" #include "util/symbol.h" @@ -7,6 +8,7 @@ #include "util/machine.h" #include "util/thread.h" #include "tests/hists_common.h" +#include <linux/kernel.h> static struct { u32 pid; diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c index 9fd54b79a788..d549a9f2c41b 100644 --- a/tools/perf/tests/hists_cumulate.c +++ b/tools/perf/tests/hists_cumulate.c @@ -1,5 +1,6 @@ #include "perf.h" #include "util/debug.h" +#include "util/event.h" #include "util/symbol.h" #include "util/sort.h" #include "util/evsel.h" @@ -9,6 +10,7 @@ #include "util/parse-events.h" #include "tests/tests.h" #include "tests/hists_common.h" +#include <linux/kernel.h> struct sample { u32 pid; diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c index 62efb14f3a5a..df9c91f49af1 100644 --- a/tools/perf/tests/hists_filter.c +++ b/tools/perf/tests/hists_filter.c @@ -3,12 +3,14 @@ #include "util/symbol.h" #include "util/sort.h" #include "util/evsel.h" +#include "util/event.h" #include "util/evlist.h" #include "util/machine.h" #include "util/thread.h" #include "util/parse-events.h" #include "tests/tests.h" #include "tests/hists_common.h" +#include <linux/kernel.h> struct sample { u32 pid; diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c index eddc7407ff8a..a26cbb79e988 100644 --- a/tools/perf/tests/hists_link.c +++ b/tools/perf/tests/hists_link.c @@ -9,6 +9,8 @@ #include "thread.h" #include "parse-events.h" #include "hists_common.h" +#include <errno.h> +#include <linux/kernel.h> struct sample { u32 pid; diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c index 63c5efaba1b5..06e5080182d3 100644 --- a/tools/perf/tests/hists_output.c +++ b/tools/perf/tests/hists_output.c @@ -1,5 +1,6 @@ #include "perf.h" #include "util/debug.h" +#include "util/event.h" #include "util/symbol.h" #include "util/sort.h" #include "util/evsel.h" @@ -9,6 +10,7 @@ #include "util/parse-events.h" #include "tests/tests.h" #include "tests/hists_common.h" +#include <linux/kernel.h> struct sample { u32 cpu; diff --git a/tools/perf/tests/is_printable_array.c b/tools/perf/tests/is_printable_array.c index 42e13393e502..a5192f6a20d7 100644 --- a/tools/perf/tests/is_printable_array.c +++ b/tools/perf/tests/is_printable_array.c @@ -1,7 +1,8 @@ #include <linux/compiler.h> +#include <linux/kernel.h> #include "tests.h" #include "debug.h" -#include "util.h" +#include "print_binary.h" int test__is_printable_array(int subtest __maybe_unused) { diff --git a/tools/perf/tests/kmod-path.c b/tools/perf/tests/kmod-path.c index 76f41f249944..6cd9e5107f77 100644 --- a/tools/perf/tests/kmod-path.c +++ b/tools/perf/tests/kmod-path.c @@ -61,6 +61,7 @@ int test__kmod_path__parse(int subtest __maybe_unused) M("/xxxx/xxxx/x-x.ko", PERF_RECORD_MISC_KERNEL, true); M("/xxxx/xxxx/x-x.ko", PERF_RECORD_MISC_USER, false); +#ifdef HAVE_ZLIB_SUPPORT /* path alloc_name alloc_ext kmod comp name ext */ T("/xxxx/xxxx/x.ko.gz", true , true , true, true, "[x]", "gz"); T("/xxxx/xxxx/x.ko.gz", false , true , true, true, NULL , "gz"); @@ -96,6 +97,7 @@ int test__kmod_path__parse(int subtest __maybe_unused) M("x.ko.gz", PERF_RECORD_MISC_CPUMODE_UNKNOWN, true); M("x.ko.gz", PERF_RECORD_MISC_KERNEL, true); M("x.ko.gz", PERF_RECORD_MISC_USER, false); +#endif /* path alloc_name alloc_ext kmod comp name ext */ T("[test_module]", true , true , true, false, "[test_module]", NULL); diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c index 02a33ebcd992..482b5365e68d 100644 --- a/tools/perf/tests/llvm.c +++ b/tools/perf/tests/llvm.c @@ -13,7 +13,7 @@ static int test__bpf_parsing(void *obj_buf, size_t obj_buf_sz) struct bpf_object *obj; obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, NULL); - if (IS_ERR(obj)) + if (libbpf_get_error(obj)) return TEST_FAIL; bpf_object__close(obj); return TEST_OK; @@ -76,7 +76,7 @@ test_llvm__fetch_bpf_obj(void **p_obj_buf, * Skip this test if user's .perfconfig doesn't set [llvm] section * and clang is not found in $PATH, and this is not perf test -v */ - if (!force && (verbose == 0 && + if (!force && (verbose <= 0 && !llvm_param.user_set_param && llvm__search_clang())) { pr_debug("No clang and no verbosive, skip this test\n"); diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c index 634bce9caebd..15c770856aac 100644 --- a/tools/perf/tests/mmap-basic.c +++ b/tools/perf/tests/mmap-basic.c @@ -1,3 +1,5 @@ +#include <errno.h> +#include <inttypes.h> /* For the CLR_() macros */ #include <pthread.h> @@ -7,6 +9,7 @@ #include "cpumap.h" #include "tests.h" #include <linux/err.h> +#include <linux/kernel.h> /* * This test will generate random numbers of calls to some getpid syscalls, diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c index 0c5ce44f723f..6ea4d8a5d26b 100644 --- a/tools/perf/tests/mmap-thread-lookup.c +++ b/tools/perf/tests/mmap-thread-lookup.c @@ -1,3 +1,4 @@ +#include <inttypes.h> #include <unistd.h> #include <sys/syscall.h> #include <sys/types.h> @@ -11,6 +12,7 @@ #include "thread_map.h" #include "symbol.h" #include "thread.h" +#include "util.h" #define THREADS 4 diff --git a/tools/perf/tests/openat-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c index c8d9592eb142..1a74dd9fd067 100644 --- a/tools/perf/tests/openat-syscall-all-cpus.c +++ b/tools/perf/tests/openat-syscall-all-cpus.c @@ -1,8 +1,14 @@ +#include <errno.h> +#include <inttypes.h> /* For the CPU_* macros */ #include <pthread.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> #include <api/fs/fs.h> #include <linux/err.h> +#include <api/fs/tracing_path.h> #include "evsel.h" #include "tests.h" #include "thread_map.h" diff --git a/tools/perf/tests/openat-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c index f52239fed361..9788fac91095 100644 --- a/tools/perf/tests/openat-syscall-tp-fields.c +++ b/tools/perf/tests/openat-syscall-tp-fields.c @@ -5,6 +5,7 @@ #include "thread_map.h" #include "tests.h" #include "debug.h" +#include <errno.h> #ifndef O_DIRECTORY #define O_DIRECTORY 00200000 diff --git a/tools/perf/tests/openat-syscall.c b/tools/perf/tests/openat-syscall.c index d7414128d7fe..e44506e21ee7 100644 --- a/tools/perf/tests/openat-syscall.c +++ b/tools/perf/tests/openat-syscall.c @@ -1,5 +1,10 @@ +#include <errno.h> +#include <inttypes.h> #include <api/fs/tracing_path.h> #include <linux/err.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> #include "thread_map.h" #include "evsel.h" #include "debug.h" diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index 20c2e641c422..7fad885491c5 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -1,4 +1,3 @@ - #include "parse-events.h" #include "evsel.h" #include "evlist.h" @@ -6,8 +5,15 @@ #include "tests.h" #include "debug.h" #include "util.h" +#include <dirent.h> +#include <errno.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> +#include <linux/kernel.h> #include <linux/hw_breakpoint.h> #include <api/fs/fs.h> +#include <api/fs/tracing_path.h> #define PERF_TP_SAMPLE_TYPE (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | \ PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD) @@ -1779,15 +1785,14 @@ static int test_pmu_events(void) } while (!ret && (ent = readdir(dir))) { -#define MAX_NAME 100 struct evlist_test e; - char name[MAX_NAME]; + char name[2 * NAME_MAX + 1 + 12 + 3]; /* Names containing . are special and cannot be used directly */ if (strchr(ent->d_name, '.')) continue; - snprintf(name, MAX_NAME, "cpu/event=%s/u", ent->d_name); + snprintf(name, sizeof(name), "cpu/event=%s/u", ent->d_name); e.name = name; e.check = test__checkevent_pmu_events; @@ -1795,11 +1800,10 @@ static int test_pmu_events(void) ret = test_event(&e); if (ret) break; - snprintf(name, MAX_NAME, "%s:u,cpu/event=%s/u", ent->d_name, ent->d_name); + snprintf(name, sizeof(name), "%s:u,cpu/event=%s/u", ent->d_name, ent->d_name); e.name = name; e.check = test__checkevent_pmu_events_mix; ret = test_event(&e); -#undef MAX_NAME } closedir(dir); @@ -1810,7 +1814,7 @@ static void debug_warn(const char *warn, va_list params) { char msg[1024]; - if (!verbose) + if (verbose <= 0) return; vsnprintf(msg, sizeof(msg), warn, params); diff --git a/tools/perf/tests/parse-no-sample-id-all.c b/tools/perf/tests/parse-no-sample-id-all.c index 81c6eeaca0f5..c6207db09f12 100644 --- a/tools/perf/tests/parse-no-sample-id-all.c +++ b/tools/perf/tests/parse-no-sample-id-all.c @@ -1,3 +1,4 @@ +#include <linux/kernel.h> #include <linux/types.h> #include <stddef.h> @@ -50,7 +51,8 @@ static int process_events(union perf_event **events, size_t count) } struct test_attr_event { - struct attr_event attr; + struct perf_event_header header; + struct perf_event_attr attr; u64 id; }; @@ -71,20 +73,16 @@ int test__parse_no_sample_id_all(int subtest __maybe_unused) int err; struct test_attr_event event1 = { - .attr = { - .header = { - .type = PERF_RECORD_HEADER_ATTR, - .size = sizeof(struct test_attr_event), - }, + .header = { + .type = PERF_RECORD_HEADER_ATTR, + .size = sizeof(struct test_attr_event), }, .id = 1, }; struct test_attr_event event2 = { - .attr = { - .header = { - .type = PERF_RECORD_HEADER_ATTR, - .size = sizeof(struct test_attr_event), - }, + .header = { + .type = PERF_RECORD_HEADER_ATTR, + .size = sizeof(struct test_attr_event), }, .id = 2, }; diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c index 8f2e1de6d0ea..d37cd9588cc0 100644 --- a/tools/perf/tests/perf-record.c +++ b/tools/perf/tests/perf-record.c @@ -1,3 +1,5 @@ +#include <errno.h> +#include <inttypes.h> /* For the CLR_() macros */ #include <pthread.h> @@ -66,7 +68,7 @@ int test__PERF_RECORD(int subtest __maybe_unused) if (evlist == NULL) /* Fallback for kernels lacking PERF_COUNT_SW_DUMMY */ evlist = perf_evlist__new_default(); - if (evlist == NULL || argv == NULL) { + if (evlist == NULL) { pr_debug("Not enough memory to create evlist\n"); goto out; } @@ -172,13 +174,13 @@ int test__PERF_RECORD(int subtest __maybe_unused) err = perf_evlist__parse_sample(evlist, event, &sample); if (err < 0) { - if (verbose) + if (verbose > 0) perf_event__fprintf(event, stderr); pr_debug("Couldn't parse sample\n"); goto out_delete_evlist; } - if (verbose) { + if (verbose > 0) { pr_info("%" PRIu64" %d ", sample.time, sample.cpu); perf_event__fprintf(event, stderr); } diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c index 1e2ba2602930..a6d7aef30030 100644 --- a/tools/perf/tests/pmu.c +++ b/tools/perf/tests/pmu.c @@ -2,6 +2,8 @@ #include "pmu.h" #include "util.h" #include "tests.h" +#include <errno.h> +#include <linux/kernel.h> /* Simulated format definitions. */ static struct test_format { diff --git a/tools/perf/tests/python-use.c b/tools/perf/tests/python-use.c index 7a52834ee0d0..fa79509da535 100644 --- a/tools/perf/tests/python-use.c +++ b/tools/perf/tests/python-use.c @@ -15,7 +15,7 @@ int test__python_use(int subtest __maybe_unused) int ret; if (asprintf(&cmd, "echo \"import sys ; sys.path.append('%s'); import perf\" | %s %s", - PYTHONPATH, PYTHON, verbose ? "" : "2> /dev/null") < 0) + PYTHONPATH, PYTHON, verbose > 0 ? "" : "2> /dev/null") < 0) return -1; ret = system(cmd) ? -1 : 0; diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c index 5f23710b9fee..bac5c3885b3b 100644 --- a/tools/perf/tests/sample-parsing.c +++ b/tools/perf/tests/sample-parsing.c @@ -1,4 +1,6 @@ #include <stdbool.h> +#include <inttypes.h> +#include <linux/kernel.h> #include <linux/types.h> #include "util.h" diff --git a/tools/perf/tests/sdt.c b/tools/perf/tests/sdt.c index f59d210e1baf..06eda675ae2c 100644 --- a/tools/perf/tests/sdt.c +++ b/tools/perf/tests/sdt.c @@ -1,6 +1,6 @@ +#include <errno.h> #include <stdio.h> #include <sys/epoll.h> -#include <util/util.h> #include <util/evlist.h> #include <linux/filter.h> #include "tests.h" @@ -43,7 +43,7 @@ static char *get_self_path(void) { char *buf = calloc(PATH_MAX, sizeof(char)); - if (buf && readlink("/proc/self/exe", buf, PATH_MAX) < 0) { + if (buf && readlink("/proc/self/exe", buf, PATH_MAX - 1) < 0) { pr_debug("Failed to get correct path of perf\n"); free(buf); return NULL; diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c index 4c9fd046d57b..828494db4a19 100644 --- a/tools/perf/tests/sw-clock.c +++ b/tools/perf/tests/sw-clock.c @@ -1,3 +1,5 @@ +#include <errno.h> +#include <inttypes.h> #include <unistd.h> #include <stdlib.h> #include <signal.h> diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c index 7ddbe267d0ac..65474fd80da7 100644 --- a/tools/perf/tests/switch-tracking.c +++ b/tools/perf/tests/switch-tracking.c @@ -1,5 +1,6 @@ #include <sys/time.h> #include <sys/prctl.h> +#include <errno.h> #include <time.h> #include <stdlib.h> diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c index 01a5ba2788c6..32873ec91a4e 100644 --- a/tools/perf/tests/task-exit.c +++ b/tools/perf/tests/task-exit.c @@ -4,6 +4,7 @@ #include "cpumap.h" #include "tests.h" +#include <errno.h> #include <signal.h> static int exited; diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index a512f0c8ff5b..631859629403 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -62,6 +62,7 @@ int test__sample_parsing(int subtest); int test__keep_tracking(int subtest); int test__parse_no_sample_id_all(int subtest); int test__dwarf_unwind(int subtest); +int test__expr(int subtest); int test__hists_filter(int subtest); int test__mmap_thread_lookup(int subtest); int test__thread_mg_share(int subtest); @@ -96,6 +97,7 @@ int test__perf_hooks(int subtest); int test__clang(int subtest); const char *test__clang_subtest_get_desc(int subtest); int test__clang_subtest_get_nr(void); +int test__unit_number__scnprint(int subtest); #if defined(__arm__) || defined(__aarch64__) #ifdef HAVE_DWARF_UNWIND_SUPPORT diff --git a/tools/perf/tests/thread-map.c b/tools/perf/tests/thread-map.c index a4a4b4625ac3..a63d6945807b 100644 --- a/tools/perf/tests/thread-map.c +++ b/tools/perf/tests/thread-map.c @@ -29,7 +29,7 @@ int test__thread_map(int subtest __maybe_unused) thread_map__comm(map, 0) && !strcmp(thread_map__comm(map, 0), NAME)); TEST_ASSERT_VAL("wrong refcnt", - atomic_read(&map->refcnt) == 1); + refcount_read(&map->refcnt) == 1); thread_map__put(map); /* test dummy pid */ @@ -44,7 +44,7 @@ int test__thread_map(int subtest __maybe_unused) thread_map__comm(map, 0) && !strcmp(thread_map__comm(map, 0), "dummy")); TEST_ASSERT_VAL("wrong refcnt", - atomic_read(&map->refcnt) == 1); + refcount_read(&map->refcnt) == 1); thread_map__put(map); return 0; } @@ -71,7 +71,7 @@ static int process_event(struct perf_tool *tool __maybe_unused, thread_map__comm(threads, 0) && !strcmp(thread_map__comm(threads, 0), NAME)); TEST_ASSERT_VAL("wrong refcnt", - atomic_read(&threads->refcnt) == 1); + refcount_read(&threads->refcnt) == 1); thread_map__put(threads); return 0; } @@ -109,7 +109,7 @@ int test__thread_map_remove(int subtest __maybe_unused) TEST_ASSERT_VAL("failed to allocate thread_map", threads); - if (verbose) + if (verbose > 0) thread_map__fprintf(threads, stderr); TEST_ASSERT_VAL("failed to remove thread", @@ -117,7 +117,7 @@ int test__thread_map_remove(int subtest __maybe_unused) TEST_ASSERT_VAL("thread_map count != 1", threads->nr == 1); - if (verbose) + if (verbose > 0) thread_map__fprintf(threads, stderr); TEST_ASSERT_VAL("failed to remove thread", @@ -125,7 +125,7 @@ int test__thread_map_remove(int subtest __maybe_unused) TEST_ASSERT_VAL("thread_map count != 0", threads->nr == 0); - if (verbose) + if (verbose > 0) thread_map__fprintf(threads, stderr); TEST_ASSERT_VAL("failed to not remove thread", diff --git a/tools/perf/tests/thread-mg-share.c b/tools/perf/tests/thread-mg-share.c index 188b63140fc8..76686dd6f5ec 100644 --- a/tools/perf/tests/thread-mg-share.c +++ b/tools/perf/tests/thread-mg-share.c @@ -43,7 +43,7 @@ int test__thread_mg_share(int subtest __maybe_unused) leader && t1 && t2 && t3 && other); mg = leader->mg; - TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 4); + TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&mg->refcnt), 4); /* test the map groups pointer is shared */ TEST_ASSERT_VAL("map groups don't match", mg == t1->mg); @@ -71,25 +71,25 @@ int test__thread_mg_share(int subtest __maybe_unused) machine__remove_thread(machine, other_leader); other_mg = other->mg; - TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&other_mg->refcnt), 2); + TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&other_mg->refcnt), 2); TEST_ASSERT_VAL("map groups don't match", other_mg == other_leader->mg); /* release thread group */ thread__put(leader); - TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 3); + TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&mg->refcnt), 3); thread__put(t1); - TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 2); + TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&mg->refcnt), 2); thread__put(t2); - TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 1); + TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&mg->refcnt), 1); thread__put(t3); /* release other group */ thread__put(other_leader); - TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&other_mg->refcnt), 1); + TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&other_mg->refcnt), 1); thread__put(other); diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c index 98fe69ac553c..803f893550d6 100644 --- a/tools/perf/tests/topology.c +++ b/tools/perf/tests/topology.c @@ -65,7 +65,9 @@ static int check_cpu_topology(char *path, struct cpu_map *map) session = perf_session__new(&file, false, NULL); TEST_ASSERT_VAL("can't get session", session); - for (i = 0; i < session->header.env.nr_cpus_online; i++) { + for (i = 0; i < session->header.env.nr_cpus_avail; i++) { + if (!cpu_map__has(map, i)) + continue; pr_debug("CPU %d, core %d, socket %d\n", i, session->header.env.cpu[i].core_id, session->header.env.cpu[i].socket_id); diff --git a/tools/perf/tests/unit_number__scnprintf.c b/tools/perf/tests/unit_number__scnprintf.c new file mode 100644 index 000000000000..44589de084b8 --- /dev/null +++ b/tools/perf/tests/unit_number__scnprintf.c @@ -0,0 +1,38 @@ +#include <inttypes.h> +#include <linux/compiler.h> +#include <linux/types.h> +#include "tests.h" +#include "units.h" +#include "debug.h" + +int test__unit_number__scnprint(int subtest __maybe_unused) +{ + struct { + u64 n; + const char *str; + } test[] = { + { 1, "1B" }, + { 10*1024, "10K" }, + { 20*1024*1024, "20M" }, + { 30*1024*1024*1024ULL, "30G" }, + { 0, "0B" }, + { 0, NULL }, + }; + unsigned i = 0; + + while (test[i].str) { + char buf[100]; + + unit_number__scnprintf(buf, sizeof(buf), test[i].n); + + pr_debug("n %" PRIu64 ", str '%s', buf '%s'\n", + test[i].n, test[i].str, buf); + + if (strcmp(test[i].str, buf)) + return TEST_FAIL; + + i++; + } + + return TEST_OK; +} diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c index a5082331f246..8456175fc234 100644 --- a/tools/perf/tests/vmlinux-kallsyms.c +++ b/tools/perf/tests/vmlinux-kallsyms.c @@ -1,5 +1,6 @@ #include <linux/compiler.h> #include <linux/rbtree.h> +#include <inttypes.h> #include <string.h> #include "map.h" #include "symbol.h" @@ -168,7 +169,7 @@ next_pair: err = -1; } - if (!verbose) + if (verbose <= 0) goto out; header_printed = false; diff --git a/tools/perf/trace/beauty/Build b/tools/perf/trace/beauty/Build new file mode 100644 index 000000000000..be95ac6ce845 --- /dev/null +++ b/tools/perf/trace/beauty/Build @@ -0,0 +1 @@ +libperf-y += statx.o diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h new file mode 100644 index 000000000000..cf50be3f17a4 --- /dev/null +++ b/tools/perf/trace/beauty/beauty.h @@ -0,0 +1,24 @@ +#ifndef _PERF_TRACE_BEAUTY_H +#define _PERF_TRACE_BEAUTY_H + +#include <linux/types.h> + +struct trace; +struct thread; + +struct syscall_arg { + unsigned long val; + struct thread *thread; + struct trace *trace; + void *parm; + u8 idx; + u8 mask; +}; + +size_t syscall_arg__scnprintf_statx_flags(char *bf, size_t size, struct syscall_arg *arg); +#define SCA_STATX_FLAGS syscall_arg__scnprintf_statx_flags + +size_t syscall_arg__scnprintf_statx_mask(char *bf, size_t size, struct syscall_arg *arg); +#define SCA_STATX_MASK syscall_arg__scnprintf_statx_mask + +#endif /* _PERF_TRACE_BEAUTY_H */ diff --git a/tools/perf/trace/beauty/signum.c b/tools/perf/trace/beauty/signum.c index d3b0b1fab077..fde8f2fc6558 100644 --- a/tools/perf/trace/beauty/signum.c +++ b/tools/perf/trace/beauty/signum.c @@ -1,3 +1,4 @@ +#include <signal.h> static size_t syscall_arg__scnprintf_signum(char *bf, size_t size, struct syscall_arg *arg) { diff --git a/tools/perf/trace/beauty/statx.c b/tools/perf/trace/beauty/statx.c new file mode 100644 index 000000000000..5643b692af4c --- /dev/null +++ b/tools/perf/trace/beauty/statx.c @@ -0,0 +1,72 @@ +/* + * trace/beauty/statx.c + * + * Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com> + * + * Released under the GPL v2. (and only v2, not any later version) + */ + +#include "trace/beauty/beauty.h" +#include <linux/kernel.h> +#include <sys/types.h> +#include <uapi/linux/fcntl.h> +#include <uapi/linux/stat.h> + +size_t syscall_arg__scnprintf_statx_flags(char *bf, size_t size, struct syscall_arg *arg) +{ + int printed = 0, flags = arg->val; + + if (flags == 0) + return scnprintf(bf, size, "SYNC_AS_STAT"); +#define P_FLAG(n) \ + if (flags & AT_##n) { \ + printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ + flags &= ~AT_##n; \ + } + + P_FLAG(SYMLINK_NOFOLLOW); + P_FLAG(REMOVEDIR); + P_FLAG(SYMLINK_FOLLOW); + P_FLAG(NO_AUTOMOUNT); + P_FLAG(EMPTY_PATH); + P_FLAG(STATX_FORCE_SYNC); + P_FLAG(STATX_DONT_SYNC); + +#undef P_FLAG + + if (flags) + printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags); + + return printed; +} + +size_t syscall_arg__scnprintf_statx_mask(char *bf, size_t size, struct syscall_arg *arg) +{ + int printed = 0, flags = arg->val; + +#define P_FLAG(n) \ + if (flags & STATX_##n) { \ + printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \ + flags &= ~STATX_##n; \ + } + + P_FLAG(TYPE); + P_FLAG(MODE); + P_FLAG(NLINK); + P_FLAG(UID); + P_FLAG(GID); + P_FLAG(ATIME); + P_FLAG(MTIME); + P_FLAG(CTIME); + P_FLAG(INO); + P_FLAG(SIZE); + P_FLAG(BLOCKS); + P_FLAG(BTIME); + +#undef P_FLAG + + if (flags) + printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags); + + return printed; +} diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c index 3eb3edb307a4..a4d3762cd825 100644 --- a/tools/perf/ui/browser.c +++ b/tools/perf/ui/browser.c @@ -1,4 +1,5 @@ #include "../util.h" +#include "../string2.h" #include "../config.h" #include "../../perf.h" #include "libslang.h" @@ -13,6 +14,7 @@ #include "helpline.h" #include "keysyms.h" #include "../color.h" +#include "sane_ctype.h" static int ui_browser__percent_color(struct ui_browser *browser, double percent, bool current) @@ -579,7 +581,7 @@ static int ui_browser__color_config(const char *var, const char *value, break; *bg = '\0'; - while (isspace(*++bg)); + bg = ltrim(++bg); ui_browser__colorsets[i].bg = bg; ui_browser__colorsets[i].fg = fg; return 0; diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index ba36aac340bc..d990ad08a3c6 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -9,7 +9,10 @@ #include "../../util/symbol.h" #include "../../util/evsel.h" #include "../../util/config.h" +#include <inttypes.h> #include <pthread.h> +#include <linux/kernel.h> +#include <sys/ttydefaults.h> struct disasm_line_samples { double percent; diff --git a/tools/perf/ui/browsers/header.c b/tools/perf/ui/browsers/header.c index edbeaaf31ace..e2c9390ff4c5 100644 --- a/tools/perf/ui/browsers/header.c +++ b/tools/perf/ui/browsers/header.c @@ -8,6 +8,8 @@ #include "util/header.h" #include "util/session.h" +#include <sys/ttydefaults.h> + static void ui_browser__argv_write(struct ui_browser *browser, void *entry, int row) { diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index 641b40234a9d..69f4570bd4f9 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -1,7 +1,11 @@ +#include <dirent.h> +#include <errno.h> +#include <inttypes.h> #include <stdio.h> #include <stdlib.h> #include <string.h> #include <linux/rbtree.h> +#include <sys/ttydefaults.h> #include "../../util/evsel.h" #include "../../util/evlist.h" @@ -10,6 +14,7 @@ #include "../../util/sort.h" #include "../../util/util.h" #include "../../util/top.h" +#include "../../util/thread.h" #include "../../arch/common.h" #include "../browsers/hists.h" @@ -18,6 +23,11 @@ #include "../ui.h" #include "map.h" #include "annotate.h" +#include "srcline.h" +#include "string2.h" +#include "units.h" + +#include "sane_ctype.h" extern void hist_browser__init_hpp(void); @@ -144,9 +154,60 @@ static void callchain_list__set_folding(struct callchain_list *cl, bool unfold) cl->unfolded = unfold ? cl->has_children : false; } +static struct inline_node *inline_node__create(struct map *map, u64 ip) +{ + struct dso *dso; + struct inline_node *node; + + if (map == NULL) + return NULL; + + dso = map->dso; + if (dso == NULL) + return NULL; + + if (dso->kernel != DSO_TYPE_USER) + return NULL; + + node = dso__parse_addr_inlines(dso, + map__rip_2objdump(map, ip)); + + return node; +} + +static int inline__count_rows(struct inline_node *node) +{ + struct inline_list *ilist; + int i = 0; + + if (node == NULL) + return 0; + + list_for_each_entry(ilist, &node->val, list) { + if ((ilist->filename != NULL) || (ilist->funcname != NULL)) + i++; + } + + return i; +} + +static int callchain_list__inline_rows(struct callchain_list *chain) +{ + struct inline_node *node; + int rows; + + node = inline_node__create(chain->ms.map, chain->ip); + if (node == NULL) + return 0; + + rows = inline__count_rows(node); + inline_node__delete(node); + return rows; +} + static int callchain_node__count_rows_rb_tree(struct callchain_node *node) { - int n = 0; + int n = 0, inline_rows; struct rb_node *nd; for (nd = rb_first(&node->rb_root); nd; nd = rb_next(nd)) { @@ -156,6 +217,13 @@ static int callchain_node__count_rows_rb_tree(struct callchain_node *node) list_for_each_entry(chain, &child->val, list) { ++n; + + if (symbol_conf.inline_name) { + inline_rows = + callchain_list__inline_rows(chain); + n += inline_rows; + } + /* We need this because we may not have children */ folded_sign = callchain_list__folded(chain); if (folded_sign == '+') @@ -207,7 +275,7 @@ static int callchain_node__count_rows(struct callchain_node *node) { struct callchain_list *chain; bool unfolded = false; - int n = 0; + int n = 0, inline_rows; if (callchain_param.mode == CHAIN_FLAT) return callchain_node__count_flat_rows(node); @@ -216,6 +284,11 @@ static int callchain_node__count_rows(struct callchain_node *node) list_for_each_entry(chain, &node->val, list) { ++n; + if (symbol_conf.inline_name) { + inline_rows = callchain_list__inline_rows(chain); + n += inline_rows; + } + unfolded = chain->unfolded; } @@ -362,6 +435,19 @@ static void hist_entry__init_have_children(struct hist_entry *he) he->init_have_children = true; } +static void hist_entry_init_inline_node(struct hist_entry *he) +{ + if (he->inline_node) + return; + + he->inline_node = inline_node__create(he->ms.map, he->ip); + + if (he->inline_node == NULL) + return; + + he->has_children = true; +} + static bool hist_browser__toggle_fold(struct hist_browser *browser) { struct hist_entry *he = browser->he_selection; @@ -393,7 +479,12 @@ static bool hist_browser__toggle_fold(struct hist_browser *browser) if (he->unfolded) { if (he->leaf) - he->nr_rows = callchain__count_rows(&he->sorted_chain); + if (he->inline_node) + he->nr_rows = inline__count_rows( + he->inline_node); + else + he->nr_rows = callchain__count_rows( + &he->sorted_chain); else he->nr_rows = hierarchy_count_rows(browser, he, false); @@ -501,8 +592,8 @@ static int hierarchy_set_folding(struct hist_browser *hb, struct hist_entry *he, return n; } -static void hist_entry__set_folding(struct hist_entry *he, - struct hist_browser *hb, bool unfold) +static void __hist_entry__set_folding(struct hist_entry *he, + struct hist_browser *hb, bool unfold) { hist_entry__init_have_children(he); he->unfolded = unfold ? he->has_children : false; @@ -520,12 +611,34 @@ static void hist_entry__set_folding(struct hist_entry *he, he->nr_rows = 0; } +static void hist_entry__set_folding(struct hist_entry *he, + struct hist_browser *browser, bool unfold) +{ + double percent; + + percent = hist_entry__get_percent_limit(he); + if (he->filtered || percent < browser->min_pcnt) + return; + + __hist_entry__set_folding(he, browser, unfold); + + if (!he->depth || unfold) + browser->nr_hierarchy_entries++; + if (he->leaf) + browser->nr_callchain_rows += he->nr_rows; + else if (unfold && !hist_entry__has_hierarchy_children(he, browser->min_pcnt)) { + browser->nr_hierarchy_entries++; + he->has_no_entry = true; + he->nr_rows = 1; + } else + he->has_no_entry = false; +} + static void __hist_browser__set_folding(struct hist_browser *browser, bool unfold) { struct rb_node *nd; struct hist_entry *he; - double percent; nd = rb_first(&browser->hists->entries); while (nd) { @@ -535,21 +648,6 @@ __hist_browser__set_folding(struct hist_browser *browser, bool unfold) nd = __rb_hierarchy_next(nd, HMD_FORCE_CHILD); hist_entry__set_folding(he, browser, unfold); - - percent = hist_entry__get_percent_limit(he); - if (he->filtered || percent < browser->min_pcnt) - continue; - - if (!he->depth || unfold) - browser->nr_hierarchy_entries++; - if (he->leaf) - browser->nr_callchain_rows += he->nr_rows; - else if (unfold && !hist_entry__has_hierarchy_children(he, browser->min_pcnt)) { - browser->nr_hierarchy_entries++; - he->has_no_entry = true; - he->nr_rows = 1; - } else - he->has_no_entry = false; } } @@ -564,6 +662,15 @@ static void hist_browser__set_folding(struct hist_browser *browser, bool unfold) ui_browser__reset_index(&browser->b); } +static void hist_browser__set_folding_selected(struct hist_browser *browser, bool unfold) +{ + if (!browser->he_selection) + return; + + hist_entry__set_folding(browser->he_selection, browser, unfold); + browser->b.nr_entries = hist_browser__nr_entries(browser); +} + static void ui_browser__warn_lost_events(struct ui_browser *browser) { ui_browser__warning(browser, 4, @@ -637,10 +744,18 @@ int hist_browser__run(struct hist_browser *browser, const char *help) /* Collapse the whole world. */ hist_browser__set_folding(browser, false); break; + case 'c': + /* Collapse the selected entry. */ + hist_browser__set_folding_selected(browser, false); + break; case 'E': /* Expand the whole world. */ hist_browser__set_folding(browser, true); break; + case 'e': + /* Expand the selected entry. */ + hist_browser__set_folding_selected(browser, true); + break; case 'H': browser->show_headers = !browser->show_headers; hist_browser__update_rows(browser); @@ -729,6 +844,71 @@ static bool hist_browser__check_dump_full(struct hist_browser *browser __maybe_u #define LEVEL_OFFSET_STEP 3 +static int hist_browser__show_inline(struct hist_browser *browser, + struct inline_node *node, + unsigned short row, + int offset) +{ + struct inline_list *ilist; + char buf[1024]; + int color, width, first_row; + + first_row = row; + width = browser->b.width - (LEVEL_OFFSET_STEP + 2); + list_for_each_entry(ilist, &node->val, list) { + if ((ilist->filename != NULL) || (ilist->funcname != NULL)) { + color = HE_COLORSET_NORMAL; + if (ui_browser__is_current_entry(&browser->b, row)) + color = HE_COLORSET_SELECTED; + + if (callchain_param.key == CCKEY_ADDRESS || + callchain_param.key == CCKEY_SRCLINE) { + if (ilist->filename != NULL) + scnprintf(buf, sizeof(buf), + "%s:%d (inline)", + ilist->filename, + ilist->line_nr); + else + scnprintf(buf, sizeof(buf), "??"); + } else if (ilist->funcname != NULL) + scnprintf(buf, sizeof(buf), "%s (inline)", + ilist->funcname); + else if (ilist->filename != NULL) + scnprintf(buf, sizeof(buf), + "%s:%d (inline)", + ilist->filename, + ilist->line_nr); + else + scnprintf(buf, sizeof(buf), "??"); + + ui_browser__set_color(&browser->b, color); + hist_browser__gotorc(browser, row, 0); + ui_browser__write_nstring(&browser->b, " ", + LEVEL_OFFSET_STEP + offset); + ui_browser__write_nstring(&browser->b, buf, width); + row++; + } + } + + return row - first_row; +} + +static size_t show_inline_list(struct hist_browser *browser, struct map *map, + u64 ip, int row, int offset) +{ + struct inline_node *node; + int ret; + + node = inline_node__create(map, ip); + if (node == NULL) + return 0; + + ret = hist_browser__show_inline(browser, node, row, offset); + + inline_node__delete(node); + return ret; +} + static int hist_browser__show_callchain_list(struct hist_browser *browser, struct callchain_node *node, struct callchain_list *chain, @@ -740,6 +920,7 @@ static int hist_browser__show_callchain_list(struct hist_browser *browser, char bf[1024], *alloc_str; char buf[64], *alloc_str2; const char *str; + int inline_rows = 0, ret = 1; if (arg->row_offset != 0) { arg->row_offset--; @@ -777,10 +958,15 @@ static int hist_browser__show_callchain_list(struct hist_browser *browser, } print(browser, chain, str, offset, row, arg); - free(alloc_str); free(alloc_str2); - return 1; + + if (symbol_conf.inline_name) { + inline_rows = show_inline_list(browser, chain->ms.map, + chain->ip, row + 1, offset); + } + + return ret + inline_rows; } static bool check_percent_display(struct rb_node *node, u64 parent_total) @@ -1204,6 +1390,12 @@ static int hist_browser__show_entry(struct hist_browser *browser, folded_sign = hist_entry__folded(entry); } + if (symbol_conf.inline_name && + (!entry->has_children)) { + hist_entry_init_inline_node(entry); + folded_sign = hist_entry__folded(entry); + } + if (row_offset == 0) { struct hpp_arg arg = { .b = &browser->b, @@ -1235,7 +1427,8 @@ static int hist_browser__show_entry(struct hist_browser *browser, } if (first) { - if (symbol_conf.use_callchain) { + if (symbol_conf.use_callchain || + symbol_conf.inline_name) { ui_browser__printf(&browser->b, "%c ", folded_sign); width -= 2; } @@ -1277,8 +1470,14 @@ static int hist_browser__show_entry(struct hist_browser *browser, .is_current_entry = current_entry, }; - printed += hist_browser__show_callchain(browser, entry, 1, row, - hist_browser__show_callchain_entry, &arg, + if (entry->inline_node) + printed += hist_browser__show_inline(browser, + entry->inline_node, row, 0); + else + printed += hist_browser__show_callchain(browser, + entry, 1, row, + hist_browser__show_callchain_entry, + &arg, hist_browser__check_output_full); } @@ -2284,7 +2483,7 @@ static int switch_data_file(void) return ret; memset(options, 0, sizeof(options)); - memset(options, 0, sizeof(abs_path)); + memset(abs_path, 0, sizeof(abs_path)); while ((dent = readdir(pwd_dir))) { char path[PATH_MAX]; diff --git a/tools/perf/ui/browsers/map.c b/tools/perf/ui/browsers/map.c index 98a34664bb7e..ffa5addf631d 100644 --- a/tools/perf/ui/browsers/map.c +++ b/tools/perf/ui/browsers/map.c @@ -11,6 +11,8 @@ #include "../keysyms.h" #include "map.h" +#include "sane_ctype.h" + struct map_browser { struct ui_browser b; struct map *map; @@ -73,7 +75,7 @@ static int map_browser__run(struct map_browser *browser) if (ui_browser__show(&browser->b, browser->map->dso->long_name, "Press ESC to exit, %s / to search", - verbose ? "" : "restart with -v to use") < 0) + verbose > 0 ? "" : "restart with -v to use") < 0) return -1; while (1) { @@ -81,7 +83,7 @@ static int map_browser__run(struct map_browser *browser) switch (key) { case '/': - if (verbose) + if (verbose > 0) map_browser__search(browser); default: break; @@ -117,7 +119,7 @@ int map__browse(struct map *map) if (maxaddr < pos->end) maxaddr = pos->end; - if (verbose) { + if (verbose > 0) { u32 *idx = symbol__browser_index(pos); *idx = mb.b.nr_entries; } diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c index 8c9308ac30b7..e99ba86158d2 100644 --- a/tools/perf/ui/gtk/annotate.c +++ b/tools/perf/ui/gtk/annotate.c @@ -3,7 +3,8 @@ #include "util/annotate.h" #include "util/evsel.h" #include "ui/helpline.h" - +#include <inttypes.h> +#include <signal.h> enum { ANN_COL__PERCENT, diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c index a4f02de7c1b5..e24f83957705 100644 --- a/tools/perf/ui/gtk/hists.c +++ b/tools/perf/ui/gtk/hists.c @@ -4,7 +4,9 @@ #include "../sort.h" #include "../hist.h" #include "../helpline.h" +#include "../string2.h" #include "gtk.h" +#include <signal.h> #define MAX_COLUMNS 32 diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c index 18cfcdc90356..59addd52d9cd 100644 --- a/tools/perf/ui/hist.c +++ b/tools/perf/ui/hist.c @@ -1,3 +1,4 @@ +#include <inttypes.h> #include <math.h> #include <linux/compiler.h> @@ -648,7 +649,7 @@ unsigned int hists__sort_list_width(struct hists *hists) ret += fmt->width(fmt, &dummy_hpp, hists); } - if (verbose && hists__has(hists, sym)) /* Addr + origin */ + if (verbose > 0 && hists__has(hists, sym)) /* Addr + origin */ ret += 3 + BITS_PER_LONG / 4; return ret; diff --git a/tools/perf/ui/setup.c b/tools/perf/ui/setup.c index 1f6b0994f4f4..caf1ce6f5152 100644 --- a/tools/perf/ui/setup.c +++ b/tools/perf/ui/setup.c @@ -4,11 +4,16 @@ #include "../util/cache.h" #include "../util/debug.h" #include "../util/hist.h" +#include "../util/util.h" pthread_mutex_t ui__lock = PTHREAD_MUTEX_INITIALIZER; void *perf_gtk_handle; +int use_browser = -1; + +#define PERF_GTK_DSO "libperf-gtk.so" #ifdef HAVE_GTK2_SUPPORT + static int setup_gtk_browser(void) { int (*perf_ui_init)(void); diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c index 668f4aecf2e6..42e432bd2eb4 100644 --- a/tools/perf/ui/stdio/hist.c +++ b/tools/perf/ui/stdio/hist.c @@ -4,7 +4,10 @@ #include "../../util/hist.h" #include "../../util/sort.h" #include "../../util/evsel.h" - +#include "../../util/srcline.h" +#include "../../util/string2.h" +#include "../../util/thread.h" +#include "../../util/sane_ctype.h" static size_t callchain__fprintf_left_margin(FILE *fp, int left_margin) { @@ -17,6 +20,67 @@ static size_t callchain__fprintf_left_margin(FILE *fp, int left_margin) return ret; } +static size_t inline__fprintf(struct map *map, u64 ip, int left_margin, + int depth, int depth_mask, FILE *fp) +{ + struct dso *dso; + struct inline_node *node; + struct inline_list *ilist; + int ret = 0, i; + + if (map == NULL) + return 0; + + dso = map->dso; + if (dso == NULL) + return 0; + + if (dso->kernel != DSO_TYPE_USER) + return 0; + + node = dso__parse_addr_inlines(dso, + map__rip_2objdump(map, ip)); + if (node == NULL) + return 0; + + list_for_each_entry(ilist, &node->val, list) { + if ((ilist->filename != NULL) || (ilist->funcname != NULL)) { + ret += callchain__fprintf_left_margin(fp, left_margin); + + for (i = 0; i < depth; i++) { + if (depth_mask & (1 << i)) + ret += fprintf(fp, "|"); + else + ret += fprintf(fp, " "); + ret += fprintf(fp, " "); + } + + if (callchain_param.key == CCKEY_ADDRESS || + callchain_param.key == CCKEY_SRCLINE) { + if (ilist->filename != NULL) + ret += fprintf(fp, "%s:%d (inline)", + ilist->filename, + ilist->line_nr); + else + ret += fprintf(fp, "??"); + } else if (ilist->funcname != NULL) + ret += fprintf(fp, "%s (inline)", + ilist->funcname); + else if (ilist->filename != NULL) + ret += fprintf(fp, "%s:%d (inline)", + ilist->filename, + ilist->line_nr); + else + ret += fprintf(fp, "??"); + + ret += fprintf(fp, "\n"); + } + } + + inline_node__delete(node); + return ret; +} + static size_t ipchain__fprintf_graph_line(FILE *fp, int depth, int depth_mask, int left_margin) { @@ -78,6 +142,10 @@ static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_node *node, fputs(str, fp); fputc('\n', fp); free(alloc_str); + + if (symbol_conf.inline_name) + ret += inline__fprintf(chain->ms.map, chain->ip, + left_margin, depth, depth_mask, fp); return ret; } @@ -229,6 +297,7 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root, if (!i++ && field_order == NULL && sort_order && !prefixcmp(sort_order, "sym")) continue; + if (!printed) { ret += callchain__fprintf_left_margin(fp, left_margin); ret += fprintf(fp, "|\n"); @@ -251,6 +320,13 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root, if (++entries_printed == callchain_param.print_limit) break; + + if (symbol_conf.inline_name) + ret += inline__fprintf(chain->ms.map, + chain->ip, + left_margin, + 0, 0, + fp); } root = &cnode->rb_root; } @@ -529,6 +605,8 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size, bool use_callchain) { int ret; + int callchain_ret = 0; + int inline_ret = 0; struct perf_hpp hpp = { .buf = bf, .size = size, @@ -547,7 +625,16 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size, ret = fprintf(fp, "%s\n", bf); if (use_callchain) - ret += hist_entry_callchain__fprintf(he, total_period, 0, fp); + callchain_ret = hist_entry_callchain__fprintf(he, total_period, + 0, fp); + + if (callchain_ret == 0 && symbol_conf.inline_name) { + inline_ret = inline__fprintf(he->ms.map, he->ip, 0, 0, 0, fp); + ret += inline_ret; + if (inline_ret > 0) + ret += fprintf(fp, "\n"); + } else + ret += callchain_ret; return ret; } diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c index 4ea2ba861fc2..d9350a1da48b 100644 --- a/tools/perf/ui/tui/setup.c +++ b/tools/perf/ui/tui/setup.c @@ -1,6 +1,7 @@ #include <errno.h> #include <signal.h> #include <stdbool.h> +#include <linux/kernel.h> #ifdef HAVE_BACKTRACE_SUPPORT #include <execinfo.h> #endif diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 3840e3a87057..79dea95a7f68 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -1,4 +1,3 @@ -libperf-y += alias.o libperf-y += annotate.o libperf-y += block-range.o libperf-y += build-id.o @@ -14,9 +13,11 @@ libperf-y += find_bit.o libperf-y += kallsyms.o libperf-y += levenshtein.o libperf-y += llvm-utils.o +libperf-y += memswap.o libperf-y += parse-events.o libperf-y += perf_regs.o libperf-y += path.o +libperf-y += print_binary.o libperf-y += rbtree.o libperf-y += libstring.o libperf-y += bitmap.o @@ -42,6 +43,7 @@ libperf-y += pstack.o libperf-y += session.o libperf-$(CONFIG_AUDIT) += syscalltbl.o libperf-y += ordered-events.o +libperf-y += namespaces.o libperf-y += comm.o libperf-y += thread.o libperf-y += thread_map.o @@ -81,13 +83,16 @@ libperf-$(CONFIG_AUXTRACE) += intel-pt-decoder/ libperf-$(CONFIG_AUXTRACE) += intel-pt.o libperf-$(CONFIG_AUXTRACE) += intel-bts.o libperf-y += parse-branch-options.o +libperf-y += dump-insn.o libperf-y += parse-regs-options.o libperf-y += term.o libperf-y += help-unknown-cmd.o libperf-y += mem-events.o libperf-y += vsprintf.o libperf-y += drv_configs.o +libperf-y += units.o libperf-y += time-utils.o +libperf-y += expr-bison.o libperf-$(CONFIG_LIBBPF) += bpf-loader.o libperf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o @@ -140,6 +145,10 @@ $(OUTPUT)util/parse-events-bison.c: util/parse-events.y $(call rule_mkdir) $(Q)$(call echo-cmd,bison)$(BISON) -v util/parse-events.y -d $(PARSER_DEBUG_BISON) -o $@ -p parse_events_ +$(OUTPUT)util/expr-bison.c: util/expr.y + $(call rule_mkdir) + $(Q)$(call echo-cmd,bison)$(BISON) -v util/expr.y -d $(PARSER_DEBUG_BISON) -o $@ -p expr__ + $(OUTPUT)util/pmu-flex.c: util/pmu.l $(OUTPUT)util/pmu-bison.c $(call rule_mkdir) $(Q)$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/pmu-flex.h util/pmu.l @@ -152,6 +161,7 @@ CFLAGS_parse-events-flex.o += -w CFLAGS_pmu-flex.o += -w CFLAGS_parse-events-bison.o += -DYYENABLE_NLS=0 -w CFLAGS_pmu-bison.o += -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w +CFLAGS_expr-bison.o += -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w $(OUTPUT)util/parse-events.o: $(OUTPUT)util/parse-events-flex.c $(OUTPUT)util/parse-events-bison.c $(OUTPUT)util/pmu.o: $(OUTPUT)util/pmu-flex.c $(OUTPUT)util/pmu-bison.c @@ -162,6 +172,7 @@ CFLAGS_rbtree.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ET CFLAGS_libstring.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" CFLAGS_hweight.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" CFLAGS_parse-events.o += -Wno-redundant-decls +CFLAGS_header.o += -include $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)util/kallsyms.o: ../lib/symbol/kallsyms.c FORCE $(call rule_mkdir) diff --git a/tools/perf/util/alias.c b/tools/perf/util/alias.c deleted file mode 100644 index 6455471d9cd1..000000000000 --- a/tools/perf/util/alias.c +++ /dev/null @@ -1,78 +0,0 @@ -#include "cache.h" -#include "util.h" -#include "config.h" - -static const char *alias_key; -static char *alias_val; - -static int alias_lookup_cb(const char *k, const char *v, - void *cb __maybe_unused) -{ - if (!prefixcmp(k, "alias.") && !strcmp(k+6, alias_key)) { - if (!v) - return config_error_nonbool(k); - alias_val = strdup(v); - return 0; - } - return 0; -} - -char *alias_lookup(const char *alias) -{ - alias_key = alias; - alias_val = NULL; - perf_config(alias_lookup_cb, NULL); - return alias_val; -} - -int split_cmdline(char *cmdline, const char ***argv) -{ - int src, dst, count = 0, size = 16; - char quoted = 0; - - *argv = malloc(sizeof(char*) * size); - - /* split alias_string */ - (*argv)[count++] = cmdline; - for (src = dst = 0; cmdline[src];) { - char c = cmdline[src]; - if (!quoted && isspace(c)) { - cmdline[dst++] = 0; - while (cmdline[++src] - && isspace(cmdline[src])) - ; /* skip */ - if (count >= size) { - size += 16; - *argv = realloc(*argv, sizeof(char*) * size); - } - (*argv)[count++] = cmdline + dst; - } else if (!quoted && (c == '\'' || c == '"')) { - quoted = c; - src++; - } else if (c == quoted) { - quoted = 0; - src++; - } else { - if (c == '\\' && quoted != '\'') { - src++; - c = cmdline[src]; - if (!c) { - zfree(argv); - return error("cmdline ends with \\"); - } - } - cmdline[dst++] = c; - src++; - } - } - - cmdline[dst] = 0; - - if (quoted) { - zfree(argv); - return error("unclosed quote"); - } - - return count; -} - diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 06cc04e5806a..683f8340460c 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -7,6 +7,8 @@ * Released under the GPL v2. (and only v2, not any later version) */ +#include <errno.h> +#include <inttypes.h> #include "util.h" #include "ui/ui.h" #include "sort.h" @@ -18,12 +20,16 @@ #include "annotate.h" #include "evsel.h" #include "block-range.h" +#include "string2.h" #include "arch/common.h" #include <regex.h> #include <pthread.h> #include <linux/bitops.h> +#include <linux/kernel.h> #include <sys/utsname.h> +#include "sane_ctype.h" + const char *disassembler_style; const char *objdump_path; static regex_t file_lineno; @@ -108,6 +114,7 @@ static int arch__associate_ins_ops(struct arch* arch, const char *name, struct i #include "arch/arm64/annotate/instructions.c" #include "arch/x86/annotate/instructions.c" #include "arch/powerpc/annotate/instructions.c" +#include "arch/s390/annotate/instructions.c" static struct arch architectures[] = { { @@ -130,6 +137,13 @@ static struct arch architectures[] = { .name = "powerpc", .init = powerpc__annotate_init, }, + { + .name = "s390", + .init = s390__annotate_init, + .objdump = { + .comment_char = '#', + }, + }, }; static void ins__delete(struct ins_operands *ops) @@ -379,9 +393,7 @@ static int mov__parse(struct arch *arch, struct ins_operands *ops, struct map *m if (comment == NULL) return 0; - while (comment[0] != '\0' && isspace(comment[0])) - ++comment; - + comment = ltrim(comment); comment__symbol(ops->source.raw, comment, &ops->source.addr, &ops->source.name); comment__symbol(ops->target.raw, comment, &ops->target.addr, &ops->target.name); @@ -426,9 +438,7 @@ static int dec__parse(struct arch *arch __maybe_unused, struct ins_operands *ops if (comment == NULL) return 0; - while (comment[0] != '\0' && isspace(comment[0])) - ++comment; - + comment = ltrim(comment); comment__symbol(ops->target.raw, comment, &ops->target.addr, &ops->target.name); return 0; @@ -777,10 +787,7 @@ static void disasm_line__init_ins(struct disasm_line *dl, struct arch *arch, str static int disasm_line__parse(char *line, const char **namep, char **rawp) { - char *name = line, tmp; - - while (isspace(name[0])) - ++name; + char tmp, *name = ltrim(line); if (name[0] == '\0') return -1; @@ -798,12 +805,7 @@ static int disasm_line__parse(char *line, const char **namep, char **rawp) goto out_free_name; (*rawp)[0] = tmp; - - if ((*rawp)[0] != '\0') { - (*rawp)++; - while (isspace((*rawp)[0])) - ++(*rawp); - } + *rawp = ltrim(*rawp); return 0; @@ -1148,7 +1150,7 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map, { struct annotation *notes = symbol__annotation(sym); struct disasm_line *dl; - char *line = NULL, *parsed_line, *tmp, *tmp2, *c; + char *line = NULL, *parsed_line, *tmp, *tmp2; size_t line_len; s64 line_ip, offset = -1; regmatch_t match[2]; @@ -1159,32 +1161,16 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map, if (!line) return -1; - while (line_len != 0 && isspace(line[line_len - 1])) - line[--line_len] = '\0'; - - c = strchr(line, '\n'); - if (c) - *c = 0; - line_ip = -1; - parsed_line = line; + parsed_line = rtrim(line); /* /filename:linenr ? Save line number and ignore. */ - if (regexec(&file_lineno, line, 2, match, 0) == 0) { - *line_nr = atoi(line + match[1].rm_so); + if (regexec(&file_lineno, parsed_line, 2, match, 0) == 0) { + *line_nr = atoi(parsed_line + match[1].rm_so); return 0; } - /* - * Strip leading spaces: - */ - tmp = line; - while (*tmp) { - if (*tmp != ' ') - break; - tmp++; - } - + tmp = ltrim(parsed_line); if (*tmp) { /* * Parse hexa addresses followed by ':' @@ -1307,6 +1293,7 @@ static int dso__disassemble_filename(struct dso *dso, char *filename, size_t fil { char linkname[PATH_MAX]; char *build_id_filename; + char *build_id_path = NULL; if (dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS && !dso__is_kcore(dso)) @@ -1322,8 +1309,14 @@ static int dso__disassemble_filename(struct dso *dso, char *filename, size_t fil goto fallback; } + build_id_path = strdup(filename); + if (!build_id_path) + return -1; + + dirname(build_id_path); + if (dso__is_kcore(dso) || - readlink(filename, linkname, sizeof(linkname)) < 0 || + readlink(build_id_path, linkname, sizeof(linkname)) < 0 || strstr(linkname, DSO__NAME_KALLSYMS) || access(filename, R_OK)) { fallback: @@ -1335,6 +1328,7 @@ fallback: __symbol__join_symfs(filename, filename_size, dso->long_name); } + free(build_id_path); return 0; } @@ -1435,7 +1429,7 @@ int symbol__disassemble(struct symbol *sym, struct map *map, const char *arch_na snprintf(command, sizeof(command), "%s %s%s --start-address=0x%016" PRIx64 " --stop-address=0x%016" PRIx64 - " -l -d %s %s -C %s 2>/dev/null|grep -v %s|expand", + " -l -d %s %s -C %s 2>/dev/null|grep -v %s:|expand", objdump_path ? objdump_path : "objdump", disassembler_style ? "-M " : "", disassembler_style ? disassembler_style : "", @@ -1482,6 +1476,12 @@ int symbol__disassemble(struct symbol *sym, struct map *map, const char *arch_na nline = 0; while (!feof(file)) { + /* + * The source code line number (lineno) needs to be kept in + * accross calls to symbol__parse_objdump_line(), so that it + * can associate it with the instructions till the next one. + * See disasm_line__new() and struct disasm_line::line_nr. + */ if (symbol__parse_objdump_line(sym, map, arch, file, privsize, &lineno) < 0) break; @@ -1651,24 +1651,31 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map, start = map__rip_2objdump(map, sym->start); for (i = 0; i < len; i++) { - u64 offset; + u64 offset, nr_samples; double percent_max = 0.0; src_line->nr_pcnt = nr_pcnt; for (k = 0; k < nr_pcnt; k++) { + double percent = 0.0; + h = annotation__histogram(notes, evidx + k); - src_line->samples[k].percent = 100.0 * h->addr[i] / h->sum; + nr_samples = h->addr[i]; + if (h->sum) + percent = 100.0 * nr_samples / h->sum; - if (src_line->samples[k].percent > percent_max) - percent_max = src_line->samples[k].percent; + if (percent > percent_max) + percent_max = percent; + src_line->samples[k].percent = percent; + src_line->samples[k].nr = nr_samples; } if (percent_max <= 0.5) goto next; offset = start + i; - src_line->path = get_srcline(map->dso, offset, NULL, false); + src_line->path = get_srcline(map->dso, offset, NULL, + false, true); insert_source_line(&tmp_root, src_line); next: @@ -1768,7 +1775,7 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map, printf("%-*.*s----\n", graph_dotted_len, graph_dotted_len, graph_dotted_line); - if (verbose) + if (verbose > 0) symbol__annotate_hits(sym, evsel); list_for_each_entry(pos, ¬es->src->source, node) { diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index 09776b5af991..948aa8e6fd39 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -98,7 +98,7 @@ struct cyc_hist { struct source_line_samples { double percent; double percent_sum; - double nr; + u64 nr; }; struct source_line { diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index c5a6e0b12452..0daf63b9ee3e 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -13,10 +13,10 @@ * */ +#include <inttypes.h> #include <sys/types.h> #include <sys/mman.h> #include <stdbool.h> -#include <ctype.h> #include <string.h> #include <limits.h> #include <errno.h> @@ -46,7 +46,6 @@ #include "cpumap.h" #include "thread_map.h" #include "asm/bug.h" -#include "symbol/kallsyms.h" #include "auxtrace.h" #include <linux/hash.h> @@ -59,6 +58,9 @@ #include "intel-pt.h" #include "intel-bts.h" +#include "sane_ctype.h" +#include "symbol/kallsyms.h" + int auxtrace_mmap__mmap(struct auxtrace_mmap *mm, struct auxtrace_mmap_params *mp, void *userpg, int fd) @@ -1826,7 +1828,7 @@ static int addr_filter__resolve_kernel_syms(struct addr_filter *filt) filt->addr = start; if (filt->range && !filt->size && !filt->sym_to) { filt->size = size; - no_size = !!size; + no_size = !size; } } @@ -1840,7 +1842,7 @@ static int addr_filter__resolve_kernel_syms(struct addr_filter *filt) if (err) return err; filt->size = start + size - filt->addr; - no_size = !!size; + no_size = !size; } /* The very last symbol in kallsyms does not imply a particular size */ diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h index 26fb1ee5746a..9f0de72d58e2 100644 --- a/tools/perf/util/auxtrace.h +++ b/tools/perf/util/auxtrace.h @@ -17,6 +17,7 @@ #define __PERF_AUXTRACE_H #include <sys/types.h> +#include <errno.h> #include <stdbool.h> #include <stddef.h> #include <linux/list.h> diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c index 36c861103291..4bd2d1d882af 100644 --- a/tools/perf/util/bpf-loader.c +++ b/tools/perf/util/bpf-loader.c @@ -9,7 +9,9 @@ #include <bpf/libbpf.h> #include <bpf/bpf.h> #include <linux/err.h> +#include <linux/kernel.h> #include <linux/string.h> +#include <errno.h> #include "perf.h" #include "debug.h" #include "bpf-loader.h" @@ -17,6 +19,7 @@ #include "probe-event.h" #include "probe-finder.h" // for MAX_PROBES #include "parse-events.h" +#include "strfilter.h" #include "llvm-utils.h" #include "c++/clang-c.h" @@ -670,13 +673,13 @@ int bpf__probe(struct bpf_object *obj) err = convert_perf_probe_events(pev, 1); if (err < 0) { - pr_debug("bpf_probe: failed to convert perf probe events"); + pr_debug("bpf_probe: failed to convert perf probe events\n"); goto out; } err = apply_perf_probe_events(pev, 1); if (err < 0) { - pr_debug("bpf_probe: failed to apply perf probe events"); + pr_debug("bpf_probe: failed to apply perf probe events\n"); goto out; } diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h index f2b737b225f2..48863867878b 100644 --- a/tools/perf/util/bpf-loader.h +++ b/tools/perf/util/bpf-loader.h @@ -85,6 +85,8 @@ int bpf__strerror_setup_stdout(struct perf_evlist *evlist, int err, char *buf, size_t size); #else +#include <errno.h> + static inline struct bpf_object * bpf__prepare_load(const char *filename __maybe_unused, bool source __maybe_unused) diff --git a/tools/perf/util/bpf-prologue.c b/tools/perf/util/bpf-prologue.c index 6cdbee119ceb..1356220a9f1b 100644 --- a/tools/perf/util/bpf-prologue.c +++ b/tools/perf/util/bpf-prologue.c @@ -12,6 +12,7 @@ #include "bpf-loader.h" #include "bpf-prologue.h" #include "probe-finder.h" +#include <errno.h> #include <dwarf-regs.h> #include <linux/filter.h> diff --git a/tools/perf/util/bpf-prologue.h b/tools/perf/util/bpf-prologue.h index d94cbea12899..ba564838375f 100644 --- a/tools/perf/util/bpf-prologue.h +++ b/tools/perf/util/bpf-prologue.h @@ -18,6 +18,8 @@ int bpf__gen_prologue(struct probe_trace_arg *args, int nargs, struct bpf_insn *new_prog, size_t *new_cnt, size_t cnt_space); #else +#include <errno.h> + static inline int bpf__gen_prologue(struct probe_trace_arg *args __maybe_unused, int nargs __maybe_unused, diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index e528c40739cc..168cc49654e7 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -7,18 +7,26 @@ * Copyright (C) 2009, 2010 Arnaldo Carvalho de Melo <acme@redhat.com> */ #include "util.h" +#include <dirent.h> +#include <errno.h> #include <stdio.h> +#include <sys/stat.h> +#include <sys/types.h> #include "build-id.h" #include "event.h" #include "symbol.h" +#include "thread.h" #include <linux/kernel.h> #include "debug.h" #include "session.h" #include "tool.h" #include "header.h" #include "vdso.h" +#include "path.h" #include "probe-file.h" +#include "strlist.h" +#include "sane_ctype.h" static bool no_buildid_cache; @@ -182,13 +190,17 @@ char *build_id_cache__origname(const char *sbuild_id) char buf[PATH_MAX]; char *ret = NULL, *p; size_t offs = 5; /* == strlen("../..") */ + ssize_t len; linkname = build_id_cache__linkname(sbuild_id, NULL, 0); if (!linkname) return NULL; - if (readlink(linkname, buf, PATH_MAX) < 0) + len = readlink(linkname, buf, sizeof(buf) - 1); + if (len <= 0) goto out; + buf[len] = '\0'; + /* The link should be "../..<origpath>/<sbuild_id>" */ p = strrchr(buf, '/'); /* Cut off the "/<sbuild_id>" */ if (p && (p > buf + offs)) { @@ -443,14 +455,14 @@ void disable_buildid_cache(void) } static bool lsdir_bid_head_filter(const char *name __maybe_unused, - struct dirent *d __maybe_unused) + struct dirent *d) { return (strlen(d->d_name) == 2) && isxdigit(d->d_name[0]) && isxdigit(d->d_name[1]); } static bool lsdir_bid_tail_filter(const char *name __maybe_unused, - struct dirent *d __maybe_unused) + struct dirent *d) { int i = 0; while (isxdigit(d->d_name[i]) && i < SBUILD_ID_SIZE - 3) @@ -690,7 +702,7 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name, err = 0; /* Update SDT cache : error is just warned */ - if (build_id_cache__add_sdt_cache(sbuild_id, realname) < 0) + if (realname && build_id_cache__add_sdt_cache(sbuild_id, realname) < 0) pr_debug4("Failed to update/scan SDT cache for %s\n", realname); out_free: diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h index d27990610f9f..8a89b195c1fc 100644 --- a/tools/perf/util/build-id.h +++ b/tools/perf/util/build-id.h @@ -5,7 +5,6 @@ #define SBUILD_ID_SIZE (BUILD_ID_SIZE * 2 + 1) #include "tool.h" -#include "strlist.h" #include <linux/types.h> extern struct perf_tool build_id__mark_dso_hit_ops; @@ -34,6 +33,9 @@ char *build_id_cache__origname(const char *sbuild_id); char *build_id_cache__linkname(const char *sbuild_id, char *bf, size_t size); char *build_id_cache__cachedir(const char *sbuild_id, const char *name, bool is_kallsyms, bool is_vdso); + +struct strlist; + struct strlist *build_id_cache__list_all(bool validonly); char *build_id_cache__complement(const char *incomplete_sbuild_id); int build_id_cache__list_build_ids(const char *pathname, @@ -42,6 +44,10 @@ bool build_id_cache__cached(const char *sbuild_id); int build_id_cache__add_s(const char *sbuild_id, const char *name, bool is_kallsyms, bool is_vdso); int build_id_cache__remove_s(const char *sbuild_id); + +extern char buildid_dir[]; + +void set_buildid_dir(const char *dir); void disable_buildid_cache(void); #endif diff --git a/tools/perf/util/c++/clang-c.h b/tools/perf/util/c++/clang-c.h index 0eadd792ab1f..ccafcf72b37a 100644 --- a/tools/perf/util/c++/clang-c.h +++ b/tools/perf/util/c++/clang-c.h @@ -20,6 +20,7 @@ extern int perf_clang__compile_bpf(const char *filename, size_t *p_obj_buf_sz); #else +#include <errno.h> static inline void perf_clang__init(void) { } static inline void perf_clang__cleanup(void) { } diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h index 512c0c83fbc6..0328f297a748 100644 --- a/tools/perf/util/cache.h +++ b/tools/perf/util/cache.h @@ -15,7 +15,6 @@ #define PERF_TRACEFS_ENVIRONMENT "PERF_TRACEFS_DIR" #define PERF_PAGER_ENVIRONMENT "PERF_PAGER" -char *alias_lookup(const char *alias); int split_cmdline(char *cmdline, const char ***argv); #define alloc_nr(x) (((x)+16)*3/2) diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 8b610dd9e2f6..81fc29ac798f 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -9,6 +9,7 @@ * */ +#include <inttypes.h> #include <stdlib.h> #include <stdio.h> #include <stdbool.h> @@ -23,6 +24,21 @@ #include "machine.h" #include "callchain.h" +#define CALLCHAIN_PARAM_DEFAULT \ + .mode = CHAIN_GRAPH_ABS, \ + .min_percent = 0.5, \ + .order = ORDER_CALLEE, \ + .key = CCKEY_FUNCTION, \ + .value = CCVAL_PERCENT, \ + +struct callchain_param callchain_param = { + CALLCHAIN_PARAM_DEFAULT +}; + +struct callchain_param callchain_param_default = { + CALLCHAIN_PARAM_DEFAULT +}; + __thread struct callchain_cursor callchain_cursor; int parse_callchain_record_opt(const char *arg, struct callchain_param *param) @@ -48,6 +64,8 @@ static int parse_callchain_mode(const char *value) callchain_param.mode = CHAIN_FOLDED; return 0; } + + pr_err("Invalid callchain mode: %s\n", value); return -1; } @@ -63,6 +81,8 @@ static int parse_callchain_order(const char *value) callchain_param.order_set = true; return 0; } + + pr_err("Invalid callchain order: %s\n", value); return -1; } @@ -76,10 +96,16 @@ static int parse_callchain_sort_key(const char *value) callchain_param.key = CCKEY_ADDRESS; return 0; } + if (!strncmp(value, "srcline", strlen(value))) { + callchain_param.key = CCKEY_SRCLINE; + return 0; + } if (!strncmp(value, "branch", strlen(value))) { callchain_param.branch_callstack = 1; return 0; } + + pr_err("Invalid callchain sort key: %s\n", value); return -1; } @@ -97,6 +123,34 @@ static int parse_callchain_value(const char *value) callchain_param.value = CCVAL_COUNT; return 0; } + + pr_err("Invalid callchain config key: %s\n", value); + return -1; +} + +static int get_stack_size(const char *str, unsigned long *_size) +{ + char *endptr; + unsigned long size; + unsigned long max_size = round_down(USHRT_MAX, sizeof(u64)); + + size = strtoul(str, &endptr, 0); + + do { + if (*endptr) + break; + + size = round_up(size, sizeof(u64)); + if (!size || size > max_size) + break; + + *_size = size; + return 0; + + } while (0); + + pr_err("callchain: Incorrect stack dump size (max %ld): %s\n", + max_size, str); return -1; } @@ -104,7 +158,7 @@ static int __parse_callchain_report_opt(const char *arg, bool allow_record_opt) { char *tok; - char *endptr; + char *endptr, *saveptr = NULL; bool minpcnt_set = false; bool record_opt_set = false; bool try_stack_size = false; @@ -115,7 +169,7 @@ __parse_callchain_report_opt(const char *arg, bool allow_record_opt) if (!arg) return 0; - while ((tok = strtok((char *)arg, ",")) != NULL) { + while ((tok = strtok_r((char *)arg, ",", &saveptr)) != NULL) { if (!strncmp(tok, "none", strlen(tok))) { callchain_param.mode = CHAIN_NONE; callchain_param.enabled = false; @@ -183,6 +237,68 @@ int parse_callchain_top_opt(const char *arg) return __parse_callchain_report_opt(arg, true); } +int parse_callchain_record(const char *arg, struct callchain_param *param) +{ + char *tok, *name, *saveptr = NULL; + char *buf; + int ret = -1; + + /* We need buffer that we know we can write to. */ + buf = malloc(strlen(arg) + 1); + if (!buf) + return -ENOMEM; + + strcpy(buf, arg); + + tok = strtok_r((char *)buf, ",", &saveptr); + name = tok ? : (char *)buf; + + do { + /* Framepointer style */ + if (!strncmp(name, "fp", sizeof("fp"))) { + if (!strtok_r(NULL, ",", &saveptr)) { + param->record_mode = CALLCHAIN_FP; + ret = 0; + } else + pr_err("callchain: No more arguments " + "needed for --call-graph fp\n"); + break; + + /* Dwarf style */ + } else if (!strncmp(name, "dwarf", sizeof("dwarf"))) { + const unsigned long default_stack_dump_size = 8192; + + ret = 0; + param->record_mode = CALLCHAIN_DWARF; + param->dump_size = default_stack_dump_size; + + tok = strtok_r(NULL, ",", &saveptr); + if (tok) { + unsigned long size = 0; + + ret = get_stack_size(tok, &size); + param->dump_size = size; + } + } else if (!strncmp(name, "lbr", sizeof("lbr"))) { + if (!strtok_r(NULL, ",", &saveptr)) { + param->record_mode = CALLCHAIN_LBR; + ret = 0; + } else + pr_err("callchain: No more arguments " + "needed for --call-graph lbr\n"); + break; + } else { + pr_err("callchain: Unknown --call-graph option " + "value: %s\n", arg); + break; + } + + } while (0); + + free(buf); + return ret; +} + int perf_callchain_config(const char *var, const char *value) { char *endptr; @@ -210,13 +326,17 @@ int perf_callchain_config(const char *var, const char *value) return parse_callchain_sort_key(value); if (!strcmp(var, "threshold")) { callchain_param.min_percent = strtod(value, &endptr); - if (value == endptr) + if (value == endptr) { + pr_err("Invalid callchain threshold: %s\n", value); return -1; + } } if (!strcmp(var, "print-limit")) { callchain_param.print_limit = strtod(value, &endptr); - if (value == endptr) + if (value == endptr) { + pr_err("Invalid callchain print limit: %s\n", value); return -1; + } } return 0; @@ -498,14 +618,51 @@ enum match_result { MATCH_GT, }; +static enum match_result match_chain_srcline(struct callchain_cursor_node *node, + struct callchain_list *cnode) +{ + char *left = get_srcline(cnode->ms.map->dso, + map__rip_2objdump(cnode->ms.map, cnode->ip), + cnode->ms.sym, true, false); + char *right = get_srcline(node->map->dso, + map__rip_2objdump(node->map, node->ip), + node->sym, true, false); + enum match_result ret = MATCH_EQ; + int cmp; + + if (left && right) + cmp = strcmp(left, right); + else if (!left && right) + cmp = 1; + else if (left && !right) + cmp = -1; + else if (cnode->ip == node->ip) + cmp = 0; + else + cmp = (cnode->ip < node->ip) ? -1 : 1; + + if (cmp != 0) + ret = cmp < 0 ? MATCH_LT : MATCH_GT; + + free_srcline(left); + free_srcline(right); + return ret; +} + static enum match_result match_chain(struct callchain_cursor_node *node, struct callchain_list *cnode) { struct symbol *sym = node->sym; u64 left, right; - if (cnode->ms.sym && sym && - callchain_param.key == CCKEY_FUNCTION) { + if (callchain_param.key == CCKEY_SRCLINE) { + enum match_result match = match_chain_srcline(node, cnode); + + if (match != MATCH_ERROR) + return match; + } + + if (cnode->ms.sym && sym && callchain_param.key == CCKEY_FUNCTION) { left = cnode->ms.sym->start; right = sym->start; } else { @@ -899,15 +1056,16 @@ out: char *callchain_list__sym_name(struct callchain_list *cl, char *bf, size_t bfsize, bool show_dso) { + bool show_addr = callchain_param.key == CCKEY_ADDRESS; + bool show_srcline = show_addr || callchain_param.key == CCKEY_SRCLINE; int printed; if (cl->ms.sym) { - if (callchain_param.key == CCKEY_ADDRESS && - cl->ms.map && !cl->srcline) + if (show_srcline && cl->ms.map && !cl->srcline) cl->srcline = get_srcline(cl->ms.map->dso, map__rip_2objdump(cl->ms.map, cl->ip), - cl->ms.sym, false); + cl->ms.sym, false, show_addr); if (cl->srcline) printed = scnprintf(bf, bfsize, "%s %s", cl->ms.sym->name, cl->srcline); @@ -1051,63 +1209,100 @@ int callchain_branch_counts(struct callchain_root *root, cycles_count); } -static int callchain_counts_printf(FILE *fp, char *bf, int bfsize, - u64 branch_count, u64 predicted_count, - u64 abort_count, u64 cycles_count, - u64 iter_count, u64 samples_count) +static int counts_str_build(char *bf, int bfsize, + u64 branch_count, u64 predicted_count, + u64 abort_count, u64 cycles_count, + u64 iter_count, u64 samples_count) { double predicted_percent = 0.0; const char *null_str = ""; char iter_str[32]; - char *str; - u64 cycles = 0; - - if (branch_count == 0) { - if (fp) - return fprintf(fp, " (calltrace)"); + char cycle_str[32]; + char *istr, *cstr; + u64 cycles; + if (branch_count == 0) return scnprintf(bf, bfsize, " (calltrace)"); - } + + cycles = cycles_count / branch_count; if (iter_count && samples_count) { - scnprintf(iter_str, sizeof(iter_str), - ", iterations:%" PRId64 "", - iter_count / samples_count); - str = iter_str; + if (cycles > 0) + scnprintf(iter_str, sizeof(iter_str), + " iterations:%" PRId64 "", + iter_count / samples_count); + else + scnprintf(iter_str, sizeof(iter_str), + "iterations:%" PRId64 "", + iter_count / samples_count); + istr = iter_str; + } else + istr = (char *)null_str; + + if (cycles > 0) { + scnprintf(cycle_str, sizeof(cycle_str), + "cycles:%" PRId64 "", cycles); + cstr = cycle_str; } else - str = (char *)null_str; + cstr = (char *)null_str; predicted_percent = predicted_count * 100.0 / branch_count; - cycles = cycles_count / branch_count; - if ((predicted_percent >= 100.0) && (abort_count == 0)) { - if (fp) - return fprintf(fp, " (cycles:%" PRId64 "%s)", - cycles, str); + if ((predicted_count == branch_count) && (abort_count == 0)) { + if ((cycles > 0) || (istr != (char *)null_str)) + return scnprintf(bf, bfsize, " (%s%s)", cstr, istr); + else + return scnprintf(bf, bfsize, "%s", (char *)null_str); + } - return scnprintf(bf, bfsize, " (cycles:%" PRId64 "%s)", - cycles, str); + if ((predicted_count < branch_count) && (abort_count == 0)) { + if ((cycles > 0) || (istr != (char *)null_str)) + return scnprintf(bf, bfsize, + " (predicted:%.1f%% %s%s)", + predicted_percent, cstr, istr); + else { + return scnprintf(bf, bfsize, + " (predicted:%.1f%%)", + predicted_percent); + } } - if ((predicted_percent < 100.0) && (abort_count == 0)) { - if (fp) - return fprintf(fp, - " (predicted:%.1f%%, cycles:%" PRId64 "%s)", - predicted_percent, cycles, str); + if ((predicted_count == branch_count) && (abort_count > 0)) { + if ((cycles > 0) || (istr != (char *)null_str)) + return scnprintf(bf, bfsize, + " (abort:%" PRId64 " %s%s)", + abort_count, cstr, istr); + else + return scnprintf(bf, bfsize, + " (abort:%" PRId64 ")", + abort_count); + } + if ((cycles > 0) || (istr != (char *)null_str)) return scnprintf(bf, bfsize, - " (predicted:%.1f%%, cycles:%" PRId64 "%s)", - predicted_percent, cycles, str); - } + " (predicted:%.1f%% abort:%" PRId64 " %s%s)", + predicted_percent, abort_count, cstr, istr); + + return scnprintf(bf, bfsize, + " (predicted:%.1f%% abort:%" PRId64 ")", + predicted_percent, abort_count); +} + +static int callchain_counts_printf(FILE *fp, char *bf, int bfsize, + u64 branch_count, u64 predicted_count, + u64 abort_count, u64 cycles_count, + u64 iter_count, u64 samples_count) +{ + char str[128]; + + counts_str_build(str, sizeof(str), branch_count, + predicted_count, abort_count, cycles_count, + iter_count, samples_count); if (fp) - return fprintf(fp, - " (predicted:%.1f%%, abort:%" PRId64 ", cycles:%" PRId64 "%s)", - predicted_percent, abort_count, cycles, str); + return fprintf(fp, "%s", str); - return scnprintf(bf, bfsize, - " (predicted:%.1f%%, abort:%" PRId64 ", cycles:%" PRId64 "%s)", - predicted_percent, abort_count, cycles, str); + return scnprintf(bf, bfsize, "%s", str); } int callchain_list_counts__printf_value(struct callchain_node *node, diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index 4f4b60f1558a..c56c23dbbf72 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -77,7 +77,8 @@ typedef void (*sort_chain_func_t)(struct rb_root *, struct callchain_root *, enum chain_key { CCKEY_FUNCTION, - CCKEY_ADDRESS + CCKEY_ADDRESS, + CCKEY_SRCLINE }; enum chain_value { diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c index 8fdee24725a7..03347748f3fa 100644 --- a/tools/perf/util/cgroup.c +++ b/tools/perf/util/cgroup.c @@ -4,6 +4,7 @@ #include "evsel.h" #include "cgroup.h" #include "evlist.h" +#include <linux/stringify.h> int nr_cgroups; @@ -12,8 +13,8 @@ cgroupfs_find_mountpoint(char *buf, size_t maxlen) { FILE *fp; char mountpoint[PATH_MAX + 1], tokens[PATH_MAX + 1], type[PATH_MAX + 1]; + char path_v1[PATH_MAX + 1], path_v2[PATH_MAX + 2], *path; char *token, *saved_ptr = NULL; - int found = 0; fp = fopen("/proc/mounts", "r"); if (!fp) @@ -24,31 +25,43 @@ cgroupfs_find_mountpoint(char *buf, size_t maxlen) * and inspect every cgroupfs mount point to find one that has * perf_event subsystem */ - while (fscanf(fp, "%*s %"STR(PATH_MAX)"s %"STR(PATH_MAX)"s %" - STR(PATH_MAX)"s %*d %*d\n", + path_v1[0] = '\0'; + path_v2[0] = '\0'; + + while (fscanf(fp, "%*s %"__stringify(PATH_MAX)"s %"__stringify(PATH_MAX)"s %" + __stringify(PATH_MAX)"s %*d %*d\n", mountpoint, type, tokens) == 3) { - if (!strcmp(type, "cgroup")) { + if (!path_v1[0] && !strcmp(type, "cgroup")) { token = strtok_r(tokens, ",", &saved_ptr); while (token != NULL) { if (!strcmp(token, "perf_event")) { - found = 1; + strcpy(path_v1, mountpoint); break; } token = strtok_r(NULL, ",", &saved_ptr); } } - if (found) + + if (!path_v2[0] && !strcmp(type, "cgroup2")) + strcpy(path_v2, mountpoint); + + if (path_v1[0] && path_v2[0]) break; } fclose(fp); - if (!found) + + if (path_v1[0]) + path = path_v1; + else if (path_v2[0]) + path = path_v2; + else return -1; - if (strlen(mountpoint) < maxlen) { - strcpy(buf, mountpoint); + if (strlen(path) < maxlen) { + strcpy(buf, path); return 0; } return -1; @@ -115,19 +128,19 @@ static int add_cgroup(struct perf_evlist *evlist, char *str) goto found; n++; } - if (atomic_read(&cgrp->refcnt) == 0) + if (refcount_read(&cgrp->refcnt) == 0) free(cgrp); return -1; found: - atomic_inc(&cgrp->refcnt); + refcount_inc(&cgrp->refcnt); counter->cgrp = cgrp; return 0; } void close_cgroup(struct cgroup_sel *cgrp) { - if (cgrp && atomic_dec_and_test(&cgrp->refcnt)) { + if (cgrp && refcount_dec_and_test(&cgrp->refcnt)) { close(cgrp->fd); zfree(&cgrp->name); free(cgrp); diff --git a/tools/perf/util/cgroup.h b/tools/perf/util/cgroup.h index 31f8dcdbd7ef..d91966b97cbd 100644 --- a/tools/perf/util/cgroup.h +++ b/tools/perf/util/cgroup.h @@ -1,14 +1,14 @@ #ifndef __CGROUP_H__ #define __CGROUP_H__ -#include <linux/atomic.h> +#include <linux/refcount.h> struct option; struct cgroup_sel { char *name; int fd; - atomic_t refcnt; + refcount_t refcnt; }; diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c index f0dcd0ee0afa..4b4f00df58a8 100644 --- a/tools/perf/util/cloexec.c +++ b/tools/perf/util/cloexec.c @@ -1,3 +1,4 @@ +#include <errno.h> #include <sched.h> #include "util.h" #include "../perf.h" diff --git a/tools/perf/util/cloexec.h b/tools/perf/util/cloexec.h index d0d465953d36..94a5a7d829d5 100644 --- a/tools/perf/util/cloexec.h +++ b/tools/perf/util/cloexec.h @@ -3,10 +3,4 @@ unsigned long perf_event_open_cloexec_flag(void); -#ifdef __GLIBC_PREREQ -#if !__GLIBC_PREREQ(2, 6) && !defined(__UCLIBC__) -int sched_getcpu(void) __THROW; -#endif -#endif - #endif /* __PERF_CLOEXEC_H */ diff --git a/tools/perf/util/color.h b/tools/perf/util/color.h index a93997f16dec..52122bcc3170 100644 --- a/tools/perf/util/color.h +++ b/tools/perf/util/color.h @@ -1,6 +1,8 @@ #ifndef __PERF_COLOR_H #define __PERF_COLOR_H +#include <stdio.h> + /* "\033[1;38;5;2xx;48;5;2xxm\0" is 23 bytes */ #define COLOR_MAXLEN 24 diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c index 21b7ff382c3f..7bc981b6bf29 100644 --- a/tools/perf/util/comm.c +++ b/tools/perf/util/comm.c @@ -1,13 +1,15 @@ #include "comm.h" #include "util.h" +#include <errno.h> #include <stdlib.h> #include <stdio.h> -#include <linux/atomic.h> +#include <string.h> +#include <linux/refcount.h> struct comm_str { char *str; struct rb_node rb_node; - atomic_t refcnt; + refcount_t refcnt; }; /* Should perhaps be moved to struct machine */ @@ -16,13 +18,13 @@ static struct rb_root comm_str_root; static struct comm_str *comm_str__get(struct comm_str *cs) { if (cs) - atomic_inc(&cs->refcnt); + refcount_inc(&cs->refcnt); return cs; } static void comm_str__put(struct comm_str *cs) { - if (cs && atomic_dec_and_test(&cs->refcnt)) { + if (cs && refcount_dec_and_test(&cs->refcnt)) { rb_erase(&cs->rb_node, &comm_str_root); zfree(&cs->str); free(cs); @@ -43,7 +45,7 @@ static struct comm_str *comm_str__alloc(const char *str) return NULL; } - atomic_set(&cs->refcnt, 0); + refcount_set(&cs->refcnt, 1); return cs; } @@ -61,7 +63,7 @@ static struct comm_str *comm_str__findnew(const char *str, struct rb_root *root) cmp = strcmp(str, iter->str); if (!cmp) - return iter; + return comm_str__get(iter); if (cmp < 0) p = &(*p)->rb_left; @@ -95,8 +97,6 @@ struct comm *comm__new(const char *str, u64 timestamp, bool exec) return NULL; } - comm_str__get(comm->comm_str); - return comm; } @@ -108,7 +108,6 @@ int comm__override(struct comm *comm, const char *str, u64 timestamp, bool exec) if (!new) return -ENOMEM; - comm_str__get(new); comm_str__put(old); comm->comm_str = new; comm->start = timestamp; diff --git a/tools/perf/util/compress.h b/tools/perf/util/compress.h new file mode 100644 index 000000000000..67fd1bb7c2b7 --- /dev/null +++ b/tools/perf/util/compress.h @@ -0,0 +1,12 @@ +#ifndef PERF_COMPRESS_H +#define PERF_COMPRESS_H + +#ifdef HAVE_ZLIB_SUPPORT +int gzip_decompress_to_file(const char *input, int output_fd); +#endif + +#ifdef HAVE_LZMA_SUPPORT +int lzma_decompress_to_file(const char *input, int output_fd); +#endif + +#endif /* PERF_COMPRESS_H */ diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index 3d906dbbef74..8d724f0fa5a8 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -8,12 +8,19 @@ * Copyright (C) Johannes Schindelin, 2005 * */ +#include <errno.h> +#include <sys/param.h> #include "util.h" #include "cache.h" #include <subcmd/exec-cmd.h> #include "util/hist.h" /* perf_hist_config */ #include "util/llvm-utils.h" /* perf_llvm_config */ #include "config.h" +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> + +#include "sane_ctype.h" #define MAXNAME (256) @@ -386,8 +393,10 @@ static int perf_buildid_config(const char *var, const char *value) if (!strcmp(var, "buildid.dir")) { const char *dir = perf_config_dirname(var, value); - if (!dir) + if (!dir) { + pr_err("Invalid buildid directory!\n"); return -1; + } strncpy(buildid_dir, dir, MAXPATHLEN-1); buildid_dir[MAXPATHLEN-1] = '\0'; } @@ -405,10 +414,9 @@ static int perf_default_core_config(const char *var __maybe_unused, static int perf_ui_config(const char *var, const char *value) { /* Add other config variables here. */ - if (!strcmp(var, "ui.show-headers")) { + if (!strcmp(var, "ui.show-headers")) symbol_conf.show_hist_headers = perf_config_bool(var, value); - return 0; - } + return 0; } @@ -626,6 +634,8 @@ static int perf_config_set__init(struct perf_config_set *set) { int ret = -1; const char *home = NULL; + char *user_config; + struct stat st; /* Setting $PERF_CONFIG makes perf read _only_ the given config file. */ if (config_exclusive_filename) @@ -636,33 +646,41 @@ static int perf_config_set__init(struct perf_config_set *set) } home = getenv("HOME"); - if (perf_config_global() && home) { - char *user_config = strdup(mkpath("%s/.perfconfig", home)); - struct stat st; - if (user_config == NULL) { - warning("Not enough memory to process %s/.perfconfig, " - "ignoring it.", home); - goto out; - } + /* + * Skip reading user config if: + * - there is no place to read it from (HOME) + * - we are asked not to (PERF_CONFIG_NOGLOBAL=1) + */ + if (!home || !*home || !perf_config_global()) + return 0; - if (stat(user_config, &st) < 0) - goto out_free; + user_config = strdup(mkpath("%s/.perfconfig", home)); + if (user_config == NULL) { + warning("Not enough memory to process %s/.perfconfig, " + "ignoring it.", home); + goto out; + } - if (st.st_uid && (st.st_uid != geteuid())) { - warning("File %s not owned by current user or root, " - "ignoring it.", user_config); - goto out_free; - } + if (stat(user_config, &st) < 0) { + if (errno == ENOENT) + ret = 0; + goto out_free; + } - if (!st.st_size) - goto out_free; + ret = 0; + if (st.st_uid && (st.st_uid != geteuid())) { + warning("File %s not owned by current user or root, " + "ignoring it.", user_config); + goto out_free; + } + + if (st.st_size) ret = perf_config_from_file(collect_config, user_config, set); out_free: - free(user_config); - } + free(user_config); out: return ret; } diff --git a/tools/perf/util/counts.c b/tools/perf/util/counts.c index e3fde313deb2..c4af82ab7808 100644 --- a/tools/perf/util/counts.c +++ b/tools/perf/util/counts.c @@ -1,6 +1,8 @@ +#include <errno.h> #include <stdlib.h> #include "evsel.h" #include "counts.h" +#include "util.h" struct perf_counts *perf_counts__new(int ncpus, int nthreads) { diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 2c0b52264a46..37b3bb79ee08 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -3,12 +3,16 @@ #include "../perf.h" #include "cpumap.h" #include <assert.h> +#include <dirent.h> #include <stdio.h> #include <stdlib.h> #include <linux/bitmap.h> #include "asm/bug.h" +#include "sane_ctype.h" + static int max_cpu_num; +static int max_present_cpu_num; static int max_node_num; static int *cpunode_map; @@ -28,7 +32,7 @@ static struct cpu_map *cpu_map__default_new(void) cpus->map[i] = i; cpus->nr = nr_cpus; - atomic_set(&cpus->refcnt, 1); + refcount_set(&cpus->refcnt, 1); } return cpus; @@ -42,7 +46,7 @@ static struct cpu_map *cpu_map__trim_new(int nr_cpus, int *tmp_cpus) if (cpus != NULL) { cpus->nr = nr_cpus; memcpy(cpus->map, tmp_cpus, payload_size); - atomic_set(&cpus->refcnt, 1); + refcount_set(&cpus->refcnt, 1); } return cpus; @@ -251,7 +255,7 @@ struct cpu_map *cpu_map__dummy_new(void) if (cpus != NULL) { cpus->nr = 1; cpus->map[0] = -1; - atomic_set(&cpus->refcnt, 1); + refcount_set(&cpus->refcnt, 1); } return cpus; @@ -268,7 +272,7 @@ struct cpu_map *cpu_map__empty_new(int nr) for (i = 0; i < nr; i++) cpus->map[i] = -1; - atomic_set(&cpus->refcnt, 1); + refcount_set(&cpus->refcnt, 1); } return cpus; @@ -277,7 +281,7 @@ struct cpu_map *cpu_map__empty_new(int nr) static void cpu_map__delete(struct cpu_map *map) { if (map) { - WARN_ONCE(atomic_read(&map->refcnt) != 0, + WARN_ONCE(refcount_read(&map->refcnt) != 0, "cpu_map refcnt unbalanced\n"); free(map); } @@ -286,13 +290,13 @@ static void cpu_map__delete(struct cpu_map *map) struct cpu_map *cpu_map__get(struct cpu_map *map) { if (map) - atomic_inc(&map->refcnt); + refcount_inc(&map->refcnt); return map; } void cpu_map__put(struct cpu_map *map) { - if (map && atomic_dec_and_test(&map->refcnt)) + if (map && refcount_dec_and_test(&map->refcnt)) cpu_map__delete(map); } @@ -356,7 +360,7 @@ int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res, /* ensure we process id in increasing order */ qsort(c->map, c->nr, sizeof(int), cmp_ids); - atomic_set(&c->refcnt, 1); + refcount_set(&c->refcnt, 1); *res = c; return 0; } @@ -442,6 +446,7 @@ static void set_max_cpu_num(void) /* set up default */ max_cpu_num = 4096; + max_present_cpu_num = 4096; mnt = sysfs__mountpoint(); if (!mnt) @@ -455,6 +460,17 @@ static void set_max_cpu_num(void) } ret = get_max_num(path, &max_cpu_num); + if (ret) + goto out; + + /* get the highest present cpu number for a sparse allocation */ + ret = snprintf(path, PATH_MAX, "%s/devices/system/cpu/present", mnt); + if (ret == PATH_MAX) { + pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX); + goto out; + } + + ret = get_max_num(path, &max_present_cpu_num); out: if (ret) @@ -505,6 +521,15 @@ int cpu__max_cpu(void) return max_cpu_num; } +int cpu__max_present_cpu(void) +{ + if (unlikely(!max_present_cpu_num)) + set_max_cpu_num(); + + return max_present_cpu_num; +} + + int cpu__get_node(int cpu) { if (unlikely(cpunode_map == NULL)) { @@ -651,3 +676,49 @@ size_t cpu_map__snprint(struct cpu_map *map, char *buf, size_t size) pr_debug("cpumask list: %s\n", buf); return ret; } + +static char hex_char(unsigned char val) +{ + if (val < 10) + return val + '0'; + if (val < 16) + return val - 10 + 'a'; + return '?'; +} + +size_t cpu_map__snprint_mask(struct cpu_map *map, char *buf, size_t size) +{ + int i, cpu; + char *ptr = buf; + unsigned char *bitmap; + int last_cpu = cpu_map__cpu(map, map->nr - 1); + + bitmap = zalloc((last_cpu + 7) / 8); + if (bitmap == NULL) { + buf[0] = '\0'; + return 0; + } + + for (i = 0; i < map->nr; i++) { + cpu = cpu_map__cpu(map, i); + bitmap[cpu / 8] |= 1 << (cpu % 8); + } + + for (cpu = last_cpu / 4 * 4; cpu >= 0; cpu -= 4) { + unsigned char bits = bitmap[cpu / 8]; + + if (cpu % 8) + bits >>= 4; + else + bits &= 0xf; + + *ptr++ = hex_char(bits); + if ((cpu % 32) == 0 && cpu > 0) + *ptr++ = ','; + } + *ptr = '\0'; + free(bitmap); + + buf[size - 1] = '\0'; + return ptr - buf; +} diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h index 06bd689f5989..6b8bff87481d 100644 --- a/tools/perf/util/cpumap.h +++ b/tools/perf/util/cpumap.h @@ -3,13 +3,13 @@ #include <stdio.h> #include <stdbool.h> -#include <linux/atomic.h> +#include <linux/refcount.h> #include "perf.h" #include "util/debug.h" struct cpu_map { - atomic_t refcnt; + refcount_t refcnt; int nr; int map[]; }; @@ -20,6 +20,7 @@ struct cpu_map *cpu_map__dummy_new(void); struct cpu_map *cpu_map__new_data(struct cpu_map_data *data); struct cpu_map *cpu_map__read(FILE *file); size_t cpu_map__snprint(struct cpu_map *map, char *buf, size_t size); +size_t cpu_map__snprint_mask(struct cpu_map *map, char *buf, size_t size); size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp); int cpu_map__get_socket_id(int cpu); int cpu_map__get_socket(struct cpu_map *map, int idx, void *data); @@ -62,6 +63,7 @@ int cpu__setup_cpunode_map(void); int cpu__max_node(void); int cpu__max_cpu(void); +int cpu__max_present_cpu(void); int cpu__get_node(int cpu); int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res, diff --git a/tools/perf/util/ctype.c b/tools/perf/util/ctype.c index d4a5a21c2a7e..4b261c2ec0f1 100644 --- a/tools/perf/util/ctype.c +++ b/tools/perf/util/ctype.c @@ -3,7 +3,7 @@ * * No surprises, and works with signed and unsigned chars. */ -#include "util.h" +#include "sane_ctype.h" enum { S = GIT_SPACE, diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c index 7123f4de32cc..89d50318833d 100644 --- a/tools/perf/util/data-convert-bt.c +++ b/tools/perf/util/data-convert-bt.c @@ -7,7 +7,10 @@ * Released under the GPL v2. (and only v2, not any later version) */ +#include <errno.h> +#include <inttypes.h> #include <linux/compiler.h> +#include <linux/kernel.h> #include <babeltrace/ctf-writer/writer.h> #include <babeltrace/ctf-writer/clock.h> #include <babeltrace/ctf-writer/stream.h> @@ -27,6 +30,7 @@ #include "evsel.h" #include "machine.h" #include "config.h" +#include "sane_ctype.h" #define pr_N(n, fmt, ...) \ eprintf(n, debug_data_convert, fmt, ##__VA_ARGS__) @@ -1468,12 +1472,13 @@ int bt_convert__perf2ctf(const char *input, const char *path, .lost = perf_event__process_lost, .tracing_data = perf_event__process_tracing_data, .build_id = perf_event__process_build_id, + .namespaces = perf_event__process_namespaces, .ordered_events = true, .ordering_requires_timestamps = true, }, }; struct ctf_writer *cw = &c.writer; - int err = -1; + int err; if (opts->all) { c.tool.comm = process_comm_event; @@ -1481,12 +1486,15 @@ int bt_convert__perf2ctf(const char *input, const char *path, c.tool.fork = process_fork_event; } - perf_config(convert__config, &c); + err = perf_config(convert__config, &c); + if (err) + return err; /* CTF writer */ if (ctf_writer__init(cw, path)) return -1; + err = -1; /* perf.data session */ session = perf_session__new(&file, 0, &c.tool); if (!session) diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index 60bfc9ca1e22..e84bbc8ec058 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -2,6 +2,7 @@ #include <linux/kernel.h> #include <sys/types.h> #include <sys/stat.h> +#include <errno.h> #include <unistd.h> #include <string.h> diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index c1838b643108..a5b3777ffee6 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -2,19 +2,26 @@ #include "../perf.h" +#include <inttypes.h> #include <string.h> #include <stdarg.h> #include <stdio.h> +#include <sys/wait.h> #include <api/debug.h> #include <linux/time64.h> - +#ifdef HAVE_BACKTRACE_SUPPORT +#include <execinfo.h> +#endif #include "cache.h" #include "color.h" #include "event.h" #include "debug.h" +#include "print_binary.h" #include "util.h" #include "target.h" +#include "sane_ctype.h" + int verbose; bool dump_trace = false, quiet = false; int debug_ordered_events; @@ -203,11 +210,28 @@ int perf_debug_option(const char *str) v = (v < 0) || (v > 10) ? 0 : v; } + if (quiet) + v = -1; + *var->ptr = v; free(s); return 0; } +int perf_quiet_option(void) +{ + struct debug_variable *var = &debug_variables[0]; + + /* disable all debug messages */ + while (var->name) { + *var->ptr = -1; + var++; + } + + quiet = true; + return 0; +} + #define DEBUG_WRAPPER(__n, __l) \ static int pr_ ## __n ## _wrapper(const char *fmt, ...) \ { \ @@ -227,3 +251,31 @@ void perf_debug_setup(void) { libapi_set_print(pr_warning_wrapper, pr_warning_wrapper, pr_debug_wrapper); } + +/* Obtain a backtrace and print it to stdout. */ +#ifdef HAVE_BACKTRACE_SUPPORT +void dump_stack(void) +{ + void *array[16]; + size_t size = backtrace(array, ARRAY_SIZE(array)); + char **strings = backtrace_symbols(array, size); + size_t i; + + printf("Obtained %zd stack frames.\n", size); + + for (i = 0; i < size; i++) + printf("%s\n", strings[i]); + + free(strings); +} +#else +void dump_stack(void) {} +#endif + +void sighandler_dump_stack(int sig) +{ + psignal(sig, "perf"); + dump_stack(); + signal(sig, SIG_DFL); + raise(sig); +} diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h index d242adc3d5a2..8a23ea1a71c7 100644 --- a/tools/perf/util/debug.h +++ b/tools/perf/util/debug.h @@ -54,5 +54,9 @@ int veprintf(int level, int var, const char *fmt, va_list args); int perf_debug_option(const char *str); void perf_debug_setup(void); +int perf_quiet_option(void); + +void dump_stack(void); +void sighandler_dump_stack(int sig); #endif /* __PERF_DEBUG_H */ diff --git a/tools/perf/util/demangle-java.c b/tools/perf/util/demangle-java.c index 3e6062ab2cdd..cb66d334f532 100644 --- a/tools/perf/util/demangle-java.c +++ b/tools/perf/util/demangle-java.c @@ -7,6 +7,8 @@ #include "demangle-java.h" +#include "sane_ctype.h" + enum { MODE_PREFIX = 0, MODE_CLASS = 1, diff --git a/tools/perf/util/drv_configs.c b/tools/perf/util/drv_configs.c index 1647f285c629..eec754243f4d 100644 --- a/tools/perf/util/drv_configs.c +++ b/tools/perf/util/drv_configs.c @@ -17,6 +17,7 @@ #include "evlist.h" #include "evsel.h" #include "pmu.h" +#include <errno.h> static int perf_evsel__apply_drv_configs(struct perf_evsel *evsel, diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index d2c6cdd9d42b..a96a99d2369f 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -1,14 +1,29 @@ #include <asm/bug.h> +#include <linux/kernel.h> #include <sys/time.h> #include <sys/resource.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> +#include <errno.h> +#include "compress.h" +#include "path.h" #include "symbol.h" #include "dso.h" #include "machine.h" #include "auxtrace.h" #include "util.h" #include "debug.h" +#include "string2.h" #include "vdso.h" +static const char * const debuglink_paths[] = { + "%.0s%s", + "%s/%s", + "%s/.debug/%s", + "/usr/lib/debug%s/%s" +}; + char dso__symtab_origin(const struct dso *dso) { static const char origin[] = { @@ -44,24 +59,43 @@ int dso__read_binary_type_filename(const struct dso *dso, size_t len; switch (type) { - case DSO_BINARY_TYPE__DEBUGLINK: { - char *debuglink; + case DSO_BINARY_TYPE__DEBUGLINK: + { + const char *last_slash; + char dso_dir[PATH_MAX]; + char symfile[PATH_MAX]; + unsigned int i; len = __symbol__join_symfs(filename, size, dso->long_name); - debuglink = filename + len; - while (debuglink != filename && *debuglink != '/') - debuglink--; - if (*debuglink == '/') - debuglink++; + last_slash = filename + len; + while (last_slash != filename && *last_slash != '/') + last_slash--; - ret = -1; - if (!is_regular_file(filename)) + strncpy(dso_dir, filename, last_slash - filename); + dso_dir[last_slash-filename] = '\0'; + + if (!is_regular_file(filename)) { + ret = -1; + break; + } + + ret = filename__read_debuglink(filename, symfile, PATH_MAX); + if (ret) break; - ret = filename__read_debuglink(filename, debuglink, - size - (debuglink - filename)); + /* Check predefined locations where debug file might reside */ + ret = -1; + for (i = 0; i < ARRAY_SIZE(debuglink_paths); i++) { + snprintf(filename, size, + debuglink_paths[i], dso_dir, symfile); + if (is_regular_file(filename)) { + ret = 0; + break; + } } + break; + } case DSO_BINARY_TYPE__BUILD_ID_CACHE: if (dso__build_id_filename(dso, filename, size) == NULL) ret = -1; @@ -925,7 +959,7 @@ static struct dso *__dso__findlink_by_longname(struct rb_root *root, if (rc == 0) { /* * In case the new DSO is a duplicate of an existing - * one, print an one-time warning & put the new entry + * one, print a one-time warning & put the new entry * at the end of the list of duplicates. */ if (!dso || (dso == this)) @@ -1032,7 +1066,7 @@ int dso__name_len(const struct dso *dso) { if (!dso) return strlen("[unknown]"); - if (verbose) + if (verbose > 0) return dso->long_name_len; return dso->short_name_len; @@ -1083,7 +1117,7 @@ struct dso *dso__new(const char *name) INIT_LIST_HEAD(&dso->node); INIT_LIST_HEAD(&dso->data.open_entry); pthread_mutex_init(&dso->lock, NULL); - atomic_set(&dso->refcnt, 1); + refcount_set(&dso->refcnt, 1); } return dso; @@ -1121,13 +1155,13 @@ void dso__delete(struct dso *dso) struct dso *dso__get(struct dso *dso) { if (dso) - atomic_inc(&dso->refcnt); + refcount_inc(&dso->refcnt); return dso; } void dso__put(struct dso *dso) { - if (dso && atomic_dec_and_test(&dso->refcnt)) + if (dso && refcount_dec_and_test(&dso->refcnt)) dso__delete(dso); } diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index ecc4bbd3f82e..12350b171727 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -1,7 +1,7 @@ #ifndef __PERF_DSO #define __PERF_DSO -#include <linux/atomic.h> +#include <linux/refcount.h> #include <linux/types.h> #include <linux/rbtree.h> #include <sys/types.h> @@ -187,7 +187,7 @@ struct dso { void *priv; u64 db_id; }; - atomic_t refcnt; + refcount_t refcnt; char name[0]; }; diff --git a/tools/perf/util/dump-insn.c b/tools/perf/util/dump-insn.c new file mode 100644 index 000000000000..ffbdb19f05d0 --- /dev/null +++ b/tools/perf/util/dump-insn.c @@ -0,0 +1,14 @@ +#include <linux/compiler.h> +#include "dump-insn.h" + +/* Fallback code */ + +__weak +const char *dump_insn(struct perf_insn *x __maybe_unused, + u64 ip __maybe_unused, u8 *inbuf __maybe_unused, + int inlen __maybe_unused, int *lenp) +{ + if (lenp) + *lenp = 0; + return "?"; +} diff --git a/tools/perf/util/dump-insn.h b/tools/perf/util/dump-insn.h new file mode 100644 index 000000000000..90fb115981cf --- /dev/null +++ b/tools/perf/util/dump-insn.h @@ -0,0 +1,22 @@ +#ifndef __PERF_DUMP_INSN_H +#define __PERF_DUMP_INSN_H 1 + +#define MAXINSN 15 + +#include <linux/types.h> + +struct thread; + +struct perf_insn { + /* Initialized by callers: */ + struct thread *thread; + u8 cpumode; + bool is64bit; + int cpu; + /* Temporary */ + char out[256]; +}; + +const char *dump_insn(struct perf_insn *x, u64 ip, + u8 *inbuf, int inlen, int *lenp); +#endif diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index 41e068e94349..f5acda13dcfa 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -17,10 +17,13 @@ * */ +#include <errno.h> +#include <inttypes.h> #include <stdbool.h> #include "util.h" #include "debug.h" #include "dwarf-aux.h" +#include "string2.h" /** * cu_find_realpath - Find the realpath of the target file diff --git a/tools/perf/util/dwarf-regs.c b/tools/perf/util/dwarf-regs.c index 62bc4a86a970..c708395b3cb6 100644 --- a/tools/perf/util/dwarf-regs.c +++ b/tools/perf/util/dwarf-regs.c @@ -8,6 +8,7 @@ #include <debug.h> #include <dwarf-regs.h> #include <elf.h> +#include <linux/kernel.h> #ifndef EM_AARCH64 #define EM_AARCH64 183 /* ARM 64 bit */ diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index bb964e86b09d..9e21538c42ae 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -1,6 +1,7 @@ #include "cpumap.h" #include "env.h" #include "util.h" +#include <errno.h> struct perf_env perf_env; @@ -66,7 +67,7 @@ int perf_env__read_cpu_topology_map(struct perf_env *env) return 0; if (env->nr_cpus_avail == 0) - env->nr_cpus_avail = sysconf(_SC_NPROCESSORS_CONF); + env->nr_cpus_avail = cpu__max_present_cpu(); nr_cpus = env->nr_cpus_avail; if (nr_cpus == -1) diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 8ab0d7da956b..dc5c3bb69d73 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -1,15 +1,24 @@ +#include <dirent.h> +#include <errno.h> +#include <inttypes.h> +#include <linux/kernel.h> #include <linux/types.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> #include <uapi/linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */ #include <api/fs/fs.h> +#include <linux/perf_event.h> #include "event.h" #include "debug.h" #include "hist.h" #include "machine.h" #include "sort.h" -#include "string.h" +#include "string2.h" #include "strlist.h" #include "thread.h" #include "thread_map.h" +#include "sane_ctype.h" #include "symbol/kallsyms.h" #include "asm/bug.h" #include "stat.h" @@ -31,6 +40,7 @@ static const char *perf_event__names[] = { [PERF_RECORD_LOST_SAMPLES] = "LOST_SAMPLES", [PERF_RECORD_SWITCH] = "SWITCH", [PERF_RECORD_SWITCH_CPU_WIDE] = "SWITCH_CPU_WIDE", + [PERF_RECORD_NAMESPACES] = "NAMESPACES", [PERF_RECORD_HEADER_ATTR] = "ATTR", [PERF_RECORD_HEADER_EVENT_TYPE] = "EVENT_TYPE", [PERF_RECORD_HEADER_TRACING_DATA] = "TRACING_DATA", @@ -49,6 +59,16 @@ static const char *perf_event__names[] = { [PERF_RECORD_TIME_CONV] = "TIME_CONV", }; +static const char *perf_ns__names[] = { + [NET_NS_INDEX] = "net", + [UTS_NS_INDEX] = "uts", + [IPC_NS_INDEX] = "ipc", + [PID_NS_INDEX] = "pid", + [USER_NS_INDEX] = "user", + [MNT_NS_INDEX] = "mnt", + [CGROUP_NS_INDEX] = "cgroup", +}; + const char *perf_event__name(unsigned int id) { if (id >= ARRAY_SIZE(perf_event__names)) @@ -58,6 +78,13 @@ const char *perf_event__name(unsigned int id) return perf_event__names[id]; } +static const char *perf_ns__name(unsigned int id) +{ + if (id >= ARRAY_SIZE(perf_ns__names)) + return "UNKNOWN"; + return perf_ns__names[id]; +} + static int perf_tool__process_synth_event(struct perf_tool *tool, union perf_event *event, struct machine *machine, @@ -88,7 +115,7 @@ static int perf_event__get_comm_ids(pid_t pid, char *comm, size_t len, int fd; size_t size = 0; ssize_t n; - char *nl, *name, *tgids, *ppids; + char *name, *tgids, *ppids; *tgid = -1; *ppid = -1; @@ -115,10 +142,10 @@ static int perf_event__get_comm_ids(pid_t pid, char *comm, size_t len, ppids = strstr(bf, "PPid:"); if (name) { - name += 5; /* strlen("Name:") */ + char *nl; - while (*name && isspace(*name)) - ++name; + name += 5; /* strlen("Name:") */ + name = ltrim(name); nl = strchr(name, '\n'); if (nl) @@ -203,6 +230,58 @@ pid_t perf_event__synthesize_comm(struct perf_tool *tool, return tgid; } +static void perf_event__get_ns_link_info(pid_t pid, const char *ns, + struct perf_ns_link_info *ns_link_info) +{ + struct stat64 st; + char proc_ns[128]; + + sprintf(proc_ns, "/proc/%u/ns/%s", pid, ns); + if (stat64(proc_ns, &st) == 0) { + ns_link_info->dev = st.st_dev; + ns_link_info->ino = st.st_ino; + } +} + +int perf_event__synthesize_namespaces(struct perf_tool *tool, + union perf_event *event, + pid_t pid, pid_t tgid, + perf_event__handler_t process, + struct machine *machine) +{ + u32 idx; + struct perf_ns_link_info *ns_link_info; + + if (!tool || !tool->namespace_events) + return 0; + + memset(&event->namespaces, 0, (sizeof(event->namespaces) + + (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) + + machine->id_hdr_size)); + + event->namespaces.pid = tgid; + event->namespaces.tid = pid; + + event->namespaces.nr_namespaces = NR_NAMESPACES; + + ns_link_info = event->namespaces.link_info; + + for (idx = 0; idx < event->namespaces.nr_namespaces; idx++) + perf_event__get_ns_link_info(pid, perf_ns__name(idx), + &ns_link_info[idx]); + + event->namespaces.header.type = PERF_RECORD_NAMESPACES; + + event->namespaces.header.size = (sizeof(event->namespaces) + + (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) + + machine->id_hdr_size); + + if (perf_tool__process_synth_event(tool, event, machine, process) != 0) + return -1; + + return 0; +} + static int perf_event__synthesize_fork(struct perf_tool *tool, union perf_event *event, pid_t pid, pid_t tgid, pid_t ppid, @@ -255,8 +334,8 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool, if (machine__is_default_guest(machine)) return 0; - snprintf(filename, sizeof(filename), "%s/proc/%d/maps", - machine->root_dir, pid); + snprintf(filename, sizeof(filename), "%s/proc/%d/task/%d/maps", + machine->root_dir, pid, pid); fp = fopen(filename, "r"); if (fp == NULL) { @@ -434,8 +513,9 @@ int perf_event__synthesize_modules(struct perf_tool *tool, static int __event__synthesize_thread(union perf_event *comm_event, union perf_event *mmap_event, union perf_event *fork_event, + union perf_event *namespaces_event, pid_t pid, int full, - perf_event__handler_t process, + perf_event__handler_t process, struct perf_tool *tool, struct machine *machine, bool mmap_data, @@ -455,6 +535,11 @@ static int __event__synthesize_thread(union perf_event *comm_event, if (tgid == -1) return -1; + if (perf_event__synthesize_namespaces(tool, namespaces_event, pid, + tgid, process, machine) < 0) + return -1; + + return perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid, process, machine, mmap_data, proc_map_timeout); @@ -488,6 +573,11 @@ static int __event__synthesize_thread(union perf_event *comm_event, if (perf_event__synthesize_fork(tool, fork_event, _pid, tgid, ppid, process, machine) < 0) break; + + if (perf_event__synthesize_namespaces(tool, namespaces_event, _pid, + tgid, process, machine) < 0) + break; + /* * Send the prepared comm event */ @@ -516,6 +606,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool, unsigned int proc_map_timeout) { union perf_event *comm_event, *mmap_event, *fork_event; + union perf_event *namespaces_event; int err = -1, thread, j; comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size); @@ -530,10 +621,16 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool, if (fork_event == NULL) goto out_free_mmap; + namespaces_event = malloc(sizeof(namespaces_event->namespaces) + + (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) + + machine->id_hdr_size); + if (namespaces_event == NULL) + goto out_free_fork; + err = 0; for (thread = 0; thread < threads->nr; ++thread) { if (__event__synthesize_thread(comm_event, mmap_event, - fork_event, + fork_event, namespaces_event, thread_map__pid(threads, thread), 0, process, tool, machine, mmap_data, proc_map_timeout)) { @@ -559,7 +656,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool, /* if not, generate events for it */ if (need_leader && __event__synthesize_thread(comm_event, mmap_event, - fork_event, + fork_event, namespaces_event, comm_event->comm.pid, 0, process, tool, machine, mmap_data, proc_map_timeout)) { @@ -568,6 +665,8 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool, } } } + free(namespaces_event); +out_free_fork: free(fork_event); out_free_mmap: free(mmap_event); @@ -587,6 +686,7 @@ int perf_event__synthesize_threads(struct perf_tool *tool, char proc_path[PATH_MAX]; struct dirent *dirent; union perf_event *comm_event, *mmap_event, *fork_event; + union perf_event *namespaces_event; int err = -1; if (machine__is_default_guest(machine)) @@ -604,11 +704,17 @@ int perf_event__synthesize_threads(struct perf_tool *tool, if (fork_event == NULL) goto out_free_mmap; + namespaces_event = malloc(sizeof(namespaces_event->namespaces) + + (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) + + machine->id_hdr_size); + if (namespaces_event == NULL) + goto out_free_fork; + snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir); proc = opendir(proc_path); if (proc == NULL) - goto out_free_fork; + goto out_free_namespaces; while ((dirent = readdir(proc)) != NULL) { char *end; @@ -620,13 +726,16 @@ int perf_event__synthesize_threads(struct perf_tool *tool, * We may race with exiting thread, so don't stop just because * one thread couldn't be synthesized. */ - __event__synthesize_thread(comm_event, mmap_event, fork_event, pid, - 1, process, tool, machine, mmap_data, + __event__synthesize_thread(comm_event, mmap_event, fork_event, + namespaces_event, pid, 1, process, + tool, machine, mmap_data, proc_map_timeout); } err = 0; closedir(proc); +out_free_namespaces: + free(namespaces_event); out_free_fork: free(fork_event); out_free_mmap: @@ -659,15 +768,16 @@ static int find_symbol_cb(void *arg, const char *name, char type, return 1; } -u64 kallsyms__get_function_start(const char *kallsyms_filename, - const char *symbol_name) +int kallsyms__get_function_start(const char *kallsyms_filename, + const char *symbol_name, u64 *addr) { struct process_symbol_args args = { .name = symbol_name, }; if (kallsyms__parse(kallsyms_filename, &args, find_symbol_cb) <= 0) - return 0; + return -1; - return args.start; + *addr = args.start; + return 0; } int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, @@ -1008,6 +1118,33 @@ size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp) return fprintf(fp, "%s: %s:%d/%d\n", s, event->comm.comm, event->comm.pid, event->comm.tid); } +size_t perf_event__fprintf_namespaces(union perf_event *event, FILE *fp) +{ + size_t ret = 0; + struct perf_ns_link_info *ns_link_info; + u32 nr_namespaces, idx; + + ns_link_info = event->namespaces.link_info; + nr_namespaces = event->namespaces.nr_namespaces; + + ret += fprintf(fp, " %d/%d - nr_namespaces: %u\n\t\t[", + event->namespaces.pid, + event->namespaces.tid, + nr_namespaces); + + for (idx = 0; idx < nr_namespaces; idx++) { + if (idx && (idx % 4 == 0)) + ret += fprintf(fp, "\n\t\t "); + + ret += fprintf(fp, "%u/%s: %" PRIu64 "/%#" PRIx64 "%s", idx, + perf_ns__name(idx), (u64)ns_link_info[idx].dev, + (u64)ns_link_info[idx].ino, + ((idx + 1) != nr_namespaces) ? ", " : "]\n"); + } + + return ret; +} + int perf_event__process_comm(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample, @@ -1016,6 +1153,14 @@ int perf_event__process_comm(struct perf_tool *tool __maybe_unused, return machine__process_comm_event(machine, event, sample); } +int perf_event__process_namespaces(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + return machine__process_namespaces_event(machine, event, sample); +} + int perf_event__process_lost(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample, @@ -1153,11 +1298,12 @@ int perf_event__process_exit(struct perf_tool *tool __maybe_unused, size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp) { - return fprintf(fp, " offset: %#"PRIx64" size: %#"PRIx64" flags: %#"PRIx64" [%s%s]\n", + return fprintf(fp, " offset: %#"PRIx64" size: %#"PRIx64" flags: %#"PRIx64" [%s%s%s]\n", event->aux.aux_offset, event->aux.aux_size, event->aux.flags, event->aux.flags & PERF_AUX_FLAG_TRUNCATED ? "T" : "", - event->aux.flags & PERF_AUX_FLAG_OVERWRITE ? "O" : ""); + event->aux.flags & PERF_AUX_FLAG_OVERWRITE ? "O" : "", + event->aux.flags & PERF_AUX_FLAG_PARTIAL ? "P" : ""); } size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp) @@ -1196,6 +1342,9 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp) case PERF_RECORD_MMAP: ret += perf_event__fprintf_mmap(event, fp); break; + case PERF_RECORD_NAMESPACES: + ret += perf_event__fprintf_namespaces(event, fp); + break; case PERF_RECORD_MMAP2: ret += perf_event__fprintf_mmap2(event, fp); break; diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index c735c53a26f8..7c3fa1c8cbcd 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -3,9 +3,9 @@ #include <limits.h> #include <stdio.h> +#include <linux/kernel.h> #include "../perf.h" -#include "map.h" #include "build-id.h" #include "perf_regs.h" @@ -39,6 +39,13 @@ struct comm_event { char comm[16]; }; +struct namespaces_event { + struct perf_event_header header; + u32 pid, tid; + u64 nr_namespaces; + struct perf_ns_link_info link_info[]; +}; + struct fork_event { struct perf_event_header header; u32 pid, ppid; @@ -222,7 +229,7 @@ struct build_id_event { enum perf_user_event_type { /* above any possible kernel type */ PERF_RECORD_USER_TYPE_START = 64, PERF_RECORD_HEADER_ATTR = 64, - PERF_RECORD_HEADER_EVENT_TYPE = 65, /* depreceated */ + PERF_RECORD_HEADER_EVENT_TYPE = 65, /* deprecated */ PERF_RECORD_HEADER_TRACING_DATA = 66, PERF_RECORD_HEADER_BUILD_ID = 67, PERF_RECORD_FINISHED_ROUND = 68, @@ -269,6 +276,7 @@ struct events_stats { u64 total_lost; u64 total_lost_samples; u64 total_aux_lost; + u64 total_aux_partial; u64 total_invalid_chains; u32 nr_events[PERF_RECORD_HEADER_MAX]; u32 nr_non_filtered_samples; @@ -485,6 +493,7 @@ union perf_event { struct mmap_event mmap; struct mmap2_event mmap2; struct comm_event comm; + struct namespaces_event namespaces; struct fork_event fork; struct lost_event lost; struct lost_samples_event lost_samples; @@ -587,6 +596,10 @@ int perf_event__process_switch(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine); +int perf_event__process_namespaces(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine); int perf_event__process_mmap(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, @@ -636,6 +649,12 @@ pid_t perf_event__synthesize_comm(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine); +int perf_event__synthesize_namespaces(struct perf_tool *tool, + union perf_event *event, + pid_t pid, pid_t tgid, + perf_event__handler_t process, + struct machine *machine); + int perf_event__synthesize_mmap_events(struct perf_tool *tool, union perf_event *event, pid_t pid, pid_t tgid, @@ -653,12 +672,21 @@ size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp); size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp); size_t perf_event__fprintf_thread_map(union perf_event *event, FILE *fp); size_t perf_event__fprintf_cpu_map(union perf_event *event, FILE *fp); +size_t perf_event__fprintf_namespaces(union perf_event *event, FILE *fp); size_t perf_event__fprintf(union perf_event *event, FILE *fp); -u64 kallsyms__get_function_start(const char *kallsyms_filename, - const char *symbol_name); +int kallsyms__get_function_start(const char *kallsyms_filename, + const char *symbol_name, u64 *addr); void *cpu_map_data__alloc(struct cpu_map *map, size_t *size, u16 *type, int *max); void cpu_map_data__synthesize(struct cpu_map_data *data, struct cpu_map *map, u16 type, int max); + +void event_attr_init(struct perf_event_attr *attr); + +int perf_event_paranoid(void); + +extern int sysctl_perf_event_max_stack; +extern int sysctl_perf_event_max_contexts_per_stack; + #endif /* __PERF_RECORD_H */ diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index d92e02006fb8..46c0faf6c502 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -8,6 +8,8 @@ */ #include "util.h" #include <api/fs/fs.h> +#include <errno.h> +#include <inttypes.h> #include <poll.h> #include "cpumap.h" #include "thread_map.h" @@ -15,12 +17,15 @@ #include "evlist.h" #include "evsel.h" #include "debug.h" +#include "units.h" #include "asm/bug.h" +#include <signal.h> #include <unistd.h> #include "parse-events.h" #include <subcmd/parse-options.h> +#include <sys/ioctl.h> #include <sys/mman.h> #include <linux/bitops.h> @@ -777,7 +782,7 @@ union perf_event *perf_mmap__read_forward(struct perf_mmap *md, bool check_messu /* * Check if event was unmapped due to a POLLHUP/POLLERR. */ - if (!atomic_read(&md->refcnt)) + if (!refcount_read(&md->refcnt)) return NULL; head = perf_mmap__read_head(md); @@ -794,7 +799,7 @@ perf_mmap__read_backward(struct perf_mmap *md) /* * Check if event was unmapped due to a POLLHUP/POLLERR. */ - if (!atomic_read(&md->refcnt)) + if (!refcount_read(&md->refcnt)) return NULL; head = perf_mmap__read_head(md); @@ -856,7 +861,7 @@ void perf_mmap__read_catchup(struct perf_mmap *md) { u64 head; - if (!atomic_read(&md->refcnt)) + if (!refcount_read(&md->refcnt)) return; head = perf_mmap__read_head(md); @@ -875,14 +880,14 @@ static bool perf_mmap__empty(struct perf_mmap *md) static void perf_mmap__get(struct perf_mmap *map) { - atomic_inc(&map->refcnt); + refcount_inc(&map->refcnt); } static void perf_mmap__put(struct perf_mmap *md) { - BUG_ON(md->base && atomic_read(&md->refcnt) == 0); + BUG_ON(md->base && refcount_read(&md->refcnt) == 0); - if (atomic_dec_and_test(&md->refcnt)) + if (refcount_dec_and_test(&md->refcnt)) perf_mmap__munmap(md); } @@ -894,7 +899,7 @@ void perf_mmap__consume(struct perf_mmap *md, bool overwrite) perf_mmap__write_tail(md, old); } - if (atomic_read(&md->refcnt) == 1 && perf_mmap__empty(md)) + if (refcount_read(&md->refcnt) == 1 && perf_mmap__empty(md)) perf_mmap__put(md); } @@ -937,7 +942,7 @@ static void perf_mmap__munmap(struct perf_mmap *map) munmap(map->base, perf_mmap__mmap_len(map)); map->base = NULL; map->fd = -1; - atomic_set(&map->refcnt, 0); + refcount_set(&map->refcnt, 0); } auxtrace_mmap__munmap(&map->auxtrace_mmap); } @@ -974,8 +979,19 @@ static struct perf_mmap *perf_evlist__alloc_mmap(struct perf_evlist *evlist) if (!map) return NULL; - for (i = 0; i < evlist->nr_mmaps; i++) + for (i = 0; i < evlist->nr_mmaps; i++) { map[i].fd = -1; + /* + * When the perf_mmap() call is made we grab one refcount, plus + * one extra to let perf_evlist__mmap_consume() get the last + * events after all real references (perf_mmap__get()) are + * dropped. + * + * Each PERF_EVENT_IOC_SET_OUTPUT points to this mmap and + * thus does perf_mmap__get() on it. + */ + refcount_set(&map[i].refcnt, 0); + } return map; } @@ -1001,7 +1017,7 @@ static int perf_mmap__mmap(struct perf_mmap *map, * evlist layer can't just drop it when filtering events in * perf_evlist__filter_pollfd(). */ - atomic_set(&map->refcnt, 2); + refcount_set(&map->refcnt, 2); map->prev = 0; map->mask = mp->mask; map->base = mmap(NULL, perf_mmap__mmap_len(map), mp->prot, @@ -1184,7 +1200,7 @@ unsigned long perf_event_mlock_kb_in_pages(void) return pages; } -static size_t perf_evlist__mmap_size(unsigned long pages) +size_t perf_evlist__mmap_size(unsigned long pages) { if (pages == UINT_MAX) pages = perf_event_mlock_kb_in_pages(); @@ -1224,12 +1240,16 @@ static long parse_pages_arg(const char *str, unsigned long min, if (pages == 0 && min == 0) { /* leave number of pages at 0 */ } else if (!is_power_of_2(pages)) { + char buf[100]; + /* round pages up to next power of 2 */ pages = roundup_pow_of_two(pages); if (!pages) return -EINVAL; - pr_info("rounding mmap pages size to %lu bytes (%lu pages)\n", - pages * page_size, pages); + + unit_number__scnprintf(buf, sizeof(buf), pages * page_size); + pr_info("rounding mmap pages size to %s (%lu pages)\n", + buf, pages); } if (pages > max) @@ -1797,7 +1817,7 @@ int perf_evlist__start_workload(struct perf_evlist *evlist) */ ret = write(evlist->workload.cork_fd, &bf, 1); if (ret < 0) - perror("enable to write to pipe"); + perror("unable to write to pipe"); close(evlist->workload.cork_fd); return ret; diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 4fd034f22d2f..94cea4398a13 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -1,7 +1,8 @@ #ifndef __PERF_EVLIST_H #define __PERF_EVLIST_H 1 -#include <linux/atomic.h> +#include <linux/kernel.h> +#include <linux/refcount.h> #include <linux/list.h> #include <api/fd/array.h> #include <stdio.h> @@ -10,6 +11,7 @@ #include "evsel.h" #include "util.h" #include "auxtrace.h" +#include <signal.h> #include <unistd.h> struct pollfd; @@ -29,7 +31,7 @@ struct perf_mmap { void *base; int mask; int fd; - atomic_t refcnt; + refcount_t refcnt; u64 prev; struct auxtrace_mmap auxtrace_mmap; char event_copy[PERF_SAMPLE_MAX_SIZE] __attribute__((aligned(8))); @@ -218,6 +220,8 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages, bool overwrite); void perf_evlist__munmap(struct perf_evlist *evlist); +size_t perf_evlist__mmap_size(unsigned long pages); + void perf_evlist__disable(struct perf_evlist *evlist); void perf_evlist__enable(struct perf_evlist *evlist); void perf_evlist__toggle_enable(struct perf_evlist *evlist); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 04e536ae4d88..e4f7902d5afa 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -8,16 +8,20 @@ */ #include <byteswap.h> +#include <errno.h> +#include <inttypes.h> #include <linux/bitops.h> #include <api/fs/tracing_path.h> #include <traceevent/event-parse.h> #include <linux/hw_breakpoint.h> #include <linux/perf_event.h> #include <linux/err.h> +#include <sys/ioctl.h> #include <sys/resource.h> #include "asm/bug.h" #include "callchain.h" #include "cgroup.h" +#include "event.h" #include "evsel.h" #include "evlist.h" #include "util.h" @@ -30,6 +34,8 @@ #include "stat.h" #include "util/parse-branch-options.h" +#include "sane_ctype.h" + static struct { bool sample_id_all; bool exclude_guest; @@ -236,6 +242,10 @@ void perf_evsel__init(struct perf_evsel *evsel, evsel->sample_size = __perf_evsel__sample_size(attr->sample_type); perf_evsel__calc_id_pos(evsel); evsel->cmdline_group_boundary = false; + evsel->metric_expr = NULL; + evsel->metric_name = NULL; + evsel->metric_events = NULL; + evsel->collect_stat = false; } struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx) @@ -932,6 +942,9 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, attr->mmap2 = track && !perf_missing_features.mmap2; attr->comm = track; + if (opts->record_namespaces) + attr->namespaces = track; + if (opts->record_switch_events) attr->context_switch = track; @@ -1232,7 +1245,7 @@ int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread, if (FD(evsel, cpu, thread) < 0) return -EINVAL; - if (readn(FD(evsel, cpu, thread), count, sizeof(*count)) < 0) + if (readn(FD(evsel, cpu, thread), count, sizeof(*count)) <= 0) return -errno; return 0; @@ -1250,7 +1263,7 @@ int __perf_evsel__read_on_cpu(struct perf_evsel *evsel, if (evsel->counts == NULL && perf_evsel__alloc_counts(evsel, cpu + 1, thread + 1) < 0) return -ENOMEM; - if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) < 0) + if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) <= 0) return -errno; perf_evsel__compute_deltas(evsel, cpu, thread, &count); @@ -1448,8 +1461,8 @@ static bool ignore_missing_thread(struct perf_evsel *evsel, return true; } -static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, - struct thread_map *threads) +int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, + struct thread_map *threads) { int cpu, thread, nthreads; unsigned long flags = PERF_FLAG_FD_CLOEXEC; @@ -1459,6 +1472,30 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, if (perf_missing_features.write_backward && evsel->attr.write_backward) return -EINVAL; + if (cpus == NULL) { + static struct cpu_map *empty_cpu_map; + + if (empty_cpu_map == NULL) { + empty_cpu_map = cpu_map__dummy_new(); + if (empty_cpu_map == NULL) + return -ENOMEM; + } + + cpus = empty_cpu_map; + } + + if (threads == NULL) { + static struct thread_map *empty_thread_map; + + if (empty_thread_map == NULL) { + empty_thread_map = thread_map__new_by_tid(-1); + if (empty_thread_map == NULL) + return -ENOMEM; + } + + threads = empty_thread_map; + } + if (evsel->system_wide) nthreads = 1; else @@ -1655,46 +1692,16 @@ void perf_evsel__close(struct perf_evsel *evsel, int ncpus, int nthreads) perf_evsel__free_fd(evsel); } -static struct { - struct cpu_map map; - int cpus[1]; -} empty_cpu_map = { - .map.nr = 1, - .cpus = { -1, }, -}; - -static struct { - struct thread_map map; - int threads[1]; -} empty_thread_map = { - .map.nr = 1, - .threads = { -1, }, -}; - -int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, - struct thread_map *threads) -{ - if (cpus == NULL) { - /* Work around old compiler warnings about strict aliasing */ - cpus = &empty_cpu_map.map; - } - - if (threads == NULL) - threads = &empty_thread_map.map; - - return __perf_evsel__open(evsel, cpus, threads); -} - int perf_evsel__open_per_cpu(struct perf_evsel *evsel, struct cpu_map *cpus) { - return __perf_evsel__open(evsel, cpus, &empty_thread_map.map); + return perf_evsel__open(evsel, cpus, NULL); } int perf_evsel__open_per_thread(struct perf_evsel *evsel, struct thread_map *threads) { - return __perf_evsel__open(evsel, &empty_cpu_map.map, threads); + return perf_evsel__open(evsel, NULL, threads); } static int perf_evsel__parse_id_sample(const struct perf_evsel *evsel, @@ -2456,11 +2463,17 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, int err, char *msg, size_t size) { char sbuf[STRERR_BUFSIZE]; + int printed = 0; switch (err) { case EPERM: case EACCES: - return scnprintf(msg, size, + if (err == EPERM) + printed = scnprintf(msg, size, + "No permission to enable %s event.\n\n", + perf_evsel__name(evsel)); + + return scnprintf(msg + printed, size - printed, "You may not have permission to collect %sstats.\n\n" "Consider tweaking /proc/sys/kernel/perf_event_paranoid,\n" "which controls use of the performance events system by\n" @@ -2469,7 +2482,9 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target, " -1: Allow use of (almost) all events by all users\n" ">= 0: Disallow raw tracepoint access by users without CAP_IOC_LOCK\n" ">= 1: Disallow CPU event access by users without CAP_SYS_ADMIN\n" - ">= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN", + ">= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN\n\n" + "To make this setting permanent, edit /etc/sysctl.conf too, e.g.:\n\n" + " kernel.perf_event_paranoid = -1\n" , target->system_wide ? "system-wide " : "", perf_event_paranoid()); case ENOENT: diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 06ef6f29efa1..d101695c482c 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -131,6 +131,11 @@ struct perf_evsel { bool cmdline_group_boundary; struct list_head config_terms; int bpf_fd; + bool merged_stat; + const char * metric_expr; + const char * metric_name; + struct perf_evsel **metric_events; + bool collect_stat; }; union u64_swap { diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c index 6b2925542c0a..e415aee6a245 100644 --- a/tools/perf/util/evsel_fprintf.c +++ b/tools/perf/util/evsel_fprintf.c @@ -1,9 +1,11 @@ +#include <inttypes.h> #include <stdio.h> #include <stdbool.h> #include <traceevent/event-parse.h> #include "evsel.h" #include "callchain.h" #include "map.h" +#include "strlist.h" #include "symbol.h" static int comma_fprintf(FILE *fp, bool *first, const char *fmt, ...) @@ -168,7 +170,6 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment, if (symbol_conf.bt_stop_list && node->sym && - node->sym->name && strlist__has_entry(symbol_conf.bt_stop_list, node->sym->name)) { break; diff --git a/tools/perf/util/expr.h b/tools/perf/util/expr.h new file mode 100644 index 000000000000..9c2760a1a96e --- /dev/null +++ b/tools/perf/util/expr.h @@ -0,0 +1,25 @@ +#ifndef PARSE_CTX_H +#define PARSE_CTX_H 1 + +#define EXPR_MAX_OTHER 8 +#define MAX_PARSE_ID EXPR_MAX_OTHER + +struct parse_id { + const char *name; + double val; +}; + +struct parse_ctx { + int num_ids; + struct parse_id ids[MAX_PARSE_ID]; +}; + +void expr__ctx_init(struct parse_ctx *ctx); +void expr__add_id(struct parse_ctx *ctx, const char *id, double val); +#ifndef IN_EXPR_Y +int expr__parse(double *final_val, struct parse_ctx *ctx, const char **pp); +#endif +int expr__find_other(const char *p, const char *one, const char ***other, + int *num_other); + +#endif diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y new file mode 100644 index 000000000000..954556bea36e --- /dev/null +++ b/tools/perf/util/expr.y @@ -0,0 +1,173 @@ +/* Simple expression parser */ +%{ +#include "util.h" +#include "util/debug.h" +#define IN_EXPR_Y 1 +#include "expr.h" +#include <string.h> + +#define MAXIDLEN 256 +%} + +%pure-parser +%parse-param { double *final_val } +%parse-param { struct parse_ctx *ctx } +%parse-param { const char **pp } +%lex-param { const char **pp } + +%union { + double num; + char id[MAXIDLEN+1]; +} + +%token <num> NUMBER +%token <id> ID +%left '|' +%left '^' +%left '&' +%left '-' '+' +%left '*' '/' '%' +%left NEG NOT +%type <num> expr + +%{ +static int expr__lex(YYSTYPE *res, const char **pp); + +static void expr__error(double *final_val __maybe_unused, + struct parse_ctx *ctx __maybe_unused, + const char **pp __maybe_unused, + const char *s) +{ + pr_debug("%s\n", s); +} + +static int lookup_id(struct parse_ctx *ctx, char *id, double *val) +{ + int i; + + for (i = 0; i < ctx->num_ids; i++) { + if (!strcasecmp(ctx->ids[i].name, id)) { + *val = ctx->ids[i].val; + return 0; + } + } + return -1; +} + +%} +%% + +all_expr: expr { *final_val = $1; } + ; + +expr: NUMBER + | ID { if (lookup_id(ctx, $1, &$$) < 0) { + pr_debug("%s not found", $1); + YYABORT; + } + } + | expr '+' expr { $$ = $1 + $3; } + | expr '-' expr { $$ = $1 - $3; } + | expr '*' expr { $$ = $1 * $3; } + | expr '/' expr { if ($3 == 0) YYABORT; $$ = $1 / $3; } + | expr '%' expr { if ((long)$3 == 0) YYABORT; $$ = (long)$1 % (long)$3; } + | '-' expr %prec NEG { $$ = -$2; } + | '(' expr ')' { $$ = $2; } + ; + +%% + +static int expr__symbol(YYSTYPE *res, const char *p, const char **pp) +{ + char *dst = res->id; + const char *s = p; + + while (isalnum(*p) || *p == '_' || *p == '.') { + if (p - s >= MAXIDLEN) + return -1; + *dst++ = *p++; + } + *dst = 0; + *pp = p; + return ID; +} + +static int expr__lex(YYSTYPE *res, const char **pp) +{ + int tok; + const char *s; + const char *p = *pp; + + while (isspace(*p)) + p++; + s = p; + switch (*p++) { + case 'a' ... 'z': + case 'A' ... 'Z': + return expr__symbol(res, p - 1, pp); + case '0' ... '9': case '.': + res->num = strtod(s, (char **)&p); + tok = NUMBER; + break; + default: + tok = *s; + break; + } + *pp = p; + return tok; +} + +/* Caller must make sure id is allocated */ +void expr__add_id(struct parse_ctx *ctx, const char *name, double val) +{ + int idx; + assert(ctx->num_ids < MAX_PARSE_ID); + idx = ctx->num_ids++; + ctx->ids[idx].name = name; + ctx->ids[idx].val = val; +} + +void expr__ctx_init(struct parse_ctx *ctx) +{ + ctx->num_ids = 0; +} + +int expr__find_other(const char *p, const char *one, const char ***other, + int *num_otherp) +{ + const char *orig = p; + int err = -1; + int num_other; + + *other = malloc((EXPR_MAX_OTHER + 1) * sizeof(char *)); + if (!*other) + return -1; + + num_other = 0; + for (;;) { + YYSTYPE val; + int tok = expr__lex(&val, &p); + if (tok == 0) { + err = 0; + break; + } + if (tok == ID && strcasecmp(one, val.id)) { + if (num_other >= EXPR_MAX_OTHER - 1) { + pr_debug("Too many extra events in %s\n", orig); + break; + } + (*other)[num_other] = strdup(val.id); + if (!(*other)[num_other]) + return -1; + num_other++; + } + } + (*other)[num_other] = NULL; + *num_otherp = num_other; + if (err) { + *num_otherp = 0; + free(*other); + *other = NULL; + } + return err; +} diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index d89c9c7ef4e5..314a07151fb7 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1,4 +1,8 @@ +#include <errno.h> +#include <inttypes.h> #include "util.h" +#include "string2.h" +#include <sys/param.h> #include <sys/types.h> #include <byteswap.h> #include <unistd.h> @@ -7,11 +11,15 @@ #include <linux/list.h> #include <linux/kernel.h> #include <linux/bitops.h> +#include <sys/stat.h> +#include <sys/types.h> #include <sys/utsname.h> +#include <unistd.h> #include "evlist.h" #include "evsel.h" #include "header.h" +#include "memswap.h" #include "../perf.h" #include "trace-event.h" #include "session.h" @@ -26,6 +34,8 @@ #include <api/fs/fs.h> #include "asm/bug.h" +#include "sane_ctype.h" + /* * magic2 = "PERFILE2" * must be a numerical value to let the endianness @@ -41,6 +51,8 @@ static const u64 __perf_magic2_sw = 0x50455246494c4532ULL; #define PERF_MAGIC __perf_magic2 +const char perf_version_string[] = PERF_VERSION; + struct perf_file_attr { struct perf_event_attr attr; struct perf_file_section ids; @@ -293,11 +305,7 @@ static int write_nrcpus(int fd, struct perf_header *h __maybe_unused, u32 nrc, nra; int ret; - nr = sysconf(_SC_NPROCESSORS_CONF); - if (nr < 0) - return -1; - - nrc = (u32)(nr & UINT_MAX); + nrc = cpu__max_present_cpu(); nr = sysconf(_SC_NPROCESSORS_ONLN); if (nr < 0) @@ -372,15 +380,11 @@ static int write_cmdline(int fd, struct perf_header *h __maybe_unused, struct perf_evlist *evlist __maybe_unused) { char buf[MAXPATHLEN]; - char proc[32]; u32 n; int i, ret; - /* - * actual atual path to perf binary - */ - sprintf(proc, "/proc/%d/exe", getpid()); - ret = readlink(proc, buf, sizeof(buf)); + /* actual path to perf binary */ + ret = readlink("/proc/self/exe", buf, sizeof(buf) - 1); if (ret <= 0) return -1; @@ -503,24 +507,29 @@ static void free_cpu_topo(struct cpu_topo *tp) static struct cpu_topo *build_cpu_topology(void) { - struct cpu_topo *tp; + struct cpu_topo *tp = NULL; void *addr; u32 nr, i; size_t sz; long ncpus; int ret = -1; + struct cpu_map *map; - ncpus = sysconf(_SC_NPROCESSORS_CONF); - if (ncpus < 0) + ncpus = cpu__max_present_cpu(); + + /* build online CPU map */ + map = cpu_map__new(NULL); + if (map == NULL) { + pr_debug("failed to get system cpumap\n"); return NULL; + } nr = (u32)(ncpus & UINT_MAX); sz = nr * sizeof(char *); - addr = calloc(1, sizeof(*tp) + 2 * sz); if (!addr) - return NULL; + goto out_free; tp = addr; tp->cpu_nr = nr; @@ -530,10 +539,16 @@ static struct cpu_topo *build_cpu_topology(void) tp->thread_siblings = addr; for (i = 0; i < nr; i++) { + if (!cpu_map__has(map, i)) + continue; + ret = build_cpu_topo(tp, i); if (ret < 0) break; } + +out_free: + cpu_map__put(map); if (ret) { free_cpu_topo(tp); tp = NULL; @@ -1124,7 +1139,7 @@ static void print_cpu_topology(struct perf_header *ph, int fd __maybe_unused, { int nr, i; char *str; - int cpu_nr = ph->env.nr_cpus_online; + int cpu_nr = ph->env.nr_cpus_avail; nr = ph->env.nr_sibling_cores; str = ph->env.sibling_cores; @@ -1779,7 +1794,7 @@ static int process_cpu_topology(struct perf_file_section *section, u32 nr, i; char *str; struct strbuf sb; - int cpu_nr = ph->env.nr_cpus_online; + int cpu_nr = ph->env.nr_cpus_avail; u64 size = 0; ph->env.cpu = calloc(cpu_nr, sizeof(*ph->env.cpu)); @@ -1860,7 +1875,7 @@ static int process_cpu_topology(struct perf_file_section *section, if (ph->needs_swap) nr = bswap_32(nr); - if (nr > (u32)cpu_nr) { + if (nr != (u32)-1 && nr > (u32)cpu_nr) { pr_debug("socket_id number is too big." "You may need to upgrade the perf tool.\n"); goto free_cpu; @@ -2265,6 +2280,9 @@ int perf_header__fprintf_info(struct perf_session *session, FILE *fp, bool full) perf_header__process_sections(header, fd, &hd, perf_file_section__fprintf_info); + if (session->file->is_pipe) + return 0; + fprintf(fp, "# missing features: "); for_each_clear_bit(bit, header->adds_features, HEADER_LAST_FEATURE) { if (bit) @@ -2801,8 +2819,10 @@ static int perf_evsel__prepare_tracepoint_event(struct perf_evsel *evsel, } event = pevent_find_event(pevent, evsel->attr.config); - if (event == NULL) + if (event == NULL) { + pr_debug("cannot find event format for %d\n", (int)evsel->attr.config); return -1; + } if (!evsel->name) { snprintf(bf, sizeof(bf), "%s:%s", event->system, event->name); @@ -3201,6 +3221,7 @@ int perf_event__process_event_update(struct perf_tool *tool __maybe_unused, case PERF_EVENT_UPDATE__SCALE: ev_scale = (struct event_update_event_scale *) ev->data; evsel->scale = ev_scale->scale; + break; case PERF_EVENT_UPDATE__CPUS: ev_cpus = (struct event_update_event_cpus *) ev->data; diff --git a/tools/perf/util/help-unknown-cmd.c b/tools/perf/util/help-unknown-cmd.c index 2821f8d77e52..1c88ad6425b8 100644 --- a/tools/perf/util/help-unknown-cmd.c +++ b/tools/perf/util/help-unknown-cmd.c @@ -1,21 +1,18 @@ #include "cache.h" #include "config.h" +#include <poll.h> #include <stdio.h> #include <subcmd/help.h> #include "../builtin.h" #include "levenshtein.h" static int autocorrect; -static struct cmdnames aliases; static int perf_unknown_cmd_config(const char *var, const char *value, void *cb __maybe_unused) { if (!strcmp(var, "help.autocorrect")) autocorrect = perf_config_int(var,value); - /* Also use aliases for command lookup */ - if (!prefixcmp(var, "alias.")) - add_cmdname(&aliases, var + 6, strlen(var + 6)); return 0; } @@ -59,14 +56,12 @@ const char *help_unknown_cmd(const char *cmd) memset(&main_cmds, 0, sizeof(main_cmds)); memset(&other_cmds, 0, sizeof(main_cmds)); - memset(&aliases, 0, sizeof(aliases)); perf_config(perf_unknown_cmd_config, NULL); load_command_list("perf-", &main_cmds, &other_cmds); - if (add_cmd_list(&main_cmds, &aliases) < 0 || - add_cmd_list(&main_cmds, &other_cmds) < 0) { + if (add_cmd_list(&main_cmds, &other_cmds) < 0) { fprintf(stderr, "ERROR: Failed to allocate command list for unknown command.\n"); goto end; } diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 7d1b7d33e644..cf0186a088c1 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -3,12 +3,17 @@ #include "hist.h" #include "map.h" #include "session.h" +#include "namespaces.h" #include "sort.h" #include "evlist.h" #include "evsel.h" #include "annotate.h" +#include "srcline.h" +#include "thread.h" #include "ui/progress.h" +#include <errno.h> #include <math.h> +#include <sys/param.h> static bool hists__filter_entry_by_dso(struct hists *hists, struct hist_entry *he); @@ -69,7 +74,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) */ if (h->ms.sym) { symlen = h->ms.sym->namelen + 4; - if (verbose) + if (verbose > 0) symlen += BITS_PER_LONG / 4 + 2 + 3; hists__new_col_len(hists, HISTC_SYMBOL, symlen); } else { @@ -93,7 +98,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) if (h->branch_info) { if (h->branch_info->from.sym) { symlen = (int)h->branch_info->from.sym->namelen + 4; - if (verbose) + if (verbose > 0) symlen += BITS_PER_LONG / 4 + 2 + 3; hists__new_col_len(hists, HISTC_SYMBOL_FROM, symlen); @@ -107,7 +112,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) if (h->branch_info->to.sym) { symlen = (int)h->branch_info->to.sym->namelen + 4; - if (verbose) + if (verbose > 0) symlen += BITS_PER_LONG / 4 + 2 + 3; hists__new_col_len(hists, HISTC_SYMBOL_TO, symlen); @@ -169,6 +174,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) hists__set_unres_dso_col_len(hists, HISTC_MEM_DADDR_DSO); } + hists__new_col_len(hists, HISTC_CGROUP_ID, 20); hists__new_col_len(hists, HISTC_CPU, 3); hists__new_col_len(hists, HISTC_SOCKET, 6); hists__new_col_len(hists, HISTC_MEM_LOCKED, 6); @@ -574,9 +580,14 @@ __hists__add_entry(struct hists *hists, bool sample_self, struct hist_entry_ops *ops) { + struct namespaces *ns = thread__namespaces(al->thread); struct hist_entry entry = { .thread = al->thread, .comm = thread__comm(al->thread), + .cgroup_id = { + .dev = ns ? ns->link_info[CGROUP_NS_INDEX].dev : 0, + .ino = ns ? ns->link_info[CGROUP_NS_INDEX].ino : 0, + }, .ms = { .map = al->map, .sym = al->sym, @@ -1129,6 +1140,11 @@ void hist_entry__delete(struct hist_entry *he) zfree(&he->mem_info); } + if (he->inline_node) { + inline_node__delete(he->inline_node); + he->inline_node = NULL; + } + zfree(&he->stat_acc); free_srcline(he->srcline); if (he->srcfile && he->srcfile[0]) @@ -2446,8 +2462,10 @@ int parse_filter_percentage(const struct option *opt __maybe_unused, symbol_conf.filter_relative = true; else if (!strcmp(arg, "absolute")) symbol_conf.filter_relative = false; - else + else { + pr_debug("Invalid percentage: %s\n", arg); return -1; + } return 0; } diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 28c216e3d5b7..ee3670a388df 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -30,6 +30,7 @@ enum hist_column { HISTC_DSO, HISTC_THREAD, HISTC_COMM, + HISTC_CGROUP_ID, HISTC_PARENT, HISTC_CPU, HISTC_SOCKET, @@ -57,6 +58,7 @@ enum hist_column { HISTC_SRCLINE_FROM, HISTC_SRCLINE_TO, HISTC_TRACE, + HISTC_SYM_SIZE, HISTC_NR_COLS, /* Last entry */ }; diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c index 6c2eb5da4afc..b2834ac7b1f5 100644 --- a/tools/perf/util/intel-bts.c +++ b/tools/perf/util/intel-bts.c @@ -14,7 +14,9 @@ */ #include <endian.h> +#include <errno.h> #include <byteswap.h> +#include <inttypes.h> #include <linux/kernel.h> #include <linux/types.h> #include <linux/bitops.h> diff --git a/tools/perf/util/intel-pt-decoder/Build b/tools/perf/util/intel-pt-decoder/Build index 9b742ea8bfe8..7aca5d6d7e1f 100644 --- a/tools/perf/util/intel-pt-decoder/Build +++ b/tools/perf/util/intel-pt-decoder/Build @@ -23,4 +23,8 @@ $(OUTPUT)util/intel-pt-decoder/intel-pt-insn-decoder.o: util/intel-pt-decoder/in $(call rule_mkdir) $(call if_changed_dep,cc_o_c) -CFLAGS_intel-pt-insn-decoder.o += -I$(OUTPUT)util/intel-pt-decoder -Wno-override-init +CFLAGS_intel-pt-insn-decoder.o += -I$(OUTPUT)util/intel-pt-decoder + +ifneq ($(CC), clang) + CFLAGS_intel-pt-insn-decoder.o += -Wno-override-init +endif diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c index e4e7dc781d21..7cf7f7aca4d2 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -22,6 +22,7 @@ #include <errno.h> #include <stdint.h> #include <inttypes.h> +#include <linux/compiler.h> #include "../cache.h" #include "../util.h" @@ -1746,6 +1747,7 @@ static int intel_pt_walk_psb(struct intel_pt_decoder *decoder) switch (decoder->packet.type) { case INTEL_PT_TIP_PGD: decoder->continuous_period = false; + __fallthrough; case INTEL_PT_TIP_PGE: case INTEL_PT_TIP: intel_pt_log("ERROR: Unexpected packet\n"); @@ -1799,6 +1801,8 @@ static int intel_pt_walk_psb(struct intel_pt_decoder *decoder) decoder->pge = false; decoder->continuous_period = false; intel_pt_clear_tx_flags(decoder); + __fallthrough; + case INTEL_PT_TNT: decoder->have_tma = false; intel_pt_log("ERROR: Unexpected packet\n"); @@ -1839,6 +1843,7 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder) switch (decoder->packet.type) { case INTEL_PT_TIP_PGD: decoder->continuous_period = false; + __fallthrough; case INTEL_PT_TIP_PGE: case INTEL_PT_TIP: decoder->pge = decoder->packet.type != INTEL_PT_TIP_PGD; diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c index 7913363bde5c..54818828023b 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c @@ -26,12 +26,13 @@ #include "insn.c" #include "intel-pt-insn-decoder.h" +#include "dump-insn.h" #if INTEL_PT_INSN_BUF_SZ < MAX_INSN_SIZE || INTEL_PT_INSN_BUF_SZ > MAX_INSN #error Instruction buffer size too small #endif -/* Based on branch_type() from perf_event_intel_lbr.c */ +/* Based on branch_type() from arch/x86/events/intel/lbr.c */ static void intel_pt_insn_decoder(struct insn *insn, struct intel_pt_insn *intel_pt_insn) { @@ -39,6 +40,8 @@ static void intel_pt_insn_decoder(struct insn *insn, enum intel_pt_insn_branch branch = INTEL_PT_BR_NO_BRANCH; int ext; + intel_pt_insn->rel = 0; + if (insn_is_avx(insn)) { intel_pt_insn->op = INTEL_PT_OP_OTHER; intel_pt_insn->branch = INTEL_PT_BR_NO_BRANCH; @@ -177,6 +180,29 @@ int intel_pt_get_insn(const unsigned char *buf, size_t len, int x86_64, return 0; } +const char *dump_insn(struct perf_insn *x, uint64_t ip __maybe_unused, + u8 *inbuf, int inlen, int *lenp) +{ + struct insn insn; + int n, i; + int left; + + insn_init(&insn, inbuf, inlen, x->is64bit); + insn_get_length(&insn); + if (!insn_complete(&insn) || insn.length > inlen) + return "<bad>"; + if (lenp) + *lenp = insn.length; + left = sizeof(x->out); + n = snprintf(x->out, left, "insn: "); + left -= n; + for (i = 0; i < insn.length; i++) { + n += snprintf(x->out + n, left, "%02x ", inbuf[i]); + left -= n; + } + return x->out; +} + const char *branch_name[] = { [INTEL_PT_OP_OTHER] = "Other", [INTEL_PT_OP_CALL] = "Call", diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c index 4f7b32020487..7528ae4f7e28 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c @@ -17,6 +17,7 @@ #include <string.h> #include <endian.h> #include <byteswap.h> +#include <linux/compiler.h> #include "intel-pt-pkt-decoder.h" @@ -498,6 +499,7 @@ int intel_pt_pkt_desc(const struct intel_pt_pkt *packet, char *buf, case INTEL_PT_FUP: if (!(packet->count)) return snprintf(buf, buf_len, "%s no ip", name); + __fallthrough; case INTEL_PT_CYC: case INTEL_PT_VMCS: case INTEL_PT_MTC: diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 85d5eeb66c75..4c7718f87a08 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -13,6 +13,7 @@ * */ +#include <inttypes.h> #include <stdio.h> #include <stdbool.h> #include <errno.h> @@ -22,6 +23,7 @@ #include "../perf.h" #include "session.h" #include "machine.h" +#include "memswap.h" #include "sort.h" #include "tool.h" #include "event.h" @@ -2159,7 +2161,9 @@ int intel_pt_process_auxtrace_info(union perf_event *event, addr_filters__init(&pt->filts); - perf_config(intel_pt_perf_config, pt); + err = perf_config(intel_pt_perf_config, pt); + if (err) + goto err_free; err = auxtrace_queues__init(&pt->queues); if (err) diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c index c9a941ef0f6d..9084930e1757 100644 --- a/tools/perf/util/jitdump.c +++ b/tools/perf/util/jitdump.c @@ -1,5 +1,6 @@ #include <sys/sysmacros.h> #include <sys/types.h> +#include <errno.h> #include <stdio.h> #include <stdlib.h> #include <string.h> @@ -9,13 +10,13 @@ #include <byteswap.h> #include <sys/stat.h> #include <sys/mman.h> +#include <linux/stringify.h> #include "util.h" #include "event.h" #include "debug.h" #include "evlist.h" #include "symbol.h" -#include "strlist.h" #include <elf.h> #include "tsc.h" @@ -25,6 +26,8 @@ #include "genelf.h" #include "../builtin.h" +#include "sane_ctype.h" + struct jit_buf_desc { struct perf_data_file *output; struct perf_session *session; @@ -181,7 +184,7 @@ jit_open(struct jit_buf_desc *jd, const char *name) jd->use_arch_timestamp); if (header.version > JITHEADER_VERSION) { - pr_err("wrong jitdump version %u, expected " STR(JITHEADER_VERSION), + pr_err("wrong jitdump version %u, expected " __stringify(JITHEADER_VERSION), header.version); goto error; } diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c index b23ff44cf214..c6a15f204c03 100644 --- a/tools/perf/util/llvm-utils.c +++ b/tools/perf/util/llvm-utils.c @@ -12,6 +12,7 @@ #include "llvm-utils.h" #include "config.h" #include "util.h" +#include <sys/wait.h> #define CLANG_BPF_CMD_DEFAULT_TEMPLATE \ "$CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS "\ @@ -48,8 +49,10 @@ int perf_llvm_config(const char *var, const char *value) llvm_param.kbuild_opts = strdup(value); else if (!strcmp(var, "dump-obj")) llvm_param.dump_obj = !!perf_config_bool(var, value); - else + else { + pr_debug("Invalid LLVM config option: %s\n", value); return -1; + } llvm_param.user_set_param = true; return 0; } diff --git a/tools/perf/util/lzma.c b/tools/perf/util/lzma.c index 9ddea5cecd94..4ca7c5c6cdcd 100644 --- a/tools/perf/util/lzma.c +++ b/tools/perf/util/lzma.c @@ -1,6 +1,8 @@ +#include <errno.h> #include <lzma.h> #include <stdio.h> #include <linux/compiler.h> +#include "compress.h" #include "util.h" #include "debug.h" diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 9b33bef54581..d97e014c3df3 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1,3 +1,7 @@ +#include <dirent.h> +#include <errno.h> +#include <inttypes.h> +#include <regex.h> #include "callchain.h" #include "debug.h" #include "event.h" @@ -10,9 +14,15 @@ #include "thread.h" #include "vdso.h" #include <stdbool.h> -#include <symbol/kallsyms.