diff options
Diffstat (limited to 'tools')
254 files changed, 10986 insertions, 6795 deletions
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index 1c17c3a24411..24223adae150 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -156,9 +156,6 @@ struct kvm_sync_regs { __u64 device_irq_level; }; -struct kvm_arch_memory_slot { -}; - /* * PMU filter structure. Describe a range of events with a particular * action. To be used with KVM_ARM_VCPU_PMU_V3_FILTER. diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index dad350d42ecf..84b887825f12 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -237,10 +237,12 @@ #define X86_FEATURE_VMCALL ( 8*32+18) /* "" Hypervisor supports the VMCALL instruction */ #define X86_FEATURE_VMW_VMMCALL ( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */ #define X86_FEATURE_SEV_ES ( 8*32+20) /* AMD Secure Encrypted Virtualization - Encrypted State */ +#define X86_FEATURE_VM_PAGE_FLUSH ( 8*32+21) /* "" VM Page Flush MSR is supported */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */ #define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/ #define X86_FEATURE_TSC_ADJUST ( 9*32+ 1) /* TSC adjustment MSR 0x3B */ +#define X86_FEATURE_SGX ( 9*32+ 2) /* Software Guard Extensions */ #define X86_FEATURE_BMI1 ( 9*32+ 3) /* 1st group bit manipulation extensions */ #define X86_FEATURE_HLE ( 9*32+ 4) /* Hardware Lock Elision */ #define X86_FEATURE_AVX2 ( 9*32+ 5) /* AVX2 instructions */ @@ -356,6 +358,7 @@ #define X86_FEATURE_MOVDIRI (16*32+27) /* MOVDIRI instruction */ #define X86_FEATURE_MOVDIR64B (16*32+28) /* MOVDIR64B instruction */ #define X86_FEATURE_ENQCMD (16*32+29) /* ENQCMD and ENQCMDS instructions */ +#define X86_FEATURE_SGX_LC (16*32+30) /* Software Guard Extensions Launch Control */ /* AMD-defined CPU features, CPUID level 0x80000007 (EBX), word 17 */ #define X86_FEATURE_OVERFLOW_RECOV (17*32+ 0) /* MCA overflow recovery support */ @@ -374,6 +377,7 @@ #define X86_FEATURE_TSXLDTRK (18*32+16) /* TSX Suspend Load Address Tracking */ #define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */ #define X86_FEATURE_ARCH_LBR (18*32+19) /* Intel ARCH LBR */ +#define X86_FEATURE_AVX512_FP16 (18*32+23) /* AVX512 FP16 */ #define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */ #define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */ #define X86_FEATURE_FLUSH_L1D (18*32+28) /* Flush L1D cache */ diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index 5861d34f9771..7947cb1782da 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -62,6 +62,12 @@ # define DISABLE_ENQCMD (1 << (X86_FEATURE_ENQCMD & 31)) #endif +#ifdef CONFIG_X86_SGX +# define DISABLE_SGX 0 +#else +# define DISABLE_SGX (1 << (X86_FEATURE_SGX & 31)) +#endif + /* * Make sure to add features to the correct mask */ @@ -74,7 +80,7 @@ #define DISABLED_MASK6 0 #define DISABLED_MASK7 (DISABLE_PTI) #define DISABLED_MASK8 0 -#define DISABLED_MASK9 (DISABLE_SMAP) +#define DISABLED_MASK9 (DISABLE_SMAP|DISABLE_SGX) #define DISABLED_MASK10 0 #define DISABLED_MASK11 0 #define DISABLED_MASK12 0 diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index 972a34d93505..546d6ecf0a35 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -139,6 +139,7 @@ #define MSR_IA32_MCG_CAP 0x00000179 #define MSR_IA32_MCG_STATUS 0x0000017a #define MSR_IA32_MCG_CTL 0x0000017b +#define MSR_ERROR_CONTROL 0x0000017f #define MSR_IA32_MCG_EXT_CTL 0x000004d0 #define MSR_OFFCORE_RSP_0 0x000001a6 @@ -326,8 +327,9 @@ #define MSR_PP1_ENERGY_STATUS 0x00000641 #define MSR_PP1_POLICY 0x00000642 -#define MSR_AMD_PKG_ENERGY_STATUS 0xc001029b #define MSR_AMD_RAPL_POWER_UNIT 0xc0010299 +#define MSR_AMD_CORE_ENERGY_STATUS 0xc001029a +#define MSR_AMD_PKG_ENERGY_STATUS 0xc001029b /* Config TDP MSRs */ #define MSR_CONFIG_TDP_NOMINAL 0x00000648 @@ -470,6 +472,7 @@ #define MSR_AMD64_ICIBSEXTDCTL 0xc001103c #define MSR_AMD64_IBSOPDATA4 0xc001103d #define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */ +#define MSR_AMD64_VM_PAGE_FLUSH 0xc001011e #define MSR_AMD64_SEV_ES_GHCB 0xc0010130 #define MSR_AMD64_SEV 0xc0010131 #define MSR_AMD64_SEV_ENABLED_BIT 0 @@ -609,6 +612,8 @@ #define FEAT_CTL_LOCKED BIT(0) #define FEAT_CTL_VMX_ENABLED_INSIDE_SMX BIT(1) #define FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX BIT(2) +#define FEAT_CTL_SGX_LC_ENABLED BIT(17) +#define FEAT_CTL_SGX_ENABLED BIT(18) #define FEAT_CTL_LMCE_ENABLED BIT(20) #define MSR_IA32_TSC_ADJUST 0x0000003b @@ -628,6 +633,12 @@ #define MSR_IA32_UCODE_WRITE 0x00000079 #define MSR_IA32_UCODE_REV 0x0000008b +/* Intel SGX Launch Enclave Public Key Hash MSRs */ +#define MSR_IA32_SGXLEPUBKEYHASH0 0x0000008C +#define MSR_IA32_SGXLEPUBKEYHASH1 0x0000008D +#define MSR_IA32_SGXLEPUBKEYHASH2 0x0000008E +#define MSR_IA32_SGXLEPUBKEYHASH3 0x0000008F + #define MSR_IA32_SMM_MONITOR_CTL 0x0000009b #define MSR_IA32_SMBASE 0x0000009e diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index 89e5f3d1bba8..8e76d3701db3 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -12,6 +12,7 @@ #define KVM_PIO_PAGE_OFFSET 1 #define KVM_COALESCED_MMIO_PAGE_OFFSET 2 +#define KVM_DIRTY_LOG_PAGE_OFFSET 64 #define DE_VECTOR 0 #define DB_VECTOR 1 diff --git a/tools/arch/x86/include/uapi/asm/svm.h b/tools/arch/x86/include/uapi/asm/svm.h index f1d8307454e0..554f75fe013c 100644 --- a/tools/arch/x86/include/uapi/asm/svm.h +++ b/tools/arch/x86/include/uapi/asm/svm.h @@ -77,10 +77,28 @@ #define SVM_EXIT_MWAIT_COND 0x08c #define SVM_EXIT_XSETBV 0x08d #define SVM_EXIT_RDPRU 0x08e +#define SVM_EXIT_EFER_WRITE_TRAP 0x08f +#define SVM_EXIT_CR0_WRITE_TRAP 0x090 +#define SVM_EXIT_CR1_WRITE_TRAP 0x091 +#define SVM_EXIT_CR2_WRITE_TRAP 0x092 +#define SVM_EXIT_CR3_WRITE_TRAP 0x093 +#define SVM_EXIT_CR4_WRITE_TRAP 0x094 +#define SVM_EXIT_CR5_WRITE_TRAP 0x095 +#define SVM_EXIT_CR6_WRITE_TRAP 0x096 +#define SVM_EXIT_CR7_WRITE_TRAP 0x097 +#define SVM_EXIT_CR8_WRITE_TRAP 0x098 +#define SVM_EXIT_CR9_WRITE_TRAP 0x099 +#define SVM_EXIT_CR10_WRITE_TRAP 0x09a +#define SVM_EXIT_CR11_WRITE_TRAP 0x09b +#define SVM_EXIT_CR12_WRITE_TRAP 0x09c +#define SVM_EXIT_CR13_WRITE_TRAP 0x09d +#define SVM_EXIT_CR14_WRITE_TRAP 0x09e +#define SVM_EXIT_CR15_WRITE_TRAP 0x09f #define SVM_EXIT_INVPCID 0x0a2 #define SVM_EXIT_NPF 0x400 #define SVM_EXIT_AVIC_INCOMPLETE_IPI 0x401 #define SVM_EXIT_AVIC_UNACCELERATED_ACCESS 0x402 +#define SVM_EXIT_VMGEXIT 0x403 /* SEV-ES software-defined VMGEXIT events */ #define SVM_VMGEXIT_MMIO_READ 0x80000001 @@ -183,10 +201,20 @@ { SVM_EXIT_MONITOR, "monitor" }, \ { SVM_EXIT_MWAIT, "mwait" }, \ { SVM_EXIT_XSETBV, "xsetbv" }, \ + { SVM_EXIT_EFER_WRITE_TRAP, "write_efer_trap" }, \ + { SVM_EXIT_CR0_WRITE_TRAP, "write_cr0_trap" }, \ + { SVM_EXIT_CR4_WRITE_TRAP, "write_cr4_trap" }, \ + { SVM_EXIT_CR8_WRITE_TRAP, "write_cr8_trap" }, \ { SVM_EXIT_INVPCID, "invpcid" }, \ { SVM_EXIT_NPF, "npf" }, \ { SVM_EXIT_AVIC_INCOMPLETE_IPI, "avic_incomplete_ipi" }, \ { SVM_EXIT_AVIC_UNACCELERATED_ACCESS, "avic_unaccelerated_access" }, \ + { SVM_EXIT_VMGEXIT, "vmgexit" }, \ + { SVM_VMGEXIT_MMIO_READ, "vmgexit_mmio_read" }, \ + { SVM_VMGEXIT_MMIO_WRITE, "vmgexit_mmio_write" }, \ + { SVM_VMGEXIT_NMI_COMPLETE, "vmgexit_nmi_complete" }, \ + { SVM_VMGEXIT_AP_HLT_LOOP, "vmgexit_ap_hlt_loop" }, \ + { SVM_VMGEXIT_AP_JUMP_TABLE, "vmgexit_ap_jump_table" }, \ { SVM_EXIT_ERR, "invalid_guest_state" } diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h index b8ff9e8ac0d5..ada955c5ebb6 100644 --- a/tools/arch/x86/include/uapi/asm/vmx.h +++ b/tools/arch/x86/include/uapi/asm/vmx.h @@ -32,6 +32,7 @@ #define EXIT_REASON_EXTERNAL_INTERRUPT 1 #define EXIT_REASON_TRIPLE_FAULT 2 #define EXIT_REASON_INIT_SIGNAL 3 +#define EXIT_REASON_SIPI_SIGNAL 4 #define EXIT_REASON_INTERRUPT_WINDOW 7 #define EXIT_REASON_NMI_WINDOW 8 @@ -94,6 +95,7 @@ { EXIT_REASON_EXTERNAL_INTERRUPT, "EXTERNAL_INTERRUPT" }, \ { EXIT_REASON_TRIPLE_FAULT, "TRIPLE_FAULT" }, \ { EXIT_REASON_INIT_SIGNAL, "INIT_SIGNAL" }, \ + { EXIT_REASON_SIPI_SIGNAL, "SIPI_SIGNAL" }, \ { EXIT_REASON_INTERRUPT_WINDOW, "INTERRUPT_WINDOW" }, \ { EXIT_REASON_NMI_WINDOW, "NMI_WINDOW" }, \ { EXIT_REASON_TASK_SWITCH, "TASK_SWITCH" }, \ diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index cdde783f3018..89ba522e377d 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -90,7 +90,7 @@ __BUILDXX = $(CXX) $(CXXFLAGS) -MD -Wall -Werror -o $@ $(patsubst %.bin,%.cpp,$( ############################### $(OUTPUT)test-all.bin: - $(BUILD) -fstack-protector-all -O2 -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -I/usr/include/slang -lslang $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl -lz -llzma -lzstd + $(BUILD) -fstack-protector-all -O2 -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -I/usr/include/slang -lslang $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl -lz -llzma -lzstd -lcap $(OUTPUT)test-hello.bin: $(BUILD) diff --git a/tools/gpio/gpio-event-mon.c b/tools/gpio/gpio-event-mon.c index 90c3155f05b1..cacd66ad7926 100644 --- a/tools/gpio/gpio-event-mon.c +++ b/tools/gpio/gpio-event-mon.c @@ -148,6 +148,7 @@ void print_usage(void) " -s Set line as open source\n" " -r Listen for rising edges\n" " -f Listen for falling edges\n" + " -w Report the wall-clock time for events\n" " -b <n> Debounce the line with period n microseconds\n" " [-c <n>] Do <n> loops (optional, infinite loop if not stated)\n" " -? This helptext\n" @@ -173,7 +174,7 @@ int main(int argc, char **argv) memset(&config, 0, sizeof(config)); config.flags = GPIO_V2_LINE_FLAG_INPUT; - while ((c = getopt(argc, argv, "c:n:o:b:dsrf?")) != -1) { + while ((c = getopt(argc, argv, "c:n:o:b:dsrfw?")) != -1) { switch (c) { case 'c': loops = strtoul(optarg, NULL, 10); @@ -204,6 +205,9 @@ int main(int argc, char **argv) case 'f': config.flags |= GPIO_V2_LINE_FLAG_EDGE_FALLING; break; + case 'w': + config.flags |= GPIO_V2_LINE_FLAG_EVENT_CLOCK_REALTIME; + break; case '?': print_usage(); return -1; diff --git a/tools/gpio/lsgpio.c b/tools/gpio/lsgpio.c index 5a05a454d0c9..c61d061247e1 100644 --- a/tools/gpio/lsgpio.c +++ b/tools/gpio/lsgpio.c @@ -65,6 +65,10 @@ struct gpio_flag flagnames[] = { .name = "bias-disabled", .mask = GPIO_V2_LINE_FLAG_BIAS_DISABLED, }, + { + .name = "clock-realtime", + .mask = GPIO_V2_LINE_FLAG_EVENT_CLOCK_REALTIME, + }, }; static void print_attributes(struct gpio_v2_line_info *info) diff --git a/tools/include/linux/build_bug.h b/tools/include/linux/build_bug.h index cc7070c7439b..ce365d212768 100644 --- a/tools/include/linux/build_bug.h +++ b/tools/include/linux/build_bug.h @@ -79,4 +79,9 @@ #define __static_assert(expr, msg, ...) _Static_assert(expr, msg) #endif // static_assert +#ifdef __GENKSYMS__ +/* genksyms gets confused by _Static_assert */ +#define _Static_assert(expr, ...) +#endif + #endif /* _LINUX_BUILD_BUG_H */ diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h index d22a974372c0..ff872dc2637c 100644 --- a/tools/include/linux/compiler.h +++ b/tools/include/linux/compiler.h @@ -2,9 +2,7 @@ #ifndef _TOOLS_LINUX_COMPILER_H_ #define _TOOLS_LINUX_COMPILER_H_ -#ifdef __GNUC__ -#include <linux/compiler-gcc.h> -#endif +#include <linux/compiler_types.h> #ifndef __compiletime_error # define __compiletime_error(message) diff --git a/tools/include/linux/compiler_types.h b/tools/include/linux/compiler_types.h new file mode 100644 index 000000000000..feea09029f61 --- /dev/null +++ b/tools/include/linux/compiler_types.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_COMPILER_TYPES_H +#define __LINUX_COMPILER_TYPES_H + +/* Builtins */ + +/* + * __has_builtin is supported on gcc >= 10, clang >= 3 and icc >= 21. + * In the meantime, to support gcc < 10, we implement __has_builtin + * by hand. + */ +#ifndef __has_builtin +#define __has_builtin(x) (0) +#endif + +/* Compiler specific macros. */ +#ifdef __GNUC__ +#include <linux/compiler-gcc.h> +#endif + +#endif /* __LINUX_COMPILER_TYPES_H */ diff --git a/tools/include/linux/ctype.h b/tools/include/linux/ctype.h index 310090b4c474..29ed3fe94404 100644 --- a/tools/include/linux/ctype.h +++ b/tools/include/linux/ctype.h @@ -2,6 +2,8 @@ #ifndef _LINUX_CTYPE_H #define _LINUX_CTYPE_H +#include <linux/compiler.h> + /* * NOTE! This ctype does not handle EOF like the standard C * library is required to. @@ -23,11 +25,6 @@ extern const unsigned char _ctype[]; #define isalnum(c) ((__ismask(c)&(_U|_L|_D)) != 0) #define isalpha(c) ((__ismask(c)&(_U|_L)) != 0) #define iscntrl(c) ((__ismask(c)&(_C)) != 0) -static inline int __isdigit(int c) -{ - return '0' <= c && c <= '9'; -} -#define isdigit(c) __isdigit(c) #define isgraph(c) ((__ismask(c)&(_P|_U|_L|_D)) != 0) #define islower(c) ((__ismask(c)&(_L)) != 0) #define isprint(c) ((__ismask(c)&(_P|_U|_L|_D|_SP)) != 0) @@ -40,6 +37,16 @@ static inline int __isdigit(int c) #define isascii(c) (((unsigned char)(c))<=0x7f) #define toascii(c) (((unsigned char)(c))&0x7f) +#if __has_builtin(__builtin_isdigit) +#define isdigit(c) __builtin_isdigit(c) +#else +static inline int __isdigit(int c) +{ + return '0' <= c && c <= '9'; +} +#define isdigit(c) __isdigit(c) +#endif + static inline unsigned char __tolower(unsigned char c) { if (isupper(c)) diff --git a/tools/include/linux/string.h b/tools/include/linux/string.h index 5e9e781905ed..db5c99318c79 100644 --- a/tools/include/linux/string.h +++ b/tools/include/linux/string.h @@ -46,4 +46,5 @@ extern char * __must_check skip_spaces(const char *); extern char *strim(char *); +extern void *memchr_inv(const void *start, int c, size_t bytes); #endif /* _TOOLS_LINUX_STRING_H_ */ diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index 2056318988f7..728752917785 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -517,7 +517,7 @@ __SC_COMP(__NR_settimeofday, sys_settimeofday, compat_sys_settimeofday) __SC_3264(__NR_adjtimex, sys_adjtimex_time32, sys_adjtimex) #endif -/* kernel/timer.c */ +/* kernel/sys.c */ #define __NR_getpid 172 __SYSCALL(__NR_getpid, sys_getpid) #define __NR_getppid 173 @@ -859,9 +859,11 @@ __SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd) __SYSCALL(__NR_faccessat2, sys_faccessat2) #define __NR_process_madvise 440 __SYSCALL(__NR_process_madvise, sys_process_madvise) +#define __NR_epoll_pwait2 441 +__SC_COMP(__NR_epoll_pwait2, sys_epoll_pwait2, compat_sys_epoll_pwait2) #undef __NR_syscalls -#define __NR_syscalls 441 +#define __NR_syscalls 442 /* * 32 bit systems traditionally used different diff --git a/tools/include/uapi/linux/const.h b/tools/include/uapi/linux/const.h index 5ed721ad5b19..af2a44c08683 100644 --- a/tools/include/uapi/linux/const.h +++ b/tools/include/uapi/linux/const.h @@ -28,4 +28,9 @@ #define _BITUL(x) (_UL(1) << (x)) #define _BITULL(x) (_ULL(1) << (x)) +#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1) +#define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask)) + +#define __KERNEL_DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d)) + #endif /* _UAPI_LINUX_CONST_H */ diff --git a/tools/include/uapi/linux/fscrypt.h b/tools/include/uapi/linux/fscrypt.h index e5de60336938..9f4428be3e36 100644 --- a/tools/include/uapi/linux/fscrypt.h +++ b/tools/include/uapi/linux/fscrypt.h @@ -20,7 +20,6 @@ #define FSCRYPT_POLICY_FLAG_DIRECT_KEY 0x04 #define FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64 0x08 #define FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32 0x10 -#define FSCRYPT_POLICY_FLAGS_VALID 0x1F /* Encryption algorithms */ #define FSCRYPT_MODE_AES_256_XTS 1 @@ -28,7 +27,7 @@ #define FSCRYPT_MODE_AES_128_CBC 5 #define FSCRYPT_MODE_AES_128_CTS 6 #define FSCRYPT_MODE_ADIANTUM 9 -#define __FSCRYPT_MODE_MAX 9 +/* If adding a mode number > 9, update FSCRYPT_MODE_MAX in fscrypt_private.h */ /* * Legacy policy version; ad-hoc KDF and no key verification. @@ -177,7 +176,7 @@ struct fscrypt_get_key_status_arg { #define FS_POLICY_FLAGS_PAD_32 FSCRYPT_POLICY_FLAGS_PAD_32 #define FS_POLICY_FLAGS_PAD_MASK FSCRYPT_POLICY_FLAGS_PAD_MASK #define FS_POLICY_FLAG_DIRECT_KEY FSCRYPT_POLICY_FLAG_DIRECT_KEY -#define FS_POLICY_FLAGS_VALID FSCRYPT_POLICY_FLAGS_VALID +#define FS_POLICY_FLAGS_VALID 0x07 /* contains old flags only */ #define FS_ENCRYPTION_MODE_INVALID 0 /* never used */ #define FS_ENCRYPTION_MODE_AES_256_XTS FSCRYPT_MODE_AES_256_XTS #define FS_ENCRYPTION_MODE_AES_256_GCM 2 /* never used */ diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index ca41220b40b8..886802b8ffba 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -250,6 +250,7 @@ struct kvm_hyperv_exit { #define KVM_EXIT_ARM_NISV 28 #define KVM_EXIT_X86_RDMSR 29 #define KVM_EXIT_X86_WRMSR 30 +#define KVM_EXIT_DIRTY_RING_FULL 31 /* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -1053,6 +1054,8 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_X86_USER_SPACE_MSR 188 #define KVM_CAP_X86_MSR_FILTER 189 #define KVM_CAP_ENFORCE_PV_FEATURE_CPUID 190 +#define KVM_CAP_SYS_HYPERV_CPUID 191 +#define KVM_CAP_DIRTY_LOG_RING 192 #ifdef KVM_CAP_IRQ_ROUTING @@ -1511,7 +1514,7 @@ struct kvm_enc_region { /* Available with KVM_CAP_MANUAL_DIRTY_LOG_PROTECT_2 */ #define KVM_CLEAR_DIRTY_LOG _IOWR(KVMIO, 0xc0, struct kvm_clear_dirty_log) -/* Available with KVM_CAP_HYPERV_CPUID */ +/* Available with KVM_CAP_HYPERV_CPUID (vcpu) / KVM_CAP_SYS_HYPERV_CPUID (system) */ #define KVM_GET_SUPPORTED_HV_CPUID _IOWR(KVMIO, 0xc1, struct kvm_cpuid2) /* Available with KVM_CAP_ARM_SVE */ @@ -1557,6 +1560,9 @@ struct kvm_pv_cmd { /* Available with KVM_CAP_X86_MSR_FILTER */ #define KVM_X86_SET_MSR_FILTER _IOW(KVMIO, 0xc6, struct kvm_msr_filter) +/* Available with KVM_CAP_DIRTY_LOG_RING */ +#define KVM_RESET_DIRTY_RINGS _IO(KVMIO, 0xc7) + /* Secure Encrypted Virtualization command */ enum sev_cmd_id { /* Guest initialization commands */ @@ -1710,4 +1716,52 @@ struct kvm_hyperv_eventfd { #define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (1 << 0) #define KVM_DIRTY_LOG_INITIALLY_SET (1 << 1) +/* + * Arch needs to define the macro after implementing the dirty ring + * feature. KVM_DIRTY_LOG_PAGE_OFFSET should be defined as the + * starting page offset of the dirty ring structures. + */ +#ifndef KVM_DIRTY_LOG_PAGE_OFFSET +#define KVM_DIRTY_LOG_PAGE_OFFSET 0 +#endif + +/* + * KVM dirty GFN flags, defined as: + * + * |---------------+---------------+--------------| + * | bit 1 (reset) | bit 0 (dirty) | Status | + * |---------------+---------------+--------------| + * | 0 | 0 | Invalid GFN | + * | 0 | 1 | Dirty GFN | + * | 1 | X | GFN to reset | + * |---------------+---------------+--------------| + * + * Lifecycle of a dirty GFN goes like: + * + * dirtied harvested reset + * 00 -----------> 01 -------------> 1X -------+ + * ^ | + * | | + * +------------------------------------------+ + * + * The userspace program is only responsible for the 01->1X state + * conversion after harvesting an entry. Also, it must not skip any + * dirty bits, so that dirty bits are always harvested in sequence. + */ +#define KVM_DIRTY_GFN_F_DIRTY BIT(0) +#define KVM_DIRTY_GFN_F_RESET BIT(1) +#define KVM_DIRTY_GFN_F_MASK 0x3 + +/* + * KVM dirty rings should be mapped at KVM_DIRTY_LOG_PAGE_OFFSET of + * per-vcpu mmaped regions as an array of struct kvm_dirty_gfn. The + * size of the gfn buffer is decided by the first argument when + * enabling KVM_CAP_DIRTY_LOG_RING. + */ +struct kvm_dirty_gfn { + __u32 flags; + __u32 slot; + __u64 offset; +}; + #endif /* __LINUX_KVM_H */ diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index b95d3c485d27..b15e3447cd9f 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -143,8 +143,10 @@ enum perf_event_sample_format { PERF_SAMPLE_PHYS_ADDR = 1U << 19, PERF_SAMPLE_AUX = 1U << 20, PERF_SAMPLE_CGROUP = 1U << 21, + PERF_SAMPLE_DATA_PAGE_SIZE = 1U << 22, + PERF_SAMPLE_CODE_PAGE_SIZE = 1U << 23, - PERF_SAMPLE_MAX = 1U << 22, /* non-ABI */ + PERF_SAMPLE_MAX = 1U << 24, /* non-ABI */ __PERF_SAMPLE_CALLCHAIN_EARLY = 1ULL << 63, /* non-ABI; internal use */ }; @@ -896,6 +898,8 @@ enum perf_event_type { * { u64 phys_addr;} && PERF_SAMPLE_PHYS_ADDR * { u64 size; * char data[size]; } && PERF_SAMPLE_AUX + * { u64 data_page_size;} && PERF_SAMPLE_DATA_PAGE_SIZE + * { u64 code_page_size;} && PERF_SAMPLE_CODE_PAGE_SIZE * }; */ PERF_RECORD_SAMPLE = 9, diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index 7f0827705c9a..90deb41c8a34 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -247,4 +247,9 @@ struct prctl_mm_map { #define PR_SET_IO_FLUSHER 57 #define PR_GET_IO_FLUSHER 58 +/* Dispatch syscalls to a userspace handler */ +#define PR_SET_SYSCALL_USER_DISPATCH 59 +# define PR_SYS_DISPATCH_OFF 0 +# define PR_SYS_DISPATCH_ON 1 + #endif /* _LINUX_PRCTL_H */ diff --git a/tools/include/uapi/linux/stat.h b/tools/include/uapi/linux/stat.h index 82cc58fe9368..1500a0f58041 100644 --- a/tools/include/uapi/linux/stat.h +++ b/tools/include/uapi/linux/stat.h @@ -171,9 +171,12 @@ struct statx { * 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 + * Note that the flags marked [I] correspond to the FS_IOC_SETFLAGS flags * semantically. Where possible, the numerical value is picked to correspond - * also. + * also. Note that the DAX attribute indicates that the file is in the CPU + * direct access state. It does not correspond to the per-inode flag that + * some filesystems support. + * */ #define STATX_ATTR_COMPRESSED 0x00000004 /* [I] File is compressed by the fs */ #define STATX_ATTR_IMMUTABLE 0x00000010 /* [I] File is marked immutable */ @@ -183,7 +186,7 @@ struct statx { #define STATX_ATTR_AUTOMOUNT 0x00001000 /* Dir: Automount trigger */ #define STATX_ATTR_MOUNT_ROOT 0x00002000 /* Root of a mount */ #define STATX_ATTR_VERITY 0x00100000 /* [I] Verity protected file */ -#define STATX_ATTR_DAX 0x00002000 /* [I] File is DAX */ +#define STATX_ATTR_DAX 0x00200000 /* File is currently in DAX state */ #endif /* _UAPI_LINUX_STAT_H */ diff --git a/tools/lib/string.c b/tools/lib/string.c index f645343815de..8b6892f959ab 100644 --- a/tools/lib/string.c +++ b/tools/lib/string.c @@ -168,3 +168,61 @@ char *strreplace(char *s, char old, char new) *s = new; return s; } + +static void *check_bytes8(const u8 *start, u8 value, unsigned int bytes) +{ + while (bytes) { + if (*start != value) + return (void *)start; + start++; + bytes--; + } + return NULL; +} + +/** + * memchr_inv - Find an unmatching character in an area of memory. + * @start: The memory area + * @c: Find a character other than c + * @bytes: The size of the area. + * + * returns the address of the first character other than @c, or %NULL + * if the whole buffer contains just @c. + */ +void *memchr_inv(const void *start, int c, size_t bytes) +{ + u8 value = c; + u64 value64; + unsigned int words, prefix; + + if (bytes <= 16) + return check_bytes8(start, value, bytes); + + value64 = value; + value64 |= value64 << 8; + value64 |= value64 << 16; + value64 |= value64 << 32; + + prefix = (unsigned long)start % 8; + if (prefix) { + u8 *r; + + prefix = 8 - prefix; + r = check_bytes8(start, value, prefix); + if (r) + return r; + start += prefix; + bytes -= prefix; + } + + words = bytes / 8; + + while (words) { + if (*(u64 *)start != value64) + return check_bytes8(start, value, 8); + start += 8; + words--; + } + + return check_bytes8(start, value, bytes % 8); +} diff --git a/tools/objtool/check.c b/tools/objtool/check.c index c6ab44543c92..5f8d3eed78a1 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -467,13 +467,20 @@ static int create_static_call_sections(struct objtool_file *file) /* populate reloc for 'addr' */ reloc = malloc(sizeof(*reloc)); + if (!reloc) { perror("malloc"); return -1; } memset(reloc, 0, sizeof(*reloc)); - reloc->sym = insn->sec->sym; - reloc->addend = insn->offset; + + insn_to_reloc_sym_addend(insn->sec, insn->offset, reloc); + if (!reloc->sym) { + WARN_FUNC("static call tramp: missing containing symbol", + insn->sec, insn->offset); + return -1; + } + reloc->type = R_X86_64_PC32; reloc->offset = idx * sizeof(struct static_call_site); reloc->sec = reloc_sec; diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index 4e1d7460574b..be89c741ba9a 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -262,6 +262,32 @@ struct reloc *find_reloc_by_dest(const struct elf *elf, struct section *sec, uns return find_reloc_by_dest_range(elf, sec, offset, 1); } +void insn_to_reloc_sym_addend(struct section *sec, unsigned long offset, + struct reloc *reloc) +{ + if (sec->sym) { + reloc->sym = sec->sym; + reloc->addend = offset; + return; + } + + /* + * The Clang assembler strips section symbols, so we have to reference + * the function symbol instead: + */ + reloc->sym = find_symbol_containing(sec, offset); + if (!reloc->sym) { + /* + * Hack alert. This happens when we need to reference the NOP + * pad insn immediately after the function. + */ + reloc->sym = find_symbol_containing(sec, offset - 1); + } + + if (reloc->sym) + reloc->addend = offset - reloc->sym->offset; +} + static int read_sections(struct elf *elf) { Elf_Scn *s = NULL; diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h index 807f8c670097..e6890cc70a25 100644 --- a/tools/objtool/elf.h +++ b/tools/objtool/elf.h @@ -140,6 +140,8 @@ struct reloc *find_reloc_by_dest(const struct elf *elf, struct section *sec, uns struct reloc *find_reloc_by_dest_range(const struct elf *elf, struct section *sec, unsigned long offset, unsigned int len); struct symbol *find_func_containing(struct section *sec, unsigned long offset); +void insn_to_reloc_sym_addend(struct section *sec, unsigned long offset, + struct reloc *reloc); int elf_rebuild_reloc_section(struct elf *elf, struct section *sec); #define for_each_sec(file, sec) \ diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c index 235663b96adc..9ce68b385a1b 100644 --- a/tools/objtool/orc_gen.c +++ b/tools/objtool/orc_gen.c @@ -105,30 +105,11 @@ static int create_orc_entry(struct elf *elf, struct section *u_sec, struct secti } memset(reloc, 0, sizeof(*reloc)); - if (insn_sec->sym) { - reloc->sym = insn_sec->sym; - reloc->addend = insn_off; - } else { - /* - * The Clang assembler doesn't produce section symbols, so we - * have to reference the function symbol instead: - */ - reloc->sym = find_symbol_containing(insn_sec, insn_off); - if (!reloc->sym) { - /* - * Hack alert. This happens when we need to reference - * the NOP pad insn immediately after the function. - */ - reloc->sym = find_symbol_containing(insn_sec, - insn_off - 1); - } - if (!reloc->sym) { - WARN("missing symbol for insn at offset 0x%lx\n", - insn_off); - return -1; - } - - reloc->addend = insn_off - reloc->sym->offset; + insn_to_reloc_sym_addend(insn_sec, insn_off, reloc); + if (!reloc->sym) { + WARN("missing symbol for insn at offset 0x%lx", + insn_off); + return -1; } reloc->type = R_X86_64_PC32; diff --git a/tools/perf/Documentation/itrace.txt b/tools/perf/Documentation/itrace.txt index d3740c8f399b..079cdfabb352 100644 --- a/tools/perf/Documentation/itrace.txt +++ b/tools/perf/Documentation/itrace.txt @@ -11,6 +11,7 @@ d create a debug log f synthesize first level cache events m synthesize last level cache events + M synthesize memory events t synthesize TLB events a synthesize remote access events g synthesize a call chain (use with i or x) diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt index 31069d8a5304..5c379adf8304 100644 --- a/tools/perf/Documentation/perf-config.txt +++ b/tools/perf/Documentation/perf-config.txt @@ -138,7 +138,7 @@ If you want to add or modify several config items, you can do like To modify the sort order of report functionality in user config file(i.e. `~/.perfconfig`), do - % perf config --user report sort-order=srcline + % perf config --user report.sort-order=srcline To change colors of selected line to other foreground and background colors in system config file (i.e. `$(sysconf)/perfconfig`), do diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 768888b9326a..34cf651ee237 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -293,6 +293,9 @@ OPTIONS --phys-data:: Record the sample physical addresses. +--data-page-size:: + Record the sampled data address data page size. + -T:: --timestamp:: Record the sample timestamps. Use it with 'perf report -D' to see the @@ -634,11 +637,17 @@ endif::HAVE_LIBPFM[] --control=fifo:ctl-fifo[,ack-fifo]:: --control=fd:ctl-fd[,ack-fd]:: ctl-fifo / ack-fifo are opened and used as ctl-fd / ack-fd as follows. -Listen on ctl-fd descriptor for command to control measurement ('enable': enable events, -'disable': disable events, 'snapshot': AUX area tracing snapshot). Measurements can be -started with events disabled using --delay=-1 option. Optionally send control command -completion ('ack\n') to ack-fd descriptor to synchronize with the controlling process. -Example of bash shell script to enable and disable events during measurements: +Listen on ctl-fd descriptor for command to control measurement. + +Available commands: + 'enable' : enable events + 'disable' : disable events + 'snapshot': AUX area tracing snapshot). + +Measurements can be started with events disabled using --delay=-1 option. Optionally +send control command completion ('ack\n') to ack-fd descriptor to synchronize with the +controlling process. Example of bash shell script to enable and disable events during +measurements: #!/bin/bash diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index d068103690cc..8f7f4e9605d8 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -150,6 +150,7 @@ OPTIONS - snoop: type of snoop (if any) for the data at the time of the sample - dcacheline: the cacheline the data address is on at the time of the sample - phys_daddr: physical address of data being executed on at the time of sample + - data_page_size: the data page size of data being executed on at the time of sample And the default sort keys are changed to local_weight, mem, sym, dso, symbol_daddr, dso_daddr, snoop, tlb, locked, see '--mem-mode'. diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index 4f712fb8f175..44d37210fc8f 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -116,8 +116,9 @@ 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, uregs, brstack, brstacksym, flags, bpf-output, brstackinsn, - brstackoff, callindent, insn, insnlen, synth, phys_addr, metric, misc, srccode, ipc. + srcline, period, iregs, uregs, brstack, brstacksym, flags, bpf-output, + brstackinsn, brstackoff, callindent, insn, insnlen, synth, phys_addr, + metric, misc, srccode, ipc, data_page_size. 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 diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index 9f9f29025e49..5d4a673d7621 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -168,8 +168,9 @@ command line can be used: 'perf stat -e cycles -G cgroup_name -a -e cycles'. --for-each-cgroup name:: Expand event list for each cgroup in "name" (allow multiple cgroups separated -by comma). This has same effect that repeating -e option and -G option for -each event x name. This option cannot be used with -G/--cgroup option. +by comma). It also support regex patterns to match multiple groups. This has same +effect that repeating -e option and -G option for each event x name. This option +cannot be used with -G/--cgroup option. -o file:: --output file:: @@ -316,6 +317,10 @@ small group that need not have multiplexing is lowered. This option forbids the event merging logic from sharing events between groups and may be used to increase accuracy in this case. +--quiet:: +Don't print output. This is useful with perf stat record below to only +write data to the perf.data file. + STAT RECORD ----------- Stores stat data into perf data file. diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index cad7bf783413..bd446aba64f7 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -395,7 +395,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, * To obtain the auxtrace buffer file descriptor, the auxtrace * event must come first. */ - perf_evlist__to_front(evlist, cs_etm_evsel); + evlist__to_front(evlist, cs_etm_evsel); /* * In the case of per-cpu mmaps, we need the CPU on the @@ -420,7 +420,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, goto out; tracking_evsel = evlist__last(evlist); - perf_evlist__set_tracking_event(evlist, tracking_evsel); + evlist__set_tracking_event(evlist, tracking_evsel); tracking_evsel->core.attr.freq = 0; tracking_evsel->core.attr.sample_period = 1; diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile index dbef716a1913..fab3095fb5d0 100644 --- a/tools/perf/arch/arm64/Makefile +++ b/tools/perf/arch/arm64/Makefile @@ -4,6 +4,7 @@ PERF_HAVE_DWARF_REGS := 1 endif PERF_HAVE_JITDUMP := 1 PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1 +HAVE_KVM_STAT_SUPPORT := 1 # # Syscall table generation for perf diff --git a/tools/perf/arch/arm64/util/Build b/tools/perf/arch/arm64/util/Build index b53294d74b01..ead2f2275eee 100644 --- a/tools/perf/arch/arm64/util/Build +++ b/tools/perf/arch/arm64/util/Build @@ -2,6 +2,7 @@ perf-y += header.o perf-y += machine.o perf-y += perf_regs.o perf-y += tsc.o +perf-y += kvm-stat.o perf-$(CONFIG_DWARF) += dwarf-regs.o perf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o @@ -9,4 +10,4 @@ perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o perf-$(CONFIG_AUXTRACE) += ../../arm/util/pmu.o \ ../../arm/util/auxtrace.o \ ../../arm/util/cs-etm.o \ - arm-spe.o + arm-spe.o mem-events.o diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c index e3593063b3d1..414c8a5584b1 100644 --- a/tools/perf/arch/arm64/util/arm-spe.c +++ b/tools/perf/arch/arm64/util/arm-spe.c @@ -118,7 +118,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, * To obtain the auxtrace buffer file descriptor, the auxtrace event * must come first. */ - perf_evlist__to_front(evlist, arm_spe_evsel); + evlist__to_front(evlist, arm_spe_evsel); evsel__set_sample_bit(arm_spe_evsel, CPU); evsel__set_sample_bit(arm_spe_evsel, TIME); @@ -130,7 +130,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, return err; tracking_evsel = evlist__last(evlist); - perf_evlist__set_tracking_event(evlist, tracking_evsel); + evlist__set_tracking_event(evlist, tracking_evsel); tracking_evsel->core.attr.freq = 0; tracking_evsel->core.attr.sample_period = 1; diff --git a/tools/perf/arch/arm64/util/arm64_exception_types.h b/tools/perf/arch/arm64/util/arm64_exception_types.h new file mode 100644 index 000000000000..27c981ebe401 --- /dev/null +++ b/tools/perf/arch/arm64/util/arm64_exception_types.h @@ -0,0 +1,92 @@ +// SPDX-License-Identifier: GPL-2.0 +#ifndef ARCH_PERF_ARM64_EXCEPTION_TYPES_H +#define ARCH_PERF_ARM64_EXCEPTION_TYPES_H + +/* Per asm/virt.h */ +#define HVC_STUB_ERR 0xbadca11 + +/* Per asm/kvm_asm.h */ +#define ARM_EXCEPTION_IRQ 0 +#define ARM_EXCEPTION_EL1_SERROR 1 +#define ARM_EXCEPTION_TRAP 2 +#define ARM_EXCEPTION_IL 3 +/* The hyp-stub will return this for any kvm_call_hyp() call */ +#define ARM_EXCEPTION_HYP_GONE HVC_STUB_ERR + +#define kvm_arm_exception_type \ + {ARM_EXCEPTION_IRQ, "IRQ" }, \ + {ARM_EXCEPTION_EL1_SERROR, "SERROR" }, \ + {ARM_EXCEPTION_TRAP, "TRAP" }, \ + {ARM_EXCEPTION_IL, "ILLEGAL" }, \ + {ARM_EXCEPTION_HYP_GONE, "HYP_GONE" } + +/* Per asm/esr.h */ +#define ESR_ELx_EC_UNKNOWN (0x00) +#define ESR_ELx_EC_WFx (0x01) +/* Unallocated EC: 0x02 */ +#define ESR_ELx_EC_CP15_32 (0x03) +#define ESR_ELx_EC_CP15_64 (0x04) +#define ESR_ELx_EC_CP14_MR (0x05) +#define ESR_ELx_EC_CP14_LS (0x06) +#define ESR_ELx_EC_FP_ASIMD (0x07) +#define ESR_ELx_EC_CP10_ID (0x08) /* EL2 only */ +#define ESR_ELx_EC_PAC (0x09) /* EL2 and above */ +/* Unallocated EC: 0x0A - 0x0B */ +#define ESR_ELx_EC_CP14_64 (0x0C) +/* Unallocated EC: 0x0d */ +#define ESR_ELx_EC_ILL (0x0E) +/* Unallocated EC: 0x0F - 0x10 */ +#define ESR_ELx_EC_SVC32 (0x11) +#define ESR_ELx_EC_HVC32 (0x12) /* EL2 only */ +#define ESR_ELx_EC_SMC32 (0x13) /* EL2 and above */ +/* Unallocated EC: 0x14 */ +#define ESR_ELx_EC_SVC64 (0x15) +#define ESR_ELx_EC_HVC64 (0x16) /* EL2 and above */ +#define ESR_ELx_EC_SMC64 (0x17) /* EL2 and above */ +#define ESR_ELx_EC_SYS64 (0x18) +#define ESR_ELx_EC_SVE (0x19) +#define ESR_ELx_EC_ERET (0x1a) /* EL2 only */ +/* Unallocated EC: 0x1b - 0x1E */ +#define ESR_ELx_EC_IMP_DEF (0x1f) /* EL3 only */ +#define ESR_ELx_EC_IABT_LOW (0x20) +#define ESR_ELx_EC_IABT_CUR (0x21) +#define ESR_ELx_EC_PC_ALIGN (0x22) +/* Unallocated EC: 0x23 */ +#define ESR_ELx_EC_DABT_LOW (0x24) +#define ESR_ELx_EC_DABT_CUR (0x25) +#define ESR_ELx_EC_SP_ALIGN (0x26) +/* Unallocated EC: 0x27 */ +#define ESR_ELx_EC_FP_EXC32 (0x28) +/* Unallocated EC: 0x29 - 0x2B */ +#define ESR_ELx_EC_FP_EXC64 (0x2C) +/* Unallocated EC: 0x2D - 0x2E */ +#define ESR_ELx_EC_SERROR (0x2F) +#define ESR_ELx_EC_BREAKPT_LOW (0x30) +#define ESR_ELx_EC_BREAKPT_CUR (0x31) +#define ESR_ELx_EC_SOFTSTP_LOW (0x32) +#define ESR_ELx_EC_SOFTSTP_CUR (0x33) +#define ESR_ELx_EC_WATCHPT_LOW (0x34) +#define ESR_ELx_EC_WATCHPT_CUR (0x35) +/* Unallocated EC: 0x36 - 0x37 */ +#define ESR_ELx_EC_BKPT32 (0x38) +/* Unallocated EC: 0x39 */ +#define ESR_ELx_EC_VECTOR32 (0x3A) /* EL2 only */ +/* Unallocated EC: 0x3B */ +#define ESR_ELx_EC_BRK64 (0x3C) +/* Unallocated EC: 0x3D - 0x3F */ +#define ESR_ELx_EC_MAX (0x3F) + +#define ECN(x) { ESR_ELx_EC_##x, #x } + +#define kvm_arm_exception_class \ + ECN(UNKNOWN), ECN(WFx), ECN(CP15_32), ECN(CP15_64), ECN(CP14_MR), \ + ECN(CP14_LS), ECN(FP_ASIMD), ECN(CP10_ID), ECN(PAC), ECN(CP14_64), \ + ECN(SVC64), ECN(HVC64), ECN(SMC64), ECN(SYS64), ECN(SVE), \ + ECN(IMP_DEF), ECN(IABT_LOW), ECN(IABT_CUR), \ + ECN(PC_ALIGN), ECN(DABT_LOW), ECN(DABT_CUR), \ + ECN(SP_ALIGN), ECN(FP_EXC32), ECN(FP_EXC64), ECN(SERROR), \ + ECN(BREAKPT_LOW), ECN(BREAKPT_CUR), ECN(SOFTSTP_LOW), \ + ECN(SOFTSTP_CUR), ECN(WATCHPT_LOW), ECN(WATCHPT_CUR), \ + ECN(BKPT32), ECN(VECTOR32), ECN(BRK64) + +#endif /* ARCH_PERF_ARM64_EXCEPTION_TYPES_H */ diff --git a/tools/perf/arch/arm64/util/kvm-stat.c b/tools/perf/arch/arm64/util/kvm-stat.c new file mode 100644 index 000000000000..50376b9062c1 --- /dev/null +++ b/tools/perf/arch/arm64/util/kvm-stat.c @@ -0,0 +1,85 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <errno.h> +#include <memory.h> +#include "../../util/evsel.h" +#include "../../util/kvm-stat.h" +#include "arm64_exception_types.h" +#include "debug.h" + +define_exit_reasons_table(arm64_exit_reasons, kvm_arm_exception_type); +define_exit_reasons_table(arm64_trap_exit_reasons, kvm_arm_exception_class); + +const char *kvm_trap_exit_reason = "esr_ec"; +const char *vcpu_id_str = "id"; +const int decode_str_len = 20; +const char *kvm_exit_reason = "ret"; +const char *kvm_entry_trace = "kvm:kvm_entry"; +const char *kvm_exit_trace = "kvm:kvm_exit"; + +const char *kvm_events_tp[] = { + "kvm:kvm_entry", + "kvm:kvm_exit", + NULL, +}; + +static void event_get_key(struct evsel *evsel, + struct perf_sample *sample, + struct event_key *key) +{ + key->info = 0; + key->key = evsel__intval(evsel, sample, kvm_exit_reason); + key->exit_reasons = arm64_exit_reasons; + + /* + * TRAP exceptions carry exception class info in esr_ec field + * and, hence, we need to use a different exit_reasons table to + * properly decode event's est_ec. + */ + if (key->key == ARM_EXCEPTION_TRAP) { + key->key = evsel__intval(evsel, sample, kvm_trap_exit_reason); + key->exit_reasons = arm64_trap_exit_reasons; + } +} + +static bool event_begin(struct evsel *evsel, + struct perf_sample *sample __maybe_unused, + struct event_key *key __maybe_unused) +{ + return !strcmp(evsel->name, kvm_entry_trace); +} + +static bool event_end(struct evsel *evsel, + struct perf_sample *sample, + struct event_key *key) +{ + if (!strcmp(evsel->name, kvm_exit_trace)) { + event_get_key(evsel, sample, key); + return true; + } + return false; +} + +static struct kvm_events_ops exit_events = { + .is_begin_event = event_begin, + .is_end_event = event_end, + .decode_key = exit_event_decode_key, + .name = "VM-EXIT" +}; + +struct kvm_reg_events_ops kvm_reg_events_ops[] = { + { + .name = "vmexit", + .ops = &exit_events, + }, + { NULL }, +}; + +const char * const kvm_skip_events[] = { + NULL, +}; + +int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid __maybe_unused) +{ + kvm->exit_reasons_isa = "arm64"; + return 0; +} diff --git a/tools/perf/arch/arm64/util/mem-events.c b/tools/perf/arch/arm64/util/mem-events.c new file mode 100644 index 000000000000..2a2497372671 --- /dev/null +++ b/tools/perf/arch/arm64/util/mem-events.c @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "map_symbol.h" +#include "mem-events.h" + +#define E(t, n, s) { .tag = t, .name = n, .sysfs_name = s } + +static struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = { + E("spe-load", "arm_spe_0/ts_enable=1,load_filter=1,store_filter=0,min_latency=%u/", "arm_spe_0"), + E("spe-store", "arm_spe_0/ts_enable=1,load_filter=0,store_filter=1/", "arm_spe_0"), + E("spe-ldst", "arm_spe_0/ts_enable=1,load_filter=1,store_filter=1,min_latency=%u/", "arm_spe_0"), +}; + +static char mem_ev_name[100]; + +struct perf_mem_event *perf_mem_events__ptr(int i) +{ + if (i >= PERF_MEM_EVENTS__MAX) + return NULL; + + return &perf_mem_events[i]; +} + +char *perf_mem_events__name(int i) +{ + struct perf_mem_event *e = perf_mem_events__ptr(i); + + if (i >= PERF_MEM_EVENTS__MAX) + return NULL; + + if (i == PERF_MEM_EVENTS__LOAD || i == PERF_MEM_EVENTS__LOAD_STORE) + scnprintf(mem_ev_name, sizeof(mem_ev_name), + e->name, perf_mem_events__loads_ldlat); + else /* PERF_MEM_EVENTS__STORE */ + scnprintf(mem_ev_name, sizeof(mem_ev_name), e->name); + + return mem_ev_name; +} diff --git a/tools/perf/arch/arm64/util/perf_regs.c b/tools/perf/arch/arm64/util/perf_regs.c index 2833e101a7c6..54efa12fdbea 100644 --- a/tools/perf/arch/arm64/util/perf_regs.c +++ b/tools/perf/arch/arm64/util/perf_regs.c @@ -2,5 +2,38 @@ #include "../../../util/perf_regs.h" const struct sample_reg sample_reg_masks[] = { + SMPL_REG(x0, PERF_REG_ARM64_X0), + SMPL_REG(x1, PERF_REG_ARM64_X1), + SMPL_REG(x2, PERF_REG_ARM64_X2), + SMPL_REG(x3, PERF_REG_ARM64_X3), + SMPL_REG(x4, PERF_REG_ARM64_X4), + SMPL_REG(x5, PERF_REG_ARM64_X5), + SMPL_REG(x6, PERF_REG_ARM64_X6), + SMPL_REG(x7, PERF_REG_ARM64_X7), + SMPL_REG(x8, PERF_REG_ARM64_X8), + SMPL_REG(x9, PERF_REG_ARM64_X9), + SMPL_REG(x10, PERF_REG_ARM64_X10), + SMPL_REG(x11, PERF_REG_ARM64_X11), + SMPL_REG(x12, PERF_REG_ARM64_X12), + SMPL_REG(x13, PERF_REG_ARM64_X13), + SMPL_REG(x14, PERF_REG_ARM64_X14), + SMPL_REG(x15, PERF_REG_ARM64_X15), + SMPL_REG(x16, PERF_REG_ARM64_X16), + SMPL_REG(x17, PERF_REG_ARM64_X17), + SMPL_REG(x18, PERF_REG_ARM64_X18), + SMPL_REG(x19, PERF_REG_ARM64_X19), + SMPL_REG(x20, PERF_REG_ARM64_X20), + SMPL_REG(x21, PERF_REG_ARM64_X21), + SMPL_REG(x22, PERF_REG_ARM64_X22), + SMPL_REG(x23, PERF_REG_ARM64_X23), + SMPL_REG(x24, PERF_REG_ARM64_X24), + SMPL_REG(x25, PERF_REG_ARM64_X25), + SMPL_REG(x26, PERF_REG_ARM64_X26), + SMPL_REG(x27, PERF_REG_ARM64_X27), + SMPL_REG(x28, PERF_REG_ARM64_X28), + SMPL_REG(x29, PERF_REG_ARM64_X29), + SMPL_REG(lr, PERF_REG_ARM64_LR), + SMPL_REG(sp, PERF_REG_ARM64_SP), + SMPL_REG(pc, PERF_REG_ARM64_PC), SMPL_REG_END }; diff --git a/tools/perf/arch/mips/Build b/tools/perf/arch/mips/Build index 1bb8bf6d7fd4..e4e5f33c84d8 100644 --- a/tools/perf/arch/mips/Build +++ b/tools/perf/arch/mips/Build @@ -1 +1 @@ -# empty +perf-y += util/ diff --git a/tools/perf/arch/mips/annotate/instructions.c b/tools/perf/arch/mips/annotate/instructions.c new file mode 100644 index 000000000000..340993f2a897 --- /dev/null +++ b/tools/perf/arch/mips/annotate/instructions.c @@ -0,0 +1,46 @@ +// SPDX-License-Identifier: GPL-2.0 + +static +struct ins_ops *mips__associate_ins_ops(struct arch *arch, const char *name) +{ + struct ins_ops *ops = NULL; + + if (!strncmp(name, "bal", 3) || + !strncmp(name, "bgezal", 6) || + !strncmp(name, "bltzal", 6) || + !strncmp(name, "bgtzal", 6) || + !strncmp(name, "blezal", 6) || + !strncmp(name, "beqzal", 6) || + !strncmp(name, "bnezal", 6) || + !strncmp(name, "bgtzl", 5) || + !strncmp(name, "bltzl", 5) || + !strncmp(name, "bgezl", 5) || + !strncmp(name, "blezl", 5) || + !strncmp(name, "jialc", 5) || + !strncmp(name, "beql", 4) || + !strncmp(name, "bnel", 4) || + !strncmp(name, "jal", 3)) + ops = &call_ops; + else if (!strncmp(name, "jr", 2)) + ops = &ret_ops; + else if (name[0] == 'j' || name[0] == 'b') + ops = &jump_ops; + else + return NULL; + + arch__associate_ins_ops(arch, name, ops); + + return ops; +} + +static +int mips__annotate_init(struct arch *arch, char *cpuid __maybe_unused) +{ + if (!arch->initialized) { + arch->associate_instruction_ops = mips__associate_ins_ops; + arch->initialized = true; + arch->objdump.comment_char = '#'; + } + + return 0; +} diff --git a/tools/perf/arch/powerpc/Makefile b/tools/perf/arch/powerpc/Makefile index e58d00d62f02..840ea0e59287 100644 --- a/tools/perf/arch/powerpc/Makefile +++ b/tools/perf/arch/powerpc/Makefile @@ -14,7 +14,6 @@ PERF_HAVE_JITDUMP := 1 out := $(OUTPUT)arch/powerpc/include/generated/asm header32 := $(out)/syscalls_32.c header64 := $(out)/syscalls_64.c -syskrn := $(srctree)/arch/powerpc/kernel/syscalls/syscall.tbl sysprf := $(srctree)/tools/perf/arch/powerpc/entry/syscalls sysdef := $(sysprf)/syscall.tbl systbl := $(sysprf)/mksyscalltbl @@ -23,15 +22,9 @@ systbl := $(sysprf)/mksyscalltbl _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') $(header64): $(sysdef) $(systbl) - @(test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \ - (diff -B $(sysdef) $(syskrn) >/dev/null) \ - || echo "Warning: Kernel ABI header at '$(sysdef)' differs from latest version at '$(syskrn)'" >&2 )) || true $(Q)$(SHELL) '$(systbl)' '64' $(sysdef) > $@ $(header32): $(sysdef) $(systbl) - @(test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \ - (diff -B $(sysdef) $(syskrn) >/dev/null) \ - || echo "Warning: Kernel ABI header at '$(sysdef)' differs from latest version at '$(syskrn)'" >&2 )) || true $(Q)$(SHELL) '$(systbl)' '32' $(sysdef) > $@ clean:: diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl index b168364ac050..f744eb5cba88 100644 --- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl @@ -9,7 +9,9 @@ # 0 nospu restart_syscall sys_restart_syscall 1 nospu exit sys_exit -2 nospu fork ppc_fork +2 32 fork ppc_fork sys_fork +2 64 fork sys_fork +2 spu fork sys_ni_syscall 3 common read sys_read 4 common write sys_write 5 common open sys_open compat_sys_open @@ -158,7 +160,9 @@ 119 32 sigreturn sys_sigreturn compat_sys_sigreturn 119 64 sigreturn sys_ni_syscall 119 spu sigreturn sys_ni_syscall -120 nospu clone ppc_clone +120 32 clone ppc_clone sys_clone +120 64 clone sys_clone +120 spu clone sys_ni_syscall 121 common setdomainname sys_setdomainname 122 common uname sys_newuname 123 common modify_ldt sys_ni_syscall @@ -240,7 +244,9 @@ 186 spu sendfile sys_sendfile64 187 common getpmsg sys_ni_syscall 188 common putpmsg sys_ni_syscall -189 nospu vfork ppc_vfork +189 32 vfork ppc_vfork sys_vfork +189 64 vfork sys_vfork +189 spu vfork sys_ni_syscall 190 common ugetrlimit sys_getrlimit compat_sys_getrlimit 191 common readahead sys_readahead compat_sys_readahead 192 32 mmap2 sys_mmap2 compat_sys_mmap2 @@ -316,8 +322,8 @@ 248 32 clock_nanosleep sys_clock_nanosleep_time32 248 64 clock_nanosleep sys_clock_nanosleep 248 spu clock_nanosleep sys_clock_nanosleep -249 32 swapcontext ppc_swapcontext ppc32_swapcontext -249 64 swapcontext ppc64_swapcontext +249 32 swapcontext ppc_swapcontext compat_sys_swapcontext +249 64 swapcontext sys_swapcontext 249 spu swapcontext sys_ni_syscall 250 common tgkill sys_tgkill 251 32 utimes sys_utimes_time32 @@ -456,7 +462,7 @@ 361 common bpf sys_bpf 362 nospu execveat sys_execveat compat_sys_execveat 363 32 switch_endian sys_ni_syscall -363 64 switch_endian ppc_switch_endian +363 64 switch_endian sys_switch_endian 363 spu switch_endian sys_ni_syscall 364 common userfaultfd sys_userfaultfd 365 common membarrier sys_membarrier @@ -516,6 +522,12 @@ 432 common fsmount sys_fsmount 433 common fspick sys_fspick 434 common pidfd_open sys_pidfd_open -435 nospu clone3 ppc_clone3 +435 32 clone3 ppc_clone3 sys_clone3 +435 64 clone3 sys_clone3 +435 spu clone3 sys_ni_syscall +436 common close_range sys_close_range 437 common openat2 sys_openat2 438 common pidfd_getfd sys_pidfd_getfd +439 common faccessat2 sys_faccessat2 +440 common process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 diff --git a/tools/perf/arch/s390/Makefile b/tools/perf/arch/s390/Makefile index 6ac8887be7c9..74bffbea03e2 100644 --- a/tools/perf/arch/s390/Makefile +++ b/tools/perf/arch/s390/Makefile @@ -12,7 +12,6 @@ PERF_HAVE_JITDUMP := 1 out := $(OUTPUT)arch/s390/include/generated/asm header := $(out)/syscalls_64.c -syskrn := $(srctree)/arch/s390/kernel/syscalls/syscall.tbl sysprf := $(srctree)/tools/perf/arch/s390/entry/syscalls sysdef := $(sysprf)/syscall.tbl systbl := $(sysprf)/mksyscalltbl @@ -21,9 +20,6 @@ systbl := $(sysprf)/mksyscalltbl _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') $(header): $(sysdef) $(systbl) - @(test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \ - (diff -B $(sysdef) $(syskrn) >/dev/null) \ - || echo "Warning: Kernel ABI header at '$(sysdef)' differs from latest version at '$(syskrn)'" >&2 )) || true $(Q)$(SHELL) '$(systbl)' $(sysdef) > $@ clean:: diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl index d2fa9647ce25..d443423495e5 100644 --- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -15,86 +15,86 @@ 5 common open sys_open compat_sys_open 6 common close sys_close sys_close 7 common restart_syscall sys_restart_syscall sys_restart_syscall -8 common creat sys_creat compat_sys_creat -9 common link sys_link compat_sys_link -10 common unlink sys_unlink compat_sys_unlink +8 common creat sys_creat sys_creat +9 common link sys_link sys_link +10 common unlink sys_unlink sys_unlink 11 common execve sys_execve compat_sys_execve -12 common chdir sys_chdir compat_sys_chdir -13 32 time - compat_sys_time -14 common mknod sys_mknod compat_sys_mknod -15 common chmod sys_chmod compat_sys_chmod -16 32 lchown - compat_sys_s390_lchown16 +12 common chdir sys_chdir sys_chdir +13 32 time - sys_time32 +14 common mknod sys_mknod sys_mknod +15 common chmod sys_chmod sys_chmod +16 32 lchown - sys_lchown16 19 common lseek sys_lseek compat_sys_lseek 20 common getpid sys_getpid sys_getpid -21 common mount sys_mount -22 common umount sys_oldumount compat_sys_oldumount -23 32 setuid - compat_sys_s390_setuid16 -24 32 getuid - compat_sys_s390_getuid16 -25 32 stime - compat_sys_stime +21 common mount sys_mount sys_mount +22 common umount sys_oldumount sys_oldumount +23 32 setuid - sys_setuid16 +24 32 getuid - sys_getuid16 +25 32 stime - sys_stime32 26 common ptrace sys_ptrace compat_sys_ptrace 27 common alarm sys_alarm sys_alarm 29 common pause sys_pause sys_pause -30 common utime sys_utime compat_sys_utime -33 common access sys_access compat_sys_access +30 common utime sys_utime sys_utime32 +33 common access sys_access sys_access 34 common nice sys_nice sys_nice 36 common sync sys_sync sys_sync 37 common kill sys_kill sys_kill -38 common rename sys_rename compat_sys_rename -39 common mkdir sys_mkdir compat_sys_mkdir -40 common rmdir sys_rmdir compat_sys_rmdir +38 common rename sys_rename sys_rename +39 common mkdir sys_mkdir sys_mkdir +40 common rmdir sys_rmdir sys_rmdir 41 common dup sys_dup sys_dup -42 common pipe sys_pipe compat_sys_pipe +42 common pipe sys_pipe sys_pipe 43 common times sys_times compat_sys_times -45 common brk sys_brk compat_sys_brk -46 32 setgid - compat_sys_s390_setgid16 -47 32 getgid - compat_sys_s390_getgid16 -48 common signal sys_signal compat_sys_signal -49 32 geteuid - compat_sys_s390_geteuid16 -50 32 getegid - compat_sys_s390_getegid16 -51 common acct sys_acct compat_sys_acct -52 common umount2 sys_umount compat_sys_umount +45 common brk sys_brk sys_brk +46 32 setgid - sys_setgid16 +47 32 getgid - sys_getgid16 +48 common signal sys_signal sys_signal +49 32 geteuid - sys_geteuid16 +50 32 getegid - sys_getegid16 +51 common acct sys_acct sys_acct +52 common umount2 sys_umount sys_umount 54 common ioctl sys_ioctl compat_sys_ioctl 55 common fcntl sys_fcntl compat_sys_fcntl 57 common setpgid sys_setpgid sys_setpgid 60 common umask sys_umask sys_umask -61 common chroot sys_chroot compat_sys_chroot +61 common chroot sys_chroot sys_chroot 62 common ustat sys_ustat compat_sys_ustat 63 common dup2 sys_dup2 sys_dup2 64 common getppid sys_getppid sys_getppid 65 common getpgrp sys_getpgrp sys_getpgrp 66 common setsid sys_setsid sys_setsid 67 common sigaction sys_sigaction compat_sys_sigaction -70 32 setreuid - compat_sys_s390_setreuid16 -71 32 setregid - compat_sys_s390_setregid16 -72 common sigsuspend sys_sigsuspend compat_sys_sigsuspend +70 32 setreuid - sys_setreuid16 +71 32 setregid - sys_setregid16 +72 common sigsuspend sys_sigsuspend sys_sigsuspend 73 common sigpending sys_sigpending compat_sys_sigpending -74 common sethostname sys_sethostname compat_sys_sethostname +74 common sethostname sys_sethostname sys_sethostname 75 common setrlimit sys_setrlimit compat_sys_setrlimit 76 32 getrlimit - compat_sys_old_getrlimit 77 common getrusage sys_getrusage compat_sys_getrusage 78 common gettimeofday sys_gettimeofday compat_sys_gettimeofday 79 common settimeofday sys_settimeofday compat_sys_settimeofday -80 32 getgroups - compat_sys_s390_getgroups16 -81 32 setgroups - compat_sys_s390_setgroups16 -83 common symlink sys_symlink compat_sys_symlink -85 common readlink sys_readlink compat_sys_readlink -86 common uselib sys_uselib compat_sys_uselib -87 common swapon sys_swapon compat_sys_swapon -88 common reboot sys_reboot compat_sys_reboot +80 32 getgroups - sys_getgroups16 +81 32 setgroups - sys_setgroups16 +83 common symlink sys_symlink sys_symlink +85 common readlink sys_readlink sys_readlink +86 common uselib sys_uselib sys_uselib +87 common swapon sys_swapon sys_swapon +88 common reboot sys_reboot sys_reboot 89 common readdir - compat_sys_old_readdir 90 common mmap sys_old_mmap compat_sys_s390_old_mmap -91 common munmap sys_munmap compat_sys_munmap +91 common munmap sys_munmap sys_munmap 92 common truncate sys_truncate compat_sys_truncate 93 common ftruncate sys_ftruncate compat_sys_ftruncate 94 common fchmod sys_fchmod sys_fchmod -95 32 fchown - compat_sys_s390_fchown16 +95 32 fchown - sys_fchown16 96 common getpriority sys_getpriority sys_getpriority 97 common setpriority sys_setpriority sys_setpriority 99 common statfs sys_statfs compat_sys_statfs 100 common fstatfs sys_fstatfs compat_sys_fstatfs 101 32 ioperm - - 102 common socketcall sys_socketcall compat_sys_socketcall -103 common syslog sys_syslog compat_sys_syslog +103 common syslog sys_syslog sys_syslog 104 common setitimer sys_setitimer compat_sys_setitimer 105 common getitimer sys_getitimer compat_sys_getitimer 106 common stat sys_newstat compat_sys_newstat @@ -104,76 +104,76 @@ 111 common vhangup sys_vhangup sys_vhangup 112 common idle - - 114 common wait4 sys_wait4 compat_sys_wait4 -115 common swapoff sys_swapoff compat_sys_swapoff +115 common swapoff sys_swapoff sys_swapoff 116 common sysinfo sys_sysinfo compat_sys_sysinfo 117 common ipc sys_s390_ipc compat_sys_s390_ipc 118 common fsync sys_fsync sys_fsync 119 common sigreturn sys_sigreturn compat_sys_sigreturn -120 common clone sys_clone compat_sys_clone -121 common setdomainname sys_setdomainname compat_sys_setdomainname -122 common uname sys_newuname compat_sys_newuname -124 common adjtimex sys_adjtimex compat_sys_adjtimex -125 common mprotect sys_mprotect compat_sys_mprotect +120 common clone sys_clone sys_clone +121 common setdomainname sys_setdomainname sys_setdomainname +122 common uname sys_newuname sys_newuname +124 common adjtimex sys_adjtimex sys_adjtimex_time32 +125 common mprotect sys_mprotect sys_mprotect 126 common sigprocmask sys_sigprocmask compat_sys_sigprocmask 127 common create_module - - -128 common init_module sys_init_module compat_sys_init_module -129 common delete_module sys_delete_module compat_sys_delete_module +128 common init_module sys_init_module sys_init_module +129 common delete_module sys_delete_module sys_delete_module 130 common get_kernel_syms - - -131 common quotactl sys_quotactl compat_sys_quotactl +131 common quotactl sys_quotactl sys_quotactl 132 common getpgid sys_getpgid sys_getpgid 133 common fchdir sys_fchdir sys_fchdir -134 common bdflush sys_bdflush compat_sys_bdflush -135 common sysfs sys_sysfs compat_sys_sysfs +134 common bdflush sys_bdflush sys_bdflush +135 common sysfs sys_sysfs sys_sysfs 136 common personality sys_s390_personality sys_s390_personality 137 common afs_syscall - - -138 32 setfsuid - compat_sys_s390_setfsuid16 -139 32 setfsgid - compat_sys_s390_setfsgid16 -140 32 _llseek - compat_sys_llseek +138 32 setfsuid - sys_setfsuid16 +139 32 setfsgid - sys_setfsgid16 +140 32 _llseek - sys_llseek 141 common getdents sys_getdents compat_sys_getdents 142 32 _newselect - compat_sys_select 142 64 select sys_select - 143 common flock sys_flock sys_flock -144 common msync sys_msync compat_sys_msync -145 common readv sys_readv -146 common writev sys_writev +144 common msync sys_msync sys_msync +145 common readv sys_readv sys_readv +146 common writev sys_writev sys_writev 147 common getsid sys_getsid sys_getsid 148 common fdatasync sys_fdatasync sys_fdatasync 149 common _sysctl - - -150 common mlock sys_mlock compat_sys_mlock -151 common munlock sys_munlock compat_sys_munlock +150 common mlock sys_mlock sys_mlock +151 common munlock sys_munlock sys_munlock 152 common mlockall sys_mlockall sys_mlockall 153 common munlockall sys_munlockall sys_munlockall -154 common sched_setparam sys_sched_setparam compat_sys_sched_setparam -155 common sched_getparam sys_sched_getparam compat_sys_sched_getparam -156 common sched_setscheduler sys_sched_setscheduler compat_sys_sched_setscheduler +154 common sched_setparam sys_sched_setparam sys_sched_setparam +155 common sched_getparam sys_sched_getparam sys_sched_getparam +156 common sched_setscheduler sys_sched_setscheduler sys_sched_setscheduler 157 common sched_getscheduler sys_sched_getscheduler sys_sched_getscheduler 158 common sched_yield sys_sched_yield sys_sched_yield 159 common sched_get_priority_max sys_sched_get_priority_max sys_sched_get_priority_max 160 common sched_get_priority_min sys_sched_get_priority_min sys_sched_get_priority_min -161 common sched_rr_get_interval sys_sched_rr_get_interval compat_sys_sched_rr_get_interval -162 common nanosleep sys_nanosleep compat_sys_nanosleep -163 common mremap sys_mremap compat_sys_mremap -164 32 setresuid - compat_sys_s390_setresuid16 -165 32 getresuid - compat_sys_s390_getresuid16 +161 common sched_rr_get_interval sys_sched_rr_get_interval sys_sched_rr_get_interval_time32 +162 common nanosleep sys_nanosleep sys_nanosleep_time32 +163 common mremap sys_mremap sys_mremap +164 32 setresuid - sys_setresuid16 +165 32 getresuid - sys_getresuid16 167 common query_module - - -168 common poll sys_poll compat_sys_poll +168 common poll sys_poll sys_poll 169 common nfsservctl - - -170 32 setresgid - compat_sys_s390_setresgid16 -171 32 getresgid - compat_sys_s390_getresgid16 -172 common prctl sys_prctl compat_sys_prctl +170 32 setresgid - sys_setresgid16 +171 32 getresgid - sys_getresgid16 +172 common prctl sys_prctl sys_prctl 173 common rt_sigreturn sys_rt_sigreturn compat_sys_rt_sigreturn 174 common rt_sigaction sys_rt_sigaction compat_sys_rt_sigaction 175 common rt_sigprocmask sys_rt_sigprocmask compat_sys_rt_sigprocmask 176 common rt_sigpending sys_rt_sigpending compat_sys_rt_sigpending -177 common rt_sigtimedwait sys_rt_sigtimedwait compat_sys_rt_sigtimedwait +177 common rt_sigtimedwait sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time32 178 common rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo 179 common rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend 180 common pread64 sys_pread64 compat_sys_s390_pread64 181 common pwrite64 sys_pwrite64 compat_sys_s390_pwrite64 -182 32 chown - compat_sys_s390_chown16 -183 common getcwd sys_getcwd compat_sys_getcwd -184 common capget sys_capget compat_sys_capget -185 common capset sys_capset compat_sys_capset +182 32 chown - sys_chown16 +183 common getcwd sys_getcwd sys_getcwd +184 common capget sys_capget sys_capget +185 common capset sys_capset sys_capset 186 common sigaltstack sys_sigaltstack compat_sys_sigaltstack 187 common sendfile sys_sendfile64 compat_sys_sendfile 188 common getpmsg - - @@ -187,7 +187,7 @@ 195 32 stat64 - compat_sys_s390_stat64 196 32 lstat64 - compat_sys_s390_lstat64 197 32 fstat64 - compat_sys_s390_fstat64 -198 32 lchown32 - compat_sys_lchown +198 32 lchown32 - sys_lchown 198 64 lchown sys_lchown - 199 32 getuid32 - sys_getuid 199 64 getuid sys_getuid - @@ -201,21 +201,21 @@ 203 64 setreuid sys_setreuid - 204 32 setregid32 - sys_setregid 204 64 setregid sys_setregid - -205 32 getgroups32 - compat_sys_getgroups +205 32 getgroups32 - sys_getgroups 205 64 getgroups sys_getgroups - -206 32 setgroups32 - compat_sys_setgroups +206 32 setgroups32 - sys_setgroups 206 64 setgroups sys_setgroups - 207 32 fchown32 - sys_fchown 207 64 fchown sys_fchown - 208 32 setresuid32 - sys_setresuid 208 64 setresuid sys_setresuid - -209 32 getresuid32 - compat_sys_getresuid +209 32 getresuid32 - sys_getresuid 209 64 getresuid sys_getresuid - 210 32 setresgid32 - sys_setresgid 210 64 setresgid sys_setresgid - -211 32 getresgid32 - compat_sys_getresgid +211 32 getresgid32 - sys_getresgid 211 64 getresgid sys_getresgid - -212 32 chown32 - compat_sys_chown +212 32 chown32 - sys_chown 212 64 chown sys_chown - 213 32 setuid32 - sys_setuid 213 64 setuid sys_setuid - @@ -225,166 +225,222 @@ 215 64 setfsuid sys_setfsuid - 216 32 setfsgid32 - sys_setfsgid 216 64 setfsgid sys_setfsgid - -217 common pivot_root sys_pivot_root compat_sys_pivot_root -218 common mincore sys_mincore compat_sys_mincore -219 common madvise sys_madvise compat_sys_madvise -220 common getdents64 sys_getdents64 compat_sys_getdents64 +217 common pivot_root sys_pivot_root sys_pivot_root +218 common mincore sys_mincore sys_mincore +219 common madvise sys_madvise sys_madvise +220 common getdents64 sys_getdents64 sys_getdents64 221 32 fcntl64 - compat_sys_fcntl64 222 common readahead sys_readahead compat_sys_s390_readahead 223 32 sendfile64 - compat_sys_sendfile64 -224 common setxattr sys_setxattr compat_sys_setxattr -225 common lsetxattr sys_lsetxattr compat_sys_lsetxattr -226 common fsetxattr sys_fsetxattr compat_sys_fsetxattr -227 common getxattr sys_getxattr compat_sys_getxattr -228 common lgetxattr sys_lgetxattr compat_sys_lgetxattr -229 common fgetxattr sys_fgetxattr compat_sys_fgetxattr -230 common listxattr sys_listxattr compat_sys_listxattr -231 common llistxattr sys_llistxattr compat_sys_llistxattr -232 common flistxattr sys_flistxattr compat_sys_flistxattr -233 common removexattr sys_removexattr compat_sys_removexattr -234 common lremovexattr sys_lremovexattr compat_sys_lremovexattr -235 common fremovexattr sys_fremovexattr compat_sys_fremovexattr +224 common setxattr sys_setxattr sys_setxattr +225 common lsetxattr sys_lsetxattr sys_lsetxattr +226 common fsetxattr sys_fsetxattr sys_fsetxattr +227 common getxattr sys_getxattr sys_getxattr +228 common lgetxattr sys_lgetxattr sys_lgetxattr +229 common fgetxattr sys_fgetxattr sys_fgetxattr +230 common listxattr sys_listxattr sys_listxattr +231 common llistxattr sys_llistxattr sys_llistxattr +232 common flistxattr sys_flistxattr sys_flistxattr +233 common removexattr sys_removexattr sys_removexattr +234 common lremovexattr sys_lremovexattr sys_lremovexattr +235 common fremovexattr sys_fremovexattr sys_fremovexattr 236 common gettid sys_gettid sys_gettid 237 common tkill sys_tkill sys_tkill -238 common futex sys_futex compat_sys_futex +238 common futex sys_futex sys_futex_time32 239 common sched_setaffinity sys_sched_setaffinity compat_sys_sched_setaffinity 240 common sched_getaffinity sys_sched_getaffinity compat_sys_sched_getaffinity 241 common tgkill sys_tgkill sys_tgkill 243 common io_setup sys_io_setup compat_sys_io_setup -244 common io_destroy sys_io_destroy compat_sys_io_destroy -245 common io_getevents sys_io_getevents compat_sys_io_getevents +244 common io_destroy sys_io_destroy sys_io_destroy +245 common io_getevents sys_io_getevents sys_io_getevents_time32 246 common io_submit sys_io_submit compat_sys_io_submit -247 common io_cancel sys_io_cancel compat_sys_io_cancel +247 common io_cancel sys_io_cancel sys_io_cancel 248 common exit_group sys_exit_group sys_exit_group 249 common epoll_create sys_epoll_create sys_epoll_create -250 common epoll_ctl sys_epoll_ctl compat_sys_epoll_ctl -251 common epoll_wait sys_epoll_wait compat_sys_epoll_wait -252 common set_tid_address sys_set_tid_address compat_sys_set_tid_address +250 common epoll_ctl sys_epoll_ctl sys_epoll_ctl +251 common epoll_wait sys_epoll_wait sys_epoll_wait +252 common set_tid_address sys_set_tid_address sys_set_tid_address 253 common fadvise64 sys_fadvise64_64 compat_sys_s390_fadvise64 254 common timer_create sys_timer_create compat_sys_timer_create -255 common timer_settime sys_timer_settime compat_sys_timer_settime -256 common timer_gettime sys_timer_gettime compat_sys_timer_gettime +255 common timer_settime sys_timer_settime sys_timer_settime32 +256 common timer_gettime sys_timer_gettime sys_timer_gettime32 257 common timer_getoverrun sys_timer_getoverrun sys_timer_getoverrun 258 common timer_delete sys_timer_delete sys_timer_delete -259 common clock_settime sys_clock_settime compat_sys_clock_settime -260 common clock_gettime sys_clock_gettime compat_sys_clock_gettime -261 common clock_getres sys_clock_getres compat_sys_clock_getres -262 common clock_nanosleep sys_clock_nanosleep compat_sys_clock_nanosleep +259 common clock_settime sys_clock_settime sys_clock_settime32 +260 common clock_gettime sys_clock_gettime sys_clock_gettime32 +261 common clock_getres sys_clock_getres sys_clock_getres_time32 +262 common clock_nanosleep sys_clock_nanosleep sys_clock_nanosleep_time32 264 32 fadvise64_64 - compat_sys_s390_fadvise64_64 265 common statfs64 sys_statfs64 compat_sys_statfs64 266 common fstatfs64 sys_fstatfs64 compat_sys_fstatfs64 -267 common remap_file_pages sys_remap_file_pages compat_sys_remap_file_pages +267 common remap_file_pages sys_remap_file_pages sys_remap_file_pages 268 common mbind sys_mbind compat_sys_mbind 269 common get_mempolicy sys_get_mempolicy compat_sys_get_mempolicy 270 common set_mempolicy sys_set_mempolicy compat_sys_set_mempolicy 271 common mq_open sys_mq_open compat_sys_mq_open -272 common mq_unlink sys_mq_unlink compat_sys_mq_unlink -273 common mq_timedsend sys_mq_timedsend compat_sys_mq_timedsend -274 common mq_timedreceive sys_mq_timedreceive compat_sys_mq_timedreceive +272 common mq_unlink sys_mq_unlink sys_mq_unlink +273 common mq_timedsend sys_mq_timedsend sys_mq_timedsend_time32 +274 common mq_timedreceive sys_mq_timedreceive sys_mq_timedreceive_time32 275 common mq_notify sys_mq_notify compat_sys_mq_notify 276 common mq_getsetattr sys_mq_getsetattr compat_sys_mq_getsetattr 277 common kexec_load sys_kexec_load compat_sys_kexec_load -278 common add_key sys_add_key compat_sys_add_key -279 common request_key sys_request_key compat_sys_request_key +278 common add_key sys_add_key sys_add_key +279 common request_key sys_request_key sys_request_key 280 common keyctl sys_keyctl compat_sys_keyctl 281 common waitid sys_waitid compat_sys_waitid 282 common ioprio_set sys_ioprio_set sys_ioprio_set 283 common ioprio_get sys_ioprio_get sys_ioprio_get 284 common inotify_init sys_inotify_init sys_inotify_init -285 common inotify_add_watch sys_inotify_add_watch compat_sys_inotify_add_watch +285 common inotify_add_watch sys_inotify_add_watch sys_inotify_add_watch 286 common inotify_rm_watch sys_inotify_rm_watch sys_inotify_rm_watch 287 common migrate_pages sys_migrate_pages compat_sys_migrate_pages 288 common openat sys_openat compat_sys_openat -289 common mkdirat sys_mkdirat compat_sys_mkdirat -290 common mknodat sys_mknodat compat_sys_mknodat -291 common fchownat sys_fchownat compat_sys_fchownat -292 common futimesat sys_futimesat compat_sys_futimesat +289 common mkdirat sys_mkdirat sys_mkdirat +290 common mknodat sys_mknodat sys_mknodat +291 common fchownat sys_fchownat sys_fchownat +292 common futimesat sys_futimesat sys_futimesat_time32 293 32 fstatat64 - compat_sys_s390_fstatat64 293 64 newfstatat sys_newfstatat - -294 common unlinkat sys_unlinkat compat_sys_unlinkat -295 common renameat sys_renameat compat_sys_renameat -296 common linkat sys_linkat compat_sys_linkat -297 common symlinkat sys_symlinkat compat_sys_symlinkat -298 common readlinkat sys_readlinkat compat_sys_readlinkat -299 common fchmodat sys_fchmodat compat_sys_fchmodat -300 common faccessat sys_faccessat compat_sys_faccessat -301 common pselect6 sys_pselect6 compat_sys_pselect6 -302 common ppoll sys_ppoll compat_sys_ppoll -303 common unshare sys_unshare compat_sys_unshare +294 common unlinkat sys_unlinkat sys_unlinkat +295 common renameat sys_renameat sys_renameat +296 common linkat sys_linkat sys_linkat +297 common symlinkat sys_symlinkat sys_symlinkat +298 common readlinkat sys_readlinkat sys_readlinkat +299 common fchmodat sys_fchmodat sys_fchmodat +300 common faccessat sys_faccessat sys_faccessat +301 common pselect6 sys_pselect6 compat_sys_pselect6_time32 +302 common ppoll sys_ppoll compat_sys_ppoll_time32 +303 common unshare sys_unshare sys_unshare 304 common set_robust_list sys_set_robust_list compat_sys_set_robust_list 305 common get_robust_list sys_get_robust_list compat_sys_get_robust_list -306 common splice sys_splice compat_sys_splice +306 common splice sys_splice sys_splice 307 common sync_file_range sys_sync_file_range compat_sys_s390_sync_file_range -308 common tee sys_tee compat_sys_tee +308 common tee sys_tee sys_tee 309 common vmsplice sys_vmsplice sys_vmsplice 310 common move_pages sys_move_pages compat_sys_move_pages -311 common getcpu sys_getcpu compat_sys_getcpu +311 common getcpu sys_getcpu sys_getcpu 312 common epoll_pwait sys_epoll_pwait compat_sys_epoll_pwait -313 common utimes sys_utimes compat_sys_utimes +313 common utimes sys_utimes sys_utimes_time32 314 common fallocate sys_fallocate compat_sys_s390_fallocate -315 common utimensat sys_utimensat compat_sys_utimensat +315 common utimensat sys_utimensat sys_utimensat_time32 316 common signalfd sys_signalfd compat_sys_signalfd 317 common timerfd - - 318 common eventfd sys_eventfd sys_eventfd 319 common timerfd_create sys_timerfd_create sys_timerfd_create -320 common timerfd_settime sys_timerfd_settime compat_sys_timerfd_settime -321 common timerfd_gettime sys_timerfd_gettime compat_sys_timerfd_gettime +320 common timerfd_settime sys_timerfd_settime sys_timerfd_settime32 +321 common timerfd_gettime sys_timerfd_gettime sys_timerfd_gettime32 322 common signalfd4 sys_signalfd4 compat_sys_signalfd4 323 common eventfd2 sys_eventfd2 sys_eventfd2 324 common inotify_init1 sys_inotify_init1 sys_inotify_init1 -325 common pipe2 sys_pipe2 compat_sys_pipe2 +325 common pipe2 sys_pipe2 sys_pipe2 326 common dup3 sys_dup3 sys_dup3 327 common epoll_create1 sys_epoll_create1 sys_epoll_create1 328 common preadv sys_preadv compat_sys_preadv 329 common pwritev sys_pwritev compat_sys_pwritev 330 common rt_tgsigqueueinfo sys_rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo -331 common perf_event_open sys_perf_event_open compat_sys_perf_event_open +331 common perf_event_open sys_perf_event_open sys_perf_event_open 332 common fanotify_init sys_fanotify_init sys_fanotify_init 333 common fanotify_mark sys_fanotify_mark compat_sys_fanotify_mark -334 common prlimit64 sys_prlimit64 compat_sys_prlimit64 -335 common name_to_handle_at sys_name_to_handle_at compat_sys_name_to_handle_at +334 common prlimit64 sys_prlimit64 sys_prlimit64 +335 common name_to_handle_at sys_name_to_handle_at sys_name_to_handle_at 336 common open_by_handle_at sys_open_by_handle_at compat_sys_open_by_handle_at -337 common clock_adjtime sys_clock_adjtime compat_sys_clock_adjtime +337 common clock_adjtime sys_clock_adjtime sys_clock_adjtime32 338 common syncfs sys_syncfs sys_syncfs 339 common setns sys_setns sys_setns 340 common process_vm_readv sys_process_vm_readv sys_process_vm_readv 341 common process_vm_writev sys_process_vm_writev sys_process_vm_writev 342 common s390_runtime_instr sys_s390_runtime_instr sys_s390_runtime_instr -343 common kcmp sys_kcmp compat_sys_kcmp -344 common finit_module sys_finit_module compat_sys_finit_module -345 common sched_setattr sys_sched_setattr compat_sys_sched_setattr -346 common sched_getattr sys_sched_getattr compat_sys_sched_getattr -347 common renameat2 sys_renameat2 compat_sys_renameat2 -348 common seccomp sys_seccomp compat_sys_seccomp -349 common getrandom sys_getrandom compat_sys_getrandom -350 common memfd_create sys_memfd_create compat_sys_memfd_create -351 common bpf sys_bpf compat_sys_bpf -352 common s390_pci_mmio_write sys_s390_pci_mmio_write compat_sys_s390_pci_mmio_write -353 common s390_pci_mmio_read sys_s390_pci_mmio_read compat_sys_s390_pci_mmio_read +343 common kcmp sys_kcmp sys_kcmp +344 common finit_module sys_finit_module sys_finit_module +345 common sched_setattr sys_sched_setattr sys_sched_setattr +346 common sched_getattr sys_sched_getattr sys_sched_getattr +347 common renameat2 sys_renameat2 sys_renameat2 +348 common seccomp sys_seccomp sys_seccomp +349 common getrandom sys_getrandom sys_getrandom +350 common memfd_create sys_memfd_create sys_memfd_create +351 common bpf sys_bpf sys_bpf +352 common s390_pci_mmio_write sys_s390_pci_mmio_write sys_s390_pci_mmio_write +353 common s390_pci_mmio_read sys_s390_pci_mmio_read sys_s390_pci_mmio_read 354 common execveat sys_execveat compat_sys_execveat 355 common userfaultfd sys_userfaultfd sys_userfaultfd 356 common membarrier sys_membarrier sys_membarrier -357 common recvmmsg sys_recvmmsg compat_sys_recvmmsg +357 common recvmmsg sys_recvmmsg compat_sys_recvmmsg_time32 358 common sendmmsg sys_sendmmsg compat_sys_sendmmsg 359 common socket sys_socket sys_socket -360 common socketpair sys_socketpair compat_sys_socketpair -361 common bind sys_bind compat_sys_bind -362 common connect sys_connect compat_sys_connect +360 common socketpair sys_socketpair sys_socketpair +361 common bind sys_bind sys_bind +362 common connect sys_connect sys_connect 363 common listen sys_listen sys_listen -364 common accept4 sys_accept4 compat_sys_accept4 +364 common accept4 sys_accept4 sys_accept4 365 common getsockopt sys_getsockopt sys_getsockopt 366 common setsockopt sys_setsockopt sys_setsockopt -367 common getsockname sys_getsockname compat_sys_getsockname -368 common getpeername sys_getpeername compat_sys_getpeername -369 common sendto sys_sendto compat_sys_sendto +367 common getsockname sys_getsockname sys_getsockname +368 common getpeername sys_getpeername sys_getpeername +369 common sendto sys_sendto sys_sendto 370 common sendmsg sys_sendmsg compat_sys_sendmsg 371 common recvfrom sys_recvfrom compat_sys_recvfrom 372 common recvmsg sys_recvmsg compat_sys_recvmsg 373 common shutdown sys_shutdown sys_shutdown -374 common mlock2 sys_mlock2 compat_sys_mlock2 -375 common copy_file_range sys_copy_file_range compat_sys_copy_file_range +374 common mlock2 sys_mlock2 sys_mlock2 +375 common copy_file_range sys_copy_file_range sys_copy_file_range 376 common preadv2 sys_preadv2 compat_sys_preadv2 377 common pwritev2 sys_pwritev2 compat_sys_pwritev2 -378 common s390_guarded_storage sys_s390_guarded_storage compat_sys_s390_guarded_storage -379 common statx sys_statx compat_sys_statx -380 common s390_sthyi sys_s390_sthyi compat_sys_s390_sthyi +378 common s390_guarded_storage sys_s390_guarded_storage sys_s390_guarded_storage +379 common statx sys_statx sys_statx +380 common s390_sthyi sys_s390_sthyi sys_s390_sthyi +381 common kexec_file_load sys_kexec_file_load sys_kexec_file_load +382 common io_pgetevents sys_io_pgetevents compat_sys_io_pgetevents +383 common rseq sys_rseq sys_rseq +384 common pkey_mprotect sys_pkey_mprotect sys_pkey_mprotect +385 common pkey_alloc sys_pkey_alloc sys_pkey_alloc +386 common pkey_free sys_pkey_free sys_pkey_free +# room for arch specific syscalls +392 64 semtimedop sys_semtimedop - +393 common semget sys_semget sys_semget +394 common semctl sys_semctl compat_sys_semctl +395 common shmget sys_shmget sys_shmget +396 common shmctl sys_shmctl compat_sys_shmctl +397 common shmat sys_shmat compat_sys_shmat +398 common shmdt sys_shmdt sys_shmdt +399 common msgget sys_msgget sys_msgget +400 common msgsnd sys_msgsnd compat_sys_msgsnd +401 common msgrcv sys_msgrcv compat_sys_msgrcv +402 common msgctl sys_msgctl compat_sys_msgctl +403 32 clock_gettime64 - sys_clock_gettime +404 32 clock_settime64 - sys_clock_settime +405 32 clock_adjtime64 - sys_clock_adjtime +406 32 clock_getres_time64 - sys_clock_getres +407 32 clock_nanosleep_time64 - sys_clock_nanosleep +408 32 timer_gettime64 - sys_timer_gettime +409 32 timer_settime64 - sys_timer_settime +410 32 timerfd_gettime64 - sys_timerfd_gettime +411 32 timerfd_settime64 - sys_timerfd_settime +412 32 utimensat_time64 - sys_utimensat +413 32 pselect6_time64 - compat_sys_pselect6_time64 +414 32 ppoll_time64 - compat_sys_ppoll_time64 +416 32 io_pgetevents_time64 - sys_io_pgetevents +417 32 recvmmsg_time64 - compat_sys_recvmmsg_time64 +418 32 mq_timedsend_time64 - sys_mq_timedsend +419 32 mq_timedreceive_time64 - sys_mq_timedreceive +420 32 semtimedop_time64 - sys_semtimedop +421 32 rt_sigtimedwait_time64 - compat_sys_rt_sigtimedwait_time64 +422 32 futex_time64 - sys_futex +423 32 sched_rr_get_interval_time64 - sys_sched_rr_get_interval +424 common pidfd_send_signal sys_pidfd_send_signal sys_pidfd_send_signal +425 common io_uring_setup sys_io_uring_setup sys_io_uring_setup +426 common io_uring_enter sys_io_uring_enter sys_io_uring_enter +427 common io_uring_register sys_io_uring_register sys_io_uring_register +428 common open_tree sys_open_tree sys_open_tree +429 common move_mount sys_move_mount sys_move_mount +430 common fsopen sys_fsopen sys_fsopen +431 common fsconfig sys_fsconfig sys_fsconfig +432 common fsmount sys_fsmount sys_fsmount +433 common fspick sys_fspick sys_fspick +434 common pidfd_open sys_pidfd_open sys_pidfd_open +435 common clone3 sys_clone3 sys_clone3 +436 common close_range sys_close_range sys_close_range +437 common openat2 sys_openat2 sys_openat2 +438 common pidfd_getfd sys_pidfd_getfd sys_pidfd_getfd +439 common faccessat2 sys_faccessat2 sys_faccessat2 +440 common process_madvise sys_process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index 379819244b91..78672124d28b 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -362,6 +362,7 @@ 438 common pidfd_getfd sys_pidfd_getfd 439 common faccessat2 sys_faccessat2 440 common process_madvise sys_process_madvise +441 common epoll_pwait2 sys_epoll_pwait2 # # Due to a historical design error, certain syscalls are numbered differently diff --git a/tools/perf/arch/x86/include/arch-tests.h b/tools/perf/arch/x86/include/arch-tests.h index c41c5affe4be..6a54b94f1c25 100644 --- a/tools/perf/arch/x86/include/arch-tests.h +++ b/tools/perf/arch/x86/include/arch-tests.h @@ -7,7 +7,6 @@ struct test; /* Tests */ int test__rdpmc(struct test *test __maybe_unused, int subtest); -int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest); int test__insn_x86(struct test *test __maybe_unused, int subtest); int test__intel_pt_pkt_decoder(struct test *test, int subtest); int test__bp_modify(struct test *test, int subtest); diff --git a/tools/perf/arch/x86/tests/Build b/tools/perf/arch/x86/tests/Build index 2997c506550c..36d4f248b51d 100644 --- a/tools/perf/arch/x86/tests/Build +++ b/tools/perf/arch/x86/tests/Build @@ -3,6 +3,5 @@ perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o perf-y += arch-tests.o perf-y += rdpmc.o -perf-y += perf-time-to-tsc.o perf-$(CONFIG_AUXTRACE) += insn-x86.o intel-pt-pkt-decoder-test.o perf-$(CONFIG_X86_64) += bp-modify.o diff --git a/tools/perf/arch/x86/tests/arch-tests.c b/tools/perf/arch/x86/tests/arch-tests.c index 6763135aec17..bc25d727b4e9 100644 --- a/tools/perf/arch/x86/tests/arch-tests.c +++ b/tools/perf/arch/x86/tests/arch-tests.c @@ -8,10 +8,6 @@ struct test arch_tests[] = { .desc = "x86 rdpmc", .func = test__rdpmc, }, - { - .desc = "Convert perf time to TSC", - .func = test__perf_time_to_tsc, - }, #ifdef HAVE_DWARF_UNWIND_SUPPORT { .desc = "DWARF unwind", diff --git a/tools/perf/arch/x86/tests/intel-cqm.c b/tools/perf/arch/x86/tests/intel-cqm.c index 3ec562a2aaba..27dd8cf9e060 100644 --- a/tools/perf/arch/x86/tests/intel-cqm.c +++ b/tools/perf/arch/x86/tests/intel-cqm.c @@ -52,7 +52,7 @@ int test__intel_cqm_count_nmi_context(struct test *test __maybe_unused, int subt evlist = evlist__new(); if (!evlist) { - pr_debug("perf_evlist__new failed\n"); + pr_debug("evlist__new failed\n"); return TEST_FAIL; } diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c index 0dc09b5809c1..4a76d49d25d6 100644 --- a/tools/perf/arch/x86/util/intel-bts.c +++ b/tools/perf/arch/x86/util/intel-bts.c @@ -218,7 +218,7 @@ static int intel_bts_recording_options(struct auxtrace_record *itr, * To obtain the auxtrace buffer file descriptor, the auxtrace event * must come first. */ - perf_evlist__to_front(evlist, intel_bts_evsel); + evlist__to_front(evlist, intel_bts_evsel); /* * In the case of per-cpu mmaps, we need the CPU on the * AUX event. @@ -238,7 +238,7 @@ static int intel_bts_recording_options(struct auxtrace_record *itr, tracking_evsel = evlist__last(evlist); - perf_evlist__set_tracking_event(evlist, tracking_evsel); + evlist__set_tracking_event(evlist, tracking_evsel); tracking_evsel->core.attr.freq = 0; tracking_evsel->core.attr.sample_period = 1; diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c index 082e5f2a415a..a6420c647959 100644 --- a/tools/perf/arch/x86/util/intel-pt.c +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -416,7 +416,7 @@ static int intel_pt_track_switches(struct evlist *evlist) struct evsel *evsel; int err; - if (!perf_evlist__can_select_event(evlist, sched_switch)) + if (!evlist__can_select_event(evlist, sched_switch)) return -EPERM; err = parse_events(evlist, sched_switch, NULL); @@ -846,7 +846,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, * To obtain the auxtrace buffer file descriptor, the auxtrace * event must come first. */ - perf_evlist__to_front(evlist, intel_pt_evsel); + evlist__to_front(evlist, intel_pt_evsel); /* * In the case of per-cpu mmaps, we need the CPU on the * AUX event. @@ -865,7 +865,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, tracking_evsel = evlist__last(evlist); - perf_evlist__set_tracking_event(evlist, tracking_evsel); + evlist__set_tracking_event(evlist, tracking_evsel); tracking_evsel->core.attr.freq = 0; tracking_evsel->core.attr.sample_period = 1; diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 4940d10074c3..a23ba6bb99b6 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -412,7 +412,7 @@ static int __cmd_annotate(struct perf_annotate *ann) if (dump_trace) { perf_session__fprintf_nr_events(session, stdout); - perf_evlist__fprintf_nr_events(session->evlist, stdout); + evlist__fprintf_nr_events(session->evlist, stdout); goto out; } @@ -598,7 +598,7 @@ int cmd_annotate(int argc, const char **argv) HEADER_BRANCH_STACK); if (annotate.group_set) - perf_evlist__force_leader(annotate.session->evlist); + evlist__force_leader(annotate.session->evlist); ret = symbol__annotation_init(); if (ret < 0) diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index d5bea5d3cd51..c5babeaa3b38 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -369,6 +369,10 @@ static struct perf_c2c c2c = { .exit = perf_event__process_exit, .fork = perf_event__process_fork, .lost = perf_event__process_lost, + .attr = perf_event__process_attr, + .auxtrace_info = perf_event__process_auxtrace_info, + .auxtrace = perf_event__process_auxtrace, + .auxtrace_error = perf_event__process_auxtrace_error, .ordered_events = true, .ordering_requires_timestamps = true, }, @@ -2678,6 +2682,12 @@ static int setup_coalesce(const char *coalesce, bool no_source) static int perf_c2c__report(int argc, const char **argv) { + struct itrace_synth_opts itrace_synth_opts = { + .set = true, + .mem = true, /* Only enable memory event */ + .default_no_sample = true, + }; + struct perf_session *session; struct ui_progress prog; struct perf_data data = { @@ -2757,6 +2767,8 @@ static int perf_c2c__report(int argc, const char **argv) goto out; } + session->itrace_synth_opts = &itrace_synth_opts; + err = setup_nodes(session); if (err) { pr_err("Failed setup nodes\n"); @@ -2867,6 +2879,7 @@ static int perf_c2c__record(int argc, const char **argv) int ret; bool all_user = false, all_kernel = false; bool event_set = false; + struct perf_mem_event *e; struct option options[] = { OPT_CALLBACK('e', "event", &event_set, "event", "event selector. Use 'perf c2c record -e list' to list available events", @@ -2894,11 +2907,24 @@ static int perf_c2c__record(int argc, const char **argv) rec_argv[i++] = "record"; if (!event_set) { - perf_mem_events[PERF_MEM_EVENTS__LOAD].record = true; - perf_mem_events[PERF_MEM_EVENTS__STORE].record = true; + e = perf_mem_events__ptr(PERF_MEM_EVENTS__LOAD_STORE); + /* + * The load and store operations are required, use the event + * PERF_MEM_EVENTS__LOAD_STORE if it is supported. + */ + if (e->tag) { + e->record = true; + } else { + e = perf_mem_events__ptr(PERF_MEM_EVENTS__LOAD); + e->record = true; + + e = perf_mem_events__ptr(PERF_MEM_EVENTS__STORE); + e->record = true; + } } - if (perf_mem_events[PERF_MEM_EVENTS__LOAD].record) + e = perf_mem_events__ptr(PERF_MEM_EVENTS__LOAD); + if (e->record) rec_argv[i++] = "-W"; rec_argv[i++] = "-d"; @@ -2906,12 +2932,13 @@ static int perf_c2c__record(int argc, const char **argv) rec_argv[i++] = "--sample-cpu"; for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) { - if (!perf_mem_events[j].record) + e = perf_mem_events__ptr(j); + if (!e->record) continue; - if (!perf_mem_events[j].supported) { + if (!e->supported) { pr_err("failed: event '%s' not supported\n", - perf_mem_events[j].name); + perf_mem_events__name(j)); free(rec_argv); return -1; } diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index cefc71506409..8f6c784ce629 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -494,7 +494,7 @@ static struct evsel *evsel_match(struct evsel *evsel, return NULL; } -static void perf_evlist__collapse_resort(struct evlist *evlist) +static void evlist__collapse_resort(struct evlist *evlist) { struct evsel *evsel; @@ -1214,7 +1214,7 @@ static int __cmd_diff(void) goto out_delete; } - perf_evlist__collapse_resort(d->session->evlist); + evlist__collapse_resort(d->session->evlist); if (pdiff.ptime_range) zfree(&pdiff.ptime_range); diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c index 98e992801251..4617b32c9c97 100644 --- a/tools/perf/builtin-evlist.c +++ b/tools/perf/builtin-evlist.c @@ -17,6 +17,14 @@ #include "util/data.h" #include "util/debug.h" #include <linux/err.h> +#include "util/tool.h" + +static int process_header_feature(struct perf_session *session __maybe_unused, + union perf_event *event __maybe_unused) +{ + session_done = 1; + return 0; +} static int __cmd_evlist(const char *file_name, struct perf_attr_details *details) { @@ -27,12 +35,20 @@ static int __cmd_evlist(const char *file_name, struct perf_attr_details *details .mode = PERF_DATA_MODE_READ, .force = details->force, }; + struct perf_tool tool = { + /* only needed for pipe mode */ + .attr = perf_event__process_attr, + .feature = process_header_feature, + }; bool has_tracepoint = false; - session = perf_session__new(&data, 0, NULL); + session = perf_session__new(&data, 0, &tool); if (IS_ERR(session)) return PTR_ERR(session); + if (data.is_pipe) + perf_session__process_events(session); + evlist__for_each_entry(session->evlist, pos) { evsel__fprintf(pos, details, stdout); diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c index 9366fad591dc..d49448a1060c 100644 --- a/tools/perf/builtin-ftrace.c +++ b/tools/perf/builtin-ftrace.c @@ -67,7 +67,7 @@ static void sig_handler(int sig __maybe_unused) } /* - * perf_evlist__prepare_workload will send a SIGUSR1 if the fork fails, since + * 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. * @@ -600,9 +600,8 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv) 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) { + if (argc && evlist__prepare_workload(ftrace->evlist, &ftrace->target, argv, false, + ftrace__workload_exec_failed_signal) < 0) { goto out; } @@ -644,7 +643,7 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv) } } - perf_evlist__start_workload(ftrace->evlist); + evlist__start_workload(ftrace->evlist); if (ftrace->initial_delay) { usleep(ftrace->initial_delay * 1000); @@ -958,7 +957,7 @@ int cmd_ftrace(int argc, const char **argv) goto out_delete_filters; } - ret = perf_evlist__create_maps(ftrace.evlist, &ftrace.target); + ret = evlist__create_maps(ftrace.evlist, &ftrace.target); if (ret < 0) goto out_delete_evlist; diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 0462dc8db2e3..43937f4b399a 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -843,10 +843,12 @@ int cmd_inject(int argc, const char **argv) .output = { .path = "-", .mode = PERF_DATA_MODE_WRITE, + .use_stdio = true, }, }; struct perf_data data = { .mode = PERF_DATA_MODE_READ, + .use_stdio = true, }; int ret; diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index a50dae2c4ae9..0062445e8ead 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -1960,18 +1960,15 @@ int cmd_kmem(int argc, const char **argv) ret = -1; if (kmem_slab) { - if (!perf_evlist__find_tracepoint_by_name(session->evlist, - "kmem:kmalloc")) { + if (!evlist__find_tracepoint_by_name(session->evlist, "kmem:kmalloc")) { pr_err(errmsg, "slab", "slab"); goto out_delete; } } if (kmem_page) { - struct evsel *evsel; + struct evsel *evsel = evlist__find_tracepoint_by_name(session->evlist, "kmem:mm_page_alloc"); - evsel = perf_evlist__find_tracepoint_by_name(session->evlist, - "kmem:mm_page_alloc"); if (evsel == NULL) { pr_err(errmsg, "page", "page"); goto out_delete; diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index 460945ded6dd..1105c9e40a80 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -764,7 +764,7 @@ static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx, return (err == -EAGAIN) ? 