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> #include "unwind.h" #include "linux/hash.h" +#include "asm/bug.h" + +#include "sane_ctype.h" +#include <symbol/kallsyms.h> static void __machine__remove_thread(struct machine *machine, struct thread *th, bool lock); @@ -87,6 +97,25 @@ out_delete: return NULL; } +struct machine *machine__new_kallsyms(void) +{ + struct machine *machine = machine__new_host(); + /* + * FIXME: + * 1) MAP__FUNCTION will go away when we stop loading separate maps for + * functions and data objects. + * 2) We should switch to machine__load_kallsyms(), i.e. not explicitely + * ask for not using the kcore parsing code, once this one is fixed + * to create a map per module. + */ + if (machine && __machine__load_kallsyms(machine, "/proc/kallsyms", MAP__FUNCTION, true) <= 0) { + machine__delete(machine); + machine = NULL; + } + + return machine; +} + static void dsos__purge(struct dsos *dsos) { struct dso *pos, *n; @@ -482,6 +511,37 @@ int machine__process_comm_event(struct machine *machine, union perf_event *event return err; } +int machine__process_namespaces_event(struct machine *machine __maybe_unused, + union perf_event *event, + struct perf_sample *sample __maybe_unused) +{ + struct thread *thread = machine__findnew_thread(machine, + event->namespaces.pid, + event->namespaces.tid); + int err = 0; + + WARN_ONCE(event->namespaces.nr_namespaces > NR_NAMESPACES, + "\nWARNING: kernel seems to support more namespaces than perf" + " tool.\nTry updating the perf tool..\n\n"); + + WARN_ONCE(event->namespaces.nr_namespaces < NR_NAMESPACES, + "\nWARNING: perf tool seems to support more namespaces than" + " the kernel.\nTry updating the kernel..\n\n"); + + if (dump_trace) + perf_event__fprintf_namespaces(event, stdout); + + if (thread == NULL || + thread__set_namespaces(thread, sample->time, &event->namespaces)) { + dump_printf("problem processing PERF_RECORD_NAMESPACES, skipping event.\n"); + err = -1; + } + + thread__put(thread); + + return err; +} + int machine__process_lost_event(struct machine *machine __maybe_unused, union perf_event *event, struct perf_sample *sample __maybe_unused) { @@ -736,11 +796,11 @@ const char *ref_reloc_sym_names[] = {"_text", "_stext", NULL}; * Returns the name of the start symbol in *symbol_name. Pass in NULL as * symbol_name if it's not that important. */ -static u64 machine__get_running_kernel_start(struct machine *machine, - const char **symbol_name) +static int machine__get_running_kernel_start(struct machine *machine, + const char **symbol_name, u64 *start) { char filename[PATH_MAX]; - int i; + int i, err = -1; const char *name; u64 addr = 0; @@ -750,21 +810,28 @@ static u64 machine__get_running_kernel_start(struct machine *machine, return 0; for (i = 0; (name = ref_reloc_sym_names[i]) != NULL; i++) { - addr = kallsyms__get_function_start(filename, name); - if (addr) + err = kallsyms__get_function_start(filename, name, &addr); + if (!err) break; } + if (err) + return -1; + if (symbol_name) *symbol_name = name; - return addr; + *start = addr; + return 0; } int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel) { - enum map_type type; - u64 start = machine__get_running_kernel_start(machine, NULL); + int type; + u64 start = 0; + + if (machine__get_running_kernel_start(machine, NULL, &start)) + return -1; /* In case of renewal the kernel map, destroy previous one */ machine__destroy_kernel_maps(machine); @@ -794,7 +861,7 @@ int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel) void machine__destroy_kernel_maps(struct machine *machine) { - enum map_type type; + int type; for (type = 0; type < MAP__NR_TYPES; ++type) { struct kmap *kmap; @@ -1125,8 +1192,8 @@ static int machine__create_modules(struct machine *machine) int machine__create_kernel_maps(struct machine *machine) { struct dso *kernel = machine__get_kernel(machine); - const char *name; - u64 addr; + const char *name = NULL; + u64 addr = 0; int ret; if (kernel == NULL) @@ -1151,8 +1218,7 @@ int machine__create_kernel_maps(struct machine *machine) */ map_groups__fixup_end(&machine->kmaps); - addr = machine__get_running_kernel_start(machine, &name); - if (!addr) { + if (machine__get_running_kernel_start(machine, &name, &addr)) { } else if (maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, name, addr)) { machine__destroy_kernel_maps(machine); return -1; @@ -1420,7 +1486,7 @@ static void __machine__remove_thread(struct machine *machine, struct thread *th, if (machine->last_match == th) machine->last_match = NULL; - BUG_ON(atomic_read(&th->refcnt) == 0); + BUG_ON(refcount_read(&th->refcnt) == 0); if (lock) pthread_rwlock_wrlock(&machine->threads_lock); rb_erase_init(&th->rb_node, &machine->threads); @@ -1519,6 +1585,8 @@ int machine__process_event(struct machine *machine, union perf_event *event, ret = machine__process_comm_event(machine, event, sample); break; case PERF_RECORD_MMAP: ret = machine__process_mmap_event(machine, event, sample); break; + case PERF_RECORD_NAMESPACES: + ret = machine__process_namespaces_event(machine, event, sample); break; case PERF_RECORD_MMAP2: ret = machine__process_mmap2_event(machine, event, sample); break; case PERF_RECORD_FORK: @@ -1546,7 +1614,7 @@ int machine__process_event(struct machine *machine, union perf_event *event, static bool symbol__match_regex(struct symbol *sym, regex_t *regex) { - if (sym->name && !regexec(regex, sym->name, 0, NULL, 0)) + if (!regexec(regex, sym->name, 0, NULL, 0)) return 1; return 0; } diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index 354de6e56109..3cdb1340f917 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -97,6 +97,9 @@ int machine__process_itrace_start_event(struct machine *machine, union perf_event *event); int machine__process_switch_event(struct machine *machine, union perf_event *event); +int machine__process_namespaces_event(struct machine *machine, + union perf_event *event, + struct perf_sample *sample); int machine__process_mmap_event(struct machine *machine, union perf_event *event, struct perf_sample *sample); int machine__process_mmap2_event(struct machine *machine, union perf_event *event, @@ -129,6 +132,7 @@ char *machine__mmap_name(struct machine *machine, char *bf, size_t size); void machines__set_comm_exec(struct machines *machines, bool comm_exec); struct machine *machine__new_host(void); +struct machine *machine__new_kallsyms(void); int machine__init(struct machine *machine, const char *root_dir, pid_t pid); void machine__exit(struct machine *machine); void machine__delete_threads(struct machine *machine); diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 4f9a71c63026..2179b2deb730 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -9,13 +9,13 @@ #include <uapi/linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */ #include "map.h" #include "thread.h" -#include "strlist.h" #include "vdso.h" #include "build-id.h" #include "util.h" #include "debug.h" #include "machine.h" #include <linux/string.h> +#include "srcline.h" #include "unwind.h" static void __maps__insert(struct maps *maps, struct map *map); @@ -141,7 +141,7 @@ void map__init(struct map *map, enum map_type type, RB_CLEAR_NODE(&map->rb_node); map->groups = NULL; map->erange_warned = false; - atomic_set(&map->refcnt, 1); + refcount_set(&map->refcnt, 1); } struct map *map__new(struct machine *machine, u64 start, u64 len, @@ -255,7 +255,7 @@ void map__delete(struct map *map) void map__put(struct map *map) { - if (map && atomic_dec_and_test(&map->refcnt)) + if (map && refcount_dec_and_test(&map->refcnt)) map__delete(map); } @@ -325,11 +325,6 @@ int map__load(struct map *map) return 0; } -int __weak arch__compare_symbol_names(const char *namea, const char *nameb) -{ - return strcmp(namea, nameb); -} - struct symbol *map__find_symbol(struct map *map, u64 addr) { if (map__load(map) < 0) @@ -354,7 +349,7 @@ struct map *map__clone(struct map *from) struct map *map = memdup(from, sizeof(*map)); if (map != NULL) { - atomic_set(&map->refcnt, 1); + refcount_set(&map->refcnt, 1); RB_CLEAR_NODE(&map->rb_node); dso__get(map->dso); map->groups = NULL; @@ -387,10 +382,10 @@ size_t map__fprintf_dsoname(struct map *map, FILE *fp) { const char *dsoname = "[unknown]"; - if (map && map->dso && (map->dso->name || map->dso->long_name)) { + if (map && map->dso) { if (symbol_conf.show_kernel_path && map->dso->long_name) dsoname = map->dso->long_name; - else if (map->dso->name) + else dsoname = map->dso->name; } @@ -405,7 +400,8 @@ int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix, if (map && map->dso) { srcline = get_srcline(map->dso, - map__rip_2objdump(map, addr), NULL, true); + map__rip_2objdump(map, addr), NULL, + true, true); if (srcline != SRCLINE_UNKNOWN) ret = fprintf(fp, "%s%s", prefix, srcline); free_srcline(srcline); @@ -485,7 +481,7 @@ void map_groups__init(struct map_groups *mg, struct machine *machine) maps__init(&mg->maps[i]); } mg->machine = machine; - atomic_set(&mg->refcnt, 1); + refcount_set(&mg->refcnt, 1); } static void __maps__purge(struct maps *maps) @@ -547,7 +543,7 @@ void map_groups__delete(struct map_groups *mg) void map_groups__put(struct map_groups *mg) { - if (mg && atomic_dec_and_test(&mg->refcnt)) + if (mg && refcount_dec_and_test(&mg->refcnt)) map_groups__delete(mg); } diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index abdacf800c98..f9e8ac8a52cd 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -1,7 +1,7 @@ #ifndef __PERF_MAP_H #define __PERF_MAP_H -#include <linux/atomic.h> +#include <linux/refcount.h> #include <linux/compiler.h> #include <linux/list.h> #include <linux/rbtree.h> @@ -51,7 +51,7 @@ struct map { struct dso *dso; struct map_groups *groups; - atomic_t refcnt; + refcount_t refcnt; }; struct kmap { @@ -67,7 +67,7 @@ struct maps { struct map_groups { struct maps maps[MAP__NR_TYPES]; struct machine *machine; - atomic_t refcnt; + refcount_t refcnt; }; struct map_groups *map_groups__new(struct machine *machine); @@ -77,7 +77,7 @@ bool map_groups__empty(struct map_groups *mg); static inline struct map_groups *map_groups__get(struct map_groups *mg) { if (mg) - atomic_inc(&mg->refcnt); + refcount_inc(&mg->refcnt); return mg; } @@ -130,13 +130,14 @@ struct thread; */ #define __map__for_each_symbol_by_name(map, sym_name, pos) \ for (pos = map__find_symbol_by_name(map, sym_name); \ - pos && arch__compare_symbol_names(pos->name, sym_name) == 0; \ + pos && \ + !symbol__match_symbol_name(pos->name, sym_name, \ + SYMBOL_TAG_INCLUDE__DEFAULT_ONLY); \ pos = symbol__next_by_name(pos)) #define map__for_each_symbol_by_name(map, sym_name, pos) \ __map__for_each_symbol_by_name(map, sym_name, (pos)) -int arch__compare_symbol_names(const char *namea, const char *nameb); void map__init(struct map *map, enum map_type type, u64 start, u64 end, u64 pgoff, struct dso *dso); struct map *map__new(struct machine *machine, u64 start, u64 len, @@ -150,7 +151,7 @@ struct map *map__clone(struct map *map); static inline struct map *map__get(struct map *map) { if (map) - atomic_inc(&map->refcnt); + refcount_inc(&map->refcnt); return map; } diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c index 1d4ab53c60ca..06f5a3a4295c 100644 --- a/tools/perf/util/mem-events.c +++ b/tools/perf/util/mem-events.c @@ -6,6 +6,7 @@ #include <sys/stat.h> #include <unistd.h> #include <api/fs/fs.h> +#include <linux/kernel.h> #include "mem-events.h" #include "debug.h" #include "symbol.h" @@ -205,8 +206,8 @@ int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info) static const char * const snoop_access[] = { "N/A", "None", - "Miss", "Hit", + "Miss", "HitM", }; diff --git a/tools/perf/util/memswap.c b/tools/perf/util/memswap.c new file mode 100644 index 000000000000..55f7faa8d9ec --- /dev/null +++ b/tools/perf/util/memswap.c @@ -0,0 +1,24 @@ +#include <byteswap.h> +#include "memswap.h" +#include <linux/types.h> + +void mem_bswap_32(void *src, int byte_size) +{ + u32 *m = src; + while (byte_size > 0) { + *m = bswap_32(*m); + byte_size -= sizeof(u32); + ++m; + } +} + +void mem_bswap_64(void *src, int byte_size) +{ + u64 *m = src; + + while (byte_size > 0) { + *m = bswap_64(*m); + byte_size -= sizeof(u64); + ++m; + } +} diff --git a/tools/perf/util/memswap.h b/tools/perf/util/memswap.h new file mode 100644 index 000000000000..7d1b1c34bb57 --- /dev/null +++ b/tools/perf/util/memswap.h @@ -0,0 +1,7 @@ +#ifndef PERF_MEMSWAP_H_ +#define PERF_MEMSWAP_H_ + +void mem_bswap_64(void *src, int byte_size); +void mem_bswap_32(void *src, int byte_size); + +#endif /* PERF_MEMSWAP_H_ */ diff --git a/tools/perf/util/namespaces.c b/tools/perf/util/namespaces.c new file mode 100644 index 000000000000..67dcbcc73c7d --- /dev/null +++ b/tools/perf/util/namespaces.c @@ -0,0 +1,37 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * Copyright (C) 2017 Hari Bathini, IBM Corporation + */ + +#include "namespaces.h" +#include "util.h" +#include "event.h" +#include <stdlib.h> +#include <stdio.h> +#include <string.h> + +struct namespaces *namespaces__new(struct namespaces_event *event) +{ + struct namespaces *namespaces; + u64 link_info_size = ((event ? event->nr_namespaces : NR_NAMESPACES) * + sizeof(struct perf_ns_link_info)); + + namespaces = zalloc(sizeof(struct namespaces) + link_info_size); + if (!namespaces) + return NULL; + + namespaces->end_time = -1; + + if (event) + memcpy(namespaces->link_info, event->link_info, link_info_size); + + return namespaces; +} + +void namespaces__free(struct namespaces *namespaces) +{ + free(namespaces); +} diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h new file mode 100644 index 000000000000..468f1e9a1484 --- /dev/null +++ b/tools/perf/util/namespaces.h @@ -0,0 +1,26 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * Copyright (C) 2017 Hari Bathini, IBM Corporation + */ + +#ifndef __PERF_NAMESPACES_H +#define __PERF_NAMESPACES_H + +#include "../perf.h" +#include <linux/list.h> + +struct namespaces_event; + +struct namespaces { + struct list_head list; + u64 end_time; + struct perf_ns_link_info link_info[]; +}; + +struct namespaces *namespaces__new(struct namespaces_event *event); +void namespaces__free(struct namespaces *namespaces); + +#endif /* __PERF_NAMESPACES_H */ diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c index fe84df1875aa..4de398cfb577 100644 --- a/tools/perf/util/ordered-events.c +++ b/tools/perf/util/ordered-events.c @@ -1,3 +1,5 @@ +#include <errno.h> +#include <inttypes.h> #include <linux/list.h> #include <linux/compiler.h> #include <linux/string.h> @@ -79,7 +81,7 @@ static union perf_event *dup_event(struct ordered_events *oe, static void free_dup_event(struct ordered_events *oe, union perf_event *event) { - if (oe->copy_on_queue) { + if (event && oe->copy_on_queue) { oe->cur_alloc_size -= event->header.size; free(event); } @@ -150,6 +152,7 @@ void ordered_events__delete(struct ordered_events *oe, struct ordered_event *eve list_move(&event->list, &oe->cache); oe->nr_events--; free_dup_event(oe, event->event); + event->event = NULL; } int ordered_events__queue(struct ordered_events *oe, union perf_event *event, diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 3c876b8ba4de..01e779b91c8e 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1,13 +1,18 @@ #include <linux/hw_breakpoint.h> #include <linux/err.h> -#include "util.h" +#include <dirent.h> +#include <errno.h> +#include <sys/ioctl.h> +#include <sys/param.h> +#include "term.h" #include "../perf.h" #include "evlist.h" #include "evsel.h" #include <subcmd/parse-options.h> #include "parse-events.h" #include <subcmd/exec-cmd.h> -#include "string.h" +#include "string2.h" +#include "strlist.h" #include "symbol.h" #include "cache.h" #include "header.h" @@ -211,6 +216,8 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config) closedir(evt_dir); closedir(sys_dir); path = zalloc(sizeof(*path)); + if (!path) + return NULL; path->system = malloc(MAX_EVENT_LENGTH); if (!path->system) { free(path); @@ -252,8 +259,7 @@ struct tracepoint_path *tracepoint_name_to_path(const char *name) if (path->system == NULL || path->name == NULL) { zfree(&path->system); zfree(&path->name); - free(path); - path = NULL; + zfree(&path); } return path; @@ -310,12 +316,14 @@ __add_event(struct list_head *list, int *idx, event_attr_init(attr); - evsel = perf_evsel__new_idx(attr, (*idx)++); + evsel = perf_evsel__new_idx(attr, *idx); if (!evsel) return NULL; - evsel->cpus = cpu_map__get(cpus); - evsel->own_cpus = cpu_map__get(cpus); + (*idx)++; + evsel->cpus = cpu_map__get(cpus); + evsel->own_cpus = cpu_map__get(cpus); + evsel->system_wide = !!cpus; if (name) evsel->name = strdup(name); @@ -1252,11 +1260,59 @@ int parse_events_add_pmu(struct parse_events_evlist *data, evsel->scale = info.scale; evsel->per_pkg = info.per_pkg; evsel->snapshot = info.snapshot; + evsel->metric_expr = info.metric_expr; + evsel->metric_name = info.metric_name; } return evsel ? 0 : -ENOMEM; } +int parse_events_multi_pmu_add(struct parse_events_evlist *data, + char *str, struct list_head **listp) +{ + struct list_head *head; + struct parse_events_term *term; + struct list_head *list; + struct perf_pmu *pmu = NULL; + int ok = 0; + + *listp = NULL; + /* Add it for all PMUs that support the alias */ + list = malloc(sizeof(struct list_head)); + if (!list) + return -1; + INIT_LIST_HEAD(list); + while ((pmu = perf_pmu__scan(pmu)) != NULL) { + struct perf_pmu_alias *alias; + + list_for_each_entry(alias, &pmu->aliases, list) { + if (!strcasecmp(alias->name, str)) { + head = malloc(sizeof(struct list_head)); + if (!head) + return -1; + INIT_LIST_HEAD(head); + if (parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, + str, 1, false, &str, NULL) < 0) + return -1; + list_add_tail(&term->list, head); + + if (!parse_events_add_pmu(data, list, + pmu->name, head)) { + pr_debug("%s -> %s/%s/\n", str, + pmu->name, alias->str); + ok++; + } + + parse_events_terms__delete(head); + } + } + } + if (!ok) + return -1; + *listp = list; + return 0; +} + int parse_events__modifier_group(struct list_head *list, char *event_mod) { @@ -1477,10 +1533,9 @@ static void perf_pmu__parse_cleanup(void) for (i = 0; i < perf_pmu_events_list_num; i++) { p = perf_pmu_events_list + i; - free(p->symbol); + zfree(&p->symbol); } - free(perf_pmu_events_list); - perf_pmu_events_list = NULL; + zfree(&perf_pmu_events_list); perf_pmu_events_list_num = 0; } } @@ -1504,35 +1559,41 @@ static void perf_pmu__parse_init(void) struct perf_pmu_alias *alias; int len = 0; - pmu = perf_pmu__find("cpu"); - if ((pmu == NULL) || list_empty(&pmu->aliases)) { + pmu = NULL; + while ((pmu = perf_pmu__scan(pmu)) != NULL) { + list_for_each_entry(alias, &pmu->aliases, list) { + if (strchr(alias->name, '-')) + len++; + len++; + } + } + + if (len == 0) { perf_pmu_events_list_num = -1; return; } - list_for_each_entry(alias, &pmu->aliases, list) { - if (strchr(alias->name, '-')) - len++; - len++; - } perf_pmu_events_list = malloc(sizeof(struct perf_pmu_event_symbol) * len); if (!perf_pmu_events_list) return; perf_pmu_events_list_num = len; len = 0; - list_for_each_entry(alias, &pmu->aliases, list) { - struct perf_pmu_event_symbol *p = perf_pmu_events_list + len; - char *tmp = strchr(alias->name, '-'); - - if (tmp != NULL) { - SET_SYMBOL(strndup(alias->name, tmp - alias->name), - PMU_EVENT_SYMBOL_PREFIX); - p++; - SET_SYMBOL(strdup(++tmp), PMU_EVENT_SYMBOL_SUFFIX); - len += 2; - } else { - SET_SYMBOL(strdup(alias->name), PMU_EVENT_SYMBOL); - len++; + pmu = NULL; + while ((pmu = perf_pmu__scan(pmu)) != NULL) { + list_for_each_entry(alias, &pmu->aliases, list) { + struct perf_pmu_event_symbol *p = perf_pmu_events_list + len; + char *tmp = strchr(alias->name, '-'); + + if (tmp != NULL) { + SET_SYMBOL(strndup(alias->name, tmp - alias->name), + PMU_EVENT_SYMBOL_PREFIX); + p++; + SET_SYMBOL(strdup(++tmp), PMU_EVENT_SYMBOL_SUFFIX); + len += 2; + } else { + SET_SYMBOL(strdup(alias->name), PMU_EVENT_SYMBOL); + len++; + } } } qsort(perf_pmu_events_list, len, @@ -1563,7 +1624,7 @@ perf_pmu__parse_check(const char *name) r = bsearch(&p, perf_pmu_events_list, (size_t) perf_pmu_events_list_num, sizeof(struct perf_pmu_event_symbol), comp_pmu); - free(p.symbol); + zfree(&p.symbol); return r ? r->type : PMU_EVENT_SYMBOL_ERR; } @@ -1710,8 +1771,8 @@ static void parse_events_print_error(struct parse_events_error *err, fprintf(stderr, "%*s\\___ %s\n", idx + 1, "", err->str); if (err->help) fprintf(stderr, "\n%s\n", err->help); - free(err->str); - free(err->help); + zfree(&err->str); + zfree(&err->help); } fprintf(stderr, "Run 'perf list' for a list of valid events\n"); @@ -2013,17 +2074,14 @@ static bool is_event_supported(u8 type, unsigned config) .config = config, .disabled = 1, }; - struct { - struct thread_map map; - int threads[1]; - } tmap = { - .map.nr = 1, - .threads = { 0 }, - }; + struct thread_map *tmap = thread_map__new_by_tid(0); + + if (tmap == NULL) + return false; evsel = perf_evsel__new(&attr); if (evsel) { - open_return = perf_evsel__open(evsel, NULL, &tmap.map); + open_return = perf_evsel__open(evsel, NULL, tmap); ret = open_return >= 0; if (open_return == -EACCES) { @@ -2035,7 +2093,7 @@ static bool is_event_supported(u8 type, unsigned config) * */ evsel->attr.exclude_kernel = 1; - ret = perf_evsel__open(evsel, NULL, &tmap.map) >= 0; + ret = perf_evsel__open(evsel, NULL, tmap) >= 0; } perf_evsel__delete(evsel); } @@ -2272,7 +2330,7 @@ out_enomem: * Print the help text for the event symbols: */ void print_events(const char *event_glob, bool name_only, bool quiet_flag, - bool long_desc) + bool long_desc, bool details_flag) { print_symbol_events(event_glob, PERF_TYPE_HARDWARE, event_symbols_hw, PERF_COUNT_HW_MAX, name_only); @@ -2282,7 +2340,8 @@ void print_events(const char *event_glob, bool name_only, bool quiet_flag, print_hwcache_events(event_glob, name_only); - print_pmu_events(event_glob, name_only, quiet_flag, long_desc); + print_pmu_events(event_glob, name_only, quiet_flag, long_desc, + details_flag); if (event_glob != NULL) return; @@ -2314,24 +2373,20 @@ int parse_events__is_hardcoded_term(struct parse_events_term *term) return term->type_term != PARSE_EVENTS__TERM_TYPE_USER; } -static int new_term(struct parse_events_term **_term, int type_val, - int type_term, char *config, - char *str, u64 num, int err_term, int err_val) +static int new_term(struct parse_events_term **_term, + struct parse_events_term *temp, + char *str, u64 num) { struct parse_events_term *term; - term = zalloc(sizeof(*term)); + term = malloc(sizeof(*term)); if (!term) return -ENOMEM; + *term = *temp; INIT_LIST_HEAD(&term->list); - term->type_val = type_val; - term->type_term = type_term; - term->config = config; - term->err_term = err_term; - term->err_val = err_val; - switch (type_val) { + switch (term->type_val) { case PARSE_EVENTS__TERM_TYPE_NUM: term->val.num = num; break; @@ -2349,15 +2404,22 @@ static int new_term(struct parse_events_term **_term, int type_val, int parse_events_term__num(struct parse_events_term **term, int type_term, char *config, u64 num, + bool no_value, void *loc_term_, void *loc_val_) { YYLTYPE *loc_term = loc_term_; YYLTYPE *loc_val = loc_val_; - return new_term(term, PARSE_EVENTS__TERM_TYPE_NUM, type_term, - config, NULL, num, - loc_term ? loc_term->first_column : 0, - loc_val ? loc_val->first_column : 0); + struct parse_events_term temp = { + .type_val = PARSE_EVENTS__TERM_TYPE_NUM, + .type_term = type_term, + .config = config, + .no_value = no_value, + .err_term = loc_term ? loc_term->first_column : 0, + .err_val = loc_val ? loc_val->first_column : 0, + }; + + return new_term(term, &temp, NULL, num); } int parse_events_term__str(struct parse_events_term **term, @@ -2367,37 +2429,70 @@ int parse_events_term__str(struct parse_events_term **term, YYLTYPE *loc_term = loc_term_; YYLTYPE *loc_val = loc_val_; - return new_term(term, PARSE_EVENTS__TERM_TYPE_STR, type_term, - config, str, 0, - loc_term ? loc_term->first_column : 0, - loc_val ? loc_val->first_column : 0); + struct parse_events_term temp = { + .type_val = PARSE_EVENTS__TERM_TYPE_STR, + .type_term = type_term, + .config = config, + .err_term = loc_term ? loc_term->first_column : 0, + .err_val = loc_val ? loc_val->first_column : 0, + }; + + return new_term(term, &temp, str, 0); } int parse_events_term__sym_hw(struct parse_events_term **term, char *config, unsigned idx) { struct event_symbol *sym; + struct parse_events_term temp = { + .type_val = PARSE_EVENTS__TERM_TYPE_STR, + .type_term = PARSE_EVENTS__TERM_TYPE_USER, + .config = config ?: (char *) "event", + }; BUG_ON(idx >= PERF_COUNT_HW_MAX); sym = &event_symbols_hw[idx]; - if (config) - return new_term(term, PARSE_EVENTS__TERM_TYPE_STR, - PARSE_EVENTS__TERM_TYPE_USER, config, - (char *) sym->symbol, 0, 0, 0); - else - return new_term(term, PARSE_EVENTS__TERM_TYPE_STR, - PARSE_EVENTS__TERM_TYPE_USER, - (char *) "event", (char *) sym->symbol, - 0, 0, 0); + return new_term(term, &temp, (char *) sym->symbol, 0); } int parse_events_term__clone(struct parse_events_term **new, struct parse_events_term *term) { - return new_term(new, term->type_val, term->type_term, term->config, - term->val.str, term->val.num, - term->err_term, term->err_val); + struct parse_events_term temp = { + .type_val = term->type_val, + .type_term = term->type_term, + .config = term->config, + .err_term = term->err_term, + .err_val = term->err_val, + }; + + return new_term(new, &temp, term->val.str, term->val.num); +} + +int parse_events_copy_term_list(struct list_head *old, + struct list_head **new) +{ + struct parse_events_term *term, *n; + int ret; + + if (!old) { + *new = NULL; + return 0; + } + + *new = malloc(sizeof(struct list_head)); + if (!*new) + return -ENOMEM; + INIT_LIST_HEAD(*new); + + list_for_each_entry (term, old, list) { + ret = parse_events_term__clone(&n, term); + if (ret) + return ret; + list_add_tail(&n->list, *new); + } + return 0; } void parse_events_terms__purge(struct list_head *terms) @@ -2406,7 +2501,7 @@ void parse_events_terms__purge(struct list_head *terms) list_for_each_entry_safe(term, h, terms, list) { if (term->array.nr_ranges) - free(term->array.ranges); + zfree(&term->array.ranges); list_del_init(&term->list); free(term); } @@ -2422,7 +2517,7 @@ void parse_events_terms__delete(struct list_head *terms) void parse_events__clear_array(struct parse_events_array *a) { - free(a->ranges); + zfree(&a->ranges); } void parse_events_evlist_error(struct parse_events_evlist *data, diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index da246a3ddb69..a235f4d6d5e5 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -8,6 +8,7 @@ #include <stdbool.h> #include <linux/types.h> #include <linux/perf_event.h> +#include <string.h> struct list_head; struct perf_evsel; @@ -94,6 +95,7 @@ struct parse_events_term { int type_term; struct list_head list; bool used; + bool no_value; /* error string indexes for within parsed string */ int err_term; @@ -122,6 +124,7 @@ void parse_events__shrink_config_terms(void); int parse_events__is_hardcoded_term(struct parse_events_term *term); int parse_events_term__num(struct parse_events_term **term, int type_term, char *config, u64 num, + bool novalue, void *loc_term, void *loc_val); int parse_events_term__str(struct parse_events_term **term, int type_term, char *config, char *str, @@ -164,6 +167,14 @@ int parse_events_add_breakpoint(struct list_head *list, int *idx, int parse_events_add_pmu(struct parse_events_evlist *data, struct list_head *list, char *name, struct list_head *head_config); + +int parse_events_multi_pmu_add(struct parse_events_evlist *data, + char *str, + struct list_head **listp); + +int parse_events_copy_term_list(struct list_head *old, + struct list_head **new); + enum perf_pmu_event_symbol_type perf_pmu__parse_check(const char *name); void parse_events__set_leader(char *name, struct list_head *list); @@ -173,7 +184,7 @@ void parse_events_evlist_error(struct parse_events_evlist *data, int idx, const char *str); void print_events(const char *event_glob, bool name_only, bool quiet, - bool long_desc); + bool long_desc, bool details_flag); struct event_symbol { const char *symbol; @@ -194,4 +205,23 @@ int is_valid_tracepoint(const char *event_string); int valid_event_mount(const char *eventfs); char *parse_events_formats_error_string(char *additional_terms); +#ifdef HAVE_LIBELF_SUPPORT +/* + * If the probe point starts with '%', + * or starts with "sdt_" and has a ':' but no '=', + * then it should be a SDT/cached probe point. + */ +static inline bool is_sdt_event(char *str) +{ + return (str[0] == '%' || + (!strncmp(str, "sdt_", 4) && + !!strchr(str, ':') && !strchr(str, '='))); +} +#else +static inline bool is_sdt_event(char *str __maybe_unused) +{ + return false; +} +#endif /* HAVE_LIBELF_SUPPORT */ + #endif /* __PERF_PARSE_EVENTS_H */ diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index 879115f93edc..04fd8c9af9f9 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -12,9 +12,13 @@ #include <linux/list.h> #include <linux/types.h> #include "util.h" +#include "pmu.h" +#include "debug.h" #include "parse-events.h" #include "parse-events-bison.h" +void parse_events_error(YYLTYPE *loc, void *data, void *scanner, char const *msg); + #define ABORT_ON(val) \ do { \ if (val) \ @@ -222,49 +226,55 @@ event_pmu: PE_NAME opt_event_config { struct parse_events_evlist *data = _data; - struct list_head *list; + struct list_head *list, *orig_terms, *terms; + + if (parse_events_copy_term_list($2, &orig_terms)) + YYABORT; ALLOC_LIST(list); - ABORT_ON(parse_events_add_pmu(data, list, $1, $2)); + if (parse_events_add_pmu(data, list, $1, $2)) { + struct perf_pmu *pmu = NULL; + int ok = 0; + + while ((pmu = perf_pmu__scan(pmu)) != NULL) { + char *name = pmu->name; + + if (!strncmp(name, "uncore_", 7) && + strncmp($1, "uncore_", 7)) + name += 7; + if (!strncmp($1, name, strlen($1))) { + if (parse_events_copy_term_list(orig_terms, &terms)) + YYABORT; + if (!parse_events_add_pmu(data, list, pmu->name, terms)) + ok++; + parse_events_terms__delete(terms); + } + } + if (!ok) + YYABORT; + } parse_events_terms__delete($2); + parse_events_terms__delete(orig_terms); $$ = list; } | PE_KERNEL_PMU_EVENT sep_dc { - struct parse_events_evlist *data = _data; - struct list_head *head; - struct parse_events_term *term; struct list_head *list; - ALLOC_LIST(head); - ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, - $1, 1, &@1, NULL)); - list_add_tail(&term->list, head); - - ALLOC_LIST(list); - ABORT_ON(parse_events_add_pmu(data, list, "cpu", head)); - parse_events_terms__delete(head); + if (parse_events_multi_pmu_add(_data, $1, &list) < 0) + YYABORT; $$ = list; } | PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF sep_dc { - struct parse_events_evlist *data = _data; - struct list_head *head; - struct parse_events_term *term; struct list_head *list; char pmu_name[128]; - snprintf(&pmu_name, 128, "%s-%s", $1, $3); - - ALLOC_LIST(head); - ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, - &pmu_name, 1, &@1, NULL)); - list_add_tail(&term->list, head); - ALLOC_LIST(list); - ABORT_ON(parse_events_add_pmu(data, list, "cpu", head)); - parse_events_terms__delete(head); + snprintf(&pmu_name, 128, "%s-%s", $1, $3); + if (parse_events_multi_pmu_add(_data, pmu_name, &list) < 0) + YYABORT; $$ = list; } @@ -525,7 +535,7 @@ PE_NAME '=' PE_VALUE struct parse_events_term *term; ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, - $1, $3, &@1, &@3)); + $1, $3, false, &@1, &@3)); $$ = term; } | @@ -543,7 +553,7 @@ PE_NAME struct parse_events_term *term; ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, - $1, 1, &@1, NULL)); + $1, 1, true, &@1, NULL)); $$ = term; } | @@ -568,7 +578,7 @@ PE_TERM '=' PE_VALUE { struct parse_events_term *term; - ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, $3, &@1, &@3)); + ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, $3, false, &@1, &@3)); $$ = term; } | @@ -576,7 +586,7 @@ PE_TERM { struct parse_events_term *term; - ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, 1, &@1, NULL)); + ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, 1, true, &@1, NULL)); $$ = term; } | @@ -597,7 +607,7 @@ PE_NAME array '=' PE_VALUE struct parse_events_term *term; ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, - $1, $4, &@1, &@4)); + $1, $4, false, &@1, &@4)); term->array = $2; $$ = term; } diff --git a/tools/perf/util/path.c b/tools/perf/util/path.c index 7c7630be5a89..50ec3bc87a60 100644 --- a/tools/perf/util/path.c +++ b/tools/perf/util/path.c @@ -11,8 +11,13 @@ * which is what it's designed for. */ #include "cache.h" -#include "util.h" +#include "path.h" +#include <linux/kernel.h> #include <limits.h> +#include <stdio.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> static char bad_path[] = "/bad-path/"; /* @@ -50,3 +55,24 @@ char *mkpath(const char *fmt, ...) return bad_path; return cleanup_path(pathname); } + +int path__join(char *bf, size_t size, const char *path1, const char *path2) +{ + return scnprintf(bf, size, "%s%s%s", path1, path1[0] ? "/" : "", path2); +} + +int path__join3(char *bf, size_t size, const char *path1, const char *path2, const char *path3) +{ + return scnprintf(bf, size, "%s%s%s%s%s", path1, path1[0] ? "/" : "", + path2, path2[0] ? "/" : "", path3); +} + +bool is_regular_file(const char *file) +{ + struct stat st; + + if (stat(file, &st)) + return false; + + return S_ISREG(st.st_mode); +} diff --git a/tools/perf/util/path.h b/tools/perf/util/path.h new file mode 100644 index 000000000000..9a276a58e3c2 --- /dev/null +++ b/tools/perf/util/path.h @@ -0,0 +1,9 @@ +#ifndef _PERF_PATH_H +#define _PERF_PATH_H + +int path__join(char *bf, size_t size, const char *path1, const char *path2); +int path__join3(char *bf, size_t size, const char *path1, const char *path2, const char *path3); + +bool is_regular_file(const char *file); + +#endif /* _PERF_PATH_H */ diff --git a/tools/perf/util/perf-hooks.c b/tools/perf/util/perf-hooks.c index cb368306b12b..d55092964da2 100644 --- a/tools/perf/util/perf-hooks.c +++ b/tools/perf/util/perf-hooks.c @@ -9,6 +9,7 @@ #include <stdlib.h> #include <setjmp.h> #include <linux/err.h> +#include <linux/kernel.h> #include "util/util.h" #include "util/debug.h" #include "util/perf-hooks.h" diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c index c4023f22f287..b2ae039eff85 100644 --- a/tools/perf/util/perf_regs.c +++ b/tools/perf/util/perf_regs.c @@ -6,6 +6,12 @@ const struct sample_reg __weak sample_reg_masks[] = { SMPL_REG_END }; +int __weak arch_sdt_arg_parse_op(char *old_op __maybe_unused, + char **new_op __maybe_unused) +{ + return SDT_ARG_SKIP; +} + #ifdef HAVE_PERF_REGS_SUPPORT int perf_reg_value(u64 *valp, struct regs_dump *regs, int id) { diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h index 679d6e493962..32b37d19dcc3 100644 --- a/tools/perf/util/perf_regs.h +++ b/tools/perf/util/perf_regs.h @@ -15,6 +15,13 @@ struct sample_reg { extern const struct sample_reg sample_reg_masks[]; +enum { + SDT_ARG_VALID = 0, + SDT_ARG_SKIP, +}; + +int arch_sdt_arg_parse_op(char *old_op, char **new_op); + #ifdef HAVE_PERF_REGS_SUPPORT #include <perf_regs.h> diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index dc6ccaa4e927..ac16a9db1fb5 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -1,6 +1,8 @@ #include <linux/list.h> #include <linux/compiler.h> #include <sys/types.h> +#include <errno.h> +#include <sys/stat.h> #include <unistd.h> #include <stdio.h> #include <stdbool.h> @@ -15,6 +17,7 @@ #include "header.h" #include "pmu-events/pmu-events.h" #include "cache.h" +#include "string2.h" struct perf_pmu_format { char *name; @@ -94,32 +97,10 @@ static int pmu_format(const char *name, struct list_head *format) return 0; } -static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *name) +static int convert_scale(const char *scale, char **end, double *sval) { - struct stat st; - ssize_t sret; - char scale[128]; - int fd, ret = -1; - char path[PATH_MAX]; char *lc; - - snprintf(path, PATH_MAX, "%s/%s.scale", dir, name); - - fd = open(path, O_RDONLY); - if (fd == -1) - return -1; - - if (fstat(fd, &st) < 0) - goto error; - - sret = read(fd, scale, sizeof(scale)-1); - if (sret < 0) - goto error; - - if (scale[sret - 1] == '\n') - scale[sret - 1] = '\0'; - else - scale[sret] = '\0'; + int ret = 0; /* * save current locale @@ -134,7 +115,7 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char * lc = strdup(lc); if (!lc) { ret = -ENOMEM; - goto error; + goto out; } /* @@ -144,14 +125,42 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char * */ setlocale(LC_NUMERIC, "C"); - alias->scale = strtod(scale, NULL); + *sval = strtod(scale, end); +out: /* restore locale */ setlocale(LC_NUMERIC, lc); - free(lc); + return ret; +} - ret = 0; +static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *name) +{ + struct stat st; + ssize_t sret; + char scale[128]; + int fd, ret = -1; + char path[PATH_MAX]; + + snprintf(path, PATH_MAX, "%s/%s.scale", dir, name); + + fd = open(path, O_RDONLY); + if (fd == -1) + return -1; + + if (fstat(fd, &st) < 0) + goto error; + + sret = read(fd, scale, sizeof(scale)-1); + if (sret < 0) + goto error; + + if (scale[sret - 1] == '\n') + scale[sret - 1] = '\0'; + else + scale[sret] = '\0'; + + ret = convert_scale(scale, NULL, &alias->scale); error: close(fd); return ret; @@ -223,11 +232,15 @@ static int perf_pmu__parse_snapshot(struct perf_pmu_alias *alias, } static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name, - char *desc, char *val, char *long_desc, - char *topic) + char *desc, char *val, + char *long_desc, char *topic, + char *unit, char *perpkg, + char *metric_expr, + char *metric_name) { struct perf_pmu_alias *alias; int ret; + int num; alias = malloc(sizeof(*alias)); if (!alias) @@ -257,10 +270,19 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name, perf_pmu__parse_snapshot(alias, dir, name); } + alias->metric_expr = metric_expr ? strdup(metric_expr) : NULL; + alias->metric_name = metric_name ? strdup(metric_name): NULL; alias->desc = desc ? strdup(desc) : NULL; alias->long_desc = long_desc ? strdup(long_desc) : desc ? strdup(desc) : NULL; alias->topic = topic ? strdup(topic) : NULL; + if (unit) { + if (convert_scale(unit, &unit, &alias->scale) < 0) + return -1; + snprintf(alias->unit, sizeof(alias->unit), "%s", unit); + } + alias->per_pkg = perpkg && sscanf(perpkg, "%d", &num) == 1 && num == 1; + alias->str = strdup(val); list_add_tail(&alias->list, list); @@ -278,7 +300,8 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI buf[ret] = 0; - return __perf_pmu__new_alias(list, dir, name, NULL, buf, NULL, NULL); + return __perf_pmu__new_alias(list, dir, name, NULL, buf, NULL, NULL, NULL, + NULL, NULL, NULL); } static inline bool pmu_alias_info_file(char *name) @@ -498,7 +521,7 @@ char * __weak get_cpuid_str(void) * to the current running CPU. Then, add all PMU events from that table * as aliases. */ -static void pmu_add_cpu_aliases(struct list_head *head) +static void pmu_add_cpu_aliases(struct list_head *head, const char *name) { int i; struct pmu_events_map *map; @@ -534,14 +557,23 @@ static void pmu_add_cpu_aliases(struct list_head *head) */ i = 0; while (1) { + const char *pname; + pe = &map->table[i++]; if (!pe->name) break; + pname = pe->pmu ? pe->pmu : "cpu"; + if (strncmp(pname, name, strlen(pname))) + continue; + /* need type casts to override 'const' */ __perf_pmu__new_alias(head, NULL, (char *)pe->name, (char *)pe->desc, (char *)pe->event, - (char *)pe->long_desc, (char *)pe->topic); + (char *)pe->long_desc, (char *)pe->topic, + (char *)pe->unit, (char *)pe->perpkg, + (char *)pe->metric_expr, + (char *)pe->metric_name); } out: @@ -569,15 +601,16 @@ static struct perf_pmu *pmu_lookup(const char *name) if (pmu_format(name, &format)) return NULL; - if (pmu_aliases(name, &aliases)) + /* + * Check the type first to avoid unnecessary work. + */ + if (pmu_type(name, &type)) return NULL; - if (!strcmp(name, "cpu")) - pmu_add_cpu_aliases(&aliases); - - if (pmu_type(name, &type)) + if (pmu_aliases(name, &aliases)) return NULL; + pmu_add_cpu_aliases(&aliases, name); pmu = zalloc(sizeof(*pmu)); if (!pmu) return NULL; @@ -721,7 +754,7 @@ static int pmu_resolve_param_term(struct parse_events_term *term, } } - if (verbose) + if (verbose > 0) printf("Required parameter '%s' not specified\n", term->config); return -1; @@ -779,7 +812,7 @@ static int pmu_config_term(struct list_head *formats, format = pmu_find_format(formats, term->config); if (!format) { - if (verbose) + if (verbose > 0) printf("Invalid event/parameter '%s'\n", term->config); if (err) { char *pmu_term = pmu_formats_string(formats); @@ -810,11 +843,20 @@ static int pmu_config_term(struct list_head *formats, * Either directly use a numeric term, or try to translate string terms * using event parameters. */ - if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM) + if (term->type_val == PARSE_EVENTS__TERM_TYPE_NUM) { + if (term->no_value && + bitmap_weight(format->bits, PERF_PMU_FORMAT_BITS) > 1) { + if (err) { + err->idx = term->err_val; + err->str = strdup("no value assigned for term"); + } + return -EINVAL; + } + val = term->val.num; - else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) { + } else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) { if (strcmp(term->val.str, "?")) { - if (verbose) { + if (verbose > 0) { pr_info("Invalid sysfs entry %s=%s\n", term->config, term->val.str); } @@ -921,12 +963,12 @@ static int check_info_data(struct perf_pmu_alias *alias, * define unit, scale and snapshot, fail * if there's more than one. */ - if ((info->unit && alias->unit) || + if ((info->unit && alias->unit[0]) || (info->scale && alias->scale) || (info->snapshot && alias->snapshot)) return -EINVAL; - if (alias->unit) + if (alias->unit[0]) info->unit = alias->unit; if (alias->scale) @@ -958,6 +1000,8 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms, info->unit = NULL; info->scale = 0.0; info->snapshot = false; + info->metric_expr = NULL; + info->metric_name = NULL; list_for_each_entry_safe(term, h, head_terms, list) { alias = pmu_find_alias(pmu, term); @@ -973,6 +1017,8 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms, if (alias->per_pkg) info->per_pkg = true; + info->metric_expr = alias->metric_expr; + info->metric_name = alias->metric_name; list_del(&term->list); free(term); @@ -1065,6 +1111,10 @@ struct sevent { char *name; char *desc; char *topic; + char *str; + char *pmu; + char *metric_expr; + char *metric_name; }; static int cmp_sevent(const void *a, const void *b) @@ -1101,13 +1151,12 @@ static void wordwrap(char *s, int start, int max, int corr) break; s += wlen; column += n; - while (isspace(*s)) - s++; + s = ltrim(s); } } void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag, - bool long_desc) + bool long_desc, bool details_flag) { struct perf_pmu *pmu; struct perf_pmu_alias *alias; @@ -1161,6 +1210,10 @@ void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag, aliases[j].desc = long_desc ? alias->long_desc : alias->desc; aliases[j].topic = alias->topic; + aliases[j].str = alias->str; + aliases[j].pmu = pmu->name; + aliases[j].metric_expr = alias->metric_expr; + aliases[j].metric_name = alias->metric_name; j++; } if (pmu->selectable && @@ -1175,6 +1228,9 @@ void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag, len = j; qsort(aliases, len, sizeof(struct sevent), cmp_sevent); for (j = 0; j < len; j++) { + /* Skip duplicates */ + if (j > 0 && !strcmp(aliases[j].name, aliases[j - 1].name)) + continue; if (name_only) { printf("%s ", aliases[j].name); continue; @@ -1192,6 +1248,14 @@ void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag, printf("%*s", 8, "["); wordwrap(aliases[j].desc, 8, columns, 0); printf("]\n"); + if (details_flag) { + printf("%*s%s/%s/ ", 8, "", aliases[j].pmu, aliases[j].str); + if (aliases[j].metric_name) + printf(" MetricName: %s", aliases[j].metric_name); + if (aliases[j].metric_expr) + printf(" MetricExpr: %s", aliases[j].metric_expr); + putchar('\n'); + } } else printf(" %-50s [Kernel PMU event]\n", aliases[j].name); printed++; diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index 25712034c815..ea7f450dc609 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -31,6 +31,8 @@ struct perf_pmu { struct perf_pmu_info { const char *unit; + const char *metric_expr; + const char *metric_name; double scale; bool per_pkg; bool snapshot; @@ -43,12 +45,15 @@ struct perf_pmu_alias { char *desc; char *long_desc; char *topic; + char *str; struct list_head terms; /* HEAD struct parse_events_term -> list */ struct list_head list; /* ELEM */ char unit[UNIT_MAX_LEN+1]; double scale; bool per_pkg; bool snapshot; + char *metric_expr; + char *metric_name; }; struct perf_pmu *perf_pmu__find(const char *name); @@ -75,7 +80,7 @@ int perf_pmu__format_parse(char *dir, struct list_head *head); struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu); void print_pmu_events(const char *event_glob, bool name_only, bool quiet, - bool long_desc); + bool long_desc, bool details_flag); bool pmu_have_event(const char *pname, const char *name); int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt, diff --git a/tools/perf/util/print_binary.c b/tools/perf/util/print_binary.c new file mode 100644 index 000000000000..e908177b9976 --- /dev/null +++ b/tools/perf/util/print_binary.c @@ -0,0 +1,55 @@ +#include "print_binary.h" +#include <linux/log2.h> +#include "sane_ctype.h" + +void print_binary(unsigned char *data, size_t len, + size_t bytes_per_line, print_binary_t printer, + void *extra) +{ + size_t i, j, mask; + + if (!printer) + return; + + bytes_per_line = roundup_pow_of_two(bytes_per_line); + mask = bytes_per_line - 1; + + printer(BINARY_PRINT_DATA_BEGIN, 0, extra); + for (i = 0; i < len; i++) { + if ((i & mask) == 0) { + printer(BINARY_PRINT_LINE_BEGIN, -1, extra); + printer(BINARY_PRINT_ADDR, i, extra); + } + + printer(BINARY_PRINT_NUM_DATA, data[i], extra); + + if (((i & mask) == mask) || i == len - 1) { + for (j = 0; j < mask-(i & mask); j++) + printer(BINARY_PRINT_NUM_PAD, -1, extra); + + printer(BINARY_PRINT_SEP, i, extra); + for (j = i & ~mask; j <= i; j++) + printer(BINARY_PRINT_CHAR_DATA, data[j], extra); + for (j = 0; j < mask-(i & mask); j++) + printer(BINARY_PRINT_CHAR_PAD, i, extra); + printer(BINARY_PRINT_LINE_END, -1, extra); + } + } + printer(BINARY_PRINT_DATA_END, -1, extra); +} + +int is_printable_array(char *p, unsigned int len) +{ + unsigned int i; + + if (!p || !len || p[len - 1] != 0) + return 0; + + len--; + + for (i = 0; i < len; i++) { + if (!isprint(p[i]) && !isspace(p[i])) + return 0; + } + return 1; +} diff --git a/tools/perf/util/print_binary.h b/tools/perf/util/print_binary.h new file mode 100644 index 000000000000..da0427263d2d --- /dev/null +++ b/tools/perf/util/print_binary.h @@ -0,0 +1,28 @@ +#ifndef PERF_PRINT_BINARY_H +#define PERF_PRINT_BINARY_H + +#include <stddef.h> + +enum binary_printer_ops { + BINARY_PRINT_DATA_BEGIN, + BINARY_PRINT_LINE_BEGIN, + BINARY_PRINT_ADDR, + BINARY_PRINT_NUM_DATA, + BINARY_PRINT_NUM_PAD, + BINARY_PRINT_SEP, + BINARY_PRINT_CHAR_DATA, + BINARY_PRINT_CHAR_PAD, + BINARY_PRINT_LINE_END, + BINARY_PRINT_DATA_END, +}; + +typedef void (*print_binary_t)(enum binary_printer_ops op, + unsigned int val, void *extra); + +void print_binary(unsigned char *data, size_t len, + size_t bytes_per_line, print_binary_t printer, + void *extra); + +int is_printable_array(char *p, unsigned int len); + +#endif /* PERF_PRINT_BINARY_H */ diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 6a6f44dd594b..84e7e698411e 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -19,6 +19,7 @@ * */ +#include <inttypes.h> #include <sys/utsname.h> #include <sys/types.h> #include <sys/stat.h> @@ -35,6 +36,7 @@ #include "util.h" #include "event.h" #include "strlist.h" +#include "strfilter.h" #include "debug.h" #include "cache.h" #include "color.h" @@ -46,8 +48,10 @@ #include "probe-finder.h" #include "probe-file.h" #include "session.h" +#include "string2.h" + +#include "sane_ctype.h" -#define MAX_CMDLEN 256 #define PERFPROBE_GROUP "probe" bool probe_event_dry_run; /* Dry run flag */ @@ -594,7 +598,7 @@ static int find_perf_probe_point_from_dwarf(struct probe_trace_point *tp, pr_debug("try to find information at %" PRIx64 " in %s\n", addr, tp->module ? : "kernel"); - dinfo = debuginfo_cache__open(tp->module, verbose == 0); + dinfo = debuginfo_cache__open(tp->module, verbose <= 0); if (dinfo) ret = debuginfo__find_probe_point(dinfo, (unsigned long)addr, pp); @@ -757,7 +761,9 @@ post_process_kernel_probe_trace_events(struct probe_trace_event *tevs, } for (i = 0; i < ntevs; i++) { - if (!tevs[i].point.address || tevs[i].point.retprobe) + if (!tevs[i].point.address) + continue; + if (tevs[i].point.retprobe && !kretprobe_offset_is_supported()) continue; /* If we found a wrong one, mark it by NULL symbol */ if (kprobe_warn_out_range(tevs[i].point.symbol, @@ -1339,14 +1345,7 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev) if (!arg) return -EINVAL; - /* - * If the probe point starts with '%', - * or starts with "sdt_" and has a ':' but no '=', - * then it should be a SDT/cached probe point. - */ - if (arg[0] == '%' || - (!strncmp(arg, "sdt_", 4) && - !!strchr(arg, ':') && !strchr(arg, '='))) { + if (is_sdt_event(arg)) { pev->sdt = true; if (arg[0] == '%') arg++; @@ -1528,11 +1527,6 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev) return -EINVAL; } - if (pp->retprobe && !pp->function) { - semantic_error("Return probe requires an entry function.\n"); - return -EINVAL; - } - if ((pp->offset || pp->line || pp->lazy_line) && pp->retprobe) { semantic_error("Offset/Line/Lazy pattern can't be used with " "return probe.\n"); @@ -2061,7 +2055,7 @@ static int find_perf_probe_point_from_map(struct probe_trace_point *tp, bool is_kprobe) { struct symbol *sym = NULL; - struct map *map; + struct map *map = NULL; u64 addr = tp->address; int ret = -ENOENT; @@ -2841,7 +2835,8 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev, } /* Note that the symbols in the kmodule are not relocated */ - if (!pev->uprobes && !pp->retprobe && !pev->target) { + if (!pev->uprobes && !pev->target && + (!pp->retprobe || kretprobe_offset_is_supported())) { reloc_sym = kernel_get_ref_reloc_sym(); if (!reloc_sym) { pr_warning("Relocated base symbol is not found!\n"); @@ -3023,20 +3018,17 @@ static int try_to_find_absolute_address(struct perf_probe_event *pev, tev->nargs = pev->nargs; tev->args = zalloc(sizeof(struct probe_trace_arg) * tev->nargs); - if (!tev->args) { - err = -ENOMEM; + if (!tev->args) goto errout; - } + for (i = 0; i < tev->nargs; i++) copy_to_probe_trace_arg(&tev->args[i], &pev->args[i]); return 1; errout: - if (*tevs) { - clear_probe_trace_events(*tevs, 1); - *tevs = NULL; - } + clear_probe_trace_events(*tevs, 1); + *tevs = NULL; return err; } @@ -3060,7 +3052,7 @@ concat_probe_trace_events(struct probe_trace_event **tevs, int *ntevs, struct probe_trace_event *new_tevs; int ret = 0; - if (ntevs == 0) { + if (*ntevs == 0) { *tevs = *tevs2; *ntevs = ntevs2; *tevs2 = NULL; diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h index 5d4e94061402..373842656fb6 100644 --- a/tools/perf/util/probe-event.h +++ b/tools/perf/util/probe-event.h @@ -3,8 +3,6 @@ #include <stdbool.h> #include "intlist.h" -#include "strlist.h" -#include "strfilter.h" /* Probe related configurations */ struct probe_conf { @@ -107,6 +105,8 @@ struct line_range { struct intlist *line_list; /* Visible lines */ }; +struct strlist; + /* List of variables */ struct variable_list { struct probe_trace_point point; /* Actual probepoint */ @@ -153,6 +153,9 @@ int convert_perf_probe_events(struct perf_probe_event *pevs, int npevs); int apply_perf_probe_events(struct perf_probe_event *pevs, int npevs); int show_probe_trace_events(struct perf_probe_event *pevs, int npevs); void cleanup_perf_probe_events(struct perf_probe_event *pevs, int npevs); + +struct strfilter; + int del_perf_probe_events(struct strfilter *filter); int show_perf_probe_event(const char *group, const char *event, diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c index 436b64731f65..d679389e627c 100644 --- a/tools/perf/util/probe-file.c +++ b/tools/perf/util/probe-file.c @@ -14,10 +14,15 @@ * GNU General Public License for more details. * */ +#include <errno.h> +#include <sys/stat.h> +#include <sys/types.h> #include <sys/uio.h> +#include <unistd.h> #include "util.h" #include "event.h" #include "strlist.h" +#include "strfilter.h" #include "debug.h" #include "cache.h" #include "color.h" @@ -27,8 +32,11 @@ #include "probe-event.h" #include "probe-file.h" #include "session.h" +#include "perf_regs.h" +#include "string2.h" -#define MAX_CMDLEN 256 +/* 4096 - 2 ('\n' + '\0') */ +#define MAX_CMDLEN 4094 static void print_open_warning(int err, bool uprobe) { @@ -70,7 +78,7 @@ static void print_both_open_warning(int kerr, int uerr) } } -static int open_probe_events(const char *trace_file, bool readwrite) +int open_trace_file(const char *trace_file, bool readwrite) { char buf[PATH_MAX]; int ret; @@ -92,12 +100,12 @@ static int open_probe_events(const char *trace_file, bool readwrite) static int open_kprobe_events(bool readwrite) { - return open_probe_events("kprobe_events", readwrite); + return open_trace_file("kprobe_events", readwrite); } static int open_uprobe_events(bool readwrite) { - return open_probe_events("uprobe_events", readwrite); + return open_trace_file("uprobe_events", readwrite); } int probe_file__open(int flag) @@ -687,6 +695,110 @@ static unsigned long long sdt_note__get_addr(struct sdt_note *note) : (unsigned long long)note->addr.a64[0]; } +static const char * const type_to_suffix[] = { + ":s64", "", "", "", ":s32", "", ":s16", ":s8", + "", ":u8", ":u16", "", ":u32", "", "", "", ":u64" +}; + +/* + * Isolate the string number and convert it into a decimal value; + * this will be an index to get suffix of the uprobe name (defining + * the type) + */ +static int sdt_arg_parse_size(char *n_ptr, const char **suffix) +{ + long type_idx; + + type_idx = strtol(n_ptr, NULL, 10); + if (type_idx < -8 || type_idx > 8) { + pr_debug4("Failed to get a valid sdt type\n"); + return -1; + } + + *suffix = type_to_suffix[type_idx + 8]; + return 0; +} + +static int synthesize_sdt_probe_arg(struct strbuf *buf, int i, const char *arg) +{ + char *op, *desc = strdup(arg), *new_op = NULL; + const char *suffix = ""; + int ret = -1; + + if (desc == NULL) { + pr_debug4("Allocation error\n"); + return ret; + } + + /* + * Argument is in N@OP format. N is size of the argument and OP is + * the actual assembly operand. N can be omitted; in that case + * argument is just OP(without @). + */ + op = strchr(desc, '@'); + if (op) { + op[0] = '\0'; + op++; + + if (sdt_arg_parse_size(desc, &suffix)) + goto error; + } else { + op = desc; + } + + ret = arch_sdt_arg_parse_op(op, &new_op); + + if (ret < 0) + goto error; + + if (ret == SDT_ARG_VALID) { + ret = strbuf_addf(buf, " arg%d=%s%s", i + 1, new_op, suffix); + if (ret < 0) + goto error; + } + + ret = 0; +error: + free(desc); + free(new_op); + return ret; +} + +static char *synthesize_sdt_probe_command(struct sdt_note *note, + const char *pathname, + const char *sdtgrp) +{ + struct strbuf buf; + char *ret = NULL, **args; + int i, args_count; + + if (strbuf_init(&buf, 32) < 0) + return NULL; + + if (strbuf_addf(&buf, "p:%s/%s %s:0x%llx", + sdtgrp, note->name, pathname, + sdt_note__get_addr(note)) < 0) + goto error; + + if (!note->args) + goto out; + + if (note->args) { + args = argv_split(note->args, &args_count); + + for (i = 0; i < args_count; ++i) { + if (synthesize_sdt_probe_arg(&buf, i, args[i]) < 0) + goto error; + } + } + +out: + ret = strbuf_detach(&buf, NULL); +error: + strbuf_release(&buf); + return ret; +} + int probe_cache__scan_sdt(struct probe_cache *pcache, const char *pathname) { struct probe_cache_entry *entry = NULL; @@ -723,11 +835,12 @@ int probe_cache__scan_sdt(struct probe_cache *pcache, const char *pathname) entry->pev.group = strdup(sdtgrp); list_add_tail(&entry->node, &pcache->entries); } - ret = asprintf(&buf, "p:%s/%s %s:0x%llx", - sdtgrp, note->name, pathname, - sdt_note__get_addr(note)); - if (ret < 0) + buf = synthesize_sdt_probe_command(note, pathname, sdtgrp); + if (!buf) { + ret = -ENOMEM; break; + } + strlist__add(entry->tevlist, buf); free(buf); entry = NULL; @@ -877,59 +990,72 @@ int probe_cache__show_all_caches(struct strfilter *filter) return 0; } +enum ftrace_readme { + FTRACE_README_PROBE_TYPE_X = 0, + FTRACE_README_KRETPROBE_OFFSET, + FTRACE_README_END, +}; + static struct { const char *pattern; - bool avail; - bool checked; -} probe_type_table[] = { -#define DEFINE_TYPE(idx, pat, def_avail) \ - [idx] = {.pattern = pat, .avail = (def_avail)} - DEFINE_TYPE(PROBE_TYPE_U, "* u8/16/32/64,*", true), - DEFINE_TYPE(PROBE_TYPE_S, "* s8/16/32/64,*", true), - DEFINE_TYPE(PROBE_TYPE_X, "* x8/16/32/64,*", false), - DEFINE_TYPE(PROBE_TYPE_STRING, "* string,*", true), - DEFINE_TYPE(PROBE_TYPE_BITFIELD, - "* b<bit-width>@<bit-offset>/<container-size>", true), + bool avail; +} ftrace_readme_table[] = { +#define DEFINE_TYPE(idx, pat) \ + [idx] = {.pattern = pat, .avail = false} + DEFINE_TYPE(FTRACE_README_PROBE_TYPE_X, "*type: * x8/16/32/64,*"), + DEFINE_TYPE(FTRACE_README_KRETPROBE_OFFSET, "*place (kretprobe): *"), }; -bool probe_type_is_available(enum probe_type type) +static bool scan_ftrace_readme(enum ftrace_readme type) { + int fd; FILE *fp; char *buf = NULL; size_t len = 0; - bool target_line = false; - bool ret = probe_type_table[type].avail; + bool ret = false; + static bool scanned = false; - if (type >= PROBE_TYPE_END) - return false; - /* We don't have to check the type which supported by default */ - if (ret || probe_type_table[type].checked) - return ret; + if (scanned) + goto result; - if (asprintf(&buf, "%s/README", tracing_path) < 0) + fd = open_trace_file("README", false); + if (fd < 0) return ret; - fp = fopen(buf, "r"); - if (!fp) - goto end; - - zfree(&buf); - while (getline(&buf, &len, fp) > 0 && !ret) { - if (!target_line) { - target_line = !!strstr(buf, " type: "); - if (!target_line) - continue; - } else if (strstr(buf, "\t ") != buf) - break; - ret = strglobmatch(buf, probe_type_table[type].pattern); + fp = fdopen(fd, "r"); + if (!fp) { + close(fd); + return ret; } - /* Cache the result */ - probe_type_table[type].checked = true; - probe_type_table[type].avail = ret; + + while (getline(&buf, &len, fp) > 0) + for (enum ftrace_readme i = 0; i < FTRACE_README_END; i++) + if (!ftrace_readme_table[i].avail) + ftrace_readme_table[i].avail = + strglobmatch(buf, ftrace_readme_table[i].pattern); + scanned = true; fclose(fp); -end: free(buf); - return ret; +result: + if (type >= FTRACE_README_END) + return false; + + return ftrace_readme_table[type].avail; +} + +bool probe_type_is_available(enum probe_type type) +{ + if (type >= PROBE_TYPE_END) + return false; + else if (type == PROBE_TYPE_X) + return scan_ftrace_readme(FTRACE_README_PROBE_TYPE_X); + + return true; +} + +bool kretprobe_offset_is_supported(void) +{ + return scan_ftrace_readme(FTRACE_README_KRETPROBE_OFFSET); } diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h index eba44c3e9dca..5ecc9d3925db 100644 --- a/tools/perf/util/probe-file.h +++ b/tools/perf/util/probe-file.h @@ -1,10 +1,11 @@ #ifndef __PROBE_FILE_H #define __PROBE_FILE_H -#include "strlist.h" -#include "strfilter.h" #include "probe-event.h" +struct strlist; +struct strfilter; + /* Cache of probe definitions */ struct probe_cache_entry { struct list_head node; @@ -35,11 +36,13 @@ enum probe_type { /* probe-file.c depends on libelf */ #ifdef HAVE_LIBELF_SUPPORT +int open_trace_file(const char *trace_file, bool readwrite); int probe_file__open(int flag); int probe_file__open_both(int *kfd, int *ufd, int flag); struct strlist *probe_file__get_namelist(int fd); struct strlist *probe_file__get_rawlist(int fd); int probe_file__add_event(int fd, struct probe_trace_event *tev); + int probe_file__del_events(int fd, struct strfilter *filter); int probe_file__get_events(int fd, struct strfilter *filter, struct strlist *plist); @@ -64,6 +67,7 @@ struct probe_cache_entry *probe_cache__find_by_name(struct probe_cache *pcache, const char *group, const char *event); int probe_cache__show_all_caches(struct strfilter *filter); bool probe_type_is_available(enum probe_type type); +bool kretprobe_offset_is_supported(void); #else /* ! HAVE_LIBELF_SUPPORT */ static inline struct probe_cache *probe_cache__new(const char *tgt __maybe_unused) { diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 0d9d6e0803b8..a5731de0e5eb 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -19,6 +19,7 @@ * */ +#include <inttypes.h> #include <sys/utsname.h> #include <sys/types.h> #include <sys/stat.h> @@ -37,9 +38,11 @@ #include "debug.h" #include "intlist.h" #include "util.h" +#include "strlist.h" #include "symbol.h" #include "probe-finder.h" #include "probe-file.h" +#include "string2.h" /* Kprobe tracer basic type is up to u64 */ #define MAX_BASIC_TYPE_BITS 64 @@ -464,7 +467,7 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname, /* Verify it is a data structure */ tag = dwarf_tag(&type); if (tag != DW_TAG_structure_type && tag != DW_TAG_union_type) { - pr_warning("%s is not a data structure nor an union.\n", + pr_warning("%s is not a data structure nor a union.\n", varname); return -EINVAL; } @@ -479,7 +482,7 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname, } else { /* Verify it is a data structure */ if (tag != DW_TAG_structure_type && tag != DW_TAG_union_type) { - pr_warning("%s is not a data structure nor an union.\n", + pr_warning("%s is not a data structure nor a union.\n", varname); return -EINVAL; } diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h index 2956c5198652..27f061551012 100644 --- a/tools/perf/util/probe-finder.h +++ b/tools/perf/util/probe-finder.h @@ -2,9 +2,9 @@ #define _PROBE_FINDER_H #include <stdbool.h> -#include "util.h" #include "intlist.h" #include "probe-event.h" +#include "sane_ctype.h" #define MAX_PROBE_BUFFER 1024 #define MAX_PROBES 128 diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index 0546a4304347..9f3b0d9754a8 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -21,8 +21,10 @@ util/cgroup.c util/parse-branch-options.c util/rblist.c util/counts.c +util/print_binary.c util/strlist.c util/trace-event.c ../lib/rbtree.c util/string.c util/symbol_fprintf.c +util/units.c diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index a5fbc012e3df..c129e99114ae 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -4,12 +4,26 @@ #include <poll.h> #include <linux/err.h> #include "evlist.h" +#include "callchain.h" #include "evsel.h" #include "event.h" #include "cpumap.h" +#include "print_binary.h" #include "thread_map.h" /* + * Provide these two so that we don't have to link against callchain.c and + * start dragging hist.c, etc. + */ +struct callchain_param callchain_param; + +int parse_callchain_record(const char *arg __maybe_unused, + struct callchain_param *param __maybe_unused) +{ + return 0; +} + +/* * Support debug printing even though util/debug.c is not linked. That means * implementing 'verbose' and 'eprintf'. */ diff --git a/tools/perf/util/quote.c b/tools/perf/util/quote.c index 293534c1a474..1ba8920151d8 100644 --- a/tools/perf/util/quote.c +++ b/tools/perf/util/quote.c @@ -1,3 +1,4 @@ +#include <errno.h> #include <stdlib.h> #include "strbuf.h" #include "quote.h" diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c index 98bf584853ea..d91bdf5a1aa4 100644 --- a/tools/perf/util/record.c +++ b/tools/perf/util/record.c @@ -2,6 +2,7 @@ #include "evsel.h" #include "cpumap.h" #include "parse-events.h" +#include <errno.h> #include <api/fs/fs.h> #include "util.h" #include "cloexec.h" diff --git a/tools/perf/util/sane_ctype.h b/tools/perf/util/sane_ctype.h new file mode 100644 index 000000000000..4308c22c22ad --- /dev/null +++ b/tools/perf/util/sane_ctype.h @@ -0,0 +1,51 @@ +#ifndef _PERF_SANE_CTYPE_H +#define _PERF_SANE_CTYPE_H + +extern const char *graph_line; +extern const char *graph_dotted_line; +extern const char *spaces; +extern const char *dots; + +/* Sane ctype - no locale, and works with signed chars */ +#undef isascii +#undef isspace +#undef isdigit +#undef isxdigit +#undef isalpha +#undef isprint +#undef isalnum +#undef islower +#undef isupper +#undef tolower +#undef toupper + +extern unsigned char sane_ctype[256]; +#define GIT_SPACE 0x01 +#define GIT_DIGIT 0x02 +#define GIT_ALPHA 0x04 +#define GIT_GLOB_SPECIAL 0x08 +#define GIT_REGEX_SPECIAL 0x10 +#define GIT_PRINT_EXTRA 0x20 +#define GIT_PRINT 0x3E +#define sane_istest(x,mask) ((sane_ctype[(unsigned char)(x)] & (mask)) != 0) +#define isascii(x) (((x) & ~0x7f) == 0) +#define isspace(x) sane_istest(x,GIT_SPACE) +#define isdigit(x) sane_istest(x,GIT_DIGIT) +#define isxdigit(x) \ + (sane_istest(toupper(x), GIT_ALPHA | GIT_DIGIT) && toupper(x) < 'G') +#define isalpha(x) sane_istest(x,GIT_ALPHA) +#define isalnum(x) sane_istest(x,GIT_ALPHA | GIT_DIGIT) +#define isprint(x) sane_istest(x,GIT_PRINT) +#define islower(x) (sane_istest(x,GIT_ALPHA) && (x & 0x20)) +#define isupper(x) (sane_istest(x,GIT_ALPHA) && !(x & 0x20)) +#define tolower(x) sane_case((unsigned char)(x), 0x20) +#define toupper(x) sane_case((unsigned char)(x), 0) + +static inline int sane_case(int x, int high) +{ + if (sane_istest(x, GIT_ALPHA)) + x = (x & ~0x20) | high; + return x; +} + +#endif /* _PERF_SANE_CTYPE_H */ diff --git a/tools/perf/util/scripting-engines/Build b/tools/perf/util/scripting-engines/Build index 6516e220c247..82d28c67e0f3 100644 --- a/tools/perf/util/scripting-engines/Build +++ b/tools/perf/util/scripting-engines/Build @@ -1,6 +1,6 @@ libperf-$(CONFIG_LIBPERL) += trace-event-perl.o libperf-$(CONFIG_LIBPYTHON) += trace-event-python.o -CFLAGS_trace-event-perl.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-undef -Wno-switch-default +CFLAGS_trace-event-perl.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-nested-externs -Wno-undef -Wno-switch-default CFLAGS_trace-event-python.o += $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index e55a132f69b7..7b79c413486b 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -19,6 +19,7 @@ * */ +#include <inttypes.h> #include <stdio.h> #include <stdlib.h> #include <string.h> @@ -27,7 +28,9 @@ #include <linux/bitmap.h> #include <linux/time64.h> -#include "../util.h" +#include <stdbool.h> +/* perl needs the following define, right after including stdbool.h */ +#define HAS_BOOL #include <EXTERN.h> #include <perl.h> @@ -217,6 +220,7 @@ static void define_event_symbols(struct event_format *event, cur_field_name); break; case PRINT_HEX: + case PRINT_HEX_STR: define_event_symbols(event, ev_name, args->hex.field); define_event_symbols(event, ev_name, args->hex.size); break; @@ -309,10 +313,10 @@ static SV *perl_process_callchain(struct perf_sample *sample, if (node->map) { struct map *map = node->map; const char *dsoname = "[unknown]"; - if (map && map->dso && (map->dso->name || map->dso->long_name)) { + if (map && map->dso) { if (symbol_conf.show_kernel_path && map->dso->long_name) dsoname = map->dso->long_name; - else if (map->dso->name) + else dsoname = map->dso->name; } if (!hv_stores(elem, "dso", newSVpv(dsoname,0))) { @@ -350,8 +354,10 @@ static void perl_process_tracepoint(struct perf_sample *sample, if (evsel->attr.type != PERF_TYPE_TRACEPOINT) return; - if (!event) - die("ug! no event found for type %" PRIu64, (u64)evsel->attr.config); + if (!event) { + pr_debug("ug! no event found for type %" PRIu64, (u64)evsel->attr.config); + return; + } pid = raw_field_value(event, "common_pid", data); diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 089438da1f7f..9d92af7d0718 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -21,6 +21,7 @@ #include <Python.h> +#include <inttypes.h> #include <stdio.h> #include <stdlib.h> #include <string.h> @@ -45,6 +46,7 @@ #include "../call-path.h" #include "thread_map.h" #include "cpumap.h" +#include "print_binary.h" #include "stat.h" PyMODINIT_FUNC initperf_trace_context(void); @@ -236,6 +238,7 @@ static void define_event_symbols(struct event_format *event, cur_field_name); break; case PRINT_HEX: + case PRINT_HEX_STR: define_event_symbols(event, ev_name, args->hex.field); define_event_symbols(event, ev_name, args->hex.size); break; @@ -368,10 +371,10 @@ static PyObject *python_process_callchain(struct perf_sample *sample, if (node->map) { struct map *map = node->map; const char *dsoname = "[unknown]"; - if (map && map->dso && (map->dso->name || map->dso->long_name)) { + if (map && map->dso) { if (symbol_conf.show_kernel_path && map->dso->long_name) dsoname = map->dso->long_name; - else if (map->dso->name) + else dsoname = map->dso->name; } pydict_set_item_string_decref(pyelem, "dso", diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index f268201048a0..7dc1096264c5 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1,5 +1,8 @@ +#include <errno.h> +#include <inttypes.h> #include <linux/kernel.h> #include <traceevent/event-parse.h> +#include <api/fs/fs.h> #include <byteswap.h> #include <unistd.h> @@ -8,6 +11,7 @@ #include "evlist.h" #include "evsel.h" +#include "memswap.h" #include "session.h" #include "tool.h" #include "sort.h" @@ -16,6 +20,7 @@ #include "perf_regs.h" #include "asm/bug.h" #include "auxtrace.h" +#include "thread.h" #include "thread-stack.h" #include "stat.h" @@ -139,8 +144,14 @@ struct perf_session *perf_session__new(struct perf_data_file *file, if (perf_session__open(session) < 0) goto out_close; - perf_session__set_id_hdr_size(session); - perf_session__set_comm_exec(session); + /* + * set session attributes that are present in perf.data + * but not in pipe-mode. + */ + if (!file->is_pipe) { + perf_session__set_id_hdr_size(session); + perf_session__set_comm_exec(session); + } } } else { session->machines.host.env = &perf_env; @@ -155,7 +166,11 @@ struct perf_session *perf_session__new(struct perf_data_file *file, pr_warning("Cannot read kernel map\n"); } - if (tool && tool->ordering_requires_timestamps && + /* + * In pipe-mode, evlist is empty until PERF_RECORD_HEADER_ATTR is + * processed, so perf_evlist__sample_id_all is not meaningful here. + */ + if ((!file || !file->is_pipe) && tool && tool->ordering_requires_timestamps && tool->ordered_events && !perf_evlist__sample_id_all(session->evlist)) { dump_printf("WARNING: No sample_id_all support, falling back to unordered processing\n"); tool->ordered_events = false; @@ -932,7 +947,7 @@ static void branch_stack__printf(struct perf_sample *sample) printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 " %hu cycles %s%s%s%s %x\n", i, e->from, e->to, - e->flags.cycles, + (unsigned short)e->flags.cycles, e->flags.mispred ? "M" : " ", e->flags.predicted ? "P" : " ", e->flags.abort ? "A" : " ", @@ -1191,7 +1206,7 @@ static int u64 sample_type = evsel->attr.sample_type; u64 read_format = evsel->attr.read_format; - /* Standard sample delievery. */ + /* Standard sample delivery. */ if (!(sample_type & PERF_SAMPLE_READ)) return tool->sample(tool, event, sample, evsel, machine); @@ -1239,6 +1254,8 @@ static int machines__deliver_event(struct machines *machines, return tool->mmap2(tool, event, sample, machine); case PERF_RECORD_COMM: return tool->comm(tool, event, sample, machine); + case PERF_RECORD_NAMESPACES: + return tool->namespaces(tool, event, sample, machine); case PERF_RECORD_FORK: return tool->fork(tool, event, sample, machine); case PERF_RECORD_EXIT: @@ -1258,9 +1275,12 @@ static int machines__deliver_event(struct machines *machines, case PERF_RECORD_UNTHROTTLE: return tool->unthrottle(tool, event, sample, machine); case PERF_RECORD_AUX: - if (tool->aux == perf_event__process_aux && - (event->aux.flags & PERF_AUX_FLAG_TRUNCATED)) - evlist->stats.total_aux_lost += 1; + if (tool->aux == perf_event__process_aux) { + if (event->aux.flags & PERF_AUX_FLAG_TRUNCATED) + evlist->stats.total_aux_lost += 1; + if (event->aux.flags & PERF_AUX_FLAG_PARTIAL) + evlist->stats.total_aux_partial += 1; + } return tool->aux(tool, event, sample, machine); case PERF_RECORD_ITRACE_START: return tool->itrace_start(tool, event, sample, machine); @@ -1494,6 +1514,11 @@ int perf_session__register_idle_thread(struct perf_session *session) err = -1; } + if (thread == NULL || thread__set_namespaces(thread, 0, NULL)) { + pr_err("problem inserting idle task.\n"); + err = -1; + } + /* machine__findnew_thread() got the thread, so put it */ thread__put(thread); return err; @@ -1548,6 +1573,23 @@ static void perf_session__warn_about_errors(const struct perf_session *session) stats->nr_events[PERF_RECORD_AUX]); } + if (session->tool->aux == perf_event__process_aux && + stats->total_aux_partial != 0) { + bool vmm_exclusive = false; + + (void)sysfs__read_bool("module/kvm_intel/parameters/vmm_exclusive", + &vmm_exclusive); + + ui__warning("AUX data had gaps in it %" PRIu64 " times out of %u!\n\n" + "Are you running a KVM guest in the background?%s\n\n", + stats->total_aux_partial, + stats->nr_events[PERF_RECORD_AUX], + vmm_exclusive ? + "\nReloading kvm_intel module with vmm_exclusive=0\n" + "will reduce the gaps to only guest's timeslices." : + ""); + } + if (stats->nr_unknown_events != 0) { ui__warning("Found %u unknown events!\n\n" "Is this an older tool processing a perf.data " @@ -1628,6 +1670,7 @@ static int __perf_session__process_pipe_events(struct perf_session *session) buf = malloc(cur_size); if (!buf) return -errno; + ordered_events__set_copy_on_queue(oe, true); more: event = buf; err = readn(fd, event, sizeof(struct perf_event_header)); @@ -1901,7 +1944,7 @@ int maps__set_kallsyms_ref_reloc_sym(struct map **maps, const char *symbol_name, u64 addr) { char *bracket; - enum map_type i; + int i; struct ref_reloc_sym *ref; ref = zalloc(sizeof(struct ref_reloc_sym)); diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index 4bd758553450..47b5e7dbcb18 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -5,14 +5,14 @@ #include "event.h" #include "header.h" #include "machine.h" -#include "symbol.h" -#include "thread.h" #include "data.h" #include "ordered-events.h" +#include <linux/kernel.h> #include <linux/rbtree.h> #include <linux/perf_event.h> struct ip_callchain; +struct symbol; struct thread; struct auxtrace; diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py index c8680984d2d6..af415febbc46 100644 --- a/tools/perf/util/setup.py +++ b/tools/perf/util/setup.py @@ -1,8 +1,15 @@ #!/usr/bin/python2 -from distutils.core import setup, Extension from os import getenv +cc = getenv("CC") +if cc == "clang": + from _sysconfigdata import build_time_vars + from re import sub + build_time_vars["CFLAGS"] = sub("-specs=[^ ]+", "", build_time_vars["CFLAGS"]) + +from distutils.core import setup, Extension + from distutils.command.build_ext import build_ext as _build_ext from distutils.command.install_lib import install_lib as _install_lib diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index df622f4e301e..5762ae4e9e91 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -1,12 +1,18 @@ +#include <errno.h> +#include <inttypes.h> +#include <regex.h> #include <sys/mman.h> #include "sort.h" #include "hist.h" #include "comm.h" #include "symbol.h" +#include "thread.h" #include "evsel.h" #include "evlist.h" +#include "strlist.h" #include <traceevent/event-parse.h> #include "mem-events.h" +#include <linux/kernel.h> regex_t parent_regex; const char default_parent_pattern[] = "^sys_|^do_page_fault"; @@ -151,7 +157,7 @@ static int64_t _sort__dso_cmp(struct map *map_l, struct map *map_r) if (!dso_l || !dso_r) return cmp_null(dso_r, dso_l); - if (verbose) { + if (verbose > 0) { dso_name_l = dso_l->long_name; dso_name_r = dso_r->long_name; } else { @@ -172,8 +178,8 @@ static int _hist_entry__dso_snprintf(struct map *map, char *bf, size_t size, unsigned int width) { if (map && map->dso) { - const char *dso_name = !verbose ? map->dso->short_name : - map->dso->long_name; + const char *dso_name = verbose > 0 ? map->dso->long_name : + map->dso->short_name; return repsep_snprintf(bf, size, "%-*.*s", width, width, dso_name); } @@ -261,7 +267,7 @@ static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym, { size_t ret = 0; - if (verbose) { + if (verbose > 0) { char o = map ? dso__symtab_origin(map->dso) : '!'; ret += repsep_snprintf(bf, size, "%-#*llx %c ", BITS_PER_LONG / 4 + 2, ip, o); @@ -323,7 +329,7 @@ char *hist_entry__get_srcline(struct hist_entry *he) return SRCLINE_UNKNOWN; return get_srcline(map->dso, map__rip_2objdump(map, he->ip), - he->ms.sym, true); + he->ms.sym, true, true); } static int64_t @@ -366,7 +372,8 @@ sort__srcline_from_cmp(struct hist_entry *left, struct hist_entry *right) left->branch_info->srcline_from = get_srcline(map->dso, map__rip_2objdump(map, left->branch_info->from.al_addr), - left->branch_info->from.sym, true); + left->branch_info->from.sym, + true, true); } if (!right->branch_info->srcline_from) { struct map *map = right->branch_info->from.map; @@ -376,7 +383,8 @@ sort__srcline_from_cmp(struct hist_entry *left, struct hist_entry *right) right->branch_info->srcline_from = get_srcline(map->dso, map__rip_2objdump(map, right->branch_info->from.al_addr), - right->branch_info->from.sym, true); + right->branch_info->from.sym, + true, true); } return strcmp(right->branch_info->srcline_from, left->branch_info->srcline_from); } @@ -407,7 +415,8 @@ sort__srcline_to_cmp(struct hist_entry *left, struct hist_entry *right) left->branch_info->srcline_to = get_srcline(map->dso, map__rip_2objdump(map, left->branch_info->to.al_addr), - left->branch_info->from.sym, true); + left->branch_info->from.sym, + true, true); } if (!right->branch_info->srcline_to) { struct map *map = right->branch_info->to.map; @@ -417,7 +426,8 @@ sort__srcline_to_cmp(struct hist_entry *left, struct hist_entry *right) right->branch_info->srcline_to = get_srcline(map->dso, map__rip_2objdump(map, right->branch_info->to.al_addr), - right->branch_info->to.sym, true); + right->branch_info->to.sym, + true, true); } return strcmp(right->branch_info->srcline_to, left->branch_info->srcline_to); } @@ -448,7 +458,7 @@ static char *hist_entry__get_srcfile(struct hist_entry *e) return no_srcfile; sf = __get_srcline(map->dso, map__rip_2objdump(map, e->ip), - e->ms.sym, false, true); + e->ms.sym, false, true, true); if (!strcmp(sf, SRCLINE_UNKNOWN)) return no_srcfile; p = strchr(sf, ':'); @@ -536,6 +546,46 @@ struct sort_entry sort_cpu = { .se_width_idx = HISTC_CPU, }; +/* --sort cgroup_id */ + +static int64_t _sort__cgroup_dev_cmp(u64 left_dev, u64 right_dev) +{ + return (int64_t)(right_dev - left_dev); +} + +static int64_t _sort__cgroup_inode_cmp(u64 left_ino, u64 right_ino) +{ + return (int64_t)(right_ino - left_ino); +} + +static int64_t +sort__cgroup_id_cmp(struct hist_entry *left, struct hist_entry *right) +{ + int64_t ret; + + ret = _sort__cgroup_dev_cmp(right->cgroup_id.dev, left->cgroup_id.dev); + if (ret != 0) + return ret; + + return _sort__cgroup_inode_cmp(right->cgroup_id.ino, + left->cgroup_id.ino); +} + +static int hist_entry__cgroup_id_snprintf(struct hist_entry *he, + char *bf, size_t size, + unsigned int width __maybe_unused) +{ + return repsep_snprintf(bf, size, "%lu/0x%lx", he->cgroup_id.dev, + he->cgroup_id.ino); +} + +struct sort_entry sort_cgroup_id = { + .se_header = "cgroup id (dev/inode)", + .se_cmp = sort__cgroup_id_cmp, + .se_snprintf = hist_entry__cgroup_id_snprintf, + .se_width_idx = HISTC_CGROUP_ID, +}; + /* --sort socket */ static int64_t @@ -846,6 +896,9 @@ static int hist_entry__mispredict_snprintf(struct hist_entry *he, char *bf, static int64_t sort__cycles_cmp(struct hist_entry *left, struct hist_entry *right) { + if (!left->branch_info || !right->branch_info) + return cmp_null(left->branch_info, right->branch_info); + return left->branch_info->flags.cycles - right->branch_info->flags.cycles; } @@ -853,6 +906,8 @@ sort__cycles_cmp(struct hist_entry *left, struct hist_entry *right) static int hist_entry__cycles_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width) { + if (!he->branch_info) + return scnprintf(bf, size, "%-.*s", width, "N/A"); if (he->branch_info->flags.cycles == 0) return repsep_snprintf(bf, size, "%-*s", width, "-"); return repsep_snprintf(bf, size, "%-*hd", width, @@ -1396,6 +1451,46 @@ struct sort_entry sort_transaction = { .se_width_idx = HISTC_TRANSACTION, }; +/* --sort symbol_size */ + +static int64_t _sort__sym_size_cmp(struct symbol *sym_l, struct symbol *sym_r) +{ + int64_t size_l = sym_l != NULL ? symbol__size(sym_l) : 0; + int64_t size_r = sym_r != NULL ? symbol__size(sym_r) : 0; + + return size_l < size_r ? -1 : + size_l == size_r ? 0 : 1; +} + +static int64_t +sort__sym_size_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return _sort__sym_size_cmp(right->ms.sym, left->ms.sym); +} + +static int _hist_entry__sym_size_snprintf(struct symbol *sym, char *bf, + size_t bf_size, unsigned int width) +{ + if (sym) + return repsep_snprintf(bf, bf_size, "%*d", width, symbol__size(sym)); + + return repsep_snprintf(bf, bf_size, "%*s", width, "unknown"); +} + +static int hist_entry__sym_size_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + return _hist_entry__sym_size_snprintf(he->ms.sym, bf, size, width); +} + +struct sort_entry sort_sym_size = { + .se_header = "Symbol size", + .se_cmp = sort__sym_size_cmp, + .se_snprintf = hist_entry__sym_size_snprintf, + .se_width_idx = HISTC_SYM_SIZE, +}; + + struct sort_dimension { const char *name; struct sort_entry *entry; @@ -1418,6 +1513,8 @@ static struct sort_dimension common_sort_dimensions[] = { DIM(SORT_GLOBAL_WEIGHT, "weight", sort_global_weight), DIM(SORT_TRANSACTION, "transaction", sort_transaction), DIM(SORT_TRACE, "trace", sort_trace), + DIM(SORT_SYM_SIZE, "symbol_size", sort_sym_size), + DIM(SORT_CGROUP_ID, "cgroup_id", sort_cgroup_id), }; #undef DIM diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 7aff317fc7c4..b7c75597e18f 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -2,7 +2,7 @@ #define __PERF_SORT_H #include "../builtin.h" -#include "util.h" +#include <regex.h> #include "color.h" #include <linux/list.h> @@ -11,7 +11,6 @@ #include "symbol.h" #include "string.h" #include "callchain.h" -#include "strlist.h" #include "values.h" #include "../perf.h" @@ -21,7 +20,9 @@ #include <subcmd/parse-options.h> #include "parse-events.h" #include "hist.h" -#include "thread.h" +#include "srcline.h" + +struct thread; extern regex_t parent_regex; extern const char *sort_order; @@ -54,6 +55,11 @@ struct he_stat { u32 nr_events; }; +struct namespace_id { + u64 dev; + u64 ino; +}; + struct hist_entry_diff { bool computed; union { @@ -91,6 +97,7 @@ struct hist_entry { struct map_symbol ms; struct thread *thread; struct comm *comm; + struct namespace_id cgroup_id; u64 ip; u64 transaction; s32 socket; @@ -108,7 +115,7 @@ struct hist_entry { /* * Since perf diff only supports the stdio output, TUI * fields are only accessed from perf report (or perf - * top). So make it an union to reduce memory usage. + * top). So make it a union to reduce memory usage. */ struct hist_entry_diff diff; struct /* for TUI */ { @@ -122,6 +129,7 @@ struct hist_entry { }; char *srcline; char *srcfile; + struct inline_node *inline_node; struct symbol *parent; struct branch_info *branch_info; struct hists *hists; @@ -211,6 +219,8 @@ enum sort_type { SORT_GLOBAL_WEIGHT, SORT_TRANSACTION, SORT_TRACE, + SORT_SYM_SIZE, + SORT_CGROUP_ID, /* branch stack specific sort keys */ __SORT_BRANCH_STACK, diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c index b4db3f48e3b0..df051a52393c 100644 --- a/tools/perf/util/srcline.c +++ b/tools/perf/util/srcline.c @@ -1,3 +1,4 @@ +#include <inttypes.h> #include <stdio.h> #include <stdlib.h> #include <string.h> @@ -7,11 +8,59 @@ #include "util/dso.h" #include "util/util.h" #include "util/debug.h" +#include "util/callchain.h" +#include "srcline.h" #include "symbol.h" bool srcline_full_filename; +static const char *dso__name(struct dso *dso) +{ + const char *dso_name; + + if (dso->symsrc_filename) + dso_name = dso->symsrc_filename; + else + dso_name = dso->long_name; + + if (dso_name[0] == '[') + return NULL; + + if (!strncmp(dso_name, "/tmp/perf-", 10)) + return NULL; + + return dso_name; +} + +static int inline_list__append(char *filename, char *funcname, int line_nr, + struct inline_node *node, struct dso *dso) +{ + struct inline_list *ilist; + char *demangled; + + ilist = zalloc(sizeof(*ilist)); + if (ilist == NULL) + return -1; + + ilist->filename = filename; + ilist->line_nr = line_nr; + + if (dso != NULL) { + demangled = dso__demangle_sym(dso, 0, funcname); + if (demangled == NULL) { + ilist->funcname = funcname; + } else { + ilist->funcname = demangled; + free(funcname); + } + } + + list_add_tail(&ilist->list, &node->val); + + return 0; +} + #ifdef HAVE_LIBBFD_SUPPORT /* @@ -151,9 +200,17 @@ static void addr2line_cleanup(struct a2l_data *a2l) #define MAX_INLINE_NEST 1024 +static void inline_list__reverse(struct inline_node *node) +{ + struct inline_list *ilist, *n; + + list_for_each_entry_safe_reverse(ilist, n, &node->val, list) + list_move_tail(&ilist->list, &node->val); +} + static int addr2line(const char *dso_name, u64 addr, char **file, unsigned int *line, struct dso *dso, - bool unwind_inlines) + bool unwind_inlines, struct inline_node *node) { int ret = 0; struct a2l_data *a2l = dso->a2l; @@ -178,8 +235,21 @@ static int addr2line(const char *dso_name, u64 addr, while (bfd_find_inliner_info(a2l->abfd, &a2l->filename, &a2l->funcname, &a2l->line) && - cnt++ < MAX_INLINE_NEST) - ; + cnt++ < MAX_INLINE_NEST) { + + if (node != NULL) { + if (inline_list__append(strdup(a2l->filename), + strdup(a2l->funcname), + a2l->line, node, + dso) != 0) + return 0; + } + } + + if ((node != NULL) && + (callchain_param.order != ORDER_CALLEE)) { + inline_list__reverse(node); + } } if (a2l->found && a2l->filename) { @@ -205,18 +275,68 @@ void dso__free_a2l(struct dso *dso) dso->a2l = NULL; } +static struct inline_node *addr2inlines(const char *dso_name, u64 addr, + struct dso *dso) +{ + char *file = NULL; + unsigned int line = 0; + struct inline_node *node; + + node = zalloc(sizeof(*node)); + if (node == NULL) { + perror("not enough memory for the inline node"); + return NULL; + } + + INIT_LIST_HEAD(&node->val); + node->addr = addr; + + if (!addr2line(dso_name, addr, &file, &line, dso, TRUE, node)) + goto out_free_inline_node; + + if (list_empty(&node->val)) + goto out_free_inline_node; + + return node; + +out_free_inline_node: + inline_node__delete(node); + return NULL; +} + #else /* HAVE_LIBBFD_SUPPORT */ +static int filename_split(char *filename, unsigned int *line_nr) +{ + char *sep; + + sep = strchr(filename, '\n'); + if (sep) + *sep = '\0'; + + if (!strcmp(filename, "??:0")) + return 0; + + sep = strchr(filename, ':'); + if (sep) { + *sep++ = '\0'; + *line_nr = strtoul(sep, NULL, 0); + return 1; + } + + return 0; +} + static int addr2line(const char *dso_name, u64 addr, char **file, unsigned int *line_nr, struct dso *dso __maybe_unused, - bool unwind_inlines __maybe_unused) + bool unwind_inlines __maybe_unused, + struct inline_node *node __maybe_unused) { FILE *fp; char cmd[PATH_MAX]; char *filename = NULL; size_t len; - char *sep; int ret = 0; scnprintf(cmd, sizeof(cmd), "addr2line -e %s %016"PRIx64, @@ -233,23 +353,14 @@ static int addr2line(const char *dso_name, u64 addr, goto out; } - sep = strchr(filename, '\n'); - if (sep) - *sep = '\0'; - - if (!strcmp(filename, "??:0")) { - pr_debug("no debugging info in %s\n", dso_name); + ret = filename_split(filename, line_nr); + if (ret != 1) { free(filename); goto out; } - sep = strchr(filename, ':'); - if (sep) { - *sep++ = '\0'; - *file = filename; - *line_nr = strtoul(sep, NULL, 0); - ret = 1; - } + *file = filename; + out: pclose(fp); return ret; @@ -259,6 +370,58 @@ void dso__free_a2l(struct dso *dso __maybe_unused) { } +static struct inline_node *addr2inlines(const char *dso_name, u64 addr, + struct dso *dso __maybe_unused) +{ + FILE *fp; + char cmd[PATH_MAX]; + struct inline_node *node; + char *filename = NULL; + size_t len; + unsigned int line_nr = 0; + + scnprintf(cmd, sizeof(cmd), "addr2line -e %s -i %016"PRIx64, + dso_name, addr); + + fp = popen(cmd, "r"); + if (fp == NULL) { + pr_err("popen failed for %s\n", dso_name); + return NULL; + } + + node = zalloc(sizeof(*node)); + if (node == NULL) { + perror("not enough memory for the inline node"); + goto out; + } + + INIT_LIST_HEAD(&node->val); + node->addr = addr; + + while (getline(&filename, &len, fp) != -1) { + if (filename_split(filename, &line_nr) != 1) { + free(filename); + goto out; + } + + if (inline_list__append(filename, NULL, line_nr, node, + NULL) != 0) + goto out; + + filename = NULL; + } + +out: + pclose(fp); + + if (list_empty(&node->val)) { + inline_node__delete(node); + return NULL; + } + + return node; +} + #endif /* HAVE_LIBBFD_SUPPORT */ /* @@ -268,7 +431,7 @@ void dso__free_a2l(struct dso *dso __maybe_unused) #define A2L_FAIL_LIMIT 123 char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym, - bool show_sym, bool unwind_inlines) + bool show_sym, bool show_addr, bool unwind_inlines) { char *file = NULL; unsigned line = 0; @@ -278,18 +441,11 @@ char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym, if (!dso->has_srcline) goto out; - if (dso->symsrc_filename) - dso_name = dso->symsrc_filename; - else - dso_name = dso->long_name; - - if (dso_name[0] == '[') - goto out; - - if (!strncmp(dso_name, "/tmp/perf-", 10)) + dso_name = dso__name(dso); + if (dso_name == NULL) goto out; - if (!addr2line(dso_name, addr, &file, &line, dso, unwind_inlines)) + if (!addr2line(dso_name, addr, &file, &line, dso, unwind_inlines, NULL)) goto out; if (asprintf(&srcline, "%s:%u", @@ -309,6 +465,11 @@ out: dso->has_srcline = 0; dso__free_a2l(dso); } + + if (!show_addr) + return (show_sym && sym) ? + strndup(sym->name, sym->namelen) : NULL; + if (sym) { if (asprintf(&srcline, "%s+%" PRIu64, show_sym ? sym->name : "", addr - sym->start) < 0) @@ -325,7 +486,32 @@ void free_srcline(char *srcline) } char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym, - bool show_sym) + bool show_sym, bool show_addr) +{ + return __get_srcline(dso, addr, sym, show_sym, show_addr, false); +} + +struct inline_node *dso__parse_addr_inlines(struct dso *dso, u64 addr) { - return __get_srcline(dso, addr, sym, show_sym, false); + const char *dso_name; + + dso_name = dso__name(dso); + if (dso_name == NULL) + return NULL; + + return addr2inlines(dso_name, addr, dso); +} + +void inline_node__delete(struct inline_node *node) +{ + struct inline_list *ilist, *tmp; + + list_for_each_entry_safe(ilist, tmp, &node->val, list) { + list_del_init(&ilist->list); + zfree(&ilist->filename); + zfree(&ilist->funcname); + free(ilist); + } + + free(node); } diff --git a/tools/perf/util/srcline.h b/tools/perf/util/srcline.h new file mode 100644 index 000000000000..7b52ba88676e --- /dev/null +++ b/tools/perf/util/srcline.h @@ -0,0 +1,34 @@ +#ifndef PERF_SRCLINE_H +#define PERF_SRCLINE_H + +#include <linux/list.h> +#include <linux/types.h> + +struct dso; +struct symbol; + +extern bool srcline_full_filename; +char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym, + bool show_sym, bool show_addr); +char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym, + bool show_sym, bool show_addr, bool unwind_inlines); +void free_srcline(char *srcline); + +#define SRCLINE_UNKNOWN ((char *) "??:0") + +struct inline_list { + char *filename; + char *funcname; + unsigned int line_nr; + struct list_head list; +}; + +struct inline_node { + u64 addr; + struct list_head val; +}; + +struct inline_node *dso__parse_addr_inlines(struct dso *dso, u64 addr); +void inline_node__delete(struct inline_node *node); + +#endif /* PERF_SRCLINE_H */ diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 8a2bbd2a4d82..ac10cc675d39 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -3,6 +3,9 @@ #include "stat.h" #include "color.h" #include "pmu.h" +#include "rblist.h" +#include "evlist.h" +#include "expr.h" enum { CTX_BIT_USER = 1 << 0, @@ -41,13 +44,73 @@ static struct stats runtime_topdown_slots_issued[NUM_CTX][MAX_NR_CPUS]; static struct stats runtime_topdown_slots_retired[NUM_CTX][MAX_NR_CPUS]; static struct stats runtime_topdown_fetch_bubbles[NUM_CTX][MAX_NR_CPUS]; static struct stats runtime_topdown_recovery_bubbles[NUM_CTX][MAX_NR_CPUS]; +static struct rblist runtime_saved_values; static bool have_frontend_stalled; struct stats walltime_nsecs_stats; +struct saved_value { + struct rb_node rb_node; + struct perf_evsel *evsel; + int cpu; + int ctx; + struct stats stats; +}; + +static int saved_value_cmp(struct rb_node *rb_node, const void *entry) +{ + struct saved_value *a = container_of(rb_node, + struct saved_value, + rb_node); + const struct saved_value *b = entry; + + if (a->ctx != b->ctx) + return a->ctx - b->ctx; + if (a->cpu != b->cpu) + return a->cpu - b->cpu; + return a->evsel - b->evsel; +} + +static struct rb_node *saved_value_new(struct rblist *rblist __maybe_unused, + const void *entry) +{ + struct saved_value *nd = malloc(sizeof(struct saved_value)); + + if (!nd) + return NULL; + memcpy(nd, entry, sizeof(struct saved_value)); + return &nd->rb_node; +} + +static struct saved_value *saved_value_lookup(struct perf_evsel *evsel, + int cpu, int ctx, + bool create) +{ + struct rb_node *nd; + struct saved_value dm = { + .cpu = cpu, + .ctx = ctx, + .evsel = evsel, + }; + nd = rblist__find(&runtime_saved_values, &dm); + if (nd) + return container_of(nd, struct saved_value, rb_node); + if (create) { + rblist__add_node(&runtime_saved_values, &dm); + nd = rblist__find(&runtime_saved_values, &dm); + if (nd) + return container_of(nd, struct saved_value, rb_node); + } + return NULL; +} + void perf_stat__init_shadow_stats(void) { have_frontend_stalled = pmu_have_event("cpu", "stalled-cycles-frontend"); + rblist__init(&runtime_saved_values); + runtime_saved_values.node_cmp = saved_value_cmp; + runtime_saved_values.node_new = saved_value_new; + /* No delete for now */ } static int evsel_context(struct perf_evsel *evsel) @@ -70,6 +133,8 @@ static int evsel_context(struct perf_evsel *evsel) void perf_stat__reset_shadow_stats(void) { + struct rb_node *pos, *next; + memset(runtime_nsecs_stats, 0, sizeof(runtime_nsecs_stats)); memset(runtime_cycles_stats, 0, sizeof(runtime_cycles_stats)); memset(runtime_stalled_cycles_front_stats, 0, sizeof(runtime_stalled_cycles_front_stats)); @@ -92,6 +157,15 @@ void perf_stat__reset_shadow_stats(void) memset(runtime_topdown_slots_issued, 0, sizeof(runtime_topdown_slots_issued)); memset(runtime_topdown_fetch_bubbles, 0, sizeof(runtime_topdown_fetch_bubbles)); memset(runtime_topdown_recovery_bubbles, 0, sizeof(runtime_topdown_recovery_bubbles)); + + next = rb_first(&runtime_saved_values.entries); + while (next) { + pos = next; + next = rb_next(pos); + memset(&container_of(pos, struct saved_value, rb_node)->stats, + 0, + sizeof(struct stats)); + } } /* @@ -143,6 +217,12 @@ void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count, update_stats(&runtime_dtlb_cache_stats[ctx][cpu], count[0]); else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_ITLB)) update_stats(&runtime_itlb_cache_stats[ctx][cpu], count[0]); + + if (counter->collect_stat) { + struct saved_value *v = saved_value_lookup(counter, cpu, ctx, + true); + update_stats(&v->stats, count[0]); + } } /* used for get_ratio_color() */ @@ -172,6 +252,95 @@ static const char *get_ratio_color(enum grc_type type, double ratio) return color; } +static struct perf_evsel *perf_stat__find_event(struct perf_evlist *evsel_list, + const char *name) +{ + struct perf_evsel *c2; + + evlist__for_each_entry (evsel_list, c2) { + if (!strcasecmp(c2->name, name)) + return c2; + } + return NULL; +} + +/* Mark MetricExpr target events and link events using them to them. */ +void perf_stat__collect_metric_expr(struct perf_evlist *evsel_list) +{ + struct perf_evsel *counter, *leader, **metric_events, *oc; + bool found; + const char **metric_names; + int i; + int num_metric_names; + + evlist__for_each_entry(evsel_list, counter) { + bool invalid = false; + + leader = counter->leader; + if (!counter->metric_expr) + continue; + metric_events = counter->metric_events; + if (!metric_events) { + if (expr__find_other(counter->metric_expr, counter->name, + &metric_names, &num_metric_names) < 0) + continue; + + metric_events = calloc(sizeof(struct perf_evsel *), + num_metric_names + 1); + if (!metric_events) + return; + counter->metric_events = metric_events; + } + + for (i = 0; i < num_metric_names; i++) { + found = false; + if (leader) { + /* Search in group */ + for_each_group_member (oc, leader) { + if (!strcasecmp(oc->name, metric_names[i])) { + found = true; + break; + } + } + } + if (!found) { + /* Search ignoring groups */ + oc = perf_stat__find_event(evsel_list, metric_names[i]); + } + if (!oc) { + /* Deduping one is good enough to handle duplicated PMUs. */ + static char *printed; + + /* + * Adding events automatically would be difficult, because + * it would risk creating groups that are not schedulable. + * perf stat doesn't understand all the scheduling constraints + * of events. So we ask the user instead to add the missing + * events. + */ + if (!printed || strcasecmp(printed, metric_names[i])) { + fprintf(stderr, + "Add %s event to groups to get metric expression for %s\n", + metric_names[i], + counter->name); + printed = strdup(metric_names[i]); + } + invalid = true; + continue; + } + metric_events[i] = oc; + oc->collect_stat = true; + } + metric_events[i] = NULL; + free(metric_names); + if (invalid) { + free(metric_events); + counter->metric_events = NULL; + counter->metric_expr = NULL; + } + } +} + static void print_stalled_cycles_frontend(int cpu, struct perf_evsel *evsel, double avg, struct perf_stat_output_ctx *out) @@ -614,6 +783,34 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel, be_bound * 100.); else print_metric(ctxp, NULL, NULL, name, 0); + } else if (evsel->metric_expr) { + struct parse_ctx pctx; + int i; + + expr__ctx_init(&pctx); + expr__add_id(&pctx, evsel->name, avg); + for (i = 0; evsel->metric_events[i]; i++) { + struct saved_value *v; + + v = saved_value_lookup(evsel->metric_events[i], cpu, ctx, false); + if (!v) + break; + expr__add_id(&pctx, evsel->metric_events[i]->name, + avg_stats(&v->stats)); + } + if (!evsel->metric_events[i]) { + const char *p = evsel->metric_expr; + + if (expr__parse(&ratio, &pctx, &p) == 0) + print_metric(ctxp, NULL, "%8.1f", + evsel->metric_name ? + evsel->metric_name : + out->force_header ? evsel->name : "", + ratio); + else + print_metric(ctxp, NULL, NULL, "", 0); + } else + print_metric(ctxp, NULL, NULL, "", 0); } else if (runtime_nsecs_stats[cpu].n != 0) { char unit = 'M'; char unit_buf[10]; diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 39345c2ddfc2..c58174443dc1 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -1,3 +1,5 @@ +#include <errno.h> +#include <inttypes.h> #include <math.h> #include "stat.h" #include "evlist.h" @@ -344,7 +346,7 @@ int perf_stat_process_counter(struct perf_stat_config *config, for (i = 0; i < 3; i++) update_stats(&ps->res_stats[i], count[i]); - if (verbose) { + if (verbose > 0) { fprintf(config->output, "%s: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n", perf_evsel__name(counter), count[0], count[1], count[2]); } diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index c29bb94c48a4..0a65ae23f495 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -85,11 +85,13 @@ struct perf_stat_output_ctx { void *ctx; print_metric_t print_metric; new_line_t new_line; + bool force_header; }; void perf_stat__print_shadow_stats(struct perf_evsel *evsel, double avg, int cpu, struct perf_stat_output_ctx *out); +void perf_stat__collect_metric_expr(struct perf_evlist *); int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw); void perf_evlist__free_stats(struct perf_evlist *evlist); diff --git a/tools/perf/util/strbuf.c b/tools/perf/util/strbuf.c index 817593908d47..aafe908b82b5 100644 --- a/tools/perf/util/strbuf.c +++ b/tools/perf/util/strbuf.c @@ -1,15 +1,7 @@ #include "debug.h" #include "util.h" #include <linux/kernel.h> - -int prefixcmp(const char *str, const char *prefix) -{ - for (; ; str++, prefix++) - if (!*prefix) - return 0; - else if (*str != *prefix) - return (unsigned char)*prefix - (unsigned char)*str; -} +#include <errno.h> /* * Used as the default ->buf value, so that people can always assume diff --git a/tools/perf/util/strfilter.c b/tools/perf/util/strfilter.c index bcae659b6546..4dc0af669a30 100644 --- a/tools/perf/util/strfilter.c +++ b/tools/perf/util/strfilter.c @@ -1,7 +1,10 @@ #include "util.h" -#include "string.h" +#include "string2.h" #include "strfilter.h" +#include <errno.h> +#include "sane_ctype.h" + /* Operators */ static const char *OP_and = "&"; /* Logical AND */ static const char *OP_or = "|"; /* Logical OR */ @@ -269,6 +272,7 @@ static int strfilter_node__sprint(struct strfilter_node *node, char *buf) len = strfilter_node__sprint_pt(node->l, buf); if (len < 0) return len; + __fallthrough; case '!': if (buf) { *(buf + len++) = *node->p; diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c index d8dfaf64b32e..cca53b693a48 100644 --- a/tools/perf/util/string.c +++ b/tools/perf/util/string.c @@ -1,5 +1,9 @@ -#include "util.h" -#include "linux/string.h" +#include "string2.h" +#include <linux/kernel.h> +#include <linux/string.h> +#include <stdlib.h> + +#include "sane_ctype.h" #define K 1024LL /* @@ -21,6 +25,8 @@ s64 perf_atoll(const char *str) case 'b': case 'B': if (*p) goto out_err; + + __fallthrough; case '\0': return length; default: @@ -97,8 +103,10 @@ static int count_argc(const char *str) void argv_free(char **argv) { char **p; - for (p = argv; *p; p++) - zfree(p); + for (p = argv; *p; p++) { + free(*p); + *p = NULL; + } free(argv); } @@ -118,7 +126,7 @@ void argv_free(char **argv) char **argv_split(const char *str, int *argcp) { int argc = count_argc(str); - char **argv = zalloc(sizeof(*argv) * (argc+1)); + char **argv = calloc(argc + 1, sizeof(*argv)); char **argvp; if (argv == NULL) @@ -320,12 +328,8 @@ char *strxfrchar(char *s, char from, char to) */ char *ltrim(char *s) { - int len = strlen(s); - - while (len && isspace(*s)) { - len--; + while (isspace(*s)) s++; - } return s; } @@ -379,7 +383,7 @@ char *asprintf_expr_inout_ints(const char *var, bool in, size_t nints, int *ints goto out_err_overflow; if (i > 0) - printed += snprintf(e + printed, size - printed, " %s ", or_and); + printed += scnprintf(e + printed, size - printed, " %s ", or_and); printed += scnprintf(e + printed, size - printed, "%s %s %d", var, eq_neq, ints[i]); } diff --git a/tools/perf/util/string2.h b/tools/perf/util/string2.h new file mode 100644 index 000000000000..2f619681bd6a --- /dev/null +++ b/tools/perf/util/string2.h @@ -0,0 +1,42 @@ +#ifndef PERF_STRING_H +#define PERF_STRING_H + +#include <linux/types.h> +#include <stddef.h> +#include <string.h> + +s64 perf_atoll(const char *str); +char **argv_split(const char *str, int *argcp); +void argv_free(char **argv); +bool strglobmatch(const char *str, const char *pat); +bool strglobmatch_nocase(const char *str, const char *pat); +bool strlazymatch(const char *str, const char *pat); +static inline bool strisglob(const char *str) +{ + return strpbrk(str, "*?[") != NULL; +} +int strtailcmp(const char *s1, const char *s2); +char *strxfrchar(char *s, char from, char to); + +char *ltrim(char *s); +char *rtrim(char *s); + +static inline char *trim(char *s) +{ + return ltrim(rtrim(s)); +} + +char *asprintf_expr_inout_ints(const char *var, bool in, size_t nints, int *ints); + +static inline char *asprintf_expr_in_ints(const char *var, size_t nints, int *ints) +{ + return asprintf_expr_inout_ints(var, true, nints, ints); +} + +static inline char *asprintf_expr_not_in_ints(const char *var, size_t nints, int *ints) +{ + return asprintf_expr_inout_ints(var, false, nints, ints); +} + + +#endif /* PERF_STRING_H */ diff --git a/tools/perf/util/strlist.c b/tools/perf/util/strlist.c index 0d3dfcb919b4..9de5434bb49e 100644 --- a/tools/perf/util/strlist.c +++ b/tools/perf/util/strlist.c @@ -10,6 +10,7 @@ #include <stdio.h> #include <stdlib.h> #include <string.h> +#include <unistd.h> static struct rb_node *strlist__node_new(struct rblist *rblist, const void *entry) diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index adbc6c02c3aa..e7ee47f7377a 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -10,8 +10,9 @@ #include "demangle-rust.h" #include "machine.h" #include "vdso.h" -#include <symbol/kallsyms.h> #include "debug.h" +#include "sane_ctype.h" +#include <symbol/kallsyms.h> #ifndef EM_AARCH64 #define EM_AARCH64 183 /* ARM 64 bit */ @@ -213,7 +214,7 @@ static bool want_demangle(bool is_kernel_sym) static char *demangle_sym(struct dso *dso, int kmodule, const char *elf_name) { - int demangle_flags = verbose ? (DMGL_PARAMS | DMGL_ANSI) : DMGL_NO_OPTS; + int demangle_flags = verbose > 0 ? (DMGL_PARAMS | DMGL_ANSI) : DMGL_NO_OPTS; char *demangled = NULL; /* @@ -390,6 +391,11 @@ out_elf_end: return 0; } +char *dso__demangle_sym(struct dso *dso, int kmodule, char *elf_name) +{ + return demangle_sym(dso, kmodule, elf_name); +} + /* * Align offset to 4 bytes as needed for note name and descriptor data. */ @@ -1828,7 +1834,7 @@ void kcore_extract__delete(struct kcore_extract *kce) static int populate_sdt_note(Elf **elf, const char *data, size_t len, struct list_head *sdt_notes) { - const char *provider, *name; + const char *provider, *name, *args; struct sdt_note *tmp = NULL; GElf_Ehdr ehdr; GElf_Addr base_off = 0; @@ -1887,6 +1893,25 @@ static int populate_sdt_note(Elf **elf, const char *data, size_t len, goto out_free_prov; } + args = memchr(name, '\0', data + len - name); + + /* + * There is no argument if: + * - We reached the end of the note; + * - There is not enough room to hold a potential string; + * - The argument string is empty or just contains ':'. + */ + if (args == NULL || data + len - args < 2 || + args[1] == ':' || args[1] == '\0') + tmp->args = NULL; + else { + tmp->args = strdup(++args); + if (!tmp->args) { + ret = -ENOMEM; + goto out_free_name; + } + } + if (gelf_getclass(*elf) == ELFCLASS32) { memcpy(&tmp->addr, &buf, 3 * sizeof(Elf32_Addr)); tmp->bit32 = true; @@ -1898,7 +1923,7 @@ static int populate_sdt_note(Elf **elf, const char *data, size_t len, if (!gelf_getehdr(*elf, &ehdr)) { pr_debug("%s : cannot get elf header.\n", __func__); ret = -EBADF; - goto out_free_name; + goto out_free_args; } /* Adjust the prelink effect : @@ -1923,6 +1948,8 @@ static int populate_sdt_note(Elf **elf, const char *data, size_t len, list_add_tail(&tmp->note_list, sdt_notes); return 0; +out_free_args: + free(tmp->args); out_free_name: free(tmp->name); out_free_prov: diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c index 11cdde980545..40bf5d4c0bfd 100644 --- a/tools/perf/util/symbol-minimal.c +++ b/tools/perf/util/symbol-minimal.c @@ -1,6 +1,7 @@ #include "symbol.h" #include "util.h" +#include <errno.h> #include <stdio.h> #include <fcntl.h> #include <string.h> @@ -373,3 +374,10 @@ int kcore_copy(const char *from_dir __maybe_unused, void symbol__elf_init(void) { } + +char *dso__demangle_sym(struct dso *dso __maybe_unused, + int kmodule __maybe_unused, + char *elf_name __maybe_unused) +{ + return NULL; +} diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index dc93940de351..8f2b068ff756 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -3,6 +3,7 @@ #include <stdlib.h> #include <stdio.h> #include <string.h> +#include <linux/kernel.h> #include <sys/types.h> #include <sys/stat.h> #include <sys/param.h> @@ -18,6 +19,8 @@ #include "strlist.h" #include "intlist.h" #include "header.h" +#include "path.h" +#include "sane_ctype.h" #include <elf.h> #include <limits.h> @@ -87,6 +90,17 @@ static int prefix_underscores_count(const char *str) return tail - str; } +int __weak arch__compare_symbol_names(const char *namea, const char *nameb) +{ + return strcmp(namea, nameb); +} + +int __weak arch__compare_symbol_names_n(const char *namea, const char *nameb, + unsigned int n) +{ + return strncmp(namea, nameb, n); +} + int __weak arch__choose_best_symbol(struct symbol *syma, struct symbol *symb __maybe_unused) { @@ -202,7 +216,7 @@ void symbols__fixup_end(struct rb_root *symbols) /* Last entry */ if (curr->end == curr->start) - curr->end = roundup(curr->start, 4096); + curr->end = roundup(curr->start, 4096) + 4096; } void __map_groups__fixup_end(struct map_groups *mg, enum map_type type) @@ -396,8 +410,26 @@ static void symbols__sort_by_name(struct rb_root *symbols, } } +int symbol__match_symbol_name(const char *name, const char *str, + enum symbol_tag_include includes) +{ + const char *versioning; + + if (includes == SYMBOL_TAG_INCLUDE__DEFAULT_ONLY && + (versioning = strstr(name, "@@"))) { + int len = strlen(str); + + if (len < versioning - name) + len = versioning - name; + + return arch__compare_symbol_names_n(name, str, len); + } else + return arch__compare_symbol_names(name, str); +} + static struct symbol *symbols__find_by_name(struct rb_root *symbols, - const char *name) + const char *name, + enum symbol_tag_include includes) { struct rb_node *n; struct symbol_name_rb_node *s = NULL; @@ -411,11 +443,11 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols, int cmp; s = rb_entry(n, struct symbol_name_rb_node, rb_node); - cmp = arch__compare_symbol_names(name, s->sym.name); + cmp = symbol__match_symbol_name(s->sym.name, name, includes); - if (cmp < 0) + if (cmp > 0) n = n->rb_left; - else if (cmp > 0) + else if (cmp < 0) n = n->rb_right; else break; @@ -424,16 +456,17 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols, if (n == NULL) return NULL; - /* return first symbol that has same name (if any) */ - for (n = rb_prev(n); n; n = rb_prev(n)) { - struct symbol_name_rb_node *tmp; + if (includes != SYMBOL_TAG_INCLUDE__DEFAULT_ONLY) + /* return first symbol that has same name (if any) */ + for (n = rb_prev(n); n; n = rb_prev(n)) { + struct symbol_name_rb_node *tmp; - tmp = rb_entry(n, struct symbol_name_rb_node, rb_node); - if (arch__compare_symbol_names(tmp->sym.name, s->sym.name)) - break; + tmp = rb_entry(n, struct symbol_name_rb_node, rb_node); + if (arch__compare_symbol_names(tmp->sym.name, s->sym.name)) + break; - s = tmp; - } + s = tmp; + } return &s->sym; } @@ -463,7 +496,7 @@ void dso__insert_symbol(struct dso *dso, enum map_type type, struct symbol *sym) struct symbol *dso__find_symbol(struct dso *dso, enum map_type type, u64 addr) { - if (dso->last_find_result[type].addr != addr) { + if (dso->last_find_result[type].addr != addr || dso->last_find_result[type].symbol == NULL) { dso->last_find_result[type].addr = addr; dso->last_find_result[type].symbol = symbols__find(&dso->symbols[type], addr); } @@ -500,7 +533,12 @@ struct symbol *symbol__next_by_name(struct symbol *sym) struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type, const char *name) { - return symbols__find_by_name(&dso->symbol_names[type], name); + struct symbol *s = symbols__find_by_name(&dso->symbol_names[type], name, + SYMBOL_TAG_INCLUDE__NONE); + if (!s) + s = symbols__find_by_name(&dso->symbol_names[type], name, + SYMBOL_TAG_INCLUDE__DEFAULT_ONLY); + return s; } void dso__sort_by_name(struct dso *dso, enum map_type type) @@ -1072,8 +1110,9 @@ static int validate_kcore_addresses(const char *kallsyms_filename, if (kmap->ref_reloc_sym && kmap->ref_reloc_sym->name) { u64 start; - start = kallsyms__get_function_start(kallsyms_filename, - kmap->ref_reloc_sym->name); + if (kallsyms__get_function_start(kallsyms_filename, + kmap->ref_reloc_sym->name, &start)) + return -ENOENT; if (start != kmap->ref_reloc_sym->addr) return -EINVAL; } @@ -1245,9 +1284,7 @@ static int kallsyms__delta(struct map *map, const char *filename, u64 *delta) if (!kmap->ref_reloc_sym || !kmap->ref_reloc_sym->name) return 0; - addr = kallsyms__get_function_start(filename, - kmap->ref_reloc_sym->name); - if (!addr) + if (kallsyms__get_function_start(filename, kmap->ref_reloc_sym->name, &addr)) return -1; *delta = addr - kmap->ref_reloc_sym->addr; @@ -1460,9 +1497,11 @@ int dso__load(struct dso *dso, struct map *map) * DSO_BINARY_TYPE__BUILDID_DEBUGINFO to work */ if (!dso->has_build_id && - is_regular_file(dso->long_name) && - filename__read_build_id(dso->long_name, build_id, BUILD_ID_SIZE) > 0) + is_regular_file(dso->long_name)) { + __symbol__join_symfs(name, PATH_MAX, dso->long_name); + if (filename__read_build_id(name, build_id, BUILD_ID_SIZE) > 0) dso__set_build_id(dso, build_id); + } /* * Iterate over candidate debug images. diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 6c358b7ed336..41ebba9a2eb2 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -13,7 +13,7 @@ #include <libgen.h> #include "build-id.h" #include "event.h" -#include "util.h" +#include "path.h" #ifdef HAVE_LIBELF_SUPPORT #include <libelf.h> @@ -118,7 +118,8 @@ struct symbol_conf { show_ref_callgraph, hide_unresolved, raw_trace, - report_hierarchy; + report_hierarchy, + inline_name; const char *vmlinux_name, *kallsyms_name, *source_prefix, @@ -305,6 +306,8 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss, int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *map); +char *dso__demangle_sym(struct dso *dso, int kmodule, char *elf_name); + void __symbols__insert(struct rb_root *symbols, struct symbol *sym, bool kernel); void symbols__insert(struct rb_root *symbols, struct symbol *sym); void symbols__fixup_duplicate(struct rb_root *symbols); @@ -345,12 +348,24 @@ void arch__sym_update(struct symbol *s, GElf_Sym *sym); #define SYMBOL_A 0 #define SYMBOL_B 1 +int arch__compare_symbol_names(const char *namea, const char *nameb); +int arch__compare_symbol_names_n(const char *namea, const char *nameb, + unsigned int n); int arch__choose_best_symbol(struct symbol *syma, struct symbol *symb); +enum symbol_tag_include { + SYMBOL_TAG_INCLUDE__NONE = 0, + SYMBOL_TAG_INCLUDE__DEFAULT_ONLY +}; + +int symbol__match_symbol_name(const char *namea, const char *nameb, + enum symbol_tag_include includes); + /* structure containing an SDT note's info */ struct sdt_note { char *name; /* name of the note*/ char *provider; /* provider name */ + char *args; bool bit32; /* whether the location is 32 bits? */ union { /* location, base and semaphore addrs */ Elf64_Addr a64[3]; diff --git a/tools/perf/util/symbol_fprintf.c b/tools/perf/util/symbol_fprintf.c index 7c6b33e8e2d2..63694e174e5c 100644 --- a/tools/perf/util/symbol_fprintf.c +++ b/tools/perf/util/symbol_fprintf.c @@ -21,7 +21,7 @@ size_t __symbol__fprintf_symname_offs(const struct symbol *sym, unsigned long offset; size_t length; - if (sym && sym->name) { + if (sym) { length = fprintf(fp, "%s", sym->name); if (al && print_offsets) { if (al->addr < sym->end) diff --git a/tools/perf/util/term.c b/tools/perf/util/term.c index 90b47d8aa19c..8f254a74d97d 100644 --- a/tools/perf/util/term.c +++ b/tools/perf/util/term.c @@ -1,4 +1,8 @@ -#include "util.h" +#include "term.h" +#include <stdlib.h> +#include <termios.h> +#include <unistd.h> +#include <sys/ioctl.h> void get_term_dimensions(struct winsize *ws) { diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c index d3301529f6a7..dd17d6a38d3a 100644 --- a/tools/perf/util/thread-stack.c +++ b/tools/perf/util/thread-stack.c @@ -15,6 +15,7 @@ #include <linux/rbtree.h> #include <linux/list.h> +#include <errno.h> #include "thread.h" #include "event.h" #include "machine.h" diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index f5af87f66663..378c418ca0c1 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -1,12 +1,15 @@ #include "../perf.h" +#include <errno.h> #include <stdlib.h> #include <stdio.h> #include <string.h> +#include <linux/kernel.h> #include "session.h" #include "thread.h" #include "thread-stack.h" #include "util.h" #include "debug.h" +#include "namespaces.h" #include "comm.h" #include "unwind.h" @@ -40,6 +43,7 @@ struct thread *thread__new(pid_t pid, pid_t tid) thread->tid = tid; thread->ppid = -1; thread->cpu = -1; + INIT_LIST_HEAD(&thread->namespaces_list); INIT_LIST_HEAD(&thread->comm_list); comm_str = malloc(32); @@ -53,7 +57,7 @@ struct thread *thread__new(pid_t pid, pid_t tid) goto err_thread; list_add(&comm->list, &thread->comm_list); - atomic_set(&thread->refcnt, 1); + refcount_set(&thread->refcnt, 1); RB_CLEAR_NODE(&thread->rb_node); } @@ -66,7 +70,8 @@ err_thread: void thread__delete(struct thread *thread) { - struct comm *comm, *tmp; + struct namespaces *namespaces, *tmp_namespaces; + struct comm *comm, *tmp_comm; BUG_ON(!RB_EMPTY_NODE(&thread->rb_node)); @@ -76,7 +81,12 @@ void thread__delete(struct thread *thread) map_groups__put(thread->mg); thread->mg = NULL; } - list_for_each_entry_safe(comm, tmp, &thread->comm_list, list) { + list_for_each_entry_safe(namespaces, tmp_namespaces, + &thread->namespaces_list, list) { + list_del(&namespaces->list); + namespaces__free(namespaces); + } + list_for_each_entry_safe(comm, tmp_comm, &thread->comm_list, list) { list_del(&comm->list); comm__free(comm); } @@ -88,13 +98,13 @@ void thread__delete(struct thread *thread) struct thread *thread__get(struct thread *thread) { if (thread) - atomic_inc(&thread->refcnt); + refcount_inc(&thread->refcnt); return thread; } void thread__put(struct thread *thread) { - if (thread && atomic_dec_and_test(&thread->refcnt)) { + if (thread && refcount_dec_and_test(&thread->refcnt)) { /* * Remove it from the dead_threads list, as last reference * is gone. @@ -104,6 +114,38 @@ void thread__put(struct thread *thread) } } +struct namespaces *thread__namespaces(const struct thread *thread) +{ + if (list_empty(&thread->namespaces_list)) + return NULL; + + return list_first_entry(&thread->namespaces_list, struct namespaces, list); +} + +int thread__set_namespaces(struct thread *thread, u64 timestamp, + struct namespaces_event *event) +{ + struct namespaces *new, *curr = thread__namespaces(thread); + + new = namespaces__new(event); + if (!new) + return -ENOMEM; + + list_add(&new->list, &thread->namespaces_list); + + if (timestamp && curr) { + /* + * setns syscall must have changed few or all the namespaces + * of this thread. Update end time for the namespaces + * previously used. + */ + curr = list_next_entry(new, list); + curr->end_time = timestamp; + } + + return 0; +} + struct comm *thread__comm(const struct thread *thread) { if (list_empty(&thread->comm_list)) diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h index 99263cb6e6b6..4eb849e9098f 100644 --- a/tools/perf/util/thread.h +++ b/tools/perf/util/thread.h @@ -1,7 +1,7 @@ #ifndef __PERF_THREAD_H #define __PERF_THREAD_H -#include <linux/atomic.h> +#include <linux/refcount.h> #include <linux/rbtree.h> #include <linux/list.h> #include <unistd.h> @@ -23,11 +23,12 @@ struct thread { pid_t tid; pid_t ppid; int cpu; - atomic_t refcnt; + refcount_t refcnt; char shortname[3]; bool comm_set; int comm_len; bool dead; /* if set thread has exited */ + struct list_head namespaces_list; struct list_head comm_list; u64 db_id; @@ -40,6 +41,7 @@ struct thread { }; struct machine; +struct namespaces; struct comm; struct thread *thread__new(pid_t pid, pid_t tid); @@ -62,6 +64,10 @@ static inline void thread__exited(struct thread *thread) thread->dead = true; } +struct namespaces *thread__namespaces(const struct thread *thread); +int thread__set_namespaces(struct thread *thread, u64 timestamp, + struct namespaces_event *event); + int __thread__set_comm(struct thread *thread, const char *comm, u64 timestamp, bool exec); static inline int thread__set_comm(struct thread *thread, const char *comm, diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c index f9eab200fd75..63ead7b06324 100644 --- a/tools/perf/util/thread_map.c +++ b/tools/perf/util/thread_map.c @@ -1,4 +1,5 @@ #include <dirent.h> +#include <errno.h> #include <limits.h> #include <stdbool.h> #include <stdlib.h> @@ -6,6 +7,7 @@ #include <sys/types.h> #include <sys/stat.h> #include <unistd.h> +#include "string2.h" #include "strlist.h" #include <string.h> #include <api/fs/fs.h> @@ -66,7 +68,7 @@ struct thread_map *thread_map__new_by_pid(pid_t pid) for (i = 0; i < items; i++) thread_map__set_pid(threads, i, atoi(namelist[i]->d_name)); threads->nr = items; - atomic_set(&threads->refcnt, 1); + refcount_set(&threads->refcnt, 1); } for (i=0; i<items; i++) @@ -83,7 +85,7 @@ struct thread_map *thread_map__new_by_tid(pid_t tid) if (threads != NULL) { thread_map__set_pid(threads, 0, tid); threads->nr = 1; - atomic_set(&threads->refcnt, 1); + refcount_set(&threads->refcnt, 1); } return threads; @@ -93,7 +95,7 @@ struct thread_map *thread_map__new_by_uid(uid_t uid) { DIR *proc; int max_threads = 32, items, i; - char path[256]; + char path[NAME_MAX + 1 + 6]; struct dirent *dirent, **namelist = NULL; struct thread_map *threads = thread_map__alloc(max_threads); @@ -105,7 +107,7 @@ struct thread_map *thread_map__new_by_uid(uid_t uid) goto out_free_threads; threads->nr = 0; - atomic_set(&threads->refcnt, 1); + refcount_set(&threads->refcnt, 1); while ((dirent = readdir(proc)) != NULL) { char *end; @@ -235,7 +237,7 @@ static struct thread_map *thread_map__new_by_pid_str(const char *pid_str) out: strlist__delete(slist); if (threads) - atomic_set(&threads->refcnt, 1); + refcount_set(&threads->refcnt, 1); return threads; out_free_namelist: @@ -255,7 +257,7 @@ struct thread_map *thread_map__new_dummy(void) if (threads != NULL) { thread_map__set_pid(threads, 0, -1); threads->nr = 1; - atomic_set(&threads->refcnt, 1); + refcount_set(&threads->refcnt, 1); } return threads; } @@ -300,7 +302,7 @@ struct thread_map *thread_map__new_by_tid_str(const char *tid_str) } out: if (threads) - atomic_set(&threads->refcnt, 1); + refcount_set(&threads->refcnt, 1); return threads; out_free_threads: @@ -326,7 +328,7 @@ static void thread_map__delete(struct thread_map *threads) if (threads) { int i; - WARN_ONCE(atomic_read(&threads->refcnt) != 0, + WARN_ONCE(refcount_read(&threads->refcnt) != 0, "thread map refcnt unbalanced\n"); for (i = 0; i < threads->nr; i++) free(thread_map__comm(threads, i)); @@ -337,13 +339,13 @@ static void thread_map__delete(struct thread_map *threads) struct thread_map *thread_map__get(struct thread_map *map) { if (map) - atomic_inc(&map->refcnt); + refcount_inc(&map->refcnt); return map; } void thread_map__put(struct thread_map *map) { - if (map && atomic_dec_and_test(&map->refcnt)) + if (map && refcount_dec_and_test(&map->refcnt)) thread_map__delete(map); } @@ -423,7 +425,7 @@ static void thread_map__copy_event(struct thread_map *threads, threads->map[i].comm = strndup(event->entries[i].comm, 16); } - atomic_set(&threads->refcnt, 1); + refcount_set(&threads->refcnt, 1); } struct thread_map *thread_map__new_event(struct thread_map_event *event) diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h index ea0ef08c6303..bd34d7a0b9fa 100644 --- a/tools/perf/util/thread_map.h +++ b/tools/perf/util/thread_map.h @@ -3,7 +3,7 @@ #include <sys/types.h> #include <stdio.h> -#include <linux/atomic.h> +#include <linux/refcount.h> struct thread_map_data { pid_t pid; @@ -11,7 +11,7 @@ struct thread_map_data { }; struct thread_map { - atomic_t refcnt; + refcount_t refcnt; int nr; struct thread_map_data map[]; }; diff --git a/tools/perf/util/time-utils.c b/tools/perf/util/time-utils.c index d1b21c72206d..5b5d0214debd 100644 --- a/tools/perf/util/time-utils.c +++ b/tools/perf/util/time-utils.c @@ -117,3 +117,28 @@ bool perf_time__skip_sample(struct perf_time_interval *ptime, u64 timestamp) return false; } + +int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz) +{ + u64 sec = timestamp / NSEC_PER_SEC; + u64 usec = (timestamp % NSEC_PER_SEC) / NSEC_PER_USEC; + + return scnprintf(buf, sz, "%"PRIu64".%06"PRIu64, sec, usec); +} + +int fetch_current_timestamp(char *buf, size_t sz) +{ + struct timeval tv; + struct tm tm; + char dt[32]; + + if (gettimeofday(&tv, NULL) || !localtime_r(&tv.tv_sec, &tm)) + return -1; + + if (!strftime(dt, sizeof(dt), "%Y%m%d%H%M%S", &tm)) + return -1; + + scnprintf(buf, sz, "%s%02u", dt, (unsigned)tv.tv_usec / 10000); + + return 0; +} diff --git a/tools/perf/util/time-utils.h b/tools/perf/util/time-utils.h index c1f197c4af6c..8656be08513b 100644 --- a/tools/perf/util/time-utils.h +++ b/tools/perf/util/time-utils.h @@ -1,6 +1,9 @@ #ifndef _TIME_UTILS_H_ #define _TIME_UTILS_H_ +#include <stddef.h> +#include <linux/types.h> + struct perf_time_interval { u64 start, end; }; @@ -11,4 +14,8 @@ int perf_time__parse_str(struct perf_time_interval *ptime, const char *ostr); bool perf_time__skip_sample(struct perf_time_interval *ptime, u64 timestamp); +int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz); + +int fetch_current_timestamp(char *buf, size_t sz); + #endif diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h index ac2590a3de2d..829471a1c6d7 100644 --- a/tools/perf/util/tool.h +++ b/tools/perf/util/tool.h @@ -40,6 +40,7 @@ struct perf_tool { event_op mmap, mmap2, comm, + namespaces, fork, exit, lost, @@ -66,6 +67,7 @@ struct perf_tool { event_op3 auxtrace; bool ordered_events; bool ordering_requires_timestamps; + bool namespace_events; }; #endif /* __PERF_TOOL_H */ diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h index b2940c88734a..9bdfb78a9a35 100644 --- a/tools/perf/util/top.h +++ b/tools/perf/util/top.h @@ -5,7 +5,7 @@ #include <linux/types.h> #include <stddef.h> #include <stdbool.h> -#include <termios.h> +#include <sys/ioctl.h> struct perf_evlist; struct perf_evsel; diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c index d995743cb673..e7d60d05596d 100644 --- a/tools/perf/util/trace-event-info.c +++ b/tools/perf/util/trace-event-info.c @@ -42,7 +42,7 @@ #include "evsel.h" #include "debug.h" -#define VERSION "0.5" +#define VERSION "0.6" static int output_fd; @@ -170,6 +170,12 @@ static bool name_in_tp_list(char *sys, struct tracepoint_path *tps) return false; } +#define for_each_event(dir, dent, tps) \ + while ((dent = readdir(dir))) \ + if (dent->d_type == DT_DIR && \ + (strcmp(dent->d_name, ".")) && \ + (strcmp(dent->d_name, ".."))) \ + static int copy_event_system(const char *sys, struct tracepoint_path *tps) { struct dirent *dent; @@ -186,12 +192,10 @@ static int copy_event_system(const char *sys, struct tracepoint_path *tps) return -errno; } - while ((dent = readdir(dir))) { - if (dent->d_type != DT_DIR || - strcmp(dent->d_name, ".") == 0 || - strcmp(dent->d_name, "..") == 0 || - !name_in_tp_list(dent->d_name, tps)) + for_each_event(dir, dent, tps) { + if (!name_in_tp_list(dent->d_name, tps)) continue; + if (asprintf(&format, "%s/%s/format", sys, dent->d_name) < 0) { err = -ENOMEM; goto out; @@ -210,12 +214,10 @@ static int copy_event_system(const char *sys, struct tracepoint_path *tps) } rewinddir(dir); - while ((dent = readdir(dir))) { - if (dent->d_type != DT_DIR || - strcmp(dent->d_name, ".") == 0 || - strcmp(dent->d_name, "..") == 0 || - !name_in_tp_list(dent->d_name, tps)) + for_each_event(dir, dent, tps) { + if (!name_in_tp_list(dent->d_name, tps)) continue; + if (asprintf(&format, "%s/%s/format", sys, dent->d_name) < 0) { err = -ENOMEM; goto out; @@ -290,13 +292,11 @@ static int record_event_files(struct tracepoint_path *tps) goto out; } - while ((dent = readdir(dir))) { - if (dent->d_type != DT_DIR || - strcmp(dent->d_name, ".") == 0 || - strcmp(dent->d_name, "..") == 0 || - strcmp(dent->d_name, "ftrace") == 0 || + for_each_event(dir, dent, tps) { + if (strcmp(dent->d_name, "ftrace") == 0 || !system_in_tp_list(dent->d_name, tps)) continue; + count++; } @@ -307,13 +307,11 @@ static int record_event_files(struct tracepoint_path *tps) } rewinddir(dir); - while ((dent = readdir(dir))) { - if (dent->d_type != DT_DIR || - strcmp(dent->d_name, ".") == 0 || - strcmp(dent->d_name, "..") == 0 || - strcmp(dent->d_name, "ftrace") == 0 || + for_each_event(dir, dent, tps) { + if (strcmp(dent->d_name, "ftrace") == 0 || !system_in_tp_list(dent->d_name, tps)) continue; + if (asprintf(&sys, "%s/%s", path, dent->d_name) < 0) { err = -ENOMEM; goto out; @@ -379,6 +377,34 @@ out: return err; } +static int record_saved_cmdline(void) +{ + unsigned int size; + char *path; + struct stat st; + int ret, err = 0; + + path = get_tracing_file("saved_cmdlines"); + if (!path) { + pr_debug("can't get tracing/saved_cmdline"); + return -ENOMEM; + } + + ret = stat(path, &st); + if (ret < 0) { + /* not found */ + size = 0; + if (write(output_fd, &size, 8) != 8) + err = -EIO; + goto out; + } + err = record_file(path, 8); + +out: + put_tracing_file(path); + return err; +} + static void put_tracepoints_path(struct tracepoint_path *tps) { @@ -539,6 +565,9 @@ struct tracing_data *tracing_data_get(struct list_head *pattrs, if (err) goto out; err = record_ftrace_printk(); + if (err) + goto out; + err = record_saved_cmdline(); out: /* diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index 33b52eaa39db..746bbee645d9 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -21,13 +21,14 @@ #include <stdio.h> #include <stdlib.h> #include <string.h> -#include <ctype.h> #include <errno.h> #include "../perf.h" #include "util.h" #include "trace-event.h" +#include "sane_ctype.h" + static int get_common_field(struct scripting_context *context, int *offset, int *size, const char *type) { @@ -160,6 +161,23 @@ void parse_ftrace_printk(struct pevent *pevent, } } +void parse_saved_cmdline(struct pevent *pevent, + char *file, unsigned int size __maybe_unused) +{ + char *comm; + char *line; + char *next = NULL; + int pid; + + line = strtok_r(file, "\n", &next); + while (line) { + sscanf(line, "%d %ms", &pid, &comm); + pevent_register_comm(pevent, comm, pid); + free(comm); + line = strtok_r(NULL, "\n", &next); + } +} + int parse_ftrace_file(struct pevent *pevent, char *buf, unsigned long size) { return pevent_parse_event(pevent, buf, size, "ftrace"); diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c index b67a0ccf5ab9..8a9a677f7576 100644 --- a/tools/perf/util/trace-event-read.c +++ b/tools/perf/util/trace-event-read.c @@ -192,7 +192,7 @@ static int read_ftrace_printk(struct pevent *pevent) if (!size) return 0; - buf = malloc(size); + buf = malloc(size + 1); if (buf == NULL) return -1; @@ -201,6 +201,8 @@ static int read_ftrace_printk(struct pevent *pevent) return -1; } + buf[size] = '\0'; + parse_ftrace_printk(pevent, buf, size); free(buf); @@ -260,39 +262,53 @@ static int read_header_files(struct pevent *pevent) static int read_ftrace_file(struct pevent *pevent, unsigned long long size) { + int ret; char *buf; buf = malloc(size); - if (buf == NULL) + if (buf == NULL) { + pr_debug("memory allocation failure\n"); return -1; + } - if (do_read(buf, size) < 0) { - free(buf); - return -1; + ret = do_read(buf, size); + if (ret < 0) { + pr_debug("error reading ftrace file.\n"); + goto out; } - parse_ftrace_file(pevent, buf, size); + ret = parse_ftrace_file(pevent, buf, size); + if (ret < 0) + pr_debug("error parsing ftrace file.\n"); +out: free(buf); - return 0; + return ret; } static int read_event_file(struct pevent *pevent, char *sys, unsigned long long size) { + int ret; char *buf; buf = malloc(size); - if (buf == NULL) + if (buf == NULL) { + pr_debug("memory allocation failure\n"); return -1; + } - if (do_read(buf, size) < 0) { + ret = do_read(buf, size); + if (ret < 0) { free(buf); - return -1; + goto out; } - parse_event_file(pevent, buf, size, sys); + ret = parse_event_file(pevent, buf, size, sys); + if (ret < 0) + pr_debug("error parsing event file.\n"); +out: free(buf); - return 0; + return ret; } static int read_ftrace_files(struct pevent *pevent) @@ -341,6 +357,36 @@ static int read_event_files(struct pevent *pevent) return 0; } +static int read_saved_cmdline(struct pevent *pevent) +{ + unsigned long long size; + char *buf; + int ret; + + /* it can have 0 size */ + size = read8(pevent); + if (!size) + return 0; + + buf = malloc(size + 1); + if (buf == NULL) { + pr_debug("memory allocation failure\n"); + return -1; + } + + ret = do_read(buf, size); + if (ret < 0) { + pr_debug("error reading saved cmdlines\n"); + goto out; + } + + parse_saved_cmdline(pevent, buf, size); + ret = 0; +out: + free(buf); + return ret; +} + ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe) { char buf[BUFSIZ]; @@ -379,10 +425,11 @@ ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe) return -1; if (show_version) printf("version = %s\n", version); - free(version); - if (do_read(buf, 1) < 0) + if (do_read(buf, 1) < 0) { + free(version); return -1; + } file_bigendian = buf[0]; host_bigendian = bigendian(); @@ -423,6 +470,11 @@ ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe) err = read_ftrace_printk(pevent); if (err) goto out; + if (atof(version) >= 0.6) { + err = read_saved_cmdline(pevent); + if (err) + goto out; + } size = trace_data_size; repipe = false; @@ -438,5 +490,6 @@ ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe) out: if (pevent) trace_event__cleanup(tevent); + free(version); return size; } diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h index b0af9c81bb0d..1fbc044f9eb0 100644 --- a/tools/perf/util/trace-event.h +++ b/tools/perf/util/trace-event.h @@ -42,6 +42,7 @@ raw_field_value(struct event_format *event, const char *name, void *data); void parse_proc_kallsyms(struct pevent *pevent, char *file, unsigned int size); void parse_ftrace_printk(struct pevent *pevent, char *file, unsigned int size); +void parse_saved_cmdline(struct pevent *pevent, char *file, unsigned int size); ssize_t trace_report(int fd, struct trace_event *tevent, bool repipe); diff --git a/tools/perf/util/units.c b/tools/perf/util/units.c new file mode 100644 index 000000000000..4767ec2c5ef6 --- /dev/null +++ b/tools/perf/util/units.c @@ -0,0 +1,68 @@ +#include "units.h" +#include <inttypes.h> +#include <limits.h> +#include <stdlib.h> +#include <string.h> +#include <linux/kernel.h> +#include <linux/time64.h> + +unsigned long parse_tag_value(const char *str, struct parse_tag *tags) +{ + struct parse_tag *i = tags; + + while (i->tag) { + char *s = strchr(str, i->tag); + + if (s) { + unsigned long int value; + char *endptr; + + value = strtoul(str, &endptr, 10); + if (s != endptr) + break; + + if (value > ULONG_MAX / i->mult) + break; + value *= i->mult; + return value; + } + i++; + } + + return (unsigned long) -1; +} + +unsigned long convert_unit(unsigned long value, char *unit) +{ + *unit = ' '; + + if (value > 1000) { + value /= 1000; + *unit = 'K'; + } + + if (value > 1000) { + value /= 1000; + *unit = 'M'; + } + + if (value > 1000) { + value /= 1000; + *unit = 'G'; + } + + return value; +} + +int unit_number__scnprintf(char *buf, size_t size, u64 n) +{ + char unit[4] = "BKMG"; + int i = 0; + + while (((n / 1024) > 1) && (i < 3)) { + n /= 1024; + i++; + } + + return scnprintf(buf, size, "%" PRIu64 "%c", n, unit[i]); +} diff --git a/tools/perf/util/units.h b/tools/perf/util/units.h new file mode 100644 index 000000000000..f02c87317150 --- /dev/null +++ b/tools/perf/util/units.h @@ -0,0 +1,17 @@ +#ifndef PERF_UNIT_H +#define PERF_UNIT_H + +#include <stddef.h> +#include <linux/types.h> + +struct parse_tag { + char tag; + int mult; +}; + +unsigned long parse_tag_value(const char *str, struct parse_tag *tags); + +unsigned long convert_unit(unsigned long value, char *unit); +int unit_number__scnprintf(char *buf, size_t size, u64 n); + +#endif /* PERF_UNIT_H */ diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index 783a53fb7a4e..f90e11a555b2 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -12,6 +12,7 @@ #include "event.h" #include "perf_regs.h" #include "callchain.h" +#include "util.h" static char *debuginfo_path; diff --git a/tools/perf/util/unwind-libdw.h b/tools/perf/util/unwind-libdw.h index 58328669ed16..4a2b269a7b3b 100644 --- a/tools/perf/util/unwind-libdw.h +++ b/tools/perf/util/unwind-libdw.h @@ -2,10 +2,12 @@ #define __PERF_UNWIND_LIBDW_H #include <elfutils/libdwfl.h> -#include "event.h" -#include "thread.h" #include "unwind.h" +struct machine; +struct perf_sample; +struct thread; + bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg); struct unwind_info { diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index 6fec84dff3f7..f8455bed6e65 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -16,8 +16,10 @@ */ #include <elf.h> +#include <errno.h> #include <gelf.h> #include <fcntl.h> +#include <inttypes.h> #include <string.h> #include <unistd.h> #include <sys/mman.h> @@ -35,6 +37,7 @@ #include "util.h" #include "debug.h" #include "asm/bug.h" +#include "dso.h" extern int UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as, @@ -297,15 +300,58 @@ static int read_unwind_spec_debug_frame(struct dso *dso, int fd; u64 ofs = dso->data.debug_frame_offset; + /* debug_frame can reside in: + * - dso + * - debug pointed by symsrc_filename + * - gnu_debuglink, which doesn't necessary + * has to be pointed by symsrc_filename + */ if (ofs == 0) { fd = dso__data_get_fd(dso, machine); - if (fd < 0) - return -EINVAL; + if (fd >= 0) { + ofs = elf_section_offset(fd, ".debug_frame"); + dso__data_put_fd(dso); + } + + if (ofs <= 0) { + fd = open(dso->symsrc_filename, O_RDONLY); + if (fd >= 0) { + ofs = elf_section_offset(fd, ".debug_frame"); + close(fd); + } + } + + if (ofs <= 0) { + char *debuglink = malloc(PATH_MAX); + int ret = 0; + + ret = dso__read_binary_type_filename( + dso, DSO_BINARY_TYPE__DEBUGLINK, + machine->root_dir, debuglink, PATH_MAX); + if (!ret) { + fd = open(debuglink, O_RDONLY); + if (fd >= 0) { + ofs = elf_section_offset(fd, + ".debug_frame"); + close(fd); + } + } + if (ofs > 0) { + if (dso->symsrc_filename != NULL) { + pr_warning( + "%s: overwrite symsrc(%s,%s)\n", + __func__, + dso->symsrc_filename, + debuglink); + free(dso->symsrc_filename); + } + dso->symsrc_filename = debuglink; + } else { + free(debuglink); + } + } - /* Check the .debug_frame section for unwinding info */ - ofs = elf_section_offset(fd, ".debug_frame"); dso->data.debug_frame_offset = ofs; - dso__data_put_fd(dso); } *offset = ofs; diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h index 61fb1e90ff51..bfbdcc6198c9 100644 --- a/tools/perf/util/unwind.h +++ b/tools/perf/util/unwind.h @@ -1,10 +1,13 @@ #ifndef __UNWIND_H #define __UNWIND_H +#include <linux/compiler.h> #include <linux/types.h> -#include "event.h" -#include "symbol.h" -#include "thread.h" + +struct map; +struct perf_sample; +struct symbol; +struct thread; struct unwind_entry { struct map *map; diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 9ddd98827d12..28c9f335006c 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -3,38 +3,22 @@ #include "debug.h" #include <api/fs/fs.h> #include <sys/mman.h> +#include <sys/stat.h> #include <sys/utsname.h> -#ifdef HAVE_BACKTRACE_SUPPORT -#include <execinfo.h> -#endif +#include <dirent.h> +#include <inttypes.h> +#include <signal.h> #include <stdio.h> #include <stdlib.h> #include <string.h> #include <errno.h> #include <limits.h> -#include <byteswap.h> #include <linux/kernel.h> #include <linux/log2.h> #include <linux/time64.h> #include <unistd.h> -#include "callchain.h" #include "strlist.h" -#define CALLCHAIN_PARAM_DEFAULT \ - .mode = CHAIN_GRAPH_ABS, \ - .min_percent = 0.5, \ - .order = ORDER_CALLEE, \ - .key = CCKEY_FUNCTION, \ - .value = CCVAL_PERCENT, \ - -struct callchain_param callchain_param = { - CALLCHAIN_PARAM_DEFAULT -}; - -struct callchain_param callchain_param_default = { - CALLCHAIN_PARAM_DEFAULT -}; - /* * XXX We need to find a better place for these things... */ @@ -85,7 +69,7 @@ int mkdir_p(char *path, mode_t mode) return (stat(path, &st) && mkdir(path, mode)) ? -1 : 0; } -int rm_rf(char *path) +int rm_rf(const char *path) { DIR *dir; int ret = 0; @@ -269,28 +253,6 @@ int copyfile(const char *from, const char *to) return copyfile_mode(from, to, 0755); } -unsigned long convert_unit(unsigned long value, char *unit) -{ - *unit = ' '; - - if (value > 1000) { - value /= 1000; - *unit = 'K'; - } - - if (value > 1000) { - value /= 1000; - *unit = 'M'; - } - - if (value > 1000) { - value /= 1000; - *unit = 'G'; - } - - return value; -} - static ssize_t ion(bool is_read, int fd, void *buf, size_t n) { void *buf_start = buf; @@ -372,171 +334,6 @@ int hex2u64(const char *ptr, u64 *long_val) return p - ptr; } -/* Obtain a backtrace and print it to stdout. */ -#ifdef HAVE_BACKTRACE_SUPPORT -void dump_stack(void) -{ - void *array[16]; - size_t size = backtrace(array, ARRAY_SIZE(array)); - char **strings = backtrace_symbols(array, size); - size_t i; - - printf("Obtained %zd stack frames.\n", size); - - for (i = 0; i < size; i++) - printf("%s\n", strings[i]); - - free(strings); -} -#else -void dump_stack(void) {} -#endif - -void sighandler_dump_stack(int sig) -{ - psignal(sig, "perf"); - dump_stack(); - signal(sig, SIG_DFL); - raise(sig); -} - -int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz) -{ - u64 sec = timestamp / NSEC_PER_SEC; - u64 usec = (timestamp % NSEC_PER_SEC) / NSEC_PER_USEC; - - return scnprintf(buf, sz, "%"PRIu64".%06"PRIu64, sec, usec); -} - -unsigned long parse_tag_value(const char *str, struct parse_tag *tags) -{ - struct parse_tag *i = tags; - - while (i->tag) { - char *s; - - s = strchr(str, i->tag); - if (s) { - unsigned long int value; - char *endptr; - - value = strtoul(str, &endptr, 10); - if (s != endptr) - break; - - if (value > ULONG_MAX / i->mult) - break; - value *= i->mult; - return value; - } - i++; - } - - return (unsigned long) -1; -} - -int get_stack_size(const char *str, unsigned long *_size) -{ - char *endptr; - unsigned long size; - unsigned long max_size = round_down(USHRT_MAX, sizeof(u64)); - - size = strtoul(str, &endptr, 0); - - do { - if (*endptr) - break; - - size = round_up(size, sizeof(u64)); - if (!size || size > max_size) - break; - - *_size = size; - return 0; - - } while (0); - - pr_err("callchain: Incorrect stack dump size (max %ld): %s\n", - max_size, str); - return -1; -} - -int parse_callchain_record(const char *arg, struct callchain_param *param) -{ - char *tok, *name, *saveptr = NULL; - char *buf; - int ret = -1; - - /* We need buffer that we know we can write to. */ - buf = malloc(strlen(arg) + 1); - if (!buf) - return -ENOMEM; - - strcpy(buf, arg); - - tok = strtok_r((char *)buf, ",", &saveptr); - name = tok ? : (char *)buf; - - do { - /* Framepointer style */ - if (!strncmp(name, "fp", sizeof("fp"))) { - if (!strtok_r(NULL, ",", &saveptr)) { - param->record_mode = CALLCHAIN_FP; - ret = 0; - } else - pr_err("callchain: No more arguments " - "needed for --call-graph fp\n"); - break; - - /* Dwarf style */ - } else if (!strncmp(name, "dwarf", sizeof("dwarf"))) { - const unsigned long default_stack_dump_size = 8192; - - ret = 0; - param->record_mode = CALLCHAIN_DWARF; - param->dump_size = default_stack_dump_size; - - tok = strtok_r(NULL, ",", &saveptr); - if (tok) { - unsigned long size = 0; - - ret = get_stack_size(tok, &size); - param->dump_size = size; - } - } else if (!strncmp(name, "lbr", sizeof("lbr"))) { - if (!strtok_r(NULL, ",", &saveptr)) { - param->record_mode = CALLCHAIN_LBR; - ret = 0; - } else - pr_err("callchain: No more arguments " - "needed for --call-graph lbr\n"); - break; - } else { - pr_err("callchain: Unknown --call-graph option " - "value: %s\n", arg); - break; - } - - } while (0); - - free(buf); - return ret; -} - -const char *get_filename_for_perf_kvm(void) -{ - const char *filename; - - if (perf_host && !perf_guest) - filename = strdup("perf.data.host"); - else if (!perf_host && perf_guest) - filename = strdup("perf.data.guest"); - else - filename = strdup("perf.data.kvm"); - - return filename; -} - int perf_event_paranoid(void) { int value; @@ -547,27 +344,6 @@ int perf_event_paranoid(void) return value; } -void mem_bswap_32(void *src, int byte_size) -{ - u32 *m = src; - while (byte_size > 0) { - *m = bswap_32(*m); - byte_size -= sizeof(u32); - ++m; - } -} - -void mem_bswap_64(void *src, int byte_size) -{ - u64 *m = src; - - while (byte_size > 0) { - *m = bswap_64(*m); - byte_size -= sizeof(u64); - ++m; - } -} - bool find_process(const char *name) { size_t len = strlen(name); @@ -696,7 +472,8 @@ const char *perf_tip(const char *dirpath) tips = strlist__new("tips.txt", &conf); if (tips == NULL) - return errno == ENOENT ? NULL : "Tip: get more memory! ;-p"; + return errno == ENOENT ? NULL : + "Tip: check path of tips.txt or get more memory! ;-p"; if (strlist__nr_entries(tips) == 0) goto out; @@ -710,82 +487,3 @@ out: return tip; } - -bool is_regular_file(const char *file) -{ - struct stat st; - - if (stat(file, &st)) - return false; - - return S_ISREG(st.st_mode); -} - -int fetch_current_timestamp(char *buf, size_t sz) -{ - struct timeval tv; - struct tm tm; - char dt[32]; - - if (gettimeofday(&tv, NULL) || !localtime_r(&tv.tv_sec, &tm)) - return -1; - - if (!strftime(dt, sizeof(dt), "%Y%m%d%H%M%S", &tm)) - return -1; - - scnprintf(buf, sz, "%s%02u", dt, (unsigned)tv.tv_usec / 10000); - - return 0; -} - -void print_binary(unsigned char *data, size_t len, - size_t bytes_per_line, print_binary_t printer, - void *extra) -{ - size_t i, j, mask; - - if (!printer) - return; - - bytes_per_line = roundup_pow_of_two(bytes_per_line); - mask = bytes_per_line - 1; - - printer(BINARY_PRINT_DATA_BEGIN, 0, extra); - for (i = 0; i < len; i++) { - if ((i & mask) == 0) { - printer(BINARY_PRINT_LINE_BEGIN, -1, extra); - printer(BINARY_PRINT_ADDR, i, extra); - } - - printer(BINARY_PRINT_NUM_DATA, data[i], extra); - - if (((i & mask) == mask) || i == len - 1) { - for (j = 0; j < mask-(i & mask); j++) - printer(BINARY_PRINT_NUM_PAD, -1, extra); - - printer(BINARY_PRINT_SEP, i, extra); - for (j = i & ~mask; j <= i; j++) - printer(BINARY_PRINT_CHAR_DATA, data[j], extra); - for (j = 0; j < mask-(i & mask); j++) - printer(BINARY_PRINT_CHAR_PAD, i, extra); - printer(BINARY_PRINT_LINE_END, -1, extra); - } - } - printer(BINARY_PRINT_DATA_END, -1, extra); -} - -int is_printable_array(char *p, unsigned int len) -{ - unsigned int i; - - if (!p || !len || p[len - 1] != 0) - return 0; - - len--; - - for (i = 0; i < len; i++) { - if (!isprint(p[i]) && !isspace(p[i])) - return 0; - } - return 1; -} diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 1d639e38aa82..5dfb9bb6482d 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -1,125 +1,17 @@ #ifndef GIT_COMPAT_UTIL_H #define GIT_COMPAT_UTIL_H -#ifndef FLEX_ARRAY -/* - * See if our compiler is known to support flexible array members. - */ -#if defined(__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) -# define FLEX_ARRAY /* empty */ -#elif defined(__GNUC__) -# if (__GNUC__ >= 3) -# define FLEX_ARRAY /* empty */ -# else -# define FLEX_ARRAY 0 /* older GNU extension */ -# endif -#endif - -/* - * Otherwise, default to safer but a bit wasteful traditional style - */ -#ifndef FLEX_ARRAY -# define FLEX_ARRAY 1 -#endif -#endif - -#define ARRAY_SIZE(x) (sizeof(x)/sizeof(x[0])) - -#ifdef __GNUC__ -#define TYPEOF(x) (__typeof__(x)) -#else -#define TYPEOF(x) -#endif - -#define MSB(x, bits) ((x) & TYPEOF(x)(~0ULL << (sizeof(x) * 8 - (bits)))) -#define HAS_MULTI_BITS(i) ((i) & ((i) - 1)) /* checks if an integer has more than 1 bit set */ - -/* Approximation of the length of the decimal representation of this type. */ -#define decimal_length(x) ((int)(sizeof(x) * 2.56 + 0.5) + 1) - #define _ALL_SOURCE 1 #define _BSD_SOURCE 1 /* glibc 2.20 deprecates _BSD_SOURCE in favour of _DEFAULT_SOURCE */ #define _DEFAULT_SOURCE 1 -#define HAS_BOOL -#include <unistd.h> -#include <stdio.h> -#include <sys/stat.h> -#include <sys/statfs.h> #include <fcntl.h> #include <stdbool.h> #include <stddef.h> #include <stdlib.h> #include <stdarg.h> -#include <string.h> -#include <term.h> -#include <errno.h> -#include <limits.h> -#include <sys/param.h> -#include <sys/types.h> -#include <dirent.h> -#include <sys/time.h> -#include <time.h> -#include <signal.h> -#include <fnmatch.h> -#include <assert.h> -#include <regex.h> -#include <utime.h> -#include <sys/wait.h> -#include <poll.h> -#include <sys/socket.h> -#include <sys/ioctl.h> -#include <inttypes.h> -#include <linux/kernel.h> #include <linux/types.h> -#include <sys/ttydefaults.h> -#include <api/fs/tracing_path.h> -#include <termios.h> -#include <linux/bitops.h> -#include <termios.h> -#include "strlist.h" - -extern const char *graph_line; -extern const char *graph_dotted_line; -extern const char *spaces; -extern const char *dots; -extern char buildid_dir[]; - -/* On most systems <limits.h> would have given us this, but - * not on some systems (e.g. GNU/Hurd). - */ -#ifndef PATH_MAX -#define PATH_MAX 4096 -#endif - -#ifndef PRIuMAX -#define PRIuMAX "llu" -#endif - -#ifndef PRIu32 -#define PRIu32 "u" -#endif - -#ifndef PRIx32 -#define PRIx32 "x" -#endif - -#ifndef PATH_SEP -#define PATH_SEP ':' -#endif - -#ifndef STRIP_EXTENSION -#define STRIP_EXTENSION "" -#endif - -#ifndef has_dos_drive_prefix -#define has_dos_drive_prefix(path) 0 -#endif - -#ifndef is_dir_sep -#define is_dir_sep(c) ((c) == '/') -#endif #ifdef __GNUC__ #define NORETURN __attribute__((__noreturn__)) @@ -130,8 +22,6 @@ extern char buildid_dir[]; #endif #endif -#define PERF_GTK_DSO "libperf-gtk.so" - /* General helper functions */ void usage(const char *err) NORETURN; void die(const char *err, ...) NORETURN __attribute__((format (printf, 1, 2))); @@ -140,25 +30,6 @@ void warning(const char *err, ...) __attribute__((format (printf, 1, 2))); void set_warning_routine(void (*routine)(const char *err, va_list params)); -int prefixcmp(const char *str, const char *prefix); -void set_buildid_dir(const char *dir); - -#ifdef __GLIBC_PREREQ -#if __GLIBC_PREREQ(2, 1) -#define HAVE_STRCHRNUL -#endif -#endif - -#ifndef HAVE_STRCHRNUL -#define strchrnul gitstrchrnul -static inline char *gitstrchrnul(const char *s, int c) -{ - while (*s && *s != c) - s++; - return (char *)s; -} -#endif - static inline void *zalloc(size_t size) { return calloc(1, size); @@ -166,162 +37,28 @@ static inline void *zalloc(size_t size) #define zfree(ptr) ({ free(*ptr); *ptr = NULL; }) -/* Sane ctype - no locale, and works with signed chars */ -#undef isascii -#undef isspace -#undef isdigit -#undef isxdigit -#undef isalpha -#undef isprint -#undef isalnum -#undef islower -#undef isupper -#undef tolower -#undef toupper - -extern unsigned char sane_ctype[256]; -#define GIT_SPACE 0x01 -#define GIT_DIGIT 0x02 -#define GIT_ALPHA 0x04 -#define GIT_GLOB_SPECIAL 0x08 -#define GIT_REGEX_SPECIAL 0x10 -#define GIT_PRINT_EXTRA 0x20 -#define GIT_PRINT 0x3E -#define sane_istest(x,mask) ((sane_ctype[(unsigned char)(x)] & (mask)) != 0) -#define isascii(x) (((x) & ~0x7f) == 0) -#define isspace(x) sane_istest(x,GIT_SPACE) -#define isdigit(x) sane_istest(x,GIT_DIGIT) -#define isxdigit(x) \ - (sane_istest(toupper(x), GIT_ALPHA | GIT_DIGIT) && toupper(x) < 'G') -#define isalpha(x) sane_istest(x,GIT_ALPHA) -#define isalnum(x) sane_istest(x,GIT_ALPHA | GIT_DIGIT) -#define isprint(x) sane_istest(x,GIT_PRINT) -#define islower(x) (sane_istest(x,GIT_ALPHA) && (x & 0x20)) -#define isupper(x) (sane_istest(x,GIT_ALPHA) && !(x & 0x20)) -#define tolower(x) sane_case((unsigned char)(x), 0x20) -#define toupper(x) sane_case((unsigned char)(x), 0) - -static inline int sane_case(int x, int high) -{ - if (sane_istest(x, GIT_ALPHA)) - x = (x & ~0x20) | high; - return x; -} +struct dirent; +struct strlist; int mkdir_p(char *path, mode_t mode); -int rm_rf(char *path); +int rm_rf(const char *path); struct strlist *lsdir(const char *name, bool (*filter)(const char *, struct dirent *)); bool lsdir_no_dot_filter(const char *name, struct dirent *d); int copyfile(const char *from, const char *to); int copyfile_mode(const char *from, const char *to, mode_t mode); int copyfile_offset(int fromfd, loff_t from_ofs, int tofd, loff_t to_ofs, u64 size); -s64 perf_atoll(const char *str); -char **argv_split(const char *str, int *argcp); -void argv_free(char **argv); -bool strglobmatch(const char *str, const char *pat); -bool strglobmatch_nocase(const char *str, const char *pat); -bool strlazymatch(const char *str, const char *pat); -static inline bool strisglob(const char *str) -{ - return strpbrk(str, "*?[") != NULL; -} -int strtailcmp(const char *s1, const char *s2); -char *strxfrchar(char *s, char from, char to); -unsigned long convert_unit(unsigned long value, char *unit); ssize_t readn(int fd, void *buf, size_t n); ssize_t writen(int fd, void *buf, size_t n); -struct perf_event_attr; - -void event_attr_init(struct perf_event_attr *attr); - -#define _STR(x) #x -#define STR(x) _STR(x) - size_t hex_width(u64 v); int hex2u64(const char *ptr, u64 *val); -char *ltrim(char *s); -char *rtrim(char *s); - -static inline char *trim(char *s) -{ - return ltrim(rtrim(s)); -} - -void dump_stack(void); -void sighandler_dump_stack(int sig); - extern unsigned int page_size; extern int cacheline_size; -extern int sysctl_perf_event_max_stack; -extern int sysctl_perf_event_max_contexts_per_stack; - -struct parse_tag { - char tag; - int mult; -}; - -unsigned long parse_tag_value(const char *str, struct parse_tag *tags); - -#define SRCLINE_UNKNOWN ((char *) "??:0") - -static inline int path__join(char *bf, size_t size, - const char *path1, const char *path2) -{ - return scnprintf(bf, size, "%s%s%s", path1, path1[0] ? "/" : "", path2); -} - -static inline int path__join3(char *bf, size_t size, - const char *path1, const char *path2, - const char *path3) -{ - return scnprintf(bf, size, "%s%s%s%s%s", - path1, path1[0] ? "/" : "", - path2, path2[0] ? "/" : "", path3); -} - -struct dso; -struct symbol; -extern bool srcline_full_filename; -char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym, - bool show_sym); -char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym, - bool show_sym, bool unwind_inlines); -void free_srcline(char *srcline); - -int perf_event_paranoid(void); - -void mem_bswap_64(void *src, int byte_size); -void mem_bswap_32(void *src, int byte_size); - -const char *get_filename_for_perf_kvm(void); bool find_process(const char *name); -#ifdef HAVE_ZLIB_SUPPORT -int gzip_decompress_to_file(const char *input, int output_fd); -#endif - -#ifdef HAVE_LZMA_SUPPORT -int lzma_decompress_to_file(const char *input, int output_fd); -#endif - -char *asprintf_expr_inout_ints(const char *var, bool in, size_t nints, int *ints); - -static inline char *asprintf_expr_in_ints(const char *var, size_t nints, int *ints) -{ - return asprintf_expr_inout_ints(var, true, nints, ints); -} - -static inline char *asprintf_expr_not_in_ints(const char *var, size_t nints, int *ints) -{ - return asprintf_expr_inout_ints(var, false, nints, ints); -} - -int get_stack_size(const char *str, unsigned long *_size); - int fetch_kernel_version(unsigned int *puint, char *str, size_t str_sz); #define KVER_VERSION(x) (((x) >> 16) & 0xff) @@ -331,36 +68,9 @@ int fetch_kernel_version(unsigned int *puint, #define KVER_PARAM(x) KVER_VERSION(x), KVER_PATCHLEVEL(x), KVER_SUBLEVEL(x) const char *perf_tip(const char *dirpath); -bool is_regular_file(const char *file); -int fetch_current_timestamp(char *buf, size_t sz); -enum binary_printer_ops { - BINARY_PRINT_DATA_BEGIN, - BINARY_PRINT_LINE_BEGIN, - BINARY_PRINT_ADDR, - BINARY_PRINT_NUM_DATA, - BINARY_PRINT_NUM_PAD, - BINARY_PRINT_SEP, - BINARY_PRINT_CHAR_DATA, - BINARY_PRINT_CHAR_PAD, - BINARY_PRINT_LINE_END, - BINARY_PRINT_DATA_END, -}; - -typedef void (*print_binary_t)(enum binary_printer_ops, - unsigned int val, - void *extra); - -void print_binary(unsigned char *data, size_t len, - size_t bytes_per_line, print_binary_t printer, - void *extra); - -#if !defined(__GLIBC__) && !defined(__ANDROID__) -extern int sched_getcpu(void); +#ifndef HAVE_SCHED_GETCPU_SUPPORT +int sched_getcpu(void); #endif -int is_printable_array(char *p, unsigned int len); - -int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz); - #endif /* GIT_COMPAT_UTIL_H */ diff --git a/tools/perf/util/values.c b/tools/perf/util/values.c index 5074be4ed467..5de2e15e2eda 100644 --- a/tools/perf/util/values.c +++ b/tools/perf/util/values.c @@ -1,4 +1,7 @@ +#include <inttypes.h> +#include <stdio.h> #include <stdlib.h> +#include <errno.h> #include "util.h" #include "values.h" @@ -108,24 +111,45 @@ static int perf_read_values__findnew_thread(struct perf_read_values *values, return i; } -static void perf_read_values__enlarge_counters(struct perf_read_values *values) +static int perf_read_values__enlarge_counters(struct perf_read_values *values) { - int i; + char **countername; + int i, counters_max = values->counters_max * 2; + u64 *counterrawid = realloc(values->counterrawid, counters_max * sizeof(*values->counterrawid)); + + if (!counterrawid) { + pr_debug("failed to enlarge read_values rawid array"); + goto out_enomem; + } - values->counters_max *= 2; - values->counterrawid = realloc(values->counterrawid, - values->counters_max * sizeof(*values->counterrawid)); - values->countername = realloc(values->countername, - values->counters_max * sizeof(*values->countername)); - if (!values->counterrawid || !values->countername) - die("failed to enlarge read_values counters arrays"); + countername = realloc(values->countername, counters_max * sizeof(*values->countername)); + if (!countername) { + pr_debug("failed to enlarge read_values rawid array"); + goto out_free_rawid; + } for (i = 0; i < values->threads; i++) { - values->value[i] = realloc(values->value[i], - values->counters_max * sizeof(**values->value)); - if (!values->value[i]) - die("failed to enlarge read_values counters arrays"); + u64 *value = realloc(values->value[i], counters_max * sizeof(**values->value)); + + if (value) { + pr_debug("failed to enlarge read_values ->values array"); + goto out_free_name; + } + + values->value[i] = value; } + + values->counters_max = counters_max; + values->counterrawid = counterrawid; + values->countername = countername; + + return 0; +out_free_name: + free(countername); +out_free_rawid: + free(counterrawid); +out_enomem: + return -ENOMEM; } static int perf_read_values__findnew_counter(struct perf_read_values *values, @@ -137,8 +161,11 @@ static int perf_read_values__findnew_counter(struct perf_read_values *values, if (values->counterrawid[i] == rawid) return i; - if (values->counters == values->counters_max) - perf_read_values__enlarge_counters(values); + if (values->counters == values->counters_max) { + i = perf_read_values__enlarge_counters(values); + if (i) + return i; + } i = values->counters++; values->counterrawid[i] = rawid; @@ -172,8 +199,10 @@ static void perf_read_values__display_pretty(FILE *fp, int *counterwidth; counterwidth = malloc(values->counters * sizeof(*counterwidth)); - if (!counterwidth) - die("failed to allocate counterwidth array"); + if (!counterwidth) { + fprintf(fp, "INTERNAL ERROR: Failed to allocate counterwidth array\n"); + return; + } tidwidth = 3; pidwidth = 3; for (j = 0; j < values->counters; j++) diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c index 7bdcad484225..d3c39eec89a8 100644 --- a/tools/perf/util/vdso.c +++ b/tools/perf/util/vdso.c @@ -1,4 +1,4 @@ - +#include <errno.h> #include <unistd.h> #include <stdio.h> #include <string.h> diff --git a/tools/perf/util/xyarray.c b/tools/perf/util/xyarray.c index c10ba41ef3f6..7251fdbabced 100644 --- a/tools/perf/util/xyarray.c +++ b/tools/perf/util/xyarray.c @@ -1,5 +1,7 @@ #include "xyarray.h" #include "util.h" +#include <stdlib.h> +#include <string.h> struct xyarray *xyarray__new(int xlen, int ylen, size_t entry_size) { diff --git a/tools/perf/util/zlib.c b/tools/perf/util/zlib.c index 495a449fc25c..1329d843eb7b 100644 --- a/tools/perf/util/zlib.c +++ b/tools/perf/util/zlib.c @@ -4,6 +4,7 @@ #include <sys/mman.h> #include <zlib.h> +#include "util/compress.h" #include "util/util.h" #include "util/debug.h" diff --git a/tools/power/acpi/common/cmfsize.c b/tools/power/acpi/common/cmfsize.c index bc82596d7354..5b38dc2fec4f 100644 --- a/tools/power/acpi/common/cmfsize.c +++ b/tools/power/acpi/common/cmfsize.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2016, Intel Corp. + * Copyright (C) 2000 - 2017, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/tools/power/acpi/common/getopt.c b/tools/power/acpi/common/getopt.c index 3919970f5aea..6e78413bb2cb 100644 --- a/tools/power/acpi/common/getopt.c +++ b/tools/power/acpi/common/getopt.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2016, Intel Corp. + * Copyright (C) 2000 - 2017, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c b/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c index 546cf4a503b7..82a2ff896a95 100644 --- a/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c +++ b/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2016, Intel Corp. + * Copyright (C) 2000 - 2017, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/tools/power/acpi/os_specific/service_layers/osunixdir.c b/tools/power/acpi/os_specific/service_layers/osunixdir.c index 66c4badf03e5..ea14eaeb268f 100644 --- a/tools/power/acpi/os_specific/service_layers/osunixdir.c +++ b/tools/power/acpi/os_specific/service_layers/osunixdir.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2016, Intel Corp. + * Copyright (C) 2000 - 2017, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/tools/power/acpi/os_specific/service_layers/osunixmap.c b/tools/power/acpi/os_specific/service_layers/osunixmap.c index cbfbce18783d..cf9b5a54df92 100644 --- a/tools/power/acpi/os_specific/service_layers/osunixmap.c +++ b/tools/power/acpi/os_specific/service_layers/osunixmap.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2016, Intel Corp. + * Copyright (C) 2000 - 2017, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/tools/power/acpi/os_specific/service_layers/osunixxf.c b/tools/power/acpi/os_specific/service_layers/osunixxf.c index 10648aaf6164..c04e8fea2c60 100644 --- a/tools/power/acpi/os_specific/service_layers/osunixxf.c +++ b/tools/power/acpi/os_specific/service_layers/osunixxf.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2016, Intel Corp. + * Copyright (C) 2000 - 2017, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -318,6 +318,28 @@ acpi_os_physical_table_override(struct acpi_table_header *existing_table, /****************************************************************************** * + * FUNCTION: acpi_os_enter_sleep + * + * PARAMETERS: sleep_state - Which sleep state to enter + * rega_value - Register A value + * regb_value - Register B value + * + * RETURN: Status + * + * DESCRIPTION: A hook before writing sleep registers to enter the sleep + * state. Return AE_CTRL_TERMINATE to skip further sleep register + * writes. + * + *****************************************************************************/ + +acpi_status acpi_os_enter_sleep(u8 sleep_state, u32 rega_value, u32 regb_value) +{ + + return (AE_OK); +} + +/****************************************************************************** + * * FUNCTION: acpi_os_redirect_output * * PARAMETERS: destination - An open file handle/pointer diff --git a/tools/power/acpi/tools/acpidump/acpidump.h b/tools/power/acpi/tools/acpidump/acpidump.h index 00423fc45e7c..d6aa40fce2b1 100644 --- a/tools/power/acpi/tools/acpidump/acpidump.h +++ b/tools/power/acpi/tools/acpidump/acpidump.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2016, Intel Corp. + * Copyright (C) 2000 - 2017, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/tools/power/acpi/tools/acpidump/apdump.c b/tools/power/acpi/tools/acpidump/apdump.c index 9031be1afe63..60df1fbd4a77 100644 --- a/tools/power/acpi/tools/acpidump/apdump.c +++ b/tools/power/acpi/tools/acpidump/apdump.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2016, Intel Corp. + * Copyright (C) 2000 - 2017, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/tools/power/acpi/tools/acpidump/apfiles.c b/tools/power/acpi/tools/acpidump/apfiles.c index dd5b861dc4a8..31b5a7f74015 100644 --- a/tools/power/acpi/tools/acpidump/apfiles.c +++ b/tools/power/acpi/tools/acpidump/apfiles.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2016, Intel Corp. + * Copyright (C) 2000 - 2017, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/tools/power/acpi/tools/acpidump/apmain.c b/tools/power/acpi/tools/acpidump/apmain.c index 7ff46be908f0..dd82afa897bd 100644 --- a/tools/power/acpi/tools/acpidump/apmain.c +++ b/tools/power/acpi/tools/acpidump/apmain.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2016, Intel Corp. + * Copyright (C) 2000 - 2017, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/tools/power/cpupower/utils/cpufreq-info.c b/tools/power/cpupower/utils/cpufreq-info.c index 590d12a25f6e..3e701f0e9c14 100644 --- a/tools/power/cpupower/utils/cpufreq-info.c +++ b/tools/power/cpupower/utils/cpufreq-info.c @@ -285,20 +285,24 @@ static int get_freq_hardware(unsigned int cpu, unsigned int human) /* --hwlimits / -l */ -static int get_hardware_limits(unsigned int cpu) +static int get_hardware_limits(unsigned int cpu, unsigned int human) { unsigned long min, max; - printf(_(" hardware limits: ")); if (cpufreq_get_hardware_limits(cpu, &min, &max)) { printf(_("Not Available\n")); return -EINVAL; } - print_speed(min); - printf(" - "); - print_speed(max); - printf("\n"); + if (human) { + printf(_(" hardware limits: ")); + print_speed(min); + printf(" - "); + print_speed(max); + printf("\n"); + } else { + printf("%lu %lu\n", min, max); + } return 0; } @@ -456,7 +460,7 @@ static void debug_output_one(unsigned int cpu) get_related_cpus(cpu); get_affected_cpus(cpu); get_latency(cpu, 1); - get_hardware_limits(cpu); + get_hardware_limits(cpu, 1); freqs = cpufreq_get_available_frequencies(cpu); if (freqs) { @@ -622,7 +626,7 @@ int cmd_freq_info(int argc, char **argv) ret = get_driver(cpu); break; case 'l': - ret = get_hardware_limits(cpu); + ret = get_hardware_limits(cpu, human); break; case 'w': ret = get_freq_hardware(cpu, human); @@ -639,7 +643,6 @@ int cmd_freq_info(int argc, char **argv) } if (ret) return ret; - printf("\n"); } return ret; } diff --git a/tools/power/cpupower/utils/helpers/cpuid.c b/tools/power/cpupower/utils/helpers/cpuid.c index 93b0aa74ca03..39c2c7d067bb 100644 --- a/tools/power/cpupower/utils/helpers/cpuid.c +++ b/tools/power/cpupower/utils/helpers/cpuid.c @@ -156,6 +156,7 @@ out: */ case 0x2C: /* Westmere EP - Gulftown */ cpu_info->caps |= CPUPOWER_CAP_HAS_TURBO_RATIO; + break; case 0x2A: /* SNB */ case 0x2D: /* SNB Xeon */ case 0x3A: /* IVB */ diff --git a/tools/power/pm-graph/Makefile b/tools/power/pm-graph/Makefile new file mode 100644 index 000000000000..4d0ccc89e6c6 --- /dev/null +++ b/tools/power/pm-graph/Makefile @@ -0,0 +1,28 @@ +PREFIX ?= /usr +DESTDIR ?= + +all: + @echo "Nothing to build" + +install : + install -d $(DESTDIR)$(PREFIX)/lib/pm-graph + install analyze_suspend.py $(DESTDIR)$(PREFIX)/lib/pm-graph + install analyze_boot.py $(DESTDIR)$(PREFIX)/lib/pm-graph + + ln -s $(DESTDIR)$(PREFIX)/lib/pm-graph/analyze_boot.py $(DESTDIR)$(PREFIX)/bin/bootgraph + ln -s $(DESTDIR)$(PREFIX)/lib/pm-graph/analyze_suspend.py $(DESTDIR)$(PREFIX)/bin/sleepgraph + + install -d $(DESTDIR)$(PREFIX)/share/man/man8 + install bootgraph.8 $(DESTDIR)$(PREFIX)/share/man/man8 + install sleepgraph.8 $(DESTDIR)$(PREFIX)/share/man/man8 + +uninstall : + rm $(DESTDIR)$(PREFIX)/share/man/man8/bootgraph.8 + rm $(DESTDIR)$(PREFIX)/share/man/man8/sleepgraph.8 + + rm $(DESTDIR)$(PREFIX)/bin/bootgraph + rm $(DESTDIR)$(PREFIX)/bin/sleepgraph + + rm $(DESTDIR)$(PREFIX)/lib/pm-graph/analyze_boot.py + rm $(DESTDIR)$(PREFIX)/lib/pm-graph/analyze_suspend.py + rmdir $(DESTDIR)$(PREFIX)/lib/pm-graph diff --git a/tools/power/pm-graph/analyze_boot.py b/tools/power/pm-graph/analyze_boot.py new file mode 100755 index 000000000000..3e1dcbbf1adc --- /dev/null +++ b/tools/power/pm-graph/analyze_boot.py @@ -0,0 +1,824 @@ +#!/usr/bin/python +# +# Tool for analyzing boot timing +# Copyright (c) 2013, Intel Corporation. +# +# This program is free software; you can redistribute it and/or modify it +# under the terms and conditions of the GNU General Public License, +# version 2, as published by the Free Software Foundation. +# +# This program is distributed in the hope it will be useful, but WITHOUT +# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or +# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for +# more details. +# +# Authors: +# Todd Brandt <todd.e.brandt@linux.intel.com> +# +# Description: +# This tool is designed to assist kernel and OS developers in optimizing +# their linux stack's boot time. It creates an html representation of +# the kernel boot timeline up to the start of the init process. +# + +# ----------------- LIBRARIES -------------------- + +import sys +import time +import os +import string +import re +import platform +import shutil +from datetime import datetime, timedelta +from subprocess import call, Popen, PIPE +import analyze_suspend as aslib + +# ----------------- CLASSES -------------------- + +# Class: SystemValues +# Description: +# A global, single-instance container used to +# store system values and test parameters +class SystemValues(aslib.SystemValues): + title = 'BootGraph' + version = 2.0 + hostname = 'localhost' + testtime = '' + kernel = '' + dmesgfile = '' + ftracefile = '' + htmlfile = 'bootgraph.html' + outfile = '' + phoronix = False + addlogs = False + useftrace = False + usedevsrc = True + suspendmode = 'boot' + max_graph_depth = 2 + graph_filter = 'do_one_initcall' + reboot = False + manual = False + iscronjob = False + timeformat = '%.6f' + def __init__(self): + if('LOG_FILE' in os.environ and 'TEST_RESULTS_IDENTIFIER' in os.environ): + self.phoronix = True + self.addlogs = True + self.outfile = os.environ['LOG_FILE'] + self.htmlfile = os.environ['LOG_FILE'] + self.hostname = platform.node() + self.testtime = datetime.now().strftime('%Y-%m-%d_%H:%M:%S') + if os.path.exists('/proc/version'): + fp = open('/proc/version', 'r') + val = fp.read().strip() + fp.close() + self.kernel = self.kernelVersion(val) + else: + self.kernel = 'unknown' + def kernelVersion(self, msg): + return msg.split()[2] + def kernelParams(self): + cmdline = 'initcall_debug log_buf_len=32M' + if self.useftrace: + cmdline += ' trace_buf_size=128M trace_clock=global '\ + 'trace_options=nooverwrite,funcgraph-abstime,funcgraph-cpu,'\ + 'funcgraph-duration,funcgraph-proc,funcgraph-tail,'\ + 'nofuncgraph-overhead,context-info,graph-time '\ + 'ftrace=function_graph '\ + 'ftrace_graph_max_depth=%d '\ + 'ftrace_graph_filter=%s' % \ + (self.max_graph_depth, self.graph_filter) + return cmdline + def setGraphFilter(self, val): + fp = open(self.tpath+'available_filter_functions') + master = fp.read().split('\n') + fp.close() + for i in val.split(','): + func = i.strip() + if func not in master: + doError('function "%s" not available for ftrace' % func) + self.graph_filter = val + def cronjobCmdString(self): + cmdline = '%s -cronjob' % os.path.abspath(sys.argv[0]) + args = iter(sys.argv[1:]) + for arg in args: + if arg in ['-h', '-v', '-cronjob', '-reboot']: + continue + elif arg in ['-o', '-dmesg', '-ftrace', '-filter']: + args.next() + continue + cmdline += ' '+arg + if self.graph_filter != 'do_one_initcall': + cmdline += ' -filter "%s"' % self.graph_filter + cmdline += ' -o "%s"' % os.path.abspath(self.htmlfile) + return cmdline + def manualRebootRequired(self): + cmdline = self.kernelParams() + print 'To generate a new timeline manually, follow these steps:\n' + print '1. Add the CMDLINE string to your kernel command line.' + print '2. Reboot the system.' + print '3. After reboot, re-run this tool with the same arguments but no command (w/o -reboot or -manual).\n' + print 'CMDLINE="%s"' % cmdline + sys.exit() + +sysvals = SystemValues() + +# Class: Data +# Description: +# The primary container for test data. +class Data(aslib.Data): + dmesg = {} # root data structure + start = 0.0 # test start + end = 0.0 # test end + dmesgtext = [] # dmesg text file in memory + testnumber = 0 + idstr = '' + html_device_id = 0 + valid = False + initstart = 0.0 + boottime = '' + phases = ['boot'] + do_one_initcall = False + def __init__(self, num): + self.testnumber = num + self.idstr = 'a' + self.dmesgtext = [] + self.dmesg = { + 'boot': {'list': dict(), 'start': -1.0, 'end': -1.0, 'row': 0, 'color': '#dddddd'} + } + def deviceTopology(self): + return '' + def newAction(self, phase, name, start, end, ret, ulen): + # new device callback for a specific phase + self.html_device_id += 1 + devid = '%s%d' % (self.idstr, self.html_device_id) + list = self.dmesg[phase]['list'] + length = -1.0 + if(start >= 0 and end >= 0): + length = end - start + i = 2 + origname = name + while(name in list): + name = '%s[%d]' % (origname, i) + i += 1 + list[name] = {'name': name, 'start': start, 'end': end, + 'pid': 0, 'length': length, 'row': 0, 'id': devid, + 'ret': ret, 'ulen': ulen } + return name + def deviceMatch(self, cg): + if cg.end - cg.start == 0: + return True + list = self.dmesg['boot']['list'] + for devname in list: + dev = list[devname] + if cg.name == 'do_one_initcall': + if(cg.start <= dev['start'] and cg.end >= dev['end'] and dev['length'] > 0): + dev['ftrace'] = cg + self.do_one_initcall = True + return True + else: + if(cg.start > dev['start'] and cg.end < dev['end']): + if 'ftraces' not in dev: + dev['ftraces'] = [] + dev['ftraces'].append(cg) + return True + return False + +# ----------------- FUNCTIONS -------------------- + +# Function: loadKernelLog +# Description: +# Load a raw kernel log from dmesg +def loadKernelLog(): + data = Data(0) + data.dmesg['boot']['start'] = data.start = ktime = 0.0 + sysvals.stamp = { + 'time': datetime.now().strftime('%B %d %Y, %I:%M:%S %p'), + 'host': sysvals.hostname, + 'mode': 'boot', 'kernel': ''} + + devtemp = dict() + if(sysvals.dmesgfile): + lf = open(sysvals.dmesgfile, 'r') + else: + lf = Popen('dmesg', stdout=PIPE).stdout + for line in lf: + line = line.replace('\r\n', '') + idx = line.find('[') + if idx > 1: + line = line[idx:] + m = re.match('[ \t]*(\[ *)(?P<ktime>[0-9\.]*)(\]) (?P<msg>.*)', line) + if(not m): + continue + ktime = float(m.group('ktime')) + if(ktime > 120): + break + msg = m.group('msg') + data.end = data.initstart = ktime + data.dmesgtext.append(line) + if(ktime == 0.0 and re.match('^Linux version .*', msg)): + if(not sysvals.stamp['kernel']): + sysvals.stamp['kernel'] = sysvals.kernelVersion(msg) + continue + m = re.match('.* setting system clock to (?P<t>.*) UTC.*', msg) + if(m): + bt = datetime.strptime(m.group('t'), '%Y-%m-%d %H:%M:%S') + bt = bt - timedelta(seconds=int(ktime)) + data.boottime = bt.strftime('%Y-%m-%d_%H:%M:%S') + sysvals.stamp['time'] = bt.strftime('%B %d %Y, %I:%M:%S %p') + continue + m = re.match('^calling *(?P<f>.*)\+.*', msg) + if(m): + devtemp[m.group('f')] = ktime + continue + m = re.match('^initcall *(?P<f>.*)\+.* returned (?P<r>.*) after (?P<t>.*) usecs', msg) + if(m): + data.valid = True + f, r, t = m.group('f', 'r', 't') + if(f in devtemp): + data.newAction('boot', f, devtemp[f], ktime, int(r), int(t)) + data.end = ktime + del devtemp[f] + continue + if(re.match('^Freeing unused kernel memory.*', msg)): + break + + data.dmesg['boot']['end'] = data.end + lf.close() + return data + +# Function: loadTraceLog +# Description: +# Check if trace is available and copy to a temp file +def loadTraceLog(data): + # load the data to a temp file if none given + if not sysvals.ftracefile: + lib = aslib.sysvals + aslib.rootCheck(True) + if not lib.verifyFtrace(): + doError('ftrace not available') + if lib.fgetVal('current_tracer').strip() != 'function_graph': + doError('ftrace not configured for a boot callgraph') + sysvals.ftracefile = '/tmp/boot_ftrace.%s.txt' % os.getpid() + call('cat '+lib.tpath+'trace > '+sysvals.ftracefile, shell=True) + if not sysvals.ftracefile: + doError('No trace data available') + + # parse the trace log + ftemp = dict() + tp = aslib.TestProps() + tp.setTracerType('function_graph') + tf = open(sysvals.ftracefile, 'r') + for line in tf: + if line[0] == '#': + continue + m = re.match(tp.ftrace_line_fmt, line.strip()) + if(not m): + continue + m_time, m_proc, m_pid, m_msg, m_dur = \ + m.group('time', 'proc', 'pid', 'msg', 'dur') + if float(m_time) > data.end: + break + if(m_time and m_pid and m_msg): + t = aslib.FTraceLine(m_time, m_msg, m_dur) + pid = int(m_pid) + else: + continue + if t.fevent or t.fkprobe: + continue + key = (m_proc, pid) + if(key not in ftemp): + ftemp[key] = [] + ftemp[key].append(aslib.FTraceCallGraph(pid)) + cg = ftemp[key][-1] + if(cg.addLine(t)): + ftemp[key].append(aslib.FTraceCallGraph(pid)) + tf.close() + + # add the callgraph data to the device hierarchy + for key in ftemp: + proc, pid = key + for cg in ftemp[key]: + if len(cg.list) < 1 or cg.invalid: + continue + if(not cg.postProcess()): + print('Sanity check failed for %s-%d' % (proc, pid)) + continue + # match cg data to devices + if not data.deviceMatch(cg): + print ' BAD: %s %s-%d [%f - %f]' % (cg.name, proc, pid, cg.start, cg.end) + +# Function: colorForName +# Description: +# Generate a repeatable color from a list for a given name +def colorForName(name): + list = [ + ('c1', '#ec9999'), + ('c2', '#ffc1a6'), + ('c3', '#fff0a6'), + ('c4', '#adf199'), + ('c5', '#9fadea'), + ('c6', '#a699c1'), + ('c7', '#ad99b4'), + ('c8', '#eaffea'), + ('c9', '#dcecfb'), + ('c10', '#ffffea') + ] + i = 0 + total = 0 + count = len(list) + while i < len(name): + total += ord(name[i]) + i += 1 + return list[total % count] + +def cgOverview(cg, minlen): + stats = dict() + large = [] + for l in cg.list: + if l.fcall and l.depth == 1: + if l.length >= minlen: + large.append(l) + if l.name not in stats: + stats[l.name] = [0, 0.0] + stats[l.name][0] += (l.length * 1000.0) + stats[l.name][1] += 1 + return (large, stats) + +# Function: createBootGraph +# Description: +# Create the output html file from the resident test data +# Arguments: +# testruns: array of Data objects from parseKernelLog or parseTraceLog +# Output: +# True if the html file was created, false if it failed +def createBootGraph(data, embedded): + # html function templates + html_srccall = '<div id={6} title="{5}" class="srccall" style="left:{1}%;top:{2}px;height:{3}px;width:{4}%;line-height:{3}px;">{0}</div>\n' + html_timetotal = '<table class="time1">\n<tr>'\ + '<td class="blue">Time from Kernel Boot to start of User Mode: <b>{0} ms</b></td>'\ + '</tr>\n</table>\n' + + # device timeline + devtl = aslib.Timeline(100, 20) + + # write the test title and general info header + devtl.createHeader(sysvals, 'noftrace') + + # Generate the header for this timeline + t0 = data.start + tMax = data.end + tTotal = tMax - t0 + if(tTotal == 0): + print('ERROR: No timeline data') + return False + boot_time = '%.0f'%(tTotal*1000) + devtl.html += html_timetotal.format(boot_time) + + # determine the maximum number of rows we need to draw + phase = 'boot' + list = data.dmesg[phase]['list'] + devlist = [] + for devname in list: + d = aslib.DevItem(0, phase, list[devname]) + devlist.append(d) + devtl.getPhaseRows(devlist) + devtl.calcTotalRows() + + # draw the timeline background + devtl.createZoomBox() + boot = data.dmesg[phase] + length = boot['end']-boot['start'] + left = '%.3f' % (((boot['start']-t0)*100.0)/tTotal) + width = '%.3f' % ((length*100.0)/tTotal) + devtl.html += devtl.html_tblock.format(phase, left, width, devtl.scaleH) + devtl.html += devtl.html_phase.format('0', '100', \ + '%.3f'%devtl.scaleH, '%.3f'%devtl.bodyH, \ + 'white', '') + + # draw the device timeline + num = 0 + devstats = dict() + for devname in sorted(list): + cls, color = colorForName(devname) + dev = list[devname] + info = '@|%.3f|%.3f|%.3f|%d' % (dev['start']*1000.0, dev['end']*1000.0, + dev['ulen']/1000.0, dev['ret']) + devstats[dev['id']] = {'info':info} + dev['color'] = color + height = devtl.phaseRowHeight(0, phase, dev['row']) + top = '%.6f' % ((dev['row']*height) + devtl.scaleH) + left = '%.6f' % (((dev['start']-t0)*100)/tTotal) + width = '%.6f' % (((dev['end']-dev['start'])*100)/tTotal) + length = ' (%0.3f ms) ' % ((dev['end']-dev['start'])*1000) + devtl.html += devtl.html_device.format(dev['id'], + devname+length+'kernel_mode', left, top, '%.3f'%height, + width, devname, ' '+cls, '') + rowtop = devtl.phaseRowTop(0, phase, dev['row']) + height = '%.6f' % (devtl.rowH / 2) + top = '%.6f' % (rowtop + devtl.scaleH + (devtl.rowH / 2)) + if data.do_one_initcall: + if('ftrace' not in dev): + continue + cg = dev['ftrace'] + large, stats = cgOverview(cg, 0.001) + devstats[dev['id']]['fstat'] = stats + for l in large: + left = '%f' % (((l.time-t0)*100)/tTotal) + width = '%f' % (l.length*100/tTotal) + title = '%s (%0.3fms)' % (l.name, l.length * 1000.0) + devtl.html += html_srccall.format(l.name, left, + top, height, width, title, 'x%d'%num) + num += 1 + continue + if('ftraces' not in dev): + continue + for cg in dev['ftraces']: + left = '%f' % (((cg.start-t0)*100)/tTotal) + width = '%f' % ((cg.end-cg.start)*100/tTotal) + cglen = (cg.end - cg.start) * 1000.0 + title = '%s (%0.3fms)' % (cg.name, cglen) + cg.id = 'x%d' % num + devtl.html += html_srccall.format(cg.name, left, + top, height, width, title, dev['id']+cg.id) + num += 1 + + # draw the time scale, try to make the number of labels readable + devtl.createTimeScale(t0, tMax, tTotal, phase) + devtl.html += '</div>\n' + + # timeline is finished + devtl.html += '</div>\n</div>\n' + + if(sysvals.outfile == sysvals.htmlfile): + hf = open(sysvals.htmlfile, 'a') + else: + hf = open(sysvals.htmlfile, 'w') + + # add the css if this is not an embedded run + extra = '\ + .c1 {background:rgba(209,0,0,0.4);}\n\ + .c2 {background:rgba(255,102,34,0.4);}\n\ + .c3 {background:rgba(255,218,33,0.4);}\n\ + .c4 {background:rgba(51,221,0,0.4);}\n\ + .c5 {background:rgba(17,51,204,0.4);}\n\ + .c6 {background:rgba(34,0,102,0.4);}\n\ + .c7 {background:rgba(51,0,68,0.4);}\n\ + .c8 {background:rgba(204,255,204,0.4);}\n\ + .c9 {background:rgba(169,208,245,0.4);}\n\ + .c10 {background:rgba(255,255,204,0.4);}\n\ + .vt {transform:rotate(-60deg);transform-origin:0 0;}\n\ + table.fstat {table-layout:fixed;padding:150px 15px 0 0;font-size:10px;column-width:30px;}\n\ + .fstat th {width:55px;}\n\ + .fstat td {text-align:left;width:35px;}\n\ + .srccall {position:absolute;font-size:10px;z-index:7;overflow:hidden;color:black;text-align:center;white-space:nowrap;border-radius:5px;border:1px solid black;background:linear-gradient(to bottom right,#CCC,#969696);}\n\ + .srccall:hover {color:white;font-weight:bold;border:1px solid white;}\n' + if(not embedded): + aslib.addCSS(hf, sysvals, 1, False, extra) + + # write the device timeline + hf.write(devtl.html) + + # add boot specific html + statinfo = 'var devstats = {\n' + for n in sorted(devstats): + statinfo += '\t"%s": [\n\t\t"%s",\n' % (n, devstats[n]['info']) + if 'fstat' in devstats[n]: + funcs = devstats[n]['fstat'] + for f in sorted(funcs, key=funcs.get, reverse=True): + if funcs[f][0] < 0.01 and len(funcs) > 10: + break + statinfo += '\t\t"%f|%s|%d",\n' % (funcs[f][0], f, funcs[f][1]) + statinfo += '\t],\n' + statinfo += '};\n' + html = \ + '<div id="devicedetailtitle"></div>\n'\ + '<div id="devicedetail" style="display:none;">\n'\ + '<div id="devicedetail0">\n'\ + '<div id="kernel_mode" class="phaselet" style="left:0%;width:100%;background:#DDDDDD"></div>\n'\ + '</div>\n</div>\n'\ + '<script type="text/javascript">\n'+statinfo+\ + '</script>\n' + hf.write(html) + + # add the callgraph html + if(sysvals.usecallgraph): + aslib.addCallgraphs(sysvals, hf, data) + + # add the dmesg log as a hidden div + if sysvals.addlogs: + hf.write('<div id="dmesglog" style="display:none;">\n') + for line in data.dmesgtext: + line = line.replace('<', '<').replace('>', '>') + hf.write(line) + hf.write('</div>\n') + + if(not embedded): + # write the footer and close + aslib.addScriptCode(hf, [data]) + hf.write('</body>\n</html>\n') + else: + # embedded out will be loaded in a page, skip the js + hf.write('<div id=bounds style=display:none>%f,%f</div>' % \ + (data.start*1000, data.initstart*1000)) + hf.close() + return True + +# Function: updateCron +# Description: +# (restore=False) Set the tool to run automatically on reboot +# (restore=True) Restore the original crontab +def updateCron(restore=False): + if not restore: + sysvals.rootUser(True) + crondir = '/var/spool/cron/crontabs/' + cronfile = crondir+'root' + backfile = crondir+'root-analyze_boot-backup' + if not os.path.exists(crondir): + doError('%s not found' % crondir) + out = Popen(['which', 'crontab'], stdout=PIPE).stdout.read() + if not out: + doError('crontab not found') + # on restore: move the backup cron back into place + if restore: + if os.path.exists(backfile): + shutil.move(backfile, cronfile) + return + # backup current cron and install new one with reboot + if os.path.exists(cronfile): + shutil.move(cronfile, backfile) + else: + fp = open(backfile, 'w') + fp.close() + res = -1 + try: + fp = open(backfile, 'r') + op = open(cronfile, 'w') + for line in fp: + if '@reboot' not in line: + op.write(line) + continue + fp.close() + op.write('@reboot python %s\n' % sysvals.cronjobCmdString()) + op.close() + res = call('crontab %s' % cronfile, shell=True) + except Exception, e: + print 'Exception: %s' % str(e) + shutil.move(backfile, cronfile) + res = -1 + if res != 0: + doError('crontab failed') + +# Function: updateGrub +# Description: +# update grub.cfg for all kernels with our parameters +def updateGrub(restore=False): + # call update-grub on restore + if restore: + try: + call(['update-grub'], stderr=PIPE, stdout=PIPE, + env={'PATH': '.:/sbin:/usr/sbin:/usr/bin:/sbin:/bin'}) + except Exception, e: + print 'Exception: %s\n' % str(e) + return + # verify we can do this + sysvals.rootUser(True) + grubfile = '/etc/default/grub' + if not os.path.exists(grubfile): + print 'ERROR: Unable to set the kernel parameters via grub.\n' + sysvals.manualRebootRequired() + out = Popen(['which', 'update-grub'], stdout=PIPE).stdout.read() + if not out: + print 'ERROR: Unable to set the kernel parameters via grub.\n' + sysvals.manualRebootRequired() + + # extract the option and create a grub config without it + tgtopt = 'GRUB_CMDLINE_LINUX_DEFAULT' + cmdline = '' + tempfile = '/etc/default/grub.analyze_boot' + shutil.move(grubfile, tempfile) + res = -1 + try: + fp = open(tempfile, 'r') + op = open(grubfile, 'w') + cont = False + for line in fp: + line = line.strip() + if len(line) == 0 or line[0] == '#': + continue + opt = line.split('=')[0].strip() + if opt == tgtopt: + cmdline = line.split('=', 1)[1].strip('\\') + if line[-1] == '\\': + cont = True + elif cont: + cmdline += line.strip('\\') + if line[-1] != '\\': + cont = False + else: + op.write('%s\n' % line) + fp.close() + # if the target option value is in quotes, strip them + sp = '"' + val = cmdline.strip() + if val[0] == '\'' or val[0] == '"': + sp = val[0] + val = val.strip(sp) + cmdline = val + # append our cmd line options + if len(cmdline) > 0: + cmdline += ' ' + cmdline += sysvals.kernelParams() + # write out the updated target option + op.write('\n%s=%s%s%s\n' % (tgtopt, sp, cmdline, sp)) + op.close() + res = call('update-grub') + os.remove(grubfile) + except Exception, e: + print 'Exception: %s' % str(e) + res = -1 + # cleanup + shutil.move(tempfile, grubfile) + if res != 0: + doError('update-grub failed') + +# Function: doError +# Description: +# generic error function for catastrphic failures +# Arguments: +# msg: the error message to print +# help: True if printHelp should be called after, False otherwise +def doError(msg, help=False): + if help == True: + printHelp() + print 'ERROR: %s\n' % msg + sys.exit() + +# Function: printHelp +# Description: +# print out the help text +def printHelp(): + print('') + print('%s v%.1f' % (sysvals.title, sysvals.version)) + print('Usage: bootgraph <options> <command>') + print('') + print('Description:') + print(' This tool reads in a dmesg log of linux kernel boot and') + print(' creates an html representation of the boot timeline up to') + print(' the start of the init process.') + print('') + print(' If no specific command is given the tool reads the current dmesg') + print(' and/or ftrace log and outputs bootgraph.html') + print('') + print('Options:') + print(' -h Print this help text') + print(' -v Print the current tool version') + print(' -addlogs Add the dmesg log to the html output') + print(' -o file Html timeline name (default: bootgraph.html)') + print(' [advanced]') + print(' -f Use ftrace to add function detail (default: disabled)') + print(' -callgraph Add callgraph detail, can be very large (default: disabled)') + print(' -maxdepth N limit the callgraph data to N call levels (default: 2)') + print(' -mincg ms Discard all callgraphs shorter than ms milliseconds (e.g. 0.001 for us)') + print(' -timeprec N Number of significant digits in timestamps (0:S, 3:ms, [6:us])') + print(' -expandcg pre-expand the callgraph data in the html output (default: disabled)') + print(' -filter list Limit ftrace to comma-delimited list of functions (default: do_one_initcall)') + print(' [commands]') + print(' -reboot Reboot the machine automatically and generate a new timeline') + print(' -manual Show the requirements to generate a new timeline manually') + print(' -dmesg file Load a stored dmesg file (used with -ftrace)') + print(' -ftrace file Load a stored ftrace file (used with -dmesg)') + print(' -flistall Print all functions capable of being captured in ftrace') + print('') + return True + +# ----------------- MAIN -------------------- +# exec start (skipped if script is loaded as library) +if __name__ == '__main__': + # loop through the command line arguments + cmd = '' + simplecmds = ['-updategrub', '-flistall'] + args = iter(sys.argv[1:]) + for arg in args: + if(arg == '-h'): + printHelp() + sys.exit() + elif(arg == '-v'): + print("Version %.1f" % sysvals.version) + sys.exit() + elif(arg in simplecmds): + cmd = arg[1:] + elif(arg == '-f'): + sysvals.useftrace = True + elif(arg == '-callgraph'): + sysvals.useftrace = True + sysvals.usecallgraph = True + elif(arg == '-mincg'): + sysvals.mincglen = aslib.getArgFloat('-mincg', args, 0.0, 10000.0) + elif(arg == '-timeprec'): + sysvals.setPrecision(aslib.getArgInt('-timeprec', args, 0, 6)) + elif(arg == '-maxdepth'): + sysvals.max_graph_depth = aslib.getArgInt('-maxdepth', args, 0, 1000) + elif(arg == '-filter'): + try: + val = args.next() + except: + doError('No filter functions supplied', True) + aslib.rootCheck(True) + sysvals.setGraphFilter(val) + elif(arg == '-ftrace'): + try: + val = args.next() + except: + doError('No ftrace file supplied', True) + if(os.path.exists(val) == False): + doError('%s does not exist' % val) + sysvals.ftracefile = val + elif(arg == '-addlogs'): + sysvals.addlogs = True + elif(arg == '-expandcg'): + sysvals.cgexp = True + elif(arg == '-dmesg'): + try: + val = args.next() + except: + doError('No dmesg file supplied', True) + if(os.path.exists(val) == False): + doError('%s does not exist' % val) + if(sysvals.htmlfile == val or sysvals.outfile == val): + doError('Output filename collision') + sysvals.dmesgfile = val + elif(arg == '-o'): + try: + val = args.next() + except: + doError('No HTML filename supplied', True) + if(sysvals.dmesgfile == val or sysvals.ftracefile == val): + doError('Output filename collision') + sysvals.htmlfile = val + elif(arg == '-reboot'): + if sysvals.iscronjob: + doError('-reboot and -cronjob are incompatible') + sysvals.reboot = True + elif(arg == '-manual'): + sysvals.reboot = True + sysvals.manual = True + # remaining options are only for cron job use + elif(arg == '-cronjob'): + sysvals.iscronjob = True + if sysvals.reboot: + doError('-reboot and -cronjob are incompatible') + else: + doError('Invalid argument: '+arg, True) + + if cmd != '': + if cmd == 'updategrub': + updateGrub() + elif cmd == 'flistall': + sysvals.getFtraceFilterFunctions(False) + sys.exit() + + # update grub, setup a cronjob, and reboot + if sysvals.reboot: + if not sysvals.manual: + updateGrub() + updateCron() + call('reboot') + else: + sysvals.manualRebootRequired() + sys.exit() + + # disable the cronjob + if sysvals.iscronjob: + updateCron(True) + updateGrub(True) + + data = loadKernelLog() + if sysvals.useftrace: + loadTraceLog(data) + if sysvals.iscronjob: + try: + sysvals.fsetVal('0', 'tracing_on') + except: + pass + + if(sysvals.outfile and sysvals.phoronix): + fp = open(sysvals.outfile, 'w') + fp.write('pass %s initstart %.3f end %.3f boot %s\n' % + (data.valid, data.initstart*1000, data.end*1000, data.boottime)) + fp.close() + if(not data.valid): + if sysvals.dmesgfile: + doError('No initcall data found in %s' % sysvals.dmesgfile) + else: + doError('No initcall data found, is initcall_debug enabled?') + + print(' Host: %s' % sysvals.hostname) + print(' Test time: %s' % sysvals.testtime) + print(' Boot time: %s' % data.boottime) + print('Kernel Version: %s' % sysvals.kernel) + print(' Kernel start: %.3f' % (data.start * 1000)) + print(' init start: %.3f' % (data.initstart * 1000)) + + createBootGraph(data, sysvals.phoronix) diff --git a/tools/power/pm-graph/analyze_suspend.py b/tools/power/pm-graph/analyze_suspend.py new file mode 100755 index 000000000000..a9206e67fc1f --- /dev/null +++ b/tools/power/pm-graph/analyze_suspend.py @@ -0,0 +1,5309 @@ +#!/usr/bin/python +# +# Tool for analyzing suspend/resume timing +# Copyright (c) 2013, Intel Corporation. +# +# This program is free software; you can redistribute it and/or modify it +# under the terms and conditions of the GNU General Public License, +# version 2, as published by the Free Software Foundation. +# +# This program is distributed in the hope it will be useful, but WITHOUT +# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or +# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for +# more details. +# +# Authors: +# Todd Brandt <todd.e.brandt@linux.intel.com> +# +# Links: +# Home Page +# https://01.org/suspendresume +# Source repo +# https://github.com/01org/pm-graph +# +# Description: +# This tool is designed to assist kernel and OS developers in optimizing +# their linux stack's suspend/resume time. Using a kernel image built +# with a few extra options enabled, the tool will execute a suspend and +# will capture dmesg and ftrace data until resume is complete. This data +# is transformed into a device timeline and a callgraph to give a quick +# and detailed view of which devices and callbacks are taking the most +# time in suspend/resume. The output is a single html file which can be +# viewed in firefox or chrome. +# +# The following kernel build options are required: +# CONFIG_PM_DEBUG=y +# CONFIG_PM_SLEEP_DEBUG=y +# CONFIG_FTRACE=y +# CONFIG_FUNCTION_TRACER=y +# CONFIG_FUNCTION_GRAPH_TRACER=y +# CONFIG_KPROBES=y +# CONFIG_KPROBES_ON_FTRACE=y +# +# For kernel versions older than 3.15: +# The following additional kernel parameters are required: +# (e.g. in file /etc/default/grub) +# GRUB_CMDLINE_LINUX_DEFAULT="... initcall_debug log_buf_len=16M ..." +# + +# ----------------- LIBRARIES -------------------- + +import sys +import time +import os +import string +import re +import platform +from datetime import datetime +import struct +import ConfigParser +from threading import Thread +from subprocess import call, Popen, PIPE + +# ----------------- CLASSES -------------------- + +# Class: SystemValues +# Description: +# A global, single-instance container used to +# store system values and test parameters +class SystemValues: + title = 'SleepGraph' + version = '4.6' + ansi = False + verbose = False + addlogs = False + mindevlen = 0.0 + mincglen = 0.0 + cgphase = '' + cgtest = -1 + max_graph_depth = 0 + callloopmaxgap = 0.0001 + callloopmaxlen = 0.005 + srgap = 0 + cgexp = False + outdir = '' + testdir = '.' + tpath = '/sys/kernel/debug/tracing/' + fpdtpath = '/sys/firmware/acpi/tables/FPDT' + epath = '/sys/kernel/debug/tracing/events/power/' + traceevents = [ + 'suspend_resume', + 'device_pm_callback_end', + 'device_pm_callback_start' + ] + logmsg = '' + testcommand = '' + mempath = '/dev/mem' + powerfile = '/sys/power/state' + suspendmode = 'mem' + hostname = 'localhost' + prefix = 'test' + teststamp = '' + dmesgstart = 0.0 + dmesgfile = '' + ftracefile = '' + htmlfile = '' + embedded = False + rtcwake = True + rtcwaketime = 15 + rtcpath = '' + devicefilter = [] + stamp = 0 + execcount = 1 + x2delay = 0 + usecallgraph = False + usetraceevents = False + usetraceeventsonly = False + usetracemarkers = True + usekprobes = True + usedevsrc = False + useprocmon = False + notestrun = False + mixedphaseheight = True + devprops = dict() + predelay = 0 + postdelay = 0 + procexecfmt = 'ps - (?P<ps>.*)$' + devpropfmt = '# Device Properties: .*' + tracertypefmt = '# tracer: (?P<t>.*)' + firmwarefmt = '# fwsuspend (?P<s>[0-9]*) fwresume (?P<r>[0-9]*)$' + stampfmt = '# suspend-(?P<m>[0-9]{2})(?P<d>[0-9]{2})(?P<y>[0-9]{2})-'+\ + '(?P<H>[0-9]{2})(?P<M>[0-9]{2})(?P<S>[0-9]{2})'+\ + ' (?P<host>.*) (?P<mode>.*) (?P<kernel>.*)$' + tracefuncs = { + 'sys_sync': dict(), + 'pm_prepare_console': dict(), + 'pm_notifier_call_chain': dict(), + 'freeze_processes': dict(), + 'freeze_kernel_threads': dict(), + 'pm_restrict_gfp_mask': dict(), + 'acpi_suspend_begin': dict(), + 'suspend_console': dict(), + 'acpi_pm_prepare': dict(), + 'syscore_suspend': dict(), + 'arch_enable_nonboot_cpus_end': dict(), + 'syscore_resume': dict(), + 'acpi_pm_finish': dict(), + 'resume_console': dict(), + 'acpi_pm_end': dict(), + 'pm_restore_gfp_mask': dict(), + 'thaw_processes': dict(), + 'pm_restore_console': dict(), + 'CPU_OFF': { + 'func':'_cpu_down', + 'args_x86_64': {'cpu':'%di:s32'}, + 'format': 'CPU_OFF[{cpu}]' + }, + 'CPU_ON': { + 'func':'_cpu_up', + 'args_x86_64': {'cpu':'%di:s32'}, + 'format': 'CPU_ON[{cpu}]' + }, + } + dev_tracefuncs = { + # general wait/delay/sleep + 'msleep': { 'args_x86_64': {'time':'%di:s32'}, 'ub': 1 }, + 'schedule_timeout_uninterruptible': { 'args_x86_64': {'timeout':'%di:s32'}, 'ub': 1 }, + 'schedule_timeout': { 'args_x86_64': {'timeout':'%di:s32'}, 'ub': 1 }, + 'udelay': { 'func':'__const_udelay', 'args_x86_64': {'loops':'%di:s32'}, 'ub': 1 }, + 'usleep_range': { 'args_x86_64': {'min':'%di:s32', 'max':'%si:s32'}, 'ub': 1 }, + 'mutex_lock_slowpath': { 'func':'__mutex_lock_slowpath', 'ub': 1 }, + 'acpi_os_stall': {'ub': 1}, + # ACPI + 'acpi_resume_power_resources': dict(), + 'acpi_ps_parse_aml': dict(), + # filesystem + 'ext4_sync_fs': dict(), + # 80211 + 'iwlagn_mac_start': dict(), + 'iwlagn_alloc_bcast_station': dict(), + 'iwl_trans_pcie_start_hw': dict(), + 'iwl_trans_pcie_start_fw': dict(), + 'iwl_run_init_ucode': dict(), + 'iwl_load_ucode_wait_alive': dict(), + 'iwl_alive_start': dict(), + 'iwlagn_mac_stop': dict(), + 'iwlagn_mac_suspend': dict(), + 'iwlagn_mac_resume': dict(), + 'iwlagn_mac_add_interface': dict(), + 'iwlagn_mac_remove_interface': dict(), + 'iwlagn_mac_change_interface': dict(), + 'iwlagn_mac_config': dict(), + 'iwlagn_configure_filter': dict(), + 'iwlagn_mac_hw_scan': dict(), + 'iwlagn_bss_info_changed': dict(), + 'iwlagn_mac_channel_switch': dict(), + 'iwlagn_mac_flush': dict(), + # ATA + 'ata_eh_recover': { 'args_x86_64': {'port':'+36(%di):s32'} }, + # i915 + 'i915_gem_resume': dict(), + 'i915_restore_state': dict(), + 'intel_opregion_setup': dict(), + 'g4x_pre_enable_dp': dict(), + 'vlv_pre_enable_dp': dict(), + 'chv_pre_enable_dp': dict(), + 'g4x_enable_dp': dict(), + 'vlv_enable_dp': dict(), + 'intel_hpd_init': dict(), + 'intel_opregion_register': dict(), + 'intel_dp_detect': dict(), + 'intel_hdmi_detect': dict(), + 'intel_opregion_init': dict(), + 'intel_fbdev_set_suspend': dict(), + } + kprobes = dict() + timeformat = '%.3f' + def __init__(self): + # if this is a phoronix test run, set some default options + if('LOG_FILE' in os.environ and 'TEST_RESULTS_IDENTIFIER' in os.environ): + self.embedded = True + self.addlogs = True + self.htmlfile = os.environ['LOG_FILE'] + self.archargs = 'args_'+platform.machine() + self.hostname = platform.node() + if(self.hostname == ''): + self.hostname = 'localhost' + rtc = "rtc0" + if os.path.exists('/dev/rtc'): + rtc = os.readlink('/dev/rtc') + rtc = '/sys/class/rtc/'+rtc + if os.path.exists(rtc) and os.path.exists(rtc+'/date') and \ + os.path.exists(rtc+'/time') and os.path.exists(rtc+'/wakealarm'): + self.rtcpath = rtc + if (hasattr(sys.stdout, 'isatty') and sys.stdout.isatty()): + self.ansi = True + def rootUser(self, fatal=False): + if 'USER' in os.environ and os.environ['USER'] == 'root': + return True + if fatal: + doError('This command must be run as root') + return False + def setPrecision(self, num): + if num < 0 or num > 6: + return + self.timeformat = '%.{0}f'.format(num) + def setOutputFolder(self, value): + args = dict() + n = datetime.now() + args['date'] = n.strftime('%y%m%d') + args['time'] = n.strftime('%H%M%S') + args['hostname'] = self.hostname + self.outdir = value.format(**args) + def setOutputFile(self): + if((self.htmlfile == '') and (self.dmesgfile != '')): + m = re.match('(?P<name>.*)_dmesg\.txt$', self.dmesgfile) + if(m): + self.htmlfile = m.group('name')+'.html' + if((self.htmlfile == '') and (self.ftracefile != '')): + m = re.match('(?P<name>.*)_ftrace\.txt$', self.ftracefile) + if(m): + self.htmlfile = m.group('name')+'.html' + if(self.htmlfile == ''): + self.htmlfile = 'output.html' + def initTestOutput(self, subdir, testpath=''): + self.prefix = self.hostname + v = open('/proc/version', 'r').read().strip() + kver = string.split(v)[2] + n = datetime.now() + testtime = n.strftime('suspend-%m%d%y-%H%M%S') + if not testpath: + testpath = n.strftime('suspend-%y%m%d-%H%M%S') + if(subdir != "."): + self.testdir = subdir+"/"+testpath + else: + self.testdir = testpath + self.teststamp = \ + '# '+testtime+' '+self.prefix+' '+self.suspendmode+' '+kver + if(self.embedded): + self.dmesgfile = \ + '/tmp/'+testtime+'_'+self.suspendmode+'_dmesg.txt' + self.ftracefile = \ + '/tmp/'+testtime+'_'+self.suspendmode+'_ftrace.txt' + return + self.dmesgfile = \ + self.testdir+'/'+self.prefix+'_'+self.suspendmode+'_dmesg.txt' + self.ftracefile = \ + self.testdir+'/'+self.prefix+'_'+self.suspendmode+'_ftrace.txt' + self.htmlfile = \ + self.testdir+'/'+self.prefix+'_'+self.suspendmode+'.html' + if not os.path.isdir(self.testdir): + os.mkdir(self.testdir) + def setDeviceFilter(self, value): + self.devicefilter = [] + if value: + value = value.split(',') + for i in value: + self.devicefilter.append(i.strip()) + def rtcWakeAlarmOn(self): + call('echo 0 > '+self.rtcpath+'/wakealarm', shell=True) + outD = open(self.rtcpath+'/date', 'r').read().strip() + outT = open(self.rtcpath+'/time', 'r').read().strip() + mD = re.match('^(?P<y>[0-9]*)-(?P<m>[0-9]*)-(?P<d>[0-9]*)', outD) + mT = re.match('^(?P<h>[0-9]*):(?P<m>[0-9]*):(?P<s>[0-9]*)', outT) + if(mD and mT): + # get the current time from hardware + utcoffset = int((datetime.now() - datetime.utcnow()).total_seconds()) + dt = datetime(\ + int(mD.group('y')), int(mD.group('m')), int(mD.group('d')), + int(mT.group('h')), int(mT.group('m')), int(mT.group('s'))) + nowtime = int(dt.strftime('%s')) + utcoffset + else: + # if hardware time fails, use the software time + nowtime = int(datetime.now().strftime('%s')) + alarm = nowtime + self.rtcwaketime + call('echo %d > %s/wakealarm' % (alarm, self.rtcpath), shell=True) + def rtcWakeAlarmOff(self): + call('echo 0 > %s/wakealarm' % self.rtcpath, shell=True) + def initdmesg(self): + # get the latest time stamp from the dmesg log + fp = Popen('dmesg', stdout=PIPE).stdout + ktime = '0' + for line in fp: + line = line.replace('\r\n', '') + idx = line.find('[') + if idx > 1: + line = line[idx:] + m = re.match('[ \t]*(\[ *)(?P<ktime>[0-9\.]*)(\]) (?P<msg>.*)', line) + if(m): + ktime = m.group('ktime') + fp.close() + self.dmesgstart = float(ktime) + def getdmesg(self): + # store all new dmesg lines since initdmesg was called + fp = Popen('dmesg', stdout=PIPE).stdout + op = open(self.dmesgfile, 'a') + for line in fp: + line = line.replace('\r\n', '') + idx = line.find('[') + if idx > 1: + line = line[idx:] + m = re.match('[ \t]*(\[ *)(?P<ktime>[0-9\.]*)(\]) (?P<msg>.*)', line) + if(not m): + continue + ktime = float(m.group('ktime')) + if ktime > self.dmesgstart: + op.write(line) + fp.close() + op.close() + def addFtraceFilterFunctions(self, file): + fp = open(file) + list = fp.read().split('\n') + fp.close() + for i in list: + if len(i) < 2: + continue + self.tracefuncs[i] = dict() + def getFtraceFilterFunctions(self, current): + rootCheck(True) + if not current: + call('cat '+self.tpath+'available_filter_functions', shell=True) + return + fp = open(self.tpath+'available_filter_functions') + master = fp.read().split('\n') + fp.close() + for i in self.tracefuncs: + if 'func' in self.tracefuncs[i]: + i = self.tracefuncs[i]['func'] + if i in master: + print i + else: + print self.colorText(i) + def setFtraceFilterFunctions(self, list): + fp = open(self.tpath+'available_filter_functions') + master = fp.read().split('\n') + fp.close() + flist = '' + for i in list: + if i not in master: + continue + if ' [' in i: + flist += i.split(' ')[0]+'\n' + else: + flist += i+'\n' + fp = open(self.tpath+'set_graph_function', 'w') + fp.write(flist) + fp.close() + def basicKprobe(self, name): + self.kprobes[name] = {'name': name,'func': name,'args': dict(),'format': name} + def defaultKprobe(self, name, kdata): + k = kdata + for field in ['name', 'format', 'func']: + if field not in k: + k[field] = name + if self.archargs in k: + k['args'] = k[self.archargs] + else: + k['args'] = dict() + k['format'] = name + self.kprobes[name] = k + def kprobeColor(self, name): + if name not in self.kprobes or 'color' not in self.kprobes[name]: + return '' + return self.kprobes[name]['color'] + def kprobeDisplayName(self, name, dataraw): + if name not in self.kprobes: + self.basicKprobe(name) + data = '' + quote=0 + # first remvoe any spaces inside quotes, and the quotes + for c in dataraw: + if c == '"': + quote = (quote + 1) % 2 + if quote and c == ' ': + data += '_' + elif c != '"': + data += c + fmt, args = self.kprobes[name]['format'], self.kprobes[name]['args'] + arglist = dict() + # now process the args + for arg in sorted(args): + arglist[arg] = '' + m = re.match('.* '+arg+'=(?P<arg>.*) ', data); + if m: + arglist[arg] = m.group('arg') + else: + m = re.match('.* '+arg+'=(?P<arg>.*)', data); + if m: + arglist[arg] = m.group('arg') + out = fmt.format(**arglist) + out = out.replace(' ', '_').replace('"', '') + return out + def kprobeText(self, kname, kprobe): + name = fmt = func = kname + args = dict() + if 'name' in kprobe: + name = kprobe['name'] + if 'format' in kprobe: + fmt = kprobe['format'] + if 'func' in kprobe: + func = kprobe['func'] + if self.archargs in kprobe: + args = kprobe[self.archargs] + if 'args' in kprobe: + args = kprobe['args'] + if re.findall('{(?P<n>[a-z,A-Z,0-9]*)}', func): + doError('Kprobe "%s" has format info in the function name "%s"' % (name, func)) + for arg in re.findall('{(?P<n>[a-z,A-Z,0-9]*)}', fmt): + if arg not in args: + doError('Kprobe "%s" is missing argument "%s"' % (name, arg)) + val = 'p:%s_cal %s' % (name, func) + for i in sorted(args): + val += ' %s=%s' % (i, args[i]) + val += '\nr:%s_ret %s $retval\n' % (name, func) + return val + def addKprobes(self, output=False): + if len(sysvals.kprobes) < 1: + return + if output: + print(' kprobe functions in this kernel:') + # first test each kprobe + rejects = [] + # sort kprobes: trace, ub-dev, custom, dev + kpl = [[], [], [], []] + for name in sorted(self.kprobes): + res = self.colorText('YES', 32) + if not self.testKprobe(name, self.kprobes[name]): + res = self.colorText('NO') + rejects.append(name) + else: + if name in self.tracefuncs: + kpl[0].append(name) + elif name in self.dev_tracefuncs: + if 'ub' in self.dev_tracefuncs[name]: + kpl[1].append(name) + else: + kpl[3].append(name) + else: + kpl[2].append(name) + if output: + print(' %s: %s' % (name, res)) + kplist = kpl[0] + kpl[1] + kpl[2] + kpl[3] + # remove all failed ones from the list + for name in rejects: + self.kprobes.pop(name) + # set the kprobes all at once + self.fsetVal('', 'kprobe_events') + kprobeevents = '' + for kp in kplist: + kprobeevents += self.kprobeText(kp, self.kprobes[kp]) + self.fsetVal(kprobeevents, 'kprobe_events') + # verify that the kprobes were set as ordered + check = self.fgetVal('kprobe_events') + linesout = len(kprobeevents.split('\n')) - 1 + linesack = len(check.split('\n')) - 1 + if output: + res = '%d/%d' % (linesack, linesout) + if linesack < linesout: + res = self.colorText(res, 31) + else: + res = self.colorText(res, 32) + print(' working kprobe functions enabled: %s' % res) + self.fsetVal('1', 'events/kprobes/enable') + def testKprobe(self, kname, kprobe): + self.fsetVal('0', 'events/kprobes/enable') + kprobeevents = self.kprobeText(kname, kprobe) + if not kprobeevents: + return False + try: + self.fsetVal(kprobeevents, 'kprobe_events') + check = self.fgetVal('kprobe_events') + except: + return False + linesout = len(kprobeevents.split('\n')) + linesack = len(check.split('\n')) + if linesack < linesout: + return False + return True + def fsetVal(self, val, path, mode='w'): + file = self.tpath+path + if not os.path.exists(file): + return False + try: + fp = open(file, mode, 0) + fp.write(val) + fp.flush() + fp.close() + except: + pass + return True + def fgetVal(self, path): + file = self.tpath+path + res = '' + if not os.path.exists(file): + return res + try: + fp = open(file, 'r') + res = fp.read() + fp.close() + except: + pass + return res + def cleanupFtrace(self): + if(self.usecallgraph or self.usetraceevents): + self.fsetVal('0', 'events/kprobes/enable') + self.fsetVal('', 'kprobe_events') + def setupAllKprobes(self): + for name in self.tracefuncs: + self.defaultKprobe(name, self.tracefuncs[name]) + for name in self.dev_tracefuncs: + self.defaultKprobe(name, self.dev_tracefuncs[name]) + def isCallgraphFunc(self, name): + if len(self.tracefuncs) < 1 and self.suspendmode == 'command': + return True + for i in self.tracefuncs: + if 'func' in self.tracefuncs[i]: + f = self.tracefuncs[i]['func'] + else: + f = i + if name == f: + return True + return False + def initFtrace(self, testing=False): + print('INITIALIZING FTRACE...') + # turn trace off + self.fsetVal('0', 'tracing_on') + self.cleanupFtrace() + # set the trace clock to global + self.fsetVal('global', 'trace_clock') + # set trace buffer to a huge value + self.fsetVal('nop', 'current_tracer') + self.fsetVal('131073', 'buffer_size_kb') + # go no further if this is just a status check + if testing: + return + # initialize the callgraph trace + if(self.usecallgraph): + # set trace type + self.fsetVal('function_graph', 'current_tracer') + self.fsetVal('', 'set_ftrace_filter') + # set trace format options + self.fsetVal('print-parent', 'trace_options') + self.fsetVal('funcgraph-abstime', 'trace_options') + self.fsetVal('funcgraph-cpu', 'trace_options') + self.fsetVal('funcgraph-duration', 'trace_options') + self.fsetVal('funcgraph-proc', 'trace_options') + self.fsetVal('funcgraph-tail', 'trace_options') + self.fsetVal('nofuncgraph-overhead', 'trace_options') + self.fsetVal('context-info', 'trace_options') + self.fsetVal('graph-time', 'trace_options') + self.fsetVal('%d' % self.max_graph_depth, 'max_graph_depth') + cf = ['dpm_run_callback'] + if(self.usetraceeventsonly): + cf += ['dpm_prepare', 'dpm_complete'] + for fn in self.tracefuncs: + if 'func' in self.tracefuncs[fn]: + cf.append(self.tracefuncs[fn]['func']) + else: + cf.append(fn) + self.setFtraceFilterFunctions(cf) + # initialize the kprobe trace + elif self.usekprobes: + for name in self.tracefuncs: + self.defaultKprobe(name, self.tracefuncs[name]) + if self.usedevsrc: + for name in self.dev_tracefuncs: + self.defaultKprobe(name, self.dev_tracefuncs[name]) + print('INITIALIZING KPROBES...') + self.addKprobes(self.verbose) + if(self.usetraceevents): + # turn trace events on + events = iter(self.traceevents) + for e in events: + self.fsetVal('1', 'events/power/'+e+'/enable') + # clear the trace buffer + self.fsetVal('', 'trace') + def verifyFtrace(self): + # files needed for any trace data + files = ['buffer_size_kb', 'current_tracer', 'trace', 'trace_clock', + 'trace_marker', 'trace_options', 'tracing_on'] + # files needed for callgraph trace data + tp = self.tpath + if(self.usecallgraph): + files += [ + 'available_filter_functions', + 'set_ftrace_filter', + 'set_graph_function' + ] + for f in files: + if(os.path.exists(tp+f) == False): + return False + return True + def verifyKprobes(self): + # files needed for kprobes to work + files = ['kprobe_events', 'events'] + tp = self.tpath + for f in files: + if(os.path.exists(tp+f) == False): + return False + return True + def colorText(self, str, color=31): + if not self.ansi: + return str + return '\x1B[%d;40m%s\x1B[m' % (color, str) + +sysvals = SystemValues() +suspendmodename = { + 'freeze': 'Freeze (S0)', + 'standby': 'Standby (S1)', + 'mem': 'Suspend (S3)', + 'disk': 'Hibernate (S4)' +} + +# Class: DevProps +# Description: +# Simple class which holds property values collected +# for all the devices used in the timeline. +class DevProps: + syspath = '' + altname = '' + async = True + xtraclass = '' + xtrainfo = '' + def out(self, dev): + return '%s,%s,%d;' % (dev, self.altname, self.async) + def debug(self, dev): + print '%s:\n\taltname = %s\n\t async = %s' % (dev, self.altname, self.async) + def altName(self, dev): + if not self.altname or self.altname == dev: + return dev + return '%s [%s]' % (self.altname, dev) + def xtraClass(self): + if self.xtraclass: + return ' '+self.xtraclass + if not self.async: + return ' sync' + return '' + def xtraInfo(self): + if self.xtraclass: + return ' '+self.xtraclass + if self.async: + return ' async_device' + return ' sync_device' + +# Class: DeviceNode +# Description: +# A container used to create a device hierachy, with a single root node +# and a tree of child nodes. Used by Data.deviceTopology() +class DeviceNode: + name = '' + children = 0 + depth = 0 + def __init__(self, nodename, nodedepth): + self.name = nodename + self.children = [] + self.depth = nodedepth + +# Class: Data +# Description: +# The primary container for suspend/resume test data. There is one for +# each test run. The data is organized into a cronological hierarchy: +# Data.dmesg { +# phases { +# 10 sequential, non-overlapping phases of S/R +# contents: times for phase start/end, order/color data for html +# devlist { +# device callback or action list for this phase +# device { +# a single device callback or generic action +# contents: start/stop times, pid/cpu/driver info +# parents/children, html id for timeline/callgraph +# optionally includes an ftrace callgraph +# optionally includes dev/ps data +# } +# } +# } +# } +# +class Data: + dmesg = {} # root data structure + phases = [] # ordered list of phases + start = 0.0 # test start + end = 0.0 # test end + tSuspended = 0.0 # low-level suspend start + tResumed = 0.0 # low-level resume start + tKernSus = 0.0 # kernel level suspend start + tKernRes = 0.0 # kernel level resume end + tLow = 0.0 # time spent in low-level suspend (standby/freeze) + fwValid = False # is firmware data available + fwSuspend = 0 # time spent in firmware suspend + fwResume = 0 # time spent in firmware resume + dmesgtext = [] # dmesg text file in memory + pstl = 0 # process timeline + testnumber = 0 + idstr = '' + html_device_id = 0 + stamp = 0 + outfile = '' + devpids = [] + kerror = False + def __init__(self, num): + idchar = 'abcdefghij' + self.pstl = dict() + self.testnumber = num + self.idstr = idchar[num] + self.dmesgtext = [] + self.phases = [] + self.dmesg = { # fixed list of 10 phases + 'suspend_prepare': {'list': dict(), 'start': -1.0, 'end': -1.0, + 'row': 0, 'color': '#CCFFCC', 'order': 0}, + 'suspend': {'list': dict(), 'start': -1.0, 'end': -1.0, + 'row': 0, 'color': '#88FF88', 'order': 1}, + 'suspend_late': {'list': dict(), 'start': -1.0, 'end': -1.0, + 'row': 0, 'color': '#00AA00', 'order': 2}, + 'suspend_noirq': {'list': dict(), 'start': -1.0, 'end': -1.0, + 'row': 0, 'color': '#008888', 'order': 3}, + 'suspend_machine': {'list': dict(), 'start': -1.0, 'end': -1.0, + 'row': 0, 'color': '#0000FF', 'order': 4}, + 'resume_machine': {'list': dict(), 'start': -1.0, 'end': -1.0, + 'row': 0, 'color': '#FF0000', 'order': 5}, + 'resume_noirq': {'list': dict(), 'start': -1.0, 'end': -1.0, + 'row': 0, 'color': '#FF9900', 'order': 6}, + 'resume_early': {'list': dict(), 'start': -1.0, 'end': -1.0, + 'row': 0, 'color': '#FFCC00', 'order': 7}, + 'resume': {'list': dict(), 'start': -1.0, 'end': -1.0, + 'row': 0, 'color': '#FFFF88', 'order': 8}, + 'resume_complete': {'list': dict(), 'start': -1.0, 'end': -1.0, + 'row': 0, 'color': '#FFFFCC', 'order': 9} + } + self.phases = self.sortedPhases() + self.devicegroups = [] + for phase in self.phases: + self.devicegroups.append([phase]) + self.errorinfo = {'suspend':[],'resume':[]} + def extractErrorInfo(self, dmesg): + error = '' + tm = 0.0 + for i in range(len(dmesg)): + if 'Call Trace:' in dmesg[i]: + m = re.match('[ \t]*(\[ *)(?P<ktime>[0-9\.]*)(\]) .*', dmesg[i]) + if not m: + continue + tm = float(m.group('ktime')) + if tm < self.start or tm > self.end: + continue + for j in range(i-10, i+1): + error += dmesg[j] + continue + if error: + m = re.match('[ \t]*\[ *[0-9\.]*\] \[\<[0-9a-fA-F]*\>\] .*', dmesg[i]) + if m: + error += dmesg[i] + else: + if tm < self.tSuspended: + dir = 'suspend' + else: + dir = 'resume' + error = error.replace('<', '<').replace('>', '>') + vprint('kernel error found in %s at %f' % (dir, tm)) + self.errorinfo[dir].append((tm, error)) + self.kerror = True + error = '' + def setStart(self, time): + self.start = time + def setEnd(self, time): + self.end = time + def isTraceEventOutsideDeviceCalls(self, pid, time): + for phase in self.phases: + list = self.dmesg[phase]['list'] + for dev in list: + d = list[dev] + if(d['pid'] == pid and time >= d['start'] and + time < d['end']): + return False + return True + def sourcePhase(self, start): + for phase in self.phases: + pend = self.dmesg[phase]['end'] + if start <= pend: + return phase + return 'resume_complete' + def sourceDevice(self, phaselist, start, end, pid, type): + tgtdev = '' + for phase in phaselist: + list = self.dmesg[phase]['list'] + for devname in list: + dev = list[devname] + # pid must match + if dev['pid'] != pid: + continue + devS = dev['start'] + devE = dev['end'] + if type == 'device': + # device target event is entirely inside the source boundary + if(start < devS or start >= devE or end <= devS or end > devE): + continue + elif type == 'thread': + # thread target event will expand the source boundary + if start < devS: + dev['start'] = start + if end > devE: + dev['end'] = end + tgtdev = dev + break + return tgtdev + def addDeviceFunctionCall(self, displayname, kprobename, proc, pid, start, end, cdata, rdata): + # try to place the call in a device + tgtdev = self.sourceDevice(self.phases, start, end, pid, 'device') + # calls with device pids that occur outside device bounds are dropped + # TODO: include these somehow + if not tgtdev and pid in self.devpids: + return False + # try to place the call in a thread + if not tgtdev: + tgtdev = self.sourceDevice(self.phases, start, end, pid, 'thread') + # create new thread blocks, expand as new calls are found + if not tgtdev: + if proc == '<...>': + threadname = 'kthread-%d' % (pid) + else: + threadname = '%s-%d' % (proc, pid) + tgtphase = self.sourcePhase(start) + self.newAction(tgtphase, threadname, pid, '', start, end, '', ' kth', '') + return self.addDeviceFunctionCall(displayname, kprobename, proc, pid, start, end, cdata, rdata) + # this should not happen + if not tgtdev: + vprint('[%f - %f] %s-%d %s %s %s' % \ + (start, end, proc, pid, kprobename, cdata, rdata)) + return False + # place the call data inside the src element of the tgtdev + if('src' not in tgtdev): + tgtdev['src'] = [] + dtf = sysvals.dev_tracefuncs + ubiquitous = False + if kprobename in dtf and 'ub' in dtf[kprobename]: + ubiquitous = True + title = cdata+' '+rdata + mstr = '\(.*\) *(?P<args>.*) *\((?P<caller>.*)\+.* arg1=(?P<ret>.*)' + m = re.match(mstr, title) + if m: + c = m.group('caller') + a = m.group('args').strip() + r = m.group('ret') + if len(r) > 6: + r = '' + else: + r = 'ret=%s ' % r + if ubiquitous and c in dtf and 'ub' in dtf[c]: + return False + color = sysvals.kprobeColor(kprobename) + e = DevFunction(displayname, a, c, r, start, end, ubiquitous, proc, pid, color) + tgtdev['src'].append(e) + return True + def overflowDevices(self): + # get a list of devices that extend beyond the end of this test run + devlist = [] + for phase in self.phases: + list = self.dmesg[phase]['list'] + for devname in list: + dev = list[devname] + if dev['end'] > self.end: + devlist.append(dev) + return devlist + def mergeOverlapDevices(self, devlist): + # merge any devices that overlap devlist + for dev in devlist: + devname = dev['name'] + for phase in self.phases: + list = self.dmesg[phase]['list'] + if devname not in list: + continue + tdev = list[devname] + o = min(dev['end'], tdev['end']) - max(dev['start'], tdev['start']) + if o <= 0: + continue + dev['end'] = tdev['end'] + if 'src' not in dev or 'src' not in tdev: + continue + dev['src'] += tdev['src'] + del list[devname] + def usurpTouchingThread(self, name, dev): + # the caller test has priority of this thread, give it to him + for phase in self.phases: + list = self.dmesg[phase]['list'] + if name in list: + tdev = list[name] + if tdev['start'] - dev['end'] < 0.1: + dev['end'] = tdev['end'] + if 'src' not in dev: + dev['src'] = [] + if 'src' in tdev: + dev['src'] += tdev['src'] + del list[name] + break + def stitchTouchingThreads(self, testlist): + # merge any threads between tests that touch + for phase in self.phases: + list = self.dmesg[phase]['list'] + for devname in list: + dev = list[devname] + if 'htmlclass' not in dev or 'kth' not in dev['htmlclass']: + continue + for data in testlist: + data.usurpTouchingThread(devname, dev) + def optimizeDevSrc(self): + # merge any src call loops to reduce timeline size + for phase in self.phases: + list = self.dmesg[phase]['list'] + for dev in list: + if 'src' not in list[dev]: + continue + src = list[dev]['src'] + p = 0 + for e in sorted(src, key=lambda event: event.time): + if not p or not e.repeat(p): + p = e + continue + # e is another iteration of p, move it into p + p.end = e.end + p.length = p.end - p.time + p.count += 1 + src.remove(e) + def trimTimeVal(self, t, t0, dT, left): + if left: + if(t > t0): + if(t - dT < t0): + return t0 + return t - dT + else: + return t + else: + if(t < t0 + dT): + if(t > t0): + return t0 + dT + return t + dT + else: + return t + def trimTime(self, t0, dT, left): + self.tSuspended = self.trimTimeVal(self.tSuspended, t0, dT, left) + self.tResumed = self.trimTimeVal(self.tResumed, t0, dT, left) + self.start = self.trimTimeVal(self.start, t0, dT, left) + self.tKernSus = self.trimTimeVal(self.tKernSus, t0, dT, left) + self.tKernRes = self.trimTimeVal(self.tKernRes, t0, dT, left) + self.end = self.trimTimeVal(self.end, t0, dT, left) + for phase in self.phases: + p = self.dmesg[phase] + p['start'] = self.trimTimeVal(p['start'], t0, dT, left) + p['end'] = self.trimTimeVal(p['end'], t0, dT, left) + list = p['list'] + for name in list: + d = list[name] + d['start'] = self.trimTimeVal(d['start'], t0, dT, left) + d['end'] = self.trimTimeVal(d['end'], t0, dT, left) + if('ftrace' in d): + cg = d['ftrace'] + cg.start = self.trimTimeVal(cg.start, t0, dT, left) + cg.end = self.trimTimeVal(cg.end, t0, dT, left) + for line in cg.list: + line.time = self.trimTimeVal(line.time, t0, dT, left) + if('src' in d): + for e in d['src']: + e.time = self.trimTimeVal(e.time, t0, dT, left) + def normalizeTime(self, tZero): + # trim out any standby or freeze clock time + if(self.tSuspended != self.tResumed): + if(self.tResumed > tZero): + self.trimTime(self.tSuspended, \ + self.tResumed-self.tSuspended, True) + else: + self.trimTime(self.tSuspended, \ + self.tResumed-self.tSuspended, False) + def setPhase(self, phase, ktime, isbegin): + if(isbegin): + self.dmesg[phase]['start'] = ktime + else: + self.dmesg[phase]['end'] = ktime + def dmesgSortVal(self, phase): + return self.dmesg[phase]['order'] + def sortedPhases(self): + return sorted(self.dmesg, key=self.dmesgSortVal) + def sortedDevices(self, phase): + list = self.dmesg[phase]['list'] + slist = [] + tmp = dict() + for devname in list: + dev = list[devname] + if dev['length'] == 0: + continue + tmp[dev['start']] = devname + for t in sorted(tmp): + slist.append(tmp[t]) + return slist + def fixupInitcalls(self, phase): + # if any calls never returned, clip them at system resume end + phaselist = self.dmesg[phase]['list'] + for devname in phaselist: + dev = phaselist[devname] + if(dev['end'] < 0): + for p in self.phases: + if self.dmesg[p]['end'] > dev['start']: + dev['end'] = self.dmesg[p]['end'] + break + vprint('%s (%s): callback didnt return' % (devname, phase)) + def deviceFilter(self, devicefilter): + for phase in self.phases: + list = self.dmesg[phase]['list'] + rmlist = [] + for name in list: + keep = False + for filter in devicefilter: + if filter in name or \ + ('drv' in list[name] and filter in list[name]['drv']): + keep = True + if not keep: + rmlist.append(name) + for name in rmlist: + del list[name] + def fixupInitcallsThatDidntReturn(self): + # if any calls never returned, clip them at system resume end + for phase in self.phases: + self.fixupInitcalls(phase) + def phaseOverlap(self, phases): + rmgroups = [] + newgroup = [] + for group in self.devicegroups: + for phase in phases: + if phase not in group: + continue + for p in group: + if p not in newgroup: + newgroup.append(p) + if group not in rmgroups: + rmgroups.append(group) + for group in rmgroups: + self.devicegroups.remove(group) + self.devicegroups.append(newgroup) + def newActionGlobal(self, name, start, end, pid=-1, color=''): + # which phase is this device callback or action in + targetphase = 'none' + htmlclass = '' + overlap = 0.0 + phases = [] + for phase in self.phases: + pstart = self.dmesg[phase]['start'] + pend = self.dmesg[phase]['end'] + # see if the action overlaps this phase + o = max(0, min(end, pend) - max(start, pstart)) + if o > 0: + phases.append(phase) + # set the target phase to the one that overlaps most + if o > overlap: + if overlap > 0 and phase == 'post_resume': + continue + targetphase = phase + overlap = o + # if no target phase was found, pin it to the edge + if targetphase == 'none': + p0start = self.dmesg[self.phases[0]]['start'] + if start <= p0start: + targetphase = self.phases[0] + else: + targetphase = self.phases[-1] + if pid == -2: + htmlclass = ' bg' + elif pid == -3: + htmlclass = ' ps' + if len(phases) > 1: + htmlclass = ' bg' + self.phaseOverlap(phases) + if targetphase in self.phases: + newname = self.newAction(targetphase, name, pid, '', start, end, '', htmlclass, color) + return (targetphase, newname) + return False + def newAction(self, phase, name, pid, parent, start, end, drv, htmlclass='', color=''): + # new device callback for a specific phase + self.html_device_id += 1 + devid = '%s%d' % (self.idstr, self.html_device_id) + list = self.dmesg[phase]['list'] + length = -1.0 + if(start >= 0 and end >= 0): + length = end - start + if pid == -2: + i = 2 + origname = name + while(name in list): + name = '%s[%d]' % (origname, i) + i += 1 + list[name] = {'name': name, 'start': start, 'end': end, 'pid': pid, + 'par': parent, 'length': length, 'row': 0, 'id': devid, 'drv': drv } + if htmlclass: + list[name]['htmlclass'] = htmlclass + if color: + list[name]['color'] = color + return name + def deviceChildren(self, devname, phase): + devlist = [] + list = self.dmesg[phase]['list'] + for child in list: + if(list[child]['par'] == devname): + devlist.append(child) + return devlist + def printDetails(self): + vprint('Timeline Details:') + vprint(' test start: %f' % self.start) + vprint('kernel suspend start: %f' % self.tKernSus) + for phase in self.phases: + dc = len(self.dmesg[phase]['list']) + vprint(' %16s: %f - %f (%d devices)' % (phase, \ + self.dmesg[phase]['start'], self.dmesg[phase]['end'], dc)) + vprint(' kernel resume end: %f' % self.tKernRes) + vprint(' test end: %f' % self.end) + def deviceChildrenAllPhases(self, devname): + devlist = [] + for phase in self.phases: + list = self.deviceChildren(devname, phase) + for dev in list: + if dev not in devlist: + devlist.append(dev) + return devlist + def masterTopology(self, name, list, depth): + node = DeviceNode(name, depth) + for cname in list: + # avoid recursions + if name == cname: + continue + clist = self.deviceChildrenAllPhases(cname) + cnode = self.masterTopology(cname, clist, depth+1) + node.children.append(cnode) + return node + def printTopology(self, node): + html = '' + if node.name: + info = '' + drv = '' + for phase in self.phases: + list = self.dmesg[phase]['list'] + if node.name in list: + s = list[node.name]['start'] + e = list[node.name]['end'] + if list[node.name]['drv']: + drv = ' {'+list[node.name]['drv']+'}' + info += ('<li>%s: %.3fms</li>' % (phase, (e-s)*1000)) + html += '<li><b>'+node.name+drv+'</b>' + if info: + html += '<ul>'+info+'</ul>' + html += '</li>' + if len(node.children) > 0: + html += '<ul>' + for cnode in node.children: + html += self.printTopology(cnode) + html += '</ul>' + return html + def rootDeviceList(self): + # list of devices graphed + real = [] + for phase in self.dmesg: + list = self.dmesg[phase]['list'] + for dev in list: + if list[dev]['pid'] >= 0 and dev not in real: + real.append(dev) + # list of top-most root devices + rootlist = [] + for phase in self.dmesg: + list = self.dmesg[phase]['list'] + for dev in list: + pdev = list[dev]['par'] + pid = list[dev]['pid'] + if(pid < 0 or re.match('[0-9]*-[0-9]*\.[0-9]*[\.0-9]*\:[\.0-9]*$', pdev)): + continue + if pdev and pdev not in real and pdev not in rootlist: + rootlist.append(pdev) + return rootlist + def deviceTopology(self): + rootlist = self.rootDeviceList() + master = self.masterTopology('', rootlist, 0) + return self.printTopology(master) + def selectTimelineDevices(self, widfmt, tTotal, mindevlen): + # only select devices that will actually show up in html + self.tdevlist = dict() + for phase in self.dmesg: + devlist = [] + list = self.dmesg[phase]['list'] + for dev in list: + length = (list[dev]['end'] - list[dev]['start']) * 1000 + width = widfmt % (((list[dev]['end']-list[dev]['start'])*100)/tTotal) + if width != '0.000000' and length >= mindevlen: + devlist.append(dev) + self.tdevlist[phase] = devlist + def addHorizontalDivider(self, devname, devend): + phase = 'suspend_prepare' + self.newAction(phase, devname, -2, '', \ + self.start, devend, '', ' sec', '') + if phase not in self.tdevlist: + self.tdevlist[phase] = [] + self.tdevlist[phase].append(devname) + d = DevItem(0, phase, self.dmesg[phase]['list'][devname]) + return d + def addProcessUsageEvent(self, name, times): + # get the start and end times for this process + maxC = 0 + tlast = 0 + start = -1 + end = -1 + for t in sorted(times): + if tlast == 0: + tlast = t + continue + if name in self.pstl[t]: + if start == -1 or tlast < start: + start = tlast + if end == -1 or t > end: + end = t + tlast = t + if start == -1 or end == -1: + return 0 + # add a new action for this process and get the object + out = self.newActionGlobal(name, start, end, -3) + if not out: + return 0 + phase, devname = out + dev = self.dmesg[phase]['list'][devname] + # get the cpu exec data + tlast = 0 + clast = 0 + cpuexec = dict() + for t in sorted(times): + if tlast == 0 or t <= start or t > end: + tlast = t + continue + list = self.pstl[t] + c = 0 + if name in list: + c = list[name] + if c > maxC: + maxC = c + if c != clast: + key = (tlast, t) + cpuexec[key] = c + tlast = t + clast = c + dev['cpuexec'] = cpuexec + return maxC + def createProcessUsageEvents(self): + # get an array of process names + proclist = [] + for t in self.pstl: + pslist = self.pstl[t] + for ps in pslist: + if ps not in proclist: + proclist.append(ps) + # get a list of data points for suspend and resume + tsus = [] + tres = [] + for t in sorted(self.pstl): + if t < self.tSuspended: + tsus.append(t) + else: + tres.append(t) + # process the events for suspend and resume + if len(proclist) > 0: + vprint('Process Execution:') + for ps in proclist: + c = self.addProcessUsageEvent(ps, tsus) + if c > 0: + vprint('%25s (sus): %d' % (ps, c)) + c = self.addProcessUsageEvent(ps, tres) + if c > 0: + vprint('%25s (res): %d' % (ps, c)) + +# Class: DevFunction +# Description: +# A container for kprobe function data we want in the dev timeline +class DevFunction: + row = 0 + count = 1 + def __init__(self, name, args, caller, ret, start, end, u, proc, pid, color): + self.name = name + self.args = args + self.caller = caller + self.ret = ret + self.time = start + self.length = end - start + self.end = end + self.ubiquitous = u + self.proc = proc + self.pid = pid + self.color = color + def title(self): + cnt = '' + if self.count > 1: + cnt = '(x%d)' % self.count + l = '%0.3fms' % (self.length * 1000) + if self.ubiquitous: + title = '%s(%s)%s <- %s, %s(%s)' % \ + (self.name, self.args, cnt, self.caller, self.ret, l) + else: + title = '%s(%s) %s%s(%s)' % (self.name, self.args, self.ret, cnt, l) + return title.replace('"', '') + def text(self): + if self.count > 1: + text = '%s(x%d)' % (self.name, self.count) + else: + text = self.name + return text + def repeat(self, tgt): + # is the tgt call just a repeat of this call (e.g. are we in a loop) + dt = self.time - tgt.end + # only combine calls if -all- attributes are identical + if tgt.caller == self.caller and \ + tgt.name == self.name and tgt.args == self.args and \ + tgt.proc == self.proc and tgt.pid == self.pid and \ + tgt.ret == self.ret and dt >= 0 and \ + dt <= sysvals.callloopmaxgap and \ + self.length < sysvals.callloopmaxlen: + return True + return False + +# Class: FTraceLine +# Description: +# A container for a single line of ftrace data. There are six basic types: +# callgraph line: +# call: " dpm_run_callback() {" +# return: " }" +# leaf: " dpm_run_callback();" +# trace event: +# tracing_mark_write: SUSPEND START or RESUME COMPLETE +# suspend_resume: phase or custom exec block data +# device_pm_callback: device callback info +class FTraceLine: + time = 0.0 + length = 0.0 + fcall = False + freturn = False + fevent = False + fkprobe = False + depth = 0 + name = '' + type = '' + def __init__(self, t, m='', d=''): + self.time = float(t) + if not m and not d: + return + # is this a trace event + if(d == 'traceevent' or re.match('^ *\/\* *(?P<msg>.*) \*\/ *$', m)): + if(d == 'traceevent'): + # nop format trace event + msg = m + else: + # function_graph format trace event + em = re.match('^ *\/\* *(?P<msg>.*) \*\/ *$', m) + msg = em.group('msg') + + emm = re.match('^(?P<call>.*?): (?P<msg>.*)', msg) + if(emm): + self.name = emm.group('msg') + self.type = emm.group('call') + else: + self.name = msg + km = re.match('^(?P<n>.*)_cal$', self.type) + if km: + self.fcall = True + self.fkprobe = True + self.type = km.group('n') + return + km = re.match('^(?P<n>.*)_ret$', self.type) + if km: + self.freturn = True + self.fkprobe = True + self.type = km.group('n') + return + self.fevent = True + return + # convert the duration to seconds + if(d): + self.length = float(d)/1000000 + # the indentation determines the depth + match = re.match('^(?P<d> *)(?P<o>.*)$', m) + if(not match): + return + self.depth = self.getDepth(match.group('d')) + m = match.group('o') + # function return + if(m[0] == '}'): + self.freturn = True + if(len(m) > 1): + # includes comment with function name + match = re.match('^} *\/\* *(?P<n>.*) *\*\/$', m) + if(match): + self.name = match.group('n').strip() + # function call + else: + self.fcall = True + # function call with children + if(m[-1] == '{'): + match = re.match('^(?P<n>.*) *\(.*', m) + if(match): + self.name = match.group('n').strip() + # function call with no children (leaf) + elif(m[-1] == ';'): + self.freturn = True + match = re.match('^(?P<n>.*) *\(.*', m) + if(match): + self.name = match.group('n').strip() + # something else (possibly a trace marker) + else: + self.name = m + def getDepth(self, str): + return len(str)/2 + def debugPrint(self, dev=''): + if(self.freturn and self.fcall): + print('%s -- %f (%02d): %s(); (%.3f us)' % (dev, self.time, \ + self.depth, self.name, self.length*1000000)) + elif(self.freturn): + print('%s -- %f (%02d): %s} (%.3f us)' % (dev, self.time, \ + self.depth, self.name, self.length*1000000)) + else: + print('%s -- %f (%02d): %s() { (%.3f us)' % (dev, self.time, \ + self.depth, self.name, self.length*1000000)) + def startMarker(self): + # Is this the starting line of a suspend? + if not self.fevent: + return False + if sysvals.usetracemarkers: + if(self.name == 'SUSPEND START'): + return True + return False + else: + if(self.type == 'suspend_resume' and + re.match('suspend_enter\[.*\] begin', self.name)): + return True + return False + def endMarker(self): + # Is this the ending line of a resume? + if not self.fevent: + return False + if sysvals.usetracemarkers: + if(self.name == 'RESUME COMPLETE'): + return True + return False + else: + if(self.type == 'suspend_resume' and + re.match('thaw_processes\[.*\] end', self.name)): + return True + return False + +# Class: FTraceCallGraph +# Description: +# A container for the ftrace callgraph of a single recursive function. +# This can be a dpm_run_callback, dpm_prepare, or dpm_complete callgraph +# Each instance is tied to a single device in a single phase, and is +# comprised of an ordered list of FTraceLine objects +class FTraceCallGraph: + id = '' + start = -1.0 + end = -1.0 + list = [] + invalid = False + depth = 0 + pid = 0 + name = '' + def __init__(self, pid): + self.start = -1.0 + self.end = -1.0 + self.list = [] + self.depth = 0 + self.pid = pid + def addLine(self, line, debug=False): + # if this is already invalid, just leave + if(self.invalid): + return False + # invalidate on too much data or bad depth + if(len(self.list) >= 1000000 or self.depth < 0): + self.invalidate(line) + return False + # compare current depth with this lines pre-call depth + prelinedep = line.depth + if(line.freturn and not line.fcall): + prelinedep += 1 + last = 0 + lasttime = line.time + virtualfname = 'execution_misalignment' + if len(self.list) > 0: + last = self.list[-1] + lasttime = last.time + # handle low misalignments by inserting returns + if prelinedep < self.depth: + if debug and last: + print '-------- task %d --------' % self.pid + last.debugPrint() + idx = 0 + # add return calls to get the depth down + while prelinedep < self.depth: + if debug: + print 'MISALIGN LOW (add returns): C%d - eC%d' % (self.depth, prelinedep) + self.depth -= 1 + if idx == 0 and last and last.fcall and not last.freturn: + # special case, turn last call into a leaf + last.depth = self.depth + last.freturn = True + last.length = line.time - last.time + if debug: + last.debugPrint() + else: + vline = FTraceLine(lasttime) + vline.depth = self.depth + vline.name = virtualfname + vline.freturn = True + self.list.append(vline) + if debug: + vline.debugPrint() + idx += 1 + if debug: + line.debugPrint() + print '' + # handle high misalignments by inserting calls + elif prelinedep > self.depth: + if debug and last: + print '-------- task %d --------' % self.pid + last.debugPrint() + idx = 0 + # add calls to get the depth up + while prelinedep > self.depth: + if debug: + print 'MISALIGN HIGH (add calls): C%d - eC%d' % (self.depth, prelinedep) + if idx == 0 and line.freturn and not line.fcall: + # special case, turn this return into a leaf + line.fcall = True + prelinedep -= 1 + else: + vline = FTraceLine(lasttime) + vline.depth = self.depth + vline.name = virtualfname + vline.fcall = True + if debug: + vline.debugPrint() + self.list.append(vline) + self.depth += 1 + if not last: + self.start = vline.time + idx += 1 + if debug: + line.debugPrint() + print '' + # process the call and set the new depth + if(line.fcall and not line.freturn): + self.depth += 1 + elif(line.freturn and not line.fcall): + self.depth -= 1 + if len(self.list) < 1: + self.start = line.time + self.list.append(line) + if(line.depth == 0 and line.freturn): + if(self.start < 0): + self.start = line.time + self.end = line.time + if line.fcall: + self.end += line.length + if self.list[0].name == virtualfname: + self.invalid = True + return True + return False + def invalidate(self, line): + if(len(self.list) > 0): + first = self.list[0] + self.list = [] + self.list.append(first) + self.invalid = True + id = 'task %s' % (self.pid) + window = '(%f - %f)' % (self.start, line.time) + if(self.depth < 0): + vprint('Too much data for '+id+\ + ' (buffer overflow), ignoring this callback') + else: + vprint('Too much data for '+id+\ + ' '+window+', ignoring this callback') + def slice(self, t0, tN): + minicg = FTraceCallGraph(0) + count = -1 + firstdepth = 0 + for l in self.list: + if(l.time < t0 or l.time > tN): + continue + if(count < 0): + if(not l.fcall or l.name == 'dev_driver_string'): + continue + firstdepth = l.depth + count = 0 + l.depth -= firstdepth + minicg.addLine(l) + if((count == 0 and l.freturn and l.fcall) or + (count > 0 and l.depth <= 0)): + break + count += 1 + return minicg + def repair(self, enddepth): + # bring the depth back to 0 with additional returns + fixed = False + last = self.list[-1] + for i in reversed(range(enddepth)): + t = FTraceLine(last.time) + t.depth = i + t.freturn = True + fixed = self.addLine(t) + if fixed: + self.end = last.time + return True + return False + def postProcess(self, debug=False): + if len(self.list) > 0: + self.name = self.list[0].name + stack = dict() + cnt = 0 + last = 0 + for l in self.list: + # ftrace bug: reported duration is not reliable + # check each leaf and clip it at max possible length + if(last and last.freturn and last.fcall): + if last.length > l.time - last.time: + last.length = l.time - last.time + if(l.fcall and not l.freturn): + stack[l.depth] = l + cnt += 1 + elif(l.freturn and not l.fcall): + if(l.depth not in stack): + if debug: + print 'Post Process Error: Depth missing' + l.debugPrint() + return False + # calculate call length from call/return lines + stack[l.depth].length = l.time - stack[l.depth].time + stack.pop(l.depth) + l.length = 0 + cnt -= 1 + last = l + if(cnt == 0): + # trace caught the whole call tree + return True + elif(cnt < 0): + if debug: + print 'Post Process Error: Depth is less than 0' + return False + # trace ended before call tree finished + return self.repair(cnt) + def deviceMatch(self, pid, data): + found = False + # add the callgraph data to the device hierarchy + borderphase = { + 'dpm_prepare': 'suspend_prepare', + 'dpm_complete': 'resume_complete' + } + if(self.name in borderphase): + p = borderphase[self.name] + list = data.dmesg[p]['list'] + for devname in list: + dev = list[devname] + if(pid == dev['pid'] and + self.start <= dev['start'] and + self.end >= dev['end']): + dev['ftrace'] = self.slice(dev['start'], dev['end']) + found = True + return found + for p in data.phases: + if(data.dmesg[p]['start'] <= self.start and + self.start <= data.dmesg[p]['end']): + list = data.dmesg[p]['list'] + for devname in list: + dev = list[devname] + if(pid == dev['pid'] and + self.start <= dev['start'] and + self.end >= dev['end']): + dev['ftrace'] = self + found = True + break + break + return found + def newActionFromFunction(self, data): + name = self.name + if name in ['dpm_run_callback', 'dpm_prepare', 'dpm_complete']: + return + fs = self.start + fe = self.end + if fs < data.start or fe > data.end: + return + phase = '' + for p in data.phases: + if(data.dmesg[p]['start'] <= self.start and + self.start < data.dmesg[p]['end']): + phase = p + break + if not phase: + return + out = data.newActionGlobal(name, fs, fe, -2) + if out: + phase, myname = out + data.dmesg[phase]['list'][myname]['ftrace'] = self + def debugPrint(self): + print('[%f - %f] %s (%d)') % (self.start, self.end, self.name, self.pid) + for l in self.list: + if(l.freturn and l.fcall): + print('%f (%02d): %s(); (%.3f us)' % (l.time, \ + l.depth, l.name, l.length*1000000)) + elif(l.freturn): + print('%f (%02d): %s} (%.3f us)' % (l.time, \ + l.depth, l.name, l.length*1000000)) + else: + print('%f (%02d): %s() { (%.3f us)' % (l.time, \ + l.depth, l.name, l.length*1000000)) + print(' ') + +class DevItem: + def __init__(self, test, phase, dev): + self.test = test + self.phase = phase + self.dev = dev + def isa(self, cls): + if 'htmlclass' in self.dev and cls in self.dev['htmlclass']: + return True + return False + +# Class: Timeline +# Description: +# A container for a device timeline which calculates +# all the html properties to display it correctly +class Timeline: + html = '' + height = 0 # total timeline height + scaleH = 20 # timescale (top) row height + rowH = 30 # device row height + bodyH = 0 # body height + rows = 0 # total timeline rows + rowlines = dict() + rowheight = dict() + html_tblock = '<div id="block{0}" class="tblock" style="left:{1}%;width:{2}%;"><div class="tback" style="height:{3}px"></div>\n' + html_device = '<div id="{0}" title="{1}" class="thread{7}" style="left:{2}%;top:{3}px;height:{4}px;width:{5}%;{8}">{6}</div>\n' + html_phase = '<div class="phase" style="left:{0}%;width:{1}%;top:{2}px;height:{3}px;background:{4}">{5}</div>\n' + html_phaselet = '<div id="{0}" class="phaselet" style="left:{1}%;width:{2}%;background:{3}"></div>\n' + def __init__(self, rowheight, scaleheight): + self.rowH = rowheight + self.scaleH = scaleheight + self.html = '' + def createHeader(self, sv, suppress=''): + if(not sv.stamp['time']): + return + self.html += '<div class="version"><a href="https://01.org/suspendresume">%s v%s</a></div>' \ + % (sv.title, sv.version) + if sv.logmsg and 'log' not in suppress: + self.html += '<button id="showtest" class="logbtn">log</button>' + if sv.addlogs and 'dmesg' not in suppress: + self.html += '<button id="showdmesg" class="logbtn">dmesg</button>' + if sv.addlogs and sv.ftracefile and 'ftrace' not in suppress: + self.html += '<button id="showftrace" class="logbtn">ftrace</button>' + headline_stamp = '<div class="stamp">{0} {1} {2} {3}</div>\n' + self.html += headline_stamp.format(sv.stamp['host'], sv.stamp['kernel'], + sv.stamp['mode'], sv.stamp['time']) + # Function: getDeviceRows + # Description: + # determine how may rows the device funcs will take + # Arguments: + # rawlist: the list of devices/actions for a single phase + # Output: + # The total number of rows needed to display this phase of the timeline + def getDeviceRows(self, rawlist): + # clear all rows and set them to undefined + sortdict = dict() + for item in rawlist: + item.row = -1 + sortdict[item] = item.length + sortlist = sorted(sortdict, key=sortdict.get, reverse=True) + remaining = len(sortlist) + rowdata = dict() + row = 1 + # try to pack each row with as many ranges as possible + while(remaining > 0): + if(row not in rowdata): + rowdata[row] = [] + for i in sortlist: + if(i.row >= 0): + continue + s = i.time + e = i.time + i.length + valid = True + for ritem in rowdata[row]: + rs = ritem.time + re = ritem.time + ritem.length + if(not (((s <= rs) and (e <= rs)) or + ((s >= re) and (e >= re)))): + valid = False + break + if(valid): + rowdata[row].append(i) + i.row = row + remaining -= 1 + row += 1 + return row + # Function: getPhaseRows + # Description: + # Organize the timeline entries into the smallest + # number of rows possible, with no entry overlapping + # Arguments: + # devlist: the list of devices/actions in a group of contiguous phases + # Output: + # The total number of rows needed to display this phase of the timeline + def getPhaseRows(self, devlist, row=0): + # clear all rows and set them to undefined + remaining = len(devlist) + rowdata = dict() + sortdict = dict() + myphases = [] + # initialize all device rows to -1 and calculate devrows + for item in devlist: + dev = item.dev + tp = (item.test, item.phase) + if tp not in myphases: + myphases.append(tp) + dev['row'] = -1 + # sort by length 1st, then name 2nd + sortdict[item] = (float(dev['end']) - float(dev['start']), item.dev['name']) + if 'src' in dev: + dev['devrows'] = self.getDeviceRows(dev['src']) + # sort the devlist by length so that large items graph on top + sortlist = sorted(sortdict, key=sortdict.get, reverse=True) + orderedlist = [] + for item in sortlist: + if item.dev['pid'] == -2: + orderedlist.append(item) + for item in sortlist: + if item not in orderedlist: + orderedlist.append(item) + # try to pack each row with as many devices as possible + while(remaining > 0): + rowheight = 1 + if(row not in rowdata): + rowdata[row] = [] + for item in orderedlist: + dev = item.dev + if(dev['row'] < 0): + s = dev['start'] + e = dev['end'] + valid = True + for ritem in rowdata[row]: + rs = ritem.dev['start'] + re = ritem.dev['end'] + if(not (((s <= rs) and (e <= rs)) or + ((s >= re) and (e >= re)))): + valid = False + break + if(valid): + rowdata[row].append(item) + dev['row'] = row + remaining -= 1 + if 'devrows' in dev and dev['devrows'] > rowheight: + rowheight = dev['devrows'] + for t, p in myphases: + if t not in self.rowlines or t not in self.rowheight: + self.rowlines[t] = dict() + self.rowheight[t] = dict() + if p not in self.rowlines[t] or p not in self.rowheight[t]: + self.rowlines[t][p] = dict() + self.rowheight[t][p] = dict() + rh = self.rowH + # section headers should use a different row height + if len(rowdata[row]) == 1 and \ + 'htmlclass' in rowdata[row][0].dev and \ + 'sec' in rowdata[row][0].dev['htmlclass']: + rh = 15 + self.rowlines[t][p][row] = rowheight + self.rowheight[t][p][row] = rowheight * rh + row += 1 + if(row > self.rows): + self.rows = int(row) + return row + def phaseRowHeight(self, test, phase, row): + return self.rowheight[test][phase][row] + def phaseRowTop(self, test, phase, row): + top = 0 + for i in sorted(self.rowheight[test][phase]): + if i >= row: + break + top += self.rowheight[test][phase][i] + return top + def calcTotalRows(self): + # Calculate the heights and offsets for the header and rows + maxrows = 0 + standardphases = [] + for t in self.rowlines: + for p in self.rowlines[t]: + total = 0 + for i in sorted(self.rowlines[t][p]): + total += self.rowlines[t][p][i] + if total > maxrows: + maxrows = total + if total == len(self.rowlines[t][p]): + standardphases.append((t, p)) + self.height = self.scaleH + (maxrows*self.rowH) + self.bodyH = self.height - self.scaleH + # if there is 1 line per row, draw them the standard way + for t, p in standardphases: + for i in sorted(self.rowheight[t][p]): + self.rowheight[t][p][i] = self.bodyH/len(self.rowlines[t][p]) + def createZoomBox(self, mode='command', testcount=1): + # Create bounding box, add buttons + html_zoombox = '<center><button id="zoomin">ZOOM IN +</button><button id="zoomout">ZOOM OUT -</button><button id="zoomdef">ZOOM 1:1</button></center>\n' + html_timeline = '<div id="dmesgzoombox" class="zoombox">\n<div id="{0}" class="timeline" style="height:{1}px">\n' + html_devlist1 = '<button id="devlist1" class="devlist" style="float:left;">Device Detail{0}</button>' + html_devlist2 = '<button id="devlist2" class="devlist" style="float:right;">Device Detail2</button>\n' + if mode != 'command': + if testcount > 1: + self.html += html_devlist2 + self.html += html_devlist1.format('1') + else: + self.html += html_devlist1.format('') + self.html += html_zoombox + self.html += html_timeline.format('dmesg', self.height) + # Function: createTimeScale + # Description: + # Create the timescale for a timeline block + # Arguments: + # m0: start time (mode begin) + # mMax: end time (mode end) + # tTotal: total timeline time + # mode: suspend or resume + # Output: + # The html code needed to display the time scale + def createTimeScale(self, m0, mMax, tTotal, mode): + timescale = '<div class="t" style="right:{0}%">{1}</div>\n' + rline = '<div class="t" style="left:0;border-left:1px solid black;border-right:0;">{0}</div>\n' + output = '<div class="timescale">\n' + # set scale for timeline + mTotal = mMax - m0 + tS = 0.1 + if(tTotal <= 0): + return output+'</div>\n' + if(tTotal > 4): + tS = 1 + divTotal = int(mTotal/tS) + 1 + divEdge = (mTotal - tS*(divTotal-1))*100/mTotal + for i in range(divTotal): + htmlline = '' + if(mode == 'suspend'): + pos = '%0.3f' % (100 - ((float(i)*tS*100)/mTotal) - divEdge) + val = '%0.fms' % (float(i-divTotal+1)*tS*1000) + if(i == divTotal - 1): + val = mode + htmlline = timescale.format(pos, val) + else: + pos = '%0.3f' % (100 - ((float(i)*tS*100)/mTotal)) + val = '%0.fms' % (float(i)*tS*1000) + htmlline = timescale.format(pos, val) + if(i == 0): + htmlline = rline.format(mode) + output += htmlline + self.html += output+'</div>\n' + +# Class: TestProps +# Description: +# A list of values describing the properties of these test runs +class TestProps: + stamp = '' + S0i3 = False + fwdata = [] + ftrace_line_fmt_fg = \ + '^ *(?P<time>[0-9\.]*) *\| *(?P<cpu>[0-9]*)\)'+\ + ' *(?P<proc>.*)-(?P<pid>[0-9]*) *\|'+\ + '[ +!#\*@$]*(?P<dur>[0-9\.]*) .*\| (?P<msg>.*)' + ftrace_line_fmt_nop = \ + ' *(?P<proc>.*)-(?P<pid>[0-9]*) *\[(?P<cpu>[0-9]*)\] *'+\ + '(?P<flags>.{4}) *(?P<time>[0-9\.]*): *'+\ + '(?P<msg>.*)' + ftrace_line_fmt = ftrace_line_fmt_nop + cgformat = False + data = 0 + ktemp = dict() + def __init__(self): + self.ktemp = dict() + def setTracerType(self, tracer): + if(tracer == 'function_graph'): + self.cgformat = True + self.ftrace_line_fmt = self.ftrace_line_fmt_fg + elif(tracer == 'nop'): + self.ftrace_line_fmt = self.ftrace_line_fmt_nop + else: + doError('Invalid tracer format: [%s]' % tracer) + +# Class: TestRun +# Description: +# A container for a suspend/resume test run. This is necessary as +# there could be more than one, and they need to be separate. +class TestRun: + ftemp = dict() + ttemp = dict() + data = 0 + def __init__(self, dataobj): + self.data = dataobj + self.ftemp = dict() + self.ttemp = dict() + +class ProcessMonitor: + proclist = dict() + running = False + def procstat(self): + c = ['cat /proc/[1-9]*/stat 2>/dev/null'] + process = Popen(c, shell=True, stdout=PIPE) + running = dict() + for line in process.stdout: + data = line.split() + pid = data[0] + name = re.sub('[()]', '', data[1]) + user = int(data[13]) + kern = int(data[14]) + kjiff = ujiff = 0 + if pid not in self.proclist: + self.proclist[pid] = {'name' : name, 'user' : user, 'kern' : kern} + else: + val = self.proclist[pid] + ujiff = user - val['user'] + kjiff = kern - val['kern'] + val['user'] = user + val['kern'] = kern + if ujiff > 0 or kjiff > 0: + running[pid] = ujiff + kjiff + process.wait() + out = '' + for pid in running: + jiffies = running[pid] + val = self.proclist[pid] + if out: + out += ',' + out += '%s-%s %d' % (val['name'], pid, jiffies) + return 'ps - '+out + def processMonitor(self, tid): + while self.running: + out = self.procstat() + if out: + sysvals.fsetVal(out, 'trace_marker') + def start(self): + self.thread = Thread(target=self.processMonitor, args=(0,)) + self.running = True + self.thread.start() + def stop(self): + self.running = False + +# ----------------- FUNCTIONS -------------------- + +# Function: vprint +# Description: +# verbose print (prints only with -verbose option) +# Arguments: +# msg: the debug/log message to print +def vprint(msg): + sysvals.logmsg += msg+'\n' + if(sysvals.verbose): + print(msg) + +# Function: parseStamp +# Description: +# Pull in the stamp comment line from the data file(s), +# create the stamp, and add it to the global sysvals object +# Arguments: +# m: the valid re.match output for the stamp line +def parseStamp(line, data): + m = re.match(sysvals.stampfmt, line) + data.stamp = {'time': '', 'host': '', 'mode': ''} + dt = datetime(int(m.group('y'))+2000, int(m.group('m')), + int(m.group('d')), int(m.group('H')), int(m.group('M')), + int(m.group('S'))) + data.stamp['time'] = dt.strftime('%B %d %Y, %I:%M:%S %p') + data.stamp['host'] = m.group('host') + data.stamp['mode'] = m.group('mode') + data.stamp['kernel'] = m.group('kernel') + sysvals.hostname = data.stamp['host'] + sysvals.suspendmode = data.stamp['mode'] + if sysvals.suspendmode == 'command' and sysvals.ftracefile != '': + modes = ['on', 'freeze', 'standby', 'mem'] + out = Popen(['grep', 'suspend_enter', sysvals.ftracefile], + stderr=PIPE, stdout=PIPE).stdout.read() + m = re.match('.* suspend_enter\[(?P<mode>.*)\]', out) + if m and m.group('mode') in ['1', '2', '3']: + sysvals.suspendmode = modes[int(m.group('mode'))] + data.stamp['mode'] = sysvals.suspendmode + if not sysvals.stamp: + sysvals.stamp = data.stamp + +# Function: doesTraceLogHaveTraceEvents +# Description: +# Quickly determine if the ftrace log has some or all of the trace events +# required for primary parsing. Set the usetraceevents and/or +# usetraceeventsonly flags in the global sysvals object +def doesTraceLogHaveTraceEvents(): + # check for kprobes + sysvals.usekprobes = False + out = call('grep -q "_cal: (" '+sysvals.ftracefile, shell=True) + if(out == 0): + sysvals.usekprobes = True + # check for callgraph data on trace event blocks + out = call('grep -q "_cpu_down()" '+sysvals.ftracefile, shell=True) + if(out == 0): + sysvals.usekprobes = True + out = Popen(['head', '-1', sysvals.ftracefile], + stderr=PIPE, stdout=PIPE).stdout.read().replace('\n', '') + m = re.match(sysvals.stampfmt, out) + if m and m.group('mode') == 'command': + sysvals.usetraceeventsonly = True + sysvals.usetraceevents = True + return + # figure out what level of trace events are supported + sysvals.usetraceeventsonly = True + sysvals.usetraceevents = False + for e in sysvals.traceevents: + out = call('grep -q "'+e+': " '+sysvals.ftracefile, shell=True) + if(out != 0): + sysvals.usetraceeventsonly = False + if(e == 'suspend_resume' and out == 0): + sysvals.usetraceevents = True + # determine is this log is properly formatted + for e in ['SUSPEND START', 'RESUME COMPLETE']: + out = call('grep -q "'+e+'" '+sysvals.ftracefile, shell=True) + if(out != 0): + sysvals.usetracemarkers = False + +# Function: appendIncompleteTraceLog +# Description: +# [deprecated for kernel 3.15 or newer] +# Legacy support of ftrace outputs that lack the device_pm_callback +# and/or suspend_resume trace events. The primary data should be +# taken from dmesg, and this ftrace is used only for callgraph data +# or custom actions in the timeline. The data is appended to the Data +# objects provided. +# Arguments: +# testruns: the array of Data objects obtained from parseKernelLog +def appendIncompleteTraceLog(testruns): + # create TestRun vessels for ftrace parsing + testcnt = len(testruns) + testidx = 0 + testrun = [] + for data in testruns: + testrun.append(TestRun(data)) + + # extract the callgraph and traceevent data + vprint('Analyzing the ftrace data...') + tp = TestProps() + tf = open(sysvals.ftracefile, 'r') + data = 0 + for line in tf: + # remove any latent carriage returns + line = line.replace('\r\n', '') + # grab the time stamp + m = re.match(sysvals.stampfmt, line) + if(m): + tp.stamp = line + continue + # determine the trace data type (required for further parsing) + m = re.match(sysvals.tracertypefmt, line) + if(m): + tp.setTracerType(m.group('t')) + continue + # device properties line + if(re.match(sysvals.devpropfmt, line)): + devProps(line) + continue + # parse only valid lines, if this is not one move on + m = re.match(tp.ftrace_line_fmt, line) + if(not m): + continue + # gather the basic message data from the line + m_time = m.group('time') + m_pid = m.group('pid') + m_msg = m.group('msg') + if(tp.cgformat): + m_param3 = m.group('dur') + else: + m_param3 = 'traceevent' + if(m_time and m_pid and m_msg): + t = FTraceLine(m_time, m_msg, m_param3) + pid = int(m_pid) + else: + continue + # the line should be a call, return, or event + if(not t.fcall and not t.freturn and not t.fevent): + continue + # look for the suspend start marker + if(t.startMarker()): + data = testrun[testidx].data + parseStamp(tp.stamp, data) + data.setStart(t.time) + continue + if(not data): + continue + # find the end of resume + if(t.endMarker()): + data.setEnd(t.time) + testidx += 1 + if(testidx >= testcnt): + break + continue + # trace event processing + if(t.fevent): + # general trace events have two types, begin and end + if(re.match('(?P<name>.*) begin$', t.name)): + isbegin = True + elif(re.match('(?P<name>.*) end$', t.name)): + isbegin = False + else: + continue + m = re.match('(?P<name>.*)\[(?P<val>[0-9]*)\] .*', t.name) + if(m): + val = m.group('val') + if val == '0': + name = m.group('name') + else: + name = m.group('name')+'['+val+']' + else: + m = re.match('(?P<name>.*) .*', t.name) + name = m.group('name') + # special processing for trace events + if re.match('dpm_prepare\[.*', name): + continue + elif re.match('machine_suspend.*', name): + continue + elif re.match('suspend_enter\[.*', name): + if(not isbegin): + data.dmesg['suspend_prepare']['end'] = t.time + continue + elif re.match('dpm_suspend\[.*', name): + if(not isbegin): + data.dmesg['suspend']['end'] = t.time + continue + elif re.match('dpm_suspend_late\[.*', name): + if(isbegin): + data.dmesg['suspend_late']['start'] = t.time + else: + data.dmesg['suspend_late']['end'] = t.time + continue + elif re.match('dpm_suspend_noirq\[.*', name): + if(isbegin): + data.dmesg['suspend_noirq']['start'] = t.time + else: + data.dmesg['suspend_noirq']['end'] = t.time + continue + elif re.match('dpm_resume_noirq\[.*', name): + if(isbegin): + data.dmesg['resume_machine']['end'] = t.time + data.dmesg['resume_noirq']['start'] = t.time + else: + data.dmesg['resume_noirq']['end'] = t.time + continue + elif re.match('dpm_resume_early\[.*', name): + if(isbegin): + data.dmesg['resume_early']['start'] = t.time + else: + data.dmesg['resume_early']['end'] = t.time + continue + elif re.match('dpm_resume\[.*', name): + if(isbegin): + data.dmesg['resume']['start'] = t.time + else: + data.dmesg['resume']['end'] = t.time + continue + elif re.match('dpm_complete\[.*', name): + if(isbegin): + data.dmesg['resume_complete']['start'] = t.time + else: + data.dmesg['resume_complete']['end'] = t.time + continue + # skip trace events inside devices calls + if(not data.isTraceEventOutsideDeviceCalls(pid, t.time)): + continue + # global events (outside device calls) are simply graphed + if(isbegin): + # store each trace event in ttemp + if(name not in testrun[testidx].ttemp): + testrun[testidx].ttemp[name] = [] + testrun[testidx].ttemp[name].append(\ + {'begin': t.time, 'end': t.time}) + else: + # finish off matching trace event in ttemp + if(name in testrun[testidx].ttemp): + testrun[testidx].ttemp[name][-1]['end'] = t.time + # call/return processing + elif sysvals.usecallgraph: + # create a callgraph object for the data + if(pid not in testrun[testidx].ftemp): + testrun[testidx].ftemp[pid] = [] + testrun[testidx].ftemp[pid].append(FTraceCallGraph(pid)) + # when the call is finished, see which device matches it + cg = testrun[testidx].ftemp[pid][-1] + if(cg.addLine(t)): + testrun[testidx].ftemp[pid].append(FTraceCallGraph(pid)) + tf.close() + + for test in testrun: + # add the traceevent data to the device hierarchy + if(sysvals.usetraceevents): + for name in test.ttemp: + for event in test.ttemp[name]: + test.data.newActionGlobal(name, event['begin'], event['end']) + + # add the callgraph data to the device hierarchy + for pid in test.ftemp: + for cg in test.ftemp[pid]: + if len(cg.list) < 1 or cg.invalid: + continue + if(not cg.postProcess()): + id = 'task %s cpu %s' % (pid, m.group('cpu')) + vprint('Sanity check failed for '+\ + id+', ignoring this callback') + continue + callstart = cg.start + callend = cg.end + for p in test.data.phases: + if(test.data.dmesg[p]['start'] <= callstart and + callstart <= test.data.dmesg[p]['end']): + list = test.data.dmesg[p]['list'] + for devname in list: + dev = list[devname] + if(pid == dev['pid'] and + callstart <= dev['start'] and + callend >= dev['end']): + dev['ftrace'] = cg + break + + test.data.printDetails() + +# Function: parseTraceLog +# Description: +# Analyze an ftrace log output file generated from this app during +# the execution phase. Used when the ftrace log is the primary data source +# and includes the suspend_resume and device_pm_callback trace events +# The ftrace filename is taken from sysvals +# Output: +# An array of Data objects +def parseTraceLog(): + vprint('Analyzing the ftrace data...') + if(os.path.exists(sysvals.ftracefile) == False): + doError('%s does not exist' % sysvals.ftracefile) + + sysvals.setupAllKprobes() + tracewatch = [] + if sysvals.usekprobes: + tracewatch += ['sync_filesystems', 'freeze_processes', 'syscore_suspend', + 'syscore_resume', 'resume_console', 'thaw_processes', 'CPU_ON', 'CPU_OFF'] + + # extract the callgraph and traceevent data + tp = TestProps() + testruns = [] + testdata = [] + testrun = 0 + data = 0 + tf = open(sysvals.ftracefile, 'r') + phase = 'suspend_prepare' + for line in tf: + # remove any latent carriage returns + line = line.replace('\r\n', '') + # stamp line: each stamp means a new test run + m = re.match(sysvals.stampfmt, line) + if(m): + tp.stamp = line + continue + # firmware line: pull out any firmware data + m = re.match(sysvals.firmwarefmt, line) + if(m): + tp.fwdata.append((int(m.group('s')), int(m.group('r')))) + continue + # tracer type line: determine the trace data type + m = re.match(sysvals.tracertypefmt, line) + if(m): + tp.setTracerType(m.group('t')) + continue + # device properties line + if(re.match(sysvals.devpropfmt, line)): + devProps(line) + continue + # ignore all other commented lines + if line[0] == '#': + continue + # ftrace line: parse only valid lines + m = re.match(tp.ftrace_line_fmt, line) + if(not m): + continue + # gather the basic message data from the line + m_time = m.group('time') + m_proc = m.group('proc') + m_pid = m.group('pid') + m_msg = m.group('msg') + if(tp.cgformat): + m_param3 = m.group('dur') + else: + m_param3 = 'traceevent' + if(m_time and m_pid and m_msg): + t = FTraceLine(m_time, m_msg, m_param3) + pid = int(m_pid) + else: + continue + # the line should be a call, return, or event + if(not t.fcall and not t.freturn and not t.fevent): + continue + # find the start of suspend + if(t.startMarker()): + phase = 'suspend_prepare' + data = Data(len(testdata)) + testdata.append(data) + testrun = TestRun(data) + testruns.append(testrun) + parseStamp(tp.stamp, data) + data.setStart(t.time) + data.tKernSus = t.time + continue + if(not data): + continue + # process cpu exec line + if t.type == 'tracing_mark_write': + m = re.match(sysvals.procexecfmt, t.name) + if(m): + proclist = dict() + for ps in m.group('ps').split(','): + val = ps.split() + if not val: + continue + name = val[0].replace('--', '-') + proclist[name] = int(val[1]) + data.pstl[t.time] = proclist + continue + # find the end of resume + if(t.endMarker()): + data.setEnd(t.time) + if data.tKernRes == 0.0: + data.tKernRes = t.time + if data.dmesg['resume_complete']['end'] < 0: + data.dmesg['resume_complete']['end'] = t.time + if sysvals.suspendmode == 'mem' and len(tp.fwdata) > data.testnumber: + data.fwSuspend, data.fwResume = tp.fwdata[data.testnumber] + if(data.tSuspended != 0 and data.tResumed != 0 and \ + (data.fwSuspend > 0 or data.fwResume > 0)): + data.fwValid = True + if(not sysvals.usetracemarkers): + # no trace markers? then quit and be sure to finish recording + # the event we used to trigger resume end + if(len(testrun.ttemp['thaw_processes']) > 0): + # if an entry exists, assume this is its end + testrun.ttemp['thaw_processes'][-1]['end'] = t.time + break + continue + # trace event processing + if(t.fevent): + if(phase == 'post_resume'): + data.setEnd(t.time) + if(t.type == 'suspend_resume'): + # suspend_resume trace events have two types, begin and end + if(re.match('(?P<name>.*) begin$', t.name)): + isbegin = True + elif(re.match('(?P<name>.*) end$', t.name)): + isbegin = False + else: + continue + m = re.match('(?P<name>.*)\[(?P<val>[0-9]*)\] .*', t.name) + if(m): + val = m.group('val') + if val == '0': + name = m.group('name') + else: + name = m.group('name')+'['+val+']' + else: + m = re.match('(?P<name>.*) .*', t.name) + name = m.group('name') + # ignore these events + if(name.split('[')[0] in tracewatch): + continue + # -- phase changes -- + # start of kernel suspend + if(re.match('suspend_enter\[.*', t.name)): + if(isbegin): + data.dmesg[phase]['start'] = t.time + data.tKernSus = t.time + continue + # suspend_prepare start + elif(re.match('dpm_prepare\[.*', t.name)): + phase = 'suspend_prepare' + if(not isbegin): + data.dmesg[phase]['end'] = t.time + continue + # suspend start + elif(re.match('dpm_suspend\[.*', t.name)): + phase = 'suspend' + data.setPhase(phase, t.time, isbegin) + continue + # suspend_late start + elif(re.match('dpm_suspend_late\[.*', t.name)): + phase = 'suspend_late' + data.setPhase(phase, t.time, isbegin) + continue + # suspend_noirq start + elif(re.match('dpm_suspend_noirq\[.*', t.name)): + phase = 'suspend_noirq' + data.setPhase(phase, t.time, isbegin) + if(not isbegin): + phase = 'suspend_machine' + data.dmesg[phase]['start'] = t.time + continue + # suspend_machine/resume_machine + elif(re.match('machine_suspend\[.*', t.name)): + if(isbegin): + phase = 'suspend_machine' + data.dmesg[phase]['end'] = t.time + data.tSuspended = t.time + else: + if(sysvals.suspendmode in ['mem', 'disk'] and not tp.S0i3): + data.dmesg['suspend_machine']['end'] = t.time + data.tSuspended = t.time + phase = 'resume_machine' + data.dmesg[phase]['start'] = t.time + data.tResumed = t.time + data.tLow = data.tResumed - data.tSuspended + continue + # acpi_suspend + elif(re.match('acpi_suspend\[.*', t.name)): + # acpi_suspend[0] S0i3 + if(re.match('acpi_suspend\[0\] begin', t.name)): + if(sysvals.suspendmode == 'mem'): + tp.S0i3 = True + data.dmesg['suspend_machine']['end'] = t.time + data.tSuspended = t.time + continue + # resume_noirq start + elif(re.match('dpm_resume_noirq\[.*', t.name)): + phase = 'resume_noirq' + data.setPhase(phase, t.time, isbegin) + if(isbegin): + data.dmesg['resume_machine']['end'] = t.time + continue + # resume_early start + elif(re.match('dpm_resume_early\[.*', t.name)): + phase = 'resume_early' + data.setPhase(phase, t.time, isbegin) + continue + # resume start + elif(re.match('dpm_resume\[.*', t.name)): + phase = 'resume' + data.setPhase(phase, t.time, isbegin) + continue + # resume complete start + elif(re.match('dpm_complete\[.*', t.name)): + phase = 'resume_complete' + if(isbegin): + data.dmesg[phase]['start'] = t.time + continue + # skip trace events inside devices calls + if(not data.isTraceEventOutsideDeviceCalls(pid, t.time)): + continue + # global events (outside device calls) are graphed + if(name not in testrun.ttemp): + testrun.ttemp[name] = [] + if(isbegin): + # create a new list entry + testrun.ttemp[name].append(\ + {'begin': t.time, 'end': t.time, 'pid': pid}) + else: + if(len(testrun.ttemp[name]) > 0): + # if an entry exists, assume this is its end + testrun.ttemp[name][-1]['end'] = t.time + elif(phase == 'post_resume'): + # post resume events can just have ends + testrun.ttemp[name].append({ + 'begin': data.dmesg[phase]['start'], + 'end': t.time}) + # device callback start + elif(t.type == 'device_pm_callback_start'): + m = re.match('(?P<drv>.*) (?P<d>.*), parent: *(?P<p>.*), .*',\ + t.name); + if(not m): + continue + drv = m.group('drv') + n = m.group('d') + p = m.group('p') + if(n and p): + data.newAction(phase, n, pid, p, t.time, -1, drv) + if pid not in data.devpids: + data.devpids.append(pid) + # device callback finish + elif(t.type == 'device_pm_callback_end'): + m = re.match('(?P<drv>.*) (?P<d>.*), err.*', t.name); + if(not m): + continue + n = m.group('d') + list = data.dmesg[phase]['list'] + if(n in list): + dev = list[n] + dev['length'] = t.time - dev['start'] + dev['end'] = t.time + # kprobe event processing + elif(t.fkprobe): + kprobename = t.type + kprobedata = t.name + key = (kprobename, pid) + # displayname is generated from kprobe data + displayname = '' + if(t.fcall): + displayname = sysvals.kprobeDisplayName(kprobename, kprobedata) + if not displayname: + continue + if(key not in tp.ktemp): + tp.ktemp[key] = [] + tp.ktemp[key].append({ + 'pid': pid, + 'begin': t.time, + 'end': t.time, + 'name': displayname, + 'cdata': kprobedata, + 'proc': m_proc, + }) + elif(t.freturn): + if(key not in tp.ktemp) or len(tp.ktemp[key]) < 1: + continue + e = tp.ktemp[key][-1] + if e['begin'] < 0.0 or t.time - e['begin'] < 0.000001: + tp.ktemp[key].pop() + else: + e['end'] = t.time + e['rdata'] = kprobedata + # end of kernel resume + if(kprobename == 'pm_notifier_call_chain' or \ + kprobename == 'pm_restore_console'): + data.dmesg[phase]['end'] = t.time + data.tKernRes = t.time + + # callgraph processing + elif sysvals.usecallgraph: + # create a callgraph object for the data + key = (m_proc, pid) + if(key not in testrun.ftemp): + testrun.ftemp[key] = [] + testrun.ftemp[key].append(FTraceCallGraph(pid)) + # when the call is finished, see which device matches it + cg = testrun.ftemp[key][-1] + if(cg.addLine(t)): + testrun.ftemp[key].append(FTraceCallGraph(pid)) + tf.close() + + if sysvals.suspendmode == 'command': + for test in testruns: + for p in test.data.phases: + if p == 'suspend_prepare': + test.data.dmesg[p]['start'] = test.data.start + test.data.dmesg[p]['end'] = test.data.end + else: + test.data.dmesg[p]['start'] = test.data.end + test.data.dmesg[p]['end'] = test.data.end + test.data.tSuspended = test.data.end + test.data.tResumed = test.data.end + test.data.tLow = 0 + test.data.fwValid = False + + # dev source and procmon events can be unreadable with mixed phase height + if sysvals.usedevsrc or sysvals.useprocmon: + sysvals.mixedphaseheight = False + + for i in range(len(testruns)): + test = testruns[i] + data = test.data + # find the total time range for this test (begin, end) + tlb, tle = data.start, data.end + if i < len(testruns) - 1: + tle = testruns[i+1].data.start + # add the process usage data to the timeline + if sysvals.useprocmon: + data.createProcessUsageEvents() + # add the traceevent data to the device hierarchy + if(sysvals.usetraceevents): + # add actual trace funcs + for name in test.ttemp: + for event in test.ttemp[name]: + data.newActionGlobal(name, event['begin'], event['end'], event['pid']) + # add the kprobe based virtual tracefuncs as actual devices + for key in tp.ktemp: + name, pid = key + if name not in sysvals.tracefuncs: + continue + for e in tp.ktemp[key]: + kb, ke = e['begin'], e['end'] + if kb == ke or tlb > kb or tle <= kb: + continue + color = sysvals.kprobeColor(name) + data.newActionGlobal(e['name'], kb, ke, pid, color) + # add config base kprobes and dev kprobes + if sysvals.usedevsrc: + for key in tp.ktemp: + name, pid = key + if name in sysvals.tracefuncs or name not in sysvals.dev_tracefuncs: + continue + for e in tp.ktemp[key]: + kb, ke = e['begin'], e['end'] + if kb == ke or tlb > kb or tle <= kb: + continue + data.addDeviceFunctionCall(e['name'], name, e['proc'], pid, kb, + ke, e['cdata'], e['rdata']) + if sysvals.usecallgraph: + # add the callgraph data to the device hierarchy + sortlist = dict() + for key in test.ftemp: + proc, pid = key + for cg in test.ftemp[key]: + if len(cg.list) < 1 or cg.invalid: + continue + if(not cg.postProcess()): + id = 'task %s' % (pid) + vprint('Sanity check failed for '+\ + id+', ignoring this callback') + continue + # match cg data to devices + if sysvals.suspendmode == 'command' or not cg.deviceMatch(pid, data): + sortkey = '%f%f%d' % (cg.start, cg.end, pid) + sortlist[sortkey] = cg + # create blocks for orphan cg data + for sortkey in sorted(sortlist): + cg = sortlist[sortkey] + name = cg.name + if sysvals.isCallgraphFunc(name): + vprint('Callgraph found for task %d: %.3fms, %s' % (cg.pid, (cg.end - cg.start)*1000, name)) + cg.newActionFromFunction(data) + + if sysvals.suspendmode == 'command': + for data in testdata: + data.printDetails() + return testdata + + # fill in any missing phases + for data in testdata: + lp = data.phases[0] + for p in data.phases: + if(data.dmesg[p]['start'] < 0 and data.dmesg[p]['end'] < 0): + vprint('WARNING: phase "%s" is missing!' % p) + if(data.dmesg[p]['start'] < 0): + data.dmesg[p]['start'] = data.dmesg[lp]['end'] + if(p == 'resume_machine'): + data.tSuspended = data.dmesg[lp]['end'] + data.tResumed = data.dmesg[lp]['end'] + data.tLow = 0 + if(data.dmesg[p]['end'] < 0): + data.dmesg[p]['end'] = data.dmesg[p]['start'] + if(p != lp and not ('machine' in p and 'machine' in lp)): + data.dmesg[lp]['end'] = data.dmesg[p]['start'] + lp = p + + if(len(sysvals.devicefilter) > 0): + data.deviceFilter(sysvals.devicefilter) + data.fixupInitcallsThatDidntReturn() + if sysvals.usedevsrc: + data.optimizeDevSrc() + data.printDetails() + + # x2: merge any overlapping devices between test runs + if sysvals.usedevsrc and len(testdata) > 1: + tc = len(testdata) + for i in range(tc - 1): + devlist = testdata[i].overflowDevices() + for j in range(i + 1, tc): + testdata[j].mergeOverlapDevices(devlist) + testdata[0].stitchTouchingThreads(testdata[1:]) + return testdata + +# Function: loadKernelLog +# Description: +# [deprecated for kernel 3.15.0 or newer] +# load the dmesg file into memory and fix up any ordering issues +# The dmesg filename is taken from sysvals +# Output: +# An array of empty Data objects with only their dmesgtext attributes set +def loadKernelLog(justtext=False): + vprint('Analyzing the dmesg data...') + if(os.path.exists(sysvals.dmesgfile) == False): + doError('%s does not exist' % sysvals.dmesgfile) + + if justtext: + dmesgtext = [] + # there can be multiple test runs in a single file + tp = TestProps() + tp.stamp = datetime.now().strftime('# suspend-%m%d%y-%H%M%S localhost mem unknown') + testruns = [] + data = 0 + lf = open(sysvals.dmesgfile, 'r') + for line in lf: + line = line.replace('\r\n', '') + idx = line.find('[') + if idx > 1: + line = line[idx:] + m = re.match(sysvals.stampfmt, line) + if(m): + tp.stamp = line + continue + m = re.match(sysvals.firmwarefmt, line) + if(m): + tp.fwdata.append((int(m.group('s')), int(m.group('r')))) + continue + m = re.match('[ \t]*(\[ *)(?P<ktime>[0-9\.]*)(\]) (?P<msg>.*)', line) + if(not m): + continue + msg = m.group("msg") + if justtext: + dmesgtext.append(line) + continue + if(re.match('PM: Syncing filesystems.*', msg)): + if(data): + testruns.append(data) + data = Data(len(testruns)) + parseStamp(tp.stamp, data) + if len(tp.fwdata) > data.testnumber: + data.fwSuspend, data.fwResume = tp.fwdata[data.testnumber] + if(data.fwSuspend > 0 or data.fwResume > 0): + data.fwValid = True + if(not data): + continue + m = re.match('.* *(?P<k>[0-9]\.[0-9]{2}\.[0-9]-.*) .*', msg) + if(m): + sysvals.stamp['kernel'] = m.group('k') + m = re.match('PM: Preparing system for (?P<m>.*) sleep', msg) + if(m): + sysvals.stamp['mode'] = sysvals.suspendmode = m.group('m') + data.dmesgtext.append(line) + lf.close() + + if justtext: + return dmesgtext + if data: + testruns.append(data) + if len(testruns) < 1: + doError(' dmesg log has no suspend/resume data: %s' \ + % sysvals.dmesgfile) + + # fix lines with same timestamp/function with the call and return swapped + for data in testruns: + last = '' + for line in data.dmesgtext: + mc = re.match('.*(\[ *)(?P<t>[0-9\.]*)(\]) calling '+\ + '(?P<f>.*)\+ @ .*, parent: .*', line) + mr = re.match('.*(\[ *)(?P<t>[0-9\.]*)(\]) call '+\ + '(?P<f>.*)\+ returned .* after (?P<dt>.*) usecs', last) + if(mc and mr and (mc.group('t') == mr.group('t')) and + (mc.group('f') == mr.group('f'))): + i = data.dmesgtext.index(last) + j = data.dmesgtext.index(line) + data.dmesgtext[i] = line + data.dmesgtext[j] = last + last = line + return testruns + +# Function: parseKernelLog +# Description: +# [deprecated for kernel 3.15.0 or newer] +# Analyse a dmesg log output file generated from this app during +# the execution phase. Create a set of device structures in memory +# for subsequent formatting in the html output file +# This call is only for legacy support on kernels where the ftrace +# data lacks the suspend_resume or device_pm_callbacks trace events. +# Arguments: +# data: an empty Data object (with dmesgtext) obtained from loadKernelLog +# Output: +# The filled Data object +def parseKernelLog(data): + phase = 'suspend_runtime' + + if(data.fwValid): + vprint('Firmware Suspend = %u ns, Firmware Resume = %u ns' % \ + (data.fwSuspend, data.fwResume)) + + # dmesg phase match table + dm = { + 'suspend_prepare': 'PM: Syncing filesystems.*', + 'suspend': 'PM: Entering [a-z]* sleep.*', + 'suspend_late': 'PM: suspend of devices complete after.*', + 'suspend_noirq': 'PM: late suspend of devices complete after.*', + 'suspend_machine': 'PM: noirq suspend of devices complete after.*', + 'resume_machine': 'ACPI: Low-level resume complete.*', + 'resume_noirq': 'ACPI: Waking up from system sleep state.*', + 'resume_early': 'PM: noirq resume of devices complete after.*', + 'resume': 'PM: early resume of devices complete after.*', + 'resume_complete': 'PM: resume of devices complete after.*', + 'post_resume': '.*Restarting tasks \.\.\..*', + } + if(sysvals.suspendmode == 'standby'): + dm['resume_machine'] = 'PM: Restoring platform NVS memory' + elif(sysvals.suspendmode == 'disk'): + dm['suspend_late'] = 'PM: freeze of devices complete after.*' + dm['suspend_noirq'] = 'PM: late freeze of devices complete after.*' + dm['suspend_machine'] = 'PM: noirq freeze of devices complete after.*' + dm['resume_machine'] = 'PM: Restoring platform NVS memory' + dm['resume_early'] = 'PM: noirq restore of devices complete after.*' + dm['resume'] = 'PM: early restore of devices complete after.*' + dm['resume_complete'] = 'PM: restore of devices complete after.*' + elif(sysvals.suspendmode == 'freeze'): + dm['resume_machine'] = 'ACPI: resume from mwait' + + # action table (expected events that occur and show up in dmesg) + at = { + 'sync_filesystems': { + 'smsg': 'PM: Syncing filesystems.