0 : -1; while ((event = perf_mmap__read_event(&md->core)) != NULL) { - err = perf_evlist__parse_sample_timestamp(evlist, event, ×tamp); + err = evlist__parse_sample_timestamp(evlist, event, ×tamp); if (err) { perf_mmap__consume(&md->core); pr_err("Failed to parse sample\n"); @@ -1022,7 +1022,7 @@ static int kvm_live_open_events(struct perf_kvm_stat *kvm) struct evlist *evlist = kvm->evlist; char sbuf[STRERR_BUFSIZE]; - perf_evlist__config(evlist, &kvm->opts, NULL); + evlist__config(evlist, &kvm->opts, NULL); /* * Note: exclude_{guest,host} do not apply here. @@ -1349,8 +1349,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm, OPT_STRING('p', "pid", &kvm->opts.target.pid, "pid", "record events on existing process id"), OPT_CALLBACK('m', "mmap-pages", &kvm->opts.mmap_pages, "pages", - "number of mmap data pages", - perf_evlist__parse_mmap_pages), + "number of mmap data pages", evlist__parse_mmap_pages), OPT_INCR('v', "verbose", &verbose, "be more verbose (show counter open errors, etc)"), OPT_BOOLEAN('a', "all-cpus", &kvm->opts.target.system_wide, @@ -1442,7 +1441,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm, goto out; } - if (perf_evlist__create_maps(kvm->evlist, &kvm->opts.target) < 0) + if (evlist__create_maps(kvm->evlist, &kvm->opts.target) < 0) usage_with_options(live_usage, live_options); /* diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c index 3523279af6af..823742036ddb 100644 --- a/tools/perf/builtin-mem.c +++ b/tools/perf/builtin-mem.c @@ -7,6 +7,7 @@ #include "perf.h" #include <subcmd/parse-options.h> +#include "util/auxtrace.h" #include "util/trace-event.h" #include "util/tool.h" #include "util/session.h" @@ -64,6 +65,7 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem) const char **rec_argv; int ret; bool all_user = false, all_kernel = false; + struct perf_mem_event *e; struct option options[] = { OPT_CALLBACK('e', "event", &mem, "event", "event selector. use 'perf mem record -e list' to list available events", @@ -76,6 +78,11 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem) OPT_END() }; + if (perf_mem_events__init()) { + pr_err("failed: memory events not supported\n"); + return -1; + } + argc = parse_options(argc, argv, options, record_mem_usage, PARSE_OPT_KEEP_UNKNOWN); @@ -86,13 +93,30 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem) rec_argv[i++] = "record"; - if (mem->operation & MEM_OPERATION_LOAD) - perf_mem_events[PERF_MEM_EVENTS__LOAD].record = true; + e = perf_mem_events__ptr(PERF_MEM_EVENTS__LOAD_STORE); - if (mem->operation & MEM_OPERATION_STORE) - perf_mem_events[PERF_MEM_EVENTS__STORE].record = true; + /* + * The load and store operations are required, use the event + * PERF_MEM_EVENTS__LOAD_STORE if it is supported. + */ + if (e->tag && + (mem->operation & MEM_OPERATION_LOAD) && + (mem->operation & MEM_OPERATION_STORE)) { + e->record = true; + } else { + if (mem->operation & MEM_OPERATION_LOAD) { + e = perf_mem_events__ptr(PERF_MEM_EVENTS__LOAD); + e->record = true; + } - if (perf_mem_events[PERF_MEM_EVENTS__LOAD].record) + if (mem->operation & MEM_OPERATION_STORE) { + e = perf_mem_events__ptr(PERF_MEM_EVENTS__STORE); + e->record = true; + } + } + + e = perf_mem_events__ptr(PERF_MEM_EVENTS__LOAD); + if (e->record) rec_argv[i++] = "-W"; rec_argv[i++] = "-d"; @@ -101,10 +125,11 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem) rec_argv[i++] = "--phys-data"; for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) { - if (!perf_mem_events[j].record) + e = perf_mem_events__ptr(j); + if (!e->record) continue; - if (!perf_mem_events[j].supported) { + if (!e->supported) { pr_err("failed: event '%s' not supported\n", perf_mem_events__name(j)); free(rec_argv); @@ -231,6 +256,12 @@ static int process_sample_event(struct perf_tool *tool, static int report_raw_events(struct perf_mem *mem) { + struct itrace_synth_opts itrace_synth_opts = { + .set = true, + .mem = true, /* Only enable memory event */ + .default_no_sample = true, + }; + struct perf_data data = { .path = input_name, .mode = PERF_DATA_MODE_READ, @@ -243,6 +274,8 @@ static int report_raw_events(struct perf_mem *mem) if (IS_ERR(session)) return PTR_ERR(session); + session->itrace_synth_opts = &itrace_synth_opts; + if (mem->cpu_list) { ret = perf_session__cpu_bitmap(session, mem->cpu_list, mem->cpu_bitmap); @@ -265,11 +298,35 @@ out_delete: perf_session__delete(session); return ret; } +static char *get_sort_order(struct perf_mem *mem) +{ + bool has_extra_options = mem->phys_addr ? true : false; + char sort[128]; + + /* + * there is no weight (cost) associated with stores, so don't print + * the column + */ + if (!(mem->operation & MEM_OPERATION_LOAD)) { + strcpy(sort, "--sort=mem,sym,dso,symbol_daddr," + "dso_daddr,tlb,locked"); + } else if (has_extra_options) { + strcpy(sort, "--sort=local_weight,mem,sym,dso,symbol_daddr," + "dso_daddr,snoop,tlb,locked"); + } else + return NULL; + + if (mem->phys_addr) + strcat(sort, ",phys_daddr"); + + return strdup(sort); +} static int report_events(int argc, const char **argv, struct perf_mem *mem) { const char **rep_argv; int ret, i = 0, j, rep_argc; + char *new_sort_order; if (mem->dump_raw) return report_raw_events(mem); @@ -283,20 +340,9 @@ static int report_events(int argc, const char **argv, struct perf_mem *mem) rep_argv[i++] = "--mem-mode"; rep_argv[i++] = "-n"; /* display number of samples */ - /* - * there is no weight (cost) associated with stores, so don't print - * the column - */ - if (!(mem->operation & MEM_OPERATION_LOAD)) { - if (mem->phys_addr) - rep_argv[i++] = "--sort=mem,sym,dso,symbol_daddr," - "dso_daddr,tlb,locked,phys_daddr"; - else - rep_argv[i++] = "--sort=mem,sym,dso,symbol_daddr," - "dso_daddr,tlb,locked"; - } else if (mem->phys_addr) - rep_argv[i++] = "--sort=local_weight,mem,sym,dso,symbol_daddr," - "dso_daddr,snoop,tlb,locked,phys_daddr"; + new_sort_order = get_sort_order(mem); + if (new_sort_order) + rep_argv[i++] = new_sort_order; for (j = 1; j < argc; j++, i++) rep_argv[i] = argv[j]; @@ -386,8 +432,12 @@ int cmd_mem(int argc, const char **argv) .comm = perf_event__process_comm, .lost = perf_event__process_lost, .fork = perf_event__process_fork, + .attr = perf_event__process_attr, .build_id = perf_event__process_build_id, .namespaces = perf_event__process_namespaces, + .auxtrace_info = perf_event__process_auxtrace_info, + .auxtrace = perf_event__process_auxtrace, + .auxtrace_error = perf_event__process_auxtrace_error, .ordered_events = true, }, .input_name = "perf.data", @@ -422,11 +472,6 @@ int cmd_mem(int argc, const char **argv) NULL }; - if (perf_mem_events__init()) { - pr_err("failed: memory events not supported\n"); - return -1; - } - argc = parse_options_subcommand(argc, argv, mem_options, mem_subcommands, mem_usage, PARSE_OPT_KEEP_UNKNOWN); diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index adf311d15d3d..fd3911650612 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -891,13 +891,13 @@ static int record__open(struct record *rec) * event synthesis. */ if (opts->initial_delay || target__has_cpu(&opts->target)) { - pos = perf_evlist__get_tracking_event(evlist); + pos = evlist__get_tracking_event(evlist); if (!evsel__is_dummy_event(pos)) { /* Set up dummy event. */ if (evlist__add_dummy(evlist)) return -ENOMEM; pos = evlist__last(evlist); - perf_evlist__set_tracking_event(evlist, pos); + evlist__set_tracking_event(evlist, pos); } /* @@ -910,7 +910,7 @@ static int record__open(struct record *rec) pos->immediate = 1; } - perf_evlist__config(evlist, opts, &callchain_param); + evlist__config(evlist, opts, &callchain_param); evlist__for_each_entry(evlist, pos) { try_again: @@ -923,7 +923,7 @@ try_again: if ((errno == EINVAL || errno == EBADF) && pos->leader != pos && pos->weak_group) { - pos = perf_evlist__reset_weak_group(evlist, pos, true); + pos = evlist__reset_weak_group(evlist, pos, true); goto try_again; } rc = -errno; @@ -935,7 +935,7 @@ try_again: pos->supported = true; } - if (symbol_conf.kptr_restrict && !perf_evlist__exclude_kernel(evlist)) { + if (symbol_conf.kptr_restrict && !evlist__exclude_kernel(evlist)) { pr_warning( "WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted,\n" "check /proc/sys/kernel/kptr_restrict and /proc/sys/kernel/perf_event_paranoid.\n\n" @@ -946,7 +946,7 @@ try_again: "even with a suitable vmlinux or kallsyms file.\n\n"); } - if (perf_evlist__apply_filters(evlist, &pos)) { + if (evlist__apply_filters(evlist, &pos)) { pr_err("failed to set filter \"%s\" on event %s with %d (%s)\n", pos->filter, evsel__name(pos), errno, str_error_r(errno, msg, sizeof(msg))); @@ -1166,7 +1166,7 @@ static int record__mmap_read_evlist(struct record *rec, struct evlist *evlist, rc = record__write(rec, NULL, &finished_round_event, sizeof(finished_round_event)); if (overwrite) - perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_EMPTY); + evlist__toggle_bkw_mmap(evlist, BKW_MMAP_EMPTY); out: return rc; } @@ -1333,7 +1333,7 @@ record__switch_output(struct record *rec, bool at_exit) static volatile int workload_exec_errno; /* - * perf_evlist__prepare_workload will send a SIGUSR1 + * evlist__prepare_workload will send a SIGUSR1 * if the fork fails, since we asked by setting its * want_signal to true. */ @@ -1349,8 +1349,7 @@ static void workload_exec_failed_signal(int signo __maybe_unused, static void snapshot_sig_handler(int sig); static void alarm_sig_handler(int sig); -static const struct perf_event_mmap_page * -perf_evlist__pick_pc(struct evlist *evlist) +static const struct perf_event_mmap_page *evlist__pick_pc(struct evlist *evlist) { if (evlist) { if (evlist->mmap && evlist->mmap[0].core.base) @@ -1363,9 +1362,7 @@ perf_evlist__pick_pc(struct evlist *evlist) static const struct perf_event_mmap_page *record__pick_pc(struct record *rec) { - const struct perf_event_mmap_page *pc; - - pc = perf_evlist__pick_pc(rec->evlist); + const struct perf_event_mmap_page *pc = evlist__pick_pc(rec->evlist); if (pc) return pc; return NULL; @@ -1444,7 +1441,7 @@ static int record__synthesize(struct record *rec, bool tail) goto out; } - if (!perf_evlist__exclude_kernel(rec->evlist)) { + if (!evlist__exclude_kernel(rec->evlist)) { err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event, machine); WARN_ONCE(err < 0, "Couldn't record kernel reference relocation symbol\n" @@ -1548,7 +1545,7 @@ static int record__setup_sb_evlist(struct record *rec) } } #endif - if (perf_evlist__start_sb_thread(rec->sb_evlist, &rec->opts.target)) { + if (evlist__start_sb_thread(rec->sb_evlist, &rec->opts.target)) { pr_debug("Couldn't start the BPF side band thread:\nBPF programs starting from now on won't be annotatable\n"); opts->no_bpf_event = true; } @@ -1689,9 +1686,8 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) record__init_features(rec); if (forks) { - err = perf_evlist__prepare_workload(rec->evlist, &opts->target, - argv, data->is_pipe, - workload_exec_failed_signal); + err = evlist__prepare_workload(rec->evlist, &opts->target, argv, data->is_pipe, + workload_exec_failed_signal); if (err < 0) { pr_err("Couldn't run the workload!\n"); status = err; @@ -1835,7 +1831,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) machine); free(event); - perf_evlist__start_workload(rec->evlist); + evlist__start_workload(rec->evlist); } if (evlist__initialize_ctlfd(rec->evlist, opts->ctl_fd, opts->ctl_fd_ack)) @@ -1861,11 +1857,11 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) * BKW_MMAP_EMPTY here: when done == true and * hits != rec->samples in previous round. * - * perf_evlist__toggle_bkw_mmap ensure we never + * evlist__toggle_bkw_mmap ensure we never * convert BKW_MMAP_EMPTY to BKW_MMAP_DATA_PENDING. */ if (trigger_is_hit(&switch_output_trigger) || done || draining) - perf_evlist__toggle_bkw_mmap(rec->evlist, BKW_MMAP_DATA_PENDING); + evlist__toggle_bkw_mmap(rec->evlist, BKW_MMAP_DATA_PENDING); if (record__mmap_read_all(rec, false) < 0) { trigger_error(&auxtrace_snapshot_trigger); @@ -1904,7 +1900,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) * record__mmap_read_all(): we should have collected * data from it. */ - perf_evlist__toggle_bkw_mmap(rec->evlist, BKW_MMAP_RUNNING); + evlist__toggle_bkw_mmap(rec->evlist, BKW_MMAP_RUNNING); if (!quiet) fprintf(stderr, "[ perf record: dump data: Woken up %ld times ]\n", @@ -2066,7 +2062,7 @@ out_delete_session: perf_session__delete(session); if (!opts->no_bpf_event) - perf_evlist__stop_sb_thread(rec->sb_evlist); + evlist__stop_sb_thread(rec->sb_evlist); return status; } @@ -2222,7 +2218,7 @@ static int record__parse_mmap_pages(const struct option *opt, *p = '\0'; if (*s) { - ret = __perf_evlist__parse_mmap_pages(&mmap_pages, s); + ret = __evlist__parse_mmap_pages(&mmap_pages, s); if (ret) goto out_free; opts->mmap_pages = mmap_pages; @@ -2233,7 +2229,7 @@ static int record__parse_mmap_pages(const struct option *opt, goto out_free; } - ret = __perf_evlist__parse_mmap_pages(&mmap_pages, p + 1); + ret = __evlist__parse_mmap_pages(&mmap_pages, p + 1); if (ret) goto out_free; @@ -2413,7 +2409,7 @@ static bool dry_run; * XXX Will stay a global variable till we fix builtin-script.c to stop messing * with it and switch to use the library functions in perf_evlist that came * from builtin-record.c, i.e. use record_opts, - * perf_evlist__prepare_workload, etc instead of fork+exec'in 'perf record', + * evlist__prepare_workload, etc instead of fork+exec'in 'perf record', * using pipes, etc. */ static struct option __record_options[] = { @@ -2476,6 +2472,8 @@ static struct option __record_options[] = { OPT_BOOLEAN('d', "data", &record.opts.sample_address, "Record the sample addresses"), OPT_BOOLEAN(0, "phys-data", &record.opts.sample_phys_addr, "Record the sample physical addresses"), + OPT_BOOLEAN(0, "data-page-size", &record.opts.sample_data_page_size, + "Record the sampled data address data page size"), OPT_BOOLEAN(0, "sample-cpu", &record.opts.sample_cpu, "Record the sample cpu"), OPT_BOOLEAN_SET('T', "timestamp", &record.opts.sample_time, &record.opts.sample_time_set, @@ -2793,7 +2791,7 @@ int cmd_record(int argc, const char **argv) rec->opts.ignore_missing_thread = rec->opts.target.uid != UINT_MAX || rec->opts.target.pid; err = -ENOMEM; - if (perf_evlist__create_maps(rec->evlist, &rec->opts.target) < 0) + if (evlist__create_maps(rec->evlist, &rec->opts.target) < 0) usage_with_options(record_usage, record_options); err = auxtrace_record__options(rec->itr, rec->evlist, &rec->opts); diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 3c74c9c0f3c3..2a845d6cac09 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -211,7 +211,7 @@ static void setup_forced_leader(struct report *report, struct evlist *evlist) { if (report->group_set) - perf_evlist__force_leader(evlist); + evlist__force_leader(evlist); } static int process_feature_event(struct perf_session *session, @@ -226,6 +226,8 @@ static int process_feature_event(struct perf_session *session, pr_err("failed: wrong feature ID: %" PRI_lu64 "\n", event->feat.feat_id); return -1; + } else if (rep->header_only) { + session_done = 1; } /* @@ -493,8 +495,7 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report return ret + fprintf(fp, "\n#\n"); } -static int perf_evlist__tui_block_hists_browse(struct evlist *evlist, - struct report *rep) +static int evlist__tui_block_hists_browse(struct evlist *evlist, struct report *rep) { struct evsel *pos; int i = 0, ret; @@ -511,9 +512,7 @@ static int perf_evlist__tui_block_hists_browse(struct evlist *evlist, return 0; } -static int perf_evlist__tty_browse_hists(struct evlist *evlist, - struct report *rep, - const char *help) +static int evlist__tty_browse_hists(struct evlist *evlist, struct report *rep, const char *help) { struct evsel *pos; int i = 0; @@ -566,7 +565,7 @@ static void report__warn_kptr_restrict(const struct report *rep) struct map *kernel_map = machine__kernel_map(&rep->session->machines.host); struct kmap *kernel_kmap = kernel_map ? map__kmap(kernel_map) : NULL; - if (perf_evlist__exclude_kernel(rep->session->evlist)) + if (evlist__exclude_kernel(rep->session->evlist)) return; if (kernel_map == NULL || @@ -595,7 +594,7 @@ static int report__gtk_browse_hists(struct report *rep, const char *help) int (*hist_browser)(struct evlist *evlist, const char *help, struct hist_browser_timer *timer, float min_pcnt); - hist_browser = dlsym(perf_gtk_handle, "perf_evlist__gtk_browse_hists"); + hist_browser = dlsym(perf_gtk_handle, "evlist__gtk_browse_hists"); if (hist_browser == NULL) { ui__error("GTK browser not found!\n"); @@ -622,14 +621,12 @@ static int report__browse_hists(struct report *rep) switch (use_browser) { case 1: if (rep->total_cycles_mode) { - ret = perf_evlist__tui_block_hists_browse(evlist, rep); + ret = evlist__tui_block_hists_browse(evlist, rep); break; } - ret = perf_evlist__tui_browse_hists(evlist, help, NULL, - rep->min_percent, - &session->header.env, - true, &rep->annotation_opts); + ret = evlist__tui_browse_hists(evlist, help, NULL, rep->min_percent, + &session->header.env, true, &rep->annotation_opts); /* * Usually "ret" is the last pressed key, and we only * care if the key notifies us to switch data file. @@ -641,7 +638,7 @@ static int report__browse_hists(struct report *rep) ret = report__gtk_browse_hists(rep, help); break; default: - ret = perf_evlist__tty_browse_hists(evlist, rep, help); + ret = evlist__tty_browse_hists(evlist, rep, help); break; } @@ -933,7 +930,7 @@ static int __cmd_report(struct report *rep) if (dump_trace) { perf_session__fprintf_nr_events(session, stdout); - perf_evlist__fprintf_nr_events(session->evlist, stdout); + evlist__fprintf_nr_events(session->evlist, stdout); return 0; } } @@ -1517,6 +1514,13 @@ repeat: perf_session__fprintf_info(session, stdout, report.show_full_info); if (report.header_only) { + if (data.is_pipe) { + /* + * we need to process first few records + * which contains PERF_RECORD_HEADER_FEATURE. + */ + perf_session__process_events(session); + } ret = 0; goto error; } diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 0e16f9d5a947..69c769b04a61 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -3036,8 +3036,7 @@ static int perf_sched__timehist(struct perf_sched *sched) setup_pager(); /* prefer sched_waking if it is captured */ - if (perf_evlist__find_tracepoint_by_name(session->evlist, - "sched:sched_waking")) + if (evlist__find_tracepoint_by_name(session->evlist, "sched:sched_waking")) handlers[1].handler = timehist_sched_wakeup_ignore; /* setup per-evsel handlers */ @@ -3045,8 +3044,7 @@ static int perf_sched__timehist(struct perf_sched *sched) goto out; /* sched_switch event at a minimum needs to exist */ - if (!perf_evlist__find_tracepoint_by_name(session->evlist, - "sched:sched_switch")) { + if (!evlist__find_tracepoint_by_name(session->evlist, "sched:sched_switch")) { pr_err("No sched_switch events found. Have you run 'perf sched record'?\n"); goto out; } diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 48588ccf902e..edacfa98d073 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -30,6 +30,7 @@ #include "util/thread-stack.h" #include "util/time-utils.h" #include "util/path.h" +#include "util/event.h" #include "ui/ui.h" #include "print_binary.h" #include "archinsn.h" @@ -115,6 +116,7 @@ enum perf_output_field { PERF_OUTPUT_SRCCODE = 1ULL << 30, PERF_OUTPUT_IPC = 1ULL << 31, PERF_OUTPUT_TOD = 1ULL << 32, + PERF_OUTPUT_DATA_PAGE_SIZE = 1ULL << 33, }; struct perf_script { @@ -179,6 +181,7 @@ struct output_option { {.str = "srccode", .field = PERF_OUTPUT_SRCCODE}, {.str = "ipc", .field = PERF_OUTPUT_IPC}, {.str = "tod", .field = PERF_OUTPUT_TOD}, + {.str = "data_page_size", .field = PERF_OUTPUT_DATA_PAGE_SIZE}, }; enum { @@ -251,7 +254,8 @@ static struct { PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET | PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD | PERF_OUTPUT_ADDR | PERF_OUTPUT_DATA_SRC | - PERF_OUTPUT_WEIGHT | PERF_OUTPUT_PHYS_ADDR, + PERF_OUTPUT_WEIGHT | PERF_OUTPUT_PHYS_ADDR | + PERF_OUTPUT_DATA_PAGE_SIZE, .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT, }, @@ -499,6 +503,10 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session) evsel__check_stype(evsel, PERF_SAMPLE_PHYS_ADDR, "PHYS_ADDR", PERF_OUTPUT_PHYS_ADDR)) return -EINVAL; + if (PRINT_FIELD(DATA_PAGE_SIZE) && + evsel__check_stype(evsel, PERF_SAMPLE_DATA_PAGE_SIZE, "DATA_PAGE_SIZE", PERF_OUTPUT_DATA_PAGE_SIZE)) + return -EINVAL; + return 0; } @@ -1847,7 +1855,7 @@ static void perf_sample__fprint_metric(struct perf_script *script, u64 val; if (!evsel->stats) - perf_evlist__alloc_stats(script->session->evlist, false); + evlist__alloc_stats(script->session->evlist, false); if (evsel_script(evsel->leader)->gnum++ == 0) perf_stat__reset_shadow_stats(); val = sample->period * evsel->scale; @@ -1920,6 +1928,7 @@ static void process_event(struct perf_script *script, unsigned int type = output_type(attr->type); struct evsel_script *es = evsel->priv; FILE *fp = es->fp; + char str[PAGE_SIZE_NAME_LEN]; if (output[type].fields == 0) return; @@ -2008,6 +2017,9 @@ static void process_event(struct perf_script *script, if (PRINT_FIELD(PHYS_ADDR)) fprintf(fp, "%16" PRIx64, sample->phys_addr); + if (PRINT_FIELD(DATA_PAGE_SIZE)) + fprintf(fp, " %s", get_page_size_name(sample->data_page_size, str)); + perf_sample__fprintf_ipc(sample, attr, fp); fprintf(fp, "\n"); @@ -2224,7 +2236,7 @@ static int print_event_with_time(struct perf_tool *tool, { struct perf_script *script = container_of(tool, struct perf_script, tool); struct perf_session *session = script->session; - struct evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); + struct evsel *evsel = evlist__id2evsel(session->evlist, sample->id); struct thread *thread = NULL; if (evsel && !evsel->core.attr.sample_id_all) { @@ -3308,7 +3320,7 @@ static int set_maps(struct perf_script *script) perf_evlist__set_maps(&evlist->core, script->cpus, script->threads); - if (perf_evlist__alloc_stats(evlist, true)) + if (evlist__alloc_stats(evlist, true)) return -ENOMEM; script->allocated = true; @@ -3506,7 +3518,8 @@ int cmd_script(int argc, const char **argv) "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso," "addr,symoff,srcline,period,iregs,uregs,brstack," "brstacksym,flags,bpf-output,brstackinsn,brstackoff," - "callindent,insn,insnlen,synth,phys_addr,metric,misc,ipc,tod", + "callindent,insn,insnlen,synth,phys_addr,metric,misc,ipc,tod," + "data_page_size", parse_output_fields), OPT_BOOLEAN('a', "all-cpus", &system_wide, "system-wide collection from all CPUs"), @@ -3935,7 +3948,7 @@ out_delete: zfree(&script.ptime_range); } - perf_evlist__free_stats(session->evlist); + evlist__free_stats(session->evlist); perf_session__delete(session); if (script_started) diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index b01af171d94f..8cc24967bc27 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -270,7 +270,7 @@ static void perf_stat__reset_stats(void) { int i; - perf_evlist__reset_stats(evsel_list); + evlist__reset_stats(evsel_list); perf_stat__reset_shadow_stats(); for (i = 0; i < stat_config.stats_num; i++) @@ -534,7 +534,7 @@ static void disable_counters(void) static volatile int workload_exec_errno; /* - * perf_evlist__prepare_workload will send a SIGUSR1 + * evlist__prepare_workload will send a SIGUSR1 * if the fork fails, since we asked by setting its * want_signal to true. */ @@ -724,8 +724,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx) bool second_pass = false; if (forks) { - if (perf_evlist__prepare_workload(evsel_list, &target, argv, is_pipe, - workload_exec_failed_signal) < 0) { + if (evlist__prepare_workload(evsel_list, &target, argv, is_pipe, workload_exec_failed_signal) < 0) { perror("failed to prepare workload"); return -1; } @@ -733,7 +732,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx) } if (group) - perf_evlist__set_leader(evsel_list); + evlist__set_leader(evsel_list); if (affinity__setup(&affinity) < 0) return -1; @@ -760,7 +759,7 @@ try_again: if ((errno == EINVAL || errno == EBADF) && counter->leader != counter && counter->weak_group) { - perf_evlist__reset_weak_group(evsel_list, counter, false); + evlist__reset_weak_group(evsel_list, counter, false); assert(counter->reset_group); second_pass = true; continue; @@ -843,7 +842,7 @@ try_again_reset: return -1; } - if (perf_evlist__apply_filters(evsel_list, &counter)) { + if (evlist__apply_filters(evsel_list, &counter)) { pr_err("failed to set filter \"%s\" on event %s with %d (%s)\n", counter->filter, evsel__name(counter), errno, str_error_r(errno, msg, sizeof(msg))); @@ -876,7 +875,7 @@ try_again_reset: clock_gettime(CLOCK_MONOTONIC, &ref_time); if (forks) { - perf_evlist__start_workload(evsel_list); + evlist__start_workload(evsel_list); enable_counters(); if (interval || timeout || evlist__ctlfd_initialized(evsel_list)) @@ -914,10 +913,10 @@ try_again_reset: update_stats(&walltime_nsecs_stats, t1 - t0); if (stat_config.aggr_mode == AGGR_GLOBAL) - perf_evlist__save_aggr_prev_raw_counts(evsel_list); + evlist__save_aggr_prev_raw_counts(evsel_list); - perf_evlist__copy_prev_raw_counts(evsel_list); - perf_evlist__reset_prev_raw_counts(evsel_list); + evlist__copy_prev_raw_counts(evsel_list); + evlist__reset_prev_raw_counts(evsel_list); runtime_stat_reset(&stat_config); perf_stat__reset_shadow_per_stat(&rt_stat); } else @@ -972,9 +971,10 @@ static void print_counters(struct timespec *ts, int argc, const char **argv) /* Do not print anything if we record to the pipe. */ if (STAT_RECORD && perf_stat.data.is_pipe) return; + if (stat_config.quiet) + return; - perf_evlist__print_counters(evsel_list, &stat_config, &target, - ts, argc, argv); + evlist__print_counters(evsel_list, &stat_config, &target, ts, argc, argv); } static volatile int signr = -1; @@ -1171,6 +1171,8 @@ static struct option stat_options[] = { "threads of same physical core"), OPT_BOOLEAN(0, "summary", &stat_config.summary, "print summary for interval mode"), + OPT_BOOLEAN(0, "quiet", &stat_config.quiet, + "don't print output (useful with record)"), #ifdef HAVE_LIBPFM OPT_CALLBACK(0, "pfm-events", &evsel_list, "event", "libpfm4 event selector. use 'perf list' to list available events", @@ -1184,65 +1186,67 @@ static struct option stat_options[] = { OPT_END() }; -static int perf_stat__get_socket(struct perf_stat_config *config __maybe_unused, +static struct aggr_cpu_id perf_stat__get_socket(struct perf_stat_config *config __maybe_unused, struct perf_cpu_map *map, int cpu) { return cpu_map__get_socket(map, cpu, NULL); } -static int perf_stat__get_die(struct perf_stat_config *config __maybe_unused, +static struct aggr_cpu_id perf_stat__get_die(struct perf_stat_config *config __maybe_unused, struct perf_cpu_map *map, int cpu) { return cpu_map__get_die(map, cpu, NULL); } -static int perf_stat__get_core(struct perf_stat_config *config __maybe_unused, +static struct aggr_cpu_id perf_stat__get_core(struct perf_stat_config *config __maybe_unused, struct perf_cpu_map *map, int cpu) { return cpu_map__get_core(map, cpu, NULL); } -static int perf_stat__get_node(struct perf_stat_config *config __maybe_unused, +static struct aggr_cpu_id perf_stat__get_node(struct perf_stat_config *config __maybe_unused, struct perf_cpu_map *map, int cpu) { return cpu_map__get_node(map, cpu, NULL); } -static int perf_stat__get_aggr(struct perf_stat_config *config, +static struct aggr_cpu_id perf_stat__get_aggr(struct perf_stat_config *config, aggr_get_id_t get_id, struct perf_cpu_map *map, int idx) { int cpu; + struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); if (idx >= map->nr) - return -1; + return id; cpu = map->map[idx]; - if (config->cpus_aggr_map->map[cpu] == -1) + if (cpu_map__aggr_cpu_id_is_empty(config->cpus_aggr_map->map[cpu])) config->cpus_aggr_map->map[cpu] = get_id(config, map, idx); - return config->cpus_aggr_map->map[cpu]; + id = config->cpus_aggr_map->map[cpu]; + return id; } -static int perf_stat__get_socket_cached(struct perf_stat_config *config, +static struct aggr_cpu_id perf_stat__get_socket_cached(struct perf_stat_config *config, struct perf_cpu_map *map, int idx) { return perf_stat__get_aggr(config, perf_stat__get_socket, map, idx); } -static int perf_stat__get_die_cached(struct perf_stat_config *config, +static struct aggr_cpu_id perf_stat__get_die_cached(struct perf_stat_config *config, struct perf_cpu_map *map, int idx) { return perf_stat__get_aggr(config, perf_stat__get_die, map, idx); } -static int perf_stat__get_core_cached(struct perf_stat_config *config, +static struct aggr_cpu_id perf_stat__get_core_cached(struct perf_stat_config *config, struct perf_cpu_map *map, int idx) { return perf_stat__get_aggr(config, perf_stat__get_core, map, idx); } -static int perf_stat__get_node_cached(struct perf_stat_config *config, +static struct aggr_cpu_id perf_stat__get_node_cached(struct perf_stat_config *config, struct perf_cpu_map *map, int idx) { return perf_stat__get_aggr(config, perf_stat__get_node, map, idx); @@ -1316,14 +1320,29 @@ static int perf_stat_init_aggr_mode(void) * the aggregation translate cpumap. */ nr = perf_cpu_map__max(evsel_list->core.cpus); - stat_config.cpus_aggr_map = perf_cpu_map__empty_new(nr + 1); + stat_config.cpus_aggr_map = cpu_aggr_map__empty_new(nr + 1); return stat_config.cpus_aggr_map ? 0 : -ENOMEM; } +static void cpu_aggr_map__delete(struct cpu_aggr_map *map) +{ + if (map) { + WARN_ONCE(refcount_read(&map->refcnt) != 0, + "cpu_aggr_map refcnt unbalanced\n"); + free(map); + } +} + +static void cpu_aggr_map__put(struct cpu_aggr_map *map) +{ + if (map && refcount_dec_and_test(&map->refcnt)) + cpu_aggr_map__delete(map); +} + static void perf_stat__exit_aggr_mode(void) { - perf_cpu_map__put(stat_config.aggr_map); - perf_cpu_map__put(stat_config.cpus_aggr_map); + cpu_aggr_map__put(stat_config.aggr_map); + cpu_aggr_map__put(stat_config.cpus_aggr_map); stat_config.aggr_map = NULL; stat_config.cpus_aggr_map = NULL; } @@ -1343,117 +1362,108 @@ static inline int perf_env__get_cpu(struct perf_env *env, struct perf_cpu_map *m return cpu; } -static int perf_env__get_socket(struct perf_cpu_map *map, int idx, void *data) +static struct aggr_cpu_id perf_env__get_socket(struct perf_cpu_map *map, int idx, void *data) { struct perf_env *env = data; int cpu = perf_env__get_cpu(env, map, idx); + struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); - return cpu == -1 ? -1 : env->cpu[cpu].socket_id; + if (cpu != -1) + id.socket = env->cpu[cpu].socket_id; + + return id; } -static int perf_env__get_die(struct perf_cpu_map *map, int idx, void *data) +static struct aggr_cpu_id perf_env__get_die(struct perf_cpu_map *map, int idx, void *data) { struct perf_env *env = data; - int die_id = -1, cpu = perf_env__get_cpu(env, map, idx); + struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); + int cpu = perf_env__get_cpu(env, map, idx); if (cpu != -1) { /* - * Encode socket in bit range 15:8 - * die_id is relative to socket, - * we need a global id. So we combine - * socket + die id + * die_id is relative to socket, so start + * with the socket ID and then add die to + * make a unique ID. */ - if (WARN_ONCE(env->cpu[cpu].socket_id >> 8, "The socket id number is too big.\n")) - return -1; - - if (WARN_ONCE(env->cpu[cpu].die_id >> 8, "The die id number is too big.\n")) - return -1; - - die_id = (env->cpu[cpu].socket_id << 8) | (env->cpu[cpu].die_id & 0xff); + id.socket = env->cpu[cpu].socket_id; + id.die = env->cpu[cpu].die_id; } - return die_id; + return id; } -static int perf_env__get_core(struct perf_cpu_map *map, int idx, void *data) +static struct aggr_cpu_id perf_env__get_core(struct perf_cpu_map *map, int idx, void *data) { struct perf_env *env = data; - int core = -1, cpu = perf_env__get_cpu(env, map, idx); + struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); + int cpu = perf_env__get_cpu(env, map, idx); if (cpu != -1) { /* - * Encode socket in bit range 31:24 - * encode die id in bit range 23:16 * core_id is relative to socket and die, - * we need a global id. So we combine - * socket + die id + core id + * we need a global id. So we set + * socket, die id and core id */ - if (WARN_ONCE(env->cpu[cpu].socket_id >> 8, "The socket id number is too big.\n")) - return -1; - - if (WARN_ONCE(env->cpu[cpu].die_id >> 8, "The die id number is too big.\n")) - return -1; - - if (WARN_ONCE(env->cpu[cpu].core_id >> 16, "The core id number is too big.\n")) - return -1; - - core = (env->cpu[cpu].socket_id << 24) | - (env->cpu[cpu].die_id << 16) | - (env->cpu[cpu].core_id & 0xffff); + id.socket = env->cpu[cpu].socket_id; + id.die = env->cpu[cpu].die_id; + id.core = env->cpu[cpu].core_id; } - return core; + return id; } -static int perf_env__get_node(struct perf_cpu_map *map, int idx, void *data) +static struct aggr_cpu_id perf_env__get_node(struct perf_cpu_map *map, int idx, void *data) { int cpu = perf_env__get_cpu(data, map, idx); + struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); - return perf_env__numa_node(data, cpu); + id.node = perf_env__numa_node(data, cpu); + return id; } static int perf_env__build_socket_map(struct perf_env *env, struct perf_cpu_map *cpus, - struct perf_cpu_map **sockp) + struct cpu_aggr_map **sockp) { return cpu_map__build_map(cpus, sockp, perf_env__get_socket, env); } static int perf_env__build_die_map(struct perf_env *env, struct perf_cpu_map *cpus, - struct perf_cpu_map **diep) + struct cpu_aggr_map **diep) { return cpu_map__build_map(cpus, diep, perf_env__get_die, env); } static int perf_env__build_core_map(struct perf_env *env, struct perf_cpu_map *cpus, - struct perf_cpu_map **corep) + struct cpu_aggr_map **corep) { return cpu_map__build_map(cpus, corep, perf_env__get_core, env); } static int perf_env__build_node_map(struct perf_env *env, struct perf_cpu_map *cpus, - struct perf_cpu_map **nodep) + struct cpu_aggr_map **nodep) { return cpu_map__build_map(cpus, nodep, perf_env__get_node, env); } -static int perf_stat__get_socket_file(struct perf_stat_config *config __maybe_unused, +static struct aggr_cpu_id perf_stat__get_socket_file(struct perf_stat_config *config __maybe_unused, struct perf_cpu_map *map, int idx) { return perf_env__get_socket(map, idx, &perf_stat.session->header.env); } -static int perf_stat__get_die_file(struct perf_stat_config *config __maybe_unused, +static struct aggr_cpu_id perf_stat__get_die_file(struct perf_stat_config *config __maybe_unused, struct perf_cpu_map *map, int idx) { return perf_env__get_die(map, idx, &perf_stat.session->header.env); } -static int perf_stat__get_core_file(struct perf_stat_config *config __maybe_unused, +static struct aggr_cpu_id perf_stat__get_core_file(struct perf_stat_config *config __maybe_unused, struct perf_cpu_map *map, int idx) { return perf_env__get_core(map, idx, &perf_stat.session->header.env); } -static int perf_stat__get_node_file(struct perf_stat_config *config __maybe_unused, +static struct aggr_cpu_id perf_stat__get_node_file(struct perf_stat_config *config __maybe_unused, struct perf_cpu_map *map, int idx) { return perf_env__get_node(map, idx, &perf_stat.session->header.env); @@ -1904,7 +1914,7 @@ static int set_maps(struct perf_stat *st) perf_evlist__set_maps(&evsel_list->core, st->cpus, st->threads); - if (perf_evlist__alloc_stats(evsel_list, true)) + if (evlist__alloc_stats(evsel_list, true)) return -ENOMEM; st->maps_allocated = true; @@ -2132,7 +2142,7 @@ int cmd_stat(int argc, const char **argv) goto out; } - if (!output) { + if (!output && !stat_config.quiet) { struct timespec tm; mode = append_file ? "a" : "w"; @@ -2235,8 +2245,11 @@ int cmd_stat(int argc, const char **argv) } if (evlist__expand_cgroup(evsel_list, stat_config.cgroup_list, - &stat_config.metric_events, true) < 0) + &stat_config.metric_events, true) < 0) { + parse_options_usage(stat_usage, stat_options, + "for-each-cgroup", 0); goto out; + } } target__validate(&target); @@ -2244,7 +2257,7 @@ int cmd_stat(int argc, const char **argv) if ((stat_config.aggr_mode == AGGR_THREAD) && (target.system_wide)) target.per_thread = true; - if (perf_evlist__create_maps(evsel_list, &target) < 0) { + if (evlist__create_maps(evsel_list, &target) < 0) { if (target__has_task(&target)) { pr_err("Problems finding threads of monitor\n"); parse_options_usage(stat_usage, stat_options, "p", 1); @@ -2303,7 +2316,7 @@ int cmd_stat(int argc, const char **argv) goto out; } - if (perf_evlist__alloc_stats(evsel_list, interval)) + if (evlist__alloc_stats(evsel_list, interval)) goto out; if (perf_stat_init_aggr_mode()) @@ -2343,7 +2356,7 @@ int cmd_stat(int argc, const char **argv) run_idx + 1); if (run_idx != 0) - perf_evlist__reset_prev_raw_counts(evsel_list); + evlist__reset_prev_raw_counts(evsel_list); status = run_perf_stat(argc, argv, run_idx); if (forever && status != -1 && !interval) { @@ -2394,7 +2407,7 @@ int cmd_stat(int argc, const char **argv) } perf_stat__exit_aggr_mode(); - perf_evlist__free_stats(evsel_list); + evlist__free_stats(evsel_list); out: zfree(&stat_config.walltime_run); diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 7c64134472c7..3673c04d16b6 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -641,12 +641,9 @@ repeat: hists->uid_filter_str = top->record_opts.target.uid_str; } - ret = perf_evlist__tui_browse_hists(top->evlist, help, &hbt, - top->min_percent, - &top->session->header.env, - !top->record_opts.overwrite, - &top->annotation_opts); - + ret = evlist__tui_browse_hists(top->evlist, help, &hbt, top->min_percent, + &top->session->header.env, !top->record_opts.overwrite, + &top->annotation_opts); if (ret == K_RELOAD) { top->zero = true; goto repeat; @@ -782,7 +779,7 @@ static void perf_event__process_sample(struct perf_tool *tool, if (!machine->kptr_restrict_warned && symbol_conf.kptr_restrict && al.cpumode == PERF_RECORD_MISC_KERNEL) { - if (!perf_evlist__exclude_kernel(top->session->evlist)) { + if (!evlist__exclude_kernel(top->session->evlist)) { ui__warning( "Kernel address maps (/proc/{kallsyms,modules}) are restricted.\n\n" "Check /proc/sys/kernel/kptr_restrict and /proc/sys/kernel/perf_event_paranoid.\n\n" @@ -890,7 +887,7 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx) while ((event = perf_mmap__read_event(&md->core)) != NULL) { int ret; - ret = perf_evlist__parse_sample_timestamp(evlist, event, &last_timestamp); + ret = evlist__parse_sample_timestamp(evlist, event, &last_timestamp); if (ret && ret != -1) break; @@ -918,14 +915,14 @@ static void perf_top__mmap_read(struct perf_top *top) int i; if (overwrite) - perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_DATA_PENDING); + evlist__toggle_bkw_mmap(evlist, BKW_MMAP_DATA_PENDING); for (i = 0; i < top->evlist->core.nr_mmaps; i++) perf_top__mmap_read_idx(top, i); if (overwrite) { - perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_EMPTY); - perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_RUNNING); + evlist__toggle_bkw_mmap(evlist, BKW_MMAP_EMPTY); + evlist__toggle_bkw_mmap(evlist, BKW_MMAP_RUNNING); } } @@ -1025,7 +1022,7 @@ static int perf_top__start_counters(struct perf_top *top) goto out_err; } - perf_evlist__config(evlist, opts, &callchain_param); + evlist__config(evlist, opts, &callchain_param); evlist__for_each_entry(evlist, counter) { try_again: @@ -1153,13 +1150,13 @@ static int deliver_event(struct ordered_events *qe, return 0; } - ret = perf_evlist__parse_sample(evlist, event, &sample); + ret = evlist__parse_sample(evlist, event, &sample); if (ret) { pr_err("Can't parse sample, err = %d\n", ret); goto next_event; } - evsel = perf_evlist__id2evsel(session->evlist, sample.id); + evsel = evlist__id2evsel(session->evlist, sample.id); assert(evsel != NULL); if (event->header.type == PERF_RECORD_SAMPLE) { @@ -1469,8 +1466,7 @@ int cmd_top(int argc, const char **argv) OPT_BOOLEAN('K', "hide_kernel_symbols", &top.hide_kernel_symbols, "hide kernel symbols"), OPT_CALLBACK('m', "mmap-pages", &opts->mmap_pages, "pages", - "number of mmap data pages", - perf_evlist__parse_mmap_pages), + "number of mmap data pages", evlist__parse_mmap_pages), OPT_INTEGER('r', "realtime", &top.realtime_prio, "collect data with this RT SCHED_FIFO priority"), OPT_INTEGER('d', "delay", &top.delay_secs, @@ -1697,7 +1693,7 @@ int cmd_top(int argc, const char **argv) if (target__none(target)) target->system_wide = true; - if (perf_evlist__create_maps(top.evlist, target) < 0) { + if (evlist__create_maps(top.evlist, target) < 0) { ui__error("Couldn't create thread/CPU maps: %s\n", errno == ENOENT ? "No such process" : str_error_r(errno, errbuf, sizeof(errbuf))); goto out_delete_evlist; @@ -1762,7 +1758,7 @@ int cmd_top(int argc, const char **argv) } #endif - if (perf_evlist__start_sb_thread(top.sb_evlist, target)) { + if (evlist__start_sb_thread(top.sb_evlist, target)) { pr_debug("Couldn't start the BPF side band thread:\nBPF programs starting from now on won't be annotatable\n"); opts->no_bpf_event = true; } @@ -1770,7 +1766,7 @@ int cmd_top(int argc, const char **argv) status = __cmd_top(&top); if (!opts->no_bpf_event) - perf_evlist__stop_sb_thread(top.sb_evlist); + evlist__stop_sb_thread(top.sb_evlist); out_delete_evlist: evlist__delete(top.evlist); diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index de80534473af..85b6a46e85b6 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -3105,7 +3105,7 @@ static void trace__handle_event(struct trace *trace, union perf_event *event, st return; } - evsel = perf_evlist__id2evsel(trace->evlist, sample->id); + evsel = evlist__id2evsel(trace->evlist, sample->id); if (evsel == NULL) { fprintf(trace->output, "Unknown tp ID %" PRIu64 ", skipping...\n", sample->id); return; @@ -3666,7 +3666,7 @@ static int trace__set_filter_loop_pids(struct trace *trace) thread = parent; } - err = perf_evlist__append_tp_filter_pids(trace->evlist, nr, pids); + err = evlist__append_tp_filter_pids(trace->evlist, nr, pids); if (!err && trace->filter_pids.map) err = bpf_map__set_filter_pids(trace->filter_pids.map, nr, pids); @@ -3680,11 +3680,11 @@ static int trace__set_filter_pids(struct trace *trace) * Better not use !target__has_task() here because we need to cover the * case where no threads were specified in the command line, but a * workload was, and in that case we will fill in the thread_map when - * we fork the workload in perf_evlist__prepare_workload. + * we fork the workload in evlist__prepare_workload. */ if (trace->filter_pids.nr > 0) { - err = perf_evlist__append_tp_filter_pids(trace->evlist, trace->filter_pids.nr, - trace->filter_pids.entries); + err = evlist__append_tp_filter_pids(trace->evlist, trace->filter_pids.nr, + trace->filter_pids.entries); if (!err && trace->filter_pids.map) { err = bpf_map__set_filter_pids(trace->filter_pids.map, trace->filter_pids.nr, trace->filter_pids.entries); @@ -3700,9 +3700,8 @@ static int __trace__deliver_event(struct trace *trace, union perf_event *event) { struct evlist *evlist = trace->evlist; struct perf_sample sample; - int err; + int err = evlist__parse_sample(evlist, event, &sample); - err = perf_evlist__parse_sample(evlist, event, &sample); if (err) fprintf(trace->output, "Can't parse sample, err = %d, skipping...\n", err); else @@ -3735,7 +3734,7 @@ static int trace__deliver_event(struct trace *trace, union perf_event *event) if (!trace->sort_events) return __trace__deliver_event(trace, event); - err = perf_evlist__parse_sample_timestamp(trace->evlist, event, &trace->oe.last); + err = evlist__parse_sample_timestamp(trace->evlist, event, &trace->oe.last); if (err && err != -1) return err; @@ -3951,7 +3950,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv) if (trace->cgroup) evlist__set_default_cgroup(trace->evlist, trace->cgroup); - err = perf_evlist__create_maps(evlist, &trace->opts.target); + err = evlist__create_maps(evlist, &trace->opts.target); if (err < 0) { fprintf(trace->output, "Problems parsing the target to trace, check your options!\n"); goto out_delete_evlist; @@ -3963,14 +3962,13 @@ static int trace__run(struct trace *trace, int argc, const char **argv) goto out_delete_evlist; } - perf_evlist__config(evlist, &trace->opts, &callchain_param); + evlist__config(evlist, &trace->opts, &callchain_param); signal(SIGCHLD, sig_handler); signal(SIGINT, sig_handler); if (forks) { - err = perf_evlist__prepare_workload(evlist, &trace->opts.target, - argv, false, NULL); + err = evlist__prepare_workload(evlist, &trace->opts.target, argv, false, NULL); if (err < 0) { fprintf(trace->output, "Couldn't run the workload!\n"); goto out_delete_evlist; @@ -4028,7 +4026,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv) err = trace__expand_filters(trace, &evsel); if (err) goto out_delete_evlist; - err = perf_evlist__apply_filters(evlist, &evsel); + err = evlist__apply_filters(evlist, &evsel); if (err < 0) goto out_error_apply_filters; @@ -4043,7 +4041,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv) evlist__enable(evlist); if (forks) - perf_evlist__start_workload(evlist); + evlist__start_workload(evlist); if (trace->opts.initial_delay) { usleep(trace->opts.initial_delay * 1000); @@ -4229,12 +4227,10 @@ static int trace__replay(struct trace *trace) if (err) goto out; - evsel = perf_evlist__find_tracepoint_by_name(session->evlist, - "raw_syscalls:sys_enter"); + evsel = evlist__find_tracepoint_by_name(session->evlist, "raw_syscalls:sys_enter"); /* older kernels have syscalls tp versus raw_syscalls */ if (evsel == NULL) - evsel = perf_evlist__find_tracepoint_by_name(session->evlist, - "syscalls:sys_enter"); + evsel = evlist__find_tracepoint_by_name(session->evlist, "syscalls:sys_enter"); if (evsel && (evsel__init_raw_syscall_tp(evsel, trace__sys_enter) < 0 || @@ -4243,11 +4239,9 @@ static int trace__replay(struct trace *trace) goto out; } - evsel = perf_evlist__find_tracepoint_by_name(session->evlist, - "raw_syscalls:sys_exit"); + evsel = evlist__find_tracepoint_by_name(session->evlist, "raw_syscalls:sys_exit"); if (evsel == NULL) - evsel = perf_evlist__find_tracepoint_by_name(session->evlist, - "syscalls:sys_exit"); + evsel = evlist__find_tracepoint_by_name(session->evlist, "syscalls:sys_exit"); if (evsel && (evsel__init_raw_syscall_tp(evsel, trace__sys_exit) < 0 || perf_evsel__init_sc_tp_uint_field(evsel, ret))) { @@ -4769,8 +4763,7 @@ int cmd_trace(int argc, const char **argv) OPT_BOOLEAN(0, "no-inherit", &trace.opts.no_inherit, "child tasks do not inherit counters"), OPT_CALLBACK('m', "mmap-pages", &trace.opts.mmap_pages, "pages", - "number of mmap data pages", - perf_evlist__parse_mmap_pages), + "number of mmap data pages", evlist__parse_mmap_pages), OPT_STRING('u', "uid", &trace.opts.target.uid_str, "user", "user to profile"), OPT_CALLBACK(0, "duration", &trace, "float", @@ -4907,7 +4900,7 @@ int cmd_trace(int argc, const char **argv) if (evsel) { trace.syscalls.events.augmented = evsel; - evsel = perf_evlist__find_tracepoint_by_name(trace.evlist, "raw_syscalls:sys_enter"); + evsel = evlist__find_tracepoint_by_name(trace.evlist, "raw_syscalls:sys_enter"); if (evsel == NULL) { pr_err("ERROR: raw_syscalls:sys_enter not found in the augmented BPF object\n"); goto out; diff --git a/tools/perf/builtin-version.c b/tools/perf/builtin-version.c index d09ec2f03071..9cd074a3d825 100644 --- a/tools/perf/builtin-version.c +++ b/tools/perf/builtin-version.c @@ -80,6 +80,7 @@ static void library_status(void) STATUS(HAVE_LIBBPF_SUPPORT, bpf); STATUS(HAVE_AIO_SUPPORT, aio); STATUS(HAVE_ZSTD_SUPPORT, zstd); + STATUS(HAVE_LIBPFM, libpfm4); } int cmd_version(int argc, const char **argv) diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index 15ecb1803fb9..dded93a2bc89 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -144,6 +144,8 @@ check arch/x86/lib/insn.c '-I "^#include [\"<]\(../include/\)*asm/in # diff non-symmetric files check_2 tools/perf/arch/x86/entry/syscalls/syscall_64.tbl arch/x86/entry/syscalls/syscall_64.tbl +check_2 tools/perf/arch/powerpc/entry/syscalls/syscall.tbl arch/powerpc/kernel/syscalls/syscall.tbl +check_2 tools/perf/arch/s390/entry/syscalls/syscall.tbl arch/s390/kernel/syscalls/syscall.tbl for i in $BEAUTY_FILES; do beauty_check $i -B diff --git a/tools/perf/pmu-events/arch/arm64/freescale/imx8mm/sys/ddrc.json b/tools/perf/pmu-events/arch/arm64/freescale/imx8mm/sys/ddrc.json new file mode 100644 index 000000000000..3b1cd708f568 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/freescale/imx8mm/sys/ddrc.json @@ -0,0 +1,39 @@ +[ + { + "BriefDescription": "ddr cycles event", + "EventCode": "0x00", + "EventName": "imx8mm_ddr.cycles", + "Unit": "imx8_ddr", + "Compat": "i.MX8MM" + }, + { + "BriefDescription": "ddr read-cycles event", + "EventCode": "0x2a", + "EventName": "imx8mm_ddr.read_cycles", + "Unit": "imx8_ddr", + "Compat": "i.MX8MM" + }, + { + "BriefDescription": "ddr write-cycles event", + "EventCode": "0x2b", + "EventName": "imx8mm_ddr.write_cycles", + "Unit": "imx8_ddr", + "Compat": "i.MX8MM" + }, + { + "BriefDescription": "ddr read event", + "EventCode": "0x35", + "EventName": "imx8mm_ddr.read", + "Unit": "imx8_ddr", + "Compat": "i.MX8MM" + }, + { + "BriefDescription": "ddr write event", + "EventCode": "0x38", + "EventName": "imx8mm_ddr.write", + "Unit": "imx8_ddr", + "Compat": "i.MX8MM" + } +] + + diff --git a/tools/perf/pmu-events/arch/arm64/freescale/imx8mm/sys/metrics.json b/tools/perf/pmu-events/arch/arm64/freescale/imx8mm/sys/metrics.json new file mode 100644 index 000000000000..8e553b67cae6 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/freescale/imx8mm/sys/metrics.json @@ -0,0 +1,18 @@ +[ + { + "BriefDescription": "bytes all masters read from ddr based on read-cycles event", + "MetricName": "imx8mm_ddr_read.all", + "MetricExpr": "imx8mm_ddr.read_cycles * 4 * 4", + "ScaleUnit": "9.765625e-4KB", + "Unit": "imx8_ddr", + "Compat": "i.MX8MM" + }, + { + "BriefDescription": "bytes all masters write to ddr based on write-cycles event", + "MetricName": "imx8mm_ddr_write.all", + "MetricExpr": "imx8mm_ddr.write_cycles * 4 * 4", + "ScaleUnit": "9.765625e-4KB", + "Unit": "imx8_ddr", + "Compat": "i.MX8MM" + } +] diff --git a/tools/perf/pmu-events/arch/test/arch-std-events.json b/tools/perf/pmu-events/arch/test/arch-std-events.json new file mode 100644 index 000000000000..43f6f729d6ae --- /dev/null +++ b/tools/perf/pmu-events/arch/test/arch-std-events.json @@ -0,0 +1,8 @@ +[ + { + "PublicDescription": "Attributable Level 3 cache access, read", + "EventCode": "0x40", + "EventName": "L3_CACHE_RD", + "BriefDescription": "L3 cache access, read" + } +] diff --git a/tools/perf/pmu-events/arch/test/test_cpu/cache.json b/tools/perf/pmu-events/arch/test/test_cpu/cache.json new file mode 100644 index 000000000000..036d0efdb2bb --- /dev/null +++ b/tools/perf/pmu-events/arch/test/test_cpu/cache.json @@ -0,0 +1,5 @@ +[ + { + "ArchStdEvent": "L3_CACHE_RD" + } +]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/skylake/cache.json b/tools/perf/pmu-events/arch/x86/skylake/cache.json index 720458139049..27ea2b00ad00 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/cache.json +++ b/tools/perf/pmu-events/arch/x86/skylake/cache.json @@ -1,2928 +1,2926 @@ [ { - "PublicDescription": "Counts the number of demand Data Read requests that miss L2 cache. Only not rejected loads are counted.", - "EventCode": "0x24", - "Counter": "0,1,2,3", - "UMask": "0x21", - "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS", - "SampleAfterValue": "200003", - "BriefDescription": "Demand Data Read miss L2, no rejects", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.", - "EventCode": "0x24", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x22", - "EventName": "L2_RQSTS.RFO_MISS", - "SampleAfterValue": "200003", - "BriefDescription": "RFO requests that miss L2 cache", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0400400002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts L2 cache misses when fetching instructions.", - "EventCode": "0x24", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x24", - "EventName": "L2_RQSTS.CODE_RD_MISS", - "SampleAfterValue": "200003", - "BriefDescription": "L2 cache misses when fetching instructions", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0400108000", + "Offcore": "1", + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Demand requests that miss L2 cache.", - "EventCode": "0x24", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x27", - "EventName": "L2_RQSTS.ALL_DEMAND_MISS", - "SampleAfterValue": "200003", - "BriefDescription": "Demand requests that miss L2 cache", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0100040002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that miss L2 cache.", - "EventCode": "0x24", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x38", - "EventName": "L2_RQSTS.PF_MISS", - "SampleAfterValue": "200003", - "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that miss L2 cache", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC0080001", + "Offcore": "1", + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "All requests that miss L2 cache.", - "EventCode": "0x24", + "BriefDescription": "Demand RFO requests including regular RFOs, locks, ItoM", "Counter": "0,1,2,3", - "UMask": "0x3f", - "EventName": "L2_RQSTS.MISS", - "SampleAfterValue": "200003", - "BriefDescription": "All requests that miss L2 cache", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB0", + "EventName": "OFFCORE_REQUESTS.DEMAND_RFO", + "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.", + "SampleAfterValue": "100003", + "UMask": "0x4" }, { - "PublicDescription": "Counts the number of demand Data Read requests, initiated by load instructions, that hit L2 cache", - "EventCode": "0x24", + "BriefDescription": "Counts all demand code readshave any response type.", "Counter": "0,1,2,3", - "UMask": "0xc1", - "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", - "SampleAfterValue": "200003", - "BriefDescription": "Demand Data Read requests that hit L2 cache", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0000010004", + "Offcore": "1", + "PublicDescription": "Counts all demand code readshave any response type.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.", - "EventCode": "0x24", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0xc2", - "EventName": "L2_RQSTS.RFO_HIT", - "SampleAfterValue": "200003", - "BriefDescription": "RFO requests that hit L2 cache", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0100020002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.", - "EventCode": "0x24", + "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that miss L2 cache", "Counter": "0,1,2,3", - "UMask": "0xc4", - "EventName": "L2_RQSTS.CODE_RD_HIT", - "SampleAfterValue": "200003", - "BriefDescription": "L2 cache hits when fetching instructions, code reads.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "PublicDescription": "Counts requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that hit L2 cache.", + "CounterHTOff": "0,1,2,3,4,5,6,7", "EventCode": "0x24", - "Counter": "0,1,2,3", - "UMask": "0xd8", - "EventName": "L2_RQSTS.PF_HIT", + "EventName": "L2_RQSTS.PF_MISS", + "PublicDescription": "Counts requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that miss L2 cache.", "SampleAfterValue": "200003", - "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that hit L2 cache", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x38" }, { - "PublicDescription": "Counts the number of demand Data Read requests (including requests from L1D hardware prefetchers). These loads may hit or miss L2 cache. Only non rejected loads are counted.", - "EventCode": "0x24", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0xe1", - "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", - "SampleAfterValue": "200003", - "BriefDescription": "Demand Data Read requests", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC01C0004", + "Offcore": "1", + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.", - "EventCode": "0x24", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0xe2", - "EventName": "L2_RQSTS.ALL_RFO", - "SampleAfterValue": "200003", - "BriefDescription": "RFO requests to L2 cache", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0100040001", + "Offcore": "1", + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts the total number of L2 code requests.", - "EventCode": "0x24", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0xe4", - "EventName": "L2_RQSTS.ALL_CODE_RD", - "SampleAfterValue": "200003", - "BriefDescription": "L2 code requests", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0040100001", + "Offcore": "1", + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Demand requests to L2 cache.", - "EventCode": "0x24", + "BriefDescription": "Demand requests that miss L2 cache", "Counter": "0,1,2,3", - "UMask": "0xe7", - "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES", - "SampleAfterValue": "200003", - "BriefDescription": "Demand requests to L2 cache", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "PublicDescription": "Counts the total number of requests from the L2 hardware prefetchers.", + "CounterHTOff": "0,1,2,3,4,5,6,7", "EventCode": "0x24", - "Counter": "0,1,2,3", - "UMask": "0xf8", - "EventName": "L2_RQSTS.ALL_PF", + "EventName": "L2_RQSTS.ALL_DEMAND_MISS", + "PublicDescription": "Demand requests that miss L2 cache.", "SampleAfterValue": "200003", - "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x27" }, { - "PublicDescription": "All L2 requests.", - "EventCode": "0x24", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0xff", - "EventName": "L2_RQSTS.REFERENCES", - "SampleAfterValue": "200003", - "BriefDescription": "All L2 requests", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0400100002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches from L1 and L2. It does not include all misses to the L3.", - "EventCode": "0x2E", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x41", - "Errata": "SKL057", - "EventName": "LONGEST_LAT_CACHE.MISS", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0080028000", + "Offcore": "1", + "PublicDescription": "Counts any other requests", "SampleAfterValue": "100003", - "BriefDescription": "Core-originated cacheable demand requests missed L3", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches from L1 and L2. It does not include all accesses to the L3.", - "EventCode": "0x2E", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x4f", - "Errata": "SKL057", - "EventName": "LONGEST_LAT_CACHE.REFERENCE", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0040080004", + "Offcore": "1", + "PublicDescription": "Counts all demand code reads", "SampleAfterValue": "100003", - "BriefDescription": "Core-originated cacheable demand requests that refer to L3", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts duration of L1D miss outstanding, that is each cycle number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch.Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.", - "EventCode": "0x48", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "L1D_PEND_MISS.PENDING", - "SampleAfterValue": "2000003", - "BriefDescription": "L1D miss outstandings duration in cycles", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC0408000", + "Offcore": "1", + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts duration of L1D miss outstanding in cycles.", - "EventCode": "0x48", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "L1D_PEND_MISS.PENDING_CYCLES", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with L1D load Misses outstanding.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0400400004", + "Offcore": "1", + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0x48", + "BriefDescription": "Retired load instructions with L3 cache hits as data sources", "Counter": "0,1,2,3", - "UMask": "0x1", - "AnyThread": "1", - "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_RETIRED.L3_HIT", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.", + "SampleAfterValue": "50021", + "UMask": "0x4" }, { - "PublicDescription": "Number of times a request needed a FB (Fill Buffer) entry but there was no entry available for it. A request includes cacheable/uncacheable demands that are load, store or SW prefetch instructions.", - "EventCode": "0x48", + "BriefDescription": "L2 writebacks that access L2 cache", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "L1D_PEND_MISS.FB_FULL", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of times a request needed a FB entry but there was no entry available for it. That is the FB unavailability was dominant reason for blocking the request. A request includes cacheable/uncacheable demands that is load, store or SW prefetch.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF0", + "EventName": "L2_TRANS.L2_WB", + "PublicDescription": "Counts L2 writebacks that access L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x40" }, { - "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.", - "EventCode": "0x51", + "BriefDescription": "L2 cache lines filling L2", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "L1D.REPLACEMENT", - "SampleAfterValue": "2000003", - "BriefDescription": "L1D data line replacements", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF1", + "EventName": "L2_LINES_IN.ALL", + "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.", + "SampleAfterValue": "100003", + "UMask": "0x1f" }, { - "PublicDescription": "Counts the number of offcore outstanding Demand Data Read transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor. See the corresponding Umask under OFFCORE_REQUESTS.Note: A prefetch promoted to Demand is counted from the promotion point.", - "EventCode": "0x60", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", - "SampleAfterValue": "2000003", - "BriefDescription": "Offcore outstanding Demand Data Read transactions in uncore queue.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0400408000", + "Offcore": "1", + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts cycles when offcore outstanding Demand Data Read transactions are present in the super queue (SQ). A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation).", - "EventCode": "0x60", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x00401C0002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0x60", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.", - "CounterMask": "6", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0400040004", + "Offcore": "1", + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", - "EventCode": "0x60", + "BriefDescription": "Demand Data Read requests sent to uncore", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD", - "SampleAfterValue": "2000003", - "BriefDescription": "Offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore, every cycle.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB0", + "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD", + "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", - "EventCode": "0x60", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC0400004", + "Offcore": "1", + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts the number of offcore outstanding RFO (store) transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", - "EventCode": "0x60", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO", - "SampleAfterValue": "2000003", - "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000400001", + "Offcore": "1", + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", - "EventCode": "0x60", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0080080002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts the number of offcore outstanding cacheable Core Data Read transactions in the super queue every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", - "EventCode": "0x60", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD", - "SampleAfterValue": "2000003", - "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0080100001", + "Offcore": "1", + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", - "EventCode": "0x60", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0100400004", + "Offcore": "1", + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.", - "EventCode": "0xB0", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10001C0004", + "Offcore": "1", + "PublicDescription": "Counts all demand code reads", "SampleAfterValue": "100003", - "BriefDescription": "Demand Data Read requests sent to uncore", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts both cacheable and non-cacheable code read requests.", - "EventCode": "0xB0", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x00801C0002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", "SampleAfterValue": "100003", - "BriefDescription": "Cacheable and noncachaeble code read requests", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.", - "EventCode": "0xB0", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "OFFCORE_REQUESTS.DEMAND_RFO", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0080100004", + "Offcore": "1", + "PublicDescription": "Counts all demand code reads", "SampleAfterValue": "100003", - "BriefDescription": "Demand RFO requests including regular RFOs, locks, ItoM", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.", - "EventCode": "0xB0", + "BriefDescription": "Retired load instructions missed L3 cache as data sources", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "OFFCORE_REQUESTS.ALL_DATA_RD", - "SampleAfterValue": "100003", - "BriefDescription": "Demand and prefetch data reads", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_RETIRED.L3_MISS", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.", + "SampleAfterValue": "100007", + "UMask": "0x20" }, { - "PublicDescription": "Counts memory transactions reached the super queue including requests initiated by the core, all L3 prefetches, page walks, etc..", - "EventCode": "0xB0", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x80", - "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0040020001", + "Offcore": "1", + "PublicDescription": "Counts demand data reads", "SampleAfterValue": "100003", - "BriefDescription": "Any memory transaction that reached the SQ.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts the number of cases when the offcore requests buffer cannot take more entries for the core. This can happen when the superqueue does not contain eligible entries, or when L1D writeback pending FIFO requests is full.Note: Writeback pending FIFO has six entries.", - "EventCode": "0xB2", + "BriefDescription": "All retired store instructions.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_REQUESTS_BUFFER.SQ_FULL", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD0", + "EventName": "MEM_INST_RETIRED.ALL_STORES", + "L1_Hit_Indication": "1", + "PEBS": "1", "SampleAfterValue": "2000003", - "BriefDescription": "Offcore requests buffer cannot take more entries for this thread core.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x82" }, { - "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "EventCode": "0xB7, 0xBB", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0080020004", + "Offcore": "1", + "PublicDescription": "Counts all demand code reads", "SampleAfterValue": "100003", - "BriefDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PEBS": "1", - "PublicDescription": "Retired load instructions that miss the STLB.", - "EventCode": "0xD0", + "BriefDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared or Exclusive state. A non-threaded event.", "Counter": "0,1,2,3", - "UMask": "0x11", - "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS", - "SampleAfterValue": "100003", - "BriefDescription": "Retired load instructions that miss the STLB. (Precise Event)", - "CounterHTOff": "0,1,2,3", - "Data_LA": "1" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF2", + "EventName": "L2_LINES_OUT.SILENT", + "SampleAfterValue": "200003", + "UMask": "0x1" }, { - "PEBS": "1", - "PublicDescription": "Retired store instructions that miss the STLB.", - "EventCode": "0xD0", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x12", - "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES", - "SampleAfterValue": "100003", - "BriefDescription": "Retired store instructions that miss the STLB. (Precise Event)", "CounterHTOff": "0,1,2,3", - "Data_LA": "1", - "L1_Hit_Indication": "1" + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0040048000", + "Offcore": "1", + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PEBS": "1", - "EventCode": "0xD0", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x21", - "EventName": "MEM_INST_RETIRED.LOCK_LOADS", - "SampleAfterValue": "100007", - "BriefDescription": "Retired load instructions with locked access. (Precise Event)", "CounterHTOff": "0,1,2,3", - "Data_LA": "1" + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000088000", + "Offcore": "1", + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PEBS": "1", - "EventCode": "0xD0", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x41", - "EventName": "MEM_INST_RETIRED.SPLIT_LOADS", - "SampleAfterValue": "100003", - "BriefDescription": "Retired load instructions that split across a cacheline boundary. (Precise Event)", "CounterHTOff": "0,1,2,3", - "Data_LA": "1" + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0040400004", + "Offcore": "1", + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PEBS": "1", - "EventCode": "0xD0", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x42", - "EventName": "MEM_INST_RETIRED.SPLIT_STORES", - "SampleAfterValue": "100003", - "BriefDescription": "Retired store instructions that split across a cacheline boundary. (Precise Event)", "CounterHTOff": "0,1,2,3", - "Data_LA": "1", - "L1_Hit_Indication": "1" + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x02001C0002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PEBS": "1", - "EventCode": "0xD0", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x81", - "EventName": "MEM_INST_RETIRED.ALL_LOADS", - "SampleAfterValue": "2000003", - "BriefDescription": "All retired load instructions. (Precise Event)", "CounterHTOff": "0,1,2,3", - "Data_LA": "1" + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0080020001", + "Offcore": "1", + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PEBS": "1", - "PublicDescription": "All retired store instructions.", - "EventCode": "0xD0", + "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.", "Counter": "0,1,2,3", - "UMask": "0x82", - "EventName": "MEM_INST_RETIRED.ALL_STORES", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", "SampleAfterValue": "2000003", - "BriefDescription": "All retired store instructions. (Precise Event)", - "CounterHTOff": "0,1,2,3", - "Data_LA": "1", - "L1_Hit_Indication": "1" + "UMask": "0x8" }, { - "PEBS": "1", - "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.", - "EventCode": "0xD1", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "MEM_LOAD_RETIRED.L1_HIT", - "SampleAfterValue": "2000003", - "BriefDescription": "Retired load instructions with L1 cache hits as data sources", "CounterHTOff": "0,1,2,3", - "Data_LA": "1" + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x02001C0004", + "Offcore": "1", + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PEBS": "1", - "PublicDescription": "Retired load instructions with L2 cache hits as data sources.", - "EventCode": "0xD1", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "MEM_LOAD_RETIRED.L2_HIT", - "SampleAfterValue": "100003", - "BriefDescription": "Retired load instructions with L2 cache hits as data sources", "CounterHTOff": "0,1,2,3", - "Data_LA": "1" + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0400040002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PEBS": "1", - "PublicDescription": "Retired load instructions with L3 cache hits as data sources.", - "EventCode": "0xD1", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "MEM_LOAD_RETIRED.L3_HIT", - "SampleAfterValue": "50021", - "BriefDescription": "Retired load instructions with L3 cache hits as data sources", "CounterHTOff": "0,1,2,3", - "Data_LA": "1" + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000028000", + "Offcore": "1", + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PEBS": "1", - "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.", - "EventCode": "0xD1", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "MEM_LOAD_RETIRED.L1_MISS", - "SampleAfterValue": "100003", - "BriefDescription": "Retired load instructions missed L1 cache as data sources", "CounterHTOff": "0,1,2,3", - "Data_LA": "1" + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0200028000", + "Offcore": "1", + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PEBS": "1", - "PublicDescription": "Retired load instructions missed L2 cache as data sources.", - "EventCode": "0xD1", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "MEM_LOAD_RETIRED.L2_MISS", - "SampleAfterValue": "50021", - "BriefDescription": "Retired load instructions missed L2 cache as data sources", "CounterHTOff": "0,1,2,3", - "Data_LA": "1" + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x04001C0001", + "Offcore": "1", + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PEBS": "1", - "PublicDescription": "Retired load instructions missed L3 cache as data sources.", - "EventCode": "0xD1", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x20", - "EventName": "MEM_LOAD_RETIRED.L3_MISS", - "SampleAfterValue": "100007", - "BriefDescription": "Retired load instructions missed L3 cache as data sources", "CounterHTOff": "0,1,2,3", - "Data_LA": "1" + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0100400001", + "Offcore": "1", + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PEBS": "1", - "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.", - "EventCode": "0xD1", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x40", - "EventName": "MEM_LOAD_RETIRED.FB_HIT", - "SampleAfterValue": "100007", - "BriefDescription": "Retired load instructions which data sources were load missed L1 but hit FB due to preceding miss to the same cache line with data not ready", "CounterHTOff": "0,1,2,3", - "Data_LA": "1" + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x04001C8000", + "Offcore": "1", + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PEBS": "1", - "EventCode": "0xD2", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS", - "SampleAfterValue": "20011", - "BriefDescription": "Retired load instructions which data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", "CounterHTOff": "0,1,2,3", - "Data_LA": "1" + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000080001", + "Offcore": "1", + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PEBS": "1", - "PublicDescription": "Retired load instructions which data sources were L3 and cross-core snoop hits in on-pkg core cache.", - "EventCode": "0xD2", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT", - "SampleAfterValue": "20011", - "BriefDescription": "Retired load instructions which data sources were L3 and cross-core snoop hits in on-pkg core cache", "CounterHTOff": "0,1,2,3", - "Data_LA": "1" + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0200020001", + "Offcore": "1", + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PEBS": "1", - "PublicDescription": "Retired load instructions which data sources were HitM responses from shared L3.", - "EventCode": "0xD2", + "BriefDescription": "Core-originated cacheable demand requests missed L3", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM", - "SampleAfterValue": "20011", - "BriefDescription": "Retired load instructions which data sources were HitM responses from shared L3", - "CounterHTOff": "0,1,2,3", - "Data_LA": "1" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL057", + "EventCode": "0x2E", + "EventName": "LONGEST_LAT_CACHE.MISS", + "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches from L1 and L2. It does not include all misses to the L3.", + "SampleAfterValue": "100003", + "UMask": "0x41" }, { - "PEBS": "1", - "PublicDescription": "Retired load instructions which data sources were hits in L3 without snoops required.", - "EventCode": "0xD2", + "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_PF", + "PublicDescription": "Counts the total number of requests from the L2 hardware prefetchers.", + "SampleAfterValue": "200003", + "UMask": "0xf8" + }, + { + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE", - "SampleAfterValue": "100003", - "BriefDescription": "Retired load instructions which data sources were hits in L3 without snoops required", "CounterHTOff": "0,1,2,3", - "Data_LA": "1" + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC0080004", + "Offcore": "1", + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PEBS": "1", - "EventCode": "0xD4", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "MEM_LOAD_MISC_RETIRED.UC", - "SampleAfterValue": "100007", - "BriefDescription": "Retired instructions with at least 1 uncacheable load or lock.", "CounterHTOff": "0,1,2,3", - "Data_LA": "1" + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0100400002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts L2 writebacks that access L2 cache.", - "EventCode": "0xF0", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x40", - "EventName": "L2_TRANS.L2_WB", - "SampleAfterValue": "200003", - "BriefDescription": "L2 writebacks that access L2 cache", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0040040002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.", - "EventCode": "0xF1", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1f", - "EventName": "L2_LINES_IN.ALL", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000400002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", "SampleAfterValue": "100003", - "BriefDescription": "L2 cache lines filling L2", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0xF2", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "L2_LINES_OUT.SILENT", - "SampleAfterValue": "200003", - "BriefDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared or Exclusive state. A non-threaded event.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0100028000", + "Offcore": "1", + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0xF2", + "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "L2_LINES_OUT.NON_SILENT", - "SampleAfterValue": "200003", - "BriefDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO", + "PublicDescription": "Counts the number of offcore outstanding RFO (store) transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "2000003", + "UMask": "0x4" }, { - "PublicDescription": "This event is deprecated. Refer to new event L2_LINES_OUT.USELESS_HWPF", - "EventCode": "0xF2", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "L2_LINES_OUT.USELESS_PREF", - "SampleAfterValue": "200003", - "BriefDescription": "This event is deprecated. Refer to new event L2_LINES_OUT.USELESS_HWPF", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0200080004", + "Offcore": "1", + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0xF2", + "BriefDescription": "RFO requests that miss L2 cache", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "L2_LINES_OUT.USELESS_HWPF", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.RFO_MISS", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.", "SampleAfterValue": "200003", - "BriefDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x22" }, { - "PublicDescription": "Counts the number of cache line split locks sent to the uncore.", - "EventCode": "0xF4", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "SQ_MISC.SPLIT_LOCK", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0400040001", + "Offcore": "1", + "PublicDescription": "Counts demand data reads", "SampleAfterValue": "100003", - "BriefDescription": "Number of cache line split locks sent to uncore.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC0408000", + "BriefDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF2", + "EventName": "L2_LINES_OUT.NON_SILENT", + "SampleAfterValue": "200003", + "UMask": "0x2" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000408000", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", "BriefDescription": "Counts any other requests", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0040028000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400408000", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0200040002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200408000", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0200408000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" - }, - { "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100408000", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080408000", + "BriefDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF2", + "EventName": "L2_LINES_OUT.USELESS_HWPF", + "SampleAfterValue": "200003", + "UMask": "0x4" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0040408000", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0200040001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC01C8000", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0200100001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10001C8000", + "BriefDescription": "Counts all demand data writes (RFOs)have any response type.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0000010002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)have any response type.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04001C8000", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x04001C0002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x02001C8000", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x00401C0004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01001C8000", + "BriefDescription": "All requests that miss L2 cache", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.MISS", + "PublicDescription": "All requests that miss L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x3f" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00801C8000", + "BriefDescription": "L2 code requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_CODE_RD", + "PublicDescription": "Counts the total number of L2 code requests.", + "SampleAfterValue": "200003", + "UMask": "0xe4" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00401C8000", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC0100002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC0108000", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0400100004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000108000", + "BriefDescription": "RFO requests that hit L2 cache", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.RFO_HIT", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0xc2" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400108000", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", "BriefDescription": "Counts any other requests", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0080048000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" - }, - { "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200108000", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100108000", + "BriefDescription": "Retired load instructions which data sources were L3 and cross-core snoop hits in on-pkg core cache", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT", + "PEBS": "1", + "PublicDescription": "Retired load instructions which data sources were L3 and cross-core snoop hits in on-pkg core cache.", + "SampleAfterValue": "20011", + "UMask": "0x2" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080108000", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10001C0001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0040108000", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000080002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC0088000", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000040002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000088000", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", "BriefDescription": "Counts any other requests", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC0028000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" - }, - { "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400088000", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200088000", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0400080001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100088000", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000080004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080088000", + "BriefDescription": "Retired load instructions missed L1 cache as data sources", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_RETIRED.L1_MISS", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.", "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x8" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0040088000", + "BriefDescription": "L2 cache misses when fetching instructions", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.CODE_RD_MISS", + "PublicDescription": "Counts L2 cache misses when fetching instructions.", + "SampleAfterValue": "200003", + "UMask": "0x24" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC0048000", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x01001C0001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000048000", + "BriefDescription": "Offcore outstanding Demand Data Read transactions in uncore queue.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", + "PublicDescription": "Counts the number of offcore outstanding Demand Data Read transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor. See the corresponding Umask under OFFCORE_REQUESTS.Note: A prefetch promoted to Demand is counted from the promotion point.", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400048000", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0040080002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200048000", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC01C0001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100048000", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", "BriefDescription": "Counts any other requests", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0400028000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" - }, - { "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080048000", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0040048000", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", "BriefDescription": "Counts any other requests", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0400088000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" - }, - { "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC0028000", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000028000", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0080400001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400028000", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0080400002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200028000", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", "BriefDescription": "Counts any other requests", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x02001C8000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100028000", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0100020001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080028000", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0100080002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0040028000", + "BriefDescription": "Cycles with offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_CODE_RD", + "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "PublicDescription": "Counts any other requests have any response type.", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0000018000", + "BriefDescription": "Demand requests to L2 cache", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.ANY_RESPONSE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests have any response type.", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES", + "PublicDescription": "Demand requests to L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0xe7" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC0400004", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0100048000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000400004", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0100108000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400400004", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000020001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200400004", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0040020002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100400004", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000108000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080400004", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0040100002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0040400004", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC0040002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC01C0004", + "AnyThread": "1", + "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10001C0004", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC01C8000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04001C0004", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x02001C0001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x02001C0004", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0200088000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01001C0004", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000100001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00801C0004", + "BriefDescription": "Core-originated cacheable demand requests that refer to L3", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL057", + "EventCode": "0x2E", + "EventName": "LONGEST_LAT_CACHE.REFERENCE", + "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches from L1 and L2. It does not include all accesses to the L3.", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x4f" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00401C0004", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0200048000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC0100004", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC0400001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000100004", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC0020004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400100004", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0080108000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200100004", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0040080001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100100004", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0100100002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080100004", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC0040004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0040100004", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0040040001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC0080004", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0100020004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000080004", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0200020004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400080004", + "BriefDescription": "Retired load instructions that miss the STLB.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD0", + "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS", + "PEBS": "1", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x11" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200080004", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0200108000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100080004", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0200400001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080080004", + "BriefDescription": "Counts demand data readshave any response type.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0000010001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data readshave any response type.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0040080004", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000400004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC0040004", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0080080004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000040004", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10001C8000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400040004", + "BriefDescription": "L1D data line replacements", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x51", + "EventName": "L1D.REPLACEMENT", + "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200040004", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0200040004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100040004", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC0400002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080040004", + "BriefDescription": "Retired instructions with at least 1 uncacheable load or lock.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD4", + "EventName": "MEM_LOAD_MISC_RETIRED.UC", + "PEBS": "1", + "SampleAfterValue": "100007", + "UMask": "0x4" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0040040004", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000040004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC0020004", + "BriefDescription": "Retired load instructions which data sources were load missed L1 but hit FB due to preceding miss to the same cache line with data not ready", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_RETIRED.FB_HIT", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.", + "SampleAfterValue": "100007", + "UMask": "0x40" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000020004", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC0020001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400020004", + "BriefDescription": "This event is deprecated. Refer to new event L2_LINES_OUT.USELESS_HWPF", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF2", + "EventName": "L2_LINES_OUT.USELESS_PREF", + "SampleAfterValue": "200003", + "UMask": "0x4" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200020004", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000020002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100020004", + "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that hit L2 cache", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.PF_HIT", + "PublicDescription": "Counts requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that hit L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0xd8" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080020004", + "BriefDescription": "Demand Data Read miss L2, no rejects", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS", + "PublicDescription": "Counts the number of demand Data Read requests that miss L2 cache. Only not rejected loads are counted.", + "SampleAfterValue": "200003", + "UMask": "0x21" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0040020004", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0040020004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any response type.", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0000010004", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any response type.", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0400100001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC0400002", + "BriefDescription": "Retired load instructions which data sources were hits in L3 without snoops required", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE", + "PEBS": "1", + "PublicDescription": "Retired load instructions which data sources were hits in L3 without snoops required.", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x8" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000400002", + "BriefDescription": "All retired load instructions.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD0", + "EventName": "MEM_INST_RETIRED.ALL_LOADS", + "PEBS": "1", + "SampleAfterValue": "2000003", + "UMask": "0x81" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400400002", + "BriefDescription": "Retired load instructions which data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS", + "PEBS": "1", + "SampleAfterValue": "20011", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200400002", + "BriefDescription": "Demand Data Read requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", + "PublicDescription": "Counts the number of demand Data Read requests (including requests from L1D hardware prefetchers). These loads may hit or miss L2 cache. Only non rejected loads are counted.", + "SampleAfterValue": "200003", + "UMask": "0xe1" + }, + { "BriefDescription": "Counts all demand data writes (RFOs)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0080020002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100400002", + "BriefDescription": "All L2 requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.REFERENCES", + "PublicDescription": "All L2 requests.", + "SampleAfterValue": "200003", + "UMask": "0xff" + }, + { "BriefDescription": "Counts all demand data writes (RFOs)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000100002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080400002", + "BriefDescription": "Cycles with L1D load Misses outstanding.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.PENDING_CYCLES", + "PublicDescription": "Counts duration of L1D miss outstanding in cycles.", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0040400002", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0100088000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC01C0002", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0200400004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10001C0002", + "BriefDescription": "Cycles with offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", + "PublicDescription": "Counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "2000003", + "UMask": "0x4" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04001C0002", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC0048000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x02001C0002", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x00401C8000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01001C0002", + "BriefDescription": "Number of cache line split locks sent to uncore.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF4", + "EventName": "SQ_MISC.SPLIT_LOCK", + "PublicDescription": "Counts the number of cache line split locks sent to the uncore.", "SampleAfterValue": "100003", + "UMask": "0x10" + }, + { "BriefDescription": "Counts all demand data writes (RFOs)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC01C0002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00801C0002", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0040408000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00401C0002", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10001C0002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts all demand data writes (RFOs)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0400080002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC0100002", + "BriefDescription": "Retired load instructions with L2 cache hits as data sources", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_RETIRED.L2_HIT", + "PEBS": "1", + "PublicDescription": "Retired load instructions with L2 cache hits as data sources.", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x2" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000100002", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC0040001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400100002", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0100100001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200100002", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0200100002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" - }, - { "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100100002", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080100002", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0080040004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0040100002", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000020004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC0080002", + "BriefDescription": "L1D miss outstandings duration in cycles", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.PENDING", + "PublicDescription": "Counts duration of L1D miss outstanding, that is each cycle number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch.Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000080002", + "BriefDescription": "Demand Data Read requests that hit L2 cache", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", + "PublicDescription": "Counts the number of demand Data Read requests, initiated by load instructions, that hit L2 cache", + "SampleAfterValue": "200003", + "UMask": "0xc1" + }, + { "BriefDescription": "Counts all demand data writes (RFOs)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0040400002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400080002", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x04001C0004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200080002", + "BriefDescription": "Retired load instructions which data sources were HitM responses from shared L3", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM", + "PEBS": "1", + "PublicDescription": "Retired load instructions which data sources were HitM responses from shared L3.", + "SampleAfterValue": "20011", + "UMask": "0x4" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100080002", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC0100001", + "Offcore": "1", + "PublicDescription": "Counts demand data reads", "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts all demand data writes (RFOs)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x01001C0002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080080002", + "BriefDescription": "Retired store instructions that split across a cacheline boundary.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD0", + "EventName": "MEM_INST_RETIRED.SPLIT_STORES", + "L1_Hit_Indication": "1", + "PEBS": "1", + "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x42" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0040080002", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0080400004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC0040002", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000100004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000040002", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x00801C0004", + "Offcore": "1", + "PublicDescription": "Counts all demand code reads", "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts all demand data writes (RFOs)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC0020002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400040002", + "BriefDescription": "Any memory transaction that reached the SQ.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB0", + "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS", + "PublicDescription": "Counts memory transactions reached the super queue including requests initiated by the core, all L3 prefetches, page walks, etc..", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x80" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200040002", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0040400001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100040002", + "BriefDescription": "Counts any other requestshave any response type.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0000018000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requestshave any response type.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080040002", + "BriefDescription": "Cacheable and noncachaeble code read requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB0", + "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD", + "PublicDescription": "Counts both cacheable and non-cacheable code read requests.", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x2" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0040040002", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0040040004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC0020002", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0100408000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000020002", + "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", + "PublicDescription": "Counts cycles when offcore outstanding Demand Data Read transactions are present in the super queue (SQ). A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation).", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400020002", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC0088000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200020002", + "BriefDescription": "L2 cache hits when fetching instructions, code reads.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.CODE_RD_HIT", + "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.", + "SampleAfterValue": "200003", + "UMask": "0xc4" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100020002", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0080040001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080020002", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0100040004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0040020002", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0080088000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs) have any response type.", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0000010002", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs) have any response type.", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000040001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC0400001", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0040088000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000400001", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0200020002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400400001", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0100100004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200400001", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0040100004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100400001", + "BriefDescription": "Number of times a request needed a FB entry but there was no entry available for it. That is the FB unavailability was dominant reason for blocking the request. A request includes cacheable/uncacheable demands that is load, store or SW prefetch.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.FB_FULL", + "PublicDescription": "Number of times a request needed a FB (Fill Buffer) entry but there was no entry available for it. A request includes cacheable/uncacheable demands that are load, store or SW prefetch instructions.", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080400001", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0400048000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0040400001", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0040108000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC01C0001", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC0108000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x10001C0001", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000048000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x04001C0001", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0400080004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x02001C0001", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0100080004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x01001C0001", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0200100004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00801C0001", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x00801C0001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00401C0001", + "BriefDescription": "Retired load instructions with L1 cache hits as data sources", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_RETIRED.L1_HIT", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC0100001", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1000408000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000100001", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0400020004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400100001", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC0100004", + "Offcore": "1", + "PublicDescription": "Counts all demand code reads", "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand data reads", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0400400001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200100001", + "BriefDescription": "Retired load instructions with locked access.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD0", + "EventName": "MEM_INST_RETIRED.LOCK_LOADS", + "PEBS": "1", + "SampleAfterValue": "100007", + "UMask": "0x21" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100100001", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x00801C8000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080100001", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0080040002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0040100001", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x01001C0004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC0080001", + "BriefDescription": "Demand and prefetch data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB0", + "EventName": "OFFCORE_REQUESTS.ALL_DATA_RD", + "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x8" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000080001", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0080408000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400080001", + "BriefDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200080001", + "BriefDescription": "Retired load instructions that split across a cacheline boundary.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD0", + "EventName": "MEM_INST_RETIRED.SPLIT_LOADS", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x41" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100080001", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0100080001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" - }, - { "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080080001", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0040080001", + "BriefDescription": "Offcore requests buffer cannot take more entries for this thread core.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB2", + "EventName": "OFFCORE_REQUESTS_BUFFER.SQ_FULL", + "PublicDescription": "Counts the number of cases when the offcore requests buffer cannot take more entries for the core. This can happen when the superqueue does not contain eligible entries, or when L1D writeback pending FIFO requests is full.Note: Writeback pending FIFO has six entries.", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC0040001", + "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "6", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000040001", + "BriefDescription": "Offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore, every cycle.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD", + "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400040001", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0200080002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200040001", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", "BriefDescription": "Counts demand data reads", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0400020001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" - }, - { "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100040001", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080040001", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0080100002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0040040001", + "BriefDescription": "Retired store instructions that miss the STLB.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD0", + "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES", + "L1_Hit_Indication": "1", + "PEBS": "1", "SampleAfterValue": "100003", + "UMask": "0x12" + }, + { "BriefDescription": "Counts demand data reads", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0200080001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC0020001", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x01001C8000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1000020001", + "BriefDescription": "RFO requests to L2 cache", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_RFO", + "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.", + "SampleAfterValue": "200003", + "UMask": "0xe2" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0400020001", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0200400002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0200020001", + "BriefDescription": "Retired load instructions missed L2 cache as data sources", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_RETIRED.L2_MISS", + "PEBS": "1", + "PublicDescription": "Retired load instructions missed L2 cache as data sources.", + "SampleAfterValue": "50021", + "UMask": "0x10" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0100020001", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0400020002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand data reads", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0080080001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0080020001", + "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD", + "PublicDescription": "Counts the number of offcore outstanding cacheable Core Data Read transactions in the super queue every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "2000003", + "UMask": "0x8" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0040020001", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC0080002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads have any response type.", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0000010001", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads have any response type.", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x00401C0001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/skylake/floating-point.json b/tools/perf/pmu-events/arch/x86/skylake/floating-point.json index 213dd6230cf2..834e1cd841fc 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/skylake/floating-point.json @@ -1,67 +1,67 @@ [ { - "EventCode": "0xC7", + "BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC7", + "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE", "SampleAfterValue": "2000003", - "BriefDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired. Each count represents 1 computation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x4" }, { - "EventCode": "0xC7", + "BriefDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", "Counter": "0,1,2,3", - "UMask": "0x2", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE", "SampleAfterValue": "2000003", - "BriefDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired. Each count represents 1 computation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" }, { - "EventCode": "0xC7", + "BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC7", + "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE", "SampleAfterValue": "2000003", - "BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired. Each count represents 2 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x10" }, { - "EventCode": "0xC7", + "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC7", + "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE", "SampleAfterValue": "2000003", - "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired. Each count represents 4 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x20" }, { - "EventCode": "0xC7", + "BriefDescription": "Cycles with any input/output SSE or FP assist", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired. Each count represents 4 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xCA", + "EventName": "FP_ASSIST.ANY", + "PublicDescription": "Counts cycles with any input and output SSE or x87 FP assist. If an input and output assist are detected on the same cycle the event increments by 1.", + "SampleAfterValue": "100003", + "UMask": "0x1e" }, { - "EventCode": "0xC7", + "BriefDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", "Counter": "0,1,2,3", - "UMask": "0x20", - "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC7", + "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", "SampleAfterValue": "2000003", - "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired. Each count represents 8 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts cycles with any input and output SSE or x87 FP assist. If an input and output assist are detected on the same cycle the event increments by 1.", - "EventCode": "0xCA", + "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", "Counter": "0,1,2,3", - "UMask": "0x1e", - "EventName": "FP_ASSIST.ANY", - "SampleAfterValue": "100003", - "BriefDescription": "Cycles with any input/output SSE or FP assist", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC7", + "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE", + "SampleAfterValue": "2000003", + "UMask": "0x8" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/skylake/frontend.json b/tools/perf/pmu-events/arch/x86/skylake/frontend.json index 7fa95a35e3ca..e84504d6adea 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/frontend.json +++ b/tools/perf/pmu-events/arch/x86/skylake/frontend.json @@ -1,482 +1,516 @@ [ { - "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).", - "EventCode": "0x79", + "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss.", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "IDQ.MITE_UOPS", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x80", + "EventName": "ICACHE_16B.IFDATA_STALL", + "PublicDescription": "Cycles where a code line fetch is stalled due to an L1 instruction cache miss. The legacy decode pipeline works at a 16 Byte granularity.", "SampleAfterValue": "2000003", - "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x4" }, { - "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ.", - "EventCode": "0x79", + "BriefDescription": "Retired Instructions who experienced iTLB true miss.", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "IDQ.MITE_CYCLES", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.ITLB_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x14", + "PEBS": "1", + "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" }, { - "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.", - "EventCode": "0x79", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "IDQ.DSB_UOPS", - "SampleAfterValue": "2000003", - "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_128", + "MSRIndex": "0x3F7", + "MSRValue": "0x408006", + "PEBS": "1", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" }, { - "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.", - "EventCode": "0x79", + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path", "Counter": "0,1,2,3", - "UMask": "0x8", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x79", "EventName": "IDQ.DSB_CYCLES", + "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x8" }, { - "PublicDescription": "Counts cycles during which uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.", - "EventCode": "0x79", + "BriefDescription": "Cycles per thread when 3 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "IDQ.MS_DSB_CYCLES", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "3", + "EventCode": "0x9C", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE", + "PublicDescription": "Counts, on the per-thread basis, cycles when less than 1 uop is delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core >= 3.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.", - "EventCode": "0x79", + "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.", "Counter": "0,1,2,3", - "UMask": "0x18", - "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops", - "CounterMask": "4", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xE6", + "EventName": "BACLEARS.ANY", + "PublicDescription": "Counts the number of times the front-end is resteered when it finds a branch instruction in a fetch line. This occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.", - "EventCode": "0x79", + "BriefDescription": "Retired Instructions who experienced decode stream buffer (DSB - the decoded instruction-cache) miss.", "Counter": "0,1,2,3", - "UMask": "0x18", - "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.DSB_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x11", + "PEBS": "1", + "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" }, { - "PublicDescription": "Counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.", - "EventCode": "0x79", + "BriefDescription": "Cycles per thread when 4 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled", "Counter": "0,1,2,3", - "UMask": "0x20", - "EventName": "IDQ.MS_MITE_UOPS", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "4", + "EventCode": "0x9C", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE", + "PublicDescription": "Counts, on the per-thread basis, cycles when no uops are delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core =4.", "SampleAfterValue": "2000003", - "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts the number of cycles 4 uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", - "EventCode": "0x79", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 16 cycles which was not interrupted by a back-end stall.", "Counter": "0,1,2,3", - "UMask": "0x24", - "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles MITE is delivering 4 Uops", - "CounterMask": "4", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_16", + "MSRIndex": "0x3F7", + "MSRValue": "0x401006", + "PEBS": "1", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" }, { - "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", - "EventCode": "0x79", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path", "Counter": "0,1,2,3", - "UMask": "0x24", - "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x79", + "EventName": "IDQ.MITE_UOPS", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles MITE is delivering any Uop", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x4" }, { - "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.", - "EventCode": "0x79", + "BriefDescription": "Cycles with less than 2 uops delivered by the front end.", "Counter": "0,1,2,3", - "UMask": "0x30", - "EventName": "IDQ.MS_CYCLES", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "2", + "EventCode": "0x9C", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_2_UOP_DELIV.CORE", + "PublicDescription": "Cycles with less than 2 uops delivered by the front-end.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.", - "EventCode": "0x79", + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", "Counter": "0,1,2,3", - "UMask": "0x30", - "EdgeDetect": "1", - "EventName": "IDQ.MS_SWITCHES", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer", + "CounterHTOff": "0,1,2,3,4,5,6,7", "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Any instruction over 4 uops will be delivered by the MS. Some instructions such as transcendentals may additionally generate uops from the MS.", "EventCode": "0x79", - "Counter": "0,1,2,3", - "UMask": "0x30", - "EventName": "IDQ.MS_UOPS", + "EventName": "IDQ.MS_CYCLES", + "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.", "SampleAfterValue": "2000003", - "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x30" }, { - "PublicDescription": "Cycles where a code line fetch is stalled due to an L1 instruction cache miss. The legacy decode pipeline works at a 16 Byte granularity.", - "EventCode": "0x80", + "BriefDescription": "Cycles MITE is delivering any Uop", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "ICACHE_16B.IFDATA_STALL", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS", + "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x24" }, { - "EventCode": "0x83", + "BriefDescription": "Instruction fetch tag lookups that hit in the instruction cache (L1I). Counts at 64-byte cache-line granularity.", "Counter": "0,1,2,3", - "UMask": "0x1", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x83", "EventName": "ICACHE_64B.IFTAG_HIT", "SampleAfterValue": "200003", - "BriefDescription": "Instruction fetch tag lookups that hit in the instruction cache (L1I). Counts at 64-byte cache-line granularity.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0x83", + "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "ICACHE_64B.IFTAG_MISS", - "SampleAfterValue": "200003", - "BriefDescription": "Instruction fetch tag lookups that miss in the instruction cache (L1I). Counts at 64-byte cache-line granularity.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0x79", + "EventName": "IDQ.MS_SWITCHES", + "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.", + "SampleAfterValue": "2000003", + "UMask": "0x30" }, { - "EventCode": "0x83", + "BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss.", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "ICACHE_64B.IFTAG_STALL", - "SampleAfterValue": "200003", - "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.L2_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x13", + "PEBS": "1", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" }, { - "PublicDescription": "Counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding \u201c4 \u2013 x\u201d when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when: a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread. b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions). c. Instruction Decode Queue (IDQ) delivers four uops.", - "EventCode": "0x9C", + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.MITE_CYCLES", + "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ.", "SampleAfterValue": "2000003", - "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x4" }, { - "PublicDescription": "Counts, on the per-thread basis, cycles when no uops are delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core =4.", - "EventCode": "0x9C", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when 4 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled", - "CounterMask": "4", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_64", + "MSRIndex": "0x3F7", + "MSRValue": "0x404006", + "PEBS": "1", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" }, { - "PublicDescription": "Counts, on the per-thread basis, cycles when less than 1 uop is delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core >= 3.", - "EventCode": "0x9C", + "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x9C", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", + "PublicDescription": "Counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding 4 x when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when: a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread. b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions). c. Instruction Decode Queue (IDQ) delivers four uops.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when 3 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled", - "CounterMask": "3", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Cycles with less than 2 uops delivered by the front-end.", - "EventCode": "0x9C", + "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_2_UOP_DELIV.CORE", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x79", + "EventName": "IDQ.MS_MITE_UOPS", + "PublicDescription": "Counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with less than 2 uops delivered by the front end.", - "CounterMask": "2", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x20" }, { - "PublicDescription": "Cycles with less than 3 uops delivered by the front-end.", - "EventCode": "0x9C", + "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_3_UOP_DELIV.CORE", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with less than 3 uops delivered by the front end.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x83", + "EventName": "ICACHE_64B.IFTAG_STALL", + "SampleAfterValue": "200003", + "UMask": "0x4" }, { - "EventCode": "0x9C", - "Invert": "1", + "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xAB", + "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", + "PublicDescription": "Counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. MM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.Penalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 02 cycles.", "SampleAfterValue": "2000003", - "BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" }, { - "PublicDescription": "Counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. MM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.Penalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 0\u20132 cycles.", - "EventCode": "0xAB", + "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS", + "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.", "SampleAfterValue": "2000003", - "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x18" }, { - "PEBS": "1", - "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.", - "EventCode": "0xC6", - "MSRValue": "0x11", + "BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "FRONTEND_RETIRED.DSB_MISS", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.STLB_MISS", "MSRIndex": "0x3F7", + "MSRValue": "0x15", + "PEBS": "1", + "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.", "SampleAfterValue": "100007", - "BriefDescription": "Retired Instructions who experienced decode stream buffer (DSB - the decoded instruction-cache) miss. Precise Event.", "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PEBS": "1", - "EventCode": "0xC6", - "MSRValue": "0x12", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "FRONTEND_RETIRED.L1I_MISS", - "MSRIndex": "0x3F7", - "SampleAfterValue": "100007", - "BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss. Precise Event.", - "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x79", + "EventName": "IDQ.DSB_UOPS", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.", + "SampleAfterValue": "2000003", + "UMask": "0x8" }, { - "PEBS": "1", - "EventCode": "0xC6", - "MSRValue": "0x13", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "FRONTEND_RETIRED.L2_MISS", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_512", "MSRIndex": "0x3F7", + "MSRValue": "0x420006", + "PEBS": "1", "SampleAfterValue": "100007", - "BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss. Precise Event.", "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PEBS": "1", - "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.", - "EventCode": "0xC6", - "MSRValue": "0x14", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 8 cycles which was not interrupted by a back-end stall.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "FRONTEND_RETIRED.ITLB_MISS", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_8", "MSRIndex": "0x3F7", + "MSRValue": "0x400806", + "PEBS": "1", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.", "SampleAfterValue": "100007", - "BriefDescription": "Retired Instructions who experienced iTLB true miss. Precise Event.", "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PEBS": "1", - "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.", - "EventCode": "0xC6", - "MSRValue": "0x15", + "BriefDescription": "Retired instructions after front-end starvation of at least 1 cycle", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "FRONTEND_RETIRED.STLB_MISS", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_1", "MSRIndex": "0x3F7", + "MSRValue": "0x400106", + "PEBS": "2", + "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall.", "SampleAfterValue": "100007", - "BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss. Precise Event.", "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PEBS": "1", - "EventCode": "0xC6", - "MSRValue": "0x400206", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 2 cycles which was not interrupted by a back-end stall.", "Counter": "0,1,2,3", - "UMask": "0x1", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", "EventName": "FRONTEND_RETIRED.LATENCY_GE_2", "MSRIndex": "0x3F7", + "MSRValue": "0x400206", + "PEBS": "1", "SampleAfterValue": "100007", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.", "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PEBS": "1", - "EventCode": "0xC6", - "MSRValue": "0x200206", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_2", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_4", "MSRIndex": "0x3F7", + "MSRValue": "0x400406", + "PEBS": "1", "SampleAfterValue": "100007", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 2 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.", "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PEBS": "1", - "EventCode": "0xC6", - "MSRValue": "0x400406", + "BriefDescription": "Cycles MITE is delivering 4 Uops", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_4", - "MSRIndex": "0x3F7", - "SampleAfterValue": "100007", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall. Precise Event.", - "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "4", + "EventCode": "0x79", + "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS", + "PublicDescription": "Counts the number of cycles 4 uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "SampleAfterValue": "2000003", + "UMask": "0x24" }, { - "PEBS": "1", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.", - "EventCode": "0xC6", - "MSRValue": "0x400806", + "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_8", - "MSRIndex": "0x3F7", - "SampleAfterValue": "100007", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 8 cycles which was not interrupted by a back-end stall.", - "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.MS_DSB_CYCLES", + "PublicDescription": "Counts cycles during which uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.", + "SampleAfterValue": "2000003", + "UMask": "0x10" }, { - "PEBS": "1", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.", - "EventCode": "0xC6", - "MSRValue": "0x401006", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_16", - "MSRIndex": "0x3F7", - "SampleAfterValue": "100007", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 16 cycles which was not interrupted by a back-end stall. Precise Event.", - "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x79", + "EventName": "IDQ.MS_UOPS", + "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Any instruction over 4 uops will be delivered by the MS. Some instructions such as transcendentals may additionally generate uops from the MS.", + "SampleAfterValue": "2000003", + "UMask": "0x30" }, { - "PEBS": "1", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.", - "EventCode": "0xC6", - "MSRValue": "0x402006", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_32", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_256", "MSRIndex": "0x3F7", + "MSRValue": "0x410006", + "PEBS": "1", "SampleAfterValue": "100007", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 32 cycles which was not interrupted by a back-end stall. Precise Event.", "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PEBS": "1", - "EventCode": "0xC6", - "MSRValue": "0x404006", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 2 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_64", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_2", "MSRIndex": "0x3F7", + "MSRValue": "0x200206", + "PEBS": "1", "SampleAfterValue": "100007", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall. Precise Event.", "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PEBS": "1", - "EventCode": "0xC6", - "MSRValue": "0x408006", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 3 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_128", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_3", "MSRIndex": "0x3F7", + "MSRValue": "0x300206", + "PEBS": "1", "SampleAfterValue": "100007", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall. Precise Event.", "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PEBS": "1", - "EventCode": "0xC6", - "MSRValue": "0x410006", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 1 bubble-slot for a period of 2 cycles which was not interrupted by a back-end stall.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_256", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1", "MSRIndex": "0x3F7", + "MSRValue": "0x100206", + "PEBS": "1", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.", "SampleAfterValue": "100007", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall. Precise Event.", "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PEBS": "1", - "EventCode": "0xC6", - "MSRValue": "0x420006", + "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_512", - "MSRIndex": "0x3F7", - "SampleAfterValue": "100007", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall. Precise Event.", - "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "4", + "EventCode": "0x79", + "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS", + "PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.", + "SampleAfterValue": "2000003", + "UMask": "0x18" }, { - "PEBS": "1", - "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.", - "EventCode": "0xC6", - "MSRValue": "0x100206", + "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switches", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xAB", + "EventName": "DSB2MITE_SWITCHES.COUNT", + "PublicDescription": "This event counts the number of the Decode Stream Buffer (DSB)-to-MITE switches including all misses because of missing Decode Stream Buffer (DSB) cache and u-arch forced misses.\nNote: Invoking MITE requires two or three cycles delay.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 32 cycles which was not interrupted by a back-end stall.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_32", "MSRIndex": "0x3F7", + "MSRValue": "0x402006", + "PEBS": "1", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.", "SampleAfterValue": "100007", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 1 bubble-slot for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.", "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PEBS": "1", - "EventCode": "0xC6", - "MSRValue": "0x300206", + "BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x9C", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK", + "Invert": "1", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Instruction fetch tag lookups that miss in the instruction cache (L1I). Counts at 64-byte cache-line granularity.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x83", + "EventName": "ICACHE_64B.IFTAG_MISS", + "SampleAfterValue": "200003", + "UMask": "0x2" + }, + { + "BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.L1I_MISS", "MSRIndex": "0x3F7", + "MSRValue": "0x12", + "PEBS": "1", "SampleAfterValue": "100007", - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 3 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.", "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles with less than 3 uops delivered by the front end.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x9C", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_3_UOP_DELIV.CORE", + "PublicDescription": "Cycles with less than 3 uops delivered by the front-end.", + "SampleAfterValue": "2000003", + "UMask": "0x1" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/skylake/memory.json b/tools/perf/pmu-events/arch/x86/skylake/memory.json index f197b4c7695b..7bd3ae338343 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/memory.json +++ b/tools/perf/pmu-events/arch/x86/skylake/memory.json @@ -1,1604 +1,1611 @@ [ { - "PublicDescription": "Number of times a TSX line had a cache conflict.", - "EventCode": "0x54", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "TX_MEM.ABORT_CONFLICT", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of times a transactional abort was signaled due to a data conflict on a transactionally accessed address", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2000080004", + "Offcore": "1", + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0x54", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "TX_MEM.ABORT_CAPACITY", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of times a transactional abort was signaled due to a data capacity limitation for transactional reads or writes.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0104000001", + "Offcore": "1", + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Number of times a TSX Abort was triggered due to a non-release/commit store to lock.", - "EventCode": "0x54", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "TX_MEM.ABORT_HLE_STORE_TO_ELIDED_LOCK", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of times a HLE transactional region aborted due to a non XRELEASE prefixed instruction writing to an elided lock in the elision buffer", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2000100002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Number of times a TSX Abort was triggered due to commit but Lock Buffer not empty.", - "EventCode": "0x54", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_NOT_EMPTY", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of times an HLE transactional execution aborted due to NoAllocatedElisionBuffer being non-zero.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0084008000", + "Offcore": "1", + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Number of times a TSX Abort was triggered due to release/commit but data and address mismatch.", - "EventCode": "0x54", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_MISMATCH", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of times an HLE transactional execution aborted due to XRELEASE lock not satisfying the address and value requirements in the elision buffer", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x007C400004", + "Offcore": "1", + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Number of times a TSX Abort was triggered due to attempting an unsupported alignment from Lock Buffer.", - "EventCode": "0x54", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x20", - "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_UNSUPPORTED_ALIGNMENT", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of times an HLE transactional execution aborted due to an unsupported read alignment from the elision buffer.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x043C408000", + "Offcore": "1", + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Number of times we could not allocate Lock Buffer.", - "EventCode": "0x54", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x40", - "EventName": "TX_MEM.HLE_ELISION_BUFFER_FULL", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of times HLE lock could not be elided due to ElisionBufferAvailable being zero.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0204000004", + "Offcore": "1", + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0x5d", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "TX_EXEC.MISC1", - "SampleAfterValue": "2000003", - "BriefDescription": "Counts the number of times a class of instructions that may cause a transactional abort was executed. Since this is the count of execution, it may not always cause a transactional abort.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2000088000", + "Offcore": "1", + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Unfriendly TSX abort triggered by a vzeroupper instruction.", - "EventCode": "0x5d", + "BriefDescription": "Cycles with at least 6 Demand Data Read requests that miss L3 cache in the superQ.", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "TX_EXEC.MISC2", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "6", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD_GE_6", "SampleAfterValue": "2000003", - "BriefDescription": "Counts the number of times a class of instructions (e.g., vzeroupper) that may cause a transactional abort was executed inside a transactional region", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x10" }, { - "PublicDescription": "Unfriendly TSX abort triggered by a nest count that is too deep.", - "EventCode": "0x5d", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "TX_EXEC.MISC3", - "SampleAfterValue": "2000003", - "BriefDescription": "Counts the number of times an instruction execution caused the transactional nest count supported to be exceeded", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x00BC408000", + "Offcore": "1", + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "RTM region detected inside HLE.", - "EventCode": "0x5d", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "TX_EXEC.MISC4", - "SampleAfterValue": "2000003", - "BriefDescription": "Counts the number of times a XBEGIN instruction was executed inside an HLE transactional region.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x103C408000", + "Offcore": "1", + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts the number of times an HLE XACQUIRE instruction was executed inside an RTM transactional region.", - "EventCode": "0x5d", + "BriefDescription": "Number of times an HLE execution aborted due to hardware timer expiration.", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "TX_EXEC.MISC5", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC8", + "EventName": "HLE_RETIRED.ABORTED_TIMER", "SampleAfterValue": "2000003", - "BriefDescription": "Counts the number of times an HLE XACQUIRE instruction was executed inside an RTM transactional region", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x10" }, { - "EventCode": "0x60", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD", - "SampleAfterValue": "2000003", - "BriefDescription": "Counts number of Offcore outstanding Demand Data Read requests that miss L3 cache in the superQ every cycle.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x023C400001", + "Offcore": "1", + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0x60", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0204000002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0x60", + "BriefDescription": "Number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts)", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD_GE_6", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC9", + "EventName": "RTM_RETIRED.ABORTED_MEM", + "PublicDescription": "Number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts).", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with at least 6 Demand Data Read requests that miss L3 cache in the superQ.", - "CounterMask": "6", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x8" }, { - "EventCode": "0xA3", + "BriefDescription": "Number of times an RTM execution aborted due to incompatible memory type", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "CYCLE_ACTIVITY.CYCLES_L3_MISS", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC9", + "EventName": "RTM_RETIRED.ABORTED_MEMTYPE", + "PublicDescription": "Number of times an RTM execution aborted due to incompatible memory type.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles while L3 cache miss demand load is outstanding.", - "CounterMask": "2", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x40" }, { - "EventCode": "0xA3", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x6", - "EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS", - "SampleAfterValue": "2000003", - "BriefDescription": "Execution stalls while L3 cache miss demand load is outstanding.", - "CounterMask": "6", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2000080002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Demand Data Read requests who miss L3 cache.", - "EventCode": "0xB0", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1004008000", + "Offcore": "1", + "PublicDescription": "Counts any other requests", "SampleAfterValue": "100003", - "BriefDescription": "Demand Data Read requests who miss L3 cache", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts the number of memory ordering Machine Clears detected. Memory Ordering Machine Clears can result from one of the following:a. memory disambiguation,b. external snoop, orc. cross SMT-HW-thread snoop (stores) hitting load buffer.", - "EventCode": "0xC3", + "BriefDescription": "Cycles while L3 cache miss demand load is outstanding.", "Counter": "0,1,2,3", - "UMask": "0x2", - "Errata": "SKL089", - "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", - "SampleAfterValue": "100003", - "BriefDescription": "Counts the number of machine clears due to memory order conflicts.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "2", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.CYCLES_L3_MISS", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "PublicDescription": "Number of times we entered an HLE region. Does not count nested transactions.", - "EventCode": "0xC8", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "HLE_RETIRED.START", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of times an HLE execution started.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2000028000", + "Offcore": "1", + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Number of times HLE commit succeeded.", - "EventCode": "0xC8", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "HLE_RETIRED.COMMIT", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of times an HLE execution successfully committed", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FFC408000", + "Offcore": "1", + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PEBS": "1", - "PublicDescription": "Number of times HLE abort was triggered. (PEBS)", - "EventCode": "0xC8", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "HLE_RETIRED.ABORTED", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of times an HLE execution aborted due to any reasons (multiple categories may count as one).", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", + "MSRIndex": "0x3F6", + "MSRValue": "0x20", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" }, { - "EventCode": "0xC8", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "HLE_RETIRED.ABORTED_MEM", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of times an HLE execution aborted due to various memory events (e.g., read/write capacity and conflicts).", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x043C400002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0xC8", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "HLE_RETIRED.ABORTED_TIMER", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of times an HLE execution aborted due to hardware timer expiration.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2000020004", + "Offcore": "1", + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).", - "EventCode": "0xC8", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x20", - "EventName": "HLE_RETIRED.ABORTED_UNFRIENDLY", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0044000002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Number of times an HLE execution aborted due to incompatible memory type.", - "EventCode": "0xC8", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x40", - "EventName": "HLE_RETIRED.ABORTED_MEMTYPE", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of times an HLE execution aborted due to incompatible memory type", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0204008000", + "Offcore": "1", + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0xC8", + "BriefDescription": "Number of times a HLE transactional region aborted due to a non XRELEASE prefixed instruction writing to an elided lock in the elision buffer", "Counter": "0,1,2,3", - "UMask": "0x80", - "EventName": "HLE_RETIRED.ABORTED_EVENTS", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_HLE_STORE_TO_ELIDED_LOCK", + "PublicDescription": "Number of times a TSX Abort was triggered due to a non-release/commit store to lock.", "SampleAfterValue": "2000003", - "BriefDescription": "Number of times an HLE execution aborted due to unfriendly events (such as interrupts).", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x4" }, { - "PublicDescription": "Number of times we entered an RTM region. Does not count nested transactions.", - "EventCode": "0xC9", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "RTM_RETIRED.START", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of times an RTM execution started.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x103C400001", + "Offcore": "1", + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Number of times RTM commit succeeded.", - "EventCode": "0xC9", + "BriefDescription": "Number of times a transactional abort was signaled due to a data conflict on a transactionally accessed address", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "RTM_RETIRED.COMMIT", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_CONFLICT", + "PublicDescription": "Number of times a TSX line had a cache conflict.", "SampleAfterValue": "2000003", - "BriefDescription": "Number of times an RTM execution successfully committed", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PEBS": "1", - "PublicDescription": "Number of times RTM abort was triggered. (PEBS)", - "EventCode": "0xC9", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "RTM_RETIRED.ABORTED", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of times an RTM execution aborted due to any reasons (multiple categories may count as one).", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1004000001", + "Offcore": "1", + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts).", - "EventCode": "0xC9", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "RTM_RETIRED.ABORTED_MEM", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts)", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2000080001", + "Offcore": "1", + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0xC9", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "RTM_RETIRED.ABORTED_TIMER", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of times an RTM execution aborted due to uncommon conditions.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", + "MSRIndex": "0x3F6", + "MSRValue": "0x40", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "2003", + "TakenAlone": "1", + "UMask": "0x1" }, { - "PublicDescription": "Number of times an RTM execution aborted due to HLE-unfriendly instructions.", - "EventCode": "0xC9", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x20", - "EventName": "RTM_RETIRED.ABORTED_UNFRIENDLY", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of times an RTM execution aborted due to HLE-unfriendly instructions", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0204000001", + "Offcore": "1", + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Number of times an RTM execution aborted due to incompatible memory type.", - "EventCode": "0xC9", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x40", - "EventName": "RTM_RETIRED.ABORTED_MEMTYPE", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of times an RTM execution aborted due to incompatible memory type", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2000020002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt).", - "EventCode": "0xC9", + "BriefDescription": "Number of times an HLE transactional execution aborted due to NoAllocatedElisionBuffer being non-zero.", "Counter": "0,1,2,3", - "UMask": "0x80", - "EventName": "RTM_RETIRED.ABORTED_EVENTS", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_NOT_EMPTY", + "PublicDescription": "Number of times a TSX Abort was triggered due to commit but Lock Buffer not empty.", "SampleAfterValue": "2000003", - "BriefDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt)", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x8" }, { - "PEBS": "2", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.", - "EventCode": "0xCD", - "MSRValue": "0x4", + "BriefDescription": "Counts the number of times an HLE XACQUIRE instruction was executed inside an RTM transactional region", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", - "MSRIndex": "0x3F6", - "SampleAfterValue": "100003", - "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.", - "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x5d", + "EventName": "TX_EXEC.MISC5", + "PublicDescription": "Counts the number of times an HLE XACQUIRE instruction was executed inside an RTM transactional region.", + "SampleAfterValue": "2000003", + "UMask": "0x10" }, { - "PEBS": "2", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.", - "EventCode": "0xCD", - "MSRValue": "0x8", + "BriefDescription": "Counts the number of times a XBEGIN instruction was executed inside an HLE transactional region.