*', + 'emsg': 'PM: Preparing system for mem sleep.*' }, + 'freeze_user_processes': { + 'smsg': 'Freezing user space processes .*', + 'emsg': 'Freezing remaining freezable tasks.*' }, + 'freeze_tasks': { + 'smsg': 'Freezing remaining freezable tasks.*', + 'emsg': 'PM: Entering (?P<mode>[a-z,A-Z]*) sleep.*' }, + 'ACPI prepare': { + 'smsg': 'ACPI: Preparing to enter system sleep state.*', + 'emsg': 'PM: Saving platform NVS memory.*' }, + 'PM vns': { + 'smsg': 'PM: Saving platform NVS memory.*', + 'emsg': 'Disabling non-boot CPUs .*' }, + } + + t0 = -1.0 + cpu_start = -1.0 + prevktime = -1.0 + actions = dict() + for line in data.dmesgtext: + # parse each dmesg line into the time and message + m = re.match('[ \t]*(\[ *)(?P<ktime>[0-9\.]*)(\]) (?P<msg>.*)', line) + if(m): + val = m.group('ktime') + try: + ktime = float(val) + except: + continue + msg = m.group('msg') + # initialize data start to first line time + if t0 < 0: + data.setStart(ktime) + t0 = ktime + else: + continue + + # hack for determining resume_machine end for freeze + if(not sysvals.usetraceevents and sysvals.suspendmode == 'freeze' \ + and phase == 'resume_machine' and \ + re.match('calling (?P<f>.*)\+ @ .*, parent: .*', msg)): + data.dmesg['resume_machine']['end'] = ktime + phase = 'resume_noirq' + data.dmesg[phase]['start'] = ktime + + # suspend start + if(re.match(dm['suspend_prepare'], msg)): + phase = 'suspend_prepare' + data.dmesg[phase]['start'] = ktime + data.setStart(ktime) + data.tKernSus = ktime + # suspend start + elif(re.match(dm['suspend'], msg)): + data.dmesg['suspend_prepare']['end'] = ktime + phase = 'suspend' + data.dmesg[phase]['start'] = ktime + # suspend_late start + elif(re.match(dm['suspend_late'], msg)): + data.dmesg['suspend']['end'] = ktime + phase = 'suspend_late' + data.dmesg[phase]['start'] = ktime + # suspend_noirq start + elif(re.match(dm['suspend_noirq'], msg)): + data.dmesg['suspend_late']['end'] = ktime + phase = 'suspend_noirq' + data.dmesg[phase]['start'] = ktime + # suspend_machine start + elif(re.match(dm['suspend_machine'], msg)): + data.dmesg['suspend_noirq']['end'] = ktime + phase = 'suspend_machine' + data.dmesg[phase]['start'] = ktime + # resume_machine start + elif(re.match(dm['resume_machine'], msg)): + if(sysvals.suspendmode in ['freeze', 'standby']): + data.tSuspended = prevktime + data.dmesg['suspend_machine']['end'] = prevktime + else: + data.tSuspended = ktime + data.dmesg['suspend_machine']['end'] = ktime + phase = 'resume_machine' + data.tResumed = ktime + data.tLow = data.tResumed - data.tSuspended + data.dmesg[phase]['start'] = ktime + # resume_noirq start + elif(re.match(dm['resume_noirq'], msg)): + data.dmesg['resume_machine']['end'] = ktime + phase = 'resume_noirq' + data.dmesg[phase]['start'] = ktime + # resume_early start + elif(re.match(dm['resume_early'], msg)): + data.dmesg['resume_noirq']['end'] = ktime + phase = 'resume_early' + data.dmesg[phase]['start'] = ktime + # resume start + elif(re.match(dm['resume'], msg)): + data.dmesg['resume_early']['end'] = ktime + phase = 'resume' + data.dmesg[phase]['start'] = ktime + # resume complete start + elif(re.match(dm['resume_complete'], msg)): + data.dmesg['resume']['end'] = ktime + phase = 'resume_complete' + data.dmesg[phase]['start'] = ktime + # post resume start + elif(re.match(dm['post_resume'], msg)): + data.dmesg['resume_complete']['end'] = ktime + data.setEnd(ktime) + data.tKernRes = ktime + break + + # -- device callbacks -- + if(phase in data.phases): + # device init call + if(re.match('calling (?P<f>.*)\+ @ .*, parent: .*', msg)): + sm = re.match('calling (?P<f>.*)\+ @ '+\ + '(?P<n>.*), parent: (?P<p>.*)', msg); + f = sm.group('f') + n = sm.group('n') + p = sm.group('p') + if(f and n and p): + data.newAction(phase, f, int(n), p, ktime, -1, '') + # device init return + elif(re.match('call (?P<f>.*)\+ returned .* after '+\ + '(?P<t>.*) usecs', msg)): + sm = re.match('call (?P<f>.*)\+ returned .* after '+\ + '(?P<t>.*) usecs(?P<a>.*)', msg); + f = sm.group('f') + t = sm.group('t') + list = data.dmesg[phase]['list'] + if(f in list): + dev = list[f] + dev['length'] = int(t) + dev['end'] = ktime + + # if trace events are not available, these are better than nothing + if(not sysvals.usetraceevents): + # look for known actions + for a in at: + if(re.match(at[a]['smsg'], msg)): + if(a not in actions): + actions[a] = [] + actions[a].append({'begin': ktime, 'end': ktime}) + if(re.match(at[a]['emsg'], msg)): + if(a in actions): + actions[a][-1]['end'] = ktime + # now look for CPU on/off events + if(re.match('Disabling non-boot CPUs .*', msg)): + # start of first cpu suspend + cpu_start = ktime + elif(re.match('Enabling non-boot CPUs .*', msg)): + # start of first cpu resume + cpu_start = ktime + elif(re.match('smpboot: CPU (?P<cpu>[0-9]*) is now offline', msg)): + # end of a cpu suspend, start of the next + m = re.match('smpboot: CPU (?P<cpu>[0-9]*) is now offline', msg) + cpu = 'CPU'+m.group('cpu') + if(cpu not in actions): + actions[cpu] = [] + actions[cpu].append({'begin': cpu_start, 'end': ktime}) + cpu_start = ktime + elif(re.match('CPU(?P<cpu>[0-9]*) is up', msg)): + # end of a cpu resume, start of the next + m = re.match('CPU(?P<cpu>[0-9]*) is up', msg) + cpu = 'CPU'+m.group('cpu') + if(cpu not in actions): + actions[cpu] = [] + actions[cpu].append({'begin': cpu_start, 'end': ktime}) + cpu_start = ktime + prevktime = ktime + + # fill in any missing phases + lp = data.phases[0] + for p in data.phases: + if(data.dmesg[p]['start'] < 0 and data.dmesg[p]['end'] < 0): + print('WARNING: phase "%s" is missing, something went wrong!' % p) + print(' In %s, this dmesg line denotes the start of %s:' % \ + (sysvals.suspendmode, p)) + print(' "%s"' % dm[p]) + if(data.dmesg[p]['start'] < 0): + data.dmesg[p]['start'] = data.dmesg[lp]['end'] + if(p == 'resume_machine'): + data.tSuspended = data.dmesg[lp]['end'] + data.tResumed = data.dmesg[lp]['end'] + data.tLow = 0 + if(data.dmesg[p]['end'] < 0): + data.dmesg[p]['end'] = data.dmesg[p]['start'] + lp = p + + # fill in any actions we've found + for name in actions: + for event in actions[name]: + data.newActionGlobal(name, event['begin'], event['end']) + + data.printDetails() + if(len(sysvals.devicefilter) > 0): + data.deviceFilter(sysvals.devicefilter) + data.fixupInitcallsThatDidntReturn() + return True + +def callgraphHTML(sv, hf, num, cg, title, color, devid): + html_func_top = '<article id="{0}" class="atop" style="background:{1}">\n<input type="checkbox" class="pf" id="f{2}" checked/><label for="f{2}">{3} {4}</label>\n' + html_func_start = '<article>\n<input type="checkbox" class="pf" id="f{0}" checked/><label for="f{0}">{1} {2}</label>\n' + html_func_end = '</article>\n' + html_func_leaf = '<article>{0} {1}</article>\n' + + cgid = devid + if cg.id: + cgid += cg.id + cglen = (cg.end - cg.start) * 1000 + if cglen < sv.mincglen: + return num + + fmt = '<r>(%.3f ms @ '+sv.timeformat+' to '+sv.timeformat+')</r>' + flen = fmt % (cglen, cg.start, cg.end) + hf.write(html_func_top.format(cgid, color, num, title, flen)) + num += 1 + for line in cg.list: + if(line.length < 0.000000001): + flen = '' + else: + fmt = '<n>(%.3f ms @ '+sv.timeformat+')</n>' + flen = fmt % (line.length*1000, line.time) + if(line.freturn and line.fcall): + hf.write(html_func_leaf.format(line.name, flen)) + elif(line.freturn): + hf.write(html_func_end) + else: + hf.write(html_func_start.format(num, line.name, flen)) + num += 1 + hf.write(html_func_end) + return num + +def addCallgraphs(sv, hf, data): + hf.write('<section id="callgraphs" class="callgraph">\n') + # write out the ftrace data converted to html + num = 0 + for p in data.phases: + if sv.cgphase and p != sv.cgphase: + continue + list = data.dmesg[p]['list'] + for devname in data.sortedDevices(p): + dev = list[devname] + color = 'white' + if 'color' in data.dmesg[p]: + color = data.dmesg[p]['color'] + if 'color' in dev: + color = dev['color'] + name = devname + if(devname in sv.devprops): + name = sv.devprops[devname].altName(devname) + if sv.suspendmode in suspendmodename: + name += ' '+p + if('ftrace' in dev): + cg = dev['ftrace'] + num = callgraphHTML(sv, hf, num, cg, + name, color, dev['id']) + if('ftraces' in dev): + for cg in dev['ftraces']: + num = callgraphHTML(sv, hf, num, cg, + name+' → '+cg.name, color, dev['id']) + + hf.write('\n\n </section>\n') + +# Function: createHTMLSummarySimple +# Description: +# Create summary html file for a series of tests +# Arguments: +# testruns: array of Data objects from parseTraceLog +def createHTMLSummarySimple(testruns, htmlfile, folder): + # write the html header first (html head, css code, up to body start) + html = '<!DOCTYPE html>\n<html>\n<head>\n\ + <meta http-equiv="content-type" content="text/html; charset=UTF-8">\n\ + <title>SleepGraph Summary</title>\n\ + <style type=\'text/css\'>\n\ + .stamp {width: 100%;text-align:center;background:#888;line-height:30px;color:white;font: 25px Arial;}\n\ + table {width:100%;border-collapse: collapse;}\n\ + .summary {border:1px solid;}\n\ + th {border: 1px solid black;background:#222;color:white;}\n\ + td {font: 16px "Times New Roman";text-align: center;}\n\ + tr.alt td {background:#ddd;}\n\ + tr.avg td {background:#aaa;}\n\ + </style>\n</head>\n<body>\n' + + # group test header + html += '<div class="stamp">%s (%d tests)</div>\n' % (folder, len(testruns)) + th = '\t<th>{0}</th>\n' + td = '\t<td>{0}</td>\n' + tdlink = '\t<td><a href="{0}">html</a></td>\n' + + # table header + html += '<table class="summary">\n<tr>\n' + th.format('#') +\ + th.format('Mode') + th.format('Host') + th.format('Kernel') +\ + th.format('Test Time') + th.format('Suspend') + th.format('Resume') +\ + th.format('Detail') + '</tr>\n' + + # test data, 1 row per test + avg = '<tr class="avg"><td></td><td></td><td></td><td></td>'+\ + '<td>Average of {0} {1} tests</td><td>{2}</td><td>{3}</td><td></td></tr>\n' + sTimeAvg = rTimeAvg = 0.0 + mode = '' + num = 0 + for data in sorted(testruns, key=lambda v:(v['mode'], v['host'], v['kernel'])): + if mode != data['mode']: + # test average line + if(num > 0): + sTimeAvg /= (num - 1) + rTimeAvg /= (num - 1) + html += avg.format('%d' % (num - 1), mode, + '%3.3f ms' % sTimeAvg, '%3.3f ms' % rTimeAvg) + sTimeAvg = rTimeAvg = 0.0 + mode = data['mode'] + num = 1 + # alternate row color + if num % 2 == 1: + html += '<tr class="alt">\n' + else: + html += '<tr>\n' + html += td.format("%d" % num) + num += 1 + # basic info + for item in ['mode', 'host', 'kernel', 'time']: + val = "unknown" + if(item in data): + val = data[item] + html += td.format(val) + # suspend time + sTime = float(data['suspend']) + sTimeAvg += sTime + html += td.format('%.3f ms' % sTime) + # resume time + rTime = float(data['resume']) + rTimeAvg += rTime + html += td.format('%.3f ms' % rTime) + # link to the output html + html += tdlink.format(data['url']) + '</tr>\n' + # last test average line + if(num > 0): + sTimeAvg /= (num - 1) + rTimeAvg /= (num - 1) + html += avg.format('%d' % (num - 1), mode, + '%3.3f ms' % sTimeAvg, '%3.3f ms' % rTimeAvg) + + # flush the data to file + hf = open(htmlfile, 'w') + hf.write(html+'</table>\n</body>\n</html>\n') + hf.close() + +def ordinal(value): + suffix = 'th' + if value < 10 or value > 19: + if value % 10 == 1: + suffix = 'st' + elif value % 10 == 2: + suffix = 'nd' + elif value % 10 == 3: + suffix = 'rd' + return '%d%s' % (value, suffix) + +# Function: createHTML +# Description: +# Create the output html file from the resident test data +# Arguments: +# testruns: array of Data objects from parseKernelLog or parseTraceLog +# Output: +# True if the html file was created, false if it failed +def createHTML(testruns): + if len(testruns) < 1: + print('ERROR: Not enough test data to build a timeline') + return + + kerror = False + for data in testruns: + if data.kerror: + kerror = True + data.normalizeTime(testruns[-1].tSuspended) + + # html function templates + html_error = '<div id="{1}" title="kernel error/warning" class="err" style="right:{0}%">ERROR→</div>\n' + html_traceevent = '<div title="{0}" class="traceevent{6}" style="left:{1}%;top:{2}px;height:{3}px;width:{4}%;line-height:{3}px;{7}">{5}</div>\n' + html_cpuexec = '<div class="jiffie" style="left:{0}%;top:{1}px;height:{2}px;width:{3}%;background:{4};"></div>\n' + html_legend = '<div id="p{3}" class="square" style="left:{0}%;background:{1}"> {2}</div>\n' + html_timetotal = '<table class="time1">\n<tr>'\ + '<td class="green" title="{3}">{2} Suspend Time: <b>{0} ms</b></td>'\ + '<td class="yellow" title="{4}">{2} Resume Time: <b>{1} ms</b></td>'\ + '</tr>\n</table>\n' + html_timetotal2 = '<table class="time1">\n<tr>'\ + '<td class="green" title="{4}">{3} Suspend Time: <b>{0} ms</b></td>'\ + '<td class="gray" title="time spent in low-power mode with clock running">'+sysvals.suspendmode+' time: <b>{1} ms</b></td>'\ + '<td class="yellow" title="{5}">{3} Resume Time: <b>{2} ms</b></td>'\ + '</tr>\n</table>\n' + html_timetotal3 = '<table class="time1">\n<tr>'\ + '<td class="green">Execution Time: <b>{0} ms</b></td>'\ + '<td class="yellow">Command: <b>{1}</b></td>'\ + '</tr>\n</table>\n' + html_timegroups = '<table class="time2">\n<tr>'\ + '<td class="green" title="time from kernel enter_state({5}) to firmware mode [kernel time only]">{4}Kernel Suspend: {0} ms</td>'\ + '<td class="purple">{4}Firmware Suspend: {1} ms</td>'\ + '<td class="purple">{4}Firmware Resume: {2} ms</td>'\ + '<td class="yellow" title="time from firmware mode to return from kernel enter_state({5}) [kernel time only]">{4}Kernel Resume: {3} ms</td>'\ + '</tr>\n</table>\n' + + # html format variables + scaleH = 20 + if kerror: + scaleH = 40 + + # device timeline + vprint('Creating Device Timeline...') + + devtl = Timeline(30, scaleH) + + # write the test title and general info header + devtl.createHeader(sysvals) + + # Generate the header for this timeline + for data in testruns: + tTotal = data.end - data.start + sktime = (data.dmesg['suspend_machine']['end'] - \ + data.tKernSus) * 1000 + rktime = (data.dmesg['resume_complete']['end'] - \ + data.dmesg['resume_machine']['start']) * 1000 + if(tTotal == 0): + print('ERROR: No timeline data') + sys.exit() + if(data.tLow > 0): + low_time = '%.0f'%(data.tLow*1000) + if sysvals.suspendmode == 'command': + run_time = '%.0f'%((data.end-data.start)*1000) + if sysvals.testcommand: + testdesc = sysvals.testcommand + else: + testdesc = 'unknown' + if(len(testruns) > 1): + testdesc = ordinal(data.testnumber+1)+' '+testdesc + thtml = html_timetotal3.format(run_time, testdesc) + devtl.html += thtml + elif data.fwValid: + suspend_time = '%.0f'%(sktime + (data.fwSuspend/1000000.0)) + resume_time = '%.0f'%(rktime + (data.fwResume/1000000.0)) + testdesc1 = 'Total' + testdesc2 = '' + stitle = 'time from kernel enter_state(%s) to low-power mode [kernel & firmware time]' % sysvals.suspendmode + rtitle = 'time from low-power mode to return from kernel enter_state(%s) [firmware & kernel time]' % sysvals.suspendmode + if(len(testruns) > 1): + testdesc1 = testdesc2 = ordinal(data.testnumber+1) + testdesc2 += ' ' + if(data.tLow == 0): + thtml = html_timetotal.format(suspend_time, \ + resume_time, testdesc1, stitle, rtitle) + else: + thtml = html_timetotal2.format(suspend_time, low_time, \ + resume_time, testdesc1, stitle, rtitle) + devtl.html += thtml + sftime = '%.3f'%(data.fwSuspend / 1000000.0) + rftime = '%.3f'%(data.fwResume / 1000000.0) + devtl.html += html_timegroups.format('%.3f'%sktime, \ + sftime, rftime, '%.3f'%rktime, testdesc2, sysvals.suspendmode) + else: + suspend_time = '%.3f' % sktime + resume_time = '%.3f' % rktime + testdesc = 'Kernel' + stitle = 'time from kernel enter_state(%s) to firmware mode [kernel time only]' % sysvals.suspendmode + rtitle = 'time from firmware mode to return from kernel enter_state(%s) [kernel time only]' % sysvals.suspendmode + if(len(testruns) > 1): + testdesc = ordinal(data.testnumber+1)+' '+testdesc + if(data.tLow == 0): + thtml = html_timetotal.format(suspend_time, \ + resume_time, testdesc, stitle, rtitle) + else: + thtml = html_timetotal2.format(suspend_time, low_time, \ + resume_time, testdesc, stitle, rtitle) + devtl.html += thtml + + # time scale for potentially multiple datasets + t0 = testruns[0].start + tMax = testruns[-1].end + tTotal = tMax - t0 + + # determine the maximum number of rows we need to draw + fulllist = [] + threadlist = [] + pscnt = 0 + devcnt = 0 + for data in testruns: + data.selectTimelineDevices('%f', tTotal, sysvals.mindevlen) + for group in data.devicegroups: + devlist = [] + for phase in group: + for devname in data.tdevlist[phase]: + d = DevItem(data.testnumber, phase, data.dmesg[phase]['list'][devname]) + devlist.append(d) + if d.isa('kth'): + threadlist.append(d) + else: + if d.isa('ps'): + pscnt += 1 + else: + devcnt += 1 + fulllist.append(d) + if sysvals.mixedphaseheight: + devtl.getPhaseRows(devlist) + if not sysvals.mixedphaseheight: + if len(threadlist) > 0 and len(fulllist) > 0: + if pscnt > 0 and devcnt > 0: + msg = 'user processes & device pm callbacks' + elif pscnt > 0: + msg = 'user processes' + else: + msg = 'device pm callbacks' + d = testruns[0].addHorizontalDivider(msg, testruns[-1].end) + fulllist.insert(0, d) + devtl.getPhaseRows(fulllist) + if len(threadlist) > 0: + d = testruns[0].addHorizontalDivider('asynchronous kernel threads', testruns[-1].end) + threadlist.insert(0, d) + devtl.getPhaseRows(threadlist, devtl.rows) + devtl.calcTotalRows() + + # draw the full timeline + devtl.createZoomBox(sysvals.suspendmode, len(testruns)) + phases = {'suspend':[],'resume':[]} + for phase in data.dmesg: + if 'resume' in phase: + phases['resume'].append(phase) + else: + phases['suspend'].append(phase) + + # draw each test run chronologically + for data in testruns: + # now draw the actual timeline blocks + for dir in phases: + # draw suspend and resume blocks separately + bname = '%s%d' % (dir[0], data.testnumber) + if dir == 'suspend': + m0 = data.start + mMax = data.tSuspended + left = '%f' % (((m0-t0)*100.0)/tTotal) + else: + m0 = data.tSuspended + mMax = data.end + # in an x2 run, remove any gap between blocks + if len(testruns) > 1 and data.testnumber == 0: + mMax = testruns[1].start + left = '%f' % ((((m0-t0)*100.0)+sysvals.srgap/2)/tTotal) + mTotal = mMax - m0 + # if a timeline block is 0 length, skip altogether + if mTotal == 0: + continue + width = '%f' % (((mTotal*100.0)-sysvals.srgap/2)/tTotal) + devtl.html += devtl.html_tblock.format(bname, left, width, devtl.scaleH) + for b in sorted(phases[dir]): + # draw the phase color background + phase = data.dmesg[b] + length = phase['end']-phase['start'] + left = '%f' % (((phase['start']-m0)*100.0)/mTotal) + width = '%f' % ((length*100.0)/mTotal) + devtl.html += devtl.html_phase.format(left, width, \ + '%.3f'%devtl.scaleH, '%.3f'%devtl.bodyH, \ + data.dmesg[b]['color'], '') + for e in data.errorinfo[dir]: + # draw red lines for any kernel errors found + t, err = e + right = '%f' % (((mMax-t)*100.0)/mTotal) + devtl.html += html_error.format(right, err) + for b in sorted(phases[dir]): + # draw the devices for this phase + phaselist = data.dmesg[b]['list'] + for d in data.tdevlist[b]: + name = d + drv = '' + dev = phaselist[d] + xtraclass = '' + xtrainfo = '' + xtrastyle = '' + if 'htmlclass' in dev: + xtraclass = dev['htmlclass'] + if 'color' in dev: + xtrastyle = 'background:%s;' % dev['color'] + if(d in sysvals.devprops): + name = sysvals.devprops[d].altName(d) + xtraclass = sysvals.devprops[d].xtraClass() + xtrainfo = sysvals.devprops[d].xtraInfo() + elif xtraclass == ' kth': + xtrainfo = ' kernel_thread' + if('drv' in dev and dev['drv']): + drv = ' {%s}' % dev['drv'] + rowheight = devtl.phaseRowHeight(data.testnumber, b, dev['row']) + rowtop = devtl.phaseRowTop(data.testnumber, b, dev['row']) + top = '%.3f' % (rowtop + devtl.scaleH) + left = '%f' % (((dev['start']-m0)*100)/mTotal) + width = '%f' % (((dev['end']-dev['start'])*100)/mTotal) + length = ' (%0.3f ms) ' % ((dev['end']-dev['start'])*1000) + title = name+drv+xtrainfo+length + if sysvals.suspendmode == 'command': + title += sysvals.testcommand + elif xtraclass == ' ps': + if 'suspend' in b: + title += 'pre_suspend_process' + else: + title += 'post_resume_process' + else: + title += b + devtl.html += devtl.html_device.format(dev['id'], \ + title, left, top, '%.3f'%rowheight, width, \ + d+drv, xtraclass, xtrastyle) + if('cpuexec' in dev): + for t in sorted(dev['cpuexec']): + start, end = t + j = float(dev['cpuexec'][t]) / 5 + if j > 1.0: + j = 1.0 + height = '%.3f' % (rowheight/3) + top = '%.3f' % (rowtop + devtl.scaleH + 2*rowheight/3) + left = '%f' % (((start-m0)*100)/mTotal) + width = '%f' % ((end-start)*100/mTotal) + color = 'rgba(255, 0, 0, %f)' % j + devtl.html += \ + html_cpuexec.format(left, top, height, width, color) + if('src' not in dev): + continue + # draw any trace events for this device + for e in dev['src']: + height = '%.3f' % devtl.rowH + top = '%.3f' % (rowtop + devtl.scaleH + (e.row*devtl.rowH)) + left = '%f' % (((e.time-m0)*100)/mTotal) + width = '%f' % (e.length*100/mTotal) + xtrastyle = '' + if e.color: + xtrastyle = 'background:%s;' % e.color + devtl.html += \ + html_traceevent.format(e.title(), \ + left, top, height, width, e.text(), '', xtrastyle) + # draw the time scale, try to make the number of labels readable + devtl.createTimeScale(m0, mMax, tTotal, dir) + devtl.html += '</div>\n' + + # timeline is finished + devtl.html += '</div>\n</div>\n' + + # draw a legend which describes the phases by color + if sysvals.suspendmode != 'command': + data = testruns[-1] + devtl.html += '<div class="legend">\n' + pdelta = 100.0/len(data.phases) + pmargin = pdelta / 4.0 + for phase in data.phases: + tmp = phase.split('_') + id = tmp[0][0] + if(len(tmp) > 1): + id += tmp[1][0] + order = '%.2f' % ((data.dmesg[phase]['order'] * pdelta) + pmargin) + name = string.replace(phase, '_', ' ') + devtl.html += html_legend.format(order, \ + data.dmesg[phase]['color'], name, id) + devtl.html += '</div>\n' + + hf = open(sysvals.htmlfile, 'w') + + # no header or css if its embedded + if(sysvals.embedded): + hf.write('pass True tSus %.3f tRes %.3f tLow %.3f fwvalid %s tSus %.3f tRes %.3f\n' % + (data.tSuspended-data.start, data.end-data.tSuspended, data.tLow, data.fwValid, \ + data.fwSuspend/1000000, data.fwResume/1000000)) + else: + addCSS(hf, sysvals, len(testruns), kerror) + + # write the device timeline + hf.write(devtl.html) + hf.write('<div id="devicedetailtitle"></div>\n') + hf.write('<div id="devicedetail" style="display:none;">\n') + # draw the colored boxes for the device detail section + for data in testruns: + hf.write('<div id="devicedetail%d">\n' % data.testnumber) + pscolor = 'linear-gradient(to top left, #ccc, #eee)' + hf.write(devtl.html_phaselet.format('pre_suspend_process', \ + '0', '0', pscolor)) + for b in data.phases: + phase = data.dmesg[b] + length = phase['end']-phase['start'] + left = '%.3f' % (((phase['start']-t0)*100.0)/tTotal) + width = '%.3f' % ((length*100.0)/tTotal) + hf.write(devtl.html_phaselet.format(b, left, width, \ + data.dmesg[b]['color'])) + hf.write(devtl.html_phaselet.format('post_resume_process', \ + '0', '0', pscolor)) + if sysvals.suspendmode == 'command': + hf.write(devtl.html_phaselet.format('cmdexec', '0', '0', pscolor)) + hf.write('</div>\n') + hf.write('</div>\n') + + # write the ftrace data (callgraph) + if sysvals.cgtest >= 0 and len(testruns) > sysvals.cgtest: + data = testruns[sysvals.cgtest] + else: + data = testruns[-1] + if(sysvals.usecallgraph and not sysvals.embedded): + addCallgraphs(sysvals, hf, data) + + # add the test log as a hidden div + if sysvals.logmsg: + hf.write('<div id="testlog" style="display:none;">\n'+sysvals.logmsg+'</div>\n') + # add the dmesg log as a hidden div + if sysvals.addlogs and sysvals.dmesgfile: + hf.write('<div id="dmesglog" style="display:none;">\n') + lf = open(sysvals.dmesgfile, 'r') + for line in lf: + line = line.replace('<', '<').replace('>', '>') + hf.write(line) + lf.close() + hf.write('</div>\n') + # add the ftrace log as a hidden div + if sysvals.addlogs and sysvals.ftracefile: + hf.write('<div id="ftracelog" style="display:none;">\n') + lf = open(sysvals.ftracefile, 'r') + for line in lf: + hf.write(line) + lf.close() + hf.write('</div>\n') + + if(not sysvals.embedded): + # write the footer and close + addScriptCode(hf, testruns) + hf.write('</body>\n</html>\n') + else: + # embedded out will be loaded in a page, skip the js + t0 = (testruns[0].start - testruns[-1].tSuspended) * 1000 + tMax = (testruns[-1].end - testruns[-1].tSuspended) * 1000 + # add js code in a div entry for later evaluation + detail = 'var bounds = [%f,%f];\n' % (t0, tMax) + detail += 'var devtable = [\n' + for data in testruns: + topo = data.deviceTopology() + detail += '\t"%s",\n' % (topo) + detail += '];\n' + hf.write('<div id=customcode style=display:none>\n'+detail+'</div>\n') + hf.close() + return True + +def addCSS(hf, sv, testcount=1, kerror=False, extra=''): + kernel = sv.stamp['kernel'] + host = sv.hostname[0].upper()+sv.hostname[1:] + mode = sv.suspendmode + if sv.suspendmode in suspendmodename: + mode = suspendmodename[sv.suspendmode] + title = host+' '+mode+' '+kernel + + # various format changes by flags + cgchk = 'checked' + cgnchk = 'not(:checked)' + if sv.cgexp: + cgchk = 'not(:checked)' + cgnchk = 'checked' + + hoverZ = 'z-index:8;' + if sv.usedevsrc: + hoverZ = '' + + devlistpos = 'absolute' + if testcount > 1: + devlistpos = 'relative' + + scaleTH = 20 + if kerror: + scaleTH = 60 + + # write the html header first (html head, css code, up to body start) + html_header = '<!DOCTYPE html>\n<html>\n<head>\n\ + <meta http-equiv="content-type" content="text/html; charset=UTF-8">\n\ + <title>'+title+'</title>\n\ + <style type=\'text/css\'>\n\ + body {overflow-y:scroll;}\n\ + .stamp {width:100%;text-align:center;background:gray;line-height:30px;color:white;font:25px Arial;}\n\ + .callgraph {margin-top:30px;box-shadow:5px 5px 20px black;}\n\ + .callgraph article * {padding-left:28px;}\n\ + h1 {color:black;font:bold 30px Times;}\n\ + t0 {color:black;font:bold 30px Times;}\n\ + t1 {color:black;font:30px Times;}\n\ + t2 {color:black;font:25px Times;}\n\ + t3 {color:black;font:20px Times;white-space:nowrap;}\n\ + t4 {color:black;font:bold 30px Times;line-height:60px;white-space:nowrap;}\n\ + cS {font:bold 13px Times;}\n\ + table {width:100%;}\n\ + .gray {background:rgba(80,80,80,0.1);}\n\ + .green {background:rgba(204,255,204,0.4);}\n\ + .purple {background:rgba(128,0,128,0.2);}\n\ + .yellow {background:rgba(255,255,204,0.4);}\n\ + .blue {background:rgba(169,208,245,0.4);}\n\ + .time1 {font:22px Arial;border:1px solid;}\n\ + .time2 {font:15px Arial;border-bottom:1px solid;border-left:1px solid;border-right:1px solid;}\n\ + td {text-align:center;}\n\ + r {color:#500000;font:15px Tahoma;}\n\ + n {color:#505050;font:15px Tahoma;}\n\ + .tdhl {color:red;}\n\ + .hide {display:none;}\n\ + .pf {display:none;}\n\ + .pf:'+cgchk+' + label {background:url(\'data:image/svg+xml;utf,<?xml version="1.0" standalone="no"?><svg xmlns="http://www.w3.org/2000/svg" height="18" width="18" version="1.1"><circle cx="9" cy="9" r="8" stroke="black" stroke-width="1" fill="white"/><rect x="4" y="8" width="10" height="2" style="fill:black;stroke-width:0"/><rect x="8" y="4" width="2" height="10" style="fill:black;stroke-width:0"/></svg>\') no-repeat left center;}\n\ + .pf:'+cgnchk+' ~ label {background:url(\'data:image/svg+xml;utf,<?xml version="1.0" standalone="no"?><svg xmlns="http://www.w3.org/2000/svg" height="18" width="18" version="1.1"><circle cx="9" cy="9" r="8" stroke="black" stroke-width="1" fill="white"/><rect x="4" y="8" width="10" height="2" style="fill:black;stroke-width:0"/></svg>\') no-repeat left center;}\n\ + .pf:'+cgchk+' ~ *:not(:nth-child(2)) {display:none;}\n\ + .zoombox {position:relative;width:100%;overflow-x:scroll;-webkit-user-select:none;-moz-user-select:none;user-select:none;}\n\ + .timeline {position:relative;font-size:14px;cursor:pointer;width:100%; overflow:hidden;background:linear-gradient(#cccccc, white);}\n\ + .thread {position:absolute;height:0%;overflow:hidden;z-index:7;line-height:30px;font-size:14px;border:1px solid;text-align:center;white-space:nowrap;}\n\ + .thread.ps {border-radius:3px;background:linear-gradient(to top, #ccc, #eee);}\n\ + .thread:hover {background:white;border:1px solid red;'+hoverZ+'}\n\ + .thread.sec,.thread.sec:hover {background:black;border:0;color:white;line-height:15px;font-size:10px;}\n\ + .hover {background:white;border:1px solid red;'+hoverZ+'}\n\ + .hover.sync {background:white;}\n\ + .hover.bg,.hover.kth,.hover.sync,.hover.ps {background:white;}\n\ + .jiffie {position:absolute;pointer-events: none;z-index:8;}\n\ + .traceevent {position:absolute;font-size:10px;z-index:7;overflow:hidden;color:black;text-align:center;white-space:nowrap;border-radius:5px;border:1px solid black;background:linear-gradient(to bottom right,#CCC,#969696);}\n\ + .traceevent:hover {color:white;font-weight:bold;border:1px solid white;}\n\ + .phase {position:absolute;overflow:hidden;border:0px;text-align:center;}\n\ + .phaselet {float:left;overflow:hidden;border:0px;text-align:center;min-height:100px;font-size:24px;}\n\ + .t {position:absolute;line-height:'+('%d'%scaleTH)+'px;pointer-events:none;top:0;height:100%;border-right:1px solid black;z-index:6;}\n\ + .err {position:absolute;top:0%;height:100%;border-right:3px solid red;color:red;font:bold 14px Times;line-height:18px;}\n\ + .legend {position:relative; width:100%; height:40px; text-align:center;margin-bottom:20px}\n\ + .legend .square {position:absolute;cursor:pointer;top:10px; width:0px;height:20px;border:1px solid;padding-left:20px;}\n\ + button {height:40px;width:200px;margin-bottom:20px;margin-top:20px;font-size:24px;}\n\ + .logbtn {position:relative;float:right;height:25px;width:50px;margin-top:3px;margin-bottom:0;font-size:10px;text-align:center;}\n\ + .devlist {position:'+devlistpos+';width:190px;}\n\ + a:link {color:white;text-decoration:none;}\n\ + a:visited {color:white;}\n\ + a:hover {color:white;}\n\ + a:active {color:white;}\n\ + .version {position:relative;float:left;color:white;font-size:10px;line-height:30px;margin-left:10px;}\n\ + #devicedetail {min-height:100px;box-shadow:5px 5px 20px black;}\n\ + .tblock {position:absolute;height:100%;background:#ddd;}\n\ + .tback {position:absolute;width:100%;background:linear-gradient(#ccc, #ddd);}\n\ + .bg {z-index:1;}\n\ +'+extra+'\ + </style>\n</head>\n<body>\n' + hf.write(html_header) + +# Function: addScriptCode +# Description: +# Adds the javascript code to the output html +# Arguments: +# hf: the open html file pointer +# testruns: array of Data objects from parseKernelLog or parseTraceLog +def addScriptCode(hf, testruns): + t0 = testruns[0].start * 1000 + tMax = testruns[-1].end * 1000 + # create an array in javascript memory with the device details + detail = ' var devtable = [];\n' + for data in testruns: + topo = data.deviceTopology() + detail += ' devtable[%d] = "%s";\n' % (data.testnumber, topo) + detail += ' var bounds = [%f,%f];\n' % (t0, tMax) + # add the code which will manipulate the data in the browser + script_code = \ + '<script type="text/javascript">\n'+detail+\ + ' var resolution = -1;\n'\ + ' var dragval = [0, 0];\n'\ + ' function redrawTimescale(t0, tMax, tS) {\n'\ + ' var rline = \'<div class="t" style="left:0;border-left:1px solid black;border-right:0;">\';\n'\ + ' var tTotal = tMax - t0;\n'\ + ' var list = document.getElementsByClassName("tblock");\n'\ + ' for (var i = 0; i < list.length; i++) {\n'\ + ' var timescale = list[i].getElementsByClassName("timescale")[0];\n'\ + ' var m0 = t0 + (tTotal*parseFloat(list[i].style.left)/100);\n'\ + ' var mTotal = tTotal*parseFloat(list[i].style.width)/100;\n'\ + ' var mMax = m0 + mTotal;\n'\ + ' var html = "";\n'\ + ' var divTotal = Math.floor(mTotal/tS) + 1;\n'\ + ' if(divTotal > 1000) continue;\n'\ + ' var divEdge = (mTotal - tS*(divTotal-1))*100/mTotal;\n'\ + ' var pos = 0.0, val = 0.0;\n'\ + ' for (var j = 0; j < divTotal; j++) {\n'\ + ' var htmlline = "";\n'\ + ' var mode = list[i].id[5];\n'\ + ' if(mode == "s") {\n'\ + ' pos = 100 - (((j)*tS*100)/mTotal) - divEdge;\n'\ + ' val = (j-divTotal+1)*tS;\n'\ + ' if(j == divTotal - 1)\n'\ + ' htmlline = \'<div class="t" style="right:\'+pos+\'%"><cS>S→</cS></div>\';\n'\ + ' else\n'\ + ' htmlline = \'<div class="t" style="right:\'+pos+\'%">\'+val+\'ms</div>\';\n'\ + ' } else {\n'\ + ' pos = 100 - (((j)*tS*100)/mTotal);\n'\ + ' val = (j)*tS;\n'\ + ' htmlline = \'<div class="t" style="right:\'+pos+\'%">\'+val+\'ms</div>\';\n'\ + ' if(j == 0)\n'\ + ' if(mode == "r")\n'\ + ' htmlline = rline+"<cS>←R</cS></div>";\n'\ + ' else\n'\ + ' htmlline = rline+"<cS>0ms</div>";\n'\ + ' }\n'\ + ' html += htmlline;\n'\ + ' }\n'\ + ' timescale.innerHTML = html;\n'\ + ' }\n'\ + ' }\n'\ + ' function zoomTimeline() {\n'\ + ' var dmesg = document.getElementById("dmesg");\n'\ + ' var zoombox = document.getElementById("dmesgzoombox");\n'\ + ' var left = zoombox.scrollLeft;\n'\ + ' var val = parseFloat(dmesg.style.width);\n'\ + ' var newval = 100;\n'\ + ' var sh = window.outerWidth / 2;\n'\ + ' if(this.id == "zoomin") {\n'\ + ' newval = val * 1.2;\n'\ + ' if(newval > 910034) newval = 910034;\n'\ + ' dmesg.style.width = newval+"%";\n'\ + ' zoombox.scrollLeft = ((left + sh) * newval / val) - sh;\n'\ + ' } else if (this.id == "zoomout") {\n'\ + ' newval = val / 1.2;\n'\ + ' if(newval < 100) newval = 100;\n'\ + ' dmesg.style.width = newval+"%";\n'\ + ' zoombox.scrollLeft = ((left + sh) * newval / val) - sh;\n'\ + ' } else {\n'\ + ' zoombox.scrollLeft = 0;\n'\ + ' dmesg.style.width = "100%";\n'\ + ' }\n'\ + ' var tS = [10000, 5000, 2000, 1000, 500, 200, 100, 50, 20, 10, 5, 2, 1];\n'\ + ' var t0 = bounds[0];\n'\ + ' var tMax = bounds[1];\n'\ + ' var tTotal = tMax - t0;\n'\ + ' var wTotal = tTotal * 100.0 / newval;\n'\ + ' var idx = 7*window.innerWidth/1100;\n'\ + ' for(var i = 0; (i < tS.length)&&((wTotal / tS[i]) < idx); i++);\n'\ + ' if(i >= tS.length) i = tS.length - 1;\n'\ + ' if(tS[i] == resolution) return;\n'\ + ' resolution = tS[i];\n'\ + ' redrawTimescale(t0, tMax, tS[i]);\n'\ + ' }\n'\ + ' function deviceName(title) {\n'\ + ' var name = title.slice(0, title.indexOf(" ("));\n'\ + ' return name;\n'\ + ' }\n'\ + ' function deviceHover() {\n'\ + ' var name = deviceName(this.title);\n'\ + ' var dmesg = document.getElementById("dmesg");\n'\ + ' var dev = dmesg.getElementsByClassName("thread");\n'\ + ' var cpu = -1;\n'\ + ' if(name.match("CPU_ON\[[0-9]*\]"))\n'\ + ' cpu = parseInt(name.slice(7));\n'\ + ' else if(name.match("CPU_OFF\[[0-9]*\]"))\n'\ + ' cpu = parseInt(name.slice(8));\n'\ + ' for (var i = 0; i < dev.length; i++) {\n'\ + ' dname = deviceName(dev[i].title);\n'\ + ' var cname = dev[i].className.slice(dev[i].className.indexOf("thread"));\n'\ + ' if((cpu >= 0 && dname.match("CPU_O[NF]*\\\[*"+cpu+"\\\]")) ||\n'\ + ' (name == dname))\n'\ + ' {\n'\ + ' dev[i].className = "hover "+cname;\n'\ + ' } else {\n'\ + ' dev[i].className = cname;\n'\ + ' }\n'\ + ' }\n'\ + ' }\n'\ + ' function deviceUnhover() {\n'\ + ' var dmesg = document.getElementById("dmesg");\n'\ + ' var dev = dmesg.getElementsByClassName("thread");\n'\ + ' for (var i = 0; i < dev.length; i++) {\n'\ + ' dev[i].className = dev[i].className.slice(dev[i].className.indexOf("thread"));\n'\ + ' }\n'\ + ' }\n'\ + ' function deviceTitle(title, total, cpu) {\n'\ + ' var prefix = "Total";\n'\ + ' if(total.length > 3) {\n'\ + ' prefix = "Average";\n'\ + ' total[1] = (total[1]+total[3])/2;\n'\ + ' total[2] = (total[2]+total[4])/2;\n'\ + ' }\n'\ + ' var devtitle = document.getElementById("devicedetailtitle");\n'\ + ' var name = deviceName(title);\n'\ + ' if(cpu >= 0) name = "CPU"+cpu;\n'\ + ' var driver = "";\n'\ + ' var tS = "<t2>(</t2>";\n'\ + ' var tR = "<t2>)</t2>";\n'\ + ' if(total[1] > 0)\n'\ + ' tS = "<t2>("+prefix+" Suspend:</t2><t0> "+total[1].toFixed(3)+" ms</t0> ";\n'\ + ' if(total[2] > 0)\n'\ + ' tR = " <t2>"+prefix+" Resume:</t2><t0> "+total[2].toFixed(3)+" ms<t2>)</t2></t0>";\n'\ + ' var s = title.indexOf("{");\n'\ + ' var e = title.indexOf("}");\n'\ + ' if((s >= 0) && (e >= 0))\n'\ + ' driver = title.slice(s+1, e) + " <t1>@</t1> ";\n'\ + ' if(total[1] > 0 && total[2] > 0)\n'\ + ' devtitle.innerHTML = "<t0>"+driver+name+"</t0> "+tS+tR;\n'\ + ' else\n'\ + ' devtitle.innerHTML = "<t0>"+title+"</t0>";\n'\ + ' return name;\n'\ + ' }\n'\ + ' function deviceDetail() {\n'\ + ' var devinfo = document.getElementById("devicedetail");\n'\ + ' devinfo.style.display = "block";\n'\ + ' var name = deviceName(this.title);\n'\ + ' var cpu = -1;\n'\ + ' if(name.match("CPU_ON\[[0-9]*\]"))\n'\ + ' cpu = parseInt(name.slice(7));\n'\ + ' else if(name.match("CPU_OFF\[[0-9]*\]"))\n'\ + ' cpu = parseInt(name.slice(8));\n'\ + ' var dmesg = document.getElementById("dmesg");\n'\ + ' var dev = dmesg.getElementsByClassName("thread");\n'\ + ' var idlist = [];\n'\ + ' var pdata = [[]];\n'\ + ' if(document.getElementById("devicedetail1"))\n'\ + ' pdata = [[], []];\n'\ + ' var pd = pdata[0];\n'\ + ' var total = [0.0, 0.0, 0.0];\n'\ + ' for (var i = 0; i < dev.length; i++) {\n'\ + ' dname = deviceName(dev[i].title);\n'\ + ' if((cpu >= 0 && dname.match("CPU_O[NF]*\\\[*"+cpu+"\\\]")) ||\n'\ + ' (name == dname))\n'\ + ' {\n'\ + ' idlist[idlist.length] = dev[i].id;\n'\ + ' var tidx = 1;\n'\ + ' if(dev[i].id[0] == "a") {\n'\ + ' pd = pdata[0];\n'\ + ' } else {\n'\ + ' if(pdata.length == 1) pdata[1] = [];\n'\ + ' if(total.length == 3) total[3]=total[4]=0.0;\n'\ + ' pd = pdata[1];\n'\ + ' tidx = 3;\n'\ + ' }\n'\ + ' var info = dev[i].title.split(" ");\n'\ + ' var pname = info[info.length-1];\n'\ + ' pd[pname] = parseFloat(info[info.length-3].slice(1));\n'\ + ' total[0] += pd[pname];\n'\ + ' if(pname.indexOf("suspend") >= 0)\n'\ + ' total[tidx] += pd[pname];\n'\ + ' else\n'\ + ' total[tidx+1] += pd[pname];\n'\ + ' }\n'\ + ' }\n'\ + ' var devname = deviceTitle(this.title, total, cpu);\n'\ + ' var left = 0.0;\n'\ + ' for (var t = 0; t < pdata.length; t++) {\n'\ + ' pd = pdata[t];\n'\ + ' devinfo = document.getElementById("devicedetail"+t);\n'\ + ' var phases = devinfo.getElementsByClassName("phaselet");\n'\ + ' for (var i = 0; i < phases.length; i++) {\n'\ + ' if(phases[i].id in pd) {\n'\ + ' var w = 100.0*pd[phases[i].id]/total[0];\n'\ + ' var fs = 32;\n'\ + ' if(w < 8) fs = 4*w | 0;\n'\ + ' var fs2 = fs*3/4;\n'\ + ' phases[i].style.width = w+"%";\n'\ + ' phases[i].style.left = left+"%";\n'\ + ' phases[i].title = phases[i].id+" "+pd[phases[i].id]+" ms";\n'\ + ' left += w;\n'\ + ' var time = "<t4 style=\\"font-size:"+fs+"px\\">"+pd[phases[i].id]+" ms<br></t4>";\n'\ + ' var pname = "<t3 style=\\"font-size:"+fs2+"px\\">"+phases[i].id.replace(new RegExp("_", "g"), " ")+"</t3>";\n'\ + ' phases[i].innerHTML = time+pname;\n'\ + ' } else {\n'\ + ' phases[i].style.width = "0%";\n'\ + ' phases[i].style.left = left+"%";\n'\ + ' }\n'\ + ' }\n'\ + ' }\n'\ + ' if(typeof devstats !== \'undefined\')\n'\ + ' callDetail(this.id, this.title);\n'\ + ' var cglist = document.getElementById("callgraphs");\n'\ + ' if(!cglist) return;\n'\ + ' var cg = cglist.getElementsByClassName("atop");\n'\ + ' if(cg.length < 10) return;\n'\ + ' for (var i = 0; i < cg.length; i++) {\n'\ + ' cgid = cg[i].id.split("x")[0]\n'\ + ' if(idlist.indexOf(cgid) >= 0) {\n'\ + ' cg[i].style.display = "block";\n'\ + ' } else {\n'\ + ' cg[i].style.display = "none";\n'\ + ' }\n'\ + ' }\n'\ + ' }\n'\ + ' function callDetail(devid, devtitle) {\n'\ + ' if(!(devid in devstats) || devstats[devid].length < 1)\n'\ + ' return;\n'\ + ' var list = devstats[devid];\n'\ + ' var tmp = devtitle.split(" ");\n'\ + ' var name = tmp[0], phase = tmp[tmp.length-1];\n'\ + ' var dd = document.getElementById(phase);\n'\ + ' var total = parseFloat(tmp[1].slice(1));\n'\ + ' var mlist = [];\n'\ + ' var maxlen = 0;\n'\ + ' var info = []\n'\ + ' for(var i in list) {\n'\ + ' if(list[i][0] == "@") {\n'\ + ' info = list[i].split("|");\n'\ + ' continue;\n'\ + ' }\n'\ + ' var tmp = list[i].split("|");\n'\ + ' var t = parseFloat(tmp[0]), f = tmp[1], c = parseInt(tmp[2]);\n'\ + ' var p = (t*100.0/total).toFixed(2);\n'\ + ' mlist[mlist.length] = [f, c, t.toFixed(2), p+"%"];\n'\ + ' if(f.length > maxlen)\n'\ + ' maxlen = f.length;\n'\ + ' }\n'\ + ' var pad = 5;\n'\ + ' if(mlist.length == 0) pad = 30;\n'\ + ' var html = \'<div style="padding-top:\'+pad+\'px"><t3> <b>\'+name+\':</b>\';\n'\ + ' if(info.length > 2)\n'\ + ' html += " start=<b>"+info[1]+"</b>, end=<b>"+info[2]+"</b>";\n'\ + ' if(info.length > 3)\n'\ + ' html += ", length<i>(w/o overhead)</i>=<b>"+info[3]+" ms</b>";\n'\ + ' if(info.length > 4)\n'\ + ' html += ", return=<b>"+info[4]+"</b>";\n'\ + ' html += "</t3></div>";\n'\ + ' if(mlist.length > 0) {\n'\ + ' html += \'<table class=fstat style="padding-top:\'+(maxlen*5)+\'px;"><tr><th>Function</th>\';\n'\ + ' for(var i in mlist)\n'\ + ' html += "<td class=vt>"+mlist[i][0]+"</td>";\n'\ + ' html += "</tr><tr><th>Calls</th>";\n'\ + ' for(var i in mlist)\n'\ + ' html += "<td>"+mlist[i][1]+"</td>";\n'\ + ' html += "</tr><tr><th>Time(ms)</th>";\n'\ + ' for(var i in mlist)\n'\ + ' html += "<td>"+mlist[i][2]+"</td>";\n'\ + ' html += "</tr><tr><th>Percent</th>";\n'\ + ' for(var i in mlist)\n'\ + ' html += "<td>"+mlist[i][3]+"</td>";\n'\ + ' html += "</tr></table>";\n'\ + ' }\n'\ + ' dd.innerHTML = html;\n'\ + ' var height = (maxlen*5)+100;\n'\ + ' dd.style.height = height+"px";\n'\ + ' document.getElementById("devicedetail").style.height = height+"px";\n'\ + ' }\n'\ + ' function callSelect() {\n'\ + ' var cglist = document.getElementById("callgraphs");\n'\ + ' if(!cglist) return;\n'\ + ' var cg = cglist.getElementsByClassName("atop");\n'\ + ' for (var i = 0; i < cg.length; i++) {\n'\ + ' if(this.id == cg[i].id) {\n'\ + ' cg[i].style.display = "block";\n'\ + ' } else {\n'\ + ' cg[i].style.display = "none";\n'\ + ' }\n'\ + ' }\n'\ + ' }\n'\ + ' function devListWindow(e) {\n'\ + ' var win = window.open();\n'\ + ' var html = "<title>"+e.target.innerHTML+"</title>"+\n'\ + ' "<style type=\\"text/css\\">"+\n'\ + ' " ul {list-style-type:circle;padding-left:10px;margin-left:10px;}"+\n'\ + ' "</style>"\n'\ + ' var dt = devtable[0];\n'\ + ' if(e.target.id != "devlist1")\n'\ + ' dt = devtable[1];\n'\ + ' win.document.write(html+dt);\n'\ + ' }\n'\ + ' function errWindow() {\n'\ + ' var text = this.id;\n'\ + ' var win = window.open();\n'\ + ' win.document.write("<pre>"+text+"</pre>");\n'\ + ' win.document.close();\n'\ + ' }\n'\ + ' function logWindow(e) {\n'\ + ' var name = e.target.id.slice(4);\n'\ + ' var win = window.open();\n'\ + ' var log = document.getElementById(name+"log");\n'\ + ' var title = "<title>"+document.title.split(" ")[0]+" "+name+" log</title>";\n'\ + ' win.document.write(title+"<pre>"+log.innerHTML+"</pre>");\n'\ + ' win.document.close();\n'\ + ' }\n'\ + ' function onClickPhase(e) {\n'\ + ' }\n'\ + ' function onMouseDown(e) {\n'\ + ' dragval[0] = e.clientX;\n'\ + ' dragval[1] = document.getElementById("dmesgzoombox").scrollLeft;\n'\ + ' document.onmousemove = onMouseMove;\n'\ + ' }\n'\ + ' function onMouseMove(e) {\n'\ + ' var zoombox = document.getElementById("dmesgzoombox");\n'\ + ' zoombox.scrollLeft = dragval[1] + dragval[0] - e.clientX;\n'\ + ' }\n'\ + ' function onMouseUp(e) {\n'\ + ' document.onmousemove = null;\n'\ + ' }\n'\ + ' function onKeyPress(e) {\n'\ + ' var c = e.charCode;\n'\ + ' if(c != 42 && c != 43 && c != 45) return;\n'\ + ' var click = document.createEvent("Events");\n'\ + ' click.initEvent("click", true, false);\n'\ + ' if(c == 43) \n'\ + ' document.getElementById("zoomin").dispatchEvent(click);\n'\ + ' else if(c == 45)\n'\ + ' document.getElementById("zoomout").dispatchEvent(click);\n'\ + ' else if(c == 42)\n'\ + ' document.getElementById("zoomdef").dispatchEvent(click);\n'\ + ' }\n'\ + ' window.addEventListener("resize", function () {zoomTimeline();});\n'\ + ' window.addEventListener("load", function () {\n'\ + ' var dmesg = document.getElementById("dmesg");\n'\ + ' dmesg.style.width = "100%"\n'\ + ' dmesg.onmousedown = onMouseDown;\n'\ + ' document.onmouseup = onMouseUp;\n'\ + ' document.onkeypress = onKeyPress;\n'\ + ' document.getElementById("zoomin").onclick = zoomTimeline;\n'\ + ' document.getElementById("zoomout").onclick = zoomTimeline;\n'\ + ' document.getElementById("zoomdef").onclick = zoomTimeline;\n'\ + ' var list = document.getElementsByClassName("square");\n'\ + ' for (var i = 0; i < list.length; i++)\n'\ + ' list[i].onclick = onClickPhase;\n'\ + ' var list = document.getElementsByClassName("err");\n'\ + ' for (var i = 0; i < list.length; i++)\n'\ + ' list[i].onclick = errWindow;\n'\ + ' var list = document.getElementsByClassName("logbtn");\n'\ + ' for (var i = 0; i < list.length; i++)\n'\ + ' list[i].onclick = logWindow;\n'\ + ' list = document.getElementsByClassName("devlist");\n'\ + ' for (var i = 0; i < list.length; i++)\n'\ + ' list[i].onclick = devListWindow;\n'\ + ' var dev = dmesg.getElementsByClassName("thread");\n'\ + ' for (var i = 0; i < dev.length; i++) {\n'\ + ' dev[i].onclick = deviceDetail;\n'\ + ' dev[i].onmouseover = deviceHover;\n'\ + ' dev[i].onmouseout = deviceUnhover;\n'\ + ' }\n'\ + ' var dev = dmesg.getElementsByClassName("srccall");\n'\ + ' for (var i = 0; i < dev.length; i++)\n'\ + ' dev[i].onclick = callSelect;\n'\ + ' zoomTimeline();\n'\ + ' });\n'\ + '</script>\n' + hf.write(script_code); + +# Function: executeSuspend +# Description: +# Execute system suspend through the sysfs interface, then copy the output +# dmesg and ftrace files to the test output directory. +def executeSuspend(): + pm = ProcessMonitor() + tp = sysvals.tpath + fwdata = [] + # mark the start point in the kernel ring buffer just as we start + sysvals.initdmesg() + # start ftrace + if(sysvals.usecallgraph or sysvals.usetraceevents): + print('START TRACING') + sysvals.fsetVal('1', 'tracing_on') + if sysvals.useprocmon: + pm.start() + # execute however many s/r runs requested + for count in range(1,sysvals.execcount+1): + # x2delay in between test runs + if(count > 1 and sysvals.x2delay > 0): + sysvals.fsetVal('WAIT %d' % sysvals.x2delay, 'trace_marker') + time.sleep(sysvals.x2delay/1000.0) + sysvals.fsetVal('WAIT END', 'trace_marker') + # start message + if sysvals.testcommand != '': + print('COMMAND START') + else: + if(sysvals.rtcwake): + print('SUSPEND START') + else: + print('SUSPEND START (press a key to resume)') + # set rtcwake + if(sysvals.rtcwake): + print('will issue an rtcwake in %d seconds' % sysvals.rtcwaketime) + sysvals.rtcWakeAlarmOn() + # start of suspend trace marker + if(sysvals.usecallgraph or sysvals.usetraceevents): + sysvals.fsetVal('SUSPEND START', 'trace_marker') + # predelay delay + if(count == 1 and sysvals.predelay > 0): + sysvals.fsetVal('WAIT %d' % sysvals.predelay, 'trace_marker') + time.sleep(sysvals.predelay/1000.0) + sysvals.fsetVal('WAIT END', 'trace_marker') + # initiate suspend or command + if sysvals.testcommand != '': + call(sysvals.testcommand+' 2>&1', shell=True); + else: + pf = open(sysvals.powerfile, 'w') + pf.write(sysvals.suspendmode) + # execution will pause here + try: + pf.close() + except: + pass + if(sysvals.rtcwake): + sysvals.rtcWakeAlarmOff() + # postdelay delay + if(count == sysvals.execcount and sysvals.postdelay > 0): + sysvals.fsetVal('WAIT %d' % sysvals.postdelay, 'trace_marker') + time.sleep(sysvals.postdelay/1000.0) + sysvals.fsetVal('WAIT END', 'trace_marker') + # return from suspend + print('RESUME COMPLETE') + if(sysvals.usecallgraph or sysvals.usetraceevents): + sysvals.fsetVal('RESUME COMPLETE', 'trace_marker') + if(sysvals.suspendmode == 'mem' or sysvals.suspendmode == 'command'): + fwdata.append(getFPDT(False)) + # stop ftrace + if(sysvals.usecallgraph or sysvals.usetraceevents): + if sysvals.useprocmon: + pm.stop() + sysvals.fsetVal('0', 'tracing_on') + print('CAPTURING TRACE') + writeDatafileHeader(sysvals.ftracefile, fwdata) + call('cat '+tp+'trace >> '+sysvals.ftracefile, shell=True) + sysvals.fsetVal('', 'trace') + devProps() + # grab a copy of the dmesg output + print('CAPTURING DMESG') + writeDatafileHeader(sysvals.dmesgfile, fwdata) + sysvals.getdmesg() + +def writeDatafileHeader(filename, fwdata): + fp = open(filename, 'a') + fp.write(sysvals.teststamp+'\n') + if(sysvals.suspendmode == 'mem' or sysvals.suspendmode == 'command'): + for fw in fwdata: + if(fw): + fp.write('# fwsuspend %u fwresume %u\n' % (fw[0], fw[1])) + fp.close() + +# Function: setUSBDevicesAuto +# Description: +# Set the autosuspend control parameter of all USB devices to auto +# This can be dangerous, so use at your own risk, most devices are set +# to always-on since the kernel cant determine if the device can +# properly autosuspend +def setUSBDevicesAuto(): + rootCheck(True) + for dirname, dirnames, filenames in os.walk('/sys/devices'): + if(re.match('.*/usb[0-9]*.*', dirname) and + 'idVendor' in filenames and 'idProduct' in filenames): + call('echo auto > %s/power/control' % dirname, shell=True) + name = dirname.split('/')[-1] + desc = Popen(['cat', '%s/product' % dirname], + stderr=PIPE, stdout=PIPE).stdout.read().replace('\n', '') + ctrl = Popen(['cat', '%s/power/control' % dirname], + stderr=PIPE, stdout=PIPE).stdout.read().replace('\n', '') + print('control is %s for %6s: %s' % (ctrl, name, desc)) + +# Function: yesno +# Description: +# Print out an equivalent Y or N for a set of known parameter values +# Output: +# 'Y', 'N', or ' ' if the value is unknown +def yesno(val): + yesvals = ['auto', 'enabled', 'active', '1'] + novals = ['on', 'disabled', 'suspended', 'forbidden', 'unsupported'] + if val in yesvals: + return 'Y' + elif val in novals: + return 'N' + return ' ' + +# Function: ms2nice +# Description: +# Print out a very concise time string in minutes and seconds +# Output: +# The time string, e.g. "1901m16s" +def ms2nice(val): + ms = 0 + try: + ms = int(val) + except: + return 0.0 + m = ms / 60000 + s = (ms / 1000) - (m * 60) + return '%3dm%2ds' % (m, s) + +# Function: detectUSB +# Description: +# Detect all the USB hosts and devices currently connected and add +# a list of USB device names to sysvals for better timeline readability +def detectUSB(): + field = {'idVendor':'', 'idProduct':'', 'product':'', 'speed':''} + power = {'async':'', 'autosuspend':'', 'autosuspend_delay_ms':'', + 'control':'', 'persist':'', 'runtime_enabled':'', + 'runtime_status':'', 'runtime_usage':'', + 'runtime_active_time':'', + 'runtime_suspended_time':'', + 'active_duration':'', + 'connected_duration':''} + + print('LEGEND') + print('---------------------------------------------------------------------------------------------') + print(' A = async/sync PM queue Y/N D = autosuspend delay (seconds)') + print(' S = autosuspend Y/N rACTIVE = runtime active (min/sec)') + print(' P = persist across suspend Y/N rSUSPEN = runtime suspend (min/sec)') + print(' E = runtime suspend enabled/forbidden Y/N ACTIVE = active duration (min/sec)') + print(' R = runtime status active/suspended Y/N CONNECT = connected duration (min/sec)') + print(' U = runtime usage count') + print('---------------------------------------------------------------------------------------------') + print(' NAME ID DESCRIPTION SPEED A S P E R U D rACTIVE rSUSPEN ACTIVE CONNECT') + print('---------------------------------------------------------------------------------------------') + + for dirname, dirnames, filenames in os.walk('/sys/devices'): + if(re.match('.*/usb[0-9]*.*', dirname) and + 'idVendor' in filenames and 'idProduct' in filenames): + for i in field: + field[i] = Popen(['cat', '%s/%s' % (dirname, i)], + stderr=PIPE, stdout=PIPE).stdout.read().replace('\n', '') + name = dirname.split('/')[-1] + for i in power: + power[i] = Popen(['cat', '%s/power/%s' % (dirname, i)], + stderr=PIPE, stdout=PIPE).stdout.read().replace('\n', '') + if(re.match('usb[0-9]*', name)): + first = '%-8s' % name + else: + first = '%8s' % name + print('%s [%s:%s] %-20s %-4s %1s %1s %1s %1s %1s %1s %1s %s %s %s %s' % \ + (first, field['idVendor'], field['idProduct'], \ + field['product'][0:20], field['speed'], \ + yesno(power['async']), \ + yesno(power['control']), \ + yesno(power['persist']), \ + yesno(power['runtime_enabled']), \ + yesno(power['runtime_status']), \ + power['runtime_usage'], \ + power['autosuspend'], \ + ms2nice(power['runtime_active_time']), \ + ms2nice(power['runtime_suspended_time']), \ + ms2nice(power['active_duration']), \ + ms2nice(power['connected_duration']))) + +# Function: devProps +# Description: +# Retrieve a list of properties for all devices in the trace log +def devProps(data=0): + props = dict() + + if data: + idx = data.index(': ') + 2 + if idx >= len(data): + return + devlist = data[idx:].split(';') + for dev in devlist: + f = dev.split(',') + if len(f) < 3: + continue + dev = f[0] + props[dev] = DevProps() + props[dev].altname = f[1] + if int(f[2]): + props[dev].async = True + else: + props[dev].async = False + sysvals.devprops = props + if sysvals.suspendmode == 'command' and 'testcommandstring' in props: + sysvals.testcommand = props['testcommandstring'].altname + return + + if(os.path.exists(sysvals.ftracefile) == False): + doError('%s does not exist' % sysvals.ftracefile) + + # first get the list of devices we need properties for + msghead = 'Additional data added by AnalyzeSuspend' + alreadystamped = False + tp = TestProps() + tf = open(sysvals.ftracefile, 'r') + for line in tf: + if msghead in line: + alreadystamped = True + continue + # determine the trace data type (required for further parsing) + m = re.match(sysvals.tracertypefmt, line) + if(m): + tp.setTracerType(m.group('t')) + continue + # parse only valid lines, if this is not one move on + m = re.match(tp.ftrace_line_fmt, line) + if(not m or 'device_pm_callback_start' not in line): + continue + m = re.match('.*: (?P<drv>.*) (?P<d>.*), parent: *(?P<p>.*), .*', m.group('msg')); + if(not m): + continue + dev = m.group('d') + if dev not in props: + props[dev] = DevProps() + tf.close() + + if not alreadystamped and sysvals.suspendmode == 'command': + out = '#\n# '+msghead+'\n# Device Properties: ' + out += 'testcommandstring,%s,0;' % (sysvals.testcommand) + with open(sysvals.ftracefile, 'a') as fp: + fp.write(out+'\n') + sysvals.devprops = props + return + + # now get the syspath for each of our target devices + for dirname, dirnames, filenames in os.walk('/sys/devices'): + if(re.match('.*/power', dirname) and 'async' in filenames): + dev = dirname.split('/')[-2] + if dev in props and (not props[dev].syspath or len(dirname) < len(props[dev].syspath)): + props[dev].syspath = dirname[:-6] + + # now fill in the properties for our target devices + for dev in props: + dirname = props[dev].syspath + if not dirname or not os.path.exists(dirname): + continue + with open(dirname+'/power/async') as fp: + text = fp.read() + props[dev].async = False + if 'enabled' in text: + props[dev].async = True + fields = os.listdir(dirname) + if 'product' in fields: + with open(dirname+'/product') as fp: + props[dev].altname = fp.read() + elif 'name' in fields: + with open(dirname+'/name') as fp: + props[dev].altname = fp.read() + elif 'model' in fields: + with open(dirname+'/model') as fp: + props[dev].altname = fp.read() + elif 'description' in fields: + with open(dirname+'/description') as fp: + props[dev].altname = fp.read() + elif 'id' in fields: + with open(dirname+'/id') as fp: + props[dev].altname = fp.read() + elif 'idVendor' in fields and 'idProduct' in fields: + idv, idp = '', '' + with open(dirname+'/idVendor') as fp: + idv = fp.read().strip() + with open(dirname+'/idProduct') as fp: + idp = fp.read().strip() + props[dev].altname = '%s:%s' % (idv, idp) + + if props[dev].altname: + out = props[dev].altname.strip().replace('\n', ' ') + out = out.replace(',', ' ') + out = out.replace(';', ' ') + props[dev].altname = out + + # and now write the data to the ftrace file + if not alreadystamped: + out = '#\n# '+msghead+'\n# Device Properties: ' + for dev in sorted(props): + out += props[dev].out(dev) + with open(sysvals.ftracefile, 'a') as fp: + fp.write(out+'\n') + + sysvals.devprops = props + +# Function: getModes +# Description: +# Determine the supported power modes on this system +# Output: +# A string list of the available modes +def getModes(): + modes = '' + if(os.path.exists(sysvals.powerfile)): + fp = open(sysvals.powerfile, 'r') + modes = string.split(fp.read()) + fp.close() + return modes + +# Function: getFPDT +# Description: +# Read the acpi bios tables and pull out FPDT, the firmware data +# Arguments: +# output: True to output the info to stdout, False otherwise +def getFPDT(output): + rectype = {} + rectype[0] = 'Firmware Basic Boot Performance Record' + rectype[1] = 'S3 Performance Table Record' + prectype = {} + prectype[0] = 'Basic S3 Resume Performance Record' + prectype[1] = 'Basic S3 Suspend Performance Record' + + rootCheck(True) + if(not os.path.exists(sysvals.fpdtpath)): + if(output): + doError('file does not exist: %s' % sysvals.fpdtpath) + return False + if(not os.access(sysvals.fpdtpath, os.R_OK)): + if(output): + doError('file is not readable: %s' % sysvals.fpdtpath) + return False + if(not os.path.exists(sysvals.mempath)): + if(output): + doError('file does not exist: %s' % sysvals.mempath) + return False + if(not os.access(sysvals.mempath, os.R_OK)): + if(output): + doError('file is not readable: %s' % sysvals.mempath) + return False + + fp = open(sysvals.fpdtpath, 'rb') + buf = fp.read() + fp.close() + + if(len(buf) < 36): + if(output): + doError('Invalid FPDT table data, should '+\ + 'be at least 36 bytes') + return False + + table = struct.unpack('4sIBB6s8sI4sI', buf[0:36]) + if(output): + print('') + print('Firmware Performance Data Table (%s)' % table[0]) + print(' Signature : %s' % table[0]) + print(' Table Length : %u' % table[1]) + print(' Revision : %u' % table[2]) + print(' Checksum : 0x%x' % table[3]) + print(' OEM ID : %s' % table[4]) + print(' OEM Table ID : %s' % table[5]) + print(' OEM Revision : %u' % table[6]) + print(' Creator ID : %s' % table[7]) + print(' Creator Revision : 0x%x' % table[8]) + print('') + + if(table[0] != 'FPDT'): + if(output): + doError('Invalid FPDT table') + return False + if(len(buf) <= 36): + return False + i = 0 + fwData = [0, 0] + records = buf[36:] + fp = open(sysvals.mempath, 'rb') + while(i < len(records)): + header = struct.unpack('HBB', records[i:i+4]) + if(header[0] not in rectype): + i += header[1] + continue + if(header[1] != 16): + i += header[1] + continue + addr = struct.unpack('Q', records[i+8:i+16])[0] + try: + fp.seek(addr) + first = fp.read(8) + except: + if(output): + print('Bad address 0x%x in %s' % (addr, sysvals.mempath)) + return [0, 0] + rechead = struct.unpack('4sI', first) + recdata = fp.read(rechead[1]-8) + if(rechead[0] == 'FBPT'): + record = struct.unpack('HBBIQQQQQ', recdata) + if(output): + print('%s (%s)' % (rectype[header[0]], rechead[0])) + print(' Reset END : %u ns' % record[4]) + print(' OS Loader LoadImage Start : %u ns' % record[5]) + print(' OS Loader StartImage Start : %u ns' % record[6]) + print(' ExitBootServices Entry : %u ns' % record[7]) + print(' ExitBootServices Exit : %u ns' % record[8]) + elif(rechead[0] == 'S3PT'): + if(output): + print('%s (%s)' % (rectype[header[0]], rechead[0])) + j = 0 + while(j < len(recdata)): + prechead = struct.unpack('HBB', recdata[j:j+4]) + if(prechead[0] not in prectype): + continue + if(prechead[0] == 0): + record = struct.unpack('IIQQ', recdata[j:j+prechead[1]]) + fwData[1] = record[2] + if(output): + print(' %s' % prectype[prechead[0]]) + print(' Resume Count : %u' % \ + record[1]) + print(' FullResume : %u ns' % \ + record[2]) + print(' AverageResume : %u ns' % \ + record[3]) + elif(prechead[0] == 1): + record = struct.unpack('QQ', recdata[j+4:j+prechead[1]]) + fwData[0] = record[1] - record[0] + if(output): + print(' %s' % prectype[prechead[0]]) + print(' SuspendStart : %u ns' % \ + record[0]) + print(' SuspendEnd : %u ns' % \ + record[1]) + print(' SuspendTime : %u ns' % \ + fwData[0]) + j += prechead[1] + if(output): + print('') + i += header[1] + fp.close() + return fwData + +# Function: statusCheck +# Description: +# Verify that the requested command and options will work, and +# print the results to the terminal +# Output: +# True if the test will work, False if not +def statusCheck(probecheck=False): + status = True + + print('Checking this system (%s)...' % platform.node()) + + # check we have root access + res = sysvals.colorText('NO (No features of this tool will work!)') + if(rootCheck(False)): + res = 'YES' + print(' have root access: %s' % res) + if(res != 'YES'): + print(' Try running this script with sudo') + return False + + # check sysfs is mounted + res = sysvals.colorText('NO (No features of this tool will work!)') + if(os.path.exists(sysvals.powerfile)): + res = 'YES' + print(' is sysfs mounted: %s' % res) + if(res != 'YES'): + return False + + # check target mode is a valid mode + if sysvals.suspendmode != 'command': + res = sysvals.colorText('NO') + modes = getModes() + if(sysvals.suspendmode in modes): + res = 'YES' + else: + status = False + print(' is "%s" a valid power mode: %s' % (sysvals.suspendmode, res)) + if(res == 'NO'): + print(' valid power modes are: %s' % modes) + print(' please choose one with -m') + + # check if ftrace is available + res = sysvals.colorText('NO') + ftgood = sysvals.verifyFtrace() + if(ftgood): + res = 'YES' + elif(sysvals.usecallgraph): + status = False + print(' is ftrace supported: %s' % res) + + # check if kprobes are available + res = sysvals.colorText('NO') + sysvals.usekprobes = sysvals.verifyKprobes() + if(sysvals.usekprobes): + res = 'YES' + else: + sysvals.usedevsrc = False + print(' are kprobes supported: %s' % res) + + # what data source are we using + res = 'DMESG' + if(ftgood): + sysvals.usetraceeventsonly = True + sysvals.usetraceevents = False + for e in sysvals.traceevents: + check = False + if(os.path.exists(sysvals.epath+e)): + check = True + if(not check): + sysvals.usetraceeventsonly = False + if(e == 'suspend_resume' and check): + sysvals.usetraceevents = True + if(sysvals.usetraceevents and sysvals.usetraceeventsonly): + res = 'FTRACE (all trace events found)' + elif(sysvals.usetraceevents): + res = 'DMESG and FTRACE (suspend_resume trace event found)' + print(' timeline data source: %s' % res) + + # check if rtcwake + res = sysvals.colorText('NO') + if(sysvals.rtcpath != ''): + res = 'YES' + elif(sysvals.rtcwake): + status = False + print(' is rtcwake supported: %s' % res) + + if not probecheck: + return status + + # verify kprobes + if sysvals.usekprobes: + for name in sysvals.tracefuncs: + sysvals.defaultKprobe(name, sysvals.tracefuncs[name]) + if sysvals.usedevsrc: + for name in sysvals.dev_tracefuncs: + sysvals.defaultKprobe(name, sysvals.dev_tracefuncs[name]) + sysvals.addKprobes(True) + + return status + +# Function: doError +# Description: +# generic error function for catastrphic failures +# Arguments: +# msg: the error message to print +# help: True if printHelp should be called after, False otherwise +def doError(msg, help=False): + if(help == True): + printHelp() + print('ERROR: %s\n') % msg + sys.exit() + +# Function: rootCheck +# Description: +# quick check to see if we have root access +def rootCheck(fatal): + if(os.access(sysvals.powerfile, os.W_OK)): + return True + if fatal: + doError('This command requires sysfs mount and root access') + return False + +# Function: getArgInt +# Description: +# pull out an integer argument from the command line with checks +def getArgInt(name, args, min, max, main=True): + if main: + try: + arg = args.next() + except: + doError(name+': no argument supplied', True) + else: + arg = args + try: + val = int(arg) + except: + doError(name+': non-integer value given', True) + if(val < min or val > max): + doError(name+': value should be between %d and %d' % (min, max), True) + return val + +# Function: getArgFloat +# Description: +# pull out a float argument from the command line with checks +def getArgFloat(name, args, min, max, main=True): + if main: + try: + arg = args.next() + except: + doError(name+': no argument supplied', True) + else: + arg = args + try: + val = float(arg) + except: + doError(name+': non-numerical value given', True) + if(val < min or val > max): + doError(name+': value should be between %f and %f' % (min, max), True) + return val + +def processData(): + print('PROCESSING DATA') + if(sysvals.usetraceeventsonly): + testruns = parseTraceLog() + if sysvals.dmesgfile: + dmesgtext = loadKernelLog(True) + for data in testruns: + data.extractErrorInfo(dmesgtext) + else: + testruns = loadKernelLog() + for data in testruns: + parseKernelLog(data) + if(sysvals.ftracefile and (sysvals.usecallgraph or sysvals.usetraceevents)): + appendIncompleteTraceLog(testruns) + createHTML(testruns) + +# Function: rerunTest +# Description: +# generate an output from an existing set of ftrace/dmesg logs +def rerunTest(): + if sysvals.ftracefile: + doesTraceLogHaveTraceEvents() + if not sysvals.dmesgfile and not sysvals.usetraceeventsonly: + doError('recreating this html output requires a dmesg file') + sysvals.setOutputFile() + vprint('Output file: %s' % sysvals.htmlfile) + if(os.path.exists(sysvals.htmlfile) and not os.access(sysvals.htmlfile, os.W_OK)): + doError('missing permission to write to %s' % sysvals.htmlfile) + processData() + +# Function: runTest +# Description: +# execute a suspend/resume, gather the logs, and generate the output +def runTest(subdir, testpath=''): + # prepare for the test + sysvals.initFtrace() + sysvals.initTestOutput(subdir, testpath) + vprint('Output files:\n\t%s\n\t%s\n\t%s' % \ + (sysvals.dmesgfile, sysvals.ftracefile, sysvals.htmlfile)) + + # execute the test + executeSuspend() + sysvals.cleanupFtrace() + processData() + + # if running as root, change output dir owner to sudo_user + if os.path.isdir(sysvals.testdir) and os.getuid() == 0 and \ + 'SUDO_USER' in os.environ: + cmd = 'chown -R {0}:{0} {1} > /dev/null 2>&1' + call(cmd.format(os.environ['SUDO_USER'], sysvals.testdir), shell=True) + +def find_in_html(html, strs, div=False): + for str in strs: + l = len(str) + i = html.find(str) + if i >= 0: + break + if i < 0: + return '' + if not div: + return re.search(r'[-+]?\d*\.\d+|\d+', html[i+l:i+l+50]).group() + n = html[i+l:].find('</div>') + if n < 0: + return '' + return html[i+l:i+l+n] + +# Function: runSummary +# Description: +# create a summary of tests in a sub-directory +def runSummary(subdir, local=True): + inpath = os.path.abspath(subdir) + outpath = inpath + if local: + outpath = os.path.abspath('.') + print('Generating a summary of folder "%s"' % inpath) + testruns = [] + for dirname, dirnames, filenames in os.walk(subdir): + for filename in filenames: + if(not re.match('.*.html', filename)): + continue + file = os.path.join(dirname, filename) + html = open(file, 'r').read(10000) + suspend = find_in_html(html, + ['Kernel Suspend: ', 'Kernel Suspend Time: ']) + resume = find_in_html(html, + ['Kernel Resume: ', 'Kernel Resume Time: ']) + line = find_in_html(html, ['<div class="stamp">'], True) + stmp = line.split() + if not suspend or not resume or len(stmp) < 4: + continue + data = { + 'host': stmp[0], + 'kernel': stmp[1], + 'mode': stmp[2], + 'time': string.join(stmp[3:], ' '), + 'suspend': suspend, + 'resume': resume, + 'url': os.path.relpath(file, outpath), + } + if len(stmp) == 7: + data['kernel'] = 'unknown' + data['mode'] = stmp[1] + data['time'] = string.join(stmp[2:], ' ') + testruns.append(data) + outfile = os.path.join(outpath, 'summary.html') + print('Summary file: %s' % outfile) + createHTMLSummarySimple(testruns, outfile, inpath) + +# Function: checkArgBool +# Description: +# check if a boolean string value is true or false +def checkArgBool(value): + yes = ['1', 'true', 'yes', 'on'] + if value.lower() in yes: + return True + return False + +# Function: configFromFile +# Description: +# Configure the script via the info in a config file +def configFromFile(file): + Config = ConfigParser.ConfigParser() + + Config.read(file) + sections = Config.sections() + overridekprobes = False + overridedevkprobes = False + if 'Settings' in sections: + for opt in Config.options('Settings'): + value = Config.get('Settings', opt).lower() + if(opt.lower() == 'verbose'): + sysvals.verbose = checkArgBool(value) + elif(opt.lower() == 'addlogs'): + sysvals.addlogs = checkArgBool(value) + elif(opt.lower() == 'dev'): + sysvals.usedevsrc = checkArgBool(value) + elif(opt.lower() == 'proc'): + sysvals.useprocmon = checkArgBool(value) + elif(opt.lower() == 'x2'): + if checkArgBool(value): + sysvals.execcount = 2 + elif(opt.lower() == 'callgraph'): + sysvals.usecallgraph = checkArgBool(value) + elif(opt.lower() == 'override-timeline-functions'): + overridekprobes = checkArgBool(value) + elif(opt.lower() == 'override-dev-timeline-functions'): + overridedevkprobes = checkArgBool(value) + elif(opt.lower() == 'devicefilter'): + sysvals.setDeviceFilter(value) + elif(opt.lower() == 'expandcg'): + sysvals.cgexp = checkArgBool(value) + elif(opt.lower() == 'srgap'): + if checkArgBool(value): + sysvals.srgap = 5 + elif(opt.lower() == 'mode'): + sysvals.suspendmode = value + elif(opt.lower() == 'command'): + sysvals.testcommand = value + elif(opt.lower() == 'x2delay'): + sysvals.x2delay = getArgInt('-x2delay', value, 0, 60000, False) + elif(opt.lower() == 'predelay'): + sysvals.predelay = getArgInt('-predelay', value, 0, 60000, False) + elif(opt.lower() == 'postdelay'): + sysvals.postdelay = getArgInt('-postdelay', value, 0, 60000, False) + elif(opt.lower() == 'maxdepth'): + sysvals.max_graph_depth = getArgInt('-maxdepth', value, 0, 1000, False) + elif(opt.lower() == 'rtcwake'): + if value.lower() == 'off': + sysvals.rtcwake = False + else: + sysvals.rtcwake = True + sysvals.rtcwaketime = getArgInt('-rtcwake', value, 0, 3600, False) + elif(opt.lower() == 'timeprec'): + sysvals.setPrecision(getArgInt('-timeprec', value, 0, 6, False)) + elif(opt.lower() == 'mindev'): + sysvals.mindevlen = getArgFloat('-mindev', value, 0.0, 10000.0, False) + elif(opt.lower() == 'callloop-maxgap'): + sysvals.callloopmaxgap = getArgFloat('-callloop-maxgap', value, 0.0, 1.0, False) + elif(opt.lower() == 'callloop-maxlen'): + sysvals.callloopmaxgap = getArgFloat('-callloop-maxlen', value, 0.0, 1.0, False) + elif(opt.lower() == 'mincg'): + sysvals.mincglen = getArgFloat('-mincg', value, 0.0, 10000.0, False) + elif(opt.lower() == 'output-dir'): + sysvals.setOutputFolder(value) + + if sysvals.suspendmode == 'command' and not sysvals.testcommand: + doError('No command supplied for mode "command"') + + # compatibility errors + if sysvals.usedevsrc and sysvals.usecallgraph: + doError('-dev is not compatible with -f') + if sysvals.usecallgraph and sysvals.useprocmon: + doError('-proc is not compatible with -f') + + if overridekprobes: + sysvals.tracefuncs = dict() + if overridedevkprobes: + sysvals.dev_tracefuncs = dict() + + kprobes = dict() + kprobesec = 'dev_timeline_functions_'+platform.machine() + if kprobesec in sections: + for name in Config.options(kprobesec): + text = Config.get(kprobesec, name) + kprobes[name] = (text, True) + kprobesec = 'timeline_functions_'+platform.machine() + if kprobesec in sections: + for name in Config.options(kprobesec): + if name in kprobes: + doError('Duplicate timeline function found "%s"' % (name)) + text = Config.get(kprobesec, name) + kprobes[name] = (text, False) + + for name in kprobes: + function = name + format = name + color = '' + args = dict() + text, dev = kprobes[name] + data = text.split() + i = 0 + for val in data: + # bracketted strings are special formatting, read them separately + if val[0] == '[' and val[-1] == ']': + for prop in val[1:-1].split(','): + p = prop.split('=') + if p[0] == 'color': + try: + color = int(p[1], 16) + color = '#'+p[1] + except: + color = p[1] + continue + # first real arg should be the format string + if i == 0: + format = val + # all other args are actual function args + else: + d = val.split('=') + args[d[0]] = d[1] + i += 1 + if not function or not format: + doError('Invalid kprobe: %s' % name) + for arg in re.findall('{(?P<n>[a-z,A-Z,0-9]*)}', format): + if arg not in args: + doError('Kprobe "%s" is missing argument "%s"' % (name, arg)) + if (dev and name in sysvals.dev_tracefuncs) or (not dev and name in sysvals.tracefuncs): + doError('Duplicate timeline function found "%s"' % (name)) + + kp = { + 'name': name, + 'func': function, + 'format': format, + sysvals.archargs: args + } + if color: + kp['color'] = color + if dev: + sysvals.dev_tracefuncs[name] = kp + else: + sysvals.tracefuncs[name] = kp + +# Function: printHelp +# Description: +# print out the help text +def printHelp(): + modes = getModes() + + print('') + print('%s v%s' % (sysvals.title, sysvals.version)) + print('Usage: sudo sleepgraph <options> <commands>') + print('') + print('Description:') + print(' This tool is designed to assist kernel and OS developers in optimizing') + print(' their linux stack\'s suspend/resume time. Using a kernel image built') + print(' with a few extra options enabled, the tool will execute a suspend and') + print(' capture dmesg and ftrace data until resume is complete. This data is') + print(' transformed into a device timeline and an optional callgraph to give') + print(' a detailed view of which devices/subsystems are taking the most') + print(' time in suspend/resume.') + print('') + print(' If no specific command is given, the default behavior is to initiate') + print(' a suspend/resume and capture the dmesg/ftrace output as an html timeline.') + print('') + print(' Generates output files in subdirectory: suspend-mmddyy-HHMMSS') + print(' HTML output: <hostname>_<mode>.html') + print(' raw dmesg output: <hostname>_<mode>_dmesg.txt') + print(' raw ftrace output: <hostname>_<mode>_ftrace.txt') + print('') + print('Options:') + print(' -h Print this help text') + print(' -v Print the current tool version') + print(' -config fn Pull arguments and config options from file fn') + print(' -verbose Print extra information during execution and analysis') + print(' -m mode Mode to initiate for suspend %s (default: %s)') % (modes, sysvals.suspendmode) + print(' -o subdir Override the output subdirectory') + print(' -rtcwake t Wakeup t seconds after suspend, set t to "off" to disable (default: 15)') + print(' -addlogs Add the dmesg and ftrace logs to the html output') + print(' -srgap Add a visible gap in the timeline between sus/res (default: disabled)') + print(' [advanced]') + print(' -cmd {s} Run the timeline over a custom command, e.g. "sync -d"') + print(' -proc Add usermode process info into the timeline (default: disabled)') + print(' -dev Add kernel function calls and threads to the timeline (default: disabled)') + print(' -x2 Run two suspend/resumes back to back (default: disabled)') + print(' -x2delay t Include t ms delay between multiple test runs (default: 0 ms)') + print(' -predelay t Include t ms delay before 1st suspend (default: 0 ms)') + print(' -postdelay t Include t ms delay after last resume (default: 0 ms)') + print(' -mindev ms Discard all device blocks shorter than ms milliseconds (e.g. 0.001 for us)') + print(' -multi n d Execute <n> consecutive tests at <d> seconds intervals. The outputs will') + print(' be created in a new subdirectory with a summary page.') + print(' [debug]') + print(' -f Use ftrace to create device callgraphs (default: disabled)') + print(' -maxdepth N limit the callgraph data to N call levels (default: 0=all)') + print(' -expandcg pre-expand the callgraph data in the html output (default: disabled)') + print(' -fadd file Add functions to be graphed in the timeline from a list in a text file') + print(' -filter "d1,d2,..." Filter out all but this comma-delimited list of device names') + print(' -mincg ms Discard all callgraphs shorter than ms milliseconds (e.g. 0.001 for us)') + print(' -cgphase P Only show callgraph data for phase P (e.g. suspend_late)') + print(' -cgtest N Only show callgraph data for test N (e.g. 0 or 1 in an x2 run)') + print(' -timeprec N Number of significant digits in timestamps (0:S, [3:ms], 6:us)') + print(' [commands]') + print(' -ftrace ftracefile Create HTML output using ftrace input (used with -dmesg)') + print(' -dmesg dmesgfile Create HTML output using dmesg (used with -ftrace)') + print(' -summary directory Create a summary of all test in this dir') + print(' -modes List available suspend modes') + print(' -status Test to see if the system is enabled to run this tool') + print(' -fpdt Print out the contents of the ACPI Firmware Performance Data Table') + print(' -usbtopo Print out the current USB topology with power info') + print(' -usbauto Enable autosuspend for all connected USB devices') + print(' -flist Print the list of functions currently being captured in ftrace') + print(' -flistall Print all functions capable of being captured in ftrace') + print('') + return True + +# ----------------- MAIN -------------------- +# exec start (skipped if script is loaded as library) +if __name__ == '__main__': + cmd = '' + cmdarg = '' + multitest = {'run': False, 'count': 0, 'delay': 0} + simplecmds = ['-modes', '-fpdt', '-flist', '-flistall', '-usbtopo', '-usbauto', '-status'] + # loop through the command line arguments + args = iter(sys.argv[1:]) + for arg in args: + if(arg == '-m'): + try: + val = args.next() + except: + doError('No mode supplied', True) + if val == 'command' and not sysvals.testcommand: + doError('No command supplied for mode "command"', True) + sysvals.suspendmode = val + elif(arg in simplecmds): + cmd = arg[1:] + elif(arg == '-h'): + printHelp() + sys.exit() + elif(arg == '-v'): + print("Version %s" % sysvals.version) + sys.exit() + elif(arg == '-x2'): + sysvals.execcount = 2 + elif(arg == '-x2delay'): + sysvals.x2delay = getArgInt('-x2delay', args, 0, 60000) + elif(arg == '-predelay'): + sysvals.predelay = getArgInt('-predelay', args, 0, 60000) + elif(arg == '-postdelay'): + sysvals.postdelay = getArgInt('-postdelay', args, 0, 60000) + elif(arg == '-f'): + sysvals.usecallgraph = True + elif(arg == '-addlogs'): + sysvals.addlogs = True + elif(arg == '-verbose'): + sysvals.verbose = True + elif(arg == '-proc'): + sysvals.useprocmon = True + elif(arg == '-dev'): + sysvals.usedevsrc = True + elif(arg == '-maxdepth'): + sysvals.max_graph_depth = getArgInt('-maxdepth', args, 0, 1000) + elif(arg == '-rtcwake'): + try: + val = args.next() + except: + doError('No rtcwake time supplied', True) + if val.lower() == 'off': + sysvals.rtcwake = False + else: + sysvals.rtcwake = True + sysvals.rtcwaketime = getArgInt('-rtcwake', val, 0, 3600, False) + elif(arg == '-timeprec'): + sysvals.setPrecision(getArgInt('-timeprec', args, 0, 6)) + elif(arg == '-mindev'): + sysvals.mindevlen = getArgFloat('-mindev', args, 0.0, 10000.0) + elif(arg == '-mincg'): + sysvals.mincglen = getArgFloat('-mincg', args, 0.0, 10000.0) + elif(arg == '-cgtest'): + sysvals.cgtest = getArgInt('-cgtest', args, 0, 1) + elif(arg == '-cgphase'): + try: + val = args.next() + except: + doError('No phase name supplied', True) + d = Data(0) + if val not in d.phases: + doError('Invalid phase, valid phaess are %s' % d.phases, True) + sysvals.cgphase = val + elif(arg == '-callloop-maxgap'): + sysvals.callloopmaxgap = getArgFloat('-callloop-maxgap', args, 0.0, 1.0) + elif(arg == '-callloop-maxlen'): + sysvals.callloopmaxlen = getArgFloat('-callloop-maxlen', args, 0.0, 1.0) + elif(arg == '-cmd'): + try: + val = args.next() + except: + doError('No command string supplied', True) + sysvals.testcommand = val + sysvals.suspendmode = 'command' + elif(arg == '-expandcg'): + sysvals.cgexp = True + elif(arg == '-srgap'): + sysvals.srgap = 5 + elif(arg == '-multi'): + multitest['run'] = True + multitest['count'] = getArgInt('-multi n (exec count)', args, 2, 1000000) + multitest['delay'] = getArgInt('-multi d (delay between tests)', args, 0, 3600) + elif(arg == '-o'): + try: + val = args.next() + except: + doError('No subdirectory name supplied', True) + sysvals.setOutputFolder(val) + elif(arg == '-config'): + try: + val = args.next() + except: + doError('No text file supplied', True) + if(os.path.exists(val) == False): + doError('%s does not exist' % val) + configFromFile(val) + elif(arg == '-fadd'): + try: + val = args.next() + except: + doError('No text file supplied', True) + if(os.path.exists(val) == False): + doError('%s does not exist' % val) + sysvals.addFtraceFilterFunctions(val) + elif(arg == '-dmesg'): + try: + val = args.next() + except: + doError('No dmesg file supplied', True) + sysvals.notestrun = True + sysvals.dmesgfile = val + if(os.path.exists(sysvals.dmesgfile) == False): + doError('%s does not exist' % sysvals.dmesgfile) + elif(arg == '-ftrace'): + try: + val = args.next() + except: + doError('No ftrace file supplied', True) + sysvals.notestrun = True + sysvals.ftracefile = val + if(os.path.exists(sysvals.ftracefile) == False): + doError('%s does not exist' % sysvals.ftracefile) + elif(arg == '-summary'): + try: + val = args.next() + except: + doError('No directory supplied', True) + cmd = 'summary' + cmdarg = val + sysvals.notestrun = True + if(os.path.isdir(val) == False): + doError('%s is not accesible' % val) + elif(arg == '-filter'): + try: + val = args.next() + except: + doError('No devnames supplied', True) + sysvals.setDeviceFilter(val) + else: + doError('Invalid argument: '+arg, True) + + # compatibility errors + if(sysvals.usecallgraph and sysvals.usedevsrc): + doError('-dev is not compatible with -f') + if(sysvals.usecallgraph and sysvals.useprocmon): + doError('-proc is not compatible with -f') + + # callgraph size cannot exceed device size + if sysvals.mincglen < sysvals.mindevlen: + sysvals.mincglen = sysvals.mindevlen + + # just run a utility command and exit + if(cmd != ''): + if(cmd == 'status'): + statusCheck(True) + elif(cmd == 'fpdt'): + getFPDT(True) + elif(cmd == 'usbtopo'): + detectUSB() + elif(cmd == 'modes'): + print getModes() + elif(cmd == 'flist'): + sysvals.getFtraceFilterFunctions(True) + elif(cmd == 'flistall'): + sysvals.getFtraceFilterFunctions(False) + elif(cmd == 'usbauto'): + setUSBDevicesAuto() + elif(cmd == 'summary'): + runSummary(cmdarg, True) + sys.exit() + + # if instructed, re-analyze existing data files + if(sysvals.notestrun): + rerunTest() + sys.exit() + + # verify that we can run a test + if(not statusCheck()): + print('Check FAILED, aborting the test run!') + sys.exit() + + if multitest['run']: + # run multiple tests in a separate subdirectory + s = 'x%d' % multitest['count'] + if not sysvals.outdir: + sysvals.outdir = datetime.now().strftime('suspend-'+s+'-%m%d%y-%H%M%S') + if not os.path.isdir(sysvals.outdir): + os.mkdir(sysvals.outdir) + for i in range(multitest['count']): + if(i != 0): + print('Waiting %d seconds...' % (multitest['delay'])) + time.sleep(multitest['delay']) + print('TEST (%d/%d) START' % (i+1, multitest['count'])) + runTest(sysvals.outdir) + print('TEST (%d/%d) COMPLETE' % (i+1, multitest['count'])) + runSummary(sysvals.outdir, False) + else: + # run the test in the current directory + runTest('.', sysvals.outdir) diff --git a/tools/power/pm-graph/bootgraph.8 b/tools/power/pm-graph/bootgraph.8 new file mode 100644 index 000000000000..55272a67b0e7 --- /dev/null +++ b/tools/power/pm-graph/bootgraph.8 @@ -0,0 +1,132 @@ +.TH BOOTGRAPH 8 +.SH NAME +bootgraph \- Kernel boot timing analysis +.SH SYNOPSIS +.ft B +.B bootgraph +.RB [ OPTIONS ] +.RB [ COMMAND ] +.SH DESCRIPTION +\fBbootgraph \fP reads the dmesg log from kernel boot and +creates an html representation of the initcall timeline up to the start +of the init process. +.PP +If no specific command is given, the tool reads the current dmesg log and +outputs bootgraph.html. +.PP +The tool can also augment the timeline with ftrace data on custom target +functions as well as full trace callgraphs. +.SH OPTIONS +.TP +\fB-h\fR +Print this help text +.TP +\fB-v\fR +Print the current tool version +.TP +\fB-addlogs\fR +Add the dmesg log to the html output. It will be viewable by +clicking a button in the timeline. +.TP +\fB-o \fIfile\fR +Override the HTML output filename (default: bootgraph.html) +.SS "Ftrace Debug" +.TP +\fB-f\fR +Use ftrace to add function detail (default: disabled) +.TP +\fB-callgraph\fR +Use ftrace to create initcall callgraphs (default: disabled). If -filter +is not used there will be one callgraph per initcall. This can produce +very large outputs, i.e. 10MB - 100MB. +.TP +\fB-maxdepth \fIlevel\fR +limit the callgraph trace depth to \fIlevel\fR (default: 2). This is +the best way to limit the output size when using -callgraph. +.TP +\fB-mincg \fIt\fR +Discard all callgraphs shorter than \fIt\fR milliseconds (default: 0=all). +This reduces the html file size as there can be many tiny callgraphs +which are barely visible in the timeline. +The value is a float: e.g. 0.001 represents 1 us. +.TP +\fB-timeprec \fIn\fR +Number of significant digits in timestamps (0:S, 3:ms, [6:us]) +.TP +\fB-expandcg\fR +pre-expand the callgraph data in the html output (default: disabled) +.TP +\fB-filter \fI"func1,func2,..."\fR +Instead of tracing each initcall, trace a custom list of functions (default: do_one_initcall) + +.SH COMMANDS +.TP +\fB-reboot\fR +Reboot the machine and generate a new timeline automatically. Works in 4 steps. + 1. updates grub with the required kernel parameters + 2. installs a cron job which re-runs the tool after reboot + 3. reboots the system + 4. after startup, extracts the data and generates the timeline +.TP +\fB-manual\fR +Show the requirements to generate a new timeline manually. Requires 3 steps. + 1. append the string to the kernel command line via your native boot manager. + 2. reboot the system + 3. after startup, re-run the tool with the same arguments and no command +.TP +\fB-dmesg \fIfile\fR +Create HTML output from an existing dmesg file. +.TP +\fB-ftrace \fIfile\fR +Create HTML output from an existing ftrace file (used with -dmesg). +.TP +\fB-flistall\fR +Print all ftrace functions capable of being captured. These are all the +possible values you can add to trace via the -filter argument. + +.SH EXAMPLES +Create a timeline using the current dmesg log. +.IP +\f(CW$ bootgraph\fR +.PP +Create a timeline using the current dmesg and ftrace log. +.IP +\f(CW$ bootgraph -callgraph\fR +.PP +Create a timeline using the current dmesg, add the log to the html and change the name. +.IP +\f(CW$ bootgraph -addlogs -o myboot.html\fR +.PP +Capture a new boot timeline by automatically rebooting the machine. +.IP +\f(CW$ sudo bootgraph -reboot -addlogs -o latestboot.html\fR +.PP +Capture a new boot timeline with function trace data. +.IP +\f(CW$ sudo bootgraph -reboot -f\fR +.PP +Capture a new boot timeline with trace & callgraph data. Skip callgraphs smaller than 5ms. +.IP +\f(CW$ sudo bootgraph -reboot -callgraph -mincg 5\fR +.PP +Capture a new boot timeline with callgraph data over custom functions. +.IP +\f(CW$ sudo bootgraph -reboot -callgraph -filter "acpi_ps_parse_aml,msleep"\fR +.PP +Capture a brand new boot timeline with manual reboot. +.IP +\f(CW$ sudo bootgraph -callgraph -manual\fR +.IP +\f(CW$ vi /etc/default/grub # add the CMDLINE string to your kernel params\fR +.IP +\f(CW$ sudo reboot # reboot the machine\fR +.IP +\f(CW$ sudo bootgraph -callgraph # re-run the tool after restart\fR +.PP + +.SH "SEE ALSO" +dmesg(1), update-grub(8), crontab(1), reboot(8) +.PP +.SH AUTHOR +.nf +Written by Todd Brandt <todd.e.brandt@linux.intel.com> diff --git a/tools/power/pm-graph/sleepgraph.8 b/tools/power/pm-graph/sleepgraph.8 new file mode 100644 index 000000000000..610e72ebbc06 --- /dev/null +++ b/tools/power/pm-graph/sleepgraph.8 @@ -0,0 +1,243 @@ +.TH SLEEPGRAPH 8 +.SH NAME +sleepgraph \- Suspend/Resume timing analysis +.SH SYNOPSIS +.ft B +.B sleepgraph +.RB [ OPTIONS ] +.RB [ COMMAND ] +.SH DESCRIPTION +\fBsleepgraph \fP is designed to assist kernel and OS developers +in optimizing their linux stack's suspend/resume time. Using a kernel +image built with a few extra options enabled, the tool will execute a +suspend and capture dmesg and ftrace data until resume is complete. +This data is transformed into a device timeline and an optional +callgraph to give a detailed view of which devices/subsystems are +taking the most time in suspend/resume. +.PP +If no specific command is given, the default behavior is to initiate +a suspend/resume. +.PP +Generates output files in subdirectory: suspend-yymmdd-HHMMSS + html timeline : <hostname>_<mode>.html + raw dmesg file : <hostname>_<mode>_dmesg.txt + raw ftrace file : <hostname>_<mode>_ftrace.txt +.SH OPTIONS +.TP +\fB-h\fR +Print the help text. +.TP +\fB-v\fR +Print the current tool version. +.TP +\fB-verbose\fR +Print extra information during execution and analysis. +.TP +\fB-config \fIfile\fR +Pull arguments and config options from a file. +.TP +\fB-m \fImode\fR +Mode to initiate for suspend e.g. standby, freeze, mem (default: mem). +.TP +\fB-o \fIsubdir\fR +Override the output subdirectory. Use {date}, {time}, {hostname} for current values. +.sp +e.g. suspend-{hostname}-{date}-{time} +.TP +\fB-rtcwake \fIt\fR | off +Use rtcwake to autoresume after \fIt\fR seconds (default: 15). Set t to "off" to +disable rtcwake and require a user keypress to resume. +.TP +\fB-addlogs\fR +Add the dmesg and ftrace logs to the html output. They will be viewable by +clicking buttons in the timeline. + +.SS "Advanced" +.TP +\fB-cmd \fIstr\fR +Run the timeline over a custom suspend command, e.g. pm-suspend. By default +the tool forces suspend via /sys/power/state so this allows testing over +an OS's official suspend method. The output file will change to +hostname_command.html and will autodetect which suspend mode was triggered. +.TP +\fB-filter \fI"d1,d2,..."\fR +Filter out all but these device callbacks. These strings can be device names +or module names. e.g. 0000:00:02.0, ata5, i915, usb, etc. +.TP +\fB-mindev \fIt\fR +Discard all device callbacks shorter than \fIt\fR milliseconds (default: 0.0). +This reduces the html file size as there can be many tiny callbacks which are barely +visible. The value is a float: e.g. 0.001 represents 1 us. +.TP +\fB-proc\fR +Add usermode process info into the timeline (default: disabled). +.TP +\fB-dev\fR +Add kernel source calls and threads to the timeline (default: disabled). +.TP +\fB-x2\fR +Run two suspend/resumes back to back (default: disabled). +.TP +\fB-x2delay \fIt\fR +Include \fIt\fR ms delay between multiple test runs (default: 0 ms). +.TP +\fB-predelay \fIt\fR +Include \fIt\fR ms delay before 1st suspend (default: 0 ms). +.TP +\fB-postdelay \fIt\fR +Include \fIt\fR ms delay after last resume (default: 0 ms). +.TP +\fB-multi \fIn d\fR +Execute \fIn\fR consecutive tests at \fId\fR seconds intervals. The outputs will +be created in a new subdirectory with a summary page: suspend-xN-{date}-{time}. + +.SS "Ftrace Debug" +.TP +\fB-f\fR +Use ftrace to create device callgraphs (default: disabled). This can produce +very large outputs, i.e. 10MB - 100MB. +.TP +\fB-maxdepth \fIlevel\fR +limit the callgraph trace depth to \fIlevel\fR (default: 0=all). This is +the best way to limit the output size when using callgraphs via -f. +.TP +\fB-expandcg\fR +pre-expand the callgraph data in the html output (default: disabled) +.TP +\fB-fadd \fIfile\fR +Add functions to be graphed in the timeline from a list in a text file +.TP +\fB-mincg \fIt\fR +Discard all callgraphs shorter than \fIt\fR milliseconds (default: 0.0). +This reduces the html file size as there can be many tiny callgraphs +which are barely visible in the timeline. +The value is a float: e.g. 0.001 represents 1 us. +.TP +\fB-cgphase \fIp\fR +Only show callgraph data for phase \fIp\fR (e.g. suspend_late). +.TP +\fB-cgtest \fIn\fR +In an x2 run, only show callgraph data for test \fIn\fR (e.g. 0 or 1). +.TP +\fB-timeprec \fIn\fR +Number of significant digits in timestamps (0:S, [3:ms], 6:us). + +.SH COMMANDS +.TP +\fB-ftrace \fIfile\fR +Create HTML output from an existing ftrace file. +.TP +\fB-dmesg \fIfile\fR +Create HTML output from an existing dmesg file. +.TP +\fB-summary \fIindir\fR +Create a summary page of all tests in \fIindir\fR. Creates summary.html +in the current folder. The output page is a table of tests with +suspend and resume values sorted by suspend mode, host, and kernel. +Includes test averages by mode and links to the test html files. +.TP +\fB-modes\fR +List available suspend modes. +.TP +\fB-status\fR +Test to see if the system is able to run this tool. Use this along +with any options you intend to use to see if they will work. +.TP +\fB-fpdt\fR +Print out the contents of the ACPI Firmware Performance Data Table. +.TP +\fB-usbtopo\fR +Print out the current USB topology with power info. +.TP +\fB-usbauto\fR +Enable autosuspend for all connected USB devices. +.TP +\fB-flist\fR +Print the list of ftrace functions currently being captured. Functions +that are not available as symbols in the current kernel are shown in red. +By default, the tool traces a list of important suspend/resume functions +in order to better fill out the timeline. If the user has added their own +with -fadd they will also be checked. +.TP +\fB-flistall\fR +Print all ftrace functions capable of being captured. These are all the +possible values you can add to trace via the -fadd argument. + +.SH EXAMPLES +.SS "Simple Commands" +Check which suspend modes are currently supported. +.IP +\f(CW$ sleepgraph -modes\fR +.PP +Read the Firmware Performance Data Table (FPDT) +.IP +\f(CW$ sudo sleepgraph -fpdt\fR +.PP +Print out the current USB power topology +.IP +\f(CW$ sleepgraph -usbtopo +.PP +Verify that you can run a command with a set of arguments +.IP +\f(CW$ sudo sleepgraph -f -rtcwake 30 -status +.PP +Generate a summary of all timelines in a particular folder. +.IP +\f(CW$ sleepgraph -summary ~/workspace/myresults/\fR +.PP +Re-generate the html output from a previous run's dmesg and ftrace log. +.IP +\f(CW$ sleepgraph -dmesg myhost_mem_dmesg.txt -ftrace myhost_mem_ftrace.txt\fR +.PP + +.SS "Capturing Simple Timelines" +Execute a mem suspend with a 15 second wakeup. Include the logs in the html. +.IP +\f(CW$ sudo sleepgraph -rtcwake 15 -addlogs\fR +.PP +Execute a standby with a 15 second wakeup. Change the output folder name. +.IP +\f(CW$ sudo sleepgraph -m standby -rtcwake 15 -o "standby-{hostname}-{date}-{time}"\fR +.PP +Execute a freeze with no wakeup (require keypress). Change output folder name. +.IP +\f(CW$ sudo sleepgraph -m freeze -rtcwake off -o "freeze-{hostname}-{date}-{time}"\fR +.PP + +.SS "Capturing Advanced Timelines" +Execute a suspend & include dev mode source calls, limit callbacks to 5ms or larger. +.IP +\f(CW$ sudo sleepgraph -m mem -rtcwake 15 -dev -mindev 5\fR +.PP +Run two suspends back to back, include a 500ms delay before, after, and in between runs. +.IP +\f(CW$ sudo sleepgraph -m mem -rtcwake 15 -x2 -predelay 500 -x2delay 500 -postdelay 500\fR +.PP +Do a batch run of 10 freezes with 30 seconds delay between runs. +.IP +\f(CW$ sudo sleepgraph -m freeze -rtcwake 15 -multi 10 30\fR +.PP +Execute a suspend using a custom command. +.IP +\f(CW$ sudo sleepgraph -cmd "echo mem > /sys/power/state" -rtcwake 15\fR +.PP + + +.SS "Capturing Timelines with Callgraph Data" +Add device callgraphs. Limit the trace depth and only show callgraphs 10ms or larger. +.IP +\f(CW$ sudo sleepgraph -m mem -rtcwake 15 -f -maxdepth 5 -mincg 10\fR +.PP +Capture a full callgraph across all suspend, then filter the html by a single phase. +.IP +\f(CW$ sudo sleepgraph -m mem -rtcwake 15 -f\fR +.IP +\f(CW$ sleepgraph -dmesg host_mem_dmesg.txt -ftrace host_mem_ftrace.txt -f -cgphase resume +.PP + +.SH "SEE ALSO" +dmesg(1) +.PP +.SH AUTHOR +.nf +Written by Todd Brandt <todd.e.brandt@linux.intel.com> diff --git a/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py b/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py new file mode 100755 index 000000000000..0b24dd9d01ff --- /dev/null +++ b/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py @@ -0,0 +1,586 @@ +#!/usr/bin/python +# -*- coding: utf-8 -*- +# +""" This utility can be used to debug and tune the performance of the +intel_pstate driver. This utility can be used in two ways: +- If there is Linux trace file with pstate_sample events enabled, then +this utility can parse the trace file and generate performance plots. +- If user has not specified a trace file as input via command line parameters, +then this utility enables and collects trace data for a user specified interval +and generates performance plots. + +Prerequisites: + Python version 2.7.x + gnuplot 5.0 or higher + gnuplot-py 1.8 + (Most of the distributions have these required packages. They may be called + gnuplot-py, phython-gnuplot. ) + + HWP (Hardware P-States are disabled) + Kernel config for Linux trace is enabled + + see print_help(): for Usage and Output details + +""" +from __future__ import print_function +from datetime import datetime +import subprocess +import os +import time +import re +import sys +import getopt +import Gnuplot +from numpy import * +from decimal import * + +__author__ = "Srinivas Pandruvada" +__copyright__ = " Copyright (c) 2017, Intel Corporation. " +__license__ = "GPL version 2" + + +MAX_CPUS = 256 + +# Define the csv file columns +C_COMM = 18 +C_GHZ = 17 +C_ELAPSED = 16 +C_SAMPLE = 15 +C_DURATION = 14 +C_LOAD = 13 +C_BOOST = 12 +C_FREQ = 11 +C_TSC = 10 +C_APERF = 9 +C_MPERF = 8 +C_TO = 7 +C_FROM = 6 +C_SCALED = 5 +C_CORE = 4 +C_USEC = 3 +C_SEC = 2 +C_CPU = 1 + +global sample_num, last_sec_cpu, last_usec_cpu, start_time, testname + +# 11 digits covers uptime to 115 days +getcontext().prec = 11 + +sample_num =0 +last_sec_cpu = [0] * MAX_CPUS +last_usec_cpu = [0] * MAX_CPUS + +def print_help(): + print('intel_pstate_tracer.py:') + print(' Usage:') + print(' If the trace file is available, then to simply parse and plot, use (sudo not required):') + print(' ./intel_pstate_tracer.py [-c cpus] -t <trace_file> -n <test_name>') + print(' Or') + print(' ./intel_pstate_tracer.py [--cpu cpus] ---trace_file <trace_file> --name <test_name>') + print(' To generate trace file, parse and plot, use (sudo required):') + print(' sudo ./intel_pstate_tracer.py [-c cpus] -i <interval> -n <test_name>') + print(' Or') + print(' sudo ./intel_pstate_tracer.py [--cpu cpus] --interval <interval> --name <test_name>') + print(' Optional argument:') + print(' cpus: comma separated list of CPUs') + print(' Output:') + print(' If not already present, creates a "results/test_name" folder in the current working directory with:') + print(' cpu.csv - comma seperated values file with trace contents and some additional calculations.') + print(' cpu???.csv - comma seperated values file for CPU number ???.') + print(' *.png - a variety of PNG format plot files created from the trace contents and the additional calculations.') + print(' Notes:') + print(' Avoid the use of _ (underscore) in test names, because in gnuplot it is a subscript directive.') + print(' Maximum number of CPUs is {0:d}. If there are more the script will abort with an error.'.format(MAX_CPUS)) + print(' Off-line CPUs cause the script to list some warnings, and create some empty files. Use the CPU mask feature for a clean run.') + print(' Empty y range warnings for autoscaled plots can occur and can be ignored.') + +def plot_perf_busy_with_sample(cpu_index): + """ Plot method to per cpu information """ + + file_name = 'cpu{:0>3}.csv'.format(cpu_index) + if os.path.exists(file_name): + output_png = "cpu%03d_perf_busy_vs_samples.png" % cpu_index + g_plot = common_all_gnuplot_settings(output_png) + g_plot('set yrange [0:40]') + g_plot('set y2range [0:200]') + g_plot('set y2tics 0, 10') + g_plot('set title "{} : cpu perf busy vs. sample : CPU {:0>3} : {:%F %H:%M}"'.format(testname, cpu_index, datetime.now())) +# Override common + g_plot('set xlabel "Samples"') + g_plot('set ylabel "P-State"') + g_plot('set y2label "Scaled Busy/performance/io-busy(%)"') + set_4_plot_linestyles(g_plot) + g_plot('plot "' + file_name + '" using {:d}:{:d} with linespoints linestyle 1 axis x1y2 title "performance",\\'.format(C_SAMPLE, C_CORE)) + g_plot('"' + file_name + '" using {:d}:{:d} with linespoints linestyle 2 axis x1y2 title "scaled-busy",\\'.format(C_SAMPLE, C_SCALED)) + g_plot('"' + file_name + '" using {:d}:{:d} with linespoints linestyle 3 axis x1y2 title "io-boost",\\'.format(C_SAMPLE, C_BOOST)) + g_plot('"' + file_name + '" using {:d}:{:d} with linespoints linestyle 4 axis x1y1 title "P-State"'.format(C_SAMPLE, C_TO)) + +def plot_perf_busy(cpu_index): + """ Plot some per cpu information """ + + file_name = 'cpu{:0>3}.csv'.format(cpu_index) + if os.path.exists(file_name): + output_png = "cpu%03d_perf_busy.png" % cpu_index + g_plot = common_all_gnuplot_settings(output_png) + g_plot('set yrange [0:40]') + g_plot('set y2range [0:200]') + g_plot('set y2tics 0, 10') + g_plot('set title "{} : perf busy : CPU {:0>3} : {:%F %H:%M}"'.format(testname, cpu_index, datetime.now())) + g_plot('set ylabel "P-State"') + g_plot('set y2label "Scaled Busy/performance/io-busy(%)"') + set_4_plot_linestyles(g_plot) + g_plot('plot "' + file_name + '" using {:d}:{:d} with linespoints linestyle 1 axis x1y2 title "performance",\\'.format(C_ELAPSED, C_CORE)) + g_plot('"' + file_name + '" using {:d}:{:d} with linespoints linestyle 2 axis x1y2 title "scaled-busy",\\'.format(C_ELAPSED, C_SCALED)) + g_plot('"' + file_name + '" using {:d}:{:d} with linespoints linestyle 3 axis x1y2 title "io-boost",\\'.format(C_ELAPSED, C_BOOST)) + g_plot('"' + file_name + '" using {:d}:{:d} with linespoints linestyle 4 axis x1y1 title "P-State"'.format(C_ELAPSED, C_TO)) + +def plot_durations(cpu_index): + """ Plot per cpu durations """ + + file_name = 'cpu{:0>3}.csv'.format(cpu_index) + if os.path.exists(file_name): + output_png = "cpu%03d_durations.png" % cpu_index + g_plot = common_all_gnuplot_settings(output_png) +# Should autoscale be used here? Should seconds be used here? + g_plot('set yrange [0:5000]') + g_plot('set ytics 0, 500') + g_plot('set title "{} : durations : CPU {:0>3} : {:%F %H:%M}"'.format(testname, cpu_index, datetime.now())) + g_plot('set ylabel "Timer Duration (MilliSeconds)"') +# override common + g_plot('set key off') + set_4_plot_linestyles(g_plot) + g_plot('plot "' + file_name + '" using {:d}:{:d} with linespoints linestyle 1 axis x1y1'.format(C_ELAPSED, C_DURATION)) + +def plot_loads(cpu_index): + """ Plot per cpu loads """ + + file_name = 'cpu{:0>3}.csv'.format(cpu_index) + if os.path.exists(file_name): + output_png = "cpu%03d_loads.png" % cpu_index + g_plot = common_all_gnuplot_settings(output_png) + g_plot('set yrange [0:100]') + g_plot('set ytics 0, 10') + g_plot('set title "{} : loads : CPU {:0>3} : {:%F %H:%M}"'.format(testname, cpu_index, datetime.now())) + g_plot('set ylabel "CPU load (percent)"') +# override common + g_plot('set key off') + set_4_plot_linestyles(g_plot) + g_plot('plot "' + file_name + '" using {:d}:{:d} with linespoints linestyle 1 axis x1y1'.format(C_ELAPSED, C_LOAD)) + +def plot_pstate_cpu_with_sample(): + """ Plot all cpu information """ + + if os.path.exists('cpu.csv'): + output_png = 'all_cpu_pstates_vs_samples.png' + g_plot = common_all_gnuplot_settings(output_png) + g_plot('set yrange [0:40]') +# override common + g_plot('set xlabel "Samples"') + g_plot('set ylabel "P-State"') + g_plot('set title "{} : cpu pstate vs. sample : {:%F %H:%M}"'.format(testname, datetime.now())) + title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ') + plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_SAMPLE, C_TO) + g_plot('title_list = "{}"'.format(title_list)) + g_plot(plot_str) + +def plot_pstate_cpu(): + """ Plot all cpu information from csv files """ + + output_png = 'all_cpu_pstates.png' + g_plot = common_all_gnuplot_settings(output_png) + g_plot('set yrange [0:40]') + g_plot('set ylabel "P-State"') + g_plot('set title "{} : cpu pstates : {:%F %H:%M}"'.format(testname, datetime.now())) + +# the following command is really cool, but doesn't work with the CPU masking option because it aborts on the first missing file. +# plot_str = 'plot for [i=0:*] file=sprintf("cpu%03d.csv",i) title_s=sprintf("cpu%03d",i) file using 16:7 pt 7 ps 1 title title_s' +# + title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ') + plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_TO) + g_plot('title_list = "{}"'.format(title_list)) + g_plot(plot_str) + +def plot_load_cpu(): + """ Plot all cpu loads """ + + output_png = 'all_cpu_loads.png' + g_plot = common_all_gnuplot_settings(output_png) + g_plot('set yrange [0:100]') + g_plot('set ylabel "CPU load (percent)"') + g_plot('set title "{} : cpu loads : {:%F %H:%M}"'.format(testname, datetime.now())) + + title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ') + plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_LOAD) + g_plot('title_list = "{}"'.format(title_list)) + g_plot(plot_str) + +def plot_frequency_cpu(): + """ Plot all cpu frequencies """ + + output_png = 'all_cpu_frequencies.png' + g_plot = common_all_gnuplot_settings(output_png) + g_plot('set yrange [0:4]') + g_plot('set ylabel "CPU Frequency (GHz)"') + g_plot('set title "{} : cpu frequencies : {:%F %H:%M}"'.format(testname, datetime.now())) + + title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ') + plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_FREQ) + g_plot('title_list = "{}"'.format(title_list)) + g_plot(plot_str) + +def plot_duration_cpu(): + """ Plot all cpu durations """ + + output_png = 'all_cpu_durations.png' + g_plot = common_all_gnuplot_settings(output_png) + g_plot('set yrange [0:5000]') + g_plot('set ytics 0, 500') + g_plot('set ylabel "Timer Duration (MilliSeconds)"') + g_plot('set title "{} : cpu durations : {:%F %H:%M}"'.format(testname, datetime.now())) + + title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ') + plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_DURATION) + g_plot('title_list = "{}"'.format(title_list)) + g_plot(plot_str) + +def plot_scaled_cpu(): + """ Plot all cpu scaled busy """ + + output_png = 'all_cpu_scaled.png' + g_plot = common_all_gnuplot_settings(output_png) +# autoscale this one, no set y range + g_plot('set ylabel "Scaled Busy (Unitless)"') + g_plot('set title "{} : cpu scaled busy : {:%F %H:%M}"'.format(testname, datetime.now())) + + title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ') + plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_SCALED) + g_plot('title_list = "{}"'.format(title_list)) + g_plot(plot_str) + +def plot_boost_cpu(): + """ Plot all cpu IO Boosts """ + + output_png = 'all_cpu_boost.png' + g_plot = common_all_gnuplot_settings(output_png) + g_plot('set yrange [0:100]') + g_plot('set ylabel "CPU IO Boost (percent)"') + g_plot('set title "{} : cpu io boost : {:%F %H:%M}"'.format(testname, datetime.now())) + + title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ') + plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_BOOST) + g_plot('title_list = "{}"'.format(title_list)) + g_plot(plot_str) + +def plot_ghz_cpu(): + """ Plot all cpu tsc ghz """ + + output_png = 'all_cpu_ghz.png' + g_plot = common_all_gnuplot_settings(output_png) +# autoscale this one, no set y range + g_plot('set ylabel "TSC Frequency (GHz)"') + g_plot('set title "{} : cpu TSC Frequencies (Sanity check calculation) : {:%F %H:%M}"'.format(testname, datetime.now())) + + title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ') + plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_GHZ) + g_plot('title_list = "{}"'.format(title_list)) + g_plot(plot_str) + +def common_all_gnuplot_settings(output_png): + """ common gnuplot settings for multiple CPUs one one graph. """ + + g_plot = common_gnuplot_settings() + g_plot('set output "' + output_png + '"') + return(g_plot) + +def common_gnuplot_settings(): + """ common gnuplot settings. """ + + g_plot = Gnuplot.Gnuplot(persist=1) +# The following line is for rigor only. It seems to be assumed for .csv files + g_plot('set datafile separator \",\"') + g_plot('set ytics nomirror') + g_plot('set xtics nomirror') + g_plot('set xtics font ", 10"') + g_plot('set ytics font ", 10"') + g_plot('set tics out scale 1.0') + g_plot('set grid') + g_plot('set key out horiz') + g_plot('set key bot center') + g_plot('set key samplen 2 spacing .8 font ", 9"') + g_plot('set term png size 1200, 600') + g_plot('set title font ", 11"') + g_plot('set ylabel font ", 10"') + g_plot('set xlabel font ", 10"') + g_plot('set xlabel offset 0, 0.5') + g_plot('set xlabel "Elapsed Time (Seconds)"') + return(g_plot) + +def set_4_plot_linestyles(g_plot): + """ set the linestyles used for 4 plots in 1 graphs. """ + + g_plot('set style line 1 linetype 1 linecolor rgb "green" pointtype -1') + g_plot('set style line 2 linetype 1 linecolor rgb "red" pointtype -1') + g_plot('set style line 3 linetype 1 linecolor rgb "purple" pointtype -1') + g_plot('set style line 4 linetype 1 linecolor rgb "blue" pointtype -1') + +def store_csv(cpu_int, time_pre_dec, time_post_dec, core_busy, scaled, _from, _to, mperf, aperf, tsc, freq_ghz, io_boost, common_comm, load, duration_ms, sample_num, elapsed_time, tsc_ghz): + """ Store master csv file information """ + + global graph_data_present + + if cpu_mask[cpu_int] == 0: + return + + try: + f_handle = open('cpu.csv', 'a') + string_buffer = "CPU_%03u, %05u, %06u, %u, %u, %u, %u, %u, %u, %u, %.4f, %u, %.2f, %.3f, %u, %.3f, %.3f, %s\n" % (cpu_int, int(time_pre_dec), int(time_post_dec), int(core_busy), int(scaled), int(_from), int(_to), int(mperf), int(aperf), int(tsc), freq_ghz, int(io_boost), load, duration_ms, sample_num, elapsed_time, tsc_ghz, common_comm) + f_handle.write(string_buffer); + f_handle.close() + except: + print('IO error cpu.csv') + return + + graph_data_present = True; + +def split_csv(): + """ seperate the all csv file into per CPU csv files. """ + + global current_max_cpu + + if os.path.exists('cpu.csv'): + for index in range(0, current_max_cpu + 1): + if cpu_mask[int(index)] != 0: + os.system('grep -m 1 common_cpu cpu.csv > cpu{:0>3}.csv'.format(index)) + os.system('grep CPU_{:0>3} cpu.csv >> cpu{:0>3}.csv'.format(index, index)) + +def fix_ownership(path): + """Change the owner of the file to SUDO_UID, if required""" + + uid = os.environ.get('SUDO_UID') + gid = os.environ.get('SUDO_GID') + if uid is not None: + os.chown(path, int(uid), int(gid)) + +def cleanup_data_files(): + """ clean up existing data files """ + + if os.path.exists('cpu.csv'): + os.remove('cpu.csv') + f_handle = open('cpu.csv', 'a') + f_handle.write('common_cpu, common_secs, common_usecs, core_busy, scaled_busy, from, to, mperf, aperf, tsc, freq, boost, load, duration_ms, sample_num, elapsed_time, tsc_ghz, common_comm') + f_handle.write('\n') + f_handle.close() + +def clear_trace_file(): + """ Clear trace file """ + + try: + f_handle = open('/sys/kernel/debug/tracing/trace', 'w') + f_handle.close() + except: + print('IO error clearing trace file ') + quit() + +def enable_trace(): + """ Enable trace """ + + try: + open('/sys/kernel/debug/tracing/events/power/pstate_sample/enable' + , 'w').write("1") + except: + print('IO error enabling trace ') + quit() + +def disable_trace(): + """ Disable trace """ + + try: + open('/sys/kernel/debug/tracing/events/power/pstate_sample/enable' + , 'w').write("0") + except: + print('IO error disabling trace ') + quit() + +def set_trace_buffer_size(): + """ Set trace buffer size """ + + try: + open('/sys/kernel/debug/tracing/buffer_size_kb' + , 'w').write("10240") + except: + print('IO error setting trace buffer size ') + quit() + +def read_trace_data(filename): + """ Read and parse trace data """ + + global current_max_cpu + global sample_num, last_sec_cpu, last_usec_cpu, start_time + + try: + data = open(filename, 'r').read() + except: + print('Error opening ', filename) + quit() + + for line in data.splitlines(): + search_obj = \ + re.search(r'(^(.*?)\[)((\d+)[^\]])(.*?)(\d+)([.])(\d+)(.*?core_busy=)(\d+)(.*?scaled=)(\d+)(.*?from=)(\d+)(.*?to=)(\d+)(.*?mperf=)(\d+)(.*?aperf=)(\d+)(.*?tsc=)(\d+)(.*?freq=)(\d+)' + , line) + + if search_obj: + cpu = search_obj.group(3) + cpu_int = int(cpu) + cpu = str(cpu_int) + + time_pre_dec = search_obj.group(6) + time_post_dec = search_obj.group(8) + core_busy = search_obj.group(10) + scaled = search_obj.group(12) + _from = search_obj.group(14) + _to = search_obj.group(16) + mperf = search_obj.group(18) + aperf = search_obj.group(20) + tsc = search_obj.group(22) + freq = search_obj.group(24) + common_comm = search_obj.group(2).replace(' ', '') + + # Not all kernel versions have io_boost field + io_boost = '0' + search_obj = re.search(r'.*?io_boost=(\d+)', line) + if search_obj: + io_boost = search_obj.group(1) + + if sample_num == 0 : + start_time = Decimal(time_pre_dec) + Decimal(time_post_dec) / Decimal(1000000) + sample_num += 1 + + if last_sec_cpu[cpu_int] == 0 : + last_sec_cpu[cpu_int] = time_pre_dec + last_usec_cpu[cpu_int] = time_post_dec + else : + duration_us = (int(time_pre_dec) - int(last_sec_cpu[cpu_int])) * 1000000 + (int(time_post_dec) - int(last_usec_cpu[cpu_int])) + duration_ms = Decimal(duration_us) / Decimal(1000) + last_sec_cpu[cpu_int] = time_pre_dec + last_usec_cpu[cpu_int] = time_post_dec + elapsed_time = Decimal(time_pre_dec) + Decimal(time_post_dec) / Decimal(1000000) - start_time + load = Decimal(int(mperf)*100)/ Decimal(tsc) + freq_ghz = Decimal(freq)/Decimal(1000000) +# Sanity check calculation, typically anomalies indicate missed samples +# However, check for 0 (should never occur) + tsc_ghz = Decimal(0) + if duration_ms != Decimal(0) : + tsc_ghz = Decimal(tsc)/duration_ms/Decimal(1000000) + store_csv(cpu_int, time_pre_dec, time_post_dec, core_busy, scaled, _from, _to, mperf, aperf, tsc, freq_ghz, io_boost, common_comm, load, duration_ms, sample_num, elapsed_time, tsc_ghz) + + if cpu_int > current_max_cpu: + current_max_cpu = cpu_int +# End of for each trace line loop +# Now seperate the main overall csv file into per CPU csv files. + split_csv() + +interval = "" +filename = "" +cpu_list = "" +testname = "" +graph_data_present = False; + +valid1 = False +valid2 = False + +cpu_mask = zeros((MAX_CPUS,), dtype=int) + +try: + opts, args = getopt.getopt(sys.argv[1:],"ht:i:c:n:",["help","trace_file=","interval=","cpu=","name="]) +except getopt.GetoptError: + print_help() + sys.exit(2) +for opt, arg in opts: + if opt == '-h': + print() + sys.exit() + elif opt in ("-t", "--trace_file"): + valid1 = True + location = os.path.realpath(os.path.join(os.getcwd(), os.path.dirname(__file__))) + filename = os.path.join(location, arg) + elif opt in ("-i", "--interval"): + valid1 = True + interval = arg + elif opt in ("-c", "--cpu"): + cpu_list = arg + elif opt in ("-n", "--name"): + valid2 = True + testname = arg + +if not (valid1 and valid2): + print_help() + sys.exit() + +if cpu_list: + for p in re.split("[,]", cpu_list): + if int(p) < MAX_CPUS : + cpu_mask[int(p)] = 1 +else: + for i in range (0, MAX_CPUS): + cpu_mask[i] = 1 + +if not os.path.exists('results'): + os.mkdir('results') + # The regular user needs to own the directory, not root. + fix_ownership('results') + +os.chdir('results') +if os.path.exists(testname): + print('The test name directory already exists. Please provide a unique test name. Test re-run not supported, yet.') + sys.exit() +os.mkdir(testname) +# The regular user needs to own the directory, not root. +fix_ownership(testname) +os.chdir(testname) + +# Temporary (or perhaps not) +cur_version = sys.version_info +print('python version (should be >= 2.7):') +print(cur_version) + +# Left as "cleanup" for potential future re-run ability. +cleanup_data_files() + +if interval: + filename = "/sys/kernel/debug/tracing/trace" + clear_trace_file() + set_trace_buffer_size() + enable_trace() + print('Sleeping for ', interval, 'seconds') + time.sleep(int(interval)) + disable_trace() + +current_max_cpu = 0 + +read_trace_data(filename) + +if graph_data_present == False: + print('No valid data to plot') + sys.exit(2) + +for cpu_no in range(0, current_max_cpu + 1): + plot_perf_busy_with_sample(cpu_no) + plot_perf_busy(cpu_no) + plot_durations(cpu_no) + plot_loads(cpu_no) + +plot_pstate_cpu_with_sample() +plot_pstate_cpu() +plot_load_cpu() +plot_frequency_cpu() +plot_duration_cpu() +plot_scaled_cpu() +plot_boost_cpu() +plot_ghz_cpu() + +# It is preferrable, but not necessary, that the regular user owns the files, not root. +for root, dirs, files in os.walk('.'): + for f in files: + fix_ownership(f) + +os.chdir('../../') diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8 index 03cb639b292e..ccf2a69365cc 100644 --- a/tools/power/x86/turbostat/turbostat.8 +++ b/tools/power/x86/turbostat/turbostat.8 @@ -16,9 +16,9 @@ idle power-state statistics, temperature and power on X86 processors. There are two ways to invoke turbostat. The first method is to supply a \fBcommand\fP, which is forked and statistics are printed -upon its completion. +in one-shot upon its completion. The second method is to omit the command, -and turbostat displays statistics every 5 seconds. +and turbostat displays statistics every 5 seconds interval. The 5-second interval can be changed using the --interval option. .PP Some information is not available on older processors. @@ -28,9 +28,10 @@ name as necessary to disambiguate it from others is necessary. Note that option .PP \fB--add attributes\fP add column with counter having specified 'attributes'. The 'location' attribute is required, all others are optional. .nf - location: {\fBmsrDDD\fP | \fBmsr0xXXX\fP} + location: {\fBmsrDDD\fP | \fBmsr0xXXX\fP | \fB/sys/path...\fP} msrDDD is a decimal offset, eg. msr16 msr0xXXX is a hex offset, eg. msr0x10 + /sys/path... is an absolute path to a sysfs attribute scope: {\fBcpu\fP | \fBcore\fP | \fBpackage\fP} sample and print the counter for every cpu, core, or package. @@ -45,12 +46,21 @@ name as necessary to disambiguate it from others is necessary. Note that option 'delta' shows the difference in values during the measurement interval. 'percent' shows the delta as a percentage of the cycles elapsed. default: delta + + name: "name_string" + Any string that does not match a key-word above is used + as the column header. .fi .PP +\fB--cpu cpu-set\fP limit output to system summary plus the specified cpu-set. If cpu-set is the string "core", then the system summary plus the first CPU in each core are printed -- eg. subsequent HT siblings are not printed. Or if cpu-set is the string "package", then the system summary plus the first CPU in each package is printed. Otherwise, the system summary plus the specified set of CPUs are printed. The cpu-set is ordered from low to high, comma delimited with ".." and "-" permitted to denote a range. eg. 1,2,8,14..17,21-44 +.PP +\fB--hide column\fP do not show the specified columns. May be invoked multiple times, or with a comma-separated list of column names. Use "--hide sysfs" to hide the sysfs statistics columns as a group. +.PP +\fB--show column\fP show only the specified columns. May be invoked multiple times, or with a comma-separated list of column names. Use "--show sysfs" to show the sysfs statistics columns as a group. +.PP \fB--Dump\fP displays the raw counter values. .PP -\fB--debug\fP displays additional system configuration information. Invoking this parameter -more than once may also enable internal turbostat debug information. +\fB--quiet\fP Do not decode and print the system configuration header information. .PP \fB--interval seconds\fP overrides the default 5.0 second measurement interval. .PP @@ -61,9 +71,7 @@ The file is truncated if it already exists, and it is created if it does not exi .PP \fB--Joules\fP displays energy in Joules, rather than dividing Joules by time to print power in Watts. .PP -\fB--Package\fP limits output to the system summary plus the 1st thread in each Package. -.PP -\fB--processor\fP limits output to the system summary plus the 1st thread in each processor of each package. Ie. it skips hyper-threaded siblings. +\fB--list\fP display column header names available for use by --show and --hide, then exit. .PP \fB--Summary\fP limits output to a 1-line System Summary for each interval. .PP @@ -74,24 +82,27 @@ The file is truncated if it already exists, and it is created if it does not exi The \fBcommand\fP parameter forks \fBcommand\fP, and upon its exit, displays the statistics gathered since it was forked. .PP -.SH DEFAULT FIELD DESCRIPTIONS +.SH ROW DESCRIPTIONS +The system configuration dump (if --quiet is not used) is followed by statistics. The first row of the statistics labels the content of each column (below). The second row of statistics is the system summary line. The system summary line has a '-' in the columns for the Package, Core, and CPU. The contents of the system summary line depends on the type of column. Columns that count items (eg. IRQ) show the sum across all CPUs in the system. Columns that show a percentage show the average across all CPUs in the system. Columns that dump raw MSR values simply show 0 in the summary. After the system summary row, each row describes a specific Package/Core/CPU. Note that if the --cpu parameter is used to limit which specific CPUs are displayed, turbostat will still collect statistics for all CPUs in the system and will still show the system summary for all CPUs in the system. +.SH COLUMN DESCRIPTIONS .nf +\fBCore\fP processor core number. Note that multiple CPUs per core indicate support for Intel(R) Hyper-Threading Technology (HT). \fBCPU\fP Linux CPU (logical processor) number. Yes, it is okay that on many systems the CPUs are not listed in numerical order -- for efficiency reasons, turbostat runs in topology order, so HT siblings appear together. -\fBAVG_MHz\fP number of cycles executed divided by time elapsed. -\fBBusy%\fP percent of the interval that the CPU retired instructions, aka. % of time in "C0" state. -\fBBzy_MHz\fP average clock rate while the CPU was busy (in "c0" state). +\fBPackage\fP processor package number -- not present on systems with a single processor package. +\fBAvg_MHz\fP number of cycles executed divided by time elapsed. Note that this includes idle-time when 0 instructions are executed. +\fBBusy%\fP percent of the measurement interval that the CPU executes instructions, aka. % of time in "C0" state. +\fBBzy_MHz\fP average clock rate while the CPU was not idle (ie. in "c0" state). \fBTSC_MHz\fP average MHz that the TSC ran during the entire interval. -.fi -.PP -.SH DEBUG FIELD DESCRIPTIONS -.nf -\fBPackage\fP processor package number. -\fBCore\fP processor core number. -Note that multiple CPUs per core indicate support for Intel(R) Hyper-Threading Technology (HT). -\fBCPU%c1, CPU%c3, CPU%c6, CPU%c7\fP show the percentage residency in hardware core idle states. +\fBIRQ\fP The number of interrupts serviced by that CPU during the measurement interval. The system total line is the sum of interrupts serviced across all CPUs. turbostat parses /proc/interrupts to generate this summary. +\fBSMI\fP The number of System Management Interrupts serviced CPU during the measurement interval. While this counter is actually per-CPU, SMI are triggered on all processors, so the number should be the same for all CPUs. +\fBC1, C2, C3...\fP The number times Linux requested the C1, C2, C3 idle state during the measurement interval. The system summary line shows the sum for all CPUs. These are C-state names as exported in /sys/devices/system/cpu/cpu*/cpuidle/state*/name. While their names are generic, their attributes are processor specific. They the system description section of output shows what MWAIT sub-states they are mapped to on each system. +\fBC1%, C2%, C3%\fP The residency percentage that Linux requested C1, C2, C3.... The system summary is the average of all CPUs in the system. Note that these are software, reflecting what was requested. The hardware counters reflect what was actually achieved. +\fBCPU%c1, CPU%c3, CPU%c6, CPU%c7\fP show the percentage residency in hardware core idle states. These numbers are from hardware residency counters. \fBCoreTmp\fP Degrees Celsius reported by the per-core Digital Thermal Sensor. \fBPkgTtmp\fP Degrees Celsius reported by the per-package Package Thermal Monitor. -\fBPkg%pc2, Pkg%pc3, Pkg%pc6, Pkg%pc7\fP percentage residency in hardware package idle states. +\fBGFX%rc6\fP The percentage of time the GPU is in the "render C6" state, rc6, during the measurement interval. From /sys/class/drm/card0/power/rc6_residency_ms. +\fBGFXMHz\fP Instantaneous snapshot of what sysfs presents at the end of the measurement interval. From /sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz. +\fBPkg%pc2, Pkg%pc3, Pkg%pc6, Pkg%pc7\fP percentage residency in hardware package idle states. These numbers are from hardware residency counters. \fBPkgWatt\fP Watts consumed by the whole package. \fBCorWatt\fP Watts consumed by the core part of the package. \fBGFXWatt\fP Watts consumed by the Graphics part of the package -- available only on client processors. @@ -99,51 +110,110 @@ Note that multiple CPUs per core indicate support for Intel(R) Hyper-Threading T \fBPKG_%\fP percent of the interval that RAPL throttling was active on the Package. \fBRAM_%\fP percent of the interval that RAPL throttling was active on DRAM. .fi +.SH TOO MUCH INFORMATION EXAMPLE +By default, turbostat dumps all possible information -- a system configuration header, followed by columns for all counters. +This is ideal for remote debugging, use the "--out" option to save everything to a text file, and get that file to the expert helping you debug. .PP -.SH PERIODIC EXAMPLE -Without any parameters, turbostat displays statistics ever 5 seconds. -Periodic output goes to stdout, by default, unless --out is used to specify an output file. -The 5-second interval can be changed with th "-i sec" option. -Or a command may be specified as in "FORK EXAMPLE" below. +When you are not interested in all that information, and there are several ways to see only what you want. First the "--quiet" option will skip the configuration information, and turbostat will show only the counter columns. Second, you can reduce the columns with the "--hide" and "--show" options. If you use the "--show" option, then turbostat will show only the columns you list. If you use the "--hide" option, turbostat will show all columns, except the ones you list. +.PP +To find out what columns are available for --show and --hide, the "--list" option is available. For convenience, the special strings "sysfs" can be used to refer to all of the sysfs C-state counters at once: +.nf +sudo ./turbostat --show sysfs --quiet sleep 10 +10.003837 sec + C1 C1E C3 C6 C7s C1% C1E% C3% C6% C7s% + 4 21 2 2 459 0.14 0.82 0.00 0.00 98.93 + 1 17 2 2 130 0.00 0.02 0.00 0.00 99.80 + 0 0 0 0 31 0.00 0.00 0.00 0.00 99.95 + 2 1 0 0 52 1.14 6.49 0.00 0.00 92.21 + 1 2 0 0 52 0.00 0.08 0.00 0.00 99.86 + 0 0 0 0 71 0.00 0.00 0.00 0.00 99.89 + 0 0 0 0 25 0.00 0.00 0.00 0.00 99.96 + 0 0 0 0 74 0.00 0.00 0.00 0.00 99.94 + 0 1 0 0 24 0.00 0.00 0.00 0.00 99.84 +.fi +.PP +.SH ONE SHOT COMMAND EXAMPLE +If turbostat is invoked with a command, it will fork that command +and output the statistics gathered after the command exits. +In this case, turbostat output goes to stderr, by default. +Output can instead be saved to a file using the --out option. +In this example, the "sleep 10" command is forked, and turbostat waits for it to complete before saving all statistics into "ts.out". Note that "sleep 10" is not part of turbostat, but is simply an example of a command that turbostat can fork. The "ts.out" file is what you want to edit in a very wide window, paste into a spreadsheet, or attach to a bugzilla entry. + .nf -[root@hsw]# ./turbostat - CPU Avg_MHz Busy% Bzy_MHz TSC_MHz - - 488 12.51 3898 3498 - 0 0 0.01 3885 3498 - 4 3897 99.99 3898 3498 - 1 0 0.00 3861 3498 - 5 0 0.00 3882 3498 - 2 1 0.02 3894 3498 - 6 2 0.06 3898 3498 - 3 0 0.00 3849 3498 - 7 0 0.00 3877 3498 +[root@hsw]# ./turbostat -o ts.out sleep 10 +[root@hsw]# +.fi +.SH PERIODIC INTERVAL EXAMPLE +Without a command to fork, turbostat displays statistics ever 5 seconds. +Periodic output goes to stdout, by default, unless --out is used to specify an output file. +The 5-second interval can be changed with the "-i sec" option. +.nf +sudo ./turbostat --quiet --hide sysfs,IRQ,SMI,CoreTmp,PkgTmp,GFX%rc6,GFXMHz,PkgWatt,CorWatt,GFXWatt + Core CPU Avg_MHz Busy% Bzy_MHz TSC_MHz CPU%c1 CPU%c3 CPU%c6 CPU%c7 + - - 488 12.52 3900 3498 12.50 0.00 0.00 74.98 + 0 0 5 0.13 3900 3498 99.87 0.00 0.00 0.00 + 0 4 3897 99.99 3900 3498 0.01 + 1 1 0 0.00 3856 3498 0.01 0.00 0.00 99.98 + 1 5 0 0.00 3861 3498 0.01 + 2 2 1 0.02 3889 3498 0.03 0.00 0.00 99.95 + 2 6 0 0.00 3863 3498 0.05 + 3 3 0 0.01 3869 3498 0.02 0.00 0.00 99.97 + 3 7 0 0.00 3878 3498 0.03 + Core CPU Avg_MHz Busy% Bzy_MHz TSC_MHz CPU%c1 CPU%c3 CPU%c6 CPU%c7 + - - 491 12.59 3900 3498 12.42 0.00 0.00 74.99 + 0 0 27 0.69 3900 3498 99.31 0.00 0.00 0.00 + 0 4 3898 99.99 3900 3498 0.01 + 1 1 0 0.00 3883 3498 0.01 0.00 0.00 99.99 + 1 5 0 0.00 3898 3498 0.01 + 2 2 0 0.01 3889 3498 0.02 0.00 0.00 99.98 + 2 6 0 0.00 3889 3498 0.02 + 3 3 0 0.00 3856 3498 0.01 0.00 0.00 99.99 + 3 7 0 0.00 3897 3498 0.01 .fi -.SH DEBUG EXAMPLE -The "--debug" option prints additional system information before measurements: +This example also shows the use of the --hide option to skip columns that are not wanted. +Note that cpu4 in this example is 99.99% busy, while the other CPUs are all under 1% busy. +Notice that cpu4's HT sibling is cpu0, which is under 1% busy, but can get into CPU%c1 only, +because its cpu4's activity on shared hardware keeps it from entering a deeper C-state. -The first row of statistics is a summary for the entire system. -For residency % columns, the summary is a weighted average. -For Temperature columns, the summary is the column maximum. -For Watts columns, the summary is a system total. -Subsequent rows show per-CPU statistics. +.SH SYSTEM CONFIGURATION INFORMATION EXAMPLE + +By default, turbostat always dumps system configuration information +before taking measurements. In the example above, "--quiet" is used +to suppress that output. Here is an example of the configuration information: .nf -turbostat version 4.1 10-Feb, 2015 - Len Brown <lenb@kernel.org> +turbostat version 2017.02.15 - Len Brown <lenb@kernel.org> CPUID(0): GenuineIntel 13 CPUID levels; family:model:stepping 0x6:3c:3 (6:60:3) -CPUID(6): APERF, DTS, PTM, EPB +CPUID(1): SSE3 MONITOR - EIST TM2 TSC MSR ACPI-TM TM +CPUID(6): APERF, TURBO, DTS, PTM, No-HWP, No-HWPnotify, No-HWPwindow, No-HWPepp, No-HWPpkg, EPB +cpu4: MSR_IA32_MISC_ENABLE: 0x00850089 (TCC EIST No-MWAIT PREFETCH TURBO) +CPUID(7): No-SGX +cpu4: MSR_MISC_PWR_MGMT: 0x00400000 (ENable-EIST_Coordination DISable-EPB DISable-OOB) RAPL: 3121 sec. Joule Counter Range, at 84 Watts -cpu0: MSR_NHM_PLATFORM_INFO: 0x80838f3012300 -8 * 100 = 800 MHz max efficiency -35 * 100 = 3500 MHz TSC frequency -cpu0: MSR_IA32_POWER_CTL: 0x0004005d (C1E auto-promotion: DISabled) -cpu0: MSR_NHM_SNB_PKG_CST_CFG_CTL: 0x1e000400 (UNdemote-C3, UNdemote-C1, demote-C3, demote-C1, UNlocked: pkg-cstate-limit=0: pc0) -cpu0: MSR_TURBO_RATIO_LIMIT: 0x25262727 -37 * 100 = 3700 MHz max turbo 4 active cores -38 * 100 = 3800 MHz max turbo 3 active cores -39 * 100 = 3900 MHz max turbo 2 active cores -39 * 100 = 3900 MHz max turbo 1 active cores +cpu4: MSR_PLATFORM_INFO: 0x80838f3012300 +8 * 100.0 = 800.0 MHz max efficiency frequency +35 * 100.0 = 3500.0 MHz base frequency +cpu4: MSR_IA32_POWER_CTL: 0x0004005d (C1E auto-promotion: DISabled) +cpu4: MSR_TURBO_RATIO_LIMIT: 0x25262727 +37 * 100.0 = 3700.0 MHz max turbo 4 active cores +38 * 100.0 = 3800.0 MHz max turbo 3 active cores +39 * 100.0 = 3900.0 MHz max turbo 2 active cores +39 * 100.0 = 3900.0 MHz max turbo 1 active cores +cpu4: MSR_CONFIG_TDP_NOMINAL: 0x00000023 (base_ratio=35) +cpu4: MSR_CONFIG_TDP_LEVEL_1: 0x00000000 () +cpu4: MSR_CONFIG_TDP_LEVEL_2: 0x00000000 () +cpu4: MSR_CONFIG_TDP_CONTROL: 0x80000000 ( lock=1) +cpu4: MSR_TURBO_ACTIVATION_RATIO: 0x00000000 (MAX_NON_TURBO_RATIO=0 lock=0) +cpu4: MSR_PKG_CST_CONFIG_CONTROL: 0x1e000400 (UNdemote-C3, UNdemote-C1, demote-C3, demote-C1, UNlocked: pkg-cstate-limit=0: pc0) +cpu4: POLL: CPUIDLE CORE POLL IDLE +cpu4: C1: MWAIT 0x00 +cpu4: C1E: MWAIT 0x01 +cpu4: C3: MWAIT 0x10 +cpu4: C6: MWAIT 0x20 +cpu4: C7s: MWAIT 0x32 +cpu4: MSR_MISC_FEATURE_CONTROL: 0x00000000 (L2-Prefetch L2-Prefetch-pair L1-Prefetch L1-IP-Prefetch) cpu0: MSR_IA32_ENERGY_PERF_BIAS: 0x00000006 (balanced) -cpu0: MSR_CORE_PERF_LIMIT_REASONS, 0x31200000 (Active: ) (Logged: Auto-HWP, Amps, MultiCoreTurbo, Transitions, ) +cpu0: MSR_CORE_PERF_LIMIT_REASONS, 0x31200000 (Active: ) (Logged: Transitions, MultiCoreTurbo, Amps, Auto-HWP, ) cpu0: MSR_GFX_PERF_LIMIT_REASONS, 0x00000000 (Active: ) (Logged: ) cpu0: MSR_RING_PERF_LIMIT_REASONS, 0x0d000000 (Active: ) (Logged: Amps, PkgPwrL1, PkgPwrL2, ) cpu0: MSR_RAPL_POWER_UNIT: 0x000a0e03 (0.125000 Watts, 0.000061 Joules, 0.000977 sec.) @@ -158,23 +228,14 @@ cpu0: MSR_PP1_POLICY: 0 cpu0: MSR_PP1_POWER_LIMIT: 0x00000000 (UNlocked) cpu0: GFX Limit: DISabled (0.000000 Watts, 0.000977 sec, clamp DISabled) cpu0: MSR_IA32_TEMPERATURE_TARGET: 0x00641400 (100 C) -cpu0: MSR_IA32_PACKAGE_THERM_STATUS: 0x88340800 (48 C) -cpu0: MSR_IA32_THERM_STATUS: 0x88340000 (48 C +/- 1) -cpu1: MSR_IA32_THERM_STATUS: 0x88440000 (32 C +/- 1) -cpu2: MSR_IA32_THERM_STATUS: 0x88450000 (31 C +/- 1) -cpu3: MSR_IA32_THERM_STATUS: 0x88490000 (27 C +/- 1) - Core CPU Avg_MHz Busy% Bzy_MHz TSC_MHz SMI CPU%c1 CPU%c3 CPU%c6 CPU%c7 CoreTmp PkgTmp PkgWatt CorWatt GFXWatt - - - 493 12.64 3898 3498 0 12.64 0.00 0.00 74.72 47 47 21.62 13.74 0.00 - 0 0 4 0.11 3894 3498 0 99.89 0.00 0.00 0.00 47 47 21.62 13.74 0.00 - 0 4 3897 99.98 3898 3498 0 0.02 - 1 1 7 0.17 3887 3498 0 0.04 0.00 0.00 99.79 32 - 1 5 0 0.00 3885 3498 0 0.21 - 2 2 29 0.76 3895 3498 0 0.10 0.01 0.01 99.13 32 - 2 6 2 0.06 3896 3498 0 0.80 - 3 3 1 0.02 3832 3498 0 0.03 0.00 0.00 99.95 28 - 3 7 0 0.00 3879 3498 0 0.04 -^C - +cpu0: MSR_IA32_PACKAGE_THERM_STATUS: 0x884c0800 (24 C) +cpu0: MSR_IA32_THERM_STATUS: 0x884c0000 (24 C +/- 1) +cpu1: MSR_IA32_THERM_STATUS: 0x88510000 (19 C +/- 1) +cpu2: MSR_IA32_THERM_STATUS: 0x884e0000 (22 C +/- 1) +cpu3: MSR_IA32_THERM_STATUS: 0x88510000 (19 C +/- 1) +cpu4: MSR_PKGC3_IRTL: 0x00008842 (valid, 67584 ns) +cpu4: MSR_PKGC6_IRTL: 0x00008873 (valid, 117760 ns) +cpu4: MSR_PKGC7_IRTL: 0x00008891 (valid, 148480 ns) .fi The \fBmax efficiency\fP frequency, a.k.a. Low Frequency Mode, is the frequency available at the minimum package voltage. The \fBTSC frequency\fP is the base @@ -184,42 +245,22 @@ should be sustainable on all CPUs indefinitely, given nominal power and cooling. The remaining rows show what maximum turbo frequency is possible depending on the number of idle cores. Note that not all information is available on all processors. -.PP -The --debug option adds additional columns to the measurement ouput, including CPU idle power-state residency processor temperature sensor readinds. -See the field definitions above. -.SH FORK EXAMPLE -If turbostat is invoked with a command, it will fork that command -and output the statistics gathered after the command exits. -In this case, turbostat output goes to stderr, by default. -Output can instead be saved to a file using the --out option. -eg. Here a cycle soaker is run on 1 CPU (see %c0) for a few seconds -until ^C while the other CPUs are mostly idle: - +.SH ADD COUNTER EXAMPLE +Here we limit turbostat to showing just the CPU number for cpu0 - cpu3. +We add a counter showing the 32-bit raw value of MSR 0x199 (MSR_IA32_PERF_CTL), +labeling it with the column header, "PRF_CTRL", and display it only once, +afte the conclusion of a 0.1 second sleep. .nf -root@hsw: turbostat cat /dev/zero > /dev/null -^C - CPU Avg_MHz Busy% Bzy_MHz TSC_MHz - - 482 12.51 3854 3498 - 0 0 0.01 1960 3498 - 4 0 0.00 2128 3498 - 1 0 0.00 3003 3498 - 5 3854 99.98 3855 3498 - 2 0 0.01 3504 3498 - 6 3 0.08 3884 3498 - 3 0 0.00 2553 3498 - 7 0 0.00 2126 3498 -10.783983 sec +sudo ./turbostat --quiet --cpu 0-3 --show CPU --add msr0x199,u32,raw,PRF_CTRL sleep .1 +0.101604 sec +CPU PRF_CTRL +- 0x00000000 +0 0x00000c00 +1 0x00000800 +2 0x00000a00 +3 0x00000800 .fi -Above the cycle soaker drives cpu5 up its 3.9 GHz turbo limit. -The first row shows the average MHz and Busy% across all the processors in the system. - -Note that the Avg_MHz column reflects the total number of cycles executed -divided by the measurement interval. If the Busy% column is 100%, -then the processor was running at that speed the entire interval. -The Avg_MHz multiplied by the Busy% results in the Bzy_MHz -- -which is the average frequency while the processor was executing -- -not including any non-busy idle time. .SH NOTES diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index f13f61b065c6..b11294730771 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -49,17 +49,14 @@ FILE *outf; int *fd_percpu; struct timespec interval_ts = {5, 0}; unsigned int debug; +unsigned int quiet; +unsigned int sums_need_wide_columns; unsigned int rapl_joules; unsigned int summary_only; +unsigned int list_header_only; unsigned int dump_only; -unsigned int do_nhm_cstates; unsigned int do_snb_cstates; unsigned int do_knl_cstates; -unsigned int do_pc2; -unsigned int do_pc3; -unsigned int do_pc6; -unsigned int do_pc7; -unsigned int do_c8_c9_c10; unsigned int do_skl_residency; unsigned int do_slm_cstates; unsigned int use_c1_residency_msr; @@ -71,25 +68,19 @@ unsigned int units = 1000000; /* MHz etc */ unsigned int genuine_intel; unsigned int has_invariant_tsc; unsigned int do_nhm_platform_info; +unsigned int no_MSR_MISC_PWR_MGMT; unsigned int aperf_mperf_multiplier = 1; -int do_irq = 1; -int do_smi; double bclk; double base_hz; unsigned int has_base_hz; double tsc_tweak = 1.0; -unsigned int show_pkg; -unsigned int show_core; -unsigned int show_cpu; unsigned int show_pkg_only; unsigned int show_core_only; char *output_buffer, *outp; unsigned int do_rapl; unsigned int do_dts; unsigned int do_ptm; -unsigned int do_gfx_rc6_ms; unsigned long long gfx_cur_rc6_ms; -unsigned int do_gfx_mhz; unsigned int gfx_cur_mhz; unsigned int tcc_activation_temp; unsigned int tcc_activation_temp_override; @@ -109,6 +100,7 @@ unsigned int has_hwp_notify; /* IA32_HWP_INTERRUPT */ unsigned int has_hwp_activity_window; /* IA32_HWP_REQUEST[bits 41:32] */ unsigned int has_hwp_epp; /* IA32_HWP_REQUEST[bits 31:24] */ unsigned int has_hwp_pkg; /* IA32_HWP_REQUEST_PKG */ +unsigned int has_misc_feature_control; #define RAPL_PKG (1 << 0) /* 0x610 MSR_PKG_POWER_LIMIT */ @@ -148,34 +140,38 @@ unsigned int has_hwp_pkg; /* IA32_HWP_REQUEST_PKG */ * Usually truncated to 7 characters, but also handles 18 columns for raw 64-bit counters */ #define NAME_BYTES 20 +#define PATH_BYTES 128 int backwards_count; char *progname; -cpu_set_t *cpu_present_set, *cpu_affinity_set; -size_t cpu_present_setsize, cpu_affinity_setsize; +#define CPU_SUBSET_MAXCPUS 1024 /* need to use before probe... */ +cpu_set_t *cpu_present_set, *cpu_affinity_set, *cpu_subset; +size_t cpu_present_setsize, cpu_affinity_setsize, cpu_subset_size; +#define MAX_ADDED_COUNTERS 16 struct thread_data { unsigned long long tsc; unsigned long long aperf; unsigned long long mperf; unsigned long long c1; - unsigned int irq_count; + unsigned long long irq_count; unsigned int smi_count; unsigned int cpu_id; unsigned int flags; #define CPU_IS_FIRST_THREAD_IN_CORE 0x2 #define CPU_IS_FIRST_CORE_IN_PACKAGE 0x4 - unsigned long long counter[1]; + unsigned long long counter[MAX_ADDED_COUNTERS]; } *thread_even, *thread_odd; struct core_data { unsigned long long c3; unsigned long long c6; unsigned long long c7; + unsigned long long mc6_us; /* duplicate as per-core for now, even though per module */ unsigned int core_temp_c; unsigned int core_id; - unsigned long long counter[1]; + unsigned long long counter[MAX_ADDED_COUNTERS]; } *core_even, *core_odd; struct pkg_data { @@ -200,7 +196,7 @@ struct pkg_data { unsigned int rapl_pkg_perf_status; /* MSR_PKG_PERF_STATUS */ unsigned int rapl_dram_perf_status; /* MSR_DRAM_PERF_STATUS */ unsigned int pkg_temp_c; - unsigned long long counter[1]; + unsigned long long counter[MAX_ADDED_COUNTERS]; } *package_even, *package_odd; #define ODD_COUNTERS thread_odd, core_odd, package_odd @@ -215,22 +211,27 @@ struct pkg_data { #define GET_PKG(pkg_base, pkg_no) (pkg_base + pkg_no) enum counter_scope {SCOPE_CPU, SCOPE_CORE, SCOPE_PACKAGE}; -enum counter_type {COUNTER_CYCLES, COUNTER_SECONDS}; +enum counter_type {COUNTER_ITEMS, COUNTER_CYCLES, COUNTER_SECONDS, COUNTER_USEC}; enum counter_format {FORMAT_RAW, FORMAT_DELTA, FORMAT_PERCENT}; struct msr_counter { unsigned int msr_num; char name[NAME_BYTES]; + char path[PATH_BYTES]; unsigned int width; enum counter_type type; enum counter_format format; struct msr_counter *next; + unsigned int flags; +#define FLAGS_HIDE (1 << 0) +#define FLAGS_SHOW (1 << 1) +#define SYSFS_PERCPU (1 << 1) }; struct sys_counters { - unsigned int thread_counter_bytes; - unsigned int core_counter_bytes; - unsigned int package_counter_bytes; + unsigned int added_thread_counters; + unsigned int added_core_counters; + unsigned int added_package_counters; struct msr_counter *tp; struct msr_counter *cp; struct msr_counter *pp; @@ -334,147 +335,333 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr) retval = pread(get_msr_fd(cpu), msr, sizeof(*msr), offset); if (retval != sizeof *msr) - err(-1, "msr %d offset 0x%llx read failed", cpu, (unsigned long long)offset); + err(-1, "cpu%d: msr offset 0x%llx read failed", cpu, (unsigned long long)offset); return 0; } /* - * Example Format w/ field column widths: - * - * Package Core CPU Avg_MHz Bzy_MHz TSC_MHz IRQ SMI Busy% CPU_%c1 CPU_%c3 CPU_%c6 CPU_%c7 ThreadC CoreTmp CoreCnt PkgTmp GFXMHz Pkg%pc2 Pkg%pc3 Pkg%pc6 Pkg%pc7 PkgWatt CorWatt GFXWatt PkgCnt - * 12345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678123456781234567812345678 + * Each string in this array is compared in --show and --hide cmdline. + * Thus, strings that are proper sub-sets must follow their more specific peers. + */ +struct msr_counter bic[] = { + { 0x0, "Package" }, + { 0x0, "Avg_MHz" }, + { 0x0, "Bzy_MHz" }, + { 0x0, "TSC_MHz" }, + { 0x0, "IRQ" }, + { 0x0, "SMI", "", 32, 0, FORMAT_DELTA, NULL}, + { 0x0, "Busy%" }, + { 0x0, "CPU%c1" }, + { 0x0, "CPU%c3" }, + { 0x0, "CPU%c6" }, + { 0x0, "CPU%c7" }, + { 0x0, "ThreadC" }, + { 0x0, "CoreTmp" }, + { 0x0, "CoreCnt" }, + { 0x0, "PkgTmp" }, + { 0x0, "GFX%rc6" }, + { 0x0, "GFXMHz" }, + { 0x0, "Pkg%pc2" }, + { 0x0, "Pkg%pc3" }, + { 0x0, "Pkg%pc6" }, + { 0x0, "Pkg%pc7" }, + { 0x0, "Pkg%pc8" }, + { 0x0, "Pkg%pc9" }, + { 0x0, "Pkg%pc10" }, + { 0x0, "PkgWatt" }, + { 0x0, "CorWatt" }, + { 0x0, "GFXWatt" }, + { 0x0, "PkgCnt" }, + { 0x0, "RAMWatt" }, + { 0x0, "PKG_%" }, + { 0x0, "RAM_%" }, + { 0x0, "Pkg_J" }, + { 0x0, "Cor_J" }, + { 0x0, "GFX_J" }, + { 0x0, "RAM_J" }, + { 0x0, "Core" }, + { 0x0, "CPU" }, + { 0x0, "Mod%c6" }, + { 0x0, "sysfs" }, +}; + +#define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter)) +#define BIC_Package (1ULL << 0) +#define BIC_Avg_MHz (1ULL << 1) +#define BIC_Bzy_MHz (1ULL << 2) +#define BIC_TSC_MHz (1ULL << 3) +#define BIC_IRQ (1ULL << 4) +#define BIC_SMI (1ULL << 5) +#define BIC_Busy (1ULL << 6) +#define BIC_CPU_c1 (1ULL << 7) +#define BIC_CPU_c3 (1ULL << 8) +#define BIC_CPU_c6 (1ULL << 9) +#define BIC_CPU_c7 (1ULL << 10) +#define BIC_ThreadC (1ULL << 11) +#define BIC_CoreTmp (1ULL << 12) +#define BIC_CoreCnt (1ULL << 13) +#define BIC_PkgTmp (1ULL << 14) +#define BIC_GFX_rc6 (1ULL << 15) +#define BIC_GFXMHz (1ULL << 16) +#define BIC_Pkgpc2 (1ULL << 17) +#define BIC_Pkgpc3 (1ULL << 18) +#define BIC_Pkgpc6 (1ULL << 19) +#define BIC_Pkgpc7 (1ULL << 20) +#define BIC_Pkgpc8 (1ULL << 21) +#define BIC_Pkgpc9 (1ULL << 22) +#define BIC_Pkgpc10 (1ULL << 23) +#define BIC_PkgWatt (1ULL << 24) +#define BIC_CorWatt (1ULL << 25) +#define BIC_GFXWatt (1ULL << 26) +#define BIC_PkgCnt (1ULL << 27) +#define BIC_RAMWatt (1ULL << 28) +#define BIC_PKG__ (1ULL << 29) +#define BIC_RAM__ (1ULL << 30) +#define BIC_Pkg_J (1ULL << 31) +#define BIC_Cor_J (1ULL << 32) +#define BIC_GFX_J (1ULL << 33) +#define BIC_RAM_J (1ULL << 34) +#define BIC_Core (1ULL << 35) +#define BIC_CPU (1ULL << 36) +#define BIC_Mod_c6 (1ULL << 37) +#define BIC_sysfs (1ULL << 38) + +unsigned long long bic_enabled = 0xFFFFFFFFFFFFFFFFULL; +unsigned long long bic_present = BIC_sysfs; + +#define DO_BIC(COUNTER_NAME) (bic_enabled & bic_present & COUNTER_NAME) +#define BIC_PRESENT(COUNTER_BIT) (bic_present |= COUNTER_BIT) +#define BIC_NOT_PRESENT(COUNTER_BIT) (bic_present &= ~COUNTER_BIT) + +#define MAX_DEFERRED 16 +char *deferred_skip_names[MAX_DEFERRED]; +int deferred_skip_index; + +/* + * HIDE_LIST - hide this list of counters, show the rest [default] + * SHOW_LIST - show this list of counters, hide the rest */ +enum show_hide_mode { SHOW_LIST, HIDE_LIST } global_show_hide_mode = HIDE_LIST; -void print_header(void) +void help(void) { - struct msr_counter *mp; + fprintf(outf, + "Usage: turbostat [OPTIONS][(--interval seconds) | COMMAND ...]\n" + "\n" + "Turbostat forks the specified COMMAND and prints statistics\n" + "when COMMAND completes.\n" + "If no COMMAND is specified, turbostat wakes every 5-seconds\n" + "to print statistics, until interrupted.\n" + "--add add a counter\n" + " eg. --add msr0x10,u64,cpu,delta,MY_TSC\n" + "--cpu cpu-set limit output to summary plus cpu-set:\n" + " {core | package | j,k,l..m,n-p }\n" + "--quiet skip decoding system configuration header\n" + "--interval sec Override default 5-second measurement interval\n" + "--help print this help message\n" + "--list list column headers only\n" + "--out file create or truncate \"file\" for all output\n" + "--version print version information\n" + "\n" + "For more help, run \"man turbostat\"\n"); +} - if (show_pkg) - outp += sprintf(outp, "\tPackage"); - if (show_core) - outp += sprintf(outp, "\tCore"); - if (show_cpu) - outp += sprintf(outp, "\tCPU"); - if (has_aperf) - outp += sprintf(outp, "\tAvg_MHz"); - if (has_aperf) - outp += sprintf(outp, "\tBusy%%"); - if (has_aperf) - outp += sprintf(outp, "\tBzy_MHz"); - outp += sprintf(outp, "\tTSC_MHz"); +/* + * bic_lookup + * for all the strings in comma separate name_list, + * set the approprate bit in return value. + */ +unsigned long long bic_lookup(char *name_list, enum show_hide_mode mode) +{ + int i; + unsigned long long retval = 0; - if (!debug) - goto done; + while (name_list) { + char *comma; - if (do_irq) - outp += sprintf(outp, "\tIRQ"); - if (do_smi) - outp += sprintf(outp, "\tSMI"); - - if (do_nhm_cstates) - outp += sprintf(outp, "\tCPU%%c1"); - if (do_nhm_cstates && !do_slm_cstates && !do_knl_cstates) - outp += sprintf(outp, "\tCPU%%c3"); - if (do_nhm_cstates) - outp += sprintf(outp, "\tCPU%%c6"); - if (do_snb_cstates) - outp += sprintf(outp, "\tCPU%%c7"); + comma = strchr(name_list, ','); + + if (comma) + *comma = '\0'; + + for (i = 0; i < MAX_BIC; ++i) { + if (!strcmp(name_list, bic[i].name)) { + retval |= (1ULL << i); + break; + } + } + if (i == MAX_BIC) { + if (mode == SHOW_LIST) { + fprintf(stderr, "Invalid counter name: %s\n", name_list); + exit(-1); + } + deferred_skip_names[deferred_skip_index++] = name_list; + if (debug) + fprintf(stderr, "deferred \"%s\"\n", name_list); + if (deferred_skip_index >= MAX_DEFERRED) { + fprintf(stderr, "More than max %d un-recognized --skip options '%s'\n", + MAX_DEFERRED, name_list); + help(); + exit(1); + } + } + + name_list = comma; + if (name_list) + name_list++; + + } + return retval; +} + + +void print_header(char *delim) +{ + struct msr_counter *mp; + int printed = 0; + + if (DO_BIC(BIC_Package)) + outp += sprintf(outp, "%sPackage", (printed++ ? delim : "")); + if (DO_BIC(BIC_Core)) + outp += sprintf(outp, "%sCore", (printed++ ? delim : "")); + if (DO_BIC(BIC_CPU)) + outp += sprintf(outp, "%sCPU", (printed++ ? delim : "")); + if (DO_BIC(BIC_Avg_MHz)) + outp += sprintf(outp, "%sAvg_MHz", (printed++ ? delim : "")); + if (DO_BIC(BIC_Busy)) + outp += sprintf(outp, "%sBusy%%", (printed++ ? delim : "")); + if (DO_BIC(BIC_Bzy_MHz)) + outp += sprintf(outp, "%sBzy_MHz", (printed++ ? delim : "")); + if (DO_BIC(BIC_TSC_MHz)) + outp += sprintf(outp, "%sTSC_MHz", (printed++ ? delim : "")); + + if (DO_BIC(BIC_IRQ)) { + if (sums_need_wide_columns) + outp += sprintf(outp, "%s IRQ", (printed++ ? delim : "")); + else + outp += sprintf(outp, "%sIRQ", (printed++ ? delim : "")); + } + + if (DO_BIC(BIC_SMI)) + outp += sprintf(outp, "%sSMI", (printed++ ? delim : "")); for (mp = sys.tp; mp; mp = mp->next) { + if (mp->format == FORMAT_RAW) { if (mp->width == 64) - outp += sprintf(outp, "\t%18.18s", mp->name); + outp += sprintf(outp, "%s%18.18s", (printed++ ? delim : ""), mp->name); else - outp += sprintf(outp, "\t%10.10s", mp->name); + outp += sprintf(outp, "%s%10.10s", (printed++ ? delim : ""), mp->name); } else { - outp += sprintf(outp, "\t%-7.7s", mp->name); + if ((mp->type == COUNTER_ITEMS) && sums_need_wide_columns) + outp += sprintf(outp, "%s%8s", (printed++ ? delim : ""), mp->name); + else + outp += sprintf(outp, "%s%s", (printed++ ? delim : ""), mp->name); } } - if (do_dts) - outp += sprintf(outp, "\tCoreTmp"); + if (DO_BIC(BIC_CPU_c1)) + outp += sprintf(outp, "%sCPU%%c1", (printed++ ? delim : "")); + if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates) + outp += sprintf(outp, "%sCPU%%c3", (printed++ ? delim : "")); + if (DO_BIC(BIC_CPU_c6)) + outp += sprintf(outp, "%sCPU%%c6", (printed++ ? delim : "")); + if (DO_BIC(BIC_CPU_c7)) + outp += sprintf(outp, "%sCPU%%c7", (printed++ ? delim : "")); + + if (DO_BIC(BIC_Mod_c6)) + outp += sprintf(outp, "%sMod%%c6", (printed++ ? delim : "")); + + if (DO_BIC(BIC_CoreTmp)) + outp += sprintf(outp, "%sCoreTmp", (printed++ ? delim : "")); for (mp = sys.cp; mp; mp = mp->next) { if (mp->format == FORMAT_RAW) { if (mp->width == 64) - outp += sprintf(outp, "\t%18.18s", mp->name); + outp += sprintf(outp, "%s%18.18s", delim, mp->name); else - outp += sprintf(outp, "\t%10.10s", mp->name); + outp += sprintf(outp, "%s%10.10s", delim, mp->name); } else { - outp += sprintf(outp, "\t%-7.7s", mp->name); + if ((mp->type == COUNTER_ITEMS) && sums_need_wide_columns) + outp += sprintf(outp, "%s%8s", delim, mp->name); + else + outp += sprintf(outp, "%s%s", delim, mp->name); } } - if (do_ptm) - outp += sprintf(outp, "\tPkgTmp"); + if (DO_BIC(BIC_PkgTmp)) + outp += sprintf(outp, "%sPkgTmp", (printed++ ? delim : "")); - if (do_gfx_rc6_ms) - outp += sprintf(outp, "\tGFX%%rc6"); + if (DO_BIC(BIC_GFX_rc6)) + outp += sprintf(outp, "%sGFX%%rc6", (printed++ ? delim : "")); - if (do_gfx_mhz) - outp += sprintf(outp, "\tGFXMHz"); + if (DO_BIC(BIC_GFXMHz)) + outp += sprintf(outp, "%sGFXMHz", (printed++ ? delim : "")); if (do_skl_residency) { - outp += sprintf(outp, "\tTotl%%C0"); - outp += sprintf(outp, "\tAny%%C0"); - outp += sprintf(outp, "\tGFX%%C0"); - outp += sprintf(outp, "\tCPUGFX%%"); - } - - if (do_pc2) - outp += sprintf(outp, "\tPkg%%pc2"); - if (do_pc3) - outp += sprintf(outp, "\tPkg%%pc3"); - if (do_pc6) - outp += sprintf(outp, "\tPkg%%pc6"); - if (do_pc7) - outp += sprintf(outp, "\tPkg%%pc7"); - if (do_c8_c9_c10) { - outp += sprintf(outp, "\tPkg%%pc8"); - outp += sprintf(outp, "\tPkg%%pc9"); - outp += sprintf(outp, "\tPk%%pc10"); + outp += sprintf(outp, "%sTotl%%C0", (printed++ ? delim : "")); + outp += sprintf(outp, "%sAny%%C0", (printed++ ? delim : "")); + outp += sprintf(outp, "%sGFX%%C0", (printed++ ? delim : "")); + outp += sprintf(outp, "%sCPUGFX%%", (printed++ ? delim : "")); } + if (DO_BIC(BIC_Pkgpc2)) + outp += sprintf(outp, "%sPkg%%pc2", (printed++ ? delim : "")); + if (DO_BIC(BIC_Pkgpc3)) + outp += sprintf(outp, "%sPkg%%pc3", (printed++ ? delim : "")); + if (DO_BIC(BIC_Pkgpc6)) + outp += sprintf(outp, "%sPkg%%pc6", (printed++ ? delim : "")); + if (DO_BIC(BIC_Pkgpc7)) + outp += sprintf(outp, "%sPkg%%pc7", (printed++ ? delim : "")); + if (DO_BIC(BIC_Pkgpc8)) + outp += sprintf(outp, "%sPkg%%pc8", (printed++ ? delim : "")); + if (DO_BIC(BIC_Pkgpc9)) + outp += sprintf(outp, "%sPkg%%pc9", (printed++ ? delim : "")); + if (DO_BIC(BIC_Pkgpc10)) + outp += sprintf(outp, "%sPk%%pc10", (printed++ ? delim : "")); + if (do_rapl && !rapl_joules) { - if (do_rapl & RAPL_PKG) - outp += sprintf(outp, "\tPkgWatt"); - if (do_rapl & RAPL_CORES_ENERGY_STATUS) - outp += sprintf(outp, "\tCorWatt"); - if (do_rapl & RAPL_GFX) - outp += sprintf(outp, "\tGFXWatt"); - if (do_rapl & RAPL_DRAM) - outp += sprintf(outp, "\tRAMWatt"); - if (do_rapl & RAPL_PKG_PERF_STATUS) - outp += sprintf(outp, "\tPKG_%%"); - if (do_rapl & RAPL_DRAM_PERF_STATUS) - outp += sprintf(outp, "\tRAM_%%"); + if (DO_BIC(BIC_PkgWatt)) + outp += sprintf(outp, "%sPkgWatt", (printed++ ? delim : "")); + if (DO_BIC(BIC_CorWatt)) + outp += sprintf(outp, "%sCorWatt", (printed++ ? delim : "")); + if (DO_BIC(BIC_GFXWatt)) + outp += sprintf(outp, "%sGFXWatt", (printed++ ? delim : "")); + if (DO_BIC(BIC_RAMWatt)) + outp += sprintf(outp, "%sRAMWatt", (printed++ ? delim : "")); + if (DO_BIC(BIC_PKG__)) + outp += sprintf(outp, "%sPKG_%%", (printed++ ? delim : "")); + if (DO_BIC(BIC_RAM__)) + outp += sprintf(outp, "%sRAM_%%", (printed++ ? delim : "")); } else if (do_rapl && rapl_joules) { - if (do_rapl & RAPL_PKG) - outp += sprintf(outp, "\tPkg_J"); - if (do_rapl & RAPL_CORES_ENERGY_STATUS) - outp += sprintf(outp, "\tCor_J"); - if (do_rapl & RAPL_GFX) - outp += sprintf(outp, "\tGFX_J"); - if (do_rapl & RAPL_DRAM) - outp += sprintf(outp, "\tRAM_J"); - if (do_rapl & RAPL_PKG_PERF_STATUS) - outp += sprintf(outp, "\tPKG_%%"); - if (do_rapl & RAPL_DRAM_PERF_STATUS) - outp += sprintf(outp, "\tRAM_%%"); + if (DO_BIC(BIC_Pkg_J)) + outp += sprintf(outp, "%sPkg_J", (printed++ ? delim : "")); + if (DO_BIC(BIC_Cor_J)) + outp += sprintf(outp, "%sCor_J", (printed++ ? delim : "")); + if (DO_BIC(BIC_GFX_J)) + outp += sprintf(outp, "%sGFX_J", (printed++ ? delim : "")); + if (DO_BIC(BIC_RAM_J)) + outp += sprintf(outp, "%sRAM_J", (printed++ ? delim : "")); + if (DO_BIC(BIC_PKG__)) + outp += sprintf(outp, "%sPKG_%%", (printed++ ? delim : "")); + if (DO_BIC(BIC_RAM__)) + outp += sprintf(outp, "%sRAM_%%", (printed++ ? delim : "")); } for (mp = sys.pp; mp; mp = mp->next) { if (mp->format == FORMAT_RAW) { if (mp->width == 64) - outp += sprintf(outp, "\t%18.18s", mp->name); + outp += sprintf(outp, "%s%18.18s", delim, mp->name); else - outp += sprintf(outp, "\t%10.10s", mp->name); + outp += sprintf(outp, "%s%10.10s", delim, mp->name); } else { - outp += sprintf(outp, "\t%-7.7s", mp->name); + if ((mp->type == COUNTER_ITEMS) && sums_need_wide_columns) + outp += sprintf(outp, "%s%8s", delim, mp->name); + else + outp += sprintf(outp, "%s%s", delim, mp->name); } } -done: outp += sprintf(outp, "\n"); } @@ -494,10 +681,10 @@ int dump_counters(struct thread_data *t, struct core_data *c, outp += sprintf(outp, "mperf: %016llX\n", t->mperf); outp += sprintf(outp, "c1: %016llX\n", t->c1); - if (do_irq) - outp += sprintf(outp, "IRQ: %08X\n", t->irq_count); - if (do_smi) - outp += sprintf(outp, "SMI: %08X\n", t->smi_count); + if (DO_BIC(BIC_IRQ)) + outp += sprintf(outp, "IRQ: %lld\n", t->irq_count); + if (DO_BIC(BIC_SMI)) + outp += sprintf(outp, "SMI: %d\n", t->smi_count); for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) { outp += sprintf(outp, "tADDED [%d] msr0x%x: %08llX\n", @@ -516,6 +703,7 @@ int dump_counters(struct thread_data *t, struct core_data *c, outp += sprintf(outp, "cADDED [%d] msr0x%x: %08llX\n", i, mp->msr_num, c->counter[i]); } + outp += sprintf(outp, "mc6_us: %016llX\n", c->mc6_us); } if (p) { @@ -527,11 +715,11 @@ int dump_counters(struct thread_data *t, struct core_data *c, outp += sprintf(outp, "CPU + GFX: %016llX\n", p->pkg_both_core_gfxe_c0); outp += sprintf(outp, "pc2: %016llX\n", p->pc2); - if (do_pc3) + if (DO_BIC(BIC_Pkgpc3)) outp += sprintf(outp, "pc3: %016llX\n", p->pc3); - if (do_pc6) + if (DO_BIC(BIC_Pkgpc6)) outp += sprintf(outp, "pc6: %016llX\n", p->pc6); - if (do_pc7) + if (DO_BIC(BIC_Pkgpc7)) outp += sprintf(outp, "pc7: %016llX\n", p->pc7); outp += sprintf(outp, "pc8: %016llX\n", p->pc8); outp += sprintf(outp, "pc9: %016llX\n", p->pc9); @@ -563,10 +751,12 @@ int dump_counters(struct thread_data *t, struct core_data *c, int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) { - double interval_float; + double interval_float, tsc; char *fmt8; int i; struct msr_counter *mp; + char *delim = "\t"; + int printed = 0; /* if showing only 1st thread in core and this isn't one, bail out */ if (show_core_only && !(t->flags & CPU_IS_FIRST_THREAD_IN_CORE)) @@ -576,106 +766,126 @@ int format_counters(struct thread_data *t, struct core_data *c, if (show_pkg_only && !(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE)) return 0; + /*if not summary line and --cpu is used */ + if ((t != &average.threads) && + (cpu_subset && !CPU_ISSET_S(t->cpu_id, cpu_subset_size, cpu_subset))) + return 0; + interval_float = tv_delta.tv_sec + tv_delta.tv_usec/1000000.0; + tsc = t->tsc * tsc_tweak; + /* topo columns, print blanks on 1st (average) line */ if (t == &average.threads) { - if (show_pkg) - outp += sprintf(outp, "\t-"); - if (show_core) - outp += sprintf(outp, "\t-"); - if (show_cpu) - outp += sprintf(outp, "\t-"); + if (DO_BIC(BIC_Package)) + outp += sprintf(outp, "%s-", (printed++ ? delim : "")); + if (DO_BIC(BIC_Core)) + outp += sprintf(outp, "%s-", (printed++ ? delim : "")); + if (DO_BIC(BIC_CPU)) + outp += sprintf(outp, "%s-", (printed++ ? delim : "")); } else { - if (show_pkg) { + if (DO_BIC(BIC_Package)) { if (p) - outp += sprintf(outp, "\t%d", p->package_id); + outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->package_id); else - outp += sprintf(outp, "\t-"); + outp += sprintf(outp, "%s-", (printed++ ? delim : "")); } - if (show_core) { + if (DO_BIC(BIC_Core)) { if (c) - outp += sprintf(outp, "\t%d", c->core_id); + outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), c->core_id); else - outp += sprintf(outp, "\t-"); + outp += sprintf(outp, "%s-", (printed++ ? delim : "")); } - if (show_cpu) - outp += sprintf(outp, "\t%d", t->cpu_id); + if (DO_BIC(BIC_CPU)) + outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), t->cpu_id); } - /* Avg_MHz */ - if (has_aperf) - outp += sprintf(outp, "\t%.0f", + if (DO_BIC(BIC_Avg_MHz)) + outp += sprintf(outp, "%s%.0f", (printed++ ? delim : ""), 1.0 / units * t->aperf / interval_float); - /* Busy% */ - if (has_aperf) - outp += sprintf(outp, "\t%.2f", 100.0 * t->mperf/t->tsc/tsc_tweak); + if (DO_BIC(BIC_Busy)) + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * t->mperf/tsc); - /* Bzy_MHz */ - if (has_aperf) { + if (DO_BIC(BIC_Bzy_MHz)) { if (has_base_hz) - outp += sprintf(outp, "\t%.0f", base_hz / units * t->aperf / t->mperf); + outp += sprintf(outp, "%s%.0f", (printed++ ? delim : ""), base_hz / units * t->aperf / t->mperf); else - outp += sprintf(outp, "\t%.0f", - 1.0 * t->tsc / units * t->aperf / t->mperf / interval_float); + outp += sprintf(outp, "%s%.0f", (printed++ ? delim : ""), + tsc / units * t->aperf / t->mperf / interval_float); } - /* TSC_MHz */ - outp += sprintf(outp, "\t%.0f", 1.0 * t->tsc/units/interval_float); - - if (!debug) - goto done; + if (DO_BIC(BIC_TSC_MHz)) + outp += sprintf(outp, "%s%.0f", (printed++ ? delim : ""), 1.0 * t->tsc/units/interval_float); /* IRQ */ - if (do_irq) - outp += sprintf(outp, "\t%d", t->irq_count); + if (DO_BIC(BIC_IRQ)) { + if (sums_need_wide_columns) + outp += sprintf(outp, "%s%8lld", (printed++ ? delim : ""), t->irq_count); + else + outp += sprintf(outp, "%s%lld", (printed++ ? delim : ""), t->irq_count); + } /* SMI */ - if (do_smi) - outp += sprintf(outp, "\t%d", t->smi_count); - - if (do_nhm_cstates) - outp += sprintf(outp, "\t%.2f", 100.0 * t->c1/t->tsc); - - /* print per-core data only for 1st thread in core */ - if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE)) - goto done; - - if (do_nhm_cstates && !do_slm_cstates && !do_knl_cstates) - outp += sprintf(outp, "\t%.2f", 100.0 * c->c3/t->tsc); - if (do_nhm_cstates) - outp += sprintf(outp, "\t%.2f", 100.0 * c->c6/t->tsc); - if (do_snb_cstates) - outp += sprintf(outp, "\t%.2f", 100.0 * c->c7/t->tsc); + if (DO_BIC(BIC_SMI)) + outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), t->smi_count); + /* Added counters */ for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) { if (mp->format == FORMAT_RAW) { if (mp->width == 32) - outp += sprintf(outp, "\t0x%08lx", (unsigned long) t->counter[i]); + outp += sprintf(outp, "%s0x%08x", (printed++ ? delim : ""), (unsigned int) t->counter[i]); else - outp += sprintf(outp, "\t0x%016llx", t->counter[i]); + outp += sprintf(outp, "%s0x%016llx", (printed++ ? delim : ""), t->counter[i]); } else if (mp->format == FORMAT_DELTA) { - outp += sprintf(outp, "\t%8lld", t->counter[i]); + if ((mp->type == COUNTER_ITEMS) && sums_need_wide_columns) + outp += sprintf(outp, "%s%8lld", (printed++ ? delim : ""), t->counter[i]); + else + outp += sprintf(outp, "%s%lld", (printed++ ? delim : ""), t->counter[i]); } else if (mp->format == FORMAT_PERCENT) { - outp += sprintf(outp, "\t%.2f", 100.0 * t->counter[i]/t->tsc); + if (mp->type == COUNTER_USEC) + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), t->counter[i]/interval_float/10000); + else + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * t->counter[i]/tsc); } } + /* C1 */ + if (DO_BIC(BIC_CPU_c1)) + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * t->c1/tsc); - if (do_dts) - outp += sprintf(outp, "\t%d", c->core_temp_c); + + /* print per-core data only for 1st thread in core */ + if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE)) + goto done; + + if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates) + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->c3/tsc); + if (DO_BIC(BIC_CPU_c6)) + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->c6/tsc); + if (DO_BIC(BIC_CPU_c7)) + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->c7/tsc); + + /* Mod%c6 */ + if (DO_BIC(BIC_Mod_c6)) + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->mc6_us / tsc); + + if (DO_BIC(BIC_CoreTmp)) + outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), c->core_temp_c); for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) { if (mp->format == FORMAT_RAW) { if (mp->width == 32) - outp += sprintf(outp, "\t0x%08lx", (unsigned long) c->counter[i]); + outp += sprintf(outp, "%s0x%08x", (printed++ ? delim : ""), (unsigned int) c->counter[i]); else - outp += sprintf(outp, "\t0x%016llx", c->counter[i]); + outp += sprintf(outp, "%s0x%016llx", (printed++ ? delim : ""), c->counter[i]); } else if (mp->format == FORMAT_DELTA) { - outp += sprintf(outp, "\t%8lld", c->counter[i]); + if ((mp->type == COUNTER_ITEMS) && sums_need_wide_columns) + outp += sprintf(outp, "%s%8lld", (printed++ ? delim : ""), c->counter[i]); + else + outp += sprintf(outp, "%s%lld", (printed++ ? delim : ""), c->counter[i]); } else if (mp->format == FORMAT_PERCENT) { - outp += sprintf(outp, "\t%.2f", 100.0 * c->counter[i]/t->tsc); + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->counter[i]/tsc); } } @@ -684,95 +894,89 @@ int format_counters(struct thread_data *t, struct core_data *c, goto done; /* PkgTmp */ - if (do_ptm) - outp += sprintf(outp, "\t%d", p->pkg_temp_c); + if (DO_BIC(BIC_PkgTmp)) + outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->pkg_temp_c); /* GFXrc6 */ - if (do_gfx_rc6_ms) { + if (DO_BIC(BIC_GFX_rc6)) { if (p->gfx_rc6_ms == -1) { /* detect GFX counter reset */ - outp += sprintf(outp, "\t**.**"); + outp += sprintf(outp, "%s**.**", (printed++ ? delim : "")); } else { - outp += sprintf(outp, "\t%.2f", + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), p->gfx_rc6_ms / 10.0 / interval_float); } } /* GFXMHz */ - if (do_gfx_mhz) - outp += sprintf(outp, "\t%d", p->gfx_mhz); + if (DO_BIC(BIC_GFXMHz)) + outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->gfx_mhz); /* Totl%C0, Any%C0 GFX%C0 CPUGFX% */ if (do_skl_residency) { - outp += sprintf(outp, "\t%.2f", 100.0 * p->pkg_wtd_core_c0/t->tsc); - outp += sprintf(outp, "\t%.2f", 100.0 * p->pkg_any_core_c0/t->tsc); - outp += sprintf(outp, "\t%.2f", 100.0 * p->pkg_any_gfxe_c0/t->tsc); - outp += sprintf(outp, "\t%.2f", 100.0 * p->pkg_both_core_gfxe_c0/t->tsc); - } - - if (do_pc2) - outp += sprintf(outp, "\t%.2f", 100.0 * p->pc2/t->tsc); - if (do_pc3) - outp += sprintf(outp, "\t%.2f", 100.0 * p->pc3/t->tsc); - if (do_pc6) - outp += sprintf(outp, "\t%.2f", 100.0 * p->pc6/t->tsc); - if (do_pc7) - outp += sprintf(outp, "\t%.2f", 100.0 * p->pc7/t->tsc); - if (do_c8_c9_c10) { - outp += sprintf(outp, "\t%.2f", 100.0 * p->pc8/t->tsc); - outp += sprintf(outp, "\t%.2f", 100.0 * p->pc9/t->tsc); - outp += sprintf(outp, "\t%.2f", 100.0 * p->pc10/t->tsc); + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pkg_wtd_core_c0/tsc); + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pkg_any_core_c0/tsc); + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pkg_any_gfxe_c0/tsc); + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pkg_both_core_gfxe_c0/tsc); } + if (DO_BIC(BIC_Pkgpc2)) + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pc2/tsc); + if (DO_BIC(BIC_Pkgpc3)) + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pc3/tsc); + if (DO_BIC(BIC_Pkgpc6)) + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pc6/tsc); + if (DO_BIC(BIC_Pkgpc7)) + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pc7/tsc); + if (DO_BIC(BIC_Pkgpc8)) + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pc8/tsc); + if (DO_BIC(BIC_Pkgpc9)) + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pc9/tsc); + if (DO_BIC(BIC_Pkgpc10)) + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pc10/tsc); + /* * If measurement interval exceeds minimum RAPL Joule Counter range, * indicate that results are suspect by printing "**" in fraction place. */ if (interval_float < rapl_joule_counter_range) - fmt8 = "\t%.2f"; + fmt8 = "%s%.2f"; else fmt8 = "%6.0f**"; - if (do_rapl && !rapl_joules) { - if (do_rapl & RAPL_PKG) - outp += sprintf(outp, fmt8, p->energy_pkg * rapl_energy_units / interval_float); - if (do_rapl & RAPL_CORES_ENERGY_STATUS) - outp += sprintf(outp, fmt8, p->energy_cores * rapl_energy_units / interval_float); - if (do_rapl & RAPL_GFX) - outp += sprintf(outp, fmt8, p->energy_gfx * rapl_energy_units / interval_float); - if (do_rapl & RAPL_DRAM) - outp += sprintf(outp, fmt8, p->energy_dram * rapl_dram_energy_units / interval_float); - if (do_rapl & RAPL_PKG_PERF_STATUS) - outp += sprintf(outp, fmt8, 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float); - if (do_rapl & RAPL_DRAM_PERF_STATUS) - outp += sprintf(outp, fmt8, 100.0 * p->rapl_dram_perf_status * rapl_time_units / interval_float); - } else if (do_rapl && rapl_joules) { - if (do_rapl & RAPL_PKG) - outp += sprintf(outp, fmt8, - p->energy_pkg * rapl_energy_units); - if (do_rapl & RAPL_CORES) - outp += sprintf(outp, fmt8, - p->energy_cores * rapl_energy_units); - if (do_rapl & RAPL_GFX) - outp += sprintf(outp, fmt8, - p->energy_gfx * rapl_energy_units); - if (do_rapl & RAPL_DRAM) - outp += sprintf(outp, fmt8, - p->energy_dram * rapl_dram_energy_units); - if (do_rapl & RAPL_PKG_PERF_STATUS) - outp += sprintf(outp, fmt8, 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float); - if (do_rapl & RAPL_DRAM_PERF_STATUS) - outp += sprintf(outp, fmt8, 100.0 * p->rapl_dram_perf_status * rapl_time_units / interval_float); - } + if (DO_BIC(BIC_PkgWatt)) + outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_pkg * rapl_energy_units / interval_float); + if (DO_BIC(BIC_CorWatt)) + outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_cores * rapl_energy_units / interval_float); + if (DO_BIC(BIC_GFXWatt)) + outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_gfx * rapl_energy_units / interval_float); + if (DO_BIC(BIC_RAMWatt)) + outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_dram * rapl_dram_energy_units / interval_float); + if (DO_BIC(BIC_Pkg_J)) + outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_pkg * rapl_energy_units); + if (DO_BIC(BIC_Cor_J)) + outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_cores * rapl_energy_units); + if (DO_BIC(BIC_GFX_J)) + outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_gfx * rapl_energy_units); + if (DO_BIC(BIC_RAM_J)) + outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_dram * rapl_dram_energy_units); + if (DO_BIC(BIC_PKG__)) + outp += sprintf(outp, fmt8, (printed++ ? delim : ""), 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float); + if (DO_BIC(BIC_RAM__)) + outp += sprintf(outp, fmt8, (printed++ ? delim : ""), 100.0 * p->rapl_dram_perf_status * rapl_time_units / interval_float); + for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) { if (mp->format == FORMAT_RAW) { if (mp->width == 32) - outp += sprintf(outp, "\t0x%08lx", (unsigned long) p->counter[i]); + outp += sprintf(outp, "%s0x%08x", (printed++ ? delim : ""), (unsigned int) p->counter[i]); else - outp += sprintf(outp, "\t0x%016llx", p->counter[i]); + outp += sprintf(outp, "%s0x%016llx", (printed++ ? delim : ""), p->counter[i]); } else if (mp->format == FORMAT_DELTA) { - outp += sprintf(outp, "\t%8lld", p->counter[i]); + if ((mp->type == COUNTER_ITEMS) && sums_need_wide_columns) + outp += sprintf(outp, "%s%8lld", (printed++ ? delim : ""), p->counter[i]); + else + outp += sprintf(outp, "%s%lld", (printed++ ? delim : ""), p->counter[i]); } else if (mp->format == FORMAT_PERCENT) { - outp += sprintf(outp, "\t%.2f", 100.0 * p->counter[i]/t->tsc); + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->counter[i]/tsc); } } @@ -807,7 +1011,7 @@ void format_all_counters(struct thread_data *t, struct core_data *c, struct pkg_ static int printed; if (!printed || !summary_only) - print_header(); + print_header("\t"); if (topo.num_cpus > 1) format_counters(&average.threads, &average.cores, @@ -841,11 +1045,11 @@ delta_package(struct pkg_data *new, struct pkg_data *old) old->pkg_both_core_gfxe_c0 = new->pkg_both_core_gfxe_c0 - old->pkg_both_core_gfxe_c0; } old->pc2 = new->pc2 - old->pc2; - if (do_pc3) + if (DO_BIC(BIC_Pkgpc3)) old->pc3 = new->pc3 - old->pc3; - if (do_pc6) + if (DO_BIC(BIC_Pkgpc6)) old->pc6 = new->pc6 - old->pc6; - if (do_pc7) + if (DO_BIC(BIC_Pkgpc7)) old->pc7 = new->pc7 - old->pc7; old->pc8 = new->pc8 - old->pc8; old->pc9 = new->pc9 - old->pc9; @@ -887,6 +1091,7 @@ delta_core(struct core_data *new, struct core_data *old) old->c6 = new->c6 - old->c6; old->c7 = new->c7 - old->c7; old->core_temp_c = new->core_temp_c; + old->mc6_us = new->mc6_us - old->mc6_us; for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) { if (mp->format == FORMAT_RAW) @@ -916,7 +1121,7 @@ delta_thread(struct thread_data *new, struct thread_data *old, old->c1 = new->c1 - old->c1; - if (has_aperf) { + if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz)) { if ((new->aperf > old->aperf) && (new->mperf > old->mperf)) { old->aperf = new->aperf - old->aperf; old->mperf = new->mperf - old->mperf; @@ -937,11 +1142,11 @@ delta_thread(struct thread_data *new, struct thread_data *old, * it is possible for mperf's non-halted cycles + idle states * to exceed TSC's all cycles: show c1 = 0% in that case. */ - if ((old->mperf + core_delta->c3 + core_delta->c6 + core_delta->c7) > old->tsc) + if ((old->mperf + core_delta->c3 + core_delta->c6 + core_delta->c7) > (old->tsc * tsc_tweak)) old->c1 = 0; else { /* normal case, derive c1 */ - old->c1 = old->tsc - old->mperf - core_delta->c3 + old->c1 = (old->tsc * tsc_tweak) - old->mperf - core_delta->c3 - core_delta->c6 - core_delta->c7; } } @@ -952,10 +1157,10 @@ delta_thread(struct thread_data *new, struct thread_data *old, old->mperf = 1; /* divide by 0 protection */ } - if (do_irq) + if (DO_BIC(BIC_IRQ)) old->irq_count = new->irq_count - old->irq_count; - if (do_smi) + if (DO_BIC(BIC_SMI)) old->smi_count = new->smi_count - old->smi_count; for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) { @@ -1008,6 +1213,7 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data c->c3 = 0; c->c6 = 0; c->c7 = 0; + c->mc6_us = 0; c->core_temp_c = 0; p->pkg_wtd_core_c0 = 0; @@ -1016,11 +1222,11 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data p->pkg_both_core_gfxe_c0 = 0; p->pc2 = 0; - if (do_pc3) + if (DO_BIC(BIC_Pkgpc3)) p->pc3 = 0; - if (do_pc6) + if (DO_BIC(BIC_Pkgpc6)) p->pc6 = 0; - if (do_pc7) + if (DO_BIC(BIC_Pkgpc7)) p->pc7 = 0; p->pc8 = 0; p->pc9 = 0; @@ -1036,7 +1242,6 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data p->gfx_rc6_ms = 0; p->gfx_mhz = 0; - for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) t->counter[i] = 0; @@ -1073,6 +1278,7 @@ int sum_counters(struct thread_data *t, struct core_data *c, average.cores.c3 += c->c3; average.cores.c6 += c->c6; average.cores.c7 += c->c7; + average.cores.mc6_us += c->mc6_us; average.cores.core_temp_c = MAX(average.cores.core_temp_c, c->core_temp_c); @@ -1094,11 +1300,11 @@ int sum_counters(struct thread_data *t, struct core_data *c, } average.packages.pc2 += p->pc2; - if (do_pc3) + if (DO_BIC(BIC_Pkgpc3)) average.packages.pc3 += p->pc3; - if (do_pc6) + if (DO_BIC(BIC_Pkgpc6)) average.packages.pc6 += p->pc6; - if (do_pc7) + if (DO_BIC(BIC_Pkgpc7)) average.packages.pc7 += p->pc7; average.packages.pc8 += p->pc8; average.packages.pc9 += p->pc9; @@ -1143,9 +1349,13 @@ void compute_average(struct thread_data *t, struct core_data *c, average.threads.mperf /= topo.num_cpus; average.threads.c1 /= topo.num_cpus; + if (average.threads.irq_count > 9999999) + sums_need_wide_columns = 1; + average.cores.c3 /= topo.num_cores; average.cores.c6 /= topo.num_cores; average.cores.c7 /= topo.num_cores; + average.cores.mc6_us /= topo.num_cores; if (do_skl_residency) { average.packages.pkg_wtd_core_c0 /= topo.num_packages; @@ -1155,11 +1365,11 @@ void compute_average(struct thread_data *t, struct core_data *c, } average.packages.pc2 /= topo.num_packages; - if (do_pc3) + if (DO_BIC(BIC_Pkgpc3)) average.packages.pc3 /= topo.num_packages; - if (do_pc6) + if (DO_BIC(BIC_Pkgpc6)) average.packages.pc6 /= topo.num_packages; - if (do_pc7) + if (DO_BIC(BIC_Pkgpc7)) average.packages.pc7 /= topo.num_packages; average.packages.pc8 /= topo.num_packages; @@ -1169,16 +1379,29 @@ void compute_average(struct thread_data *t, struct core_data *c, for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) { if (mp->format == FORMAT_RAW) continue; + if (mp->type == COUNTER_ITEMS) { + if (average.threads.counter[i] > 9999999) + sums_need_wide_columns = 1; + continue; + } average.threads.counter[i] /= topo.num_cpus; } for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) { if (mp->format == FORMAT_RAW) continue; + if (mp->type == COUNTER_ITEMS) { + if (average.cores.counter[i] > 9999999) + sums_need_wide_columns = 1; + } average.cores.counter[i] /= topo.num_cores; } for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) { if (mp->format == FORMAT_RAW) continue; + if (mp->type == COUNTER_ITEMS) { + if (average.packages.counter[i] > 9999999) + sums_need_wide_columns = 1; + } average.packages.counter[i] /= topo.num_packages; } } @@ -1193,6 +1416,60 @@ static unsigned long long rdtsc(void) } /* + * Open a file, and exit on failure + */ +FILE *fopen_or_die(const char *path, const char *mode) +{ + FILE *filep = fopen(path, mode); + + if (!filep) + err(1, "%s: open failed", path); + return filep; +} +/* + * snapshot_sysfs_counter() + * + * return snapshot of given counter + */ +unsigned long long snapshot_sysfs_counter(char *path) +{ + FILE *fp; + int retval; + unsigned long long counter; + + fp = fopen_or_die(path, "r"); + + retval = fscanf(fp, "%lld", &counter); + if (retval != 1) + err(1, "snapshot_sysfs_counter(%s)", path); + + fclose(fp); + + return counter; +} + +int get_mp(int cpu, struct msr_counter *mp, unsigned long long *counterp) +{ + if (mp->msr_num != 0) { + if (get_msr(cpu, mp->msr_num, counterp)) + return -1; + } else { + char path[128]; + + if (mp->flags & SYSFS_PERCPU) { + sprintf(path, "/sys/devices/system/cpu/cpu%d/%s", + cpu, mp->path); + + *counterp = snapshot_sysfs_counter(path); + } else { + *counterp = snapshot_sysfs_counter(mp->path); + } + } + + return 0; +} + +/* * get_counters(...) * migrate to cpu * acquire and record local counters for that cpu @@ -1213,7 +1490,7 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) retry: t->tsc = rdtsc(); /* we are running on local CPU of interest */ - if (has_aperf) { + if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz)) { unsigned long long tsc_before, tsc_between, tsc_after, aperf_time, mperf_time; /* @@ -1269,35 +1546,33 @@ retry: t->mperf = t->mperf * aperf_mperf_multiplier; } - if (do_irq) + if (DO_BIC(BIC_IRQ)) t->irq_count = irqs_per_cpu[cpu]; - if (do_smi) { + if (DO_BIC(BIC_SMI)) { if (get_msr(cpu, MSR_SMI_COUNT, &msr)) return -5; t->smi_count = msr & 0xFFFFFFFF; } - - if (use_c1_residency_msr) { + if (DO_BIC(BIC_CPU_c1) && use_c1_residency_msr) { if (get_msr(cpu, MSR_CORE_C1_RES, &t->c1)) return -6; } for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) { - if (get_msr(cpu, mp->msr_num, &t->counter[i])) + if (get_mp(cpu, mp, &t->counter[i])) return -10; } - /* collect core counters only for 1st thread in core */ if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE)) return 0; - if (do_nhm_cstates && !do_slm_cstates && !do_knl_cstates) { + if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates) { if (get_msr(cpu, MSR_CORE_C3_RESIDENCY, &c->c3)) return -6; } - if (do_nhm_cstates && !do_knl_cstates) { + if (DO_BIC(BIC_CPU_c6) && !do_knl_cstates) { if (get_msr(cpu, MSR_CORE_C6_RESIDENCY, &c->c6)) return -7; } else if (do_knl_cstates) { @@ -1305,18 +1580,22 @@ retry: return -7; } - if (do_snb_cstates) + if (DO_BIC(BIC_CPU_c7)) if (get_msr(cpu, MSR_CORE_C7_RESIDENCY, &c->c7)) return -8; - if (do_dts) { + if (DO_BIC(BIC_Mod_c6)) + if (get_msr(cpu, MSR_MODULE_C6_RES_MS, &c->mc6_us)) + return -8; + + if (DO_BIC(BIC_CoreTmp)) { if (get_msr(cpu, MSR_IA32_THERM_STATUS, &msr)) return -9; c->core_temp_c = tcc_activation_temp - ((msr >> 16) & 0x7F); } for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) { - if (get_msr(cpu, mp->msr_num, &c->counter[i])) + if (get_mp(cpu, mp, &c->counter[i])) return -10; } @@ -1334,26 +1613,35 @@ retry: if (get_msr(cpu, MSR_PKG_BOTH_CORE_GFXE_C0_RES, &p->pkg_both_core_gfxe_c0)) return -13; } - if (do_pc3) + if (DO_BIC(BIC_Pkgpc3)) if (get_msr(cpu, MSR_PKG_C3_RESIDENCY, &p->pc3)) return -9; - if (do_pc6) - if (get_msr(cpu, MSR_PKG_C6_RESIDENCY, &p->pc6)) - return -10; - if (do_pc2) + if (DO_BIC(BIC_Pkgpc6)) { + if (do_slm_cstates) { + if (get_msr(cpu, MSR_ATOM_PKG_C6_RESIDENCY, &p->pc6)) + return -10; + } else { + if (get_msr(cpu, MSR_PKG_C6_RESIDENCY, &p->pc6)) + return -10; + } + } + + if (DO_BIC(BIC_Pkgpc2)) if (get_msr(cpu, MSR_PKG_C2_RESIDENCY, &p->pc2)) return -11; - if (do_pc7) + if (DO_BIC(BIC_Pkgpc7)) if (get_msr(cpu, MSR_PKG_C7_RESIDENCY, &p->pc7)) return -12; - if (do_c8_c9_c10) { + if (DO_BIC(BIC_Pkgpc8)) if (get_msr(cpu, MSR_PKG_C8_RESIDENCY, &p->pc8)) return -13; + if (DO_BIC(BIC_Pkgpc9)) if (get_msr(cpu, MSR_PKG_C9_RESIDENCY, &p->pc9)) return -13; + if (DO_BIC(BIC_Pkgpc10)) if (get_msr(cpu, MSR_PKG_C10_RESIDENCY, &p->pc10)) return -13; - } + if (do_rapl & RAPL_PKG) { if (get_msr(cpu, MSR_PKG_ENERGY_STATUS, &msr)) return -13; @@ -1384,20 +1672,20 @@ retry: return -16; p->rapl_dram_perf_status = msr & 0xFFFFFFFF; } - if (do_ptm) { + if (DO_BIC(BIC_PkgTmp)) { if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_STATUS, &msr)) return -17; p->pkg_temp_c = tcc_activation_temp - ((msr >> 16) & 0x7F); } - if (do_gfx_rc6_ms) + if (DO_BIC(BIC_GFX_rc6)) p->gfx_rc6_ms = gfx_cur_rc6_ms; - if (do_gfx_mhz) + if (DO_BIC(BIC_GFXMHz)) p->gfx_mhz = gfx_cur_mhz; for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) { - if (get_msr(cpu, mp->msr_num, &p->counter[i])) + if (get_mp(cpu, mp, &p->counter[i])) return -10; } @@ -1433,8 +1721,8 @@ char *pkg_cstate_limit_strings[] = { "reserved", "unknown", "pc0", "pc1", "pc2", int nhm_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCL__3, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV}; int snb_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCL__7, PCL_7S, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV}; int hsw_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL__3, PCL__6, PCL__7, PCL_7S, PCL__8, PCL__9, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV}; -int slv_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCLRSV, PCLRSV, PCL__4, PCLRSV, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV}; -int amt_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCL__2, PCLRSV, PCLRSV, PCLRSV, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV}; +int slv_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCLRSV, PCLRSV, PCL__4, PCLRSV, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCL__6, PCL__7}; +int amt_pkg_cstate_limits[16] = {PCLUNL, PCL__1, PCL__2, PCLRSV, PCLRSV, PCLRSV, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV}; int phi_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV}; int bxt_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV}; int skx_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV}; @@ -1457,11 +1745,11 @@ dump_nhm_platform_info(void) fprintf(outf, "cpu%d: MSR_PLATFORM_INFO: 0x%08llx\n", base_cpu, msr); ratio = (msr >> 40) & 0xFF; - fprintf(outf, "%d * %.0f = %.0f MHz max efficiency frequency\n", + fprintf(outf, "%d * %.1f = %.1f MHz max efficiency frequency\n", ratio, bclk, ratio * bclk); ratio = (msr >> 8) & 0xFF; - fprintf(outf, "%d * %.0f = %.0f MHz base frequency\n", + fprintf(outf, "%d * %.1f = %.1f MHz base frequency\n", ratio, bclk, ratio * bclk); get_msr(base_cpu, MSR_IA32_POWER_CTL, &msr); @@ -1483,12 +1771,12 @@ dump_hsw_turbo_ratio_limits(void) ratio = (msr >> 8) & 0xFF; if (ratio) - fprintf(outf, "%d * %.0f = %.0f MHz max turbo 18 active cores\n", + fprintf(outf, "%d * %.1f = %.1f MHz max turbo 18 active cores\n", ratio, bclk, ratio * bclk); ratio = (msr >> 0) & 0xFF; if (ratio) - fprintf(outf, "%d * %.0f = %.0f MHz max turbo 17 active cores\n", + fprintf(outf, "%d * %.1f = %.1f MHz max turbo 17 active cores\n", ratio, bclk, ratio * bclk); return; } @@ -1505,99 +1793,175 @@ dump_ivt_turbo_ratio_limits(void) ratio = (msr >> 56) & 0xFF; if (ratio) - fprintf(outf, "%d * %.0f = %.0f MHz max turbo 16 active cores\n", + fprintf(outf, "%d * %.1f = %.1f MHz max turbo 16 active cores\n", ratio, bclk, ratio * bclk); ratio = (msr >> 48) & 0xFF; if (ratio) - fprintf(outf, "%d * %.0f = %.0f MHz max turbo 15 active cores\n", + fprintf(outf, "%d * %.1f = %.1f MHz max turbo 15 active cores\n", ratio, bclk, ratio * bclk); ratio = (msr >> 40) & 0xFF; if (ratio) - fprintf(outf, "%d * %.0f = %.0f MHz max turbo 14 active cores\n", + fprintf(outf, "%d * %.1f = %.1f MHz max turbo 14 active cores\n", ratio, bclk, ratio * bclk); ratio = (msr >> 32) & 0xFF; if (ratio) - fprintf(outf, "%d * %.0f = %.0f MHz max turbo 13 active cores\n", + fprintf(outf, "%d * %.1f = %.1f MHz max turbo 13 active cores\n", ratio, bclk, ratio * bclk); ratio = (msr >> 24) & 0xFF; if (ratio) - fprintf(outf, "%d * %.0f = %.0f MHz max turbo 12 active cores\n", + fprintf(outf, "%d * %.1f = %.1f MHz max turbo 12 active cores\n", ratio, bclk, ratio * bclk); ratio = (msr >> 16) & 0xFF; if (ratio) - fprintf(outf, "%d * %.0f = %.0f MHz max turbo 11 active cores\n", + fprintf(outf, "%d * %.1f = %.1f MHz max turbo 11 active cores\n", ratio, bclk, ratio * bclk); ratio = (msr >> 8) & 0xFF; if (ratio) - fprintf(outf, "%d * %.0f = %.0f MHz max turbo 10 active cores\n", + fprintf(outf, "%d * %.1f = %.1f MHz max turbo 10 active cores\n", ratio, bclk, ratio * bclk); ratio = (msr >> 0) & 0xFF; if (ratio) - fprintf(outf, "%d * %.0f = %.0f MHz max turbo 9 active cores\n", + fprintf(outf, "%d * %.1f = %.1f MHz max turbo 9 active cores\n", ratio, bclk, ratio * bclk); return; } +int has_turbo_ratio_group_limits(int family, int model) +{ + + if (!genuine_intel) + return 0; + + switch (model) { + case INTEL_FAM6_ATOM_GOLDMONT: + case INTEL_FAM6_SKYLAKE_X: + case INTEL_FAM6_ATOM_DENVERTON: + return 1; + } + return 0; +} static void -dump_nhm_turbo_ratio_limits(void) +dump_turbo_ratio_limits(int family, int model) { - unsigned long long msr; - unsigned int ratio; + unsigned long long msr, core_counts; + unsigned int ratio, group_size; get_msr(base_cpu, MSR_TURBO_RATIO_LIMIT, &msr); - fprintf(outf, "cpu%d: MSR_TURBO_RATIO_LIMIT: 0x%08llx\n", base_cpu, msr); + if (has_turbo_ratio_group_limits(family, model)) { + get_msr(base_cpu, MSR_TURBO_RATIO_LIMIT1, &core_counts); + fprintf(outf, "cpu%d: MSR_TURBO_RATIO_LIMIT1: 0x%08llx\n", base_cpu, core_counts); + } else { + core_counts = 0x0807060504030201; + } + ratio = (msr >> 56) & 0xFF; + group_size = (core_counts >> 56) & 0xFF; if (ratio) - fprintf(outf, "%d * %.0f = %.0f MHz max turbo 8 active cores\n", - ratio, bclk, ratio * bclk); + fprintf(outf, "%d * %.1f = %.1f MHz max turbo %d active cores\n", + ratio, bclk, ratio * bclk, group_size); ratio = (msr >> 48) & 0xFF; + group_size = (core_counts >> 48) & 0xFF; if (ratio) - fprintf(outf, "%d * %.0f = %.0f MHz max turbo 7 active cores\n", - ratio, bclk, ratio * bclk); + fprintf(outf, "%d * %.1f = %.1f MHz max turbo %d active cores\n", + ratio, bclk, ratio * bclk, group_size); ratio = (msr >> 40) & 0xFF; + group_size = (core_counts >> 40) & 0xFF; if (ratio) - fprintf(outf, "%d * %.0f = %.0f MHz max turbo 6 active cores\n", - ratio, bclk, ratio * bclk); + fprintf(outf, "%d * %.1f = %.1f MHz max turbo %d active cores\n", + ratio, bclk, ratio * bclk, group_size); ratio = (msr >> 32) & 0xFF; + group_size = (core_counts >> 32) & 0xFF; if (ratio) - fprintf(outf, "%d * %.0f = %.0f MHz max turbo 5 active cores\n", - ratio, bclk, ratio * bclk); + fprintf(outf, "%d * %.1f = %.1f MHz max turbo %d active cores\n", + ratio, bclk, ratio * bclk, group_size); ratio = (msr >> 24) & 0xFF; + group_size = (core_counts >> 24) & 0xFF; if (ratio) - fprintf(outf, "%d * %.0f = %.0f MHz max turbo 4 active cores\n", - ratio, bclk, ratio * bclk); + fprintf(outf, "%d * %.1f = %.1f MHz max turbo %d active cores\n", + ratio, bclk, ratio * bclk, group_size); ratio = (msr >> 16) & 0xFF; + group_size = (core_counts >> 16) & 0xFF; if (ratio) - fprintf(outf, "%d * %.0f = %.0f MHz max turbo 3 active cores\n", - ratio, bclk, ratio * bclk); + fprintf(outf, "%d * %.1f = %.1f MHz max turbo %d active cores\n", + ratio, bclk, ratio * bclk, group_size); ratio = (msr >> 8) & 0xFF; + group_size = (core_counts >> 8) & 0xFF; if (ratio) - fprintf(outf, "%d * %.0f = %.0f MHz max turbo 2 active cores\n", - ratio, bclk, ratio * bclk); + fprintf(outf, "%d * %.1f = %.1f MHz max turbo %d active cores\n", + ratio, bclk, ratio * bclk, group_size); ratio = (msr >> 0) & 0xFF; + group_size = (core_counts >> 0) & 0xFF; if (ratio) - fprintf(outf, "%d * %.0f = %.0f MHz max turbo 1 active cores\n", - ratio, bclk, ratio * bclk); + fprintf(outf, "%d * %.1f = %.1f MHz max turbo %d active cores\n", + ratio, bclk, ratio * bclk, group_size); return; } static void +dump_atom_turbo_ratio_limits(void) +{ + unsigned long long msr; + unsigned int ratio; + + get_msr(base_cpu, MSR_ATOM_CORE_RATIOS, &msr); + fprintf(outf, "cpu%d: MSR_ATOM_CORE_RATIOS: 0x%08llx\n", base_cpu, msr & 0xFFFFFFFF); + + ratio = (msr >> 0) & 0x3F; + if (ratio) + fprintf(outf, "%d * %.1f = %.1f MHz minimum operating frequency\n", + ratio, bclk, ratio * bclk); + + ratio = (msr >> 8) & 0x3F; + if (ratio) + fprintf(outf, "%d * %.1f = %.1f MHz low frequency mode (LFM)\n", + ratio, bclk, ratio * bclk); + + ratio = (msr >> 16) & 0x3F; + if (ratio) + fprintf(outf, "%d * %.1f = %.1f MHz base frequency\n", + ratio, bclk, ratio * bclk); + + get_msr(base_cpu, MSR_ATOM_CORE_TURBO_RATIOS, &msr); + fprintf(outf, "cpu%d: MSR_ATOM_CORE_TURBO_RATIOS: 0x%08llx\n", base_cpu, msr & 0xFFFFFFFF); + + ratio = (msr >> 24) & 0x3F; + if (ratio) + fprintf(outf, "%d * %.1f = %.1f MHz max turbo 4 active cores\n", + ratio, bclk, ratio * bclk); + + ratio = (msr >> 16) & 0x3F; + if (ratio) + fprintf(outf, "%d * %.1f = %.1f MHz max turbo 3 active cores\n", + ratio, bclk, ratio * bclk); + + ratio = (msr >> 8) & 0x3F; + if (ratio) + fprintf(outf, "%d * %.1f = %.1f MHz max turbo 2 active cores\n", + ratio, bclk, ratio * bclk); + + ratio = (msr >> 0) & 0x3F; + if (ratio) + fprintf(outf, "%d * %.1f = %.1f MHz max turbo 1 active core\n", + ratio, bclk, ratio * bclk); +} + +static void dump_knl_turbo_ratio_limits(void) { const unsigned int buckets_no = 7; @@ -1652,7 +2016,7 @@ dump_knl_turbo_ratio_limits(void) for (i = buckets_no - 1; i >= 0; i--) if (i > 0 ? ratio[i] != ratio[i - 1] : 1) fprintf(outf, - "%d * %.0f = %.0f MHz max turbo %d active cores\n", + "%d * %.1f = %.1f MHz max turbo %d active cores\n", ratio[i], bclk, ratio[i] * bclk, cores[i]); } @@ -1661,12 +2025,12 @@ dump_nhm_cst_cfg(void) { unsigned long long msr; - get_msr(base_cpu, MSR_NHM_SNB_PKG_CST_CFG_CTL, &msr); + get_msr(base_cpu, MSR_PKG_CST_CONFIG_CONTROL, &msr); #define SNB_C1_AUTO_UNDEMOTE (1UL << 27) #define SNB_C3_AUTO_UNDEMOTE (1UL << 28) - fprintf(outf, "cpu%d: MSR_NHM_SNB_PKG_CST_CFG_CTL: 0x%08llx", base_cpu, msr); + fprintf(outf, "cpu%d: MSR_PKG_CST_CONFIG_CONTROL: 0x%08llx", base_cpu, msr); fprintf(outf, " (%s%s%s%s%slocked: pkg-cstate-limit=%d: %s)\n", (msr & SNB_C3_AUTO_UNDEMOTE) ? "UNdemote-C3, " : "", @@ -1810,16 +2174,6 @@ void free_all_buffers(void) free(irqs_per_cpu); } -/* - * Open a file, and exit on failure - */ -FILE *fopen_or_die(const char *path, const char *mode) -{ - FILE *filep = fopen(path, mode); - if (!filep) - err(1, "%s: open failed", path); - return filep; -} /* * Parse a file containing a single int. @@ -2131,8 +2485,10 @@ int snapshot_gfx_mhz(void) if (fp == NULL) fp = fopen_or_die("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", "r"); - else + else { rewind(fp); + fflush(fp); + } retval = fscanf(fp, "%d", &gfx_cur_mhz); if (retval != 1) @@ -2148,13 +2504,14 @@ int snapshot_gfx_mhz(void) */ int snapshot_proc_sysfs_files(void) { - if (snapshot_proc_interrupts()) - return 1; + if (DO_BIC(BIC_IRQ)) + if (snapshot_proc_interrupts()) + return 1; - if (do_gfx_rc6_ms) + if (DO_BIC(BIC_GFX_rc6)) snapshot_gfx_rc6_ms(); - if (do_gfx_mhz) + if (DO_BIC(BIC_GFXMHz)) snapshot_gfx_mhz(); return 0; @@ -2283,7 +2640,9 @@ void check_permissions() * MSR_SMI_COUNT 0x00000034 * * MSR_PLATFORM_INFO 0x000000ce - * MSR_NHM_SNB_PKG_CST_CFG_CTL 0x000000e2 + * MSR_PKG_CST_CONFIG_CONTROL 0x000000e2 + * + * MSR_MISC_PWR_MGMT 0x000001aa * * MSR_PKG_C3_RESIDENCY 0x000003f8 * MSR_PKG_C6_RESIDENCY 0x000003f9 @@ -2291,7 +2650,8 @@ void check_permissions() * MSR_CORE_C6_RESIDENCY 0x000003fd * * Side effect: - * sets global pkg_cstate_limit to decode MSR_NHM_SNB_PKG_CST_CFG_CTL + * sets global pkg_cstate_limit to decode MSR_PKG_CST_CONFIG_CONTROL + * sets has_misc_feature_control */ int probe_nhm_msrs(unsigned int family, unsigned int model) { @@ -2322,6 +2682,7 @@ int probe_nhm_msrs(unsigned int family, unsigned int model) case INTEL_FAM6_IVYBRIDGE: /* IVB */ case INTEL_FAM6_IVYBRIDGE_X: /* IVB Xeon */ pkg_cstate_limits = snb_pkg_cstate_limits; + has_misc_feature_control = 1; break; case INTEL_FAM6_HASWELL_CORE: /* HSW */ case INTEL_FAM6_HASWELL_X: /* HSX */ @@ -2336,29 +2697,34 @@ int probe_nhm_msrs(unsigned int family, unsigned int model) case INTEL_FAM6_KABYLAKE_MOBILE: /* KBL */ case INTEL_FAM6_KABYLAKE_DESKTOP: /* KBL */ pkg_cstate_limits = hsw_pkg_cstate_limits; + has_misc_feature_control = 1; break; case INTEL_FAM6_SKYLAKE_X: /* SKX */ pkg_cstate_limits = skx_pkg_cstate_limits; + has_misc_feature_control = 1; break; case INTEL_FAM6_ATOM_SILVERMONT1: /* BYT */ + no_MSR_MISC_PWR_MGMT = 1; case INTEL_FAM6_ATOM_SILVERMONT2: /* AVN */ pkg_cstate_limits = slv_pkg_cstate_limits; break; case INTEL_FAM6_ATOM_AIRMONT: /* AMT */ pkg_cstate_limits = amt_pkg_cstate_limits; + no_MSR_MISC_PWR_MGMT = 1; break; case INTEL_FAM6_XEON_PHI_KNL: /* PHI */ case INTEL_FAM6_XEON_PHI_KNM: pkg_cstate_limits = phi_pkg_cstate_limits; break; case INTEL_FAM6_ATOM_GOLDMONT: /* BXT */ + case INTEL_FAM6_ATOM_GEMINI_LAKE: case INTEL_FAM6_ATOM_DENVERTON: /* DNV */ pkg_cstate_limits = bxt_pkg_cstate_limits; break; default: return 0; } - get_msr(base_cpu, MSR_NHM_SNB_PKG_CST_CFG_CTL, &msr); + get_msr(base_cpu, MSR_PKG_CST_CONFIG_CONTROL, &msr); pkg_cstate_limit = pkg_cstate_limits[msr & 0xF]; get_msr(base_cpu, MSR_PLATFORM_INFO, &msr); @@ -2368,8 +2734,69 @@ int probe_nhm_msrs(unsigned int family, unsigned int model) has_base_hz = 1; return 1; } -int has_nhm_turbo_ratio_limit(unsigned int family, unsigned int model) +/* + * SLV client has support for unique MSRs: + * + * MSR_CC6_DEMOTION_POLICY_CONFIG + * MSR_MC6_DEMOTION_POLICY_CONFIG + */ + +int has_slv_msrs(unsigned int family, unsigned int model) { + if (!genuine_intel) + return 0; + + switch (model) { + case INTEL_FAM6_ATOM_SILVERMONT1: + case INTEL_FAM6_ATOM_MERRIFIELD: + case INTEL_FAM6_ATOM_MOOREFIELD: + return 1; + } + return 0; +} +int is_dnv(unsigned int family, unsigned int model) +{ + + if (!genuine_intel) + return 0; + + switch (model) { + case INTEL_FAM6_ATOM_DENVERTON: + return 1; + } + return 0; +} +int is_bdx(unsigned int family, unsigned int model) +{ + + if (!genuine_intel) + return 0; + + switch (model) { + case INTEL_FAM6_BROADWELL_X: + case INTEL_FAM6_BROADWELL_XEON_D: + return 1; + } + return 0; +} +int is_skx(unsigned int family, unsigned int model) +{ + + if (!genuine_intel) + return 0; + + switch (model) { + case INTEL_FAM6_SKYLAKE_X: + return 1; + } + return 0; +} + +int has_turbo_ratio_limit(unsigned int family, unsigned int model) +{ + if (has_slv_msrs(family, model)) + return 0; + switch (model) { /* Nehalem compatible, but do not include turbo-ratio limit support */ case INTEL_FAM6_NEHALEM_EX: /* Nehalem-EX Xeon - Beckton */ @@ -2381,6 +2808,13 @@ int has_nhm_turbo_ratio_limit(unsigned int family, unsigned int model) return 1; } } +int has_atom_turbo_ratio_limit(unsigned int family, unsigned int model) +{ + if (has_slv_msrs(family, model)) + return 1; + + return 0; +} int has_ivt_turbo_ratio_limit(unsigned int family, unsigned int model) { if (!genuine_intel) @@ -2429,6 +2863,22 @@ int has_knl_turbo_ratio_limit(unsigned int family, unsigned int model) return 0; } } +int has_glm_turbo_ratio_limit(unsigned int family, unsigned int model) +{ + if (!genuine_intel) + return 0; + + if (family != 6) + return 0; + + switch (model) { + case INTEL_FAM6_ATOM_GOLDMONT: + case INTEL_FAM6_SKYLAKE_X: + return 1; + default: + return 0; + } +} int has_config_tdp(unsigned int family, unsigned int model) { if (!genuine_intel) @@ -2475,8 +2925,11 @@ dump_cstate_pstate_config_info(unsigned int family, unsigned int model) if (has_ivt_turbo_ratio_limit(family, model)) dump_ivt_turbo_ratio_limits(); - if (has_nhm_turbo_ratio_limit(family, model)) - dump_nhm_turbo_ratio_limits(); + if (has_turbo_ratio_limit(family, model)) + dump_turbo_ratio_limits(family, model); + + if (has_atom_turbo_ratio_limit(family, model)) + dump_atom_turbo_ratio_limits(); if (has_knl_turbo_ratio_limit(family, model)) dump_knl_turbo_ratio_limits(); @@ -2487,6 +2940,96 @@ dump_cstate_pstate_config_info(unsigned int family, unsigned int model) dump_nhm_cst_cfg(); } +static void +dump_sysfs_cstate_config(void) +{ + char path[64]; + char name_buf[16]; + char desc[64]; + FILE *input; + int state; + char *sp; + + if (!DO_BIC(BIC_sysfs)) + return; + + for (state = 0; state < 10; ++state) { + + sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/name", + base_cpu, state); + input = fopen(path, "r"); + if (input == NULL) + continue; + fgets(name_buf, sizeof(name_buf), input); + + /* truncate "C1-HSW\n" to "C1", or truncate "C1\n" to "C1" */ + sp = strchr(name_buf, '-'); + if (!sp) + sp = strchrnul(name_buf, '\n'); + *sp = '\0'; + + fclose(input); + + sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/desc", + base_cpu, state); + input = fopen(path, "r"); + if (input == NULL) + continue; + fgets(desc, sizeof(desc), input); + + fprintf(outf, "cpu%d: %s: %s", base_cpu, name_buf, desc); + fclose(input); + } +} +static void +dump_sysfs_pstate_config(void) +{ + char path[64]; + char driver_buf[64]; + char governor_buf[64]; + FILE *input; + int turbo; + + sprintf(path, "/sys/devices/system/cpu/cpu%d/cpufreq/scaling_driver", + base_cpu); + input = fopen(path, "r"); + if (input == NULL) { + fprintf(stderr, "NSFOD %s\n", path); + return; + } + fgets(driver_buf, sizeof(driver_buf), input); + fclose(input); + + sprintf(path, "/sys/devices/system/cpu/cpu%d/cpufreq/scaling_governor", + base_cpu); + input = fopen(path, "r"); + if (input == NULL) { + fprintf(stderr, "NSFOD %s\n", path); + return; + } + fgets(governor_buf, sizeof(governor_buf), input); + fclose(input); + + fprintf(outf, "cpu%d: cpufreq driver: %s", base_cpu, driver_buf); + fprintf(outf, "cpu%d: cpufreq governor: %s", base_cpu, governor_buf); + + sprintf(path, "/sys/devices/system/cpu/cpufreq/boost"); + input = fopen(path, "r"); + if (input != NULL) { + fscanf(input, "%d", &turbo); + fprintf(outf, "cpufreq boost: %d\n", turbo); + fclose(input); + } + + sprintf(path, "/sys/devices/system/cpu/intel_pstate/no_turbo"); + input = fopen(path, "r"); + if (input != NULL) { + fscanf(input, "%d", &turbo); + fprintf(outf, "cpufreq intel_pstate no_turbo: %d\n", turbo); + fclose(input); + } +} + /* * print_epb() @@ -2570,7 +3113,7 @@ int print_hwp(struct thread_data *t, struct core_data *c, struct pkg_data *p) return 0; fprintf(outf, "cpu%d: MSR_HWP_CAPABILITIES: 0x%08llx " - "(high 0x%x guar 0x%x eff 0x%x low 0x%x)\n", + "(high %d guar %d eff %d low %d)\n", cpu, msr, (unsigned int)HWP_HIGHEST_PERF(msr), (unsigned int)HWP_GUARANTEED_PERF(msr), @@ -2581,7 +3124,7 @@ int print_hwp(struct thread_data *t, struct core_data *c, struct pkg_data *p) return 0; fprintf(outf, "cpu%d: MSR_HWP_REQUEST: 0x%08llx " - "(min 0x%x max 0x%x des 0x%x epp 0x%x window 0x%x pkg 0x%x)\n", + "(min %d max %d des %d epp 0x%x window 0x%x pkg 0x%x)\n", cpu, msr, (unsigned int)(((msr) >> 0) & 0xff), (unsigned int)(((msr) >> 8) & 0xff), @@ -2595,7 +3138,7 @@ int print_hwp(struct thread_data *t, struct core_data *c, struct pkg_data *p) return 0; fprintf(outf, "cpu%d: MSR_HWP_REQUEST_PKG: 0x%08llx " - "(min 0x%x max 0x%x des 0x%x epp 0x%x window 0x%x)\n", + "(min %d max %d des %d epp 0x%x window 0x%x)\n", cpu, msr, (unsigned int)(((msr) >> 0) & 0xff), (unsigned int)(((msr) >> 8) & 0xff), @@ -2790,15 +3333,42 @@ void rapl_probe(unsigned int family, unsigned int model) case INTEL_FAM6_BROADWELL_CORE: /* BDW */ case INTEL_FAM6_BROADWELL_GT3E: /* BDW */ do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_GFX | RAPL_PKG_POWER_INFO; + if (rapl_joules) { + BIC_PRESENT(BIC_Pkg_J); + BIC_PRESENT(BIC_Cor_J); + BIC_PRESENT(BIC_GFX_J); + } else { + BIC_PRESENT(BIC_PkgWatt); + BIC_PRESENT(BIC_CorWatt); + BIC_PRESENT(BIC_GFXWatt); + } break; case INTEL_FAM6_ATOM_GOLDMONT: /* BXT */ + case INTEL_FAM6_ATOM_GEMINI_LAKE: do_rapl = RAPL_PKG | RAPL_PKG_POWER_INFO; + if (rapl_joules) + BIC_PRESENT(BIC_Pkg_J); + else + BIC_PRESENT(BIC_PkgWatt); break; case INTEL_FAM6_SKYLAKE_MOBILE: /* SKL */ case INTEL_FAM6_SKYLAKE_DESKTOP: /* SKL */ case INTEL_FAM6_KABYLAKE_MOBILE: /* KBL */ case INTEL_FAM6_KABYLAKE_DESKTOP: /* KBL */ - do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO; + do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_GFX | RAPL_PKG_POWER_INFO; + BIC_PRESENT(BIC_PKG__); + BIC_PRESENT(BIC_RAM__); + if (rapl_joules) { + BIC_PRESENT(BIC_Pkg_J); + BIC_PRESENT(BIC_Cor_J); + BIC_PRESENT(BIC_RAM_J); + BIC_PRESENT(BIC_GFX_J); + } else { + BIC_PRESENT(BIC_PkgWatt); + BIC_PRESENT(BIC_CorWatt); + BIC_PRESENT(BIC_RAMWatt); + BIC_PRESENT(BIC_GFXWatt); + } break; case INTEL_FAM6_HASWELL_X: /* HSX */ case INTEL_FAM6_BROADWELL_X: /* BDX */ @@ -2807,17 +3377,55 @@ void rapl_probe(unsigned int family, unsigned int model) case INTEL_FAM6_XEON_PHI_KNL: /* KNL */ case INTEL_FAM6_XEON_PHI_KNM: do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_POWER_INFO | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO; + BIC_PRESENT(BIC_PKG__); + BIC_PRESENT(BIC_RAM__); + if (rapl_joules) { + BIC_PRESENT(BIC_Pkg_J); + BIC_PRESENT(BIC_RAM_J); + } else { + BIC_PRESENT(BIC_PkgWatt); + BIC_PRESENT(BIC_RAMWatt); + } break; case INTEL_FAM6_SANDYBRIDGE_X: case INTEL_FAM6_IVYBRIDGE_X: do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_DRAM_POWER_INFO | RAPL_PKG_PERF_STATUS | RAPL_DRAM_PERF_STATUS | RAPL_PKG_POWER_INFO; + BIC_PRESENT(BIC_PKG__); + BIC_PRESENT(BIC_RAM__); + if (rapl_joules) { + BIC_PRESENT(BIC_Pkg_J); + BIC_PRESENT(BIC_Cor_J); + BIC_PRESENT(BIC_RAM_J); + } else { + BIC_PRESENT(BIC_PkgWatt); + BIC_PRESENT(BIC_CorWatt); + BIC_PRESENT(BIC_RAMWatt); + } break; case INTEL_FAM6_ATOM_SILVERMONT1: /* BYT */ case INTEL_FAM6_ATOM_SILVERMONT2: /* AVN */ do_rapl = RAPL_PKG | RAPL_CORES; + if (rapl_joules) { + BIC_PRESENT(BIC_Pkg_J); + BIC_PRESENT(BIC_Cor_J); + } else { + BIC_PRESENT(BIC_PkgWatt); + BIC_PRESENT(BIC_CorWatt); + } break; case INTEL_FAM6_ATOM_DENVERTON: /* DNV */ do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_POWER_INFO | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO | RAPL_CORES_ENERGY_STATUS; + BIC_PRESENT(BIC_PKG__); + BIC_PRESENT(BIC_RAM__); + if (rapl_joules) { + BIC_PRESENT(BIC_Pkg_J); + BIC_PRESENT(BIC_Cor_J); + BIC_PRESENT(BIC_RAM_J); + } else { + BIC_PRESENT(BIC_PkgWatt); + BIC_PRESENT(BIC_CorWatt); + BIC_PRESENT(BIC_RAMWatt); + } break; default: return; @@ -2844,7 +3452,7 @@ void rapl_probe(unsigned int family, unsigned int model) tdp = get_tdp(model); rapl_joule_counter_range = 0xFFFFFFFF * rapl_energy_units / tdp; - if (debug) + if (!quiet) fprintf(outf, "RAPL: %.0f sec. Joule Counter Range, at %.0f Watts\n", rapl_joule_counter_range, tdp); return; @@ -2874,7 +3482,7 @@ void perf_limit_reasons_probe(unsigned int family, unsigned int model) int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p) { unsigned long long msr; - unsigned int dts; + unsigned int dts, dts2; int cpu; if (!(do_dts || do_ptm)) @@ -2899,7 +3507,6 @@ int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p fprintf(outf, "cpu%d: MSR_IA32_PACKAGE_THERM_STATUS: 0x%08llx (%d C)\n", cpu, msr, tcc_activation_temp - dts); -#ifdef THERM_DEBUG if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT, &msr)) return 0; @@ -2907,11 +3514,10 @@ int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p dts2 = (msr >> 8) & 0x7F; fprintf(outf, "cpu%d: MSR_IA32_PACKAGE_THERM_INTERRUPT: 0x%08llx (%d C, %d C)\n", cpu, msr, tcc_activation_temp - dts, tcc_activation_temp - dts2); -#endif } - if (do_dts) { + if (do_dts && debug) { unsigned int resolution; if (get_msr(cpu, MSR_IA32_THERM_STATUS, &msr)) @@ -2922,7 +3528,6 @@ int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p fprintf(outf, "cpu%d: MSR_IA32_THERM_STATUS: 0x%08llx (%d C +/- %d)\n", cpu, msr, tcc_activation_temp - dts, resolution); -#ifdef THERM_DEBUG if (get_msr(cpu, MSR_IA32_THERM_INTERRUPT, &msr)) return 0; @@ -2930,7 +3535,6 @@ int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p dts2 = (msr >> 8) & 0x7F; fprintf(outf, "cpu%d: MSR_IA32_THERM_INTERRUPT: 0x%08llx (%d C, %d C)\n", cpu, msr, tcc_activation_temp - dts, tcc_activation_temp - dts2); -#endif } return 0; @@ -2969,11 +3573,9 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p) if (get_msr(cpu, MSR_RAPL_POWER_UNIT, &msr)) return -1; - if (debug) { - fprintf(outf, "cpu%d: MSR_RAPL_POWER_UNIT: 0x%08llx " - "(%f Watts, %f Joules, %f sec.)\n", cpu, msr, - rapl_power_units, rapl_energy_units, rapl_time_units); - } + fprintf(outf, "cpu%d: MSR_RAPL_POWER_UNIT: 0x%08llx (%f Watts, %f Joules, %f sec.)\n", cpu, msr, + rapl_power_units, rapl_energy_units, rapl_time_units); + if (do_rapl & RAPL_PKG_POWER_INFO) { if (get_msr(cpu, MSR_PKG_POWER_INFO, &msr)) @@ -2994,7 +3596,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p) return -9; fprintf(outf, "cpu%d: MSR_PKG_POWER_LIMIT: 0x%08llx (%slocked)\n", - cpu, msr, (msr >> 63) & 1 ? "": "UN"); + cpu, msr, (msr >> 63) & 1 ? "" : "UN"); print_power_limit_msr(cpu, msr, "PKG Limit #1"); fprintf(outf, "cpu%d: PKG Limit #2: %sabled (%f Watts, %f* sec, clamp %sabled)\n", @@ -3020,40 +3622,34 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p) if (get_msr(cpu, MSR_DRAM_POWER_LIMIT, &msr)) return -9; fprintf(outf, "cpu%d: MSR_DRAM_POWER_LIMIT: 0x%08llx (%slocked)\n", - cpu, msr, (msr >> 31) & 1 ? "": "UN"); + cpu, msr, (msr >> 31) & 1 ? "" : "UN"); print_power_limit_msr(cpu, msr, "DRAM Limit"); } if (do_rapl & RAPL_CORE_POLICY) { - if (debug) { - if (get_msr(cpu, MSR_PP0_POLICY, &msr)) - return -7; + if (get_msr(cpu, MSR_PP0_POLICY, &msr)) + return -7; - fprintf(outf, "cpu%d: MSR_PP0_POLICY: %lld\n", cpu, msr & 0xF); - } + fprintf(outf, "cpu%d: MSR_PP0_POLICY: %lld\n", cpu, msr & 0xF); } if (do_rapl & RAPL_CORES_POWER_LIMIT) { - if (debug) { - if (get_msr(cpu, MSR_PP0_POWER_LIMIT, &msr)) - return -9; - fprintf(outf, "cpu%d: MSR_PP0_POWER_LIMIT: 0x%08llx (%slocked)\n", - cpu, msr, (msr >> 31) & 1 ? "": "UN"); - print_power_limit_msr(cpu, msr, "Cores Limit"); - } + if (get_msr(cpu, MSR_PP0_POWER_LIMIT, &msr)) + return -9; + fprintf(outf, "cpu%d: MSR_PP0_POWER_LIMIT: 0x%08llx (%slocked)\n", + cpu, msr, (msr >> 31) & 1 ? "" : "UN"); + print_power_limit_msr(cpu, msr, "Cores Limit"); } if (do_rapl & RAPL_GFX) { - if (debug) { - if (get_msr(cpu, MSR_PP1_POLICY, &msr)) - return -8; + if (get_msr(cpu, MSR_PP1_POLICY, &msr)) + return -8; - fprintf(outf, "cpu%d: MSR_PP1_POLICY: %lld\n", cpu, msr & 0xF); + fprintf(outf, "cpu%d: MSR_PP1_POLICY: %lld\n", cpu, msr & 0xF); - if (get_msr(cpu, MSR_PP1_POWER_LIMIT, &msr)) - return -9; - fprintf(outf, "cpu%d: MSR_PP1_POWER_LIMIT: 0x%08llx (%slocked)\n", - cpu, msr, (msr >> 31) & 1 ? "": "UN"); - print_power_limit_msr(cpu, msr, "GFX Limit"); - } + if (get_msr(cpu, MSR_PP1_POWER_LIMIT, &msr)) + return -9; + fprintf(outf, "cpu%d: MSR_PP1_POWER_LIMIT: 0x%08llx (%slocked)\n", + cpu, msr, (msr >> 31) & 1 ? "" : "UN"); + print_power_limit_msr(cpu, msr, "GFX Limit"); } return 0; } @@ -3090,6 +3686,7 @@ int has_snb_msrs(unsigned int family, unsigned int model) case INTEL_FAM6_KABYLAKE_DESKTOP: /* KBL */ case INTEL_FAM6_SKYLAKE_X: /* SKX */ case INTEL_FAM6_ATOM_GOLDMONT: /* BXT */ + case INTEL_FAM6_ATOM_GEMINI_LAKE: case INTEL_FAM6_ATOM_DENVERTON: /* DNV */ return 1; } @@ -3121,6 +3718,7 @@ int has_hsw_msrs(unsigned int family, unsigned int model) case INTEL_FAM6_KABYLAKE_MOBILE: /* KBL */ case INTEL_FAM6_KABYLAKE_DESKTOP: /* KBL */ case INTEL_FAM6_ATOM_GOLDMONT: /* BXT */ + case INTEL_FAM6_ATOM_GEMINI_LAKE: return 1; } return 0; @@ -3149,8 +3747,6 @@ int has_skl_msrs(unsigned int family, unsigned int model) return 0; } - - int is_slm(unsigned int family, unsigned int model) { if (!genuine_intel) @@ -3201,7 +3797,8 @@ double slm_bclk(void) } freq = slm_freq_table[i]; - fprintf(outf, "SLM BCLK: %.1f Mhz\n", freq); + if (!quiet) + fprintf(outf, "SLM BCLK: %.1f Mhz\n", freq); return freq; } @@ -3264,7 +3861,7 @@ int set_temperature_target(struct thread_data *t, struct core_data *c, struct pk target_c_local = (msr >> 16) & 0xFF; - if (debug) + if (!quiet) fprintf(outf, "cpu%d: MSR_IA32_TEMPERATURE_TARGET: 0x%08llx (%d C)\n", cpu, msr, target_c_local); @@ -3299,13 +3896,30 @@ void decode_misc_enable_msr(void) unsigned long long msr; if (!get_msr(base_cpu, MSR_IA32_MISC_ENABLE, &msr)) - fprintf(outf, "cpu%d: MSR_IA32_MISC_ENABLE: 0x%08llx (%s %s %s)\n", + fprintf(outf, "cpu%d: MSR_IA32_MISC_ENABLE: 0x%08llx (%sTCC %sEIST %sMWAIT %sPREFETCH %sTURBO)\n", base_cpu, msr, - msr & (1 << 3) ? "TCC" : "", - msr & (1 << 16) ? "EIST" : "", - msr & (1 << 18) ? "MONITOR" : ""); + msr & MSR_IA32_MISC_ENABLE_TM1 ? "" : "No-", + msr & MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP ? "" : "No-", + msr & MSR_IA32_MISC_ENABLE_MWAIT ? "No-" : "", + msr & MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE ? "No-" : "", + msr & MSR_IA32_MISC_ENABLE_TURBO_DISABLE ? "No-" : ""); } +void decode_misc_feature_control(void) +{ + unsigned long long msr; + + if (!has_misc_feature_control) + return; + + if (!get_msr(base_cpu, MSR_MISC_FEATURE_CONTROL, &msr)) + fprintf(outf, "cpu%d: MSR_MISC_FEATURE_CONTROL: 0x%08llx (%sL2-Prefetch %sL2-Prefetch-pair %sL1-Prefetch %sL1-IP-Prefetch)\n", + base_cpu, msr, + msr & (0 << 0) ? "No-" : "", + msr & (1 << 0) ? "No-" : "", + msr & (2 << 0) ? "No-" : "", + msr & (3 << 0) ? "No-" : ""); +} /* * Decode MSR_MISC_PWR_MGMT * @@ -3320,6 +3934,9 @@ void decode_misc_pwr_mgmt_msr(void) if (!do_nhm_platform_info) return; + if (no_MSR_MISC_PWR_MGMT) + return; + if (!get_msr(base_cpu, MSR_MISC_PWR_MGMT, &msr)) fprintf(outf, "cpu%d: MSR_MISC_PWR_MGMT: 0x%08llx (%sable-EIST_Coordination %sable-EPB %sable-OOB)\n", base_cpu, msr, @@ -3327,11 +3944,30 @@ void decode_misc_pwr_mgmt_msr(void) msr & (1 << 1) ? "EN" : "DIS", msr & (1 << 8) ? "EN" : "DIS"); } +/* + * Decode MSR_CC6_DEMOTION_POLICY_CONFIG, MSR_MC6_DEMOTION_POLICY_CONFIG + * + * This MSRs are present on Silvermont processors, + * Intel Atom processor E3000 series (Baytrail), and friends. + */ +void decode_c6_demotion_policy_msr(void) +{ + unsigned long long msr; + + if (!get_msr(base_cpu, MSR_CC6_DEMOTION_POLICY_CONFIG, &msr)) + fprintf(outf, "cpu%d: MSR_CC6_DEMOTION_POLICY_CONFIG: 0x%08llx (%sable-CC6-Demotion)\n", + base_cpu, msr, msr & (1 << 0) ? "EN" : "DIS"); + + if (!get_msr(base_cpu, MSR_MC6_DEMOTION_POLICY_CONFIG, &msr)) + fprintf(outf, "cpu%d: MSR_MC6_DEMOTION_POLICY_CONFIG: 0x%08llx (%sable-MC6-Demotion)\n", + base_cpu, msr, msr & (1 << 0) ? "EN" : "DIS"); +} void process_cpuid() { unsigned int eax, ebx, ecx, edx, max_level, max_extended_level; unsigned int fms, family, model, stepping; + unsigned int has_turbo; eax = ebx = ecx = edx = 0; @@ -3340,7 +3976,7 @@ void process_cpuid() if (ebx == 0x756e6547 && edx == 0x49656e69 && ecx == 0x6c65746e) genuine_intel = 1; - if (debug) + if (!quiet) fprintf(outf, "CPUID(0): %.4s%.4s%.4s ", (char *)&ebx, (char *)&edx, (char *)&ecx); @@ -3351,7 +3987,7 @@ void process_cpuid() if (family == 6 || family == 0xf) model += ((fms >> 16) & 0xf) << 4; - if (debug) { + if (!quiet) { fprintf(outf, "%d CPUID levels; family:model:stepping 0x%x:%x:%x (%d:%d:%d)\n", max_level, family, model, stepping, family, model, stepping); fprintf(outf, "CPUID(1): %s %s %s %s %s %s %s %s %s\n", @@ -3394,8 +4030,18 @@ void process_cpuid() __cpuid(0x6, eax, ebx, ecx, edx); has_aperf = ecx & (1 << 0); + if (has_aperf) { + BIC_PRESENT(BIC_Avg_MHz); + BIC_PRESENT(BIC_Busy); + BIC_PRESENT(BIC_Bzy_MHz); + } do_dts = eax & (1 << 0); + if (do_dts) + BIC_PRESENT(BIC_CoreTmp); + has_turbo = eax & (1 << 1); do_ptm = eax & (1 << 6); + if (do_ptm) + BIC_PRESENT(BIC_PkgTmp); has_hwp = eax & (1 << 7); has_hwp_notify = eax & (1 << 8); has_hwp_activity_window = eax & (1 << 9); @@ -3403,10 +4049,11 @@ void process_cpuid() has_hwp_pkg = eax & (1 << 11); has_epb = ecx & (1 << 3); - if (debug) - fprintf(outf, "CPUID(6): %sAPERF, %sDTS, %sPTM, %sHWP, " + if (!quiet) + fprintf(outf, "CPUID(6): %sAPERF, %sTURBO, %sDTS, %sPTM, %sHWP, " "%sHWPnotify, %sHWPwindow, %sHWPepp, %sHWPpkg, %sEPB\n", has_aperf ? "" : "No-", + has_turbo ? "" : "No-", do_dts ? "" : "No-", do_ptm ? "" : "No-", has_hwp ? "" : "No-", @@ -3416,10 +4063,11 @@ void process_cpuid() has_hwp_pkg ? "" : "No-", has_epb ? "" : "No-"); - if (debug) + if (!quiet) decode_misc_enable_msr(); - if (max_level >= 0x7 && debug) { + + if (max_level >= 0x7 && !quiet) { int has_sgx; ecx = 0; @@ -3445,7 +4093,7 @@ void process_cpuid() if (ebx_tsc != 0) { - if (debug && (ebx != 0)) + if (!quiet && (ebx != 0)) fprintf(outf, "CPUID(0x15): eax_crystal: %d ebx_tsc: %d ecx_crystal_hz: %d\n", eax_crystal, ebx_tsc, crystal_hz); @@ -3462,6 +4110,7 @@ void process_cpuid() crystal_hz = 25000000; /* 25.0 MHz */ break; case INTEL_FAM6_ATOM_GOLDMONT: /* BXT */ + case INTEL_FAM6_ATOM_GEMINI_LAKE: crystal_hz = 19200000; /* 19.2 MHz */ break; default: @@ -3470,7 +4119,7 @@ void process_cpuid() if (crystal_hz) { tsc_hz = (unsigned long long) crystal_hz * ebx_tsc / eax_crystal; - if (debug) + if (!quiet) fprintf(outf, "TSC: %lld MHz (%d Hz * %d / %d / 1000000)\n", tsc_hz / 1000000, crystal_hz, ebx_tsc, eax_crystal); } @@ -3485,7 +4134,7 @@ void process_cpuid() base_mhz = max_mhz = bus_mhz = edx = 0; __cpuid(0x16, base_mhz, max_mhz, bus_mhz, edx); - if (debug) + if (!quiet) fprintf(outf, "CPUID(0x16): base_mhz: %d max_mhz: %d bus_mhz: %d\n", base_mhz, max_mhz, bus_mhz); } @@ -3493,56 +4142,96 @@ void process_cpuid() if (has_aperf) aperf_mperf_multiplier = get_aperf_mperf_multiplier(family, model); - do_nhm_platform_info = do_nhm_cstates = do_smi = probe_nhm_msrs(family, model); + BIC_PRESENT(BIC_IRQ); + BIC_PRESENT(BIC_TSC_MHz); + + if (probe_nhm_msrs(family, model)) { + do_nhm_platform_info = 1; + BIC_PRESENT(BIC_CPU_c1); + BIC_PRESENT(BIC_CPU_c3); + BIC_PRESENT(BIC_CPU_c6); + BIC_PRESENT(BIC_SMI); + } do_snb_cstates = has_snb_msrs(family, model); + + if (do_snb_cstates) + BIC_PRESENT(BIC_CPU_c7); + do_irtl_snb = has_snb_msrs(family, model); - do_pc2 = do_snb_cstates && (pkg_cstate_limit >= PCL__2); - do_pc3 = (pkg_cstate_limit >= PCL__3); - do_pc6 = (pkg_cstate_limit >= PCL__6); - do_pc7 = do_snb_cstates && (pkg_cstate_limit >= PCL__7); - do_c8_c9_c10 = has_hsw_msrs(family, model); + if (do_snb_cstates && (pkg_cstate_limit >= PCL__2)) + BIC_PRESENT(BIC_Pkgpc2); + if (pkg_cstate_limit >= PCL__3) + BIC_PRESENT(BIC_Pkgpc3); + if (pkg_cstate_limit >= PCL__6) + BIC_PRESENT(BIC_Pkgpc6); + if (do_snb_cstates && (pkg_cstate_limit >= PCL__7)) + BIC_PRESENT(BIC_Pkgpc7); + if (has_slv_msrs(family, model)) { + BIC_NOT_PRESENT(BIC_Pkgpc2); + BIC_NOT_PRESENT(BIC_Pkgpc3); + BIC_PRESENT(BIC_Pkgpc6); + BIC_NOT_PRESENT(BIC_Pkgpc7); + BIC_PRESENT(BIC_Mod_c6); + use_c1_residency_msr = 1; + } + if (is_dnv(family, model)) { + BIC_PRESENT(BIC_CPU_c1); + BIC_NOT_PRESENT(BIC_CPU_c3); + BIC_NOT_PRESENT(BIC_Pkgpc3); + BIC_NOT_PRESENT(BIC_CPU_c7); + BIC_NOT_PRESENT(BIC_Pkgpc7); + use_c1_residency_msr = 1; + } + if (is_skx(family, model)) { + BIC_NOT_PRESENT(BIC_CPU_c3); + BIC_NOT_PRESENT(BIC_Pkgpc3); + BIC_NOT_PRESENT(BIC_CPU_c7); + BIC_NOT_PRESENT(BIC_Pkgpc7); + } + if (is_bdx(family, model)) { + BIC_NOT_PRESENT(BIC_CPU_c7); + BIC_NOT_PRESENT(BIC_Pkgpc7); + } + if (has_hsw_msrs(family, model)) { + BIC_PRESENT(BIC_Pkgpc8); + BIC_PRESENT(BIC_Pkgpc9); + BIC_PRESENT(BIC_Pkgpc10); + } do_irtl_hsw = has_hsw_msrs(family, model); do_skl_residency = has_skl_msrs(family, model); do_slm_cstates = is_slm(family, model); do_knl_cstates = is_knl(family, model); - if (debug) + if (!quiet) decode_misc_pwr_mgmt_msr(); + if (!quiet && has_slv_msrs(family, model)) + decode_c6_demotion_policy_msr(); + rapl_probe(family, model); perf_limit_reasons_probe(family, model); - if (debug) + if (!quiet) dump_cstate_pstate_config_info(family, model); + if (!quiet) + dump_sysfs_cstate_config(); + if (!quiet) + dump_sysfs_pstate_config(); + if (has_skl_msrs(family, model)) calculate_tsc_tweak(); - do_gfx_rc6_ms = !access("/sys/class/drm/card0/power/rc6_residency_ms", R_OK); + if (!access("/sys/class/drm/card0/power/rc6_residency_ms", R_OK)) + BIC_PRESENT(BIC_GFX_rc6); - do_gfx_mhz = !access("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", R_OK); + if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", R_OK)) + BIC_PRESENT(BIC_GFXMHz); - return; -} + if (!quiet) + decode_misc_feature_control(); -void help() -{ - fprintf(outf, - "Usage: turbostat [OPTIONS][(--interval seconds) | COMMAND ...]\n" - "\n" - "Turbostat forks the specified COMMAND and prints statistics\n" - "when COMMAND completes.\n" - "If no COMMAND is specified, turbostat wakes every 5-seconds\n" - "to print statistics, until interrupted.\n" - "--add add a counter\n" - " eg. --add msr0x10,u64,cpu,delta,MY_TSC\n" - "--debug run in \"debug\" mode\n" - "--interval sec Override default 5-second measurement interval\n" - "--help print this help message\n" - "--out file create or truncate \"file\" for all output\n" - "--version print version information\n" - "\n" - "For more help, run \"man turbostat\"\n"); + return; } @@ -3579,7 +4268,7 @@ void topology_probe() topo.max_cpu_num = 0; for_all_proc_cpus(count_cpus); if (!summary_only && topo.num_cpus > 1) - show_cpu = 1; + BIC_PRESENT(BIC_CPU); if (debug > 1) fprintf(outf, "num_cpus %d max_cpu_num %d\n", topo.num_cpus, topo.max_cpu_num); @@ -3599,6 +4288,15 @@ void topology_probe() for_all_proc_cpus(mark_cpu_present); /* + * Validate that all cpus in cpu_subset are also in cpu_present_set + */ + for (i = 0; i < CPU_SUBSET_MAXCPUS; ++i) { + if (CPU_ISSET_S(i, cpu_subset_size, cpu_subset)) + if (!CPU_ISSET_S(i, cpu_present_setsize, cpu_present_set)) + err(1, "cpu%d not present", i); + } + + /* * Allocate and initialize cpu_affinity_set */ cpu_affinity_set = CPU_ALLOC((topo.max_cpu_num + 1)); @@ -3639,15 +4337,15 @@ void topology_probe() if (debug > 1) fprintf(outf, "max_core_id %d, sizing for %d cores per package\n", max_core_id, topo.num_cores_per_pkg); - if (debug && !summary_only && topo.num_cores_per_pkg > 1) - show_core = 1; + if (!summary_only && topo.num_cores_per_pkg > 1) + BIC_PRESENT(BIC_Core); topo.num_packages = max_package_id + 1; if (debug > 1) fprintf(outf, "max_package_id %d, sizing for %d packages\n", max_package_id, topo.num_packages); - if (debug && !summary_only && topo.num_packages > 1) - show_pkg = 1; + if (!summary_only && topo.num_packages > 1) + BIC_PRESENT(BIC_Package); topo.num_threads_per_core = max_siblings; if (debug > 1) @@ -3662,7 +4360,7 @@ allocate_counters(struct thread_data **t, struct core_data **c, struct pkg_data int i; *t = calloc(topo.num_threads_per_core * topo.num_cores_per_pkg * - topo.num_packages, sizeof(struct thread_data) + sys.thread_counter_bytes); + topo.num_packages, sizeof(struct thread_data)); if (*t == NULL) goto error; @@ -3671,14 +4369,14 @@ allocate_counters(struct thread_data **t, struct core_data **c, struct pkg_data (*t)[i].cpu_id = -1; *c = calloc(topo.num_cores_per_pkg * topo.num_packages, - sizeof(struct core_data) + sys.core_counter_bytes); + sizeof(struct core_data)); if (*c == NULL) goto error; for (i = 0; i < topo.num_cores_per_pkg * topo.num_packages; i++) (*c)[i].core_id = -1; - *p = calloc(topo.num_packages, sizeof(struct pkg_data) + sys.package_counter_bytes); + *p = calloc(topo.num_packages, sizeof(struct pkg_data)); if (*p == NULL) goto error; @@ -3789,24 +4487,24 @@ void turbostat_init() process_cpuid(); - if (debug) + if (!quiet) for_all_cpus(print_hwp, ODD_COUNTERS); - if (debug) + if (!quiet) for_all_cpus(print_epb, ODD_COUNTERS); - if (debug) + if (!quiet) for_all_cpus(print_perf_limit, ODD_COUNTERS); - if (debug) + if (!quiet) for_all_cpus(print_rapl, ODD_COUNTERS); for_all_cpus(set_temperature_target, ODD_COUNTERS); - if (debug) + if (!quiet) for_all_cpus(print_thermal, ODD_COUNTERS); - if (debug && do_irtl_snb) + if (!quiet && do_irtl_snb) print_irtl(); } @@ -3815,6 +4513,7 @@ int fork_it(char **argv) pid_t child_pid; int status; + snapshot_proc_sysfs_files(); status = for_all_cpus(get_counters, EVEN_COUNTERS); if (status) exit(status); @@ -3826,6 +4525,7 @@ int fork_it(char **argv) if (!child_pid) { /* child */ execvp(argv[0], argv); + err(errno, "exec %s", argv[0]); } else { /* parent */ @@ -3841,6 +4541,7 @@ int fork_it(char **argv) * n.b. fork_it() does not check for errors from for_all_cpus() * because re-starting is problematic when forking */ + snapshot_proc_sysfs_files(); for_all_cpus(get_counters, ODD_COUNTERS); gettimeofday(&tv_odd, (struct timezone *)NULL); timersub(&tv_odd, &tv_even, &tv_delta); @@ -3862,6 +4563,7 @@ int get_and_dump_counters(void) { int status; + snapshot_proc_sysfs_files(); status = for_all_cpus(get_counters, ODD_COUNTERS); if (status) return status; @@ -3876,13 +4578,13 @@ int get_and_dump_counters(void) } void print_version() { - fprintf(outf, "turbostat version 4.16 24 Dec 2016" + fprintf(outf, "turbostat version 17.04.12" " - Len Brown <lenb@kernel.org>\n"); } -int add_counter(unsigned int msr_num, char *name, unsigned int width, - enum counter_scope scope, enum counter_type type, - enum counter_format format) +int add_counter(unsigned int msr_num, char *path, char *name, + unsigned int width, enum counter_scope scope, + enum counter_type type, enum counter_format format, int flags) { struct msr_counter *msrp; @@ -3894,31 +4596,46 @@ int add_counter(unsigned int msr_num, char *name, unsigned int width, msrp->msr_num = msr_num; strncpy(msrp->name, name, NAME_BYTES); + if (path) + strncpy(msrp->path, path, PATH_BYTES); msrp->width = width; msrp->type = type; msrp->format = format; + msrp->flags = flags; switch (scope) { case SCOPE_CPU: - sys.thread_counter_bytes += 64; msrp->next = sys.tp; sys.tp = msrp; - sys.thread_counter_bytes += sizeof(unsigned long long); + sys.added_thread_counters++; + if (sys.added_thread_counters > MAX_ADDED_COUNTERS) { + fprintf(stderr, "exceeded max %d added thread counters\n", + MAX_ADDED_COUNTERS); + exit(-1); + } break; case SCOPE_CORE: - sys.core_counter_bytes += 64; msrp->next = sys.cp; sys.cp = msrp; - sys.core_counter_bytes += sizeof(unsigned long long); + sys.added_core_counters++; + if (sys.added_core_counters > MAX_ADDED_COUNTERS) { + fprintf(stderr, "exceeded max %d added core counters\n", + MAX_ADDED_COUNTERS); + exit(-1); + } break; case SCOPE_PACKAGE: - sys.package_counter_bytes += 64; msrp->next = sys.pp; sys.pp = msrp; - sys.package_counter_bytes += sizeof(unsigned long long); + sys.added_package_counters++; + if (sys.added_package_counters > MAX_ADDED_COUNTERS) { + fprintf(stderr, "exceeded max %d added package counters\n", + MAX_ADDED_COUNTERS); + exit(-1); + } break; } @@ -3928,7 +4645,8 @@ int add_counter(unsigned int msr_num, char *name, unsigned int width, void parse_add_command(char *add_command) { int msr_num = 0; - char name_buffer[NAME_BYTES]; + char *path = NULL; + char name_buffer[NAME_BYTES] = ""; int width = 64; int fail = 0; enum counter_scope scope = SCOPE_CPU; @@ -3943,6 +4661,11 @@ void parse_add_command(char *add_command) if (sscanf(add_command, "msr%d", &msr_num) == 1) goto next; + if (*add_command == '/') { + path = add_command; + goto next; + } + if (sscanf(add_command, "u%d", &width) == 1) { if ((width == 32) || (width == 64)) goto next; @@ -3968,6 +4691,10 @@ void parse_add_command(char *add_command) type = COUNTER_SECONDS; goto next; } + if (!strncmp(add_command, "usec", strlen("usec"))) { + type = COUNTER_USEC; + goto next; + } if (!strncmp(add_command, "raw", strlen("raw"))) { format = FORMAT_RAW; goto next; @@ -3992,36 +4719,26 @@ void parse_add_command(char *add_command) next: add_command = strchr(add_command, ','); - if (add_command) + if (add_command) { + *add_command = '\0'; add_command++; + } } - if (msr_num == 0) { - fprintf(stderr, "--add: (msrDDD | msr0xXXX) required\n"); + if ((msr_num == 0) && (path == NULL)) { + fprintf(stderr, "--add: (msrDDD | msr0xXXX | /path_to_counter ) required\n"); fail++; } /* generate default column header */ if (*name_buffer == '\0') { - if (format == FORMAT_RAW) { - if (width == 32) - sprintf(name_buffer, "msr%d", msr_num); - else - sprintf(name_buffer, "MSR%d", msr_num); - } else if (format == FORMAT_DELTA) { - if (width == 32) - sprintf(name_buffer, "cnt%d", msr_num); - else - sprintf(name_buffer, "CNT%d", msr_num); - } else if (format == FORMAT_PERCENT) { - if (width == 32) - sprintf(name_buffer, "msr%d%%", msr_num); - else - sprintf(name_buffer, "MSR%d%%", msr_num); - } + if (width == 32) + sprintf(name_buffer, "M0x%x%s", msr_num, format == FORMAT_PERCENT ? "%" : ""); + else + sprintf(name_buffer, "M0X%x%s", msr_num, format == FORMAT_PERCENT ? "%" : ""); } - if (add_counter(msr_num, name_buffer, width, scope, type, format)) + if (add_counter(msr_num, path, name_buffer, width, scope, type, format, 0)) fail++; if (fail) { @@ -4029,20 +4746,214 @@ next: exit(1); } } + +int is_deferred_skip(char *name) +{ + int i; + + for (i = 0; i < deferred_skip_index; ++i) + if (!strcmp(name, deferred_skip_names[i])) + return 1; + return 0; +} + +void probe_sysfs(void) +{ + char path[64]; + char name_buf[16]; + FILE *input; + int state; + char *sp; + + if (!DO_BIC(BIC_sysfs)) + return; + + for (state = 10; state > 0; --state) { + + sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/name", + base_cpu, state); + input = fopen(path, "r"); + if (input == NULL) + continue; + fgets(name_buf, sizeof(name_buf), input); + + /* truncate "C1-HSW\n" to "C1", or truncate "C1\n" to "C1" */ + sp = strchr(name_buf, '-'); + if (!sp) + sp = strchrnul(name_buf, '\n'); + *sp = '%'; + *(sp + 1) = '\0'; + + fclose(input); + + sprintf(path, "cpuidle/state%d/time", state); + + if (is_deferred_skip(name_buf)) + continue; + + add_counter(0, path, name_buf, 64, SCOPE_CPU, COUNTER_USEC, + FORMAT_PERCENT, SYSFS_PERCPU); + } + + for (state = 10; state > 0; --state) { + + sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/name", + base_cpu, state); + input = fopen(path, "r"); + if (input == NULL) + continue; + fgets(name_buf, sizeof(name_buf), input); + /* truncate "C1-HSW\n" to "C1", or truncate "C1\n" to "C1" */ + sp = strchr(name_buf, '-'); + if (!sp) + sp = strchrnul(name_buf, '\n'); + *sp = '\0'; + fclose(input); + + sprintf(path, "cpuidle/state%d/usage", state); + + if (is_deferred_skip(name_buf)) + continue; + + add_counter(0, path, name_buf, 64, SCOPE_CPU, COUNTER_ITEMS, + FORMAT_DELTA, SYSFS_PERCPU); + } + +} + + +/* + * parse cpuset with following syntax + * 1,2,4..6,8-10 and set bits in cpu_subset + */ +void parse_cpu_command(char *optarg) +{ + unsigned int start, end; + char *next; + + if (!strcmp(optarg, "core")) { + if (cpu_subset) + goto error; + show_core_only++; + return; + } + if (!strcmp(optarg, "package")) { + if (cpu_subset) + goto error; + show_pkg_only++; + return; + } + if (show_core_only || show_pkg_only) + goto error; + + cpu_subset = CPU_ALLOC(CPU_SUBSET_MAXCPUS); + if (cpu_subset == NULL) + err(3, "CPU_ALLOC"); + cpu_subset_size = CPU_ALLOC_SIZE(CPU_SUBSET_MAXCPUS); + + CPU_ZERO_S(cpu_subset_size, cpu_subset); + + next = optarg; + + while (next && *next) { + + if (*next == '-') /* no negative cpu numbers */ + goto error; + + start = strtoul(next, &next, 10); + + if (start >= CPU_SUBSET_MAXCPUS) + goto error; + CPU_SET_S(start, cpu_subset_size, cpu_subset); + + if (*next == '\0') + break; + + if (*next == ',') { + next += 1; + continue; + } + + if (*next == '-') { + next += 1; /* start range */ + } else if (*next == '.') { + next += 1; + if (*next == '.') + next += 1; /* start range */ + else + goto error; + } + + end = strtoul(next, &next, 10); + if (end <= start) + goto error; + + while (++start <= end) { + if (start >= CPU_SUBSET_MAXCPUS) + goto error; + CPU_SET_S(start, cpu_subset_size, cpu_subset); + } + + if (*next == ',') + next += 1; + else if (*next != '\0') + goto error; + } + + return; + +error: + fprintf(stderr, "\"--cpu %s\" malformed\n", optarg); + help(); + exit(-1); +} + +int shown; +/* + * parse_show_hide() - process cmdline to set default counter action + */ +void parse_show_hide(char *optarg, enum show_hide_mode new_mode) +{ + /* + * --show: show only those specified + * The 1st invocation will clear and replace the enabled mask + * subsequent invocations can add to it. + */ + if (new_mode == SHOW_LIST) { + if (shown == 0) + bic_enabled = bic_lookup(optarg, new_mode); + else + bic_enabled |= bic_lookup(optarg, new_mode); + shown = 1; + + return; + } + + /* + * --hide: do not show those specified + * multiple invocations simply clear more bits in enabled mask + */ + bic_enabled &= ~bic_lookup(optarg, new_mode); + +} + void cmdline(int argc, char **argv) { int opt; int option_index = 0; static struct option long_options[] = { {"add", required_argument, 0, 'a'}, + {"cpu", required_argument, 0, 'c'}, {"Dump", no_argument, 0, 'D'}, - {"debug", no_argument, 0, 'd'}, + {"debug", no_argument, 0, 'd'}, /* internal, not documented */ {"interval", required_argument, 0, 'i'}, {"help", no_argument, 0, 'h'}, + {"hide", required_argument, 0, 'H'}, // meh, -h taken by --help {"Joules", no_argument, 0, 'J'}, + {"list", no_argument, 0, 'l'}, {"out", required_argument, 0, 'o'}, - {"Package", no_argument, 0, 'p'}, - {"processor", no_argument, 0, 'p'}, + {"quiet", no_argument, 0, 'q'}, + {"show", required_argument, 0, 's'}, {"Summary", no_argument, 0, 'S'}, {"TCC", required_argument, 0, 'T'}, {"version", no_argument, 0, 'v' }, @@ -4051,18 +4962,24 @@ void cmdline(int argc, char **argv) progname = argv[0]; - while ((opt = getopt_long_only(argc, argv, "+C:c:Ddhi:JM:m:o:PpST:v", + while ((opt = getopt_long_only(argc, argv, "+C:c:Ddhi:JM:m:o:qST:v", long_options, &option_index)) != -1) { switch (opt) { case 'a': parse_add_command(optarg); break; + case 'c': + parse_cpu_command(optarg); + break; case 'D': dump_only++; break; case 'd': debug++; break; + case 'H': + parse_show_hide(optarg, HIDE_LIST); + break; case 'h': default: help(); @@ -4084,14 +5001,18 @@ void cmdline(int argc, char **argv) case 'J': rapl_joules++; break; + case 'l': + list_header_only++; + quiet++; + break; case 'o': outf = fopen_or_die(optarg, "w"); break; - case 'P': - show_pkg_only++; + case 'q': + quiet = 1; break; - case 'p': - show_core_only++; + case 's': + parse_show_hide(optarg, SHOW_LIST); break; case 'S': summary_only++; @@ -4113,15 +5034,24 @@ int main(int argc, char **argv) cmdline(argc, argv); - if (debug) + if (!quiet) print_version(); + probe_sysfs(); + turbostat_init(); /* dump counters and exit */ if (dump_only) return get_and_dump_counters(); + /* list header and exit */ + if (list_header_only) { + print_header(","); + flush_output_stdout(); + return 0; + } + /* * if any params left, it must be a command to fork */ diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include index 8abbef164b4e..fc74db62fef4 100644 --- a/tools/scripts/Makefile.include +++ b/tools/scripts/Makefile.include @@ -32,7 +32,6 @@ EXTRA_WARNINGS += -Wold-style-definition EXTRA_WARNINGS += -Wpacked EXTRA_WARNINGS += -Wredundant-decls EXTRA_WARNINGS += -Wshadow -EXTRA_WARNINGS += -Wstrict-aliasing=3 EXTRA_WARNINGS += -Wstrict-prototypes EXTRA_WARNINGS += -Wswitch-default EXTRA_WARNINGS += -Wswitch-enum @@ -40,12 +39,35 @@ EXTRA_WARNINGS += -Wundef EXTRA_WARNINGS += -Wwrite-strings EXTRA_WARNINGS += -Wformat +ifneq ($(CC), clang) +EXTRA_WARNINGS += -Wstrict-aliasing=3 +endif + +# Hack to avoid type-punned warnings on old systems such as RHEL5: +# We should be changing CFLAGS and checking gcc version, but this +# will do for now and keep the above -Wstrict-aliasing=3 in place +# in newer systems. +# Needed for the __raw_cmpxchg in tools/arch/x86/include/asm/cmpxchg.h +ifneq ($(filter 3.%,$(MAKE_VERSION)),) # make-3 +EXTRA_WARNINGS += -fno-strict-aliasing +endif + ifneq ($(findstring $(MAKEFLAGS), w),w) PRINT_DIR = --no-print-directory else NO_SUBDIR = : endif +ifneq ($(filter 4.%,$(MAKE_VERSION)),) # make-4 +ifneq ($(filter %s ,$(firstword x$(MAKEFLAGS))),) + silent=1 +endif +else # make-3.8x +ifneq ($(filter s% -s%,$(MAKEFLAGS)),) + silent=1 +endif +endif + # # Define a callable command for descending to a new directory # @@ -58,7 +80,7 @@ descend = \ QUIET_SUBDIR0 = +$(MAKE) $(COMMAND_O) -C # space to separate -C and subdir QUIET_SUBDIR1 = -ifneq ($(findstring $(MAKEFLAGS),s),s) +ifneq ($(silent),1) ifneq ($(V),1) QUIET_CC = @echo ' CC '$@; QUIET_CC_FPIC = @echo ' CC FPIC '$@; diff --git a/tools/spi/spidev_test.c b/tools/spi/spidev_test.c index 816f119c9b7b..8c590cd1171a 100644 --- a/tools/spi/spidev_test.c +++ b/tools/spi/spidev_test.c @@ -18,6 +18,7 @@ #include <string.h> #include <getopt.h> #include <fcntl.h> +#include <time.h> #include <sys/ioctl.h> #include <linux/ioctl.h> #include <sys/stat.h> @@ -40,6 +41,9 @@ static char *output_file; static uint32_t speed = 500000; static uint16_t delay; static int verbose; +static int transfer_size; +static int iterations; +static int interval = 5; /* interval in seconds for showing transfer rate */ uint8_t default_tx[] = { 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, @@ -156,13 +160,13 @@ static void transfer(int fd, uint8_t const *tx, uint8_t const *rx, size_t len) close(out_fd); } - if (verbose || !output_file) + if (verbose) hex_dump(rx, len, 32, "RX"); } static void print_usage(const char *prog) { - printf("Usage: %s [-DsbdlHOLC3]\n", 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" @@ -180,7 +184,9 @@ static void print_usage(const char *prog) " -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"); + " -4 --quad quad transfer\n" + " -S --size transfer size\n" + " -I --iter iterations\n"); exit(1); } @@ -205,11 +211,13 @@ static void parse_opts(int argc, char *argv[]) { "dual", 0, 0, '2' }, { "verbose", 0, 0, 'v' }, { "quad", 0, 0, '4' }, + { "size", 1, 0, 'S' }, + { "iter", 1, 0, 'I' }, { NULL, 0, 0, 0 }, }; int c; - c = getopt_long(argc, argv, "D:s:d:b:i:o:lHOLC3NR24p:v", + c = getopt_long(argc, argv, "D:s:d:b:i:o:lHOLC3NR24p:vS:I:", lopts, NULL); if (c == -1) @@ -270,6 +278,12 @@ static void parse_opts(int argc, char *argv[]) case '4': mode |= SPI_TX_QUAD; break; + case 'S': + transfer_size = atoi(optarg); + break; + case 'I': + iterations = atoi(optarg); + break; default: print_usage(argv[0]); break; @@ -336,6 +350,57 @@ static void transfer_file(int fd, char *filename) close(tx_fd); } +static uint64_t _read_count; +static uint64_t _write_count; + +static void show_transfer_rate(void) +{ + static uint64_t prev_read_count, prev_write_count; + double rx_rate, tx_rate; + + rx_rate = ((_read_count - prev_read_count) * 8) / (interval*1000.0); + tx_rate = ((_write_count - prev_write_count) * 8) / (interval*1000.0); + + printf("rate: tx %.1fkbps, rx %.1fkbps\n", rx_rate, tx_rate); + + prev_read_count = _read_count; + prev_write_count = _write_count; +} + +static void transfer_buf(int fd, int len) +{ + uint8_t *tx; + uint8_t *rx; + int i; + + tx = malloc(len); + if (!tx) + pabort("can't allocate tx buffer"); + for (i = 0; i < len; i++) + tx[i] = random(); + + rx = malloc(len); + if (!rx) + pabort("can't allocate rx buffer"); + + transfer(fd, tx, rx, len); + + _write_count += len; + _read_count += len; + + if (mode & SPI_LOOP) { + if (memcmp(tx, rx, len)) { + fprintf(stderr, "transfer error !\n"); + hex_dump(tx, len, 32, "TX"); + hex_dump(rx, len, 32, "RX"); + exit(1); + } + } + + free(rx); + free(tx); +} + int main(int argc, char *argv[]) { int ret = 0; @@ -391,7 +456,25 @@ int main(int argc, char *argv[]) transfer_escaped_string(fd, input_tx); else if (input_file) transfer_file(fd, input_file); - else + else if (transfer_size) { + struct timespec last_stat; + + clock_gettime(CLOCK_MONOTONIC, &last_stat); + + while (iterations-- > 0) { + struct timespec current; + + transfer_buf(fd, transfer_size); + + clock_gettime(CLOCK_MONOTONIC, ¤t); + if (current.tv_sec - last_stat.tv_sec > interval) { + show_transfer_rate(); + last_stat = current; + } + } + printf("total: tx %.1fKB, rx %.1fKB\n", + _write_count/1024.0, _read_count/1024.0); + } else transfer(fd, default_tx, default_rx, sizeof(default_tx)); close(fd); diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl index be93ab02b490..0c8b61f8398e 100755 --- a/tools/testing/ktest/ktest.pl +++ b/tools/testing/ktest/ktest.pl @@ -179,6 +179,7 @@ my $localversion; my $iteration = 0; my $successes = 0; my $stty_orig; +my $run_command_status = 0; my $bisect_good; my $bisect_bad; @@ -1325,26 +1326,44 @@ sub wait_for_monitor; sub reboot { my ($time) = @_; + my $powercycle = 0; - # Make sure everything has been written to disk - run_ssh("sync"); + # test if the machine can be connected to within 5 seconds + my $stat = run_ssh("echo check machine status", 5); + if (!$stat) { + doprint("power cycle\n"); + $powercycle = 1; + } + + if ($powercycle) { + run_command "$power_cycle"; - if (defined($time)) { start_monitor; # flush out current monitor # May contain the reboot success line wait_for_monitor 1; - } - # try to reboot normally - if (run_command $reboot) { - if (defined($powercycle_after_reboot)) { - sleep $powercycle_after_reboot; + } else { + # Make sure everything has been written to disk + run_ssh("sync"); + + if (defined($time)) { + start_monitor; + # flush out current monitor + # May contain the reboot success line + wait_for_monitor 1; + } + + # try to reboot normally + if (run_command $reboot) { + if (defined($powercycle_after_reboot)) { + sleep $powercycle_after_reboot; + run_command "$power_cycle"; + } + } else { + # nope? power cycle it. run_command "$power_cycle"; } - } else { - # nope? power cycle it. - run_command "$power_cycle"; } if (defined($time)) { @@ -1412,6 +1431,10 @@ sub dodie { system("stty $stty_orig"); } + if (defined($post_test)) { + run_command $post_test; + } + die @_, "\n"; } @@ -1624,10 +1647,6 @@ sub save_logs { sub fail { - if (defined($post_test)) { - run_command $post_test; - } - if ($die_on_failure) { dodie @_; } @@ -1660,23 +1679,26 @@ sub fail { save_logs "fail", $store_failures; } + if (defined($post_test)) { + run_command $post_test; + } + return 1; } sub run_command { - my ($command, $redirect) = @_; + my ($command, $redirect, $timeout) = @_; my $start_time; my $end_time; my $dolog = 0; my $dord = 0; my $pid; - $start_time = time; - $command =~ s/\$SSH_USER/$ssh_user/g; $command =~ s/\$MACHINE/$machine/g; doprint("$command ... "); + $start_time = time; $pid = open(CMD, "$command 2>&1 |") or (fail "unable to exec $command" and return 0); @@ -1693,13 +1715,30 @@ sub run_command { $dord = 1; } - while (<CMD>) { - print LOG if ($dolog); - print RD if ($dord); + my $hit_timeout = 0; + + while (1) { + my $fp = \*CMD; + if (defined($timeout)) { + doprint "timeout = $timeout\n"; + } + my $line = wait_for_input($fp, $timeout); + if (!defined($line)) { + my $now = time; + if (defined($timeout) && (($now - $start_time) >= $timeout)) { + doprint "Hit timeout of $timeout, killing process\n"; + $hit_timeout = 1; + kill 9, $pid; + } + last; + } + print LOG $line if ($dolog); + print RD $line if ($dord); } waitpid($pid, 0); - my $failed = $?; + # shift 8 for real exit status + $run_command_status = $? >> 8; close(CMD); close(LOG) if ($dolog); @@ -1714,21 +1753,25 @@ sub run_command { doprint "[$delta seconds] "; } - if ($failed) { + if ($hit_timeout) { + $run_command_status = 1; + } + + if ($run_command_status) { doprint "FAILED!\n"; } else { doprint "SUCCESS\n"; } - return !$failed; + return !$run_command_status; } sub run_ssh { - my ($cmd) = @_; + my ($cmd, $timeout) = @_; my $cp_exec = $ssh_exec; $cp_exec =~ s/\$SSH_COMMAND/$cmd/g; - return run_command "$cp_exec"; + return run_command "$cp_exec", undef , $timeout; } sub run_scp { @@ -1837,6 +1880,7 @@ sub get_grub_index { sub wait_for_input { my ($fp, $time) = @_; + my $start_time; my $rin; my $rout; my $nr; @@ -1852,17 +1896,22 @@ sub wait_for_input vec($rin, fileno($fp), 1) = 1; vec($rin, fileno(\*STDIN), 1) = 1; + $start_time = time; + while (1) { $nr = select($rout=$rin, undef, undef, $time); - if ($nr <= 0) { - return undef; - } + last if ($nr <= 0); # copy data from stdin to the console if (vec($rout, fileno(\*STDIN), 1) == 1) { - sysread(\*STDIN, $buf, 1000); - syswrite($fp, $buf, 1000); + $nr = sysread(\*STDIN, $buf, 1000); + syswrite($fp, $buf, $nr) if ($nr > 0); + } + + # The timeout is based on time waiting for the fp data + if (vec($rout, fileno($fp), 1) != 1) { + last if (defined($time) && (time - $start_time > $time)); next; } @@ -1874,12 +1923,11 @@ sub wait_for_input last if ($ch eq "\n"); } - if (!length($line)) { - return undef; - } + last if (!length($line)); return $line; } + return undef; } sub reboot_to { @@ -2489,10 +2537,6 @@ sub halt { sub success { my ($i) = @_; - if (defined($post_test)) { - run_command $post_test; - } - $successes++; my $name = ""; @@ -2517,6 +2561,10 @@ sub success { doprint "Reboot and wait $sleep_time seconds\n"; reboot_to_good $sleep_time; } + + if (defined($post_test)) { + run_command $post_test; + } } sub answer_bisect { @@ -2537,16 +2585,15 @@ sub answer_bisect { } sub child_run_test { - my $failed = 0; # child should have no power $reboot_on_error = 0; $poweroff_on_error = 0; $die_on_failure = 1; - run_command $run_test, $testlog or $failed = 1; + run_command $run_test, $testlog; - exit $failed; + exit $run_command_status; } my $child_done; @@ -2629,7 +2676,7 @@ sub do_run_test { } waitpid $child_pid, 0; - $child_exit = $?; + $child_exit = $? >> 8; my $end_time = time; $test_time = $end_time - $start_time; @@ -3330,7 +3377,6 @@ sub config_bisect { save_config \%good_configs, $good_config; save_config \%bad_configs, $bad_config; - if (defined($config_bisect_check) && $config_bisect_check ne "0") { if ($config_bisect_check ne "good") { doprint "Testing bad config\n"; diff --git a/tools/testing/nvdimm/Kbuild b/tools/testing/nvdimm/Kbuild index 405212be044a..d870520da68b 100644 --- a/tools/testing/nvdimm/Kbuild +++ b/tools/testing/nvdimm/Kbuild @@ -28,7 +28,10 @@ obj-$(CONFIG_ND_BTT) += nd_btt.o obj-$(CONFIG_ND_BLK) += nd_blk.o obj-$(CONFIG_X86_PMEM_LEGACY) += nd_e820.o obj-$(CONFIG_ACPI_NFIT) += nfit.o -obj-$(CONFIG_DEV_DAX) += dax.o +ifeq ($(CONFIG_DAX),m) +obj-$(CONFIG_DAX) += dax.o +endif +obj-$(CONFIG_DEV_DAX) += device_dax.o obj-$(CONFIG_DEV_DAX_PMEM) += dax_pmem.o nfit-y := $(ACPI_SRC)/core.o @@ -48,9 +51,13 @@ nd_blk-y += config_check.o nd_e820-y := $(NVDIMM_SRC)/e820.o nd_e820-y += config_check.o -dax-y := $(DAX_SRC)/dax.o +dax-y := $(DAX_SRC)/super.o dax-y += config_check.o +device_dax-y := $(DAX_SRC)/device.o +device_dax-y += dax-dev.o +device_dax-y += config_check.o + dax_pmem-y := $(DAX_SRC)/pmem.o dax_pmem-y += config_check.o diff --git a/tools/testing/nvdimm/dax-dev.c b/tools/testing/nvdimm/dax-dev.c new file mode 100644 index 000000000000..36ee3d8797c3 --- /dev/null +++ b/tools/testing/nvdimm/dax-dev.c @@ -0,0 +1,49 @@ +/* + * Copyright (c) 2016, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ +#include "test/nfit_test.h" +#include <linux/mm.h> +#include "../../../drivers/dax/dax-private.h" + +phys_addr_t dax_pgoff_to_phys(struct dev_dax *dev_dax, pgoff_t pgoff, + unsigned long size) +{ + struct resource *res; + phys_addr_t addr; + int i; + + for (i = 0; i < dev_dax->num_resources; i++) { + res = &dev_dax->res[i]; + addr = pgoff * PAGE_SIZE + res->start; + if (addr >= res->start && addr <= res->end) + break; + pgoff -= PHYS_PFN(resource_size(res)); + } + + if (i < dev_dax->num_resources) { + res = &dev_dax->res[i]; + if (addr + size - 1 <= res->end) { + if (get_nfit_res(addr)) { + struct page *page; + + if (dev_dax->region->align > PAGE_SIZE) + return -1; + + page = vmalloc_to_page((void *)addr); + return PFN_PHYS(page_to_pfn(page)); + } else + return addr; + } + } + + return -1; +} diff --git a/tools/testing/nvdimm/pmem-dax.c b/tools/testing/nvdimm/pmem-dax.c index c9b8c48f85fc..b53596ad601b 100644 --- a/tools/testing/nvdimm/pmem-dax.c +++ b/tools/testing/nvdimm/pmem-dax.c @@ -15,13 +15,13 @@ #include <pmem.h> #include <nd.h> -long pmem_direct_access(struct block_device *bdev, sector_t sector, - void **kaddr, pfn_t *pfn, long size) +long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff, + long nr_pages, void **kaddr, pfn_t *pfn) { - struct pmem_device *pmem = bdev->bd_queue->queuedata; - resource_size_t offset = sector * 512 + pmem->data_offset; + resource_size_t offset = PFN_PHYS(pgoff) + pmem->data_offset; - if (unlikely(is_bad_pmem(&pmem->bb, sector, size))) + if (unlikely(is_bad_pmem(&pmem->bb, PFN_PHYS(pgoff) / 512, + PFN_PHYS(nr_pages)))) return -EIO; /* @@ -34,11 +34,10 @@ long pmem_direct_access(struct block_device *bdev, sector_t sector, *kaddr = pmem->virt_addr + offset; page = vmalloc_to_page(pmem->virt_addr + offset); *pfn = page_to_pfn_t(page); - dev_dbg_ratelimited(disk_to_dev(bdev->bd_disk)->parent, - "%s: sector: %#llx pfn: %#lx\n", __func__, - (unsigned long long) sector, page_to_pfn(page)); + pr_debug_ratelimited("%s: pmem: %p pgoff: %#lx pfn: %#lx\n", + __func__, pmem, pgoff, page_to_pfn(page)); - return PAGE_SIZE; + return 1; } *kaddr = pmem->virt_addr + offset; @@ -49,6 +48,6 @@ long pmem_direct_access(struct block_device *bdev, sector_t sector, * requested range. */ if (unlikely(pmem->bb.count)) - return size; - return pmem->size - pmem->pfn_pad - offset; + return nr_pages; + return PHYS_PFN(pmem->size - pmem->pfn_pad - offset); } diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index 45be8b55a663..c2187178fb13 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -132,6 +132,7 @@ static u32 handle[] = { [3] = NFIT_DIMM_HANDLE(0, 0, 1, 0, 1), [4] = NFIT_DIMM_HANDLE(0, 1, 0, 0, 0), [5] = NFIT_DIMM_HANDLE(1, 0, 0, 0, 0), + [6] = NFIT_DIMM_HANDLE(1, 0, 0, 0, 1), }; static unsigned long dimm_fail_cmd_flags[NUM_DCR]; @@ -728,8 +729,8 @@ static int nfit_test0_alloc(struct nfit_test *t) static int nfit_test1_alloc(struct nfit_test *t) { size_t nfit_size = sizeof(struct acpi_nfit_system_address) * 2 - + sizeof(struct acpi_nfit_memory_map) - + offsetof(struct acpi_nfit_control_region, window_size); + + sizeof(struct acpi_nfit_memory_map) * 2 + + offsetof(struct acpi_nfit_control_region, window_size) * 2; int i; t->nfit_buf = test_alloc(t, nfit_size, &t->nfit_dma); @@ -887,7 +888,7 @@ static void nfit_test0_setup(struct nfit_test *t) memdev->range_index = 0+1; memdev->region_index = 4+1; memdev->region_size = SPA0_SIZE/2; - memdev->region_offset = t->spa_set_dma[0]; + memdev->region_offset = 1; memdev->address = 0; memdev->interleave_index = 0; memdev->interleave_ways = 2; @@ -902,10 +903,11 @@ static void nfit_test0_setup(struct nfit_test *t) memdev->range_index = 0+1; memdev->region_index = 5+1; memdev->region_size = SPA0_SIZE/2; - memdev->region_offset = t->spa_set_dma[0] + SPA0_SIZE/2; + memdev->region_offset = (1 << 8); memdev->address = 0; memdev->interleave_index = 0; memdev->interleave_ways = 2; + memdev->flags = ACPI_NFIT_MEM_HEALTH_ENABLED; /* mem-region2 (spa1, dimm0) */ memdev = nfit_buf + offset + sizeof(struct acpi_nfit_memory_map) * 2; @@ -917,10 +919,11 @@ static void nfit_test0_setup(struct nfit_test *t) memdev->range_index = 1+1; memdev->region_index = 4+1; memdev->region_size = SPA1_SIZE/4; - memdev->region_offset = t->spa_set_dma[1]; + memdev->region_offset = (1 << 16); memdev->address = SPA0_SIZE/2; memdev->interleave_index = 0; memdev->interleave_ways = 4; + memdev->flags = ACPI_NFIT_MEM_HEALTH_ENABLED; /* mem-region3 (spa1, dimm1) */ memdev = nfit_buf + offset + sizeof(struct acpi_nfit_memory_map) * 3; @@ -932,7 +935,7 @@ static void nfit_test0_setup(struct nfit_test *t) memdev->range_index = 1+1; memdev->region_index = 5+1; memdev->region_size = SPA1_SIZE/4; - memdev->region_offset = t->spa_set_dma[1] + SPA1_SIZE/4; + memdev->region_offset = (1 << 24); memdev->address = SPA0_SIZE/2; memdev->interleave_index = 0; memdev->interleave_ways = 4; @@ -947,10 +950,11 @@ static void nfit_test0_setup(struct nfit_test *t) memdev->range_index = 1+1; memdev->region_index = 6+1; memdev->region_size = SPA1_SIZE/4; - memdev->region_offset = t->spa_set_dma[1] + 2*SPA1_SIZE/4; + memdev->region_offset = (1ULL << 32); memdev->address = SPA0_SIZE/2; memdev->interleave_index = 0; memdev->interleave_ways = 4; + memdev->flags = ACPI_NFIT_MEM_HEALTH_ENABLED; /* mem-region5 (spa1, dimm3) */ memdev = nfit_buf + offset + sizeof(struct acpi_nfit_memory_map) * 5; @@ -962,7 +966,7 @@ static void nfit_test0_setup(struct nfit_test *t) memdev->range_index = 1+1; memdev->region_index = 7+1; memdev->region_size = SPA1_SIZE/4; - memdev->region_offset = t->spa_set_dma[1] + 3*SPA1_SIZE/4; + memdev->region_offset = (1ULL << 40); memdev->address = SPA0_SIZE/2; memdev->interleave_index = 0; memdev->interleave_ways = 4; @@ -1086,6 +1090,7 @@ static void nfit_test0_setup(struct nfit_test *t) memdev->address = 0; memdev->interleave_index = 0; memdev->interleave_ways = 1; + memdev->flags = ACPI_NFIT_MEM_HEALTH_ENABLED; offset = offset + sizeof(struct acpi_nfit_memory_map) * 14; /* dcr-descriptor0: blk */ @@ -1380,10 +1385,11 @@ static void nfit_test0_setup(struct nfit_test *t) memdev->range_index = 11+1; memdev->region_index = 9+1; memdev->region_size = SPA0_SIZE; - memdev->region_offset = t->spa_set_dma[2]; + memdev->region_offset = (1ULL << 48); memdev->address = 0; memdev->interleave_index = 0; memdev->interleave_ways = 1; + memdev->flags = ACPI_NFIT_MEM_HEALTH_ENABLED; /* mem-region16 (spa/bdw4, dimm4) */ memdev = nfit_buf + offset + @@ -1486,6 +1492,34 @@ static void nfit_test1_setup(struct nfit_test *t) dcr->code = NFIT_FIC_BYTE; dcr->windows = 0; + offset += dcr->header.length; + memdev = nfit_buf + offset; + memdev->header.type = ACPI_NFIT_TYPE_MEMORY_MAP; + memdev->header.length = sizeof(*memdev); + memdev->device_handle = handle[6]; + memdev->physical_id = 0; + memdev->region_id = 0; + memdev->range_index = 0; + memdev->region_index = 0+2; + memdev->region_size = SPA2_SIZE; + memdev->region_offset = 0; + memdev->address = 0; + memdev->interleave_index = 0; + memdev->interleave_ways = 1; + memdev->flags = ACPI_NFIT_MEM_MAP_FAILED; + + /* dcr-descriptor1 */ + offset += sizeof(*memdev); + dcr = nfit_buf + offset; + dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION; + dcr->header.length = offsetof(struct acpi_nfit_control_region, + window_size); + dcr->region_index = 0+2; + dcr_common_init(dcr); + dcr->serial_number = ~handle[6]; + dcr->code = NFIT_FIC_BYTE; + dcr->windows = 0; + post_ars_status(&t->ars_state, t->spa_set_dma[0], SPA2_SIZE); acpi_desc = &t->acpi_desc; @@ -1817,6 +1851,10 @@ static int nfit_test_probe(struct platform_device *pdev) if (rc) return rc; + rc = devm_add_action_or_reset(&pdev->dev, acpi_nfit_shutdown, acpi_desc); + if (rc) + return rc; + if (nfit_test->setup != nfit_test0_setup) return 0; @@ -1907,7 +1945,7 @@ static __init int nfit_test_init(void) case 1: nfit_test->num_pm = 1; nfit_test->dcr_idx = NUM_DCR; - nfit_test->num_dcr = 1; + nfit_test->num_dcr = 2; nfit_test->alloc = nfit_test1_alloc; nfit_test->setup = nfit_test1_setup; break; @@ -1924,6 +1962,7 @@ static __init int nfit_test_init(void) put_device(&pdev->dev); goto err_register; } + get_device(&pdev->dev); rc = dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); if (rc) @@ -1942,6 +1981,10 @@ static __init int nfit_test_init(void) if (instances[i]) platform_device_unregister(&instances[i]->pdev); nfit_test_teardown(); + for (i = 0; i < NUM_NFITS; i++) + if (instances[i]) + put_device(&instances[i]->pdev.dev); + return rc; } @@ -1949,10 +1992,13 @@ static __exit void nfit_test_exit(void) { int i; - platform_driver_unregister(&nfit_test_driver); for (i = 0; i < NUM_NFITS; i++) platform_device_unregister(&instances[i]->pdev); + platform_driver_unregister(&nfit_test_driver); nfit_test_teardown(); + + for (i = 0; i < NUM_NFITS; i++) + put_device(&instances[i]->pdev.dev); class_destroy(nfit_test_dimm); } diff --git a/tools/testing/radix-tree/.gitignore b/tools/testing/radix-tree/.gitignore index 11d888ca6a92..d4706c0ffceb 100644 --- a/tools/testing/radix-tree/.gitignore +++ b/tools/testing/radix-tree/.gitignore @@ -1,2 +1,6 @@ +generated/map-shift.h +idr.c +idr-test main +multiorder radix-tree.c diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile index 3635e4d3eca7..6a9480c03cbd 100644 --- a/tools/testing/radix-tree/Makefile +++ b/tools/testing/radix-tree/Makefile @@ -1,29 +1,50 @@ -CFLAGS += -I. -I../../include -g -O2 -Wall -D_LGPL_SOURCE -LDFLAGS += -lpthread -lurcu -TARGETS = main -OFILES = main.o radix-tree.o linux.o test.o tag_check.o find_next_bit.o \ - regression1.o regression2.o regression3.o multiorder.o \ - iteration_check.o benchmark.o - -ifdef BENCHMARK - CFLAGS += -DBENCHMARK=1 +CFLAGS += -I. -I../../include -g -O2 -Wall -D_LGPL_SOURCE -fsanitize=address +LDFLAGS += -fsanitize=address +LDLIBS+= -lpthread -lurcu +TARGETS = main idr-test multiorder +CORE_OFILES := radix-tree.o idr.o linux.o test.o find_bit.o +OFILES = main.o $(CORE_OFILES) regression1.o regression2.o regression3.o \ + tag_check.o multiorder.o idr-test.o iteration_check.o benchmark.o + +ifndef SHIFT + SHIFT=3 endif -targets: $(TARGETS) +ifeq ($(BUILD), 32) + CFLAGS += -m32 + LDFLAGS += -m32 +endif + +targets: mapshift $(TARGETS) main: $(OFILES) - $(CC) $(CFLAGS) $(LDFLAGS) $(OFILES) -o main + +idr-test: idr-test.o $(CORE_OFILES) + +multiorder: multiorder.o $(CORE_OFILES) clean: - $(RM) -f $(TARGETS) *.o radix-tree.c + $(RM) $(TARGETS) *.o radix-tree.c idr.c generated/map-shift.h -find_next_bit.o: ../../lib/find_bit.c - $(CC) $(CFLAGS) -c -o $@ $< +vpath %.c ../../lib -$(OFILES): *.h */*.h \ +$(OFILES): Makefile *.h */*.h generated/map-shift.h \ ../../include/linux/*.h \ - ../../../include/linux/radix-tree.h + ../../include/asm/*.h \ + ../../../include/linux/radix-tree.h \ + ../../../include/linux/idr.h radix-tree.c: ../../../lib/radix-tree.c sed -e 's/^static //' -e 's/__always_inline //' -e 's/inline //' < $< > $@ + +idr.c: ../../../lib/idr.c + sed -e 's/^static //' -e 's/__always_inline //' -e 's/inline //' < $< > $@ + +.PHONY: mapshift + +mapshift: + @if ! grep -qws $(SHIFT) generated/map-shift.h; then \ + echo "#define RADIX_TREE_MAP_SHIFT $(SHIFT)" > \ + generated/map-shift.h; \ + fi diff --git a/tools/testing/radix-tree/benchmark.c b/tools/testing/radix-tree/benchmark.c index 215ca86c7605..99c40f3ed133 100644 --- a/tools/testing/radix-tree/benchmark.c +++ b/tools/testing/radix-tree/benchmark.c @@ -17,6 +17,9 @@ #include <time.h> #include "test.h" +#define for_each_index(i, base, order) \ + for (i = base; i < base + (1 << order); i++) + #define NSEC_PER_SEC 1000000000L static long long benchmark_iter(struct radix_tree_root *root, bool tagged) @@ -57,27 +60,176 @@ again: return nsec; } +static void benchmark_insert(struct radix_tree_root *root, + unsigned long size, unsigned long step, int order) +{ + struct timespec start, finish; + unsigned long index; + long long nsec; + + clock_gettime(CLOCK_MONOTONIC, &start); + + for (index = 0 ; index < size ; index += step) + item_insert_order(root, index, order); + + clock_gettime(CLOCK_MONOTONIC, &finish); + + nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC + + (finish.tv_nsec - start.tv_nsec); + + printv(2, "Size: %8ld, step: %8ld, order: %d, insertion: %15lld ns\n", + size, step, order, nsec); +} + +static void benchmark_tagging(struct radix_tree_root *root, + unsigned long size, unsigned long step, int order) +{ + struct timespec start, finish; + unsigned long index; + long long nsec; + + clock_gettime(CLOCK_MONOTONIC, &start); + + for (index = 0 ; index < size ; index += step) + radix_tree_tag_set(root, index, 0); + + clock_gettime(CLOCK_MONOTONIC, &finish); + + nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC + + (finish.tv_nsec - start.tv_nsec); + + printv(2, "Size: %8ld, step: %8ld, order: %d, tagging: %17lld ns\n", + size, step, order, nsec); +} + +static void benchmark_delete(struct radix_tree_root *root, + unsigned long size, unsigned long step, int order) +{ + struct timespec start, finish; + unsigned long index, i; + long long nsec; + + clock_gettime(CLOCK_MONOTONIC, &start); + + for (index = 0 ; index < size ; index += step) + for_each_index(i, index, order) + item_delete(root, i); + + clock_gettime(CLOCK_MONOTONIC, &finish); + + nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC + + (finish.tv_nsec - start.tv_nsec); + + printv(2, "Size: %8ld, step: %8ld, order: %d, deletion: %16lld ns\n", + size, step, order, nsec); +} + static void benchmark_size(unsigned long size, unsigned long step, int order) { RADIX_TREE(tree, GFP_KERNEL); long long normal, tagged; - unsigned long index; - for (index = 0 ; index < size ; index += step) { - item_insert_order(&tree, index, order); - radix_tree_tag_set(&tree, index, 0); - } + benchmark_insert(&tree, size, step, order); + benchmark_tagging(&tree, size, step, order); tagged = benchmark_iter(&tree, true); normal = benchmark_iter(&tree, false); - printf("Size %ld, step %6ld, order %d tagged %10lld ns, normal %10lld ns\n", - size, step, order, tagged, normal); + printv(2, "Size: %8ld, step: %8ld, order: %d, tagged iteration: %8lld ns\n", + size, step, order, tagged); + printv(2, "Size: %8ld, step: %8ld, order: %d, normal iteration: %8lld ns\n", + size, step, order, normal); + + benchmark_delete(&tree, size, step, order); item_kill_tree(&tree); rcu_barrier(); } +static long long __benchmark_split(unsigned long index, + int old_order, int new_order) +{ + struct timespec start, finish; + long long nsec; + RADIX_TREE(tree, GFP_ATOMIC); + + item_insert_order(&tree, index, old_order); + + clock_gettime(CLOCK_MONOTONIC, &start); + radix_tree_split(&tree, index, new_order); + clock_gettime(CLOCK_MONOTONIC, &finish); + nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC + + (finish.tv_nsec - start.tv_nsec); + + item_kill_tree(&tree); + + return nsec; + +} + +static void benchmark_split(unsigned long size, unsigned long step) +{ + int i, j, idx; + long long nsec = 0; + + + for (idx = 0; idx < size; idx += step) { + for (i = 3; i < 11; i++) { + for (j = 0; j < i; j++) { + nsec += __benchmark_split(idx, i, j); + } + } + } + + printv(2, "Size %8ld, step %8ld, split time %10lld ns\n", + size, step, nsec); + +} + +static long long __benchmark_join(unsigned long index, + unsigned order1, unsigned order2) +{ + unsigned long loc; + struct timespec start, finish; + long long nsec; + void *item, *item2 = item_create(index + 1, order1); + RADIX_TREE(tree, GFP_KERNEL); + + item_insert_order(&tree, index, order2); + item = radix_tree_lookup(&tree, index); + + clock_gettime(CLOCK_MONOTONIC, &start); + radix_tree_join(&tree, index + 1, order1, item2); + clock_gettime(CLOCK_MONOTONIC, &finish); + nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC + + (finish.tv_nsec - start.tv_nsec); + + loc = find_item(&tree, item); + if (loc == -1) + free(item); + + item_kill_tree(&tree); + + return nsec; +} + +static void benchmark_join(unsigned long step) +{ + int i, j, idx; + long long nsec = 0; + + for (idx = 0; idx < 1 << 10; idx += step) { + for (i = 1; i < 15; i++) { + for (j = 0; j < i; j++) { + nsec += __benchmark_join(idx, i, j); + } + } + } + + printv(2, "Size %8d, step %8ld, join time %10lld ns\n", + 1 << 10, step, nsec); +} + void benchmark(void) { unsigned long size[] = {1 << 10, 1 << 20, 0}; @@ -85,8 +237,8 @@ void benchmark(void) 128, 256, 512, 12345, 0}; int c, s; - printf("starting benchmarks\n"); - printf("RADIX_TREE_MAP_SHIFT = %d\n", RADIX_TREE_MAP_SHIFT); + printv(1, "starting benchmarks\n"); + printv(1, "RADIX_TREE_MAP_SHIFT = %d\n", RADIX_TREE_MAP_SHIFT); for (c = 0; size[c]; c++) for (s = 0; step[s]; s++) @@ -95,4 +247,11 @@ void benchmark(void) for (c = 0; size[c]; c++) for (s = 0; step[s]; s++) benchmark_size(size[c], step[s] << 9, 9); + + for (c = 0; size[c]; c++) + for (s = 0; step[s]; s++) + benchmark_split(size[c], step[s]); + + for (s = 0; step[s]; s++) + benchmark_join(step[s]); } diff --git a/tools/testing/radix-tree/generated/autoconf.h b/tools/testing/radix-tree/generated/autoconf.h index ad18cf5a2a3a..cf88dc5b8832 100644 --- a/tools/testing/radix-tree/generated/autoconf.h +++ b/tools/testing/radix-tree/generated/autoconf.h @@ -1,3 +1 @@ #define CONFIG_RADIX_TREE_MULTIORDER 1 -#define CONFIG_SHMEM 1 -#define CONFIG_SWAP 1 diff --git a/tools/testing/radix-tree/idr-test.c b/tools/testing/radix-tree/idr-test.c new file mode 100644 index 000000000000..30cd0b296f1a --- /dev/null +++ b/tools/testing/radix-tree/idr-test.c @@ -0,0 +1,516 @@ +/* + * idr-test.c: Test the IDR API + * Copyright (c) 2016 Matthew Wilcox <willy@infradead.org> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ +#include <linux/bitmap.h> +#include <linux/idr.h> +#include <linux/slab.h> +#include <linux/kernel.h> +#include <linux/errno.h> + +#include "test.h" + +#define DUMMY_PTR ((void *)0x12) + +int item_idr_free(int id, void *p, void *data) +{ + struct item *item = p; + assert(item->index == id); + free(p); + + return 0; +} + +void item_idr_remove(struct idr *idr, int id) +{ + struct item *item = idr_find(idr, id); + assert(item->index == id); + idr_remove(idr, id); + free(item); +} + +void idr_alloc_test(void) +{ + unsigned long i; + DEFINE_IDR(idr); + + assert(idr_alloc_cyclic(&idr, DUMMY_PTR, 0, 0x4000, GFP_KERNEL) == 0); + assert(idr_alloc_cyclic(&idr, DUMMY_PTR, 0x3ffd, 0x4000, GFP_KERNEL) == 0x3ffd); + idr_remove(&idr, 0x3ffd); + idr_remove(&idr, 0); + + for (i = 0x3ffe; i < 0x4003; i++) { + int id; + struct item *item; + + if (i < 0x4000) + item = item_create(i, 0); + else + item = item_create(i - 0x3fff, 0); + + id = idr_alloc_cyclic(&idr, item, 1, 0x4000, GFP_KERNEL); + assert(id == item->index); + } + + idr_for_each(&idr, item_idr_free, &idr); + idr_destroy(&idr); +} + +void idr_replace_test(void) +{ + DEFINE_IDR(idr); + + idr_alloc(&idr, (void *)-1, 10, 11, GFP_KERNEL); + idr_replace(&idr, &idr, 10); + + idr_destroy(&idr); +} + +/* + * Unlike the radix tree, you can put a NULL pointer -- with care -- into + * the IDR. Some interfaces, like idr_find() do not distinguish between + * "present, value is NULL" and "not present", but that's exactly what some + * users want. + */ +void idr_null_test(void) +{ + int i; + DEFINE_IDR(idr); + + assert(idr_is_empty(&idr)); + + assert(idr_alloc(&idr, NULL, 0, 0, GFP_KERNEL) == 0); + assert(!idr_is_empty(&idr)); + idr_remove(&idr, 0); + assert(idr_is_empty(&idr)); + + assert(idr_alloc(&idr, NULL, 0, 0, GFP_KERNEL) == 0); + assert(!idr_is_empty(&idr)); + idr_destroy(&idr); + assert(idr_is_empty(&idr)); + + for (i = 0; i < 10; i++) { + assert(idr_alloc(&idr, NULL, 0, 0, GFP_KERNEL) == i); + } + + assert(idr_replace(&idr, DUMMY_PTR, 3) == NULL); + assert(idr_replace(&idr, DUMMY_PTR, 4) == NULL); + assert(idr_replace(&idr, NULL, 4) == DUMMY_PTR); + assert(idr_replace(&idr, DUMMY_PTR, 11) == ERR_PTR(-ENOENT)); + idr_remove(&idr, 5); + assert(idr_alloc(&idr, NULL, 0, 0, GFP_KERNEL) == 5); + idr_remove(&idr, 5); + + for (i = 0; i < 9; i++) { + idr_remove(&idr, i); + assert(!idr_is_empty(&idr)); + } + idr_remove(&idr, 8); + assert(!idr_is_empty(&idr)); + idr_remove(&idr, 9); + assert(idr_is_empty(&idr)); + + assert(idr_alloc(&idr, NULL, 0, 0, GFP_KERNEL) == 0); + assert(idr_replace(&idr, DUMMY_PTR, 3) == ERR_PTR(-ENOENT)); + assert(idr_replace(&idr, DUMMY_PTR, 0) == NULL); + assert(idr_replace(&idr, NULL, 0) == DUMMY_PTR); + + idr_destroy(&idr); + assert(idr_is_empty(&idr)); + + for (i = 1; i < 10; i++) { + assert(idr_alloc(&idr, NULL, 1, 0, GFP_KERNEL) == i); + } + + idr_destroy(&idr); + assert(idr_is_empty(&idr)); +} + +void idr_nowait_test(void) +{ + unsigned int i; + DEFINE_IDR(idr); + + idr_preload(GFP_KERNEL); + + for (i = 0; i < 3; i++) { + struct item *item = item_create(i, 0); + assert(idr_alloc(&idr, item, i, i + 1, GFP_NOWAIT) == i); + } + + idr_preload_end(); + + idr_for_each(&idr, item_idr_free, &idr); + idr_destroy(&idr); +} + +void idr_get_next_test(void) +{ + unsigned long i; + int nextid; + DEFINE_IDR(idr); + + int indices[] = {4, 7, 9, 15, 65, 128, 1000, 99999, 0}; + + for(i = 0; indices[i]; i++) { + struct item *item = item_create(indices[i], 0); + assert(idr_alloc(&idr, item, indices[i], indices[i+1], + GFP_KERNEL) == indices[i]); + } + + for(i = 0, nextid = 0; indices[i]; i++) { + idr_get_next(&idr, &nextid); + assert(nextid == indices[i]); + nextid++; + } + + idr_for_each(&idr, item_idr_free, &idr); + idr_destroy(&idr); +} + +void idr_checks(void) +{ + unsigned long i; + DEFINE_IDR(idr); + + for (i = 0; i < 10000; i++) { + struct item *item = item_create(i, 0); + assert(idr_alloc(&idr, item, 0, 20000, GFP_KERNEL) == i); + } + + assert(idr_alloc(&idr, DUMMY_PTR, 5, 30, GFP_KERNEL) < 0); + + for (i = 0; i < 5000; i++) + item_idr_remove(&idr, i); + + idr_remove(&idr, 3); + + idr_for_each(&idr, item_idr_free, &idr); + idr_destroy(&idr); + + assert(idr_is_empty(&idr)); + + idr_remove(&idr, 3); + idr_remove(&idr, 0); + + for (i = INT_MAX - 3UL; i < INT_MAX + 1UL; i++) { + struct item *item = item_create(i, 0); + assert(idr_alloc(&idr, item, i, i + 10, GFP_KERNEL) == i); + } + assert(idr_alloc(&idr, DUMMY_PTR, i - 2, i, GFP_KERNEL) == -ENOSPC); + + idr_for_each(&idr, item_idr_free, &idr); + idr_destroy(&idr); + idr_destroy(&idr); + + assert(idr_is_empty(&idr)); + + for (i = 1; i < 10000; i++) { + struct item *item = item_create(i, 0); + assert(idr_alloc(&idr, item, 1, 20000, GFP_KERNEL) == i); + } + + idr_for_each(&idr, item_idr_free, &idr); + idr_destroy(&idr); + + idr_replace_test(); + idr_alloc_test(); + idr_null_test(); + idr_nowait_test(); + idr_get_next_test(); +} + +/* + * Check that we get the correct error when we run out of memory doing + * allocations. To ensure we run out of memory, just "forget" to preload. + * The first test is for not having a bitmap available, and the second test + * is for not being able to allocate a level of the radix tree. + */ +void ida_check_nomem(void) +{ + DEFINE_IDA(ida); + int id, err; + + err = ida_get_new_above(&ida, 256, &id); + assert(err == -EAGAIN); + err = ida_get_new_above(&ida, 1UL << 30, &id); + assert(err == -EAGAIN); +} + +/* + * Check what happens when we fill a leaf and then delete it. This may + * discover mishandling of IDR_FREE. + */ +void ida_check_leaf(void) +{ + DEFINE_IDA(ida); + int id; + unsigned long i; + + for (i = 0; i < IDA_BITMAP_BITS; i++) { + assert(ida_pre_get(&ida, GFP_KERNEL)); + assert(!ida_get_new(&ida, &id)); + assert(id == i); + } + + ida_destroy(&ida); + assert(ida_is_empty(&ida)); + + assert(ida_pre_get(&ida, GFP_KERNEL)); + assert(!ida_get_new(&ida, &id)); + assert(id == 0); + ida_destroy(&ida); + assert(ida_is_empty(&ida)); +} + +/* + * Check handling of conversions between exceptional entries and full bitmaps. + */ +void ida_check_conv(void) +{ + DEFINE_IDA(ida); + int id; + unsigned long i; + + for (i = 0; i < IDA_BITMAP_BITS * 2; i += IDA_BITMAP_BITS) { + assert(ida_pre_get(&ida, GFP_KERNEL)); + assert(!ida_get_new_above(&ida, i + 1, &id)); + assert(id == i + 1); + assert(!ida_get_new_above(&ida, i + BITS_PER_LONG, &id)); + assert(id == i + BITS_PER_LONG); + ida_remove(&ida, i + 1); + ida_remove(&ida, i + BITS_PER_LONG); + assert(ida_is_empty(&ida)); + } + + assert(ida_pre_get(&ida, GFP_KERNEL)); + + for (i = 0; i < IDA_BITMAP_BITS * 2; i++) { + assert(ida_pre_get(&ida, GFP_KERNEL)); + assert(!ida_get_new(&ida, &id)); + assert(id == i); + } + + for (i = IDA_BITMAP_BITS * 2; i > 0; i--) { + ida_remove(&ida, i - 1); + } + assert(ida_is_empty(&ida)); + + for (i = 0; i < IDA_BITMAP_BITS + BITS_PER_LONG - 4; i++) { + assert(ida_pre_get(&ida, GFP_KERNEL)); + assert(!ida_get_new(&ida, &id)); + assert(id == i); + } + + for (i = IDA_BITMAP_BITS + BITS_PER_LONG - 4; i > 0; i--) { + ida_remove(&ida, i - 1); + } + assert(ida_is_empty(&ida)); + + radix_tree_cpu_dead(1); + for (i = 0; i < 1000000; i++) { + int err = ida_get_new(&ida, &id); + if (err == -EAGAIN) { + assert((i % IDA_BITMAP_BITS) == (BITS_PER_LONG - 2)); + assert(ida_pre_get(&ida, GFP_KERNEL)); + err = ida_get_new(&ida, &id); + } else { + assert((i % IDA_BITMAP_BITS) != (BITS_PER_LONG - 2)); + } + assert(!err); + assert(id == i); + } + ida_destroy(&ida); +} + +/* + * Check allocations up to and slightly above the maximum allowed (2^31-1) ID. + * Allocating up to 2^31-1 should succeed, and then allocating the next one + * should fail. + */ +void ida_check_max(void) +{ + DEFINE_IDA(ida); + int id, err; + unsigned long i, j; + + for (j = 1; j < 65537; j *= 2) { + unsigned long base = (1UL << 31) - j; + for (i = 0; i < j; i++) { + assert(ida_pre_get(&ida, GFP_KERNEL)); + assert(!ida_get_new_above(&ida, base, &id)); + assert(id == base + i); + } + assert(ida_pre_get(&ida, GFP_KERNEL)); + err = ida_get_new_above(&ida, base, &id); + assert(err == -ENOSPC); + ida_destroy(&ida); + assert(ida_is_empty(&ida)); + rcu_barrier(); + } +} + +void ida_check_random(void) +{ + DEFINE_IDA(ida); + DECLARE_BITMAP(bitmap, 2048); + int id, err; + unsigned int i; + time_t s = time(NULL); + + repeat: + memset(bitmap, 0, sizeof(bitmap)); + for (i = 0; i < 100000; i++) { + int i = rand(); + int bit = i & 2047; + if (test_bit(bit, bitmap)) { + __clear_bit(bit, bitmap); + ida_remove(&ida, bit); + } else { + __set_bit(bit, bitmap); + do { + ida_pre_get(&ida, GFP_KERNEL); + err = ida_get_new_above(&ida, bit, &id); + } while (err == -ENOMEM); + assert(!err); + assert(id == bit); + } + } + ida_destroy(&ida); + if (time(NULL) < s + 10) + goto repeat; +} + +void ida_simple_get_remove_test(void) +{ + DEFINE_IDA(ida); + unsigned long i; + + for (i = 0; i < 10000; i++) { + assert(ida_simple_get(&ida, 0, 20000, GFP_KERNEL) == i); + } + assert(ida_simple_get(&ida, 5, 30, GFP_KERNEL) < 0); + + for (i = 0; i < 10000; i++) { + ida_simple_remove(&ida, i); + } + assert(ida_is_empty(&ida)); + + ida_destroy(&ida); +} + +void ida_checks(void) +{ + DEFINE_IDA(ida); + int id; + unsigned long i; + + radix_tree_cpu_dead(1); + ida_check_nomem(); + + for (i = 0; i < 10000; i++) { + assert(ida_pre_get(&ida, GFP_KERNEL)); + assert(!ida_get_new(&ida, &id)); + assert(id == i); + } + + ida_remove(&ida, 20); + ida_remove(&ida, 21); + for (i = 0; i < 3; i++) { + assert(ida_pre_get(&ida, GFP_KERNEL)); + assert(!ida_get_new(&ida, &id)); + if (i == 2) + assert(id == 10000); + } + + for (i = 0; i < 5000; i++) + ida_remove(&ida, i); + + assert(ida_pre_get(&ida, GFP_KERNEL)); + assert(!ida_get_new_above(&ida, 5000, &id)); + assert(id == 10001); + + ida_destroy(&ida); + + assert(ida_is_empty(&ida)); + + assert(ida_pre_get(&ida, GFP_KERNEL)); + assert(!ida_get_new_above(&ida, 1, &id)); + assert(id == 1); + + ida_remove(&ida, id); + assert(ida_is_empty(&ida)); + ida_destroy(&ida); + assert(ida_is_empty(&ida)); + + assert(ida_pre_get(&ida, GFP_KERNEL)); + assert(!ida_get_new_above(&ida, 1, &id)); + ida_destroy(&ida); + assert(ida_is_empty(&ida)); + + assert(ida_pre_get(&ida, GFP_KERNEL)); + assert(!ida_get_new_above(&ida, 1, &id)); + assert(id == 1); + assert(ida_pre_get(&ida, GFP_KERNEL)); + assert(!ida_get_new_above(&ida, 1025, &id)); + assert(id == 1025); + assert(ida_pre_get(&ida, GFP_KERNEL)); + assert(!ida_get_new_above(&ida, 10000, &id)); + assert(id == 10000); + ida_remove(&ida, 1025); + ida_destroy(&ida); + assert(ida_is_empty(&ida)); + + ida_check_leaf(); + ida_check_max(); + ida_check_conv(); + ida_check_random(); + ida_simple_get_remove_test(); + + radix_tree_cpu_dead(1); +} + +static void *ida_random_fn(void *arg) +{ + rcu_register_thread(); + ida_check_random(); + rcu_unregister_thread(); + return NULL; +} + +void ida_thread_tests(void) +{ + pthread_t threads[10]; + int i; + + for (i = 0; i < ARRAY_SIZE(threads); i++) + if (pthread_create(&threads[i], NULL, ida_random_fn, NULL)) { + perror("creating ida thread"); + exit(1); + } + + while (i--) + pthread_join(threads[i], NULL); +} + +int __weak main(void) +{ + radix_tree_init(); + idr_checks(); + ida_checks(); + ida_thread_tests(); + radix_tree_cpu_dead(1); + rcu_barrier(); + if (nr_allocated) + printf("nr_allocated = %d\n", nr_allocated); + return 0; +} diff --git a/tools/testing/radix-tree/iteration_check.c b/tools/testing/radix-tree/iteration_check.c index 7572b7ed930e..a92bab513701 100644 --- a/tools/testing/radix-tree/iteration_check.c +++ b/tools/testing/radix-tree/iteration_check.c @@ -177,7 +177,7 @@ void iteration_test(unsigned order, unsigned test_duration) { int i; - printf("Running %siteration tests for %d seconds\n", + printv(1, "Running %siteration tests for %d seconds\n", order > 0 ? "multiorder " : "", test_duration); max_order = order; diff --git a/tools/testing/radix-tree/linux.c b/tools/testing/radix-tree/linux.c index d31ea7c9abec..cf48c8473f48 100644 --- a/tools/testing/radix-tree/linux.c +++ b/tools/testing/radix-tree/linux.c @@ -5,7 +5,7 @@ #include <unistd.h> #include <assert.h> -#include <linux/mempool.h> +#include <linux/gfp.h> #include <linux/poison.h> #include <linux/slab.h> #include <linux/radix-tree.h> @@ -13,6 +13,8 @@ int nr_allocated; int preempt_count; +int kmalloc_verbose; +int test_verbose; struct kmem_cache { pthread_mutex_t lock; @@ -22,27 +24,6 @@ struct kmem_cache { void (*ctor)(void *); }; -void *mempool_alloc(mempool_t *pool, int gfp_mask) -{ - return pool->alloc(gfp_mask, pool->data); -} - -void mempool_free(void *element, mempool_t *pool) -{ - pool->free(element, pool->data); -} - -mempool_t *mempool_create(int min_nr, mempool_alloc_t *alloc_fn, - mempool_free_t *free_fn, void *pool_data) -{ - mempool_t *ret = malloc(sizeof(*ret)); - - ret->alloc = alloc_fn; - ret->free = free_fn; - ret->data = pool_data; - return ret; -} - void *kmem_cache_alloc(struct kmem_cache *cachep, int flags) { struct radix_tree_node *node; @@ -54,9 +35,9 @@ void *kmem_cache_alloc(struct kmem_cache *cachep, int flags) if (cachep->nr_objs) { cachep->nr_objs--; node = cachep->objs; - cachep->objs = node->private_data; + cachep->objs = node->parent; pthread_mutex_unlock(&cachep->lock); - node->private_data = NULL; + node->parent = NULL; } else { pthread_mutex_unlock(&cachep->lock); node = malloc(cachep->size); @@ -65,6 +46,8 @@ void *kmem_cache_alloc(struct kmem_cache *cachep, int flags) } uatomic_inc(&nr_allocated); + if (kmalloc_verbose) + printf("Allocating %p from slab\n", node); return node; } @@ -72,6 +55,8 @@ void kmem_cache_free(struct kmem_cache *cachep, void *objp) { assert(objp); uatomic_dec(&nr_allocated); + if (kmalloc_verbose) + printf("Freeing %p to slab\n", objp); pthread_mutex_lock(&cachep->lock); if (cachep->nr_objs > 10) { memset(objp, POISON_FREE, cachep->size); @@ -79,7 +64,7 @@ void kmem_cache_free(struct kmem_cache *cachep, void *objp) } else { struct radix_tree_node *node = objp; cachep->nr_objs++; - node->private_data = cachep->objs; + node->parent = cachep->objs; cachep->objs = node; } pthread_mutex_unlock(&cachep->lock); @@ -89,6 +74,8 @@ void *kmalloc(size_t size, gfp_t gfp) { void *ret = malloc(size); uatomic_inc(&nr_allocated); + if (kmalloc_verbose) + printf("Allocating %p from malloc\n", ret); return ret; } @@ -97,6 +84,8 @@ void kfree(void *p) if (!p) return; uatomic_dec(&nr_allocated); + if (kmalloc_verbose) + printf("Freeing %p to malloc\n", p); free(p); } diff --git a/tools/testing/radix-tree/linux/bitops.h b/tools/testing/radix-tree/linux/bitops.h deleted file mode 100644 index a13e9bc76eec..000000000000 --- a/tools/testing/radix-tree/linux/bitops.h +++ /dev/null @@ -1,160 +0,0 @@ -#ifndef _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ -#define _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ - -#include <linux/types.h> -#include <linux/bitops/find.h> -#include <linux/bitops/hweight.h> -#include <linux/kernel.h> - -#define BIT_MASK(nr) (1UL << ((nr) % BITS_PER_LONG)) -#define BIT_WORD(nr) ((nr) / BITS_PER_LONG) -#define BITS_PER_BYTE 8 -#define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long)) - -/** - * __set_bit - Set a bit in memory - * @nr: the bit to set - * @addr: the address to start counting from - * - * Unlike set_bit(), this function is non-atomic and may be reordered. - * If it's called on the same region of memory simultaneously, the effect - * may be that only one operation succeeds. - */ -static inline void __set_bit(int nr, volatile unsigned long *addr) -{ - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); - - *p |= mask; -} - -static inline void __clear_bit(int nr, volatile unsigned long *addr) -{ - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); - - *p &= ~mask; -} - -/** - * __change_bit - Toggle a bit in memory - * @nr: the bit to change - * @addr: the address to start counting from - * - * Unlike change_bit(), this function is non-atomic and may be reordered. - * If it's called on the same region of memory simultaneously, the effect - * may be that only one operation succeeds. - */ -static inline void __change_bit(int nr, volatile unsigned long *addr) -{ - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); - - *p ^= mask; -} - -/** - * __test_and_set_bit - Set a bit and return its old value - * @nr: Bit to set - * @addr: Address to count from - * - * This operation is non-atomic and can be reordered. - * If two examples of this operation race, one can appear to succeed - * but actually fail. You must protect multiple accesses with a lock. - */ -static inline int __test_and_set_bit(int nr, volatile unsigned long *addr) -{ - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); - unsigned long old = *p; - - *p = old | mask; - return (old & mask) != 0; -} - -/** - * __test_and_clear_bit - Clear a bit and return its old value - * @nr: Bit to clear - * @addr: Address to count from - * - * This operation is non-atomic and can be reordered. - * If two examples of this operation race, one can appear to succeed - * but actually fail. You must protect multiple accesses with a lock. - */ -static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr) -{ - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); - unsigned long old = *p; - - *p = old & ~mask; - return (old & mask) != 0; -} - -/* WARNING: non atomic and it can be reordered! */ -static inline int __test_and_change_bit(int nr, - volatile unsigned long *addr) -{ - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); - unsigned long old = *p; - - *p = old ^ mask; - return (old & mask) != 0; -} - -/** - * test_bit - Determine whether a bit is set - * @nr: bit number to test - * @addr: Address to start counting from - */ -static inline int test_bit(int nr, const volatile unsigned long *addr) -{ - return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1))); -} - -/** - * __ffs - find first bit in word. - * @word: The word to search - * - * Undefined if no bit exists, so code should check against 0 first. - */ -static inline unsigned long __ffs(unsigned long word) -{ - int num = 0; - - if ((word & 0xffffffff) == 0) { - num += 32; - word >>= 32; - } - if ((word & 0xffff) == 0) { - num += 16; - word >>= 16; - } - if ((word & 0xff) == 0) { - num += 8; - word >>= 8; - } - if ((word & 0xf) == 0) { - num += 4; - word >>= 4; - } - if ((word & 0x3) == 0) { - num += 2; - word >>= 2; - } - if ((word & 0x1) == 0) - num += 1; - return num; -} - -unsigned long find_next_bit(const unsigned long *addr, - unsigned long size, - unsigned long offset); - -static inline unsigned long hweight_long(unsigned long w) -{ - return sizeof(w) == 4 ? hweight32(w) : hweight64(w); -} - -#endif /* _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ */ diff --git a/tools/testing/radix-tree/linux/bitops/__ffs.h b/tools/testing/radix-tree/linux/bitops/__ffs.h deleted file mode 100644 index 9a3274aecf83..000000000000 --- a/tools/testing/radix-tree/linux/bitops/__ffs.h +++ /dev/null @@ -1,43 +0,0 @@ -#ifndef _ASM_GENERIC_BITOPS___FFS_H_ -#define _ASM_GENERIC_BITOPS___FFS_H_ - -#include <asm/types.h> - -/** - * __ffs - find first bit in word. - * @word: The word to search - * - * Undefined if no bit exists, so code should check against 0 first. - */ -static inline unsigned long __ffs(unsigned long word) -{ - int num = 0; - -#if BITS_PER_LONG == 64 - if ((word & 0xffffffff) == 0) { - num += 32; - word >>= 32; - } -#endif - if ((word & 0xffff) == 0) { - num += 16; - word >>= 16; - } - if ((word & 0xff) == 0) { - num += 8; - word >>= 8; - } - if ((word & 0xf) == 0) { - num += 4; - word >>= 4; - } - if ((word & 0x3) == 0) { - num += 2; - word >>= 2; - } - if ((word & 0x1) == 0) - num += 1; - return num; -} - -#endif /* _ASM_GENERIC_BITOPS___FFS_H_ */ diff --git a/tools/testing/radix-tree/linux/bitops/ffs.h b/tools/testing/radix-tree/linux/bitops/ffs.h deleted file mode 100644 index fbbb43af7dc0..000000000000 --- a/tools/testing/radix-tree/linux/bitops/ffs.h +++ /dev/null @@ -1,41 +0,0 @@ -#ifndef _ASM_GENERIC_BITOPS_FFS_H_ -#define _ASM_GENERIC_BITOPS_FFS_H_ - -/** - * ffs - find first bit set - * @x: the word to search - * - * This is defined the same way as - * the libc and compiler builtin ffs routines, therefore - * differs in spirit from the above ffz (man ffs). - */ -static inline int ffs(int x) -{ - int r = 1; - - if (!x) - return 0; - if (!(x & 0xffff)) { - x >>= 16; - r += 16; - } - if (!(x & 0xff)) { - x >>= 8; - r += 8; - } - if (!(x & 0xf)) { - x >>= 4; - r += 4; - } - if (!(x & 3)) { - x >>= 2; - r += 2; - } - if (!(x & 1)) { - x >>= 1; - r += 1; - } - return r; -} - -#endif /* _ASM_GENERIC_BITOPS_FFS_H_ */ diff --git a/tools/testing/radix-tree/linux/bitops/ffz.h b/tools/testing/radix-tree/linux/bitops/ffz.h deleted file mode 100644 index 6744bd4cdf46..000000000000 --- a/tools/testing/radix-tree/linux/bitops/ffz.h +++ /dev/null @@ -1,12 +0,0 @@ -#ifndef _ASM_GENERIC_BITOPS_FFZ_H_ -#define _ASM_GENERIC_BITOPS_FFZ_H_ - -/* - * ffz - find first zero in word. - * @word: The word to search - * - * Undefined if no zero exists, so code should check against ~0UL first. - */ -#define ffz(x) __ffs(~(x)) - -#endif /* _ASM_GENERIC_BITOPS_FFZ_H_ */ diff --git a/tools/testing/radix-tree/linux/bitops/find.h b/tools/testing/radix-tree/linux/bitops/find.h deleted file mode 100644 index 72a51e5a12ef..000000000000 --- a/tools/testing/radix-tree/linux/bitops/find.h +++ /dev/null @@ -1,13 +0,0 @@ -#ifndef _ASM_GENERIC_BITOPS_FIND_H_ -#define _ASM_GENERIC_BITOPS_FIND_H_ - -extern unsigned long find_next_bit(const unsigned long *addr, unsigned long - size, unsigned long offset); - -extern unsigned long find_next_zero_bit(const unsigned long *addr, unsigned - long size, unsigned long offset); - -#define find_first_bit(addr, size) find_next_bit((addr), (size), 0) -#define find_first_zero_bit(addr, size) find_next_zero_bit((addr), (size), 0) - -#endif /*_ASM_GENERIC_BITOPS_FIND_H_ */ diff --git a/tools/testing/radix-tree/linux/bitops/fls.h b/tools/testing/radix-tree/linux/bitops/fls.h deleted file mode 100644 index 850859bc5069..000000000000 --- a/tools/testing/radix-tree/linux/bitops/fls.h +++ /dev/null @@ -1,41 +0,0 @@ -#ifndef _ASM_GENERIC_BITOPS_FLS_H_ -#define _ASM_GENERIC_BITOPS_FLS_H_ - -/** - * fls - find last (most-significant) bit set - * @x: the word to search - * - * This is defined the same way as ffs. - * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32. - */ - -static inline int fls(int x) -{ - int r = 32; - - if (!x) - return 0; - if (!(x & 0xffff0000u)) { - x <<= 16; - r -= 16; - } - if (!(x & 0xff000000u)) { - x <<= 8; - r -= 8; - } - if (!(x & 0xf0000000u)) { - x <<= 4; - r -= 4; - } - if (!(x & 0xc0000000u)) { - x <<= 2; - r -= 2; - } - if (!