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", - "MSRIndex": "0x3F6", - "SampleAfterValue": "50021", - "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.", - "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x5d", + "EventName": "TX_EXEC.MISC4", + "PublicDescription": "RTM region detected inside HLE.", + "SampleAfterValue": "2000003", + "UMask": "0x8" }, { - "PEBS": "2", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.", - "EventCode": "0xCD", - "MSRValue": "0x10", + "BriefDescription": "Counts the number of times an instruction execution caused the transactional nest count supported to be exceeded", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", - "MSRIndex": "0x3F6", - "SampleAfterValue": "20011", - "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.", - "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x5d", + "EventName": "TX_EXEC.MISC3", + "PublicDescription": "Unfriendly TSX abort triggered by a nest count that is too deep.", + "SampleAfterValue": "2000003", + "UMask": "0x4" }, { - "PEBS": "2", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.", - "EventCode": "0xCD", - "MSRValue": "0x20", + "BriefDescription": "Counts the number of times a class of instructions (e.g., vzeroupper) that may cause a transactional abort was executed inside a transactional region", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", - "MSRIndex": "0x3F6", - "SampleAfterValue": "100007", - "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.", - "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x5d", + "EventName": "TX_EXEC.MISC2", + "PublicDescription": "Unfriendly TSX abort triggered by a vzeroupper instruction.", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "PEBS": "2", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.", - "EventCode": "0xCD", - "MSRValue": "0x40", + "BriefDescription": "Counts the number of times a class of instructions that may cause a transactional abort was executed. Since this is the count of execution, it may not always cause a transactional abort.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", - "MSRIndex": "0x3F6", - "SampleAfterValue": "2003", - "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.", - "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x5d", + "EventName": "TX_EXEC.MISC1", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "PEBS": "2", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.", - "EventCode": "0xCD", - "MSRValue": "0x80", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", - "MSRIndex": "0x3F6", - "SampleAfterValue": "1009", - "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.", - "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0404000001", + "Offcore": "1", + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PEBS": "2", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.", - "EventCode": "0xCD", - "MSRValue": "0x100", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", - "MSRIndex": "0x3F6", - "SampleAfterValue": "503", - "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.", - "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0084000004", + "Offcore": "1", + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PEBS": "2", - "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.", - "EventCode": "0xCD", - "MSRValue": "0x200", + "BriefDescription": "Number of times an RTM execution successfully committed", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", - "MSRIndex": "0x3F6", - "SampleAfterValue": "101", - "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.", - "TakenAlone": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC9", + "EventName": "RTM_RETIRED.COMMIT", + "PublicDescription": "Number of times RTM commit succeeded.", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FFC408000", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2000100001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x203C408000", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x103C400004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x103C408000", + "BriefDescription": "Counts number of Offcore outstanding Demand Data Read requests that miss L3 cache in the superQ every cycle.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD", + "SampleAfterValue": "2000003", + "UMask": "0x10" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x043C408000", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", "BriefDescription": "Counts any other requests", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2000048000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" - }, - { "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x023C408000", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x013C408000", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0104000002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00BC408000", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x203C400004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x007C408000", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x007C408000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" - }, - { "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC4008000", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2004008000", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0104000004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1004008000", + "BriefDescription": "Number of times an RTM execution aborted due to uncommon conditions.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC9", + "EventName": "RTM_RETIRED.ABORTED_TIMER", + "SampleAfterValue": "2000003", + "UMask": "0x10" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0404008000", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2004000004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0204008000", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1004000004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0104008000", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", "BriefDescription": "Counts any other requests", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0044008000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" - }, - { "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0084008000", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0044008000", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0044000001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000408000", + "BriefDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC8", + "EventName": "HLE_RETIRED.ABORTED_UNFRIENDLY", + "SampleAfterValue": "2000003", + "UMask": "0x20" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x20001C8000", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0084000002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000108000", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x043C400004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000088000", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x00BC400002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000048000", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", "BriefDescription": "Counts any other requests", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2000408000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" - }, - { "PublicDescription": "Counts any other requests", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000028000", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts any other requests", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FFC400004", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2000040004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x203C400004", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2000400004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x103C400004", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2000400002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x043C400004", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x20001C0004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x023C400004", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x103C400002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x013C400004", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x013C400004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00BC400004", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0404008000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x007C400004", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0104008000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC4000004", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2000400001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2004000004", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x013C408000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1004000004", + "BriefDescription": "Number of times an HLE execution successfully committed", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC8", + "EventName": "HLE_RETIRED.COMMIT", + "PublicDescription": "Number of times HLE commit succeeded.", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0404000004", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2000020001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0204000004", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x203C408000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0104000004", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x023C400002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0084000004", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2000040002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0044000004", + "BriefDescription": "Demand Data Read requests who miss L3 cache", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB0", + "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", + "PublicDescription": "Demand Data Read requests who miss L3 cache.", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x10" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000400004", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x00BC400001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x20001C0004", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2004000002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000100004", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x023C400004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000080004", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FFC400001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000040004", + "BriefDescription": "Number of times an RTM execution aborted due to HLE-unfriendly instructions", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC9", + "EventName": "RTM_RETIRED.ABORTED_UNFRIENDLY", + "PublicDescription": "Number of times an RTM execution aborted due to HLE-unfriendly instructions.", + "SampleAfterValue": "2000003", + "UMask": "0x20" }, { - "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000020004", + "BriefDescription": "Number of times an HLE execution aborted due to various memory events (e.g., read/write capacity and conflicts).", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC8", + "EventName": "HLE_RETIRED.ABORTED_MEM", + "SampleAfterValue": "2000003", + "UMask": "0x8" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FFC400002", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", + "MSRIndex": "0x3F6", + "MSRValue": "0x100", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "503", + "TakenAlone": "1", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x203C400002", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x013C400001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x103C400002", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x203C400001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x043C400002", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", "BriefDescription": "Counts all demand data writes (RFOs)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x007C400002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x023C400002", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC4008000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x013C400002", + "BriefDescription": "Number of times an RTM execution aborted due to any reasons (multiple categories may count as one).", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC9", + "EventName": "RTM_RETIRED.ABORTED", + "PEBS": "1", + "PublicDescription": "Number of times RTM abort was triggered.", + "SampleAfterValue": "2000003", + "UMask": "0x4" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00BC400002", + "BriefDescription": "Number of times an HLE execution aborted due to any reasons (multiple categories may count as one).", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC8", + "EventName": "HLE_RETIRED.ABORTED", + "PEBS": "1", + "PublicDescription": "Number of times HLE abort was triggered.", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { "BriefDescription": "Counts all demand data writes (RFOs)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x203C400002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x007C400002", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0404000004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC4000002", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", + "MSRIndex": "0x3F6", + "MSRValue": "0x10", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "20011", + "TakenAlone": "1", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2004000002", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2004008000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1004000002", + "BriefDescription": "Number of times an HLE transactional execution aborted due to an unsupported read alignment from the elision buffer.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_UNSUPPORTED_ALIGNMENT", + "PublicDescription": "Number of times a TSX Abort was triggered due to attempting an unsupported alignment from Lock Buffer.", + "SampleAfterValue": "2000003", + "UMask": "0x20" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0404000002", + "BriefDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD", + "SampleAfterValue": "2000003", + "UMask": "0x10" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0204000002", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC4000004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0104000002", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", + "MSRIndex": "0x3F6", + "MSRValue": "0x200", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "101", + "TakenAlone": "1", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0084000002", + "BriefDescription": "Number of times a transactional abort was signaled due to a data capacity limitation for transactional reads or writes.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_CAPACITY", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0044000002", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0084000001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000400002", + "BriefDescription": "Number of times an HLE execution aborted due to incompatible memory type", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC8", + "EventName": "HLE_RETIRED.ABORTED_MEMTYPE", + "PublicDescription": "Number of times an HLE execution aborted due to incompatible memory type.", + "SampleAfterValue": "2000003", + "UMask": "0x40" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x20001C0002", + "BriefDescription": "Number of times an RTM execution started.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC9", + "EventName": "RTM_RETIRED.START", + "PublicDescription": "Number of times we entered an RTM region. Does not count nested transactions.", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000100002", + "BriefDescription": "Counts the number of machine clears due to memory order conflicts.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL089", + "EventCode": "0xC3", + "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", + "PublicDescription": "Counts the number of memory ordering Machine Clears detected. Memory Ordering Machine Clears can result from one of the following:a. memory disambiguation,b. external snoop, orc. cross SMT-HW-thread snoop (stores) hitting load buffer.", "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x2" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000080002", + "BriefDescription": "Number of times an HLE transactional execution aborted due to XRELEASE lock not satisfying the address and value requirements in the elision buffer", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_MISMATCH", + "PublicDescription": "Number of times a TSX Abort was triggered due to release/commit but data and address mismatch.", + "SampleAfterValue": "2000003", + "UMask": "0x10" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000040002", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x20001C0002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts all demand data writes (RFOs)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1004000002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all demand data writes (RFOs)", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000020002", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts all demand data writes (RFOs)", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x20001C0001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FFC400001", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC4000002", + "Offcore": "1", + "PublicDescription": "Counts all demand data writes (RFOs)", "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand data reads", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x007C400001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x203C400001", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2000100004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x103C400001", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NONE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x00BC400004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x043C400001", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x043C400001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" - }, - { "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x023C400001", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x013C400001", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FFC400002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x00BC400001", + "BriefDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC9", + "EventName": "RTM_RETIRED.ABORTED_EVENTS", + "PublicDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt).", + "SampleAfterValue": "2000003", + "UMask": "0x80" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x007C400001", + "BriefDescription": "Number of times an HLE execution started.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC8", + "EventName": "HLE_RETIRED.START", + "PublicDescription": "Number of times we entered an HLE region. Does not count nested transactions.", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x3FC4000001", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FFC400004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2004000001", + "BriefDescription": "Counts demand data reads", "Counter": "0,1,2,3", - "UMask": "0x1", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2004000001", + "Offcore": "1", + "PublicDescription": "Counts demand data reads", "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand data reads", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FC4000001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x1004000001", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", + "MSRIndex": "0x3F6", + "MSRValue": "0x80", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "1009", + "TakenAlone": "1", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0404000001", + "BriefDescription": "Number of times HLE lock could not be elided due to ElisionBufferAvailable being zero.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x54", + "EventName": "TX_MEM.HLE_ELISION_BUFFER_FULL", + "PublicDescription": "Number of times we could not allocate Lock Buffer.", + "SampleAfterValue": "2000003", + "UMask": "0x40" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0204000001", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2000108000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0104000001", + "BriefDescription": "Counts all demand code reads", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SPL_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0044000004", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand code reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0084000001", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NOT_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x013C400002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x0044000001", + "BriefDescription": "Execution stalls while L3 cache miss demand load is outstanding.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SPL_HIT", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "6", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS", + "SampleAfterValue": "2000003", + "UMask": "0x6" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000400001", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x023C408000", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts any other requests", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x20001C0001", + "BriefDescription": "Number of times an HLE execution aborted due to unfriendly events (such as interrupts).", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC8", + "EventName": "HLE_RETIRED.ABORTED_EVENTS", + "SampleAfterValue": "2000003", + "UMask": "0x80" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000100001", + "BriefDescription": "Counts any other requests", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x20001C8000", + "Offcore": "1", + "PublicDescription": "Counts any other requests", "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { "BriefDescription": "Counts demand data reads", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_NON_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x2000040001", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts demand data reads", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000080001", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", + "MSRIndex": "0x3F6", + "MSRValue": "0x4", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "TakenAlone": "1", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000040001", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", - "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", + "MSRIndex": "0x3F6", + "MSRValue": "0x8", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "50021", + "TakenAlone": "1", + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data reads", - "EventCode": "0xB7, 0xBB", - "MSRValue": "0x2000020001", + "BriefDescription": "Counts all demand data writes (RFOs)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NON_DRAM", - "MSRIndex": "0x1a6, 0x1a7", - "SampleAfterValue": "100003", - "BriefDescription": "Counts demand data reads", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0404000002", "Offcore": "1", - "CounterHTOff": "0,1,2,3" + "PublicDescription": "Counts all demand data writes (RFOs)", + "SampleAfterValue": "100003", + "UMask": "0x1" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/skylake/other.json b/tools/perf/pmu-events/arch/x86/skylake/other.json index 84a316d380ac..1a3683f1de91 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/other.json +++ b/tools/perf/pmu-events/arch/x86/skylake/other.json @@ -1,48 +1,56 @@ [ { - "EventCode": "0x32", + "BriefDescription": "Number of PREFETCHW instructions executed.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "SW_PREFETCH_ACCESS.NTA", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x32", + "EventName": "SW_PREFETCH_ACCESS.PREFETCHW", "SampleAfterValue": "2000003", - "BriefDescription": "Number of PREFETCHNTA instructions executed.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x8" }, { - "EventCode": "0x32", + "BriefDescription": "Number of PREFETCHT0 instructions executed.", "Counter": "0,1,2,3", - "UMask": "0x2", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x32", "EventName": "SW_PREFETCH_ACCESS.T0", "SampleAfterValue": "2000003", - "BriefDescription": "Number of PREFETCHT0 instructions executed.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" }, { - "EventCode": "0x32", + "BriefDescription": "Number of hardware interrupts received by the processor.", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "SW_PREFETCH_ACCESS.T1_T2", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of PREFETCHT1 or PREFETCHT2 instructions executed.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xCB", + "EventName": "HW_INTERRUPTS.RECEIVED", + "PublicDescription": "Counts the number of hardware interruptions received by the processor.", + "SampleAfterValue": "203", + "UMask": "0x1" }, { + "BriefDescription": "Number of PREFETCHNTA instructions executed.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", "EventCode": "0x32", + "EventName": "SW_PREFETCH_ACCESS.NTA", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of PREFETCHT1 or PREFETCHT2 instructions executed.", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "SW_PREFETCH_ACCESS.PREFETCHW", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x32", + "EventName": "SW_PREFETCH_ACCESS.T1_T2", "SampleAfterValue": "2000003", - "BriefDescription": "Number of PREFETCHW instructions executed.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x4" }, { - "PublicDescription": "Counts the number of hardware interruptions received by the processor.", - "EventCode": "0xCB", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "HW_INTERRUPTS.RECEIVED", - "SampleAfterValue": "203", - "BriefDescription": "Number of hardware interrupts received by the processor.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x09", + "EventName": "MEMORY_DISAMBIGUATION.HISTORY_RESET", + "SampleAfterValue": "2000003", + "UMask": "0x1" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/skylake/pipeline.json b/tools/perf/pmu-events/arch/x86/skylake/pipeline.json index 4a891fbbc4bb..f46e93a57fb4 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/skylake/pipeline.json @@ -1,967 +1,969 @@ [ { - "PublicDescription": "Counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, Counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. INST_RETIRED.ANY_P is counted by a programmable counter and it is an architectural performance event. Counting: Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.", - "Counter": "Fixed counter 0", - "UMask": "0x1", - "EventName": "INST_RETIRED.ANY", - "SampleAfterValue": "2000003", - "BriefDescription": "Instructions retired from execution.", - "CounterHTOff": "Fixed counter 0" - }, - { - "PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.", - "Counter": "Fixed counter 1", - "UMask": "0x2", - "EventName": "CPU_CLK_UNHALTED.THREAD", - "SampleAfterValue": "2000003", - "BriefDescription": "Core cycles when the thread is not in halt state", - "CounterHTOff": "Fixed counter 1" + "BriefDescription": "Number of instructions retired. General Counter - architectural event", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL091, SKL044", + "EventCode": "0xC0", + "EventName": "INST_RETIRED.ANY_P", + "PublicDescription": "Counts the number of instructions (EOMs) retired. Counting covers macro-fused instructions individually (that is, increments by two).", + "SampleAfterValue": "2000003" }, { - "Counter": "Fixed counter 1", - "UMask": "0x2", - "AnyThread": "1", - "EventName": "CPU_CLK_UNHALTED.THREAD_ANY", + "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.STALL_CYCLES", + "Invert": "1", + "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.", "SampleAfterValue": "2000003", - "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", - "CounterHTOff": "Fixed counter 1" + "UMask": "0x1" }, { - "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", - "Counter": "Fixed counter 2", - "UMask": "0x3", - "EventName": "CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station was not empty.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA6", + "EventName": "EXE_ACTIVITY.4_PORTS_UTIL", + "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty.", "SampleAfterValue": "2000003", - "BriefDescription": "Reference cycles when the core is not in halt state.", - "CounterHTOff": "Fixed counter 2" + "UMask": "0x10" }, { - "PublicDescription": "Counts how many times the load operation got the true Block-on-Store blocking code preventing store forwarding. This includes cases when:a. preceding store conflicts with the load (incomplete overlap),b. store forwarding is impossible due to u-arch limitations,c. preceding lock RMW operations are not forwarded,d. store has the no-forward bit set (uncacheable/page-split/masked stores),e. all-blocking stores are used (mostly, fences and port I/O), and others.The most common case is a load blocked due to its address range overlapping with a preceding smaller uncompleted store. Note: This event does not take into account cases of out-of-SW-control (for example, SbTailHit), unknown physical STA, and cases of blocking loads on store due to being non-WB memory type or a lock. These cases are covered by other events. See the table of not supported store forwards in the Optimization Guide.", - "EventCode": "0x03", + "BriefDescription": "Cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "LD_BLOCKS.STORE_FORWARD", - "SampleAfterValue": "100003", - "BriefDescription": "Loads blocked by overlapping with store buffer that cannot be forwarded .", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x14", + "EventName": "ARITH.DIVIDER_ACTIVE", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "PublicDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.", - "EventCode": "0x03", + "BriefDescription": "False dependencies in MOB due to partial compare on address.", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "LD_BLOCKS.NO_SR", - "SampleAfterValue": "100003", - "BriefDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "PublicDescription": "Counts false dependencies in MOB when the partial comparison upon loose net check and dependency was resolved by the Enhanced Loose net mechanism. This may not result in high performance penalties. Loose net checks can fail when loads and stores are 4k aliased.", + "CounterHTOff": "0,1,2,3,4,5,6,7", "EventCode": "0x07", - "Counter": "0,1,2,3", - "UMask": "0x1", "EventName": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS", + "PublicDescription": "Counts false dependencies in MOB when the partial comparison upon loose net check and dependency was resolved by the Enhanced Loose net mechanism. This may not result in high performance penalties. Loose net checks can fail when loads and stores are 4k aliased.", "SampleAfterValue": "100003", - "BriefDescription": "False dependencies in MOB due to partial compare on address.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Core cycles the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.", - "EventCode": "0x0D", + "BriefDescription": "Far branch instructions retired.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "INT_MISC.RECOVERY_CYCLES", - "SampleAfterValue": "2000003", - "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for this thread (e.g. misprediction or memory nuke)", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL091", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.FAR_BRANCH", + "PEBS": "1", + "PublicDescription": "This event counts far branch instructions retired.", + "SampleAfterValue": "100007", + "UMask": "0x40" }, { - "EventCode": "0x0D", + "BriefDescription": "Counts the number of x87 uops dispatched.", "Counter": "0,1,2,3", - "UMask": "0x1", - "AnyThread": "1", - "EventName": "INT_MISC.RECOVERY_CYCLES_ANY", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.X87", + "PublicDescription": "Counts the number of x87 uops executed.", "SampleAfterValue": "2000003", - "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x10" }, { - "EventCode": "0x0D", + "BriefDescription": "Demand load dispatches that hit L1D fill buffer (FB) allocated for software prefetch.", "Counter": "0,1,2,3", - "UMask": "0x80", - "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles the issue-stage is waiting for front-end to fetch from resteered path following branch misprediction or machine clear events.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x4C", + "EventName": "LOAD_HIT_PRE.SW_PF", + "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).", - "EventCode": "0x0E", + "BriefDescription": "Mispredicted direct and indirect near call instructions retired.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "UOPS_ISSUED.ANY", - "SampleAfterValue": "2000003", - "BriefDescription": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS)", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC5", + "EventName": "BR_MISP_RETIRED.NEAR_CALL", + "PEBS": "1", + "PublicDescription": "Counts both taken and not taken retired mispredicted direct and indirect near calls, including both register and memory indirect.", + "SampleAfterValue": "400009", + "UMask": "0x2" }, { - "PublicDescription": "Counts cycles during which the Resource Allocation Table (RAT) does not issue any Uops to the reservation station (RS) for the current thread.", - "EventCode": "0x0E", - "Invert": "1", + "BriefDescription": "Total execution stalls.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "UOPS_ISSUED.STALL_CYCLES", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "4", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x4" }, { - "PublicDescription": "Counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting with the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register. For more information, refer to \u201cMixing Intel AVX and Intel SSE Code\u201d section of the Optimization Guide.", - "EventCode": "0x0E", + "BriefDescription": "Number of slow LEA uops being allocated. A uop is generally considered SlowLea if it has 3 sources (e.g. 2 sources + immediate) regardless if as a result of LEA instruction or not.", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH", - "SampleAfterValue": "2000003", - "BriefDescription": "Uops inserted at issue-stage in order to preserve upper bits of vector registers.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { + "CounterHTOff": "0,1,2,3,4,5,6,7", "EventCode": "0x0E", - "Counter": "0,1,2,3", - "UMask": "0x20", "EventName": "UOPS_ISSUED.SLOW_LEA", "SampleAfterValue": "2000003", - "BriefDescription": "Number of slow LEA uops being allocated. A uop is generally considered SlowLea if it has 3 sources (e.g. 2 sources + immediate) regardless if as a result of LEA instruction or not.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x20" }, { - "EventCode": "0x14", + "BriefDescription": "Cycles with less than 10 actually retired uops.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "ARITH.DIVIDER_ACTIVE", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "10", + "EventCode": "0xC2", + "EventName": "UOPS_RETIRED.TOTAL_CYCLES", + "Invert": "1", + "PublicDescription": "Number of cycles using always true condition (uops_ret < 16) applied to non PEBS uops retired event.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" }, { - "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.", - "EventCode": "0x3C", + "BriefDescription": "Thread cycles when thread is not in halt state", "Counter": "0,1,2,3", - "UMask": "0x0", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x3C", "EventName": "CPU_CLK_UNHALTED.THREAD_P", - "SampleAfterValue": "2000003", - "BriefDescription": "Thread cycles when thread is not in halt state", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.", + "SampleAfterValue": "2000003" }, { - "EventCode": "0x3C", + "BriefDescription": "Cycles where at least 2 uops were executed per-thread", "Counter": "0,1,2,3", - "UMask": "0x0", - "AnyThread": "1", - "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "2", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC", + "PublicDescription": "Cycles where at least 2 uops were executed per-thread.", "SampleAfterValue": "2000003", - "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts when the Current Privilege Level (CPL) transitions from ring 1, 2 or 3 to ring 0 (Kernel).", - "EventCode": "0x3C", + "BriefDescription": "Core crystal clock cycles when the thread is unhalted.", "Counter": "0,1,2,3", - "UMask": "0x0", - "EdgeDetect": "1", - "EventName": "CPU_CLK_UNHALTED.RING0_TRANS", - "SampleAfterValue": "100007", - "BriefDescription": "Counts when there is a transition from ring 1, 2 or 3 to ring 0.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { + "CounterHTOff": "0,1,2,3,4,5,6,7", "EventCode": "0x3C", - "Counter": "0,1,2,3", - "UMask": "0x1", "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK", - "SampleAfterValue": "2503", - "BriefDescription": "Core crystal clock cycles when the thread is unhalted.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "SampleAfterValue": "25003", + "UMask": "0x1" }, { - "EventCode": "0x3C", + "BriefDescription": "Number of machine clears (nukes) of any type.", "Counter": "0,1,2,3", - "UMask": "0x1", - "AnyThread": "1", - "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY", - "SampleAfterValue": "2503", - "BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0xC3", + "EventName": "MACHINE_CLEARS.COUNT", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "EventCode": "0x3C", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "CPU_CLK_UNHALTED.REF_XCLK", - "SampleAfterValue": "2503", - "BriefDescription": "Core crystal clock cycles when the thread is unhalted.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "AnyThread": "1", + "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", + "Counter": "Fixed counter 1", + "CounterHTOff": "Fixed counter 1", + "EventName": "CPU_CLK_UNHALTED.THREAD_ANY", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "EventCode": "0x3C", + "BriefDescription": "Counts the number of uops to be executed per-thread each cycle.", "Counter": "0,1,2,3", - "UMask": "0x1", - "AnyThread": "1", - "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY", - "SampleAfterValue": "2503", - "BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.THREAD", + "PublicDescription": "Number of uops to be executed per-thread each cycle.", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "EventCode": "0x3C", + "BriefDescription": "Cycles where at least 3 uops were executed per-thread", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "3", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC", + "PublicDescription": "Cycles where at least 3 uops were executed per-thread.", "SampleAfterValue": "2000003", - "BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0x3C", + "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE", - "SampleAfterValue": "2503", - "BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE", + "Invert": "1", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions.", - "EventCode": "0x4C", + "BriefDescription": "Cycles where the Store Buffer was full and no outstanding load.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "LOAD_HIT_PRE.SW_PF", - "SampleAfterValue": "100003", - "BriefDescription": "Demand load dispatches that hit L1D fill buffer (FB) allocated for software prefetch.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA6", + "EventName": "EXE_ACTIVITY.BOUND_ON_STORES", + "SampleAfterValue": "2000003", + "UMask": "0x40" }, { - "PublicDescription": "This event counts cycles during which the microcode scoreboard stalls happen.", - "EventCode": "0x59", + "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "PARTIAL_RAT_STALLS.SCOREBOARD", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "8", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles where the pipeline is stalled due to serializing operations.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x8" }, { - "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for the thread.; Note: In ST-mode, not active thread should drive 0. This is usually caused by severely costly branch mispredictions, or allocator/FE issues.", - "EventCode": "0x5E", + "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "RS_EVENTS.EMPTY_CYCLES", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xA8", + "EventName": "LSD.CYCLES_ACTIVE", + "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate front-end Latency Bound issues.", - "EventCode": "0x5E", - "Invert": "1", + "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for this thread (e.g. misprediction or memory nuke)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EdgeDetect": "1", - "EventName": "RS_EVENTS.EMPTY_END", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x0D", + "EventName": "INT_MISC.RECOVERY_CYCLES", + "PublicDescription": "Core cycles the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.", "SampleAfterValue": "2000003", - "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.", - "EventCode": "0x87", + "BriefDescription": "Core crystal clock cycles when the thread is unhalted.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "ILD_STALL.LCP", - "SampleAfterValue": "2000003", - "BriefDescription": "Stalls caused by changing prefix length of the instruction.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x3C", + "EventName": "CPU_CLK_UNHALTED.REF_XCLK", + "SampleAfterValue": "25003", + "UMask": "0x1" }, { - "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 0.", - "EventCode": "0xA1", + "BriefDescription": "Cycles per thread when uops are executed in port 0", "Counter": "0,1,2,3", - "UMask": "0x1", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", "EventName": "UOPS_DISPATCHED_PORT.PORT_0", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 0.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when uops are executed in port 0", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 1.", - "EventCode": "0xA1", + "BriefDescription": "Cycles per thread when uops are executed in port 1", "Counter": "0,1,2,3", - "UMask": "0x2", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", "EventName": "UOPS_DISPATCHED_PORT.PORT_1", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 1.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when uops are executed in port 1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" }, { - "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 2.", - "EventCode": "0xA1", + "BriefDescription": "Cycles per thread when uops are executed in port 2", "Counter": "0,1,2,3", - "UMask": "0x4", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", "EventName": "UOPS_DISPATCHED_PORT.PORT_2", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 2.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when uops are executed in port 2", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x4" }, { - "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 3.", - "EventCode": "0xA1", + "BriefDescription": "Cycles per thread when uops are executed in port 3", "Counter": "0,1,2,3", - "UMask": "0x8", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", "EventName": "UOPS_DISPATCHED_PORT.PORT_3", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 3.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when uops are executed in port 3", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x8" }, { - "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 4.", - "EventCode": "0xA1", + "BriefDescription": "Cycles per thread when uops are executed in port 4", "Counter": "0,1,2,3", - "UMask": "0x10", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", "EventName": "UOPS_DISPATCHED_PORT.PORT_4", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 4.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when uops are executed in port 4", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x10" }, { - "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 5.", - "EventCode": "0xA1", + "BriefDescription": "Cycles per thread when uops are executed in port 5", "Counter": "0,1,2,3", - "UMask": "0x20", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", "EventName": "UOPS_DISPATCHED_PORT.PORT_5", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 5.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when uops are executed in port 5", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x20" }, { - "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 6.", - "EventCode": "0xA1", + "BriefDescription": "Cycles per thread when uops are executed in port 6", "Counter": "0,1,2,3", - "UMask": "0x40", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", "EventName": "UOPS_DISPATCHED_PORT.PORT_6", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 6.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when uops are executed in port 6", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x40" }, { - "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 7.", - "EventCode": "0xA1", + "BriefDescription": "Cycles per thread when uops are executed in port 7", "Counter": "0,1,2,3", - "UMask": "0x80", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA1", "EventName": "UOPS_DISPATCHED_PORT.PORT_7", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 7.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles per thread when uops are executed in port 7", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x80" }, { - "PublicDescription": "Counts resource-related stall cycles.", - "EventCode": "0xa2", + "AnyThread": "1", + "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "RESOURCE_STALLS.ANY", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x0D", + "EventName": "INT_MISC.RECOVERY_CYCLES_ANY", "SampleAfterValue": "2000003", - "BriefDescription": "Resource-related stall cycles", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.", - "EventCode": "0xA2", - "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "RESOURCE_STALLS.SB", + "BriefDescription": "Precise instruction retired event with HW to reduce effect of PEBS shadow in IP distribution", + "Counter": "1", + "CounterHTOff": "1", + "Errata": "SKL091, SKL044", + "EventCode": "0xC0", + "EventName": "INST_RETIRED.PREC_DIST", + "PEBS": "2", + "PublicDescription": "A version of INST_RETIRED that allows for a more unbiased distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR) feature to mitigate some bias in how retired instructions get sampled.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles stalled due to no store buffers available. (not including draining form sync).", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0xA3", + "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "4", + "EventCode": "0xA8", + "EventName": "LSD.CYCLES_4_UOPS", + "PublicDescription": "Counts the cycles when 4 uops are delivered by the LSD (Loop-stream detector).", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles while L2 cache miss demand load is outstanding.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0xA3", + "BriefDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station was not empty.", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA6", + "EventName": "EXE_ACTIVITY.3_PORTS_UTIL", + "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty.", "SampleAfterValue": "2000003", - "BriefDescription": "Total execution stalls.", - "CounterMask": "4", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x8" }, { - "EventCode": "0xA3", + "BriefDescription": "Loads blocked due to overlapping with a preceding store that cannot be forwarded.", "Counter": "0,1,2,3", - "UMask": "0x5", - "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS", - "SampleAfterValue": "2000003", - "BriefDescription": "Execution stalls while L2 cache miss demand load is outstanding.", - "CounterMask": "5", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.STORE_FORWARD", + "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide.", + "SampleAfterValue": "100003", + "UMask": "0x2" }, { - "EventCode": "0xA3", + "AnyThread": "1", + "BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.", - "CounterMask": "8", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x3C", + "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY", + "SampleAfterValue": "25003", + "UMask": "0x1" }, { - "EventCode": "0xA3", + "BriefDescription": "Cycles where the pipeline is stalled due to serializing operations.", "Counter": "0,1,2,3", - "UMask": "0xc", - "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x59", + "EventName": "PARTIAL_RAT_STALLS.SCOREBOARD", + "PublicDescription": "This event counts cycles during which the microcode scoreboard stalls happen.", "SampleAfterValue": "2000003", - "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.", - "CounterMask": "12", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0xA3", + "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x0E", + "EventName": "UOPS_ISSUED.STALL_CYCLES", + "Invert": "1", + "PublicDescription": "Counts cycles during which the Resource Allocation Table (RAT) does not issue any Uops to the reservation station (RS) for the current thread.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles while memory subsystem has an outstanding load.", - "CounterMask": "16", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0xA3", + "BriefDescription": "Not taken branch instructions retired.", "Counter": "0,1,2,3", - "UMask": "0x14", - "EventName": "CYCLE_ACTIVITY.STALLS_MEM_ANY", - "SampleAfterValue": "2000003", - "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.", - "CounterMask": "20", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL091", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.COND_NTAKEN", + "PublicDescription": "This event counts not taken branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x10" }, { - "PublicDescription": "Counts cycles during which no uops were executed on all ports and Reservation Station (RS) was not empty.", - "EventCode": "0xA6", + "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "3", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles where no uops were executed, the Reservation Station was not empty, the Store Buffer was full and there was no outstanding load.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" }, { - "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty.", - "EventCode": "0xA6", + "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "EXE_ACTIVITY.1_PORTS_UTIL", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles total of 1 uop is executed on all ports and Reservation Station was not empty.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" }, { - "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty.", - "EventCode": "0xA6", + "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "EXE_ACTIVITY.2_PORTS_UTIL", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "4", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles total of 2 uops are executed on all ports and Reservation Station was not empty.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" }, { - "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty.", - "EventCode": "0xA6", - "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "EXE_ACTIVITY.3_PORTS_UTIL", + "BriefDescription": "Reference cycles when the core is not in halt state.", + "Counter": "Fixed counter 2", + "CounterHTOff": "Fixed counter 2", + "EventName": "CPU_CLK_UNHALTED.REF_TSC", + "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station was not empty.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x3" }, { - "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty.", - "EventCode": "0xA6", + "BriefDescription": "All mispredicted macro branch instructions retired.", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "EXE_ACTIVITY.4_PORTS_UTIL", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station was not empty.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC5", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", + "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.", + "SampleAfterValue": "400009" }, { - "EventCode": "0xA6", + "BriefDescription": "Number of times a microcode assist is invoked by HW other than FP-assist. Examples include AD (page Access Dirty) and AVX* related assists.", "Counter": "0,1,2,3", - "UMask": "0x40", - "EventName": "EXE_ACTIVITY.BOUND_ON_STORES", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC1", + "EventName": "OTHER_ASSISTS.ANY", + "SampleAfterValue": "100003", + "UMask": "0x3f" + }, + { + "BriefDescription": "Cycles without actually retired uops.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xC2", + "EventName": "UOPS_RETIRED.STALL_CYCLES", + "Invert": "1", + "PublicDescription": "This event counts cycles without actually retired uops.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles where the Store Buffer was full and no outstanding load.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" }, { - "PublicDescription": "Number of uops delivered to the back-end by the LSD(Loop Stream Detector).", - "EventCode": "0xA8", + "BriefDescription": "Number of Uops delivered by the LSD.", "Counter": "0,1,2,3", - "UMask": "0x1", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA8", "EventName": "LSD.UOPS", + "PublicDescription": "Number of uops delivered to the back-end by the LSD(Loop Stream Detector).", "SampleAfterValue": "2000003", - "BriefDescription": "Number of Uops delivered by the LSD.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).", - "EventCode": "0xA8", + "BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "LSD.CYCLES_ACTIVE", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x3C", + "EventName": "CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE", + "SampleAfterValue": "25003", + "UMask": "0x2" }, { - "PublicDescription": "Counts the cycles when 4 uops are delivered by the LSD (Loop-stream detector).", - "EventCode": "0xA8", + "BriefDescription": "Stalls caused by changing prefix length of the instruction.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "LSD.CYCLES_4_UOPS", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x87", + "EventName": "ILD_STALL.LCP", + "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.", - "CounterMask": "4", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Number of uops to be executed per-thread each cycle.", - "EventCode": "0xB1", + "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "UOPS_EXECUTED.THREAD", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0x5E", + "EventName": "RS_EVENTS.EMPTY_END", + "Invert": "1", + "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate front-end Latency Bound issues.", "SampleAfterValue": "2000003", - "BriefDescription": "Counts the number of uops to be executed per-thread each cycle.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.", - "EventCode": "0xB1", - "Invert": "1", + "BriefDescription": "Cycles while memory subsystem has an outstanding load.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "UOPS_EXECUTED.STALL_CYCLES", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "16", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY", "SampleAfterValue": "2000003", - "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x10" }, { - "PublicDescription": "Cycles where at least 1 uop was executed per-thread.", - "EventCode": "0xB1", + "BriefDescription": "Taken branch instructions retired.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles where at least 1 uop was executed per-thread", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL091", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.NEAR_TAKEN", + "PEBS": "1", + "PublicDescription": "This event counts taken branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x20" }, { - "PublicDescription": "Cycles where at least 2 uops were executed per-thread.", - "EventCode": "0xB1", + "BriefDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles where at least 2 uops were executed per-thread", - "CounterMask": "2", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.NO_SR", + "PublicDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.", + "SampleAfterValue": "100003", + "UMask": "0x8" }, { - "PublicDescription": "Cycles where at least 3 uops were executed per-thread.", - "EventCode": "0xB1", + "BriefDescription": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x0E", + "EventName": "UOPS_ISSUED.ANY", + "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles where at least 3 uops were executed per-thread", - "CounterMask": "3", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Cycles where at least 4 uops were executed per-thread.", - "EventCode": "0xB1", - "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC", + "BriefDescription": "Core cycles when the thread is not in halt state", + "Counter": "Fixed counter 1", + "CounterHTOff": "Fixed counter 1", + "EventName": "CPU_CLK_UNHALTED.THREAD", + "PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles where at least 4 uops were executed per-thread", - "CounterMask": "4", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" }, { - "PublicDescription": "Number of uops executed from any thread.", - "EventCode": "0xB1", + "AnyThread": "1", + "BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "UOPS_EXECUTED.CORE", - "SampleAfterValue": "2000003", - "BriefDescription": "Number of uops executed on the core.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x3C", + "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY", + "SampleAfterValue": "25003", + "UMask": "0x1" }, { - "EventCode": "0xB1", + "BriefDescription": "Direct and indirect near call instructions retired.", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL091", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.NEAR_CALL", + "PEBS": "1", + "PublicDescription": "This event counts both direct and indirect near call instructions retired.", + "SampleAfterValue": "100007", + "UMask": "0x2" }, { - "EventCode": "0xB1", + "BriefDescription": "Number of retired PAUSE instructions (that do not end up with a VMExit to the VMM; TSX aborted Instructions may be counted). This event is not supported on first SKL and KBL products.", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xCC", + "EventName": "ROB_MISC_EVENTS.PAUSE_INST", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.", - "CounterMask": "2", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x40" }, { - "EventCode": "0xB1", + "BriefDescription": "Resource-related stall cycles", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xa2", + "EventName": "RESOURCE_STALLS.ANY", + "PublicDescription": "Counts resource-related stall cycles.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.", - "CounterMask": "3", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "EventCode": "0xB1", + "BriefDescription": "Self-modifying code (SMC) detected.", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4", - "SampleAfterValue": "2000003", - "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.", - "CounterMask": "4", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC3", + "EventName": "MACHINE_CLEARS.SMC", + "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.", + "SampleAfterValue": "100003", + "UMask": "0x4" }, { - "EventCode": "0xB1", - "Invert": "1", + "BriefDescription": "Execution stalls while L2 cache miss demand load is outstanding.", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "5", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x5" }, { - "PublicDescription": "Counts the number of x87 uops executed.", - "EventCode": "0xB1", + "BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted.", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "UOPS_EXECUTED.X87", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x3C", + "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE", + "SampleAfterValue": "25003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles where at least 4 uops were executed per-thread", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "4", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC", + "PublicDescription": "Cycles where at least 4 uops were executed per-thread.", "SampleAfterValue": "2000003", - "BriefDescription": "Counts the number of x87 uops dispatched.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts the number of instructions (EOMs) retired. Counting covers macro-fused instructions individually (that is, increments by two).", - "EventCode": "0xC0", + "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken.", "Counter": "0,1,2,3", - "UMask": "0x0", - "Errata": "SKL091, SKL044", - "EventName": "INST_RETIRED.ANY_P", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC5", + "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", + "PEBS": "1", + "SampleAfterValue": "400009", + "UMask": "0x20" + }, + { + "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "CounterMask": "20", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.STALLS_MEM_ANY", "SampleAfterValue": "2000003", - "BriefDescription": "Number of instructions retired. General Counter - architectural event", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x14" }, { - "PEBS": "2", - "PublicDescription": "A version of INST_RETIRED that allows for a more unbiased distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR) feature to mitigate some bias in how retired instructions get sampled.", - "EventCode": "0xC0", - "Counter": "1", - "UMask": "0x1", - "Errata": "SKL091, SKL044", - "EventName": "INST_RETIRED.PREC_DIST", + "BriefDescription": "Cycles where no uops were executed, the Reservation Station was not empty, the Store Buffer was full and there was no outstanding load.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA6", + "EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS", + "PublicDescription": "Counts cycles during which no uops were executed on all ports and Reservation Station (RS) was not empty.", "SampleAfterValue": "2000003", - "BriefDescription": "Precise instruction retired event with HW to reduce effect of PEBS shadow in IP distribution", - "CounterHTOff": "1" + "UMask": "0x1" }, { - "PEBS": "2", - "PublicDescription": "Number of cycles using an always true condition applied to PEBS instructions retired event. (inst_ret< 16)", - "EventCode": "0xC0", - "Invert": "1", + "BriefDescription": "Number of cycles using always true condition applied to PEBS instructions retired event.", "Counter": "0,2,3", - "UMask": "0x1", + "CounterHTOff": "0,2,3", + "CounterMask": "10", "Errata": "SKL091, SKL044", + "EventCode": "0xC0", "EventName": "INST_RETIRED.TOTAL_CYCLES_PS", + "Invert": "1", + "PEBS": "2", + "PublicDescription": "Number of cycles using an always true condition applied to PEBS instructions retired event. (inst_ret< 16)", "SampleAfterValue": "2000003", - "BriefDescription": "Number of cycles using always true condition applied to PEBS instructions retired event.", - "CounterMask": "10", - "CounterHTOff": "0,2,3" + "UMask": "0x1" }, { - "EventCode": "0xC1", + "BriefDescription": "Retirement slots used.", "Counter": "0,1,2,3", - "UMask": "0x3f", - "EventName": "OTHER_ASSISTS.ANY", - "SampleAfterValue": "100003", - "BriefDescription": "Number of times a microcode assist is invoked by HW other than FP-assist. Examples include AD (page Access Dirty) and AVX* related assists.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "PublicDescription": "Counts the retirement slots used.", + "CounterHTOff": "0,1,2,3,4,5,6,7", "EventCode": "0xC2", - "Counter": "0,1,2,3", - "UMask": "0x2", "EventName": "UOPS_RETIRED.RETIRE_SLOTS", + "PublicDescription": "Counts the retirement slots used.", "SampleAfterValue": "2000003", - "BriefDescription": "Retirement slots used.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" }, { - "PublicDescription": "This event counts cycles without actually retired uops.", - "EventCode": "0xC2", - "Invert": "1", + "AnyThread": "1", + "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "UOPS_RETIRED.STALL_CYCLES", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x3C", + "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY", + "SampleAfterValue": "2000003" + }, + { + "BriefDescription": "Uops inserted at issue-stage in order to preserve upper bits of vector registers.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x0E", + "EventName": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH", + "PublicDescription": "Counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting with the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register. For more information, refer to Mixing Intel AVX and Intel SSE Code section of the Optimization Guide.", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles without actually retired uops.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" }, { - "PublicDescription": "Number of cycles using always true condition (uops_ret < 16) applied to non PEBS uops retired event.", - "EventCode": "0xC2", - "Invert": "1", + "BriefDescription": "Number of macro-fused uops retired. (non precise)", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "UOPS_RETIRED.TOTAL_CYCLES", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.MACRO_FUSED", + "PublicDescription": "Counts the number of macro-fused uops retired. (non precise)", "SampleAfterValue": "2000003", - "BriefDescription": "Cycles with less than 10 actually retired uops.", - "CounterMask": "10", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x4" }, { - "PublicDescription": "Number of machine clears (nukes) of any type.", - "EventCode": "0xC3", + "BriefDescription": "Increments whenever there is an update to the LBR array.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EdgeDetect": "1", - "EventName": "MACHINE_CLEARS.COUNT", - "SampleAfterValue": "100003", - "BriefDescription": "Number of machine clears (nukes) of any type.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xCC", + "EventName": "ROB_MISC_EVENTS.LBR_INSERTS", + "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT.", + "SampleAfterValue": "2000003", + "UMask": "0x20" }, { - "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.", - "EventCode": "0xC3", + "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "MACHINE_CLEARS.SMC", - "SampleAfterValue": "100003", - "BriefDescription": "Self-modifying code (SMC) detected.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x5E", + "EventName": "RS_EVENTS.EMPTY_CYCLES", + "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for the thread.; Note: In ST-mode, not active thread should drive 0. This is usually caused by severely costly branch mispredictions, or allocator/FE issues.", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "PublicDescription": "Counts all (macro) branch instructions retired.", - "EventCode": "0xC4", + "BriefDescription": "Instructions retired from execution.", + "Counter": "Fixed counter 0", + "CounterHTOff": "Fixed counter 0", + "EventName": "INST_RETIRED.ANY", + "PublicDescription": "Counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, Counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. INST_RETIRED.ANY_P is counted by a programmable counter and it is an architectural performance event. Counting: Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.", "Counter": "0,1,2,3", - "UMask": "0x0", - "Errata": "SKL091", - "EventName": "BR_INST_RETIRED.ALL_BRANCHES", - "SampleAfterValue": "400009", - "BriefDescription": "All (macro) branch instructions retired.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "2", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts conditional branch instructions retired.", - "EventCode": "0xC4", + "BriefDescription": "Cycles stalled due to no store buffers available. (not including draining form sync).", "Counter": "0,1,2,3", - "UMask": "0x1", - "Errata": "SKL091", - "EventName": "BR_INST_RETIRED.CONDITIONAL", - "SampleAfterValue": "400009", - "BriefDescription": "Conditional branch instructions retired.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA2", + "EventName": "RESOURCE_STALLS.SB", + "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.", + "SampleAfterValue": "2000003", + "UMask": "0x8" }, { - "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts both direct and indirect near call instructions retired.", - "EventCode": "0xC4", + "BriefDescription": "Counts when there is a transition from ring 1, 2 or 3 to ring 0.", "Counter": "0,1,2,3", - "UMask": "0x2", - "Errata": "SKL091", - "EventName": "BR_INST_RETIRED.NEAR_CALL", - "SampleAfterValue": "100007", - "BriefDescription": "Direct and indirect near call instructions retired.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0x3C", + "EventName": "CPU_CLK_UNHALTED.RING0_TRANS", + "PublicDescription": "Counts when the Current Privilege Level (CPL) transitions from ring 1, 2 or 3 to ring 0 (Kernel).", + "SampleAfterValue": "100007" }, { - "PEBS": "2", - "PublicDescription": "This is a precise version of BR_INST_RETIRED.ALL_BRANCHES that counts all (macro) branch instructions retired.", - "EventCode": "0xC4", + "BriefDescription": "All (macro) branch instructions retired.", "Counter": "0,1,2,3", - "UMask": "0x4", + "CounterHTOff": "0,1,2,3", "Errata": "SKL091", + "EventCode": "0xC4", "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS", + "PEBS": "2", + "PublicDescription": "This is a precise version of BR_INST_RETIRED.ALL_BRANCHES that counts all (macro) branch instructions retired.", "SampleAfterValue": "400009", - "BriefDescription": "All (macro) branch instructions retired.", - "CounterHTOff": "0,1,2,3" + "UMask": "0x4" }, { - "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts return instructions retired.", - "EventCode": "0xC4", + "BriefDescription": "Mispredicted macro branch instructions retired.", "Counter": "0,1,2,3", - "UMask": "0x8", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC5", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_PEBS", + "PEBS": "2", + "PublicDescription": "This is a precise version of BR_MISP_RETIRED.ALL_BRANCHES that counts all mispredicted macro branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x4" + }, + { + "BriefDescription": "Return instructions retired.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", "Errata": "SKL091", + "EventCode": "0xC4", "EventName": "BR_INST_RETIRED.NEAR_RETURN", + "PEBS": "1", + "PublicDescription": "This event counts return instructions retired.", "SampleAfterValue": "100007", - "BriefDescription": "Return instructions retired.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x8" }, { - "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts not taken branch instructions retired.", - "EventCode": "0xC4", + "BriefDescription": "Cycles total of 1 uop is executed on all ports and Reservation Station was not empty.", "Counter": "0,1,2,3", - "UMask": "0x10", - "Errata": "SKL091", - "EventName": "BR_INST_RETIRED.NOT_TAKEN", - "SampleAfterValue": "400009", - "BriefDescription": "Counts all not taken macro branch instructions retired.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA6", + "EventName": "EXE_ACTIVITY.1_PORTS_UTIL", + "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts taken branch instructions retired.", - "EventCode": "0xC4", + "BriefDescription": "Not taken branch instructions retired.", "Counter": "0,1,2,3", - "UMask": "0x20", + "CounterHTOff": "0,1,2,3,4,5,6,7", "Errata": "SKL091", - "EventName": "BR_INST_RETIRED.NEAR_TAKEN", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.NOT_TAKEN", + "PublicDescription": "This event counts not taken branch instructions retired.", "SampleAfterValue": "400009", - "BriefDescription": "Taken branch instructions retired.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x10" }, { - "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts far branch instructions retired.", - "EventCode": "0xC4", + "BriefDescription": "Conditional branch instructions retired.", "Counter": "0,1,2,3", - "UMask": "0x40", + "CounterHTOff": "0,1,2,3,4,5,6,7", "Errata": "SKL091", - "EventName": "BR_INST_RETIRED.FAR_BRANCH", - "SampleAfterValue": "100007", - "BriefDescription": "Counts the number of far branch instructions retired.", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.", - "EventCode": "0xC5", - "Counter": "0,1,2,3", - "UMask": "0x0", - "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.CONDITIONAL", + "PEBS": "1", + "PublicDescription": "This event counts conditional branch instructions retired.", "SampleAfterValue": "400009", - "BriefDescription": "All mispredicted macro branch instructions retired.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts mispredicted conditional branch instructions retired.", - "EventCode": "0xC5", + "BriefDescription": "Mispredicted conditional branch instructions retired.", "Counter": "0,1,2,3", - "UMask": "0x1", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC5", "EventName": "BR_MISP_RETIRED.CONDITIONAL", + "PEBS": "1", + "PublicDescription": "This event counts mispredicted conditional branch instructions retired.", "SampleAfterValue": "400009", - "BriefDescription": "Mispredicted conditional branch instructions retired.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PEBS": "1", - "PublicDescription": "This event counts both taken and not taken retired mispredicted direct and indirect near calls, including both register and memory indirect.", - "EventCode": "0xC5", + "BriefDescription": "Number of uops executed on the core.", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "BR_MISP_RETIRED.NEAR_CALL", - "SampleAfterValue": "400009", - "BriefDescription": "Mispredicted direct and indirect near call instructions retired.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CORE", + "PublicDescription": "Number of uops executed from any thread.", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "PEBS": "2", - "PublicDescription": "This is a precise version of BR_MISP_RETIRED.ALL_BRANCHES that counts all mispredicted macro branch instructions retired.", - "EventCode": "0xC5", + "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_PEBS", - "SampleAfterValue": "400009", - "BriefDescription": "Mispredicted macro branch instructions retired.", - "CounterHTOff": "0,1,2,3" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "12", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS", + "SampleAfterValue": "2000003", + "UMask": "0xc" }, { - "PEBS": "1", - "PublicDescription": "Number of near branch instructions retired that were mispredicted and taken.", - "EventCode": "0xC5", + "BriefDescription": "Cycles total of 2 uops are executed on all ports and Reservation Station was not empty.", "Counter": "0,1,2,3", - "UMask": "0x20", - "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", - "SampleAfterValue": "400009", - "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xA6", + "EventName": "EXE_ACTIVITY.2_PORTS_UTIL", + "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "UMask": "0x4" }, { - "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT.", - "EventCode": "0xCC", + "BriefDescription": "Cycles the issue-stage is waiting for front-end to fetch from resteered path following branch misprediction or machine clear events.", "Counter": "0,1,2,3", - "UMask": "0x20", - "EventName": "ROB_MISC_EVENTS.LBR_INSERTS", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x0D", + "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES", "SampleAfterValue": "2000003", - "BriefDescription": "Increments whenever there is an update to the LBR array.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x80" }, { - "EventCode": "0xCC", + "BriefDescription": "All (macro) branch instructions retired.", "Counter": "0,1,2,3", - "UMask": "0x40", - "EventName": "ROB_MISC_EVENTS.PAUSE_INST", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL091", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.ALL_BRANCHES", + "PublicDescription": "Counts all (macro) branch instructions retired.", + "SampleAfterValue": "400009" + }, + { + "BriefDescription": "Cycles where at least 1 uop was executed per-thread", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC", + "PublicDescription": "Cycles where at least 1 uop was executed per-thread.", "SampleAfterValue": "2000003", - "BriefDescription": "Number of retired PAUSE instructions (that do not end up with a VMExit to the VMM; TSX aborted Instructions may be counted). This event is not supported on first SKL and KBL products.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts the number of times the front-end is resteered when it finds a branch instruction in a fetch line. This occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.", - "EventCode": "0xE6", + "BriefDescription": "Cycles while L2 cache miss demand load is outstanding.", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "BACLEARS.ANY", - "SampleAfterValue": "100003", - "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS", + "SampleAfterValue": "2000003", + "UMask": "0x1" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json index 8704efeb8d31..4cd246782dde 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json @@ -1,370 +1,371 @@ [ { - "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", "MetricGroup": "TopdownL1", - "MetricName": "Frontend_Bound", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound." + "MetricName": "Frontend_Bound" }, { + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", - "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", "MetricGroup": "TopdownL1_SMT", - "MetricName": "Frontend_Bound_SMT", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU." + "MetricName": "Frontend_Bound_SMT" }, { - "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", "MetricGroup": "TopdownL1", - "MetricName": "Bad_Speculation", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example." + "MetricName": "Bad_Speculation" }, { + "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.", "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.", - "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", "MetricGroup": "TopdownL1_SMT", - "MetricName": "Bad_Speculation_SMT", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU." + "MetricName": "Bad_Speculation_SMT" }, { + "MetricConstraint": "NO_NMI_WATCHDOG", + "MetricGroup": "TopdownL1", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )", - "MetricGroup": "TopdownL1", - "MetricName": "Backend_Bound", - "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound." + "MetricName": "Backend_Bound" }, { + "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) )", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.", "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.", - "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )", "MetricGroup": "TopdownL1_SMT", - "MetricName": "Backend_Bound_SMT", - "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU." + "MetricName": "Backend_Bound_SMT" }, { - "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. ", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", "MetricGroup": "TopdownL1", - "MetricName": "Retiring", - "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. " + "MetricName": "Retiring" }, { + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. SMT version; use when SMT is enabled and measuring per logical CPU.", "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))", "MetricGroup": "TopdownL1_SMT", - "MetricName": "Retiring_SMT", - "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved. Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU." + "MetricName": "Retiring_SMT" }, { - "BriefDescription": "Instructions Per Cycle (per Logical Processor)", "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "TopDownL1", + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricGroup": "Summary", "MetricName": "IPC" }, { - "BriefDescription": "Uops Per Instruction", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", + "BriefDescription": "Uops Per Instruction", "MetricGroup": "Pipeline;Retire", "MetricName": "UPI" }, { - "BriefDescription": "Instruction per taken branch", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "BriefDescription": "Instruction per taken branch", "MetricGroup": "Branches;Fetch_BW;PGO", "MetricName": "IpTB" }, { - "BriefDescription": "Branch instructions per taken branch. ", - "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;PGO", - "MetricName": "BpTB" - }, - { - "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions", - "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1 ) )", - "MetricGroup": "PGO;IcMiss", - "MetricName": "IFetch_Line_Utilization" - }, - { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", - "MetricGroup": "DSB;Fetch_BW", - "MetricName": "DSB_Coverage" - }, - { - "BriefDescription": "Cycles Per Instruction (per Logical Processor)", "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)", - "MetricGroup": "Pipeline;Summary", + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricGroup": "Pipeline", "MetricName": "CPI" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", "MetricGroup": "Summary", "MetricName": "CLKS" }, { - "BriefDescription": "Total issue-pipeline slots (per-Physical Core)", "MetricExpr": "4 * cycles", + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", "MetricGroup": "TopDownL1", "MetricName": "SLOTS" }, { - "BriefDescription": "Total issue-pipeline slots (per-Physical Core)", - "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", + "MetricExpr": "4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", "MetricGroup": "TopDownL1_SMT", "MetricName": "SLOTS_SMT" }, { - "BriefDescription": "Instructions per Load (lower number means higher occurance rate)", - "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS", - "MetricGroup": "Instruction_Type", - "MetricName": "IpL" - }, - { - "BriefDescription": "Instructions per Store (lower number means higher occurance rate)", - "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES", - "MetricGroup": "Instruction_Type", - "MetricName": "IpS" - }, - { - "BriefDescription": "Instructions per Branch (lower number means higher occurance rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Branches;Instruction_Type", - "MetricName": "IpB" - }, - { - "BriefDescription": "Instruction per (near) call (lower number means higher occurance rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", - "MetricGroup": "Branches", - "MetricName": "IpCall" - }, - { - "BriefDescription": "Total number of retired Instructions", - "MetricExpr": "INST_RETIRED.ANY", - "MetricGroup": "Summary", - "MetricName": "Instructions" - }, - { - "BriefDescription": "Instructions Per Cycle (per physical core)", "MetricExpr": "INST_RETIRED.ANY / cycles", - "MetricGroup": "SMT", + "BriefDescription": "Instructions Per Cycle (per physical core)", + "MetricGroup": "SMT;TopDownL1", "MetricName": "CoreIPC" }, { + "MetricExpr": "INST_RETIRED.ANY / ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", "BriefDescription": "Instructions Per Cycle (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", - "MetricGroup": "SMT", + "MetricGroup": "SMT;TopDownL1", "MetricName": "CoreIPC_SMT" }, { + "MetricExpr": "( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE ) / cycles", "BriefDescription": "Floating Point Operations Per Cycle", - "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / cycles", "MetricGroup": "FLOPS", "MetricName": "FLOPc" }, { + "MetricExpr": "( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE ) / ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", "BriefDescription": "Floating Point Operations Per Cycle", - "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))", "MetricGroup": "FLOPS_SMT", "MetricName": "FLOPc_SMT" }, { + "MetricExpr": "UOPS_EXECUTED.THREAD / ( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 )", "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)", - "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 ) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", - "MetricGroup": "Pipeline", + "MetricGroup": "Pipeline;Ports_Utilization", "MetricName": "ILP" }, { - "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per non-speculative branch misprediction (jeclear)", "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) ) * (4 * cycles) / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", "MetricGroup": "BrMispredicts", "MetricName": "Branch_Misprediction_Cost" }, { - "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per non-speculative branch misprediction (jeclear)", - "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) ) * (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY / 2 ) ) / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) ) * (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )) / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", "MetricGroup": "BrMispredicts_SMT", "MetricName": "Branch_Misprediction_Cost_SMT" }, { - "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)", "MetricGroup": "BrMispredicts", "MetricName": "IpMispredict" }, { - "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )", + "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", "MetricGroup": "SMT", "MetricName": "CORE_CLKS" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)", + "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS", + "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", + "MetricGroup": "Instruction_Type", + "MetricName": "IpLoad" + }, + { + "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES", + "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", + "MetricGroup": "Instruction_Type", + "MetricName": "IpStore" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", + "MetricGroup": "Branches;Instruction_Type", + "MetricName": "IpBranch" + }, + { + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", + "MetricGroup": "Branches", + "MetricName": "IpCall" + }, + { + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "BriefDescription": "Branch instructions per taken branch. ", + "MetricGroup": "Branches;PGO", + "MetricName": "BpTkBranch" + }, + { + "MetricExpr": "INST_RETIRED.ANY / ( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )", + "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", + "MetricGroup": "FLOPS;FP_Arith;Instruction_Type", + "MetricName": "IpFLOP" + }, + { + "MetricExpr": "INST_RETIRED.ANY", + "BriefDescription": "Total number of retired Instructions", + "MetricGroup": "Summary;TopDownL1", + "MetricName": "Instructions" + }, + { + "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricGroup": "DSB;Fetch_BW", + "MetricName": "DSB_Coverage" + }, + { "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT )", + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)", "MetricGroup": "Memory_Bound;Memory_Lat", "MetricName": "Load_Miss_Real_Latency" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)", "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)", "MetricGroup": "Memory_Bound;Memory_BW", "MetricName": "MLP" }, { - "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricConstraint": "NO_NMI_WATCHDOG", "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * cycles )", + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", "MetricGroup": "TLB", - "MetricName": "Page_Walks_Utilization", - "MetricConstraint": "NO_NMI_WATCHDOG" + "MetricName": "Page_Walks_Utilization" }, { + "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ) )", "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )) )", "MetricGroup": "TLB_SMT", "MetricName": "Page_Walks_Utilization_SMT" }, { - "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]", "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time", + "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]", "MetricGroup": "Memory_BW", "MetricName": "L1D_Cache_Fill_BW" }, { - "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]", "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time", + "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]", "MetricGroup": "Memory_BW", "MetricName": "L2_Cache_Fill_BW" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time", + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", "MetricGroup": "Memory_BW", "MetricName": "L3_Cache_Fill_BW" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1000000000 / duration_time", - "MetricGroup": "Memory_BW", + "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]", + "MetricGroup": "Memory_BW;Offcore", "MetricName": "L3_Cache_Access_BW" }, { - "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", "MetricExpr": "1000 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY", + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", "MetricGroup": "Cache_Misses", "MetricName": "L1MPKI" }, { - "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", "MetricExpr": "1000 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", "MetricGroup": "Cache_Misses", "MetricName": "L2MPKI" }, { - "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)", "MetricExpr": "1000 * L2_RQSTS.MISS / INST_RETIRED.ANY", - "MetricGroup": "Cache_Misses", + "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)", + "MetricGroup": "Cache_Misses;Offcore", "MetricName": "L2MPKI_All" }, { - "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", "MetricExpr": "1000 * ( L2_RQSTS.REFERENCES - L2_RQSTS.MISS ) / INST_RETIRED.ANY", + "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", "MetricGroup": "Cache_Misses", "MetricName": "L2HPKI_All" }, { - "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", "MetricExpr": "1000 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", "MetricGroup": "Cache_Misses", "MetricName": "L3MPKI" }, { - "BriefDescription": "Average CPU Utilization", "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", - "MetricGroup": "Summary", + "BriefDescription": "Average CPU Utilization", + "MetricGroup": "HPC;Summary", "MetricName": "CPU_Utilization" }, { + "MetricExpr": "( ( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE ) / 1000000000 ) / duration_time", "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "( (( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 ) / duration_time", - "MetricGroup": "FLOPS;Summary", + "MetricGroup": "FLOPS;HPC", "MetricName": "GFLOPs" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC", + "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricGroup": "Power", "MetricName": "Turbo_Utilization" }, { + "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 )", "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", - "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0", - "MetricGroup": "SMT;Summary", + "MetricGroup": "SMT", "MetricName": "SMT_2T_Utilization" }, { - "BriefDescription": "Fraction of cycles spent in Kernel mode", "MetricExpr": "CPU_CLK_UNHALTED.THREAD:k / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "Summary", + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", + "MetricGroup": "OS", "MetricName": "Kernel_Utilization" }, { - "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", "MetricExpr": "64 * ( arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@ ) / 1000000 / duration_time / 1000", - "MetricGroup": "Memory_BW", + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricGroup": "HPC;Memory_BW;SoC", "MetricName": "DRAM_BW_Use" }, { + "MetricExpr": "arb@event\\=0x80\\,umask\\=0x2@ / arb@event\\=0x80\\,umask\\=0x2\\,cmask\\=1@", "BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches", - "MetricExpr": "arb@event\\=0x80\\,umask\\=0x2@ / arb@event\\=0x80\\,umask\\=0x2\\,thresh\\=1@", - "MetricGroup": "Memory_BW", - "MetricName": "DRAM_Parallel_Reads" + "MetricGroup": "Memory_BW;SoC", + "MetricName": "MEM_Parallel_Reads" }, { - "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions. )", "MetricExpr": "INST_RETIRED.ANY / ( BR_INST_RETIRED.FAR_BRANCH / 2 )", - "MetricGroup": "", + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricGroup": "Branches;OS", "MetricName": "IpFarBranch" }, { - "BriefDescription": "C3 residency percent per core", "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100", + "BriefDescription": "C3 residency percent per core", "MetricGroup": "Power", "MetricName": "C3_Core_Residency" }, { - "BriefDescription": "C6 residency percent per core", "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100", + "BriefDescription": "C6 residency percent per core", "MetricGroup": "Power", "MetricName": "C6_Core_Residency" }, { - "BriefDescription": "C7 residency percent per core", "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100", + "BriefDescription": "C7 residency percent per core", "MetricGroup": "Power", "MetricName": "C7_Core_Residency" }, { - "BriefDescription": "C2 residency percent per package", "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100", + "BriefDescription": "C2 residency percent per package", "MetricGroup": "Power", "MetricName": "C2_Pkg_Residency" }, { - "BriefDescription": "C3 residency percent per package", "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100", + "BriefDescription": "C3 residency percent per package", "MetricGroup": "Power", "MetricName": "C3_Pkg_Residency" }, { - "BriefDescription": "C6 residency percent per package", "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", + "BriefDescription": "C6 residency percent per package", "MetricGroup": "Power", "MetricName": "C6_Pkg_Residency" }, { - "BriefDescription": "C7 residency percent per package", "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100", + "BriefDescription": "C7 residency percent per package", "MetricGroup": "Power", "MetricName": "C7_Pkg_Residency" } diff --git a/tools/perf/pmu-events/arch/x86/skylake/virtual-memory.json b/tools/perf/pmu-events/arch/x86/skylake/virtual-memory.json index 2bcba7daca14..432530d15c26 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/skylake/virtual-memory.json @@ -1,284 +1,284 @@ [ { - "PublicDescription": "Counts demand data loads that caused a page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels, but the walk need not have completed.", - "EventCode": "0x08", + "BriefDescription": "Store misses in all DTLB levels that cause page walks", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.MISS_CAUSES_A_WALK", + "PublicDescription": "Counts demand data stores that caused a page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels, but the walk need not have completed.", "SampleAfterValue": "100003", - "BriefDescription": "Load misses in all DTLB levels that cause page walks", - "CounterHTOff": "0,1,2,3,4,5,6,7" - }, - { - "PublicDescription": "Counts page walks completed due to demand data loads whose address translations missed in the TLB and were mapped to 4K pages. The page walks can end with or without a page fault.", - "EventCode": "0x08", - "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K", - "SampleAfterValue": "2000003", - "BriefDescription": "Page walk completed due to a demand data load to a 4K page", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts page walks completed due to demand data loads whose address translations missed in the TLB and were mapped to 2M/4M pages. The page walks can end with or without a page fault.", - "EventCode": "0x08", + "BriefDescription": "Page walk completed due to a demand data store to a 2M/4M page", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M", - "SampleAfterValue": "2000003", - "BriefDescription": "Page walk completed due to a demand data load to a 2M/4M page", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x4" }, { - "PublicDescription": "Counts page walks completed due to demand data loads whose address translations missed in the TLB and were mapped to 4K pages. The page walks can end with or without a page fault.", - "EventCode": "0x08", + "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake.", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G", - "SampleAfterValue": "2000003", - "BriefDescription": "Page walk completed due to a demand data load to a 1G page", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_PENDING", + "PublicDescription": "Counts 1 per cycle for each PMH (Page Miss Handler) that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake michroarchitecture.", + "SampleAfterValue": "100003", + "UMask": "0x10" }, { - "PublicDescription": "Counts demand data loads that caused a completed page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels. The page walk can end with or without a fault.", - "EventCode": "0x08", + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)", "Counter": "0,1,2,3", - "UMask": "0xe", - "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", - "BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (All page sizes)", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" }, { - "PublicDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a load. EPT page walk duration are excluded in Skylake microarchitecture.", - "EventCode": "0x08", + "BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "DTLB_LOAD_MISSES.WALK_PENDING", - "SampleAfterValue": "2000003", - "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a load. EPT page walk duration are excluded in Skylake.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xAE", + "EventName": "ITLB.ITLB_FLUSH", + "PublicDescription": "Counts the number of flushes of the big or small ITLB pages. Counting include both TLB Flush (covering all sets) and TLB Set Clear (set-specific).", + "SampleAfterValue": "100007", + "UMask": "0x1" }, { - "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a load.", - "EventCode": "0x08", + "BriefDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request. EPT page walk duration are excluded in Skylake.", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE", - "SampleAfterValue": "100003", - "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a load. EPT page walk duration are excluded in Skylake.", + "CounterHTOff": "0,1,2,3,4,5,6,7", "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_ACTIVE", + "PublicDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request. EPT page walk duration are excluded in Skylake microarchitecture.", + "SampleAfterValue": "100003", + "UMask": "0x10" }, { - "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).", - "EventCode": "0x08", + "BriefDescription": "Loads that miss the DTLB and hit the STLB.", "Counter": "0,1,2,3", - "UMask": "0x20", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", "EventName": "DTLB_LOAD_MISSES.STLB_HIT", + "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).", "SampleAfterValue": "2000003", - "BriefDescription": "Loads that miss the DTLB and hit the STLB.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x20" }, { - "PublicDescription": "Counts demand data stores that caused a page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels, but the walk need not have completed.", + "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a store. EPT page walk duration are excluded in Skylake.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_PENDING", + "PublicDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a store. EPT page walk duration are excluded in Skylake microarchitecture.", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "DTLB flush attempts of the thread-specific entries", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "DTLB_STORE_MISSES.MISS_CAUSES_A_WALK", - "SampleAfterValue": "100003", - "BriefDescription": "Store misses in all DTLB levels that cause page walks", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xBD", + "EventName": "TLB_FLUSH.DTLB_THREAD", + "PublicDescription": "Counts the number of DTLB flush attempts of the thread-specific entries.", + "SampleAfterValue": "100007", + "UMask": "0x1" }, { - "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 4K pages. The page walks can end with or without a page fault.", - "EventCode": "0x49", + "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a load. EPT page walk duration are excluded in Skylake.", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K", - "SampleAfterValue": "100003", - "BriefDescription": "Page walk completed due to a demand data store to a 4K page", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_PENDING", + "PublicDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a load. EPT page walk duration are excluded in Skylake microarchitecture.", + "SampleAfterValue": "2000003", + "UMask": "0x10" }, { - "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 2M/4M pages. The page walks can end with or without a page fault.", - "EventCode": "0x49", + "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a store. EPT page walk duration are excluded in Skylake.", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.", "SampleAfterValue": "100003", - "BriefDescription": "Page walk completed due to a demand data store to a 2M/4M page", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x10" }, { - "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 1G pages. The page walks can end with or without a page fault.", - "EventCode": "0x49", + "BriefDescription": "Misses at all ITLB levels that cause page walks", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.MISS_CAUSES_A_WALK", + "PublicDescription": "Counts page walks of any page size (4K/2M/4M/1G) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB, but the walk need not have completed.", "SampleAfterValue": "100003", - "BriefDescription": "Page walk completed due to a demand data store to a 1G page", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts demand data stores that caused a completed page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels. The page walk can end with or without a fault.", - "EventCode": "0x49", + "BriefDescription": "Stores that miss the DTLB and hit the STLB.", "Counter": "0,1,2,3", - "UMask": "0xe", - "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.STLB_HIT", + "PublicDescription": "Stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).", "SampleAfterValue": "100003", - "BriefDescription": "Store misses in all TLB levels causes a page walk that completes. (All page sizes)", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x20" }, { - "PublicDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a store. EPT page walk duration are excluded in Skylake microarchitecture.", - "EventCode": "0x49", + "BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (All page sizes)", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "DTLB_STORE_MISSES.WALK_PENDING", - "SampleAfterValue": "2000003", - "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a store. EPT page walk duration are excluded in Skylake.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0xe" }, { - "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.", - "EventCode": "0x49", + "BriefDescription": "Page walk completed due to a demand data store to a 4K page", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", - "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a store. EPT page walk duration are excluded in Skylake.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x2" }, { - "PublicDescription": "Stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).", - "EventCode": "0x49", + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (1G)", "Counter": "0,1,2,3", - "UMask": "0x20", - "EventName": "DTLB_STORE_MISSES.STLB_HIT", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_COMPLETED_1G", + "PublicDescription": "Counts completed page walks (1G page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", - "BriefDescription": "Stores that miss the DTLB and hit the STLB.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x8" }, { - "PublicDescription": "Counts cycles for each PMH (Page Miss Handler) that is busy with an EPT (Extended Page Table) walk for any request type.", - "EventCode": "0x4F", + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (All page sizes)", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "EPT.WALK_PENDING", - "SampleAfterValue": "2000003", - "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a EPT (Extended Page Table) walk for any request type.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0xe" }, { - "PublicDescription": "Counts page walks of any page size (4K/2M/4M/1G) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB, but the walk need not have completed.", - "EventCode": "0x85", + "BriefDescription": "Page walk completed due to a demand data load to a 4K page", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "ITLB_MISSES.MISS_CAUSES_A_WALK", - "SampleAfterValue": "100003", - "BriefDescription": "Misses at all ITLB levels that cause page walks", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "PublicDescription": "Counts completed page walks (4K page size) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB. The page walk can end with or without a fault.", - "EventCode": "0x85", + "BriefDescription": "Instruction fetch requests that miss the ITLB and hit the STLB.", "Counter": "0,1,2,3", - "UMask": "0x2", - "EventName": "ITLB_MISSES.WALK_COMPLETED_4K", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.STLB_HIT", "SampleAfterValue": "100003", - "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x20" }, { - "PublicDescription": "Counts code misses in all ITLB levels that caused a completed page walk (2M and 4M page sizes). The page walk can end with or without a fault.", - "EventCode": "0x85", + "BriefDescription": "Page walk completed due to a demand data load to a 2M/4M page", "Counter": "0,1,2,3", - "UMask": "0x4", - "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M", - "SampleAfterValue": "100003", - "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "2000003", + "UMask": "0x4" }, { - "PublicDescription": "Counts store misses in all DTLB levels that cause a completed page walk (1G page size). The page walk can end with or without a fault.", - "EventCode": "0x85", + "BriefDescription": "Load misses in all DTLB levels that cause page walks", "Counter": "0,1,2,3", - "UMask": "0x8", - "EventName": "ITLB_MISSES.WALK_COMPLETED_1G", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK", + "PublicDescription": "Counts demand data loads that caused a page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels, but the walk need not have completed.", "SampleAfterValue": "100003", - "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (1G)", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x1" }, { - "PublicDescription": "Counts completed page walks (2M and 4M page sizes) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB. The page walk can end with or without a fault.", - "EventCode": "0x85", + "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a EPT (Extended Page Table) walk for any request type.", "Counter": "0,1,2,3", - "UMask": "0xe", - "EventName": "ITLB_MISSES.WALK_COMPLETED", - "SampleAfterValue": "100003", - "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (All page sizes)", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x4f", + "EventName": "EPT.WALK_PENDING", + "PublicDescription": "Counts cycles for each PMH (Page Miss Handler) that is busy with an EPT (Extended Page Table) walk for any request type.", + "SampleAfterValue": "2000003", + "UMask": "0x10" }, { - "PublicDescription": "Counts 1 per cycle for each PMH (Page Miss Handler) that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake michroarchitecture.", - "EventCode": "0x85", + "BriefDescription": "STLB flush attempts", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "ITLB_MISSES.WALK_PENDING", - "SampleAfterValue": "100003", - "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xBD", + "EventName": "TLB_FLUSH.STLB_ANY", + "PublicDescription": "Counts the number of any STLB flush attempts (such as entire, VPID, PCID, InvPage, CR3 write, etc.).", + "SampleAfterValue": "100007", + "UMask": "0x20" }, { - "PublicDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request. EPT page walk duration are excluded in Skylake microarchitecture.", - "EventCode": "0x85", + "BriefDescription": "Page walk completed due to a demand data load to a 1G page", "Counter": "0,1,2,3", - "UMask": "0x10", - "EventName": "ITLB_MISSES.WALK_ACTIVE", - "SampleAfterValue": "100003", - "BriefDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request. EPT page walk duration are excluded in Skylake.", - "CounterMask": "1", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G", + "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "2000003", + "UMask": "0x8" }, { - "EventCode": "0x85", + "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a load. EPT page walk duration are excluded in Skylake.", "Counter": "0,1,2,3", - "UMask": "0x20", - "EventName": "ITLB_MISSES.STLB_HIT", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a load.", "SampleAfterValue": "100003", - "BriefDescription": "Instruction fetch requests that miss the ITLB and hit the STLB.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "UMask": "0x10" }, { - "PublicDescription": "Counts the number of flushes of the big or small ITLB pages. Counting include both TLB Flush (covering all sets) and TLB Set Clear (set-specific).", - "EventCode": "0xAE", + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "ITLB.ITLB_FLUSH", - "SampleAfterValue": "100007", - "BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x4" }, { - "PublicDescription": "Counts the number of DTLB flush attempts of the thread-specific entries.", - "EventCode": "0xBD", + "BriefDescription": "Store misses in all TLB levels causes a page walk that completes. (All page sizes)", "Counter": "0,1,2,3", - "UMask": "0x1", - "EventName": "TLB_FLUSH.DTLB_THREAD", - "SampleAfterValue": "100007", - "BriefDescription": "DTLB flush attempts of the thread-specific entries", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0xe" }, { - "PublicDescription": "Counts the number of any STLB flush attempts (such as entire, VPID, PCID, InvPage, CR3 write, etc.).", - "EventCode": "0xBD", + "BriefDescription": "Page walk completed due to a demand data store to a 1G page", "Counter": "0,1,2,3", - "UMask": "0x20", - "EventName": "TLB_FLUSH.STLB_ANY", - "SampleAfterValue": "100007", - "BriefDescription": "STLB flush attempts", - "CounterHTOff": "0,1,2,3,4,5,6,7" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G", + "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x8" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index e47644cab3fa..e1f3f5c8c550 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -55,6 +55,7 @@ char *prog; struct json_event { char *name; + char *compat; char *event; char *desc; char *long_desc; @@ -82,6 +83,23 @@ enum aggr_mode_class convert(const char *aggr_mode) typedef int (*func)(void *data, struct json_event *je); +static LIST_HEAD(sys_event_tables); + +struct sys_event_table { + struct list_head list; + char *soc_id; +}; + +static void free_sys_event_tables(void) +{ + struct sys_event_table *et, *next; + + list_for_each_entry_safe(et, next, &sys_event_tables, list) { + free(et->soc_id); + free(et); + } +} + int eprintf(int level, int var, const char *fmt, ...) { @@ -263,6 +281,8 @@ static struct map { { "hisi_sccl,ddrc", "hisi_sccl,ddrc" }, { "hisi_sccl,hha", "hisi_sccl,hha" }, { "hisi_sccl,l3c", "hisi_sccl,l3c" }, + /* it's not realistic to keep adding these, we need something more scalable ... */ + { "imx8_ddr", "imx8_ddr" }, { "L3PMC", "amd_l3" }, { "DFPMC", "amd_df" }, {} @@ -360,6 +380,8 @@ static int print_events_table_entry(void *data, struct json_event *je) if (je->event) fprintf(outfp, "\t.event = \"%s\",\n", je->event); fprintf(outfp, "\t.desc = \"%s\",\n", je->desc); + if (je->compat) + fprintf(outfp, "\t.compat = \"%s\",\n", je->compat); fprintf(outfp, "\t.topic = \"%s\",\n", topic); if (je->long_desc && je->long_desc[0]) fprintf(outfp, "\t.long_desc = \"%s\",\n", je->long_desc); @@ -390,6 +412,7 @@ struct event_struct { struct list_head list; char *name; char *event; + char *compat; char *desc; char *long_desc; char *pmu; @@ -583,6 +606,8 @@ static int json_events(const char *fn, free(code); } else if (json_streq(map, field, "EventName")) { addfield(map, &je.name, "", "", val); + } else if (json_streq(map, field, "Compat")) { + addfield(map, &je.compat, "", "", val); } else if (json_streq(map, field, "BriefDescription")) { addfield(map, &je.desc, "", "", val); fixdesc(je.desc); @@ -683,6 +708,7 @@ free_strings: free(event); free(je.desc); free(je.name); + free(je.compat); free(je.long_desc); free(extra_desc); free(je.pmu); @@ -747,6 +773,15 @@ static char *file_name_to_table_name(char *fname) return tblname; } +static bool is_sys_dir(char *fname) +{ + size_t len = strlen(fname), len2 = strlen("/sys"); + + if (len2 > len) + return false; + return !strcmp(fname+len-len2, "/sys"); +} + static void print_mapping_table_prefix(FILE *outfp) { fprintf(outfp, "struct pmu_events_map pmu_events_map[] = {\n"); @@ -781,6 +816,33 @@ static void print_mapping_test_table(FILE *outfp) fprintf(outfp, "},\n"); } +static void print_system_event_mapping_table_prefix(FILE *outfp) +{ + fprintf(outfp, "\nstruct pmu_sys_events pmu_sys_event_tables[] = {"); +} + +static void print_system_event_mapping_table_suffix(FILE *outfp) +{ + fprintf(outfp, "\n\t{\n\t\t.table = 0\n\t},"); + fprintf(outfp, "\n};\n"); +} + +static int process_system_event_tables(FILE *outfp) +{ + struct sys_event_table *sys_event_table; + + print_system_event_mapping_table_prefix(outfp); + + list_for_each_entry(sys_event_table, &sys_event_tables, list) { + fprintf(outfp, "\n\t{\n\t\t.table = %s,\n\t},", + sys_event_table->soc_id); + } + + print_system_event_mapping_table_suffix(outfp); + + return 0; +} + static int process_mapfile(FILE *outfp, char *fpath) { int n = 16384; @@ -886,6 +948,8 @@ static void create_empty_mapping(const char *output_file) fprintf(outfp, "#include \"pmu-events/pmu-events.h\"\n"); print_mapping_table_prefix(outfp); print_mapping_table_suffix(outfp); + print_system_event_mapping_table_prefix(outfp); + print_system_event_mapping_table_suffix(outfp); fclose(outfp); } @@ -978,15 +1042,20 @@ static int process_one_file(const char *fpath, const struct stat *sb, int level = ftwbuf->level; int err = 0; - if (level == 2 && is_dir) { + if (level >= 2 && is_dir) { + int count = 0; /* * For level 2 directory, bname will include parent name, * like vendor/platform. So search back from platform dir * to find this. + * Something similar for level 3 directory, but we're a PMU + * category folder, like vendor/platform/cpu. */ bname = (char *) fpath + ftwbuf->base - 2; for (;;) { if (*bname == '/') + count++; + if (count == level - 1) break; bname--; } @@ -999,13 +1068,13 @@ static int process_one_file(const char *fpath, const struct stat *sb, level, sb->st_size, bname, fpath); /* base dir or too deep */ - if (level == 0 || level > 3) + if (level == 0 || level > 4) return 0; /* model directory, reset topic */ if ((level == 1 && is_dir && is_leaf_dir(fpath)) || - (level == 2 && is_dir)) { + (level >= 2 && is_dir && is_leaf_dir(fpath))) { if (close_table) print_events_table_suffix(eventsfp); @@ -1021,6 +1090,22 @@ static int process_one_file(const char *fpath, const struct stat *sb, return -1; } + if (is_sys_dir(bname)) { + struct sys_event_table *sys_event_table; + + sys_event_table = malloc(sizeof(*sys_event_table)); + if (!sys_event_table) + return -1; + + sys_event_table->soc_id = strdup(tblname); + if (!sys_event_table->soc_id) { + free(sys_event_table); + return -1; + } + list_add_tail(&sys_event_table->list, + &sys_event_tables); + } + print_events_table_prefix(eventsfp, tblname); return 0; } @@ -1100,12 +1185,13 @@ static int process_one_file(const char *fpath, const struct stat *sb, */ int main(int argc, char *argv[]) { - int rc, ret = 0; + int rc, ret = 0, empty_map = 0; int maxfds; char ldirname[PATH_MAX]; const char *arch; const char *output_file; const char *start_dirname; + char *err_string_ext = ""; struct stat stbuf; prog = basename(argv[0]); @@ -1133,7 +1219,8 @@ int main(int argc, char *argv[]) /* If architecture does not have any event lists, bail out */ if (stat(ldirname, &stbuf) < 0) { pr_info("%s: Arch %s has no PMU event lists\n", prog, arch); - goto empty_map; + empty_map = 1; + goto err_close_eventsfp; } /* Include pmu-events.h first */ @@ -1150,75 +1237,70 @@ int main(int argc, char *argv[]) */ maxfds = get_maxfds(); - mapfile = NULL; rc = nftw(ldirname, preprocess_arch_std_files, maxfds, 0); - if (rc && verbose) { - pr_info("%s: Error preprocessing arch standard files %s\n", - prog, ldirname); - goto empty_map; - } else if (rc < 0) { - /* Make build fail */ - fclose(eventsfp); - free_arch_std_events(); - return 1; - } else if (rc) { - goto empty_map; - } + if (rc) + goto err_processing_std_arch_event_dir; rc = nftw(ldirname, process_one_file, maxfds, 0); - if (rc && verbose) { - pr_info("%s: Error walking file tree %s\n", prog, ldirname); - goto empty_map; - } else if (rc < 0) { - /* Make build fail */ - fclose(eventsfp); - free_arch_std_events(); - ret = 1; - goto out_free_mapfile; - } else if (rc) { - goto empty_map; - } + if (rc) + goto err_processing_dir; sprintf(ldirname, "%s/test", start_dirname); + rc = nftw(ldirname, preprocess_arch_std_files, maxfds, 0); + if (rc) + goto err_processing_std_arch_event_dir; + rc = nftw(ldirname, process_one_file, maxfds, 0); - if (rc && verbose) { - pr_info("%s: Error walking file tree %s rc=%d for test\n", - prog, ldirname, rc); - goto empty_map; - } else if (rc < 0) { - /* Make build fail */ - free_arch_std_events(); - ret = 1; - goto out_free_mapfile; - } else if (rc) { - goto empty_map; - } + if (rc) + goto err_processing_dir; if (close_table) print_events_table_suffix(eventsfp); if (!mapfile) { pr_info("%s: No CPU->JSON mapping?\n", prog); - goto empty_map; + empty_map = 1; + goto err_close_eventsfp; } - if (process_mapfile(eventsfp, mapfile)) { + rc = process_mapfile(eventsfp, mapfile); + if (rc) { pr_info("%s: Error processing mapfile %s\n", prog, mapfile); /* Make build fail */ - fclose(eventsfp); - free_arch_std_events(); ret = 1; + goto err_close_eventsfp; } + rc = process_system_event_tables(eventsfp); + fclose(eventsfp); + if (rc) { + ret = 1; + goto err_out; + } - goto out_free_mapfile; + free_arch_std_events(); + free(mapfile); + return 0; -empty_map: +err_processing_std_arch_event_dir: + err_string_ext = " for std arch event"; +err_processing_dir: + if (verbose) { + pr_info("%s: Error walking file tree %s%s\n", prog, ldirname, + err_string_ext); + empty_map = 1; + } else if (rc < 0) { + ret = 1; + } else { + empty_map = 1; + } +err_close_eventsfp: fclose(eventsfp); - create_empty_mapping(output_file); + if (empty_map) + create_empty_mapping(output_file); +err_out: free_arch_std_events(); -out_free_mapfile: free(mapfile); return ret; } diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h index 7da1a3743b77..d1172f6aebf1 100644 --- a/tools/perf/pmu-events/pmu-events.h +++ b/tools/perf/pmu-events/pmu-events.h @@ -12,6 +12,7 @@ enum aggr_mode_class { */ struct pmu_event { const char *name; + const char *compat; const char *event; const char *desc; const char *topic; @@ -43,10 +44,15 @@ struct pmu_events_map { struct pmu_event *table; }; +struct pmu_sys_events { + struct pmu_event *table; +}; + /* * Global table mapping each known CPU for the architecture to its * table of PMU events. */ extern struct pmu_events_map pmu_events_map[]; +extern struct pmu_sys_events pmu_sys_event_tables[]; #endif diff --git a/tools/perf/python/tracepoint.py b/tools/perf/python/tracepoint.py index eb76f6516247..461848c7f57d 100755 --- a/tools/perf/python/tracepoint.py +++ b/tools/perf/python/tracepoint.py @@ -1,4 +1,4 @@ -#! /usr/bin/python +#! /usr/bin/env python # SPDX-License-Identifier: GPL-2.0 # -*- python -*- # -*- coding: utf-8 -*- diff --git a/tools/perf/python/twatch.py b/tools/perf/python/twatch.py index ff87ccf5b708..04f3db29b9bc 100755 --- a/tools/perf/python/twatch.py +++ b/tools/perf/python/twatch.py @@ -1,4 +1,4 @@ -#! /usr/bin/python +#! /usr/bin/env python # SPDX-License-Identifier: GPL-2.0-only # -*- python -*- # -*- coding: utf-8 -*- diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build index 4d15bf6041fb..aa4dc4f5abde 100644 --- a/tools/perf/tests/Build +++ b/tools/perf/tests/Build @@ -62,6 +62,7 @@ perf-y += pfm.o perf-y += parse-metric.o perf-y += pe-file-parsing.o perf-y += expand-cgroup.o +perf-y += perf-time-to-tsc.o $(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build $(call rule_mkdir) diff --git a/tools/perf/tests/backward-ring-buffer.c b/tools/perf/tests/backward-ring-buffer.c index 15cea518f5ad..b4b9a9488d51 100644 --- a/tools/perf/tests/backward-ring-buffer.c +++ b/tools/perf/tests/backward-ring-buffer.c @@ -109,7 +109,7 @@ int test__backward_ring_buffer(struct test *test __maybe_unused, int subtest __m return TEST_FAIL; } - err = perf_evlist__create_maps(evlist, &opts.target); + err = evlist__create_maps(evlist, &opts.target); if (err < 0) { pr_debug("Not enough memory to create thread/cpu maps\n"); goto out_delete_evlist; @@ -127,7 +127,7 @@ int test__backward_ring_buffer(struct test *test __maybe_unused, int subtest __m goto out_delete_evlist; } - perf_evlist__config(evlist, &opts, NULL); + evlist__config(evlist, &opts, NULL); err = evlist__open(evlist); if (err < 0) { diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c index cd77e334e577..f57e075b0ed2 100644 --- a/tools/perf/tests/bpf.c +++ b/tools/perf/tests/bpf.c @@ -9,12 +9,10 @@ #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 <linux/string.h> #include <api/fs/fs.h> -#include <bpf/bpf.h> #include <perf/mmap.h> #include "tests.h" #include "llvm.h" @@ -25,6 +23,8 @@ #define PERF_TEST_BPF_PATH "/sys/fs/bpf/perf_test" #ifdef HAVE_LIBBPF_SUPPORT +#include <linux/bpf.h> +#include <bpf/bpf.h> static int epoll_pwait_loop(void) { @@ -144,23 +144,23 @@ static int do_test(struct bpf_object *obj, int (*func)(void), pid[sizeof(pid) - 1] = '\0'; opts.target.tid = opts.target.pid = pid; - /* Instead of perf_evlist__new_default, don't add default events */ + /* Instead of evlist__new_default, don't add default events */ evlist = evlist__new(); if (!evlist) { pr_debug("Not enough memory to create evlist\n"); return TEST_FAIL; } - err = perf_evlist__create_maps(evlist, &opts.target); + err = evlist__create_maps(evlist, &opts.target); if (err < 0) { pr_debug("Not enough memory to create thread/cpu maps\n"); goto out_delete_evlist; } - perf_evlist__splice_list_tail(evlist, &parse_state.list); + evlist__splice_list_tail(evlist, &parse_state.list); evlist->nr_groups = parse_state.nr_groups; - perf_evlist__config(evlist, &opts, NULL); + evlist__config(evlist, &opts, NULL); err = evlist__open(evlist); if (err < 0) { diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index 132bdb3e6c31..7273823d0d02 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -142,6 +142,7 @@ static struct test generic_tests[] = { .skip_if_fail = false, .get_nr = test__wp_subtest_get_nr, .get_desc = test__wp_subtest_get_desc, + .skip_reason = test__wp_subtest_skip_reason, }, }, { @@ -350,6 +351,11 @@ static struct test generic_tests[] = { .func = test__expand_cgroup_events, }, { + .desc = "Convert perf time to TSC", + .func = test__perf_time_to_tsc, + .is_supported = test__tsc_is_supported, + }, + { .func = NULL, }, }; diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index 035c9123549a..7c098d49c77e 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -378,8 +378,8 @@ static int process_sample_event(struct machine *machine, struct thread *thread; int ret; - if (perf_evlist__parse_sample(evlist, event, &sample)) { - pr_debug("perf_evlist__parse_sample failed\n"); + if (evlist__parse_sample(evlist, event, &sample)) { + pr_debug("evlist__parse_sample failed\n"); return -1; } @@ -637,7 +637,7 @@ static int do_test_code_reading(bool try_kcore) evlist = evlist__new(); if (!evlist) { - pr_debug("perf_evlist__new failed\n"); + pr_debug("evlist__new failed\n"); goto out_put; } @@ -651,7 +651,7 @@ static int do_test_code_reading(bool try_kcore) goto out_put; } - perf_evlist__config(evlist, &opts, NULL); + evlist__config(evlist, &opts, NULL); evsel = evlist__first(evlist); diff --git a/tools/perf/tests/event-times.c b/tools/perf/tests/event-times.c index db68894a6f40..04ce4401f775 100644 --- a/tools/perf/tests/event-times.c +++ b/tools/perf/tests/event-times.c @@ -26,13 +26,13 @@ static int attach__enable_on_exec(struct evlist *evlist) pr_debug("attaching to spawned child, enable on exec\n"); - err = perf_evlist__create_maps(evlist, &target); + err = evlist__create_maps(evlist, &target); if (err < 0) { pr_debug("Not enough memory to create thread/cpu maps\n"); return err; } - err = perf_evlist__prepare_workload(evlist, &target, argv, false, NULL); + err = evlist__prepare_workload(evlist, &target, argv, false, NULL); if (err < 0) { pr_debug("Couldn't run the workload!\n"); return err; @@ -47,7 +47,7 @@ static int attach__enable_on_exec(struct evlist *evlist) return err; } - return perf_evlist__start_workload(evlist) == 1 ? TEST_OK : TEST_FAIL; + return evlist__start_workload(evlist) == 1 ? TEST_OK : TEST_FAIL; } static int detach__enable_on_exec(struct evlist *evlist) diff --git a/tools/perf/tests/event_update.c b/tools/perf/tests/event_update.c index bdcf032f8516..656218179222 100644 --- a/tools/perf/tests/event_update.c +++ b/tools/perf/tests/event_update.c @@ -85,11 +85,10 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused, int test__event_update(struct test *test __maybe_unused, int subtest __maybe_unused) { - struct evlist *evlist; struct evsel *evsel; struct event_name tmp; + struct evlist *evlist = evlist__new_default(); - evlist = perf_evlist__new_default(); TEST_ASSERT_VAL("failed to get evlist", evlist); evsel = evlist__first(evlist); diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c index 0e224a0a55d9..f9e34bd26cf3 100644 --- a/tools/perf/tests/evsel-tp-sched.c +++ b/tools/perf/tests/evsel-tp-sched.c @@ -5,8 +5,7 @@ #include "tests.h" #include "debug.h" -static int perf_evsel__test_field(struct evsel *evsel, const char *name, - int size, bool should_be_signed) +static int evsel__test_field(struct evsel *evsel, const char *name, int size, bool should_be_signed) { struct tep_format_field *field = evsel__field(evsel, name); int is_signed; @@ -43,25 +42,25 @@ int test__perf_evsel__tp_sched_test(struct test *test __maybe_unused, int subtes return -1; } - if (perf_evsel__test_field(evsel, "prev_comm", 16, false)) + if (evsel__test_field(evsel, "prev_comm", 16, false)) ret = -1; - if (perf_evsel__test_field(evsel, "prev_pid", 4, true)) + if (evsel__test_field(evsel, "prev_pid", 4, true)) ret = -1; - if (perf_evsel__test_field(evsel, "prev_prio", 4, true)) + if (evsel__test_field(evsel, "prev_prio", 4, true)) ret = -1; - if (perf_evsel__test_field(evsel, "prev_state", sizeof(long), true)) + if (evsel__test_field(evsel, "prev_state", sizeof(long), true)) ret = -1; - if (perf_evsel__test_field(evsel, "next_comm", 16, false)) + if (evsel__test_field(evsel, "next_comm", 16, false)) ret = -1; - if (perf_evsel__test_field(evsel, "next_pid", 4, true)) + if (evsel__test_field(evsel, "next_pid", 4, true)) ret = -1; - if (perf_evsel__test_field(evsel, "next_prio", 4, true)) + if (evsel__test_field(evsel, "next_prio", 4, true)) ret = -1; evsel__delete(evsel); @@ -73,16 +72,16 @@ int test__perf_evsel__tp_sched_test(struct test *test __maybe_unused, int subtes return -1; } - if (perf_evsel__test_field(evsel, "comm", 16, false)) + if (evsel__test_field(evsel, "comm", 16, false)) ret = -1; - if (perf_evsel__test_field(evsel, "pid", 4, true)) + if (evsel__test_field(evsel, "pid", 4, true)) ret = -1; - if (perf_evsel__test_field(evsel, "prio", 4, true)) + if (evsel__test_field(evsel, "prio", 4, true)) ret = -1; - if (perf_evsel__test_field(evsel, "target_cpu", 4, true)) + if (evsel__test_field(evsel, "target_cpu", 4, true)) ret = -1; evsel__delete(evsel); diff --git a/tools/perf/tests/expand-cgroup.c b/tools/perf/tests/expand-cgroup.c index d5771e4d094f..0e46aeb843ce 100644 --- a/tools/perf/tests/expand-cgroup.c +++ b/tools/perf/tests/expand-cgroup.c @@ -26,7 +26,7 @@ static int test_expand_events(struct evlist *evlist, char **ev_name; struct evsel *evsel; - TEST_ASSERT_VAL("evlist is empty", !perf_evlist__empty(evlist)); + TEST_ASSERT_VAL("evlist is empty", !evlist__empty(evlist)); nr_events = evlist->core.nr_entries; ev_name = calloc(nr_events, sizeof(*ev_name)); @@ -100,10 +100,9 @@ out: for (i = 0; i < nr_events; i++) static int expand_default_events(void) { int ret; - struct evlist *evlist; struct rblist metric_events; + struct evlist *evlist = evlist__new_default(); - evlist = perf_evlist__new_default(); TEST_ASSERT_VAL("failed to get evlist", evlist); rblist__init(&metric_events); @@ -145,7 +144,7 @@ static int expand_libpfm_events(void) int ret; struct evlist *evlist; struct rblist metric_events; - const char event_str[] = "UNHALTED_CORE_CYCLES"; + const char event_str[] = "CYCLES"; struct option opt = { .value = &evlist, }; @@ -161,7 +160,7 @@ static int expand_libpfm_events(void) event_str, ret); goto out; } - if (perf_evlist__empty(evlist)) { + if (evlist__empty(evlist)) { pr_debug("libpfm was not enabled\n"); goto out; } diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c index 50a0c9fcde7d..e6f1b2a38e03 100644 --- a/tools/perf/tests/keep-tracking.c +++ b/tools/perf/tests/keep-tracking.c @@ -92,7 +92,7 @@ int test__keep_tracking(struct test *test __maybe_unused, int subtest __maybe_un CHECK__(parse_events(evlist, "dummy:u", NULL)); CHECK__(parse_events(evlist, "cycles:u", NULL)); - perf_evlist__config(evlist, &opts, NULL); + evlist__config(evlist, &opts, NULL); evsel = evlist__first(evlist); diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c index ae6cda81c209..98da8a8757ab 100644 --- a/tools/perf/tests/llvm.c +++ b/tools/perf/tests/llvm.c @@ -2,13 +2,13 @@ #include <stdio.h> #include <stdlib.h> #include <string.h> -#include <bpf/libbpf.h> -#include <util/llvm-utils.h> -#include "llvm.h" #include "tests.h" #include "debug.h" #ifdef HAVE_LIBBPF_SUPPORT +#include <bpf/libbpf.h> +#include <util/llvm-utils.h> +#include "llvm.h" static int test__bpf_parsing(void *obj_buf, size_t obj_buf_sz) { struct bpf_object *obj; @@ -19,14 +19,6 @@ static int test__bpf_parsing(void *obj_buf, size_t obj_buf_sz) bpf_object__close(obj); return TEST_OK; } -#else -static int test__bpf_parsing(void *obj_buf __maybe_unused, - size_t obj_buf_sz __maybe_unused) -{ - pr_debug("Skip bpf parsing\n"); - return TEST_OK; -} -#endif static struct { const char *source; @@ -170,3 +162,19 @@ const char *test__llvm_subtest_get_desc(int subtest) return bpf_source_table[subtest].desc; } +#else //HAVE_LIBBPF_SUPPORT +int test__llvm(struct test *test __maybe_unused, int subtest __maybe_unused) +{ + return TEST_SKIP; +} + +int test__llvm_subtest_get_nr(void) +{ + return 0; +} + +const char *test__llvm_subtest_get_desc(int subtest __maybe_unused) +{ + return NULL; +} +#endif // HAVE_LIBBPF_SUPPORT diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c index 7b0dbfc0e17d..57093aeacc6f 100644 --- a/tools/perf/tests/mmap-basic.c +++ b/tools/perf/tests/mmap-basic.c @@ -69,7 +69,7 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse evlist = evlist__new(); if (evlist == NULL) { - pr_debug("perf_evlist__new\n"); + pr_debug("evlist__new\n"); goto out_free_cpus; } @@ -126,14 +126,14 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse goto out_delete_evlist; } - err = perf_evlist__parse_sample(evlist, event, &sample); + err = evlist__parse_sample(evlist, event, &sample); if (err) { pr_err("Can't parse sample, err = %d\n", err); goto out_delete_evlist; } err = -1; - evsel = perf_evlist__id2evsel(evlist, sample.id); + evsel = evlist__id2evsel(evlist, sample.id); if (evsel == NULL) { pr_debug("event with id %" PRIu64 " doesn't map to an evsel\n", sample.id); diff --git a/tools/perf/tests/openat-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c index 1f5f5e79ae25..5e4af2f0f14a 100644 --- a/tools/perf/tests/openat-syscall-tp-fields.c +++ b/tools/perf/tests/openat-syscall-tp-fields.c @@ -42,7 +42,7 @@ int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest char sbuf[STRERR_BUFSIZE]; if (evlist == NULL) { - pr_debug("%s: perf_evlist__new\n", __func__); + pr_debug("%s: evlist__new\n", __func__); goto out; } @@ -54,9 +54,9 @@ int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest evlist__add(evlist, evsel); - err = perf_evlist__create_maps(evlist, &opts.target); + err = evlist__create_maps(evlist, &opts.target); if (err < 0) { - pr_debug("%s: perf_evlist__create_maps\n", __func__); + pr_debug("%s: evlist__create_maps\n", __func__); goto out_delete_evlist; } diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index 611512f22b34..a7f6661e6112 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -115,7 +115,7 @@ static int test__checkevent_symbolic_name_config(struct evlist *evlist) TEST_ASSERT_VAL("wrong config", PERF_COUNT_HW_CPU_CYCLES == evsel->core.attr.config); /* - * The period value gets configured within perf_evlist__config, + * The period value gets configured within evlist__config, * while this test executes only parse events method. */ TEST_ASSERT_VAL("wrong period", @@ -443,7 +443,7 @@ static int test__checkevent_pmu(struct evlist *evlist) TEST_ASSERT_VAL("wrong config1", 1 == evsel->core.attr.config1); TEST_ASSERT_VAL("wrong config2", 3 == evsel->core.attr.config2); /* - * The period value gets configured within perf_evlist__config, + * The period value gets configured within evlist__config, * while this test executes only parse events method. */ TEST_ASSERT_VAL("wrong period", 0 == evsel->core.attr.sample_period); @@ -520,8 +520,7 @@ static int test__checkevent_pmu_partial_time_callgraph(struct evlist *evlist) TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", 1 == evsel->core.attr.config); /* - * The period, time and callgraph value gets configured - * within perf_evlist__config, + * The period, time and callgraph value gets configured within evlist__config, * while this test executes only parse events method. */ TEST_ASSERT_VAL("wrong period", 0 == evsel->core.attr.sample_period); @@ -533,8 +532,7 @@ static int test__checkevent_pmu_partial_time_callgraph(struct evlist *evlist) TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type); TEST_ASSERT_VAL("wrong config", 2 == evsel->core.attr.config); /* - * The period, time and callgraph value gets configured - * within perf_evlist__config, + * The period, time and callgraph value gets configured within evlist__config, * while this test executes only parse events method. */ TEST_ASSERT_VAL("wrong period", 0 == evsel->core.attr.sample_period); diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c index 7c1bde01cb50..ce7be37f0d88 100644 --- a/tools/perf/tests/parse-metric.c +++ b/tools/perf/tests/parse-metric.c @@ -166,7 +166,7 @@ static int __compute_metric(const char *name, struct value *vals, if (err) goto out; - err = perf_evlist__alloc_stats(evlist, false); + err = evlist__alloc_stats(evlist, false); if (err) goto out; @@ -183,7 +183,7 @@ out: /* ... clenup. */ metricgroup__rblist_exit(&metric_events); runtime_stat__exit(&st); - perf_evlist__free_stats(evlist); + evlist__free_stats(evlist); perf_cpu_map__put(cpus); evlist__delete(evlist); return err; diff --git a/tools/perf/tests/parse-no-sample-id-all.c b/tools/perf/tests/parse-no-sample-id-all.c index adf3c9c4a416..471273676701 100644 --- a/tools/perf/tests/parse-no-sample-id-all.c +++ b/tools/perf/tests/parse-no-sample-id-all.c @@ -27,8 +27,8 @@ static int process_event(struct evlist **pevlist, union perf_event *event) if (!*pevlist) return -1; - if (perf_evlist__parse_sample(*pevlist, event, &sample)) { - pr_debug("perf_evlist__parse_sample failed\n"); + if (evlist__parse_sample(*pevlist, event, &sample)) { + pr_debug("evlist__parse_sample failed\n"); return -1; } diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c index 67d3f5aad016..0df471bf1590 100644 --- a/tools/perf/tests/perf-record.c +++ b/tools/perf/tests/perf-record.c @@ -53,7 +53,7 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus }; cpu_set_t cpu_mask; size_t cpu_mask_size = sizeof(cpu_mask); - struct evlist *evlist = perf_evlist__new_dummy(); + struct evlist *evlist = evlist__new_dummy(); struct evsel *evsel; struct perf_sample sample; const char *cmd = "sleep"; @@ -71,7 +71,7 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus char sbuf[STRERR_BUFSIZE]; if (evlist == NULL) /* Fallback for kernels lacking PERF_COUNT_SW_DUMMY */ - evlist = perf_evlist__new_default(); + evlist = evlist__new_default(); if (evlist == NULL) { pr_debug("Not enough memory to create evlist\n"); @@ -81,10 +81,10 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus /* * Create maps of threads and cpus to monitor. In this case * we start with all threads and cpus (-1, -1) but then in - * perf_evlist__prepare_workload we'll fill in the only thread + * evlist__prepare_workload we'll fill in the only thread * we're monitoring, the one forked there. */ - err = perf_evlist__create_maps(evlist, &opts.target); + err = evlist__create_maps(evlist, &opts.target); if (err < 0) { pr_debug("Not enough memory to create thread/cpu maps\n"); goto out_delete_evlist; @@ -92,11 +92,11 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus /* * Prepare the workload in argv[] to run, it'll fork it, and then wait - * for perf_evlist__start_workload() to exec it. This is done this way + * for evlist__start_workload() to exec it. This is done this way * so that we have time to open the evlist (calling sys_perf_event_open * on all the fds) and then mmap them. */ - err = perf_evlist__prepare_workload(evlist, &opts.target, argv, false, NULL); + err = evlist__prepare_workload(evlist, &opts.target, argv, false, NULL); if (err < 0) { pr_debug("Couldn't run the workload!\n"); goto out_delete_evlist; @@ -109,7 +109,7 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus evsel__set_sample_bit(evsel, CPU); evsel__set_sample_bit(evsel, TID); evsel__set_sample_bit(evsel, TIME); - perf_evlist__config(evlist, &opts, NULL); + evlist__config(evlist, &opts, NULL); err = sched__get_first_possible_cpu(evlist->workload.pid, &cpu_mask); if (err < 0) { @@ -161,7 +161,7 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus /* * Now! */ - perf_evlist__start_workload(evlist); + evlist__start_workload(evlist); while (1) { int before = total_events; @@ -182,7 +182,7 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus if (type < PERF_RECORD_MAX) nr_events[type]++; - err = perf_evlist__parse_sample(evlist, event, &sample); + err = evlist__parse_sample(evlist, event, &sample); if (err < 0) { if (verbose > 0) perf_event__fprintf(event, NULL, stderr); diff --git a/tools/perf/arch/x86/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c index 026d32ed078e..7cff02664d0e 100644 --- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c +++ b/tools/perf/tests/perf-time-to-tsc.c @@ -18,10 +18,8 @@ #include "thread_map.h" #include "record.h" #include "tsc.h" -#include "util/mmap.h" -#include "tests/tests.h" - -#include "arch-tests.h" +#include "mmap.h" +#include "tests.h" #define CHECK__(x) { \ while ((x) < 0) { \ @@ -82,7 +80,7 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe CHECK__(parse_events(evlist, "cycles:u", NULL)); - perf_evlist__config(evlist, &opts, NULL); + evlist__config(evlist, &opts, NULL); evsel = evlist__first(evlist); @@ -171,3 +169,16 @@ out_err: evlist__delete(evlist); return err; } + +bool test__tsc_is_supported(void) +{ + /* + * Except x86_64/i386 and Arm64, other archs don't support TSC in perf. + * Just enable the test for x86_64/i386 and Arm64 archs. + */ +#if defined(__x86_64__) || defined(__i386__) || defined(__aarch64__) + return true; +#else + return false; +#endif +} diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c index d3517a74d95e..0ca6a5a53523 100644 --- a/tools/perf/tests/pmu-events.c +++ b/tools/perf/tests/pmu-events.c @@ -14,8 +14,10 @@ #include "util/parse-events.h" struct perf_pmu_test_event { + /* used for matching against events from generated pmu-events.c */ struct pmu_event event; + /* used for matching against event aliases */ /* extra events for aliases */ const char *alias_str; @@ -78,6 +80,17 @@ static struct perf_pmu_test_event test_cpu_events[] = { .alias_str = "umask=0,(null)=0x30d40,event=0x3a", .alias_long_desc = "Number of Enhanced Intel SpeedStep(R) Technology (EIST) transitions", }, + { + .event = { + .name = "l3_cache_rd", + .event = "event=0x40", + .desc = "L3 cache access, read", + .long_desc = "Attributable Level 3 cache access, read", + .topic = "cache", + }, + .alias_str = "event=0x40", + .alias_long_desc = "Attributable Level 3 cache access, read", + }, { /* sentinel */ .event = { .name = NULL, @@ -357,6 +370,7 @@ static int __test__pmu_event_aliases(char *pmu_name, int *count) } +/* Test that aliases generated are as expected */ static int test_aliases(void) { struct perf_pmu *pmu = NULL; @@ -561,7 +575,7 @@ static int metric_parse_fake(const char *str) } } - if (expr__parse(&result, &ctx, str, 1)) + if (expr__parse(&result, &ctx, str, 0)) pr_err("expr__parse failed\n"); else ret = 0; diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c index a0bdaf390ac8..2393916f6128 100644 --- a/tools/perf/tests/sample-parsing.c +++ b/tools/perf/tests/sample-parsing.c @@ -154,6 +154,9 @@ static bool samples_same(const struct perf_sample *s1, if (type & PERF_SAMPLE_CGROUP) COMP(cgroup); + if (type & PERF_SAMPLE_DATA_PAGE_SIZE) + COMP(data_page_size); + if (type & PERF_SAMPLE_AUX) { COMP(aux_sample.size); if (memcmp(s1->aux_sample.data, s2->aux_sample.data, @@ -234,6 +237,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format) }, .phys_addr = 113, .cgroup = 114, + .data_page_size = 115, .aux_sample = { .size = sizeof(aux_data), .data = (void *)aux_data, @@ -340,7 +344,7 @@ int test__sample_parsing(struct test *test __maybe_unused, int subtest __maybe_u * were added. Please actually update the test rather than just change * the condition below. */ - if (PERF_SAMPLE_MAX > PERF_SAMPLE_CGROUP << 1) { + if (PERF_SAMPLE_MAX > PERF_SAMPLE_CODE_PAGE_SIZE << 1) { pr_debug("sample format has changed, some new PERF_SAMPLE_ bit was introduced - test needs updating\n"); return -1; } diff --git a/tools/perf/tests/shell/stat+shadow_stat.sh b/tools/perf/tests/shell/stat+shadow_stat.sh new file mode 100755 index 000000000000..249dfe48cf6a --- /dev/null +++ b/tools/perf/tests/shell/stat+shadow_stat.sh @@ -0,0 +1,80 @@ +#!/bin/sh +# perf stat metrics (shadow stat) test +# SPDX-License-Identifier: GPL-2.0 + +set -e + +# skip if system-wide mode is forbidden +perf stat -a true > /dev/null 2>&1 || exit 2 + +test_global_aggr() +{ + local cyc + + perf stat -a --no-big-num -e cycles,instructions sleep 1 2>&1 | \ + grep -e cycles -e instructions | \ + while read num evt hash ipc rest + do + # skip not counted events + if [[ $num == "<not" ]]; then + continue + fi + + # save cycles count + if [[ $evt == "cycles" ]]; then + cyc=$num + continue + fi + + # skip if no cycles + if [[ -z $cyc ]]; then + continue + fi + + # use printf for rounding and a leading zero + local res=`printf "%.2f" $(echo "scale=6; $num / $cyc" | bc -q)` + if [[ $ipc != $res ]]; then + echo "IPC is different: $res != $ipc ($num / $cyc)" + exit 1 + fi + done +} + +test_no_aggr() +{ + declare -A results + + perf stat -a -A --no-big-num -e cycles,instructions sleep 1 2>&1 | \ + grep ^CPU | \ + while read cpu num evt hash ipc rest + do + # skip not counted events + if [[ $num == "<not" ]]; then + continue + fi + + # save cycles count + if [[ $evt == "cycles" ]]; then + results[$cpu]=$num + continue + fi + + # skip if no cycles + local cyc=${results[$cpu]} + if [[ -z $cyc ]]; then + continue + fi + + # use printf for rounding and a leading zero + local res=`printf "%.2f" $(echo "scale=6; $num / $cyc" | bc -q)` + if [[ $ipc != $res ]]; then + echo "IPC is different for $cpu: $res != $ipc ($num / $cyc)" + exit 1 + fi + done +} + +test_global_aggr +test_no_aggr + +exit 0 diff --git a/tools/perf/tests/shell/trace+probe_vfs_getname.sh b/tools/perf/tests/shell/trace+probe_vfs_getname.sh index 11cc2af13f2b..3d31c1d560d6 100755 --- a/tools/perf/tests/shell/trace+probe_vfs_getname.sh +++ b/tools/perf/tests/shell/trace+probe_vfs_getname.sh @@ -20,7 +20,7 @@ skip_if_no_perf_trace || exit 2 file=$(mktemp /tmp/temporary_file.XXXXX) trace_open_vfs_getname() { - evts=$(echo $(perf list syscalls:sys_enter_open* 2>&1 | egrep 'open(at)? ' | sed -r 's/.*sys_enter_([a-z]+) +\[.*$/\1/') | sed 's/ /,/') + evts=$(echo $(perf list syscalls:sys_enter_open* 2>/dev/null | egrep 'open(at)? ' | sed -r 's/.*sys_enter_([a-z]+) +\[.*$/\1/') | sed 's/ /,/') perf trace -e $evts touch $file 2>&1 | \ egrep " +[0-9]+\.[0-9]+ +\( +[0-9]+\.[0-9]+ ms\): +touch\/[0-9]+ open(at)?\((dfd: +CWD, +)?filename: +${file}, +flags: CREAT\|NOCTTY\|NONBLOCK\|WRONLY, +mode: +IRUGO\|IWUGO\) += +[0-9]+$" } diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c index 4b9b731977c8..a49c9e23053b 100644 --- a/tools/perf/tests/sw-clock.c +++ b/tools/perf/tests/sw-clock.c @@ -109,7 +109,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id) if (event->header.type != PERF_RECORD_SAMPLE) goto next_event; - err = perf_evlist__parse_sample(evlist, event, &sample); + err = evlist__parse_sample(evlist, event, &sample); if (err < 0) { pr_debug("Error during parse sample\n"); goto out_delete_evlist; diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c index db5e1f70053a..15a2ab765d89 100644 --- a/tools/perf/tests/switch-tracking.c +++ b/tools/perf/tests/switch-tracking.c @@ -128,12 +128,12 @@ static int process_sample_event(struct evlist *evlist, pid_t next_tid, prev_tid; int cpu, err; - if (perf_evlist__parse_sample(evlist, event, &sample)) { - pr_debug("perf_evlist__parse_sample failed\n"); + if (evlist__parse_sample(evlist, event, &sample)) { + pr_debug("evlist__parse_sample failed\n"); return -1; } - evsel = perf_evlist__id2evsel(evlist, sample.id); + evsel = evlist__id2evsel(evlist, sample.id); if (evsel == switch_tracking->switch_evsel) { next_tid = evsel__intval(evsel, &sample, "next_pid"); prev_tid = evsel__intval(evsel, &sample, "prev_pid"); @@ -223,8 +223,8 @@ static int add_event(struct evlist *evlist, struct list_head *events, node->event = event; list_add(&node->list, events); - if (perf_evlist__parse_sample(evlist, event, &sample)) { - pr_debug("perf_evlist__parse_sample failed\n"); + if (evlist__parse_sample(evlist, event, &sample)) { + pr_debug("evlist__parse_sample failed\n"); return -1; } @@ -380,7 +380,7 @@ int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_ cycles_evsel = evlist__last(evlist); /* Third event */ - if (!perf_evlist__can_select_event(evlist, sched_switch)) { + if (!evlist__can_select_event(evlist, sched_switch)) { pr_debug("No sched_switch\n"); err = 0; goto out; @@ -406,7 +406,7 @@ int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_ pr_debug("cycles event already at front"); goto out_err; } - perf_evlist__to_front(evlist, cycles_evsel); + evlist__to_front(evlist, cycles_evsel); if (cycles_evsel != evlist__first(evlist)) { pr_debug("Failed to move cycles event to front"); goto out_err; @@ -424,7 +424,7 @@ int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_ tracking_evsel = evlist__last(evlist); - perf_evlist__set_tracking_event(evlist, tracking_evsel); + evlist__set_tracking_event(evlist, tracking_evsel); tracking_evsel->core.attr.freq = 0; tracking_evsel->core.attr.sample_period = 1; @@ -432,7 +432,7 @@ int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_ evsel__set_sample_bit(tracking_evsel, TIME); /* Config events */ - perf_evlist__config(evlist, &opts, NULL); + evlist__config(evlist, &opts, NULL); /* Check moved event is still at the front */ if (cycles_evsel != evlist__first(evlist)) { diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c index adaff9044331..bbf94e4aa145 100644 --- a/tools/perf/tests/task-exit.c +++ b/tools/perf/tests/task-exit.c @@ -23,7 +23,7 @@ static void sig_handler(int sig __maybe_unused) } /* - * perf_evlist__prepare_workload will send a SIGUSR1 if the fork fails, since + * evlist__prepare_workload will send a SIGUSR1 if the fork fails, since * we asked by setting its exec_error to this handler. */ static void workload_exec_failed_signal(int signo __maybe_unused, @@ -58,16 +58,16 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused signal(SIGCHLD, sig_handler); - evlist = perf_evlist__new_default(); + evlist = evlist__new_default(); if (evlist == NULL) { - pr_debug("perf_evlist__new_default\n"); + pr_debug("evlist__new_default\n"); return -1; } /* * Create maps of threads and cpus to monitor. In this case * we start with all threads and cpus (-1, -1) but then in - * perf_evlist__prepare_workload we'll fill in the only thread + * evlist__prepare_workload we'll fill in the only thread * we're monitoring, the one forked there. */ cpus = perf_cpu_map__dummy_new(); @@ -83,8 +83,7 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused cpus = NULL; threads = NULL; - err = perf_evlist__prepare_workload(evlist, &target, argv, false, - workload_exec_failed_signal); + err = evlist__prepare_workload(evlist, &target, argv, false, workload_exec_failed_signal); if (err < 0) { pr_debug("Couldn't run the workload!\n"); goto out_delete_evlist; @@ -116,7 +115,7 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused goto out_delete_evlist; } - perf_evlist__start_workload(evlist); + evlist__start_workload(evlist); retry: md = &evlist->mmap[0]; diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index c85a2c08e407..8e24a61fe4c2 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -66,6 +66,7 @@ int test__bp_signal_overflow(struct test *test, int subtest); int test__bp_accounting(struct test *test, int subtest); int test__wp(struct test *test, int subtest); const char *test__wp_subtest_get_desc(int subtest); +const char *test__wp_subtest_skip_reason(int subtest); int test__wp_subtest_get_nr(void); int test__task_exit(struct test *test, int subtest); int test__mem(struct test *test, int subtest); @@ -124,10 +125,12 @@ int test__pfm_subtest_get_nr(void); int test__parse_metric(struct test *test, int subtest); int test__pe_file_parsing(struct test *test, int subtest); int test__expand_cgroup_events(struct test *test, int subtest); +int test__perf_time_to_tsc(struct test *test, int subtest); bool test__bp_signal_is_supported(void); bool test__bp_account_is_supported(void); bool test__wp_is_supported(void); +bool test__tsc_is_supported(void); #if defined(__arm__) || defined(__aarch64__) #ifdef HAVE_DWARF_UNWIND_SUPPORT diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c index 22daf2bdf5fa..74748ed75b2c 100644 --- a/tools/perf/tests/topology.c +++ b/tools/perf/tests/topology.c @@ -40,7 +40,7 @@ static int session_write_header(char *path) session = perf_session__new(&data, false, NULL); TEST_ASSERT_VAL("can't get session", !IS_ERR(session)); - session->evlist = perf_evlist__new_default(); + session->evlist = evlist__new_default(); TEST_ASSERT_VAL("can't get evlist", session->evlist); perf_header__set_feat(&session->header, HEADER_CPU_TOPOLOGY); @@ -65,9 +65,11 @@ static int check_cpu_topology(char *path, struct perf_cpu_map *map) .mode = PERF_DATA_MODE_READ, }; int i; + struct aggr_cpu_id id; session = perf_session__new(&data, false, NULL); TEST_ASSERT_VAL("can't get session", !IS_ERR(session)); + cpu__setup_cpunode_map(); /* On platforms with large numbers of CPUs process_cpu_topology() * might issue an error while reading the perf.data file section @@ -85,11 +87,18 @@ static int check_cpu_topology(char *path, struct perf_cpu_map *map) * "socket_id number is too big. You may need to upgrade the * perf tool." * - * This is the reason why this test might be skipped. + * This is the reason why this test might be skipped. aarch64 and + * s390 always write this part of the header, even when the above + * condition is true (see do_core_id_test in header.c). So always + * run this test on those platforms. */ - if (!session->header.env.cpu) + if (!session->header.env.cpu + && strncmp(session->header.env.arch, "s390", 4) + && strncmp(session->header.env.arch, "aarch64", 7)) return TEST_SKIP; + TEST_ASSERT_VAL("Session header CPU map not set", session->header.env.cpu); + for (i = 0; i < session->header.env.nr_cpus_avail; i++) { if (!cpu_map__has(map, i)) continue; @@ -98,14 +107,57 @@ static int check_cpu_topology(char *path, struct perf_cpu_map *map) session->header.env.cpu[i].socket_id); } + // Test that core ID contains socket, die and core + for (i = 0; i < map->nr; i++) { + id = cpu_map__get_core(map, i, NULL); + TEST_ASSERT_VAL("Core map - Core ID doesn't match", + session->header.env.cpu[map->map[i]].core_id == id.core); + + TEST_ASSERT_VAL("Core map - Socket ID doesn't match", + session->header.env.cpu[map->map[i]].socket_id == id.socket); + + TEST_ASSERT_VAL("Core map - Die ID doesn't match", + session->header.env.cpu[map->map[i]].die_id == id.die); + TEST_ASSERT_VAL("Core map - Node ID is set", id.node == -1); + TEST_ASSERT_VAL("Core map - Thread is set", id.thread == -1); + } + + // Test that die ID contains socket and die for (i = 0; i < map->nr; i++) { - TEST_ASSERT_VAL("Core ID doesn't match", - (session->header.env.cpu[map->map[i]].core_id == (cpu_map__get_core(map, i, NULL) & 0xffff))); + id = cpu_map__get_die(map, i, NULL); + TEST_ASSERT_VAL("Die map - Socket ID doesn't match", + session->header.env.cpu[map->map[i]].socket_id == id.socket); - TEST_ASSERT_VAL("Socket ID doesn't match", - (session->header.env.cpu[map->map[i]].socket_id == cpu_map__get_socket(map, i, NULL))); + TEST_ASSERT_VAL("Die map - Die ID doesn't match", + session->header.env.cpu[map->map[i]].die_id == id.die); + + TEST_ASSERT_VAL("Die map - Node ID is set", id.node == -1); + TEST_ASSERT_VAL("Die map - Core is set", id.core == -1); + TEST_ASSERT_VAL("Die map - Thread is set", id.thread == -1); + } + + // Test that socket ID contains only socket + for (i = 0; i < map->nr; i++) { + id = cpu_map__get_socket(map, i, NULL); + TEST_ASSERT_VAL("Socket map - Socket ID doesn't match", + session->header.env.cpu[map->map[i]].socket_id == id.socket); + + TEST_ASSERT_VAL("Socket map - Node ID is set", id.node == -1); + TEST_ASSERT_VAL("Socket map - Die ID is set", id.die == -1); + TEST_ASSERT_VAL("Socket map - Core is set", id.core == -1); + TEST_ASSERT_VAL("Socket map - Thread is set", id.thread == -1); } + // Test that node ID contains only node + for (i = 0; i < map->nr; i++) { + id = cpu_map__get_node(map, i, NULL); + TEST_ASSERT_VAL("Node map - Node ID doesn't match", + cpu__get_node(map->map[i]) == id.node); + TEST_ASSERT_VAL("Node map - Socket is set", id.socket == -1); + TEST_ASSERT_VAL("Node map - Die ID is set", id.die == -1); + TEST_ASSERT_VAL("Node map - Core is set", id.core == -1); + TEST_ASSERT_VAL("Node map - Thread is set", id.thread == -1); + } perf_session__delete(session); return 0; diff --git a/tools/perf/tests/wp.c b/tools/perf/tests/wp.c index d262d6639829..9387fa76faa5 100644 --- a/tools/perf/tests/wp.c +++ b/tools/perf/tests/wp.c @@ -174,10 +174,12 @@ static bool wp_ro_supported(void) #endif } -static void wp_ro_skip_msg(void) +static const char *wp_ro_skip_msg(void) { #if defined (__x86_64__) || defined (__i386__) - pr_debug("Hardware does not support read only watchpoints.\n"); + return "missing hardware support"; +#else + return NULL; #endif } @@ -185,7 +187,7 @@ static struct { const char *desc; int (*target_func)(void); bool (*is_supported)(void); - void (*skip_msg)(void); + const char *(*skip_msg)(void); } wp_testcase_table[] = { { .desc = "Read Only Watchpoint", @@ -219,16 +221,23 @@ const char *test__wp_subtest_get_desc(int i) return wp_testcase_table[i].desc; } +const char *test__wp_subtest_skip_reason(int i) +{ + if (i < 0 || i >= (int)ARRAY_SIZE(wp_testcase_table)) + return NULL; + if (!wp_testcase_table[i].skip_msg) + return NULL; + return wp_testcase_table[i].skip_msg(); +} + int test__wp(struct test *test __maybe_unused, int i) { if (i < 0 || i >= (int)ARRAY_SIZE(wp_testcase_table)) return TEST_FAIL; if (wp_testcase_table[i].is_supported && - !wp_testcase_table[i].is_supported()) { - wp_testcase_table[i].skip_msg(); + !wp_testcase_table[i].is_supported()) return TEST_SKIP; - } return !wp_testcase_table[i].target_func() ? TEST_OK : TEST_FAIL; } diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h index e9cb30d8cbfb..385894b4a8bb 100644 --- a/tools/perf/trace/beauty/include/linux/socket.h +++ b/tools/perf/trace/beauty/include/linux/socket.h @@ -436,6 +436,7 @@ extern int __sys_getpeername(int fd, struct sockaddr __user *usockaddr, int __user *usockaddr_len); extern int __sys_socketpair(int family, int type, int protocol, int __user *usockvec); +extern int __sys_shutdown_sock(struct socket *sock, int how); extern int __sys_shutdown(int fd, int how); extern struct ns_common *get_net_ns(struct ns_common *ns); diff --git a/tools/perf/trace/beauty/mmap_flags.sh b/tools/perf/trace/beauty/mmap_flags.sh index 39eb2595983b..76825710c725 100755 --- a/tools/perf/trace/beauty/mmap_flags.sh +++ b/tools/perf/trace/beauty/mmap_flags.sh @@ -28,12 +28,12 @@ egrep -q $regex ${linux_mman} && \ egrep -vw 'MAP_(UNINITIALIZED|TYPE|SHARED_VALIDATE)' | \ sed -r "s/$regex/\2 \1 \1 \1 \2/g" | \ xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n#ifndef MAP_%s\n#define MAP_%s %s\n#endif\n") -([ ! -f ${arch_mman} ] || egrep -q '#[[:space:]]*include[[:space:]]+<uapi/asm-generic/mman.*' ${arch_mman}) && +([ ! -f ${arch_mman} ] || egrep -q '#[[:space:]]*include[[:space:]]+.*uapi/asm-generic/mman.*' ${arch_mman}) && (egrep $regex ${header_dir}/mman-common.h | \ egrep -vw 'MAP_(UNINITIALIZED|TYPE|SHARED_VALIDATE)' | \ sed -r "s/$regex/\2 \1 \1 \1 \2/g" | \ xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n#ifndef MAP_%s\n#define MAP_%s %s\n#endif\n") -([ ! -f ${arch_mman} ] || egrep -q '#[[:space:]]*include[[:space:]]+<uapi/asm-generic/mman.h>.*' ${arch_mman}) && +([ ! -f ${arch_mman} ] || egrep -q '#[[:space:]]*include[[:space:]]+.*uapi/asm-generic/mman.h>.*' ${arch_mman}) && (egrep $regex ${header_dir}/mman.h | \ sed -r "s/$regex/\2 \1 \1 \1 \2/g" | \ xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n#ifndef MAP_%s\n#define MAP_%s %s\n#endif\n") diff --git a/tools/perf/trace/beauty/mmap_prot.sh b/tools/perf/trace/beauty/mmap_prot.sh index 28f638f8d216..664d8d534a50 100755 --- a/tools/perf/trace/beauty/mmap_prot.sh +++ b/tools/perf/trace/beauty/mmap_prot.sh @@ -17,7 +17,7 @@ prefix="PROT" printf "static const char *mmap_prot[] = {\n" regex=`printf '^[[:space:]]*#[[:space:]]*define[[:space:]]+%s_([[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*.*' ${prefix}` -([ ! -f ${arch_mman} ] || egrep -q '#[[:space:]]*include[[:space:]]+<uapi/asm-generic/mman.*' ${arch_mman}) && +([ ! -f ${arch_mman} ] || egrep -q '#[[:space:]]*include[[:space:]]+.*uapi/asm-generic/mman.*' ${arch_mman}) && (egrep $regex ${common_mman} | \ egrep -vw PROT_NONE | \ sed -r "s/$regex/\2 \1 \1 \1 \2/g" | \ diff --git a/tools/perf/trace/beauty/tracepoints/x86_msr.sh b/tools/perf/trace/beauty/tracepoints/x86_msr.sh index 831c02cf0586..27ee1ea1fe94 100755 --- a/tools/perf/trace/beauty/tracepoints/x86_msr.sh +++ b/tools/perf/trace/beauty/tracepoints/x86_msr.sh @@ -15,7 +15,7 @@ x86_msr_index=${arch_x86_header_dir}/msr-index.h printf "static const char *x86_MSRs[] = {\n" regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MSR_([[:alnum:]][[:alnum:]_]+)[[:space:]]+(0x00000[[:xdigit:]]+)[[:space:]]*.*' -egrep $regex ${x86_msr_index} | egrep -v 'MSR_(ATOM|P[46]|AMD64|IA32_TSCDEADLINE|IDT_FCR4)' | \ +egrep $regex ${x86_msr_index} | egrep -v 'MSR_(ATOM|P[46]|IA32_(TSCDEADLINE|UCODE_REV)|IDT_FCR4)' | \ sed -r "s/$regex/\2 \1/g" | sort -n | \ xargs printf "\t[%s] = \"%s\",\n" printf "};\n\n" diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index b0e1880cf992..3b9818ee9546 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -2946,14 +2946,10 @@ next: } } -static int perf_evsel__hists_browse(struct evsel *evsel, int nr_events, - const char *helpline, - bool left_exits, - struct hist_browser_timer *hbt, - float min_pcnt, - struct perf_env *env, - bool warn_lost_event, - struct annotation_options *annotation_opts) +static int evsel__hists_browse(struct evsel *evsel, int nr_events, const char *helpline, + bool left_exits, struct hist_browser_timer *hbt, float min_pcnt, + struct perf_env *env, bool warn_lost_event, + struct annotation_options *annotation_opts) { struct hists *hists = evsel__hists(evsel); struct hist_browser *browser = perf_evsel_browser__new(evsel, hbt, env, annotation_opts); @@ -3268,7 +3264,7 @@ do_hotkey: // key came straight from options ui__popup_menu() if (!is_report_browser(hbt)) { struct perf_top *top = hbt->arg; - perf_evlist__toggle_enable(top->evlist); + evlist__toggle_enable(top->evlist); /* * No need to refresh, resort/decay histogram * entries if we are not collecting samples: @@ -3498,19 +3494,17 @@ static int perf_evsel_menu__run(struct evsel_menu *menu, continue; pos = menu->selection; browse_hists: - perf_evlist__set_selected(evlist, pos); + evlist__set_selected(evlist, pos); /* * Give the calling tool a chance to populate the non * default evsel resorted hists tree. */ if (hbt) hbt->timer(hbt->arg); - key = perf_evsel__hists_browse(pos, nr_events, help, - true, hbt, - menu->min_pcnt, - menu->env, - warn_lost_event, - menu->annotation_opts); + key = evsel__hists_browse(pos, nr_events, help, true, hbt, + menu->min_pcnt, menu->env, + warn_lost_event, + menu->annotation_opts); ui_browser__show_title(&menu->b, title); switch (key) { case K_TAB: @@ -3565,13 +3559,9 @@ static bool filter_group_entries(struct ui_browser *browser __maybe_unused, return false; } -static int __perf_evlist__tui_browse_hists(struct evlist *evlist, - int nr_entries, const char *help, - struct hist_browser_timer *hbt, - float min_pcnt, - struct perf_env *env, - bool warn_lost_event, - struct annotation_options *annotation_opts) +static int __evlist__tui_browse_hists(struct evlist *evlist, int nr_entries, const char *help, + struct hist_browser_timer *hbt, float min_pcnt, struct perf_env *env, + bool warn_lost_event, struct annotation_options *annotation_opts) { struct evsel *pos; struct evsel_menu menu = { @@ -3603,7 +3593,7 @@ static int __perf_evlist__tui_browse_hists(struct evlist *evlist, hbt, warn_lost_event); } -static bool perf_evlist__single_entry(struct evlist *evlist) +static bool evlist__single_entry(struct evlist *evlist) { int nr_entries = evlist->core.nr_entries; @@ -3620,23 +3610,18 @@ static bool perf_evlist__single_entry(struct evlist *evlist) return false; } -int perf_evlist__tui_browse_hists(struct evlist *evlist, const char *help, - struct hist_browser_timer *hbt, - float min_pcnt, - struct perf_env *env, - bool warn_lost_event, - struct annotation_options *annotation_opts) +int evlist__tui_browse_hists(struct evlist *evlist, const char *help, struct hist_browser_timer *hbt, + float min_pcnt, struct perf_env *env, bool warn_lost_event, + struct annotation_options *annotation_opts) { int nr_entries = evlist->core.nr_entries; - if (perf_evlist__single_entry(evlist)) { + if (evlist__single_entry(evlist)) { single_entry: { struct evsel *first = evlist__first(evlist); - return perf_evsel__hists_browse(first, nr_entries, help, - false, hbt, min_pcnt, - env, warn_lost_event, - annotation_opts); + return evsel__hists_browse(first, nr_entries, help, false, hbt, min_pcnt, + env, warn_lost_event, annotation_opts); } } @@ -3653,10 +3638,8 @@ single_entry: { goto single_entry; } - return __perf_evlist__tui_browse_hists(evlist, nr_entries, help, - hbt, min_pcnt, env, - warn_lost_event, - annotation_opts); + return __evlist__tui_browse_hists(evlist, nr_entries, help, hbt, min_pcnt, env, + warn_lost_event, annotation_opts); } static int block_hists_browser__title(struct hist_browser *browser, char *bf, diff --git a/tools/perf/ui/gtk/gtk.h b/tools/perf/ui/gtk/gtk.h index a9563932fa04..a2b497f03fd6 100644 --- a/tools/perf/ui/gtk/gtk.h +++ b/tools/perf/ui/gtk/gtk.h @@ -57,9 +57,8 @@ struct evlist; struct hist_entry; struct hist_browser_timer; -int perf_evlist__gtk_browse_hists(struct evlist *evlist, const char *help, - struct hist_browser_timer *hbt, - float min_pcnt); +int evlist__gtk_browse_hists(struct evlist *evlist, const char *help, + struct hist_browser_timer *hbt, float min_pcnt); int hist_entry__gtk_annotate(struct hist_entry *he, struct evsel *evsel, struct hist_browser_timer *hbt); diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c index 53ef71a1b15d..c83be2d57f7e 100644 --- a/tools/perf/ui/gtk/hists.c +++ b/tools/perf/ui/gtk/hists.c @@ -590,10 +590,8 @@ static void perf_gtk__show_hierarchy(GtkWidget *window, struct hists *hists, gtk_container_add(GTK_CONTAINER(window), view); } -int perf_evlist__gtk_browse_hists(struct evlist *evlist, - const char *help, - struct hist_browser_timer *hbt __maybe_unused, - float min_pcnt) +int evlist__gtk_browse_hists(struct evlist *evlist, const char *help, + struct hist_browser_timer *hbt __maybe_unused, float min_pcnt) { struct evsel *pos; GtkWidget *vbox; diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 6c8575e182ed..ce8c07bc8c56 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -10,10 +10,6 @@ #include <inttypes.h> #include <libgen.h> #include <stdlib.h> -#include <bpf/bpf.h> -#include <bpf/btf.h> -#include <bpf/libbpf.h> -#include <linux/btf.h> #include "util.h" // hex_width() #include "ui/ui.h" #include "sort.h" @@ -152,6 +148,7 @@ static int arch__associate_ins_ops(struct arch* arch, const char *name, struct i #include "arch/arm/annotate/instructions.c" #include "arch/arm64/annotate/instructions.c" #include "arch/csky/annotate/instructions.c" +#include "arch/mips/annotate/instructions.c" #include "arch/x86/annotate/instructions.c" #include "arch/powerpc/annotate/instructions.c" #include "arch/s390/annotate/instructions.c" @@ -175,6 +172,13 @@ static struct arch architectures[] = { .init = csky__annotate_init, }, { + .name = "mips", + .init = mips__annotate_init, + .objdump = { + .comment_char = '#', + }, + }, + { .name = "x86", .init = x86__annotate_init, .instructions = x86__instructions, @@ -1676,6 +1680,10 @@ fallback: #define PACKAGE "perf" #include <bfd.h> #include <dis-asm.h> +#include <bpf/bpf.h> +#include <bpf/btf.h> +#include <bpf/libbpf.h> +#include <linux/btf.h> static int symbol__disassemble_bpf(struct symbol *sym, struct annotate_args *args) diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c index 93e063f22be5..90d575cee1b9 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c +++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c @@ -12,6 +12,7 @@ #include <string.h> #include <stdint.h> #include <stdlib.h> +#include <linux/bitops.h> #include <linux/compiler.h> #include <linux/zalloc.h> @@ -21,42 +22,51 @@ #include "arm-spe-decoder.h" -#ifndef BIT -#define BIT(n) (1UL << (n)) -#endif - static u64 arm_spe_calc_ip(int index, u64 payload) { - u8 *addr = (u8 *)&payload; - int ns, el; + u64 ns, el, val; /* Instruction virtual address or Branch target address */ if (index == SPE_ADDR_PKT_HDR_INDEX_INS || index == SPE_ADDR_PKT_HDR_INDEX_BRANCH) { - ns = addr[7] & SPE_ADDR_PKT_NS; - el = (addr[7] & SPE_ADDR_PKT_EL_MASK) >> SPE_ADDR_PKT_EL_OFFSET; + ns = SPE_ADDR_PKT_GET_NS(payload); + el = SPE_ADDR_PKT_GET_EL(payload); + + /* Clean highest byte */ + payload = SPE_ADDR_PKT_ADDR_GET_BYTES_0_6(payload); /* Fill highest byte for EL1 or EL2 (VHE) mode */ if (ns && (el == SPE_ADDR_PKT_EL1 || el == SPE_ADDR_PKT_EL2)) - addr[7] = 0xff; - /* Clean highest byte for other cases */ - else - addr[7] = 0x0; + payload |= 0xffULL << SPE_ADDR_PKT_ADDR_BYTE7_SHIFT; /* Data access virtual address */ } else if (index == SPE_ADDR_PKT_HDR_INDEX_DATA_VIRT) { - /* Fill highest byte if bits [48..55] is 0xff */ - if (addr[6] == 0xff) - addr[7] = 0xff; - /* Otherwise, cleanup tags */ - else - addr[7] = 0x0; + /* Clean tags */ + payload = SPE_ADDR_PKT_ADDR_GET_BYTES_0_6(payload); + + /* + * Armv8 ARM (ARM DDI 0487F.c), chapter "D10.2.1 Address packet" + * defines the data virtual address payload format, the top byte + * (bits [63:56]) is assigned as top-byte tag; so we only can + * retrieve address value from bits [55:0]. + * + * According to Documentation/arm64/memory.rst, if detects the + * specific pattern in bits [55:52] of payload which falls in + * the kernel space, should fixup the top byte and this allows + * perf tool to parse DSO symbol for data address correctly. + * + * For this reason, if detects the bits [55:52] is 0xf, will + * fill 0xff into the top byte. + */ + val = SPE_ADDR_PKT_ADDR_GET_BYTE_6(payload); + if ((val & 0xf0ULL) == 0xf0ULL) + payload |= 0xffULL << SPE_ADDR_PKT_ADDR_BYTE7_SHIFT; /* Data access physical address */ } else if (index == SPE_ADDR_PKT_HDR_INDEX_DATA_PHYS) { - /* Cleanup byte 7 */ - addr[7] = 0x0; + /* Clean highest byte */ + payload = SPE_ADDR_PKT_ADDR_GET_BYTES_0_6(payload); } else { pr_err("unsupported address packet index: 0x%x\n", index); } @@ -182,16 +192,13 @@ static int arm_spe_read_record(struct arm_spe_decoder *decoder) if (payload & BIT(EV_TLB_ACCESS)) decoder->record.type |= ARM_SPE_TLB_ACCESS; - if ((idx == 2 || idx == 4 || idx == 8) && - (payload & BIT(EV_LLC_MISS))) + if (payload & BIT(EV_LLC_MISS)) decoder->record.type |= ARM_SPE_LLC_MISS; - if ((idx == 2 || idx == 4 || idx == 8) && - (payload & BIT(EV_LLC_ACCESS))) + if (payload & BIT(EV_LLC_ACCESS)) decoder->record.type |= ARM_SPE_LLC_ACCESS; - if ((idx == 2 || idx == 4 || idx == 8) && - (payload & BIT(EV_REMOTE_ACCESS))) + if (payload & BIT(EV_REMOTE_ACCESS)) decoder->record.type |= ARM_SPE_REMOTE_ACCESS; if (payload & BIT(EV_MISPRED)) diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h index a5111a8d4360..24727b8ca7ff 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h +++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h @@ -13,23 +13,6 @@ #include "arm-spe-pkt-decoder.h" -enum arm_spe_events { - EV_EXCEPTION_GEN = 0, - EV_RETIRED = 1, - EV_L1D_ACCESS = 2, - EV_L1D_REFILL = 3, - EV_TLB_ACCESS = 4, - EV_TLB_WALK = 5, - EV_NOT_TAKEN = 6, - EV_MISPRED = 7, - EV_LLC_ACCESS = 8, - EV_LLC_MISS = 9, - EV_REMOTE_ACCESS = 10, - EV_ALIGNMENT = 11, - EV_PARTIAL_PREDICATE = 17, - EV_EMPTY_PREDICATE = 18, -}; - enum arm_spe_sample_type { ARM_SPE_L1D_ACCESS = 1 << 0, ARM_SPE_L1D_MISS = 1 << 1, diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c index b94001b756c7..f3ac9d40cebf 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c +++ b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c @@ -8,36 +8,11 @@ #include <string.h> #include <endian.h> #include <byteswap.h> +#include <linux/bitops.h> +#include <stdarg.h> #include "arm-spe-pkt-decoder.h" -#define BIT(n) (1ULL << (n)) - -#define NS_FLAG BIT(63) -#define EL_FLAG (BIT(62) | BIT(61)) - -#define SPE_HEADER0_PAD 0x0 -#define SPE_HEADER0_END 0x1 -#define SPE_HEADER0_ADDRESS 0x30 /* address packet (short) */ -#define SPE_HEADER0_ADDRESS_MASK 0x38 -#define SPE_HEADER0_COUNTER 0x18 /* counter packet (short) */ -#define SPE_HEADER0_COUNTER_MASK 0x38 -#define SPE_HEADER0_TIMESTAMP 0x71 -#define SPE_HEADER0_TIMESTAMP 0x71 -#define SPE_HEADER0_EVENTS 0x2 -#define SPE_HEADER0_EVENTS_MASK 0xf -#define SPE_HEADER0_SOURCE 0x3 -#define SPE_HEADER0_SOURCE_MASK 0xf -#define SPE_HEADER0_CONTEXT 0x24 -#define SPE_HEADER0_CONTEXT_MASK 0x3c -#define SPE_HEADER0_OP_TYPE 0x8 -#define SPE_HEADER0_OP_TYPE_MASK 0x3c -#define SPE_HEADER1_ALIGNMENT 0x0 -#define SPE_HEADER1_ADDRESS 0xb0 /* address packet (extended) */ -#define SPE_HEADER1_ADDRESS_MASK 0xf8 -#define SPE_HEADER1_COUNTER 0x98 /* counter packet (extended) */ -#define SPE_HEADER1_COUNTER_MASK 0xf8 - #if __BYTE_ORDER == __BIG_ENDIAN #define le16_to_cpu bswap_16 #define le32_to_cpu bswap_32 @@ -70,27 +45,28 @@ const char *arm_spe_pkt_name(enum arm_spe_pkt_type type) return arm_spe_packet_name[type]; } -/* return ARM SPE payload size from its encoding, - * which is in bits 5:4 of the byte. - * 00 : byte - * 01 : halfword (2) - * 10 : word (4) - * 11 : doubleword (8) +/* + * Extracts the field "sz" from header bits and converts to bytes: + * 00 : byte (1) + * 01 : halfword (2) + * 10 : word (4) + * 11 : doubleword (8) */ -static int payloadlen(unsigned char byte) +static unsigned int arm_spe_payload_len(unsigned char hdr) { - return 1 << ((byte & 0x30) >> 4); + return 1U << ((hdr & GENMASK_ULL(5, 4)) >> 4); } static int arm_spe_get_payload(const unsigned char *buf, size_t len, + unsigned char ext_hdr, struct arm_spe_pkt *packet) { - size_t payload_len = payloadlen(buf[0]); + size_t payload_len = arm_spe_payload_len(buf[ext_hdr]); - if (len < 1 + payload_len) + if (len < 1 + ext_hdr + payload_len) return ARM_SPE_NEED_MORE_BYTES; - buf++; + buf += 1 + ext_hdr; switch (payload_len) { case 1: packet->payload = *(uint8_t *)buf; break; @@ -100,7 +76,7 @@ static int arm_spe_get_payload(const unsigned char *buf, size_t len, default: return ARM_SPE_BAD_PACKET; } - return 1 + payload_len; + return 1 + ext_hdr + payload_len; } static int arm_spe_get_pad(struct arm_spe_pkt *packet) @@ -131,127 +107,128 @@ static int arm_spe_get_timestamp(const unsigned char *buf, size_t len, struct arm_spe_pkt *packet) { packet->type = ARM_SPE_TIMESTAMP; - return arm_spe_get_payload(buf, len, packet); + return arm_spe_get_payload(buf, len, 0, packet); } static int arm_spe_get_events(const unsigned char *buf, size_t len, struct arm_spe_pkt *packet) { - int ret = arm_spe_get_payload(buf, len, packet); - packet->type = ARM_SPE_EVENTS; /* we use index to identify Events with a less number of * comparisons in arm_spe_pkt_desc(): E.g., the LLC-ACCESS, - * LLC-REFILL, and REMOTE-ACCESS events are identified iff + * LLC-REFILL, and REMOTE-ACCESS events are identified if * index > 1. */ - packet->index = ret - 1; + packet->index = arm_spe_payload_len(buf[0]); - return ret; + return arm_spe_get_payload(buf, len, 0, packet); } static int arm_spe_get_data_source(const unsigned char *buf, size_t len, struct arm_spe_pkt *packet) { packet->type = ARM_SPE_DATA_SOURCE; - return arm_spe_get_payload(buf, len, packet); + return arm_spe_get_payload(buf, len, 0, packet); } static int arm_spe_get_context(const unsigned char *buf, size_t len, struct arm_spe_pkt *packet) { packet->type = ARM_SPE_CONTEXT; - packet->index = buf[0] & 0x3; - - return arm_spe_get_payload(buf, len, packet); + packet->index = SPE_CTX_PKT_HDR_INDEX(buf[0]); + return arm_spe_get_payload(buf, len, 0, packet); } static int arm_spe_get_op_type(const unsigned char *buf, size_t len, struct arm_spe_pkt *packet) { packet->type = ARM_SPE_OP_TYPE; - packet->index = buf[0] & 0x3; - return arm_spe_get_payload(buf, len, packet); + packet->index = SPE_OP_PKT_HDR_CLASS(buf[0]); + return arm_spe_get_payload(buf, len, 0, packet); } static int arm_spe_get_counter(const unsigned char *buf, size_t len, const unsigned char ext_hdr, struct arm_spe_pkt *packet) { - if (len < 2) - return ARM_SPE_NEED_MORE_BYTES; - packet->type = ARM_SPE_COUNTER; + if (ext_hdr) - packet->index = ((buf[0] & 0x3) << 3) | (buf[1] & 0x7); + packet->index = SPE_HDR_EXTENDED_INDEX(buf[0], buf[1]); else - packet->index = buf[0] & 0x7; - - packet->payload = le16_to_cpu(*(uint16_t *)(buf + 1)); + packet->index = SPE_HDR_SHORT_INDEX(buf[0]); - return 1 + ext_hdr + 2; + return arm_spe_get_payload(buf, len, ext_hdr, packet); } static int arm_spe_get_addr(const unsigned char *buf, size_t len, const unsigned char ext_hdr, struct arm_spe_pkt *packet) { - if (len < 8) - return ARM_SPE_NEED_MORE_BYTES; - packet->type = ARM_SPE_ADDRESS; + if (ext_hdr) - packet->index = ((buf[0] & 0x3) << 3) | (buf[1] & 0x7); + packet->index = SPE_HDR_EXTENDED_INDEX(buf[0], buf[1]); else - packet->index = buf[0] & 0x7; - - memcpy_le64(&packet->payload, buf + 1, 8); + packet->index = SPE_HDR_SHORT_INDEX(buf[0]); - return 1 + ext_hdr + 8; + return arm_spe_get_payload(buf, len, ext_hdr, packet); } static int arm_spe_do_get_packet(const unsigned char *buf, size_t len, struct arm_spe_pkt *packet) { - unsigned int byte; + unsigned int hdr; + unsigned char ext_hdr = 0; memset(packet, 0, sizeof(struct arm_spe_pkt)); if (!len) return ARM_SPE_NEED_MORE_BYTES; - byte = buf[0]; - if (byte == SPE_HEADER0_PAD) + hdr = buf[0]; + + if (hdr == SPE_HEADER0_PAD) return arm_spe_get_pad(packet); - else if (byte == SPE_HEADER0_END) /* no timestamp at end of record */ + + if (hdr == SPE_HEADER0_END) /* no timestamp at end of record */ return arm_spe_get_end(packet); - else if (byte & 0xc0 /* 0y11xxxxxx */) { - if (byte & 0x80) { - if ((byte & SPE_HEADER0_ADDRESS_MASK) == SPE_HEADER0_ADDRESS) - return arm_spe_get_addr(buf, len, 0, packet); - if ((byte & SPE_HEADER0_COUNTER_MASK) == SPE_HEADER0_COUNTER) - return arm_spe_get_counter(buf, len, 0, packet); - } else - if (byte == SPE_HEADER0_TIMESTAMP) - return arm_spe_get_timestamp(buf, len, packet); - else if ((byte & SPE_HEADER0_EVENTS_MASK) == SPE_HEADER0_EVENTS) - return arm_spe_get_events(buf, len, packet); - else if ((byte & SPE_HEADER0_SOURCE_MASK) == SPE_HEADER0_SOURCE) - return arm_spe_get_data_source(buf, len, packet); - else if ((byte & SPE_HEADER0_CONTEXT_MASK) == SPE_HEADER0_CONTEXT) - return arm_spe_get_context(buf, len, packet); - else if ((byte & SPE_HEADER0_OP_TYPE_MASK) == SPE_HEADER0_OP_TYPE) - return arm_spe_get_op_type(buf, len, packet); - } else if ((byte & 0xe0) == 0x20 /* 0y001xxxxx */) { - /* 16-bit header */ - byte = buf[1]; - if (byte == SPE_HEADER1_ALIGNMENT) + + if (hdr == SPE_HEADER0_TIMESTAMP) + return arm_spe_get_timestamp(buf, len, packet); + + if ((hdr & SPE_HEADER0_MASK1) == SPE_HEADER0_EVENTS) + return arm_spe_get_events(buf, len, packet); + + if ((hdr & SPE_HEADER0_MASK1) == SPE_HEADER0_SOURCE) + return arm_spe_get_data_source(buf, len, packet); + + if ((hdr & SPE_HEADER0_MASK2) == SPE_HEADER0_CONTEXT) + return arm_spe_get_context(buf, len, packet); + + if ((hdr & SPE_HEADER0_MASK2) == SPE_HEADER0_OP_TYPE) + return arm_spe_get_op_type(buf, len, packet); + + if ((hdr & SPE_HEADER0_MASK2) == SPE_HEADER0_EXTENDED) { + /* 16-bit extended format header */ + ext_hdr = 1; + + hdr = buf[1]; + if (hdr == SPE_HEADER1_ALIGNMENT) return arm_spe_get_alignment(buf, len, packet); - else if ((byte & SPE_HEADER1_ADDRESS_MASK) == SPE_HEADER1_ADDRESS) - return arm_spe_get_addr(buf, len, 1, packet); - else if ((byte & SPE_HEADER1_COUNTER_MASK) == SPE_HEADER1_COUNTER) - return arm_spe_get_counter(buf, len, 1, packet); } + /* + * The short format header's byte 0 or the extended format header's + * byte 1 has been assigned to 'hdr', which uses the same encoding for + * address packet and counter packet, so don't need to distinguish if + * it's short format or extended format and handle in once. + */ + if ((hdr & SPE_HEADER0_MASK3) == SPE_HEADER0_ADDRESS) + return arm_spe_get_addr(buf, len, ext_hdr, packet); + + if ((hdr & SPE_HEADER0_MASK3) == SPE_HEADER0_COUNTER) + return arm_spe_get_counter(buf, len, ext_hdr, packet); + return ARM_SPE_BAD_PACKET; } @@ -271,192 +248,286 @@ int arm_spe_get_packet(const unsigned char *buf, size_t len, return ret; } +static int arm_spe_pkt_out_string(int *err, char **buf_p, size_t *blen, + const char *fmt, ...) +{ + va_list ap; + int ret; + + /* Bail out if any error occurred */ + if (err && *err) + return *err; + + va_start(ap, fmt); + ret = vsnprintf(*buf_p, *blen, fmt, ap); + va_end(ap); + + if (ret < 0) { + if (err && !*err) + *err = ret; + + /* + * A return value of *blen or more means that the output was + * truncated and the buffer is overrun. + */ + } else if ((size_t)ret >= *blen) { + (*buf_p)[*blen - 1] = '\0'; + + /* + * Set *err to 'ret' to avoid overflow if tries to + * fill this buffer sequentially. + */ + if (err && !*err) + *err = ret; + } else { + *buf_p += ret; + *blen -= ret; + } + + return ret; +} + +static int arm_spe_pkt_desc_event(const struct arm_spe_pkt *packet, + char *buf, size_t buf_len) +{ + u64 payload = packet->payload; + int err = 0; + + arm_spe_pkt_out_string(&err, &buf, &buf_len, "EV"); + + if (payload & BIT(EV_EXCEPTION_GEN)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " EXCEPTION-GEN"); + if (payload & BIT(EV_RETIRED)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " RETIRED"); + if (payload & BIT(EV_L1D_ACCESS)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " L1D-ACCESS"); + if (payload & BIT(EV_L1D_REFILL)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " L1D-REFILL"); + if (payload & BIT(EV_TLB_ACCESS)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " TLB-ACCESS"); + if (payload & BIT(EV_TLB_WALK)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " TLB-REFILL"); + if (payload & BIT(EV_NOT_TAKEN)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " NOT-TAKEN"); + if (payload & BIT(EV_MISPRED)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " MISPRED"); + if (payload & BIT(EV_LLC_ACCESS)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " LLC-ACCESS"); + if (payload & BIT(EV_LLC_MISS)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " LLC-REFILL"); + if (payload & BIT(EV_REMOTE_ACCESS)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " REMOTE-ACCESS"); + if (payload & BIT(EV_ALIGNMENT)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " ALIGNMENT"); + if (payload & BIT(EV_PARTIAL_PREDICATE)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " SVE-PARTIAL-PRED"); + if (payload & BIT(EV_EMPTY_PREDICATE)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " SVE-EMPTY-PRED"); + + return err; +} + +static int arm_spe_pkt_desc_op_type(const struct arm_spe_pkt *packet, + char *buf, size_t buf_len) +{ + u64 payload = packet->payload; + int err = 0; + + switch (packet->index) { + case SPE_OP_PKT_HDR_CLASS_OTHER: + if (SPE_OP_PKT_IS_OTHER_SVE_OP(payload)) { + arm_spe_pkt_out_string(&err, &buf, &buf_len, "SVE-OTHER"); + + /* SVE effective vector length */ + arm_spe_pkt_out_string(&err, &buf, &buf_len, " EVLEN %d", + SPE_OP_PKG_SVE_EVL(payload)); + + if (payload & SPE_OP_PKT_SVE_FP) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " FP"); + if (payload & SPE_OP_PKT_SVE_PRED) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " PRED"); + } else { + arm_spe_pkt_out_string(&err, &buf, &buf_len, "OTHER"); + arm_spe_pkt_out_string(&err, &buf, &buf_len, " %s", + payload & SPE_OP_PKT_COND ? + "COND-SELECT" : "INSN-OTHER"); + } + break; + case SPE_OP_PKT_HDR_CLASS_LD_ST_ATOMIC: + arm_spe_pkt_out_string(&err, &buf, &buf_len, + payload & 0x1 ? "ST" : "LD"); + + if (SPE_OP_PKT_IS_LDST_ATOMIC(payload)) { + if (payload & SPE_OP_PKT_AT) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " AT"); + if (payload & SPE_OP_PKT_EXCL) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " EXCL"); + if (payload & SPE_OP_PKT_AR) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " AR"); + } + + switch (SPE_OP_PKT_LDST_SUBCLASS_GET(payload)) { + case SPE_OP_PKT_LDST_SUBCLASS_SIMD_FP: + arm_spe_pkt_out_string(&err, &buf, &buf_len, " SIMD-FP"); + break; + case SPE_OP_PKT_LDST_SUBCLASS_GP_REG: + arm_spe_pkt_out_string(&err, &buf, &buf_len, " GP-REG"); + break; + case SPE_OP_PKT_LDST_SUBCLASS_UNSPEC_REG: + arm_spe_pkt_out_string(&err, &buf, &buf_len, " UNSPEC-REG"); + break; + case SPE_OP_PKT_LDST_SUBCLASS_NV_SYSREG: + arm_spe_pkt_out_string(&err, &buf, &buf_len, " NV-SYSREG"); + break; + default: + break; + } + + if (SPE_OP_PKT_IS_LDST_SVE(payload)) { + /* SVE effective vector length */ + arm_spe_pkt_out_string(&err, &buf, &buf_len, " EVLEN %d", + SPE_OP_PKG_SVE_EVL(payload)); + + if (payload & SPE_OP_PKT_SVE_PRED) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " PRED"); + if (payload & SPE_OP_PKT_SVE_SG) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " SG"); + } + break; + case SPE_OP_PKT_HDR_CLASS_BR_ERET: + arm_spe_pkt_out_string(&err, &buf, &buf_len, "B"); + + if (payload & SPE_OP_PKT_COND) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " COND"); + + if (SPE_OP_PKT_IS_INDIRECT_BRANCH(payload)) + arm_spe_pkt_out_string(&err, &buf, &buf_len, " IND"); + + break; + default: + /* Unknown index */ + err = -1; + break; + } + + return err; +} + +static int arm_spe_pkt_desc_addr(const struct arm_spe_pkt *packet, + char *buf, size_t buf_len) +{ + int ns, el, idx = packet->index; + int ch, pat; + u64 payload = packet->payload; + int err = 0; + + switch (idx) { + case SPE_ADDR_PKT_HDR_INDEX_INS: + case SPE_ADDR_PKT_HDR_INDEX_BRANCH: + ns = !!SPE_ADDR_PKT_GET_NS(payload); + el = SPE_ADDR_PKT_GET_EL(payload); + payload = SPE_ADDR_PKT_ADDR_GET_BYTES_0_6(payload); + arm_spe_pkt_out_string(&err, &buf, &buf_len, + "%s 0x%llx el%d ns=%d", + (idx == 1) ? "TGT" : "PC", payload, el, ns); + break; + case SPE_ADDR_PKT_HDR_INDEX_DATA_VIRT: + arm_spe_pkt_out_string(&err, &buf, &buf_len, + "VA 0x%llx", payload); + break; + case SPE_ADDR_PKT_HDR_INDEX_DATA_PHYS: + ns = !!SPE_ADDR_PKT_GET_NS(payload); + ch = !!SPE_ADDR_PKT_GET_CH(payload); + pat = SPE_ADDR_PKT_GET_PAT(payload); + payload = SPE_ADDR_PKT_ADDR_GET_BYTES_0_6(payload); + arm_spe_pkt_out_string(&err, &buf, &buf_len, + "PA 0x%llx ns=%d ch=%d pat=%x", + payload, ns, ch, pat); + break; + default: + /* Unknown index */ + err = -1; + break; + } + + return err; +} + +static int arm_spe_pkt_desc_counter(const struct arm_spe_pkt *packet, + char *buf, size_t buf_len) +{ + u64 payload = packet->payload; + const char *name = arm_spe_pkt_name(packet->type); + int err = 0; + + arm_spe_pkt_out_string(&err, &buf, &buf_len, "%s %d ", name, + (unsigned short)payload); + + switch (packet->index) { + case SPE_CNT_PKT_HDR_INDEX_TOTAL_LAT: + arm_spe_pkt_out_string(&err, &buf, &buf_len, "TOT"); + break; + case SPE_CNT_PKT_HDR_INDEX_ISSUE_LAT: + arm_spe_pkt_out_string(&err, &buf, &buf_len, "ISSUE"); + break; + case SPE_CNT_PKT_HDR_INDEX_TRANS_LAT: + arm_spe_pkt_out_string(&err, &buf, &buf_len, "XLAT"); + break; + default: + break; + } + + return err; +} + int arm_spe_pkt_desc(const struct arm_spe_pkt *packet, char *buf, size_t buf_len) { - int ret, ns, el, idx = packet->index; + int idx = packet->index; unsigned long long payload = packet->payload; const char *name = arm_spe_pkt_name(packet->type); + char *buf_orig = buf; + size_t blen = buf_len; + int err = 0; switch (packet->type) { case ARM_SPE_BAD: case ARM_SPE_PAD: case ARM_SPE_END: - return snprintf(buf, buf_len, "%s", name); - case ARM_SPE_EVENTS: { - size_t blen = buf_len; - - ret = 0; - ret = snprintf(buf, buf_len, "EV"); - buf += ret; - blen -= ret; - if (payload & 0x1) { - ret = snprintf(buf, buf_len, " EXCEPTION-GEN"); - buf += ret; - blen -= ret; - } - if (payload & 0x2) { - ret = snprintf(buf, buf_len, " RETIRED"); - buf += ret; - blen -= ret; - } - if (payload & 0x4) { - ret = snprintf(buf, buf_len, " L1D-ACCESS"); - buf += ret; - blen -= ret; - } - if (payload & 0x8) { - ret = snprintf(buf, buf_len, " L1D-REFILL"); - buf += ret; - blen -= ret; - } - if (payload & 0x10) { - ret = snprintf(buf, buf_len, " TLB-ACCESS"); - buf += ret; - blen -= ret; - } - if (payload & 0x20) { - ret = snprintf(buf, buf_len, " TLB-REFILL"); - buf += ret; - blen -= ret; - } - if (payload & 0x40) { - ret = snprintf(buf, buf_len, " NOT-TAKEN"); - buf += ret; - blen -= ret; - } - if (payload & 0x80) { - ret = snprintf(buf, buf_len, " MISPRED"); - buf += ret; - blen -= ret; - } - if (idx > 1) { - if (payload & 0x100) { - ret = snprintf(buf, buf_len, " LLC-ACCESS"); - buf += ret; - blen -= ret; - } - if (payload & 0x200) { - ret = snprintf(buf, buf_len, " LLC-REFILL"); - buf += ret; - blen -= ret; - } - if (payload & 0x400) { - ret = snprintf(buf, buf_len, " REMOTE-ACCESS"); - buf += ret; - blen -= ret; - } - } - if (ret < 0) - return ret; - blen -= ret; - return buf_len - blen; - } + arm_spe_pkt_out_string(&err, &buf, &blen, "%s", name); + break; + case ARM_SPE_EVENTS: + err = arm_spe_pkt_desc_event(packet, buf, buf_len); + break; case ARM_SPE_OP_TYPE: - switch (idx) { - case 0: return snprintf(buf, buf_len, "%s", payload & 0x1 ? - "COND-SELECT" : "INSN-OTHER"); - case 1: { - size_t blen = buf_len; - - if (payload & 0x1) - ret = snprintf(buf, buf_len, "ST"); - else - ret = snprintf(buf, buf_len, "LD"); - buf += ret; - blen -= ret; - if (payload & 0x2) { - if (payload & 0x4) { - ret = snprintf(buf, buf_len, " AT"); - buf += ret; - blen -= ret; - } - if (payload & 0x8) { - ret = snprintf(buf, buf_len, " EXCL"); - buf += ret; - blen -= ret; - } - if (payload & 0x10) { - ret = snprintf(buf, buf_len, " AR"); - buf += ret; - blen -= ret; - } - } else if (payload & 0x4) { - ret = snprintf(buf, buf_len, " SIMD-FP"); - buf += ret; - blen -= ret; - } - if (ret < 0) - return ret; - blen -= ret; - return buf_len - blen; - } - case 2: { - size_t blen = buf_len; - - ret = snprintf(buf, buf_len, "B"); - buf += ret; - blen -= ret; - if (payload & 0x1) { - ret = snprintf(buf, buf_len, " COND"); - buf += ret; - blen -= ret; - } - if (payload & 0x2) { - ret = snprintf(buf, buf_len, " IND"); - buf += ret; - blen -= ret; - } - if (ret < 0) - return ret; - blen -= ret; - return buf_len - blen; - } - default: return 0; - } + err = arm_spe_pkt_desc_op_type(packet, buf, buf_len); + break; case ARM_SPE_DATA_SOURCE: case ARM_SPE_TIMESTAMP: - return snprintf(buf, buf_len, "%s %lld", name, payload); + arm_spe_pkt_out_string(&err, &buf, &blen, "%s %lld", name, payload); + break; case ARM_SPE_ADDRESS: - switch (idx) { - case 0: - case 1: ns = !!(packet->payload & NS_FLAG); - el = (packet->payload & EL_FLAG) >> 61; - payload &= ~(0xffULL << 56); - return snprintf(buf, buf_len, "%s 0x%llx el%d ns=%d", - (idx == 1) ? "TGT" : "PC", payload, el, ns); - case 2: return snprintf(buf, buf_len, "VA 0x%llx", payload); - case 3: ns = !!(packet->payload & NS_FLAG); - payload &= ~(0xffULL << 56); - return snprintf(buf, buf_len, "PA 0x%llx ns=%d", - payload, ns); - default: return 0; - } + err = arm_spe_pkt_desc_addr(packet, buf, buf_len); + break; case ARM_SPE_CONTEXT: - return snprintf(buf, buf_len, "%s 0x%lx el%d", name, - (unsigned long)payload, idx + 1); - case ARM_SPE_COUNTER: { - size_t blen = buf_len; - - ret = snprintf(buf, buf_len, "%s %d ", name, - (unsigned short)payload); - buf += ret; - blen -= ret; - switch (idx) { - case 0: ret = snprintf(buf, buf_len, "TOT"); break; - case 1: ret = snprintf(buf, buf_len, "ISSUE"); break; - case 2: ret = snprintf(buf, buf_len, "XLAT"); break; - default: ret = 0; - } - if (ret < 0) - return ret; - blen -= ret; - return buf_len - blen; - } + arm_spe_pkt_out_string(&err, &buf, &blen, "%s 0x%lx el%d", + name, (unsigned long)payload, idx + 1); + break; + case ARM_SPE_COUNTER: + err = arm_spe_pkt_desc_counter(packet, buf, buf_len); + break; default: + /* Unknown packet type */ + err = -1; break; } - return snprintf(buf, buf_len, "%s 0x%llx (%d)", - name, payload, packet->index); + /* Output raw data if detect any error */ + if (err) { + err = 0; + arm_spe_pkt_out_string(&err, &buf_orig, &buf_len, "%s 0x%llx (%d)", + name, payload, packet->index); + } + + return err; } diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.h b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.h index 4c870521b8eb..9b970e7bf1e2 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.h +++ b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.h @@ -36,19 +36,115 @@ struct arm_spe_pkt { uint64_t payload; }; -#define SPE_ADDR_PKT_HDR_INDEX_INS (0x0) -#define SPE_ADDR_PKT_HDR_INDEX_BRANCH (0x1) -#define SPE_ADDR_PKT_HDR_INDEX_DATA_VIRT (0x2) -#define SPE_ADDR_PKT_HDR_INDEX_DATA_PHYS (0x3) - -#define SPE_ADDR_PKT_NS BIT(7) -#define SPE_ADDR_PKT_CH BIT(6) -#define SPE_ADDR_PKT_EL_OFFSET (5) -#define SPE_ADDR_PKT_EL_MASK (0x3 << SPE_ADDR_PKT_EL_OFFSET) -#define SPE_ADDR_PKT_EL0 (0) -#define SPE_ADDR_PKT_EL1 (1) -#define SPE_ADDR_PKT_EL2 (2) -#define SPE_ADDR_PKT_EL3 (3) +/* Short header (HEADER0) and extended header (HEADER1) */ +#define SPE_HEADER0_PAD 0x0 +#define SPE_HEADER0_END 0x1 +#define SPE_HEADER0_TIMESTAMP 0x71 +/* Mask for event & data source */ +#define SPE_HEADER0_MASK1 (GENMASK_ULL(7, 6) | GENMASK_ULL(3, 0)) +#define SPE_HEADER0_EVENTS 0x42 +#define SPE_HEADER0_SOURCE 0x43 +/* Mask for context & operation */ +#define SPE_HEADER0_MASK2 GENMASK_ULL(7, 2) +#define SPE_HEADER0_CONTEXT 0x64 +#define SPE_HEADER0_OP_TYPE 0x48 +/* Mask for extended format */ +#define SPE_HEADER0_EXTENDED 0x20 +/* Mask for address & counter */ +#define SPE_HEADER0_MASK3 GENMASK_ULL(7, 3) +#define SPE_HEADER0_ADDRESS 0xb0 +#define SPE_HEADER0_COUNTER 0x98 +#define SPE_HEADER1_ALIGNMENT 0x0 + +#define SPE_HDR_SHORT_INDEX(h) ((h) & GENMASK_ULL(2, 0)) +#define SPE_HDR_EXTENDED_INDEX(h0, h1) (((h0) & GENMASK_ULL(1, 0)) << 3 | \ + SPE_HDR_SHORT_INDEX(h1)) + +/* Address packet header */ +#define SPE_ADDR_PKT_HDR_INDEX_INS 0x0 +#define SPE_ADDR_PKT_HDR_INDEX_BRANCH 0x1 +#define SPE_ADDR_PKT_HDR_INDEX_DATA_VIRT 0x2 +#define SPE_ADDR_PKT_HDR_INDEX_DATA_PHYS 0x3 + +/* Address packet payload */ +#define SPE_ADDR_PKT_ADDR_BYTE7_SHIFT 56 +#define SPE_ADDR_PKT_ADDR_GET_BYTES_0_6(v) ((v) & GENMASK_ULL(55, 0)) +#define SPE_ADDR_PKT_ADDR_GET_BYTE_6(v) (((v) & GENMASK_ULL(55, 48)) >> 48) + +#define SPE_ADDR_PKT_GET_NS(v) (((v) & BIT_ULL(63)) >> 63) +#define SPE_ADDR_PKT_GET_EL(v) (((v) & GENMASK_ULL(62, 61)) >> 61) +#define SPE_ADDR_PKT_GET_CH(v) (((v) & BIT_ULL(62)) >> 62) +#define SPE_ADDR_PKT_GET_PAT(v) (((v) & GENMASK_ULL(59, 56)) >> 56) + +#define SPE_ADDR_PKT_EL0 0 +#define SPE_ADDR_PKT_EL1 1 +#define SPE_ADDR_PKT_EL2 2 +#define SPE_ADDR_PKT_EL3 3 + +/* Context packet header */ +#define SPE_CTX_PKT_HDR_INDEX(h) ((h) & GENMASK_ULL(1, 0)) + +/* Counter packet header */ +#define SPE_CNT_PKT_HDR_INDEX_TOTAL_LAT 0x0 +#define SPE_CNT_PKT_HDR_INDEX_ISSUE_LAT 0x1 +#define SPE_CNT_PKT_HDR_INDEX_TRANS_LAT 0x2 + +/* Event packet payload */ +enum arm_spe_events { + EV_EXCEPTION_GEN = 0, + EV_RETIRED = 1, + EV_L1D_ACCESS = 2, + EV_L1D_REFILL = 3, + EV_TLB_ACCESS = 4, + EV_TLB_WALK = 5, + EV_NOT_TAKEN = 6, + EV_MISPRED = 7, + EV_LLC_ACCESS = 8, + EV_LLC_MISS = 9, + EV_REMOTE_ACCESS = 10, + EV_ALIGNMENT = 11, + EV_PARTIAL_PREDICATE = 17, + EV_EMPTY_PREDICATE = 18, +}; + +/* Operation packet header */ +#define SPE_OP_PKT_HDR_CLASS(h) ((h) & GENMASK_ULL(1, 0)) +#define SPE_OP_PKT_HDR_CLASS_OTHER 0x0 +#define SPE_OP_PKT_HDR_CLASS_LD_ST_ATOMIC 0x1 +#define SPE_OP_PKT_HDR_CLASS_BR_ERET 0x2 + +#define SPE_OP_PKT_IS_OTHER_SVE_OP(v) (((v) & (BIT(7) | BIT(3) | BIT(0))) == 0x8) + +#define SPE_OP_PKT_COND BIT(0) + +#define SPE_OP_PKT_LDST_SUBCLASS_GET(v) ((v) & GENMASK_ULL(7, 1)) +#define SPE_OP_PKT_LDST_SUBCLASS_GP_REG 0x0 +#define SPE_OP_PKT_LDST_SUBCLASS_SIMD_FP 0x4 +#define SPE_OP_PKT_LDST_SUBCLASS_UNSPEC_REG 0x10 +#define SPE_OP_PKT_LDST_SUBCLASS_NV_SYSREG 0x30 + +#define SPE_OP_PKT_IS_LDST_ATOMIC(v) (((v) & (GENMASK_ULL(7, 5) | BIT(1))) == 0x2) + +#define SPE_OP_PKT_AR BIT(4) +#define SPE_OP_PKT_EXCL BIT(3) +#define SPE_OP_PKT_AT BIT(2) +#define SPE_OP_PKT_ST BIT(0) + +#define SPE_OP_PKT_IS_LDST_SVE(v) (((v) & (BIT(3) | BIT(1))) == 0x8) + +#define SPE_OP_PKT_SVE_SG BIT(7) +/* + * SVE effective vector length (EVL) is stored in byte 0 bits [6:4]; + * the length is rounded up to a power of two and use 32 as one step, + * so EVL calculation is: + * + * 32 * (2 ^ bits [6:4]) = 32 << (bits [6:4]) + */ +#define SPE_OP_PKG_SVE_EVL(v) (32 << (((v) & GENMASK_ULL(6, 4)) >> 4)) +#define SPE_OP_PKT_SVE_PRED BIT(2) +#define SPE_OP_PKT_SVE_FP BIT(1) + +#define SPE_OP_PKT_IS_INDIRECT_BRANCH(v) (((v) & GENMASK_ULL(7, 1)) == 0x2) const char *arm_spe_pkt_name(enum arm_spe_pkt_type); diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c index 3882a5360ada..8901a1656a41 100644 --- a/tools/perf/util/arm-spe.c +++ b/tools/perf/util/arm-spe.c @@ -113,7 +113,7 @@ static void arm_spe_dump(struct arm_spe *spe __maybe_unused, if (ret > 0) { ret = arm_spe_pkt_desc(&packet, desc, ARM_SPE_PKT_DESC_MAX); - if (ret > 0) + if (!ret) color_fprintf(stdout, color, " %s\n", desc); } else { color_fprintf(stdout, color, " Bad packet!\n"); diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index 42a85c86421d..a60878498139 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -62,9 +62,7 @@ * Make a group from 'leader' to 'last', requiring that the events were not * already grouped to a different leader. */ -static int perf_evlist__regroup(struct evlist *evlist, - struct evsel *leader, - struct evsel *last) +static int evlist__regroup(struct evlist *evlist, struct evsel *leader, struct evsel *last) { struct evsel *evsel; bool grp; @@ -658,8 +656,7 @@ int auxtrace_record__read_finish(struct auxtrace_record *itr, int idx) if (evsel->core.attr.type == itr->pmu->type) { if (evsel->disabled) return 0; - return perf_evlist__enable_event_idx(itr->evlist, evsel, - idx); + return evlist__enable_event_idx(itr->evlist, evsel, idx); } } return -EINVAL; @@ -776,7 +773,7 @@ no_opt: evsel->core.attr.aux_sample_size = term->val.aux_sample_size; /* If possible, group with the AUX event */ if (aux_evsel && evsel->core.attr.aux_sample_size) - perf_evlist__regroup(evlist, aux_evsel, evsel); + evlist__regroup(evlist, aux_evsel, evsel); } } @@ -1017,7 +1014,7 @@ struct auxtrace_queue *auxtrace_queues__sample_queue(struct auxtrace_queues *que if (!id) return NULL; - sid = perf_evlist__id2sid(session->evlist, id); + sid = evlist__id2sid(session->evlist, id); if (!sid) return NULL; @@ -1047,7 +1044,7 @@ int auxtrace_queues__add_sample(struct auxtrace_queues *queues, if (!id) return -EINVAL; - sid = perf_evlist__id2sid(session->evlist, id); + sid = evlist__id2sid(session->evlist, id); if (!sid) return -ENOENT; @@ -1082,7 +1079,7 @@ static int auxtrace_queue_data_cb(struct perf_session *session, if (!qd->samples || event->header.type != PERF_RECORD_SAMPLE) return 0; - err = perf_evlist__parse_sample(session->evlist, event, &sample); + err = evlist__parse_sample(session->evlist, event, &sample); if (err) return err; @@ -1333,6 +1330,7 @@ void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts, synth_opts->flc = true; synth_opts->llc = true; synth_opts->tlb = true; + synth_opts->mem = true; synth_opts->remote_access = true; if (no_sample) { @@ -1554,6 +1552,9 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str, case 'a': synth_opts->remote_access = true; break; + case 'M': + synth_opts->mem = true; + break; case 'q': synth_opts->quick += 1; break; diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h index 951d2d14cf24..7e5c9e1552bd 100644 --- a/tools/perf/util/auxtrace.h +++ b/tools/perf/util/auxtrace.h @@ -88,6 +88,7 @@ enum itrace_period_type { * @llc: whether to synthesize last level cache events * @tlb: whether to synthesize TLB events * @remote_access: whether to synthesize remote access events + * @mem: whether to synthesize memory events * @callchain_sz: maximum callchain size * @last_branch_sz: branch context size * @period: 'instructions' events period @@ -126,6 +127,7 @@ struct itrace_synth_opts { bool llc; bool tlb; bool remote_access; + bool mem; unsigned int callchain_sz; unsigned int last_branch_sz; unsigned long long period; diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c index 3742511a08d1..57d58c81a5f8 100644 --- a/tools/perf/util/bpf-event.c +++ b/tools/perf/util/bpf-event.c @@ -526,7 +526,7 @@ int evlist__add_bpf_sb_event(struct evlist *evlist, struct perf_env *env) */ attr.wakeup_watermark = 1; - return perf_evlist__add_sb_event(evlist, &attr, bpf_event__sb_cb, env); + return evlist__add_sb_event(evlist, &attr, bpf_event__sb_cb, env); } void bpf_event__print_bpf_prog_info(struct bpf_prog_info *info, diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c index 0374adcb223c..9087f1bffd3d 100644 --- a/tools/perf/util/bpf-loader.c +++ b/tools/perf/util/bpf-loader.c @@ -1058,12 +1058,11 @@ __bpf_map__config_event(struct bpf_map *map, struct parse_events_term *term, struct evlist *evlist) { - struct evsel *evsel; const struct bpf_map_def *def; struct bpf_map_op *op; const char *map_name = bpf_map__name(map); + struct evsel *evsel = evlist__find_evsel_by_str(evlist, term->val.str); - evsel = perf_evlist__find_evsel_by_str(evlist, term->val.str); if (!evsel) { pr_debug("Event (for '%s') '%s' doesn't exist\n", map_name, term->val.str); diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h index 25251d63164c..5d1c725cea29 100644 --- a/tools/perf/util/bpf-loader.h +++ b/tools/perf/util/bpf-loader.h @@ -8,6 +8,8 @@ #include <linux/compiler.h> #include <linux/err.h> + +#ifdef HAVE_LIBBPF_SUPPORT #include <bpf/libbpf.h> enum bpf_loader_errno { @@ -38,6 +40,7 @@ enum bpf_loader_errno { BPF_LOADER_ERRNO__OBJCONF_MAP_IDX2BIG, /* Index too large */ __BPF_LOADER_ERRNO__END, }; +#endif // HAVE_LIBBPF_SUPPORT struct evsel; struct evlist; diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index 6b410c3d52dc..02df36b30ac5 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -37,6 +37,7 @@ #include <linux/ctype.h> #include <linux/zalloc.h> +#include <linux/string.h> #include <asm/bug.h> static bool no_buildid_cache; @@ -260,10 +261,9 @@ static const char *build_id_cache__basename(bool is_kallsyms, bool is_vdso, "debug" : "elf")); } -char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size, - bool is_debug) +char *__dso__build_id_filename(const struct dso *dso, char *bf, size_t size, + bool is_debug, bool is_kallsyms) { - bool is_kallsyms = dso__is_kallsyms((struct dso *)dso); bool is_vdso = dso__is_vdso((struct dso *)dso); char sbuild_id[SBUILD_ID_SIZE]; char *linkname; @@ -292,6 +292,14 @@ char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size, return bf; } +char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size, + bool is_debug) +{ + bool is_kallsyms = dso__is_kallsyms((struct dso *)dso); + + return __dso__build_id_filename(dso, bf, size, is_debug, is_kallsyms); +} + #define dsos__for_each_with_build_id(pos, head) \ list_for_each_entry(pos, head, node) \ if (!pos->has_build_id) \ @@ -663,24 +671,15 @@ out: return realname; } -int build_id_cache__add_s(const char *sbuild_id, const char *name, - struct nsinfo *nsi, bool is_kallsyms, bool is_vdso) +int +build_id_cache__add(const char *sbuild_id, const char *name, const char *realname, + struct nsinfo *nsi, bool is_kallsyms, bool is_vdso) { const size_t size = PATH_MAX; - char *realname = NULL, *filename = NULL, *dir_name = NULL, - *linkname = zalloc(size), *tmp; + char *filename = NULL, *dir_name = NULL, *linkname = zalloc(size), *tmp; char *debugfile = NULL; int err = -1; - if (!is_kallsyms) { - if (!is_vdso) - realname = nsinfo__realpath(name, nsi); - else - realname = realpath(name, NULL); - if (!realname) - goto out_free; - } - dir_name = build_id_cache__cachedir(sbuild_id, name, nsi, is_kallsyms, is_vdso); if (!dir_name) @@ -754,8 +753,25 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name, tmp = dir_name + strlen(buildid_dir) - 5; memcpy(tmp, "../..", 5); - if (symlink(tmp, linkname) == 0) + if (symlink(tmp, linkname) == 0) { + err = 0; + } else if (errno == EEXIST) { + char path[PATH_MAX]; + ssize_t len; + + len = readlink(linkname, path, sizeof(path) - 1); + if (len <= 0) { + pr_err("Cant read link: %s\n", linkname); + goto out_free; + } + path[len] = '\0'; + + if (strcmp(tmp, path)) { + pr_debug("build <%s> already linked to %s\n", + sbuild_id, linkname); + } err = 0; + } /* Update SDT cache : error is just warned */ if (realname && @@ -763,8 +779,6 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name, pr_debug4("Failed to update/scan SDT cache for %s\n", realname); out_free: - if (!is_kallsyms) - free(realname); free(filename); free(debugfile); free(dir_name); @@ -772,6 +786,29 @@ out_free: return err; } +int build_id_cache__add_s(const char *sbuild_id, const char *name, + struct nsinfo *nsi, bool is_kallsyms, bool is_vdso) +{ + char *realname = NULL; + int err = -1; + + if (!is_kallsyms) { + if (!is_vdso) + realname = nsinfo__realpath(name, nsi); + else + realname = realpath(name, NULL); + if (!realname) + goto out_free; + } + + err = build_id_cache__add(sbuild_id, name, realname, nsi, is_kallsyms, is_vdso); + +out_free: + if (!is_kallsyms) + free(realname); + return err; +} + static int build_id_cache__add_b(const struct build_id *bid, const char *name, struct nsinfo *nsi, bool is_kallsyms, bool is_vdso) @@ -834,12 +871,16 @@ out_free: return err; } -static int dso__cache_build_id(struct dso *dso, struct machine *machine) +static int dso__cache_build_id(struct dso *dso, struct machine *machine, + void *priv __maybe_unused) { bool is_kallsyms = dso__is_kallsyms(dso); bool is_vdso = dso__is_vdso(dso); const char *name = dso->long_name; + if (!dso->has_build_id) + return 0; + if (dso__is_kcore(dso)) { is_kallsyms = true; name = machine->mmap_name; @@ -848,43 +889,36 @@ static int dso__cache_build_id(struct dso *dso, struct machine *machine) is_kallsyms, is_vdso); } -static int __dsos__cache_build_ids(struct list_head *head, - struct machine *machine) +static int +machines__for_each_dso(struct machines *machines, machine__dso_t fn, void *priv) { - struct dso *pos; - int err = 0; - - dsos__for_each_with_build_id(pos, head) - if (dso__cache_build_id(pos, machine)) - err = -1; + int ret = machine__for_each_dso(&machines->host, fn, priv); + struct rb_node *nd; - return err; -} + for (nd = rb_first_cached(&machines->guests); nd; + nd = rb_next(nd)) { + struct machine *pos = rb_entry(nd, struct machine, rb_node); -static int machine__cache_build_ids(struct machine *machine) -{ - return __dsos__cache_build_ids(&machine->dsos.head, machine); + ret |= machine__for_each_dso(pos, fn, priv); + } + return ret ? -1 : 0; } -int perf_session__cache_build_ids(struct perf_session *session) +int __perf_session__cache_build_ids(struct perf_session *session, + machine__dso_t fn, void *priv) { - struct rb_node *nd; - int ret; - if (no_buildid_cache) return 0; if (mkdir(buildid_dir, 0755) != 0 && errno != EEXIST) return -1; - ret = machine__cache_build_ids(&session->machines.host); + return machines__for_each_dso(&session->machines, fn, priv) ? -1 : 0; +} - for (nd = rb_first_cached(&session->machines.guests); nd; - nd = rb_next(nd)) { - struct machine *pos = rb_entry(nd, struct machine, rb_node); - ret |= machine__cache_build_ids(pos); - } - return ret ? -1 : 0; +int perf_session__cache_build_ids(struct perf_session *session) +{ + return __perf_session__cache_build_ids(session, dso__cache_build_id, NULL); } static bool machine__read_build_ids(struct machine *machine, bool with_hits) @@ -912,3 +946,8 @@ void build_id__init(struct build_id *bid, const u8 *data, size_t size) memcpy(bid->data, data, size); bid->size = size; } + +bool build_id__is_defined(const struct build_id *bid) +{ + return bid && bid->size ? !!memchr_inv(bid->data, 0, bid->size) : false; +} diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h index f293f99d5dba..02613f4b2c29 100644 --- a/tools/perf/util/build-id.h +++ b/tools/perf/util/build-id.h @@ -5,6 +5,7 @@ #define BUILD_ID_SIZE 20 #define SBUILD_ID_SIZE (BUILD_ID_SIZE * 2 + 1) +#include "machine.h" #include "tool.h" #include <linux/types.h> @@ -21,6 +22,7 @@ struct feat_fd; void build_id__init(struct build_id *bid, const u8 *data, size_t size); int build_id__sprintf(const struct build_id *build_id, char *bf); +bool build_id__is_defined(const struct build_id *bid); int sysfs__sprintf_build_id(const char *root_dir, char *sbuild_id); int filename__sprintf_build_id(const char *pathname, char *sbuild_id); char *build_id_cache__kallsyms_path(const char *sbuild_id, char *bf, @@ -28,6 +30,8 @@ char *build_id_cache__kallsyms_path(const char *sbuild_id, char *bf, char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size, bool is_debug); +char *__dso__build_id_filename(const struct dso *dso, char *bf, size_t size, + bool is_debug, bool is_kallsyms); int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct evsel *evsel, @@ -43,6 +47,8 @@ bool perf_session__read_build_ids(struct perf_session *session, bool with_hits); int perf_session__write_buildid_table(struct perf_session *session, struct feat_fd *fd); int perf_session__cache_build_ids(struct perf_session *session); +int __perf_session__cache_build_ids(struct perf_session *session, + machine__dso_t fn, void *priv); char *build_id_cache__origname(const char *sbuild_id); char *build_id_cache__linkname(const char *sbuild_id, char *bf, size_t size); @@ -57,6 +63,8 @@ char *build_id_cache__complement(const char *incomplete_sbuild_id); int build_id_cache__list_build_ids(const char *pathname, struct nsinfo *nsi, struct strlist **result); bool build_id_cache__cached(const char *sbuild_id); +int build_id_cache__add(const char *sbuild_id, const char *name, const char *realname, + struct nsinfo *nsi, bool is_kallsyms, bool is_vdso); int build_id_cache__add_s(const char *sbuild_id, const char *name, struct nsinfo *nsi, bool is_kallsyms, bool is_vdso); diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c index b81324a13a2b..5dff7e489921 100644 --- a/tools/perf/util/cgroup.c +++ b/tools/perf/util/cgroup.c @@ -13,9 +13,19 @@ #include <stdlib.h> #include <string.h> #include <api/fs/fs.h> +#include <ftw.h> +#include <regex.h> int nr_cgroups; +/* used to match cgroup name with patterns */ +struct cgroup_name { + struct list_head list; + bool used; + char name[]; +}; +static LIST_HEAD(cgroup_list); + static int open_cgroup(const char *name) { char path[PATH_MAX + 1]; @@ -149,6 +159,137 @@ void evlist__set_default_cgroup(struct evlist *evlist, struct cgroup *cgroup) evsel__set_default_cgroup(evsel, cgroup); } +/* helper function for ftw() in match_cgroups and list_cgroups */ +static int add_cgroup_name(const char *fpath, const struct stat *sb __maybe_unused, + int typeflag) +{ + struct cgroup_name *cn; + + if (typeflag != FTW_D) + return 0; + + cn = malloc(sizeof(*cn) + strlen(fpath) + 1); + if (cn == NULL) + return -1; + + cn->used = false; + strcpy(cn->name, fpath); + + list_add_tail(&cn->list, &cgroup_list); + return 0; +} + +static void release_cgroup_list(void) +{ + struct cgroup_name *cn; + + while (!list_empty(&cgroup_list)) { + cn = list_first_entry(&cgroup_list, struct cgroup_name, list); + list_del(&cn->list); + free(cn); + } +} + +/* collect given cgroups only */ +static int list_cgroups(const char *str) +{ + const char *p, *e, *eos = str + strlen(str); + struct cgroup_name *cn; + char *s; + + /* use given name as is - for testing purpose */ + for (;;) { + p = strchr(str, ','); + e = p ? p : eos; + + if (e - str) { + int ret; + + s = strndup(str, e - str); + if (!s) + return -1; + /* pretend if it's added by ftw() */ + ret = add_cgroup_name(s, NULL, FTW_D); + free(s); + if (ret) + return -1; + } else { + if (add_cgroup_name("", NULL, FTW_D) < 0) + return -1; + } + + if (!p) + break; + str = p+1; + } + + /* these groups will be used */ + list_for_each_entry(cn, &cgroup_list, list) + cn->used = true; + + return 0; +} + +/* collect all cgroups first and then match with the pattern */ +static int match_cgroups(const char *str) +{ + char mnt[PATH_MAX]; + const char *p, *e, *eos = str + strlen(str); + struct cgroup_name *cn; + regex_t reg; + int prefix_len; + char *s; + + if (cgroupfs_find_mountpoint(mnt, sizeof(mnt), "perf_event")) + return -1; + + /* cgroup_name will have a full path, skip the root directory */ + prefix_len = strlen(mnt); + + /* collect all cgroups in the cgroup_list */ + if (ftw(mnt, add_cgroup_name, 20) < 0) + return -1; + + for (;;) { + p = strchr(str, ','); + e = p ? p : eos; + + /* allow empty cgroups, i.e., skip */ + if (e - str) { + /* termination added */ + s = strndup(str, e - str); + if (!s) + return -1; + if (regcomp(®, s, REG_NOSUB)) { + free(s); + return -1; + } + + /* check cgroup name with the pattern */ + list_for_each_entry(cn, &cgroup_list, list) { + char *name = cn->name + prefix_len; + + if (name[0] == '/' && name[1]) + name++; + if (!regexec(®, name, 0, NULL, 0)) + cn->used = true; + } + regfree(®); + free(s); + } else { + /* first entry to root cgroup */ + cn = list_first_entry(&cgroup_list, struct cgroup_name, + list); + cn->used = true; + } + + if (!p) + break; + str = p+1; + } + return prefix_len; +} + int parse_cgroups(const struct option *opt, const char *str, int unset __maybe_unused) { @@ -201,6 +342,11 @@ int parse_cgroups(const struct option *opt, const char *str, return 0; } +static bool has_pattern_string(const char *str) +{ + return !!strpbrk(str, "{}[]()|*+?^$"); +} + int evlist__expand_cgroup(struct evlist *evlist, const char *str, struct rblist *metric_events, bool open_cgroup) { @@ -208,8 +354,9 @@ int evlist__expand_cgroup(struct evlist *evlist, const char *str, struct evsel *pos, *evsel, *leader; struct rblist orig_metric_events; struct cgroup *cgrp = NULL; - const char *p, *e, *eos = str + strlen(str); + struct cgroup_name *cn; int ret = -1; + int prefix_len; if (evlist->core.nr_entries == 0) { fprintf(stderr, "must define events before cgroups\n"); @@ -224,7 +371,7 @@ int evlist__expand_cgroup(struct evlist *evlist, const char *str, } /* save original events and init evlist */ - perf_evlist__splice_list_tail(orig_list, &evlist->core.entries); + evlist__splice_list_tail(orig_list, &evlist->core.entries); evlist->core.nr_entries = 0; if (metric_events) { @@ -234,24 +381,27 @@ int evlist__expand_cgroup(struct evlist *evlist, const char *str, rblist__init(&orig_metric_events); } - for (;;) { - p = strchr(str, ','); - e = p ? p : eos; + if (has_pattern_string(str)) + prefix_len = match_cgroups(str); + else + prefix_len = list_cgroups(str); - /* allow empty cgroups, i.e., skip */ - if (e - str) { - /* termination added */ - char *name = strndup(str, e - str); - if (!name) - goto out_err; + if (prefix_len < 0) + goto out_err; - cgrp = cgroup__new(name, open_cgroup); - free(name); - if (cgrp == NULL) - goto out_err; - } else { - cgrp = NULL; - } + list_for_each_entry(cn, &cgroup_list, list) { + char *name; + + if (!cn->used) + continue; + + /* cgroup_name might have a full path, skip the prefix */ + name = cn->name + prefix_len; + if (name[0] == '/' && name[1]) + name++; + cgrp = cgroup__new(name, open_cgroup); + if (cgrp == NULL) + goto out_err; leader = NULL; evlist__for_each_entry(orig_list, pos) { @@ -277,23 +427,25 @@ int evlist__expand_cgroup(struct evlist *evlist, const char *str, if (metricgroup__copy_metric_events(tmp_list, cgrp, metric_events, &orig_metric_events) < 0) - break; + goto out_err; } - perf_evlist__splice_list_tail(evlist, &tmp_list->core.entries); + evlist__splice_list_tail(evlist, &tmp_list->core.entries); tmp_list->core.nr_entries = 0; + } - if (!p) { - ret = 0; - break; - } - str = p+1; + if (list_empty(&evlist->core.entries)) { + fprintf(stderr, "no cgroup matched: %s\n", str); + goto out_err; } + ret = 0; + out_err: evlist__delete(orig_list); evlist__delete(tmp_list); rblist__exit(&orig_metric_events); + release_cgroup_list(); return ret; } diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index dc5c5e6fc502..87d3eca9b872 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -95,6 +95,23 @@ struct perf_cpu_map *perf_cpu_map__empty_new(int nr) return cpus; } +struct cpu_aggr_map *cpu_aggr_map__empty_new(int nr) +{ + struct cpu_aggr_map *cpus = malloc(sizeof(*cpus) + sizeof(struct aggr_cpu_id) * nr); + + if (cpus != NULL) { + int i; + + cpus->nr = nr; + for (i = 0; i < nr; i++) + cpus->map[i] = cpu_map__empty_aggr_cpu_id(); + + refcount_set(&cpus->refcnt, 1); + } + + return cpus; +} + static int cpu__get_topology_int(int cpu, const char *name, int *value) { char path[PATH_MAX]; @@ -111,40 +128,57 @@ int cpu_map__get_socket_id(int cpu) return ret ?: value; } -int cpu_map__get_socket(struct perf_cpu_map *map, int idx, void *data __maybe_unused) +struct aggr_cpu_id cpu_map__get_socket(struct perf_cpu_map *map, int idx, + void *data __maybe_unused) { int cpu; + struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); if (idx > map->nr) - return -1; + return id; cpu = map->map[idx]; - return cpu_map__get_socket_id(cpu); + id.socket = cpu_map__get_socket_id(cpu); + return id; } -static int cmp_ids(const void *a, const void *b) +static int cmp_aggr_cpu_id(const void *a_pointer, const void *b_pointer) { - return *(int *)a - *(int *)b; + struct aggr_cpu_id *a = (struct aggr_cpu_id *)a_pointer; + struct aggr_cpu_id *b = (struct aggr_cpu_id *)b_pointer; + + if (a->node != b->node) + return a->node - b->node; + else if (a->socket != b->socket) + return a->socket - b->socket; + else if (a->die != b->die) + return a->die - b->die; + else if (a->core != b->core) + return a->core - b->core; + else + return a->thread - b->thread; } -int cpu_map__build_map(struct perf_cpu_map *cpus, struct perf_cpu_map **res, - int (*f)(struct perf_cpu_map *map, int cpu, void *data), +int cpu_map__build_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **res, + struct aggr_cpu_id (*f)(struct perf_cpu_map *map, int cpu, void *data), void *data) { - struct perf_cpu_map *c; int nr = cpus->nr; - int cpu, s1, s2; + struct cpu_aggr_map *c = cpu_aggr_map__empty_new(nr); + int cpu, s2; + struct aggr_cpu_id s1; - /* allocate as much as possible */ - c = calloc(1, sizeof(*c) + nr * sizeof(int)); if (!c) return -1; + /* Reset size as it may only be partially filled */ + c->nr = 0; + for (cpu = 0; cpu < nr; cpu++) { s1 = f(cpus, cpu, data); for (s2 = 0; s2 < c->nr; s2++) { - if (s1 == c->map[s2]) + if (cpu_map__compare_aggr_cpu_id(s1, c->map[s2])) break; } if (s2 == c->nr) { @@ -153,9 +187,8 @@ int cpu_map__build_map(struct perf_cpu_map *cpus, struct perf_cpu_map **res, } } /* ensure we process id in increasing order */ - qsort(c->map, c->nr, sizeof(int), cmp_ids); + qsort(c->map, c->nr, sizeof(struct aggr_cpu_id), cmp_aggr_cpu_id); - refcount_set(&c->refcnt, 1); *res = c; return 0; } @@ -167,37 +200,32 @@ int cpu_map__get_die_id(int cpu) return ret ?: value; } -int cpu_map__get_die(struct perf_cpu_map *map, int idx, void *data) +struct aggr_cpu_id cpu_map__get_die(struct perf_cpu_map *map, int idx, void *data) { - int cpu, die_id, s; + int cpu, die; + struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); if (idx > map->nr) - return -1; + return id; cpu = map->map[idx]; - die_id = cpu_map__get_die_id(cpu); + die = cpu_map__get_die_id(cpu); /* There is no die_id on legacy system. */ - if (die_id == -1) - die_id = 0; - - s = cpu_map__get_socket(map, idx, data); - if (s == -1) - return -1; + if (die == -1) + die = 0; /* - * Encode socket in bit range 15:8 - * die_id is relative to socket, and - * we need a global id. So we combine - * socket + die id + * die_id is relative to socket, so start + * with the socket ID and then add die to + * make a unique ID. */ - if (WARN_ONCE(die_id >> 8, "The die id number is too big.\n")) - return -1; - - if (WARN_ONCE(s >> 8, "The socket id number is too big.\n")) - return -1; + id = cpu_map__get_socket(map, idx, data); + if (cpu_map__aggr_cpu_id_is_empty(id)) + return id; - return (s << 8) | (die_id & 0xff); + id.die = die; + return id; } int cpu_map__get_core_id(int cpu) @@ -211,59 +239,58 @@ int cpu_map__get_node_id(int cpu) return cpu__get_node(cpu); } -int cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data) +struct aggr_cpu_id cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data) { - int cpu, s_die; + int cpu; + struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); if (idx > map->nr) - return -1; + return id; cpu = map->map[idx]; cpu = cpu_map__get_core_id(cpu); - /* s_die is the combination of socket + die id */ - s_die = cpu_map__get_die(map, idx, data); - if (s_die == -1) - return -1; + /* cpu_map__get_die returns a struct with socket and die set*/ + id = cpu_map__get_die(map, idx, data); + if (cpu_map__aggr_cpu_id_is_empty(id)) + return id; /* - * encode socket in bit range 31:24 - * encode die id in bit range 23:16 - * core_id is relative to socket and die, - * we need a global id. So we combine - * socket + die id + core id + * core_id is relative to socket and die, we need a global id. + * So we combine the result from cpu_map__get_die with the core id */ - if (WARN_ONCE(cpu >> 16, "The core id number is too big.\n")) - return -1; - - return (s_die << 16) | (cpu & 0xffff); + id.core = cpu; + return id; } -int cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data __maybe_unused) +struct aggr_cpu_id cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data __maybe_unused) { + struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); + if (idx < 0 || idx >= map->nr) - return -1; + return id; - return cpu_map__get_node_id(map->map[idx]); + id.node = cpu_map__get_node_id(map->map[idx]); + return id; } -int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct perf_cpu_map **sockp) +int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **sockp) { return cpu_map__build_map(cpus, sockp, cpu_map__get_socket, NULL); } -int cpu_map__build_die_map(struct perf_cpu_map *cpus, struct perf_cpu_map **diep) +int cpu_map__build_die_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **diep) { return cpu_map__build_map(cpus, diep, cpu_map__get_die, NULL); } -int cpu_map__build_core_map(struct perf_cpu_map *cpus, struct perf_cpu_map **corep) +int cpu_map__build_core_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **corep) { return cpu_map__build_map(cpus, corep, cpu_map__get_core, NULL); } -int cpu_map__build_node_map(struct perf_cpu_map *cpus, struct perf_cpu_map **numap) +int cpu_map__build_node_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **numap) { return cpu_map__build_map(cpus, numap, cpu_map__get_node, NULL); } @@ -586,3 +613,33 @@ const struct perf_cpu_map *cpu_map__online(void) /* thread unsafe */ return online; } + +bool cpu_map__compare_aggr_cpu_id(struct aggr_cpu_id a, struct aggr_cpu_id b) +{ + return a.thread == b.thread && + a.node == b.node && + a.socket == b.socket && + a.die == b.die && + a.core == b.core; +} + +bool cpu_map__aggr_cpu_id_is_empty(struct aggr_cpu_id a) +{ + return a.thread == -1 && + a.node == -1 && + a.socket == -1 && + a.die == -1 && + a.core == -1; +} + +struct aggr_cpu_id cpu_map__empty_aggr_cpu_id(void) +{ + struct aggr_cpu_id ret = { + .thread = -1, + .node = -1, + .socket = -1, + .die = -1, + .core = -1 + }; + return ret; +} diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h index 3a442f021468..a27eeaf086e8 100644 --- a/tools/perf/util/cpumap.h +++ b/tools/perf/util/cpumap.h @@ -7,25 +7,41 @@ #include <internal/cpumap.h> #include <perf/cpumap.h> +struct aggr_cpu_id { + int thread; + int node; + int socket; + int die; + int core; +}; + +struct cpu_aggr_map { + refcount_t refcnt; + int nr; + struct aggr_cpu_id map[]; +}; + struct perf_record_cpu_map_data; struct perf_cpu_map *perf_cpu_map__empty_new(int nr); +struct cpu_aggr_map *cpu_aggr_map__empty_new(int nr); + struct perf_cpu_map *cpu_map__new_data(struct perf_record_cpu_map_data *data); size_t cpu_map__snprint(struct perf_cpu_map *map, char *buf, size_t size); size_t cpu_map__snprint_mask(struct perf_cpu_map *map, char *buf, size_t size); size_t cpu_map__fprintf(struct perf_cpu_map *map, FILE *fp); int cpu_map__get_socket_id(int cpu); -int cpu_map__get_socket(struct perf_cpu_map *map, int idx, void *data); +struct aggr_cpu_id cpu_map__get_socket(struct perf_cpu_map *map, int idx, void *data); int cpu_map__get_die_id(int cpu); -int cpu_map__get_die(struct perf_cpu_map *map, int idx, void *data); +struct aggr_cpu_id cpu_map__get_die(struct perf_cpu_map *map, int idx, void *data); int cpu_map__get_core_id(int cpu); -int cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data); +struct aggr_cpu_id cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data); int cpu_map__get_node_id(int cpu); -int cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data); -int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct perf_cpu_map **sockp); -int cpu_map__build_die_map(struct perf_cpu_map *cpus, struct perf_cpu_map **diep); -int cpu_map__build_core_map(struct perf_cpu_map *cpus, struct perf_cpu_map **corep); -int cpu_map__build_node_map(struct perf_cpu_map *cpus, struct perf_cpu_map **nodep); +struct aggr_cpu_id cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data); +int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **sockp); +int cpu_map__build_die_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **diep); +int cpu_map__build_core_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **corep); +int cpu_map__build_node_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **nodep); const struct perf_cpu_map *cpu_map__online(void); /* thread unsafe */ static inline int cpu_map__socket(struct perf_cpu_map *sock, int s) @@ -35,21 +51,6 @@ static inline int cpu_map__socket(struct perf_cpu_map *sock, int s) return sock->map[s]; } -static inline int cpu_map__id_to_socket(int id) -{ - return id >> 24; -} - -static inline int cpu_map__id_to_die(int id) -{ - return (id >> 16) & 0xff; -} - -static inline int cpu_map__id_to_cpu(int id) -{ - return id & 0xffff; -} - int cpu__setup_cpunode_map(void); int cpu__max_node(void); @@ -57,11 +58,15 @@ int cpu__max_cpu(void); int cpu__max_present_cpu(void); int cpu__get_node(int cpu); -int cpu_map__build_map(struct perf_cpu_map *cpus, struct perf_cpu_map **res, - int (*f)(struct perf_cpu_map *map, int cpu, void *data), +int cpu_map__build_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **res, + struct aggr_cpu_id (*f)(struct perf_cpu_map *map, int cpu, void *data), void *data); int cpu_map__cpu(struct perf_cpu_map *cpus, int idx); bool cpu_map__has(struct perf_cpu_map *cpus, int cpu); +bool cpu_map__compare_aggr_cpu_id(struct aggr_cpu_id a, struct aggr_cpu_id b); +bool cpu_map__aggr_cpu_id_is_empty(struct aggr_cpu_id a); +struct aggr_cpu_id cpu_map__empty_aggr_cpu_id(void); + #endif /* __PERF_CPUMAP_H */ diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index c47aa34fdc0a..f29af4fc3d09 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -174,8 +174,21 @@ static bool check_pipe(struct perf_data *data) is_pipe = true; } - if (is_pipe) - data->file.fd = fd; + if (is_pipe) { + if (data->use_stdio) { + const char *mode; + + mode = perf_data__is_read(data) ? "r" : "w"; + data->file.fptr = fdopen(fd, mode); + + if (data->file.fptr == NULL) { + data->file.fd = fd; + data->use_stdio = false; + } + } else { + data->file.fd = fd; + } + } return data->is_pipe = is_pipe; } @@ -334,6 +347,9 @@ int perf_data__open(struct perf_data *data) if (check_pipe(data)) return 0; + /* currently it allows stdio for pipe only */ + data->use_stdio = false; + if (!data->path) data->path = "perf.data"; @@ -353,7 +369,21 @@ void perf_data__close(struct perf_data *data) perf_data__close_dir(data); zfree(&data->file.path); - close(data->file.fd); + + if (data->use_stdio) + fclose(data->file.fptr); + else + close(data->file.fd); +} + +ssize_t perf_data__read(struct perf_data *data, void *buf, size_t size) +{ + if (data->use_stdio) { + if (fread(buf, size, 1, data->file.fptr) == 1) + return size; + return feof(data->file.fptr) ? 0 : -1; + } + return readn(data->file.fd, buf, size); } ssize_t perf_data_file__write(struct perf_data_file *file, @@ -365,6 +395,11 @@ ssize_t perf_data_file__write(struct perf_data_file *file, ssize_t perf_data__write(struct perf_data *data, void *buf, size_t size) { + if (data->use_stdio) { + if (fwrite(buf, size, 1, data->file.fptr) == 1) + return size; + return -1; + } return perf_data_file__write(&data->file, buf, size); } @@ -457,3 +492,22 @@ char *perf_data__kallsyms_name(struct perf_data *data) return kallsyms_name; } + +bool is_perf_data(const char *path) +{ + bool ret = false; + FILE *file; + u64 magic; + + file = fopen(path, "r"); + if (!file) + return false; + + if (fread(&magic, 1, 8, file) < 8) + goto out; + + ret = is_perf_magic(magic); +out: + fclose(file); + return ret; +} diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h index 75947ef6bc17..62a3e66fbee8 100644 --- a/tools/perf/util/data.h +++ b/tools/perf/util/data.h @@ -2,6 +2,7 @@ #ifndef __PERF_DATA_H #define __PERF_DATA_H +#include <stdio.h> #include <stdbool.h> enum perf_data_mode { @@ -16,7 +17,10 @@ enum perf_dir_version { struct perf_data_file { char *path; - int fd; + union { + int fd; + FILE *fptr; + }; unsigned long size; }; @@ -26,6 +30,7 @@ struct perf_data { bool is_pipe; bool is_dir; bool force; + bool use_stdio; enum perf_data_mode mode; struct { @@ -62,11 +67,15 @@ static inline bool perf_data__is_single_file(struct perf_data *data) static inline int perf_data__fd(struct perf_data *data) { + if (data->use_stdio) + return fileno(data->file.fptr); + return data->file.fd; } int perf_data__open(struct perf_data *data); void perf_data__close(struct perf_data *data); +ssize_t perf_data__read(struct perf_data *data, void *buf, size_t size); ssize_t perf_data__write(struct perf_data *data, void *buf, size_t size); ssize_t perf_data_file__write(struct perf_data_file *file, @@ -89,4 +98,5 @@ int perf_data__update_dir(struct perf_data *data); unsigned long perf_data__size(struct perf_data *data); int perf_data__make_kcore_dir(struct perf_data *data, char *buf, size_t buf_sz); char *perf_data__kallsyms_name(struct perf_data *data); +bool is_perf_data(const char *path); #endif /* __PERF_DATA_H */ diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c index 5cda5565777a..50fd6a4be4e0 100644 --- a/tools/perf/util/debug.c +++ b/tools/perf/util/debug.c @@ -30,6 +30,12 @@ bool dump_trace = false, quiet = false; int debug_ordered_events; static int redirect_to_stderr; int debug_data_convert; +static FILE *debug_file; + +void debug_set_file(FILE *file) +{ + debug_file = file; +} int veprintf(int level, int var, const char *fmt, va_list args) { @@ -39,7 +45,7 @@ int veprintf(int level, int var, const char *fmt, va_list args) if (use_browser >= 1 && !redirect_to_stderr) ui_helpline__vshow(fmt, args); else - ret = vfprintf(stderr, fmt, args); + ret = vfprintf(debug_file, fmt, args); } return ret; @@ -227,6 +233,7 @@ DEBUG_WRAPPER(debug, 1); void perf_debug_setup(void) { + debug_set_file(stderr); libapi_set_print(pr_warning_wrapper, pr_warning_wrapper, pr_debug_wrapper); } diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h index f1734abd98dd..43f712295645 100644 --- a/tools/perf/util/debug.h +++ b/tools/perf/util/debug.h @@ -5,6 +5,7 @@ #include <stdarg.h> #include <stdbool.h> +#include <stdio.h> #include <linux/compiler.h> extern int verbose; @@ -62,6 +63,7 @@ int eprintf_time(int level, int var, u64 t, const char *fmt, ...) __printf(4, 5) int veprintf(int level, int var, const char *fmt, va_list args); int perf_debug_option(const char *str); +void debug_set_file(FILE *file); void perf_debug_setup(void); int perf_quiet_option(void); diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index 55c11e854fe4..d786cf6b0cfa 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -11,8 +11,10 @@ #include <errno.h> #include <fcntl.h> #include <stdlib.h> +#ifdef HAVE_LIBBPF_SUPPORT #include <bpf/libbpf.h> #include "bpf-event.h" +#endif #include "compress.h" #include "env.h" #include "namespaces.h" @@ -277,18 +279,12 @@ bool dso__needs_decompress(struct dso *dso) dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP; } -static int decompress_kmodule(struct dso *dso, const char *name, - char *pathname, size_t len) +int filename__decompress(const char *name, char *pathname, + size_t len, int comp, int *err) { char tmpbuf[] = KMOD_DECOMP_NAME; int fd = -1; - if (!dso__needs_decompress(dso)) - return -1; - - if (dso->comp == COMP_ID__NONE) - return -1; - /* * We have proper compression id for DSO and yet the file * behind the 'name' can still be plain uncompressed object. @@ -302,17 +298,17 @@ static int decompress_kmodule(struct dso *dso, const char *name, * To keep this transparent, we detect this and return the file * descriptor to the uncompressed file. */ - if (!compressions[dso->comp].is_compressed(name)) + if (!compressions[comp].is_compressed(name)) return open(name, O_RDONLY); fd = mkstemp(tmpbuf); if (fd < 0) { - dso->load_errno = errno; + *err = errno; return -1; } - if (compressions[dso->comp].decompress(name, fd)) { - dso->load_errno = DSO_LOAD_ERRNO__DECOMPRESSION_FAILURE; + if (compressions[comp].decompress(name, fd)) { + *err = DSO_LOAD_ERRNO__DECOMPRESSION_FAILURE; close(fd); fd = -1; } @@ -326,6 +322,19 @@ static int decompress_kmodule(struct dso *dso, const char *name, return fd; } +static int decompress_kmodule(struct dso *dso, const char *name, + char *pathname, size_t len) +{ + if (!dso__needs_decompress(dso)) + return -1; + + if (dso->comp == COMP_ID__NONE) + return -1; + + return filename__decompress(name, pathname, len, dso->comp, + &dso->load_errno); +} + int dso__decompress_kmodule_fd(struct dso *dso, const char *name) { return decompress_kmodule(dso, name, NULL, 0); @@ -728,6 +737,7 @@ bool dso__data_status_seen(struct dso *dso, enum dso_data_status_seen by) return false; } +#ifdef HAVE_LIBBPF_SUPPORT static ssize_t bpf_read(struct dso *dso, u64 offset, char *data) { struct bpf_prog_info_node *node; @@ -765,6 +775,7 @@ static int bpf_size(struct dso *dso) dso->data.file_size = node->info_linear->info.jited_prog_len; return 0; } +#endif // HAVE_LIBBPF_SUPPORT static void dso_cache__free(struct dso *dso) @@ -894,10 +905,12 @@ static struct dso_cache *dso_cache__populate(struct dso *dso, *ret = -ENOMEM; return NULL; } - +#ifdef HAVE_LIBBPF_SUPPORT if (dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO) *ret = bpf_read(dso, cache_offset, cache->data); - else if (dso->binary_type == DSO_BINARY_TYPE__OOL) + else +#endif + if (dso->binary_type == DSO_BINARY_TYPE__OOL) *ret = DSO__DATA_CACHE_SIZE; else *ret = file_read(dso, machine, cache_offset, cache->data); @@ -1018,10 +1031,10 @@ int dso__data_file_size(struct dso *dso, struct machine *machine) if (dso->data.status == DSO_DATA_STATUS_ERROR) return -1; - +#ifdef HAVE_LIBBPF_SUPPORT if (dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO) return bpf_size(dso); - +#endif return file_size(dso, machine); } diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index d8cb4f5680a4..cd2fe64a3c5d 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -274,6 +274,8 @@ bool dso__needs_decompress(struct dso *dso); int dso__decompress_kmodule_fd(struct dso *dso, const char *name); int dso__decompress_kmodule_path(struct dso *dso, const char *name, char *pathname, size_t len); +int filename__decompress(const char *name, char *pathname, + size_t len, int comp, int *err); #define KMOD_DECOMP_NAME "/tmp/perf-kmod-XXXXXX" #define KMOD_DECOMP_LEN sizeof(KMOD_DECOMP_NAME) diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index fadc59708ece..9130f6fad8d5 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -5,16 +5,18 @@ #include "util/header.h" #include <linux/ctype.h> #include <linux/zalloc.h> -#include "bpf-event.h" #include "cgroup.h" #include <errno.h> #include <sys/utsname.h> -#include <bpf/libbpf.h> #include <stdlib.h> #include <string.h> struct perf_env perf_env; +#ifdef HAVE_LIBBPF_SUPPORT +#include "bpf-event.h" +#include <bpf/libbpf.h> + void perf_env__insert_bpf_prog_info(struct perf_env *env, struct bpf_prog_info_node *info_node) { @@ -163,6 +165,11 @@ static void perf_env__purge_bpf(struct perf_env *env) up_write(&env->bpf_progs.lock); } +#else // HAVE_LIBBPF_SUPPORT +static void perf_env__purge_bpf(struct perf_env *env __maybe_unused) +{ +} +#endif // HAVE_LIBBPF_SUPPORT void perf_env__exit(struct perf_env *env) { @@ -197,11 +204,13 @@ void perf_env__exit(struct perf_env *env) zfree(&env->memory_nodes); } -void perf_env__init(struct perf_env *env) +void perf_env__init(struct perf_env *env __maybe_unused) { +#ifdef HAVE_LIBBPF_SUPPORT env->bpf_progs.infos = RB_ROOT; env->bpf_progs.btfs = RB_ROOT; init_rwsem(&env->bpf_progs.lock); +#endif } int perf_env__set_cmdline(struct perf_env *env, int argc, const char *argv[]) diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h index a12972652006..ca249bf5e984 100644 --- a/tools/perf/util/env.h +++ b/tools/perf/util/env.h @@ -77,7 +77,7 @@ struct perf_env { struct numa_node *numa_nodes; struct memory_node *memory_nodes; unsigned long long memory_bsize; - +#ifdef HAVE_LIBBPF_SUPPORT /* * bpf_info_lock protects bpf rbtrees. This is needed because the * trees are accessed by different threads in perf-top @@ -89,7 +89,7 @@ struct perf_env { struct rb_root btfs; u32 btfs_cnt; } bpf_progs; - +#endif // HAVE_LIBBPF_SUPPORT /* same reason as above (for perf-top) */ struct { struct rw_semaphore lock; diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index b828b99176f4..ff403ea578e1 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -135,6 +135,7 @@ struct perf_sample { u32 raw_size; u64 data_src; u64 phys_addr; + u64 data_page_size; u64 cgroup; u32 flags; u16 insn_len; @@ -408,4 +409,7 @@ extern int sysctl_perf_event_max_stack; extern int sysctl_perf_event_max_contexts_per_stack; extern unsigned int proc_map_timeout; +#define PAGE_SIZE_NAME_LEN 32 +char *get_page_size_name(u64 size, char *str); + #endif /* __PERF_RECORD_H */ diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 8bdf3d2c907c..05363a7247c4 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -78,7 +78,7 @@ struct evlist *evlist__new(void) return evlist; } -struct evlist *perf_evlist__new_default(void) +struct evlist *evlist__new_default(void) { struct evlist *evlist = evlist__new(); @@ -90,7 +90,7 @@ struct evlist *perf_evlist__new_default(void) return evlist; } -struct evlist *perf_evlist__new_dummy(void) +struct evlist *evlist__new_dummy(void) { struct evlist *evlist = evlist__new(); @@ -103,13 +103,13 @@ struct evlist *perf_evlist__new_dummy(void) } /** - * perf_evlist__set_id_pos - set the positions of event ids. + * evlist__set_id_pos - set the positions of event ids. * @evlist: selected event list * * Events with compatible sample types all have the same id_pos * and is_pos. For convenience, put a copy on evlist. */ -void perf_evlist__set_id_pos(struct evlist *evlist) +void evlist__set_id_pos(struct evlist *evlist) { struct evsel *first = evlist__first(evlist); @@ -117,14 +117,14 @@ void perf_evlist__set_id_pos(struct evlist *evlist) evlist->is_pos = first->is_pos; } -static void perf_evlist__update_id_pos(struct evlist *evlist) +static void evlist__update_id_pos(struct evlist *evlist) { struct evsel *evsel; evlist__for_each_entry(evlist, evsel) evsel__calc_id_pos(evsel); - perf_evlist__set_id_pos(evlist); + evlist__set_id_pos(evlist); } static void evlist__purge(struct evlist *evlist) @@ -168,7 +168,7 @@ void evlist__add(struct evlist *evlist, struct evsel *entry) perf_evlist__add(&evlist->core, &entry->core); if (evlist->core.nr_entries == 1) - perf_evlist__set_id_pos(evlist); + evlist__set_id_pos(evlist); } void evlist__remove(struct evlist *evlist, struct evsel *evsel) @@ -177,27 +177,36 @@ void evlist__remove(struct evlist *evlist, struct evsel *evsel) perf_evlist__remove(&evlist->core, &evsel->core); } -void perf_evlist__splice_list_tail(struct evlist *evlist, - struct list_head *list) +void evlist__splice_list_tail(struct evlist *evlist, struct list_head *list) { - struct evsel *evsel, *temp; + while (!list_empty(list)) { + struct evsel *evsel, *temp, *leader = NULL; - __evlist__for_each_entry_safe(list, temp, evsel) { - list_del_init(&evsel->core.node); - evlist__add(evlist, evsel); + __evlist__for_each_entry_safe(list, temp, evsel) { + list_del_init(&evsel->core.node); + evlist__add(evlist, evsel); + leader = evsel; + break; + } + + __evlist__for_each_entry_safe(list, temp, evsel) { + if (evsel->leader == leader) { + list_del_init(&evsel->core.node); + evlist__add(evlist, evsel); + } + } } } int __evlist__set_tracepoints_handlers(struct evlist *evlist, const struct evsel_str_handler *assocs, size_t nr_assocs) { - struct evsel *evsel; size_t i; int err; for (i = 0; i < nr_assocs; i++) { // Adding a handler for an event not in this evlist, just ignore it. - evsel = perf_evlist__find_tracepoint_by_name(evlist, assocs[i].name); + struct evsel *evsel = evlist__find_tracepoint_by_name(evlist, assocs[i].name); if (evsel == NULL) continue; @@ -212,7 +221,7 @@ out: return err; } -void __perf_evlist__set_leader(struct list_head *list) +void __evlist__set_leader(struct list_head *list) { struct evsel *evsel, *leader; @@ -226,11 +235,11 @@ void __perf_evlist__set_leader(struct list_head *list) } } -void perf_evlist__set_leader(struct evlist *evlist) +void evlist__set_leader(struct evlist *evlist) { if (evlist->core.nr_entries) { evlist->nr_groups = evlist->core.nr_entries > 1 ? 