(x & 0x80000000u)) { - x <<= 1; - r -= 1; - } - return r; -} - -#endif /* _ASM_GENERIC_BITOPS_FLS_H_ */ diff --git a/tools/testing/radix-tree/linux/bitops/fls64.h b/tools/testing/radix-tree/linux/bitops/fls64.h deleted file mode 100644 index 1b6b17ce2428..000000000000 --- a/tools/testing/radix-tree/linux/bitops/fls64.h +++ /dev/null @@ -1,14 +0,0 @@ -#ifndef _ASM_GENERIC_BITOPS_FLS64_H_ -#define _ASM_GENERIC_BITOPS_FLS64_H_ - -#include <asm/types.h> - -static inline int fls64(__u64 x) -{ - __u32 h = x >> 32; - if (h) - return fls(h) + 32; - return fls(x); -} - -#endif /* _ASM_GENERIC_BITOPS_FLS64_H_ */ diff --git a/tools/testing/radix-tree/linux/bitops/hweight.h b/tools/testing/radix-tree/linux/bitops/hweight.h deleted file mode 100644 index fbbc383771da..000000000000 --- a/tools/testing/radix-tree/linux/bitops/hweight.h +++ /dev/null @@ -1,11 +0,0 @@ -#ifndef _ASM_GENERIC_BITOPS_HWEIGHT_H_ -#define _ASM_GENERIC_BITOPS_HWEIGHT_H_ - -#include <asm/types.h> - -extern unsigned int hweight32(unsigned int w); -extern unsigned int hweight16(unsigned int w); -extern unsigned int hweight8(unsigned int w); -extern unsigned long hweight64(__u64 w); - -#endif /* _ASM_GENERIC_BITOPS_HWEIGHT_H_ */ diff --git a/tools/testing/radix-tree/linux/bitops/le.h b/tools/testing/radix-tree/linux/bitops/le.h deleted file mode 100644 index b9c7e5d2d2ad..000000000000 --- a/tools/testing/radix-tree/linux/bitops/le.h +++ /dev/null @@ -1,53 +0,0 @@ -#ifndef _ASM_GENERIC_BITOPS_LE_H_ -#define _ASM_GENERIC_BITOPS_LE_H_ - -#include <asm/types.h> -#include <asm/byteorder.h> - -#define BITOP_WORD(nr) ((nr) / BITS_PER_LONG) -#define BITOP_LE_SWIZZLE ((BITS_PER_LONG-1) & ~0x7) - -#if defined(__LITTLE_ENDIAN) - -#define generic_test_le_bit(nr, addr) test_bit(nr, addr) -#define generic___set_le_bit(nr, addr) __set_bit(nr, addr) -#define generic___clear_le_bit(nr, addr) __clear_bit(nr, addr) - -#define generic_test_and_set_le_bit(nr, addr) test_and_set_bit(nr, addr) -#define generic_test_and_clear_le_bit(nr, addr) test_and_clear_bit(nr, addr) - -#define generic___test_and_set_le_bit(nr, addr) __test_and_set_bit(nr, addr) -#define generic___test_and_clear_le_bit(nr, addr) __test_and_clear_bit(nr, addr) - -#define generic_find_next_zero_le_bit(addr, size, offset) find_next_zero_bit(addr, size, offset) - -#elif defined(__BIG_ENDIAN) - -#define generic_test_le_bit(nr, addr) \ - test_bit((nr) ^ BITOP_LE_SWIZZLE, (addr)) -#define generic___set_le_bit(nr, addr) \ - __set_bit((nr) ^ BITOP_LE_SWIZZLE, (addr)) -#define generic___clear_le_bit(nr, addr) \ - __clear_bit((nr) ^ BITOP_LE_SWIZZLE, (addr)) - -#define generic_test_and_set_le_bit(nr, addr) \ - test_and_set_bit((nr) ^ BITOP_LE_SWIZZLE, (addr)) -#define generic_test_and_clear_le_bit(nr, addr) \ - test_and_clear_bit((nr) ^ BITOP_LE_SWIZZLE, (addr)) - -#define generic___test_and_set_le_bit(nr, addr) \ - __test_and_set_bit((nr) ^ BITOP_LE_SWIZZLE, (addr)) -#define generic___test_and_clear_le_bit(nr, addr) \ - __test_and_clear_bit((nr) ^ BITOP_LE_SWIZZLE, (addr)) - -extern unsigned long generic_find_next_zero_le_bit(const unsigned long *addr, - unsigned long size, unsigned long offset); - -#else -#error "Please fix <asm/byteorder.h>" -#endif - -#define generic_find_first_zero_le_bit(addr, size) \ - generic_find_next_zero_le_bit((addr), (size), 0) - -#endif /* _ASM_GENERIC_BITOPS_LE_H_ */ diff --git a/tools/testing/radix-tree/linux/bitops/non-atomic.h b/tools/testing/radix-tree/linux/bitops/non-atomic.h deleted file mode 100644 index 6a1bcb9d2c4a..000000000000 --- a/tools/testing/radix-tree/linux/bitops/non-atomic.h +++ /dev/null @@ -1,110 +0,0 @@ -#ifndef _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ -#define _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ - -#include <asm/types.h> - -#define BITOP_WORD(nr) ((nr) / BITS_PER_LONG) - -/** - * __set_bit - Set a bit in memory - * @nr: the bit to set - * @addr: the address to start counting from - * - * Unlike set_bit(), this function is non-atomic and may be reordered. - * If it's called on the same region of memory simultaneously, the effect - * may be that only one operation succeeds. - */ -static inline void __set_bit(int nr, volatile unsigned long *addr) -{ - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr); - - *p |= mask; -} - -static inline void __clear_bit(int nr, volatile unsigned long *addr) -{ - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr); - - *p &= ~mask; -} - -/** - * __change_bit - Toggle a bit in memory - * @nr: the bit to change - * @addr: the address to start counting from - * - * Unlike change_bit(), this function is non-atomic and may be reordered. - * If it's called on the same region of memory simultaneously, the effect - * may be that only one operation succeeds. - */ -static inline void __change_bit(int nr, volatile unsigned long *addr) -{ - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr); - - *p ^= mask; -} - -/** - * __test_and_set_bit - Set a bit and return its old value - * @nr: Bit to set - * @addr: Address to count from - * - * This operation is non-atomic and can be reordered. - * If two examples of this operation race, one can appear to succeed - * but actually fail. You must protect multiple accesses with a lock. - */ -static inline int __test_and_set_bit(int nr, volatile unsigned long *addr) -{ - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr); - unsigned long old = *p; - - *p = old | mask; - return (old & mask) != 0; -} - -/** - * __test_and_clear_bit - Clear a bit and return its old value - * @nr: Bit to clear - * @addr: Address to count from - * - * This operation is non-atomic and can be reordered. - * If two examples of this operation race, one can appear to succeed - * but actually fail. You must protect multiple accesses with a lock. - */ -static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr) -{ - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr); - unsigned long old = *p; - - *p = old & ~mask; - return (old & mask) != 0; -} - -/* WARNING: non atomic and it can be reordered! */ -static inline int __test_and_change_bit(int nr, - volatile unsigned long *addr) -{ - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr); - unsigned long old = *p; - - *p = old ^ mask; - return (old & mask) != 0; -} - -/** - * test_bit - Determine whether a bit is set - * @nr: bit number to test - * @addr: Address to start counting from - */ -static inline int test_bit(int nr, const volatile unsigned long *addr) -{ - return 1UL & (addr[BITOP_WORD(nr)] >> (nr & (BITS_PER_LONG-1))); -} - -#endif /* _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ */ diff --git a/tools/testing/radix-tree/linux/export.h b/tools/testing/radix-tree/linux/export.h deleted file mode 100644 index b6afd131998d..000000000000 --- a/tools/testing/radix-tree/linux/export.h +++ /dev/null @@ -1,2 +0,0 @@ - -#define EXPORT_SYMBOL(sym) diff --git a/tools/testing/radix-tree/linux/gfp.h b/tools/testing/radix-tree/linux/gfp.h index 5b09b2ce6c33..39a0dcb9475a 100644 --- a/tools/testing/radix-tree/linux/gfp.h +++ b/tools/testing/radix-tree/linux/gfp.h @@ -1,6 +1,8 @@ #ifndef _GFP_H #define _GFP_H +#include <linux/types.h> + #define __GFP_BITS_SHIFT 26 #define __GFP_BITS_MASK ((gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) @@ -13,10 +15,12 @@ #define __GFP_DIRECT_RECLAIM 0x400000u #define __GFP_KSWAPD_RECLAIM 0x2000000u -#define __GFP_RECLAIM (__GFP_DIRECT_RECLAIM|__GFP_KSWAPD_RECLAIM) +#define __GFP_RECLAIM (__GFP_DIRECT_RECLAIM|__GFP_KSWAPD_RECLAIM) + +#define GFP_ATOMIC (__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM) +#define GFP_KERNEL (__GFP_RECLAIM | __GFP_IO | __GFP_FS) +#define GFP_NOWAIT (__GFP_KSWAPD_RECLAIM) -#define GFP_ATOMIC (__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM) -#define GFP_KERNEL (__GFP_RECLAIM | __GFP_IO | __GFP_FS) static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags) { diff --git a/tools/testing/radix-tree/linux/idr.h b/tools/testing/radix-tree/linux/idr.h new file mode 100644 index 000000000000..4e342f2e37cf --- /dev/null +++ b/tools/testing/radix-tree/linux/idr.h @@ -0,0 +1 @@ +#include "../../../../include/linux/idr.h" diff --git a/tools/testing/radix-tree/linux/init.h b/tools/testing/radix-tree/linux/init.h index 360cabb3c4e7..1bb0afc21309 100644 --- a/tools/testing/radix-tree/linux/init.h +++ b/tools/testing/radix-tree/linux/init.h @@ -1 +1 @@ -/* An empty file stub that allows radix-tree.c to compile. */ +#define __init diff --git a/tools/testing/radix-tree/linux/kernel.h b/tools/testing/radix-tree/linux/kernel.h index 9b43b4975d83..b21a77fddcf7 100644 --- a/tools/testing/radix-tree/linux/kernel.h +++ b/tools/testing/radix-tree/linux/kernel.h @@ -1,64 +1,21 @@ #ifndef _KERNEL_H #define _KERNEL_H -#include <assert.h> +#include "../../include/linux/kernel.h" #include <string.h> #include <stdio.h> -#include <stddef.h> #include <limits.h> -#include "../../include/linux/compiler.h" -#include "../../include/linux/err.h" +#include <linux/compiler.h> +#include <linux/err.h> +#include <linux/bitops.h> +#include <linux/log2.h> #include "../../../include/linux/kconfig.h" -#ifdef BENCHMARK -#define RADIX_TREE_MAP_SHIFT 6 -#else -#define RADIX_TREE_MAP_SHIFT 3 -#endif - -#ifndef NULL -#define NULL 0 -#endif - -#define BUG_ON(expr) assert(!(expr)) -#define WARN_ON(expr) assert(!(expr)) -#define __init -#define __must_check -#define panic(expr) #define printk printf -#define __force -#define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d)) #define pr_debug printk - -#define smp_rmb() barrier() -#define smp_wmb() barrier() -#define cpu_relax() barrier() +#define pr_cont printk #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0])) -#define container_of(ptr, type, member) ({ \ - const typeof( ((type *)0)->member ) *__mptr = (ptr); \ - (type *)( (char *)__mptr - offsetof(type, member) );}) -#define min(a, b) ((a) < (b) ? (a) : (b)) - -#define cond_resched() sched_yield() - -static inline int in_interrupt(void) -{ - return 0; -} - -/* - * This looks more complex than it should be. But we need to - * get the type for the ~ right in round_down (it needs to be - * as wide as the result!), and we want to evaluate the macro - * arguments just once each. - */ -#define __round_mask(x, y) ((__typeof__(x))((y)-1)) -#define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1) -#define round_down(x, y) ((x) & ~__round_mask(x, y)) - -#define xchg(ptr, x) uatomic_xchg(ptr, x) - #endif /* _KERNEL_H */ diff --git a/tools/testing/radix-tree/linux/mempool.h b/tools/testing/radix-tree/linux/mempool.h deleted file mode 100644 index 6a2dc55b41d6..000000000000 --- a/tools/testing/radix-tree/linux/mempool.h +++ /dev/null @@ -1,16 +0,0 @@ - -#include <linux/slab.h> - -typedef void *(mempool_alloc_t)(int gfp_mask, void *pool_data); -typedef void (mempool_free_t)(void *element, void *pool_data); - -typedef struct { - mempool_alloc_t *alloc; - mempool_free_t *free; - void *data; -} mempool_t; - -void *mempool_alloc(mempool_t *pool, int gfp_mask); -void mempool_free(void *element, mempool_t *pool); -mempool_t *mempool_create(int min_nr, mempool_alloc_t *alloc_fn, - mempool_free_t *free_fn, void *pool_data); diff --git a/tools/testing/radix-tree/linux/percpu.h b/tools/testing/radix-tree/linux/percpu.h index 5837f1d56f17..3ea01a1a88c2 100644 --- a/tools/testing/radix-tree/linux/percpu.h +++ b/tools/testing/radix-tree/linux/percpu.h @@ -1,7 +1,10 @@ - +#define DECLARE_PER_CPU(type, val) extern type val #define DEFINE_PER_CPU(type, val) type val #define __get_cpu_var(var) var #define this_cpu_ptr(var) var +#define this_cpu_read(var) var +#define this_cpu_xchg(var, val) uatomic_xchg(&var, val) +#define this_cpu_cmpxchg(var, old, new) uatomic_cmpxchg(&var, old, new) #define per_cpu_ptr(ptr, cpu) ({ (void)(cpu); (ptr); }) #define per_cpu(var, cpu) (*per_cpu_ptr(&(var), cpu)) diff --git a/tools/testing/radix-tree/linux/preempt.h b/tools/testing/radix-tree/linux/preempt.h index 65c04c226965..35c5ac81529f 100644 --- a/tools/testing/radix-tree/linux/preempt.h +++ b/tools/testing/radix-tree/linux/preempt.h @@ -1,4 +1,14 @@ +#ifndef __LINUX_PREEMPT_H +#define __LINUX_PREEMPT_H + extern int preempt_count; #define preempt_disable() uatomic_inc(&preempt_count) #define preempt_enable() uatomic_dec(&preempt_count) + +static inline int in_interrupt(void) +{ + return 0; +} + +#endif /* __LINUX_PREEMPT_H */ diff --git a/tools/testing/radix-tree/linux/radix-tree.h b/tools/testing/radix-tree/linux/radix-tree.h index ce694ddd4aea..bf1bb231f9b5 100644 --- a/tools/testing/radix-tree/linux/radix-tree.h +++ b/tools/testing/radix-tree/linux/radix-tree.h @@ -1 +1,26 @@ +#ifndef _TEST_RADIX_TREE_H +#define _TEST_RADIX_TREE_H + +#include "generated/map-shift.h" #include "../../../../include/linux/radix-tree.h" + +extern int kmalloc_verbose; +extern int test_verbose; + +static inline void trace_call_rcu(struct rcu_head *head, + void (*func)(struct rcu_head *head)) +{ + if (kmalloc_verbose) + printf("Delaying free of %p to slab\n", (char *)head - + offsetof(struct radix_tree_node, rcu_head)); + call_rcu(head, func); +} + +#define printv(verbosity_level, fmt, ...) \ + if(test_verbose >= verbosity_level) \ + printf(fmt, ##__VA_ARGS__) + +#undef call_rcu +#define call_rcu(x, y) trace_call_rcu(x, y) + +#endif /* _TEST_RADIX_TREE_H */ diff --git a/tools/testing/radix-tree/linux/types.h b/tools/testing/radix-tree/linux/types.h deleted file mode 100644 index 8491d89873bb..000000000000 --- a/tools/testing/radix-tree/linux/types.h +++ /dev/null @@ -1,23 +0,0 @@ -#ifndef _TYPES_H -#define _TYPES_H - -#include "../../include/linux/types.h" - -#define __rcu -#define __read_mostly - -static inline void INIT_LIST_HEAD(struct list_head *list) -{ - list->next = list; - list->prev = list; -} - -typedef struct { - unsigned int x; -} spinlock_t; - -#define uninitialized_var(x) x = x - -#include <linux/gfp.h> - -#endif diff --git a/tools/testing/radix-tree/main.c b/tools/testing/radix-tree/main.c index f7e9801a6754..bc9a78449572 100644 --- a/tools/testing/radix-tree/main.c +++ b/tools/testing/radix-tree/main.c @@ -3,6 +3,7 @@ #include <unistd.h> #include <time.h> #include <assert.h> +#include <limits.h> #include <linux/slab.h> #include <linux/radix-tree.h> @@ -67,7 +68,7 @@ void big_gang_check(bool long_run) for (i = 0; i < (long_run ? 1000 : 3); i++) { __big_gang_check(); - printf("%d ", i); + printv(2, "%d ", i); fflush(stdout); } } @@ -128,14 +129,19 @@ void check_copied_tags(struct radix_tree_root *tree, unsigned long start, unsign putchar('.'); */ if (idx[i] < start || idx[i] > end) { if (item_tag_get(tree, idx[i], totag)) { - printf("%lu-%lu: %lu, tags %d-%d\n", start, end, idx[i], item_tag_get(tree, idx[i], fromtag), item_tag_get(tree, idx[i], totag)); + printv(2, "%lu-%lu: %lu, tags %d-%d\n", start, + end, idx[i], item_tag_get(tree, idx[i], + fromtag), + item_tag_get(tree, idx[i], totag)); } assert(!item_tag_get(tree, idx[i], totag)); continue; } if (item_tag_get(tree, idx[i], fromtag) ^ item_tag_get(tree, idx[i], totag)) { - printf("%lu-%lu: %lu, tags %d-%d\n", start, end, idx[i], item_tag_get(tree, idx[i], fromtag), item_tag_get(tree, idx[i], totag)); + printv(2, "%lu-%lu: %lu, tags %d-%d\n", start, end, + idx[i], item_tag_get(tree, idx[i], fromtag), + item_tag_get(tree, idx[i], totag)); } assert(!(item_tag_get(tree, idx[i], fromtag) ^ item_tag_get(tree, idx[i], totag))); @@ -237,7 +243,7 @@ static void __locate_check(struct radix_tree_root *tree, unsigned long index, item = item_lookup(tree, index); index2 = find_item(tree, item); if (index != index2) { - printf("index %ld order %d inserted; found %ld\n", + printv(2, "index %ld order %d inserted; found %ld\n", index, order, index2); abort(); } @@ -288,43 +294,48 @@ static void single_thread_tests(bool long_run) { int i; - printf("starting single_thread_tests: %d allocated, preempt %d\n", + printv(1, "starting single_thread_tests: %d allocated, preempt %d\n", nr_allocated, preempt_count); multiorder_checks(); rcu_barrier(); - printf("after multiorder_check: %d allocated, preempt %d\n", + printv(2, "after multiorder_check: %d allocated, preempt %d\n", nr_allocated, preempt_count); locate_check(); rcu_barrier(); - printf("after locate_check: %d allocated, preempt %d\n", + printv(2, "after locate_check: %d allocated, preempt %d\n", nr_allocated, preempt_count); tag_check(); rcu_barrier(); - printf("after tag_check: %d allocated, preempt %d\n", + printv(2, "after tag_check: %d allocated, preempt %d\n", nr_allocated, preempt_count); gang_check(); rcu_barrier(); - printf("after gang_check: %d allocated, preempt %d\n", + printv(2, "after gang_check: %d allocated, preempt %d\n", nr_allocated, preempt_count); add_and_check(); rcu_barrier(); - printf("after add_and_check: %d allocated, preempt %d\n", + printv(2, "after add_and_check: %d allocated, preempt %d\n", nr_allocated, preempt_count); dynamic_height_check(); rcu_barrier(); - printf("after dynamic_height_check: %d allocated, preempt %d\n", + printv(2, "after dynamic_height_check: %d allocated, preempt %d\n", + nr_allocated, preempt_count); + idr_checks(); + ida_checks(); + rcu_barrier(); + printv(2, "after idr_checks: %d allocated, preempt %d\n", nr_allocated, preempt_count); big_gang_check(long_run); rcu_barrier(); - printf("after big_gang_check: %d allocated, preempt %d\n", + printv(2, "after big_gang_check: %d allocated, preempt %d\n", nr_allocated, preempt_count); for (i = 0; i < (long_run ? 2000 : 3); i++) { copy_tag_check(); - printf("%d ", i); + printv(2, "%d ", i); fflush(stdout); } rcu_barrier(); - printf("after copy_tag_check: %d allocated, preempt %d\n", + printv(2, "after copy_tag_check: %d allocated, preempt %d\n", nr_allocated, preempt_count); } @@ -334,25 +345,30 @@ int main(int argc, char **argv) int opt; unsigned int seed = time(NULL); - while ((opt = getopt(argc, argv, "ls:")) != -1) { + while ((opt = getopt(argc, argv, "ls:v")) != -1) { if (opt == 'l') long_run = true; else if (opt == 's') seed = strtoul(optarg, NULL, 0); + else if (opt == 'v') + test_verbose++; } printf("random seed %u\n", seed); srand(seed); + printf("running tests\n"); + rcu_register_thread(); radix_tree_init(); regression1_test(); regression2_test(); regression3_test(); - iteration_test(0, 10); - iteration_test(7, 20); + iteration_test(0, 10 + 90 * long_run); + iteration_test(7, 10 + 90 * long_run); single_thread_tests(long_run); + ida_thread_tests(); /* Free any remaining preallocated nodes */ radix_tree_cpu_dead(0); @@ -360,9 +376,11 @@ int main(int argc, char **argv) benchmark(); rcu_barrier(); - printf("after rcu_barrier: %d allocated, preempt %d\n", + printv(2, "after rcu_barrier: %d allocated, preempt %d\n", nr_allocated, preempt_count); rcu_unregister_thread(); + printf("tests completed\n"); + exit(0); } diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c index f79812a5e070..06c71178d07d 100644 --- a/tools/testing/radix-tree/multiorder.c +++ b/tools/testing/radix-tree/multiorder.c @@ -30,7 +30,7 @@ static void __multiorder_tag_test(int index, int order) /* our canonical entry */ base = index & ~((1 << order) - 1); - printf("Multiorder tag test with index %d, canonical entry %d\n", + printv(2, "Multiorder tag test with index %d, canonical entry %d\n", index, base); err = item_insert_order(&tree, index, order); @@ -150,7 +150,7 @@ static void multiorder_check(unsigned long index, int order) struct item *item2 = item_create(min, order); RADIX_TREE(tree, GFP_KERNEL); - printf("Multiorder index %ld, order %d\n", index, order); + printv(2, "Multiorder index %ld, order %d\n", index, order); assert(item_insert_order(&tree, index, order) == 0); @@ -188,7 +188,7 @@ static void multiorder_shrink(unsigned long index, int order) RADIX_TREE(tree, GFP_KERNEL); struct radix_tree_node *node; - printf("Multiorder shrink index %ld, order %d\n", index, order); + printv(2, "Multiorder shrink index %ld, order %d\n", index, order); assert(item_insert_order(&tree, 0, order) == 0); @@ -209,7 +209,8 @@ static void multiorder_shrink(unsigned long index, int order) item_check_absent(&tree, i); if (!item_delete(&tree, 0)) { - printf("failed to delete index %ld (order %d)\n", index, order); abort(); + printv(2, "failed to delete index %ld (order %d)\n", index, order); + abort(); } for (i = 0; i < 2*max; i++) @@ -234,7 +235,7 @@ void multiorder_iteration(void) void **slot; int i, j, err; - printf("Multiorder iteration test\n"); + printv(1, "Multiorder iteration test\n"); #define NUM_ENTRIES 11 int index[NUM_ENTRIES] = {0, 2, 4, 8, 16, 32, 34, 36, 64, 72, 128}; @@ -275,7 +276,7 @@ void multiorder_tagged_iteration(void) void **slot; int i, j; - printf("Multiorder tagged iteration test\n"); + printv(1, "Multiorder tagged iteration test\n"); #define MT_NUM_ENTRIES 9 int index[MT_NUM_ENTRIES] = {0, 2, 4, 16, 32, 40, 64, 72, 128}; @@ -355,6 +356,10 @@ void multiorder_tagged_iteration(void) item_kill_tree(&tree); } +/* + * Basic join checks: make sure we can't find an entry in the tree after + * a larger entry has replaced it + */ static void multiorder_join1(unsigned long index, unsigned order1, unsigned order2) { @@ -373,6 +378,10 @@ static void multiorder_join1(unsigned long index, item_kill_tree(&tree); } +/* + * Check that the accounting of exceptional entries is handled correctly + * by joining an exceptional entry to a normal pointer. + */ static void multiorder_join2(unsigned order1, unsigned order2) { RADIX_TREE(tree, GFP_KERNEL); @@ -386,6 +395,9 @@ static void multiorder_join2(unsigned order1, unsigned order2) assert(item2 == (void *)0x12UL); assert(node->exceptional == 1); + item2 = radix_tree_lookup(&tree, 0); + free(item2); + radix_tree_join(&tree, 0, order1, item1); item2 = __radix_tree_lookup(&tree, 1 << order2, &node, NULL); assert(item2 == item1); @@ -453,7 +465,7 @@ static void check_mem(unsigned old_order, unsigned new_order, unsigned alloc) { struct radix_tree_preload *rtp = &radix_tree_preloads; if (rtp->nr != 0) - printf("split(%u %u) remaining %u\n", old_order, new_order, + printv(2, "split(%u %u) remaining %u\n", old_order, new_order, rtp->nr); /* * Can't check for equality here as some nodes may have been @@ -461,7 +473,7 @@ static void check_mem(unsigned old_order, unsigned new_order, unsigned alloc) * nodes allocated since they should have all been preloaded. */ if (nr_allocated > alloc) - printf("split(%u %u) allocated %u %u\n", old_order, new_order, + printv(2, "split(%u %u) allocated %u %u\n", old_order, new_order, alloc, nr_allocated); } @@ -471,6 +483,7 @@ static void __multiorder_split(int old_order, int new_order) void **slot; struct radix_tree_iter iter; unsigned alloc; + struct item *item; radix_tree_preload(GFP_KERNEL); assert(item_insert_order(&tree, 0, old_order) == 0); @@ -479,7 +492,7 @@ static void __multiorder_split(int old_order, int new_order) /* Wipe out the preloaded cache or it'll confuse check_mem() */ radix_tree_cpu_dead(0); - radix_tree_tag_set(&tree, 0, 2); + item = radix_tree_tag_set(&tree, 0, 2); radix_tree_split_preload(old_order, new_order, GFP_KERNEL); alloc = nr_allocated; @@ -492,6 +505,7 @@ static void __multiorder_split(int old_order, int new_order) radix_tree_preload_end(); item_kill_tree(&tree); + free(item); } static void __multiorder_split2(int old_order, int new_order) @@ -633,3 +647,10 @@ void multiorder_checks(void) radix_tree_cpu_dead(0); } + +int __weak main(void) +{ + radix_tree_init(); + multiorder_checks(); + return 0; +} diff --git a/tools/testing/radix-tree/regression1.c b/tools/testing/radix-tree/regression1.c index 0d6813a61b37..bf97742fc18c 100644 --- a/tools/testing/radix-tree/regression1.c +++ b/tools/testing/radix-tree/regression1.c @@ -193,7 +193,7 @@ void regression1_test(void) long arg; /* Regression #1 */ - printf("running regression test 1, should finish in under a minute\n"); + printv(1, "running regression test 1, should finish in under a minute\n"); nr_threads = 2; pthread_barrier_init(&worker_barrier, NULL, nr_threads); @@ -216,5 +216,5 @@ void regression1_test(void) free(threads); - printf("regression test 1, done\n"); + printv(1, "regression test 1, done\n"); } diff --git a/tools/testing/radix-tree/regression2.c b/tools/testing/radix-tree/regression2.c index a41325d7a170..42dd2a33ed24 100644 --- a/tools/testing/radix-tree/regression2.c +++ b/tools/testing/radix-tree/regression2.c @@ -80,7 +80,7 @@ void regression2_test(void) unsigned long int start, end; struct page *pages[1]; - printf("running regression test 2 (should take milliseconds)\n"); + printv(1, "running regression test 2 (should take milliseconds)\n"); /* 0. */ for (i = 0; i <= max_slots - 1; i++) { p = page_alloc(); @@ -103,7 +103,7 @@ void regression2_test(void) /* 4. */ for (i = max_slots - 1; i >= 0; i--) - radix_tree_delete(&mt_tree, i); + free(radix_tree_delete(&mt_tree, i)); /* 5. */ // NOTE: start should not be 0 because radix_tree_gang_lookup_tag_slot @@ -114,7 +114,9 @@ void regression2_test(void) PAGECACHE_TAG_TOWRITE); /* We remove all the remained nodes */ - radix_tree_delete(&mt_tree, max_slots); + free(radix_tree_delete(&mt_tree, max_slots)); - printf("regression test 2, done\n"); + BUG_ON(!radix_tree_empty(&mt_tree)); + + printv(1, "regression test 2, done\n"); } diff --git a/tools/testing/radix-tree/regression3.c b/tools/testing/radix-tree/regression3.c index b594841fae85..670c3d2ae7b1 100644 --- a/tools/testing/radix-tree/regression3.c +++ b/tools/testing/radix-tree/regression3.c @@ -34,21 +34,21 @@ void regression3_test(void) void **slot; bool first; - printf("running regression test 3 (should take milliseconds)\n"); + printv(1, "running regression test 3 (should take milliseconds)\n"); radix_tree_insert(&root, 0, ptr0); radix_tree_tag_set(&root, 0, 0); first = true; radix_tree_for_each_tagged(slot, &root, &iter, 0, 0) { - printf("tagged %ld %p\n", iter.index, *slot); + printv(2, "tagged %ld %p\n", iter.index, *slot); if (first) { radix_tree_insert(&root, 1, ptr); radix_tree_tag_set(&root, 1, 0); first = false; } if (radix_tree_deref_retry(*slot)) { - printf("retry at %ld\n", iter.index); + printv(2, "retry at %ld\n", iter.index); slot = radix_tree_iter_retry(&iter); continue; } @@ -57,13 +57,13 @@ void regression3_test(void) first = true; radix_tree_for_each_slot(slot, &root, &iter, 0) { - printf("slot %ld %p\n", iter.index, *slot); + printv(2, "slot %ld %p\n", iter.index, *slot); if (first) { radix_tree_insert(&root, 1, ptr); first = false; } if (radix_tree_deref_retry(*slot)) { - printk("retry at %ld\n", iter.index); + printv(2, "retry at %ld\n", iter.index); slot = radix_tree_iter_retry(&iter); continue; } @@ -72,30 +72,30 @@ void regression3_test(void) first = true; radix_tree_for_each_contig(slot, &root, &iter, 0) { - printk("contig %ld %p\n", iter.index, *slot); + printv(2, "contig %ld %p\n", iter.index, *slot); if (first) { radix_tree_insert(&root, 1, ptr); first = false; } if (radix_tree_deref_retry(*slot)) { - printk("retry at %ld\n", iter.index); + printv(2, "retry at %ld\n", iter.index); slot = radix_tree_iter_retry(&iter); continue; } } radix_tree_for_each_slot(slot, &root, &iter, 0) { - printf("slot %ld %p\n", iter.index, *slot); + printv(2, "slot %ld %p\n", iter.index, *slot); if (!iter.index) { - printf("next at %ld\n", iter.index); + printv(2, "next at %ld\n", iter.index); slot = radix_tree_iter_resume(slot, &iter); } } radix_tree_for_each_contig(slot, &root, &iter, 0) { - printf("contig %ld %p\n", iter.index, *slot); + printv(2, "contig %ld %p\n", iter.index, *slot); if (!iter.index) { - printf("next at %ld\n", iter.index); + printv(2, "next at %ld\n", iter.index); slot = radix_tree_iter_resume(slot, &iter); } } @@ -103,9 +103,9 @@ void regression3_test(void) radix_tree_tag_set(&root, 0, 0); radix_tree_tag_set(&root, 1, 0); radix_tree_for_each_tagged(slot, &root, &iter, 0, 0) { - printf("tagged %ld %p\n", iter.index, *slot); + printv(2, "tagged %ld %p\n", iter.index, *slot); if (!iter.index) { - printf("next at %ld\n", iter.index); + printv(2, "next at %ld\n", iter.index); slot = radix_tree_iter_resume(slot, &iter); } } @@ -113,5 +113,5 @@ void regression3_test(void) radix_tree_delete(&root, 0); radix_tree_delete(&root, 1); - printf("regression test 3 passed\n"); + printv(1, "regression test 3 passed\n"); } diff --git a/tools/testing/radix-tree/tag_check.c b/tools/testing/radix-tree/tag_check.c index fd98c132207a..36dcf7d6945d 100644 --- a/tools/testing/radix-tree/tag_check.c +++ b/tools/testing/radix-tree/tag_check.c @@ -49,10 +49,10 @@ void simple_checks(void) } verify_tag_consistency(&tree, 0); verify_tag_consistency(&tree, 1); - printf("before item_kill_tree: %d allocated\n", nr_allocated); + printv(2, "before item_kill_tree: %d allocated\n", nr_allocated); item_kill_tree(&tree); rcu_barrier(); - printf("after item_kill_tree: %d allocated\n", nr_allocated); + printv(2, "after item_kill_tree: %d allocated\n", nr_allocated); } /* @@ -257,7 +257,7 @@ static void do_thrash(struct radix_tree_root *tree, char *thrash_state, int tag) gang_check(tree, thrash_state, tag); - printf("%d(%d) %d(%d) %d(%d) %d(%d) / " + printv(2, "%d(%d) %d(%d) %d(%d) %d(%d) / " "%d(%d) present, %d(%d) tagged\n", insert_chunk, nr_inserted, delete_chunk, nr_deleted, @@ -296,13 +296,13 @@ static void __leak_check(void) { RADIX_TREE(tree, GFP_KERNEL); - printf("%d: nr_allocated=%d\n", __LINE__, nr_allocated); + printv(2, "%d: nr_allocated=%d\n", __LINE__, nr_allocated); item_insert(&tree, 1000000); - printf("%d: nr_allocated=%d\n", __LINE__, nr_allocated); + printv(2, "%d: nr_allocated=%d\n", __LINE__, nr_allocated); item_delete(&tree, 1000000); - printf("%d: nr_allocated=%d\n", __LINE__, nr_allocated); + printv(2, "%d: nr_allocated=%d\n", __LINE__, nr_allocated); item_kill_tree(&tree); - printf("%d: nr_allocated=%d\n", __LINE__, nr_allocated); + printv(2, "%d: nr_allocated=%d\n", __LINE__, nr_allocated); } static void single_check(void) @@ -330,21 +330,50 @@ static void single_check(void) item_kill_tree(&tree); } +void radix_tree_clear_tags_test(void) +{ + unsigned long index; + struct radix_tree_node *node; + struct radix_tree_iter iter; + void **slot; + + RADIX_TREE(tree, GFP_KERNEL); + + item_insert(&tree, 0); + item_tag_set(&tree, 0, 0); + __radix_tree_lookup(&tree, 0, &node, &slot); + radix_tree_clear_tags(&tree, node, slot); + assert(item_tag_get(&tree, 0, 0) == 0); + + for (index = 0; index < 1000; index++) { + item_insert(&tree, index); + item_tag_set(&tree, index, 0); + } + + radix_tree_for_each_slot(slot, &tree, &iter, 0) { + radix_tree_clear_tags(&tree, iter.node, slot); + assert(item_tag_get(&tree, iter.index, 0) == 0); + } + + item_kill_tree(&tree); +} + void tag_check(void) { single_check(); extend_checks(); contract_checks(); rcu_barrier(); - printf("after extend_checks: %d allocated\n", nr_allocated); + printv(2, "after extend_checks: %d allocated\n", nr_allocated); __leak_check(); leak_check(); rcu_barrier(); - printf("after leak_check: %d allocated\n", nr_allocated); + printv(2, "after leak_check: %d allocated\n", nr_allocated); simple_checks(); rcu_barrier(); - printf("after simple_checks: %d allocated\n", nr_allocated); + printv(2, "after simple_checks: %d allocated\n", nr_allocated); thrash_tags(); rcu_barrier(); - printf("after thrash_tags: %d allocated\n", nr_allocated); + printv(2, "after thrash_tags: %d allocated\n", nr_allocated); + radix_tree_clear_tags_test(); } diff --git a/tools/testing/radix-tree/test.c b/tools/testing/radix-tree/test.c index e5726e373646..1a257d738a1e 100644 --- a/tools/testing/radix-tree/test.c +++ b/tools/testing/radix-tree/test.c @@ -29,15 +29,28 @@ int __item_insert(struct radix_tree_root *root, struct item *item) return __radix_tree_insert(root, item->index, item->order, item); } -int item_insert(struct radix_tree_root *root, unsigned long index) +struct item *item_create(unsigned long index, unsigned int order) { - return __item_insert(root, item_create(index, 0)); + struct item *ret = malloc(sizeof(*ret)); + + ret->index = index; + ret->order = order; + return ret; } int item_insert_order(struct radix_tree_root *root, unsigned long index, unsigned order) { - return __item_insert(root, item_create(index, order)); + struct item *item = item_create(index, order); + int err = __item_insert(root, item); + if (err) + free(item); + return err; +} + +int item_insert(struct radix_tree_root *root, unsigned long index) +{ + return item_insert_order(root, index, 0); } void item_sanity(struct item *item, unsigned long index) @@ -61,15 +74,6 @@ int item_delete(struct radix_tree_root *root, unsigned long index) return 0; } -struct item *item_create(unsigned long index, unsigned int order) -{ - struct item *ret = malloc(sizeof(*ret)); - - ret->index = index; - ret->order = order; - return ret; -} - void item_check_present(struct radix_tree_root *root, unsigned long index) { struct item *item; diff --git a/tools/testing/radix-tree/test.h b/tools/testing/radix-tree/test.h index 056a23b56467..0f8220cc6166 100644 --- a/tools/testing/radix-tree/test.h +++ b/tools/testing/radix-tree/test.h @@ -34,6 +34,9 @@ void tag_check(void); void multiorder_checks(void); void iteration_test(unsigned order, unsigned duration); void benchmark(void); +void idr_checks(void); +void ida_checks(void); +void ida_thread_tests(void); struct item * item_tag_set(struct radix_tree_root *root, unsigned long index, int tag); diff --git a/tools/testing/selftests/.gitignore b/tools/testing/selftests/.gitignore index f0600d20ce7d..91750352459d 100644 --- a/tools/testing/selftests/.gitignore +++ b/tools/testing/selftests/.gitignore @@ -1 +1,5 @@ kselftest +gpiogpio-event-mon +gpiogpio-hammer +gpioinclude/ +gpiolsgpio diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 831022b12848..26ce4f7168be 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -1,6 +1,7 @@ TARGETS = bpf TARGETS += breakpoints TARGETS += capabilities +TARGETS += cpufreq TARGETS += cpu-hotplug TARGETS += efivarfs TARGETS += exec @@ -8,6 +9,7 @@ TARGETS += firmware TARGETS += ftrace TARGETS += futex TARGETS += gpio +TARGETS += intel_pstate TARGETS += ipc TARGETS += kcmp TARGETS += lib @@ -24,6 +26,7 @@ TARGETS += ptrace TARGETS += seccomp TARGETS += sigaltstack TARGETS += size +TARGETS += splice TARGETS += static_keys TARGETS += sync TARGETS += sysctl @@ -36,7 +39,7 @@ TARGETS += x86 TARGETS += zram #Please keep the TARGETS list alphabetically sorted # Run "make quicktest=1 run_tests" or -# "make quicktest=1 kselftest from top level Makefile +# "make quicktest=1 kselftest" from top level Makefile TARGETS_HOTPLUG = cpu-hotplug TARGETS_HOTPLUG += memory-hotplug @@ -49,29 +52,44 @@ override LDFLAGS = override MAKEFLAGS = endif +BUILD := $(O) +ifndef BUILD + BUILD := $(KBUILD_OUTPUT) +endif +ifndef BUILD + BUILD := $(shell pwd) +endif + +export BUILD all: - for TARGET in $(TARGETS); do \ - make -C $$TARGET; \ + for TARGET in $(TARGETS); do \ + BUILD_TARGET=$$BUILD/$$TARGET; \ + mkdir $$BUILD_TARGET -p; \ + make OUTPUT=$$BUILD_TARGET -C $$TARGET;\ done; run_tests: all for TARGET in $(TARGETS); do \ - make -C $$TARGET run_tests; \ + BUILD_TARGET=$$BUILD/$$TARGET; \ + make OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests;\ done; hotplug: for TARGET in $(TARGETS_HOTPLUG); do \ - make -C $$TARGET; \ + BUILD_TARGET=$$BUILD/$$TARGET; \ + make OUTPUT=$$BUILD_TARGET -C $$TARGET;\ done; run_hotplug: hotplug for TARGET in $(TARGETS_HOTPLUG); do \ - make -C $$TARGET run_full_test; \ + BUILD_TARGET=$$BUILD/$$TARGET; \ + make OUTPUT=$$BUILD_TARGET -C $$TARGET run_full_test;\ done; clean_hotplug: for TARGET in $(TARGETS_HOTPLUG); do \ - make -C $$TARGET clean; \ + BUILD_TARGET=$$BUILD/$$TARGET; \ + make OUTPUT=$$BUILD_TARGET -C $$TARGET clean;\ done; run_pstore_crash: @@ -86,7 +104,8 @@ ifdef INSTALL_PATH @# Ask all targets to install their files mkdir -p $(INSTALL_PATH) for TARGET in $(TARGETS); do \ - make -C $$TARGET INSTALL_PATH=$(INSTALL_PATH)/$$TARGET install; \ + BUILD_TARGET=$$BUILD/$$TARGET; \ + make OUTPUT=$$BUILD_TARGET -C $$TARGET INSTALL_PATH=$(INSTALL_PATH)/$$TARGET install; \ done; @# Ask all targets to emit their test scripts @@ -95,10 +114,11 @@ ifdef INSTALL_PATH echo "ROOT=\$$PWD" >> $(ALL_SCRIPT) for TARGET in $(TARGETS); do \ + BUILD_TARGET=$$BUILD/$$TARGET; \ echo "echo ; echo Running tests in $$TARGET" >> $(ALL_SCRIPT); \ echo "echo ========================================" >> $(ALL_SCRIPT); \ echo "cd $$TARGET" >> $(ALL_SCRIPT); \ - make -s --no-print-directory -C $$TARGET emit_tests >> $(ALL_SCRIPT); \ + make -s --no-print-directory OUTPUT=$$BUILD_TARGET -C $$TARGET emit_tests >> $(ALL_SCRIPT); \ echo "cd \$$ROOT" >> $(ALL_SCRIPT); \ done; @@ -109,7 +129,8 @@ endif clean: for TARGET in $(TARGETS); do \ - make -C $$TARGET clean; \ + BUILD_TARGET=$$BUILD/$$TARGET; \ + make OUTPUT=$$BUILD_TARGET -C $$TARGET clean;\ done; -.PHONY: install +.PHONY: all run_tests hotplug run_hotplug clean_hotplug run_pstore_crash install clean diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index 071431bedde8..541d9d7fad5a 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -1,3 +1,5 @@ test_verifier test_maps test_lru_map +test_lpm_map +test_tag diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 7a5f24543a5f..91edd0566237 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -1,13 +1,39 @@ -CFLAGS += -Wall -O2 -I../../../../usr/include +LIBDIR := ../../../lib +BPFDIR := $(LIBDIR)/bpf +APIDIR := ../../../include/uapi +GENDIR := ../../../../include/generated +GENHDR := $(GENDIR)/autoconf.h -test_objs = test_verifier test_maps test_lru_map +ifneq ($(wildcard $(GENHDR)),) + GENFLAGS := -DHAVE_GENHDR +endif -TEST_PROGS := test_verifier test_maps test_lru_map test_kmod.sh -TEST_FILES := $(test_objs) +CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS) -I../../../include +LDLIBS += -lcap -lelf -all: $(test_objs) +TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs + +TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o + +TEST_PROGS := test_kmod.sh include ../lib.mk -clean: - $(RM) $(test_objs) +BPFOBJ := $(OUTPUT)/libbpf.a + +$(TEST_GEN_PROGS): $(BPFOBJ) + +.PHONY: force + +# force a rebuild of BPFOBJ when its dependencies are updated +force: + +$(BPFOBJ): force + $(MAKE) -C $(BPFDIR) OUTPUT=$(OUTPUT)/ + +CLANG ?= clang + +%.o: %.c + $(CLANG) -I. -I../../../include/uapi -I../../../../samples/bpf/ \ + -Wno-compare-distinct-pointer-types \ + -O2 -target bpf -c $< -o $@ diff --git a/tools/testing/selftests/bpf/bpf_endian.h b/tools/testing/selftests/bpf/bpf_endian.h new file mode 100644 index 000000000000..19d0604f8694 --- /dev/null +++ b/tools/testing/selftests/bpf/bpf_endian.h @@ -0,0 +1,23 @@ +#ifndef __BPF_ENDIAN__ +#define __BPF_ENDIAN__ + +#include <asm/byteorder.h> + +#if __BYTE_ORDER == __LITTLE_ENDIAN +# define __bpf_ntohs(x) __builtin_bswap16(x) +# define __bpf_htons(x) __builtin_bswap16(x) +#elif __BYTE_ORDER == __BIG_ENDIAN +# define __bpf_ntohs(x) (x) +# define __bpf_htons(x) (x) +#else +# error "Fix your __BYTE_ORDER?!" +#endif + +#define bpf_htons(x) \ + (__builtin_constant_p(x) ? \ + __constant_htons(x) : __bpf_htons(x)) +#define bpf_ntohs(x) \ + (__builtin_constant_p(x) ? \ + __constant_ntohs(x) : __bpf_ntohs(x)) + +#endif diff --git a/tools/testing/selftests/bpf/bpf_sys.h b/tools/testing/selftests/bpf/bpf_sys.h deleted file mode 100644 index 6b4565f2a3f2..000000000000 --- a/tools/testing/selftests/bpf/bpf_sys.h +++ /dev/null @@ -1,108 +0,0 @@ -#ifndef __BPF_SYS__ -#define __BPF_SYS__ - -#include <stdint.h> -#include <stdlib.h> - -#include <sys/syscall.h> - -#include <linux/bpf.h> - -static inline __u64 bpf_ptr_to_u64(const void *ptr) -{ - return (__u64)(unsigned long) ptr; -} - -static inline int bpf(int cmd, union bpf_attr *attr, unsigned int size) -{ -#ifdef __NR_bpf - return syscall(__NR_bpf, cmd, attr, size); -#else - fprintf(stderr, "No bpf syscall, kernel headers too old?\n"); - errno = ENOSYS; - return -1; -#endif -} - -static inline int bpf_map_lookup(int fd, const void *key, void *value) -{ - union bpf_attr attr = {}; - - attr.map_fd = fd; - attr.key = bpf_ptr_to_u64(key); - attr.value = bpf_ptr_to_u64(value); - - return bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr)); -} - -static inline int bpf_map_update(int fd, const void *key, const void *value, - uint64_t flags) -{ - union bpf_attr attr = {}; - - attr.map_fd = fd; - attr.key = bpf_ptr_to_u64(key); - attr.value = bpf_ptr_to_u64(value); - attr.flags = flags; - - return bpf(BPF_MAP_UPDATE_ELEM, &attr, sizeof(attr)); -} - -static inline int bpf_map_delete(int fd, const void *key) -{ - union bpf_attr attr = {}; - - attr.map_fd = fd; - attr.key = bpf_ptr_to_u64(key); - - return bpf(BPF_MAP_DELETE_ELEM, &attr, sizeof(attr)); -} - -static inline int bpf_map_next_key(int fd, const void *key, void *next_key) -{ - union bpf_attr attr = {}; - - attr.map_fd = fd; - attr.key = bpf_ptr_to_u64(key); - attr.next_key = bpf_ptr_to_u64(next_key); - - return bpf(BPF_MAP_GET_NEXT_KEY, &attr, sizeof(attr)); -} - -static inline int bpf_map_create(enum bpf_map_type type, uint32_t size_key, - uint32_t size_value, uint32_t max_elem, - uint32_t flags) -{ - union bpf_attr attr = {}; - - attr.map_type = type; - attr.key_size = size_key; - attr.value_size = size_value; - attr.max_entries = max_elem; - attr.map_flags = flags; - - return bpf(BPF_MAP_CREATE, &attr, sizeof(attr)); -} - -static inline int bpf_prog_load(enum bpf_prog_type type, - const struct bpf_insn *insns, size_t size_insns, - const char *license, char *log, size_t size_log) -{ - union bpf_attr attr = {}; - - attr.prog_type = type; - attr.insns = bpf_ptr_to_u64(insns); - attr.insn_cnt = size_insns / sizeof(struct bpf_insn); - attr.license = bpf_ptr_to_u64(license); - - if (size_log > 0) { - attr.log_buf = bpf_ptr_to_u64(log); - attr.log_size = size_log; - attr.log_level = 1; - log[0] = 0; - } - - return bpf(BPF_PROG_LOAD, &attr, sizeof(attr)); -} - -#endif /* __BPF_SYS__ */ diff --git a/tools/testing/selftests/bpf/bpf_util.h b/tools/testing/selftests/bpf/bpf_util.h index 84a5d1823f02..20ecbaa0d85d 100644 --- a/tools/testing/selftests/bpf/bpf_util.h +++ b/tools/testing/selftests/bpf/bpf_util.h @@ -35,4 +35,11 @@ static inline unsigned int bpf_num_possible_cpus(void) return possible_cpus; } +#define __bpf_percpu_val_align __attribute__((__aligned__(8))) + +#define BPF_DECLARE_PERCPU(type, name) \ + struct { type v; /* padding */ } __bpf_percpu_val_align \ + name[bpf_num_possible_cpus()] +#define bpf_percpu(name, cpu) name[(cpu)].v + #endif /* __BPF_UTIL__ */ diff --git a/tools/testing/selftests/bpf/gnu/stubs.h b/tools/testing/selftests/bpf/gnu/stubs.h new file mode 100644 index 000000000000..719225b16626 --- /dev/null +++ b/tools/testing/selftests/bpf/gnu/stubs.h @@ -0,0 +1 @@ +/* dummy .h to trick /usr/include/features.h to work with 'clang -target bpf' */ diff --git a/tools/testing/selftests/bpf/test_iptunnel_common.h b/tools/testing/selftests/bpf/test_iptunnel_common.h new file mode 100644 index 000000000000..e4cd252a1b20 --- /dev/null +++ b/tools/testing/selftests/bpf/test_iptunnel_common.h @@ -0,0 +1,37 @@ +/* Copyright (c) 2016 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#ifndef _TEST_IPTNL_COMMON_H +#define _TEST_IPTNL_COMMON_H + +#include <linux/types.h> + +#define MAX_IPTNL_ENTRIES 256U + +struct vip { + union { + __u32 v6[4]; + __u32 v4; + } daddr; + __u16 dport; + __u16 family; + __u8 protocol; +}; + +struct iptnl_info { + union { + __u32 v6[4]; + __u32 v4; + } saddr; + union { + __u32 v6[4]; + __u32 v4; + } daddr; + __u16 family; + __u8 dmac[6]; +}; + +#endif diff --git a/tools/testing/selftests/bpf/test_l4lb.c b/tools/testing/selftests/bpf/test_l4lb.c new file mode 100644 index 000000000000..1e10c9590991 --- /dev/null +++ b/tools/testing/selftests/bpf/test_l4lb.c @@ -0,0 +1,473 @@ +/* Copyright (c) 2017 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <stddef.h> +#include <stdbool.h> +#include <string.h> +#include <linux/pkt_cls.h> +#include <linux/bpf.h> +#include <linux/in.h> +#include <linux/if_ether.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/icmp.h> +#include <linux/icmpv6.h> +#include <linux/tcp.h> +#include <linux/udp.h> +#include "bpf_helpers.h" +#include "test_iptunnel_common.h" +#include "bpf_endian.h" + +int _version SEC("version") = 1; + +static inline __u32 rol32(__u32 word, unsigned int shift) +{ + return (word << shift) | (word >> ((-shift) & 31)); +} + +/* copy paste of jhash from kernel sources to make sure llvm + * can compile it into valid sequence of bpf instructions + */ +#define __jhash_mix(a, b, c) \ +{ \ + a -= c; a ^= rol32(c, 4); c += b; \ + b -= a; b ^= rol32(a, 6); a += c; \ + c -= b; c ^= rol32(b, 8); b += a; \ + a -= c; a ^= rol32(c, 16); c += b; \ + b -= a; b ^= rol32(a, 19); a += c; \ + c -= b; c ^= rol32(b, 4); b += a; \ +} + +#define __jhash_final(a, b, c) \ +{ \ + c ^= b; c -= rol32(b, 14); \ + a ^= c; a -= rol32(c, 11); \ + b ^= a; b -= rol32(a, 25); \ + c ^= b; c -= rol32(b, 16); \ + a ^= c; a -= rol32(c, 4); \ + b ^= a; b -= rol32(a, 14); \ + c ^= b; c -= rol32(b, 24); \ +} + +#define JHASH_INITVAL 0xdeadbeef + +typedef unsigned int u32; + +static inline u32 jhash(const void *key, u32 length, u32 initval) +{ + u32 a, b, c; + const unsigned char *k = key; + + a = b = c = JHASH_INITVAL + length + initval; + + while (length > 12) { + a += *(u32 *)(k); + b += *(u32 *)(k + 4); + c += *(u32 *)(k + 8); + __jhash_mix(a, b, c); + length -= 12; + k += 12; + } + switch (length) { + case 12: c += (u32)k[11]<<24; + case 11: c += (u32)k[10]<<16; + case 10: c += (u32)k[9]<<8; + case 9: c += k[8]; + case 8: b += (u32)k[7]<<24; + case 7: b += (u32)k[6]<<16; + case 6: b += (u32)k[5]<<8; + case 5: b += k[4]; + case 4: a += (u32)k[3]<<24; + case 3: a += (u32)k[2]<<16; + case 2: a += (u32)k[1]<<8; + case 1: a += k[0]; + __jhash_final(a, b, c); + case 0: /* Nothing left to add */ + break; + } + + return c; +} + +static inline u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval) +{ + a += initval; + b += initval; + c += initval; + __jhash_final(a, b, c); + return c; +} + +static inline u32 jhash_2words(u32 a, u32 b, u32 initval) +{ + return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2)); +} + +#define PCKT_FRAGMENTED 65343 +#define IPV4_HDR_LEN_NO_OPT 20 +#define IPV4_PLUS_ICMP_HDR 28 +#define IPV6_PLUS_ICMP_HDR 48 +#define RING_SIZE 2 +#define MAX_VIPS 12 +#define MAX_REALS 5 +#define CTL_MAP_SIZE 16 +#define CH_RINGS_SIZE (MAX_VIPS * RING_SIZE) +#define F_IPV6 (1 << 0) +#define F_HASH_NO_SRC_PORT (1 << 0) +#define F_ICMP (1 << 0) +#define F_SYN_SET (1 << 1) + +struct packet_description { + union { + __be32 src; + __be32 srcv6[4]; + }; + union { + __be32 dst; + __be32 dstv6[4]; + }; + union { + __u32 ports; + __u16 port16[2]; + }; + __u8 proto; + __u8 flags; +}; + +struct ctl_value { + union { + __u64 value; + __u32 ifindex; + __u8 mac[6]; + }; +}; + +struct vip_meta { + __u32 flags; + __u32 vip_num; +}; + +struct real_definition { + union { + __be32 dst; + __be32 dstv6[4]; + }; + __u8 flags; +}; + +struct vip_stats { + __u64 bytes; + __u64 pkts; +}; + +struct eth_hdr { + unsigned char eth_dest[ETH_ALEN]; + unsigned char eth_source[ETH_ALEN]; + unsigned short eth_proto; +}; + +struct bpf_map_def SEC("maps") vip_map = { + .type = BPF_MAP_TYPE_HASH, + .key_size = sizeof(struct vip), + .value_size = sizeof(struct vip_meta), + .max_entries = MAX_VIPS, +}; + +struct bpf_map_def SEC("maps") ch_rings = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(__u32), + .max_entries = CH_RINGS_SIZE, +}; + +struct bpf_map_def SEC("maps") reals = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(struct real_definition), + .max_entries = MAX_REALS, +}; + +struct bpf_map_def SEC("maps") stats = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(struct vip_stats), + .max_entries = MAX_VIPS, +}; + +struct bpf_map_def SEC("maps") ctl_array = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(struct ctl_value), + .max_entries = CTL_MAP_SIZE, +}; + +static __always_inline __u32 get_packet_hash(struct packet_description *pckt, + bool ipv6) +{ + if (ipv6) + return jhash_2words(jhash(pckt->srcv6, 16, MAX_VIPS), + pckt->ports, CH_RINGS_SIZE); + else + return jhash_2words(pckt->src, pckt->ports, CH_RINGS_SIZE); +} + +static __always_inline bool get_packet_dst(struct real_definition **real, + struct packet_description *pckt, + struct vip_meta *vip_info, + bool is_ipv6) +{ + __u32 hash = get_packet_hash(pckt, is_ipv6) % RING_SIZE; + __u32 key = RING_SIZE * vip_info->vip_num + hash; + __u32 *real_pos; + + real_pos = bpf_map_lookup_elem(&ch_rings, &key); + if (!real_pos) + return false; + key = *real_pos; + *real = bpf_map_lookup_elem(&reals, &key); + if (!(*real)) + return false; + return true; +} + +static __always_inline int parse_icmpv6(void *data, void *data_end, __u64 off, + struct packet_description *pckt) +{ + struct icmp6hdr *icmp_hdr; + struct ipv6hdr *ip6h; + + icmp_hdr = data + off; + if (icmp_hdr + 1 > data_end) + return TC_ACT_SHOT; + if (icmp_hdr->icmp6_type != ICMPV6_PKT_TOOBIG) + return TC_ACT_OK; + off += sizeof(struct icmp6hdr); + ip6h = data + off; + if (ip6h + 1 > data_end) + return TC_ACT_SHOT; + pckt->proto = ip6h->nexthdr; + pckt->flags |= F_ICMP; + memcpy(pckt->srcv6, ip6h->daddr.s6_addr32, 16); + memcpy(pckt->dstv6, ip6h->saddr.s6_addr32, 16); + return TC_ACT_UNSPEC; +} + +static __always_inline int parse_icmp(void *data, void *data_end, __u64 off, + struct packet_description *pckt) +{ + struct icmphdr *icmp_hdr; + struct iphdr *iph; + + icmp_hdr = data + off; + if (icmp_hdr + 1 > data_end) + return TC_ACT_SHOT; + if (icmp_hdr->type != ICMP_DEST_UNREACH || + icmp_hdr->code != ICMP_FRAG_NEEDED) + return TC_ACT_OK; + off += sizeof(struct icmphdr); + iph = data + off; + if (iph + 1 > data_end) + return TC_ACT_SHOT; + if (iph->ihl != 5) + return TC_ACT_SHOT; + pckt->proto = iph->protocol; + pckt->flags |= F_ICMP; + pckt->src = iph->daddr; + pckt->dst = iph->saddr; + return TC_ACT_UNSPEC; +} + +static __always_inline bool parse_udp(void *data, __u64 off, void *data_end, + struct packet_description *pckt) +{ + struct udphdr *udp; + udp = data + off; + + if (udp + 1 > data_end) + return false; + + if (!(pckt->flags & F_ICMP)) { + pckt->port16[0] = udp->source; + pckt->port16[1] = udp->dest; + } else { + pckt->port16[0] = udp->dest; + pckt->port16[1] = udp->source; + } + return true; +} + +static __always_inline bool parse_tcp(void *data, __u64 off, void *data_end, + struct packet_description *pckt) +{ + struct tcphdr *tcp; + + tcp = data + off; + if (tcp + 1 > data_end) + return false; + + if (tcp->syn) + pckt->flags |= F_SYN_SET; + + if (!(pckt->flags & F_ICMP)) { + pckt->port16[0] = tcp->source; + pckt->port16[1] = tcp->dest; + } else { + pckt->port16[0] = tcp->dest; + pckt->port16[1] = tcp->source; + } + return true; +} + +static __always_inline int process_packet(void *data, __u64 off, void *data_end, + bool is_ipv6, struct __sk_buff *skb) +{ + void *pkt_start = (void *)(long)skb->data; + struct packet_description pckt = {}; + struct eth_hdr *eth = pkt_start; + struct bpf_tunnel_key tkey = {}; + struct vip_stats *data_stats; + struct real_definition *dst; + struct vip_meta *vip_info; + struct ctl_value *cval; + __u32 v4_intf_pos = 1; + __u32 v6_intf_pos = 2; + struct ipv6hdr *ip6h; + struct vip vip = {}; + struct iphdr *iph; + int tun_flag = 0; + __u16 pkt_bytes; + __u64 iph_len; + __u32 ifindex; + __u8 protocol; + __u32 vip_num; + int action; + + tkey.tunnel_ttl = 64; + if (is_ipv6) { + ip6h = data + off; + if (ip6h + 1 > data_end) + return TC_ACT_SHOT; + + iph_len = sizeof(struct ipv6hdr); + protocol = ip6h->nexthdr; + pckt.proto = protocol; + pkt_bytes = bpf_ntohs(ip6h->payload_len); + off += iph_len; + if (protocol == IPPROTO_FRAGMENT) { + return TC_ACT_SHOT; + } else if (protocol == IPPROTO_ICMPV6) { + action = parse_icmpv6(data, data_end, off, &pckt); + if (action >= 0) + return action; + off += IPV6_PLUS_ICMP_HDR; + } else { + memcpy(pckt.srcv6, ip6h->saddr.s6_addr32, 16); + memcpy(pckt.dstv6, ip6h->daddr.s6_addr32, 16); + } + } else { + iph = data + off; + if (iph + 1 > data_end) + return TC_ACT_SHOT; + if (iph->ihl != 5) + return TC_ACT_SHOT; + + protocol = iph->protocol; + pckt.proto = protocol; + pkt_bytes = bpf_ntohs(iph->tot_len); + off += IPV4_HDR_LEN_NO_OPT; + + if (iph->frag_off & PCKT_FRAGMENTED) + return TC_ACT_SHOT; + if (protocol == IPPROTO_ICMP) { + action = parse_icmp(data, data_end, off, &pckt); + if (action >= 0) + return action; + off += IPV4_PLUS_ICMP_HDR; + } else { + pckt.src = iph->saddr; + pckt.dst = iph->daddr; + } + } + protocol = pckt.proto; + + if (protocol == IPPROTO_TCP) { + if (!parse_tcp(data, off, data_end, &pckt)) + return TC_ACT_SHOT; + } else if (protocol == IPPROTO_UDP) { + if (!parse_udp(data, off, data_end, &pckt)) + return TC_ACT_SHOT; + } else { + return TC_ACT_SHOT; + } + + if (is_ipv6) + memcpy(vip.daddr.v6, pckt.dstv6, 16); + else + vip.daddr.v4 = pckt.dst; + + vip.dport = pckt.port16[1]; + vip.protocol = pckt.proto; + vip_info = bpf_map_lookup_elem(&vip_map, &vip); + if (!vip_info) { + vip.dport = 0; + vip_info = bpf_map_lookup_elem(&vip_map, &vip); + if (!vip_info) + return TC_ACT_SHOT; + pckt.port16[1] = 0; + } + + if (vip_info->flags & F_HASH_NO_SRC_PORT) + pckt.port16[0] = 0; + + if (!get_packet_dst(&dst, &pckt, vip_info, is_ipv6)) + return TC_ACT_SHOT; + + if (dst->flags & F_IPV6) { + cval = bpf_map_lookup_elem(&ctl_array, &v6_intf_pos); + if (!cval) + return TC_ACT_SHOT; + ifindex = cval->ifindex; + memcpy(tkey.remote_ipv6, dst->dstv6, 16); + tun_flag = BPF_F_TUNINFO_IPV6; + } else { + cval = bpf_map_lookup_elem(&ctl_array, &v4_intf_pos); + if (!cval) + return TC_ACT_SHOT; + ifindex = cval->ifindex; + tkey.remote_ipv4 = dst->dst; + } + vip_num = vip_info->vip_num; + data_stats = bpf_map_lookup_elem(&stats, &vip_num); + if (!data_stats) + return TC_ACT_SHOT; + data_stats->pkts++; + data_stats->bytes += pkt_bytes; + bpf_skb_set_tunnel_key(skb, &tkey, sizeof(tkey), tun_flag); + *(u32 *)eth->eth_dest = tkey.remote_ipv4; + return bpf_redirect(ifindex, 0); +} + +SEC("l4lb-demo") +int balancer_ingress(struct __sk_buff *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct eth_hdr *eth = data; + __u32 eth_proto; + __u32 nh_off; + + nh_off = sizeof(struct eth_hdr); + if (data + nh_off > data_end) + return TC_ACT_SHOT; + eth_proto = eth->eth_proto; + if (eth_proto == bpf_htons(ETH_P_IP)) + return process_packet(data, nh_off, data_end, false, ctx); + else if (eth_proto == bpf_htons(ETH_P_IPV6)) + return process_packet(data, nh_off, data_end, true, ctx); + else + return TC_ACT_SHOT; +} +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_lpm_map.c b/tools/testing/selftests/bpf/test_lpm_map.c new file mode 100644 index 000000000000..e97565243d59 --- /dev/null +++ b/tools/testing/selftests/bpf/test_lpm_map.c @@ -0,0 +1,358 @@ +/* + * Randomized tests for eBPF longest-prefix-match maps + * + * This program runs randomized tests against the lpm-bpf-map. It implements a + * "Trivial Longest Prefix Match" (tlpm) based on simple, linear, singly linked + * lists. The implementation should be pretty straightforward. + * + * Based on tlpm, this inserts randomized data into bpf-lpm-maps and verifies + * the trie-based bpf-map implementation behaves the same way as tlpm. + */ + +#include <assert.h> +#include <errno.h> +#include <inttypes.h> +#include <linux/bpf.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <time.h> +#include <unistd.h> +#include <arpa/inet.h> +#include <sys/time.h> +#include <sys/resource.h> + +#include <bpf/bpf.h> +#include "bpf_util.h" + +struct tlpm_node { + struct tlpm_node *next; + size_t n_bits; + uint8_t key[]; +}; + +static struct tlpm_node *tlpm_add(struct tlpm_node *list, + const uint8_t *key, + size_t n_bits) +{ + struct tlpm_node *node; + size_t n; + + /* add new entry with @key/@n_bits to @list and return new head */ + + n = (n_bits + 7) / 8; + node = malloc(sizeof(*node) + n); + assert(node); + + node->next = list; + node->n_bits = n_bits; + memcpy(node->key, key, n); + + return node; +} + +static void tlpm_clear(struct tlpm_node *list) +{ + struct tlpm_node *node; + + /* free all entries in @list */ + + while ((node = list)) { + list = list->next; + free(node); + } +} + +static struct tlpm_node *tlpm_match(struct tlpm_node *list, + const uint8_t *key, + size_t n_bits) +{ + struct tlpm_node *best = NULL; + size_t i; + + /* Perform longest prefix-match on @key/@n_bits. That is, iterate all + * entries and match each prefix against @key. Remember the "best" + * entry we find (i.e., the longest prefix that matches) and return it + * to the caller when done. + */ + + for ( ; list; list = list->next) { + for (i = 0; i < n_bits && i < list->n_bits; ++i) { + if ((key[i / 8] & (1 << (7 - i % 8))) != + (list->key[i / 8] & (1 << (7 - i % 8)))) + break; + } + + if (i >= list->n_bits) { + if (!best || i > best->n_bits) + best = list; + } + } + + return best; +} + +static void test_lpm_basic(void) +{ + struct tlpm_node *list = NULL, *t1, *t2; + + /* very basic, static tests to verify tlpm works as expected */ + + assert(!tlpm_match(list, (uint8_t[]){ 0xff }, 8)); + + t1 = list = tlpm_add(list, (uint8_t[]){ 0xff }, 8); + assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff }, 8)); + assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff, 0xff }, 16)); + assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff, 0x00 }, 16)); + assert(!tlpm_match(list, (uint8_t[]){ 0x7f }, 8)); + assert(!tlpm_match(list, (uint8_t[]){ 0xfe }, 8)); + assert(!tlpm_match(list, (uint8_t[]){ 0xff }, 7)); + + t2 = list = tlpm_add(list, (uint8_t[]){ 0xff, 0xff }, 16); + assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff }, 8)); + assert(t2 == tlpm_match(list, (uint8_t[]){ 0xff, 0xff }, 16)); + assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff, 0xff }, 15)); + assert(!tlpm_match(list, (uint8_t[]){ 0x7f, 0xff }, 16)); + + tlpm_clear(list); +} + +static void test_lpm_order(void) +{ + struct tlpm_node *t1, *t2, *l1 = NULL, *l2 = NULL; + size_t i, j; + + /* Verify the tlpm implementation works correctly regardless of the + * order of entries. Insert a random set of entries into @l1, and copy + * the same data in reverse order into @l2. Then verify a lookup of + * random keys will yield the same result in both sets. + */ + + for (i = 0; i < (1 << 12); ++i) + l1 = tlpm_add(l1, (uint8_t[]){ + rand() % 0xff, + rand() % 0xff, + }, rand() % 16 + 1); + + for (t1 = l1; t1; t1 = t1->next) + l2 = tlpm_add(l2, t1->key, t1->n_bits); + + for (i = 0; i < (1 << 8); ++i) { + uint8_t key[] = { rand() % 0xff, rand() % 0xff }; + + t1 = tlpm_match(l1, key, 16); + t2 = tlpm_match(l2, key, 16); + + assert(!t1 == !t2); + if (t1) { + assert(t1->n_bits == t2->n_bits); + for (j = 0; j < t1->n_bits; ++j) + assert((t1->key[j / 8] & (1 << (7 - j % 8))) == + (t2->key[j / 8] & (1 << (7 - j % 8)))); + } + } + + tlpm_clear(l1); + tlpm_clear(l2); +} + +static void test_lpm_map(int keysize) +{ + size_t i, j, n_matches, n_nodes, n_lookups; + struct tlpm_node *t, *list = NULL; + struct bpf_lpm_trie_key *key; + uint8_t *data, *value; + int r, map; + + /* Compare behavior of tlpm vs. bpf-lpm. Create a randomized set of + * prefixes and insert it into both tlpm and bpf-lpm. Then run some + * randomized lookups and verify both maps return the same result. + */ + + n_matches = 0; + n_nodes = 1 << 8; + n_lookups = 1 << 16; + + data = alloca(keysize); + memset(data, 0, keysize); + + value = alloca(keysize + 1); + memset(value, 0, keysize + 1); + + key = alloca(sizeof(*key) + keysize); + memset(key, 0, sizeof(*key) + keysize); + + map = bpf_create_map(BPF_MAP_TYPE_LPM_TRIE, + sizeof(*key) + keysize, + keysize + 1, + 4096, + BPF_F_NO_PREALLOC); + assert(map >= 0); + + for (i = 0; i < n_nodes; ++i) { + for (j = 0; j < keysize; ++j) + value[j] = rand() & 0xff; + value[keysize] = rand() % (8 * keysize + 1); + + list = tlpm_add(list, value, value[keysize]); + + key->prefixlen = value[keysize]; + memcpy(key->data, value, keysize); + r = bpf_map_update_elem(map, key, value, 0); + assert(!r); + } + + for (i = 0; i < n_lookups; ++i) { + for (j = 0; j < keysize; ++j) + data[j] = rand() & 0xff; + + t = tlpm_match(list, data, 8 * keysize); + + key->prefixlen = 8 * keysize; + memcpy(key->data, data, keysize); + r = bpf_map_lookup_elem(map, key, value); + assert(!r || errno == ENOENT); + assert(!t == !!r); + + if (t) { + ++n_matches; + assert(t->n_bits == value[keysize]); + for (j = 0; j < t->n_bits; ++j) + assert((t->key[j / 8] & (1 << (7 - j % 8))) == + (value[j / 8] & (1 << (7 - j % 8)))); + } + } + + close(map); + tlpm_clear(list); + + /* With 255 random nodes in the map, we are pretty likely to match + * something on every lookup. For statistics, use this: + * + * printf(" nodes: %zu\n" + * "lookups: %zu\n" + * "matches: %zu\n", n_nodes, n_lookups, n_matches); + */ +} + +/* Test the implementation with some 'real world' examples */ + +static void test_lpm_ipaddr(void) +{ + struct bpf_lpm_trie_key *key_ipv4; + struct bpf_lpm_trie_key *key_ipv6; + size_t key_size_ipv4; + size_t key_size_ipv6; + int map_fd_ipv4; + int map_fd_ipv6; + __u64 value; + + key_size_ipv4 = sizeof(*key_ipv4) + sizeof(__u32); + key_size_ipv6 = sizeof(*key_ipv6) + sizeof(__u32) * 4; + key_ipv4 = alloca(key_size_ipv4); + key_ipv6 = alloca(key_size_ipv6); + + map_fd_ipv4 = bpf_create_map(BPF_MAP_TYPE_LPM_TRIE, + key_size_ipv4, sizeof(value), + 100, BPF_F_NO_PREALLOC); + assert(map_fd_ipv4 >= 0); + + map_fd_ipv6 = bpf_create_map(BPF_MAP_TYPE_LPM_TRIE, + key_size_ipv6, sizeof(value), + 100, BPF_F_NO_PREALLOC); + assert(map_fd_ipv6 >= 0); + + /* Fill data some IPv4 and IPv6 address ranges */ + value = 1; + key_ipv4->prefixlen = 16; + inet_pton(AF_INET, "192.168.0.0", key_ipv4->data); + assert(bpf_map_update_elem(map_fd_ipv4, key_ipv4, &value, 0) == 0); + + value = 2; + key_ipv4->prefixlen = 24; + inet_pton(AF_INET, "192.168.0.0", key_ipv4->data); + assert(bpf_map_update_elem(map_fd_ipv4, key_ipv4, &value, 0) == 0); + + value = 3; + key_ipv4->prefixlen = 24; + inet_pton(AF_INET, "192.168.128.0", key_ipv4->data); + assert(bpf_map_update_elem(map_fd_ipv4, key_ipv4, &value, 0) == 0); + + value = 5; + key_ipv4->prefixlen = 24; + inet_pton(AF_INET, "192.168.1.0", key_ipv4->data); + assert(bpf_map_update_elem(map_fd_ipv4, key_ipv4, &value, 0) == 0); + + value = 4; + key_ipv4->prefixlen = 23; + inet_pton(AF_INET, "192.168.0.0", key_ipv4->data); + assert(bpf_map_update_elem(map_fd_ipv4, key_ipv4, &value, 0) == 0); + + value = 0xdeadbeef; + key_ipv6->prefixlen = 64; + inet_pton(AF_INET6, "2a00:1450:4001:814::200e", key_ipv6->data); + assert(bpf_map_update_elem(map_fd_ipv6, key_ipv6, &value, 0) == 0); + + /* Set tprefixlen to maximum for lookups */ + key_ipv4->prefixlen = 32; + key_ipv6->prefixlen = 128; + + /* Test some lookups that should come back with a value */ + inet_pton(AF_INET, "192.168.128.23", key_ipv4->data); + assert(bpf_map_lookup_elem(map_fd_ipv4, key_ipv4, &value) == 0); + assert(value == 3); + + inet_pton(AF_INET, "192.168.0.1", key_ipv4->data); + assert(bpf_map_lookup_elem(map_fd_ipv4, key_ipv4, &value) == 0); + assert(value == 2); + + inet_pton(AF_INET6, "2a00:1450:4001:814::", key_ipv6->data); + assert(bpf_map_lookup_elem(map_fd_ipv6, key_ipv6, &value) == 0); + assert(value == 0xdeadbeef); + + inet_pton(AF_INET6, "2a00:1450:4001:814::1", key_ipv6->data); + assert(bpf_map_lookup_elem(map_fd_ipv6, key_ipv6, &value) == 0); + assert(value == 0xdeadbeef); + + /* Test some lookups that should not match any entry */ + inet_pton(AF_INET, "10.0.0.1", key_ipv4->data); + assert(bpf_map_lookup_elem(map_fd_ipv4, key_ipv4, &value) == -1 && + errno == ENOENT); + + inet_pton(AF_INET, "11.11.11.11", key_ipv4->data); + assert(bpf_map_lookup_elem(map_fd_ipv4, key_ipv4, &value) == -1 && + errno == ENOENT); + + inet_pton(AF_INET6, "2a00:ffff::", key_ipv6->data); + assert(bpf_map_lookup_elem(map_fd_ipv6, key_ipv6, &value) == -1 && + errno == ENOENT); + + close(map_fd_ipv4); + close(map_fd_ipv6); +} + +int main(void) +{ + struct rlimit limit = { RLIM_INFINITY, RLIM_INFINITY }; + int i, ret; + + /* we want predictable, pseudo random tests */ + srand(0xf00ba1); + + /* allow unlimited locked memory */ + ret = setrlimit(RLIMIT_MEMLOCK, &limit); + if (ret < 0) + perror("Unable to lift memlock rlimit"); + + test_lpm_basic(); + test_lpm_order(); + + /* Test with 8, 16, 24, 32, ... 128 bit prefix length */ + for (i = 1; i <= 16; ++i) + test_lpm_map(i); + + test_lpm_ipaddr(); + + printf("test_lpm: OK\n"); + return 0; +} diff --git a/tools/testing/selftests/bpf/test_lru_map.c b/tools/testing/selftests/bpf/test_lru_map.c index 9f7bd1915c21..8c10c9180c1a 100644 --- a/tools/testing/selftests/bpf/test_lru_map.c +++ b/tools/testing/selftests/bpf/test_lru_map.c @@ -18,11 +18,11 @@ #include <sys/wait.h> #include <sys/resource.h> -#include "bpf_sys.h" +#include <bpf/bpf.h> #include "bpf_util.h" #define LOCAL_FREE_TARGET (128) -#define PERCPU_FREE_TARGET (16) +#define PERCPU_FREE_TARGET (4) static int nr_cpus; @@ -30,11 +30,11 @@ static int create_map(int map_type, int map_flags, unsigned int size) { int map_fd; - map_fd = bpf_map_create(map_type, sizeof(unsigned long long), + map_fd = bpf_create_map(map_type, sizeof(unsigned long long), sizeof(unsigned long long), size, map_flags); if (map_fd == -1) - perror("bpf_map_create"); + perror("bpf_create_map"); return map_fd; } @@ -45,9 +45,9 @@ static int map_subset(int map0, int map1) unsigned long long value0[nr_cpus], value1[nr_cpus]; int ret; - while (!bpf_map_next_key(map1, &next_key, &next_key)) { - assert(!bpf_map_lookup(map1, &next_key, value1)); - ret = bpf_map_lookup(map0, &next_key, value0); + while (!bpf_map_get_next_key(map1, &next_key, &next_key)) { + assert(!bpf_map_lookup_elem(map1, &next_key, value1)); + ret = bpf_map_lookup_elem(map0, &next_key, value0); if (ret) { printf("key:%llu not found from map. %s(%d)\n", next_key, strerror(errno), errno); @@ -119,52 +119,54 @@ static void test_lru_sanity0(int map_type, int map_flags) /* insert key=1 element */ key = 1; - assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST)); - assert(!bpf_map_update(expected_map_fd, &key, value, BPF_NOEXIST)); + assert(!bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST)); + assert(!bpf_map_update_elem(expected_map_fd, &key, value, + BPF_NOEXIST)); /* BPF_NOEXIST means: add new element if it doesn't exist */ - assert(bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST) == -1 && + assert(bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST) == -1 /* key=1 already exists */ - errno == EEXIST); + && errno == EEXIST); - assert(bpf_map_update(lru_map_fd, &key, value, -1) == -1 && + assert(bpf_map_update_elem(lru_map_fd, &key, value, -1) == -1 && errno == EINVAL); /* insert key=2 element */ /* check that key=2 is not found */ key = 2; - assert(bpf_map_lookup(lru_map_fd, &key, value) == -1 && + assert(bpf_map_lookup_elem(lru_map_fd, &key, value) == -1 && errno == ENOENT); /* BPF_EXIST means: update existing element */ - assert(bpf_map_update(lru_map_fd, &key, value, BPF_EXIST) == -1 && + assert(bpf_map_update_elem(lru_map_fd, &key, value, BPF_EXIST) == -1 && /* key=2 is not there */ errno == ENOENT); - assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST)); + assert(!bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST)); /* insert key=3 element */ /* check that key=3 is not found */ key = 3; - assert(bpf_map_lookup(lru_map_fd, &key, value) == -1 && + assert(bpf_map_lookup_elem(lru_map_fd, &key, value) == -1 && errno == ENOENT); /* check that key=1 can be found and mark the ref bit to * stop LRU from removing key=1 */ key = 1; - assert(!bpf_map_lookup(lru_map_fd, &key, value)); + assert(!bpf_map_lookup_elem(lru_map_fd, &key, value)); assert(value[0] == 1234); key = 3; - assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST)); - assert(!bpf_map_update(expected_map_fd, &key, value, BPF_NOEXIST)); + assert(!bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST)); + assert(!bpf_map_update_elem(expected_map_fd, &key, value, + BPF_NOEXIST)); /* key=2 has been removed from the LRU */ key = 2; - assert(bpf_map_lookup(lru_map_fd, &key, value) == -1); + assert(bpf_map_lookup_elem(lru_map_fd, &key, value) == -1); assert(map_equal(lru_map_fd, expected_map_fd)); @@ -189,12 +191,7 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free) int next_cpu = 0; if (map_flags & BPF_F_NO_COMMON_LRU) - /* Ther percpu lru list (i.e each cpu has its own LRU - * list) does not have a local free list. Hence, - * it will only free old nodes till there is no free - * from the LRU list. Hence, this test does not apply - * to BPF_F_NO_COMMON_LRU - */ + /* This test is only applicable to common LRU list */ return; printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type, @@ -217,14 +214,15 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free) /* Insert 1 to tgt_free (+tgt_free keys) */ end_key = 1 + tgt_free; for (key = 1; key < end_key; key++) - assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST)); + assert(!bpf_map_update_elem(lru_map_fd, &key, value, + BPF_NOEXIST)); /* Lookup 1 to tgt_free/2 */ end_key = 1 + batch_size; for (key = 1; key < end_key; key++) { - assert(!bpf_map_lookup(lru_map_fd, &key, value)); - assert(!bpf_map_update(expected_map_fd, &key, value, - BPF_NOEXIST)); + assert(!bpf_map_lookup_elem(lru_map_fd, &key, value)); + assert(!bpf_map_update_elem(expected_map_fd, &key, value, + BPF_NOEXIST)); } /* Insert 1+tgt_free to 2*tgt_free @@ -234,9 +232,10 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free) key = 1 + tgt_free; end_key = key + tgt_free; for (; key < end_key; key++) { - assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST)); - assert(!bpf_map_update(expected_map_fd, &key, value, - BPF_NOEXIST)); + assert(!bpf_map_update_elem(lru_map_fd, &key, value, + BPF_NOEXIST)); + assert(!bpf_map_update_elem(expected_map_fd, &key, value, + BPF_NOEXIST)); } assert(map_equal(lru_map_fd, expected_map_fd)); @@ -269,12 +268,7 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free) int next_cpu = 0; if (map_flags & BPF_F_NO_COMMON_LRU) - /* Ther percpu lru list (i.e each cpu has its own LRU - * list) does not have a local free list. Hence, - * it will only free old nodes till there is no free - * from the LRU list. Hence, this test does not apply - * to BPF_F_NO_COMMON_LRU - */ + /* This test is only applicable to common LRU list */ return; printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type, @@ -286,11 +280,7 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free) assert(batch_size * 2 == tgt_free); map_size = tgt_free + batch_size; - if (map_flags & BPF_F_NO_COMMON_LRU) - lru_map_fd = create_map(map_type, map_flags, - map_size * nr_cpus); - else - lru_map_fd = create_map(map_type, map_flags, map_size); + lru_map_fd = create_map(map_type, map_flags, map_size); assert(lru_map_fd != -1); expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0, map_size); @@ -301,9 +291,10 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free) /* Insert 1 to tgt_free (+tgt_free keys) */ end_key = 1 + tgt_free; for (key = 1; key < end_key; key++) - assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST)); + assert(!bpf_map_update_elem(lru_map_fd, &key, value, + BPF_NOEXIST)); - /* Any bpf_map_update will require to acquire a new node + /* Any bpf_map_update_elem will require to acquire a new node * from LRU first. * * The local list is running out of free nodes. @@ -316,10 +307,12 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free) */ key = 1; if (map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { - assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST)); - assert(!bpf_map_delete(lru_map_fd, &key)); + assert(!bpf_map_update_elem(lru_map_fd, &key, value, + BPF_NOEXIST)); + assert(!bpf_map_delete_elem(lru_map_fd, &key)); } else { - assert(bpf_map_update(lru_map_fd, &key, value, BPF_EXIST)); + assert(bpf_map_update_elem(lru_map_fd, &key, value, + BPF_EXIST)); } /* Re-insert 1 to tgt_free/2 again and do a lookup @@ -328,12 +321,13 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free) end_key = 1 + batch_size; value[0] = 4321; for (key = 1; key < end_key; key++) { - assert(bpf_map_lookup(lru_map_fd, &key, value)); - assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST)); - assert(!bpf_map_lookup(lru_map_fd, &key, value)); + assert(bpf_map_lookup_elem(lru_map_fd, &key, value)); + assert(!bpf_map_update_elem(lru_map_fd, &key, value, + BPF_NOEXIST)); + assert(!bpf_map_lookup_elem(lru_map_fd, &key, value)); assert(value[0] == 4321); - assert(!bpf_map_update(expected_map_fd, &key, value, - BPF_NOEXIST)); + assert(!bpf_map_update_elem(expected_map_fd, &key, value, + BPF_NOEXIST)); } value[0] = 1234; @@ -344,14 +338,16 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free) /* These newly added but not referenced keys will be * gone during the next LRU shrink. */ - assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST)); + assert(!bpf_map_update_elem(lru_map_fd, &key, value, + BPF_NOEXIST)); /* Insert 1+tgt_free*3/2 to tgt_free*5/2 */ end_key = key + tgt_free; for (; key < end_key; key++) { - assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST)); - assert(!bpf_map_update(expected_map_fd, &key, value, - BPF_NOEXIST)); + assert(!bpf_map_update_elem(lru_map_fd, &key, value, + BPF_NOEXIST)); + assert(!bpf_map_update_elem(expected_map_fd, &key, value, + BPF_NOEXIST)); } assert(map_equal(lru_map_fd, expected_map_fd)); @@ -377,6 +373,10 @@ static void test_lru_sanity3(int map_type, int map_flags, unsigned int tgt_free) unsigned int map_size; int next_cpu = 0; + if (map_flags & BPF_F_NO_COMMON_LRU) + /* This test is only applicable to common LRU list */ + return; + printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type, map_flags); @@ -386,11 +386,7 @@ static void test_lru_sanity3(int map_type, int map_flags, unsigned int tgt_free) assert(batch_size * 2 == tgt_free); map_size = tgt_free * 2; - if (map_flags & BPF_F_NO_COMMON_LRU) - lru_map_fd = create_map(map_type, map_flags, - map_size * nr_cpus); - else - lru_map_fd = create_map(map_type, map_flags, map_size); + lru_map_fd = create_map(map_type, map_flags, map_size); assert(lru_map_fd != -1); expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0, map_size); @@ -401,14 +397,15 @@ static void test_lru_sanity3(int map_type, int map_flags, unsigned int tgt_free) /* Insert 1 to 2*tgt_free (+2*tgt_free keys) */ end_key = 1 + (2 * tgt_free); for (key = 1; key < end_key; key++) - assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST)); + assert(!bpf_map_update_elem(lru_map_fd, &key, value, + BPF_NOEXIST)); /* Lookup key 1 to tgt_free*3/2 */ end_key = tgt_free + batch_size; for (key = 1; key < end_key; key++) { - assert(!bpf_map_lookup(lru_map_fd, &key, value)); - assert(!bpf_map_update(expected_map_fd, &key, value, - BPF_NOEXIST)); + assert(!bpf_map_lookup_elem(lru_map_fd, &key, value)); + assert(!bpf_map_update_elem(expected_map_fd, &key, value, + BPF_NOEXIST)); } /* Add 1+2*tgt_free to tgt_free*5/2 @@ -417,9 +414,10 @@ static void test_lru_sanity3(int map_type, int map_flags, unsigned int tgt_free) key = 2 * tgt_free + 1; end_key = key + batch_size; for (; key < end_key; key++) { - assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST)); - assert(!bpf_map_update(expected_map_fd, &key, value, - BPF_NOEXIST)); + assert(!bpf_map_update_elem(lru_map_fd, &key, value, + BPF_NOEXIST)); + assert(!bpf_map_update_elem(expected_map_fd, &key, value, + BPF_NOEXIST)); } assert(map_equal(lru_map_fd, expected_map_fd)); @@ -457,27 +455,29 @@ static void test_lru_sanity4(int map_type, int map_flags, unsigned int tgt_free) value[0] = 1234; for (key = 1; key <= 2 * tgt_free; key++) - assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST)); + assert(!bpf_map_update_elem(lru_map_fd, &key, value, + BPF_NOEXIST)); key = 1; - assert(bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST)); + assert(bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST)); for (key = 1; key <= tgt_free; key++) { - assert(!bpf_map_lookup(lru_map_fd, &key, value)); - assert(!bpf_map_update(expected_map_fd, &key, value, - BPF_NOEXIST)); + assert(!bpf_map_lookup_elem(lru_map_fd, &key, value)); + assert(!bpf_map_update_elem(expected_map_fd, &key, value, + BPF_NOEXIST)); } for (; key <= 2 * tgt_free; key++) { - assert(!bpf_map_delete(lru_map_fd, &key)); - assert(bpf_map_delete(lru_map_fd, &key)); + assert(!bpf_map_delete_elem(lru_map_fd, &key)); + assert(bpf_map_delete_elem(lru_map_fd, &key)); } end_key = key + 2 * tgt_free; for (; key < end_key; key++) { - assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST)); - assert(!bpf_map_update(expected_map_fd, &key, value, - BPF_NOEXIST)); + assert(!bpf_map_update_elem(lru_map_fd, &key, value, + BPF_NOEXIST)); + assert(!bpf_map_update_elem(expected_map_fd, &key, value, + BPF_NOEXIST)); } assert(map_equal(lru_map_fd, expected_map_fd)); @@ -493,16 +493,16 @@ static void do_test_lru_sanity5(unsigned long long last_key, int map_fd) unsigned long long key, value[nr_cpus]; /* Ensure the last key inserted by previous CPU can be found */ - assert(!bpf_map_lookup(map_fd, &last_key, value)); + assert(!bpf_map_lookup_elem(map_fd, &last_key, value)); value[0] = 1234; key = last_key + 1; - assert(!bpf_map_update(map_fd, &key, value, BPF_NOEXIST)); - assert(!bpf_map_lookup(map_fd, &key, value)); + assert(!bpf_map_update_elem(map_fd, &key, value, BPF_NOEXIST)); + assert(!bpf_map_lookup_elem(map_fd, &key, value)); /* Cannot find the last key because it was removed by LRU */ - assert(bpf_map_lookup(map_fd, &last_key, value)); + assert(bpf_map_lookup_elem(map_fd, &last_key, value)); } /* Test map with only one element */ @@ -523,7 +523,7 @@ static void test_lru_sanity5(int map_type, int map_flags) value[0] = 1234; key = 0; - assert(!bpf_map_update(map_fd, &key, value, BPF_NOEXIST)); + assert(!bpf_map_update_elem(map_fd, &key, value, BPF_NOEXIST)); while (sched_next_online(0, &next_cpu) != -1) { pid_t pid; @@ -552,6 +552,65 @@ static void test_lru_sanity5(int map_type, int map_flags) printf("Pass\n"); } +/* Test list rotation for BPF_F_NO_COMMON_LRU map */ +static void test_lru_sanity6(int map_type, int map_flags, int tgt_free) +{ + int lru_map_fd, expected_map_fd; + unsigned long long key, value[nr_cpus]; + unsigned int map_size = tgt_free * 2; + int next_cpu = 0; + + if (!(map_flags & BPF_F_NO_COMMON_LRU)) + return; + + printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type, + map_flags); + + assert(sched_next_online(0, &next_cpu) != -1); + + expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0, map_size); + assert(expected_map_fd != -1); + + lru_map_fd = create_map(map_type, map_flags, map_size * nr_cpus); + assert(lru_map_fd != -1); + + value[0] = 1234; + + for (key = 1; key <= tgt_free; key++) { + assert(!bpf_map_update_elem(lru_map_fd, &key, value, + BPF_NOEXIST)); + assert(!bpf_map_update_elem(expected_map_fd, &key, value, + BPF_NOEXIST)); + } + + for (; key <= tgt_free * 2; key++) { + unsigned long long stable_key; + + /* Make ref bit sticky for key: [1, tgt_free] */ + for (stable_key = 1; stable_key <= tgt_free; stable_key++) { + /* Mark the ref bit */ + assert(!bpf_map_lookup_elem(lru_map_fd, &stable_key, + value)); + } + assert(!bpf_map_update_elem(lru_map_fd, &key, value, + BPF_NOEXIST)); + } + + for (; key <= tgt_free * 3; key++) { + assert(!bpf_map_update_elem(lru_map_fd, &key, value, + BPF_NOEXIST)); + assert(!bpf_map_update_elem(expected_map_fd, &key, value, + BPF_NOEXIST)); + } + + assert(map_equal(lru_map_fd, expected_map_fd)); + + close(expected_map_fd); + close(lru_map_fd); + + printf("Pass\n"); +} + int main(int argc, char **argv) { struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; @@ -579,6 +638,7 @@ int main(int argc, char **argv) test_lru_sanity3(map_types[t], map_flags[f], tgt_free); test_lru_sanity4(map_types[t], map_flags[f], tgt_free); test_lru_sanity5(map_types[t], map_flags[f]); + test_lru_sanity6(map_types[t], map_flags[f], tgt_free); printf("\n"); } diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index eedfef8d2946..93314524de0d 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -21,17 +21,17 @@ #include <linux/bpf.h> -#include "bpf_sys.h" +#include <bpf/bpf.h> #include "bpf_util.h" static int map_flags; static void test_hashmap(int task, void *data) { - long long key, next_key, value; + long long key, next_key, first_key, value; int fd; - fd = bpf_map_create(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value), + fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value), 2, map_flags); if (fd < 0) { printf("Failed to create hashmap '%s'!\n", strerror(errno)); @@ -41,145 +41,178 @@ static void test_hashmap(int task, void *data) key = 1; value = 1234; /* Insert key=1 element. */ - assert(bpf_map_update(fd, &key, &value, BPF_ANY) == 0); + assert(bpf_map_update_elem(fd, &key, &value, BPF_ANY) == 0); value = 0; /* BPF_NOEXIST means add new element if it doesn't exist. */ - assert(bpf_map_update(fd, &key, &value, BPF_NOEXIST) == -1 && + assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) == -1 && /* key=1 already exists. */ errno == EEXIST); /* -1 is an invalid flag. */ - assert(bpf_map_update(fd, &key, &value, -1) == -1 && errno == EINVAL); + assert(bpf_map_update_elem(fd, &key, &value, -1) == -1 && + errno == EINVAL); /* Check that key=1 can be found. */ - assert(bpf_map_lookup(fd, &key, &value) == 0 && value == 1234); + assert(bpf_map_lookup_elem(fd, &key, &value) == 0 && value == 1234); key = 2; /* Check that key=2 is not found. */ - assert(bpf_map_lookup(fd, &key, &value) == -1 && errno == ENOENT); + assert(bpf_map_lookup_elem(fd, &key, &value) == -1 && errno == ENOENT); /* BPF_EXIST means update existing element. */ - assert(bpf_map_update(fd, &key, &value, BPF_EXIST) == -1 && + assert(bpf_map_update_elem(fd, &key, &value, BPF_EXIST) == -1 && /* key=2 is not there. */ errno == ENOENT); /* Insert key=2 element. */ - assert(bpf_map_update(fd, &key, &value, BPF_NOEXIST) == 0); + assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) == 0); /* key=1 and key=2 were inserted, check that key=0 cannot be * inserted due to max_entries limit. */ key = 0; - assert(bpf_map_update(fd, &key, &value, BPF_NOEXIST) == -1 && + assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) == -1 && errno == E2BIG); /* Update existing element, though the map is full. */ key = 1; - assert(bpf_map_update(fd, &key, &value, BPF_EXIST) == 0); + assert(bpf_map_update_elem(fd, &key, &value, BPF_EXIST) == 0); key = 2; - assert(bpf_map_update(fd, &key, &value, BPF_ANY) == 0); - key = 1; - assert(bpf_map_update(fd, &key, &value, BPF_ANY) == 0); + assert(bpf_map_update_elem(fd, &key, &value, BPF_ANY) == 0); + key = 3; + assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) == -1 && + errno == E2BIG); /* Check that key = 0 doesn't exist. */ key = 0; - assert(bpf_map_delete(fd, &key) == -1 && errno == ENOENT); + assert(bpf_map_delete_elem(fd, &key) == -1 && errno == ENOENT); /* Iterate over two elements. */ - assert(bpf_map_next_key(fd, &key, &next_key) == 0 && - (next_key == 1 || next_key == 2)); - assert(bpf_map_next_key(fd, &next_key, &next_key) == 0 && - (next_key == 1 || next_key == 2)); - assert(bpf_map_next_key(fd, &next_key, &next_key) == -1 && + assert(bpf_map_get_next_key(fd, NULL, &first_key) == 0 && + (first_key == 1 || first_key == 2)); + assert(bpf_map_get_next_key(fd, &key, &next_key) == 0 && + (next_key == first_key)); + assert(bpf_map_get_next_key(fd, &next_key, &next_key) == 0 && + (next_key == 1 || next_key == 2) && + (next_key != first_key)); + assert(bpf_map_get_next_key(fd, &next_key, &next_key) == -1 && errno == ENOENT); /* Delete both elements. */ key = 1; - assert(bpf_map_delete(fd, &key) == 0); + assert(bpf_map_delete_elem(fd, &key) == 0); key = 2; - assert(bpf_map_delete(fd, &key) == 0); - assert(bpf_map_delete(fd, &key) == -1 && errno == ENOENT); + assert(bpf_map_delete_elem(fd, &key) == 0); + assert(bpf_map_delete_elem(fd, &key) == -1 && errno == ENOENT); key = 0; /* Check that map is empty. */ - assert(bpf_map_next_key(fd, &key, &next_key) == -1 && + assert(bpf_map_get_next_key(fd, NULL, &next_key) == -1 && + errno == ENOENT); + assert(bpf_map_get_next_key(fd, &key, &next_key) == -1 && errno == ENOENT); close(fd); } +static void test_hashmap_sizes(int task, void *data) +{ + int fd, i, j; + + for (i = 1; i <= 512; i <<= 1) + for (j = 1; j <= 1 << 18; j <<= 1) { + fd = bpf_create_map(BPF_MAP_TYPE_HASH, i, j, + 2, map_flags); + if (fd < 0) { + printf("Failed to create hashmap key=%d value=%d '%s'\n", + i, j, strerror(errno)); + exit(1); + } + close(fd); + usleep(10); /* give kernel time to destroy */ + } +} + static void test_hashmap_percpu(int task, void *data) { unsigned int nr_cpus = bpf_num_possible_cpus(); - long long value[nr_cpus]; - long long key, next_key; + BPF_DECLARE_PERCPU(long, value); + long long key, next_key, first_key; int expected_key_mask = 0; int fd, i; - fd = bpf_map_create(BPF_MAP_TYPE_PERCPU_HASH, sizeof(key), - sizeof(value[0]), 2, map_flags); + fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_HASH, sizeof(key), + sizeof(bpf_percpu(value, 0)), 2, map_flags); if (fd < 0) { printf("Failed to create hashmap '%s'!\n", strerror(errno)); exit(1); } for (i = 0; i < nr_cpus; i++) - value[i] = i + 100; + bpf_percpu(value, i) = i + 100; key = 1; /* Insert key=1 element. */ assert(!(expected_key_mask & key)); - assert(bpf_map_update(fd, &key, value, BPF_ANY) == 0); + assert(bpf_map_update_elem(fd, &key, value, BPF_ANY) == 0); expected_key_mask |= key; /* BPF_NOEXIST means add new element if it doesn't exist. */ - assert(bpf_map_update(fd, &key, value, BPF_NOEXIST) == -1 && + assert(bpf_map_update_elem(fd, &key, value, BPF_NOEXIST) == -1 && /* key=1 already exists. */ errno == EEXIST); /* -1 is an invalid flag. */ - assert(bpf_map_update(fd, &key, value, -1) == -1 && errno == EINVAL); + assert(bpf_map_update_elem(fd, &key, value, -1) == -1 && + errno == EINVAL); /* Check that key=1 can be found. Value could be 0 if the lookup * was run from a different CPU. */ - value[0] = 1; - assert(bpf_map_lookup(fd, &key, value) == 0 && value[0] == 100); + bpf_percpu(value, 0) = 1; + assert(bpf_map_lookup_elem(fd, &key, value) == 0 && + bpf_percpu(value, 0) == 100); key = 2; /* Check that key=2 is not found. */ - assert(bpf_map_lookup(fd, &key, value) == -1 && errno == ENOENT); + assert(bpf_map_lookup_elem(fd, &key, value) == -1 && errno == ENOENT); /* BPF_EXIST means update existing element. */ - assert(bpf_map_update(fd, &key, value, BPF_EXIST) == -1 && + assert(bpf_map_update_elem(fd, &key, value, BPF_EXIST) == -1 && /* key=2 is not there. */ errno == ENOENT); /* Insert key=2 element. */ assert(!(expected_key_mask & key)); - assert(bpf_map_update(fd, &key, value, BPF_NOEXIST) == 0); + assert(bpf_map_update_elem(fd, &key, value, BPF_NOEXIST) == 0); expected_key_mask |= key; /* key=1 and key=2 were inserted, check that key=0 cannot be * inserted due to max_entries limit. */ key = 0; - assert(bpf_map_update(fd, &key, value, BPF_NOEXIST) == -1 && + assert(bpf_map_update_elem(fd, &key, value, BPF_NOEXIST) == -1 && errno == E2BIG); /* Check that key = 0 doesn't exist. */ - assert(bpf_map_delete(fd, &key) == -1 && errno == ENOENT); + assert(bpf_map_delete_elem(fd, &key) == -1 && errno == ENOENT); /* Iterate over two elements. */ - while (!bpf_map_next_key(fd, &key, &next_key)) { + assert(bpf_map_get_next_key(fd, NULL, &first_key) == 0 && + ((expected_key_mask & first_key) == first_key)); + while (!bpf_map_get_next_key(fd, &key, &next_key)) { + if (first_key) { + assert(next_key == first_key); + first_key = 0; + } assert((expected_key_mask & next_key) == next_key); expected_key_mask &= ~next_key; - assert(bpf_map_lookup(fd, &next_key, value) == 0); + assert(bpf_map_lookup_elem(fd, &next_key, value) == 0); for (i = 0; i < nr_cpus; i++) - assert(value[i] == i + 100); + assert(bpf_percpu(value, i) == i + 100); key = next_key; } @@ -187,18 +220,20 @@ static void test_hashmap_percpu(int task, void *data) /* Update with BPF_EXIST. */ key = 1; - assert(bpf_map_update(fd, &key, value, BPF_EXIST) == 0); + assert(bpf_map_update_elem(fd, &key, value, BPF_EXIST) == 0); /* Delete both elements. */ key = 1; - assert(bpf_map_delete(fd, &key) == 0); + assert(bpf_map_delete_elem(fd, &key) == 0); key = 2; - assert(bpf_map_delete(fd, &key) == 0); - assert(bpf_map_delete(fd, &key) == -1 && errno == ENOENT); + assert(bpf_map_delete_elem(fd, &key) == 0); + assert(bpf_map_delete_elem(fd, &key) == -1 && errno == ENOENT); key = 0; /* Check that map is empty. */ - assert(bpf_map_next_key(fd, &key, &next_key) == -1 && + assert(bpf_map_get_next_key(fd, NULL, &next_key) == -1 && + errno == ENOENT); + assert(bpf_map_get_next_key(fd, &key, &next_key) == -1 && errno == ENOENT); close(fd); @@ -209,7 +244,7 @@ static void test_arraymap(int task, void *data) int key, next_key, fd; long long value; - fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, sizeof(key), sizeof(value), + fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, sizeof(key), sizeof(value), 2, 0); if (fd < 0) { printf("Failed to create arraymap '%s'!\n", strerror(errno)); @@ -219,40 +254,42 @@ static void test_arraymap(int task, void *data) key = 1; value = 1234; /* Insert key=1 element. */ - assert(bpf_map_update(fd, &key, &value, BPF_ANY) == 0); + assert(bpf_map_update_elem(fd, &key, &value, BPF_ANY) == 0); value = 0; - assert(bpf_map_update(fd, &key, &value, BPF_NOEXIST) == -1 && + assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) == -1 && errno == EEXIST); /* Check that key=1 can be found. */ - assert(bpf_map_lookup(fd, &key, &value) == 0 && value == 1234); + assert(bpf_map_lookup_elem(fd, &key, &value) == 0 && value == 1234); key = 0; /* Check that key=0 is also found and zero initialized. */ - assert(bpf_map_lookup(fd, &key, &value) == 0 && value == 0); + assert(bpf_map_lookup_elem(fd, &key, &value) == 0 && value == 0); /* key=0 and key=1 were inserted, check that key=2 cannot be inserted * due to max_entries limit. */ key = 2; - assert(bpf_map_update(fd, &key, &value, BPF_EXIST) == -1 && + assert(bpf_map_update_elem(fd, &key, &value, BPF_EXIST) == -1 && errno == E2BIG); /* Check that key = 2 doesn't exist. */ - assert(bpf_map_lookup(fd, &key, &value) == -1 && errno == ENOENT); + assert(bpf_map_lookup_elem(fd, &key, &value) == -1 && errno == ENOENT); /* Iterate over two elements. */ - assert(bpf_map_next_key(fd, &key, &next_key) == 0 && + assert(bpf_map_get_next_key(fd, NULL, &next_key) == 0 && + next_key == 0); + assert(bpf_map_get_next_key(fd, &key, &next_key) == 0 && next_key == 0); - assert(bpf_map_next_key(fd, &next_key, &next_key) == 0 && + assert(bpf_map_get_next_key(fd, &next_key, &next_key) == 0 && next_key == 1); - assert(bpf_map_next_key(fd, &next_key, &next_key) == -1 && + assert(bpf_map_get_next_key(fd, &next_key, &next_key) == -1 && errno == ENOENT); /* Delete shouldn't succeed. */ key = 1; - assert(bpf_map_delete(fd, &key) == -1 && errno == EINVAL); + assert(bpf_map_delete_elem(fd, &key) == -1 && errno == EINVAL); close(fd); } @@ -260,54 +297,58 @@ static void test_arraymap(int task, void *data) static void test_arraymap_percpu(int task, void *data) { unsigned int nr_cpus = bpf_num_possible_cpus(); + BPF_DECLARE_PERCPU(long, values); int key, next_key, fd, i; - long values[nr_cpus]; - fd = bpf_map_create(BPF_MAP_TYPE_PERCPU_ARRAY, sizeof(key), - sizeof(values[0]), 2, 0); + fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_ARRAY, sizeof(key), + sizeof(bpf_percpu(values, 0)), 2, 0); if (fd < 0) { printf("Failed to create arraymap '%s'!\n", strerror(errno)); exit(1); } for (i = 0; i < nr_cpus; i++) - values[i] = i + 100; + bpf_percpu(values, i) = i + 100; key = 1; /* Insert key=1 element. */ - assert(bpf_map_update(fd, &key, values, BPF_ANY) == 0); + assert(bpf_map_update_elem(fd, &key, values, BPF_ANY) == 0); - values[0] = 0; - assert(bpf_map_update(fd, &key, values, BPF_NOEXIST) == -1 && + bpf_percpu(values, 0) = 0; + assert(bpf_map_update_elem(fd, &key, values, BPF_NOEXIST) == -1 && errno == EEXIST); /* Check that key=1 can be found. */ - assert(bpf_map_lookup(fd, &key, values) == 0 && values[0] == 100); + assert(bpf_map_lookup_elem(fd, &key, values) == 0 && + bpf_percpu(values, 0) == 100); key = 0; /* Check that key=0 is also found and zero initialized. */ - assert(bpf_map_lookup(fd, &key, values) == 0 && - values[0] == 0 && values[nr_cpus - 1] == 0); + assert(bpf_map_lookup_elem(fd, &key, values) == 0 && + bpf_percpu(values, 0) == 0 && + bpf_percpu(values, nr_cpus - 1) == 0); /* Check that key=2 cannot be inserted due to max_entries limit. */ key = 2; - assert(bpf_map_update(fd, &key, values, BPF_EXIST) == -1 && + assert(bpf_map_update_elem(fd, &key, values, BPF_EXIST) == -1 && errno == E2BIG); /* Check that key = 2 doesn't exist. */ - assert(bpf_map_lookup(fd, &key, values) == -1 && errno == ENOENT); + assert(bpf_map_lookup_elem(fd, &key, values) == -1 && errno == ENOENT); /* Iterate over two elements. */ - assert(bpf_map_next_key(fd, &key, &next_key) == 0 && + assert(bpf_map_get_next_key(fd, NULL, &next_key) == 0 && next_key == 0); - assert(bpf_map_next_key(fd, &next_key, &next_key) == 0 && + assert(bpf_map_get_next_key(fd, &key, &next_key) == 0 && + next_key == 0); + assert(bpf_map_get_next_key(fd, &next_key, &next_key) == 0 && next_key == 1); - assert(bpf_map_next_key(fd, &next_key, &next_key) == -1 && + assert(bpf_map_get_next_key(fd, &next_key, &next_key) == -1 && errno == ENOENT); /* Delete shouldn't succeed. */ key = 1; - assert(bpf_map_delete(fd, &key) == -1 && errno == EINVAL); + assert(bpf_map_delete_elem(fd, &key) == -1 && errno == EINVAL); close(fd); } @@ -315,12 +356,15 @@ static void test_arraymap_percpu(int task, void *data) static void test_arraymap_percpu_many_keys(void) { unsigned int nr_cpus = bpf_num_possible_cpus(); - unsigned int nr_keys = 20000; - long values[nr_cpus]; + BPF_DECLARE_PERCPU(long, values); + /* nr_keys is not too large otherwise the test stresses percpu + * allocator more than anything else + */ + unsigned int nr_keys = 2000; int key, fd, i; - fd = bpf_map_create(BPF_MAP_TYPE_PERCPU_ARRAY, sizeof(key), - sizeof(values[0]), nr_keys, 0); + fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_ARRAY, sizeof(key), + sizeof(bpf_percpu(values, 0)), nr_keys, 0); if (fd < 0) { printf("Failed to create per-cpu arraymap '%s'!\n", strerror(errno)); @@ -328,19 +372,19 @@ static void test_arraymap_percpu_many_keys(void) } for (i = 0; i < nr_cpus; i++) - values[i] = i + 10; + bpf_percpu(values, i) = i + 10; for (key = 0; key < nr_keys; key++) - assert(bpf_map_update(fd, &key, values, BPF_ANY) == 0); + assert(bpf_map_update_elem(fd, &key, values, BPF_ANY) == 0); for (key = 0; key < nr_keys; key++) { for (i = 0; i < nr_cpus; i++) - values[i] = 0; + bpf_percpu(values, i) = 0; - assert(bpf_map_lookup(fd, &key, values) == 0); + assert(bpf_map_lookup_elem(fd, &key, values) == 0); for (i = 0; i < nr_cpus; i++) - assert(values[i] == i + 10); + assert(bpf_percpu(values, i) == i + 10); } close(fd); @@ -357,7 +401,7 @@ static void test_map_large(void) } key; int fd, i, value; - fd = bpf_map_create(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value), + fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value), MAP_SIZE, map_flags); if (fd < 0) { printf("Failed to create large map '%s'!\n", strerror(errno)); @@ -368,22 +412,24 @@ static void test_map_large(void) key = (struct bigkey) { .c = i }; value = i; - assert(bpf_map_update(fd, &key, &value, BPF_NOEXIST) == 0); + assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) == 0); } key.c = -1; - assert(bpf_map_update(fd, &key, &value, BPF_NOEXIST) == -1 && + assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) == -1 && errno == E2BIG); /* Iterate through all elements. */ + assert(bpf_map_get_next_key(fd, NULL, &key) == 0); + key.c = -1; for (i = 0; i < MAP_SIZE; i++) - assert(bpf_map_next_key(fd, &key, &key) == 0); - assert(bpf_map_next_key(fd, &key, &key) == -1 && errno == ENOENT); + assert(bpf_map_get_next_key(fd, &key, &key) == 0); + assert(bpf_map_get_next_key(fd, &key, &key) == -1 && errno == ENOENT); key.c = 0; - assert(bpf_map_lookup(fd, &key, &value) == 0 && value == 0); + assert(bpf_map_lookup_elem(fd, &key, &value) == 0 && value == 0); key.a = 1; - assert(bpf_map_lookup(fd, &key, &value) == -1 && errno == ENOENT); + assert(bpf_map_lookup_elem(fd, &key, &value) == -1 && errno == ENOENT); close(fd); } @@ -417,6 +463,7 @@ static void test_map_stress(void) { run_parallel(100, test_hashmap, NULL); run_parallel(100, test_hashmap_percpu, NULL); + run_parallel(100, test_hashmap_sizes, NULL); run_parallel(100, test_arraymap, NULL); run_parallel(100, test_arraymap_percpu, NULL); @@ -437,10 +484,12 @@ static void do_work(int fn, void *data) key = value = i; if (do_update) { - assert(bpf_map_update(fd, &key, &value, BPF_NOEXIST) == 0); - assert(bpf_map_update(fd, &key, &value, BPF_EXIST) == 0); + assert(bpf_map_update_elem(fd, &key, &value, + BPF_NOEXIST) == 0); + assert(bpf_map_update_elem(fd, &key, &value, + BPF_EXIST) == 0); } else { - assert(bpf_map_delete(fd, &key) == 0); + assert(bpf_map_delete_elem(fd, &key) == 0); } } } @@ -450,7 +499,7 @@ static void test_map_parallel(void) int i, fd, key = 0, value = 0; int data[2]; - fd = bpf_map_create(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value), + fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value), MAP_SIZE, map_flags); if (fd < 0) { printf("Failed to create map for parallel test '%s'!\n", @@ -468,20 +517,21 @@ static void test_map_parallel(void) run_parallel(TASKS, do_work, data); /* Check that key=0 is already there. */ - assert(bpf_map_update(fd, &key, &value, BPF_NOEXIST) == -1 && + assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) == -1 && errno == EEXIST); /* Check that all elements were inserted. */ + assert(bpf_map_get_next_key(fd, NULL, &key) == 0); key = -1; for (i = 0; i < MAP_SIZE; i++) - assert(bpf_map_next_key(fd, &key, &key) == 0); - assert(bpf_map_next_key(fd, &key, &key) == -1 && errno == ENOENT); + assert(bpf_map_get_next_key(fd, &key, &key) == 0); + assert(bpf_map_get_next_key(fd, &key, &key) == -1 && errno == ENOENT); /* Another check for all elements */ for (i = 0; i < MAP_SIZE; i++) { key = MAP_SIZE - i - 1; - assert(bpf_map_lookup(fd, &key, &value) == 0 && + assert(bpf_map_lookup_elem(fd, &key, &value) == 0 && value == key); } @@ -491,7 +541,8 @@ static void test_map_parallel(void) /* Nothing should be left. */ key = -1; - assert(bpf_map_next_key(fd, &key, &key) == -1 && errno == ENOENT); + assert(bpf_map_get_next_key(fd, NULL, &key) == -1 && errno == ENOENT); + assert(bpf_map_get_next_key(fd, &key, &key) == -1 && errno == ENOENT); } static void run_all_tests(void) diff --git a/tools/testing/selftests/bpf/test_pkt_access.c b/tools/testing/selftests/bpf/test_pkt_access.c new file mode 100644 index 000000000000..39387bb7e08c --- /dev/null +++ b/tools/testing/selftests/bpf/test_pkt_access.c @@ -0,0 +1,64 @@ +/* Copyright (c) 2017 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <stddef.h> +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/in.h> +#include <linux/tcp.h> +#include <linux/pkt_cls.h> +#include "bpf_helpers.h" +#include "bpf_endian.h" + +#define barrier() __asm__ __volatile__("": : :"memory") +int _version SEC("version") = 1; + +SEC("test1") +int process(struct __sk_buff *skb) +{ + void *data_end = (void *)(long)skb->data_end; + void *data = (void *)(long)skb->data; + struct ethhdr *eth = (struct ethhdr *)(data); + struct tcphdr *tcp = NULL; + __u8 proto = 255; + __u64 ihl_len; + + if (eth + 1 > data_end) + return TC_ACT_SHOT; + + if (eth->h_proto == bpf_htons(ETH_P_IP)) { + struct iphdr *iph = (struct iphdr *)(eth + 1); + + if (iph + 1 > data_end) + return TC_ACT_SHOT; + ihl_len = iph->ihl * 4; + proto = iph->protocol; + tcp = (struct tcphdr *)((void *)(iph) + ihl_len); + } else if (eth->h_proto == bpf_htons(ETH_P_IPV6)) { + struct ipv6hdr *ip6h = (struct ipv6hdr *)(eth + 1); + + if (ip6h + 1 > data_end) + return TC_ACT_SHOT; + ihl_len = sizeof(*ip6h); + proto = ip6h->nexthdr; + tcp = (struct tcphdr *)((void *)(ip6h) + ihl_len); + } + + if (tcp) { + if (((void *)(tcp) + 20) > data_end || proto != 6) + return TC_ACT_SHOT; + barrier(); /* to force ordering of checks */ + if (((void *)(tcp) + 18) > data_end) + return TC_ACT_SHOT; + if (tcp->urg_ptr == 123) + return TC_ACT_OK; + } + + return TC_ACT_UNSPEC; +} diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c new file mode 100644 index 000000000000..b59f5ed4ae40 --- /dev/null +++ b/tools/testing/selftests/bpf/test_progs.c @@ -0,0 +1,299 @@ +/* Copyright (c) 2017 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <stdio.h> +#include <unistd.h> +#include <errno.h> +#include <string.h> +#include <assert.h> +#include <stdlib.h> + +#include <linux/types.h> +typedef __u16 __sum16; +#include <arpa/inet.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/tcp.h> + +#include <sys/wait.h> +#include <sys/resource.h> + +#include <linux/bpf.h> +#include <linux/err.h> +#include <bpf/bpf.h> +#include <bpf/libbpf.h> +#include "test_iptunnel_common.h" +#include "bpf_util.h" +#include "bpf_endian.h" + +static int error_cnt, pass_cnt; + +#define MAGIC_BYTES 123 + +/* ipv4 test vector */ +static struct { + struct ethhdr eth; + struct iphdr iph; + struct tcphdr tcp; +} __packed pkt_v4 = { + .eth.h_proto = bpf_htons(ETH_P_IP), + .iph.ihl = 5, + .iph.protocol = 6, + .iph.tot_len = bpf_htons(MAGIC_BYTES), + .tcp.urg_ptr = 123, +}; + +/* ipv6 test vector */ +static struct { + struct ethhdr eth; + struct ipv6hdr iph; + struct tcphdr tcp; +} __packed pkt_v6 = { + .eth.h_proto = bpf_htons(ETH_P_IPV6), + .iph.nexthdr = 6, + .iph.payload_len = bpf_htons(MAGIC_BYTES), + .tcp.urg_ptr = 123, +}; + +#define CHECK(condition, tag, format...) ({ \ + int __ret = !!(condition); \ + if (__ret) { \ + error_cnt++; \ + printf("%s:FAIL:%s ", __func__, tag); \ + printf(format); \ + } else { \ + pass_cnt++; \ + printf("%s:PASS:%s %d nsec\n", __func__, tag, duration);\ + } \ +}) + +static int bpf_prog_load(const char *file, enum bpf_prog_type type, + struct bpf_object **pobj, int *prog_fd) +{ + struct bpf_program *prog; + struct bpf_object *obj; + int err; + + obj = bpf_object__open(file); + if (IS_ERR(obj)) { + error_cnt++; + return -ENOENT; + } + + prog = bpf_program__next(NULL, obj); + if (!prog) { + bpf_object__close(obj); + error_cnt++; + return -ENOENT; + } + + bpf_program__set_type(prog, type); + err = bpf_object__load(obj); + if (err) { + bpf_object__close(obj); + error_cnt++; + return -EINVAL; + } + + *pobj = obj; + *prog_fd = bpf_program__fd(prog); + return 0; +} + +static int bpf_find_map(const char *test, struct bpf_object *obj, + const char *name) +{ + struct bpf_map *map; + + map = bpf_object__find_map_by_name(obj, name); + if (!map) { + printf("%s:FAIL:map '%s' not found\n", test, name); + error_cnt++; + return -1; + } + return bpf_map__fd(map); +} + +static void test_pkt_access(void) +{ + const char *file = "./test_pkt_access.o"; + struct bpf_object *obj; + __u32 duration, retval; + int err, prog_fd; + + err = bpf_prog_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); + if (err) + return; + + err = bpf_prog_test_run(prog_fd, 100000, &pkt_v4, sizeof(pkt_v4), + NULL, NULL, &retval, &duration); + CHECK(err || errno || retval, "ipv4", + "err %d errno %d retval %d duration %d\n", + err, errno, retval, duration); + + err = bpf_prog_test_run(prog_fd, 100000, &pkt_v6, sizeof(pkt_v6), + NULL, NULL, &retval, &duration); + CHECK(err || errno || retval, "ipv6", + "err %d errno %d retval %d duration %d\n", + err, errno, retval, duration); + bpf_object__close(obj); +} + +static void test_xdp(void) +{ + struct vip key4 = {.protocol = 6, .family = AF_INET}; + struct vip key6 = {.protocol = 6, .family = AF_INET6}; + struct iptnl_info value4 = {.family = AF_INET}; + struct iptnl_info value6 = {.family = AF_INET6}; + const char *file = "./test_xdp.o"; + struct bpf_object *obj; + char buf[128]; + struct ipv6hdr *iph6 = (void *)buf + sizeof(struct ethhdr); + struct iphdr *iph = (void *)buf + sizeof(struct ethhdr); + __u32 duration, retval, size; + int err, prog_fd, map_fd; + + err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); + if (err) + return; + + map_fd = bpf_find_map(__func__, obj, "vip2tnl"); + if (map_fd < 0) + goto out; + bpf_map_update_elem(map_fd, &key4, &value4, 0); + bpf_map_update_elem(map_fd, &key6, &value6, 0); + + err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), + buf, &size, &retval, &duration); + + CHECK(err || errno || retval != XDP_TX || size != 74 || + iph->protocol != IPPROTO_IPIP, "ipv4", + "err %d errno %d retval %d size %d\n", + err, errno, retval, size); + + err = bpf_prog_test_run(prog_fd, 1, &pkt_v6, sizeof(pkt_v6), + buf, &size, &retval, &duration); + CHECK(err || errno || retval != XDP_TX || size != 114 || + iph6->nexthdr != IPPROTO_IPV6, "ipv6", + "err %d errno %d retval %d size %d\n", + err, errno, retval, size); +out: + bpf_object__close(obj); +} + +#define MAGIC_VAL 0x1234 +#define NUM_ITER 100000 +#define VIP_NUM 5 + +static void test_l4lb(void) +{ + unsigned int nr_cpus = bpf_num_possible_cpus(); + const char *file = "./test_l4lb.o"; + struct vip key = {.protocol = 6}; + struct vip_meta { + __u32 flags; + __u32 vip_num; + } value = {.vip_num = VIP_NUM}; + __u32 stats_key = VIP_NUM; + struct vip_stats { + __u64 bytes; + __u64 pkts; + } stats[nr_cpus]; + struct real_definition { + union { + __be32 dst; + __be32 dstv6[4]; + }; + __u8 flags; + } real_def = {.dst = MAGIC_VAL}; + __u32 ch_key = 11, real_num = 3; + __u32 duration, retval, size; + int err, i, prog_fd, map_fd; + __u64 bytes = 0, pkts = 0; + struct bpf_object *obj; + char buf[128]; + u32 *magic = (u32 *)buf; + + err = bpf_prog_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); + if (err) + return; + + map_fd = bpf_find_map(__func__, obj, "vip_map"); + if (map_fd < 0) + goto out; + bpf_map_update_elem(map_fd, &key, &value, 0); + + map_fd = bpf_find_map(__func__, obj, "ch_rings"); + if (map_fd < 0) + goto out; + bpf_map_update_elem(map_fd, &ch_key, &real_num, 0); + + map_fd = bpf_find_map(__func__, obj, "reals"); + if (map_fd < 0) + goto out; + bpf_map_update_elem(map_fd, &real_num, &real_def, 0); + + err = bpf_prog_test_run(prog_fd, NUM_ITER, &pkt_v4, sizeof(pkt_v4), + buf, &size, &retval, &duration); + CHECK(err || errno || retval != 7/*TC_ACT_REDIRECT*/ || size != 54 || + *magic != MAGIC_VAL, "ipv4", + "err %d errno %d retval %d size %d magic %x\n", + err, errno, retval, size, *magic); + + err = bpf_prog_test_run(prog_fd, NUM_ITER, &pkt_v6, sizeof(pkt_v6), + buf, &size, &retval, &duration); + CHECK(err || errno || retval != 7/*TC_ACT_REDIRECT*/ || size != 74 || + *magic != MAGIC_VAL, "ipv6", + "err %d errno %d retval %d size %d magic %x\n", + err, errno, retval, size, *magic); + + map_fd = bpf_find_map(__func__, obj, "stats"); + if (map_fd < 0) + goto out; + bpf_map_lookup_elem(map_fd, &stats_key, stats); + for (i = 0; i < nr_cpus; i++) { + bytes += stats[i].bytes; + pkts += stats[i].pkts; + } + if (bytes != MAGIC_BYTES * NUM_ITER * 2 || pkts != NUM_ITER * 2) { + error_cnt++; + printf("test_l4lb:FAIL:stats %lld %lld\n", bytes, pkts); + } +out: + bpf_object__close(obj); +} + +static void test_tcp_estats(void) +{ + const char *file = "./test_tcp_estats.o"; + int err, prog_fd; + struct bpf_object *obj; + __u32 duration = 0; + + err = bpf_prog_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj, &prog_fd); + CHECK(err, "", "err %d errno %d\n", err, errno); + if (err) + return; + + bpf_object__close(obj); +} + +int main(void) +{ + struct rlimit rinf = { RLIM_INFINITY, RLIM_INFINITY }; + + setrlimit(RLIMIT_MEMLOCK, &rinf); + + test_pkt_access(); + test_xdp(); + test_l4lb(); + test_tcp_estats(); + + printf("Summary: %d PASSED, %d FAILED\n", pass_cnt, error_cnt); + return 0; +} diff --git a/tools/testing/selftests/bpf/test_tag.c b/tools/testing/selftests/bpf/test_tag.c new file mode 100644 index 000000000000..de409fc50c35 --- /dev/null +++ b/tools/testing/selftests/bpf/test_tag.c @@ -0,0 +1,203 @@ +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <ctype.h> +#include <time.h> +#include <errno.h> +#include <unistd.h> +#include <string.h> +#include <sched.h> +#include <limits.h> +#include <assert.h> + +#include <sys/socket.h> +#include <sys/resource.h> + +#include <linux/filter.h> +#include <linux/bpf.h> +#include <linux/if_alg.h> + +#include <bpf/bpf.h> + +#include "../../../include/linux/filter.h" + +static struct bpf_insn prog[BPF_MAXINSNS]; + +static void bpf_gen_imm_prog(unsigned int insns, int fd_map) +{ + int i; + + srand(time(NULL)); + for (i = 0; i < insns; i++) + prog[i] = BPF_ALU64_IMM(BPF_MOV, i % BPF_REG_10, rand()); + prog[i - 1] = BPF_EXIT_INSN(); +} + +static void bpf_gen_map_prog(unsigned int insns, int fd_map) +{ + int i, j = 0; + + for (i = 0; i + 1 < insns; i += 2) { + struct bpf_insn tmp[] = { + BPF_LD_MAP_FD(j++ % BPF_REG_10, fd_map) + }; + + memcpy(&prog[i], tmp, sizeof(tmp)); + } + if (insns % 2 == 0) + prog[insns - 2] = BPF_ALU64_IMM(BPF_MOV, i % BPF_REG_10, 42); + prog[insns - 1] = BPF_EXIT_INSN(); +} + +static int bpf_try_load_prog(int insns, int fd_map, + void (*bpf_filler)(unsigned int insns, + int fd_map)) +{ + int fd_prog; + + bpf_filler(insns, fd_map); + fd_prog = bpf_load_program(BPF_PROG_TYPE_SCHED_CLS, prog, insns, "", 0, + NULL, 0); + assert(fd_prog > 0); + if (fd_map > 0) + bpf_filler(insns, 0); + return fd_prog; +} + +static int __hex2bin(char ch) +{ + if ((ch >= '0') && (ch <= '9')) + return ch - '0'; + ch = tolower(ch); + if ((ch >= 'a') && (ch <= 'f')) + return ch - 'a' + 10; + return -1; +} + +static int hex2bin(uint8_t *dst, const char *src, size_t count) +{ + while (count--) { + int hi = __hex2bin(*src++); + int lo = __hex2bin(*src++); + + if ((hi < 0) || (lo < 0)) + return -1; + *dst++ = (hi << 4) | lo; + } + return 0; +} + +static void tag_from_fdinfo(int fd_prog, uint8_t *tag, uint32_t len) +{ + const int prefix_len = sizeof("prog_tag:\t") - 1; + char buff[256]; + int ret = -1; + FILE *fp; + + snprintf(buff, sizeof(buff), "/proc/%d/fdinfo/%d", getpid(), + fd_prog); + fp = fopen(buff, "r"); + assert(fp); + + while (fgets(buff, sizeof(buff), fp)) { + if (strncmp(buff, "prog_tag:\t", prefix_len)) + continue; + ret = hex2bin(tag, buff + prefix_len, len); + break; + } + + fclose(fp); + assert(!ret); +} + +static void tag_from_alg(int insns, uint8_t *tag, uint32_t len) +{ + static const struct sockaddr_alg alg = { + .salg_family = AF_ALG, + .salg_type = "hash", + .salg_name = "sha1", + }; + int fd_base, fd_alg, ret; + ssize_t size; + + fd_base = socket(AF_ALG, SOCK_SEQPACKET, 0); + assert(fd_base > 0); + + ret = bind(fd_base, (struct sockaddr *)&alg, sizeof(alg)); + assert(!ret); + + fd_alg = accept(fd_base, NULL, 0); + assert(fd_alg > 0); + + insns *= sizeof(struct bpf_insn); + size = write(fd_alg, prog, insns); + assert(size == insns); + + size = read(fd_alg, tag, len); + assert(size == len); + + close(fd_alg); + close(fd_base); +} + +static void tag_dump(const char *prefix, uint8_t *tag, uint32_t len) +{ + int i; + + printf("%s", prefix); + for (i = 0; i < len; i++) + printf("%02x", tag[i]); + printf("\n"); +} + +static void tag_exit_report(int insns, int fd_map, uint8_t *ftag, + uint8_t *atag, uint32_t len) +{ + printf("Program tag mismatch for %d insns%s!\n", insns, + fd_map < 0 ? "" : " with map"); + + tag_dump(" fdinfo result: ", ftag, len); + tag_dump(" af_alg result: ", atag, len); + exit(1); +} + +static void do_test(uint32_t *tests, int start_insns, int fd_map, + void (*bpf_filler)(unsigned int insns, int fd)) +{ + int i, fd_prog; + + for (i = start_insns; i <= BPF_MAXINSNS; i++) { + uint8_t ftag[8], atag[sizeof(ftag)]; + + fd_prog = bpf_try_load_prog(i, fd_map, bpf_filler); + tag_from_fdinfo(fd_prog, ftag, sizeof(ftag)); + tag_from_alg(i, atag, sizeof(atag)); + if (memcmp(ftag, atag, sizeof(ftag))) + tag_exit_report(i, fd_map, ftag, atag, sizeof(ftag)); + + close(fd_prog); + sched_yield(); + (*tests)++; + } +} + +int main(void) +{ + struct rlimit rinf = { RLIM_INFINITY, RLIM_INFINITY }; + uint32_t tests = 0; + int i, fd_map; + + setrlimit(RLIMIT_MEMLOCK, &rinf); + fd_map = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(int), + sizeof(int), 1, BPF_F_NO_PREALLOC); + assert(fd_map > 0); + + for (i = 0; i < 5; i++) { + do_test(&tests, 2, -1, bpf_gen_imm_prog); + do_test(&tests, 3, fd_map, bpf_gen_map_prog); + } + + printf("test_tag: OK (%u tests)\n", tests); + close(fd_map); + return 0; +} diff --git a/tools/testing/selftests/bpf/test_tcp_estats.c b/tools/testing/selftests/bpf/test_tcp_estats.c new file mode 100644 index 000000000000..bee3bbecc0c4 --- /dev/null +++ b/tools/testing/selftests/bpf/test_tcp_estats.c @@ -0,0 +1,258 @@ +/* Copyright (c) 2017 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ + +/* This program shows clang/llvm is able to generate code pattern + * like: + * _tcp_send_active_reset: + * 0: bf 16 00 00 00 00 00 00 r6 = r1 + * ...... + * 335: b7 01 00 00 0f 00 00 00 r1 = 15 + * 336: 05 00 48 00 00 00 00 00 goto 72 + * + * LBB0_3: + * 337: b7 01 00 00 01 00 00 00 r1 = 1 + * 338: 63 1a d0 ff 00 00 00 00 *(u32 *)(r10 - 48) = r1 + * 408: b7 01 00 00 03 00 00 00 r1 = 3 + * + * LBB0_4: + * 409: 71 a2 fe ff 00 00 00 00 r2 = *(u8 *)(r10 - 2) + * 410: bf a7 00 00 00 00 00 00 r7 = r10 + * 411: 07 07 00 00 b8 ff ff ff r7 += -72 + * 412: bf 73 00 00 00 00 00 00 r3 = r7 + * 413: 0f 13 00 00 00 00 00 00 r3 += r1 + * 414: 73 23 2d 00 00 00 00 00 *(u8 *)(r3 + 45) = r2 + * + * From the above code snippet, the code generated by the compiler + * is reasonable. The "r1" is assigned to different values in basic + * blocks "_tcp_send_active_reset" and "LBB0_3", and used in "LBB0_4". + * The verifier should be able to handle such code patterns. + */ +#include <string.h> +#include <linux/bpf.h> +#include <linux/ipv6.h> +#include <linux/version.h> +#include <sys/socket.h> +#include "bpf_helpers.h" + +#define _(P) ({typeof(P) val = 0; bpf_probe_read(&val, sizeof(val), &P); val;}) +#define TCP_ESTATS_MAGIC 0xBAADBEEF + +/* This test case needs "sock" and "pt_regs" data structure. + * Recursively, "sock" needs "sock_common" and "inet_sock". + * However, this is a unit test case only for + * verifier purpose without bpf program execution. + * We can safely mock much simpler data structures, basically + * only taking the necessary fields from kernel headers. + */ +typedef __u32 __bitwise __portpair; +typedef __u64 __bitwise __addrpair; + +struct sock_common { + unsigned short skc_family; + union { + __addrpair skc_addrpair; + struct { + __be32 skc_daddr; + __be32 skc_rcv_saddr; + }; + }; + union { + __portpair skc_portpair; + struct { + __be16 skc_dport; + __u16 skc_num; + }; + }; + struct in6_addr skc_v6_daddr; + struct in6_addr skc_v6_rcv_saddr; +}; + +struct sock { + struct sock_common __sk_common; +#define sk_family __sk_common.skc_family +#define sk_v6_daddr __sk_common.skc_v6_daddr +#define sk_v6_rcv_saddr __sk_common.skc_v6_rcv_saddr +}; + +struct inet_sock { + struct sock sk; +#define inet_daddr sk.__sk_common.skc_daddr +#define inet_dport sk.__sk_common.skc_dport + __be32 inet_saddr; + __be16 inet_sport; +}; + +struct pt_regs { + long di; +}; + +static inline struct inet_sock *inet_sk(const struct sock *sk) +{ + return (struct inet_sock *)sk; +} + +/* Define various data structures for state recording. + * Some fields are not used due to test simplification. + */ +enum tcp_estats_addrtype { + TCP_ESTATS_ADDRTYPE_IPV4 = 1, + TCP_ESTATS_ADDRTYPE_IPV6 = 2 +}; + +enum tcp_estats_event_type { + TCP_ESTATS_ESTABLISH, + TCP_ESTATS_PERIODIC, + TCP_ESTATS_TIMEOUT, + TCP_ESTATS_RETRANSMIT_TIMEOUT, + TCP_ESTATS_RETRANSMIT_OTHER, + TCP_ESTATS_SYN_RETRANSMIT, + TCP_ESTATS_SYNACK_RETRANSMIT, + TCP_ESTATS_TERM, + TCP_ESTATS_TX_RESET, + TCP_ESTATS_RX_RESET, + TCP_ESTATS_WRITE_TIMEOUT, + TCP_ESTATS_CONN_TIMEOUT, + TCP_ESTATS_ACK_LATENCY, + TCP_ESTATS_NEVENTS, +}; + +struct tcp_estats_event { + int pid; + int cpu; + unsigned long ts; + unsigned int magic; + enum tcp_estats_event_type event_type; +}; + +/* The below data structure is packed in order for + * llvm compiler to generate expected code. + */ +struct tcp_estats_conn_id { + unsigned int localaddressType; + struct { + unsigned char data[16]; + } localaddress; + struct { + unsigned char data[16]; + } remaddress; + unsigned short localport; + unsigned short remport; +} __attribute__((__packed__)); + +struct tcp_estats_basic_event { + struct tcp_estats_event event; + struct tcp_estats_conn_id conn_id; +}; + +struct bpf_map_def SEC("maps") ev_record_map = { + .type = BPF_MAP_TYPE_HASH, + .key_size = sizeof(__u32), + .value_size = sizeof(struct tcp_estats_basic_event), + .max_entries = 1024, +}; + +struct dummy_tracepoint_args { + unsigned long long pad; + struct sock *sock; +}; + +static __always_inline void tcp_estats_ev_init(struct tcp_estats_event *event, + enum tcp_estats_event_type type) +{ + event->magic = TCP_ESTATS_MAGIC; + event->ts = bpf_ktime_get_ns(); + event->event_type = type; +} + +static __always_inline void unaligned_u32_set(unsigned char *to, __u8 *from) +{ + to[0] = _(from[0]); + to[1] = _(from[1]); + to[2] = _(from[2]); + to[3] = _(from[3]); +} + +static __always_inline void conn_id_ipv4_init(struct tcp_estats_conn_id *conn_id, + __be32 *saddr, __be32 *daddr) +{ + conn_id->localaddressType = TCP_ESTATS_ADDRTYPE_IPV4; + + unaligned_u32_set(conn_id->localaddress.data, (__u8 *)saddr); + unaligned_u32_set(conn_id->remaddress.data, (__u8 *)daddr); +} + +static __always_inline void conn_id_ipv6_init(struct tcp_estats_conn_id *conn_id, + __be32 *saddr, __be32 *daddr) +{ + conn_id->localaddressType = TCP_ESTATS_ADDRTYPE_IPV6; + + unaligned_u32_set(conn_id->localaddress.data, (__u8 *)saddr); + unaligned_u32_set(conn_id->localaddress.data + sizeof(__u32), + (__u8 *)(saddr + 1)); + unaligned_u32_set(conn_id->localaddress.data + sizeof(__u32) * 2, + (__u8 *)(saddr + 2)); + unaligned_u32_set(conn_id->localaddress.data + sizeof(__u32) * 3, + (__u8 *)(saddr + 3)); + + unaligned_u32_set(conn_id->remaddress.data, + (__u8 *)(daddr)); + unaligned_u32_set(conn_id->remaddress.data + sizeof(__u32), + (__u8 *)(daddr + 1)); + unaligned_u32_set(conn_id->remaddress.data + sizeof(__u32) * 2, + (__u8 *)(daddr + 2)); + unaligned_u32_set(conn_id->remaddress.data + sizeof(__u32) * 3, + (__u8 *)(daddr + 3)); +} + +static __always_inline void tcp_estats_conn_id_init(struct tcp_estats_conn_id *conn_id, + struct sock *sk) +{ + conn_id->localport = _(inet_sk(sk)->inet_sport); + conn_id->remport = _(inet_sk(sk)->inet_dport); + + if (_(sk->sk_family) == AF_INET6) + conn_id_ipv6_init(conn_id, + sk->sk_v6_rcv_saddr.s6_addr32, + sk->sk_v6_daddr.s6_addr32); + else + conn_id_ipv4_init(conn_id, + &inet_sk(sk)->inet_saddr, + &inet_sk(sk)->inet_daddr); +} + +static __always_inline void tcp_estats_init(struct sock *sk, + struct tcp_estats_event *event, + struct tcp_estats_conn_id *conn_id, + enum tcp_estats_event_type type) +{ + tcp_estats_ev_init(event, type); + tcp_estats_conn_id_init(conn_id, sk); +} + +static __always_inline void send_basic_event(struct sock *sk, + enum tcp_estats_event_type type) +{ + struct tcp_estats_basic_event ev; + __u32 key = bpf_get_prandom_u32(); + + memset(&ev, 0, sizeof(ev)); + tcp_estats_init(sk, &ev.event, &ev.conn_id, type); + bpf_map_update_elem(&ev_record_map, &key, &ev, BPF_ANY); +} + +SEC("dummy_tracepoint") +int _dummy_tracepoint(struct dummy_tracepoint_args *arg) +{ + if (!arg->sock) + return 0; + + send_basic_event(arg->sock, TCP_ESTATS_TX_RESET); + return 0; +} + +char _license[] SEC("license") = "GPL"; +__u32 _version SEC("version") = 1; /* ignored by tracepoints, required by libbpf.a */ diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 853d7e43434a..3773562056da 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -8,7 +8,11 @@ * License as published by the Free Software Foundation. */ +#include <asm/types.h> +#include <linux/types.h> +#include <stdint.h> #include <stdio.h> +#include <stdlib.h> #include <unistd.h> #include <errno.h> #include <string.h> @@ -16,6 +20,7 @@ #include <stdbool.h> #include <sched.h> +#include <sys/capability.h> #include <sys/resource.h> #include <linux/unistd.h> @@ -23,9 +28,17 @@ #include <linux/bpf_perf_event.h> #include <linux/bpf.h> -#include "../../../include/linux/filter.h" +#include <bpf/bpf.h> + +#ifdef HAVE_GENHDR +# include "autoconf.h" +#else +# if defined(__i386) || defined(__x86_64) || defined(__s390x__) || defined(__aarch64__) +# define CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS 1 +# endif +#endif -#include "bpf_sys.h" +#include "../../../include/linux/filter.h" #ifndef ARRAY_SIZE # define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) @@ -33,6 +46,9 @@ #define MAX_INSNS 512 #define MAX_FIXUPS 8 +#define MAX_NR_MAPS 4 + +#define F_NEEDS_EFFICIENT_UNALIGNED_ACCESS (1 << 0) struct bpf_test { const char *descr; @@ -40,6 +56,7 @@ struct bpf_test { int fixup_map1[MAX_FIXUPS]; int fixup_map2[MAX_FIXUPS]; int fixup_prog[MAX_FIXUPS]; + int fixup_map_in_map[MAX_FIXUPS]; const char *errstr; const char *errstr_unpriv; enum { @@ -48,6 +65,7 @@ struct bpf_test { REJECT } result, result_unpriv; enum bpf_prog_type prog_type; + uint8_t flags; }; /* Note we want this to be 64 bit aligned so that the end of our array is @@ -173,6 +191,86 @@ static struct bpf_test tests[] = { .result = REJECT, }, { + "test6 ld_imm64", + .insns = { + BPF_RAW_INSN(BPF_LD | BPF_IMM | BPF_DW, 0, 0, 0, 0), + BPF_RAW_INSN(0, 0, 0, 0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + }, + { + "test7 ld_imm64", + .insns = { + BPF_RAW_INSN(BPF_LD | BPF_IMM | BPF_DW, 0, 0, 0, 1), + BPF_RAW_INSN(0, 0, 0, 0, 1), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + }, + { + "test8 ld_imm64", + .insns = { + BPF_RAW_INSN(BPF_LD | BPF_IMM | BPF_DW, 0, 0, 1, 1), + BPF_RAW_INSN(0, 0, 0, 0, 1), + BPF_EXIT_INSN(), + }, + .errstr = "uses reserved fields", + .result = REJECT, + }, + { + "test9 ld_imm64", + .insns = { + BPF_RAW_INSN(BPF_LD | BPF_IMM | BPF_DW, 0, 0, 0, 1), + BPF_RAW_INSN(0, 0, 0, 1, 1), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_ld_imm64 insn", + .result = REJECT, + }, + { + "test10 ld_imm64", + .insns = { + BPF_RAW_INSN(BPF_LD | BPF_IMM | BPF_DW, 0, 0, 0, 1), + BPF_RAW_INSN(0, BPF_REG_1, 0, 0, 1), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_ld_imm64 insn", + .result = REJECT, + }, + { + "test11 ld_imm64", + .insns = { + BPF_RAW_INSN(BPF_LD | BPF_IMM | BPF_DW, 0, 0, 0, 1), + BPF_RAW_INSN(0, 0, BPF_REG_1, 0, 1), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_ld_imm64 insn", + .result = REJECT, + }, + { + "test12 ld_imm64", + .insns = { + BPF_MOV64_IMM(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_LD | BPF_IMM | BPF_DW, 0, BPF_REG_1, 0, 1), + BPF_RAW_INSN(0, 0, 0, 0, 1), + BPF_EXIT_INSN(), + }, + .errstr = "not pointing to valid bpf_map", + .result = REJECT, + }, + { + "test13 ld_imm64", + .insns = { + BPF_MOV64_IMM(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_LD | BPF_IMM | BPF_DW, 0, BPF_REG_1, 0, 1), + BPF_RAW_INSN(0, 0, BPF_REG_1, 0, 1), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_ld_imm64 insn", + .result = REJECT, + }, + { "no bpf_exit", .insns = { BPF_ALU64_REG(BPF_MOV, BPF_REG_0, BPF_REG_2), @@ -313,6 +411,30 @@ static struct bpf_test tests[] = { .result = REJECT, }, { + "invalid fp arithmetic", + /* If this gets ever changed, make sure JITs can deal with it. */ + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 8), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr_unpriv = "R1 pointer arithmetic", + .result_unpriv = REJECT, + .errstr = "R1 invalid mem access", + .result = REJECT, + }, + { + "non-invalid fp arithmetic", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + }, + { "invalid argument register", .insns = { BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, @@ -754,6 +876,9 @@ static struct bpf_test tests[] = { BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, offsetof(struct __sk_buff, vlan_tci)), BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 0, 0), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, napi_id)), + BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 0, 0), BPF_EXIT_INSN(), }, .result = ACCEPT, @@ -859,15 +984,451 @@ static struct bpf_test tests[] = { .result = REJECT, }, { - "check non-u32 access to cb", + "check cb access: byte", .insns = { - BPF_STX_MEM(BPF_H, BPF_REG_1, BPF_REG_1, + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[0])), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[0]) + 1), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[0]) + 2), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[0]) + 3), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[1])), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[1]) + 1), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[1]) + 2), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[1]) + 3), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[2])), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[2]) + 1), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[2]) + 2), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[2]) + 3), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[3])), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[3]) + 1), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[3]) + 2), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[3]) + 3), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[4])), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[4]) + 1), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[4]) + 2), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[4]) + 3), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[0])), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[0]) + 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[0]) + 2), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[0]) + 3), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[1])), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[1]) + 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[1]) + 2), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[1]) + 3), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[2])), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[2]) + 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[2]) + 2), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[2]) + 3), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[3])), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[3]) + 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[3]) + 2), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[3]) + 3), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[4])), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[4]) + 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[4]) + 2), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[4]) + 3), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + }, + { + "check cb access: byte, oob 1", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[4]) + 4), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + }, + { + "check cb access: byte, oob 2", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[0]) - 1), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + }, + { + "check cb access: byte, oob 3", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[4]) + 4), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + }, + { + "check cb access: byte, oob 4", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[0]) - 1), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + }, + { + "check cb access: byte, wrong type", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, offsetof(struct __sk_buff, cb[0])), BPF_EXIT_INSN(), }, .errstr = "invalid bpf_context access", - .errstr_unpriv = "R1 leaks addr", .result = REJECT, + .prog_type = BPF_PROG_TYPE_CGROUP_SOCK, + }, + { + "check cb access: half", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_H, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[0])), + BPF_STX_MEM(BPF_H, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[0]) + 2), + BPF_STX_MEM(BPF_H, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[1])), + BPF_STX_MEM(BPF_H, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[1]) + 2), + BPF_STX_MEM(BPF_H, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[2])), + BPF_STX_MEM(BPF_H, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[2]) + 2), + BPF_STX_MEM(BPF_H, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[3])), + BPF_STX_MEM(BPF_H, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[3]) + 2), + BPF_STX_MEM(BPF_H, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[4])), + BPF_STX_MEM(BPF_H, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[4]) + 2), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[0])), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[0]) + 2), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[1])), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[1]) + 2), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[2])), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[2]) + 2), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[3])), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[3]) + 2), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[4])), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[4]) + 2), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + }, + { + "check cb access: half, unaligned", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_H, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[0]) + 1), + BPF_EXIT_INSN(), + }, + .errstr = "misaligned access", + .result = REJECT, + }, + { + "check cb access: half, oob 1", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_H, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[4]) + 4), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + }, + { + "check cb access: half, oob 2", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_H, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[0]) - 2), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + }, + { + "check cb access: half, oob 3", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[4]) + 4), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + }, + { + "check cb access: half, oob 4", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[0]) - 2), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + }, + { + "check cb access: half, wrong type", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_H, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[0])), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_CGROUP_SOCK, + }, + { + "check cb access: word", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[0])), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[1])), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[2])), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[3])), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[4])), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[0])), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[1])), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[2])), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[3])), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[4])), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + }, + { + "check cb access: word, unaligned 1", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[0]) + 2), + BPF_EXIT_INSN(), + }, + .errstr = "misaligned access", + .result = REJECT, + }, + { + "check cb access: word, unaligned 2", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[4]) + 1), + BPF_EXIT_INSN(), + }, + .errstr = "misaligned access", + .result = REJECT, + }, + { + "check cb access: word, unaligned 3", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[4]) + 2), + BPF_EXIT_INSN(), + }, + .errstr = "misaligned access", + .result = REJECT, + }, + { + "check cb access: word, unaligned 4", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[4]) + 3), + BPF_EXIT_INSN(), + }, + .errstr = "misaligned access", + .result = REJECT, + }, + { + "check cb access: double", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[0])), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[2])), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[0])), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[2])), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + }, + { + "check cb access: double, unaligned 1", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[1])), + BPF_EXIT_INSN(), + }, + .errstr = "misaligned access", + .result = REJECT, + }, + { + "check cb access: double, unaligned 2", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[3])), + BPF_EXIT_INSN(), + }, + .errstr = "misaligned access", + .result = REJECT, + }, + { + "check cb access: double, oob 1", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[4])), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + }, + { + "check cb access: double, oob 2", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[4]) + 8), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + }, + { + "check cb access: double, oob 3", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[0]) - 8), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + }, + { + "check cb access: double, oob 4", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[4])), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + }, + { + "check cb access: double, oob 5", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[4]) + 8), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + }, + { + "check cb access: double, oob 6", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[0]) - 8), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + }, + { + "check cb access: double, wrong type", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[0])), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_CGROUP_SOCK, }, { "check out of range skb->cb access", @@ -1344,6 +1905,20 @@ static struct bpf_test tests[] = { .result = ACCEPT, }, { + "unpriv: adding of fp", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_1, 0), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_10), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, -8), + BPF_EXIT_INSN(), + }, + .errstr_unpriv = "pointer arithmetic prohibited", + .result_unpriv = REJECT, + .errstr = "R1 invalid mem access", + .result = REJECT, + }, + { "unpriv: cmp of stack pointer", .insns = { BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), @@ -1357,16 +1932,22 @@ static struct bpf_test tests[] = { .result = ACCEPT, }, { - "unpriv: obfuscate stack pointer", + "stack pointer arithmetic", .insns = { - BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_MOV64_IMM(BPF_REG_1, 4), + BPF_JMP_IMM(BPF_JA, 0, 0, 0), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -10), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_7), + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_1), + BPF_ST_MEM(0, BPF_REG_2, 4, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_7), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 8), + BPF_ST_MEM(0, BPF_REG_2, 4, 0), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr_unpriv = "R2 pointer arithmetic", - .result_unpriv = REJECT, .result = ACCEPT, }, { @@ -1890,6 +2471,150 @@ static struct bpf_test tests[] = { .