1 : 0; - __perf_evlist__set_leader(&evlist->core.entries); + __evlist__set_leader(&evlist->core.entries); } } @@ -274,7 +283,7 @@ static int evlist__add_attrs(struct evlist *evlist, struct perf_event_attr *attr list_add_tail(&evsel->core.node, &head); } - perf_evlist__splice_list_tail(evlist, &head); + evlist__splice_list_tail(evlist, &head); return 0; @@ -294,8 +303,7 @@ int __evlist__add_default_attrs(struct evlist *evlist, struct perf_event_attr *a return evlist__add_attrs(evlist, attrs, nr_attrs); } -struct evsel * -perf_evlist__find_tracepoint_by_id(struct evlist *evlist, int id) +struct evsel *evlist__find_tracepoint_by_id(struct evlist *evlist, int id) { struct evsel *evsel; @@ -308,9 +316,7 @@ perf_evlist__find_tracepoint_by_id(struct evlist *evlist, int id) return NULL; } -struct evsel * -perf_evlist__find_tracepoint_by_name(struct evlist *evlist, - const char *name) +struct evsel *evlist__find_tracepoint_by_name(struct evlist *evlist, const char *name) { struct evsel *evsel; @@ -335,8 +341,7 @@ int evlist__add_newtp(struct evlist *evlist, const char *sys, const char *name, return 0; } -static int perf_evlist__nr_threads(struct evlist *evlist, - struct evsel *evsel) +static int evlist__nr_threads(struct evlist *evlist, struct evsel *evsel) { if (evsel->core.system_wide) return 1; @@ -376,7 +381,30 @@ bool evsel__cpu_iter_skip(struct evsel *ev, int cpu) return true; } -void evlist__disable(struct evlist *evlist) +static int evsel__strcmp(struct evsel *pos, char *evsel_name) +{ + if (!evsel_name) + return 0; + if (evsel__is_dummy_event(pos)) + return 1; + return strcmp(pos->name, evsel_name); +} + +static int evlist__is_enabled(struct evlist *evlist) +{ + struct evsel *pos; + + evlist__for_each_entry(evlist, pos) { + if (!evsel__is_group_leader(pos) || !pos->core.fd) + continue; + /* If at least one event is enabled, evlist is enabled. */ + if (!pos->disabled) + return true; + } + return false; +} + +static void __evlist__disable(struct evlist *evlist, char *evsel_name) { struct evsel *pos; struct affinity affinity; @@ -392,6 +420,8 @@ void evlist__disable(struct evlist *evlist) affinity__set(&affinity, cpu); evlist__for_each_entry(evlist, pos) { + if (evsel__strcmp(pos, evsel_name)) + continue; if (evsel__cpu_iter_skip(pos, cpu)) continue; if (pos->disabled || !evsel__is_group_leader(pos) || !pos->core.fd) @@ -409,15 +439,34 @@ void evlist__disable(struct evlist *evlist) affinity__cleanup(&affinity); evlist__for_each_entry(evlist, pos) { + if (evsel__strcmp(pos, evsel_name)) + continue; if (!evsel__is_group_leader(pos) || !pos->core.fd) continue; pos->disabled = true; } - evlist->enabled = false; + /* + * If we disabled only single event, we need to check + * the enabled state of the evlist manually. + */ + if (evsel_name) + evlist->enabled = evlist__is_enabled(evlist); + else + evlist->enabled = false; } -void evlist__enable(struct evlist *evlist) +void evlist__disable(struct evlist *evlist) +{ + __evlist__disable(evlist, NULL); +} + +void evlist__disable_evsel(struct evlist *evlist, char *evsel_name) +{ + __evlist__disable(evlist, evsel_name); +} + +static void __evlist__enable(struct evlist *evlist, char *evsel_name) { struct evsel *pos; struct affinity affinity; @@ -430,6 +479,8 @@ void evlist__enable(struct evlist *evlist) affinity__set(&affinity, cpu); evlist__for_each_entry(evlist, pos) { + if (evsel__strcmp(pos, evsel_name)) + continue; if (evsel__cpu_iter_skip(pos, cpu)) continue; if (!evsel__is_group_leader(pos) || !pos->core.fd) @@ -439,24 +490,40 @@ void evlist__enable(struct evlist *evlist) } affinity__cleanup(&affinity); evlist__for_each_entry(evlist, pos) { + if (evsel__strcmp(pos, evsel_name)) + continue; if (!evsel__is_group_leader(pos) || !pos->core.fd) continue; pos->disabled = false; } + /* + * Even single event sets the 'enabled' for evlist, + * so the toggle can work properly and toggle to + * 'disabled' state. + */ evlist->enabled = true; } -void perf_evlist__toggle_enable(struct evlist *evlist) +void evlist__enable(struct evlist *evlist) +{ + __evlist__enable(evlist, NULL); +} + +void evlist__enable_evsel(struct evlist *evlist, char *evsel_name) +{ + __evlist__enable(evlist, evsel_name); +} + +void evlist__toggle_enable(struct evlist *evlist) { (evlist->enabled ? evlist__disable : evlist__enable)(evlist); } -static int perf_evlist__enable_event_cpu(struct evlist *evlist, - struct evsel *evsel, int cpu) +static int evlist__enable_event_cpu(struct evlist *evlist, struct evsel *evsel, int cpu) { int thread; - int nr_threads = perf_evlist__nr_threads(evlist, evsel); + int nr_threads = evlist__nr_threads(evlist, evsel); if (!evsel->core.fd) return -EINVAL; @@ -469,9 +536,7 @@ static int perf_evlist__enable_event_cpu(struct evlist *evlist, return 0; } -static int perf_evlist__enable_event_thread(struct evlist *evlist, - struct evsel *evsel, - int thread) +static int evlist__enable_event_thread(struct evlist *evlist, struct evsel *evsel, int thread) { int cpu; int nr_cpus = perf_cpu_map__nr(evlist->core.cpus); @@ -487,15 +552,14 @@ static int perf_evlist__enable_event_thread(struct evlist *evlist, return 0; } -int perf_evlist__enable_event_idx(struct evlist *evlist, - struct evsel *evsel, int idx) +int evlist__enable_event_idx(struct evlist *evlist, struct evsel *evsel, int idx) { bool per_cpu_mmaps = !perf_cpu_map__empty(evlist->core.cpus); if (per_cpu_mmaps) - return perf_evlist__enable_event_cpu(evlist, evsel, idx); - else - return perf_evlist__enable_event_thread(evlist, evsel, idx); + return evlist__enable_event_cpu(evlist, evsel, idx); + + return evlist__enable_event_thread(evlist, evsel, idx); } int evlist__add_pollfd(struct evlist *evlist, int fd) @@ -513,7 +577,7 @@ int evlist__poll(struct evlist *evlist, int timeout) return perf_evlist__poll(&evlist->core, timeout); } -struct perf_sample_id *perf_evlist__id2sid(struct evlist *evlist, u64 id) +struct perf_sample_id *evlist__id2sid(struct evlist *evlist, u64 id) { struct hlist_head *head; struct perf_sample_id *sid; @@ -529,14 +593,14 @@ struct perf_sample_id *perf_evlist__id2sid(struct evlist *evlist, u64 id) return NULL; } -struct evsel *perf_evlist__id2evsel(struct evlist *evlist, u64 id) +struct evsel *evlist__id2evsel(struct evlist *evlist, u64 id) { struct perf_sample_id *sid; if (evlist->core.nr_entries == 1 || !id) return evlist__first(evlist); - sid = perf_evlist__id2sid(evlist, id); + sid = evlist__id2sid(evlist, id); if (sid) return container_of(sid->evsel, struct evsel, core); @@ -546,23 +610,21 @@ struct evsel *perf_evlist__id2evsel(struct evlist *evlist, u64 id) return NULL; } -struct evsel *perf_evlist__id2evsel_strict(struct evlist *evlist, - u64 id) +struct evsel *evlist__id2evsel_strict(struct evlist *evlist, u64 id) { struct perf_sample_id *sid; if (!id) return NULL; - sid = perf_evlist__id2sid(evlist, id); + sid = evlist__id2sid(evlist, id); if (sid) return container_of(sid->evsel, struct evsel, core); return NULL; } -static int perf_evlist__event2id(struct evlist *evlist, - union perf_event *event, u64 *id) +static int evlist__event2id(struct evlist *evlist, union perf_event *event, u64 *id) { const __u64 *array = event->sample.array; ssize_t n; @@ -582,8 +644,7 @@ static int perf_evlist__event2id(struct evlist *evlist, return 0; } -struct evsel *perf_evlist__event2evsel(struct evlist *evlist, - union perf_event *event) +struct evsel *evlist__event2evsel(struct evlist *evlist, union perf_event *event) { struct evsel *first = evlist__first(evlist); struct hlist_head *head; @@ -598,7 +659,7 @@ struct evsel *perf_evlist__event2evsel(struct evlist *evlist, event->header.type != PERF_RECORD_SAMPLE) return first; - if (perf_evlist__event2id(evlist, event, &id)) + if (evlist__event2id(evlist, event, &id)) return NULL; /* Synthesized events have an id of zero */ @@ -615,7 +676,7 @@ struct evsel *perf_evlist__event2evsel(struct evlist *evlist, return NULL; } -static int perf_evlist__set_paused(struct evlist *evlist, bool value) +static int evlist__set_paused(struct evlist *evlist, bool value) { int i; @@ -635,14 +696,14 @@ static int perf_evlist__set_paused(struct evlist *evlist, bool value) return 0; } -static int perf_evlist__pause(struct evlist *evlist) +static int evlist__pause(struct evlist *evlist) { - return perf_evlist__set_paused(evlist, true); + return evlist__set_paused(evlist, true); } -static int perf_evlist__resume(struct evlist *evlist) +static int evlist__resume(struct evlist *evlist) { - return perf_evlist__set_paused(evlist, false); + return evlist__set_paused(evlist, false); } static void evlist__munmap_nofree(struct evlist *evlist) @@ -727,7 +788,7 @@ perf_evlist__mmap_cb_get(struct perf_evlist *_evlist, bool overwrite, int idx) if (overwrite) { evlist->overwrite_mmap = maps; if (evlist->bkw_mmap_state == BKW_MMAP_NOTREADY) - perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_RUNNING); + evlist__toggle_bkw_mmap(evlist, BKW_MMAP_RUNNING); } else { evlist->mmap = maps; } @@ -827,7 +888,7 @@ static long parse_pages_arg(const char *str, unsigned long min, return pages; } -int __perf_evlist__parse_mmap_pages(unsigned int *mmap_pages, const char *str) +int __evlist__parse_mmap_pages(unsigned int *mmap_pages, const char *str) { unsigned long max = UINT_MAX; long pages; @@ -845,10 +906,9 @@ int __perf_evlist__parse_mmap_pages(unsigned int *mmap_pages, const char *str) return 0; } -int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str, - int unset __maybe_unused) +int evlist__parse_mmap_pages(const struct option *opt, const char *str, int unset __maybe_unused) { - return __perf_evlist__parse_mmap_pages(opt->value, str); + return __evlist__parse_mmap_pages(opt->value, str); } /** @@ -904,7 +964,7 @@ int evlist__mmap(struct evlist *evlist, unsigned int pages) return evlist__mmap_ex(evlist, pages, 0, false, 0, PERF_AFFINITY_SYS, 1, 0); } -int perf_evlist__create_maps(struct evlist *evlist, struct target *target) +int evlist__create_maps(struct evlist *evlist, struct target *target) { bool all_threads = (target->per_thread && target->system_wide); struct perf_cpu_map *cpus; @@ -957,25 +1017,7 @@ out_delete_threads: return -1; } -void __perf_evlist__set_sample_bit(struct evlist *evlist, - enum perf_event_sample_format bit) -{ - struct evsel *evsel; - - evlist__for_each_entry(evlist, evsel) - __evsel__set_sample_bit(evsel, bit); -} - -void __perf_evlist__reset_sample_bit(struct evlist *evlist, - enum perf_event_sample_format bit) -{ - struct evsel *evsel; - - evlist__for_each_entry(evlist, evsel) - __evsel__reset_sample_bit(evsel, bit); -} - -int perf_evlist__apply_filters(struct evlist *evlist, struct evsel **err_evsel) +int evlist__apply_filters(struct evlist *evlist, struct evsel **err_evsel) { struct evsel *evsel; int err = 0; @@ -998,7 +1040,7 @@ int perf_evlist__apply_filters(struct evlist *evlist, struct evsel **err_evsel) return err; } -int perf_evlist__set_tp_filter(struct evlist *evlist, const char *filter) +int evlist__set_tp_filter(struct evlist *evlist, const char *filter) { struct evsel *evsel; int err = 0; @@ -1018,7 +1060,7 @@ int perf_evlist__set_tp_filter(struct evlist *evlist, const char *filter) return err; } -int perf_evlist__append_tp_filter(struct evlist *evlist, const char *filter) +int evlist__append_tp_filter(struct evlist *evlist, const char *filter) { struct evsel *evsel; int err = 0; @@ -1064,32 +1106,32 @@ out_free: return NULL; } -int perf_evlist__set_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids) +int evlist__set_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids) { char *filter = asprintf__tp_filter_pids(npids, pids); - int ret = perf_evlist__set_tp_filter(evlist, filter); + int ret = evlist__set_tp_filter(evlist, filter); free(filter); return ret; } -int perf_evlist__set_tp_filter_pid(struct evlist *evlist, pid_t pid) +int evlist__set_tp_filter_pid(struct evlist *evlist, pid_t pid) { - return perf_evlist__set_tp_filter_pids(evlist, 1, &pid); + return evlist__set_tp_filter_pids(evlist, 1, &pid); } -int perf_evlist__append_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids) +int evlist__append_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids) { char *filter = asprintf__tp_filter_pids(npids, pids); - int ret = perf_evlist__append_tp_filter(evlist, filter); + int ret = evlist__append_tp_filter(evlist, filter); free(filter); return ret; } -int perf_evlist__append_tp_filter_pid(struct evlist *evlist, pid_t pid) +int evlist__append_tp_filter_pid(struct evlist *evlist, pid_t pid) { - return perf_evlist__append_tp_filter_pids(evlist, 1, &pid); + return evlist__append_tp_filter_pids(evlist, 1, &pid); } bool evlist__valid_sample_type(struct evlist *evlist) @@ -1140,7 +1182,7 @@ u64 evlist__combined_branch_type(struct evlist *evlist) return branch_type; } -bool perf_evlist__valid_read_format(struct evlist *evlist) +bool evlist__valid_read_format(struct evlist *evlist) { struct evsel *first = evlist__first(evlist), *pos = first; u64 read_format = first->core.attr.read_format; @@ -1162,7 +1204,7 @@ bool perf_evlist__valid_read_format(struct evlist *evlist) return true; } -u16 perf_evlist__id_hdr_size(struct evlist *evlist) +u16 evlist__id_hdr_size(struct evlist *evlist) { struct evsel *first = evlist__first(evlist); struct perf_sample *data; @@ -1213,8 +1255,7 @@ bool evlist__sample_id_all(struct evlist *evlist) return first->core.attr.sample_id_all; } -void perf_evlist__set_selected(struct evlist *evlist, - struct evsel *evsel) +void evlist__set_selected(struct evlist *evlist, struct evsel *evsel) { evlist->selected = evsel; } @@ -1253,7 +1294,7 @@ void evlist__close(struct evlist *evlist) } } -static int perf_evlist__create_syswide_maps(struct evlist *evlist) +static int evlist__create_syswide_maps(struct evlist *evlist) { struct perf_cpu_map *cpus; struct perf_thread_map *threads; @@ -1295,12 +1336,12 @@ int evlist__open(struct evlist *evlist) * as sys_perf_event_open(cpu = -1, thread = -1) is EINVAL */ if (evlist->core.threads == NULL && evlist->core.cpus == NULL) { - err = perf_evlist__create_syswide_maps(evlist); + err = evlist__create_syswide_maps(evlist); if (err < 0) goto out_err; } - perf_evlist__update_id_pos(evlist); + evlist__update_id_pos(evlist); evlist__for_each_entry(evlist, evsel) { err = evsel__open(evsel, evsel->core.cpus, evsel->core.threads); @@ -1315,9 +1356,8 @@ out_err: return err; } -int perf_evlist__prepare_workload(struct evlist *evlist, struct target *target, - const char *argv[], bool pipe_output, - void (*exec_error)(int signo, siginfo_t *info, void *ucontext)) +int evlist__prepare_workload(struct evlist *evlist, struct target *target, const char *argv[], + bool pipe_output, void (*exec_error)(int signo, siginfo_t *info, void *ucontext)) { int child_ready_pipe[2], go_pipe[2]; char bf; @@ -1362,7 +1402,7 @@ int perf_evlist__prepare_workload(struct evlist *evlist, struct target *target, /* * The parent will ask for the execvp() to be performed by * writing exactly one byte, in workload.cork_fd, usually via - * perf_evlist__start_workload(). + * evlist__start_workload(). * * For cancelling the workload without actually running it, * the parent will just close workload.cork_fd, without writing @@ -1429,7 +1469,7 @@ out_close_ready_pipe: return -1; } -int perf_evlist__start_workload(struct evlist *evlist) +int evlist__start_workload(struct evlist *evlist) { if (evlist->workload.cork_fd > 0) { char bf = 0; @@ -1448,21 +1488,18 @@ int perf_evlist__start_workload(struct evlist *evlist) return 0; } -int perf_evlist__parse_sample(struct evlist *evlist, union perf_event *event, - struct perf_sample *sample) +int evlist__parse_sample(struct evlist *evlist, union perf_event *event, struct perf_sample *sample) { - struct evsel *evsel = perf_evlist__event2evsel(evlist, event); + struct evsel *evsel = evlist__event2evsel(evlist, event); if (!evsel) return -EFAULT; return evsel__parse_sample(evsel, event, sample); } -int perf_evlist__parse_sample_timestamp(struct evlist *evlist, - union perf_event *event, - u64 *timestamp) +int evlist__parse_sample_timestamp(struct evlist *evlist, union perf_event *event, u64 *timestamp) { - struct evsel *evsel = perf_evlist__event2evsel(evlist, event); + struct evsel *evsel = evlist__event2evsel(evlist, event); if (!evsel) return -EFAULT; @@ -1553,8 +1590,7 @@ int evlist__strerror_mmap(struct evlist *evlist, int err, char *buf, size_t size return 0; } -void perf_evlist__to_front(struct evlist *evlist, - struct evsel *move_evsel) +void evlist__to_front(struct evlist *evlist, struct evsel *move_evsel) { struct evsel *evsel, *n; LIST_HEAD(move); @@ -1570,7 +1606,7 @@ void perf_evlist__to_front(struct evlist *evlist, list_splice(&move, &evlist->core.entries); } -struct evsel *perf_evlist__get_tracking_event(struct evlist *evlist) +struct evsel *evlist__get_tracking_event(struct evlist *evlist) { struct evsel *evsel; @@ -1582,8 +1618,7 @@ struct evsel *perf_evlist__get_tracking_event(struct evlist *evlist) return evlist__first(evlist); } -void perf_evlist__set_tracking_event(struct evlist *evlist, - struct evsel *tracking_evsel) +void evlist__set_tracking_event(struct evlist *evlist, struct evsel *tracking_evsel) { struct evsel *evsel; @@ -1598,9 +1633,7 @@ void perf_evlist__set_tracking_event(struct evlist *evlist, tracking_evsel->tracking = true; } -struct evsel * -perf_evlist__find_evsel_by_str(struct evlist *evlist, - const char *str) +struct evsel *evlist__find_evsel_by_str(struct evlist *evlist, const char *str) { struct evsel *evsel; @@ -1614,8 +1647,7 @@ perf_evlist__find_evsel_by_str(struct evlist *evlist, return NULL; } -void perf_evlist__toggle_bkw_mmap(struct evlist *evlist, - enum bkw_mmap_state state) +void evlist__toggle_bkw_mmap(struct evlist *evlist, enum bkw_mmap_state state) { enum bkw_mmap_state old_state = evlist->bkw_mmap_state; enum action { @@ -1658,10 +1690,10 @@ void perf_evlist__toggle_bkw_mmap(struct evlist *evlist, switch (action) { case PAUSE: - perf_evlist__pause(evlist); + evlist__pause(evlist); break; case RESUME: - perf_evlist__resume(evlist); + evlist__resume(evlist); break; case NONE: default: @@ -1672,7 +1704,7 @@ state_err: return; } -bool perf_evlist__exclude_kernel(struct evlist *evlist) +bool evlist__exclude_kernel(struct evlist *evlist) { struct evsel *evsel; @@ -1689,19 +1721,17 @@ bool perf_evlist__exclude_kernel(struct evlist *evlist) * the group display. Set the artificial group and set the leader's * forced_leader flag to notify the display code. */ -void perf_evlist__force_leader(struct evlist *evlist) +void evlist__force_leader(struct evlist *evlist) { if (!evlist->nr_groups) { struct evsel *leader = evlist__first(evlist); - perf_evlist__set_leader(evlist); + evlist__set_leader(evlist); leader->forced_leader = true; } } -struct evsel *perf_evlist__reset_weak_group(struct evlist *evsel_list, - struct evsel *evsel, - bool close) +struct evsel *evlist__reset_weak_group(struct evlist *evsel_list, struct evsel *evsel, bool close) { struct evsel *c2, *leader; bool is_open = true; diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index e1a450322bc5..1aae75895dea 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -87,8 +87,8 @@ struct evsel_str_handler { }; struct evlist *evlist__new(void); -struct evlist *perf_evlist__new_default(void); -struct evlist *perf_evlist__new_dummy(void); +struct evlist *evlist__new_default(void); +struct evlist *evlist__new_dummy(void); void evlist__init(struct evlist *evlist, struct perf_cpu_map *cpus, struct perf_thread_map *threads); void evlist__exit(struct evlist *evlist); @@ -112,14 +112,11 @@ int __evlist__add_default_attrs(struct evlist *evlist, int evlist__add_dummy(struct evlist *evlist); -int perf_evlist__add_sb_event(struct evlist *evlist, - struct perf_event_attr *attr, - evsel__sb_cb_t cb, - void *data); +int evlist__add_sb_event(struct evlist *evlist, struct perf_event_attr *attr, + evsel__sb_cb_t cb, void *data); void evlist__set_cb(struct evlist *evlist, evsel__sb_cb_t cb, void *data); -int perf_evlist__start_sb_thread(struct evlist *evlist, - struct target *target); -void perf_evlist__stop_sb_thread(struct evlist *evlist); +int evlist__start_sb_thread(struct evlist *evlist, struct target *target); +void evlist__stop_sb_thread(struct evlist *evlist); int evlist__add_newtp(struct evlist *evlist, const char *sys, const char *name, void *handler); @@ -130,45 +127,29 @@ int __evlist__set_tracepoints_handlers(struct evlist *evlist, #define evlist__set_tracepoints_handlers(evlist, array) \ __evlist__set_tracepoints_handlers(evlist, array, ARRAY_SIZE(array)) -void __perf_evlist__set_sample_bit(struct evlist *evlist, - enum perf_event_sample_format bit); -void __perf_evlist__reset_sample_bit(struct evlist *evlist, - enum perf_event_sample_format bit); +int evlist__set_tp_filter(struct evlist *evlist, const char *filter); +int evlist__set_tp_filter_pid(struct evlist *evlist, pid_t pid); +int evlist__set_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids); -#define perf_evlist__set_sample_bit(evlist, bit) \ - __perf_evlist__set_sample_bit(evlist, PERF_SAMPLE_##bit) +int evlist__append_tp_filter(struct evlist *evlist, const char *filter); -#define perf_evlist__reset_sample_bit(evlist, bit) \ - __perf_evlist__reset_sample_bit(evlist, PERF_SAMPLE_##bit) +int evlist__append_tp_filter_pid(struct evlist *evlist, pid_t pid); +int evlist__append_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids); -int perf_evlist__set_tp_filter(struct evlist *evlist, const char *filter); -int perf_evlist__set_tp_filter_pid(struct evlist *evlist, pid_t pid); -int perf_evlist__set_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids); - -int perf_evlist__append_tp_filter(struct evlist *evlist, const char *filter); - -int perf_evlist__append_tp_filter_pid(struct evlist *evlist, pid_t pid); -int perf_evlist__append_tp_filter_pids(struct evlist *evlist, size_t npids, pid_t *pids); - -struct evsel * -perf_evlist__find_tracepoint_by_id(struct evlist *evlist, int id); - -struct evsel * -perf_evlist__find_tracepoint_by_name(struct evlist *evlist, - const char *name); +struct evsel *evlist__find_tracepoint_by_id(struct evlist *evlist, int id); +struct evsel *evlist__find_tracepoint_by_name(struct evlist *evlist, const char *name); int evlist__add_pollfd(struct evlist *evlist, int fd); int evlist__filter_pollfd(struct evlist *evlist, short revents_and_mask); int evlist__poll(struct evlist *evlist, int timeout); -struct evsel *perf_evlist__id2evsel(struct evlist *evlist, u64 id); -struct evsel *perf_evlist__id2evsel_strict(struct evlist *evlist, - u64 id); +struct evsel *evlist__id2evsel(struct evlist *evlist, u64 id); +struct evsel *evlist__id2evsel_strict(struct evlist *evlist, u64 id); -struct perf_sample_id *perf_evlist__id2sid(struct evlist *evlist, u64 id); +struct perf_sample_id *evlist__id2sid(struct evlist *evlist, u64 id); -void perf_evlist__toggle_bkw_mmap(struct evlist *evlist, enum bkw_mmap_state state); +void evlist__toggle_bkw_mmap(struct evlist *evlist, enum bkw_mmap_state state); void evlist__mmap_consume(struct evlist *evlist, int idx); @@ -177,24 +158,19 @@ void evlist__close(struct evlist *evlist); struct callchain_param; -void perf_evlist__set_id_pos(struct evlist *evlist); -void perf_evlist__config(struct evlist *evlist, struct record_opts *opts, - struct callchain_param *callchain); +void evlist__set_id_pos(struct evlist *evlist); +void evlist__config(struct evlist *evlist, struct record_opts *opts, struct callchain_param *callchain); int record_opts__config(struct record_opts *opts); -int perf_evlist__prepare_workload(struct evlist *evlist, - struct target *target, - const char *argv[], bool pipe_output, - void (*exec_error)(int signo, siginfo_t *info, - void *ucontext)); -int perf_evlist__start_workload(struct evlist *evlist); +int evlist__prepare_workload(struct evlist *evlist, struct target *target, + const char *argv[], bool pipe_output, + void (*exec_error)(int signo, siginfo_t *info, void *ucontext)); +int evlist__start_workload(struct evlist *evlist); struct option; -int __perf_evlist__parse_mmap_pages(unsigned int *mmap_pages, const char *str); -int perf_evlist__parse_mmap_pages(const struct option *opt, - const char *str, - int unset); +int __evlist__parse_mmap_pages(unsigned int *mmap_pages, const char *str); +int evlist__parse_mmap_pages(const struct option *opt, const char *str, int unset); unsigned long perf_event_mlock_kb_in_pages(void); @@ -209,41 +185,36 @@ size_t evlist__mmap_size(unsigned long pages); void evlist__disable(struct evlist *evlist); void evlist__enable(struct evlist *evlist); -void perf_evlist__toggle_enable(struct evlist *evlist); +void evlist__toggle_enable(struct evlist *evlist); +void evlist__disable_evsel(struct evlist *evlist, char *evsel_name); +void evlist__enable_evsel(struct evlist *evlist, char *evsel_name); -int perf_evlist__enable_event_idx(struct evlist *evlist, - struct evsel *evsel, int idx); +int evlist__enable_event_idx(struct evlist *evlist, struct evsel *evsel, int idx); -void perf_evlist__set_selected(struct evlist *evlist, - struct evsel *evsel); +void evlist__set_selected(struct evlist *evlist, struct evsel *evsel); -int perf_evlist__create_maps(struct evlist *evlist, struct target *target); -int perf_evlist__apply_filters(struct evlist *evlist, struct evsel **err_evsel); +int evlist__create_maps(struct evlist *evlist, struct target *target); +int evlist__apply_filters(struct evlist *evlist, struct evsel **err_evsel); -void __perf_evlist__set_leader(struct list_head *list); -void perf_evlist__set_leader(struct evlist *evlist); +void __evlist__set_leader(struct list_head *list); +void evlist__set_leader(struct evlist *evlist); u64 __evlist__combined_sample_type(struct evlist *evlist); u64 evlist__combined_sample_type(struct evlist *evlist); u64 evlist__combined_branch_type(struct evlist *evlist); bool evlist__sample_id_all(struct evlist *evlist); -u16 perf_evlist__id_hdr_size(struct evlist *evlist); - -int perf_evlist__parse_sample(struct evlist *evlist, union perf_event *event, - struct perf_sample *sample); +u16 evlist__id_hdr_size(struct evlist *evlist); -int perf_evlist__parse_sample_timestamp(struct evlist *evlist, - union perf_event *event, - u64 *timestamp); +int evlist__parse_sample(struct evlist *evlist, union perf_event *event, struct perf_sample *sample); +int evlist__parse_sample_timestamp(struct evlist *evlist, union perf_event *event, u64 *timestamp); bool evlist__valid_sample_type(struct evlist *evlist); bool evlist__valid_sample_id_all(struct evlist *evlist); -bool perf_evlist__valid_read_format(struct evlist *evlist); +bool evlist__valid_read_format(struct evlist *evlist); -void perf_evlist__splice_list_tail(struct evlist *evlist, - struct list_head *list); +void evlist__splice_list_tail(struct evlist *evlist, struct list_head *list); -static inline bool perf_evlist__empty(struct evlist *evlist) +static inline bool evlist__empty(struct evlist *evlist) { return list_empty(&evlist->core.entries); } @@ -265,9 +236,8 @@ static inline struct evsel *evlist__last(struct evlist *evlist) int evlist__strerror_open(struct evlist *evlist, int err, char *buf, size_t size); int evlist__strerror_mmap(struct evlist *evlist, int err, char *buf, size_t size); -bool perf_evlist__can_select_event(struct evlist *evlist, const char *str); -void perf_evlist__to_front(struct evlist *evlist, - struct evsel *move_evsel); +bool evlist__can_select_event(struct evlist *evlist, const char *str); +void evlist__to_front(struct evlist *evlist, struct evsel *move_evsel); /** * __evlist__for_each_entry - iterate thru all the evsels @@ -339,27 +309,23 @@ void perf_evlist__to_front(struct evlist *evlist, evlist__cpu_iter_start(evlist); \ perf_cpu_map__for_each_cpu (cpu, index, (evlist)->core.all_cpus) -struct evsel *perf_evlist__get_tracking_event(struct evlist *evlist); -void perf_evlist__set_tracking_event(struct evlist *evlist, - struct evsel *tracking_evsel); +struct evsel *evlist__get_tracking_event(struct evlist *evlist); +void evlist__set_tracking_event(struct evlist *evlist, struct evsel *tracking_evsel); void evlist__cpu_iter_start(struct evlist *evlist); bool evsel__cpu_iter_skip(struct evsel *ev, int cpu); bool evsel__cpu_iter_skip_no_inc(struct evsel *ev, int cpu); -struct evsel * -perf_evlist__find_evsel_by_str(struct evlist *evlist, const char *str); +struct evsel *evlist__find_evsel_by_str(struct evlist *evlist, const char *str); + +struct evsel *evlist__event2evsel(struct evlist *evlist, union perf_event *event); -struct evsel *perf_evlist__event2evsel(struct evlist *evlist, - union perf_event *event); +bool evlist__exclude_kernel(struct evlist *evlist); -bool perf_evlist__exclude_kernel(struct evlist *evlist); +void evlist__force_leader(struct evlist *evlist); -void perf_evlist__force_leader(struct evlist *evlist); +struct evsel *evlist__reset_weak_group(struct evlist *evlist, struct evsel *evsel, bool close); -struct evsel *perf_evlist__reset_weak_group(struct evlist *evlist, - struct evsel *evsel, - bool close); #define EVLIST_CTL_CMD_ENABLE_TAG "enable" #define EVLIST_CTL_CMD_DISABLE_TAG "disable" #define EVLIST_CTL_CMD_ACK_TAG "ack\n" diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 1cad6051d8b0..c26ea82220bd 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -497,7 +497,7 @@ static const char *__evsel__hw_name(u64 config) return "unknown-hardware"; } -static int perf_evsel__add_modifiers(struct evsel *evsel, char *bf, size_t size) +static int evsel__add_modifiers(struct evsel *evsel, char *bf, size_t size) { int colon = 0, r = 0; struct perf_event_attr *attr = &evsel->core.attr; @@ -536,7 +536,7 @@ static int perf_evsel__add_modifiers(struct evsel *evsel, char *bf, size_t size) static int evsel__hw_name(struct evsel *evsel, char *bf, size_t size) { int r = scnprintf(bf, size, "%s", __evsel__hw_name(evsel->core.attr.config)); - return r + perf_evsel__add_modifiers(evsel, bf + r, size - r); + return r + evsel__add_modifiers(evsel, bf + r, size - r); } const char *evsel__sw_names[PERF_COUNT_SW_MAX] = { @@ -562,7 +562,7 @@ static const char *__evsel__sw_name(u64 config) static int evsel__sw_name(struct evsel *evsel, char *bf, size_t size) { int r = scnprintf(bf, size, "%s", __evsel__sw_name(evsel->core.attr.config)); - return r + perf_evsel__add_modifiers(evsel, bf + r, size - r); + return r + evsel__add_modifiers(evsel, bf + r, size - r); } static int __evsel__bp_name(char *bf, size_t size, u64 addr, u64 type) @@ -587,7 +587,7 @@ static int evsel__bp_name(struct evsel *evsel, char *bf, size_t size) { struct perf_event_attr *attr = &evsel->core.attr; int r = __evsel__bp_name(bf, size, attr->bp_addr, attr->bp_type); - return r + perf_evsel__add_modifiers(evsel, bf + r, size - r); + return r + evsel__add_modifiers(evsel, bf + r, size - r); } const char *evsel__hw_cache[PERF_COUNT_HW_CACHE_MAX][EVSEL__MAX_ALIASES] = { @@ -682,13 +682,13 @@ out_err: static int evsel__hw_cache_name(struct evsel *evsel, char *bf, size_t size) { int ret = __evsel__hw_cache_name(evsel->core.attr.config, bf, size); - return ret + perf_evsel__add_modifiers(evsel, bf + ret, size - ret); + return ret + evsel__add_modifiers(evsel, bf + ret, size - ret); } static int evsel__raw_name(struct evsel *evsel, char *bf, size_t size) { int ret = scnprintf(bf, size, "raw 0x%" PRIx64, evsel->core.attr.config); - return ret + perf_evsel__add_modifiers(evsel, bf + ret, size - ret); + return ret + evsel__add_modifiers(evsel, bf + ret, size - ret); } static int evsel__tool_name(char *bf, size_t size) @@ -850,9 +850,7 @@ void evsel__config_callchain(struct evsel *evsel, struct record_opts *opts, return __evsel__config_callchain(evsel, opts, param); } -static void -perf_evsel__reset_callgraph(struct evsel *evsel, - struct callchain_param *param) +static void evsel__reset_callgraph(struct evsel *evsel, struct callchain_param *param) { struct perf_event_attr *attr = &evsel->core.attr; @@ -988,7 +986,7 @@ static void evsel__apply_config_terms(struct evsel *evsel, /* If global callgraph set, clear it */ if (callchain_param.enabled) - perf_evsel__reset_callgraph(evsel, &callchain_param); + evsel__reset_callgraph(evsel, &callchain_param); /* set perf-event callgraph */ if (param.enabled) { @@ -1190,6 +1188,9 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts, evsel__set_sample_bit(evsel, CGROUP); } + if (opts->sample_data_page_size) + evsel__set_sample_bit(evsel, DATA_PAGE_SIZE); + if (opts->record_switch_events) attr->context_switch = track; @@ -1434,9 +1435,7 @@ static int evsel__read_one(struct evsel *evsel, int cpu, int thread) return perf_evsel__read(&evsel->core, cpu, thread, count); } -static void -perf_evsel__set_count(struct evsel *counter, int cpu, int thread, - u64 val, u64 ena, u64 run) +static void evsel__set_count(struct evsel *counter, int cpu, int thread, u64 val, u64 ena, u64 run) { struct perf_counts_values *count; @@ -1449,9 +1448,7 @@ perf_evsel__set_count(struct evsel *counter, int cpu, int thread, perf_counts__set_loaded(counter->counts, cpu, thread, true); } -static int -perf_evsel__process_group_data(struct evsel *leader, - int cpu, int thread, u64 *data) +static int evsel__process_group_data(struct evsel *leader, int cpu, int thread, u64 *data) { u64 read_format = leader->core.attr.read_format; struct sample_read_value *v; @@ -1470,18 +1467,16 @@ perf_evsel__process_group_data(struct evsel *leader, v = (struct sample_read_value *) data; - perf_evsel__set_count(leader, cpu, thread, - v[0].value, ena, run); + evsel__set_count(leader, cpu, thread, v[0].value, ena, run); for (i = 1; i < nr; i++) { struct evsel *counter; - counter = perf_evlist__id2evsel(leader->evlist, v[i].id); + counter = evlist__id2evsel(leader->evlist, v[i].id); if (!counter) return -EINVAL; - perf_evsel__set_count(counter, cpu, thread, - v[i].value, ena, run); + evsel__set_count(counter, cpu, thread, v[i].value, ena, run); } return 0; @@ -1514,7 +1509,7 @@ static int evsel__read_group(struct evsel *leader, int cpu, int thread) if (readn(FD(leader, cpu, thread), data, size) <= 0) return -errno; - return perf_evsel__process_group_data(leader, cpu, thread, data); + return evsel__process_group_data(leader, cpu, thread, data); } int evsel__read_counter(struct evsel *evsel, int cpu, int thread) @@ -1567,9 +1562,7 @@ static int get_group_fd(struct evsel *evsel, int cpu, int thread) return fd; } -static void perf_evsel__remove_fd(struct evsel *pos, - int nr_cpus, int nr_threads, - int thread_idx) +static void evsel__remove_fd(struct evsel *pos, int nr_cpus, int nr_threads, int thread_idx) { for (int cpu = 0; cpu < nr_cpus; cpu++) for (int thread = thread_idx; thread < nr_threads - 1; thread++) @@ -1588,7 +1581,7 @@ static int update_fds(struct evsel *evsel, evlist__for_each_entry(evsel->evlist, pos) { nr_cpus = pos != evsel ? nr_cpus : cpu_idx; - perf_evsel__remove_fd(pos, nr_cpus, nr_threads, thread_idx); + evsel__remove_fd(pos, nr_cpus, nr_threads, thread_idx); /* * Since fds for next evsel has not been created, @@ -1880,7 +1873,12 @@ try_fallback: * Must probe features in the order they were added to the * perf_event_attr interface. */ - if (!perf_missing_features.cgroup && evsel->core.attr.cgroup) { + if (!perf_missing_features.data_page_size && + (evsel->core.attr.sample_type & PERF_SAMPLE_DATA_PAGE_SIZE)) { + perf_missing_features.data_page_size = true; + pr_debug2_peo("Kernel has no PERF_SAMPLE_DATA_PAGE_SIZE support, bailing out\n"); + goto out_close; + } else if (!perf_missing_features.cgroup && evsel->core.attr.cgroup) { perf_missing_features.cgroup = true; pr_debug2_peo("Kernel has no cgroup sampling support, bailing out\n"); goto out_close; @@ -2365,6 +2363,12 @@ int evsel__parse_sample(struct evsel *evsel, union perf_event *event, array++; } + data->data_page_size = 0; + if (type & PERF_SAMPLE_DATA_PAGE_SIZE) { + data->data_page_size = *array; + array++; + } + if (type & PERF_SAMPLE_AUX) { OVERFLOW_CHECK_u64(array); sz = *array++; @@ -2674,6 +2678,8 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target, "We found oprofile daemon running, please stop it and try again."); break; case EINVAL: + if (evsel->core.attr.sample_type & PERF_SAMPLE_DATA_PAGE_SIZE && perf_missing_features.data_page_size) + return scnprintf(msg, size, "Asking for the data page size isn't supported by this kernel."); if (evsel->core.attr.write_backward && perf_missing_features.write_backward) return scnprintf(msg, size, "Reading from overwrite event is not supported by this kernel."); if (perf_missing_features.clockid) diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 79a860d8e3ee..cd1d8dd43199 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -144,6 +144,7 @@ struct perf_missing_features { bool aux_output; bool branch_hw_idx; bool cgroup; + bool data_page_size; }; extern struct perf_missing_features perf_missing_features; diff --git a/tools/perf/util/evswitch.c b/tools/perf/util/evswitch.c index 3ba72f743d3c..40cb56a9347d 100644 --- a/tools/perf/util/evswitch.c +++ b/tools/perf/util/evswitch.c @@ -41,7 +41,7 @@ static int evswitch__fprintf_enoent(FILE *fp, const char *evtype, const char *ev int evswitch__init(struct evswitch *evswitch, struct evlist *evlist, FILE *fp) { if (evswitch->on_name) { - evswitch->on = perf_evlist__find_evsel_by_str(evlist, evswitch->on_name); + evswitch->on = evlist__find_evsel_by_str(evlist, evswitch->on_name); if (evswitch->on == NULL) { evswitch__fprintf_enoent(fp, "on", evswitch->on_name); return -ENOENT; @@ -50,7 +50,7 @@ int evswitch__init(struct evswitch *evswitch, struct evlist *evlist, FILE *fp) } if (evswitch->off_name) { - evswitch->off = perf_evlist__find_evsel_by_str(evlist, evswitch->off_name); + evswitch->off = evlist__find_evsel_by_str(evlist, evswitch->off_name); if (evswitch->off == NULL) { evswitch__fprintf_enoent(fp, "off", evswitch->off_name); return -ENOENT; diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c index 53482ef53c41..a850fd0be3ee 100644 --- a/tools/perf/util/expr.c +++ b/tools/perf/util/expr.c @@ -17,6 +17,29 @@ extern int expr_debug; #endif +struct expr_id_data { + union { + double val; + struct { + double val; + const char *metric_name; + const char *metric_expr; + } ref; + struct expr_id *parent; + }; + + enum { + /* Holding a double value. */ + EXPR_ID_DATA__VALUE, + /* Reference to another metric. */ + EXPR_ID_DATA__REF, + /* A reference but the value has been computed. */ + EXPR_ID_DATA__REF_VALUE, + /* A parent is remembered for the recursion check. */ + EXPR_ID_DATA__PARENT, + } kind; +}; + static size_t key_hash(const void *key, void *ctx __maybe_unused) { const char *str = (const char *)key; @@ -48,6 +71,7 @@ int expr__add_id(struct expr_parse_ctx *ctx, const char *id) return -ENOMEM; data_ptr->parent = ctx->parent; + data_ptr->kind = EXPR_ID_DATA__PARENT; ret = hashmap__set(&ctx->ids, id, data_ptr, (const void **)&old_key, (void **)&old_data); @@ -69,7 +93,7 @@ int expr__add_id_val(struct expr_parse_ctx *ctx, const char *id, double val) if (!data_ptr) return -ENOMEM; data_ptr->val = val; - data_ptr->is_ref = false; + data_ptr->kind = EXPR_ID_DATA__VALUE; ret = hashmap__set(&ctx->ids, id, data_ptr, (const void **)&old_key, (void **)&old_data); @@ -114,8 +138,7 @@ int expr__add_ref(struct expr_parse_ctx *ctx, struct metric_ref *ref) */ data_ptr->ref.metric_name = ref->metric_name; data_ptr->ref.metric_expr = ref->metric_expr; - data_ptr->ref.counted = false; - data_ptr->is_ref = true; + data_ptr->kind = EXPR_ID_DATA__REF; ret = hashmap__set(&ctx->ids, name, data_ptr, (const void **)&old_key, (void **)&old_data); @@ -148,17 +171,30 @@ int expr__resolve_id(struct expr_parse_ctx *ctx, const char *id, data = *datap; - pr_debug2("lookup: is_ref %d, counted %d, val %f: %s\n", - data->is_ref, data->ref.counted, data->val, id); - - if (data->is_ref && !data->ref.counted) { - data->ref.counted = true; + switch (data->kind) { + case EXPR_ID_DATA__VALUE: + pr_debug2("lookup(%s): val %f\n", id, data->val); + break; + case EXPR_ID_DATA__PARENT: + pr_debug2("lookup(%s): parent %s\n", id, data->parent->id); + break; + case EXPR_ID_DATA__REF: + pr_debug2("lookup(%s): ref metric name %s\n", id, + data->ref.metric_name); pr_debug("processing metric: %s ENTRY\n", id); - if (expr__parse(&data->val, ctx, data->ref.metric_expr, 1)) { + data->kind = EXPR_ID_DATA__REF_VALUE; + if (expr__parse(&data->ref.val, ctx, data->ref.metric_expr, 1)) { pr_debug("%s failed to count\n", id); return -1; } pr_debug("processing metric: %s EXIT: %f\n", id, data->val); + break; + case EXPR_ID_DATA__REF_VALUE: + pr_debug2("lookup(%s): ref val %f metric name %s\n", id, + data->ref.val, data->ref.metric_name); + break; + default: + assert(0); /* Unreachable. */ } return 0; @@ -241,3 +277,17 @@ int expr__find_other(const char *expr, const char *one, return ret; } + +double expr_id_data__value(const struct expr_id_data *data) +{ + if (data->kind == EXPR_ID_DATA__VALUE) + return data->val; + assert(data->kind == EXPR_ID_DATA__REF_VALUE); + return data->ref.val; +} + +struct expr_id *expr_id_data__parent(struct expr_id_data *data) +{ + assert(data->kind == EXPR_ID_DATA__PARENT); + return data->parent; +} diff --git a/tools/perf/util/expr.h b/tools/perf/util/expr.h index fc2b5e824a66..dcf8d19b83c8 100644 --- a/tools/perf/util/expr.h +++ b/tools/perf/util/expr.h @@ -23,19 +23,7 @@ struct expr_parse_ctx { struct expr_id *parent; }; -struct expr_id_data { - union { - double val; - struct { - const char *metric_name; - const char *metric_expr; - bool counted; - } ref; - struct expr_id *parent; - }; - - bool is_ref; -}; +struct expr_id_data; struct expr_scanner_ctx { int start_token; @@ -57,4 +45,7 @@ int expr__parse(double *final_val, struct expr_parse_ctx *ctx, int expr__find_other(const char *expr, const char *one, struct expr_parse_ctx *ids, int runtime); +double expr_id_data__value(const struct expr_id_data *data); +struct expr_id *expr_id_data__parent(struct expr_id_data *data); + #endif diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y index d34b370391c6..b2ada8f8309a 100644 --- a/tools/perf/util/expr.y +++ b/tools/perf/util/expr.y @@ -93,7 +93,7 @@ expr: NUMBER YYABORT; } - $$ = data->val; + $$ = expr_id_data__value(data); free($1); } | expr '|' expr { $$ = (long)$1 | (long)$3; } diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index be850e9f8852..062383e225a3 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -19,7 +19,9 @@ #include <sys/utsname.h> #include <linux/time64.h> #include <dirent.h> +#ifdef HAVE_LIBBPF_SUPPORT #include <bpf/libbpf.h> +#endif #include <perf/cpumap.h> #include "dso.h" @@ -987,13 +989,6 @@ out: up_read(&env->bpf_progs.lock); return ret; } -#else // HAVE_LIBBPF_SUPPORT -static int write_bpf_prog_info(struct feat_fd *ff __maybe_unused, - struct evlist *evlist __maybe_unused) -{ - return 0; -} -#endif // HAVE_LIBBPF_SUPPORT static int write_bpf_btf(struct feat_fd *ff, struct evlist *evlist __maybe_unused) @@ -1027,6 +1022,7 @@ out: up_read(&env->bpf_progs.lock); return ret; } +#endif // HAVE_LIBBPF_SUPPORT static int cpu_cache_level__sort(const void *a, const void *b) { @@ -1638,6 +1634,7 @@ static void print_dir_format(struct feat_fd *ff, FILE *fp) fprintf(fp, "# directory data version : %"PRIu64"\n", data->dir.version); } +#ifdef HAVE_LIBBPF_SUPPORT static void print_bpf_prog_info(struct feat_fd *ff, FILE *fp) { struct perf_env *env = &ff->ph->env; @@ -1683,6 +1680,7 @@ static void print_bpf_btf(struct feat_fd *ff, FILE *fp) up_read(&env->bpf_progs.lock); } +#endif // HAVE_LIBBPF_SUPPORT static void free_event_desc(struct evsel *events) { @@ -2265,8 +2263,7 @@ static int process_total_mem(struct feat_fd *ff, void *data __maybe_unused) return 0; } -static struct evsel * -perf_evlist__find_by_index(struct evlist *evlist, int idx) +static struct evsel *evlist__find_by_index(struct evlist *evlist, int idx) { struct evsel *evsel; @@ -2278,16 +2275,14 @@ perf_evlist__find_by_index(struct evlist *evlist, int idx) return NULL; } -static void -perf_evlist__set_event_name(struct evlist *evlist, - struct evsel *event) +static void evlist__set_event_name(struct evlist *evlist, struct evsel *event) { struct evsel *evsel; if (!event->name) return; - evsel = perf_evlist__find_by_index(evlist, event->idx); + evsel = evlist__find_by_index(evlist, event->idx); if (!evsel) return; @@ -2315,7 +2310,7 @@ process_event_desc(struct feat_fd *ff, void *data __maybe_unused) } for (evsel = events; evsel->core.attr.size; evsel++) - perf_evlist__set_event_name(session->evlist, evsel); + evlist__set_event_name(session->evlist, evsel); if (!session->data->is_pipe) free_event_desc(events); @@ -2938,12 +2933,6 @@ out: up_write(&env->bpf_progs.lock); return err; } -#else // HAVE_LIBBPF_SUPPORT -static int process_bpf_prog_info(struct feat_fd *ff __maybe_unused, void *data __maybe_unused) -{ - return 0; -} -#endif // HAVE_LIBBPF_SUPPORT static int process_bpf_btf(struct feat_fd *ff, void *data __maybe_unused) { @@ -2990,6 +2979,7 @@ out: free(node); return err; } +#endif // HAVE_LIBBPF_SUPPORT static int process_compressed(struct feat_fd *ff, void *data __maybe_unused) @@ -3120,8 +3110,10 @@ const struct perf_header_feature_ops feat_ops[HEADER_LAST_FEATURE] = { FEAT_OPR(MEM_TOPOLOGY, mem_topology, true), FEAT_OPR(CLOCKID, clockid, false), FEAT_OPN(DIR_FORMAT, dir_format, false), +#ifdef HAVE_LIBBPF_SUPPORT FEAT_OPR(BPF_PROG_INFO, bpf_prog_info, false), FEAT_OPR(BPF_BTF, bpf_btf, false), +#endif FEAT_OPR(COMPRESSED, compressed, false), FEAT_OPR(CPU_PMU_CAPS, cpu_pmu_caps, false), FEAT_OPR(CLOCK_DATA, clock_data, false), @@ -3652,7 +3644,8 @@ static int perf_file_section__process(struct perf_file_section *section, } static int perf_file_header__read_pipe(struct perf_pipe_file_header *header, - struct perf_header *ph, int fd, + struct perf_header *ph, + struct perf_data* data, bool repipe) { struct feat_fd ff = { @@ -3661,7 +3654,7 @@ static int perf_file_header__read_pipe(struct perf_pipe_file_header *header, }; ssize_t ret; - ret = readn(fd, header, sizeof(*header)); + ret = perf_data__read(data, header, sizeof(*header)); if (ret <= 0) return -1; @@ -3684,8 +3677,7 @@ static int perf_header__read_pipe(struct perf_session *session) struct perf_header *header = &session->header; struct perf_pipe_file_header f_header; - if (perf_file_header__read_pipe(&f_header, header, - perf_data__fd(session->data), + if (perf_file_header__read_pipe(&f_header, header, session->data, session->repipe) < 0) { pr_debug("incompatible file format\n"); return -EINVAL; @@ -3740,8 +3732,7 @@ static int read_attr(int fd, struct perf_header *ph, return ret <= 0 ? -1 : 0; } -static int perf_evsel__prepare_tracepoint_event(struct evsel *evsel, - struct tep_handle *pevent) +static int evsel__prepare_tracepoint_event(struct evsel *evsel, struct tep_handle *pevent) { struct tep_event *event; char bf[128]; @@ -3772,14 +3763,13 @@ static int perf_evsel__prepare_tracepoint_event(struct evsel *evsel, return 0; } -static int perf_evlist__prepare_tracepoint_events(struct evlist *evlist, - struct tep_handle *pevent) +static int evlist__prepare_tracepoint_events(struct evlist *evlist, struct tep_handle *pevent) { struct evsel *pos; evlist__for_each_entry(evlist, pos) { if (pos->core.attr.type == PERF_TYPE_TRACEPOINT && - perf_evsel__prepare_tracepoint_event(pos, pevent)) + evsel__prepare_tracepoint_event(pos, pevent)) return -1; } @@ -3888,8 +3878,7 @@ int perf_session__read_header(struct perf_session *session) perf_header__process_sections(header, fd, &session->tevent, perf_file_section__process); - if (perf_evlist__prepare_tracepoint_events(session->evlist, - session->tevent.pevent)) + if (evlist__prepare_tracepoint_events(session->evlist, session->tevent.pevent)) goto out_delete_evlist; return 0; @@ -4037,7 +4026,7 @@ int perf_event__process_event_update(struct perf_tool *tool __maybe_unused, evlist = *pevlist; - evsel = perf_evlist__id2evsel(evlist, ev->id); + evsel = evlist__id2evsel(evlist, ev->id); if (evsel == NULL) return -EINVAL; @@ -4110,8 +4099,7 @@ int perf_event__process_tracing_data(struct perf_session *session, return -1; } - perf_evlist__prepare_tracepoint_events(session->evlist, - session->tevent.pevent); + evlist__prepare_tracepoint_events(session->evlist, session->tevent.pevent); return size_read + padding; } diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 8a793e4c9400..a08fb9ea411b 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -188,6 +188,9 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) hists__new_col_len(hists, HISTC_MEM_PHYS_DADDR, unresolved_col_width + 4 + 2); + hists__new_col_len(hists, HISTC_MEM_DATA_PAGE_SIZE, + unresolved_col_width + 4 + 2); + } else { symlen = unresolved_col_width + 4 + 2; hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL, symlen); @@ -2654,7 +2657,7 @@ void hist__account_cycles(struct branch_stack *bs, struct addr_location *al, } } -size_t perf_evlist__fprintf_nr_events(struct evlist *evlist, FILE *fp) +size_t evlist__fprintf_nr_events(struct evlist *evlist, FILE *fp) { struct evsel *pos; size_t ret = 0; diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 96b1c13bbccc..14f66330923d 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -56,6 +56,7 @@ enum hist_column { HISTC_MEM_DADDR_SYMBOL, HISTC_MEM_DADDR_DSO, HISTC_MEM_PHYS_DADDR, + HISTC_MEM_DATA_PAGE_SIZE, HISTC_MEM_LOCKED, HISTC_MEM_TLB, HISTC_MEM_LVL, @@ -196,7 +197,7 @@ void hists__inc_nr_samples(struct hists *hists, bool filtered); size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, int max_cols, float min_pcnt, FILE *fp, bool ignore_callchains); -size_t perf_evlist__fprintf_nr_events(struct evlist *evlist, FILE *fp); +size_t evlist__fprintf_nr_events(struct evlist *evlist, FILE *fp); void hists__filter_by_dso(struct hists *hists); void hists__filter_by_thread(struct hists *hists); @@ -464,12 +465,9 @@ int hist_entry__tui_annotate(struct hist_entry *he, struct evsel *evsel, struct hist_browser_timer *hbt, struct annotation_options *annotation_opts); -int perf_evlist__tui_browse_hists(struct evlist *evlist, const char *help, - struct hist_browser_timer *hbt, - float min_pcnt, - struct perf_env *env, - bool warn_lost_event, - struct annotation_options *annotation_options); +int evlist__tui_browse_hists(struct evlist *evlist, const char *help, struct hist_browser_timer *hbt, + float min_pcnt, struct perf_env *env, bool warn_lost_event, + struct annotation_options *annotation_options); int script_browse(const char *script_opt, struct evsel *evsel); @@ -483,13 +481,13 @@ int block_hists_tui_browse(struct block_hist *bh, struct evsel *evsel, struct annotation_options *annotation_opts); #else static inline -int perf_evlist__tui_browse_hists(struct evlist *evlist __maybe_unused, - const char *help __maybe_unused, - struct hist_browser_timer *hbt __maybe_unused, - float min_pcnt __maybe_unused, - struct perf_env *env __maybe_unused, - bool warn_lost_event __maybe_unused, - struct annotation_options *annotation_options __maybe_unused) +int evlist__tui_browse_hists(struct evlist *evlist __maybe_unused, + const char *help __maybe_unused, + struct hist_browser_timer *hbt __maybe_unused, + float min_pcnt __maybe_unused, + struct perf_env *env __maybe_unused, + bool warn_lost_event __maybe_unused, + struct annotation_options *annotation_options __maybe_unused) { return 0; } diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 3a0348caec7d..60214de42f31 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -2520,11 +2520,10 @@ static int intel_pt_sync_switch(struct intel_pt *pt, int cpu, pid_t tid, static int intel_pt_process_switch(struct intel_pt *pt, struct perf_sample *sample) { - struct evsel *evsel; pid_t tid; int cpu, ret; + struct evsel *evsel = evlist__id2evsel(pt->session->evlist, sample->id); - evsel = perf_evlist__id2evsel(pt->session->evlist, sample->id); if (evsel != pt->switch_evsel) return 0; diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 15385ea00190..f841f3503cae 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1581,32 +1581,25 @@ static bool machine__uses_kcore(struct machine *machine) } static bool perf_event__is_extra_kernel_mmap(struct machine *machine, - union perf_event *event) + struct extra_kernel_map *xm) { return machine__is(machine, "x86_64") && - is_entry_trampoline(event->mmap.filename); + is_entry_trampoline(xm->name); } static int machine__process_extra_kernel_map(struct machine *machine, - union perf_event *event) + struct extra_kernel_map *xm) { struct dso *kernel = machine__kernel_dso(machine); - struct extra_kernel_map xm = { - .start = event->mmap.start, - .end = event->mmap.start + event->mmap.len, - .pgoff = event->mmap.pgoff, - }; if (kernel == NULL) return -1; - strlcpy(xm.name, event->mmap.filename, KMAP_NAME_LEN); - - return machine__create_extra_kernel_map(machine, kernel, &xm); + return machine__create_extra_kernel_map(machine, kernel, xm); } static int machine__process_kernel_mmap_event(struct machine *machine, - union perf_event *event) + struct extra_kernel_map *xm) { struct map *map; enum dso_space_type dso_space; @@ -1621,20 +1614,18 @@ static int machine__process_kernel_mmap_event(struct machine *machine, else dso_space = DSO_SPACE__KERNEL_GUEST; - is_kernel_mmap = memcmp(event->mmap.filename, - machine->mmap_name, + is_kernel_mmap = memcmp(xm->name, machine->mmap_name, strlen(machine->mmap_name) - 1) == 0; - if (event->mmap.filename[0] == '/' || - (!is_kernel_mmap && event->mmap.filename[0] == '[')) { - map = machine__addnew_module_map(machine, event->mmap.start, - event->mmap.filename); + if (xm->name[0] == '/' || + (!is_kernel_mmap && xm->name[0] == '[')) { + map = machine__addnew_module_map(machine, xm->start, + xm->name); if (map == NULL) goto out_problem; - map->end = map->start + event->mmap.len; + map->end = map->start + xm->end - xm->start; } else if (is_kernel_mmap) { - const char *symbol_name = (event->mmap.filename + - strlen(machine->mmap_name)); + const char *symbol_name = (xm->name + strlen(machine->mmap_name)); /* * Should be there already, from the build-id table in * the header. @@ -1688,18 +1679,17 @@ static int machine__process_kernel_mmap_event(struct machine *machine, if (strstr(kernel->long_name, "vmlinux")) dso__set_short_name(kernel, "[kernel.vmlinux]", false); - machine__update_kernel_mmap(machine, event->mmap.start, - event->mmap.start + event->mmap.len); + machine__update_kernel_mmap(machine, xm->start, xm->end); /* * Avoid using a zero address (kptr_restrict) for the ref reloc * symbol. Effectively having zero here means that at record * time /proc/sys/kernel/kptr_restrict was non zero. */ - if (event->mmap.pgoff != 0) { + if (xm->pgoff != 0) { map__set_kallsyms_ref_reloc_sym(machine->vmlinux_map, symbol_name, - event->mmap.pgoff); + xm->pgoff); } if (machine__is_default_guest(machine)) { @@ -1708,8 +1698,8 @@ static int machine__process_kernel_mmap_event(struct machine *machine, */ dso__load(kernel, machine__kernel_map(machine)); } - } else if (perf_event__is_extra_kernel_mmap(machine, event)) { - return machine__process_extra_kernel_map(machine, event); + } else if (perf_event__is_extra_kernel_mmap(machine, xm)) { + return machine__process_extra_kernel_map(machine, xm); } return 0; out_problem: @@ -1735,7 +1725,14 @@ int machine__process_mmap2_event(struct machine *machine, if (sample->cpumode == PERF_RECORD_MISC_GUEST_KERNEL || sample->cpumode == PERF_RECORD_MISC_KERNEL) { - ret = machine__process_kernel_mmap_event(machine, event); + struct extra_kernel_map xm = { + .start = event->mmap2.start, + .end = event->mmap2.start + event->mmap2.len, + .pgoff = event->mmap2.pgoff, + }; + + strlcpy(xm.name, event->mmap2.filename, KMAP_NAME_LEN); + ret = machine__process_kernel_mmap_event(machine, &xm); if (ret < 0) goto out_problem; return 0; @@ -1785,7 +1782,14 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event if (sample->cpumode == PERF_RECORD_MISC_GUEST_KERNEL || sample->cpumode == PERF_RECORD_MISC_KERNEL) { - ret = machine__process_kernel_mmap_event(machine, event); + struct extra_kernel_map xm = { + .start = event->mmap.start, + .end = event->mmap.start + event->mmap.len, + .pgoff = event->mmap.pgoff, + }; + + strlcpy(xm.name, event->mmap.filename, KMAP_NAME_LEN); + ret = machine__process_kernel_mmap_event(machine, &xm); if (ret < 0) goto out_problem; return 0; @@ -2019,11 +2023,12 @@ static void ip__resolve_ams(struct thread *thread, ams->ms.sym = al.sym; ams->ms.map = al.map; ams->phys_addr = 0; + ams->data_page_size = 0; } static void ip__resolve_data(struct thread *thread, u8 m, struct addr_map_symbol *ams, - u64 addr, u64 phys_addr) + u64 addr, u64 phys_addr, u64 daddr_page_size) { struct addr_location al; @@ -2037,6 +2042,7 @@ static void ip__resolve_data(struct thread *thread, ams->ms.sym = al.sym; ams->ms.map = al.map; ams->phys_addr = phys_addr; + ams->data_page_size = daddr_page_size; } struct mem_info *sample__resolve_mem(struct perf_sample *sample, @@ -2049,7 +2055,8 @@ struct mem_info *sample__resolve_mem(struct perf_sample *sample, ip__resolve_ams(al->thread, &mi->iaddr, sample->ip); ip__resolve_data(al->thread, al->cpumode, &mi->daddr, - sample->addr, sample->phys_addr); + sample->addr, sample->phys_addr, + sample->data_page_size); mi->data_src.val = sample->data_src; return mi; diff --git a/tools/perf/util/map_symbol.h b/tools/perf/util/map_symbol.h index 5b8ca93798e9..7d22ade082c8 100644 --- a/tools/perf/util/map_symbol.h +++ b/tools/perf/util/map_symbol.h @@ -19,5 +19,6 @@ struct addr_map_symbol { u64 addr; u64 al_addr; u64 phys_addr; + u64 data_page_size; }; #endif // __PERF_MAP_SYMBOL diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c index ea0af0bc4314..19007e463b8a 100644 --- a/tools/perf/util/mem-events.c +++ b/tools/perf/util/mem-events.c @@ -17,9 +17,10 @@ unsigned int perf_mem_events__loads_ldlat = 30; #define E(t, n, s) { .tag = t, .name = n, .sysfs_name = s } -struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = { - E("ldlat-loads", "cpu/mem-loads,ldlat=%u/P", "mem-loads"), - E("ldlat-stores", "cpu/mem-stores/P", "mem-stores"), +static struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = { + E("ldlat-loads", "cpu/mem-loads,ldlat=%u/P", "cpu/events/mem-loads"), + E("ldlat-stores", "cpu/mem-stores/P", "cpu/events/mem-stores"), + E(NULL, NULL, NULL), }; #undef E @@ -28,19 +29,31 @@ struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = { static char mem_loads_name[100]; static bool mem_loads_name__init; +struct perf_mem_event * __weak perf_mem_events__ptr(int i) +{ + if (i >= PERF_MEM_EVENTS__MAX) + return NULL; + + return &perf_mem_events[i]; +} + char * __weak perf_mem_events__name(int i) { + struct perf_mem_event *e = perf_mem_events__ptr(i); + + if (!e) + return NULL; + if (i == PERF_MEM_EVENTS__LOAD) { if (!mem_loads_name__init) { mem_loads_name__init = true; scnprintf(mem_loads_name, sizeof(mem_loads_name), - perf_mem_events[i].name, - perf_mem_events__loads_ldlat); + e->name, perf_mem_events__loads_ldlat); } return mem_loads_name; } - return (char *)perf_mem_events[i].name; + return (char *)e->name; } int perf_mem_events__parse(const char *str) @@ -61,7 +74,10 @@ int perf_mem_events__parse(const char *str) while (tok) { for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) { - struct perf_mem_event *e = &perf_mem_events[j]; + struct perf_mem_event *e = perf_mem_events__ptr(j); + + if (!e->tag) + continue; if (strstr(e->tag, tok)) e->record = found = true; @@ -90,10 +106,17 @@ int perf_mem_events__init(void) for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) { char path[PATH_MAX]; - struct perf_mem_event *e = &perf_mem_events[j]; + struct perf_mem_event *e = perf_mem_events__ptr(j); struct stat st; - scnprintf(path, PATH_MAX, "%s/devices/cpu/events/%s", + /* + * If the event entry isn't valid, skip initialization + * and "e->supported" will keep false. + */ + if (!e->tag) + continue; + + scnprintf(path, PATH_MAX, "%s/devices/%s", mnt, e->sysfs_name); if (!stat(path, &st)) @@ -108,10 +131,10 @@ void perf_mem_events__list(void) int j; for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) { - struct perf_mem_event *e = &perf_mem_events[j]; + struct perf_mem_event *e = perf_mem_events__ptr(j); fprintf(stderr, "%-13s%-*s%s\n", - e->tag, + e->tag ?: "", verbose > 0 ? 25 : 0, verbose > 0 ? perf_mem_events__name(j) : "", e->supported ? ": available" : ""); diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h index 904dad34f7f7..5ef178278909 100644 --- a/tools/perf/util/mem-events.h +++ b/tools/perf/util/mem-events.h @@ -28,16 +28,17 @@ struct mem_info { enum { PERF_MEM_EVENTS__LOAD, PERF_MEM_EVENTS__STORE, + PERF_MEM_EVENTS__LOAD_STORE, PERF_MEM_EVENTS__MAX, }; -extern struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX]; extern unsigned int perf_mem_events__loads_ldlat; int perf_mem_events__parse(const char *str); int perf_mem_events__init(void); char *perf_mem_events__name(int i); +struct perf_mem_event *perf_mem_events__ptr(int i); void perf_mem_events__list(void); diff --git a/tools/perf/util/mem2node.c b/tools/perf/util/mem2node.c index c84f5841c7ab..03a7d7b27737 100644 --- a/tools/perf/util/mem2node.c +++ b/tools/perf/util/mem2node.c @@ -96,7 +96,8 @@ int mem2node__init(struct mem2node *map, struct perf_env *env) /* Cut unused entries, due to merging. */ tmp_entries = realloc(entries, sizeof(*entries) * j); - if (tmp_entries || WARN_ON_ONCE(j == 0)) + if (tmp_entries || + WARN_ONCE(j == 0, "No memory nodes, is CONFIG_MEMORY_HOTPLUG enabled?\n")) entries = tmp_entries; for (i = 0; i < j; i++) { diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index 060454a17293..ee94d3e8dd65 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -279,7 +279,9 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist, * when then group is left. */ if (!has_constraint && - ev->leader != metric_events[i]->leader) + ev->leader != metric_events[i]->leader && + !strcmp(ev->leader->pmu_name, + metric_events[i]->leader->pmu_name)) break; if (!strcmp(metric_events[i]->name, ev->name)) { set_bit(ev->idx, evlist_used); @@ -413,6 +415,12 @@ static bool match_metric(const char *n, const char *list) return false; } +static bool match_pe_metric(struct pmu_event *pe, const char *metric) +{ + return match_metric(pe->metric_group, metric) || + match_metric(pe->metric_name, metric); +} + struct mep { struct rb_node nd; const char *name; @@ -491,6 +499,115 @@ static void metricgroup__print_strlist(struct strlist *metrics, bool raw) putchar('\n'); } +static int metricgroup__print_pmu_event(struct pmu_event *pe, + bool metricgroups, char *filter, + bool raw, bool details, + struct rblist *groups, + struct strlist *metriclist) +{ + const char *g; + char *omg, *mg; + + g = pe->metric_group; + if (!g && pe->metric_name) { + if (pe->name) + return 0; + g = "No_group"; + } + + if (!g) + return 0; + + mg = strdup(g); + + if (!mg) + return -ENOMEM; + omg = mg; + while ((g = strsep(&mg, ";")) != NULL) { + struct mep *me; + char *s; + + g = skip_spaces(g); + if (*g == 0) + g = "No_group"; + if (filter && !strstr(g, filter)) + continue; + if (raw) + s = (char *)pe->metric_name; + else { + if (asprintf(&s, "%s\n%*s%s]", + pe->metric_name, 8, "[", pe->desc) < 0) + return -1; + if (details) { + if (asprintf(&s, "%s\n%*s%s]", + s, 8, "[", pe->metric_expr) < 0) + return -1; + } + } + + if (!s) + continue; + + if (!metricgroups) { + strlist__add(metriclist, s); + } else { + me = mep_lookup(groups, g); + if (!me) + continue; + strlist__add(me->metrics, s); + } + + if (!raw) + free(s); + } + free(omg); + + return 0; +} + +struct metricgroup_print_sys_idata { + struct strlist *metriclist; + char *filter; + struct rblist *groups; + bool metricgroups; + bool raw; + bool details; +}; + +typedef int (*metricgroup_sys_event_iter_fn)(struct pmu_event *pe, void *); + +struct metricgroup_iter_data { + metricgroup_sys_event_iter_fn fn; + void *data; +}; + +static int metricgroup__sys_event_iter(struct pmu_event *pe, void *data) +{ + struct metricgroup_iter_data *d = data; + struct perf_pmu *pmu = NULL; + + if (!pe->metric_expr || !pe->compat) + return 0; + + while ((pmu = perf_pmu__scan(pmu))) { + + if (!pmu->id || strcmp(pmu->id, pe->compat)) + continue; + + return d->fn(pe, d->data); + } + + return 0; +} + +static int metricgroup__print_sys_event_iter(struct pmu_event *pe, void *data) +{ + struct metricgroup_print_sys_idata *d = data; + + return metricgroup__print_pmu_event(pe, d->metricgroups, d->filter, d->raw, + d->details, d->groups, d->metriclist); +} + void metricgroup__print(bool metrics, bool metricgroups, char *filter, bool raw, bool details) { @@ -501,9 +618,6 @@ void metricgroup__print(bool metrics, bool metricgroups, char *filter, struct rb_node *node, *next; struct strlist *metriclist = NULL; - if (!map) - return; - if (!metricgroups) { metriclist = strlist__new(NULL, NULL); if (!metriclist) @@ -514,67 +628,33 @@ void metricgroup__print(bool metrics, bool metricgroups, char *filter, groups.node_new = mep_new; groups.node_cmp = mep_cmp; groups.node_delete = mep_delete; - for (i = 0; ; i++) { - const char *g; + for (i = 0; map; i++) { pe = &map->table[i]; if (!pe->name && !pe->metric_group && !pe->metric_name) break; if (!pe->metric_expr) continue; - g = pe->metric_group; - if (!g && pe->metric_name) { - if (pe->name) - continue; - g = "No_group"; - } - if (g) { - char *omg; - char *mg = strdup(g); - - if (!mg) - return; - omg = mg; - while ((g = strsep(&mg, ";")) != NULL) { - struct mep *me; - char *s; - - g = skip_spaces(g); - if (*g == 0) - g = "No_group"; - if (filter && !strstr(g, filter)) - continue; - if (raw) - s = (char *)pe->metric_name; - else { - if (asprintf(&s, "%s\n%*s%s]", - pe->metric_name, 8, "[", pe->desc) < 0) - return; - - if (details) { - if (asprintf(&s, "%s\n%*s%s]", - s, 8, "[", pe->metric_expr) < 0) - return; - } - } - - if (!s) - continue; + if (metricgroup__print_pmu_event(pe, metricgroups, filter, + raw, details, &groups, + metriclist) < 0) + return; + } - if (!metricgroups) { - strlist__add(metriclist, s); - } else { - me = mep_lookup(&groups, g); - if (!me) - continue; - strlist__add(me->metrics, s); - } + { + struct metricgroup_iter_data data = { + .fn = metricgroup__print_sys_event_iter, + .data = (void *) &(struct metricgroup_print_sys_idata){ + .metriclist = metriclist, + .metricgroups = metricgroups, + .filter = filter, + .raw = raw, + .details = details, + .groups = &groups, + }, + }; - if (!raw) - free(s); - } - free(omg); - } + pmu_for_each_sys_event(metricgroup__sys_event_iter, &data); } if (!filter || !rblist__empty(&groups)) { @@ -683,6 +763,16 @@ int __weak arch_get_runtimeparam(struct pmu_event *pe __maybe_unused) return 1; } +struct metricgroup_add_iter_data { + struct list_head *metric_list; + const char *metric; + struct metric **m; + struct expr_ids *ids; + int *ret; + bool *has_match; + bool metric_no_group; +}; + static int __add_metric(struct list_head *metric_list, struct pmu_event *pe, bool metric_no_group, @@ -792,10 +882,11 @@ static int __add_metric(struct list_head *metric_list, return 0; } -#define map_for_each_event(__pe, __idx, __map) \ - for (__idx = 0, __pe = &__map->table[__idx]; \ - __pe->name || __pe->metric_group || __pe->metric_name; \ - __pe = &__map->table[++__idx]) +#define map_for_each_event(__pe, __idx, __map) \ + if (__map) \ + for (__idx = 0, __pe = &__map->table[__idx]; \ + __pe->name || __pe->metric_group || __pe->metric_name; \ + __pe = &__map->table[++__idx]) #define map_for_each_metric(__pe, __idx, __map, __metric) \ map_for_each_event(__pe, __idx, __map) \ @@ -833,7 +924,7 @@ static int recursion_check(struct metric *m, const char *id, struct expr_id **pa if (ret) return ret; - p = data->parent; + p = expr_id_data__parent(data); while (p->parent) { if (!strcmp(p->id, id)) { @@ -854,7 +945,7 @@ static int recursion_check(struct metric *m, const char *id, struct expr_id **pa } p->id = strdup(id); - p->parent = data->parent; + p->parent = expr_id_data__parent(data); *parent = p; return p->id ? 0 : -ENOMEM; @@ -963,6 +1054,29 @@ static int add_metric(struct list_head *metric_list, return ret; } +static int metricgroup__add_metric_sys_event_iter(struct pmu_event *pe, + void *data) +{ + struct metricgroup_add_iter_data *d = data; + int ret; + + if (!match_pe_metric(pe, d->metric)) + return 0; + + ret = add_metric(d->metric_list, pe, d->metric_no_group, d->m, NULL, d->ids); + if (ret) + return ret; + + ret = resolve_metric(d->metric_no_group, + d->metric_list, NULL, d->ids); + if (ret) + return ret; + + *(d->has_match) = true; + + return *d->ret; +} + static int metricgroup__add_metric(const char *metric, bool metric_no_group, struct strbuf *events, struct list_head *metric_list, @@ -993,6 +1107,22 @@ static int metricgroup__add_metric(const char *metric, bool metric_no_group, goto out; } + { + struct metricgroup_iter_data data = { + .fn = metricgroup__add_metric_sys_event_iter, + .data = (void *) &(struct metricgroup_add_iter_data) { + .metric_list = &list, + .metric = metric, + .metric_no_group = metric_no_group, + .m = &m, + .ids = &ids, + .has_match = &has_match, + .ret = &ret, + }, + }; + + pmu_for_each_sys_event(metricgroup__sys_event_iter, &data); + } /* End of pmu events. */ if (!has_match) { ret = -EINVAL; @@ -1119,8 +1249,6 @@ int metricgroup__parse_groups(const struct option *opt, struct evlist *perf_evlist = *(struct evlist **)opt->value; struct pmu_events_map *map = perf_pmu__find_map(NULL); - if (!map) - return 0; return parse_groups(perf_evlist, str, metric_no_group, metric_no_merge, NULL, metric_events, map); diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 3b273580fb84..42c84adeb2fb 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -668,6 +668,7 @@ static int add_tracepoint_multi_sys(struct list_head *list, int *idx, return ret; } +#ifdef HAVE_LIBBPF_SUPPORT struct __add_bpf_event_param { struct parse_events_state *parse_state; struct list_head *list; @@ -900,6 +901,30 @@ int parse_events_load_bpf(struct parse_events_state *parse_state, list_splice_tail(&obj_head_config, head_config); return err; } +#else // HAVE_LIBBPF_SUPPORT +int parse_events_load_bpf_obj(struct parse_events_state *parse_state, + struct list_head *list __maybe_unused, + struct bpf_object *obj __maybe_unused, + struct list_head *head_config __maybe_unused) +{ + parse_events__handle_error(parse_state->error, 0, + strdup("BPF support is not compiled"), + strdup("Make sure libbpf-devel is available at build time.")); + return -ENOTSUP; +} + +int parse_events_load_bpf(struct parse_events_state *parse_state, + struct list_head *list __maybe_unused, + char *bpf_file_name __maybe_unused, + bool source __maybe_unused, + struct list_head *head_config __maybe_unused) +{ + parse_events__handle_error(parse_state->error, 0, + strdup("BPF support is not compiled"), + strdup("Make sure libbpf-devel is available at build time.")); + return -ENOTSUP; +} +#endif // HAVE_LIBBPF_SUPPORT static int parse_breakpoint_type(const char *type, struct perf_event_attr *attr) @@ -1744,7 +1769,7 @@ void parse_events__set_leader(char *name, struct list_head *list, if (parse_events__set_leader_for_uncore_aliase(name, list, parse_state)) return; - __perf_evlist__set_leader(list); + __evlist__set_leader(list); leader = list_entry(list->next, struct evsel, core.node); leader->group_name = name ? strdup(name) : NULL; } @@ -2158,7 +2183,7 @@ int __parse_events(struct evlist *evlist, const char *str, /* * Add list to the evlist even with errors to allow callers to clean up. */ - perf_evlist__splice_list_tail(evlist, &parse_state.list); + evlist__splice_list_tail(evlist, &parse_state.list); if (!ret) { struct evsel *last; diff --git a/tools/perf/util/parse-regs-options.c b/tools/perf/util/parse-regs-options.c index e687497b3aac..a4a100425b3a 100644 --- a/tools/perf/util/parse-regs-options.c +++ b/tools/perf/util/parse-regs-options.c @@ -54,7 +54,7 @@ __parse_regs(const struct option *opt, const char *str, int unset, bool intr) #endif fputc('\n', stderr); /* just printing available regs */ - return -1; + goto error; } #ifdef HAVE_PERF_REGS_SUPPORT for (r = sample_reg_masks; r->name; r++) { diff --git a/tools/perf/util/perf_event_attr_fprintf.c b/tools/perf/util/perf_event_attr_fprintf.c index e67a227c0ce7..fb0bb6684438 100644 --- a/tools/perf/util/perf_event_attr_fprintf.c +++ b/tools/perf/util/perf_event_attr_fprintf.c @@ -35,7 +35,7 @@ static void __p_sample_type(char *buf, size_t size, u64 value) bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER), bit_name(IDENTIFIER), bit_name(REGS_INTR), bit_name(DATA_SRC), bit_name(WEIGHT), bit_name(PHYS_ADDR), bit_name(AUX), - bit_name(CGROUP), + bit_name(CGROUP), bit_name(DATA_PAGE_SIZE), { .name = NULL, } }; #undef bit_name diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index d41caeb35cf6..44ef28302fc7 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -597,6 +597,7 @@ static struct perf_cpu_map *__pmu_cpumask(const char *path) * Uncore PMUs have a "cpumask" file under sysfs. CPU PMUs (e.g. on arm/arm64) * may have a "cpus" file. */ +#define SYS_TEMPLATE_ID "./bus/event_source/devices/%s/identifier" #define CPUS_TEMPLATE_UNCORE "%s/bus/event_source/devices/%s/cpumask" #define CPUS_TEMPLATE_CPU "%s/bus/event_source/devices/%s/cpus" @@ -635,6 +636,21 @@ static bool pmu_is_uncore(const char *name) return file_available(path); } +static char *pmu_id(const char *name) +{ + char path[PATH_MAX], *str; + size_t len; + + snprintf(path, PATH_MAX, SYS_TEMPLATE_ID, name); + + if (sysfs__read_str(path, &str, &len) < 0) + return NULL; + + str[len - 1] = 0; /* remove line feed */ + + return str; +} + /* * PMU CORE devices have different name other than cpu in sysfs on some * platforms. @@ -796,6 +812,83 @@ static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu) pmu_add_cpu_aliases_map(head, pmu, map); } +void pmu_for_each_sys_event(pmu_sys_event_iter_fn fn, void *data) +{ + int i = 0; + + while (1) { + struct pmu_sys_events *event_table; + int j = 0; + + event_table = &pmu_sys_event_tables[i++]; + + if (!event_table->table) + break; + + while (1) { + struct pmu_event *pe = &event_table->table[j++]; + int ret; + + if (!pe->name && !pe->metric_group && !pe->metric_name) + break; + + ret = fn(pe, data); + if (ret) + break; + } + } +} + +struct pmu_sys_event_iter_data { + struct list_head *head; + struct perf_pmu *pmu; +}; + +static int pmu_add_sys_aliases_iter_fn(struct pmu_event *pe, void *data) +{ + struct pmu_sys_event_iter_data *idata = data; + struct perf_pmu *pmu = idata->pmu; + + if (!pe->name) { + if (pe->metric_group || pe->metric_name) + return 0; + return -EINVAL; + } + + if (!pe->compat || !pe->pmu) + return 0; + + if (!strcmp(pmu->id, pe->compat) && + pmu_uncore_alias_match(pe->pmu, pmu->name)) { + __perf_pmu__new_alias(idata->head, NULL, + (char *)pe->name, + (char *)pe->desc, + (char *)pe->event, + (char *)pe->long_desc, + (char *)pe->topic, + (char *)pe->unit, + (char *)pe->perpkg, + (char *)pe->metric_expr, + (char *)pe->metric_name, + (char *)pe->deprecated); + } + + return 0; +} + +static void pmu_add_sys_aliases(struct list_head *head, struct perf_pmu *pmu) +{ + struct pmu_sys_event_iter_data idata = { + .head = head, + .pmu = pmu, + }; + + if (!pmu->id) + return; + + pmu_for_each_sys_event(pmu_add_sys_aliases_iter_fn, &idata); +} + struct perf_event_attr * __weak perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused) { @@ -847,8 +940,11 @@ static struct perf_pmu *pmu_lookup(const char *name) pmu->name = strdup(name); pmu->type = type; pmu->is_uncore = pmu_is_uncore(name); + if (pmu->is_uncore) + pmu->id = pmu_id(name); pmu->max_precise = pmu_max_precise(name); pmu_add_cpu_aliases(&aliases, pmu); + pmu_add_sys_aliases(&aliases, pmu); INIT_LIST_HEAD(&pmu->format); INIT_LIST_HEAD(&pmu->aliases); diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index a64e9c9ce731..8164388478c6 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -30,6 +30,7 @@ struct perf_pmu_caps { struct perf_pmu { char *name; + char *id; __u32 type; bool selectable; bool is_uncore; @@ -116,6 +117,8 @@ struct pmu_events_map *perf_pmu__find_map(struct perf_pmu *pmu); bool pmu_uncore_alias_match(const char *pmu_name, const char *name); void perf_pmu_free_alias(struct perf_pmu_alias *alias); +typedef int (*pmu_sys_event_iter_fn)(struct pmu_event *pe, void *data); +void pmu_for_each_sys_event(pmu_sys_event_iter_fn fn, void *data); int perf_pmu__convert_scale(const char *scale, char **end, double *sval); int perf_pmu__caps_parse(struct perf_pmu *pmu); diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c index 064b63a6a3f3..bbecb449ea94 100644 --- a/tools/perf/util/probe-file.c +++ b/tools/perf/util/probe-file.c @@ -791,7 +791,7 @@ static char *synthesize_sdt_probe_command(struct sdt_note *note, const char *sdtgrp) { struct strbuf buf; - char *ret = NULL, **args; + char *ret = NULL; int i, args_count, err; unsigned long long ref_ctr_offset; @@ -813,12 +813,19 @@ static char *synthesize_sdt_probe_command(struct sdt_note *note, goto out; if (note->args) { - args = argv_split(note->args, &args_count); + char **args = argv_split(note->args, &args_count); + + if (args == NULL) + goto error; for (i = 0; i < args_count; ++i) { - if (synthesize_sdt_probe_arg(&buf, i, args[i]) < 0) + if (synthesize_sdt_probe_arg(&buf, i, args[i]) < 0) { + argv_free(args); goto error; + } } + + argv_free(args); } out: diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index ae8edde7c50e..cc5ade85a33f 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -1055,7 +1055,7 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist, if (pyevent == NULL) return PyErr_NoMemory(); - evsel = perf_evlist__event2evsel(evlist, event); + evsel = evlist__event2evsel(evlist, event); if (!evsel) { Py_INCREF(Py_None); return Py_None; @@ -1089,7 +1089,7 @@ static PyObject *pyrf_evlist__open(struct pyrf_evlist *pevlist, return NULL; if (group) - perf_evlist__set_leader(evlist); + evlist__set_leader(evlist); if (evlist__open(evlist) < 0) { PyErr_SetFromErrno(PyExc_OSError); diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c index 07e4b96a6625..e70c9dd04567 100644 --- a/tools/perf/util/record.c +++ b/tools/perf/util/record.c @@ -89,8 +89,7 @@ static void evsel__config_leader_sampling(struct evsel *evsel, struct evlist *ev leader->core.attr.sample_type; } -void perf_evlist__config(struct evlist *evlist, struct record_opts *opts, - struct callchain_param *callchain) +void evlist__config(struct evlist *evlist, struct record_opts *opts, struct callchain_param *callchain) { struct evsel *evsel; bool use_sample_identifier = false; @@ -102,7 +101,7 @@ void perf_evlist__config(struct evlist *evlist, struct record_opts *opts, * since some might depend on this info. */ if (opts->group) - perf_evlist__set_leader(evlist); + evlist__set_leader(evlist); if (evlist->core.cpus->map[0] < 0) opts->no_inherit = true; @@ -144,7 +143,7 @@ void perf_evlist__config(struct evlist *evlist, struct record_opts *opts, evsel__set_sample_id(evsel, use_sample_identifier); } - perf_evlist__set_id_pos(evlist); + evlist__set_id_pos(evlist); } static int get_max_rate(unsigned int *rate) @@ -217,7 +216,7 @@ int record_opts__config(struct record_opts *opts) return record_opts__config_freq(opts); } -bool perf_evlist__can_select_event(struct evlist *evlist, const char *str) +bool evlist__can_select_event(struct evlist *evlist, const char *str) { struct evlist *temp_evlist; struct evsel *evsel; diff --git a/tools/perf/util/record.h b/tools/perf/util/record.h index 266760ac9143..694b351dcd27 100644 --- a/tools/perf/util/record.h +++ b/tools/perf/util/record.h @@ -22,6 +22,7 @@ struct record_opts { bool raw_samples; bool sample_address; bool sample_phys_addr; + bool sample_data_page_size; bool sample_weight; bool sample_time; bool sample_time_set; diff --git a/tools/perf/util/s390-cpumsf.c b/tools/perf/util/s390-cpumsf.c index f8861998e5bd..078a71773565 100644 --- a/tools/perf/util/s390-cpumsf.c +++ b/tools/perf/util/s390-cpumsf.c @@ -96,9 +96,9 @@ * | than PERF_RECORD_USER_TYPE_START) are handled by * | perf_session__process_user_event(see below) * | - Those generated by the kernel are handled by - * | perf_evlist__parse_sample_timestamp() + * | evlist__parse_sample_timestamp() * | - * perf_evlist__parse_sample_timestamp() + * evlist__parse_sample_timestamp() * | Extract time stamp from sample data. * | * perf_session__queue_event() @@ -932,7 +932,7 @@ s390_cpumsf_process_event(struct perf_session *session, if (event->header.type == PERF_RECORD_SAMPLE && sample->raw_size) { /* Handle event with raw data */ - ev_bc000 = perf_evlist__event2evsel(session->evlist, event); + ev_bc000 = evlist__event2evsel(session->evlist, event); if (ev_bc000 && ev_bc000->core.attr.config == PERF_EVENT_CPUM_CF_DIAG) err = s390_cpumcf_dumpctr(sf, sample); diff --git a/tools/perf/util/s390-sample-raw.c b/tools/perf/util/s390-sample-raw.c index 05b43ab4eeef..cfcf8d534d76 100644 --- a/tools/perf/util/s390-sample-raw.c +++ b/tools/perf/util/s390-sample-raw.c @@ -197,15 +197,14 @@ static void s390_cpumcfdg_dump(struct perf_sample *sample) * its raw data. * The function is only invoked when the dump flag -D is set. */ -void perf_evlist__s390_sample_raw(struct evlist *evlist, union perf_event *event, - struct perf_sample *sample) +void evlist__s390_sample_raw(struct evlist *evlist, union perf_event *event, struct perf_sample *sample) { struct evsel *ev_bc000; if (event->header.type != PERF_RECORD_SAMPLE) return; - ev_bc000 = perf_evlist__event2evsel(evlist, event); + ev_bc000 = evlist__event2evsel(evlist, event); if (ev_bc000 == NULL || ev_bc000->core.attr.config != PERF_EVENT_CPUM_CF_DIAG) return; diff --git a/tools/perf/util/sample-raw.c b/tools/perf/util/sample-raw.c index e84bbe0e441a..cde5cd3ce49b 100644 --- a/tools/perf/util/sample-raw.c +++ b/tools/perf/util/sample-raw.c @@ -9,10 +9,10 @@ * Check platform the perf data file was created on and perform platform * specific interpretation. */ -void perf_evlist__init_trace_event_sample_raw(struct evlist *evlist) +void evlist__init_trace_event_sample_raw(struct evlist *evlist) { const char *arch_pf = perf_env__arch(evlist->env); if (arch_pf && !strcmp("s390", arch_pf)) - evlist->trace_event_sample_raw = perf_evlist__s390_sample_raw; + evlist->trace_event_sample_raw = evlist__s390_sample_raw; } diff --git a/tools/perf/util/sample-raw.h b/tools/perf/util/sample-raw.h index afe1491a117e..4be84a5510cf 100644 --- a/tools/perf/util/sample-raw.h +++ b/tools/perf/util/sample-raw.h @@ -6,9 +6,6 @@ struct evlist; union perf_event; struct perf_sample; -void perf_evlist__s390_sample_raw(struct evlist *evlist, - union perf_event *event, - struct perf_sample *sample); - -void perf_evlist__init_trace_event_sample_raw(struct evlist *evlist); +void evlist__s390_sample_raw(struct evlist *evlist, union perf_event *event, struct perf_sample *sample); +void evlist__init_trace_event_sample_raw(struct evlist *evlist); #endif /* __PERF_EVLIST_H */ diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 098080287c68..50ff9795a4f1 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -32,6 +32,7 @@ #include "ui/progress.h" #include "../perf.h" #include "arch/common.h" +#include "units.h" #include <internal/lib.h> #ifdef HAVE_ZSTD_SUPPORT @@ -125,7 +126,7 @@ static int perf_session__open(struct perf_session *session) return -1; } - if (!perf_evlist__valid_read_format(session->evlist)) { + if (!evlist__valid_read_format(session->evlist)) { pr_err("non matching read_format\n"); return -1; } @@ -135,7 +136,7 @@ static int perf_session__open(struct perf_session *session) void perf_session__set_id_hdr_size(struct perf_session *session) { - u16 id_hdr_size = perf_evlist__id_hdr_size(session->evlist); + u16 id_hdr_size = evlist__id_hdr_size(session->evlist); machines__set_id_hdr_size(&session->machines, id_hdr_size); } @@ -221,7 +222,7 @@ struct perf_session *perf_session__new(struct perf_data *data, perf_session__set_comm_exec(session); } - perf_evlist__init_trace_event_sample_raw(session->evlist); + evlist__init_trace_event_sample_raw(session->evlist); /* Open the directory data. */ if (data->is_dir) { @@ -1191,9 +1192,7 @@ static void stack_user__printf(struct stack_dump *dump) dump->size, dump->offset); } -static void perf_evlist__print_tstamp(struct evlist *evlist, - union perf_event *event, - struct perf_sample *sample) +static void evlist__print_tstamp(struct evlist *evlist, union perf_event *event, struct perf_sample *sample) { u64 sample_type = __evlist__combined_sample_type(evlist); @@ -1254,16 +1253,25 @@ static void dump_event(struct evlist *evlist, union perf_event *event, evlist->trace_event_sample_raw(evlist, event, sample); if (sample) - perf_evlist__print_tstamp(evlist, event, sample); + evlist__print_tstamp(evlist, event, sample); printf("%#" PRIx64 " [%#x]: PERF_RECORD_%s", file_offset, event->header.size, perf_event__name(event->header.type)); } +char *get_page_size_name(u64 size, char *str) +{ + if (!size || !unit_number__scnprintf(str, PAGE_SIZE_NAME_LEN, size)) + snprintf(str, PAGE_SIZE_NAME_LEN, "%s", "N/A"); + + return str; +} + static void dump_sample(struct evsel *evsel, union perf_event *event, struct perf_sample *sample) { u64 sample_type; + char str[PAGE_SIZE_NAME_LEN]; if (!dump_trace) return; @@ -1298,6 +1306,9 @@ static void dump_sample(struct evsel *evsel, union perf_event *event, if (sample_type & PERF_SAMPLE_PHYS_ADDR) printf(" .. phys_addr: 0x%"PRIx64"\n", sample->phys_addr); + if (sample_type & PERF_SAMPLE_DATA_PAGE_SIZE) + printf(" .. data page size: %s\n", get_page_size_name(sample->data_page_size, str)); + if (sample_type & PERF_SAMPLE_TRANSACTION) printf("... transaction: %" PRIx64 "\n", sample->transaction); @@ -1364,7 +1375,7 @@ static int deliver_sample_value(struct evlist *evlist, struct sample_read_value *v, struct machine *machine) { - struct perf_sample_id *sid = perf_evlist__id2sid(evlist, v->id); + struct perf_sample_id *sid = evlist__id2sid(evlist, v->id); struct evsel *evsel; if (sid) { @@ -1409,13 +1420,9 @@ static int deliver_sample_group(struct evlist *evlist, return ret; } -static int - perf_evlist__deliver_sample(struct evlist *evlist, - struct perf_tool *tool, - union perf_event *event, - struct perf_sample *sample, - struct evsel *evsel, - struct machine *machine) +static int evlist__deliver_sample(struct evlist *evlist, struct perf_tool *tool, + union perf_event *event, struct perf_sample *sample, + struct evsel *evsel, struct machine *machine) { /* We know evsel != NULL. */ u64 sample_type = evsel->core.attr.sample_type; @@ -1445,7 +1452,7 @@ static int machines__deliver_event(struct machines *machines, dump_event(evlist, event, file_offset, sample); - evsel = perf_evlist__id2evsel(evlist, sample->id); + evsel = evlist__id2evsel(evlist, sample->id); machine = machines__find_for_cpumode(machines, event, sample); @@ -1460,7 +1467,7 @@ static int machines__deliver_event(struct machines *machines, ++evlist->stats.nr_unprocessable_samples; return 0; } - return perf_evlist__deliver_sample(evlist, tool, event, sample, evsel, machine); + return evlist__deliver_sample(evlist, tool, event, sample, evsel, machine); case PERF_RECORD_MMAP: return tool->mmap(tool, event, sample, machine); case PERF_RECORD_MMAP2: @@ -1523,9 +1530,8 @@ static int perf_session__deliver_event(struct perf_session *session, u64 file_offset) { struct perf_sample sample; - int ret; + int ret = evlist__parse_sample(session->evlist, event, &sample); - ret = perf_evlist__parse_sample(session->evlist, event, &sample); if (ret) { pr_err("Can't parse sample, err = %d\n", ret); return ret; @@ -1697,7 +1703,7 @@ int perf_session__peek_event(struct perf_session *session, off_t file_offset, out_parse_sample: if (sample && event->header.type < PERF_RECORD_USER_TYPE_START && - perf_evlist__parse_sample(session->evlist, event, sample)) + evlist__parse_sample(session->evlist, event, sample)) return -1; *event_ptr = event; @@ -1754,7 +1760,7 @@ static s64 perf_session__process_event(struct perf_session *session, if (tool->ordered_events) { u64 timestamp = -1ULL; - ret = perf_evlist__parse_sample_timestamp(evlist, event, ×tamp); + ret = evlist__parse_sample_timestamp(evlist, event, ×tamp); if (ret && ret != -1) return ret; @@ -1937,7 +1943,6 @@ static int __perf_session__process_pipe_events(struct perf_session *session) { struct ordered_events *oe = &session->ordered_events; struct perf_tool *tool = session->tool; - int fd = perf_data__fd(session->data); union perf_event *event; uint32_t size, cur_size = 0; void *buf = NULL; @@ -1957,7 +1962,8 @@ static int __perf_session__process_pipe_events(struct perf_session *session) ordered_events__set_copy_on_queue(oe, true); more: event = buf; - err = readn(fd, event, sizeof(struct perf_event_header)); + err = perf_data__read(session->data, event, + sizeof(struct perf_event_header)); if (err <= 0) { if (err == 0) goto done; @@ -1989,7 +1995,8 @@ more: p += sizeof(struct perf_event_header); if (size - sizeof(struct perf_event_header)) { - err = readn(fd, p, size - sizeof(struct perf_event_header)); + err = perf_data__read(session->data, p, + size - sizeof(struct perf_event_header)); if (err <= 0) { if (err == 0) { pr_err("unexpected end of event stream\n"); @@ -2476,7 +2483,7 @@ int perf_event__process_id_index(struct perf_session *session, fprintf(stdout, " tid: %"PRI_ld64"\n", e->tid); } - sid = perf_evlist__id2sid(evlist, e->id); + sid = evlist__id2sid(evlist, e->id); if (!sid) return -ENOENT; sid->idx = e->idx; diff --git a/tools/perf/util/sideband_evlist.c b/tools/perf/util/sideband_evlist.c index ded9ced02797..748371ac22be 100644 --- a/tools/perf/util/sideband_evlist.c +++ b/tools/perf/util/sideband_evlist.c @@ -12,8 +12,8 @@ #include <sched.h> #include <stdbool.h> -int perf_evlist__add_sb_event(struct evlist *evlist, struct perf_event_attr *attr, - evsel__sb_cb_t cb, void *data) +int evlist__add_sb_event(struct evlist *evlist, struct perf_event_attr *attr, + evsel__sb_cb_t cb, void *data) { struct evsel *evsel; @@ -62,7 +62,7 @@ static void *perf_evlist__poll_thread(void *arg) if (perf_mmap__read_init(&map->core)) continue; while ((event = perf_mmap__read_event(&map->core)) != NULL) { - struct evsel *evsel = perf_evlist__event2evsel(evlist, event); + struct evsel *evsel = evlist__event2evsel(evlist, event); if (evsel && evsel->side_band.cb) evsel->side_band.cb(event, evsel->side_band.data); @@ -94,14 +94,14 @@ void evlist__set_cb(struct evlist *evlist, evsel__sb_cb_t cb, void *data) } } -int perf_evlist__start_sb_thread(struct evlist *evlist, struct target *target) +int evlist__start_sb_thread(struct evlist *evlist, struct target *target) { struct evsel *counter; if (!evlist) return 0; - if (perf_evlist__create_maps(evlist, target)) + if (evlist__create_maps(evlist, target)) goto out_delete_evlist; if (evlist->core.nr_entries > 1) { @@ -110,7 +110,7 @@ int perf_evlist__start_sb_thread(struct evlist *evlist, struct target *target) evlist__for_each_entry(evlist, counter) evsel__set_sample_id(counter, can_sample_identifier); - perf_evlist__set_id_pos(evlist); + evlist__set_id_pos(evlist); } evlist__for_each_entry(evlist, counter) { @@ -138,7 +138,7 @@ out_delete_evlist: return -1; } -void perf_evlist__stop_sb_thread(struct evlist *evlist) +void evlist__stop_sb_thread(struct evlist *evlist) { if (!evlist) return; diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index d42339df20f8..80907bc32683 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -1463,6 +1463,35 @@ struct sort_entry sort_mem_phys_daddr = { }; static int64_t +sort__data_page_size_cmp(struct hist_entry *left, struct hist_entry *right) +{ + uint64_t l = 0, r = 0; + + if (left->mem_info) + l = left->mem_info->daddr.data_page_size; + if (right->mem_info) + r = right->mem_info->daddr.data_page_size; + + return (int64_t)(r - l); +} + +static int hist_entry__data_page_size_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + char str[PAGE_SIZE_NAME_LEN]; + + return repsep_snprintf(bf, size, "%-*s", width, + get_page_size_name(he->mem_info->daddr.data_page_size, str)); +} + +struct sort_entry sort_mem_data_page_size = { + .se_header = "Data Page Size", + .se_cmp = sort__data_page_size_cmp, + .se_snprintf = hist_entry__data_page_size_snprintf, + .se_width_idx = HISTC_MEM_DATA_PAGE_SIZE, +}; + +static int64_t sort__abort_cmp(struct hist_entry *left, struct hist_entry *right) { if (!left->branch_info || !right->branch_info) @@ -1740,6 +1769,7 @@ static struct sort_dimension memory_sort_dimensions[] = { DIM(SORT_MEM_SNOOP, "snoop", sort_mem_snoop), DIM(SORT_MEM_DCACHELINE, "dcacheline", sort_mem_dcacheline), DIM(SORT_MEM_PHYS_DADDR, "phys_daddr", sort_mem_phys_daddr), + DIM(SORT_MEM_DATA_PAGE_SIZE, "data_page_size", sort_mem_data_page_size), }; #undef DIM @@ -2756,7 +2786,7 @@ static const char *get_default_sort_order(struct evlist *evlist) BUG_ON(sort__mode >= ARRAY_SIZE(default_sort_orders)); - if (evlist == NULL || perf_evlist__empty(evlist)) + if (evlist == NULL || evlist__empty(evlist)) goto out_no_evlist; evlist__for_each_entry(evlist, evsel) { diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 66d39c4cfe2b..e50f2b695bc4 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -255,6 +255,7 @@ enum sort_type { SORT_MEM_DCACHELINE, SORT_MEM_IADDR_SYMBOL, SORT_MEM_PHYS_DADDR, + SORT_MEM_DATA_PAGE_SIZE, }; /* diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index a963b5b8eb72..583ae4f09c5d 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -68,15 +68,15 @@ static void print_cgroup(struct perf_stat_config *config, struct evsel *evsel) static void aggr_printout(struct perf_stat_config *config, - struct evsel *evsel, int id, int nr) + struct evsel *evsel, struct aggr_cpu_id id, int nr) { switch (config->aggr_mode) { case AGGR_CORE: fprintf(config->output, "S%d-D%d-C%*d%s%*d%s", - cpu_map__id_to_socket(id), - cpu_map__id_to_die(id), + id.socket, + id.die, config->csv_output ? 