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, { + "direct packet access: test11 (shift, good access)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 22), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 8), + BPF_MOV64_IMM(BPF_REG_3, 144), + BPF_MOV64_REG(BPF_REG_5, BPF_REG_3), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 23), + BPF_ALU64_IMM(BPF_RSH, BPF_REG_5, 3), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_6, BPF_REG_5), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "direct packet access: test12 (and, good access)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 22), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 8), + BPF_MOV64_IMM(BPF_REG_3, 144), + BPF_MOV64_REG(BPF_REG_5, BPF_REG_3), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 23), + BPF_ALU64_IMM(BPF_AND, BPF_REG_5, 15), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_6, BPF_REG_5), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "direct packet access: test13 (branches, good access)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 22), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 13), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, mark)), + BPF_MOV64_IMM(BPF_REG_4, 1), + BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_4, 2), + BPF_MOV64_IMM(BPF_REG_3, 14), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_MOV64_IMM(BPF_REG_3, 24), + BPF_MOV64_REG(BPF_REG_5, BPF_REG_3), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 23), + BPF_ALU64_IMM(BPF_AND, BPF_REG_5, 15), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_6, BPF_REG_5), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "direct packet access: test14 (pkt_ptr += 0, CONST_IMM, good access)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 22), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 7), + BPF_MOV64_IMM(BPF_REG_5, 12), + BPF_ALU64_IMM(BPF_RSH, BPF_REG_5, 4), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_6, BPF_REG_5), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_6, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "direct packet access: test15 (spill with xadd)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 8), + BPF_MOV64_IMM(BPF_REG_5, 4096), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0), + BPF_STX_XADD(BPF_DW, BPF_REG_4, BPF_REG_5, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_4, 0), + BPF_STX_MEM(BPF_W, BPF_REG_2, BPF_REG_5, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R2 invalid mem access 'inv'", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "direct packet access: test16 (arith on data_end)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 16), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), + BPF_STX_MEM(BPF_B, BPF_REG_2, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid access to packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { "helper access to packet: test1, valid packet_ptr range", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, @@ -2392,6 +3117,7 @@ static struct bpf_test tests[] = { .errstr_unpriv = "R0 pointer arithmetic prohibited", .result_unpriv = REJECT, .result = ACCEPT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "valid map access into an array with a variable", @@ -2415,6 +3141,7 @@ static struct bpf_test tests[] = { .errstr_unpriv = "R0 pointer arithmetic prohibited", .result_unpriv = REJECT, .result = ACCEPT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "valid map access into an array with a signed variable", @@ -2442,6 +3169,7 @@ static struct bpf_test tests[] = { .errstr_unpriv = "R0 pointer arithmetic prohibited", .result_unpriv = REJECT, .result = ACCEPT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "invalid map access into an array with a constant", @@ -2483,6 +3211,7 @@ static struct bpf_test tests[] = { .errstr = "R0 min value is outside of the array range", .result_unpriv = REJECT, .result = REJECT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "invalid map access into an array with a variable", @@ -2506,6 +3235,7 @@ static struct bpf_test tests[] = { .errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.", .result_unpriv = REJECT, .result = REJECT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "invalid map access into an array with no floor check", @@ -2532,6 +3262,7 @@ static struct bpf_test tests[] = { .errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.", .result_unpriv = REJECT, .result = REJECT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "invalid map access into an array with a invalid max check", @@ -2558,6 +3289,7 @@ static struct bpf_test tests[] = { .errstr = "invalid access to map value, value_size=48 off=44 size=8", .result_unpriv = REJECT, .result = REJECT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "invalid map access into an array with a invalid max check", @@ -2587,6 +3319,7 @@ static struct bpf_test tests[] = { .errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.", .result_unpriv = REJECT, .result = REJECT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "multiple registers share map_lookup_elem result", @@ -2710,6 +3443,7 @@ static struct bpf_test tests[] = { .result = REJECT, .errstr_unpriv = "R0 pointer arithmetic prohibited", .result_unpriv = REJECT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "constant register |= constant should keep constant type", @@ -2876,6 +3610,26 @@ static struct bpf_test tests[] = { .prog_type = BPF_PROG_TYPE_LWT_XMIT, }, { + "overlapping checks for direct packet access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_2, 6), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_LWT_XMIT, + }, + { "invalid access of tc_classid for LWT_IN", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, @@ -2905,6 +3659,1285 @@ static struct bpf_test tests[] = { .result = REJECT, .errstr = "invalid bpf_context access", }, + { + "helper access to map: full range", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_2, sizeof(struct test_val)), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to map: partial range", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_2, 8), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to map: empty range", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr = "invalid access to map value, value_size=48 off=0 size=0", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to map: out-of-bound range", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_2, sizeof(struct test_val) + 8), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr = "invalid access to map value, value_size=48 off=0 size=56", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to map: negative range", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_2, -8), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr = "invalid access to map value, value_size=48 off=0 size=-8", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to adjusted map (via const imm): full range", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, + offsetof(struct test_val, foo)), + BPF_MOV64_IMM(BPF_REG_2, + sizeof(struct test_val) - + offsetof(struct test_val, foo)), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to adjusted map (via const imm): partial range", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, + offsetof(struct test_val, foo)), + BPF_MOV64_IMM(BPF_REG_2, 8), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to adjusted map (via const imm): empty range", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, + offsetof(struct test_val, foo)), + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr = "R1 min value is outside of the array range", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to adjusted map (via const imm): out-of-bound range", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, + offsetof(struct test_val, foo)), + BPF_MOV64_IMM(BPF_REG_2, + sizeof(struct test_val) - + offsetof(struct test_val, foo) + 8), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr = "invalid access to map value, value_size=48 off=4 size=52", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to adjusted map (via const imm): negative range (> adjustment)", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, + offsetof(struct test_val, foo)), + BPF_MOV64_IMM(BPF_REG_2, -8), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr = "invalid access to map value, value_size=48 off=4 size=-8", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to adjusted map (via const imm): negative range (< adjustment)", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, + offsetof(struct test_val, foo)), + BPF_MOV64_IMM(BPF_REG_2, -1), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr = "R1 min value is outside of the array range", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to adjusted map (via const reg): full range", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_3, + offsetof(struct test_val, foo)), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3), + BPF_MOV64_IMM(BPF_REG_2, + sizeof(struct test_val) - + offsetof(struct test_val, foo)), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to adjusted map (via const reg): partial range", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_3, + offsetof(struct test_val, foo)), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3), + BPF_MOV64_IMM(BPF_REG_2, 8), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to adjusted map (via const reg): empty range", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3), + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr = "R1 min value is outside of the array range", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to adjusted map (via const reg): out-of-bound range", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_3, + offsetof(struct test_val, foo)), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3), + BPF_MOV64_IMM(BPF_REG_2, + sizeof(struct test_val) - + offsetof(struct test_val, foo) + 8), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr = "invalid access to map value, value_size=48 off=4 size=52", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to adjusted map (via const reg): negative range (> adjustment)", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_3, + offsetof(struct test_val, foo)), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3), + BPF_MOV64_IMM(BPF_REG_2, -8), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr = "invalid access to map value, value_size=48 off=4 size=-8", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to adjusted map (via const reg): negative range (< adjustment)", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_3, + offsetof(struct test_val, foo)), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3), + BPF_MOV64_IMM(BPF_REG_2, -1), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr = "R1 min value is outside of the array range", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to adjusted map (via variable): full range", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JGT, BPF_REG_3, + offsetof(struct test_val, foo), 4), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3), + BPF_MOV64_IMM(BPF_REG_2, + sizeof(struct test_val) - + offsetof(struct test_val, foo)), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to adjusted map (via variable): partial range", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JGT, BPF_REG_3, + offsetof(struct test_val, foo), 4), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3), + BPF_MOV64_IMM(BPF_REG_2, 8), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to adjusted map (via variable): empty range", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JGT, BPF_REG_3, + offsetof(struct test_val, foo), 4), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3), + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr = "R1 min value is outside of the array range", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to adjusted map (via variable): no max check", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3), + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr = "R1 min value is negative, either use unsigned index or do a if (index >=0) check", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to adjusted map (via variable): wrong max check", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JGT, BPF_REG_3, + offsetof(struct test_val, foo), 4), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3), + BPF_MOV64_IMM(BPF_REG_2, + sizeof(struct test_val) - + offsetof(struct test_val, foo) + 1), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr = "invalid access to map value, value_size=48 off=4 size=45", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map element value is preserved across register spilling", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 42), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -184), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_1, 0), + BPF_ST_MEM(BPF_DW, BPF_REG_3, 0, 42), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr_unpriv = "R0 leaks addr", + .result = ACCEPT, + .result_unpriv = REJECT, + }, + { + "map element value or null is marked on register spilling", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -152), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_1, 0), + BPF_ST_MEM(BPF_DW, BPF_REG_3, 0, 42), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr_unpriv = "R0 leaks addr", + .result = ACCEPT, + .result_unpriv = REJECT, + }, + { + "map element value store of cleared call register", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 0), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr_unpriv = "R1 !read_ok", + .errstr = "R1 !read_ok", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "map element value with unaligned store", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 17), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 3), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 42), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 2, 43), + BPF_ST_MEM(BPF_DW, BPF_REG_0, -2, 44), + BPF_MOV64_REG(BPF_REG_8, BPF_REG_0), + BPF_ST_MEM(BPF_DW, BPF_REG_8, 0, 32), + BPF_ST_MEM(BPF_DW, BPF_REG_8, 2, 33), + BPF_ST_MEM(BPF_DW, BPF_REG_8, -2, 34), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_8, 5), + BPF_ST_MEM(BPF_DW, BPF_REG_8, 0, 22), + BPF_ST_MEM(BPF_DW, BPF_REG_8, 4, 23), + BPF_ST_MEM(BPF_DW, BPF_REG_8, -7, 24), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_8), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, 3), + BPF_ST_MEM(BPF_DW, BPF_REG_7, 0, 22), + BPF_ST_MEM(BPF_DW, BPF_REG_7, 4, 23), + BPF_ST_MEM(BPF_DW, BPF_REG_7, -4, 24), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .result = ACCEPT, + .result_unpriv = REJECT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, + }, + { + "map element value with unaligned load", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11), + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JGE, BPF_REG_1, MAX_ENTRIES, 9), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 3), + BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 2), + BPF_MOV64_REG(BPF_REG_8, BPF_REG_0), + BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_8, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_8, 2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 5), + BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 4), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .result = ACCEPT, + .result_unpriv = REJECT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, + }, + { + "map element value illegal alu op, 1", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 8), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "invalid mem access 'inv'", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "map element value illegal alu op, 2", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_ALU32_IMM(BPF_ADD, BPF_REG_0, 0), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "invalid mem access 'inv'", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "map element value illegal alu op, 3", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_ALU64_IMM(BPF_DIV, BPF_REG_0, 42), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "invalid mem access 'inv'", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "map element value illegal alu op, 4", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_ENDIAN(BPF_FROM_BE, BPF_REG_0, 64), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "invalid mem access 'inv'", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "map element value illegal alu op, 5", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), + BPF_MOV64_IMM(BPF_REG_3, 4096), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 0), + BPF_STX_XADD(BPF_DW, BPF_REG_2, BPF_REG_3, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_2, 0), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr_unpriv = "R0 invalid mem access 'inv'", + .errstr = "R0 invalid mem access 'inv'", + .result = REJECT, + .result_unpriv = REJECT, + }, + { + "map element value is preserved across register spilling", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, + offsetof(struct test_val, foo)), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 42), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -184), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_1, 0), + BPF_ST_MEM(BPF_DW, BPF_REG_3, 0, 42), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .result = ACCEPT, + .result_unpriv = REJECT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, + }, + { + "helper access to variable memory: stack, bitwise AND + JMP, correct bounds", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -64), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -56), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -48), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -40), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -32), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -24), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8), + BPF_MOV64_IMM(BPF_REG_2, 16), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128), + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128), + BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 64), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to variable memory: stack, bitwise AND, zero included", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64), + BPF_MOV64_IMM(BPF_REG_2, 16), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128), + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128), + BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 64), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_EXIT_INSN(), + }, + .errstr = "invalid stack type R1 off=-64 access_size=0", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to variable memory: stack, bitwise AND + JMP, wrong max", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64), + BPF_MOV64_IMM(BPF_REG_2, 16), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128), + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128), + BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 65), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid stack type R1 off=-64 access_size=65", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to variable memory: stack, JMP, correct bounds", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -64), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -56), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -48), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -40), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -32), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -24), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8), + BPF_MOV64_IMM(BPF_REG_2, 16), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128), + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128), + BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 64, 4), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to variable memory: stack, JMP (signed), correct bounds", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -64), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -56), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -48), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -40), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -32), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -24), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8), + BPF_MOV64_IMM(BPF_REG_2, 16), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128), + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_2, 64, 4), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_JMP_REG(BPF_JSGE, BPF_REG_4, BPF_REG_2, 2), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to variable memory: stack, JMP, bounds + offset", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64), + BPF_MOV64_IMM(BPF_REG_2, 16), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128), + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128), + BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 64, 5), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 3), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 1), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid stack type R1 off=-64 access_size=65", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to variable memory: stack, JMP, wrong max", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64), + BPF_MOV64_IMM(BPF_REG_2, 16), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128), + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128), + BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 65, 4), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid stack type R1 off=-64 access_size=65", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to variable memory: stack, JMP, no max check", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64), + BPF_MOV64_IMM(BPF_REG_2, 16), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128), + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R2 unbounded memory access", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to variable memory: stack, JMP, no min check", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64), + BPF_MOV64_IMM(BPF_REG_2, 16), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128), + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128), + BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 64, 3), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid stack type R1 off=-64 access_size=0", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to variable memory: stack, JMP (signed), no min check", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64), + BPF_MOV64_IMM(BPF_REG_2, 16), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128), + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_2, 64, 3), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R2 min value is negative", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to variable memory: map, JMP, correct bounds", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 10), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_2, sizeof(struct test_val)), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -128), + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -128), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_2, + sizeof(struct test_val), 4), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to variable memory: map, JMP, wrong max", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 10), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_2, sizeof(struct test_val)), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -128), + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -128), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_2, + sizeof(struct test_val) + 1, 4), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr = "invalid access to map value, value_size=48 off=0 size=49", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to variable memory: map adjusted, JMP, correct bounds", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 20), + BPF_MOV64_IMM(BPF_REG_2, sizeof(struct test_val)), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -128), + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -128), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_2, + sizeof(struct test_val) - 20, 4), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to variable memory: map adjusted, JMP, wrong max", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 20), + BPF_MOV64_IMM(BPF_REG_2, sizeof(struct test_val)), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -128), + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -128), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_2, + sizeof(struct test_val) - 19, 4), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr = "R1 min value is outside of the array range", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to variable memory: size > 0 not allowed on NULL", + .insns = { + BPF_MOV64_IMM(BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -128), + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -128), + BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 64), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_MOV64_IMM(BPF_REG_5, 0), + BPF_EMIT_CALL(BPF_FUNC_csum_diff), + BPF_EXIT_INSN(), + }, + .errstr = "R1 type=imm expected=fp", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "helper access to variable memory: size = 0 not allowed on != NULL", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, 0), + BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 8), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_MOV64_IMM(BPF_REG_5, 0), + BPF_EMIT_CALL(BPF_FUNC_csum_diff), + BPF_EXIT_INSN(), + }, + .errstr = "invalid stack type R1 off=-8 access_size=0", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "helper access to variable memory: 8 bytes leak", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -64), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -56), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -48), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -40), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -24), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8), + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -128), + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -128), + BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 63), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 1), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_EXIT_INSN(), + }, + .errstr = "invalid indirect read from stack off -64+32 size 64", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to variable memory: 8 bytes no leak (init memory)", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -64), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -56), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -48), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -40), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -32), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -24), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64), + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 32), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 32), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "invalid and of negative number", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_IMM(BPF_REG_1, 6), + BPF_ALU64_IMM(BPF_AND, BPF_REG_1, -4), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, + offsetof(struct test_val, foo)), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.", + .result = REJECT, + .result_unpriv = REJECT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, + }, + { + "invalid range check", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 12), + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_9, 1), + BPF_ALU32_IMM(BPF_MOD, BPF_REG_1, 2), + BPF_ALU32_IMM(BPF_ADD, BPF_REG_1, 1), + BPF_ALU32_REG(BPF_AND, BPF_REG_9, BPF_REG_1), + BPF_ALU32_IMM(BPF_ADD, BPF_REG_9, 1), + BPF_ALU32_IMM(BPF_RSH, BPF_REG_9, 1), + BPF_MOV32_IMM(BPF_REG_3, 1), + BPF_ALU32_REG(BPF_SUB, BPF_REG_3, BPF_REG_9), + BPF_ALU32_IMM(BPF_MUL, BPF_REG_3, 0x10000000), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_3), + BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_3, 0), + BPF_MOV64_REG(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.", + .result = REJECT, + .result_unpriv = REJECT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, + }, + { + "map in map access", + .insns = { + BPF_ST_MEM(0, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5), + BPF_ST_MEM(0, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_MOV64_REG(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_in_map = { 3 }, + .result = ACCEPT, + }, + { + "invalid inner map pointer", + .insns = { + BPF_ST_MEM(0, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + BPF_ST_MEM(0, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_MOV64_REG(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_in_map = { 3 }, + .errstr = "R1 type=inv expected=map_ptr", + .errstr_unpriv = "R1 pointer arithmetic prohibited", + .result = REJECT, + }, + { + "forgot null checking on the inner map pointer", + .insns = { + BPF_ST_MEM(0, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_ST_MEM(0, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_MOV64_REG(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_in_map = { 3 }, + .errstr = "R1 type=map_value_or_null expected=map_ptr", + .result = REJECT, + } }; static int probe_filter_length(const struct bpf_insn *fp) @@ -2921,7 +4954,7 @@ static int create_map(uint32_t size_value, uint32_t max_elem) { int fd; - fd = bpf_map_create(BPF_MAP_TYPE_HASH, sizeof(long long), + fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(long long), size_value, max_elem, BPF_F_NO_PREALLOC); if (fd < 0) printf("Failed to create hash map '%s'!\n", strerror(errno)); @@ -2933,7 +4966,7 @@ static int create_prog_array(void) { int fd; - fd = bpf_map_create(BPF_MAP_TYPE_PROG_ARRAY, sizeof(int), + fd = bpf_create_map(BPF_MAP_TYPE_PROG_ARRAY, sizeof(int), sizeof(int), 4, 0); if (fd < 0) printf("Failed to create prog array '%s'!\n", strerror(errno)); @@ -2941,66 +4974,112 @@ static int create_prog_array(void) return fd; } +static int create_map_in_map(void) +{ + int inner_map_fd, outer_map_fd; + + inner_map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, sizeof(int), + sizeof(int), 1, 0); + if (inner_map_fd < 0) { + printf("Failed to create array '%s'!\n", strerror(errno)); + return inner_map_fd; + } + + outer_map_fd = bpf_create_map_in_map(BPF_MAP_TYPE_ARRAY_OF_MAPS, + sizeof(int), inner_map_fd, 1, 0); + if (outer_map_fd < 0) + printf("Failed to create array of maps '%s'!\n", + strerror(errno)); + + close(inner_map_fd); + + return outer_map_fd; +} + static char bpf_vlog[32768]; static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog, - int *fd_f1, int *fd_f2, int *fd_f3) + int *map_fds) { int *fixup_map1 = test->fixup_map1; int *fixup_map2 = test->fixup_map2; int *fixup_prog = test->fixup_prog; + int *fixup_map_in_map = test->fixup_map_in_map; /* Allocating HTs with 1 elem is fine here, since we only test * for verifier and not do a runtime lookup, so the only thing * that really matters is value size in this case. */ if (*fixup_map1) { - *fd_f1 = create_map(sizeof(long long), 1); + map_fds[0] = create_map(sizeof(long long), 1); do { - prog[*fixup_map1].imm = *fd_f1; + prog[*fixup_map1].imm = map_fds[0]; fixup_map1++; } while (*fixup_map1); } if (*fixup_map2) { - *fd_f2 = create_map(sizeof(struct test_val), 1); + map_fds[1] = create_map(sizeof(struct test_val), 1); do { - prog[*fixup_map2].imm = *fd_f2; + prog[*fixup_map2].imm = map_fds[1]; fixup_map2++; } while (*fixup_map2); } if (*fixup_prog) { - *fd_f3 = create_prog_array(); + map_fds[2] = create_prog_array(); do { - prog[*fixup_prog].imm = *fd_f3; + prog[*fixup_prog].imm = map_fds[2]; fixup_prog++; } while (*fixup_prog); } + + if (*fixup_map_in_map) { + map_fds[3] = create_map_in_map(); + do { + prog[*fixup_map_in_map].imm = map_fds[3]; + fixup_map_in_map++; + } while (*fixup_map_in_map); + } } static void do_test_single(struct bpf_test *test, bool unpriv, int *passes, int *errors) { + int fd_prog, expected_ret, reject_from_alignment; struct bpf_insn *prog = test->insns; int prog_len = probe_filter_length(prog); int prog_type = test->prog_type; - int fd_f1 = -1, fd_f2 = -1, fd_f3 = -1; - int fd_prog, expected_ret; + int map_fds[MAX_NR_MAPS]; const char *expected_err; + int i; - do_test_fixup(test, prog, &fd_f1, &fd_f2, &fd_f3); + for (i = 0; i < MAX_NR_MAPS; i++) + map_fds[i] = -1; - fd_prog = bpf_prog_load(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER, - prog, prog_len * sizeof(struct bpf_insn), - "GPL", bpf_vlog, sizeof(bpf_vlog)); + do_test_fixup(test, prog, map_fds); + + fd_prog = bpf_load_program(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER, + prog, prog_len, "GPL", 0, bpf_vlog, + sizeof(bpf_vlog)); expected_ret = unpriv && test->result_unpriv != UNDEF ? test->result_unpriv : test->result; expected_err = unpriv && test->errstr_unpriv ? test->errstr_unpriv : test->errstr; + + reject_from_alignment = fd_prog < 0 && + (test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS) && + strstr(bpf_vlog, "Unknown alignment."); +#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS + if (reject_from_alignment) { + printf("FAIL\nFailed due to alignment despite having efficient unaligned access: '%s'!\n", + strerror(errno)); + goto fail_log; + } +#endif if (expected_ret == ACCEPT) { - if (fd_prog < 0) { + if (fd_prog < 0 && !reject_from_alignment) { printf("FAIL\nFailed to load prog '%s'!\n", strerror(errno)); goto fail_log; @@ -3010,19 +5089,19 @@ static void do_test_single(struct bpf_test *test, bool unpriv, printf("FAIL\nUnexpected success to load!\n"); goto fail_log; } - if (!strstr(bpf_vlog, expected_err)) { + if (!strstr(bpf_vlog, expected_err) && !reject_from_alignment) { printf("FAIL\nUnexpected error message!\n"); goto fail_log; } } (*passes)++; - printf("OK\n"); + printf("OK%s\n", reject_from_alignment ? + " (NOTE: reject due to unknown alignment)" : ""); close_fds: close(fd_prog); - close(fd_f1); - close(fd_f2); - close(fd_f3); + for (i = 0; i < MAX_NR_MAPS; i++) + close(map_fds[i]); sched_yield(); return; fail_log: @@ -3031,6 +5110,57 @@ fail_log: goto close_fds; } +static bool is_admin(void) +{ + cap_t caps; + cap_flag_value_t sysadmin = CAP_CLEAR; + const cap_value_t cap_val = CAP_SYS_ADMIN; + +#ifdef CAP_IS_SUPPORTED + if (!CAP_IS_SUPPORTED(CAP_SETFCAP)) { + perror("cap_get_flag"); + return false; + } +#endif + caps = cap_get_proc(); + if (!caps) { + perror("cap_get_proc"); + return false; + } + if (cap_get_flag(caps, cap_val, CAP_EFFECTIVE, &sysadmin)) + perror("cap_get_flag"); + if (cap_free(caps)) + perror("cap_free"); + return (sysadmin == CAP_SET); +} + +static int set_admin(bool admin) +{ + cap_t caps; + const cap_value_t cap_val = CAP_SYS_ADMIN; + int ret = -1; + + caps = cap_get_proc(); + if (!caps) { + perror("cap_get_proc"); + return -1; + } + if (cap_set_flag(caps, CAP_EFFECTIVE, 1, &cap_val, + admin ? CAP_SET : CAP_CLEAR)) { + perror("cap_set_flag"); + goto out; + } + if (cap_set_proc(caps)) { + perror("cap_set_proc"); + goto out; + } + ret = 0; +out: + if (cap_free(caps)) + perror("cap_free"); + return ret; +} + static int do_test(bool unpriv, unsigned int from, unsigned int to) { int i, passes = 0, errors = 0; @@ -3041,11 +5171,19 @@ static int do_test(bool unpriv, unsigned int from, unsigned int to) /* Program types that are not supported by non-root we * skip right away. */ - if (unpriv && test->prog_type) - continue; + if (!test->prog_type) { + if (!unpriv) + set_admin(false); + printf("#%d/u %s ", i, test->descr); + do_test_single(test, true, &passes, &errors); + if (!unpriv) + set_admin(true); + } - printf("#%d %s ", i, test->descr); - do_test_single(test, unpriv, &passes, &errors); + if (!unpriv) { + printf("#%d/p %s ", i, test->descr); + do_test_single(test, false, &passes, &errors); + } } printf("Summary: %d PASSED, %d FAILED\n", passes, errors); @@ -3057,7 +5195,7 @@ int main(int argc, char **argv) struct rlimit rinf = { RLIM_INFINITY, RLIM_INFINITY }; struct rlimit rlim = { 1 << 20, 1 << 20 }; unsigned int from = 0, to = ARRAY_SIZE(tests); - bool unpriv = geteuid() != 0; + bool unpriv = !is_admin(); if (argc == 3) { unsigned int l = atoi(argv[argc - 2]); diff --git a/tools/testing/selftests/bpf/test_xdp.c b/tools/testing/selftests/bpf/test_xdp.c new file mode 100644 index 000000000000..5e7df8bb5b5d --- /dev/null +++ b/tools/testing/selftests/bpf/test_xdp.c @@ -0,0 +1,235 @@ +/* Copyright (c) 2016,2017 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <stddef.h> +#include <string.h> +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/in.h> +#include <linux/udp.h> +#include <linux/tcp.h> +#include <linux/pkt_cls.h> +#include <sys/socket.h> +#include "bpf_helpers.h" +#include "bpf_endian.h" +#include "test_iptunnel_common.h" + +int _version SEC("version") = 1; + +struct bpf_map_def SEC("maps") rxcnt = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(__u64), + .max_entries = 256, +}; + +struct bpf_map_def SEC("maps") vip2tnl = { + .type = BPF_MAP_TYPE_HASH, + .key_size = sizeof(struct vip), + .value_size = sizeof(struct iptnl_info), + .max_entries = MAX_IPTNL_ENTRIES, +}; + +static __always_inline void count_tx(__u32 protocol) +{ + __u64 *rxcnt_count; + + rxcnt_count = bpf_map_lookup_elem(&rxcnt, &protocol); + if (rxcnt_count) + *rxcnt_count += 1; +} + +static __always_inline int get_dport(void *trans_data, void *data_end, + __u8 protocol) +{ + struct tcphdr *th; + struct udphdr *uh; + + switch (protocol) { + case IPPROTO_TCP: + th = (struct tcphdr *)trans_data; + if (th + 1 > data_end) + return -1; + return th->dest; + case IPPROTO_UDP: + uh = (struct udphdr *)trans_data; + if (uh + 1 > data_end) + return -1; + return uh->dest; + default: + return 0; + } +} + +static __always_inline void set_ethhdr(struct ethhdr *new_eth, + const struct ethhdr *old_eth, + const struct iptnl_info *tnl, + __be16 h_proto) +{ + memcpy(new_eth->h_source, old_eth->h_dest, sizeof(new_eth->h_source)); + memcpy(new_eth->h_dest, tnl->dmac, sizeof(new_eth->h_dest)); + new_eth->h_proto = h_proto; +} + +static __always_inline int handle_ipv4(struct xdp_md *xdp) +{ + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + struct iptnl_info *tnl; + struct ethhdr *new_eth; + struct ethhdr *old_eth; + struct iphdr *iph = data + sizeof(struct ethhdr); + __u16 *next_iph; + __u16 payload_len; + struct vip vip = {}; + int dport; + __u32 csum = 0; + int i; + + if (iph + 1 > data_end) + return XDP_DROP; + + dport = get_dport(iph + 1, data_end, iph->protocol); + if (dport == -1) + return XDP_DROP; + + vip.protocol = iph->protocol; + vip.family = AF_INET; + vip.daddr.v4 = iph->daddr; + vip.dport = dport; + payload_len = bpf_ntohs(iph->tot_len); + + tnl = bpf_map_lookup_elem(&vip2tnl, &vip); + /* It only does v4-in-v4 */ + if (!tnl || tnl->family != AF_INET) + return XDP_PASS; + + if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(struct iphdr))) + return XDP_DROP; + + data = (void *)(long)xdp->data; + data_end = (void *)(long)xdp->data_end; + + new_eth = data; + iph = data + sizeof(*new_eth); + old_eth = data + sizeof(*iph); + + if (new_eth + 1 > data_end || + old_eth + 1 > data_end || + iph + 1 > data_end) + return XDP_DROP; + + set_ethhdr(new_eth, old_eth, tnl, bpf_htons(ETH_P_IP)); + + iph->version = 4; + iph->ihl = sizeof(*iph) >> 2; + iph->frag_off = 0; + iph->protocol = IPPROTO_IPIP; + iph->check = 0; + iph->tos = 0; + iph->tot_len = bpf_htons(payload_len + sizeof(*iph)); + iph->daddr = tnl->daddr.v4; + iph->saddr = tnl->saddr.v4; + iph->ttl = 8; + + next_iph = (__u16 *)iph; +#pragma clang loop unroll(full) + for (i = 0; i < sizeof(*iph) >> 1; i++) + csum += *next_iph++; + + iph->check = ~((csum & 0xffff) + (csum >> 16)); + + count_tx(vip.protocol); + + return XDP_TX; +} + +static __always_inline int handle_ipv6(struct xdp_md *xdp) +{ + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + struct iptnl_info *tnl; + struct ethhdr *new_eth; + struct ethhdr *old_eth; + struct ipv6hdr *ip6h = data + sizeof(struct ethhdr); + __u16 payload_len; + struct vip vip = {}; + int dport; + + if (ip6h + 1 > data_end) + return XDP_DROP; + + dport = get_dport(ip6h + 1, data_end, ip6h->nexthdr); + if (dport == -1) + return XDP_DROP; + + vip.protocol = ip6h->nexthdr; + vip.family = AF_INET6; + memcpy(vip.daddr.v6, ip6h->daddr.s6_addr32, sizeof(vip.daddr)); + vip.dport = dport; + payload_len = ip6h->payload_len; + + tnl = bpf_map_lookup_elem(&vip2tnl, &vip); + /* It only does v6-in-v6 */ + if (!tnl || tnl->family != AF_INET6) + return XDP_PASS; + + if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(struct ipv6hdr))) + return XDP_DROP; + + data = (void *)(long)xdp->data; + data_end = (void *)(long)xdp->data_end; + + new_eth = data; + ip6h = data + sizeof(*new_eth); + old_eth = data + sizeof(*ip6h); + + if (new_eth + 1 > data_end || old_eth + 1 > data_end || + ip6h + 1 > data_end) + return XDP_DROP; + + set_ethhdr(new_eth, old_eth, tnl, bpf_htons(ETH_P_IPV6)); + + ip6h->version = 6; + ip6h->priority = 0; + memset(ip6h->flow_lbl, 0, sizeof(ip6h->flow_lbl)); + ip6h->payload_len = bpf_htons(bpf_ntohs(payload_len) + sizeof(*ip6h)); + ip6h->nexthdr = IPPROTO_IPV6; + ip6h->hop_limit = 8; + memcpy(ip6h->saddr.s6_addr32, tnl->saddr.v6, sizeof(tnl->saddr.v6)); + memcpy(ip6h->daddr.s6_addr32, tnl->daddr.v6, sizeof(tnl->daddr.v6)); + + count_tx(vip.protocol); + + return XDP_TX; +} + +SEC("xdp_tx_iptunnel") +int _xdp_tx_iptunnel(struct xdp_md *xdp) +{ + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + struct ethhdr *eth = data; + __u16 h_proto; + + if (eth + 1 > data_end) + return XDP_DROP; + + h_proto = eth->h_proto; + + if (h_proto == bpf_htons(ETH_P_IP)) + return handle_ipv4(xdp); + else if (h_proto == bpf_htons(ETH_P_IPV6)) + + return handle_ipv6(xdp); + else + return XDP_DROP; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/breakpoints/Makefile b/tools/testing/selftests/breakpoints/Makefile index 61b79e8df1f4..6b214b7b10fb 100644 --- a/tools/testing/selftests/breakpoints/Makefile +++ b/tools/testing/selftests/breakpoints/Makefile @@ -3,17 +3,13 @@ uname_M := $(shell uname -m 2>/dev/null || echo not) ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/) ifeq ($(ARCH),x86) -TEST_PROGS := breakpoint_test +TEST_GEN_PROGS := breakpoint_test endif -ifeq ($(ARCH),aarch64) -TEST_PROGS := breakpoint_test_arm64 +ifneq (,$(filter $(ARCH),aarch64 arm64)) +TEST_GEN_PROGS := breakpoint_test_arm64 endif -TEST_PROGS += step_after_suspend_test - -all: $(TEST_PROGS) +TEST_GEN_PROGS += step_after_suspend_test include ../lib.mk -clean: - rm -fr breakpoint_test breakpoint_test_arm64 step_after_suspend_test diff --git a/tools/testing/selftests/capabilities/Makefile b/tools/testing/selftests/capabilities/Makefile index 008602aed920..29b8adfdac71 100644 --- a/tools/testing/selftests/capabilities/Makefile +++ b/tools/testing/selftests/capabilities/Makefile @@ -1,15 +1,8 @@ -TEST_FILES := validate_cap -TEST_PROGS := test_execve - -BINARIES := $(TEST_FILES) $(TEST_PROGS) +TEST_GEN_FILES := validate_cap +TEST_GEN_PROGS := test_execve CFLAGS += -O2 -g -std=gnu99 -Wall LDLIBS += -lcap-ng -lrt -ldl -all: $(BINARIES) - -clean: - $(RM) $(BINARIES) - include ../lib.mk diff --git a/tools/testing/selftests/cpufreq/Makefile b/tools/testing/selftests/cpufreq/Makefile new file mode 100644 index 000000000000..3955cd96f3a2 --- /dev/null +++ b/tools/testing/selftests/cpufreq/Makefile @@ -0,0 +1,8 @@ +all: + +TEST_PROGS := main.sh +TEST_FILES := cpu.sh cpufreq.sh governor.sh module.sh special-tests.sh + +include ../lib.mk + +clean: diff --git a/tools/testing/selftests/cpufreq/config b/tools/testing/selftests/cpufreq/config new file mode 100644 index 000000000000..27ff72ebd0f5 --- /dev/null +++ b/tools/testing/selftests/cpufreq/config @@ -0,0 +1,15 @@ +CONFIG_CPU_FREQ=y +CONFIG_CPU_FREQ_STAT=y +CONFIG_CPU_FREQ_GOV_POWERSAVE=y +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_PI_LIST=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/cpufreq/cpu.sh b/tools/testing/selftests/cpufreq/cpu.sh new file mode 100755 index 000000000000..8e08a83d65f2 --- /dev/null +++ b/tools/testing/selftests/cpufreq/cpu.sh @@ -0,0 +1,84 @@ +#!/bin/bash +# +# CPU helpers + +# protect against multiple inclusion +if [ $FILE_CPU ]; then + return 0 +else + FILE_CPU=DONE +fi + +source cpufreq.sh + +for_each_cpu() +{ + cpus=$(ls $CPUROOT | grep "cpu[0-9].*") + for cpu in $cpus; do + $@ $cpu + done +} + +for_each_non_boot_cpu() +{ + cpus=$(ls $CPUROOT | grep "cpu[1-9].*") + for cpu in $cpus; do + $@ $cpu + done +} + +#$1: cpu +offline_cpu() +{ + printf "Offline $1\n" + echo 0 > $CPUROOT/$1/online +} + +#$1: cpu +online_cpu() +{ + printf "Online $1\n" + echo 1 > $CPUROOT/$1/online +} + +#$1: cpu +reboot_cpu() +{ + offline_cpu $1 + online_cpu $1 +} + +# Reboot CPUs +# param: number of times we want to run the loop +reboot_cpus() +{ + printf "** Test: Running ${FUNCNAME[0]} for $1 loops **\n\n" + + for i in `seq 1 $1`; do + for_each_non_boot_cpu offline_cpu + for_each_non_boot_cpu online_cpu + printf "\n" + done + + printf "\n%s\n\n" "------------------------------------------------" +} + +# Prints warning for all CPUs with missing cpufreq directory +print_unmanaged_cpus() +{ + for_each_cpu cpu_should_have_cpufreq_directory +} + +# Counts CPUs with cpufreq directories +count_cpufreq_managed_cpus() +{ + count=0; + + for cpu in `ls $CPUROOT | grep "cpu[0-9].*"`; do + if [ -d $CPUROOT/$cpu/cpufreq ]; then + let count=count+1; + fi + done + + echo $count; +} diff --git a/tools/testing/selftests/cpufreq/cpufreq.sh b/tools/testing/selftests/cpufreq/cpufreq.sh new file mode 100755 index 000000000000..1ed3832030b4 --- /dev/null +++ b/tools/testing/selftests/cpufreq/cpufreq.sh @@ -0,0 +1,241 @@ +#!/bin/bash + +# protect against multiple inclusion +if [ $FILE_CPUFREQ ]; then + return 0 +else + FILE_CPUFREQ=DONE +fi + +source cpu.sh + + +# $1: cpu +cpu_should_have_cpufreq_directory() +{ + if [ ! -d $CPUROOT/$1/cpufreq ]; then + printf "Warning: No cpufreq directory present for $1\n" + fi +} + +cpu_should_not_have_cpufreq_directory() +{ + if [ -d $CPUROOT/$1/cpufreq ]; then + printf "Warning: cpufreq directory present for $1\n" + fi +} + +for_each_policy() +{ + policies=$(ls $CPUFREQROOT| grep "policy[0-9].*") + for policy in $policies; do + $@ $policy + done +} + +for_each_policy_concurrent() +{ + policies=$(ls $CPUFREQROOT| grep "policy[0-9].*") + for policy in $policies; do + $@ $policy & + done +} + +# $1: Path +read_cpufreq_files_in_dir() +{ + local files=`ls $1` + + printf "Printing directory: $1\n\n" + + for file in $files; do + if [ -f $1/$file ]; then + printf "$file:" + cat $1/$file + else + printf "\n" + read_cpufreq_files_in_dir "$1/$file" + fi + done + printf "\n" +} + + +read_all_cpufreq_files() +{ + printf "** Test: Running ${FUNCNAME[0]} **\n\n" + + read_cpufreq_files_in_dir $CPUFREQROOT + + printf "%s\n\n" "------------------------------------------------" +} + + +# UPDATE CPUFREQ FILES + +# $1: directory path +update_cpufreq_files_in_dir() +{ + local files=`ls $1` + + printf "Updating directory: $1\n\n" + + for file in $files; do + if [ -f $1/$file ]; then + # file is writable ? + local wfile=$(ls -l $1/$file | awk '$1 ~ /^.*w.*/ { print $NF; }') + + if [ ! -z $wfile ]; then + # scaling_setspeed is a special file and we + # should skip updating it + if [ $file != "scaling_setspeed" ]; then + local val=$(cat $1/$file) + printf "Writing $val to: $file\n" + echo $val > $1/$file + fi + fi + else + printf "\n" + update_cpufreq_files_in_dir "$1/$file" + fi + done + + printf "\n" +} + +# Update all writable files with their existing values +update_all_cpufreq_files() +{ + printf "** Test: Running ${FUNCNAME[0]} **\n\n" + + update_cpufreq_files_in_dir $CPUFREQROOT + + printf "%s\n\n" "------------------------------------------------" +} + + +# CHANGE CPU FREQUENCIES + +# $1: policy +find_current_freq() +{ + cat $CPUFREQROOT/$1/scaling_cur_freq +} + +# $1: policy +# $2: frequency +set_cpu_frequency() +{ + printf "Change frequency for $1 to $2\n" + echo $2 > $CPUFREQROOT/$1/scaling_setspeed +} + +# $1: policy +test_all_frequencies() +{ + local filepath="$CPUFREQROOT/$1" + + backup_governor $1 + + local found=$(switch_governor $1 "userspace") + if [ $found = 1 ]; then + printf "${FUNCNAME[0]}: userspace governor not available for: $1\n" + return; + fi + + printf "Switched governor for $1 to userspace\n\n" + + local freqs=$(cat $filepath/scaling_available_frequencies) + printf "Available frequencies for $1: $freqs\n\n" + + # Set all frequencies one-by-one + for freq in $freqs; do + set_cpu_frequency $1 $freq + done + + printf "\n" + + restore_governor $1 +} + +# $1: loop count +shuffle_frequency_for_all_cpus() +{ + printf "** Test: Running ${FUNCNAME[0]} for $1 loops **\n\n" + + for i in `seq 1 $1`; do + for_each_policy test_all_frequencies + done + printf "\n%s\n\n" "------------------------------------------------" +} + +# Basic cpufreq tests +cpufreq_basic_tests() +{ + printf "*** RUNNING CPUFREQ SANITY TESTS ***\n" + printf "====================================\n\n" + + count=$(count_cpufreq_managed_cpus) + if [ $count = 0 ]; then + printf "No cpu is managed by cpufreq core, exiting\n" + exit; + else + printf "CPUFreq manages: $count CPUs\n\n" + fi + + # Detect & print which CPUs are not managed by cpufreq + print_unmanaged_cpus + + # read/update all cpufreq files + read_all_cpufreq_files + update_all_cpufreq_files + + # hotplug cpus + reboot_cpus 5 + + # Test all frequencies + shuffle_frequency_for_all_cpus 2 + + # Test all governors + shuffle_governors_for_all_cpus 1 +} + +# Suspend/resume +# $1: "suspend" or "hibernate", $2: loop count +do_suspend() +{ + printf "** Test: Running ${FUNCNAME[0]}: Trying $1 for $2 loops **\n\n" + + # Is the directory available + if [ ! -d $SYSFS/power/ -o ! -f $SYSFS/power/state ]; then + printf "$SYSFS/power/state not available\n" + return 1 + fi + + if [ $1 = "suspend" ]; then + filename="mem" + elif [ $1 = "hibernate" ]; then + filename="disk" + else + printf "$1 is not a valid option\n" + return 1 + fi + + if [ -n $filename ]; then + present=$(cat $SYSFS/power/state | grep $filename) + + if [ -z "$present" ]; then + printf "Tried to $1 but $filename isn't present in $SYSFS/power/state\n" + return 1; + fi + + for i in `seq 1 $2`; do + printf "Starting $1\n" + echo $filename > $SYSFS/power/state + printf "Came out of $1\n" + + printf "Do basic tests after finishing $1 to verify cpufreq state\n\n" + cpufreq_basic_tests + done + fi +} diff --git a/tools/testing/selftests/cpufreq/governor.sh b/tools/testing/selftests/cpufreq/governor.sh new file mode 100755 index 000000000000..def645103555 --- /dev/null +++ b/tools/testing/selftests/cpufreq/governor.sh @@ -0,0 +1,153 @@ +#!/bin/bash +# +# Test governors + +# protect against multiple inclusion +if [ $FILE_GOVERNOR ]; then + return 0 +else + FILE_GOVERNOR=DONE +fi + +source cpu.sh +source cpufreq.sh + +CUR_GOV= +CUR_FREQ= + +# Find governor's directory path +# $1: policy, $2: governor +find_gov_directory() +{ + if [ -d $CPUFREQROOT/$2 ]; then + printf "$CPUFREQROOT/$2\n" + elif [ -d $CPUFREQROOT/$1/$2 ]; then + printf "$CPUFREQROOT/$1/$2\n" + else + printf "INVALID\n" + fi +} + +# $1: policy +find_current_governor() +{ + cat $CPUFREQROOT/$1/scaling_governor +} + +# $1: policy +backup_governor() +{ + CUR_GOV=$(find_current_governor $1) + + printf "Governor backup done for $1: $CUR_GOV\n" + + if [ $CUR_GOV == "userspace" ]; then + CUR_FREQ=$(find_current_freq $1) + printf "Governor frequency backup done for $1: $CUR_FREQ\n" + fi + + printf "\n" +} + +# $1: policy +restore_governor() +{ + __switch_governor $1 $CUR_GOV + + printf "Governor restored for $1 to $CUR_GOV\n" + + if [ $CUR_GOV == "userspace" ]; then + set_cpu_frequency $1 $CUR_FREQ + printf "Governor frequency restored for $1: $CUR_FREQ\n" + fi + + printf "\n" +} + +# param: +# $1: policy, $2: governor +__switch_governor() +{ + echo $2 > $CPUFREQROOT/$1/scaling_governor +} + +# param: +# $1: cpu, $2: governor +__switch_governor_for_cpu() +{ + echo $2 > $CPUROOT/$1/cpufreq/scaling_governor +} + +# SWITCH GOVERNORS + +# $1: cpu, $2: governor +switch_governor() +{ + local filepath=$CPUFREQROOT/$1/scaling_available_governors + + # check if governor is available + local found=$(cat $filepath | grep $2 | wc -l) + if [ $found = 0 ]; then + echo 1; + return + fi + + __switch_governor $1 $2 + echo 0; +} + +# $1: policy, $2: governor +switch_show_governor() +{ + cur_gov=find_current_governor + if [ $cur_gov == "userspace" ]; then + cur_freq=find_current_freq + fi + + # switch governor + __switch_governor $1 $2 + + printf "\nSwitched governor for $1 to $2\n\n" + + if [ $2 == "userspace" -o $2 == "powersave" -o $2 == "performance" ]; then + printf "No files to read for $2 governor\n\n" + return + fi + + # show governor files + local govpath=$(find_gov_directory $1 $2) + read_cpufreq_files_in_dir $govpath +} + +# $1: function to be called, $2: policy +call_for_each_governor() +{ + local filepath=$CPUFREQROOT/$2/scaling_available_governors + + # Exit if cpu isn't managed by cpufreq core + if [ ! -f $filepath ]; then + return; + fi + + backup_governor $2 + + local governors=$(cat $filepath) + printf "Available governors for $2: $governors\n" + + for governor in $governors; do + $1 $2 $governor + done + + restore_governor $2 +} + +# $1: loop count +shuffle_governors_for_all_cpus() +{ + printf "** Test: Running ${FUNCNAME[0]} for $1 loops **\n\n" + + for i in `seq 1 $1`; do + for_each_policy call_for_each_governor switch_show_governor + done + printf "%s\n\n" "------------------------------------------------" +} diff --git a/tools/testing/selftests/cpufreq/main.sh b/tools/testing/selftests/cpufreq/main.sh new file mode 100755 index 000000000000..01bac76ac0ec --- /dev/null +++ b/tools/testing/selftests/cpufreq/main.sh @@ -0,0 +1,194 @@ +#!/bin/bash + +source cpu.sh +source cpufreq.sh +source governor.sh +source module.sh +source special-tests.sh + +FUNC=basic # do basic tests by default +OUTFILE=cpufreq_selftest +SYSFS= +CPUROOT= +CPUFREQROOT= + +helpme() +{ + printf "Usage: $0 [-h] [-todg args] + [-h <help>] + [-o <output-file-for-dump>] + [-t <basic: Basic cpufreq testing + suspend: suspend/resume, + hibernate: hibernate/resume, + modtest: test driver or governor modules. Only to be used with -d or -g options, + sptest1: Simple governor switch to produce lockdep. + sptest2: Concurrent governor switch to produce lockdep. + sptest3: Governor races, shuffle between governors quickly. + sptest4: CPU hotplugs with updates to cpufreq files.>] + [-d <driver's module name: only with \"-t modtest>\"] + [-g <governor's module name: only with \"-t modtest>\"] + \n" + exit 2 +} + +prerequisite() +{ + msg="skip all tests:" + + if [ $UID != 0 ]; then + echo $msg must be run as root >&2 + exit 2 + fi + + taskset -p 01 $$ + + SYSFS=`mount -t sysfs | head -1 | awk '{ print $3 }'` + + if [ ! -d "$SYSFS" ]; then + echo $msg sysfs is not mounted >&2 + exit 2 + fi + + CPUROOT=$SYSFS/devices/system/cpu + CPUFREQROOT="$CPUROOT/cpufreq" + + if ! ls $CPUROOT/cpu* > /dev/null 2>&1; then + echo $msg cpus not available in sysfs >&2 + exit 2 + fi + + if ! ls $CPUROOT/cpufreq > /dev/null 2>&1; then + echo $msg cpufreq directory not available in sysfs >&2 + exit 2 + fi +} + +parse_arguments() +{ + while getopts ht:o:d:g: arg + do + case $arg in + h) # --help + helpme + ;; + + t) # --func_type (Function to perform: basic, suspend, hibernate, modtest, sptest1/2/3/4 (default: basic)) + FUNC=$OPTARG + ;; + + o) # --output-file (Output file to store dumps) + OUTFILE=$OPTARG + ;; + + d) # --driver-mod-name (Name of the driver module) + DRIVER_MOD=$OPTARG + ;; + + g) # --governor-mod-name (Name of the governor module) + GOVERNOR_MOD=$OPTARG + ;; + + \?) + helpme + ;; + esac + done +} + +do_test() +{ + # Check if CPUs are managed by cpufreq or not + count=$(count_cpufreq_managed_cpus) + + if [ $count = 0 -a $FUNC != "modtest" ]; then + echo "No cpu is managed by cpufreq core, exiting" + exit 2; + fi + + case "$FUNC" in + "basic") + cpufreq_basic_tests + ;; + + "suspend") + do_suspend "suspend" 1 + ;; + + "hibernate") + do_suspend "hibernate" 1 + ;; + + "modtest") + # Do we have modules in place? + if [ -z $DRIVER_MOD ] && [ -z $GOVERNOR_MOD ]; then + echo "No driver or governor module passed with -d or -g" + exit 2; + fi + + if [ $DRIVER_MOD ]; then + if [ $GOVERNOR_MOD ]; then + module_test $DRIVER_MOD $GOVERNOR_MOD + else + module_driver_test $DRIVER_MOD + fi + else + if [ $count = 0 ]; then + echo "No cpu is managed by cpufreq core, exiting" + exit 2; + fi + + module_governor_test $GOVERNOR_MOD + fi + ;; + + "sptest1") + simple_lockdep + ;; + + "sptest2") + concurrent_lockdep + ;; + + "sptest3") + governor_race + ;; + + "sptest4") + hotplug_with_updates + ;; + + *) + echo "Invalid [-f] function type" + helpme + ;; + esac +} + +# clear dumps +# $1: file name +clear_dumps() +{ + echo "" > $1.txt + echo "" > $1.dmesg_cpufreq.txt + echo "" > $1.dmesg_full.txt +} + +# $1: output file name +dmesg_dumps() +{ + dmesg | grep cpufreq >> $1.dmesg_cpufreq.txt + + # We may need the full logs as well + dmesg >> $1.dmesg_full.txt +} + +# Parse arguments +parse_arguments $@ + +# Make sure all requirements are met +prerequisite + +# Run requested functions +clear_dumps $OUTFILE +do_test >> $OUTFILE.txt +dmesg_dumps $OUTFILE diff --git a/tools/testing/selftests/cpufreq/module.sh b/tools/testing/selftests/cpufreq/module.sh new file mode 100755 index 000000000000..8ff2244a33a1 --- /dev/null +++ b/tools/testing/selftests/cpufreq/module.sh @@ -0,0 +1,243 @@ +#!/bin/bash +# +# Modules specific tests cases + +# protect against multiple inclusion +if [ $FILE_MODULE ]; then + return 0 +else + FILE_MODULE=DONE +fi + +source cpu.sh +source cpufreq.sh +source governor.sh + +# Check basic insmod/rmmod +# $1: module +test_basic_insmod_rmmod() +{ + printf "** Test: Running ${FUNCNAME[0]} **\n\n" + + printf "Inserting $1 module\n" + # insert module + insmod $1 + if [ $? != 0 ]; then + printf "Insmod $1 failed\n" + exit; + fi + + printf "Removing $1 module\n" + # remove module + rmmod $1 + if [ $? != 0 ]; then + printf "rmmod $1 failed\n" + exit; + fi + + printf "\n" +} + +# Insert cpufreq driver module and perform basic tests +# $1: cpufreq-driver module to insert +# $2: If we want to play with CPUs (1) or not (0) +module_driver_test_single() +{ + printf "** Test: Running ${FUNCNAME[0]} for driver $1 and cpus_hotplug=$2 **\n\n" + + if [ $2 -eq 1 ]; then + # offline all non-boot CPUs + for_each_non_boot_cpu offline_cpu + printf "\n" + fi + + # insert module + printf "Inserting $1 module\n\n" + insmod $1 + if [ $? != 0 ]; then + printf "Insmod $1 failed\n" + return; + fi + + if [ $2 -eq 1 ]; then + # online all non-boot CPUs + for_each_non_boot_cpu online_cpu + printf "\n" + fi + + # run basic tests + cpufreq_basic_tests + + # remove module + printf "Removing $1 module\n\n" + rmmod $1 + if [ $? != 0 ]; then + printf "rmmod $1 failed\n" + return; + fi + + # There shouldn't be any cpufreq directories now. + for_each_cpu cpu_should_not_have_cpufreq_directory + printf "\n" +} + +# $1: cpufreq-driver module to insert +module_driver_test() +{ + printf "** Test: Running ${FUNCNAME[0]} **\n\n" + + # check if module is present or not + ls $1 > /dev/null + if [ $? != 0 ]; then + printf "$1: not present in `pwd` folder\n" + return; + fi + + # test basic module tests + test_basic_insmod_rmmod $1 + + # Do simple module test + module_driver_test_single $1 0 + + # Remove CPUs before inserting module and then bring them back + module_driver_test_single $1 1 + printf "\n" +} + +# find governor name based on governor module name +# $1: governor module name +find_gov_name() +{ + if [ $1 = "cpufreq_ondemand.ko" ]; then + printf "ondemand" + elif [ $1 = "cpufreq_conservative.ko" ]; then + printf "conservative" + elif [ $1 = "cpufreq_userspace.ko" ]; then + printf "userspace" + elif [ $1 = "cpufreq_performance.ko" ]; then + printf "performance" + elif [ $1 = "cpufreq_powersave.ko" ]; then + printf "powersave" + elif [ $1 = "cpufreq_schedutil.ko" ]; then + printf "schedutil" + fi +} + +# $1: governor string, $2: governor module, $3: policy +# example: module_governor_test_single "ondemand" "cpufreq_ondemand.ko" 2 +module_governor_test_single() +{ + printf "** Test: Running ${FUNCNAME[0]} for $3 **\n\n" + + backup_governor $3 + + # switch to new governor + printf "Switch from $CUR_GOV to $1\n" + switch_show_governor $3 $1 + + # try removing module, it should fail as governor is used + printf "Removing $2 module\n\n" + rmmod $2 + if [ $? = 0 ]; then + printf "WARN: rmmod $2 succeeded even if governor is used\n" + insmod $2 + else + printf "Pass: unable to remove $2 while it is being used\n\n" + fi + + # switch back to old governor + printf "Switchback to $CUR_GOV from $1\n" + restore_governor $3 + printf "\n" +} + +# Insert cpufreq governor module and perform basic tests +# $1: cpufreq-governor module to insert +module_governor_test() +{ + printf "** Test: Running ${FUNCNAME[0]} **\n\n" + + # check if module is present or not + ls $1 > /dev/null + if [ $? != 0 ]; then + printf "$1: not present in `pwd` folder\n" + return; + fi + + # test basic module tests + test_basic_insmod_rmmod $1 + + # insert module + printf "Inserting $1 module\n\n" + insmod $1 + if [ $? != 0 ]; then + printf "Insmod $1 failed\n" + return; + fi + + # switch to new governor for each cpu + for_each_policy module_governor_test_single $(find_gov_name $1) $1 + + # remove module + printf "Removing $1 module\n\n" + rmmod $1 + if [ $? != 0 ]; then + printf "rmmod $1 failed\n" + return; + fi + printf "\n" +} + +# test modules: driver and governor +# $1: driver module, $2: governor module +module_test() +{ + printf "** Test: Running ${FUNCNAME[0]} **\n\n" + + # check if modules are present or not + ls $1 $2 > /dev/null + if [ $? != 0 ]; then + printf "$1 or $2: is not present in `pwd` folder\n" + return; + fi + + # TEST1: Insert gov after driver + # insert driver module + printf "Inserting $1 module\n\n" + insmod $1 + if [ $? != 0 ]; then + printf "Insmod $1 failed\n" + return; + fi + + # run governor tests + module_governor_test $2 + + # remove driver module + printf "Removing $1 module\n\n" + rmmod $1 + if [ $? != 0 ]; then + printf "rmmod $1 failed\n" + return; + fi + + # TEST2: Insert driver after governor + # insert governor module + printf "Inserting $2 module\n\n" + insmod $2 + if [ $? != 0 ]; then + printf "Insmod $2 failed\n" + return; + fi + + # run governor tests + module_driver_test $1 + + # remove driver module + printf "Removing $2 module\n\n" + rmmod $2 + if [ $? != 0 ]; then + printf "rmmod $2 failed\n" + return; + fi +} diff --git a/tools/testing/selftests/cpufreq/special-tests.sh b/tools/testing/selftests/cpufreq/special-tests.sh new file mode 100755 index 000000000000..58b730f23ef7 --- /dev/null +++ b/tools/testing/selftests/cpufreq/special-tests.sh @@ -0,0 +1,115 @@ +#!/bin/bash +# +# Special test cases reported by people + +# Testcase 1: Reported here: http://marc.info/?l=linux-pm&m=140618592709858&w=2 + +# protect against multiple inclusion +if [ $FILE_SPECIAL ]; then + return 0 +else + FILE_SPECIAL=DONE +fi + +source cpu.sh +source cpufreq.sh +source governor.sh + +# Test 1 +# $1: policy +__simple_lockdep() +{ + # switch to ondemand + __switch_governor $1 "ondemand" + + # cat ondemand files + local ondir=$(find_gov_directory $1 "ondemand") + if [ -z $ondir ]; then + printf "${FUNCNAME[0]}Ondemand directory not created, quit" + return + fi + + cat $ondir/* + + # switch to conservative + __switch_governor $1 "conservative" +} + +simple_lockdep() +{ + printf "** Test: Running ${FUNCNAME[0]} **\n" + + for_each_policy __simple_lockdep +} + +# Test 2 +# $1: policy +__concurrent_lockdep() +{ + for i in `seq 0 100`; do + __simple_lockdep $1 + done +} + +concurrent_lockdep() +{ + printf "** Test: Running ${FUNCNAME[0]} **\n" + + for_each_policy_concurrent __concurrent_lockdep +} + +# Test 3 +quick_shuffle() +{ + # this is called concurrently from governor_race + for I in `seq 1000` + do + echo ondemand | sudo tee $CPUFREQROOT/policy*/scaling_governor & + echo userspace | sudo tee $CPUFREQROOT/policy*/scaling_governor & + done +} + +governor_race() +{ + printf "** Test: Running ${FUNCNAME[0]} **\n" + + # run 8 concurrent instances + for I in `seq 8` + do + quick_shuffle & + done +} + +# Test 4 +# $1: cpu +hotplug_with_updates_cpu() +{ + local filepath="$CPUROOT/$1/cpufreq" + + # switch to ondemand + __switch_governor_for_cpu $1 "ondemand" + + for i in `seq 1 5000` + do + reboot_cpu $1 + done & + + local freqs=$(cat $filepath/scaling_available_frequencies) + local oldfreq=$(cat $filepath/scaling_min_freq) + + for j in `seq 1 5000` + do + # Set all frequencies one-by-one + for freq in $freqs; do + echo $freq > $filepath/scaling_min_freq + done + done + + # restore old freq + echo $oldfreq > $filepath/scaling_min_freq +} + +hotplug_with_updates() +{ + for_each_non_boot_cpu hotplug_with_updates_cpu +} diff --git a/tools/testing/selftests/drivers/gpu/drm_mm.sh b/tools/testing/selftests/drivers/gpu/drm_mm.sh new file mode 100755 index 000000000000..96dd55c92799 --- /dev/null +++ b/tools/testing/selftests/drivers/gpu/drm_mm.sh @@ -0,0 +1,15 @@ +#!/bin/sh +# Runs API tests for struct drm_mm (DRM range manager) + +if ! /sbin/modprobe -n -q test-drm_mm; then + echo "drivers/gpu/drm_mm: [skip]" + exit 77 +fi + +if /sbin/modprobe -q test-drm_mm; then + /sbin/modprobe -q -r test-drm_mm + echo "drivers/gpu/drm_mm: ok" +else + echo "drivers/gpu/drm_mm: [FAIL]" + exit 1 +fi diff --git a/tools/testing/selftests/drivers/gpu/i915.sh b/tools/testing/selftests/drivers/gpu/i915.sh index d407f0fa1e3a..c06d6e8a8dcc 100755 --- a/tools/testing/selftests/drivers/gpu/i915.sh +++ b/tools/testing/selftests/drivers/gpu/i915.sh @@ -7,6 +7,7 @@ if ! /sbin/modprobe -q -r i915; then fi if /sbin/modprobe -q i915 mock_selftests=-1; then + /sbin/modprobe -q -r i915 echo "drivers/gpu/i915: ok" else echo "drivers/gpu/i915: [FAIL]" diff --git a/tools/testing/selftests/efivarfs/Makefile b/tools/testing/selftests/efivarfs/Makefile index 736c3ddfc787..c49dcea69319 100644 --- a/tools/testing/selftests/efivarfs/Makefile +++ b/tools/testing/selftests/efivarfs/Makefile @@ -1,13 +1,7 @@ CFLAGS = -Wall -test_objs = open-unlink create-read - -all: $(test_objs) - +TEST_GEN_FILES := open-unlink create-read TEST_PROGS := efivarfs.sh -TEST_FILES := $(test_objs) include ../lib.mk -clean: - rm -f $(test_objs) diff --git a/tools/testing/selftests/exec/Makefile b/tools/testing/selftests/exec/Makefile index d4300602bf37..2e13035dff7f 100644 --- a/tools/testing/selftests/exec/Makefile +++ b/tools/testing/selftests/exec/Makefile @@ -1,27 +1,23 @@ CFLAGS = -Wall -BINARIES = execveat -DEPS = execveat.symlink execveat.denatured script subdir -all: $(BINARIES) $(DEPS) -subdir: +TEST_GEN_PROGS := execveat +TEST_GEN_FILES := execveat.symlink execveat.denatured script subdir +# Makefile is a run-time dependency, since it's accessed by the execveat test +TEST_FILES := Makefile + +EXTRA_CLEAN := $(OUTPUT)/subdir.moved $(OUTPUT)/execveat.moved $(OUTPUT)/xxxxx* + +include ../lib.mk + +$(OUTPUT)/subdir: mkdir -p $@ -script: +$(OUTPUT)/script: echo '#!/bin/sh' > $@ echo 'exit $$*' >> $@ chmod +x $@ -execveat.symlink: execveat - ln -s -f $< $@ -execveat.denatured: execveat +$(OUTPUT)/execveat.symlink: $(OUTPUT)/execveat + cd $(OUTPUT) && ln -s -f $(shell basename $<) $(shell basename $@) +$(OUTPUT)/execveat.denatured: $(OUTPUT)/execveat cp $< $@ chmod -x $@ -%: %.c - $(CC) $(CFLAGS) -o $@ $^ - -TEST_PROGS := execveat -# Makefile is a run-time dependency, since it's accessed by the execveat test -TEST_FILES := $(DEPS) Makefile - -include ../lib.mk -clean: - rm -rf $(BINARIES) $(DEPS) subdir.moved execveat.moved xxxxx* diff --git a/tools/testing/selftests/firmware/Makefile b/tools/testing/selftests/firmware/Makefile index 9bf82234855b..1894d625af2d 100644 --- a/tools/testing/selftests/firmware/Makefile +++ b/tools/testing/selftests/firmware/Makefile @@ -3,7 +3,7 @@ # No binaries, but make sure arg-less "make" doesn't trigger "run_tests" all: -TEST_PROGS := fw_filesystem.sh fw_userhelper.sh +TEST_PROGS := fw_filesystem.sh fw_fallback.sh include ../lib.mk diff --git a/tools/testing/selftests/firmware/fw_fallback.sh b/tools/testing/selftests/firmware/fw_fallback.sh new file mode 100755 index 000000000000..2e4c22d5abf7 --- /dev/null +++ b/tools/testing/selftests/firmware/fw_fallback.sh @@ -0,0 +1,224 @@ +#!/bin/sh +# This validates that the kernel will fall back to using the fallback mechanism +# to load firmware it can't find on disk itself. We must request a firmware +# that the kernel won't find, and any installed helper (e.g. udev) also +# won't find so that we can do the load ourself manually. +set -e + +modprobe test_firmware + +DIR=/sys/devices/virtual/misc/test_firmware + +# CONFIG_FW_LOADER_USER_HELPER has a sysfs class under /sys/class/firmware/ +# These days no one enables CONFIG_FW_LOADER_USER_HELPER so check for that +# as an indicator for CONFIG_FW_LOADER_USER_HELPER. +HAS_FW_LOADER_USER_HELPER=$(if [ -d /sys/class/firmware/ ]; then echo yes; else echo no; fi) + +if [ "$HAS_FW_LOADER_USER_HELPER" = "yes" ]; then + OLD_TIMEOUT=$(cat /sys/class/firmware/timeout) +else + echo "usermode helper disabled so ignoring test" + exit 0 +fi + +FWPATH=$(mktemp -d) +FW="$FWPATH/test-firmware.bin" + +test_finish() +{ + echo "$OLD_TIMEOUT" >/sys/class/firmware/timeout + rm -f "$FW" + rmdir "$FWPATH" +} + +load_fw() +{ + local name="$1" + local file="$2" + + # This will block until our load (below) has finished. + echo -n "$name" >"$DIR"/trigger_request & + + # Give kernel a chance to react. + local timeout=10 + while [ ! -e "$DIR"/"$name"/loading ]; do + sleep 0.1 + timeout=$(( $timeout - 1 )) + if [ "$timeout" -eq 0 ]; then + echo "$0: firmware interface never appeared" >&2 + exit 1 + fi + done + + echo 1 >"$DIR"/"$name"/loading + cat "$file" >"$DIR"/"$name"/data + echo 0 >"$DIR"/"$name"/loading + + # Wait for request to finish. + wait +} + +load_fw_cancel() +{ + local name="$1" + local file="$2" + + # This will block until our load (below) has finished. + echo -n "$name" >"$DIR"/trigger_request 2>/dev/null & + + # Give kernel a chance to react. + local timeout=10 + while [ ! -e "$DIR"/"$name"/loading ]; do + sleep 0.1 + timeout=$(( $timeout - 1 )) + if [ "$timeout" -eq 0 ]; then + echo "$0: firmware interface never appeared" >&2 + exit 1 + fi + done + + echo -1 >"$DIR"/"$name"/loading + + # Wait for request to finish. + wait +} + +load_fw_custom() +{ + local name="$1" + local file="$2" + + echo -n "$name" >"$DIR"/trigger_custom_fallback 2>/dev/null & + + # Give kernel a chance to react. + local timeout=10 + while [ ! -e "$DIR"/"$name"/loading ]; do + sleep 0.1 + timeout=$(( $timeout - 1 )) + if [ "$timeout" -eq 0 ]; then + echo "$0: firmware interface never appeared" >&2 + exit 1 + fi + done + + echo 1 >"$DIR"/"$name"/loading + cat "$file" >"$DIR"/"$name"/data + echo 0 >"$DIR"/"$name"/loading + + # Wait for request to finish. + wait +} + + +load_fw_custom_cancel() +{ + local name="$1" + local file="$2" + + echo -n "$name" >"$DIR"/trigger_custom_fallback 2>/dev/null & + + # Give kernel a chance to react. + local timeout=10 + while [ ! -e "$DIR"/"$name"/loading ]; do + sleep 0.1 + timeout=$(( $timeout - 1 )) + if [ "$timeout" -eq 0 ]; then + echo "$0: firmware interface never appeared" >&2 + exit 1 + fi + done + + echo -1 >"$DIR"/"$name"/loading + + # Wait for request to finish. + wait +} + + +trap "test_finish" EXIT + +# This is an unlikely real-world firmware content. :) +echo "ABCD0123" >"$FW" +NAME=$(basename "$FW") + +DEVPATH="$DIR"/"nope-$NAME"/loading + +# Test failure when doing nothing (timeout works). +echo -n 2 >/sys/class/firmware/timeout +echo -n "nope-$NAME" >"$DIR"/trigger_request 2>/dev/null & + +# Give the kernel some time to load the loading file, must be less +# than the timeout above. +sleep 1 +if [ ! -f $DEVPATH ]; then + echo "$0: fallback mechanism immediately cancelled" + echo "" + echo "The file never appeared: $DEVPATH" + echo "" + echo "This might be a distribution udev rule setup by your distribution" + echo "to immediately cancel all fallback requests, this must be" + echo "removed before running these tests. To confirm look for" + echo "a firmware rule like /lib/udev/rules.d/50-firmware.rules" + echo "and see if you have something like this:" + echo "" + echo "SUBSYSTEM==\"firmware\", ACTION==\"add\", ATTR{loading}=\"-1\"" + echo "" + echo "If you do remove this file or comment out this line before" + echo "proceeding with these tests." + exit 1 +fi + +if diff -q "$FW" /dev/test_firmware >/dev/null ; then + echo "$0: firmware was not expected to match" >&2 + exit 1 +else + echo "$0: timeout works" +fi + +# Put timeout high enough for us to do work but not so long that failures +# slow down this test too much. +echo 4 >/sys/class/firmware/timeout + +# Load this script instead of the desired firmware. +load_fw "$NAME" "$0" +if diff -q "$FW" /dev/test_firmware >/dev/null ; then + echo "$0: firmware was not expected to match" >&2 + exit 1 +else + echo "$0: firmware comparison works" +fi + +# Do a proper load, which should work correctly. +load_fw "$NAME" "$FW" +if ! diff -q "$FW" /dev/test_firmware >/dev/null ; then + echo "$0: firmware was not loaded" >&2 + exit 1 +else + echo "$0: fallback mechanism works" +fi + +load_fw_cancel "nope-$NAME" "$FW" +if diff -q "$FW" /dev/test_firmware >/dev/null ; then + echo "$0: firmware was expected to be cancelled" >&2 + exit 1 +else + echo "$0: cancelling fallback mechanism works" +fi + +load_fw_custom "$NAME" "$FW" +if ! diff -q "$FW" /dev/test_firmware >/dev/null ; then + echo "$0: firmware was not loaded" >&2 + exit 1 +else + echo "$0: custom fallback loading mechanism works" +fi + +load_fw_custom_cancel "nope-$NAME" "$FW" +if diff -q "$FW" /dev/test_firmware >/dev/null ; then + echo "$0: firmware was expected to be cancelled" >&2 + exit 1 +else + echo "$0: cancelling custom fallback mechanism works" +fi + +exit 0 diff --git a/tools/testing/selftests/firmware/fw_filesystem.sh b/tools/testing/selftests/firmware/fw_filesystem.sh index 5c495ad7958a..e35691239350 100755 --- a/tools/testing/selftests/firmware/fw_filesystem.sh +++ b/tools/testing/selftests/firmware/fw_filesystem.sh @@ -5,9 +5,24 @@ # know so we can be sure we're not accidentally testing the user helper. set -e -modprobe test_firmware - DIR=/sys/devices/virtual/misc/test_firmware +TEST_DIR=$(dirname $0) + +test_modprobe() +{ + if [ ! -d $DIR ]; then + echo "$0: $DIR not present" + echo "You must have the following enabled in your kernel:" + cat $TEST_DIR/config + exit 1 + fi +} + +trap "test_modprobe" EXIT + +if [ ! -d $DIR ]; then + modprobe test_firmware +fi # CONFIG_FW_LOADER_USER_HELPER has a sysfs class under /sys/class/firmware/ # These days no one enables CONFIG_FW_LOADER_USER_HELPER so check for that @@ -48,18 +63,18 @@ echo "ABCD0123" >"$FW" NAME=$(basename "$FW") -if printf '\000' >"$DIR"/trigger_request; then +if printf '\000' >"$DIR"/trigger_request 2> /dev/null; then echo "$0: empty filename should not succeed" >&2 exit 1 fi -if printf '\000' >"$DIR"/trigger_async_request; then +if printf '\000' >"$DIR"/trigger_async_request 2> /dev/null; then echo "$0: empty filename should not succeed (async)" >&2 exit 1 fi # Request a firmware that doesn't exist, it should fail. -if echo -n "nope-$NAME" >"$DIR"/trigger_request; then +if echo -n "nope-$NAME" >"$DIR"/trigger_request 2> /dev/null; then echo "$0: firmware shouldn't have loaded" >&2 exit 1 fi diff --git a/tools/testing/selftests/firmware/fw_userhelper.sh b/tools/testing/selftests/firmware/fw_userhelper.sh deleted file mode 100755 index b9983f8e09f6..000000000000 --- a/tools/testing/selftests/firmware/fw_userhelper.sh +++ /dev/null @@ -1,99 +0,0 @@ -#!/bin/sh -# This validates that the kernel will fall back to using the user helper -# to load firmware it can't find on disk itself. We must request a firmware -# that the kernel won't find, and any installed helper (e.g. udev) also -# won't find so that we can do the load ourself manually. -set -e - -modprobe test_firmware - -DIR=/sys/devices/virtual/misc/test_firmware - -# CONFIG_FW_LOADER_USER_HELPER has a sysfs class under /sys/class/firmware/ -# These days no one enables CONFIG_FW_LOADER_USER_HELPER so check for that -# as an indicator for CONFIG_FW_LOADER_USER_HELPER. -HAS_FW_LOADER_USER_HELPER=$(if [ -d /sys/class/firmware/ ]; then echo yes; else echo no; fi) - -if [ "$HAS_FW_LOADER_USER_HELPER" = "yes" ]; then - OLD_TIMEOUT=$(cat /sys/class/firmware/timeout) -else - echo "usermode helper disabled so ignoring test" - exit 0 -fi - -FWPATH=$(mktemp -d) -FW="$FWPATH/test-firmware.bin" - -test_finish() -{ - echo "$OLD_TIMEOUT" >/sys/class/firmware/timeout - rm -f "$FW" - rmdir "$FWPATH" -} - -load_fw() -{ - local name="$1" - local file="$2" - - # This will block until our load (below) has finished. - echo -n "$name" >"$DIR"/trigger_request & - - # Give kernel a chance to react. - local timeout=10 - while [ ! -e "$DIR"/"$name"/loading ]; do - sleep 0.1 - timeout=$(( $timeout - 1 )) - if [ "$timeout" -eq 0 ]; then - echo "$0: firmware interface never appeared" >&2 - exit 1 - fi - done - - echo 1 >"$DIR"/"$name"/loading - cat "$file" >"$DIR"/"$name"/data - echo 0 >"$DIR"/"$name"/loading - - # Wait for request to finish. - wait -} - -trap "test_finish" EXIT - -# This is an unlikely real-world firmware content. :) -echo "ABCD0123" >"$FW" -NAME=$(basename "$FW") - -# Test failure when doing nothing (timeout works). -echo 1 >/sys/class/firmware/timeout -echo -n "$NAME" >"$DIR"/trigger_request -if diff -q "$FW" /dev/test_firmware >/dev/null ; then - echo "$0: firmware was not expected to match" >&2 - exit 1 -else - echo "$0: timeout works" -fi - -# Put timeout high enough for us to do work but not so long that failures -# slow down this test too much. -echo 4 >/sys/class/firmware/timeout - -# Load this script instead of the desired firmware. -load_fw "$NAME" "$0" -if diff -q "$FW" /dev/test_firmware >/dev/null ; then - echo "$0: firmware was not expected to match" >&2 - exit 1 -else - echo "$0: firmware comparison works" -fi - -# Do a proper load, which should work correctly. -load_fw "$NAME" "$FW" -if ! diff -q "$FW" /dev/test_firmware >/dev/null ; then - echo "$0: firmware was not loaded" >&2 - exit 1 -else - echo "$0: user helper firmware loading works" -fi - -exit 0 diff --git a/tools/testing/selftests/ftrace/Makefile b/tools/testing/selftests/ftrace/Makefile index 4e6ed13e7f66..a8a5e21850e7 100644 --- a/tools/testing/selftests/ftrace/Makefile +++ b/tools/testing/selftests/ftrace/Makefile @@ -1,9 +1,7 @@ all: TEST_PROGS := ftracetest -TEST_DIRS := test.d +TEST_FILES := test.d +EXTRA_CLEAN := $(OUTPUT)/logs/* include ../lib.mk - -clean: - rm -rf logs/* diff --git a/tools/testing/selftests/ftrace/config b/tools/testing/selftests/ftrace/config index ef8214661612..8a1c9f949fe0 100644 --- a/tools/testing/selftests/ftrace/config +++ b/tools/testing/selftests/ftrace/config @@ -1 +1,2 @@ +CONFIG_KPROBES=y CONFIG_FTRACE=y diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest index 52e3c4df28d6..32e6211e1c6e 100755 --- a/tools/testing/selftests/ftrace/ftracetest +++ b/tools/testing/selftests/ftrace/ftracetest @@ -16,6 +16,7 @@ echo " -k|--keep Keep passed test logs" echo " -v|--verbose Increase verbosity of test messages" echo " -vv Alias of -v -v (Show all results in stdout)" echo " -d|--debug Debug mode (trace all shell commands)" +echo " -l|--logdir <dir> Save logs on the <dir>" exit $1 } @@ -64,6 +65,10 @@ parse_opts() { # opts DEBUG=1 shift 1 ;; + --logdir|-l) + LOG_DIR=$2 + shift 2 + ;; *.tc) if [ -f "$1" ]; then OPT_TEST_CASES="$OPT_TEST_CASES `abspath $1`" @@ -145,11 +150,16 @@ XFAILED_CASES= UNDEFINED_CASES= TOTAL_RESULT=0 +INSTANCE= CASENO=0 testcase() { # testfile CASENO=$((CASENO+1)) desc=`grep "^#[ \t]*description:" $1 | cut -f2 -d:` - prlog -n "[$CASENO]$desc" + prlog -n "[$CASENO]$INSTANCE$desc" +} + +test_on_instance() { # testfile + grep -q "^#[ \t]*flags:.*instance" $1 } eval_result() { # sigval @@ -266,6 +276,17 @@ for t in $TEST_CASES; do run_test $t done +# Test on instance loop +INSTANCE=" (instance) " +for t in $TEST_CASES; do + test_on_instance $t || continue + SAVED_TRACING_DIR=$TRACING_DIR + export TRACING_DIR=`mktemp -d $TRACING_DIR/instances/ftracetest.XXXXXX` + run_test $t + rmdir $TRACING_DIR + TRACING_DIR=$SAVED_TRACING_DIR +done + prlog "" prlog "# of passed: " `echo $PASSED_CASES | wc -w` prlog "# of failed: " `echo $FAILED_CASES | wc -w` diff --git a/tools/testing/selftests/ftrace/test.d/00basic/basic2.tc b/tools/testing/selftests/ftrace/test.d/00basic/basic2.tc index bf9a7b037924..ebfce83f35b4 100644 --- a/tools/testing/selftests/ftrace/test.d/00basic/basic2.tc +++ b/tools/testing/selftests/ftrace/test.d/00basic/basic2.tc @@ -1,5 +1,6 @@ #!/bin/sh # description: Basic test for tracers +# flags: instance test -f available_tracers for t in `cat available_tracers`; do echo $t > current_tracer diff --git a/tools/testing/selftests/ftrace/test.d/00basic/basic3.tc b/tools/testing/selftests/ftrace/test.d/00basic/basic3.tc index bde6625d9785..9e33f841812f 100644 --- a/tools/testing/selftests/ftrace/test.d/00basic/basic3.tc +++ b/tools/testing/selftests/ftrace/test.d/00basic/basic3.tc @@ -1,5 +1,6 @@ #!/bin/sh # description: Basic trace clock test +# flags: instance test -f trace_clock for c in `cat trace_clock | tr -d \[\]`; do echo $c > trace_clock diff --git a/tools/testing/selftests/ftrace/test.d/event/event-enable.tc b/tools/testing/selftests/ftrace/test.d/event/event-enable.tc index 87eb9d6dd4ca..283b45ecb199 100644 --- a/tools/testing/selftests/ftrace/test.d/event/event-enable.tc +++ b/tools/testing/selftests/ftrace/test.d/event/event-enable.tc @@ -1,5 +1,6 @@ #!/bin/sh # description: event tracing - enable/disable with event level files +# flags: instance do_reset() { echo > set_event diff --git a/tools/testing/selftests/ftrace/test.d/event/event-pid.tc b/tools/testing/selftests/ftrace/test.d/event/event-pid.tc index d4ab27b522f8..96c1a95be4f7 100644 --- a/tools/testing/selftests/ftrace/test.d/event/event-pid.tc +++ b/tools/testing/selftests/ftrace/test.d/event/event-pid.tc @@ -1,5 +1,6 @@ #!/bin/sh # description: event tracing - restricts events based on pid +# flags: instance do_reset() { echo > set_event diff --git a/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc b/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc index ced27ef0638f..b8fe2e5b9e67 100644 --- a/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc +++ b/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc @@ -1,5 +1,6 @@ #!/bin/sh # description: event tracing - enable/disable with subsystem level files +# flags: instance do_reset() { echo > set_event diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc new file mode 100644 index 000000000000..bab5ff7c607e --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-pid.tc @@ -0,0 +1,117 @@ +#!/bin/sh +# description: ftrace - function pid filters + +# Make sure that function pid matching filter works. +# Also test it on an instance directory + +if ! grep -q function available_tracers; then + echo "no function tracer configured" + exit_unsupported +fi + +if [ ! -f set_ftrace_pid ]; then + echo "set_ftrace_pid not found? Is function tracer not set?" + exit_unsupported +fi + +if [ ! -f set_ftrace_filter ]; then + echo "set_ftrace_filter not found? Is function tracer not set?" + exit_unsupported +fi + +do_function_fork=1 + +if [ ! -f options/function-fork ]; then + do_function_fork=0 + echo "no option for function-fork found. Option will not be tested." +fi + +read PID _ < /proc/self/stat + +if [ $do_function_fork -eq 1 ]; then + # default value of function-fork option + orig_value=`grep function-fork trace_options` +fi + +do_reset() { + reset_tracer + clear_trace + enable_tracing + echo > set_ftrace_filter + echo > set_ftrace_pid + + if [ $do_function_fork -eq 0 ]; then + return + fi + + echo $orig_value > trace_options +} + +fail() { # msg + do_reset + echo $1 + exit $FAIL +} + +yield() { + ping localhost -c 1 || sleep .001 || usleep 1 || sleep 1 +} + +do_test() { + disable_tracing + + echo do_execve* > set_ftrace_filter + echo *do_fork >> set_ftrace_filter + + echo $PID > set_ftrace_pid + echo function > current_tracer + + if [ $do_function_fork -eq 1 ]; then + # don't allow children to be traced + echo nofunction-fork > trace_options + fi + + enable_tracing + yield + + count_pid=`cat trace | grep -v ^# | grep $PID | wc -l` + count_other=`cat trace | grep -v ^# | grep -v $PID | wc -l` + + # count_other should be 0 + if [ $count_pid -eq 0 -o $count_other -ne 0 ]; then + fail "PID filtering not working?" + fi + + disable_tracing + clear_trace + + if [ $do_function_fork -eq 0 ]; then + return + fi + + # allow children to be traced + echo function-fork > trace_options + + enable_tracing + yield + + count_pid=`cat trace | grep -v ^# | grep $PID | wc -l` + count_other=`cat trace | grep -v ^# | grep -v $PID | wc -l` + + # count_other should NOT be 0 + if [ $count_pid -eq 0 -o $count_other -eq 0 ]; then + fail "PID filtering not following fork?" + fi +} + +do_test + +mkdir instances/foo +cd instances/foo +do_test +cd ../../ +rmdir instances/foo + +do_reset + +exit 0 diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc new file mode 100644 index 000000000000..07bb3e5930b4 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_event_triggers.tc @@ -0,0 +1,114 @@ +#!/bin/sh +# description: ftrace - test for function event triggers +# flags: instance +# +# Ftrace allows to add triggers to functions, such as enabling or disabling +# tracing, enabling or disabling trace events, or recording a stack trace +# within the ring buffer. +# +# This test is designed to test event triggers +# + +# The triggers are set within the set_ftrace_filter file +if [ ! -f set_ftrace_filter ]; then + echo "set_ftrace_filter not found? Is dynamic ftrace not set?" + exit_unsupported +fi + +do_reset() { + reset_ftrace_filter + reset_tracer + disable_events + clear_trace + enable_tracing +} + +fail() { # mesg + do_reset + echo $1 + exit $FAIL +} + +SLEEP_TIME=".1" + +do_reset + +echo "Testing function probes with events:" + +EVENT="sched:sched_switch" +EVENT_ENABLE="events/sched/sched_switch/enable" + +cnt_trace() { + grep -v '^#' trace | wc -l +} + +test_event_enabled() { + val=$1 + + e=`cat $EVENT_ENABLE` + if [ "$e" != $val ]; then + echo "Expected $val but found $e" + exit -1 + fi +} + +run_enable_disable() { + enable=$1 # enable + Enable=$2 # Enable + check_disable=$3 # 0 + check_enable_star=$4 # 1* + check_disable_star=$5 # 0* + + cnt=`cnt_trace` + if [ $cnt -ne 0 ]; then + fail "Found junk in trace file" + fi + + echo "$Enable event all the time" + + echo $check_disable > $EVENT_ENABLE + sleep $SLEEP_TIME + + test_event_enabled $check_disable + + echo "schedule:${enable}_event:$EVENT" > set_ftrace_filter + + echo " make sure it works 5 times" + + for i in `seq 5`; do + sleep $SLEEP_TIME + echo " test $i" + test_event_enabled $check_enable_star + + echo $check_disable > $EVENT_ENABLE + done + sleep $SLEEP_TIME + echo " make sure it's still works" + test_event_enabled $check_enable_star + + reset_ftrace_filter + + echo " make sure it only works 3 times" + + echo $check_disable > $EVENT_ENABLE + sleep $SLEEP_TIME + + echo "schedule:${enable}_event:$EVENT:3" > set_ftrace_filter + + for i in `seq 3`; do + sleep $SLEEP_TIME + echo " test $i" + test_event_enabled $check_enable_star + + echo $check_disable > $EVENT_ENABLE + done + + sleep $SLEEP_TIME + echo " make sure it stop working" + test_event_enabled $check_disable_star + + do_reset +} + +run_enable_disable enable Enable 0 "1*" "0*" +run_enable_disable disable Disable 1 "0*" "1*" diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc new file mode 100644 index 000000000000..113b4d9bc733 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc @@ -0,0 +1,132 @@ +#!/bin/sh +# description: ftrace - test reading of set_ftrace_filter +# +# The set_ftrace_filter file of ftrace is used to list functions as well as +# triggers (probes) attached to functions. The code to read this file is not +# straight forward and has had various bugs in the past. This test is designed +# to add functions and triggers to that file in various ways and read that +# file in various ways (cat vs dd). +# + +# The triggers are set within the set_ftrace_filter file +if [ ! -f set_ftrace_filter ]; then + echo "set_ftrace_filter not found? Is dynamic ftrace not set?" + exit_unsupported +fi + +do_reset() { + reset_tracer + reset_ftrace_filter + disable_events + clear_trace + enable_tracing +} + +fail() { # mesg + do_reset + echo $1 + exit $FAIL +} + +do_reset + +FILTER=set_ftrace_filter +FUNC1="schedule" +FUNC2="do_IRQ" + +ALL_FUNCS="#### all functions enabled ####" + +test_func() { + if ! echo "$1" | grep -q "^$2\$"; then + return 0 + fi + echo "$1" | grep -v "^$2\$" + return 1 +} + +check_set_ftrace_filter() { + cat=`cat $FILTER` + dd1=`dd if=$FILTER bs=1 | grep -v -e 'records in' -e 'records out' -e 'bytes copied'` + dd100=`dd if=$FILTER bs=100 | grep -v -e 'records in' -e 'records out' -e 'bytes copied'` + + echo "Testing '$@'" + + while [ $# -gt 0 ]; do + echo "test $1" + if cat=`test_func "$cat" "$1"`; then + return 0 + fi + if dd1=`test_func "$dd1" "$1"`; then + return 0 + fi + if dd100=`test_func "$dd100" "$1"`; then + return 0 + fi + shift + done + + if [ -n "$cat" ]; then + return 0 + fi + if [ -n "$dd1" ]; then + return 0 + fi + if [ -n "$dd100" ]; then + return 0 + fi + return 1; +} + +if check_set_ftrace_filter "$ALL_FUNCS"; then + fail "Expected only $ALL_FUNCS" +fi + +echo "$FUNC1:traceoff" > set_ftrace_filter +if check_set_ftrace_filter "$ALL_FUNCS" "$FUNC1:traceoff:unlimited"; then + fail "Expected $ALL_FUNCS and $FUNC1:traceoff:unlimited" +fi + +echo "$FUNC1" > set_ftrace_filter +if check_set_ftrace_filter "$FUNC1" "$FUNC1:traceoff:unlimited"; then + fail "Expected $FUNC1 and $FUNC1:traceoff:unlimited" +fi + +echo "$FUNC2" >> set_ftrace_filter +if check_set_ftrace_filter "$FUNC1" "$FUNC2" "$FUNC1:traceoff:unlimited"; then + fail "Expected $FUNC1 $FUNC2 and $FUNC1:traceoff:unlimited" +fi + +echo "$FUNC2:traceoff" >> set_ftrace_filter +if check_set_ftrace_filter "$FUNC1" "$FUNC2" "$FUNC1:traceoff:unlimited" "$FUNC2:traceoff:unlimited"; then + fail "Expected $FUNC1 $FUNC2 $FUNC1:traceoff:unlimited and $FUNC2:traceoff:unlimited" +fi + +echo "$FUNC1" > set_ftrace_filter +if check_set_ftrace_filter "$FUNC1" "$FUNC1:traceoff:unlimited" "$FUNC2:traceoff:unlimited"; then + fail "Expected $FUNC1 $FUNC1:traceoff:unlimited and $FUNC2:traceoff:unlimited" +fi + +echo > set_ftrace_filter +if check_set_ftrace_filter "$ALL_FUNCS" "$FUNC1:traceoff:unlimited" "$FUNC2:traceoff:unlimited"; then + fail "Expected $ALL_FUNCS $FUNC1:traceoff:unlimited and $FUNC2:traceoff:unlimited" +fi + +reset_ftrace_filter + +if check_set_ftrace_filter "$ALL_FUNCS"; then + fail "Expected $ALL_FUNCS" +fi + +echo "$FUNC1" > set_ftrace_filter +if check_set_ftrace_filter "$FUNC1" ; then + fail "Expected $FUNC1" +fi + +echo "$FUNC2" >> set_ftrace_filter +if check_set_ftrace_filter "$FUNC1" "$FUNC2" ; then + fail "Expected $FUNC1 and $FUNC2" +fi + +do_reset + +exit 0 diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc new file mode 100644 index 000000000000..c8e02ec01eaf --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_traceonoff_triggers.tc @@ -0,0 +1,172 @@ +#!/bin/sh +# description: ftrace - test for function traceon/off triggers +# flags: instance +# +# Ftrace allows to add triggers to functions, such as enabling or disabling +# tracing, enabling or disabling trace events, or recording a stack trace +# within the ring buffer. +# +# This test is designed to test enabling and disabling tracing triggers +# + +# The triggers are set within the set_ftrace_filter file +if [ ! -f set_ftrace_filter ]; then + echo "set_ftrace_filter not found? Is dynamic ftrace not set?" + exit_unsupported +fi + +do_reset() { + reset_ftrace_filter + reset_tracer + disable_events + clear_trace + enable_tracing +} + +fail() { # mesg + do_reset + echo $1 + exit $FAIL +} + +SLEEP_TIME=".1" + +do_reset + +echo "Testing function probes with enabling disabling tracing:" + +cnt_trace() { + grep -v '^#' trace | wc -l +} + +echo '** DISABLE TRACING' +disable_tracing +clear_trace + +cnt=`cnt_trace` +if [ $cnt -ne 0 ]; then + fail "Found junk in trace" +fi + + +echo '** ENABLE EVENTS' + +echo 1 > events/enable + +echo '** ENABLE TRACING' +enable_tracing + +cnt=`cnt_trace` +if [ $cnt -eq 0 ]; then + fail "Nothing found in trace" +fi + +# powerpc uses .schedule +func="schedule" +x=`grep '^\.schedule$' available_filter_functions | wc -l` +if [ "$x" -eq 1 ]; then + func=".schedule" +fi + +echo '** SET TRACEOFF' + +echo "$func:traceoff" > set_ftrace_filter + +cnt=`grep schedule set_ftrace_filter | wc -l` +if [ $cnt -ne 1 ]; then + fail "Did not find traceoff trigger" +fi + +cnt=`cnt_trace` +sleep $SLEEP_TIME +cnt2=`cnt_trace` + +if [ $cnt -ne $cnt2 ]; then + fail "Tracing is not stopped" +fi + +on=`cat tracing_on` +if [ $on != "0" ]; then + fail "Tracing is not off" +fi + +line1=`cat trace | tail -1` +sleep $SLEEP_TIME +line2=`cat trace | tail -1` + +if [ "$line1" != "$line2" ]; then + fail "Tracing file is still changing" +fi + +clear_trace + +cnt=`cnt_trace` +if [ $cnt -ne 0 ]; then + fail "Tracing is still happeing" +fi + +echo "!$func:traceoff" >> set_ftrace_filter + +cnt=`grep schedule set_ftrace_filter | wc -l` +if [ $cnt -ne 0 ]; then + fail "traceoff trigger still exists" +fi + +on=`cat tracing_on` +if [ $on != "0" ]; then + fail "Tracing is started again" +fi + +echo "$func:traceon" > set_ftrace_filter + +cnt=`grep schedule set_ftrace_filter | wc -l` +if [ $cnt -ne 1 ]; then + fail "traceon trigger not found" +fi + +cnt=`cnt_trace` +if [ $cnt -eq 0 ]; then + fail "Tracing did not start" +fi + +on=`cat tracing_on` +if [ $on != "1" ]; then + fail "Tracing was not enabled" +fi + + +echo "!$func:traceon" >> set_ftrace_filter + +cnt=`grep schedule set_ftrace_filter | wc -l` +if [ $cnt -ne 0 ]; then + fail "traceon trigger still exists" +fi + +check_sleep() { + val=$1 + sleep $SLEEP_TIME + cat set_ftrace_filter + on=`cat tracing_on` + if [ $on != "$val" ]; then + fail "Expected tracing_on to be $val, but it was $on" + fi +} + + +echo "$func:traceoff:3" > set_ftrace_filter +check_sleep "0" +echo 1 > tracing_on +check_sleep "0" +echo 1 > tracing_on +check_sleep "0" +echo 1 > tracing_on +check_sleep "1" +echo "!$func:traceoff:0" > set_ftrace_filter + +if grep -e traceon -e traceoff set_ftrace_filter; then + fail "Tracing on and off triggers still exist" +fi + +disable_events + +exit 0 diff --git a/tools/testing/selftests/ftrace/test.d/functions b/tools/testing/selftests/ftrace/test.d/functions index 91de1a8e4f19..9aec6fcb7729 100644 --- a/tools/testing/selftests/ftrace/test.d/functions +++ b/tools/testing/selftests/ftrace/test.d/functions @@ -30,6 +30,27 @@ reset_events_filter() { # reset all current setting filters done } +reset_ftrace_filter() { # reset all triggers in set_ftrace_filter + echo > set_ftrace_filter + grep -v '^#' set_ftrace_filter | while read t; do + tr=`echo $t | cut -d: -f2` + if [ "$tr" == "" ]; then + continue + fi + if [ $tr == "enable_event" -o $tr == "disable_event" ]; then + tr=`echo $t | cut -d: -f1-4` + limit=`echo $t | cut -d: -f5` + else + tr=`echo $t | cut -d: -f1-2` + limit=`echo $t | cut -d: -f3` + fi + if [ "$limit" != "unlimited" ]; then + tr="$tr:$limit" + fi + echo "!$tr" > set_ftrace_filter + done +} + disable_events() { echo 0 > events/enable } diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc index 0a78705b43b2..c75faefb4fff 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc @@ -26,7 +26,7 @@ check_types() { test $X2 = $X3 test 0x$X3 = $3 - B4=`printf "%x" $4` + B4=`printf "%02x" $4` B3=`echo -n $X3 | tail -c 3 | head -c 2` test $B3 = $B4 } diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_maxactive.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_maxactive.tc new file mode 100644 index 000000000000..57abdf1caabf --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_maxactive.tc @@ -0,0 +1,39 @@ +#!/bin/sh +# description: Kretprobe dynamic event with maxactive + +[ -f kprobe_events ] || exit_unsupported # this is configurable + +echo > kprobe_events + +# Test if we successfully reject unknown messages +if echo 'a:myprobeaccept inet_csk_accept' > kprobe_events; then false; else true; fi + +# Test if we successfully reject too big maxactive +if echo 'r1000000:myprobeaccept inet_csk_accept' > kprobe_events; then false; else true; fi + +# Test if we successfully reject unparsable numbers for maxactive +if echo 'r10fuzz:myprobeaccept inet_csk_accept' > kprobe_events; then false; else true; fi + +# Test for kretprobe with event name without maxactive +echo 'r:myprobeaccept inet_csk_accept' > kprobe_events +grep myprobeaccept kprobe_events +test -d events/kprobes/myprobeaccept +echo '-:myprobeaccept' >> kprobe_events + +# Test for kretprobe with event name with a small maxactive +echo 'r10:myprobeaccept inet_csk_accept' > kprobe_events +grep myprobeaccept kprobe_events +test -d events/kprobes/myprobeaccept +echo '-:myprobeaccept' >> kprobe_events + +# Test for kretprobe without event name without maxactive +echo 'r inet_csk_accept' > kprobe_events +grep inet_csk_accept kprobe_events +echo > kprobe_events + +# Test for kretprobe without event name with a small maxactive +echo 'r10 inet_csk_accept' > kprobe_events +grep inet_csk_accept kprobe_events +echo > kprobe_events + +clear_trace diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-eventonoff.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-eventonoff.tc index 1a9445021bf1..c5435adfdd93 100644 --- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-eventonoff.tc +++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-eventonoff.tc @@ -1,5 +1,6 @@ #!/bin/sh # description: event trigger - test event enable/disable trigger +# flags: instance do_reset() { reset_trigger diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-filter.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-filter.tc index 514e466e198b..48849a8d577f 100644 --- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-filter.tc +++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-filter.tc @@ -1,5 +1,6 @@ #!/bin/sh # description: event trigger - test trigger filter +# flags: instance do_reset() { reset_trigger diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc index 400e98b64948..b7f86d10b549 100644 --- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc +++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc @@ -1,5 +1,6 @@ #!/bin/sh # description: event trigger - test histogram modifiers +# flags: instance do_reset() { reset_trigger diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist.tc index a00184cd9c95..fb66f7d9339d 100644 --- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist.tc +++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist.tc @@ -1,5 +1,6 @@ #!/bin/sh # description: event trigger - test histogram trigger +# flags: instance do_reset() { reset_trigger diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-multihist.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-multihist.tc index 3478b00ead57..f9153087dd7c 100644 --- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-multihist.tc +++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-multihist.tc @@ -1,5 +1,6 @@ #!/bin/sh # description: event trigger - test multiple histogram triggers +# flags: instance do_reset() { reset_trigger diff --git a/tools/testing/selftests/futex/Makefile b/tools/testing/selftests/futex/Makefile index 6a1752956283..e2fbb890aef9 100644 --- a/tools/testing/selftests/futex/Makefile +++ b/tools/testing/selftests/futex/Makefile @@ -3,13 +3,18 @@ SUBDIRS := functional TEST_PROGS := run.sh .PHONY: all clean -all: - for DIR in $(SUBDIRS); do $(MAKE) -C $$DIR $@ ; done include ../lib.mk +all: + for DIR in $(SUBDIRS); do \ + BUILD_TARGET=$(OUTPUT)/$$DIR; \ + mkdir $$BUILD_TARGET -p; \ + make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\ + done + override define RUN_TESTS - ./run.sh + @if [ `dirname $(OUTPUT)` = $(PWD) ]; then ./run.sh; fi endef override define INSTALL_RULE @@ -17,7 +22,9 @@ override define INSTALL_RULE install -t $(INSTALL_PATH) $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) @for SUBDIR in $(SUBDIRS); do \ - $(MAKE) -C $$SUBDIR INSTALL_PATH=$(INSTALL_PATH)/$$SUBDIR install; \ + BUILD_TARGET=$(OUTPUT)/$$SUBDIR; \ + mkdir $$BUILD_TARGET -p; \ + $(MAKE) OUTPUT=$$BUILD_TARGET -C $$SUBDIR INSTALL_PATH=$(INSTALL_PATH)/$$SUBDIR install; \ done; endef @@ -25,5 +32,10 @@ override define EMIT_TESTS echo "./run.sh" endef -clean: - for DIR in $(SUBDIRS); do $(MAKE) -C $$DIR $@ ; done +override define CLEAN + for DIR in $(SUBDIRS); do \ + BUILD_TARGET=$(OUTPUT)/$$DIR; \ + mkdir $$BUILD_TARGET -p; \ + make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\ + done +endef diff --git a/tools/testing/selftests/futex/functional/Makefile b/tools/testing/selftests/futex/functional/Makefile index 9d6b75ef7b5d..a648e7a6cbc3 100644 --- a/tools/testing/selftests/futex/functional/Makefile +++ b/tools/testing/selftests/futex/functional/Makefile @@ -2,8 +2,11 @@ INCLUDES := -I../include -I../../ CFLAGS := $(CFLAGS) -g -O2 -Wall -D_GNU_SOURCE -pthread $(INCLUDES) LDFLAGS := $(LDFLAGS) -pthread -lrt -HEADERS := ../include/futextest.h -TARGETS := \ +HEADERS := \ + ../include/futextest.h \ + ../include/atomic.h \ + ../include/logging.h +TEST_GEN_FILES := \ futex_wait_timeout \ futex_wait_wouldblock \ futex_requeue_pi \ @@ -12,14 +15,8 @@ TARGETS := \ futex_wait_uninitialized_heap \ futex_wait_private_mapped_file -TEST_PROGS := $(TARGETS) run.sh - -.PHONY: all clean -all: $(TARGETS) - -$(TARGETS): $(HEADERS) +TEST_PROGS := run.sh include ../../lib.mk -clean: - rm -f $(TARGETS) +$(TEST_GEN_FILES): $(HEADERS) diff --git a/tools/testing/selftests/futex/include/logging.h b/tools/testing/selftests/futex/include/logging.h index 014aa01197af..e14469103f07 100644 --- a/tools/testing/selftests/futex/include/logging.h +++ b/tools/testing/selftests/futex/include/logging.h @@ -21,6 +21,7 @@ #ifndef _LOGGING_H #define _LOGGING_H +#include <stdio.h> #include <string.h> #include <unistd.h> #include <linux/futex.h> diff --git a/tools/testing/selftests/gpio/.gitignore b/tools/testing/selftests/gpio/.gitignore new file mode 100644 index 000000000000..7d14f743d1a4 --- /dev/null +++ b/tools/testing/selftests/gpio/.gitignore @@ -0,0 +1 @@ +gpio-mockup-chardev diff --git a/tools/testing/selftests/gpio/Makefile b/tools/testing/selftests/gpio/Makefile index 205e4d10e085..298929df97e6 100644 --- a/tools/testing/selftests/gpio/Makefile +++ b/tools/testing/selftests/gpio/Makefile @@ -2,13 +2,20 @@ TEST_PROGS := gpio-mockup.sh TEST_FILES := gpio-mockup-sysfs.sh $(BINARIES) BINARIES := gpio-mockup-chardev +EXTRA_PROGS := ../gpiogpio-event-mon ../gpiogpio-hammer ../gpiolsgpio +EXTRA_DIRS := ../gpioinclude/ +EXTRA_OBJS := ../gpiogpio-event-mon-in.o ../gpiogpio-event-mon.o +EXTRA_OBJS += ../gpiogpio-hammer-in.o ../gpiogpio-utils.o ../gpiolsgpio-in.o +EXTRA_OBJS += ../gpiolsgpio.o include ../lib.mk all: $(BINARIES) -clean: - $(RM) $(BINARIES) +override define CLEAN + $(RM) $(BINARIES) $(EXTRA_PROGS) $(EXTRA_OBJS) + $(RM) -r $(EXTRA_DIRS) +endef CFLAGS += -O2 -g -std=gnu99 -Wall -I../../../../usr/include/ LDLIBS += -lmount -I/usr/include/libmount diff --git a/tools/testing/selftests/gpio/config b/tools/testing/selftests/gpio/config new file mode 100644 index 000000000000..abaa6902b7b6 --- /dev/null +++ b/tools/testing/selftests/gpio/config @@ -0,0 +1,2 @@ +CONFIG_GPIOLIB=y +CONFIG_GPIO_MOCKUP=m diff --git a/tools/testing/selftests/intel_pstate/Makefile b/tools/testing/selftests/intel_pstate/Makefile index f5f1a28715ff..19678e90efb2 100644 --- a/tools/testing/selftests/intel_pstate/Makefile +++ b/tools/testing/selftests/intel_pstate/Makefile @@ -1,15 +1,10 @@ -CC := $(CROSS_COMPILE)gcc CFLAGS := $(CFLAGS) -Wall -D_GNU_SOURCE LDFLAGS := $(LDFLAGS) -lm -TARGETS := msr aperf +TEST_GEN_FILES := msr aperf -TEST_PROGS := $(TARGETS) run.sh +TEST_PROGS := run.sh -.PHONY: all clean -all: $(TARGETS) +include ../lib.mk -$(TARGETS): $(HEADERS) - -clean: - rm -f $(TARGETS) +$(TEST_GEN_FILES): $(HEADERS) diff --git a/tools/testing/selftests/intel_pstate/aperf.c b/tools/testing/selftests/intel_pstate/aperf.c index 6046e183f4ad..cd72f3dc83e9 100644 --- a/tools/testing/selftests/intel_pstate/aperf.c +++ b/tools/testing/selftests/intel_pstate/aperf.c @@ -14,7 +14,7 @@ void usage(char *name) { } int main(int argc, char **argv) { - int i, cpu, fd; + unsigned int i, cpu, fd; char msr_file_name[64]; long long tsc, old_tsc, new_tsc; long long aperf, old_aperf, new_aperf; diff --git a/tools/testing/selftests/ipc/.gitignore b/tools/testing/selftests/ipc/.gitignore index 84b66a3c1f74..9af04c9353c0 100644 --- a/tools/testing/selftests/ipc/.gitignore +++ b/tools/testing/selftests/ipc/.gitignore @@ -1 +1,2 @@ msgque_test +msgque diff --git a/tools/testing/selftests/ipc/Makefile b/tools/testing/selftests/ipc/Makefile index 25d2e702c68a..30ef4c7f53ea 100644 --- a/tools/testing/selftests/ipc/Makefile +++ b/tools/testing/selftests/ipc/Makefile @@ -11,12 +11,7 @@ endif CFLAGS += -I../../../../usr/include/ -all: - $(CC) $(CFLAGS) msgque.c -o msgque_test - -TEST_PROGS := msgque_test +TEST_GEN_PROGS := msgque include ../lib.mk -clean: - rm -fr ./msgque_test diff --git a/tools/testing/selftests/kcmp/Makefile b/tools/testing/selftests/kcmp/Makefile index 2ae7450a9a89..47aa9887f9d4 100644 --- a/tools/testing/selftests/kcmp/Makefile +++ b/tools/testing/selftests/kcmp/Makefile @@ -1,10 +1,8 @@ CFLAGS += -I../../../../usr/include/ -all: kcmp_test +TEST_GEN_PROGS := kcmp_test -TEST_PROGS := kcmp_test +EXTRA_CLEAN := $(OUTPUT)/kcmp-test-file include ../lib.mk -clean: - $(RM) kcmp_test kcmp-test-file diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index 50a93f5f13d6..959273c3a52e 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -2,9 +2,19 @@ # Makefile can operate with or without the kbuild infrastructure. CC := $(CROSS_COMPILE)gcc +ifeq (0,$(MAKELEVEL)) +OUTPUT := $(shell pwd) +endif + +TEST_GEN_PROGS := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS)) +TEST_GEN_FILES := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_FILES)) + +all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) + define RUN_TESTS - @for TEST in $(TEST_PROGS); do \ - (./$$TEST && echo "selftests: $$TEST [PASS]") || echo "selftests: $$TEST [FAIL]"; \ + @for TEST in $(TEST_GEN_PROGS) $(TEST_PROGS); do \ + BASENAME_TEST=`basename $$TEST`; \ + cd `dirname $$TEST`; (./$$BASENAME_TEST && echo "selftests: $$BASENAME_TEST [PASS]") || echo "selftests: $$BASENAME_TEST [FAIL]"; cd -;\ done; endef @@ -14,8 +24,13 @@ run_tests: all define INSTALL_RULE @if [ "X$(TEST_PROGS)$(TEST_PROGS_EXTENDED)$(TEST_FILES)" != "X" ]; then \ mkdir -p ${INSTALL_PATH}; \ - echo "rsync -a $(TEST_DIRS) $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/"; \ - rsync -a $(TEST_DIRS) $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/; \ + echo "rsync -a $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/"; \ + rsync -a $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/; \ + fi + @if [ "X$(TEST_GEN_PROGS)$(TEST_GEN_PROGS_EXTENDED)$(TEST_GEN_FILES)" != "X" ]; then \ + mkdir -p ${INSTALL_PATH}; \ + echo "rsync -a $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/"; \ + rsync -a $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/; \ fi endef @@ -27,12 +42,29 @@ else endif define EMIT_TESTS - @for TEST in $(TEST_PROGS); do \ - echo "(./$$TEST && echo \"selftests: $$TEST [PASS]\") || echo \"selftests: $$TEST [FAIL]\""; \ + @for TEST in $(TEST_GEN_PROGS) $(TEST_PROGS); do \ + BASENAME_TEST=`basename $$TEST`; \ + echo "(./$$BASENAME_TEST && echo \"selftests: $$BASENAME_TEST [PASS]\") || echo \"selftests: $$BASENAME_TEST [FAIL]\""; \ done; endef emit_tests: $(EMIT_TESTS) +define CLEAN + $(RM) -r $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(EXTRA_CLEAN) +endef + +clean: + $(CLEAN) + +$(OUTPUT)/%:%.c + $(LINK.c) $^ $(LDLIBS) -o $@ + +$(OUTPUT)/%.o:%.S + $(COMPILE.S) $^ -o $@ + +$(OUTPUT)/%:%.S + $(LINK.S) $^ $(LDLIBS) -o $@ + .PHONY: run_tests all clean install emit_tests diff --git a/tools/testing/selftests/lib/config b/tools/testing/selftests/lib/config new file mode 100644 index 000000000000..126933bcc950 --- /dev/null +++ b/tools/testing/selftests/lib/config @@ -0,0 +1,3 @@ +CONFIG_TEST_PRINTF=m +CONFIG_TEST_BITMAP=m +CONFIG_PRIME_NUMBERS=m diff --git a/tools/testing/selftests/lib/prime_numbers.sh b/tools/testing/selftests/lib/prime_numbers.sh new file mode 100755 index 000000000000..da4cbcd766f5 --- /dev/null +++ b/tools/testing/selftests/lib/prime_numbers.sh @@ -0,0 +1,15 @@ +#!/bin/sh +# Checks fast/slow prime_number generation for inconsistencies + +if ! /sbin/modprobe -q -r prime_numbers; then + echo "prime_numbers: [SKIP]" + exit 77 +fi + +if /sbin/modprobe -q prime_numbers selftest=65536; then + /sbin/modprobe -q -r prime_numbers + echo "prime_numbers: ok" +else + echo "prime_numbers: [FAIL]" + exit 1 +fi diff --git a/tools/testing/selftests/locking/ww_mutex.sh b/tools/testing/selftests/locking/ww_mutex.sh new file mode 100644 index 000000000000..6905da965f3b --- /dev/null +++ b/tools/testing/selftests/locking/ww_mutex.sh @@ -0,0 +1,10 @@ +#!/bin/sh +# Runs API tests for struct ww_mutex (Wait/Wound mutexes) + +if /sbin/modprobe -q test-ww_mutex; then + /sbin/modprobe -q -r test-ww_mutex + echo "locking/ww_mutex: ok" +else + echo "locking/ww_mutex: [FAIL]" + exit 1 +fi diff --git a/tools/testing/selftests/membarrier/Makefile b/tools/testing/selftests/membarrier/Makefile index a1a97085847d..02845532b059 100644 --- a/tools/testing/selftests/membarrier/Makefile +++ b/tools/testing/selftests/membarrier/Makefile @@ -1,10 +1,6 @@ CFLAGS += -g -I../../../../usr/include/ -TEST_PROGS := membarrier_test - -all: $(TEST_PROGS) +TEST_GEN_PROGS := membarrier_test include ../lib.mk -clean: - $(RM) $(TEST_PROGS) diff --git a/tools/testing/selftests/memfd/Makefile b/tools/testing/selftests/memfd/Makefile index fd396ac811b6..79891d033de1 100644 --- a/tools/testing/selftests/memfd/Makefile +++ b/tools/testing/selftests/memfd/Makefile @@ -1,22 +1,13 @@ -CC = $(CROSS_COMPILE)gcc CFLAGS += -D_FILE_OFFSET_BITS=64 CFLAGS += -I../../../../include/uapi/ CFLAGS += -I../../../../include/ CFLAGS += -I../../../../usr/include/ -TEST_PROGS := memfd_test - -all: $(TEST_PROGS) - -include ../lib.mk - -build_fuse: fuse_mnt fuse_test +TEST_PROGS := run_fuse_test.sh +TEST_GEN_FILES := memfd_test fuse_mnt fuse_test fuse_mnt.o: CFLAGS += $(shell pkg-config fuse --cflags) fuse_mnt: LDFLAGS += $(shell pkg-config fuse --libs) -run_fuse: build_fuse - @./run_fuse_test.sh || echo "fuse_test: [FAIL]" +include ../lib.mk -clean: - $(RM) memfd_test fuse_test diff --git a/tools/testing/selftests/mount/Makefile b/tools/testing/selftests/mount/Makefile index 5e35c9c50b72..9093d7ffe87f 100644 --- a/tools/testing/selftests/mount/Makefile +++ b/tools/testing/selftests/mount/Makefile @@ -1,14 +1,11 @@ # Makefile for mount selftests. CFLAGS = -Wall \ -O2 -all: unprivileged-remount-test -unprivileged-remount-test: unprivileged-remount-test.c - $(CC) $(CFLAGS) unprivileged-remount-test.c -o unprivileged-remount-test +TEST_GEN_PROGS := unprivileged-remount-test include ../lib.mk -TEST_PROGS := unprivileged-remount-test override RUN_TESTS := if [ -f /proc/self/uid_map ] ; \ then \ ./unprivileged-remount-test ; \ @@ -17,5 +14,3 @@ override RUN_TESTS := if [ -f /proc/self/uid_map ] ; \ fi override EMIT_TESTS := echo "$(RUN_TESTS)" -clean: - rm -f unprivileged-remount-test diff --git a/tools/testing/selftests/mqueue/Makefile b/tools/testing/selftests/mqueue/Makefile index eebac29acbd9..79a664aeb8d7 100644 --- a/tools/testing/selftests/mqueue/Makefile +++ b/tools/testing/selftests/mqueue/Makefile @@ -1,8 +1,6 @@ CFLAGS += -O2 LDLIBS = -lrt -lpthread -lpopt -TEST_PROGS := mq_open_tests mq_perf_tests - -all: $(TEST_PROGS) +TEST_GEN_PROGS := mq_open_tests mq_perf_tests include ../lib.mk @@ -16,5 +14,3 @@ override define EMIT_TESTS echo "./mq_perf_tests || echo \"selftests: mq_perf_tests [FAIL]\"" endef -clean: - rm -f mq_open_tests mq_perf_tests diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index e24e4c82542e..35cbb4cba410 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -3,20 +3,13 @@ CFLAGS = -Wall -Wl,--no-as-needed -O2 -g CFLAGS += -I../../../../usr/include/ -NET_PROGS = socket -NET_PROGS += psock_fanout psock_tpacket -NET_PROGS += reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa -NET_PROGS += reuseport_dualstack - -all: $(NET_PROGS) reuseport_bpf_numa: LDFLAGS += -lnuma -%: %.c - $(CC) $(CFLAGS) $(LDFLAGS) -o $@ $^ -TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh -TEST_FILES := $(NET_PROGS) +TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh +TEST_GEN_FILES = socket +TEST_GEN_FILES += psock_fanout psock_tpacket +TEST_GEN_FILES += reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa +TEST_GEN_FILES += reuseport_dualstack include ../lib.mk -clean: - $(RM) $(NET_PROGS) diff --git a/tools/testing/selftests/net/netdevice.sh b/tools/testing/selftests/net/netdevice.sh new file mode 100755 index 000000000000..4e00568d70c2 --- /dev/null +++ b/tools/testing/selftests/net/netdevice.sh @@ -0,0 +1,200 @@ +#!/bin/sh +# +# This test is for checking network interface +# For the moment it tests only ethernet interface (but wifi could be easily added) +# +# We assume that all network driver are loaded +# if not they probably have failed earlier in the boot process and their logged error will be catched by another test +# + +# this function will try to up the interface +# if already up, nothing done +# arg1: network interface name +kci_net_start() +{ + netdev=$1 + + ip link show "$netdev" |grep -q UP + if [ $? -eq 0 ];then + echo "SKIP: $netdev: interface already up" + return 0 + fi + + ip link set "$netdev" up + if [ $? -ne 0 ];then + echo "FAIL: $netdev: Fail to up interface" + return 1 + else + echo "PASS: $netdev: set interface up" + NETDEV_STARTED=1 + fi + return 0 +} + +# this function will try to setup an IP and MAC address on a network interface +# Doing nothing if the interface was already up +# arg1: network interface name +kci_net_setup() +{ + netdev=$1 + + # do nothing if the interface was already up + if [ $NETDEV_STARTED -eq 0 ];then + return 0 + fi + + MACADDR='02:03:04:05:06:07' + ip link set dev $netdev address "$MACADDR" + if [ $? -ne 0 ];then + echo "FAIL: $netdev: Cannot set MAC address" + else + ip link show $netdev |grep -q "$MACADDR" + if [ $? -eq 0 ];then + echo "PASS: $netdev: set MAC address" + else + echo "FAIL: $netdev: Cannot set MAC address" + fi + fi + + #check that the interface did not already have an IP + ip address show "$netdev" |grep '^[[:space:]]*inet' + if [ $? -eq 0 ];then + echo "SKIP: $netdev: already have an IP" + return 0 + fi + + # TODO what ipaddr to set ? DHCP ? + echo "SKIP: $netdev: set IP address" + return 0 +} + +# test an ethtool command +# arg1: return code for not supported (see ethtool code source) +# arg2: summary of the command +# arg3: command to execute +kci_netdev_ethtool_test() +{ + if [ $# -le 2 ];then + echo "SKIP: $netdev: ethtool: invalid number of arguments" + return 1 + fi + $3 >/dev/null + ret=$? + if [ $ret -ne 0 ];then + if [ $ret -eq "$1" ];then + echo "SKIP: $netdev: ethtool $2 not supported" + else + echo "FAIL: $netdev: ethtool $2" + return 1 + fi + else + echo "PASS: $netdev: ethtool $2" + fi + return 0 +} + +# test ethtool commands +# arg1: network interface name +kci_netdev_ethtool() +{ + netdev=$1 + + #check presence of ethtool + ethtool --version 2>/dev/null >/dev/null + if [ $? -ne 0 ];then + echo "SKIP: ethtool not present" + return 1 + fi + + TMP_ETHTOOL_FEATURES="$(mktemp)" + if [ ! -e "$TMP_ETHTOOL_FEATURES" ];then + echo "SKIP: Cannot create a tmp file" + return 1 + fi + + ethtool -k "$netdev" > "$TMP_ETHTOOL_FEATURES" + if [ $? -ne 0 ];then + echo "FAIL: $netdev: ethtool list features" + rm "$TMP_ETHTOOL_FEATURES" + return 1 + fi + echo "PASS: $netdev: ethtool list features" + #TODO for each non fixed features, try to turn them on/off + rm "$TMP_ETHTOOL_FEATURES" + + kci_netdev_ethtool_test 74 'dump' "ethtool -d $netdev" + kci_netdev_ethtool_test 94 'stats' "ethtool -S $netdev" + return 0 +} + +# stop a netdev +# arg1: network interface name +kci_netdev_stop() +{ + netdev=$1 + + if [ $NETDEV_STARTED -eq 0 ];then + echo "SKIP: $netdev: interface kept up" + return 0 + fi + + ip link set "$netdev" down + if [ $? -ne 0 ];then + echo "FAIL: $netdev: stop interface" + return 1 + fi + echo "PASS: $netdev: stop interface" + return 0 +} + +# run all test on a netdev +# arg1: network interface name +kci_test_netdev() +{ + NETDEV_STARTED=0 + IFACE_TO_UPDOWN="$1" + IFACE_TO_TEST="$1" + #check for VLAN interface + MASTER_IFACE="$(echo $1 | cut -d@ -f2)" + if [ ! -z "$MASTER_IFACE" ];then + IFACE_TO_UPDOWN="$MASTER_IFACE" + IFACE_TO_TEST="$(echo $1 | cut -d@ -f1)" + fi + + NETDEV_STARTED=0 + kci_net_start "$IFACE_TO_UPDOWN" + + kci_net_setup "$IFACE_TO_TEST" + + kci_netdev_ethtool "$IFACE_TO_TEST" + + kci_netdev_stop "$IFACE_TO_UPDOWN" + return 0 +} + +#check for needed privileges +if [ "$(id -u)" -ne 0 ];then + echo "SKIP: Need root privileges" + exit 0 +fi + +ip -Version 2>/dev/null >/dev/null +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without the ip tool" + exit 0 +fi + +TMP_LIST_NETDEV="$(mktemp)" +if [ ! -e "$TMP_LIST_NETDEV" ];then + echo "FAIL: Cannot create a tmp file" + exit 1 +fi + +ip link show |grep '^[0-9]' | grep -oE '[[:space:]].*eth[0-9]*:|[[:space:]].*enp[0-9]s[0-9]:' | cut -d\ -f2 | cut -d: -f1> "$TMP_LIST_NETDEV" +while read netdev +do + kci_test_netdev "$netdev" +done < "$TMP_LIST_NETDEV" + +rm "$TMP_LIST_NETDEV" +exit 0 diff --git a/tools/testing/selftests/net/psock_fanout.c b/tools/testing/selftests/net/psock_fanout.c index 412459369686..989f917068d1 100644 --- a/tools/testing/selftests/net/psock_fanout.c +++ b/tools/testing/selftests/net/psock_fanout.c @@ -71,18 +71,17 @@ /* Open a socket in a given fanout mode. * @return -1 if mode is bad, a valid socket otherwise */ -static int sock_fanout_open(uint16_t typeflags, int num_packets) +static int sock_fanout_open(uint16_t typeflags, uint16_t group_id) { int fd, val; - fd = socket(PF_PACKET, SOCK_DGRAM, htons(ETH_P_IP)); + fd = socket(PF_PACKET, SOCK_RAW, htons(ETH_P_IP)); if (fd < 0) { perror("socket packet"); exit(1); } - /* fanout group ID is always 0: tests whether old groups are deleted */ - val = ((int) typeflags) << 16; + val = (((int) typeflags) << 16) | group_id; if (setsockopt(fd, SOL_PACKET, PACKET_FANOUT, &val, sizeof(val))) { if (close(fd)) { perror("close packet"); @@ -95,6 +94,38 @@ static int sock_fanout_open(uint16_t typeflags, int num_packets) return fd; } +static void sock_fanout_set_cbpf(int fd) +{ + struct sock_filter bpf_filter[] = { + BPF_STMT(BPF_LD+BPF_B+BPF_ABS, 80), /* ldb [80] */ + BPF_STMT(BPF_RET+BPF_A, 0), /* ret A */ + }; + struct sock_fprog bpf_prog; + + bpf_prog.filter = bpf_filter; + bpf_prog.len = sizeof(bpf_filter) / sizeof(struct sock_filter); + + if (setsockopt(fd, SOL_PACKET, PACKET_FANOUT_DATA, &bpf_prog, + sizeof(bpf_prog))) { + perror("fanout data cbpf"); + exit(1); + } +} + +static void sock_fanout_getopts(int fd, uint16_t *typeflags, uint16_t *group_id) +{ + int sockopt; + socklen_t sockopt_len = sizeof(sockopt); + + if (getsockopt(fd, SOL_PACKET, PACKET_FANOUT, + &sockopt, &sockopt_len)) { + perror("failed to getsockopt"); + exit(1); + } + *typeflags = sockopt >> 16; + *group_id = sockopt & 0xfffff; +} + static void sock_fanout_set_ebpf(int fd) { const int len_off = __builtin_offsetof(struct __sk_buff, len); @@ -223,26 +254,26 @@ static void test_control_group(void) fprintf(stderr, "test: control multiple sockets\n"); - fds[0] = sock_fanout_open(PACKET_FANOUT_HASH, 20); + fds[0] = sock_fanout_open(PACKET_FANOUT_HASH, 0); if (fds[0] == -1) { fprintf(stderr, "ERROR: failed to open HASH socket\n"); exit(1); } if (sock_fanout_open(PACKET_FANOUT_HASH | - PACKET_FANOUT_FLAG_DEFRAG, 10) != -1) { + PACKET_FANOUT_FLAG_DEFRAG, 0) != -1) { fprintf(stderr, "ERROR: joined group with wrong flag defrag\n"); exit(1); } if (sock_fanout_open(PACKET_FANOUT_HASH | - PACKET_FANOUT_FLAG_ROLLOVER, 10) != -1) { + PACKET_FANOUT_FLAG_ROLLOVER, 0) != -1) { fprintf(stderr, "ERROR: joined group with wrong flag ro\n"); exit(1); } - if (sock_fanout_open(PACKET_FANOUT_CPU, 10) != -1) { + if (sock_fanout_open(PACKET_FANOUT_CPU, 0) != -1) { fprintf(stderr, "ERROR: joined group with wrong mode\n"); exit(1); } - fds[1] = sock_fanout_open(PACKET_FANOUT_HASH, 20); + fds[1] = sock_fanout_open(PACKET_FANOUT_HASH, 0); if (fds[1] == -1) { fprintf(stderr, "ERROR: failed to join group\n"); exit(1); @@ -253,6 +284,61 @@ static void test_control_group(void) } } +/* Test creating a unique fanout group ids */ +static void test_unique_fanout_group_ids(void) +{ + int fds[3]; + uint16_t typeflags, first_group_id, second_group_id; + + fprintf(stderr, "test: unique ids\n"); + + fds[0] = sock_fanout_open(PACKET_FANOUT_HASH | + PACKET_FANOUT_FLAG_UNIQUEID, 0); + if (fds[0] == -1) { + fprintf(stderr, "ERROR: failed to create a unique id group.\n"); + exit(1); + } + + sock_fanout_getopts(fds[0], &typeflags, &first_group_id); + if (typeflags != PACKET_FANOUT_HASH) { + fprintf(stderr, "ERROR: unexpected typeflags %x\n", typeflags); + exit(1); + } + + if (sock_fanout_open(PACKET_FANOUT_CPU, first_group_id) != -1) { + fprintf(stderr, "ERROR: joined group with wrong type.\n"); + exit(1); + } + + fds[1] = sock_fanout_open(PACKET_FANOUT_HASH, first_group_id); + if (fds[1] == -1) { + fprintf(stderr, + "ERROR: failed to join previously created group.\n"); + exit(1); + } + + fds[2] = sock_fanout_open(PACKET_FANOUT_HASH | + PACKET_FANOUT_FLAG_UNIQUEID, 0); + if (fds[2] == -1) { + fprintf(stderr, + "ERROR: failed to create a second unique id group.\n"); + exit(1); + } + + sock_fanout_getopts(fds[2], &typeflags, &second_group_id); + if (sock_fanout_open(PACKET_FANOUT_HASH | PACKET_FANOUT_FLAG_UNIQUEID, + second_group_id) != -1) { + fprintf(stderr, + "ERROR: specified a group id when requesting unique id\n"); + exit(1); + } + + if (close(fds[0]) || close(fds[1]) || close(fds[2])) { + fprintf(stderr, "ERROR: closing sockets\n"); + exit(1); + } +} + static int test_datapath(uint16_t typeflags, int port_off, const int expect1[], const int expect2[]) { @@ -263,14 +349,14 @@ static int test_datapath(uint16_t typeflags, int port_off, fprintf(stderr, "test: datapath 0x%hx\n", typeflags); - fds[0] = sock_fanout_open(typeflags, 20); - fds[1] = sock_fanout_open(typeflags, 20); + fds[0] = sock_fanout_open(typeflags, 0); + fds[1] = sock_fanout_open(typeflags, 0); if (fds[0] == -1 || fds[1] == -1) { fprintf(stderr, "ERROR: failed open\n"); exit(1); } if (type == PACKET_FANOUT_CBPF) - sock_setfilter(fds[0], SOL_PACKET, PACKET_FANOUT_DATA); + sock_fanout_set_cbpf(fds[0]); else if (type == PACKET_FANOUT_EBPF) sock_fanout_set_ebpf(fds[0]); @@ -331,10 +417,12 @@ int main(int argc, char **argv) const int expect_cpu0[2][2] = { { 20, 0 }, { 20, 0 } }; const int expect_cpu1[2][2] = { { 0, 20 }, { 0, 20 } }; const int expect_bpf[2][2] = { { 15, 5 }, { 15, 20 } }; + const int expect_uniqueid[2][2] = { { 20, 20}, { 20, 20 } }; int port_off = 2, tries = 5, ret; test_control_single(); test_control_group(); + test_unique_fanout_group_ids(); /* find a set of ports that do not collide onto the same socket */ ret = test_datapath(PACKET_FANOUT_HASH, port_off, @@ -365,6 +453,9 @@ int main(int argc, char **argv) ret |= test_datapath(PACKET_FANOUT_CPU, port_off, expect_cpu1[0], expect_cpu1[1]); + ret |= test_datapath(PACKET_FANOUT_FLAG_UNIQUEID, port_off, + expect_uniqueid[0], expect_uniqueid[1]); + if (ret) return 1; diff --git a/tools/testing/selftests/net/psock_lib.h b/tools/testing/selftests/net/psock_lib.h index 24bc7ec1be7d..7d990d6c861b 100644 --- a/tools/testing/selftests/net/psock_lib.h +++ b/tools/testing/selftests/net/psock_lib.h @@ -38,36 +38,54 @@ # define __maybe_unused __attribute__ ((__unused__)) #endif -static __maybe_unused void sock_setfilter(int fd, int lvl, int optnum) +static __maybe_unused void pair_udp_setfilter(int fd) { + /* the filter below checks for all of the following conditions that + * are based on the contents of create_payload() + * ether type 0x800 and + * ip proto udp and + * skb->len == DATA_LEN and + * udp[38] == 'a' or udp[38] == 'b' + * It can be generated from the following bpf_asm input: + * ldh [12] + * jne #0x800, drop ; ETH_P_IP + * ldb [23] + * jneq #17, drop ; IPPROTO_UDP + * ld len ; ld skb->len + * jlt #100, drop ; DATA_LEN + * ldb [80] + * jeq #97, pass ; DATA_CHAR + * jne #98, drop ; DATA_CHAR_1 + * pass: + * ret #-1 + * drop: + * ret #0 + */ struct sock_filter bpf_filter[] = { - { 0x80, 0, 0, 0x00000000 }, /* LD pktlen */ - { 0x35, 0, 4, DATA_LEN }, /* JGE DATA_LEN [f goto nomatch]*/ - { 0x30, 0, 0, 0x00000050 }, /* LD ip[80] */ - { 0x15, 1, 0, DATA_CHAR }, /* JEQ DATA_CHAR [t goto match]*/ - { 0x15, 0, 1, DATA_CHAR_1}, /* JEQ DATA_CHAR_1 [t goto match]*/ - { 0x06, 0, 0, 0x00000060 }, /* RET match */ - { 0x06, 0, 0, 0x00000000 }, /* RET no match */ + { 0x28, 0, 0, 0x0000000c }, + { 0x15, 0, 8, 0x00000800 }, + { 0x30, 0, 0, 0x00000017 }, + { 0x15, 0, 6, 0x00000011 }, + { 0x80, 0, 0, 0000000000 }, + { 0x35, 0, 4, 0x00000064 }, + { 0x30, 0, 0, 0x00000050 }, + { 0x15, 1, 0, 0x00000061 }, + { 0x15, 0, 1, 0x00000062 }, + { 0x06, 0, 0, 0xffffffff }, + { 0x06, 0, 0, 0000000000 }, }; struct sock_fprog bpf_prog; - if (lvl == SOL_PACKET && optnum == PACKET_FANOUT_DATA) - bpf_filter[5].code = 0x16; /* RET A */ - bpf_prog.filter = bpf_filter; bpf_prog.len = sizeof(bpf_filter) / sizeof(struct sock_filter); - if (setsockopt(fd, lvl, optnum, &bpf_prog, + + if (setsockopt(fd, SOL_SOCKET, SO_ATTACH_FILTER, &bpf_prog, sizeof(bpf_prog))) { perror("setsockopt SO_ATTACH_FILTER"); exit(1); } } -static __maybe_unused void pair_udp_setfilter(int fd) -{ - sock_setfilter(fd, SOL_SOCKET, SO_ATTACH_FILTER); -} - static __maybe_unused void pair_udp_open(int fds[], uint16_t port) { struct sockaddr_in saddr, daddr; diff --git a/tools/testing/selftests/net/psock_tpacket.c b/tools/testing/selftests/net/psock_tpacket.c index 24adf709bd9d..7f6cd9fdacf3 100644 --- a/tools/testing/selftests/net/psock_tpacket.c +++ b/tools/testing/selftests/net/psock_tpacket.c @@ -110,7 +110,7 @@ static unsigned int total_packets, total_bytes; static int pfsocket(int ver) { - int ret, sock = socket(PF_PACKET, SOCK_RAW, htons(ETH_P_ALL)); + int ret, sock = socket(PF_PACKET, SOCK_RAW, 0); if (sock == -1) { perror("socket"); exit(1); @@ -239,7 +239,6 @@ static void walk_v1_v2_rx(int sock, struct ring *ring) bug_on(ring->type != PACKET_RX_RING); pair_udp_open(udp_sock, PORT_BASE); - pair_udp_setfilter(sock); memset(&pfd, 0, sizeof(pfd)); pfd.fd = sock; @@ -311,20 +310,33 @@ static inline void __v2_tx_user_ready(struct tpacket2_hdr *hdr) __sync_synchronize(); } -static inline int __v1_v2_tx_kernel_ready(void *base, int version) +static inline int __v3_tx_kernel_ready(struct tpacket3_hdr *hdr) +{ + return !(hdr->tp_status & (TP_STATUS_SEND_REQUEST | TP_STATUS_SENDING)); +} + +static inline void __v3_tx_user_ready(struct tpacket3_hdr *hdr) +{ + hdr->tp_status = TP_STATUS_SEND_REQUEST; + __sync_synchronize(); +} + +static inline int __tx_kernel_ready(void *base, int version) { switch (version) { case TPACKET_V1: return __v1_tx_kernel_ready(base); case TPACKET_V2: return __v2_tx_kernel_ready(base); + case TPACKET_V3: + return __v3_tx_kernel_ready(base); default: bug_on(1); return 0; } } -static inline void __v1_v2_tx_user_ready(void *base, int version) +static inline void __tx_user_ready(void *base, int version) { switch (version) { case TPACKET_V1: @@ -333,6 +345,9 @@ static inline void __v1_v2_tx_user_ready(void *base, int version) case TPACKET_V2: __v2_tx_user_ready(base); break; + case TPACKET_V3: + __v3_tx_user_ready(base); + break; } } @@ -348,7 +363,22 @@ static void __v1_v2_set_packet_loss_discard(int sock) } } -static void walk_v1_v2_tx(int sock, struct ring *ring) +static inline void *get_next_frame(struct ring *ring, int n) +{ + uint8_t *f0 = ring->rd[0].iov_base; + + switch (ring->version) { + case TPACKET_V1: + case TPACKET_V2: + return ring->rd[n].iov_base; + case TPACKET_V3: + return f0 + (n * ring->req3.tp_frame_size); + default: + bug_on(1); + } +} + +static void walk_tx(int sock, struct ring *ring) { struct pollfd pfd; int rcv_sock, ret; @@ -360,9 +390,19 @@ static void walk_v1_v2_tx(int sock, struct ring *ring) .sll_family = PF_PACKET, .sll_halen = ETH_ALEN, }; + int nframes; + + /* TPACKET_V{1,2} sets up the ring->rd* related variables based + * on frames (e.g., rd_num is tp_frame_nr) whereas V3 sets these + * up based on blocks (e.g, rd_num is tp_block_nr) + */ + if (ring->version <= TPACKET_V2) + nframes = ring->rd_num; + else + nframes = ring->req3.tp_frame_nr; bug_on(ring->type != PACKET_TX_RING); - bug_on(ring->rd_num < NUM_PACKETS); + bug_on(nframes < NUM_PACKETS); rcv_sock = socket(PF_PACKET, SOCK_RAW, htons(ETH_P_ALL)); if (rcv_sock == -1) { @@ -388,10 +428,11 @@ static void walk_v1_v2_tx(int sock, struct ring *ring) create_payload(packet, &packet_len); while (total_packets > 0) { - while (__v1_v2_tx_kernel_ready(ring->rd[frame_num].iov_base, - ring->version) && + void *next = get_next_frame(ring, frame_num); + + while (__tx_kernel_ready(next, ring->version) && total_packets > 0) { - ppd.raw = ring->rd[frame_num].iov_base; + ppd.raw = next; switch (ring->version) { case TPACKET_V1: @@ -413,14 +454,27 @@ static void walk_v1_v2_tx(int sock, struct ring *ring) packet_len); total_bytes += ppd.v2->tp_h.tp_snaplen; break; + case TPACKET_V3: { + struct tpacket3_hdr *tx = next; + + tx->tp_snaplen = packet_len; + tx->tp_len = packet_len; + tx->tp_next_offset = 0; + + memcpy((uint8_t *)tx + TPACKET3_HDRLEN - + sizeof(struct sockaddr_ll), packet, + packet_len); + total_bytes += tx->tp_snaplen; + break; + } } status_bar_update(); total_packets--; - __v1_v2_tx_user_ready(ppd.raw, ring->version); + __tx_user_ready(next, ring->version); - frame_num = (frame_num + 1) % ring->rd_num; + frame_num = (frame_num + 1) % nframes; } poll(&pfd, 1, 1); @@ -460,7 +514,7 @@ static void walk_v1_v2(int sock, struct ring *ring) if (ring->type == PACKET_RX_RING) walk_v1_v2_rx(sock, ring); else - walk_v1_v2_tx(sock, ring); + walk_tx(sock, ring); } static uint64_t __v3_prev_block_seq_num = 0; @@ -546,7 +600,6 @@ static void walk_v3_rx(int sock, struct ring *ring) bug_on(ring->type != PACKET_RX_RING); pair_udp_open(udp_sock, PORT_BASE); - pair_udp_setfilter(sock); memset(&pfd, 0, sizeof(pfd)); pfd.fd = sock; @@ -583,7 +636,7 @@ static void walk_v3(int sock, struct ring *ring) if (ring->type == PACKET_RX_RING) walk_v3_rx(sock, ring); else - bug_on(1); + walk_tx(sock, ring); } static void __v1_v2_fill(struct ring *ring, unsigned int blocks) @@ -602,12 +655,13 @@ static void __v1_v2_fill(struct ring *ring, unsigned int blocks) ring->flen = ring->req.tp_frame_size; } -static void __v3_fill(struct ring *ring, unsigned int blocks) +static void __v3_fill(struct ring *ring, unsigned int blocks, int type) { - ring->req3.tp_retire_blk_tov = 64; - ring->req3.tp_sizeof_priv = 0; - ring->req3.tp_feature_req_word = TP_FT_REQ_FILL_RXHASH; - + if (type == PACKET_RX_RING) { + ring->req3.tp_retire_blk_tov = 64; + ring->req3.tp_sizeof_priv = 0; + ring->req3.tp_feature_req_word = TP_FT_REQ_FILL_RXHASH; + } ring->req3.tp_block_size = getpagesize() << 2; ring->req3.tp_frame_size = TPACKET_ALIGNMENT << 7; ring->req3.tp_block_nr = blocks; @@ -641,7 +695,7 @@ static void setup_ring(int sock, struct ring *ring, int version, int type) break; case TPACKET_V3: - __v3_fill(ring, blocks); + __v3_fill(ring, blocks, type); ret = setsockopt(sock, SOL_PACKET, type, &ring->req3, sizeof(ring->req3)); break; @@ -685,6 +739,8 @@ static void bind_ring(int sock, struct ring *ring) { int ret; + pair_udp_setfilter(sock); + ring->ll.sll_family = PF_PACKET; ring->ll.sll_protocol = htons(ETH_P_ALL); ring->ll.sll_ifindex = if_nametoindex("lo"); @@ -796,6 +852,7 @@ int main(void) ret |= test_tpacket(TPACKET_V2, PACKET_TX_RING); ret |= test_tpacket(TPACKET_V3, PACKET_RX_RING); + ret |= test_tpacket(TPACKET_V3, PACKET_TX_RING); if (ret) return 1; diff --git a/tools/testing/selftests/nsfs/Makefile b/tools/testing/selftests/nsfs/Makefile index 2306054a901a..9ff7c7f80625 100644 --- a/tools/testing/selftests/nsfs/Makefile +++ b/tools/testing/selftests/nsfs/Makefile @@ -1,12 +1,5 @@ -TEST_PROGS := owner pidns +TEST_GEN_PROGS := owner pidns CFLAGS := -Wall -Werror -all: owner pidns -owner: owner.c -pidns: pidns.c - -clean: - $(RM) owner pidns - include ../lib.mk diff --git a/tools/testing/selftests/powerpc/Makefile b/tools/testing/selftests/powerpc/Makefile index c2c4211ba58b..72c3ac2323e1 100644 --- a/tools/testing/selftests/powerpc/Makefile +++ b/tools/testing/selftests/powerpc/Makefile @@ -8,12 +8,13 @@ ifeq ($(ARCH),powerpc) GIT_VERSION = $(shell git describe --always --long --dirty || echo "unknown") -CFLAGS := -std=gnu99 -Wall -O2 -Wall -Werror -DGIT_VERSION='"$(GIT_VERSION)"' -I$(CURDIR)/include $(CFLAGS) +CFLAGS := -std=gnu99 -O2 -Wall -Werror -DGIT_VERSION='"$(GIT_VERSION)"' -I$(CURDIR)/include $(CFLAGS) export CFLAGS SUB_DIRS = alignment \ benchmarks \ + cache_shape \ copyloops \ context_switch \ dscr \ @@ -34,33 +35,38 @@ endif all: $(SUB_DIRS) $(SUB_DIRS): - $(MAKE) -k -C $@ all + BUILD_TARGET=$(OUTPUT)/$@; mkdir -p $$BUILD_TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -k -C $@ all include ../lib.mk override define RUN_TESTS @for TARGET in $(SUB_DIRS); do \ - $(MAKE) -C $$TARGET run_tests; \ + BUILD_TARGET=$(OUTPUT)/$$TARGET; \ + $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests;\ done; endef override define INSTALL_RULE @for TARGET in $(SUB_DIRS); do \ - $(MAKE) -C $$TARGET install; \ + BUILD_TARGET=$(OUTPUT)/$$TARGET; \ + $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET install;\ done; endef override define EMIT_TESTS @for TARGET in $(SUB_DIRS); do \ - $(MAKE) -s -C $$TARGET emit_tests; \ + BUILD_TARGET=$(OUTPUT)/$$TARGET; \ + $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests;\ done; endef -clean: +override define CLEAN @for TARGET in $(SUB_DIRS); do \ - $(MAKE) -C $$TARGET clean; \ + BUILD_TARGET=$(OUTPUT)/$$TARGET; \ + $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean; \ done; rm -f tags +endef tags: find . -name '*.c' -o -name '*.h' | xargs ctags diff --git a/tools/testing/selftests/powerpc/alignment/Makefile b/tools/testing/selftests/powerpc/alignment/Makefile index ad6a4e49da91..16b22004e75f 100644 --- a/tools/testing/selftests/powerpc/alignment/Makefile +++ b/tools/testing/selftests/powerpc/alignment/Makefile @@ -1,10 +1,5 @@ -TEST_PROGS := copy_unaligned copy_first_unaligned paste_unaligned paste_last_unaligned - -all: $(TEST_PROGS) - -$(TEST_PROGS): ../harness.c ../utils.c copy_paste_unaligned_common.c +TEST_GEN_PROGS := copy_unaligned copy_first_unaligned paste_unaligned paste_last_unaligned include ../../lib.mk -clean: - rm -f $(TEST_PROGS) +$(TEST_GEN_PROGS): ../harness.c ../utils.c copy_paste_unaligned_common.c diff --git a/tools/testing/selftests/powerpc/benchmarks/Makefile b/tools/testing/selftests/powerpc/benchmarks/Makefile index 545077f98f72..fb96a89bd953 100644 --- a/tools/testing/selftests/powerpc/benchmarks/Makefile +++ b/tools/testing/selftests/powerpc/benchmarks/Makefile @@ -1,16 +1,11 @@ -TEST_PROGS := gettimeofday context_switch mmap_bench futex_bench null_syscall +TEST_GEN_PROGS := gettimeofday context_switch mmap_bench futex_bench null_syscall CFLAGS += -O2 -all: $(TEST_PROGS) - -$(TEST_PROGS): ../harness.c - -context_switch: ../utils.c -context_switch: CFLAGS += -maltivec -mvsx -mabi=altivec -context_switch: LDLIBS += -lpthread - include ../../lib.mk -clean: - rm -f $(TEST_PROGS) *.o +$(TEST_GEN_PROGS): ../harness.c + +$(OUTPUT)/context_switch: ../utils.c +$(OUTPUT)/context_switch: CFLAGS += -maltivec -mvsx -mabi=altivec +$(OUTPUT)/context_switch: LDLIBS += -lpthread diff --git a/tools/testing/selftests/powerpc/cache_shape/.gitignore b/tools/testing/selftests/powerpc/cache_shape/.gitignore new file mode 100644 index 000000000000..ec1848434be5 --- /dev/null +++ b/tools/testing/selftests/powerpc/cache_shape/.gitignore @@ -0,0 +1 @@ +cache_shape diff --git a/tools/testing/selftests/powerpc/cache_shape/Makefile b/tools/testing/selftests/powerpc/cache_shape/Makefile new file mode 100644 index 000000000000..b24485ab30e2 --- /dev/null +++ b/tools/testing/selftests/powerpc/cache_shape/Makefile @@ -0,0 +1,10 @@ +TEST_PROGS := cache_shape + +all: $(TEST_PROGS) + +$(TEST_PROGS): ../harness.c ../utils.c + +include ../../lib.mk + +clean: + rm -f $(TEST_PROGS) *.o diff --git a/tools/testing/selftests/powerpc/cache_shape/cache_shape.c b/tools/testing/selftests/powerpc/cache_shape/cache_shape.c new file mode 100644 index 000000000000..29ec07eba7f9 --- /dev/null +++ b/tools/testing/selftests/powerpc/cache_shape/cache_shape.c @@ -0,0 +1,125 @@ +/* + * Copyright 2017, Michael Ellerman, IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <elf.h> +#include <errno.h> +#include <fcntl.h> +#include <link.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <unistd.h> + +#include "utils.h" + +#ifndef AT_L1I_CACHESIZE +#define AT_L1I_CACHESIZE 40 +#define AT_L1I_CACHEGEOMETRY 41 +#define AT_L1D_CACHESIZE 42 +#define AT_L1D_CACHEGEOMETRY 43 +#define AT_L2_CACHESIZE 44 +#define AT_L2_CACHEGEOMETRY 45 +#define AT_L3_CACHESIZE 46 +#define AT_L3_CACHEGEOMETRY 47 +#endif + +static void print_size(const char *label, uint32_t val) +{ + printf("%s cache size: %#10x %10dB %10dK\n", label, val, val, val / 1024); +} + +static void print_geo(const char *label, uint32_t val) +{ + uint16_t assoc; + + printf("%s line size: %#10x ", label, val & 0xFFFF); + + assoc = val >> 16; + if (assoc) + printf("%u-way", assoc); + else + printf("fully"); + + printf(" associative\n"); +} + +static int test_cache_shape() +{ + static char buffer[4096]; + ElfW(auxv_t) *p; + int found; + + FAIL_IF(read_auxv(buffer, sizeof(buffer))); + + found = 0; + + p = find_auxv_entry(AT_L1I_CACHESIZE, buffer); + if (p) { + found++; + print_size("L1I ", (uint32_t)p->a_un.a_val); + } + + p = find_auxv_entry(AT_L1I_CACHEGEOMETRY, buffer); + if (p) { + found++; + print_geo("L1I ", (uint32_t)p->a_un.a_val); + } + + p = find_auxv_entry(AT_L1D_CACHESIZE, buffer); + if (p) { + found++; + print_size("L1D ", (uint32_t)p->a_un.a_val); + } + + p = find_auxv_entry(AT_L1D_CACHEGEOMETRY, buffer); + if (p) { + found++; + print_geo("L1D ", (uint32_t)p->a_un.a_val); + } + + p = find_auxv_entry(AT_L2_CACHESIZE, buffer); + if (p) { + found++; + print_size("L2 ", (uint32_t)p->a_un.a_val); + } + + p = find_auxv_entry(AT_L2_CACHEGEOMETRY, buffer); + if (p) { + found++; + print_geo("L2 ", (uint32_t)p->a_un.a_val); + } + + p = find_auxv_entry(AT_L3_CACHESIZE, buffer); + if (p) { + found++; + print_size("L3 ", (uint32_t)p->a_un.a_val); + } + + p = find_auxv_entry(AT_L3_CACHEGEOMETRY, buffer); + if (p) { + found++; + print_geo("L3 ", (uint32_t)p->a_un.a_val); + } + + /* If we found none we're probably on a system where they don't exist */ + SKIP_IF(found == 0); + + /* But if we found any, we expect to find them all */ + FAIL_IF(found != 8); + + return 0; +} + +int main(void) +{ + return test_harness(test_cache_shape, "cache_shape"); +} diff --git a/tools/testing/selftests/powerpc/context_switch/Makefile b/tools/testing/selftests/powerpc/context_switch/Makefile index e164d1466466..e9351bb4285d 100644 --- a/tools/testing/selftests/powerpc/context_switch/Makefile +++ b/tools/testing/selftests/powerpc/context_switch/Makefile @@ -1,10 +1,5 @@ -TEST_PROGS := cp_abort - -all: $(TEST_PROGS) - -$(TEST_PROGS): ../harness.c ../utils.c +TEST_GEN_PROGS := cp_abort include ../../lib.mk -clean: - rm -f $(TEST_PROGS) +$(TEST_GEN_PROGS): ../harness.c ../utils.c diff --git a/tools/testing/selftests/powerpc/copyloops/Makefile b/tools/testing/selftests/powerpc/copyloops/Makefile index 384843ea0d40..681ab19d0a84 100644 --- a/tools/testing/selftests/powerpc/copyloops/Makefile +++ b/tools/testing/selftests/powerpc/copyloops/Makefile @@ -7,19 +7,14 @@ CFLAGS += -maltivec # Use our CFLAGS for the implicit .S rule ASFLAGS = $(CFLAGS) -TEST_PROGS := copyuser_64 copyuser_power7 memcpy_64 memcpy_power7 +TEST_GEN_PROGS := copyuser_64 copyuser_power7 memcpy_64 memcpy_power7 EXTRA_SOURCES := validate.c ../harness.c -all: $(TEST_PROGS) - -copyuser_64: CPPFLAGS += -D COPY_LOOP=test___copy_tofrom_user_base -copyuser_power7: CPPFLAGS += -D COPY_LOOP=test___copy_tofrom_user_power7 -memcpy_64: CPPFLAGS += -D COPY_LOOP=test_memcpy -memcpy_power7: CPPFLAGS += -D COPY_LOOP=test_memcpy_power7 - -$(TEST_PROGS): $(EXTRA_SOURCES) - include ../../lib.mk -clean: - rm -f $(TEST_PROGS) *.o +$(OUTPUT)/copyuser_64: CPPFLAGS += -D COPY_LOOP=test___copy_tofrom_user_base +$(OUTPUT)/copyuser_power7: CPPFLAGS += -D COPY_LOOP=test___copy_tofrom_user_power7 +$(OUTPUT)/memcpy_64: CPPFLAGS += -D COPY_LOOP=test_memcpy +$(OUTPUT)/memcpy_power7: CPPFLAGS += -D COPY_LOOP=test_memcpy_power7 + +$(TEST_GEN_PROGS): $(EXTRA_SOURCES) diff --git a/tools/testing/selftests/powerpc/dscr/Makefile b/tools/testing/selftests/powerpc/dscr/Makefile index 49327ee84e3a..c5639deb8887 100644 --- a/tools/testing/selftests/powerpc/dscr/Makefile +++ b/tools/testing/selftests/powerpc/dscr/Makefile @@ -1,14 +1,9 @@ -TEST_PROGS := dscr_default_test dscr_explicit_test dscr_user_test \ +TEST_GEN_PROGS := dscr_default_test dscr_explicit_test dscr_user_test \ dscr_inherit_test dscr_inherit_exec_test dscr_sysfs_test \ dscr_sysfs_thread_test -dscr_default_test: LDLIBS += -lpthread - -all: $(TEST_PROGS) - -$(TEST_PROGS): ../harness.c - include ../../lib.mk -clean: - rm -f $(TEST_PROGS) *.o +$(OUTPUT)/dscr_default_test: LDLIBS += -lpthread + +$(TEST_GEN_PROGS): ../harness.c diff --git a/tools/testing/selftests/powerpc/harness.c b/tools/testing/selftests/powerpc/harness.c index 248a820048df..66d31de60b9a 100644 --- a/tools/testing/selftests/powerpc/harness.c +++ b/tools/testing/selftests/powerpc/harness.c @@ -114,9 +114,11 @@ int test_harness(int (test_function)(void), char *name) rc = run_test(test_function, name); - if (rc == MAGIC_SKIP_RETURN_VALUE) + if (rc == MAGIC_SKIP_RETURN_VALUE) { test_skip(name); - else + /* so that skipped test is not marked as failed */ + rc = 0; + } else test_finish(name, rc); return rc; diff --git a/tools/testing/selftests/powerpc/include/utils.h b/tools/testing/selftests/powerpc/include/utils.h index 53405e8a52ab..735815b3ad7f 100644 --- a/tools/testing/selftests/powerpc/include/utils.h +++ b/tools/testing/selftests/powerpc/include/utils.h @@ -24,7 +24,11 @@ typedef uint8_t u8; void test_harness_set_timeout(uint64_t time); int test_harness(int (test_function)(void), char *name); -extern void *get_auxv_entry(int type); + +int read_auxv(char *buf, ssize_t buf_size); +void *find_auxv_entry(int type, char *auxv); +void *get_auxv_entry(int type); + int pick_online_cpu(void); static inline bool have_hwcap(unsigned long ftr) diff --git a/tools/testing/selftests/powerpc/include/vsx_asm.h b/tools/testing/selftests/powerpc/include/vsx_asm.h index d828bfb6ef2d..54064ced9e95 100644 --- a/tools/testing/selftests/powerpc/include/vsx_asm.h +++ b/tools/testing/selftests/powerpc/include/vsx_asm.h @@ -16,56 +16,56 @@ */ FUNC_START(load_vsx) li r5,0 - lxvx vs20,r5,r3 + lxvd2x vs20,r5,r3 addi r5,r5,16 - lxvx vs21,r5,r3 + lxvd2x vs21,r5,r3 addi r5,r5,16 - lxvx vs22,r5,r3 + lxvd2x vs22,r5,r3 addi r5,r5,16 - lxvx vs23,r5,r3 + lxvd2x vs23,r5,r3 addi r5,r5,16 - lxvx vs24,r5,r3 + lxvd2x vs24,r5,r3 addi r5,r5,16 - lxvx vs25,r5,r3 + lxvd2x vs25,r5,r3 addi r5,r5,16 - lxvx vs26,r5,r3 + lxvd2x vs26,r5,r3 addi r5,r5,16 - lxvx vs27,r5,r3 + lxvd2x vs27,r5,r3 addi r5,r5,16 - lxvx vs28,r5,r3 + lxvd2x vs28,r5,r3 addi r5,r5,16 - lxvx vs29,r5,r3 + lxvd2x vs29,r5,r3 addi r5,r5,16 - lxvx vs30,r5,r3 + lxvd2x vs30,r5,r3 addi r5,r5,16 - lxvx vs31,r5,r3 + lxvd2x vs31,r5,r3 blr FUNC_END(load_vsx) FUNC_START(store_vsx) li r5,0 - stxvx vs20,r5,r3 + stxvd2x vs20,r5,r3 addi r5,r5,16 - stxvx vs21,r5,r3 + stxvd2x vs21,r5,r3 addi r5,r5,16 - stxvx vs22,r5,r3 + stxvd2x vs22,r5,r3 addi r5,r5,16 - stxvx vs23,r5,r3 + stxvd2x vs23,r5,r3 addi r5,r5,16 - stxvx vs24,r5,r3 + stxvd2x vs24,r5,r3 addi r5,r5,16 - stxvx vs25,r5,r3 + stxvd2x vs25,r5,r3 addi r5,r5,16 - stxvx vs26,r5,r3 + stxvd2x vs26,r5,r3 addi r5,r5,16 - stxvx vs27,r5,r3 + stxvd2x vs27,r5,r3 addi r5,r5,16 - stxvx vs28,r5,r3 + stxvd2x vs28,r5,r3 addi r5,r5,16 - stxvx vs29,r5,r3 + stxvd2x vs29,r5,r3 addi r5,r5,16 - stxvx vs30,r5,r3 + stxvd2x vs30,r5,r3 addi r5,r5,16 - stxvx vs31,r5,r3 + stxvd2x vs31,r5,r3 blr FUNC_END(store_vsx) diff --git a/tools/testing/selftests/powerpc/math/Makefile b/tools/testing/selftests/powerpc/math/Makefile index a505b66d408a..fa8bae920c91 100644 --- a/tools/testing/selftests/powerpc/math/Makefile +++ b/tools/testing/selftests/powerpc/math/Makefile @@ -1,22 +1,17 @@ -TEST_PROGS := fpu_syscall fpu_preempt fpu_signal vmx_syscall vmx_preempt vmx_signal vsx_preempt +TEST_GEN_PROGS := fpu_syscall fpu_preempt fpu_signal vmx_syscall vmx_preempt vmx_signal vsx_preempt -all: $(TEST_PROGS) - -$(TEST_PROGS): ../harness.c -$(TEST_PROGS): CFLAGS += -O2 -g -pthread -m64 -maltivec - -fpu_syscall: fpu_asm.S -fpu_preempt: fpu_asm.S -fpu_signal: fpu_asm.S +include ../../lib.mk -vmx_syscall: vmx_asm.S -vmx_preempt: vmx_asm.S -vmx_signal: vmx_asm.S +$(TEST_GEN_PROGS): ../harness.c +$(TEST_GEN_PROGS): CFLAGS += -O2 -g -pthread -m64 -maltivec -vsx_preempt: CFLAGS += -mvsx -vsx_preempt: vsx_asm.S +$(OUTPUT)/fpu_syscall: fpu_asm.S +$(OUTPUT)/fpu_preempt: fpu_asm.S +$(OUTPUT)/fpu_signal: fpu_asm.S -include ../../lib.mk +$(OUTPUT)/vmx_syscall: vmx_asm.S +$(OUTPUT)/vmx_preempt: vmx_asm.S +$(OUTPUT)/vmx_signal: vmx_asm.S -clean: - rm -f $(TEST_PROGS) *.o +$(OUTPUT)/vsx_preempt: CFLAGS += -mvsx +$(OUTPUT)/vsx_preempt: vsx_asm.S diff --git a/tools/testing/selftests/powerpc/mm/Makefile b/tools/testing/selftests/powerpc/mm/Makefile index 3bdb96eae558..1cffe54dccfb 100644 --- a/tools/testing/selftests/powerpc/mm/Makefile +++ b/tools/testing/selftests/powerpc/mm/Makefile @@ -1,19 +1,15 @@ noarg: $(MAKE) -C ../ -TEST_PROGS := hugetlb_vs_thp_test subpage_prot prot_sao -TEST_FILES := tempfile +TEST_GEN_PROGS := hugetlb_vs_thp_test subpage_prot prot_sao +TEST_GEN_FILES := tempfile -all: $(TEST_PROGS) $(TEST_FILES) - -$(TEST_PROGS): ../harness.c +include ../../lib.mk -prot_sao: ../utils.c +$(TEST_GEN_PROGS): ../harness.c -include ../../lib.mk +$(OUTPUT)/prot_sao: ../utils.c -tempfile: - dd if=/dev/zero of=tempfile bs=64k count=1 +$(OUTPUT)/tempfile: + dd if=/dev/zero of=$@ bs=64k count=1 -clean: - rm -f $(TEST_PROGS) tempfile diff --git a/tools/testing/selftests/powerpc/pmu/Makefile b/tools/testing/selftests/powerpc/pmu/Makefile index ac41a7177f2e..e4e55d1d3e0f 100644 --- a/tools/testing/selftests/powerpc/pmu/Makefile +++ b/tools/testing/selftests/powerpc/pmu/Makefile @@ -1,44 +1,44 @@ noarg: $(MAKE) -C ../ -TEST_PROGS := count_instructions l3_bank_test per_event_excludes +TEST_GEN_PROGS := count_instructions l3_bank_test per_event_excludes EXTRA_SOURCES := ../harness.c event.c lib.c ../utils.c -all: $(TEST_PROGS) ebb +include ../../lib.mk + +all: $(TEST_GEN_PROGS) ebb -$(TEST_PROGS): $(EXTRA_SOURCES) +$(TEST_GEN_PROGS): $(EXTRA_SOURCES) # loop.S can only be built 64-bit -count_instructions: loop.S count_instructions.c $(EXTRA_SOURCES) +$(OUTPUT)/count_instructions: loop.S count_instructions.c $(EXTRA_SOURCES) $(CC) $(CFLAGS) -m64 -o $@ $^ -per_event_excludes: ../utils.c - -include ../../lib.mk +$(OUTPUT)/per_event_excludes: ../utils.c DEFAULT_RUN_TESTS := $(RUN_TESTS) override define RUN_TESTS $(DEFAULT_RUN_TESTS) - $(MAKE) -C ebb run_tests + TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests endef DEFAULT_EMIT_TESTS := $(EMIT_TESTS) override define EMIT_TESTS $(DEFAULT_EMIT_TESTS) - $(MAKE) -s -C ebb emit_tests + TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests endef DEFAULT_INSTALL_RULE := $(INSTALL_RULE) override define INSTALL_RULE $(DEFAULT_INSTALL_RULE) - $(MAKE) -C ebb install + TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET install endef clean: - rm -f $(TEST_PROGS) loop.o - $(MAKE) -C ebb clean + $(RM) $(TEST_GEN_PROGS) $(OUTPUT)/loop.o + TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean ebb: - $(MAKE) -k -C $@ all + TARGET=$@; BUILD_TARGET=$$OUTPUT/$$TARGET; mkdir -p $$BUILD_TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -k -C $$TARGET all .PHONY: all run_tests clean ebb diff --git a/tools/testing/selftests/powerpc/pmu/ebb/Makefile b/tools/testing/selftests/powerpc/pmu/ebb/Makefile index 8d2279c4bb4b..6001fb0a377a 100644 --- a/tools/testing/selftests/powerpc/pmu/ebb/Makefile +++ b/tools/testing/selftests/powerpc/pmu/ebb/Makefile @@ -4,7 +4,7 @@ noarg: # The EBB handler is 64-bit code and everything links against it CFLAGS += -m64 -TEST_PROGS := reg_access_test event_attributes_test cycles_test \ +TEST_GEN_PROGS := reg_access_test event_attributes_test cycles_test \ cycles_with_freeze_test pmc56_overflow_test \ ebb_vs_cpu_event_test cpu_event_vs_ebb_test \ cpu_event_pinned_vs_ebb_test task_event_vs_ebb_test \ @@ -16,16 +16,11 @@ TEST_PROGS := reg_access_test event_attributes_test cycles_test \ lost_exception_test no_handler_test \ cycles_with_mmcr2_test -all: $(TEST_PROGS) +include ../../../lib.mk -$(TEST_PROGS): ../../harness.c ../../utils.c ../event.c ../lib.c \ +$(TEST_GEN_PROGS): ../../harness.c ../../utils.c ../event.c ../lib.c \ ebb.c ebb_handler.S trace.c busy_loop.S -instruction_count_test: ../loop.S - -lost_exception_test: ../lib.c - -include ../../../lib.mk +$(OUTPUT)/instruction_count_test: ../loop.S -clean: - rm -f $(TEST_PROGS) +$(OUTPUT)/lost_exception_test: ../lib.c diff --git a/tools/testing/selftests/powerpc/primitives/Makefile b/tools/testing/selftests/powerpc/primitives/Makefile index b68c6221d3d1..175366db7be8 100644 --- a/tools/testing/selftests/powerpc/primitives/Makefile +++ b/tools/testing/selftests/powerpc/primitives/Makefile @@ -1,12 +1,7 @@ CFLAGS += -I$(CURDIR) -TEST_PROGS := load_unaligned_zeropad - -all: $(TEST_PROGS) - -$(TEST_PROGS): ../harness.c +TEST_GEN_PROGS := load_unaligned_zeropad include ../../lib.mk -clean: - rm -f $(TEST_PROGS) *.o +$(TEST_GEN_PROGS): ../harness.c diff --git a/tools/testing/selftests/powerpc/stringloops/Makefile b/tools/testing/selftests/powerpc/stringloops/Makefile index 2a728f4d2873..557b9379f3bb 100644 --- a/tools/testing/selftests/powerpc/stringloops/Makefile +++ b/tools/testing/selftests/powerpc/stringloops/Makefile @@ -2,14 +2,9 @@ CFLAGS += -m64 CFLAGS += -I$(CURDIR) -TEST_PROGS := memcmp +TEST_GEN_PROGS := memcmp EXTRA_SOURCES := memcmp_64.S ../harness.c -all: $(TEST_PROGS) - -$(TEST_PROGS): $(EXTRA_SOURCES) - include ../../lib.mk -clean: - rm -f $(TEST_PROGS) *.o +$(TEST_GEN_PROGS): $(EXTRA_SOURCES) diff --git a/tools/testing/selftests/powerpc/switch_endian/Makefile b/tools/testing/selftests/powerpc/switch_endian/Makefile index e21d10674e54..b92c2a132c4f 100644 --- a/tools/testing/selftests/powerpc/switch_endian/Makefile +++ b/tools/testing/selftests/powerpc/switch_endian/Makefile @@ -1,18 +1,15 @@ -TEST_PROGS := switch_endian_test +TEST_GEN_PROGS := switch_endian_test ASFLAGS += -O2 -Wall -g -nostdlib -m64 -all: $(TEST_PROGS) +EXTRA_CLEAN = $(OUTPUT)/*.o $(OUTPUT)/check-reversed.S -switch_endian_test: check-reversed.S +include ../../lib.mk + +$(OUTPUT)/switch_endian_test: $(OUTPUT)/check-reversed.S -check-reversed.o: check.o +$(OUTPUT)/check-reversed.o: $(OUTPUT)/check.o $(CROSS_COMPILE)objcopy -j .text --reverse-bytes=4 -O binary $< $@ -check-reversed.S: check-reversed.o +$(OUTPUT)/check-reversed.S: $(OUTPUT)/check-reversed.o hexdump -v -e '/1 ".byte 0x%02X\n"' $< > $@ - -include ../../lib.mk - -clean: - rm -f $(TEST_PROGS) *.o check-reversed.S diff --git a/tools/testing/selftests/powerpc/syscalls/Makefile b/tools/testing/selftests/powerpc/syscalls/Makefile index b35c7945bec5..da22ca7c38c1 100644 --- a/tools/testing/selftests/powerpc/syscalls/Makefile +++ b/tools/testing/selftests/powerpc/syscalls/Makefile @@ -1,12 +1,7 @@ -TEST_PROGS := ipc_unmuxed +TEST_GEN_PROGS := ipc_unmuxed CFLAGS += -I../../../../../usr/include -all: $(TEST_PROGS) - -$(TEST_PROGS): ../harness.c - include ../../lib.mk -clean: - rm -f $(TEST_PROGS) *.o +$(TEST_GEN_PROGS): ../harness.c diff --git a/tools/testing/selftests/powerpc/tm/Makefile b/tools/testing/selftests/powerpc/tm/Makefile index c6c53c82fdd6..5576ee6a51f2 100644 --- a/tools/testing/selftests/powerpc/tm/Makefile +++ b/tools/testing/selftests/powerpc/tm/Makefile @@ -1,23 +1,19 @@ SIGNAL_CONTEXT_CHK_TESTS := tm-signal-context-chk-gpr tm-signal-context-chk-fpu \ tm-signal-context-chk-vmx tm-signal-context-chk-vsx -TEST_PROGS := tm-resched-dscr tm-syscall tm-signal-msr-resv tm-signal-stack \ +TEST_GEN_PROGS := tm-resched-dscr tm-syscall tm-signal-msr-resv tm-signal-stack \ tm-vmxcopy tm-fork tm-tar tm-tmspr $(SIGNAL_CONTEXT_CHK_TESTS) -all: $(TEST_PROGS) +include ../../lib.mk -$(TEST_PROGS): ../harness.c ../utils.c +$(TEST_GEN_PROGS): ../harness.c ../utils.c CFLAGS += -mhtm -tm-syscall: tm-syscall-asm.S -tm-syscall: CFLAGS += -I../../../../../usr/include -tm-tmspr: CFLAGS += -pthread +$(OUTPUT)/tm-syscall: tm-syscall-asm.S +$(OUTPUT)/tm-syscall: CFLAGS += -I../../../../../usr/include +$(OUTPUT)/tm-tmspr: CFLAGS += -pthread +SIGNAL_CONTEXT_CHK_TESTS := $(patsubst %,$(OUTPUT)/%,$(SIGNAL_CONTEXT_CHK_TESTS)) $(SIGNAL_CONTEXT_CHK_TESTS): tm-signal.S $(SIGNAL_CONTEXT_CHK_TESTS): CFLAGS += -mhtm -m64 -mvsx - -include ../../lib.mk - -clean: - rm -f $(TEST_PROGS) *.o diff --git a/tools/testing/selftests/powerpc/utils.c b/tools/testing/selftests/powerpc/utils.c index dcf74184bfd0..d46916867a6f 100644 --- a/tools/testing/selftests/powerpc/utils.c +++ b/tools/testing/selftests/powerpc/utils.c @@ -19,45 +19,64 @@ static char auxv[4096]; -void *get_auxv_entry(int type) +int read_auxv(char *buf, ssize_t buf_size) { - ElfW(auxv_t) *p; - void *result; ssize_t num; - int fd; + int rc, fd; fd = open("/proc/self/auxv", O_RDONLY); if (fd == -1) { perror("open"); - return NULL; + return -errno; } - result = NULL; - - num = read(fd, auxv, sizeof(auxv)); + num = read(fd, buf, buf_size); if (num < 0) { perror("read"); + rc = -EIO; goto out; } - if (num > sizeof(auxv)) { - printf("Overflowed auxv buffer\n"); + if (num > buf_size) { + printf("overflowed auxv buffer\n"); + rc = -EOVERFLOW; goto out; } + rc = 0; +out: + close(fd); + return rc; +} + +void *find_auxv_entry(int type, char *auxv) +{ + ElfW(auxv_t) *p; + p = (ElfW(auxv_t) *)auxv; while (p->a_type != AT_NULL) { - if (p->a_type == type) { - result = (void *)p->a_un.a_val; - break; - } + if (p->a_type == type) + return p; p++; } -out: - close(fd); - return result; + + return NULL; +} + +void *get_auxv_entry(int type) +{ + ElfW(auxv_t) *p; + + if (read_auxv(auxv, sizeof(auxv))) + return NULL; + + p = find_auxv_entry(type, auxv); + if (p) + return (void *)p->a_un.a_val; + + return NULL; } int pick_online_cpu(void) diff --git a/tools/testing/selftests/powerpc/vphn/Makefile b/tools/testing/selftests/powerpc/vphn/Makefile index a485f2e286ae..f8ced26748f8 100644 --- a/tools/testing/selftests/powerpc/vphn/Makefile +++ b/tools/testing/selftests/powerpc/vphn/Makefile @@ -1,12 +1,8 @@ -TEST_PROGS := test-vphn +TEST_GEN_PROGS := test-vphn CFLAGS += -m64 -all: $(TEST_PROGS) - -$(TEST_PROGS): ../harness.c - include ../../lib.mk -clean: - rm -f $(TEST_PROGS) +$(TEST_GEN_PROGS): ../harness.c + diff --git a/tools/testing/selftests/pstore/Makefile b/tools/testing/selftests/pstore/Makefile index bd7abe24ea08..c5f2440ba1f7 100644 --- a/tools/testing/selftests/pstore/Makefile +++ b/tools/testing/selftests/pstore/Makefile @@ -5,11 +5,9 @@ all: TEST_PROGS := pstore_tests pstore_post_reboot_tests TEST_FILES := common_tests pstore_crash_test +EXTRA_CLEAN := logs/* *uuid include ../lib.mk run_crash: @sh pstore_crash_test || { echo "pstore_crash_test: [FAIL]"; exit 1; } - -clean: - rm -rf logs/* *uuid diff --git a/tools/testing/selftests/ptrace/Makefile b/tools/testing/selftests/ptrace/Makefile index 453927fea90c..8a2bc5562179 100644 --- a/tools/testing/selftests/ptrace/Makefile +++ b/tools/testing/selftests/ptrace/Makefile @@ -1,11 +1,5 @@ CFLAGS += -iquote../../../../include/uapi -Wall -peeksiginfo: peeksiginfo.c -all: peeksiginfo - -clean: - rm -f peeksiginfo - -TEST_PROGS := peeksiginfo +TEST_GEN_PROGS := peeksiginfo include ../lib.mk diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh index ea6e373edc27..93eede4e8fbe 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh @@ -170,7 +170,7 @@ qemu_append="`identify_qemu_append "$QEMU"`" # Pull in Kconfig-fragment boot parameters boot_args="`configfrag_boot_params "$boot_args" "$config_template"`" # Generate kernel-version-specific boot parameters -boot_args="`per_version_boot_params "$boot_args" $builddir/.config $seconds`" +boot_args="`per_version_boot_params "$boot_args" $resdir/.config $seconds`" if test -n "$TORTURE_BUILDONLY" then diff --git a/tools/testing/selftests/rcutorture/configs/lock/CFLIST b/tools/testing/selftests/rcutorture/configs/lock/CFLIST index b9611c523723..41bae5824339 100644 --- a/tools/testing/selftests/rcutorture/configs/lock/CFLIST +++ b/tools/testing/selftests/rcutorture/configs/lock/CFLIST @@ -4,3 +4,4 @@ LOCK03 LOCK04 LOCK05 LOCK06 +LOCK07 diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK07 b/tools/testing/selftests/rcutorture/configs/lock/LOCK07 new file mode 100644 index 000000000000..1d1da1477fc3 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK07 @@ -0,0 +1,6 @@ +CONFIG_SMP=y +CONFIG_NR_CPUS=4 +CONFIG_HOTPLUG_CPU=y +CONFIG_PREEMPT_NONE=n +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=y diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK07.boot b/tools/testing/selftests/rcutorture/configs/lock/LOCK07.boot new file mode 100644 index 000000000000..97dadd1a9e45 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK07.boot @@ -0,0 +1 @@ +locktorture.torture_type=ww_mutex_lock diff --git a/tools/testing/selftests/rcutorture/configs/rcu/CFcommon b/tools/testing/selftests/rcutorture/configs/rcu/CFcommon index f824b4c9d9d9..d2d2a86139db 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/CFcommon +++ b/tools/testing/selftests/rcutorture/configs/rcu/CFcommon @@ -1,5 +1,2 @@ CONFIG_RCU_TORTURE_TEST=y CONFIG_PRINTK_TIME=y -CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y -CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y -CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TINY01 b/tools/testing/selftests/rcutorture/configs/rcu/TINY01 index 0a63e073a00c..6db705e55487 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TINY01 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TINY01 @@ -7,6 +7,7 @@ CONFIG_HZ_PERIODIC=n CONFIG_NO_HZ_IDLE=y CONFIG_NO_HZ_FULL=n CONFIG_RCU_TRACE=n +#CHECK#CONFIG_RCU_STALL_COMMON=n CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_PREEMPT_COUNT=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TINY02 b/tools/testing/selftests/rcutorture/configs/rcu/TINY02 index f1892e0371c9..a59f7686e219 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TINY02 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TINY02 @@ -8,7 +8,8 @@ CONFIG_NO_HZ_IDLE=n CONFIG_NO_HZ_FULL=n CONFIG_RCU_TRACE=y CONFIG_PROVE_LOCKING=y +CONFIG_PROVE_RCU_REPEATEDLY=y #CHECK#CONFIG_PROVE_RCU=y CONFIG_DEBUG_LOCK_ALLOC=y -CONFIG_DEBUG_OBJECTS_RCU_HEAD=n +CONFIG_DEBUG_OBJECTS_RCU_HEAD=y CONFIG_PREEMPT_COUNT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE01 b/tools/testing/selftests/rcutorture/configs/rcu/TREE01 index f572b873c620..359cb258f639 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE01 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE01 @@ -16,3 +16,6 @@ CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_RCU_BOOST=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y +CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y +CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y +CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE02 b/tools/testing/selftests/rcutorture/configs/rcu/TREE02 index ef6a22c44dea..c1ab5926568b 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE02 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE02 @@ -20,3 +20,7 @@ CONFIG_PROVE_LOCKING=n CONFIG_RCU_BOOST=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y +CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y +CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y +CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y +CONFIG_DEBUG_OBJECTS_RCU_HEAD=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE03 b/tools/testing/selftests/rcutorture/configs/rcu/TREE03 index 7a17c503b382..3b93ee544e70 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE03 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE03 @@ -17,3 +17,6 @@ CONFIG_RCU_BOOST=y CONFIG_RCU_KTHREAD_PRIO=2 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y +CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y +CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y +CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 b/tools/testing/selftests/rcutorture/configs/rcu/TREE04 index 17cbe098b115..5af758e783c7 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE04 @@ -19,3 +19,7 @@ CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y +CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y +CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y +CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y +CONFIG_RCU_EQS_DEBUG=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE05 b/tools/testing/selftests/rcutorture/configs/rcu/TREE05 index 1257d3227b1e..d4cdc0d74e16 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE05 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE05 @@ -19,3 +19,6 @@ CONFIG_PROVE_LOCKING=y #CHECK#CONFIG_PROVE_RCU=y CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y +CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y +CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y +CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE06 b/tools/testing/selftests/rcutorture/configs/rcu/TREE06 index d3e456b74cbe..4cb02bd28f08 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE06 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE06 @@ -20,3 +20,6 @@ CONFIG_PROVE_LOCKING=y #CHECK#CONFIG_PROVE_RCU=y CONFIG_DEBUG_OBJECTS_RCU_HEAD=y CONFIG_RCU_EXPERT=y +CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y +CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y +CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE07 b/tools/testing/selftests/rcutorture/configs/rcu/TREE07 index 3956b4131f72..b12a3ea1867e 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE07 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE07 @@ -19,3 +19,6 @@ CONFIG_RCU_NOCB_CPU=n CONFIG_DEBUG_LOCK_ALLOC=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y +CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y +CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y +CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08 b/tools/testing/selftests/rcutorture/configs/rcu/TREE08 index bb9b0c1a23c2..099cc63c6a3b 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08 @@ -17,8 +17,8 @@ CONFIG_RCU_FANOUT_LEAF=2 CONFIG_RCU_NOCB_CPU=y CONFIG_RCU_NOCB_CPU_ALL=y CONFIG_DEBUG_LOCK_ALLOC=n -CONFIG_PROVE_LOCKING=y -#CHECK#CONFIG_PROVE_RCU=y +CONFIG_PROVE_LOCKING=n CONFIG_RCU_BOOST=n CONFIG_DEBUG_OBJECTS_RCU_HEAD=n CONFIG_RCU_EXPERT=y +CONFIG_RCU_EQS_DEBUG=y diff --git a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt index 4e2b1893d40d..364801b1a230 100644 --- a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt +++ b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt @@ -14,6 +14,7 @@ CONFIG_NO_HZ_FULL_SYSIDLE -- Do one. CONFIG_PREEMPT -- Do half. (First three and #8.) CONFIG_PROVE_LOCKING -- Do several, covering CONFIG_DEBUG_LOCK_ALLOC=y and not. CONFIG_PROVE_RCU -- Hardwired to CONFIG_PROVE_LOCKING. +CONFIG_PROVE_RCU_REPEATEDLY -- Do one. CONFIG_RCU_BOOST -- one of PREEMPT_RCU. CONFIG_RCU_KTHREAD_PRIO -- set to 2 for _BOOST testing. CONFIG_RCU_FANOUT -- Cover hierarchy, but overlap with others. @@ -25,7 +26,12 @@ CONFIG_RCU_NOCB_CPU_NONE -- Do one. CONFIG_RCU_NOCB_CPU_ZERO -- Do one. CONFIG_RCU_TRACE -- Do half. CONFIG_SMP -- Need one !SMP for PREEMPT_RCU. -!RCU_EXPERT -- Do a few, but these have to be vanilla configurations. +CONFIG_RCU_EXPERT=n -- Do a few, but these have to be vanilla configurations. +CONFIG_RCU_EQS_DEBUG -- Do at least one for CONFIG_NO_HZ_FULL and not. +CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP -- Do for all but a couple TREE scenarios. +CONFIG_RCU_TORTURE_TEST_SLOW_INIT -- Do for all but a couple TREE scenarios. +CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT -- Do for all but a couple TREE scenarios. + RCU-bh: Do one with PREEMPT and one with !PREEMPT. RCU-sched: Do one with PREEMPT but not BOOST. @@ -72,7 +78,30 @@ CONFIG_RCU_TORTURE_TEST_RUNNABLE Always used in KVM testing. +CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT_DELAY +CONFIG_RCU_TORTURE_TEST_SLOW_INIT_DELAY +CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP_DELAY + + Inspection suffices, ignore. + CONFIG_PREEMPT_RCU CONFIG_TREE_RCU +CONFIG_TINY_RCU + + These are controlled by CONFIG_PREEMPT and/or CONFIG_SMP. + +CONFIG_SPARSE_RCU_POINTER + + Makes sense only for sparse runs, not for kernel builds. + +CONFIG_SRCU +CONFIG_TASKS_RCU + + Selected by CONFIG_RCU_TORTURE_TEST, so cannot disable. + +CONFIG_RCU_TRACE + + Implied by CONFIG_RCU_TRACE for Tree RCU. + - These are controlled by CONFIG_PREEMPT. +boot parameters ignored: TBD diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/.gitignore b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/.gitignore new file mode 100644 index 000000000000..712a3d41a325 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/.gitignore @@ -0,0 +1 @@ +srcu.c diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/Makefile b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/Makefile new file mode 100644 index 000000000000..16b01559fa55 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/Makefile @@ -0,0 +1,16 @@ +all: srcu.c store_buffering + +LINUX_SOURCE = ../../../../../.. + +modified_srcu_input = $(LINUX_SOURCE)/include/linux/srcu.h \ + $(LINUX_SOURCE)/kernel/rcu/srcu.c + +modified_srcu_output = include/linux/srcu.h srcu.c + +include/linux/srcu.h: srcu.c + +srcu.c: modify_srcu.awk Makefile $(modified_srcu_input) + awk -f modify_srcu.awk $(modified_srcu_input) $(modified_srcu_output) + +store_buffering: + @cd tests/store_buffering; make diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/delay.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/delay.h new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/delay.h diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/export.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/export.h new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/export.h diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/mutex.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/mutex.h new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/mutex.h diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/percpu.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/percpu.h new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/percpu.h diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/preempt.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/preempt.h new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/preempt.h diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/rcupdate.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/rcupdate.h new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/rcupdate.h diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/sched.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/sched.h new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/sched.h diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/smp.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/smp.h new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/smp.h diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/workqueue.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/workqueue.h new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/workqueue.h diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/uapi/linux/types.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/uapi/linux/types.h new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/uapi/linux/types.h diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/.gitignore b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/.gitignore new file mode 100644 index 000000000000..1d016e66980a --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/.gitignore @@ -0,0 +1 @@ +srcu.h diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/kconfig.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/kconfig.h new file mode 100644 index 000000000000..f2860dd1b407 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/kconfig.h @@ -0,0 +1 @@ +#include <LINUX_SOURCE/linux/kconfig.h> diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/types.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/types.h new file mode 100644 index 000000000000..4a3d538fef12 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/types.h @@ -0,0 +1,155 @@ +/* + * This header has been modifies to remove definitions of types that + * are defined in standard userspace headers or are problematic for some + * other reason. + */ + +#ifndef _LINUX_TYPES_H +#define _LINUX_TYPES_H + +#define __EXPORTED_HEADERS__ +#include <uapi/linux/types.h> + +#ifndef __ASSEMBLY__ + +#define DECLARE_BITMAP(name, bits) \ + unsigned long name[BITS_TO_LONGS(bits)] + +typedef __u32 __kernel_dev_t; + +/* bsd */ +typedef unsigned char u_char; +typedef unsigned short u_short; +typedef unsigned int u_int; +typedef unsigned long u_long; + +/* sysv */ +typedef unsigned char unchar; +typedef unsigned short ushort; +typedef unsigned int uint; +typedef unsigned long ulong; + +#ifndef __BIT_TYPES_DEFINED__ +#define __BIT_TYPES_DEFINED__ + +typedef __u8 u_int8_t; +typedef __s8 int8_t; +typedef __u16 u_int16_t; +typedef __s16 int16_t; +typedef __u32 u_int32_t; +typedef __s32 int32_t; + +#endif /* !(__BIT_TYPES_DEFINED__) */ + +typedef __u8 uint8_t; +typedef __u16 uint16_t; +typedef __u32 uint32_t; + +/* this is a special 64bit data type that is 8-byte aligned */ +#define aligned_u64 __u64 __attribute__((aligned(8))) +#define aligned_be64 __be64 __attribute__((aligned(8))) +#define aligned_le64 __le64 __attribute__((aligned(8))) + +/** + * The type used for indexing onto a disc or disc partition. + * + * Linux always considers sectors to be 512 bytes long independently + * of the devices real block size. + * + * blkcnt_t is the type of the inode's block count. + */ +#ifdef CONFIG_LBDAF +typedef u64 sector_t; +#else +typedef unsigned long sector_t; +#endif + +/* + * The type of an index into the pagecache. + */ +#define pgoff_t unsigned long + +/* + * A dma_addr_t can hold any valid DMA address, i.e., any address returned + * by the DMA API. + * + * If the DMA API only uses 32-bit addresses, dma_addr_t need only be 32 + * bits wide. Bus addresses, e.g., PCI BARs, may be wider than 32 bits, + * but drivers do memory-mapped I/O to ioremapped kernel virtual addresses, + * so they don't care about the size of the actual bus addresses. + */ +#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT +typedef u64 dma_addr_t; +#else +typedef u32 dma_addr_t; +#endif + +#ifdef CONFIG_PHYS_ADDR_T_64BIT +typedef u64 phys_addr_t; +#else +typedef u32 phys_addr_t; +#endif + +typedef phys_addr_t resource_size_t; + +/* + * This type is the placeholder for a hardware interrupt number. It has to be + * big enough to enclose whatever representation is used by a given platform. + */ +typedef unsigned long irq_hw_number_t; + +typedef struct { + int counter; +} atomic_t; + +#ifdef CONFIG_64BIT +typedef struct { + long counter; +} atomic64_t; +#endif + +struct list_head { + struct list_head *next, *prev; +}; + +struct hlist_head { + struct hlist_node *first; +}; + +struct hlist_node { + struct hlist_node *next, **pprev; +}; + +/** + * struct callback_head - callback structure for use with RCU and task_work + * @next: next update requests in a list + * @func: actual update function to call after the grace period. + * + * The struct is aligned to size of pointer. On most architectures it happens + * naturally due ABI requirements, but some architectures (like CRIS) have + * weird ABI and we need to ask it explicitly. + * + * The alignment is required to guarantee that bits 0 and 1 of @next will be + * clear under normal conditions -- as long as we use call_rcu(), + * call_rcu_bh(), call_rcu_sched(), or call_srcu() to queue callback. + * + * This guarantee is important for few reasons: + * - future call_rcu_lazy() will make use of lower bits in the pointer; + * - the structure shares storage spacer in struct page with @compound_head, + * which encode PageTail() in bit 0. The guarantee is needed to avoid + * false-positive PageTail(). + */ +struct callback_head { + struct callback_head *next; + void (*func)(struct callback_head *head); +} __attribute__((aligned(sizeof(void *)))); +#define rcu_head callback_head + +typedef void (*rcu_callback_t)(struct rcu_head *head); +typedef void (*call_rcu_func_t)(struct rcu_head *head, rcu_callback_t func); + +/* clocksource cycle base type */ +typedef u64 cycle_t; + +#endif /* __ASSEMBLY__ */ +#endif /* _LINUX_TYPES_H */ diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/modify_srcu.awk b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/modify_srcu.awk new file mode 100755 index 000000000000..8ff89043d0a9 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/modify_srcu.awk @@ -0,0 +1,375 @@ +#!/bin/awk -f + +# Modify SRCU for formal verification. The first argument should be srcu.h and +# the second should be srcu.c. Outputs modified srcu.h and srcu.c into the +# current directory. + +BEGIN { + if (ARGC != 5) { + print "Usange: input.h input.c output.h output.c" > "/dev/stderr"; + exit 1; + } + h_output = ARGV[3]; + c_output = ARGV[4]; + ARGC = 3; + + # Tokenize using FS and not RS as FS supports regular expressions. Each + # record is one line of source, except that backslashed lines are + # combined. Comments are treated as field separators, as are quotes. + quote_regexp="\"([^\\\\\"]|\\\\.)*\""; + comment_regexp="\\/\\*([^*]|\\*+[^*/])*\\*\\/|\\/\\/.*(\n|$)"; + FS="([ \\\\\t\n\v\f;,.=(){}+*/<>&|^-]|\\[|\\]|" comment_regexp "|" quote_regexp ")+"; + + inside_srcu_struct = 0; + inside_srcu_init_def = 0; + srcu_init_param_name = ""; + in_macro = 0; + brace_nesting = 0; + paren_nesting = 0; + + # Allow the manipulation of the last field separator after has been + # seen. + last_fs = ""; + # Whether the last field separator was intended to be output. + last_fs_print = 0; + + # rcu_batches stores the initialization for each instance of struct + # rcu_batch + + in_comment = 0; + + outputfile = ""; +} + +{ + prev_outputfile = outputfile; + if (FILENAME ~ /\.h$/) { + outputfile = h_output; + if (FNR != NR) { + print "Incorrect file order" > "/dev/stderr"; + exit 1; + } + } + else + outputfile = c_output; + + if (prev_outputfile && outputfile != prev_outputfile) { + new_outputfile = outputfile; + outputfile = prev_outputfile; + update_fieldsep("", 0); + outputfile = new_outputfile; + } +} + +# Combine the next line into $0. +function combine_line() { + ret = getline next_line; + if (ret == 0) { + # Don't allow two consecutive getlines at the end of the file + if (eof_found) { + print "Error: expected more input." > "/dev/stderr"; + exit 1; + } else { + eof_found = 1; + } + } else if (ret == -1) { + print "Error reading next line of file" FILENAME > "/dev/stderr"; + exit 1; + } + $0 = $0 "\n" next_line; +} + +# Combine backslashed lines and multiline comments. +function combine_backslashes() { + while (/\\$|\/\*([^*]|\*+[^*\/])*\**$/) { + combine_line(); + } +} + +function read_line() { + combine_line(); + combine_backslashes(); +} + +# Print out field separators and update variables that depend on them. Only +# print if p is true. Call with sep="" and p=0 to print out the last field +# separator. +function update_fieldsep(sep, p) { + # Count braces + sep_tmp = sep; + gsub(quote_regexp "|" comment_regexp, "", sep_tmp); + while (1) + { + if (sub("[^{}()]*\\{", "", sep_tmp)) { + brace_nesting++; + continue; + } + if (sub("[^{}()]*\\}", "", sep_tmp)) { + brace_nesting--; + if (brace_nesting < 0) { + print "Unbalanced braces!" > "/dev/stderr"; + exit 1; + } + continue; + } + if (sub("[^{}()]*\\(", "", sep_tmp)) { + paren_nesting++; + continue; + } + if (sub("[^{}()]*\\)", "", sep_tmp)) { + paren_nesting--; + if (paren_nesting < 0) { + print "Unbalanced parenthesis!" > "/dev/stderr"; + exit 1; + } + continue; + } + + break; + } + + if (last_fs_print) + printf("%s", last_fs) > outputfile; + last_fs = sep; + last_fs_print = p; +} + +# Shifts the fields down by n positions. Calls next if there are no more. If p +# is true then print out field separators. +function shift_fields(n, p) { + do { + if (match($0, FS) > 0) { + update_fieldsep(substr($0, RSTART, RLENGTH), p); + if (RSTART + RLENGTH <= length()) + $0 = substr($0, RSTART + RLENGTH); + else + $0 = ""; + } else { + update_fieldsep("", 0); + print "" > outputfile; + next; + } + } while (--n > 0); +} + +# Shifts and prints the first n fields. +function print_fields(n) { + do { + update_fieldsep("", 0); + printf("%s", $1) > outputfile; + shift_fields(1, 1); + } while (--n > 0); +} + +{ + combine_backslashes(); +} + +# Print leading FS +{ + if (match($0, "^(" FS ")+") > 0) { + update_fieldsep(substr($0, RSTART, RLENGTH), 1); + if (RSTART + RLENGTH <= length()) + $0 = substr($0, RSTART + RLENGTH); + else + $0 = ""; + } +} + +# Parse the line. +{ + while (NF > 0) { + if ($1 == "struct" && NF < 3) { + read_line(); + continue; + } + + if (FILENAME ~ /\.h$/ && !inside_srcu_struct && + brace_nesting == 0 && paren_nesting == 0 && + $1 == "struct" && $2 == "srcu_struct" && + $0 ~ "^struct(" FS ")+srcu_struct(" FS ")+\\{") { + inside_srcu_struct = 1; + print_fields(2); + continue; + } + if (inside_srcu_struct && brace_nesting == 0 && + paren_nesting == 0) { + inside_srcu_struct = 0; + update_fieldsep("", 0); + for (name in rcu_batches) + print "extern struct rcu_batch " name ";" > outputfile; + } + + if (inside_srcu_struct && $1 == "struct" && $2 == "rcu_batch") { + # Move rcu_batches outside of the struct. + rcu_batches[$3] = ""; + shift_fields(3, 1); + sub(/;[[:space:]]*$/, "", last_fs); + continue; + } + + if (FILENAME ~ /\.h$/ && !inside_srcu_init_def && + $1 == "#define" && $2 == "__SRCU_STRUCT_INIT") { + inside_srcu_init_def = 1; + srcu_init_param_name = $3; + in_macro = 1; + print_fields(3); + continue; + } + if (inside_srcu_init_def && brace_nesting == 0 && + paren_nesting == 0) { + inside_srcu_init_def = 0; + in_macro = 0; + continue; + } + + if (inside_srcu_init_def && brace_nesting == 1 && + paren_nesting == 0 && last_fs ~ /\.[[:space:]]*$/ && + $1 ~ /^[[:alnum:]_]+$/) { + name = $1; + if (name in rcu_batches) { + # Remove the dot. + sub(/\.[[:space:]]*$/, "", last_fs); + + old_record = $0; + do + shift_fields(1, 0); + while (last_fs !~ /,/ || paren_nesting > 0); + end_loc = length(old_record) - length($0); + end_loc += index(last_fs, ",") - length(last_fs); + + last_fs = substr(last_fs, index(last_fs, ",") + 1); + last_fs_print = 1; + + match(old_record, "^"name"("FS")+="); + start_loc = RSTART + RLENGTH; + + len = end_loc - start_loc; + initializer = substr(old_record, start_loc, len); + gsub(srcu_init_param_name "\\.", "", initializer); + rcu_batches[name] = initializer; + continue; + } + } + + # Don't include a nonexistent file + if (!in_macro && $1 == "#include" && /^#include[[:space:]]+"rcu\.h"/) { + update_fieldsep("", 0); + next; + } + + # Ignore most preprocessor stuff. + if (!in_macro && $1 ~ /#/) { + break; + } + + if (brace_nesting > 0 && $1 ~ "^[[:alnum:]_]+$" && NF < 2) { + read_line(); + continue; + } + if (brace_nesting > 0 && + $0 ~ "^[[:alnum:]_]+[[:space:]]*(\\.|->)[[:space:]]*[[:alnum:]_]+" && + $2 in rcu_batches) { + # Make uses of rcu_batches global. Somewhat unreliable. + shift_fields(1, 0); + print_fields(1); + continue; + } + + if ($1 == "static" && NF < 3) { + read_line(); + continue; + } + if ($1 == "static" && ($2 == "bool" && $3 == "try_check_zero" || + $2 == "void" && $3 == "srcu_flip")) { + shift_fields(1, 1); + print_fields(2); + continue; + } + + # Distinguish between read-side and write-side memory barriers. + if ($1 == "smp_mb" && NF < 2) { + read_line(); + continue; + } + if (match($0, /^smp_mb[[:space:]();\/*]*[[:alnum:]]/)) { + barrier_letter = substr($0, RLENGTH, 1); + if (barrier_letter ~ /A|D/) + new_barrier_name = "sync_smp_mb"; + else if (barrier_letter ~ /B|C/) + new_barrier_name = "rs_smp_mb"; + else { + print "Unrecognized memory barrier." > "/dev/null"; + exit 1; + } + + shift_fields(1, 1); + printf("%s", new_barrier_name) > outputfile; + continue; + } + + # Skip definition of rcu_synchronize, since it is already + # defined in misc.h. Only present in old versions of srcu. + if (brace_nesting == 0 && paren_nesting == 0 && + $1 == "struct" && $2 == "rcu_synchronize" && + $0 ~ "^struct(" FS ")+rcu_synchronize(" FS ")+\\{") { + shift_fields(2, 0); + while (brace_nesting) { + if (NF < 2) + read_line(); + shift_fields(1, 0); + } + } + + # Skip definition of wakeme_after_rcu for the same reason + if (brace_nesting == 0 && $1 == "static" && $2 == "void" && + $3 == "wakeme_after_rcu") { + while (NF < 5) + read_line(); + shift_fields(3, 0); + do { + while (NF < 3) + read_line(); + shift_fields(1, 0); + } while (paren_nesting || brace_nesting); + } + + if ($1 ~ /^(unsigned|long)$/ && NF < 3) { + read_line(); + continue; + } + + # Give srcu_batches_completed the correct type for old SRCU. + if (brace_nesting == 0 && $1 == "long" && + $2 == "srcu_batches_completed") { + update_fieldsep("", 0); + printf("unsigned ") > outputfile; + print_fields(2); + continue; + } + if (brace_nesting == 0 && $1 == "unsigned" && $2 == "long" && + $3 == "srcu_batches_completed") { + print_fields(3); + continue; + } + + # Just print out the input code by default. + print_fields(1); + } + update_fieldsep("", 0); + print > outputfile; + next; +} + +END { + update_fieldsep("", 0); + + if (brace_nesting != 0) { + print "Unbalanced braces!" > "/dev/stderr"; + exit 1; + } + + # Define the rcu_batches + for (name in rcu_batches) + print "struct rcu_batch " name " = " rcu_batches[name] ";" > c_output; +} diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/assume.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/assume.h new file mode 100644 index 000000000000..a64955447995 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/assume.h @@ -0,0 +1,16 @@ +#ifndef ASSUME_H +#define ASSUME_H + +/* Provide an assumption macro that can be disabled for gcc. */ +#ifdef RUN +#define assume(x) \ + do { \ + /* Evaluate x to suppress warnings. */ \ + (void) (x); \ + } while (0) + +#else +#define assume(x) __CPROVER_assume(x) +#endif + +#endif diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/barriers.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/barriers.h new file mode 100644 index 000000000000..6687acc08e6d --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/barriers.h @@ -0,0 +1,41 @@ +#ifndef BARRIERS_H +#define BARRIERS_H + +#define barrier() __asm__ __volatile__("" : : : "memory") + +#ifdef RUN +#define smp_mb() __sync_synchronize() +#define smp_mb__after_unlock_lock() __sync_synchronize() +#else +/* + * Copied from CBMC's implementation of __sync_synchronize(), which + * seems to be disabled by default. + */ +#define smp_mb() __CPROVER_fence("WWfence", "RRfence", "RWfence", "WRfence", \ + "WWcumul", "RRcumul", "RWcumul", "WRcumul") +#define smp_mb__after_unlock_lock() __CPROVER_fence("WWfence", "RRfence", "RWfence", "WRfence", \ + "WWcumul", "RRcumul", "RWcumul", "WRcumul") +#endif + +/* + * Allow memory barriers to be disabled in either the read or write side + * of SRCU individually. + */ + +#ifndef NO_SYNC_SMP_MB +#define sync_smp_mb() smp_mb() +#else +#define sync_smp_mb() do {} while (0) +#endif + +#ifndef NO_READ_SIDE_SMP_MB +#define rs_smp_mb() smp_mb() +#else +#define rs_smp_mb() do {} while (0) +#endif + +#define ACCESS_ONCE(x) (*(volatile typeof(x) *) &(x)) +#define READ_ONCE(x) ACCESS_ONCE(x) +#define WRITE_ONCE(x, val) (ACCESS_ONCE(x) = (val)) + +#endif diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/bug_on.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/bug_on.h new file mode 100644 index 000000000000..2a80e91f78e7 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/bug_on.h @@ -0,0 +1,13 @@ +#ifndef BUG_ON_H +#define BUG_ON_H + +#include <assert.h> + +#define BUG() assert(0) +#define BUG_ON(x) assert(!(x)) + +/* Does it make sense to treat warnings as errors? */ +#define WARN() BUG() +#define WARN_ON(x) (BUG_ON(x), false) + +#endif diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/combined_source.c b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/combined_source.c new file mode 100644 index 000000000000..29eb5d2697ed --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/combined_source.c @@ -0,0 +1,13 @@ +#include <config.h> + +/* Include all source files. */ + +#include "include_srcu.c" + +#include "preempt.c" +#include "misc.c" + +/* Used by test.c files */ +#include <pthread.h> +#include <stdlib.h> +#include <linux/srcu.h> diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/config.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/config.h new file mode 100644 index 000000000000..a60038aeea7a --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/config.h @@ -0,0 +1,27 @@ +/* "Cheater" definitions based on restricted Kconfig choices. */ + +#undef CONFIG_TINY_RCU +#undef __CHECKER__ +#undef CONFIG_DEBUG_LOCK_ALLOC +#undef CONFIG_DEBUG_OBJECTS_RCU_HEAD +#undef CONFIG_HOTPLUG_CPU +#undef CONFIG_MODULES +#undef CONFIG_NO_HZ_FULL_SYSIDLE +#undef CONFIG_PREEMPT_COUNT +#undef CONFIG_PREEMPT_RCU +#undef CONFIG_PROVE_RCU +#undef CONFIG_RCU_NOCB_CPU +#undef CONFIG_RCU_NOCB_CPU_ALL +#undef CONFIG_RCU_STALL_COMMON +#undef CONFIG_RCU_TRACE +#undef CONFIG_RCU_USER_QS +#undef CONFIG_TASKS_RCU +#define CONFIG_TREE_RCU + +#define CONFIG_GENERIC_ATOMIC64 + +#if NR_CPUS > 1 +#define CONFIG_SMP +#else +#undef CONFIG_SMP +#endif diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/include_srcu.c b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/include_srcu.c new file mode 100644 index 000000000000..5ec582a53018 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/include_srcu.c @@ -0,0 +1,31 @@ +#include <config.h> + +#include <assert.h> +#include <errno.h> +#include <inttypes.h> +#include <pthread.h> +#include <stddef.h> +#include <string.h> +#include <sys/types.h> + +#include "int_typedefs.h" + +#include "barriers.h" +#include "bug_on.h" +#include "locks.h" +#include "misc.h" +#include "preempt.h" +#include "percpu.h" +#include "workqueues.h" + +#ifdef USE_SIMPLE_SYNC_SRCU +#define synchronize_srcu(sp) synchronize_srcu_original(sp) +#endif + +#include <srcu.c> + +#ifdef USE_SIMPLE_SYNC_SRCU +#undef synchronize_srcu + +#include "simple_sync_srcu.c" +#endif diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/int_typedefs.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/int_typedefs.h new file mode 100644 index 000000000000..3aad63917858 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/int_typedefs.h @@ -0,0 +1,33 @@ +#ifndef INT_TYPEDEFS_H +#define INT_TYPEDEFS_H + +#include <inttypes.h> + +typedef int8_t s8; +typedef uint8_t u8; +typedef int16_t s16; +typedef uint16_t u16; +typedef int32_t s32; +typedef uint32_t u32; +typedef int64_t s64; +typedef uint64_t u64; + +typedef int8_t __s8; +typedef uint8_t __u8; +typedef int16_t __s16; +typedef uint16_t __u16; +typedef int32_t __s32; +typedef uint32_t __u32; +typedef int64_t __s64; +typedef uint64_t __u64; + +#define S8_C(x) INT8_C(x) +#define U8_C(x) UINT8_C(x) +#define S16_C(x) INT16_C(x) +#define U16_C(x) UINT16_C(x) +#define S32_C(x) INT32_C(x) +#define U32_C(x) UINT32_C(x) +#define S64_C(x) INT64_C(x) +#define U64_C(x) UINT64_C(x) + +#endif diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/locks.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/locks.h new file mode 100644 index 000000000000..356004665576 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/locks.h @@ -0,0 +1,220 @@ +#ifndef LOCKS_H +#define LOCKS_H + +#include <limits.h> +#include <pthread.h> +#include <stdbool.h> + +#include "assume.h" +#include "bug_on.h" +#include "preempt.h" + +int nondet_int(void); + +#define __acquire(x) +#define __acquires(x) +#define __release(x) +#define __releases(x) + +/* Only use one lock mechanism. Select which one. */ +#ifdef PTHREAD_LOCK +struct lock_impl { + pthread_mutex_t mutex; +}; + +static inline void lock_impl_lock(struct lock_impl *lock) +{ + BUG_ON(pthread_mutex_lock(&lock->mutex)); +} + +static inline void lock_impl_unlock(struct lock_impl *lock) +{ + BUG_ON(pthread_mutex_unlock(&lock->mutex)); +} + +static inline bool lock_impl_trylock(struct lock_impl *lock) +{ + int err = pthread_mutex_trylock(&lock->mutex); + + if (!err) + return true; + else if (err == EBUSY) + return false; + BUG(); +} + +static inline void lock_impl_init(struct lock_impl *lock) +{ + pthread_mutex_init(&lock->mutex, NULL); +} + +#define LOCK_IMPL_INITIALIZER {.mutex = PTHREAD_MUTEX_INITIALIZER} + +#else /* !defined(PTHREAD_LOCK) */ +/* Spinlock that assumes that it always gets the lock immediately. */ + +struct lock_impl { + bool locked; +}; + +static inline bool lock_impl_trylock(struct lock_impl *lock) +{ +#ifdef RUN + /* TODO: Should this be a test and set? */ + return __sync_bool_compare_and_swap(&lock->locked, false, true); +#else + __CPROVER_atomic_begin(); + bool old_locked = lock->locked; + lock->locked = true; + __CPROVER_atomic_end(); + + /* Minimal barrier to prevent accesses leaking out of lock. */ + __CPROVER_fence("RRfence", "RWfence"); + + return !old_locked; +#endif +} + +static inline void lock_impl_lock(struct lock_impl *lock) +{ + /* + * CBMC doesn't support busy waiting, so just assume that the + * lock is available. + */ + assume(lock_impl_trylock(lock)); + + /* + * If the lock was already held by this thread then the assumption + * is unsatisfiable (deadlock). + */ +} + +static inline void lock_impl_unlock(struct lock_impl *lock) +{ +#ifdef RUN + BUG_ON(!__sync_bool_compare_and_swap(&lock->locked, true, false)); +#else + /* Minimal barrier to prevent accesses leaking out of lock. */ + __CPROVER_fence("RWfence", "WWfence"); + + __CPROVER_atomic_begin(); + bool old_locked = lock->locked; + lock->locked = false; + __CPROVER_atomic_end(); + + BUG_ON(!old_locked); +#endif +} + +static inline void lock_impl_init(struct lock_impl *lock) +{ + lock->locked = false; +} + +#define LOCK_IMPL_INITIALIZER {.locked = false} + +#endif /* !defined(PTHREAD_LOCK) */ + +/* + * Implement spinlocks using the lock mechanism. Wrap the lock to prevent mixing + * locks of different types. + */ +typedef struct { + struct lock_impl internal_lock; +} spinlock_t; + +#define SPIN_LOCK_UNLOCKED {.internal_lock = LOCK_IMPL_INITIALIZER} +#define __SPIN_LOCK_UNLOCKED(x) SPIN_LOCK_UNLOCKED +#define DEFINE_SPINLOCK(x) spinlock_t x = SPIN_LOCK_UNLOCKED + +static inline void spin_lock_init(spinlock_t *lock) +{ + lock_impl_init(&lock->internal_lock); +} + +static inline void spin_lock(spinlock_t *lock) +{ + /* + * Spin locks also need to be removed in order to eliminate all + * memory barriers. They are only used by the write side anyway. + */ +#ifndef NO_SYNC_SMP_MB + preempt_disable(); + lock_impl_lock(&lock->internal_lock); +#endif +} + +static inline void spin_unlock(spinlock_t *lock) +{ +#ifndef NO_SYNC_SMP_MB + lock_impl_unlock(&lock->internal_lock); + preempt_enable(); +#endif +} + +/* Don't bother with interrupts */ +#define spin_lock_irq(lock) spin_lock(lock) +#define spin_unlock_irq(lock) spin_unlock(lock) +#define spin_lock_irqsave(lock, flags) spin_lock(lock) +#define spin_unlock_irqrestore(lock, flags) spin_unlock(lock) + +/* + * This is supposed to return an int, but I think that a bool should work as + * well. + */ +static inline bool spin_trylock(spinlock_t *lock) +{ +#ifndef NO_SYNC_SMP_MB + preempt_disable(); + return lock_impl_trylock(&lock->internal_lock); +#else + return true; +#endif +} + +struct completion { + /* Hopefuly this won't overflow. */ + unsigned int count; +}; + +#define COMPLETION_INITIALIZER(x) {.count = 0} +#define DECLARE_COMPLETION(x) struct completion x = COMPLETION_INITIALIZER(x) +#define DECLARE_COMPLETION_ONSTACK(x) DECLARE_COMPLETION(x) + +static inline void init_completion(struct completion *c) +{ + c->count = 0; +} + +static inline void wait_for_completion(struct completion *c) +{ + unsigned int prev_count = __sync_fetch_and_sub(&c->count, 1); + + assume(prev_count); +} + +static inline void complete(struct completion *c) +{ + unsigned int prev_count = __sync_fetch_and_add(&c->count, 1); + + BUG_ON(prev_count == UINT_MAX); +} + +/* This function probably isn't very useful for CBMC. */ +static inline bool try_wait_for_completion(struct completion *c) +{ + BUG(); +} + +static inline bool completion_done(struct completion *c) +{ + return c->count; +} + +/* TODO: Implement complete_all */ +static inline void complete_all(struct completion *c) +{ + BUG(); +} + +#endif diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/misc.c b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/misc.c new file mode 100644 index 000000000000..ca892e3b2351 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/misc.c @@ -0,0 +1,11 @@ +#include <config.h> + +#include "misc.h" +#include "bug_on.h" + +struct rcu_head; + +void wakeme_after_rcu(struct rcu_head *head) +{ + BUG(); +} diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/misc.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/misc.h new file mode 100644 index 000000000000..aca50030f954 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/misc.h @@ -0,0 +1,58 @@ +#ifndef MISC_H +#define MISC_H + +#include "assume.h" +#include "int_typedefs.h" +#include "locks.h" + +#include <linux/types.h> + +/* Probably won't need to deal with bottom halves. */ +static inline void local_bh_disable(void) {} +static inline void local_bh_enable(void) {} + +#define MODULE_ALIAS(X) +#define module_param(...) +#define EXPORT_SYMBOL_GPL(x) + +#define container_of(ptr, type, member) ({ \ + const typeof(((type *)0)->member) *__mptr = (ptr); \ + (type *)((char *)__mptr - offsetof(type, member)); \ +}) + +#ifndef USE_SIMPLE_SYNC_SRCU +/* Abuse udelay to make sure that busy loops terminate. */ +#define udelay(x) assume(0) + +#else + +/* The simple custom synchronize_srcu is ok with try_check_zero failing. */ +#define udelay(x) do { } while (0) +#endif + +#define trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c) \ + do { } while (0) + +#define notrace + +/* Avoid including rcupdate.h */ +struct rcu_synchronize { + struct rcu_head head; + struct completion completion; +}; + +void wakeme_after_rcu(struct rcu_head *head); + +#define rcu_lock_acquire(a) do { } while (0) +#define rcu_lock_release(a) do { } while (0) +#define rcu_lockdep_assert(c, s) do { } while (0) +#define RCU_LOCKDEP_WARN(c, s) do { } while (0) + +/* Let CBMC non-deterministically choose switch between normal and expedited. */ +bool rcu_gp_is_normal(void); +bool rcu_gp_is_expedited(void); + +/* Do the same for old versions of rcu. */ +#define rcu_expedited (rcu_gp_is_expedited()) + +#endif diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/percpu.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/percpu.h new file mode 100644 index 000000000000..3de5a49de49b --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/percpu.h @@ -0,0 +1,92 @@ +#ifndef PERCPU_H +#define PERCPU_H + +#include <stddef.h> +#include "bug_on.h" +#include "preempt.h" + +#define __percpu + +/* Maximum size of any percpu data. */ +#define PERCPU_OFFSET (4 * sizeof(long)) + +/* Ignore alignment, as CBMC doesn't care about false sharing. */ +#define alloc_percpu(type) __alloc_percpu(sizeof(type), 1) + +static inline void *__alloc_percpu(size_t size, size_t align) +{ + BUG(); + return NULL; +} + +static inline void free_percpu(void *ptr) +{ + BUG(); +} + +#define per_cpu_ptr(ptr, cpu) \ + ((typeof(ptr)) ((char *) (ptr) + PERCPU_OFFSET * cpu)) + +#define __this_cpu_inc(pcp) __this_cpu_add(pcp, 1) +#define __this_cpu_dec(pcp) __this_cpu_sub(pcp, 1) +#define __this_cpu_sub(pcp, n) __this_cpu_add(pcp, -(typeof(pcp)) (n)) + +#define this_cpu_inc(pcp) this_cpu_add(pcp, 1) +#define this_cpu_dec(pcp) this_cpu_sub(pcp, 1) +#define this_cpu_sub(pcp, n) this_cpu_add(pcp, -(typeof(pcp)) (n)) + +/* Make CBMC use atomics to work around bug. */ +#ifdef RUN +#define THIS_CPU_ADD_HELPER(ptr, x) (*(ptr) += (x)) +#else +/* + * Split the atomic into a read and a write so that it has the least + * possible ordering. + */ +#define THIS_CPU_ADD_HELPER(ptr, x) \ + do { \ + typeof(ptr) this_cpu_add_helper_ptr = (ptr); \ + typeof(ptr) this_cpu_add_helper_x = (x); \ + typeof(*ptr) this_cpu_add_helper_temp; \ + __CPROVER_atomic_begin(); \ + this_cpu_add_helper_temp = *(this_cpu_add_helper_ptr); \ + __CPROVER_atomic_end(); \ + this_cpu_add_helper_temp += this_cpu_add_helper_x; \ + __CPROVER_atomic_begin(); \ + *(this_cpu_add_helper_ptr) = this_cpu_add_helper_temp; \ + __CPROVER_atomic_end(); \ + } while (0) +#endif + +/* + * For some reason CBMC needs an atomic operation even though this is percpu + * data. + */ +#define __this_cpu_add(pcp, n) \ + do { \ + BUG_ON(preemptible()); \ + THIS_CPU_ADD_HELPER(per_cpu_ptr(&(pcp), thread_cpu_id), \ + (typeof(pcp)) (n)); \ + } while (0) + +#define this_cpu_add(pcp, n) \ + do { \ + int this_cpu_add_impl_cpu = get_cpu(); \ + THIS_CPU_ADD_HELPER(per_cpu_ptr(&(pcp), this_cpu_add_impl_cpu), \ + (typeof(pcp)) (n)); \ + put_cpu(); \ + } while (0) + +/* + * This will cause a compiler warning because of the cast from char[][] to + * type*. This will cause a compile time error if type is too big. + */ +#define DEFINE_PER_CPU(type, name) \ + char name[NR_CPUS][PERCPU_OFFSET]; \ + typedef char percpu_too_big_##name \ + [sizeof(type) > PERCPU_OFFSET ? -1 : 1] + +#define for_each_possible_cpu(cpu) \ + for ((cpu) = 0; (cpu) < NR_CPUS; ++(cpu)) + +#endif diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/preempt.c b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/preempt.c new file mode 100644 index 000000000000..4f1b068e9b7a --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/preempt.c @@ -0,0 +1,78 @@ +#include <config.h> + +#include "preempt.h" + +#include "assume.h" +#include "locks.h" + +/* Support NR_CPUS of at most 64 */ +#define CPU_PREEMPTION_LOCKS_INIT0 LOCK_IMPL_INITIALIZER +#define CPU_PREEMPTION_LOCKS_INIT1 \ + CPU_PREEMPTION_LOCKS_INIT0, CPU_PREEMPTION_LOCKS_INIT0 +#define CPU_PREEMPTION_LOCKS_INIT2 \ + CPU_PREEMPTION_LOCKS_INIT1, CPU_PREEMPTION_LOCKS_INIT1 +#define CPU_PREEMPTION_LOCKS_INIT3 \ + CPU_PREEMPTION_LOCKS_INIT2, CPU_PREEMPTION_LOCKS_INIT2 +#define CPU_PREEMPTION_LOCKS_INIT4 \ + CPU_PREEMPTION_LOCKS_INIT3, CPU_PREEMPTION_LOCKS_INIT3 +#define CPU_PREEMPTION_LOCKS_INIT5 \ + CPU_PREEMPTION_LOCKS_INIT4, CPU_PREEMPTION_LOCKS_INIT4 + +/* + * Simulate disabling preemption by locking a particular cpu. NR_CPUS + * should be the actual number of cpus, not just the maximum. + */ +struct lock_impl cpu_preemption_locks[NR_CPUS] = { + CPU_PREEMPTION_LOCKS_INIT0 +#if (NR_CPUS - 1) & 1 + , CPU_PREEMPTION_LOCKS_INIT0 +#endif +#if (NR_CPUS - 1) & 2 + , CPU_PREEMPTION_LOCKS_INIT1 +#endif +#if (NR_CPUS - 1) & 4 + , CPU_PREEMPTION_LOCKS_INIT2 +#endif +#if (NR_CPUS - 1) & 8 + , CPU_PREEMPTION_LOCKS_INIT3 +#endif +#if (NR_CPUS - 1) & 16 + , CPU_PREEMPTION_LOCKS_INIT4 +#endif +#if (NR_CPUS - 1) & 32 + , CPU_PREEMPTION_LOCKS_INIT5 +#endif +}; + +#undef CPU_PREEMPTION_LOCKS_INIT0 +#undef CPU_PREEMPTION_LOCKS_INIT1 +#undef CPU_PREEMPTION_LOCKS_INIT2 +#undef CPU_PREEMPTION_LOCKS_INIT3 +#undef CPU_PREEMPTION_LOCKS_INIT4 +#undef CPU_PREEMPTION_LOCKS_INIT5 + +__thread int thread_cpu_id; +__thread int preempt_disable_count; + +void preempt_disable(void) +{ + BUG_ON(preempt_disable_count < 0 || preempt_disable_count == INT_MAX); + + if (preempt_disable_count++) + return; + + thread_cpu_id = nondet_int(); + assume(thread_cpu_id >= 0); + assume(thread_cpu_id < NR_CPUS); + lock_impl_lock(&cpu_preemption_locks[thread_cpu_id]); +} + +void preempt_enable(void) +{ + BUG_ON(preempt_disable_count < 1); + + if (--preempt_disable_count) + return; + + lock_impl_unlock(&cpu_preemption_locks[thread_cpu_id]); +} diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/preempt.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/preempt.h new file mode 100644 index 000000000000..2f95ee0e4dd5 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/preempt.h @@ -0,0 +1,58 @@ +#ifndef PREEMPT_H +#define PREEMPT_H + +#include <stdbool.h> + +#include "bug_on.h" + +/* This flag contains garbage if preempt_disable_count is 0. */ +extern __thread int thread_cpu_id; + +/* Support recursive preemption disabling. */ +extern __thread int preempt_disable_count; + +void preempt_disable(void); +void preempt_enable(void); + +static inline void preempt_disable_notrace(void) +{ + preempt_disable(); +} + +static inline void preempt_enable_no_resched(void) +{ + preempt_enable(); +} + +static inline void preempt_enable_notrace(void) +{ + preempt_enable(); +} + +static inline int preempt_count(void) +{ + return preempt_disable_count; +} + +static inline bool preemptible(void) +{ + return !preempt_count(); +} + +static inline int get_cpu(void) +{ + preempt_disable(); + return thread_cpu_id; +} + +static inline void put_cpu(void) +{ + preempt_enable(); +} + +static inline void might_sleep(void) +{ + BUG_ON(preempt_disable_count); +} + +#endif diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/simple_sync_srcu.c b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/simple_sync_srcu.c new file mode 100644 index 000000000000..ac9cbc62b411 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/simple_sync_srcu.c @@ -0,0 +1,50 @@ +#include <config.h> + +#include <assert.h> +#include <errno.h> +#include <inttypes.h> +#include <pthread.h> +#include <stddef.h> +#include <string.h> +#include <sys/types.h> + +#include "int_typedefs.h" + +#include "barriers.h" +#include "bug_on.h" +#include "locks.h" +#include "misc.h" +#include "preempt.h" +#include "percpu.h" +#include "workqueues.h" + +#include <linux/srcu.h> + +/* Functions needed from modify_srcu.c */ +bool try_check_zero(struct srcu_struct *sp, int idx, int trycount); +void srcu_flip(struct srcu_struct *sp); + +/* Simpler implementation of synchronize_srcu that ignores batching. */ +void synchronize_srcu(struct srcu_struct *sp) +{ + int idx; + /* + * This code assumes that try_check_zero will succeed anyway, + * so there is no point in multiple tries. + */ + const int trycount = 1; + + might_sleep(); + + /* Ignore the lock, as multiple writers aren't working yet anyway. */ + + idx = 1 ^ (sp->completed & 1); + + /* For comments see srcu_advance_batches. */ + + assume(try_check_zero(sp, idx, trycount)); + + srcu_flip(sp); + + assume(try_check_zero(sp, idx^1, trycount)); +} diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/workqueues.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/workqueues.h new file mode 100644 index 000000000000..e58c8dfd3e90 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/workqueues.h @@ -0,0 +1,102 @@ +#ifndef WORKQUEUES_H +#define WORKQUEUES_H + +#include <stdbool.h> + +#include "barriers.h" +#include "bug_on.h" +#include "int_typedefs.h" + +#include <linux/types.h> + +/* Stub workqueue implementation. */ + +struct work_struct; +typedef void (*work_func_t)(struct work_struct *work); +void delayed_work_timer_fn(unsigned long __data); + +struct work_struct { +/* atomic_long_t data; */ + unsigned long data; + + struct list_head entry; + work_func_t func; +#ifdef CONFIG_LOCKDEP + struct lockdep_map lockdep_map; +#endif +}; + +struct timer_list { + struct hlist_node entry; + unsigned long expires; + void (*function)(unsigned long); + unsigned long data; + u32 flags; + int slack; +}; + +struct delayed_work { + struct work_struct work; + struct timer_list timer; + + /* target workqueue and CPU ->timer uses to queue ->work */ + struct workqueue_struct *wq; + int cpu; +}; + + +static inline bool schedule_work(struct work_struct *work) +{ + BUG(); + return true; +} + +static inline bool schedule_work_on(int cpu, struct work_struct *work) +{ + BUG(); + return true; +} + +static inline bool queue_work(struct workqueue_struct *wq, + struct work_struct *work) +{ + BUG(); + return true; +} + +static inline bool queue_delayed_work(struct workqueue_struct *wq, + struct delayed_work *dwork, + unsigned long delay) +{ + BUG(); + return true; +} + +#define INIT_WORK(w, f) \ + do { \ + (w)->data = 0; \ + (w)->func = (f); \ + } while (0) + +#define INIT_DELAYED_WORK(w, f) INIT_WORK(&(w)->work, (f)) + +#define __WORK_INITIALIZER(n, f) { \ + .data = 0, \ + .entry = { &(n).entry, &(n).entry }, \ + .func = f \ + } + +/* Don't bother initializing timer. */ +#define __DELAYED_WORK_INITIALIZER(n, f, tflags) { \ + .work = __WORK_INITIALIZER((n).work, (f)), \ + } + +#define DECLARE_WORK(n, f) \ + struct workqueue_struct n = __WORK_INITIALIZER + +#define DECLARE_DELAYED_WORK(n, f) \ + struct delayed_work n = __DELAYED_WORK_INITIALIZER(n, f, 0) + +#define system_power_efficient_wq ((struct workqueue_struct *) NULL) + +#endif diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/.gitignore b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/.gitignore new file mode 100644 index 000000000000..f47cb2045f13 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/.gitignore @@ -0,0 +1 @@ +*.out diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/Makefile b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/Makefile new file mode 100644 index 000000000000..3a3aee149225 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/Makefile @@ -0,0 +1,11 @@ +CBMC_FLAGS = -I../.. -I../../src -I../../include -I../../empty_includes -32 -pointer-check -mm pso + +all: + for i in ./*.pass; do \ + echo $$i ; \ + CBMC_FLAGS="$(CBMC_FLAGS)" sh ../test_script.sh --should-pass $$i > $$i.out 2>&1 ; \ + done + for i in ./*.fail; do \ + echo $$i ; \ + CBMC_FLAGS="$(CBMC_FLAGS)" sh ../test_script.sh --should-fail $$i > $$i.out 2>&1 ; \ + done diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/assert_end.fail b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/assert_end.fail new file mode 100644 index 000000000000..40c8075919d1 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/assert_end.fail @@ -0,0 +1 @@ +test_cbmc_options="-DASSERT_END" diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force.fail b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force.fail new file mode 100644 index 000000000000..ada5baf0b60d --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force.fail @@ -0,0 +1 @@ +test_cbmc_options="-DFORCE_FAILURE" diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force2.fail b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force2.fail new file mode 100644 index 000000000000..8fe00c8db466 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force2.fail @@ -0,0 +1 @@ +test_cbmc_options="-DFORCE_FAILURE_2" diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force3.fail b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force3.fail new file mode 100644 index 000000000000..612ed6772844 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force3.fail @@ -0,0 +1 @@ +test_cbmc_options="-DFORCE_FAILURE_3" diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/main.pass b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/main.pass new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/main.pass diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/test.c b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/test.c new file mode 100644 index 000000000000..470b1105a112 --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/test.c @@ -0,0 +1,72 @@ +#include <src/combined_source.c> + +int x; +int y; + +int __unbuffered_tpr_x; +int __unbuffered_tpr_y; + +DEFINE_SRCU(ss); + +void rcu_reader(void) +{ + int idx; + +#ifndef FORCE_FAILURE_3 + idx = srcu_read_lock(&ss); +#endif + might_sleep(); + + __unbuffered_tpr_y = READ_ONCE(y); +#ifdef FORCE_FAILURE + srcu_read_unlock(&ss, idx); + idx = srcu_read_lock(&ss); +#endif + WRITE_ONCE(x, 1); + +#ifndef FORCE_FAILURE_3 + srcu_read_unlock(&ss, idx); +#endif + might_sleep(); +} + +void *thread_update(void *arg) +{ + WRITE_ONCE(y, 1); +#ifndef FORCE_FAILURE_2 + synchronize_srcu(&ss); +#endif + might_sleep(); + __unbuffered_tpr_x = READ_ONCE(x); + + return NULL; +} + +void *thread_process_reader(void *arg) +{ + rcu_reader(); + + return NULL; +} + +int main(int argc, char *argv[]) +{ + pthread_t tu; + pthread_t tpr; + + if (pthread_create(&tu, NULL, thread_update, NULL)) + abort(); + if (pthread_create(&tpr, NULL, thread_process_reader, NULL)) + abort(); + if (pthread_join(tu, NULL)) + abort(); + if (pthread_join(tpr, NULL)) + abort(); + assert(__unbuffered_tpr_y != 0 || __unbuffered_tpr_x != 0); + +#ifdef ASSERT_END + assert(0); +#endif + + return 0; +} diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/test_script.sh b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/test_script.sh new file mode 100755 index 000000000000..d1545972a0fa --- /dev/null +++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/test_script.sh @@ -0,0 +1,102 @@ +#!/bin/sh + +# This script expects a mode (either --should-pass or --should-fail) followed by +# an input file. The script uses the following environment variables. The test C +# source file is expected to be named test.c in the directory containing the +# input file. +# +# CBMC: The command to run CBMC. Default: cbmc +# CBMC_FLAGS: Additional flags to pass to CBMC +# NR_CPUS: Number of cpus to run tests with. Default specified by the test +# SYNC_SRCU_MODE: Choose implementation of synchronize_srcu. Defaults to simple. +# kernel: Version included in the linux kernel source. +# simple: Use try_check_zero directly. +# +# The input file is a script that is sourced by this file. It can define any of +# the following variables to configure the test. +# +# test_cbmc_options: Extra options to pass to CBMC. +# min_cpus_fail: Minimum number of CPUs (NR_CPUS) for verification to fail. +# The test is expected to pass if it is run with fewer. (Only +# useful for .fail files) +# default_cpus: Quantity of CPUs to use for the test, if not specified on the +# command line. Default: Larger of 2 and MIN_CPUS_FAIL. + +set -e + +if test "$#" -ne 2; then + echo "Expected one option followed by an input file" 1>&2 + exit 99 +fi + +if test "x$1" = "x--should-pass"; then + should_pass="yes" +elif test "x$1" = "x--should-fail"; then + should_pass="no" +else + echo "Unrecognized argument '$1'" 1>&2 + + # Exit code 99 indicates a hard error. + exit 99 +fi + +CBMC=${CBMC:-cbmc} + +SYNC_SRCU_MODE=${SYNC_SRCU_MODE:-simple} + +case ${SYNC_SRCU_MODE} in +kernel) sync_srcu_mode_flags="" ;; +simple) sync_srcu_mode_flags="-DUSE_SIMPLE_SYNC_SRCU" ;; + +*) + echo "Unrecognized argument '${SYNC_SRCU_MODE}'" 1>&2 + exit 99 + ;; +esac + +min_cpus_fail=1 + +c_file=`dirname "$2"`/test.c + +# Source the input file. +. $2 + +if test ${min_cpus_fail} -gt 2; then + default_default_cpus=${min_cpus_fail} +else + default_default_cpus=2 +fi +default_cpus=${default_cpus:-${default_default_cpus}} +cpus=${NR_CPUS:-${default_cpus}} + +# Check if there are two few cpus to make the test fail. +if test $cpus -lt ${min_cpus_fail:-0}; then + should_pass="yes" +fi + +cbmc_opts="-DNR_CPUS=${cpus} ${sync_srcu_mode_flags} ${test_cbmc_options} ${CBMC_FLAGS}" + +echo "Running CBMC: ${CBMC} ${cbmc_opts} ${c_file}" +if ${CBMC} ${cbmc_opts} "${c_file}"; then + # Verification successful. Make sure that it was supposed to verify. + test "x${should_pass}" = xyes +else + cbmc_exit_status=$? + + # An exit status of 10 indicates a failed verification. + # (see cbmc_parse_optionst::do_bmc in the CBMC source code) + if test ${cbmc_exit_status} -eq 10 && test "x${should_pass}" = xno; then + : + else + echo "CBMC returned ${cbmc_exit_status} exit status" 1>&2 + + # Parse errors have exit status 6. Any other type of error + # should be considered a hard error. + if test ${cbmc_exit_status} -ne 6 && \ + test ${cbmc_exit_status} -ne 10; then + exit 99 + else + exit 1 + fi + fi +fi diff --git a/tools/testing/selftests/seccomp/Makefile b/tools/testing/selftests/seccomp/Makefile index 8401e87e34e1..5fa6fd2246b1 100644 --- a/tools/testing/selftests/seccomp/Makefile +++ b/tools/testing/selftests/seccomp/Makefile @@ -1,10 +1,6 @@ -TEST_PROGS := seccomp_bpf +TEST_GEN_PROGS := seccomp_bpf CFLAGS += -Wl,-no-as-needed -Wall LDFLAGS += -lpthread -all: $(TEST_PROGS) - include ../lib.mk -clean: - $(RM) $(TEST_PROGS) diff --git a/tools/testing/selftests/sigaltstack/Makefile b/tools/testing/selftests/sigaltstack/Makefile index 56af56eda6fa..f68fbf80d8be 100644 --- a/tools/testing/selftests/sigaltstack/Makefile +++ b/tools/testing/selftests/sigaltstack/Makefile @@ -1,8 +1,5 @@ CFLAGS = -Wall -BINARIES = sas -all: $(BINARIES) +TEST_GEN_PROGS = sas include ../lib.mk -clean: - rm -rf $(BINARIES) diff --git a/tools/testing/selftests/sigaltstack/sas.c b/tools/testing/selftests/sigaltstack/sas.c index 1bb01258e559..ccd07343d418 100644 --- a/tools/testing/selftests/sigaltstack/sas.c +++ b/tools/testing/selftests/sigaltstack/sas.c @@ -57,7 +57,7 @@ void my_usr1(int sig, siginfo_t *si, void *u) exit(EXIT_FAILURE); } if (stk.ss_flags != SS_DISABLE) - printf("[FAIL]\tss_flags=%i, should be SS_DISABLE\n", + printf("[FAIL]\tss_flags=%x, should be SS_DISABLE\n", stk.ss_flags); else printf("[OK]\tsigaltstack is disabled in sighandler\n"); @@ -122,7 +122,8 @@ int main(void) if (stk.ss_flags == SS_DISABLE) { printf("[OK]\tInitial sigaltstack state was SS_DISABLE\n"); } else { - printf("[FAIL]\tInitial sigaltstack state was %i; should have been SS_DISABLE\n", stk.ss_flags); + printf("[FAIL]\tInitial sigaltstack state was %x; " + "should have been SS_DISABLE\n", stk.ss_flags); return EXIT_FAILURE; } @@ -165,7 +166,7 @@ int main(void) exit(EXIT_FAILURE); } if (stk.ss_flags != SS_AUTODISARM) { - printf("[FAIL]\tss_flags=%i, should be SS_AUTODISARM\n", + printf("[FAIL]\tss_flags=%x, should be SS_AUTODISARM\n", stk.ss_flags); exit(EXIT_FAILURE); } diff --git a/tools/testing/selftests/size/Makefile b/tools/testing/selftests/size/Makefile index bbd0b5398b61..4685b3e421fc 100644 --- a/tools/testing/selftests/size/Makefile +++ b/tools/testing/selftests/size/Makefile @@ -1,11 +1,5 @@ -all: get_size +CFLAGS := -static -ffreestanding -nostartfiles -s -get_size: get_size.c - $(CC) -static -ffreestanding -nostartfiles -s $< -o $@ - -TEST_PROGS := get_size +TEST_GEN_PROGS := get_size include ../lib.mk - -clean: - $(RM) get_size diff --git a/tools/testing/selftests/splice/Makefile b/tools/testing/selftests/splice/Makefile new file mode 100644 index 000000000000..9fc78e5e5451 --- /dev/null +++ b/tools/testing/selftests/splice/Makefile @@ -0,0 +1,7 @@ +TEST_PROGS := default_file_splice_read.sh +EXTRA := default_file_splice_read +all: $(TEST_PROGS) $(EXTRA) + +include ../lib.mk + +EXTRA_CLEAN := $(EXTRA) diff --git a/tools/testing/selftests/splice/default_file_splice_read.c b/tools/testing/selftests/splice/default_file_splice_read.c new file mode 100644 index 000000000000..01dd6091554c --- /dev/null +++ b/tools/testing/selftests/splice/default_file_splice_read.c @@ -0,0 +1,8 @@ +#define _GNU_SOURCE +#include <fcntl.h> + +int main(int argc, char **argv) +{ + splice(0, 0, 1, 0, 1<<30, 0); + return 0; +} diff --git a/tools/testing/selftests/splice/default_file_splice_read.sh b/tools/testing/selftests/splice/default_file_splice_read.sh new file mode 100755 index 000000000000..1ea2adeabc94 --- /dev/null +++ b/tools/testing/selftests/splice/default_file_splice_read.sh @@ -0,0 +1,7 @@ +#!/bin/sh +n=`./default_file_splice_read </dev/null | wc -c` + +test "$n" = 0 && exit 0 + +echo "default_file_splice_read broken: leaked $n" +exit 1 diff --git a/tools/testing/selftests/sync/Makefile b/tools/testing/selftests/sync/Makefile index 87ac400507c0..4981c6b6d050 100644 --- a/tools/testing/selftests/sync/Makefile +++ b/tools/testing/selftests/sync/Makefile @@ -20,5 +20,4 @@ TESTS += sync_stress_merge.o sync_test: $(OBJS) $(TESTS) -clean: - $(RM) sync_test $(OBJS) $(TESTS) +EXTRA_CLEAN := sync_test $(OBJS) $(TESTS) diff --git a/tools/testing/selftests/timers/Makefile b/tools/testing/selftests/timers/Makefile index 1d5556869137..5fa1d7e9a915 100644 --- a/tools/testing/selftests/timers/Makefile +++ b/tools/testing/selftests/timers/Makefile @@ -1,24 +1,20 @@ -CC = $(CROSS_COMPILE)gcc BUILD_FLAGS = -DKTEST CFLAGS += -O3 -Wl,-no-as-needed -Wall $(BUILD_FLAGS) LDFLAGS += -lrt -lpthread # these are all "safe" tests that don't modify -# system time or require escalated privledges -TEST_PROGS = posix_timers nanosleep nsleep-lat set-timer-lat mqueue-lat \ +# system time or require escalated privileges +TEST_GEN_PROGS = posix_timers nanosleep nsleep-lat set-timer-lat mqueue-lat \ inconsistency-check raw_skew threadtest rtctest -TEST_PROGS_EXTENDED = alarmtimer-suspend valid-adjtimex adjtick change_skew \ +TEST_GEN_PROGS_EXTENDED = alarmtimer-suspend valid-adjtimex adjtick change_skew \ skew_consistency clocksource-switch leap-a-day \ leapcrash set-tai set-2038 set-tz -bins = $(TEST_PROGS) $(TEST_PROGS_EXTENDED) - -all: ${bins} include ../lib.mk -# these tests require escalated privledges +# these tests require escalated privileges # and may modify the system time or trigger # other behavior like suspend run_destructive_tests: run_tests @@ -34,5 +30,3 @@ run_destructive_tests: run_tests ./set-tai ./set-2038 -clean: - rm -f ${bins} diff --git a/tools/testing/selftests/timers/clocksource-switch.c b/tools/testing/selftests/timers/clocksource-switch.c index fd88e3025bed..5ff165373f8b 100644 --- a/tools/testing/selftests/timers/clocksource-switch.c +++ b/tools/testing/selftests/timers/clocksource-switch.c @@ -159,7 +159,7 @@ int main(int argv, char **argc) } - printf("Running Asyncrhonous Switching Tests...\n"); + printf("Running Asynchronous Switching Tests...\n"); pid = fork(); if (!pid) return run_tests(60); diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index bbab7f4664ac..cbb29e41ef2b 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -1,33 +1,31 @@ # Makefile for vm selftests -CFLAGS = -Wall -I ../../../../usr/include $(EXTRA_CFLAGS) -BINARIES = compaction_test -BINARIES += hugepage-mmap -BINARIES += hugepage-shm -BINARIES += map_hugetlb -BINARIES += mlock2-tests -BINARIES += on-fault-limit -BINARIES += thuge-gen -BINARIES += transhuge-stress -BINARIES += userfaultfd -BINARIES += mlock-random-test - -all: $(BINARIES) -%: %.c - $(CC) $(CFLAGS) -o $@ $^ -lrt -userfaultfd: userfaultfd.c ../../../../usr/include/linux/kernel.h - $(CC) $(CFLAGS) -O2 -o $@ $< -lpthread - -mlock-random-test: mlock-random-test.c - $(CC) $(CFLAGS) -o $@ $< -lcap +ifndef OUTPUT + OUTPUT := $(shell pwd) +endif -../../../../usr/include/linux/kernel.h: - make -C ../../../.. headers_install +CFLAGS = -Wall -I ../../../../usr/include $(EXTRA_CFLAGS) +LDLIBS = -lrt +TEST_GEN_FILES = compaction_test +TEST_GEN_FILES += hugepage-mmap +TEST_GEN_FILES += hugepage-shm +TEST_GEN_FILES += map_hugetlb +TEST_GEN_FILES += mlock2-tests +TEST_GEN_FILES += on-fault-limit +TEST_GEN_FILES += thuge-gen +TEST_GEN_FILES += transhuge-stress +TEST_GEN_FILES += userfaultfd +TEST_GEN_FILES += mlock-random-test +TEST_GEN_FILES += virtual_address_range TEST_PROGS := run_vmtests -TEST_FILES := $(BINARIES) include ../lib.mk -clean: - $(RM) $(BINARIES) +$(OUTPUT)/userfaultfd: ../../../../usr/include/linux/kernel.h +$(OUTPUT)/userfaultfd: LDLIBS += -lpthread + +$(OUTPUT)/mlock-random-test: LDLIBS += -lcap + +../../../../usr/include/linux/kernel.h: + make -C ../../../.. headers_install diff --git a/tools/testing/selftests/vm/config b/tools/testing/selftests/vm/config index 698c7ed28a26..1c0d76cb5adf 100644 --- a/tools/testing/selftests/vm/config +++ b/tools/testing/selftests/vm/config @@ -1 +1,2 @@ +CONFIG_SYSVIPC=y CONFIG_USERFAULTFD=y diff --git a/tools/testing/selftests/vm/map_hugetlb.c b/tools/testing/selftests/vm/map_hugetlb.c index addcd6fc1ecc..77687ab59f77 100644 --- a/tools/testing/selftests/vm/map_hugetlb.c +++ b/tools/testing/selftests/vm/map_hugetlb.c @@ -62,7 +62,7 @@ int main(void) void *addr; int ret; - addr = mmap(ADDR, LENGTH, PROTECTION, FLAGS, 0, 0); + addr = mmap(ADDR, LENGTH, PROTECTION, FLAGS, -1, 0); if (addr == MAP_FAILED) { perror("mmap"); exit(1); diff --git a/tools/testing/selftests/vm/mlock2-tests.c b/tools/testing/selftests/vm/mlock2-tests.c index ff0cda2b19c9..e5dbc87b4297 100644 --- a/tools/testing/selftests/vm/mlock2-tests.c +++ b/tools/testing/selftests/vm/mlock2-tests.c @@ -293,7 +293,7 @@ static int test_mlock_lock() unsigned long page_size = getpagesize(); map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE, - MAP_ANONYMOUS | MAP_PRIVATE, 0, 0); + MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); if (map == MAP_FAILED) { perror("test_mlock_locked mmap"); goto out; @@ -402,7 +402,7 @@ static int test_mlock_onfault() unsigned long page_size = getpagesize(); map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE, - MAP_ANONYMOUS | MAP_PRIVATE, 0, 0); + MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); if (map == MAP_FAILED) { perror("test_mlock_locked mmap"); goto out; @@ -445,7 +445,7 @@ static int test_lock_onfault_of_present() uint64_t page1_flags, page2_flags; map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE, - MAP_ANONYMOUS | MAP_PRIVATE, 0, 0); + MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); if (map == MAP_FAILED) { perror("test_mlock_locked mmap"); goto out; @@ -492,7 +492,7 @@ static int test_munlockall() unsigned long page_size = getpagesize(); map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE, - MAP_ANONYMOUS | MAP_PRIVATE, 0, 0); + MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); if (map == MAP_FAILED) { perror("test_munlockall mmap"); @@ -518,7 +518,7 @@ static int test_munlockall() munmap(map, 2 * page_size); map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE, - MAP_ANONYMOUS | MAP_PRIVATE, 0, 0); + MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); if (map == MAP_FAILED) { perror("test_munlockall second mmap"); @@ -573,7 +573,7 @@ static int test_vma_management(bool call_mlock) struct vm_boundaries page3; map = mmap(NULL, 3 * page_size, PROT_READ | PROT_WRITE, - MAP_ANONYMOUS | MAP_PRIVATE, 0, 0); + MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); if (map == MAP_FAILED) { perror("mmap()"); return ret; diff --git a/tools/testing/selftests/vm/on-fault-limit.c b/tools/testing/selftests/vm/on-fault-limit.c index 0ae458f32fdb..7f96a5c2e292 100644 --- a/tools/testing/selftests/vm/on-fault-limit.c +++ b/tools/testing/selftests/vm/on-fault-limit.c @@ -26,7 +26,7 @@ static int test_limit(void) } map = mmap(NULL, 2 * lims.rlim_max, PROT_READ | PROT_WRITE, - MAP_PRIVATE | MAP_ANONYMOUS | MAP_POPULATE, 0, 0); + MAP_PRIVATE | MAP_ANONYMOUS | MAP_POPULATE, -1, 0); if (map != MAP_FAILED) printf("mmap should have failed, but didn't\n"); else { diff --git a/tools/testing/selftests/vm/run_vmtests b/tools/testing/selftests/vm/run_vmtests index e11968b3677e..07548a1fa901 100755 --- a/tools/testing/selftests/vm/run_vmtests +++ b/tools/testing/selftests/vm/run_vmtests @@ -49,9 +49,9 @@ fi mkdir $mnt mount -t hugetlbfs none $mnt -echo "--------------------" +echo "---------------------" echo "running hugepage-mmap" -echo "--------------------" +echo "---------------------" ./hugepage-mmap if [ $? -ne 0 ]; then echo "[FAIL]" @@ -77,9 +77,9 @@ fi echo $shmmax > /proc/sys/kernel/shmmax echo $shmall > /proc/sys/kernel/shmall -echo "--------------------" +echo "-------------------" echo "running map_hugetlb" -echo "--------------------" +echo "-------------------" ./map_hugetlb if [ $? -ne 0 ]; then echo "[FAIL]" @@ -92,10 +92,34 @@ echo "NOTE: The above hugetlb tests provide minimal coverage. Use" echo " https://github.com/libhugetlbfs/libhugetlbfs.git for" echo " hugetlb regression testing." -echo "--------------------" +echo "-------------------" echo "running userfaultfd" -echo "--------------------" -./userfaultfd 128 32 +echo "-------------------" +./userfaultfd anon 128 32 +if [ $? -ne 0 ]; then + echo "[FAIL]" + exitcode=1 +else + echo "[PASS]" +fi + +echo "---------------------------" +echo "running userfaultfd_hugetlb" +echo "---------------------------" +# 256MB total huge pages == 128MB src and 128MB dst +./userfaultfd hugetlb 128 32 $mnt/ufd_test_file +if [ $? -ne 0 ]; then + echo "[FAIL]" + exitcode=1 +else + echo "[PASS]" +fi +rm -f $mnt/ufd_test_file + +echo "-------------------------" +echo "running userfaultfd_shmem" +echo "-------------------------" +./userfaultfd shmem 128 32 if [ $? -ne 0 ]; then echo "[FAIL]" exitcode=1 @@ -119,9 +143,9 @@ else echo "[PASS]" fi -echo "--------------------" +echo "----------------------" echo "running on-fault-limit" -echo "--------------------" +echo "----------------------" sudo -u nobody ./on-fault-limit if [ $? -ne 0 ]; then echo "[FAIL]" @@ -141,4 +165,15 @@ else echo "[PASS]" fi +echo "-----------------------------" +echo "running virtual_address_range" +echo "-----------------------------" +./virtual_address_range +if [ $? -ne 0 ]; then + echo "[FAIL]" + exitcode=1 +else + echo "[PASS]" +fi + exit $exitcode diff --git a/tools/testing/selftests/vm/thuge-gen.c b/tools/testing/selftests/vm/thuge-gen.c index 0bc737a75150..88a2ab535e01 100644 --- a/tools/testing/selftests/vm/thuge-gen.c +++ b/tools/testing/selftests/vm/thuge-gen.c @@ -146,7 +146,7 @@ void test_mmap(unsigned long size, unsigned flags) before = read_free(size); map = mmap(NULL, size*NUM_PAGES, PROT_READ|PROT_WRITE, - MAP_PRIVATE|MAP_ANONYMOUS|MAP_HUGETLB|flags, 0, 0); + MAP_PRIVATE|MAP_ANONYMOUS|MAP_HUGETLB|flags, -1, 0); if (map == (char *)-1) err("mmap"); memset(map, 0xff, size*NUM_PAGES); diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c index d77ed41b2094..1eae79ae5b4e 100644 --- a/tools/testing/selftests/vm/userfaultfd.c +++ b/tools/testing/selftests/vm/userfaultfd.c @@ -63,6 +63,7 @@ #include <sys/mman.h> #include <sys/syscall.h> #include <sys/ioctl.h> +#include <sys/wait.h> #include <pthread.h> #include <linux/userfaultfd.h> @@ -76,8 +77,15 @@ static unsigned long nr_cpus, nr_pages, nr_pages_per_cpu, page_size; #define BOUNCE_POLL (1<<3) static int bounces; +#define TEST_ANON 1 +#define TEST_HUGETLB 2 +#define TEST_SHMEM 3 +static int test_type; + +static int huge_fd; +static char *huge_fd_off0; static unsigned long long *count_verify; -static int uffd, finished, *pipefd; +static int uffd, uffd_flags, finished, *pipefd; static char *area_src, *area_dst; static char *zeropage; pthread_attr_t attr; @@ -97,6 +105,112 @@ pthread_attr_t attr; ~(unsigned long)(sizeof(unsigned long long) \ - 1))) +static int anon_release_pages(char *rel_area) +{ + int ret = 0; + + if (madvise(rel_area, nr_pages * page_size, MADV_DONTNEED)) { + perror("madvise"); + ret = 1; + } + + return ret; +} + +static void anon_allocate_area(void **alloc_area) +{ + if (posix_memalign(alloc_area, page_size, nr_pages * page_size)) { + fprintf(stderr, "out of memory\n"); + *alloc_area = NULL; + } +} + + +/* HugeTLB memory */ +static int hugetlb_release_pages(char *rel_area) +{ + int ret = 0; + + if (fallocate(huge_fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, + rel_area == huge_fd_off0 ? 0 : + nr_pages * page_size, + nr_pages * page_size)) { + perror("fallocate"); + ret = 1; + } + + return ret; +} + + +static void hugetlb_allocate_area(void **alloc_area) +{ + *alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_HUGETLB, huge_fd, + *alloc_area == area_src ? 0 : + nr_pages * page_size); + if (*alloc_area == MAP_FAILED) { + fprintf(stderr, "mmap of hugetlbfs file failed\n"); + *alloc_area = NULL; + } + + if (*alloc_area == area_src) + huge_fd_off0 = *alloc_area; +} + +/* Shared memory */ +static int shmem_release_pages(char *rel_area) +{ + int ret = 0; + + if (madvise(rel_area, nr_pages * page_size, MADV_REMOVE)) { + perror("madvise"); + ret = 1; + } + + return ret; +} + +static void shmem_allocate_area(void **alloc_area) +{ + *alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_SHARED, -1, 0); + if (*alloc_area == MAP_FAILED) { + fprintf(stderr, "shared memory mmap failed\n"); + *alloc_area = NULL; + } +} + +struct uffd_test_ops { + unsigned long expected_ioctls; + void (*allocate_area)(void **alloc_area); + int (*release_pages)(char *rel_area); +}; + +#define ANON_EXPECTED_IOCTLS ((1 << _UFFDIO_WAKE) | \ + (1 << _UFFDIO_COPY) | \ + (1 << _UFFDIO_ZEROPAGE)) + +static struct uffd_test_ops anon_uffd_test_ops = { + .expected_ioctls = ANON_EXPECTED_IOCTLS, + .allocate_area = anon_allocate_area, + .release_pages = anon_release_pages, +}; + +static struct uffd_test_ops shmem_uffd_test_ops = { + .expected_ioctls = UFFD_API_RANGE_IOCTLS_BASIC, + .allocate_area = shmem_allocate_area, + .release_pages = shmem_release_pages, +}; + +static struct uffd_test_ops hugetlb_uffd_test_ops = { + .expected_ioctls = UFFD_API_RANGE_IOCTLS_BASIC, + .allocate_area = hugetlb_allocate_area, + .release_pages = hugetlb_release_pages, +}; + +static struct uffd_test_ops *uffd_test_ops; + static int my_bcmp(char *str1, char *str2, size_t n) { unsigned long i; @@ -217,7 +331,7 @@ static void *locking_thread(void *arg) return NULL; } -static int copy_page(unsigned long offset) +static int copy_page(int ufd, unsigned long offset) { struct uffdio_copy uffdio_copy; @@ -229,7 +343,7 @@ static int copy_page(unsigned long offset) uffdio_copy.len = page_size; uffdio_copy.mode = 0; uffdio_copy.copy = 0; - if (ioctl(uffd, UFFDIO_COPY, &uffdio_copy)) { + if (ioctl(ufd, UFFDIO_COPY, &uffdio_copy)) { /* real retval in ufdio_copy.copy */ if (uffdio_copy.copy != -EEXIST) fprintf(stderr, "UFFDIO_COPY error %Ld\n", @@ -247,6 +361,7 @@ static void *uffd_poll_thread(void *arg) unsigned long cpu = (unsigned long) arg; struct pollfd pollfd[2]; struct uffd_msg msg; + struct uffdio_register uffd_reg; int ret; unsigned long offset; char tmp_chr; @@ -278,16 +393,35 @@ static void *uffd_poll_thread(void *arg) continue; perror("nonblocking read error"), exit(1); } - if (msg.event != UFFD_EVENT_PAGEFAULT) + switch (msg.event) { + default: fprintf(stderr, "unexpected msg event %u\n", msg.event), exit(1); - if (msg.arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE) - fprintf(stderr, "unexpected write fault\n"), exit(1); - offset = (char *)(unsigned long)msg.arg.pagefault.address - - area_dst; - offset &= ~(page_size-1); - if (copy_page(offset)) - userfaults++; + break; + case UFFD_EVENT_PAGEFAULT: + if (msg.arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE) + fprintf(stderr, "unexpected write fault\n"), exit(1); + offset = (char *)(unsigned long)msg.arg.pagefault.address - + area_dst; + offset &= ~(page_size-1); + if (copy_page(uffd, offset)) + userfaults++; + break; + case UFFD_EVENT_FORK: + uffd = msg.arg.fork.ufd; + pollfd[0].fd = uffd; + break; + case UFFD_EVENT_REMOVE: + uffd_reg.range.start = msg.arg.remove.start; + uffd_reg.range.len = msg.arg.remove.end - + msg.arg.remove.start; + if (ioctl(uffd, UFFDIO_UNREGISTER, &uffd_reg.range)) + fprintf(stderr, "remove failure\n"), exit(1); + break; + case UFFD_EVENT_REMAP: + area_dst = (char *)(unsigned long)msg.arg.remap.to; + break; + } } return (void *)userfaults; } @@ -324,7 +458,7 @@ static void *uffd_read_thread(void *arg) offset = (char *)(unsigned long)msg.arg.pagefault.address - area_dst; offset &= ~(page_size-1); - if (copy_page(offset)) + if (copy_page(uffd, offset)) (*this_cpu_userfaults)++; } return (void *)NULL; @@ -338,7 +472,7 @@ static void *background_thread(void *arg) for (page_nr = cpu * nr_pages_per_cpu; page_nr < (cpu+1) * nr_pages_per_cpu; page_nr++) - copy_page(page_nr * page_size); + copy_page(uffd, page_nr * page_size); return NULL; } @@ -384,10 +518,8 @@ static int stress(unsigned long *userfaults) * UFFDIO_COPY without writing zero pages into area_dst * because the background threads already completed). */ - if (madvise(area_src, nr_pages * page_size, MADV_DONTNEED)) { - perror("madvise"); + if (uffd_test_ops->release_pages(area_src)) return 1; - } for (cpu = 0; cpu < nr_cpus; cpu++) { char c; @@ -414,27 +546,9 @@ static int stress(unsigned long *userfaults) return 0; } -static int userfaultfd_stress(void) +static int userfaultfd_open(int features) { - void *area; - char *tmp_area; - unsigned long nr; - struct uffdio_register uffdio_register; struct uffdio_api uffdio_api; - unsigned long cpu; - int uffd_flags, err; - unsigned long userfaults[nr_cpus]; - - if (posix_memalign(&area, page_size, nr_pages * page_size)) { - fprintf(stderr, "out of memory\n"); - return 1; - } - area_src = area; - if (posix_memalign(&area, page_size, nr_pages * page_size)) { - fprintf(stderr, "out of memory\n"); - return 1; - } - area_dst = area; uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK); if (uffd < 0) { @@ -445,7 +559,7 @@ static int userfaultfd_stress(void) uffd_flags = fcntl(uffd, F_GETFD, NULL); uffdio_api.api = UFFD_API; - uffdio_api.features = 0; + uffdio_api.features = features; if (ioctl(uffd, UFFDIO_API, &uffdio_api)) { fprintf(stderr, "UFFDIO_API\n"); return 1; @@ -455,6 +569,235 @@ static int userfaultfd_stress(void) return 1; } + return 0; +} + +/* + * For non-cooperative userfaultfd test we fork() a process that will + * generate pagefaults, will mremap the area monitored by the + * userfaultfd and at last this process will release the monitored + * area. + * For the anonymous and shared memory the area is divided into two + * parts, the first part is accessed before mremap, and the second + * part is accessed after mremap. Since hugetlbfs does not support + * mremap, the entire monitored area is accessed in a single pass for + * HUGETLB_TEST. + * The release of the pages currently generates event for shmem and + * anonymous memory (UFFD_EVENT_REMOVE), hence it is not checked + * for hugetlb. + */ +static int faulting_process(void) +{ + unsigned long nr; + unsigned long long count; + unsigned long split_nr_pages; + + if (test_type != TEST_HUGETLB) + split_nr_pages = (nr_pages + 1) / 2; + else + split_nr_pages = nr_pages; + + for (nr = 0; nr < split_nr_pages; nr++) { + count = *area_count(area_dst, nr); + if (count != count_verify[nr]) { + fprintf(stderr, + "nr %lu memory corruption %Lu %Lu\n", + nr, count, + count_verify[nr]), exit(1); + } + } + + if (test_type == TEST_HUGETLB) + return 0; + + area_dst = mremap(area_dst, nr_pages * page_size, nr_pages * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, area_src); + if (area_dst == MAP_FAILED) + perror("mremap"), exit(1); + + for (; nr < nr_pages; nr++) { + count = *area_count(area_dst, nr); + if (count != count_verify[nr]) { + fprintf(stderr, + "nr %lu memory corruption %Lu %Lu\n", + nr, count, + count_verify[nr]), exit(1); + } + } + + if (uffd_test_ops->release_pages(area_dst)) + return 1; + + for (nr = 0; nr < nr_pages; nr++) { + if (my_bcmp(area_dst + nr * page_size, zeropage, page_size)) + fprintf(stderr, "nr %lu is not zero\n", nr), exit(1); + } + + return 0; +} + +static int uffdio_zeropage(int ufd, unsigned long offset) +{ + struct uffdio_zeropage uffdio_zeropage; + int ret; + unsigned long has_zeropage; + + has_zeropage = uffd_test_ops->expected_ioctls & (1 << _UFFDIO_ZEROPAGE); + + if (offset >= nr_pages * page_size) + fprintf(stderr, "unexpected offset %lu\n", + offset), exit(1); + uffdio_zeropage.range.start = (unsigned long) area_dst + offset; + uffdio_zeropage.range.len = page_size; + uffdio_zeropage.mode = 0; + ret = ioctl(ufd, UFFDIO_ZEROPAGE, &uffdio_zeropage); + if (ret) { + /* real retval in ufdio_zeropage.zeropage */ + if (has_zeropage) { + if (uffdio_zeropage.zeropage == -EEXIST) + fprintf(stderr, "UFFDIO_ZEROPAGE -EEXIST\n"), + exit(1); + else + fprintf(stderr, "UFFDIO_ZEROPAGE error %Ld\n", + uffdio_zeropage.zeropage), exit(1); + } else { + if (uffdio_zeropage.zeropage != -EINVAL) + fprintf(stderr, + "UFFDIO_ZEROPAGE not -EINVAL %Ld\n", + uffdio_zeropage.zeropage), exit(1); + } + } else if (has_zeropage) { + if (uffdio_zeropage.zeropage != page_size) { + fprintf(stderr, "UFFDIO_ZEROPAGE unexpected %Ld\n", + uffdio_zeropage.zeropage), exit(1); + } else + return 1; + } else { + fprintf(stderr, + "UFFDIO_ZEROPAGE succeeded %Ld\n", + uffdio_zeropage.zeropage), exit(1); + } + + return 0; +} + +/* exercise UFFDIO_ZEROPAGE */ +static int userfaultfd_zeropage_test(void) +{ + struct uffdio_register uffdio_register; + unsigned long expected_ioctls; + + printf("testing UFFDIO_ZEROPAGE: "); + fflush(stdout); + + if (uffd_test_ops->release_pages(area_dst)) + return 1; + + if (userfaultfd_open(0) < 0) + return 1; + uffdio_register.range.start = (unsigned long) area_dst; + uffdio_register.range.len = nr_pages * page_size; + uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING; + if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) + fprintf(stderr, "register failure\n"), exit(1); + + expected_ioctls = uffd_test_ops->expected_ioctls; + if ((uffdio_register.ioctls & expected_ioctls) != + expected_ioctls) + fprintf(stderr, + "unexpected missing ioctl for anon memory\n"), + exit(1); + + if (uffdio_zeropage(uffd, 0)) { + if (my_bcmp(area_dst, zeropage, page_size)) + fprintf(stderr, "zeropage is not zero\n"), exit(1); + } + + close(uffd); + printf("done.\n"); + return 0; +} + +static int userfaultfd_events_test(void) +{ + struct uffdio_register uffdio_register; + unsigned long expected_ioctls; + unsigned long userfaults; + pthread_t uffd_mon; + int err, features; + pid_t pid; + char c; + + printf("testing events (fork, remap, remove): "); + fflush(stdout); + + if (uffd_test_ops->release_pages(area_dst)) + return 1; + + features = UFFD_FEATURE_EVENT_FORK | UFFD_FEATURE_EVENT_REMAP | + UFFD_FEATURE_EVENT_REMOVE; + if (userfaultfd_open(features) < 0) + return 1; + fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK); + + uffdio_register.range.start = (unsigned long) area_dst; + uffdio_register.range.len = nr_pages * page_size; + uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING; + if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) + fprintf(stderr, "register failure\n"), exit(1); + + expected_ioctls = uffd_test_ops->expected_ioctls; + if ((uffdio_register.ioctls & expected_ioctls) != + expected_ioctls) + fprintf(stderr, + "unexpected missing ioctl for anon memory\n"), + exit(1); + + if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, NULL)) + perror("uffd_poll_thread create"), exit(1); + + pid = fork(); + if (pid < 0) + perror("fork"), exit(1); + + if (!pid) + return faulting_process(); + + waitpid(pid, &err, 0); + if (err) + fprintf(stderr, "faulting process failed\n"), exit(1); + + if (write(pipefd[1], &c, sizeof(c)) != sizeof(c)) + perror("pipe write"), exit(1); + if (pthread_join(uffd_mon, (void **)&userfaults)) + return 1; + + close(uffd); + printf("userfaults: %ld\n", userfaults); + + return userfaults != nr_pages; +} + +static int userfaultfd_stress(void) +{ + void *area; + char *tmp_area; + unsigned long nr; + struct uffdio_register uffdio_register; + unsigned long cpu; + int err; + unsigned long userfaults[nr_cpus]; + + uffd_test_ops->allocate_area((void **)&area_src); + if (!area_src) + return 1; + uffd_test_ops->allocate_area((void **)&area_dst); + if (!area_dst) + return 1; + + if (userfaultfd_open(0) < 0) + return 1; + count_verify = malloc(nr_pages * sizeof(unsigned long long)); if (!count_verify) { perror("count_verify"); @@ -528,9 +871,7 @@ static int userfaultfd_stress(void) fprintf(stderr, "register failure\n"); return 1; } - expected_ioctls = (1 << _UFFDIO_WAKE) | - (1 << _UFFDIO_COPY) | - (1 << _UFFDIO_ZEROPAGE); + expected_ioctls = uffd_test_ops->expected_ioctls; if ((uffdio_register.ioctls & expected_ioctls) != expected_ioctls) { fprintf(stderr, @@ -562,10 +903,8 @@ static int userfaultfd_stress(void) * MADV_DONTNEED only after the UFFDIO_REGISTER, so it's * required to MADV_DONTNEED here. */ - if (madvise(area_dst, nr_pages * page_size, MADV_DONTNEED)) { - perror("madvise 2"); + if (uffd_test_ops->release_pages(area_dst)) return 1; - } /* bounce pass */ if (stress(userfaults)) @@ -603,30 +942,104 @@ static int userfaultfd_stress(void) printf("\n"); } - return err; + if (err) + return err; + + close(uffd); + return userfaultfd_zeropage_test() || userfaultfd_events_test(); } -int main(int argc, char **argv) +/* + * Copied from mlock2-tests.c + */ +unsigned long default_huge_page_size(void) { - if (argc < 3) - fprintf(stderr, "Usage: <MiB> <bounces>\n"), exit(1); - nr_cpus = sysconf(_SC_NPROCESSORS_ONLN); - page_size = sysconf(_SC_PAGE_SIZE); + unsigned long hps = 0; + char *line = NULL; + size_t linelen = 0; + FILE *f = fopen("/proc/meminfo", "r"); + + if (!f) + return 0; + while (getline(&line, &linelen, f) > 0) { + if (sscanf(line, "Hugepagesize: %lu kB", &hps) == 1) { + hps <<= 10; + break; + } + } + + free(line); + fclose(f); + return hps; +} + +static void set_test_type(const char *type) +{ + if (!strcmp(type, "anon")) { + test_type = TEST_ANON; + uffd_test_ops = &anon_uffd_test_ops; + } else if (!strcmp(type, "hugetlb")) { + test_type = TEST_HUGETLB; + uffd_test_ops = &hugetlb_uffd_test_ops; + } else if (!strcmp(type, "shmem")) { + test_type = TEST_SHMEM; + uffd_test_ops = &shmem_uffd_test_ops; + } else { + fprintf(stderr, "Unknown test type: %s\n", type), exit(1); + } + + if (test_type == TEST_HUGETLB) + page_size = default_huge_page_size(); + else + page_size = sysconf(_SC_PAGE_SIZE); + + if (!page_size) + fprintf(stderr, "Unable to determine page size\n"), + exit(2); if ((unsigned long) area_count(NULL, 0) + sizeof(unsigned long long) * 2 > page_size) fprintf(stderr, "Impossible to run this test\n"), exit(2); - nr_pages_per_cpu = atol(argv[1]) * 1024*1024 / page_size / +} + +int main(int argc, char **argv) +{ + if (argc < 4) + fprintf(stderr, "Usage: <test type> <MiB> <bounces> [hugetlbfs_file]\n"), + exit(1); + + set_test_type(argv[1]); + + nr_cpus = sysconf(_SC_NPROCESSORS_ONLN); + nr_pages_per_cpu = atol(argv[2]) * 1024*1024 / page_size / nr_cpus; if (!nr_pages_per_cpu) { fprintf(stderr, "invalid MiB\n"); fprintf(stderr, "Usage: <MiB> <bounces>\n"), exit(1); } - bounces = atoi(argv[2]); + + bounces = atoi(argv[3]); if (bounces <= 0) { fprintf(stderr, "invalid bounces\n"); fprintf(stderr, "Usage: <MiB> <bounces>\n"), exit(1); } nr_pages = nr_pages_per_cpu * nr_cpus; + + if (test_type == TEST_HUGETLB) { + if (argc < 5) + fprintf(stderr, "Usage: hugetlb <MiB> <bounces> <hugetlbfs_file>\n"), + exit(1); + huge_fd = open(argv[4], O_CREAT | O_RDWR, 0755); + if (huge_fd < 0) { + fprintf(stderr, "Open of %s failed", argv[3]); + perror("open"); + exit(1); + } + if (ftruncate(huge_fd, 0)) { + fprintf(stderr, "ftruncate %s to size 0 failed", argv[3]); + perror("ftruncate"); + exit(1); + } + } printf("nr_pages: %lu, nr_pages_per_cpu: %lu\n", nr_pages, nr_pages_per_cpu); return userfaultfd_stress(); diff --git a/tools/testing/selftests/vm/virtual_address_range.c b/tools/testing/selftests/vm/virtual_address_range.c new file mode 100644 index 000000000000..3b02aa6eb9da --- /dev/null +++ b/tools/testing/selftests/vm/virtual_address_range.c @@ -0,0 +1,122 @@ +/* + * Copyright 2017, Anshuman Khandual, IBM Corp. + * Licensed under GPLv2. + * + * Works on architectures which support 128TB virtual + * address range and beyond. + */ +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <errno.h> +#include <numaif.h> +#include <sys/mman.h> +#include <sys/time.h> + +/* + * Maximum address range mapped with a single mmap() + * call is little bit more than 16GB. Hence 16GB is + * chosen as the single chunk size for address space + * mapping. + */ +#define MAP_CHUNK_SIZE 17179869184UL /* 16GB */ + +/* + * Address space till 128TB is mapped without any hint + * and is enabled by default. Address space beyond 128TB + * till 512TB is obtained by passing hint address as the + * first argument into mmap() system call. + * + * The process heap address space is divided into two + * different areas one below 128TB and one above 128TB + * till it reaches 512TB. One with size 128TB and the + * other being 384TB. + */ +#define NR_CHUNKS_128TB 8192UL /* Number of 16GB chunks for 128TB */ +#define NR_CHUNKS_384TB 24576UL /* Number of 16GB chunks for 384TB */ + +#define ADDR_MARK_128TB (1UL << 47) /* First address beyond 128TB */ + +static char *hind_addr(void) +{ + int bits = 48 + rand() % 15; + + return (char *) (1UL << bits); +} + +static int validate_addr(char *ptr, int high_addr) +{ + unsigned long addr = (unsigned long) ptr; + + if (high_addr) { + if (addr < ADDR_MARK_128TB) { + printf("Bad address %lx\n", addr); + return 1; + } + return 0; + } + + if (addr > ADDR_MARK_128TB) { + printf("Bad address %lx\n", addr); + return 1; + } + return 0; +} + +static int validate_lower_address_hint(void) +{ + char *ptr; + + ptr = mmap((void *) (1UL << 45), MAP_CHUNK_SIZE, PROT_READ | + PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + + if (ptr == MAP_FAILED) + return 0; + + return 1; +} + +int main(int argc, char *argv[]) +{ + char *ptr[NR_CHUNKS_128TB]; + char *hptr[NR_CHUNKS_384TB]; + char *hint; + unsigned long i, lchunks, hchunks; + + for (i = 0; i < NR_CHUNKS_128TB; i++) { + ptr[i] = mmap(NULL, MAP_CHUNK_SIZE, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + + if (ptr[i] == MAP_FAILED) { + if (validate_lower_address_hint()) + return 1; + break; + } + + if (validate_addr(ptr[i], 0)) + return 1; + } + lchunks = i; + + for (i = 0; i < NR_CHUNKS_384TB; i++) { + hint = hind_addr(); + hptr[i] = mmap(hint, MAP_CHUNK_SIZE, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + + if (hptr[i] == MAP_FAILED) + break; + + if (validate_addr(hptr[i], 1)) + return 1; + } + hchunks = i; + + for (i = 0; i < lchunks; i++) + munmap(ptr[i], MAP_CHUNK_SIZE); + + for (i = 0; i < hchunks; i++) + munmap(hptr[i], MAP_CHUNK_SIZE); + + return 0; +} diff --git a/tools/testing/selftests/watchdog/watchdog-test.c b/tools/testing/selftests/watchdog/watchdog-test.c index 6983d05097e2..a74c9d739d07 100644 --- a/tools/testing/selftests/watchdog/watchdog-test.c +++ b/tools/testing/selftests/watchdog/watchdog-test.c @@ -24,9 +24,11 @@ const char v = 'V'; static void keep_alive(void) { int dummy; + int ret; - printf("."); - ioctl(fd, WDIOC_KEEPALIVE, &dummy); + ret = ioctl(fd, WDIOC_KEEPALIVE, &dummy); + if (!ret) + printf("."); } /* @@ -51,6 +53,7 @@ int main(int argc, char *argv[]) int flags; unsigned int ping_rate = 1; int ret; + int i; setbuf(stdout, NULL); @@ -61,31 +64,35 @@ int main(int argc, char *argv[]) exit(-1); } - if (argc > 1) { - if (!strncasecmp(argv[1], "-d", 2)) { - flags = WDIOS_DISABLECARD; - ioctl(fd, WDIOC_SETOPTIONS, &flags); - printf("Watchdog card disabled.\n"); - goto end; - } else if (!strncasecmp(argv[1], "-e", 2)) { - flags = WDIOS_ENABLECARD; - ioctl(fd, WDIOC_SETOPTIONS, &flags); - printf("Watchdog card enabled.\n"); - goto end; - } else if (!strncasecmp(argv[1], "-t", 2) && argv[2]) { - flags = atoi(argv[2]); - ioctl(fd, WDIOC_SETTIMEOUT, &flags); - printf("Watchdog timeout set to %u seconds.\n", flags); - goto end; - } else if (!strncasecmp(argv[1], "-p", 2) && argv[2]) { - ping_rate = strtoul(argv[2], NULL, 0); - printf("Watchdog ping rate set to %u seconds.\n", ping_rate); - } else { - printf("-d to disable, -e to enable, -t <n> to set " \ - "the timeout,\n-p <n> to set the ping rate, and \n"); - printf("run by itself to tick the card.\n"); - goto end; - } + for (i = 1; i < argc; i++) { + if (!strncasecmp(argv[i], "-d", 2)) { + flags = WDIOS_DISABLECARD; + ret = ioctl(fd, WDIOC_SETOPTIONS, &flags); + if (!ret) + printf("Watchdog card disabled.\n"); + } else if (!strncasecmp(argv[i], "-e", 2)) { + flags = WDIOS_ENABLECARD; + ret = ioctl(fd, WDIOC_SETOPTIONS, &flags); + if (!ret) + printf("Watchdog card enabled.\n"); + } else if (!strncasecmp(argv[i], "-t", 2) && argv[2]) { + flags = atoi(argv[i + 1]); + ret = ioctl(fd, WDIOC_SETTIMEOUT, &flags); + if (!ret) + printf("Watchdog timeout set to %u seconds.\n", flags); + i++; + } else if (!strncasecmp(argv[i], "-p", 2) && argv[2]) { + ping_rate = strtoul(argv[i + 1], NULL, 0); + printf("Watchdog ping rate set to %u seconds.\n", ping_rate); + i++; + } else { + printf("-d to disable, -e to enable, -t <n> to set " + "the timeout,\n-p <n> to set the ping rate, and "); + printf("run by itself to tick the card.\n"); + printf("Parameters are parsed left-to-right in real-time.\n"); + printf("Example: %s -d -t 10 -p 5 -e\n", argv[0]); + goto end; + } } printf("Watchdog Ticking Away!\n"); diff --git a/tools/testing/selftests/x86/.gitignore b/tools/testing/selftests/x86/.gitignore index 15034fef9698..7757f73ff9a3 100644 --- a/tools/testing/selftests/x86/.gitignore +++ b/tools/testing/selftests/x86/.gitignore @@ -1,2 +1,15 @@ *_32 *_64 +single_step_syscall +sysret_ss_attrs +syscall_nt +ptrace_syscall +test_mremap_vdso +check_initial_reg_state +sigreturn +ldt_gdt +iopl +mpx-mini-test +ioperm +protection_keys +test_vdso diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index 8c1cb423cfe6..97f187e2663f 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -5,18 +5,21 @@ include ../lib.mk .PHONY: all all_32 all_64 warn_32bit_failure clean TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt ptrace_syscall test_mremap_vdso \ - check_initial_reg_state sigreturn ldt_gdt iopl \ + check_initial_reg_state sigreturn ldt_gdt iopl mpx-mini-test ioperm \ protection_keys test_vdso TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault test_syscall_vdso unwind_vdso \ test_FCMOV test_FCOMI test_FISTTP \ vdso_restorer -TARGETS_C_64BIT_ONLY := fsgsbase +TARGETS_C_64BIT_ONLY := fsgsbase sysret_rip TARGETS_C_32BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_32BIT_ONLY) TARGETS_C_64BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_64BIT_ONLY) BINARIES_32 := $(TARGETS_C_32BIT_ALL:%=%_32) BINARIES_64 := $(TARGETS_C_64BIT_ALL:%=%_64) +BINARIES_32 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_32)) +BINARIES_64 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_64)) + CFLAGS := -O2 -g -std=gnu99 -pthread -Wall UNAME_M := $(shell uname -m) @@ -37,13 +40,12 @@ all_32: $(BINARIES_32) all_64: $(BINARIES_64) -clean: - $(RM) $(BINARIES_32) $(BINARIES_64) +EXTRA_CLEAN := $(BINARIES_32) $(BINARIES_64) -$(TARGETS_C_32BIT_ALL:%=%_32): %_32: %.c +$(BINARIES_32): $(OUTPUT)/%_32: %.c $(CC) -m32 -o $@ $(CFLAGS) $(EXTRA_CFLAGS) $^ -lrt -ldl -lm -$(TARGETS_C_64BIT_ALL:%=%_64): %_64: %.c +$(BINARIES_64): $(OUTPUT)/%_64: %.c $(CC) -m64 -o $@ $(CFLAGS) $(EXTRA_CFLAGS) $^ -lrt -ldl # x86_64 users should be encouraged to install 32-bit libraries @@ -65,12 +67,12 @@ warn_32bit_failure: endif # Some tests have additional dependencies. -sysret_ss_attrs_64: thunks.S -ptrace_syscall_32: raw_syscall_helper_32.S -test_syscall_vdso_32: thunks_32.S +$(OUTPUT)/sysret_ss_attrs_64: thunks.S +$(OUTPUT)/ptrace_syscall_32: raw_syscall_helper_32.S +$(OUTPUT)/test_syscall_vdso_32: thunks_32.S # check_initial_reg_state is special: it needs a custom entry, and it # needs to be static so that its interpreter doesn't destroy its initial # state. -check_initial_reg_state_32: CFLAGS += -Wl,-ereal_start -static -check_initial_reg_state_64: CFLAGS += -Wl,-ereal_start -static +$(OUTPUT)/check_initial_reg_state_32: CFLAGS += -Wl,-ereal_start -static +$(OUTPUT)/check_initial_reg_state_64: CFLAGS += -Wl,-ereal_start -static diff --git a/tools/testing/selftests/x86/fsgsbase.c b/tools/testing/selftests/x86/fsgsbase.c index 5b2b4b3c634c..b4967d875236 100644 --- a/tools/testing/selftests/x86/fsgsbase.c +++ b/tools/testing/selftests/x86/fsgsbase.c @@ -245,7 +245,7 @@ void do_unexpected_base(void) long ret; asm volatile ("int $0x80" : "=a" (ret) : "a" (243), "b" (low_desc) - : "flags"); + : "r8", "r9", "r10", "r11"); memcpy(&desc, low_desc, sizeof(desc)); munmap(low_desc, sizeof(desc)); diff --git a/tools/testing/selftests/x86/ioperm.c b/tools/testing/selftests/x86/ioperm.c new file mode 100644 index 000000000000..b77313ba2ab1 --- /dev/null +++ b/tools/testing/selftests/x86/ioperm.c @@ -0,0 +1,170 @@ +/* + * ioperm.c - Test case for ioperm(2) + * Copyright (c) 2015 Andrew Lutomirski + */ + +#define _GNU_SOURCE +#include <err.h> +#include <stdio.h> +#include <stdint.h> +#include <signal.h> +#include <setjmp.h> +#include <stdlib.h> +#include <string.h> +#include <errno.h> +#include <unistd.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <stdbool.h> +#include <sched.h> +#include <sys/io.h> + +static int nerrs = 0; + +static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *), + int flags) +{ + struct sigaction sa; + memset(&sa, 0, sizeof(sa)); + sa.sa_sigaction = handler; + sa.sa_flags = SA_SIGINFO | flags; + sigemptyset(&sa.sa_mask); + if (sigaction(sig, &sa, 0)) + err(1, "sigaction"); + +} + +static void clearhandler(int sig) +{ + struct sigaction sa; + memset(&sa, 0, sizeof(sa)); + sa.sa_handler = SIG_DFL; + sigemptyset(&sa.sa_mask); + if (sigaction(sig, &sa, 0)) + err(1, "sigaction"); +} + +static jmp_buf jmpbuf; + +static void sigsegv(int sig, siginfo_t *si, void *ctx_void) +{ + siglongjmp(jmpbuf, 1); +} + +static bool try_outb(unsigned short port) +{ + sethandler(SIGSEGV, sigsegv, SA_RESETHAND); + if (sigsetjmp(jmpbuf, 1) != 0) { + return false; + } else { + asm volatile ("outb %%al, %w[port]" + : : [port] "Nd" (port), "a" (0)); + return true; + } + clearhandler(SIGSEGV); +} + +static void expect_ok(unsigned short port) +{ + if (!try_outb(port)) { + printf("[FAIL]\toutb to 0x%02hx failed\n", port); + exit(1); + } + + printf("[OK]\toutb to 0x%02hx worked\n", port); +} + +static void expect_gp(unsigned short port) +{ + if (try_outb(port)) { + printf("[FAIL]\toutb to 0x%02hx worked\n", port); + exit(1); + } + + printf("[OK]\toutb to 0x%02hx failed\n", port); +} + +int main(void) +{ + cpu_set_t cpuset; + CPU_ZERO(&cpuset); + CPU_SET(0, &cpuset); + if (sched_setaffinity(0, sizeof(cpuset), &cpuset) != 0) + err(1, "sched_setaffinity to CPU 0"); + + expect_gp(0x80); + expect_gp(0xed); + + /* + * Probe for ioperm support. Note that clearing ioperm bits + * works even as nonroot. + */ + printf("[RUN]\tenable 0x80\n"); + if (ioperm(0x80, 1, 1) != 0) { + printf("[OK]\tioperm(0x80, 1, 1) failed (%d) -- try running as root\n", + errno); + return 0; + } + expect_ok(0x80); + expect_gp(0xed); + + printf("[RUN]\tdisable 0x80\n"); + if (ioperm(0x80, 1, 0) != 0) { + printf("[FAIL]\tioperm(0x80, 1, 0) failed (%d)", errno); + return 1; + } + expect_gp(0x80); + expect_gp(0xed); + + /* Make sure that fork() preserves ioperm. */ + if (ioperm(0x80, 1, 1) != 0) { + printf("[FAIL]\tioperm(0x80, 1, 0) failed (%d)", errno); + return 1; + } + + pid_t child = fork(); + if (child == -1) + err(1, "fork"); + + if (child == 0) { + printf("[RUN]\tchild: check that we inherited permissions\n"); + expect_ok(0x80); + expect_gp(0xed); + return 0; + } else { + int status; + if (waitpid(child, &status, 0) != child || + !WIFEXITED(status)) { + printf("[FAIL]\tChild died\n"); + nerrs++; + } else if (WEXITSTATUS(status) != 0) { + printf("[FAIL]\tChild failed\n"); + nerrs++; + } else { + printf("[OK]\tChild succeeded\n"); + } + } + + /* Test the capability checks. */ + + printf("\tDrop privileges\n"); + if (setresuid(1, 1, 1) != 0) { + printf("[WARN]\tDropping privileges failed\n"); + return 0; + } + + printf("[RUN]\tdisable 0x80\n"); + if (ioperm(0x80, 1, 0) != 0) { + printf("[FAIL]\tioperm(0x80, 1, 0) failed (%d)", errno); + return 1; + } + printf("[OK]\tit worked\n"); + + printf("[RUN]\tenable 0x80 again\n"); + if (ioperm(0x80, 1, 1) == 0) { + printf("[FAIL]\tit succeeded but should have failed.\n"); + return 1; + } + printf("[OK]\tit failed\n"); + return 0; +} diff --git a/tools/testing/selftests/x86/ldt_gdt.c b/tools/testing/selftests/x86/ldt_gdt.c index 4af47079cf04..b9a22f18566a 100644 --- a/tools/testing/selftests/x86/ldt_gdt.c +++ b/tools/testing/selftests/x86/ldt_gdt.c @@ -45,6 +45,12 @@ #define AR_DB (1 << 22) #define AR_G (1 << 23) +#ifdef __x86_64__ +# define INT80_CLOBBERS "r8", "r9", "r10", "r11" +#else +# define INT80_CLOBBERS +#endif + static int nerrs; /* Points to an array of 1024 ints, each holding its own index. */ @@ -403,6 +409,51 @@ static void *threadproc(void *ctx) } } +#ifdef __i386__ + +#ifndef SA_RESTORE +#define SA_RESTORER 0x04000000 +#endif + +/* + * The UAPI header calls this 'struct sigaction', which conflicts with + * glibc. Sigh. + */ +struct fake_ksigaction { + void *handler; /* the real type is nasty */ + unsigned long sa_flags; + void (*sa_restorer)(void); + unsigned char sigset[8]; +}; + +static void fix_sa_restorer(int sig) +{ + struct fake_ksigaction ksa; + + if (syscall(SYS_rt_sigaction, sig, NULL, &ksa, 8) == 0) { + /* + * glibc has a nasty bug: it sometimes writes garbage to + * sa_restorer. This interacts quite badly with anything + * that fiddles with SS because it can trigger legacy + * stack switching. Patch it up. See: + * + * https://sourceware.org/bugzilla/show_bug.cgi?id=21269 + */ + if (!(ksa.sa_flags & SA_RESTORER) && ksa.sa_restorer) { + ksa.sa_restorer = NULL; + if (syscall(SYS_rt_sigaction, sig, &ksa, NULL, + sizeof(ksa.sigset)) != 0) + err(1, "rt_sigaction"); + } + } +} +#else +static void fix_sa_restorer(int sig) +{ + /* 64-bit glibc works fine. */ +} +#endif + static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *), int flags) { @@ -414,6 +465,7 @@ static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *), if (sigaction(sig, &sa, 0)) err(1, "sigaction"); + fix_sa_restorer(sig); } static jmp_buf jmpbuf; @@ -588,7 +640,7 @@ static int invoke_set_thread_area(void) asm volatile ("int $0x80" : "=a" (ret), "+m" (low_user_desc) : "a" (243), "b" (low_user_desc) - : "flags"); + : INT80_CLOBBERS); return ret; } @@ -657,7 +709,7 @@ static void test_gdt_invalidation(void) "+a" (eax) : "m" (low_user_desc_clear), [arg1] "r" ((unsigned int)(unsigned long)low_user_desc_clear) - : "flags"); + : INT80_CLOBBERS); if (sel != 0) { result = "FAIL"; @@ -688,7 +740,7 @@ static void test_gdt_invalidation(void) "+a" (eax) : "m" (low_user_desc_clear), [arg1] "r" ((unsigned int)(unsigned long)low_user_desc_clear) - : "flags"); + : INT80_CLOBBERS); if (sel != 0) { result = "FAIL"; @@ -721,7 +773,7 @@ static void test_gdt_invalidation(void) "+a" (eax) : "m" (low_user_desc_clear), [arg1] "r" ((unsigned int)(unsigned long)low_user_desc_clear) - : "flags"); + : INT80_CLOBBERS); #ifdef __x86_64__ syscall(SYS_arch_prctl, ARCH_GET_FS, &new_base); @@ -774,7 +826,7 @@ static void test_gdt_invalidation(void) "+a" (eax) : "m" (low_user_desc_clear), [arg1] "r" ((unsigned int)(unsigned long)low_user_desc_clear) - : "flags"); + : INT80_CLOBBERS); #ifdef __x86_64__ syscall(SYS_arch_prctl, ARCH_GET_GS, &new_base); diff --git a/tools/testing/selftests/x86/mpx-mini-test.c b/tools/testing/selftests/x86/mpx-mini-test.c index 616ee9673339..a8df159a8924 100644 --- a/tools/testing/selftests/x86/mpx-mini-test.c +++ b/tools/testing/selftests/x86/mpx-mini-test.c @@ -404,8 +404,6 @@ void handler(int signum, siginfo_t *si, void *vucontext) dprintf2("info->si_lower: %p\n", __si_bounds_lower(si)); dprintf2("info->si_upper: %p\n", __si_bounds_upper(si)); - check_siginfo_vs_shadow(si); - for (i = 0; i < 8; i++) dprintf3("[%d]: %p\n", i, si_addr_ptr[i]); switch (br_reason) { @@ -416,6 +414,9 @@ void handler(int signum, siginfo_t *si, void *vucontext) exit(5); case 1: /* #BR MPX bounds exception */ /* these are normal and we expect to see them */ + + check_siginfo_vs_shadow(si); + dprintf1("bounds exception (normal): status 0x%jx at %p si_addr: %p\n", status, (void *)ip, si->si_addr); num_bnd_chk++; diff --git a/tools/testing/selftests/x86/protection_keys.c b/tools/testing/selftests/x86/protection_keys.c index df9e0a0cdf29..3237bc010e1c 100644 --- a/tools/testing/selftests/x86/protection_keys.c +++ b/tools/testing/selftests/x86/protection_keys.c @@ -192,7 +192,7 @@ void lots_o_noops_around_write(int *write_to_me) #define SYS_pkey_alloc 381 #define SYS_pkey_free 382 #define REG_IP_IDX REG_EIP -#define si_pkey_offset 0x18 +#define si_pkey_offset 0x14 #else #define SYS_mprotect_key 329 #define SYS_pkey_alloc 330 @@ -462,7 +462,7 @@ void pkey_disable_set(int pkey, int flags) unsigned long syscall_flags = 0; int ret; int pkey_rights; - u32 orig_pkru; + u32 orig_pkru = rdpkru(); dprintf1("START->%s(%d, 0x%x)\n", __func__, pkey, flags); @@ -812,8 +812,6 @@ void setup_hugetlbfs(void) { int err; int fd; - int validated_nr_pages; - int i; char buf[] = "123"; if (geteuid() != 0) { @@ -1116,11 +1114,6 @@ void test_pkey_syscalls_on_non_allocated_pkey(int *ptr, u16 pkey) err = sys_pkey_free(i); pkey_assert(err); - /* not enforced when pkey_get() is not a syscall - err = pkey_get(i, 0); - pkey_assert(err < 0); - */ - err = sys_pkey_free(i); pkey_assert(err); @@ -1133,14 +1126,8 @@ void test_pkey_syscalls_on_non_allocated_pkey(int *ptr, u16 pkey) void test_pkey_syscalls_bad_args(int *ptr, u16 pkey) { int err; - int bad_flag = (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE) + 1; int bad_pkey = NR_PKEYS+99; - /* not enforced when pkey_get() is not a syscall - err = pkey_get(bad_pkey, bad_flag); - pkey_assert(err < 0); - */ - /* pass a known-invalid pkey in: */ err = sys_mprotect_pkey(ptr, PAGE_SIZE, PROT_READ, bad_pkey); pkey_assert(err); @@ -1149,8 +1136,6 @@ void test_pkey_syscalls_bad_args(int *ptr, u16 pkey) /* Assumes that all pkeys other than 'pkey' are unallocated */ void test_pkey_alloc_exhaust(int *ptr, u16 pkey) { - unsigned long flags; - unsigned long init_val; int err; int allocated_pkeys[NR_PKEYS] = {0}; int nr_allocated_pkeys = 0; diff --git a/tools/testing/selftests/x86/ptrace_syscall.c b/tools/testing/selftests/x86/ptrace_syscall.c index b037ce9cf116..eaea92439708 100644 --- a/tools/testing/selftests/x86/ptrace_syscall.c +++ b/tools/testing/selftests/x86/ptrace_syscall.c @@ -58,7 +58,8 @@ static void do_full_int80(struct syscall_args32 *args) asm volatile ("int $0x80" : "+a" (args->nr), "+b" (args->arg0), "+c" (args->arg1), "+d" (args->arg2), - "+S" (args->arg3), "+D" (args->arg4), "+r" (bp)); + "+S" (args->arg3), "+D" (args->arg4), "+r" (bp) + : : "r8", "r9", "r10", "r11"); args->arg5 = bp; #else sys32_helper(args, int80_and_ret); diff --git a/tools/testing/selftests/x86/single_step_syscall.c b/tools/testing/selftests/x86/single_step_syscall.c index 50c26358e8b7..a48da95c18fd 100644 --- a/tools/testing/selftests/x86/single_step_syscall.c +++ b/tools/testing/selftests/x86/single_step_syscall.c @@ -56,9 +56,11 @@ static volatile sig_atomic_t sig_traps; #ifdef __x86_64__ # define REG_IP REG_RIP # define WIDTH "q" +# define INT80_CLOBBERS "r8", "r9", "r10", "r11" #else # define REG_IP REG_EIP # define WIDTH "l" +# define INT80_CLOBBERS #endif static unsigned long get_eflags(void) @@ -140,7 +142,8 @@ int main() printf("[RUN]\tSet TF and check int80\n"); set_eflags(get_eflags() | X86_EFLAGS_TF); - asm volatile ("int $0x80" : "=a" (tmp) : "a" (SYS_getpid)); + asm volatile ("int $0x80" : "=a" (tmp) : "a" (SYS_getpid) + : INT80_CLOBBERS); check_result(); /* diff --git a/tools/testing/selftests/x86/sysret_rip.c b/tools/testing/selftests/x86/sysret_rip.c new file mode 100644 index 000000000000..d85ec5b3671c --- /dev/null +++ b/tools/testing/selftests/x86/sysret_rip.c @@ -0,0 +1,195 @@ +/* + * sigreturn.c - tests that x86 avoids Intel SYSRET pitfalls + * Copyright (c) 2014-2016 Andrew Lutomirski + * + * This program is free software; you can redistribute it and/or modify + * it under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ + +#define _GNU_SOURCE + +#include <stdlib.h> +#include <unistd.h> +#include <stdio.h> +#include <string.h> +#include <inttypes.h> +#include <sys/signal.h> +#include <sys/ucontext.h> +#include <sys/syscall.h> +#include <err.h> +#include <stddef.h> +#include <stdbool.h> +#include <setjmp.h> +#include <sys/user.h> +#include <sys/mman.h> +#include <assert.h> + + +asm ( + ".pushsection \".text\", \"ax\"\n\t" + ".balign 4096\n\t" + "test_page: .globl test_page\n\t" + ".fill 4094,1,0xcc\n\t" + "test_syscall_insn:\n\t" + "syscall\n\t" + ".ifne . - test_page - 4096\n\t" + ".error \"test page is not one page long\"\n\t" + ".endif\n\t" + ".popsection" + ); + +extern const char test_page[]; +static void const *current_test_page_addr = test_page; + +static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *), + int flags) +{ + struct sigaction sa; + memset(&sa, 0, sizeof(sa)); + sa.sa_sigaction = handler; + sa.sa_flags = SA_SIGINFO | flags; + sigemptyset(&sa.sa_mask); + if (sigaction(sig, &sa, 0)) + err(1, "sigaction"); +} + +static void clearhandler(int sig) +{ + struct sigaction sa; + memset(&sa, 0, sizeof(sa)); + sa.sa_handler = SIG_DFL; + sigemptyset(&sa.sa_mask); + if (sigaction(sig, &sa, 0)) + err(1, "sigaction"); +} + +/* State used by our signal handlers. */ +static gregset_t initial_regs; + +static volatile unsigned long rip; + +static void sigsegv_for_sigreturn_test(int sig, siginfo_t *info, void *ctx_void) +{ + ucontext_t *ctx = (ucontext_t*)ctx_void; + + if (rip != ctx->uc_mcontext.gregs[REG_RIP]) { + printf("[FAIL]\tRequested RIP=0x%lx but got RIP=0x%lx\n", + rip, (unsigned long)ctx->uc_mcontext.gregs[REG_RIP]); + fflush(stdout); + _exit(1); + } + + memcpy(&ctx->uc_mcontext.gregs, &initial_regs, sizeof(gregset_t)); + + printf("[OK]\tGot SIGSEGV at RIP=0x%lx\n", rip); +} + +static void sigusr1(int sig, siginfo_t *info, void *ctx_void) +{ + ucontext_t *ctx = (ucontext_t*)ctx_void; + + memcpy(&initial_regs, &ctx->uc_mcontext.gregs, sizeof(gregset_t)); + + /* Set IP and CX to match so that SYSRET can happen. */ + ctx->uc_mcontext.gregs[REG_RIP] = rip; + ctx->uc_mcontext.gregs[REG_RCX] = rip; + + /* R11 and EFLAGS should already match. */ + assert(ctx->uc_mcontext.gregs[REG_EFL] == + ctx->uc_mcontext.gregs[REG_R11]); + + sethandler(SIGSEGV, sigsegv_for_sigreturn_test, SA_RESETHAND); + + return; +} + +static void test_sigreturn_to(unsigned long ip) +{ + rip = ip; + printf("[RUN]\tsigreturn to 0x%lx\n", ip); + raise(SIGUSR1); +} + +static jmp_buf jmpbuf; + +static void sigsegv_for_fallthrough(int sig, siginfo_t *info, void *ctx_void) +{ + ucontext_t *ctx = (ucontext_t*)ctx_void; + + if (rip != ctx->uc_mcontext.gregs[REG_RIP]) { + printf("[FAIL]\tExpected SIGSEGV at 0x%lx but got RIP=0x%lx\n", + rip, (unsigned long)ctx->uc_mcontext.gregs[REG_RIP]); + fflush(stdout); + _exit(1); + } + + siglongjmp(jmpbuf, 1); +} + +static void test_syscall_fallthrough_to(unsigned long ip) +{ + void *new_address = (void *)(ip - 4096); + void *ret; + + printf("[RUN]\tTrying a SYSCALL that falls through to 0x%lx\n", ip); + + ret = mremap((void *)current_test_page_addr, 4096, 4096, + MREMAP_MAYMOVE | MREMAP_FIXED, new_address); + if (ret == MAP_FAILED) { + if (ip <= (1UL << 47) - PAGE_SIZE) { + err(1, "mremap to %p", new_address); + } else { + printf("[OK]\tmremap to %p failed\n", new_address); + return; + } + } + + if (ret != new_address) + errx(1, "mremap malfunctioned: asked for %p but got %p\n", + new_address, ret); + + current_test_page_addr = new_address; + rip = ip; + + if (sigsetjmp(jmpbuf, 1) == 0) { + asm volatile ("call *%[syscall_insn]" :: "a" (SYS_getpid), + [syscall_insn] "rm" (ip - 2)); + errx(1, "[FAIL]\tSyscall trampoline returned"); + } + + printf("[OK]\tWe survived\n"); +} + +int main() +{ + /* + * When the kernel returns from a slow-path syscall, it will + * detect whether SYSRET is appropriate. If it incorrectly + * thinks that SYSRET is appropriate when RIP is noncanonical, + * it'll crash on Intel CPUs. + */ + sethandler(SIGUSR1, sigusr1, 0); + for (int i = 47; i < 64; i++) + test_sigreturn_to(1UL<<i); + + clearhandler(SIGUSR1); + + sethandler(SIGSEGV, sigsegv_for_fallthrough, 0); + + /* One extra test to check that we didn't screw up the mremap logic. */ + test_syscall_fallthrough_to((1UL << 47) - 2*PAGE_SIZE); + + /* These are the interesting cases. */ + for (int i = 47; i < 64; i++) { + test_syscall_fallthrough_to((1UL<<i) - PAGE_SIZE); + test_syscall_fallthrough_to(1UL<<i); + } + + return 0; +} diff --git a/tools/testing/selftests/zram/Makefile b/tools/testing/selftests/zram/Makefile index 29d80346e3eb..c3a87e5f9d36 100644 --- a/tools/testing/selftests/zram/Makefile +++ b/tools/testing/selftests/zram/Makefile @@ -2,8 +2,7 @@ all: TEST_PROGS := zram.sh TEST_FILES := zram01.sh zram02.sh zram_lib.sh +EXTRA_CLEAN := err.log include ../lib.mk -clean: - $(RM) err.log diff --git a/tools/usb/.gitignore b/tools/usb/.gitignore new file mode 100644 index 000000000000..1b7448981435 --- /dev/null +++ b/tools/usb/.gitignore @@ -0,0 +1,2 @@ +ffs-test +testusb diff --git a/tools/usb/ffs-test.c b/tools/usb/ffs-test.c index 88d5e71be044..95dd14648ba5 100644 --- a/tools/usb/ffs-test.c +++ b/tools/usb/ffs-test.c @@ -22,7 +22,7 @@ /* $(CROSS_COMPILE)cc -Wall -Wextra -g -o ffs-test ffs-test.c -lpthread */ -#define _BSD_SOURCE /* for endian.h */ +#define _DEFAULT_SOURCE /* for endian.h */ #include <endian.h> #include <errno.h> @@ -110,16 +110,25 @@ static const struct { struct usb_functionfs_descs_head_v2 header; __le32 fs_count; __le32 hs_count; + __le32 ss_count; struct { struct usb_interface_descriptor intf; struct usb_endpoint_descriptor_no_audio sink; struct usb_endpoint_descriptor_no_audio source; } __attribute__((packed)) fs_descs, hs_descs; + struct { + struct usb_interface_descriptor intf; + struct usb_endpoint_descriptor_no_audio sink; + struct usb_ss_ep_comp_descriptor sink_comp; + struct usb_endpoint_descriptor_no_audio source; + struct usb_ss_ep_comp_descriptor source_comp; + } ss_descs; } __attribute__((packed)) descriptors = { .header = { .magic = cpu_to_le32(FUNCTIONFS_DESCRIPTORS_MAGIC_V2), .flags = cpu_to_le32(FUNCTIONFS_HAS_FS_DESC | - FUNCTIONFS_HAS_HS_DESC), + FUNCTIONFS_HAS_HS_DESC | + FUNCTIONFS_HAS_SS_DESC), .length = cpu_to_le32(sizeof descriptors), }, .fs_count = cpu_to_le32(3), @@ -171,6 +180,45 @@ static const struct { .bInterval = 1, /* NAK every 1 uframe */ }, }, + .ss_count = cpu_to_le32(5), + .ss_descs = { + .intf = { + .bLength = sizeof descriptors.fs_descs.intf, + .bDescriptorType = USB_DT_INTERFACE, + .bNumEndpoints = 2, + .bInterfaceClass = USB_CLASS_VENDOR_SPEC, + .iInterface = 1, + }, + .sink = { + .bLength = sizeof descriptors.hs_descs.sink, + .bDescriptorType = USB_DT_ENDPOINT, + .bEndpointAddress = 1 | USB_DIR_IN, + .bmAttributes = USB_ENDPOINT_XFER_BULK, + .wMaxPacketSize = cpu_to_le16(1024), + }, + .sink_comp = { + .bLength = USB_DT_SS_EP_COMP_SIZE, + .bDescriptorType = USB_DT_SS_ENDPOINT_COMP, + .bMaxBurst = 0, + .bmAttributes = 0, + .wBytesPerInterval = 0, + }, + .source = { + .bLength = sizeof descriptors.hs_descs.source, + .bDescriptorType = USB_DT_ENDPOINT, + .bEndpointAddress = 2 | USB_DIR_OUT, + .bmAttributes = USB_ENDPOINT_XFER_BULK, + .wMaxPacketSize = cpu_to_le16(1024), + .bInterval = 1, /* NAK every 1 uframe */ + }, + .source_comp = { + .bLength = USB_DT_SS_EP_COMP_SIZE, + .bDescriptorType = USB_DT_SS_ENDPOINT_COMP, + .bMaxBurst = 0, + .bmAttributes = 0, + .wBytesPerInterval = 0, + }, + }, }; static size_t descs_to_legacy(void **legacy, const void *descriptors_v2) diff --git a/tools/usb/usbip/README b/tools/usb/usbip/README index 831f49fea3ce..7844490fc603 100644 --- a/tools/usb/usbip/README +++ b/tools/usb/usbip/README @@ -4,10 +4,33 @@ # Copyright (C) 2011 matt mooney <mfm@muteddisk.com> # 2005-2008 Takahiro Hirofuchi +[Overview] +USB/IP protocol allows to pass USB device from server to client over the +network. Server is a machine which provides (shares) a USB device. Client is +a machine which uses USB device provided by server over the network. +The USB device may be either physical device connected to a server or +software entity created on a server using USB gadget subsystem. +Whole project consists of four parts: + + - usbip-vhci + A client side kernel module which provides a virtual USB Host Controller + and allows to import a USB device from a remote machine. + + - usbip-host (stub driver) + A server side module which provides a USB device driver which can be + bound to a physical USB device to make it exportable. + + - usbip-vudc + A server side module which provides a virtual USB Device Controller and allows + to export a USB device created using USB Gadget Subsystem. + + - usbip-utils + A set of userspace tools used to handle connection and management. + Used on both sides. [Requirements] - USB/IP device drivers - Found in the staging directory of the Linux kernel. + Found in the drivers/usb/usbip/ directory of the Linux kernel tree. - libudev >= 2.0 libudev library @@ -36,6 +59,10 @@ [Usage] +On a server side there are two entities which can be shared. +First of them is physical usb device connected to the machine. +To make it available below steps should be executed: + server:# (Physically attach your USB device.) server:# insmod usbip-core.ko @@ -52,6 +79,30 @@ - The USB device 1-2 is now exportable to other hosts! - Use `usbip unbind --busid 1-2' to stop exporting the device. +Second of shareable entities is USB Gadget created using USB Gadget Subsystem +on a server machine. To make it available below steps should be executed: + + server:# (Create your USB gadget) + - Currently the most preferable way of creating a new USB gadget + is ConfigFS Composite Gadget. Please refer to its documentation + for details. + - See vudc_server_example.sh for a short example of USB gadget creation + + server:# insmod usbip-core.ko + server:# insmod usbip-vudc.ko + - To create more than one instance of vudc use num module param + + server:# (Bind gadget to one of available vudc) + - Assign your new gadget to USB/IP UDC + - Using ConfigFS interface you may do this simply by: + server:# cd /sys/kernel/config/usb_gadget/<gadget_name> + server:# echo "usbip-vudc.0" > UDC + + server:# usbipd -D --device + - Start usbip daemon. + +To attach new device to client machine below commands should be used: + client:# insmod usbip-core.ko client:# insmod vhci-hcd.ko @@ -60,6 +111,8 @@ client:# usbip attach --remote <host> --busid 1-2 - Connect the remote USB device. + - When using vudc on a server side busid is really vudc instance name. + For example: usbip-vudc.0 client:# usbip port - Show virtual port status. @@ -191,7 +244,9 @@ Detach the imported device: - See 'Debug Tips' on the project wiki. - http://usbip.wiki.sourceforge.net/how-to-debug-usbip - usbip-host.ko must be bound to the target device. - - See /proc/bus/usb/devices and find "Driver=..." lines of the device. + - See /sys/kernel/debug/usb/devices and find "Driver=..." lines of the device. + - Target USB gadget must be bound to vudc + (using USB gadget susbsys, not usbip bind command) - Shutdown firewall. - usbip now uses TCP port 3240. - Disable SELinux. diff --git a/tools/usb/usbip/libsrc/usbip_common.c b/tools/usb/usbip/libsrc/usbip_common.c index ac73710473de..1517a232ab18 100644 --- a/tools/usb/usbip/libsrc/usbip_common.c +++ b/tools/usb/usbip/libsrc/usbip_common.c @@ -215,9 +215,16 @@ int read_usb_interface(struct usbip_usb_device *udev, int i, struct usbip_usb_interface *uinf) { char busid[SYSFS_BUS_ID_SIZE]; + int size; struct udev_device *sif; - sprintf(busid, "%s:%d.%d", udev->busid, udev->bConfigurationValue, i); + size = snprintf(busid, sizeof(busid), "%s:%d.%d", + udev->busid, udev->bConfigurationValue, i); + if (size < 0 || (unsigned int)size >= sizeof(busid)) { + err("busid length %i >= %lu or < 0", size, + (long unsigned)sizeof(busid)); + return -1; + } sif = udev_device_new_from_subsystem_sysname(udev_context, "usb", busid); if (!sif) { diff --git a/tools/usb/usbip/libsrc/usbip_host_common.c b/tools/usb/usbip/libsrc/usbip_host_common.c index 9d415228883d..6ff7b601f854 100644 --- a/tools/usb/usbip/libsrc/usbip_host_common.c +++ b/tools/usb/usbip/libsrc/usbip_host_common.c @@ -40,13 +40,20 @@ struct udev *udev_context; static int32_t read_attr_usbip_status(struct usbip_usb_device *udev) { char status_attr_path[SYSFS_PATH_MAX]; + int size; int fd; int length; char status; int value = 0; - snprintf(status_attr_path, SYSFS_PATH_MAX, "%s/usbip_status", - udev->path); + size = snprintf(status_attr_path, sizeof(status_attr_path), + "%s/usbip_status", udev->path); + if (size < 0 || (unsigned int)size >= sizeof(status_attr_path)) { + err("usbip_status path length %i >= %lu or < 0", size, + (long unsigned)sizeof(status_attr_path)); + return -1; + } + fd = open(status_attr_path, O_RDONLY); if (fd < 0) { @@ -218,6 +225,7 @@ int usbip_export_device(struct usbip_exported_device *edev, int sockfd) { char attr_name[] = "usbip_sockfd"; char sockfd_attr_path[SYSFS_PATH_MAX]; + int size; char sockfd_buff[30]; int ret; @@ -237,10 +245,20 @@ int usbip_export_device(struct usbip_exported_device *edev, int sockfd) } /* only the first interface is true */ - snprintf(sockfd_attr_path, sizeof(sockfd_attr_path), "%s/%s", - edev->udev.path, attr_name); + size = snprintf(sockfd_attr_path, sizeof(sockfd_attr_path), "%s/%s", + edev->udev.path, attr_name); + if (size < 0 || (unsigned int)size >= sizeof(sockfd_attr_path)) { + err("exported device path length %i >= %lu or < 0", size, + (long unsigned)sizeof(sockfd_attr_path)); + return -1; + } - snprintf(sockfd_buff, sizeof(sockfd_buff), "%d\n", sockfd); + size = snprintf(sockfd_buff, sizeof(sockfd_buff), "%d\n", sockfd); + if (size < 0 || (unsigned int)size >= sizeof(sockfd_buff)) { + err("socket length %i >= %lu or < 0", size, + (long unsigned)sizeof(sockfd_buff)); + return -1; + } ret = write_sysfs_attribute(sockfd_attr_path, sockfd_buff, strlen(sockfd_buff)); diff --git a/tools/usb/usbip/libsrc/vhci_driver.c b/tools/usb/usbip/libsrc/vhci_driver.c index ad9204773533..f659c146cdc8 100644 --- a/tools/usb/usbip/libsrc/vhci_driver.c +++ b/tools/usb/usbip/libsrc/vhci_driver.c @@ -123,33 +123,15 @@ static int refresh_imported_device_list(void) static int get_nports(void) { - char *c; - int nports = 0; - const char *attr_status; + const char *attr_nports; - attr_status = udev_device_get_sysattr_value(vhci_driver->hc_device, - "status"); - if (!attr_status) { - err("udev_device_get_sysattr_value failed"); + attr_nports = udev_device_get_sysattr_value(vhci_driver->hc_device, "nports"); + if (!attr_nports) { + err("udev_device_get_sysattr_value nports failed"); return -1; } - /* skip a header line */ - c = strchr(attr_status, '\n'); - if (!c) - return 0; - c++; - - while (*c != '\0') { - /* go to the next line */ - c = strchr(c, '\n'); - if (!c) - return nports; - c++; - nports += 1; - } - - return nports; + return (int)strtoul(attr_nports, NULL, 10); } /* diff --git a/tools/usb/usbip/src/usbip.c b/tools/usb/usbip/src/usbip.c index d7599d943529..73d8eee8130b 100644 --- a/tools/usb/usbip/src/usbip.c +++ b/tools/usb/usbip/src/usbip.c @@ -176,6 +176,8 @@ int main(int argc, char *argv[]) break; case '?': printf("usbip: invalid option\n"); + /* Terminate after printing error */ + /* FALLTHRU */ default: usbip_usage(); goto out; diff --git a/tools/usb/usbip/vudc/vudc_server_example.sh b/tools/usb/usbip/vudc/vudc_server_example.sh new file mode 100755 index 000000000000..2736be64f203 --- /dev/null +++ b/tools/usb/usbip/vudc/vudc_server_example.sh @@ -0,0 +1,107 @@ +#!/bin/bash + +################################################################################ +# This is free and unencumbered software released into the public domain. +# +# Anyone is free to copy, modify, publish, use, compile, sell, or +# distribute this software, either in source code form or as a compiled +# binary, for any purpose, commercial or non-commercial, and by any +# means. +# +# In jurisdictions that recognize copyright laws, the author or authors +# of this software dedicate any and all copyright interest in the +# software to the public domain. We make this dedication for the benefit +# of the public at large and to the detriment of our heirs and +# successors. We intend this dedication to be an overt act of +# relinquishment in perpetuity of all present and future rights to this +# software under copyright law. +# +# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF +# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. +# IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR +# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, +# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR +# OTHER DEALINGS IN THE SOFTWARE. +# +# For more information, please refer to <http://unlicense.org/> +################################################################################ + +################################################################################ +# This is a sample script which shows how to use vUDC with ConfigFS gadgets +################################################################################ + +# Stop script on error +set -e + +################################################################################ +# Create your USB gadget +# You may use bare ConfigFS interface (as below) +# or libusbgx or gt toool +# Instead of ConfigFS gadgets you may use any of legacy gadgets. +################################################################################ +CONFIGFS_MOUNT_POINT="/sys/kernel/config" +GADGET_NAME="g1" +ID_VENDOR="0x1d6b" +ID_PRODUCT="0x0104" + +cd ${CONFIGFS_MOUNT_POINT}/usb_gadget +# Create a new USB gadget +mkdir ${GADGET_NAME} +cd ${GADGET_NAME} + +# This gadget contains one function - ACM (serial port over USB) +FUNC_DIR="functions/acm.ser0" +mkdir ${FUNC_DIR} + +# Just one configuration +mkdir configs/c.1 +ln -s ${FUNC_DIR} configs/c.1 + +# Set our gadget identity +echo ${ID_VENDOR} > idVendor +echo ${ID_PRODUCT} > idProduct + +################################################################################ +# Load vudc-module if vudc is not available +# You may change value of num param to get more than one vUDC instance +################################################################################ +[[ -d /sys/class/udc/usbip-vudc.0 ]] || modprobe usbip-vudc num=1 + +################################################################################ +# Bind gadget to our vUDC +# By default we bind to first one but you may change this if you would like +# to use more than one instance +################################################################################ +echo "usbip-vudc.0" > UDC + +################################################################################ +# Let's now run our usbip daemon in a USB device mode +################################################################################ +usbipd --device & + +################################################################################ +# Now your USB gadget is available using USB/IP protocol. +# To prepare your client, you should ensure that usbip-vhci module is inside +# your kernel. If it's not then you can load it: +# +# $ modprobe usbip-vhci +# +# To check availability of your gadget you may try to list devices exported +# on a remote server: +# +# $ modprobe usbip-vhci +# $ usbip list -r $SERVER_IP +# Exportable USB devices +# ====================== +# usbipd: info: request 0x8005(6): complete +# - 127.0.0.1 +# usbip-vudc.0: Linux Foundation : unknown product (1d6b:0104) +# : /sys/devices/platform/usbip-vudc.0 +# : (Defined at Interface level) (00/00/00) +# +# To attach this device to your client you may use: +# +# $ usbip attach -r $SERVER_IP -d usbip-vudc.0 +# +################################################################################ diff --git a/tools/virtio/linux/virtio.h b/tools/virtio/linux/virtio.h index 9377c8b4ac16..d8f534025b7f 100644 --- a/tools/virtio/linux/virtio.h +++ b/tools/virtio/linux/virtio.h @@ -57,6 +57,7 @@ struct virtqueue *vring_new_virtqueue(unsigned int index, unsigned int vring_align, struct virtio_device *vdev, bool weak_barriers, + bool ctx, void *pages, bool (*notify)(struct virtqueue *vq), void (*callback)(struct virtqueue *vq), diff --git a/tools/virtio/ringtest/main.c b/tools/virtio/ringtest/main.c index f31353fac541..453ca3c21193 100644 --- a/tools/virtio/ringtest/main.c +++ b/tools/virtio/ringtest/main.c @@ -20,6 +20,7 @@ int runcycles = 10000000; int max_outstanding = INT_MAX; int batch = 1; +int param = 0; bool do_sleep = false; bool do_relax = false; @@ -86,7 +87,7 @@ void set_affinity(const char *arg) cpu = strtol(arg, &endptr, 0); assert(!*endptr); - assert(cpu >= 0 || cpu < CPU_SETSIZE); + assert(cpu >= 0 && cpu < CPU_SETSIZE); self = pthread_self(); CPU_ZERO(&cpuset); @@ -247,6 +248,11 @@ static const struct option longopts[] = { .val = 'b', }, { + .name = "param", + .has_arg = required_argument, + .val = 'p', + }, + { .name = "sleep", .has_arg = no_argument, .val = 's', @@ -274,6 +280,7 @@ static void help(void) " [--run-cycles C (default: %d)]" " [--batch b]" " [--outstanding o]" + " [--param p]" " [--sleep]" " [--relax]" " [--exit]" @@ -328,6 +335,12 @@ int main(int argc, char **argv) assert(c > 0 && c < INT_MAX); max_outstanding = c; break; + case 'p': + c = strtol(optarg, &endptr, 0); + assert(!*endptr); + assert(c > 0 && c < INT_MAX); + param = c; + break; case 'b': c = strtol(optarg, &endptr, 0); assert(!*endptr); diff --git a/tools/virtio/ringtest/main.h b/tools/virtio/ringtest/main.h index 14142faf040b..90b0133004e1 100644 --- a/tools/virtio/ringtest/main.h +++ b/tools/virtio/ringtest/main.h @@ -10,6 +10,8 @@ #include <stdbool.h> +extern int param; + extern bool do_exit; #if defined(__x86_64__) || defined(__i386__) diff --git a/tools/virtio/ringtest/ptr_ring.c b/tools/virtio/ringtest/ptr_ring.c index 635b07b4fdd3..7b22f1b20652 100644 --- a/tools/virtio/ringtest/ptr_ring.c +++ b/tools/virtio/ringtest/ptr_ring.c @@ -97,6 +97,9 @@ void alloc_ring(void) { int ret = ptr_ring_init(&array, ring_size, 0); assert(!ret); + /* Hacky way to poke at ring internals. Useful for testing though. */ + if (param) + array.batch = param; } /* guest side */ diff --git a/tools/virtio/virtio_test.c b/tools/virtio/virtio_test.c index e0445898f08f..0fecaec90d0d 100644 --- a/tools/virtio/virtio_test.c +++ b/tools/virtio/virtio_test.c @@ -100,7 +100,7 @@ static void vq_info_add(struct vdev_info *dev, int num) vring_init(&info->vring, num, info->ring, 4096); info->vq = vring_new_virtqueue(info->idx, info->vring.num, 4096, &dev->vdev, - true, info->ring, + true, false, info->ring, vq_notify, vq_callback, "test"); assert(info->vq); info->vq->priv = info; @@ -202,7 +202,7 @@ static void run_test(struct vdev_info *dev, struct vq_info *vq, test = 0; r = ioctl(dev->control, VHOST_TEST_RUN, &test); assert(r >= 0); - fprintf(stderr, "spurious wakeus: 0x%llx\n", spurious); + fprintf(stderr, "spurious wakeups: 0x%llx\n", spurious); } const char optstring[] = "h"; diff --git a/tools/virtio/vringh_test.c b/tools/virtio/vringh_test.c index 5f94f5105678..9476c616d064 100644 --- a/tools/virtio/vringh_test.c +++ b/tools/virtio/vringh_test.c @@ -314,7 +314,8 @@ static int parallel_test(u64 features, err(1, "Could not set affinity to cpu %u", first_cpu); vq = vring_new_virtqueue(0, RINGSIZE, ALIGN, &gvdev.vdev, true, - guest_map, fast_vringh ? no_notify_host + false, guest_map, + fast_vringh ? no_notify_host : parallel_notify_host, never_callback_guest, "guest vq"); @@ -479,7 +480,7 @@ int main(int argc, char *argv[]) memset(__user_addr_min, 0, vring_size(RINGSIZE, ALIGN)); /* Set up guest side. */ - vq = vring_new_virtqueue(0, RINGSIZE, ALIGN, &vdev, true, + vq = vring_new_virtqueue(0, RINGSIZE, ALIGN, &vdev, true, false, __user_addr_min, never_notify_host, never_callback_guest, "guest vq"); @@ -663,7 +664,7 @@ int main(int argc, char *argv[]) /* Force creation of direct, which we modify. */ __virtio_clear_bit(&vdev, VIRTIO_RING_F_INDIRECT_DESC); vq = vring_new_virtqueue(0, RINGSIZE, ALIGN, &vdev, true, - __user_addr_min, + false, __user_addr_min, never_notify_host, never_callback_guest, "guest vq"); diff --git a/tools/vm/Makefile b/tools/vm/Makefile index 93aadaf7ff63..006029456988 100644 --- a/tools/vm/Makefile +++ b/tools/vm/Makefile @@ -9,6 +9,8 @@ CC = $(CROSS_COMPILE)gcc CFLAGS = -Wall -Wextra -I../lib/ LDFLAGS = $(LIBS) +all: $(TARGETS) + $(TARGETS): $(LIBS) $(LIBS): @@ -20,3 +22,9 @@ $(LIBS): clean: $(RM) page-types slabinfo page_owner_sort make -C $(LIB_DIR) clean + +sbindir ?= /usr/sbin + +install: all + install -d $(DESTDIR)$(sbindir) + install -m 755 -p $(TARGETS) $(DESTDIR)$(sbindir) |