0 : -8, - cpu_map__id_to_cpu(id), + id.core, config->csv_sep, config->csv_output ? 0 : 4, nr, @@ -84,9 +84,9 @@ static void aggr_printout(struct perf_stat_config *config, break; case AGGR_DIE: fprintf(config->output, "S%d-D%*d%s%*d%s", - cpu_map__id_to_socket(id << 16), + id.socket, config->csv_output ? 0 : -8, - cpu_map__id_to_die(id << 16), + id.die, config->csv_sep, config->csv_output ? 0 : 4, nr, @@ -95,7 +95,7 @@ static void aggr_printout(struct perf_stat_config *config, case AGGR_SOCKET: fprintf(config->output, "S%*d%s%*d%s", config->csv_output ? 0 : -5, - id, + id.socket, config->csv_sep, config->csv_output ? 0 : 4, nr, @@ -104,7 +104,7 @@ static void aggr_printout(struct perf_stat_config *config, case AGGR_NODE: fprintf(config->output, "N%*d%s%*d%s", config->csv_output ? 0 : -5, - id, + id.node, config->csv_sep, config->csv_output ? 0 : 4, nr, @@ -113,23 +113,23 @@ static void aggr_printout(struct perf_stat_config *config, case AGGR_NONE: if (evsel->percore && !config->percore_show_thread) { fprintf(config->output, "S%d-D%d-C%*d%s", - cpu_map__id_to_socket(id), - cpu_map__id_to_die(id), + id.socket, + id.die, config->csv_output ? 0 : -3, - cpu_map__id_to_cpu(id), config->csv_sep); - } else if (id > -1) { + id.core, config->csv_sep); + } else if (id.core > -1) { fprintf(config->output, "CPU%*d%s", config->csv_output ? 0 : -7, - evsel__cpus(evsel)->map[id], + evsel__cpus(evsel)->map[id.core], config->csv_sep); } break; case AGGR_THREAD: fprintf(config->output, "%*s-%*d%s", config->csv_output ? 0 : 16, - perf_thread_map__comm(evsel->core.threads, id), + perf_thread_map__comm(evsel->core.threads, id.thread), config->csv_output ? 0 : -8, - perf_thread_map__pid(evsel->core.threads, id), + perf_thread_map__pid(evsel->core.threads, id.thread), config->csv_sep); break; case AGGR_GLOBAL: @@ -144,7 +144,8 @@ struct outstate { bool newline; const char *prefix; int nfields; - int id, nr; + int nr; + struct aggr_cpu_id id; struct evsel *evsel; }; @@ -319,13 +320,13 @@ static void print_metric_header(struct perf_stat_config *config, } static int first_shadow_cpu(struct perf_stat_config *config, - struct evsel *evsel, int id) + struct evsel *evsel, struct aggr_cpu_id id) { struct evlist *evlist = evsel->evlist; int i; if (config->aggr_mode == AGGR_NONE) - return id; + return id.core; if (!config->aggr_get_id) return 0; @@ -333,14 +334,17 @@ static int first_shadow_cpu(struct perf_stat_config *config, for (i = 0; i < evsel__nr_cpus(evsel); i++) { int cpu2 = evsel__cpus(evsel)->map[i]; - if (config->aggr_get_id(config, evlist->core.cpus, cpu2) == id) + if (cpu_map__compare_aggr_cpu_id( + config->aggr_get_id(config, evlist->core.cpus, cpu2), + id)) { return cpu2; + } } return 0; } static void abs_printout(struct perf_stat_config *config, - int id, int nr, struct evsel *evsel, double avg) + struct aggr_cpu_id id, int nr, struct evsel *evsel, double avg) { FILE *output = config->output; double sc = evsel->scale; @@ -393,7 +397,7 @@ static bool is_mixed_hw_group(struct evsel *counter) return false; } -static void printout(struct perf_stat_config *config, int id, int nr, +static void printout(struct perf_stat_config *config, struct aggr_cpu_id id, int nr, struct evsel *counter, double uval, char *prefix, u64 run, u64 ena, double noise, struct runtime_stat *st) @@ -496,7 +500,8 @@ static void printout(struct perf_stat_config *config, int id, int nr, static void aggr_update_shadow(struct perf_stat_config *config, struct evlist *evlist) { - int cpu, s2, id, s; + int cpu, s; + struct aggr_cpu_id s2, id; u64 val; struct evsel *counter; @@ -506,7 +511,7 @@ static void aggr_update_shadow(struct perf_stat_config *config, val = 0; for (cpu = 0; cpu < evsel__nr_cpus(counter); cpu++) { s2 = config->aggr_get_id(config, evlist->core.cpus, cpu); - if (s2 != id) + if (!cpu_map__compare_aggr_cpu_id(s2, id)) continue; val += perf_counts(counter->counts, cpu, 0)->val; } @@ -584,7 +589,7 @@ static bool collect_data(struct perf_stat_config *config, struct evsel *counter, struct aggr_data { u64 ena, run, val; - int id; + struct aggr_cpu_id id; int nr; int cpu; }; @@ -593,13 +598,14 @@ static void aggr_cb(struct perf_stat_config *config, struct evsel *counter, void *data, bool first) { struct aggr_data *ad = data; - int cpu, s2; + int cpu; + struct aggr_cpu_id s2; for (cpu = 0; cpu < evsel__nr_cpus(counter); cpu++) { struct perf_counts_values *counts; s2 = config->aggr_get_id(config, evsel__cpus(counter), cpu); - if (s2 != ad->id) + if (!cpu_map__compare_aggr_cpu_id(s2, ad->id)) continue; if (first) ad->nr++; @@ -628,7 +634,8 @@ static void print_counter_aggrdata(struct perf_stat_config *config, struct aggr_data ad; FILE *output = config->output; u64 ena, run, val; - int id, nr; + int nr; + struct aggr_cpu_id id; double uval; ad.id = id = config->aggr_map->map[s]; @@ -649,8 +656,12 @@ static void print_counter_aggrdata(struct perf_stat_config *config, fprintf(output, "%s", prefix); uval = val * counter->scale; - printout(config, cpu != -1 ? cpu : id, nr, counter, uval, prefix, - run, ena, 1.0, &rt_stat); + if (cpu != -1) { + id = cpu_map__empty_aggr_cpu_id(); + id.core = cpu; + } + printout(config, id, nr, counter, uval, + prefix, run, ena, 1.0, &rt_stat); if (!metric_only) fputc('\n', output); } @@ -728,7 +739,8 @@ static struct perf_aggr_thread_value *sort_aggr_thread( continue; buf[i].counter = counter; - buf[i].id = thread; + buf[i].id = cpu_map__empty_aggr_cpu_id(); + buf[i].id.thread = thread; buf[i].uval = uval; buf[i].val = val; buf[i].run = run; @@ -751,7 +763,8 @@ static void print_aggr_thread(struct perf_stat_config *config, FILE *output = config->output; int nthreads = perf_thread_map__nr(counter->core.threads); int ncpus = perf_cpu_map__nr(counter->core.cpus); - int thread, sorted_threads, id; + int thread, sorted_threads; + struct aggr_cpu_id id; struct perf_aggr_thread_value *buf; buf = sort_aggr_thread(counter, nthreads, ncpus, &sorted_threads, _target); @@ -768,7 +781,7 @@ static void print_aggr_thread(struct perf_stat_config *config, if (config->stats) printout(config, id, 0, buf[thread].counter, buf[thread].uval, prefix, buf[thread].run, buf[thread].ena, 1.0, - &config->stats[id]); + &config->stats[id.thread]); else printout(config, id, 0, buf[thread].counter, buf[thread].uval, prefix, buf[thread].run, buf[thread].ena, 1.0, @@ -814,8 +827,8 @@ static void print_counter_aggr(struct perf_stat_config *config, fprintf(output, "%s", prefix); uval = cd.avg * counter->scale; - printout(config, -1, 0, counter, uval, prefix, cd.avg_running, cd.avg_enabled, - cd.avg, &rt_stat); + printout(config, cpu_map__empty_aggr_cpu_id(), 0, counter, uval, prefix, cd.avg_running, + cd.avg_enabled, cd.avg, &rt_stat); if (!metric_only) fprintf(output, "\n"); } @@ -842,6 +855,7 @@ static void print_counter(struct perf_stat_config *config, u64 ena, run, val; double uval; int cpu; + struct aggr_cpu_id id; for (cpu = 0; cpu < evsel__nr_cpus(counter); cpu++) { struct aggr_data ad = { .cpu = cpu }; @@ -856,8 +870,10 @@ static void print_counter(struct perf_stat_config *config, fprintf(output, "%s", prefix); uval = val * counter->scale; - printout(config, cpu, 0, counter, uval, prefix, run, ena, 1.0, - &rt_stat); + id = cpu_map__empty_aggr_cpu_id(); + id.core = cpu; + printout(config, id, 0, counter, uval, prefix, + run, ena, 1.0, &rt_stat); fputc('\n', output); } @@ -872,6 +888,7 @@ static void print_no_aggr_metric(struct perf_stat_config *config, struct evsel *counter; u64 ena, run, val; double uval; + struct aggr_cpu_id id; nrcpus = evlist->core.cpus->nr; for (cpu = 0; cpu < nrcpus; cpu++) { @@ -880,8 +897,10 @@ static void print_no_aggr_metric(struct perf_stat_config *config, if (prefix) fputs(prefix, config->output); evlist__for_each_entry(evlist, counter) { + id = cpu_map__empty_aggr_cpu_id(); + id.core = cpu; if (first) { - aggr_printout(config, counter, cpu, 0); + aggr_printout(config, counter, id, 0); first = false; } val = perf_counts(counter->counts, cpu, 0)->val; @@ -889,8 +908,8 @@ static void print_no_aggr_metric(struct perf_stat_config *config, run = perf_counts(counter->counts, cpu, 0)->run; uval = val * counter->scale; - printout(config, cpu, 0, counter, uval, prefix, run, ena, 1.0, - &rt_stat); + printout(config, id, 0, counter, uval, prefix, + run, ena, 1.0, &rt_stat); } fputc('\n', config->output); } @@ -1140,14 +1159,15 @@ static void print_footer(struct perf_stat_config *config) static void print_percore_thread(struct perf_stat_config *config, struct evsel *counter, char *prefix) { - int s, s2, id; + int s; + struct aggr_cpu_id s2, id; bool first = true; for (int i = 0; i < evsel__nr_cpus(counter); i++) { s2 = config->aggr_get_id(config, evsel__cpus(counter), i); for (s = 0; s < config->aggr_map->nr; s++) { id = config->aggr_map->map[s]; - if (s2 == id) + if (cpu_map__compare_aggr_cpu_id(s2, id)) break; } @@ -1184,12 +1204,8 @@ static void print_percore(struct perf_stat_config *config, fputc('\n', output); } -void -perf_evlist__print_counters(struct evlist *evlist, - struct perf_stat_config *config, - struct target *_target, - struct timespec *ts, - int argc, const char **argv) +void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *config, + struct target *_target, struct timespec *ts, int argc, const char **argv) { bool metric_only = config->metric_only; int interval = config->interval; diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index bd0decd6d753..8ce1479c98f0 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -184,7 +184,7 @@ static int evsel__alloc_stats(struct evsel *evsel, bool alloc_raw) return 0; } -int perf_evlist__alloc_stats(struct evlist *evlist, bool alloc_raw) +int evlist__alloc_stats(struct evlist *evlist, bool alloc_raw) { struct evsel *evsel; @@ -196,11 +196,11 @@ int perf_evlist__alloc_stats(struct evlist *evlist, bool alloc_raw) return 0; out_free: - perf_evlist__free_stats(evlist); + evlist__free_stats(evlist); return -1; } -void perf_evlist__free_stats(struct evlist *evlist) +void evlist__free_stats(struct evlist *evlist) { struct evsel *evsel; @@ -211,7 +211,7 @@ void perf_evlist__free_stats(struct evlist *evlist) } } -void perf_evlist__reset_stats(struct evlist *evlist) +void evlist__reset_stats(struct evlist *evlist) { struct evsel *evsel; @@ -221,7 +221,7 @@ void perf_evlist__reset_stats(struct evlist *evlist) } } -void perf_evlist__reset_prev_raw_counts(struct evlist *evlist) +void evlist__reset_prev_raw_counts(struct evlist *evlist) { struct evsel *evsel; @@ -229,7 +229,7 @@ void perf_evlist__reset_prev_raw_counts(struct evlist *evlist) evsel__reset_prev_raw_counts(evsel); } -static void perf_evsel__copy_prev_raw_counts(struct evsel *evsel) +static void evsel__copy_prev_raw_counts(struct evsel *evsel) { int ncpus = evsel__nr_cpus(evsel); int nthreads = perf_thread_map__nr(evsel->core.threads); @@ -245,15 +245,15 @@ static void perf_evsel__copy_prev_raw_counts(struct evsel *evsel) evsel->counts->aggr = evsel->prev_raw_counts->aggr; } -void perf_evlist__copy_prev_raw_counts(struct evlist *evlist) +void evlist__copy_prev_raw_counts(struct evlist *evlist) { struct evsel *evsel; evlist__for_each_entry(evlist, evsel) - perf_evsel__copy_prev_raw_counts(evsel); + evsel__copy_prev_raw_counts(evsel); } -void perf_evlist__save_aggr_prev_raw_counts(struct evlist *evlist) +void evlist__save_aggr_prev_raw_counts(struct evlist *evlist) { struct evsel *evsel; @@ -313,7 +313,7 @@ static int check_per_pkg(struct evsel *counter, if (!(vals->run && vals->ena)) return 0; - s = cpu_map__get_socket(cpus, cpu, NULL); + s = cpu_map__get_socket(cpus, cpu, NULL).socket; if (s < 0) return -1; @@ -458,7 +458,7 @@ int perf_event__process_stat_event(struct perf_session *session, count.ena = st->ena; count.run = st->run; - counter = perf_evlist__id2evsel(session->evlist, st->id); + counter = evlist__id2evsel(session->evlist, st->id); if (!counter) { pr_err("Failed to resolve counter for stat event.\n"); return -EINVAL; diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 487010c624be..b5369730b4a2 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -6,6 +6,7 @@ #include <stdio.h> #include <sys/types.h> #include <sys/resource.h> +#include "cpumap.h" #include "rblist.h" struct perf_cpu_map; @@ -99,7 +100,7 @@ struct runtime_stat { struct rblist value_list; }; -typedef int (*aggr_get_id_t)(struct perf_stat_config *config, +typedef struct aggr_cpu_id (*aggr_get_id_t)(struct perf_stat_config *config, struct perf_cpu_map *m, int cpu); struct perf_stat_config { @@ -122,6 +123,7 @@ struct perf_stat_config { bool metric_no_group; bool metric_no_merge; bool stop_read_counter; + bool quiet; FILE *output; unsigned int interval; unsigned int timeout; @@ -137,9 +139,9 @@ struct perf_stat_config { const char *csv_sep; struct stats *walltime_nsecs_stats; struct rusage ru_data; - struct perf_cpu_map *aggr_map; + struct cpu_aggr_map *aggr_map; aggr_get_id_t aggr_get_id; - struct perf_cpu_map *cpus_aggr_map; + struct cpu_aggr_map *cpus_aggr_map; u64 *walltime_run; struct rblist metric_events; int ctl_fd; @@ -169,7 +171,7 @@ struct evlist; struct perf_aggr_thread_value { struct evsel *counter; - int id; + struct aggr_cpu_id id; double uval; u64 val; u64 run; @@ -212,12 +214,12 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, struct runtime_stat *st); void perf_stat__collect_metric_expr(struct evlist *); -int perf_evlist__alloc_stats(struct evlist *evlist, bool alloc_raw); -void perf_evlist__free_stats(struct evlist *evlist); -void perf_evlist__reset_stats(struct evlist *evlist); -void perf_evlist__reset_prev_raw_counts(struct evlist *evlist); -void perf_evlist__copy_prev_raw_counts(struct evlist *evlist); -void perf_evlist__save_aggr_prev_raw_counts(struct evlist *evlist); +int evlist__alloc_stats(struct evlist *evlist, bool alloc_raw); +void evlist__free_stats(struct evlist *evlist); +void evlist__reset_stats(struct evlist *evlist); +void evlist__reset_prev_raw_counts(struct evlist *evlist); +void evlist__copy_prev_raw_counts(struct evlist *evlist); +void evlist__save_aggr_prev_raw_counts(struct evlist *evlist); int perf_stat_process_counter(struct perf_stat_config *config, struct evsel *counter); @@ -237,12 +239,8 @@ int create_perf_stat_counter(struct evsel *evsel, struct perf_stat_config *config, struct target *target, int cpu); -void -perf_evlist__print_counters(struct evlist *evlist, - struct perf_stat_config *config, - struct target *_target, - struct timespec *ts, - int argc, const char **argv); +void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *config, + struct target *_target, struct timespec *ts, int argc, const char **argv); struct metric_expr; double test_generic_metric(struct metric_expr *mexp, int cpu, struct runtime_stat *st); diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 44dd86a4f25f..f3577f7d72fe 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -534,7 +534,7 @@ out: #ifdef HAVE_LIBBFD_BUILDID_SUPPORT -int filename__read_build_id(const char *filename, struct build_id *bid) +static int read_build_id(const char *filename, struct build_id *bid) { size_t size = sizeof(bid->data); int err = -1; @@ -563,7 +563,7 @@ out_close: #else // HAVE_LIBBFD_BUILDID_SUPPORT -int filename__read_build_id(const char *filename, struct build_id *bid) +static int read_build_id(const char *filename, struct build_id *bid) { size_t size = sizeof(bid->data); int fd, err = -1; @@ -595,6 +595,39 @@ out: #endif // HAVE_LIBBFD_BUILDID_SUPPORT +int filename__read_build_id(const char *filename, struct build_id *bid) +{ + struct kmod_path m = { .name = NULL, }; + char path[PATH_MAX]; + int err; + + if (!filename) + return -EFAULT; + + err = kmod_path__parse(&m, filename); + if (err) + return -1; + + if (m.comp) { + int error = 0, fd; + + fd = filename__decompress(filename, path, sizeof(path), m.comp, &error); + if (fd < 0) { + pr_debug("Failed to decompress (error %d) %s\n", + error, filename); + return -1; + } + close(fd); + filename = path; + } + + err = read_build_id(filename, bid); + + if (m.comp) + unlink(filename); + return err; +} + int sysfs__read_build_id(const char *filename, struct build_id *bid) { size_t size = sizeof(bid->data); diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 0d14abdf3d72..64a039cbba1b 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -2189,6 +2189,8 @@ static int dso__load_kernel_sym(struct dso *dso, struct map *map) int err; const char *kallsyms_filename = NULL; char *kallsyms_allocated_filename = NULL; + char *filename = NULL; + /* * Step 1: if the user specified a kallsyms or vmlinux filename, use * it and only it, reporting errors to the user if it cannot be used. @@ -2213,6 +2215,20 @@ static int dso__load_kernel_sym(struct dso *dso, struct map *map) return dso__load_vmlinux(dso, map, symbol_conf.vmlinux_name, false); } + /* + * Before checking on common vmlinux locations, check if it's + * stored as standard build id binary (not kallsyms) under + * .debug cache. + */ + if (!symbol_conf.ignore_vmlinux_buildid) + filename = __dso__build_id_filename(dso, NULL, 0, false, false); + if (filename != NULL) { + err = dso__load_vmlinux(dso, map, filename, true); + if (err > 0) + return err; + free(filename); + } + if (!symbol_conf.ignore_vmlinux && vmlinux_path != NULL) { err = dso__load_vmlinux_path(dso, map); if (err > 0) diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index d9c624377da7..2947e3f3c6d9 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -1409,6 +1409,9 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, if (type & PERF_SAMPLE_CGROUP) result += sizeof(u64); + if (type & PERF_SAMPLE_DATA_PAGE_SIZE) + result += sizeof(u64); + if (type & PERF_SAMPLE_AUX) { result += sizeof(u64); result += sample->aux_sample.size; @@ -1588,6 +1591,11 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_fo array++; } + if (type & PERF_SAMPLE_DATA_PAGE_SIZE) { + *array = sample->data_page_size; + array++; + } + if (type & PERF_SAMPLE_AUX) { sz = sample->aux_sample.size; *array++ = sz; @@ -1643,7 +1651,7 @@ int perf_event__synthesize_id_index(struct perf_tool *tool, perf_event__handler_ e->id = evsel->core.id[j]; - sid = perf_evlist__id2sid(evlist, e->id); + sid = evlist__id2sid(evlist, e->id); if (!sid) { free(ev); return -ENOENT; diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index 7a3dbc259cec..0ada907c60d4 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -20,10 +20,24 @@ static char *debuginfo_path; +static int __find_debuginfo(Dwfl_Module *mod __maybe_unused, void **userdata, + const char *modname __maybe_unused, Dwarf_Addr base __maybe_unused, + const char *file_name, const char *debuglink_file __maybe_unused, + GElf_Word debuglink_crc __maybe_unused, char **debuginfo_file_name) +{ + const struct dso *dso = *userdata; + + assert(dso); + if (dso->symsrc_filename && strcmp (file_name, dso->symsrc_filename)) + *debuginfo_file_name = strdup(dso->symsrc_filename); + return -1; +} + static const Dwfl_Callbacks offline_callbacks = { - .find_debuginfo = dwfl_standard_find_debuginfo, + .find_debuginfo = __find_debuginfo, .debuginfo_path = &debuginfo_path, .section_address = dwfl_offline_section_address, + // .find_elf is not set as we use dwfl_report_elf() instead. }; static int __report_module(struct addr_location *al, u64 ip, @@ -46,16 +60,24 @@ static int __report_module(struct addr_location *al, u64 ip, mod = dwfl_addrmodule(ui->dwfl, ip); if (mod) { Dwarf_Addr s; + void **userdatap; - dwfl_module_info(mod, NULL, &s, NULL, NULL, NULL, NULL, NULL); + dwfl_module_info(mod, &userdatap, &s, NULL, NULL, NULL, NULL, NULL); + *userdatap = dso; if (s != al->map->start - al->map->pgoff) mod = 0; } if (!mod) - mod = dwfl_report_elf(ui->dwfl, dso->short_name, - (dso->symsrc_filename ? dso->symsrc_filename : dso->long_name), -1, al->map->start - al->map->pgoff, - false); + mod = dwfl_report_elf(ui->dwfl, dso->short_name, dso->long_name, -1, + al->map->start - al->map->pgoff, false); + if (!mod) { + char filename[PATH_MAX]; + + if (dso__build_id_filename(dso, filename, sizeof(filename), false)) + mod = dwfl_report_elf(ui->dwfl, dso->short_name, filename, -1, + al->map->start - al->map->pgoff, false); + } return mod && dwfl_addrmodule(ui->dwfl, ip) == mod ? 0 : -1; } diff --git a/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py b/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py index 3c47865bb247..e15e20696d17 100755 --- a/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py +++ b/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py @@ -1,4 +1,4 @@ -#!/usr/bin/python +#!/usr/bin/env python # SPDX-License-Identifier: GPL-2.0-only # -*- coding: utf-8 -*- # diff --git a/tools/testing/ktest/compare-ktest-sample.pl b/tools/testing/ktest/compare-ktest-sample.pl index 4118eb4a842d..ebea21d0a1be 100755 --- a/tools/testing/ktest/compare-ktest-sample.pl +++ b/tools/testing/ktest/compare-ktest-sample.pl @@ -1,4 +1,4 @@ -#!/usr/bin/perl +#!/usr/bin/env perl # SPDX-License-Identifier: GPL-2.0 open (IN,"ktest.pl"); diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl index 54188ee16c48..4e2450964517 100755 --- a/tools/testing/ktest/ktest.pl +++ b/tools/testing/ktest/ktest.pl @@ -1499,17 +1499,16 @@ sub dodie { my $log_file; if (defined($opt{"LOG_FILE"})) { - my $whence = 0; # beginning of file - my $pos = $test_log_start; + my $whence = 2; # End of file + my $log_size = tell LOG; + my $size = $log_size - $test_log_start; if (defined($mail_max_size)) { - my $log_size = tell LOG; - $log_size -= $test_log_start; - if ($log_size > $mail_max_size) { - $whence = 2; # end of file - $pos = - $mail_max_size; + if ($size > $mail_max_size) { + $size = $mail_max_size; } } + my $pos = - $size; $log_file = "$tmpdir/log"; open (L, "$opt{LOG_FILE}") or die "Can't open $opt{LOG_FILE} to read)"; open (O, "> $tmpdir/log") or die "Can't open $tmpdir/log\n"; @@ -4253,7 +4252,12 @@ sub do_send_mail { $mail_command =~ s/\$SUBJECT/$subject/g; $mail_command =~ s/\$MESSAGE/$message/g; - run_command $mail_command; + my $ret = run_command $mail_command; + if (!$ret && defined($file)) { + # try again without the file + $message .= "\n\n*** FAILED TO SEND LOG ***\n\n"; + do_send_email($subject, $message); + } } sub send_email { diff --git a/tools/testing/kunit/kunit.py b/tools/testing/kunit/kunit.py index d4f7846d0745..21516e293d17 100755 --- a/tools/testing/kunit/kunit.py +++ b/tools/testing/kunit/kunit.py @@ -1,4 +1,4 @@ -#!/usr/bin/python3 +#!/usr/bin/env python3 # SPDX-License-Identifier: GPL-2.0 # # A thin wrapper on top of the KUnit Kernel diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py index 497ab51bc170..b593f4448e83 100755 --- a/tools/testing/kunit/kunit_tool_test.py +++ b/tools/testing/kunit/kunit_tool_test.py @@ -1,4 +1,4 @@ -#!/usr/bin/python3 +#!/usr/bin/env python3 # SPDX-License-Identifier: GPL-2.0 # # A collection of tests for tools/testing/kunit/kunit.py diff --git a/tools/testing/selftests/arm64/mte/Makefile b/tools/testing/selftests/arm64/mte/Makefile index 2480226dfe57..0b3af552632a 100644 --- a/tools/testing/selftests/arm64/mte/Makefile +++ b/tools/testing/selftests/arm64/mte/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 # Copyright (C) 2020 ARM Limited -CFLAGS += -std=gnu99 -I. +CFLAGS += -std=gnu99 -I. -lpthread SRCS := $(filter-out mte_common_util.c,$(wildcard *.c)) PROGS := $(patsubst %.c,%,$(SRCS)) diff --git a/tools/testing/selftests/arm64/mte/check_gcr_el1_cswitch.c b/tools/testing/selftests/arm64/mte/check_gcr_el1_cswitch.c new file mode 100644 index 000000000000..a876db1f096a --- /dev/null +++ b/tools/testing/selftests/arm64/mte/check_gcr_el1_cswitch.c @@ -0,0 +1,154 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2020 ARM Limited + +#define _GNU_SOURCE + +#include <errno.h> +#include <pthread.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <time.h> +#include <unistd.h> +#include <sys/auxv.h> +#include <sys/mman.h> +#include <sys/prctl.h> +#include <sys/types.h> +#include <sys/wait.h> + +#include "kselftest.h" +#include "mte_common_util.h" + +#define PR_SET_TAGGED_ADDR_CTRL 55 +#define PR_GET_TAGGED_ADDR_CTRL 56 +# define PR_TAGGED_ADDR_ENABLE (1UL << 0) +# define PR_MTE_TCF_SHIFT 1 +# define PR_MTE_TCF_NONE (0UL << PR_MTE_TCF_SHIFT) +# define PR_MTE_TCF_SYNC (1UL << PR_MTE_TCF_SHIFT) +# define PR_MTE_TCF_ASYNC (2UL << PR_MTE_TCF_SHIFT) +# define PR_MTE_TCF_MASK (3UL << PR_MTE_TCF_SHIFT) +# define PR_MTE_TAG_SHIFT 3 +# define PR_MTE_TAG_MASK (0xffffUL << PR_MTE_TAG_SHIFT) + +#include "mte_def.h" + +#define NUM_ITERATIONS 1024 +#define MAX_THREADS 5 +#define THREAD_ITERATIONS 1000 + +void *execute_thread(void *x) +{ + pid_t pid = *((pid_t *)x); + pid_t tid = gettid(); + uint64_t prctl_tag_mask; + uint64_t prctl_set; + uint64_t prctl_get; + uint64_t prctl_tcf; + + srand(time(NULL) ^ (pid << 16) ^ (tid << 16)); + + prctl_tag_mask = rand() & 0xffff; + + if (prctl_tag_mask % 2) + prctl_tcf = PR_MTE_TCF_SYNC; + else + prctl_tcf = PR_MTE_TCF_ASYNC; + + prctl_set = PR_TAGGED_ADDR_ENABLE | prctl_tcf | (prctl_tag_mask << PR_MTE_TAG_SHIFT); + + for (int j = 0; j < THREAD_ITERATIONS; j++) { + if (prctl(PR_SET_TAGGED_ADDR_CTRL, prctl_set, 0, 0, 0)) { + perror("prctl() failed"); + goto fail; + } + + prctl_get = prctl(PR_GET_TAGGED_ADDR_CTRL, 0, 0, 0, 0); + + if (prctl_set != prctl_get) { + ksft_print_msg("Error: prctl_set: 0x%lx != prctl_get: 0x%lx\n", + prctl_set, prctl_get); + goto fail; + } + } + + return (void *)KSFT_PASS; + +fail: + return (void *)KSFT_FAIL; +} + +int execute_test(pid_t pid) +{ + pthread_t thread_id[MAX_THREADS]; + int thread_data[MAX_THREADS]; + + for (int i = 0; i < MAX_THREADS; i++) + pthread_create(&thread_id[i], NULL, + execute_thread, (void *)&pid); + + for (int i = 0; i < MAX_THREADS; i++) + pthread_join(thread_id[i], (void *)&thread_data[i]); + + for (int i = 0; i < MAX_THREADS; i++) + if (thread_data[i] == KSFT_FAIL) + return KSFT_FAIL; + + return KSFT_PASS; +} + +int mte_gcr_fork_test(void) +{ + pid_t pid; + int results[NUM_ITERATIONS]; + pid_t cpid; + int res; + + for (int i = 0; i < NUM_ITERATIONS; i++) { + pid = fork(); + + if (pid < 0) + return KSFT_FAIL; + + if (pid == 0) { + cpid = getpid(); + + res = execute_test(cpid); + + exit(res); + } + } + + for (int i = 0; i < NUM_ITERATIONS; i++) { + wait(&res); + + if (WIFEXITED(res)) + results[i] = WEXITSTATUS(res); + else + --i; + } + + for (int i = 0; i < NUM_ITERATIONS; i++) + if (results[i] == KSFT_FAIL) + return KSFT_FAIL; + + return KSFT_PASS; +} + +int main(int argc, char *argv[]) +{ + int err; + + err = mte_default_setup(); + if (err) + return err; + + ksft_set_plan(1); + + evaluate_test(mte_gcr_fork_test(), + "Verify that GCR_EL1 is set correctly on context switch\n"); + + mte_restore_setup(); + ksft_print_cnts(); + + return ksft_get_fail_cnt() == 0 ? KSFT_PASS : KSFT_FAIL; +} diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py index b99bb8ed3ed4..edaffd43da83 100755 --- a/tools/testing/selftests/bpf/test_offload.py +++ b/tools/testing/selftests/bpf/test_offload.py @@ -1,4 +1,4 @@ -#!/usr/bin/python3 +#!/usr/bin/env python3 # Copyright (C) 2017 Netronome Systems, Inc. # Copyright (c) 2019 Mellanox Technologies. All rights reserved diff --git a/tools/testing/selftests/core/close_range_test.c b/tools/testing/selftests/core/close_range_test.c index 87e16d65d9d7..73eb29c916d1 100644 --- a/tools/testing/selftests/core/close_range_test.c +++ b/tools/testing/selftests/core/close_range_test.c @@ -17,7 +17,23 @@ #include "../clone3/clone3_selftests.h" #ifndef __NR_close_range -#define __NR_close_range -1 + #if defined __alpha__ + #define __NR_close_range 546 + #elif defined _MIPS_SIM + #if _MIPS_SIM == _MIPS_SIM_ABI32 /* o32 */ + #define __NR_close_range (436 + 4000) + #endif + #if _MIPS_SIM == _MIPS_SIM_NABI32 /* n32 */ + #define __NR_close_range (436 + 6000) + #endif + #if _MIPS_SIM == _MIPS_SIM_ABI64 /* n64 */ + #define __NR_close_range (436 + 5000) + #endif + #elif defined __ia64__ + #define __NR_close_range (436 + 1024) + #else + #define __NR_close_range 436 + #endif #endif #ifndef CLOSE_RANGE_UNSHARE @@ -102,7 +118,7 @@ TEST(close_range_unshare) int i, ret, status; pid_t pid; int open_fds[101]; - struct clone_args args = { + struct __clone_args args = { .flags = CLONE_FILES, .exit_signal = SIGCHLD, }; @@ -191,7 +207,7 @@ TEST(close_range_unshare_capped) int i, ret, status; pid_t pid; int open_fds[101]; - struct clone_args args = { + struct __clone_args args = { .flags = CLONE_FILES, .exit_signal = SIGCHLD, }; @@ -241,7 +257,7 @@ TEST(close_range_cloexec) fd = open("/dev/null", O_RDONLY); ASSERT_GE(fd, 0) { if (errno == ENOENT) - XFAIL(return, "Skipping test since /dev/null does not exist"); + SKIP(return, "Skipping test since /dev/null does not exist"); } open_fds[i] = fd; @@ -250,9 +266,9 @@ TEST(close_range_cloexec) ret = sys_close_range(1000, 1000, CLOSE_RANGE_CLOEXEC); if (ret < 0) { if (errno == ENOSYS) - XFAIL(return, "close_range() syscall not supported"); + SKIP(return, "close_range() syscall not supported"); if (errno == EINVAL) - XFAIL(return, "close_range() doesn't support CLOSE_RANGE_CLOEXEC"); + SKIP(return, "close_range() doesn't support CLOSE_RANGE_CLOEXEC"); } /* Ensure the FD_CLOEXEC bit is set also with a resource limit in place. */ @@ -297,5 +313,258 @@ TEST(close_range_cloexec) } } +TEST(close_range_cloexec_unshare) +{ + int i, ret; + int open_fds[101]; + struct rlimit rlimit; + + for (i = 0; i < ARRAY_SIZE(open_fds); i++) { + int fd; + + fd = open("/dev/null", O_RDONLY); + ASSERT_GE(fd, 0) { + if (errno == ENOENT) + SKIP(return, "Skipping test since /dev/null does not exist"); + } + + open_fds[i] = fd; + } + + ret = sys_close_range(1000, 1000, CLOSE_RANGE_CLOEXEC); + if (ret < 0) { + if (errno == ENOSYS) + SKIP(return, "close_range() syscall not supported"); + if (errno == EINVAL) + SKIP(return, "close_range() doesn't support CLOSE_RANGE_CLOEXEC"); + } + + /* Ensure the FD_CLOEXEC bit is set also with a resource limit in place. */ + ASSERT_EQ(0, getrlimit(RLIMIT_NOFILE, &rlimit)); + rlimit.rlim_cur = 25; + ASSERT_EQ(0, setrlimit(RLIMIT_NOFILE, &rlimit)); + + /* Set close-on-exec for two ranges: [0-50] and [75-100]. */ + ret = sys_close_range(open_fds[0], open_fds[50], + CLOSE_RANGE_CLOEXEC | CLOSE_RANGE_UNSHARE); + ASSERT_EQ(0, ret); + ret = sys_close_range(open_fds[75], open_fds[100], + CLOSE_RANGE_CLOEXEC | CLOSE_RANGE_UNSHARE); + ASSERT_EQ(0, ret); + + for (i = 0; i <= 50; i++) { + int flags = fcntl(open_fds[i], F_GETFD); + + EXPECT_GT(flags, -1); + EXPECT_EQ(flags & FD_CLOEXEC, FD_CLOEXEC); + } + + for (i = 51; i <= 74; i++) { + int flags = fcntl(open_fds[i], F_GETFD); + + EXPECT_GT(flags, -1); + EXPECT_EQ(flags & FD_CLOEXEC, 0); + } + + for (i = 75; i <= 100; i++) { + int flags = fcntl(open_fds[i], F_GETFD); + + EXPECT_GT(flags, -1); + EXPECT_EQ(flags & FD_CLOEXEC, FD_CLOEXEC); + } + + /* Test a common pattern. */ + ret = sys_close_range(3, UINT_MAX, + CLOSE_RANGE_CLOEXEC | CLOSE_RANGE_UNSHARE); + for (i = 0; i <= 100; i++) { + int flags = fcntl(open_fds[i], F_GETFD); + + EXPECT_GT(flags, -1); + EXPECT_EQ(flags & FD_CLOEXEC, FD_CLOEXEC); + } +} + +/* + * Regression test for syzbot+96cfd2b22b3213646a93@syzkaller.appspotmail.com + */ +TEST(close_range_cloexec_syzbot) +{ + int fd1, fd2, fd3, flags, ret, status; + pid_t pid; + struct __clone_args args = { + .flags = CLONE_FILES, + .exit_signal = SIGCHLD, + }; + + /* Create a huge gap in the fd table. */ + fd1 = open("/dev/null", O_RDWR); + EXPECT_GT(fd1, 0); + + fd2 = dup2(fd1, 1000); + EXPECT_GT(fd2, 0); + + pid = sys_clone3(&args, sizeof(args)); + ASSERT_GE(pid, 0); + + if (pid == 0) { + ret = sys_close_range(3, ~0U, CLOSE_RANGE_CLOEXEC); + if (ret) + exit(EXIT_FAILURE); + + /* + * We now have a private file descriptor table and all + * our open fds should still be open but made + * close-on-exec. + */ + flags = fcntl(fd1, F_GETFD); + EXPECT_GT(flags, -1); + EXPECT_EQ(flags & FD_CLOEXEC, FD_CLOEXEC); + + flags = fcntl(fd2, F_GETFD); + EXPECT_GT(flags, -1); + EXPECT_EQ(flags & FD_CLOEXEC, FD_CLOEXEC); + + fd3 = dup2(fd1, 42); + EXPECT_GT(fd3, 0); + + /* + * Duplicating the file descriptor must remove the + * FD_CLOEXEC flag. + */ + flags = fcntl(fd3, F_GETFD); + EXPECT_GT(flags, -1); + EXPECT_EQ(flags & FD_CLOEXEC, 0); + + exit(EXIT_SUCCESS); + } + + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); + + /* + * We had a shared file descriptor table before along with requesting + * close-on-exec so the original fds must not be close-on-exec. + */ + flags = fcntl(fd1, F_GETFD); + EXPECT_GT(flags, -1); + EXPECT_EQ(flags & FD_CLOEXEC, FD_CLOEXEC); + + flags = fcntl(fd2, F_GETFD); + EXPECT_GT(flags, -1); + EXPECT_EQ(flags & FD_CLOEXEC, FD_CLOEXEC); + + fd3 = dup2(fd1, 42); + EXPECT_GT(fd3, 0); + + flags = fcntl(fd3, F_GETFD); + EXPECT_GT(flags, -1); + EXPECT_EQ(flags & FD_CLOEXEC, 0); + + EXPECT_EQ(close(fd1), 0); + EXPECT_EQ(close(fd2), 0); + EXPECT_EQ(close(fd3), 0); +} + +/* + * Regression test for syzbot+96cfd2b22b3213646a93@syzkaller.appspotmail.com + */ +TEST(close_range_cloexec_unshare_syzbot) +{ + int i, fd1, fd2, fd3, flags, ret, status; + pid_t pid; + struct __clone_args args = { + .flags = CLONE_FILES, + .exit_signal = SIGCHLD, + }; + + /* + * Create a huge gap in the fd table. When we now call + * CLOSE_RANGE_UNSHARE with a shared fd table and and with ~0U as upper + * bound the kernel will only copy up to fd1 file descriptors into the + * new fd table. If the kernel is buggy and doesn't handle + * CLOSE_RANGE_CLOEXEC correctly it will not have copied all file + * descriptors and we will oops! + * + * On a buggy kernel this should immediately oops. But let's loop just + * to be sure. + */ + fd1 = open("/dev/null", O_RDWR); + EXPECT_GT(fd1, 0); + + fd2 = dup2(fd1, 1000); + EXPECT_GT(fd2, 0); + + for (i = 0; i < 100; i++) { + + pid = sys_clone3(&args, sizeof(args)); + ASSERT_GE(pid, 0); + + if (pid == 0) { + ret = sys_close_range(3, ~0U, CLOSE_RANGE_UNSHARE | + CLOSE_RANGE_CLOEXEC); + if (ret) + exit(EXIT_FAILURE); + + /* + * We now have a private file descriptor table and all + * our open fds should still be open but made + * close-on-exec. + */ + flags = fcntl(fd1, F_GETFD); + EXPECT_GT(flags, -1); + EXPECT_EQ(flags & FD_CLOEXEC, FD_CLOEXEC); + + flags = fcntl(fd2, F_GETFD); + EXPECT_GT(flags, -1); + EXPECT_EQ(flags & FD_CLOEXEC, FD_CLOEXEC); + + fd3 = dup2(fd1, 42); + EXPECT_GT(fd3, 0); + + /* + * Duplicating the file descriptor must remove the + * FD_CLOEXEC flag. + */ + flags = fcntl(fd3, F_GETFD); + EXPECT_GT(flags, -1); + EXPECT_EQ(flags & FD_CLOEXEC, 0); + + EXPECT_EQ(close(fd1), 0); + EXPECT_EQ(close(fd2), 0); + EXPECT_EQ(close(fd3), 0); + + exit(EXIT_SUCCESS); + } + + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); + } + + /* + * We created a private file descriptor table before along with + * requesting close-on-exec so the original fds must not be + * close-on-exec. + */ + flags = fcntl(fd1, F_GETFD); + EXPECT_GT(flags, -1); + EXPECT_EQ(flags & FD_CLOEXEC, 0); + + flags = fcntl(fd2, F_GETFD); + EXPECT_GT(flags, -1); + EXPECT_EQ(flags & FD_CLOEXEC, 0); + + fd3 = dup2(fd1, 42); + EXPECT_GT(fd3, 0); + + flags = fcntl(fd3, F_GETFD); + EXPECT_GT(flags, -1); + EXPECT_EQ(flags & FD_CLOEXEC, 0); + + EXPECT_EQ(close(fd1), 0); + EXPECT_EQ(close(fd2), 0); + EXPECT_EQ(close(fd3), 0); +} TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/dma/Makefile b/tools/testing/selftests/dma/Makefile new file mode 100644 index 000000000000..aa8e8b5b3864 --- /dev/null +++ b/tools/testing/selftests/dma/Makefile @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0 +CFLAGS += -I../../../../usr/include/ + +TEST_GEN_PROGS := dma_map_benchmark + +include ../lib.mk diff --git a/tools/testing/selftests/dma/config b/tools/testing/selftests/dma/config new file mode 100644 index 000000000000..6102ee3c43cd --- /dev/null +++ b/tools/testing/selftests/dma/config @@ -0,0 +1 @@ +CONFIG_DMA_MAP_BENCHMARK=y diff --git a/tools/testing/selftests/dma/dma_map_benchmark.c b/tools/testing/selftests/dma/dma_map_benchmark.c new file mode 100644 index 000000000000..7065163a8388 --- /dev/null +++ b/tools/testing/selftests/dma/dma_map_benchmark.c @@ -0,0 +1,123 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020 Hisilicon Limited. + */ + +#include <fcntl.h> +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <sys/ioctl.h> +#include <sys/mman.h> +#include <linux/types.h> + +#define DMA_MAP_BENCHMARK _IOWR('d', 1, struct map_benchmark) +#define DMA_MAP_MAX_THREADS 1024 +#define DMA_MAP_MAX_SECONDS 300 + +#define DMA_MAP_BIDIRECTIONAL 0 +#define DMA_MAP_TO_DEVICE 1 +#define DMA_MAP_FROM_DEVICE 2 + +static char *directions[] = { + "BIDIRECTIONAL", + "TO_DEVICE", + "FROM_DEVICE", +}; + +struct map_benchmark { + __u64 avg_map_100ns; /* average map latency in 100ns */ + __u64 map_stddev; /* standard deviation of map latency */ + __u64 avg_unmap_100ns; /* as above */ + __u64 unmap_stddev; + __u32 threads; /* how many threads will do map/unmap in parallel */ + __u32 seconds; /* how long the test will last */ + __s32 node; /* which numa node this benchmark will run on */ + __u32 dma_bits; /* DMA addressing capability */ + __u32 dma_dir; /* DMA data direction */ + __u64 expansion[10]; /* For future use */ +}; + +int main(int argc, char **argv) +{ + struct map_benchmark map; + int fd, opt; + /* default single thread, run 20 seconds on NUMA_NO_NODE */ + int threads = 1, seconds = 20, node = -1; + /* default dma mask 32bit, bidirectional DMA */ + int bits = 32, dir = DMA_MAP_BIDIRECTIONAL; + + int cmd = DMA_MAP_BENCHMARK; + char *p; + + while ((opt = getopt(argc, argv, "t:s:n:b:d:")) != -1) { + switch (opt) { + case 't': + threads = atoi(optarg); + break; + case 's': + seconds = atoi(optarg); + break; + case 'n': + node = atoi(optarg); + break; + case 'b': + bits = atoi(optarg); + break; + case 'd': + dir = atoi(optarg); + break; + default: + return -1; + } + } + + if (threads <= 0 || threads > DMA_MAP_MAX_THREADS) { + fprintf(stderr, "invalid number of threads, must be in 1-%d\n", + DMA_MAP_MAX_THREADS); + exit(1); + } + + if (seconds <= 0 || seconds > DMA_MAP_MAX_SECONDS) { + fprintf(stderr, "invalid number of seconds, must be in 1-%d\n", + DMA_MAP_MAX_SECONDS); + exit(1); + } + + /* suppose the mininum DMA zone is 1MB in the world */ + if (bits < 20 || bits > 64) { + fprintf(stderr, "invalid dma mask bit, must be in 20-64\n"); + exit(1); + } + + if (dir != DMA_MAP_BIDIRECTIONAL && dir != DMA_MAP_TO_DEVICE && + dir != DMA_MAP_FROM_DEVICE) { + fprintf(stderr, "invalid dma direction\n"); + exit(1); + } + + fd = open("/sys/kernel/debug/dma_map_benchmark", O_RDWR); + if (fd == -1) { + perror("open"); + exit(1); + } + + map.seconds = seconds; + map.threads = threads; + map.node = node; + map.dma_bits = bits; + map.dma_dir = dir; + if (ioctl(fd, cmd, &map)) { + perror("ioctl"); + exit(1); + } + + printf("dma mapping benchmark: threads:%d seconds:%d node:%d dir:%s\n", + threads, seconds, node, dir[directions]); + printf("average map latency(us):%.1f standard deviation:%.1f\n", + map.avg_map_100ns/10.0, map.map_stddev/10.0); + printf("average unmap latency(us):%.1f standard deviation:%.1f\n", + map.avg_unmap_100ns/10.0, map.unmap_stddev/10.0); + + return 0; +} diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh index 4d900bc1f76c..5c7700212f75 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh @@ -230,7 +230,7 @@ switch_create() __mlnx_qos -i $swp4 --pfc=0,1,0,0,0,0,0,0 >/dev/null # PG0 will get autoconfigured to Xoff, give PG1 arbitrarily 100K, which # is (-2*MTU) about 80K of delay provision. - __mlnx_qos -i $swp3 --buffer_size=0,$_100KB,0,0,0,0,0,0 >/dev/null + __mlnx_qos -i $swp4 --buffer_size=0,$_100KB,0,0,0,0,0,0 >/dev/null # bridges # ------- diff --git a/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer_configuration.py b/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer_configuration.py index 0d4b9327c9b3..2223337eed0c 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer_configuration.py +++ b/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer_configuration.py @@ -1,4 +1,4 @@ -#!/usr/bin/python +#!/usr/bin/env python # SPDX-License-Identifier: GPL-2.0 import subprocess diff --git a/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c b/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c index 8f82f99f7748..ad7fabd575f9 100644 --- a/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c +++ b/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 #define _GNU_SOURCE +#include <asm/unistd.h> +#include <linux/time_types.h> #include <poll.h> #include <unistd.h> #include <assert.h> @@ -21,6 +23,19 @@ struct epoll_mtcontext pthread_t waiter; }; +#ifndef __NR_epoll_pwait2 +#define __NR_epoll_pwait2 -1 +#endif + +static inline int sys_epoll_pwait2(int fd, struct epoll_event *events, + int maxevents, + const struct __kernel_timespec *timeout, + const sigset_t *sigset, size_t sigsetsize) +{ + return syscall(__NR_epoll_pwait2, fd, events, maxevents, timeout, + sigset, sigsetsize); +} + static void signal_handler(int signum) { } @@ -3377,4 +3392,61 @@ TEST(epoll61) close(ctx.evfd); } +/* Equivalent to basic test epoll1, but exercising epoll_pwait2. */ +TEST(epoll62) +{ + int efd; + int sfd[2]; + struct epoll_event e; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, sfd), 0); + + efd = epoll_create(1); + ASSERT_GE(efd, 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd, EPOLL_CTL_ADD, sfd[0], &e), 0); + + ASSERT_EQ(write(sfd[1], "w", 1), 1); + + EXPECT_EQ(sys_epoll_pwait2(efd, &e, 1, NULL, NULL, 0), 1); + EXPECT_EQ(sys_epoll_pwait2(efd, &e, 1, NULL, NULL, 0), 1); + + close(efd); + close(sfd[0]); + close(sfd[1]); +} + +/* Epoll_pwait2 basic timeout test. */ +TEST(epoll63) +{ + const int cfg_delay_ms = 10; + unsigned long long tdiff; + struct __kernel_timespec ts; + int efd; + int sfd[2]; + struct epoll_event e; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, sfd), 0); + + efd = epoll_create(1); + ASSERT_GE(efd, 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd, EPOLL_CTL_ADD, sfd[0], &e), 0); + + ts.tv_sec = 0; + ts.tv_nsec = cfg_delay_ms * 1000 * 1000; + + tdiff = msecs(); + EXPECT_EQ(sys_epoll_pwait2(efd, &e, 1, &ts, NULL, 0), 0); + tdiff = msecs() - tdiff; + + EXPECT_GE(tdiff, cfg_delay_ms); + + close(efd); + close(sfd[0]); + close(sfd[1]); +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/kselftest/prefix.pl b/tools/testing/selftests/kselftest/prefix.pl index 31f7c2a0a8bd..12a7f4ca2684 100755 --- a/tools/testing/selftests/kselftest/prefix.pl +++ b/tools/testing/selftests/kselftest/prefix.pl @@ -1,4 +1,4 @@ -#!/usr/bin/perl +#!/usr/bin/env perl # SPDX-License-Identifier: GPL-2.0 # Prefix all lines with "# ", unbuffered. Command being piped in may need # to have unbuffering forced with "stdbuf -i0 -o0 -e0 $cmd". diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index 7a2c242b7152..ce8f4ad39684 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -14,17 +14,17 @@ /x86_64/set_sregs_test /x86_64/smm_test /x86_64/state_test -/x86_64/user_msr_test -/x86_64/vmx_preemption_timer_test /x86_64/svm_vmcall_test /x86_64/sync_regs_test +/x86_64/tsc_msrs_test +/x86_64/userspace_msr_exit_test /x86_64/vmx_apic_access_test /x86_64/vmx_close_while_nested_test /x86_64/vmx_dirty_log_test +/x86_64/vmx_preemption_timer_test /x86_64/vmx_set_nested_state_test /x86_64/vmx_tsc_adjust_test /x86_64/xss_msr_test -/clear_dirty_log_test /demand_paging_test /dirty_log_test /dirty_log_perf_test diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 3d14ef77755e..c7ca4faba272 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -36,7 +36,7 @@ endif LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c lib/test_util.c LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c lib/x86_64/handlers.S LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c -LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c +LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c lib/s390x/diag318_test_handler.c TEST_GEN_PROGS_x86_64 = x86_64/cr4_cpuid_sync_test TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test @@ -50,6 +50,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/state_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_preemption_timer_test TEST_GEN_PROGS_x86_64 += x86_64/svm_vmcall_test TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test +TEST_GEN_PROGS_x86_64 += x86_64/userspace_msr_exit_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_apic_access_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_close_while_nested_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_dirty_log_test @@ -58,7 +59,6 @@ TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test TEST_GEN_PROGS_x86_64 += x86_64/xss_msr_test TEST_GEN_PROGS_x86_64 += x86_64/debug_regs TEST_GEN_PROGS_x86_64 += x86_64/tsc_msrs_test -TEST_GEN_PROGS_x86_64 += x86_64/user_msr_test TEST_GEN_PROGS_x86_64 += demand_paging_test TEST_GEN_PROGS_x86_64 += dirty_log_test TEST_GEN_PROGS_x86_64 += dirty_log_perf_test @@ -70,6 +70,7 @@ TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list-sve TEST_GEN_PROGS_aarch64 += demand_paging_test TEST_GEN_PROGS_aarch64 += dirty_log_test +TEST_GEN_PROGS_aarch64 += dirty_log_perf_test TEST_GEN_PROGS_aarch64 += kvm_create_max_vcpus TEST_GEN_PROGS_aarch64 += set_memory_region_test TEST_GEN_PROGS_aarch64 += steal_time diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c index 33218a395d9f..486932164cf2 100644 --- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c +++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c @@ -42,12 +42,16 @@ #define for_each_reg(i) \ for ((i) = 0; (i) < reg_list->n; ++(i)) +#define for_each_reg_filtered(i) \ + for_each_reg(i) \ + if (!filter_reg(reg_list->reg[i])) + #define for_each_missing_reg(i) \ for ((i) = 0; (i) < blessed_n; ++(i)) \ if (!find_reg(reg_list->reg, reg_list->n, blessed_reg[i])) #define for_each_new_reg(i) \ - for ((i) = 0; (i) < reg_list->n; ++(i)) \ + for_each_reg_filtered(i) \ if (!find_reg(blessed_reg, blessed_n, reg_list->reg[i])) @@ -57,6 +61,18 @@ static __u64 base_regs[], vregs[], sve_regs[], rejects_set[]; static __u64 base_regs_n, vregs_n, sve_regs_n, rejects_set_n; static __u64 *blessed_reg, blessed_n; +static bool filter_reg(__u64 reg) +{ + /* + * DEMUX register presence depends on the host's CLIDR_EL1. + * This means there's no set of them that we can bless. + */ + if ((reg & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_DEMUX) + return true; + + return false; +} + static bool find_reg(__u64 regs[], __u64 nr_regs, __u64 reg) { int i; @@ -325,7 +341,7 @@ int main(int ac, char **av) struct kvm_vcpu_init init = { .target = -1, }; int new_regs = 0, missing_regs = 0, i; int failed_get = 0, failed_set = 0, failed_reject = 0; - bool print_list = false, fixup_core_regs = false; + bool print_list = false, print_filtered = false, fixup_core_regs = false; struct kvm_vm *vm; __u64 *vec_regs; @@ -336,8 +352,10 @@ int main(int ac, char **av) fixup_core_regs = true; else if (strcmp(av[i], "--list") == 0) print_list = true; + else if (strcmp(av[i], "--list-filtered") == 0) + print_filtered = true; else - fprintf(stderr, "Ignoring unknown option: %s\n", av[i]); + TEST_FAIL("Unknown option: %s\n", av[i]); } vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR); @@ -350,10 +368,14 @@ int main(int ac, char **av) if (fixup_core_regs) core_reg_fixup(); - if (print_list) { + if (print_list || print_filtered) { putchar('\n'); - for_each_reg(i) - print_reg(reg_list->reg[i]); + for_each_reg(i) { + __u64 id = reg_list->reg[i]; + if ((print_list && !filter_reg(id)) || + (print_filtered && filter_reg(id))) + print_reg(id); + } putchar('\n'); return 0; } @@ -458,6 +480,8 @@ int main(int ac, char **av) /* * The current blessed list was primed with the output of kernel version * v4.15 with --core-reg-fixup and then later updated with new registers. + * + * The blessed list is up to date with kernel version v5.10-rc5 */ static __u64 base_regs[] = { KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[0]), @@ -736,9 +760,6 @@ static __u64 base_regs[] = { ARM64_SYS_REG(3, 4, 3, 0, 0), /* DACR32_EL2 */ ARM64_SYS_REG(3, 4, 5, 0, 1), /* IFSR32_EL2 */ ARM64_SYS_REG(3, 4, 5, 3, 0), /* FPEXC32_EL2 */ - KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | 0, - KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | 1, - KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | 2, }; static __u64 base_regs_n = ARRAY_SIZE(base_regs); diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c index 85c9b8f73142..9c6a7be31e03 100644 --- a/tools/testing/selftests/kvm/dirty_log_perf_test.c +++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c @@ -27,6 +27,7 @@ #define TEST_HOST_LOOP_N 2UL /* Host variables */ +static u64 dirty_log_manual_caps; static bool host_quit; static uint64_t iteration; static uint64_t vcpu_last_completed_iteration[MAX_VCPUS]; @@ -88,10 +89,6 @@ static void *vcpu_worker(void *data) return NULL; } -#ifdef USE_CLEAR_DIRTY_LOG -static u64 dirty_log_manual_caps; -#endif - static void run_test(enum vm_guest_mode mode, unsigned long iterations, uint64_t phys_offset, int wr_fract) { @@ -106,10 +103,8 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations, struct timespec get_dirty_log_total = (struct timespec){0}; struct timespec vcpu_dirty_total = (struct timespec){0}; struct timespec avg; -#ifdef USE_CLEAR_DIRTY_LOG struct kvm_enable_cap cap = {}; struct timespec clear_dirty_log_total = (struct timespec){0}; -#endif vm = create_vm(mode, nr_vcpus, guest_percpu_mem_size); @@ -120,11 +115,11 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations, host_num_pages = vm_num_host_pages(mode, guest_num_pages); bmap = bitmap_alloc(host_num_pages); -#ifdef USE_CLEAR_DIRTY_LOG - cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2; - cap.args[0] = dirty_log_manual_caps; - vm_enable_cap(vm, &cap); -#endif + if (dirty_log_manual_caps) { + cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2; + cap.args[0] = dirty_log_manual_caps; + vm_enable_cap(vm, &cap); + } vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads)); TEST_ASSERT(vcpu_threads, "Memory allocation failed"); @@ -190,17 +185,17 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations, pr_info("Iteration %lu get dirty log time: %ld.%.9lds\n", iteration, ts_diff.tv_sec, ts_diff.tv_nsec); -#ifdef USE_CLEAR_DIRTY_LOG - clock_gettime(CLOCK_MONOTONIC, &start); - kvm_vm_clear_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap, 0, - host_num_pages); + if (dirty_log_manual_caps) { + clock_gettime(CLOCK_MONOTONIC, &start); + kvm_vm_clear_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap, 0, + host_num_pages); - ts_diff = timespec_diff_now(start); - clear_dirty_log_total = timespec_add(clear_dirty_log_total, - ts_diff); - pr_info("Iteration %lu clear dirty log time: %ld.%.9lds\n", - iteration, ts_diff.tv_sec, ts_diff.tv_nsec); -#endif + ts_diff = timespec_diff_now(start); + clear_dirty_log_total = timespec_add(clear_dirty_log_total, + ts_diff); + pr_info("Iteration %lu clear dirty log time: %ld.%.9lds\n", + iteration, ts_diff.tv_sec, ts_diff.tv_nsec); + } } /* Tell the vcpu thread to quit */ @@ -220,12 +215,12 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations, iterations, get_dirty_log_total.tv_sec, get_dirty_log_total.tv_nsec, avg.tv_sec, avg.tv_nsec); -#ifdef USE_CLEAR_DIRTY_LOG - avg = timespec_div(clear_dirty_log_total, iterations); - pr_info("Clear dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n", - iterations, clear_dirty_log_total.tv_sec, - clear_dirty_log_total.tv_nsec, avg.tv_sec, avg.tv_nsec); -#endif + if (dirty_log_manual_caps) { + avg = timespec_div(clear_dirty_log_total, iterations); + pr_info("Clear dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n", + iterations, clear_dirty_log_total.tv_sec, + clear_dirty_log_total.tv_nsec, avg.tv_sec, avg.tv_nsec); + } free(bmap); free(vcpu_threads); @@ -284,16 +279,10 @@ int main(int argc, char *argv[]) int opt, i; int wr_fract = 1; -#ifdef USE_CLEAR_DIRTY_LOG dirty_log_manual_caps = kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2); - if (!dirty_log_manual_caps) { - print_skip("KVM_CLEAR_DIRTY_LOG not available"); - exit(KSFT_SKIP); - } dirty_log_manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | KVM_DIRTY_LOG_INITIALLY_SET); -#endif #ifdef __x86_64__ guest_mode_init(VM_MODE_PXXV48_4K, true, true); diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c index 54da9cc20db4..471baecb7772 100644 --- a/tools/testing/selftests/kvm/dirty_log_test.c +++ b/tools/testing/selftests/kvm/dirty_log_test.c @@ -12,8 +12,13 @@ #include <unistd.h> #include <time.h> #include <pthread.h> +#include <semaphore.h> +#include <sys/types.h> +#include <signal.h> +#include <errno.h> #include <linux/bitmap.h> #include <linux/bitops.h> +#include <asm/barrier.h> #include "test_util.h" #include "kvm_util.h" @@ -57,6 +62,10 @@ # define test_and_clear_bit_le test_and_clear_bit #endif +#define TEST_DIRTY_RING_COUNT 65536 + +#define SIG_IPI SIGUSR1 + /* * Guest/Host shared variables. Ensure addr_gva2hva() and/or * sync_global_to/from_guest() are used when accessing from @@ -128,6 +137,31 @@ static uint64_t host_dirty_count; static uint64_t host_clear_count; static uint64_t host_track_next_count; +/* Whether dirty ring reset is requested, or finished */ +static sem_t dirty_ring_vcpu_stop; +static sem_t dirty_ring_vcpu_cont; +/* + * This is updated by the vcpu thread to tell the host whether it's a + * ring-full event. It should only be read until a sem_wait() of + * dirty_ring_vcpu_stop and before vcpu continues to run. + */ +static bool dirty_ring_vcpu_ring_full; +/* + * This is only used for verifying the dirty pages. Dirty ring has a very + * tricky case when the ring just got full, kvm will do userspace exit due to + * ring full. When that happens, the very last PFN is set but actually the + * data is not changed (the guest WRITE is not really applied yet), because + * we found that the dirty ring is full, refused to continue the vcpu, and + * recorded the dirty gfn with the old contents. + * + * For this specific case, it's safe to skip checking this pfn for this + * bit, because it's a redundant bit, and when the write happens later the bit + * will be set again. We use this variable to always keep track of the latest + * dirty gfn we've collected, so that if a mismatch of data found later in the + * verifying process, we let it pass. + */ +static uint64_t dirty_ring_last_page; + enum log_mode_t { /* Only use KVM_GET_DIRTY_LOG for logging */ LOG_MODE_DIRTY_LOG = 0, @@ -135,6 +169,9 @@ enum log_mode_t { /* Use both KVM_[GET|CLEAR]_DIRTY_LOG for logging */ LOG_MODE_CLEAR_LOG = 1, + /* Use dirty ring for logging */ + LOG_MODE_DIRTY_RING = 2, + LOG_MODE_NUM, /* Run all supported modes */ @@ -145,6 +182,26 @@ enum log_mode_t { static enum log_mode_t host_log_mode_option = LOG_MODE_ALL; /* Logging mode for current run */ static enum log_mode_t host_log_mode; +static pthread_t vcpu_thread; +static uint32_t test_dirty_ring_count = TEST_DIRTY_RING_COUNT; + +static void vcpu_kick(void) +{ + pthread_kill(vcpu_thread, SIG_IPI); +} + +/* + * In our test we do signal tricks, let's use a better version of + * sem_wait to avoid signal interrupts + */ +static void sem_wait_until(sem_t *sem) +{ + int ret; + + do + ret = sem_wait(sem); + while (ret == -1 && errno == EINTR); +} static bool clear_log_supported(void) { @@ -178,6 +235,152 @@ static void clear_log_collect_dirty_pages(struct kvm_vm *vm, int slot, kvm_vm_clear_dirty_log(vm, slot, bitmap, 0, num_pages); } +static void default_after_vcpu_run(struct kvm_vm *vm, int ret, int err) +{ + struct kvm_run *run = vcpu_state(vm, VCPU_ID); + + TEST_ASSERT(ret == 0 || (ret == -1 && err == EINTR), + "vcpu run failed: errno=%d", err); + + TEST_ASSERT(get_ucall(vm, VCPU_ID, NULL) == UCALL_SYNC, + "Invalid guest sync status: exit_reason=%s\n", + exit_reason_str(run->exit_reason)); +} + +static bool dirty_ring_supported(void) +{ + return kvm_check_cap(KVM_CAP_DIRTY_LOG_RING); +} + +static void dirty_ring_create_vm_done(struct kvm_vm *vm) +{ + /* + * Switch to dirty ring mode after VM creation but before any + * of the vcpu creation. + */ + vm_enable_dirty_ring(vm, test_dirty_ring_count * + sizeof(struct kvm_dirty_gfn)); +} + +static inline bool dirty_gfn_is_dirtied(struct kvm_dirty_gfn *gfn) +{ + return gfn->flags == KVM_DIRTY_GFN_F_DIRTY; +} + +static inline void dirty_gfn_set_collected(struct kvm_dirty_gfn *gfn) +{ + gfn->flags = KVM_DIRTY_GFN_F_RESET; +} + +static uint32_t dirty_ring_collect_one(struct kvm_dirty_gfn *dirty_gfns, + int slot, void *bitmap, + uint32_t num_pages, uint32_t *fetch_index) +{ + struct kvm_dirty_gfn *cur; + uint32_t count = 0; + + while (true) { + cur = &dirty_gfns[*fetch_index % test_dirty_ring_count]; + if (!dirty_gfn_is_dirtied(cur)) + break; + TEST_ASSERT(cur->slot == slot, "Slot number didn't match: " + "%u != %u", cur->slot, slot); + TEST_ASSERT(cur->offset < num_pages, "Offset overflow: " + "0x%llx >= 0x%x", cur->offset, num_pages); + //pr_info("fetch 0x%x page %llu\n", *fetch_index, cur->offset); + set_bit_le(cur->offset, bitmap); + dirty_ring_last_page = cur->offset; + dirty_gfn_set_collected(cur); + (*fetch_index)++; + count++; + } + + return count; +} + +static void dirty_ring_wait_vcpu(void) +{ + /* This makes sure that hardware PML cache flushed */ + vcpu_kick(); + sem_wait_until(&dirty_ring_vcpu_stop); +} + +static void dirty_ring_continue_vcpu(void) +{ + pr_info("Notifying vcpu to continue\n"); + sem_post(&dirty_ring_vcpu_cont); +} + +static void dirty_ring_collect_dirty_pages(struct kvm_vm *vm, int slot, + void *bitmap, uint32_t num_pages) +{ + /* We only have one vcpu */ + static uint32_t fetch_index = 0; + uint32_t count = 0, cleared; + bool continued_vcpu = false; + + dirty_ring_wait_vcpu(); + + if (!dirty_ring_vcpu_ring_full) { + /* + * This is not a ring-full event, it's safe to allow + * vcpu to continue + */ + dirty_ring_continue_vcpu(); + continued_vcpu = true; + } + + /* Only have one vcpu */ + count = dirty_ring_collect_one(vcpu_map_dirty_ring(vm, VCPU_ID), + slot, bitmap, num_pages, &fetch_index); + + cleared = kvm_vm_reset_dirty_ring(vm); + + /* Cleared pages should be the same as collected */ + TEST_ASSERT(cleared == count, "Reset dirty pages (%u) mismatch " + "with collected (%u)", cleared, count); + + if (!continued_vcpu) { + TEST_ASSERT(dirty_ring_vcpu_ring_full, + "Didn't continue vcpu even without ring full"); + dirty_ring_continue_vcpu(); + } + + pr_info("Iteration %ld collected %u pages\n", iteration, count); +} + +static void dirty_ring_after_vcpu_run(struct kvm_vm *vm, int ret, int err) +{ + struct kvm_run *run = vcpu_state(vm, VCPU_ID); + + /* A ucall-sync or ring-full event is allowed */ + if (get_ucall(vm, VCPU_ID, NULL) == UCALL_SYNC) { + /* We should allow this to continue */ + ; + } else if (run->exit_reason == KVM_EXIT_DIRTY_RING_FULL || + (ret == -1 && err == EINTR)) { + /* Update the flag first before pause */ + WRITE_ONCE(dirty_ring_vcpu_ring_full, + run->exit_reason == KVM_EXIT_DIRTY_RING_FULL); + sem_post(&dirty_ring_vcpu_stop); + pr_info("vcpu stops because %s...\n", + dirty_ring_vcpu_ring_full ? + "dirty ring is full" : "vcpu is kicked out"); + sem_wait_until(&dirty_ring_vcpu_cont); + pr_info("vcpu continues now.\n"); + } else { + TEST_ASSERT(false, "Invalid guest sync status: " + "exit_reason=%s\n", + exit_reason_str(run->exit_reason)); + } +} + +static void dirty_ring_before_vcpu_join(void) +{ + /* Kick another round of vcpu just to make sure it will quit */ + sem_post(&dirty_ring_vcpu_cont); +} + struct log_mode { const char *name; /* Return true if this mode is supported, otherwise false */ @@ -187,16 +390,29 @@ struct log_mode { /* Hook to collect the dirty pages into the bitmap provided */ void (*collect_dirty_pages) (struct kvm_vm *vm, int slot, void *bitmap, uint32_t num_pages); + /* Hook to call when after each vcpu run */ + void (*after_vcpu_run)(struct kvm_vm *vm, int ret, int err); + void (*before_vcpu_join) (void); } log_modes[LOG_MODE_NUM] = { { .name = "dirty-log", .collect_dirty_pages = dirty_log_collect_dirty_pages, + .after_vcpu_run = default_after_vcpu_run, }, { .name = "clear-log", .supported = clear_log_supported, .create_vm_done = clear_log_create_vm_done, .collect_dirty_pages = clear_log_collect_dirty_pages, + .after_vcpu_run = default_after_vcpu_run, + }, + { + .name = "dirty-ring", + .supported = dirty_ring_supported, + .create_vm_done = dirty_ring_create_vm_done, + .collect_dirty_pages = dirty_ring_collect_dirty_pages, + .before_vcpu_join = dirty_ring_before_vcpu_join, + .after_vcpu_run = dirty_ring_after_vcpu_run, }, }; @@ -247,6 +463,22 @@ static void log_mode_collect_dirty_pages(struct kvm_vm *vm, int slot, mode->collect_dirty_pages(vm, slot, bitmap, num_pages); } +static void log_mode_after_vcpu_run(struct kvm_vm *vm, int ret, int err) +{ + struct log_mode *mode = &log_modes[host_log_mode]; + + if (mode->after_vcpu_run) + mode->after_vcpu_run(vm, ret, err); +} + +static void log_mode_before_vcpu_join(void) +{ + struct log_mode *mode = &log_modes[host_log_mode]; + + if (mode->before_vcpu_join) + mode->before_vcpu_join(); +} + static void generate_random_array(uint64_t *guest_array, uint64_t size) { uint64_t i; @@ -257,29 +489,44 @@ static void generate_random_array(uint64_t *guest_array, uint64_t size) static void *vcpu_worker(void *data) { - int ret; + int ret, vcpu_fd; struct kvm_vm *vm = data; uint64_t *guest_array; uint64_t pages_count = 0; - struct kvm_run *run; + struct kvm_signal_mask *sigmask = alloca(offsetof(struct kvm_signal_mask, sigset) + + sizeof(sigset_t)); + sigset_t *sigset = (sigset_t *) &sigmask->sigset; + + vcpu_fd = vcpu_get_fd(vm, VCPU_ID); + + /* + * SIG_IPI is unblocked atomically while in KVM_RUN. It causes the + * ioctl to return with -EINTR, but it is still pending and we need + * to accept it with the sigwait. + */ + sigmask->len = 8; + pthread_sigmask(0, NULL, sigset); + vcpu_ioctl(vm, VCPU_ID, KVM_SET_SIGNAL_MASK, sigmask); + sigaddset(sigset, SIG_IPI); + pthread_sigmask(SIG_BLOCK, sigset, NULL); - run = vcpu_state(vm, VCPU_ID); + sigemptyset(sigset); + sigaddset(sigset, SIG_IPI); guest_array = addr_gva2hva(vm, (vm_vaddr_t)random_array); - generate_random_array(guest_array, TEST_PAGES_PER_LOOP); while (!READ_ONCE(host_quit)) { + /* Clear any existing kick signals */ + generate_random_array(guest_array, TEST_PAGES_PER_LOOP); + pages_count += TEST_PAGES_PER_LOOP; /* Let the guest dirty the random pages */ - ret = _vcpu_run(vm, VCPU_ID); - TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret); - if (get_ucall(vm, VCPU_ID, NULL) == UCALL_SYNC) { - pages_count += TEST_PAGES_PER_LOOP; - generate_random_array(guest_array, TEST_PAGES_PER_LOOP); - } else { - TEST_FAIL("Invalid guest sync status: " - "exit_reason=%s\n", - exit_reason_str(run->exit_reason)); + ret = ioctl(vcpu_fd, KVM_RUN, NULL); + if (ret == -1 && errno == EINTR) { + int sig = -1; + sigwait(sigset, &sig); + assert(sig == SIG_IPI); } + log_mode_after_vcpu_run(vm, ret, errno); } pr_info("Dirtied %"PRIu64" pages\n", pages_count); @@ -292,6 +539,7 @@ static void vm_dirty_log_verify(enum vm_guest_mode mode, unsigned long *bmap) uint64_t step = vm_num_host_pages(mode, 1); uint64_t page; uint64_t *value_ptr; + uint64_t min_iter = 0; for (page = 0; page < host_num_pages; page += step) { value_ptr = host_test_mem + page * host_page_size; @@ -306,14 +554,64 @@ static void vm_dirty_log_verify(enum vm_guest_mode mode, unsigned long *bmap) } if (test_and_clear_bit_le(page, bmap)) { + bool matched; + host_dirty_count++; + /* * If the bit is set, the value written onto * the corresponding page should be either the * previous iteration number or the current one. */ - TEST_ASSERT(*value_ptr == iteration || - *value_ptr == iteration - 1, + matched = (*value_ptr == iteration || + *value_ptr == iteration - 1); + + if (host_log_mode == LOG_MODE_DIRTY_RING && !matched) { + if (*value_ptr == iteration - 2 && min_iter <= iteration - 2) { + /* + * Short answer: this case is special + * only for dirty ring test where the + * page is the last page before a kvm + * dirty ring full in iteration N-2. + * + * Long answer: Assuming ring size R, + * one possible condition is: + * + * main thr vcpu thr + * -------- -------- + * iter=1 + * write 1 to page 0~(R-1) + * full, vmexit + * collect 0~(R-1) + * kick vcpu + * write 1 to (R-1)~(2R-2) + * full, vmexit + * iter=2 + * collect (R-1)~(2R-2) + * kick vcpu + * write 1 to (2R-2) + * (NOTE!!! "1" cached in cpu reg) + * write 2 to (2R-1)~(3R-3) + * full, vmexit + * iter=3 + * collect (2R-2)~(3R-3) + * (here if we read value on page + * "2R-2" is 1, while iter=3!!!) + * + * This however can only happen once per iteration. + */ + min_iter = iteration - 1; + continue; + } else if (page == dirty_ring_last_page) { + /* + * Please refer to comments in + * dirty_ring_last_page. + */ + continue; + } + } + + TEST_ASSERT(matched, "Set page %"PRIu64" value %"PRIu64 " incorrect (iteration=%"PRIu64")", page, *value_ptr, iteration); @@ -378,7 +676,6 @@ static struct kvm_vm *create_vm(enum vm_guest_mode mode, uint32_t vcpuid, static void run_test(enum vm_guest_mode mode, unsigned long iterations, unsigned long interval, uint64_t phys_offset) { - pthread_t vcpu_thread; struct kvm_vm *vm; unsigned long *bmap; @@ -443,9 +740,6 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations, /* Cache the HVA pointer of the region */ host_test_mem = addr_gpa2hva(vm, (vm_paddr_t)guest_test_phys_mem); -#ifdef __x86_64__ - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); -#endif ucall_init(vm, NULL); /* Export the shared variables to the guest */ @@ -476,6 +770,7 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations, /* Tell the vcpu thread to quit */ host_quit = true; + log_mode_before_vcpu_join(); pthread_join(vcpu_thread, NULL); pr_info("Total bits checked: dirty (%"PRIu64"), clear (%"PRIu64"), " @@ -506,6 +801,9 @@ static void help(char *name) printf("usage: %s [-h] [-i iterations] [-I interval] " "[-p offset] [-m mode]\n", name); puts(""); + printf(" -c: specify dirty ring size, in number of entries\n"); + printf(" (only useful for dirty-ring test; default: %"PRIu32")\n", + TEST_DIRTY_RING_COUNT); printf(" -i: specify iteration counts (default: %"PRIu64")\n", TEST_HOST_LOOP_N); printf(" -I: specify interval in ms (default: %"PRIu64" ms)\n", @@ -536,6 +834,9 @@ int main(int argc, char *argv[]) unsigned int mode; int opt, i, j; + sem_init(&dirty_ring_vcpu_stop, 0, 0); + sem_init(&dirty_ring_vcpu_cont, 0, 0); + #ifdef __x86_64__ guest_mode_init(VM_MODE_PXXV48_4K, true, true); #endif @@ -558,8 +859,11 @@ int main(int argc, char *argv[]) guest_mode_init(VM_MODE_P40V48_4K, true, true); #endif - while ((opt = getopt(argc, argv, "hi:I:p:m:M:")) != -1) { + while ((opt = getopt(argc, argv, "c:hi:I:p:m:M:")) != -1) { switch (opt) { + case 'c': + test_dirty_ring_count = strtol(optarg, NULL, 10); + break; case 'i': iterations = strtol(optarg, NULL, 10); break; diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index 7d29aa786959..dfa9d369e8fc 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -45,13 +45,28 @@ enum vm_guest_mode { }; #if defined(__aarch64__) -#define VM_MODE_DEFAULT VM_MODE_P40V48_4K + +#define VM_MODE_DEFAULT VM_MODE_P40V48_4K +#define MIN_PAGE_SHIFT 12U +#define ptes_per_page(page_size) ((page_size) / 8) + #elif defined(__x86_64__) -#define VM_MODE_DEFAULT VM_MODE_PXXV48_4K -#else -#define VM_MODE_DEFAULT VM_MODE_P52V48_4K + +#define VM_MODE_DEFAULT VM_MODE_PXXV48_4K +#define MIN_PAGE_SHIFT 12U +#define ptes_per_page(page_size) ((page_size) / 8) + +#elif defined(__s390x__) + +#define VM_MODE_DEFAULT VM_MODE_P52V48_4K +#define MIN_PAGE_SHIFT 12U +#define ptes_per_page(page_size) ((page_size) / 16) + #endif +#define MIN_PAGE_SIZE (1U << MIN_PAGE_SHIFT) +#define PTES_PER_MIN_PAGE ptes_per_page(MIN_PAGE_SIZE) + #define vm_guest_mode_string(m) vm_guest_mode_string[m] extern const char * const vm_guest_mode_string[]; @@ -74,6 +89,7 @@ void kvm_vm_release(struct kvm_vm *vmp); void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log); void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log, uint64_t first_page, uint32_t num_pages); +uint32_t kvm_vm_reset_dirty_ring(struct kvm_vm *vm); int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, const vm_vaddr_t gva, size_t len); @@ -114,6 +130,8 @@ void vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, unsigned long ioctl, int _vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, unsigned long ioctl, void *arg); void vm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg); +void kvm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg); +int _kvm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg); void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags); void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa); void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot); @@ -146,6 +164,7 @@ vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva); struct kvm_run *vcpu_state(struct kvm_vm *vm, uint32_t vcpuid); void vcpu_run(struct kvm_vm *vm, uint32_t vcpuid); int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid); +int vcpu_get_fd(struct kvm_vm *vm, uint32_t vcpuid); void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid); void vcpu_set_guest_debug(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_guest_debug *debug); @@ -199,6 +218,7 @@ void vcpu_nested_state_get(struct kvm_vm *vm, uint32_t vcpuid, int vcpu_nested_state_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_nested_state *state, bool ignore_error); #endif +void *vcpu_map_dirty_ring(struct kvm_vm *vm, uint32_t vcpuid); const char *exit_reason_str(unsigned int exit_reason); @@ -246,6 +266,16 @@ vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, void *guest_code); +/* Same as vm_create_default, but can be used for more than one vcpu */ +struct kvm_vm *vm_create_default_with_vcpus(uint32_t nr_vcpus, uint64_t extra_mem_pages, + uint32_t num_percpu_pages, void *guest_code, + uint32_t vcpuids[]); + +/* Like vm_create_default_with_vcpus, but accepts mode as a parameter */ +struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus, + uint64_t extra_mem_pages, uint32_t num_percpu_pages, + void *guest_code, uint32_t vcpuids[]); + /* * Adds a vCPU with reasonable defaults (e.g. a stack) * diff --git a/tools/testing/selftests/kvm/include/perf_test_util.h b/tools/testing/selftests/kvm/include/perf_test_util.h index 2618052057b1..239421e4f6b8 100644 --- a/tools/testing/selftests/kvm/include/perf_test_util.h +++ b/tools/testing/selftests/kvm/include/perf_test_util.h @@ -179,10 +179,6 @@ static void add_vcpus(struct kvm_vm *vm, int vcpus, uint64_t vcpu_memory_bytes) vm_vcpu_add_default(vm, vcpu_id, guest_code); -#ifdef __x86_64__ - vcpu_set_cpuid(vm, vcpu_id, kvm_get_supported_cpuid()); -#endif - vcpu_args->vcpu_id = vcpu_id; vcpu_args->gva = guest_test_virt_mem + (vcpu_id * vcpu_memory_bytes); diff --git a/tools/testing/selftests/kvm/include/s390x/diag318_test_handler.h b/tools/testing/selftests/kvm/include/s390x/diag318_test_handler.h new file mode 100644 index 000000000000..b0ed71302722 --- /dev/null +++ b/tools/testing/selftests/kvm/include/s390x/diag318_test_handler.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later + * + * Test handler for the s390x DIAGNOSE 0x0318 instruction. + * + * Copyright (C) 2020, IBM + */ + +#ifndef SELFTEST_KVM_DIAG318_TEST_HANDLER +#define SELFTEST_KVM_DIAG318_TEST_HANDLER + +uint64_t get_diag318_info(void); + +#endif diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 8e61340b3911..90cd5984751b 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -27,6 +27,7 @@ #define X86_CR4_OSFXSR (1ul << 9) #define X86_CR4_OSXMMEXCPT (1ul << 10) #define X86_CR4_UMIP (1ul << 11) +#define X86_CR4_LA57 (1ul << 12) #define X86_CR4_VMXE (1ul << 13) #define X86_CR4_SMXE (1ul << 14) #define X86_CR4_FSGSBASE (1ul << 16) @@ -36,6 +37,22 @@ #define X86_CR4_SMAP (1ul << 21) #define X86_CR4_PKE (1ul << 22) +/* CPUID.1.ECX */ +#define CPUID_VMX (1ul << 5) +#define CPUID_SMX (1ul << 6) +#define CPUID_PCID (1ul << 17) +#define CPUID_XSAVE (1ul << 26) + +/* CPUID.7.EBX */ +#define CPUID_FSGSBASE (1ul << 0) +#define CPUID_SMEP (1ul << 7) +#define CPUID_SMAP (1ul << 20) + +/* CPUID.7.ECX */ +#define CPUID_UMIP (1ul << 2) +#define CPUID_PKU (1ul << 3) +#define CPUID_LA57 (1ul << 16) + #define UNEXPECTED_VECTOR_PORT 0xfff0u /* General Registers in 64-Bit Mode */ diff --git a/tools/testing/selftests/kvm/include/x86_64/vmx.h b/tools/testing/selftests/kvm/include/x86_64/vmx.h index e78d7e26ba61..65eb1079a161 100644 --- a/tools/testing/selftests/kvm/include/x86_64/vmx.h +++ b/tools/testing/selftests/kvm/include/x86_64/vmx.h @@ -11,10 +11,6 @@ #include <stdint.h> #include "processor.h" -#define CPUID_VMX_BIT 5 - -#define CPUID_VMX (1 << 5) - /* * Definitions of Primary Processor-Based VM-Execution Controls. */ diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c index d6c32c328e9a..cee92d477dc0 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/processor.c +++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c @@ -5,8 +5,6 @@ * Copyright (C) 2018, Red Hat, Inc. */ -#define _GNU_SOURCE /* for program_invocation_name */ - #include <linux/compiler.h> #include "kvm_util.h" @@ -219,21 +217,6 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) } } -struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, - void *guest_code) -{ - uint64_t ptrs_per_4k_pte = 512; - uint64_t extra_pg_pages = (extra_mem_pages / ptrs_per_4k_pte) * 2; - struct kvm_vm *vm; - - vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR); - - kvm_vm_elf_load(vm, program_invocation_name, 0, 0); - vm_vcpu_add_default(vm, vcpuid, guest_code); - - return vm; -} - void aarch64_vcpu_setup(struct kvm_vm *vm, int vcpuid, struct kvm_vcpu_init *init) { struct kvm_vcpu_init default_init = { .target = -1, }; diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 126c6727a6b0..88ef7067f1e6 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -5,6 +5,7 @@ * Copyright (C) 2018, Google LLC. */ +#define _GNU_SOURCE /* for program_invocation_name */ #include "test_util.h" #include "kvm_util.h" #include "kvm_util_internal.h" @@ -114,6 +115,16 @@ int vcpu_enable_cap(struct kvm_vm *vm, uint32_t vcpu_id, return r; } +void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size) +{ + struct kvm_enable_cap cap = { 0 }; + + cap.cap = KVM_CAP_DIRTY_LOG_RING; + cap.args[0] = ring_size; + vm_enable_cap(vm, &cap); + vm->dirty_ring_size = ring_size; +} + static void vm_open(struct kvm_vm *vm, int perm) { vm->kvm_fd = open(KVM_DEV_PATH, perm); @@ -271,6 +282,63 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) return vm; } +struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus, + uint64_t extra_mem_pages, uint32_t num_percpu_pages, + void *guest_code, uint32_t vcpuids[]) +{ + /* The maximum page table size for a memory region will be when the + * smallest pages are used. Considering each page contains x page + * table descriptors, the total extra size for page tables (for extra + * N pages) will be: N/x+N/x^2+N/x^3+... which is definitely smaller + * than N/x*2. + */ + uint64_t vcpu_pages = (DEFAULT_STACK_PGS + num_percpu_pages) * nr_vcpus; + uint64_t extra_pg_pages = (extra_mem_pages + vcpu_pages) / PTES_PER_MIN_PAGE * 2; + uint64_t pages = DEFAULT_GUEST_PHY_PAGES + vcpu_pages + extra_pg_pages; + struct kvm_vm *vm; + int i; + + TEST_ASSERT(nr_vcpus <= kvm_check_cap(KVM_CAP_MAX_VCPUS), + "nr_vcpus = %d too large for host, max-vcpus = %d", + nr_vcpus, kvm_check_cap(KVM_CAP_MAX_VCPUS)); + + pages = vm_adjust_num_guest_pages(mode, pages); + vm = vm_create(mode, pages, O_RDWR); + + kvm_vm_elf_load(vm, program_invocation_name, 0, 0); + +#ifdef __x86_64__ + vm_create_irqchip(vm); +#endif + + for (i = 0; i < nr_vcpus; ++i) { + uint32_t vcpuid = vcpuids ? vcpuids[i] : i; + + vm_vcpu_add_default(vm, vcpuid, guest_code); + +#ifdef __x86_64__ + vcpu_set_cpuid(vm, vcpuid, kvm_get_supported_cpuid()); +#endif + } + + return vm; +} + +struct kvm_vm *vm_create_default_with_vcpus(uint32_t nr_vcpus, uint64_t extra_mem_pages, + uint32_t num_percpu_pages, void *guest_code, + uint32_t vcpuids[]) +{ + return vm_create_with_vcpus(VM_MODE_DEFAULT, nr_vcpus, extra_mem_pages, + num_percpu_pages, guest_code, vcpuids); +} + +struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, + void *guest_code) +{ + return vm_create_default_with_vcpus(1, extra_mem_pages, 0, guest_code, + (uint32_t []){ vcpuid }); +} + /* * VM Restart * @@ -328,6 +396,11 @@ void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log, __func__, strerror(-ret)); } +uint32_t kvm_vm_reset_dirty_ring(struct kvm_vm *vm) +{ + return ioctl(vm->fd, KVM_RESET_DIRTY_RINGS); +} + /* * Userspace Memory Region Find * @@ -432,10 +505,17 @@ struct vcpu *vcpu_find(struct kvm_vm *vm, uint32_t vcpuid) * * Removes a vCPU from a VM and frees its resources. */ -static void vm_vcpu_rm(struct vcpu *vcpu) +static void vm_vcpu_rm(struct kvm_vm *vm, struct vcpu *vcpu) { int ret; + if (vcpu->dirty_gfns) { + ret = munmap(vcpu->dirty_gfns, vm->dirty_ring_size); + TEST_ASSERT(ret == 0, "munmap of VCPU dirty ring failed, " + "rc: %i errno: %i", ret, errno); + vcpu->dirty_gfns = NULL; + } + ret = munmap(vcpu->state, sizeof(*vcpu->state)); TEST_ASSERT(ret == 0, "munmap of VCPU fd failed, rc: %i " "errno: %i", ret, errno); @@ -453,7 +533,7 @@ void kvm_vm_release(struct kvm_vm *vmp) int ret; list_for_each_entry_safe(vcpu, tmp, &vmp->vcpus, list) - vm_vcpu_rm(vcpu); + vm_vcpu_rm(vmp, vcpu); ret = close(vmp->fd); TEST_ASSERT(ret == 0, "Close of vm fd failed,\n" @@ -1233,6 +1313,15 @@ int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid) return rc; } +int vcpu_get_fd(struct kvm_vm *vm, uint32_t vcpuid) +{ + struct vcpu *vcpu = vcpu_find(vm, vcpuid); + + TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); + + return vcpu->fd; +} + void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid) { struct vcpu *vcpu = vcpu_find(vm, vcpuid); @@ -1561,6 +1650,42 @@ int _vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, return ret; } +void *vcpu_map_dirty_ring(struct kvm_vm *vm, uint32_t vcpuid) +{ + struct vcpu *vcpu; + uint32_t size = vm->dirty_ring_size; + + TEST_ASSERT(size > 0, "Should enable dirty ring first"); + + vcpu = vcpu_find(vm, vcpuid); + + TEST_ASSERT(vcpu, "Cannot find vcpu %u", vcpuid); + + if (!vcpu->dirty_gfns) { + void *addr; + + addr = mmap(NULL, size, PROT_READ, + MAP_PRIVATE, vcpu->fd, + vm->page_size * KVM_DIRTY_LOG_PAGE_OFFSET); + TEST_ASSERT(addr == MAP_FAILED, "Dirty ring mapped private"); + + addr = mmap(NULL, size, PROT_READ | PROT_EXEC, + MAP_PRIVATE, vcpu->fd, + vm->page_size * KVM_DIRTY_LOG_PAGE_OFFSET); + TEST_ASSERT(addr == MAP_FAILED, "Dirty ring mapped exec"); + + addr = mmap(NULL, size, PROT_READ | PROT_WRITE, + MAP_SHARED, vcpu->fd, + vm->page_size * KVM_DIRTY_LOG_PAGE_OFFSET); + TEST_ASSERT(addr != MAP_FAILED, "Dirty ring map failed"); + + vcpu->dirty_gfns = addr; + vcpu->dirty_gfns_count = size / sizeof(struct kvm_dirty_gfn); + } + + return vcpu->dirty_gfns; +} + /* * VM Ioctl * @@ -1583,6 +1708,32 @@ void vm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg) } /* + * KVM system ioctl + * + * Input Args: + * vm - Virtual Machine + * cmd - Ioctl number + * arg - Argument to pass to the ioctl + * + * Return: None + * + * Issues an arbitrary ioctl on a KVM fd. + */ +void kvm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg) +{ + int ret; + + ret = ioctl(vm->kvm_fd, cmd, arg); + TEST_ASSERT(ret == 0, "KVM ioctl %lu failed, rc: %i errno: %i (%s)", + cmd, ret, errno, strerror(errno)); +} + +int _kvm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg) +{ + return ioctl(vm->kvm_fd, cmd, arg); +} + +/* * VM Dump * * Input Args: @@ -1654,6 +1805,9 @@ static struct exit_reason { {KVM_EXIT_INTERNAL_ERROR, "INTERNAL_ERROR"}, {KVM_EXIT_OSI, "OSI"}, {KVM_EXIT_PAPR_HCALL, "PAPR_HCALL"}, + {KVM_EXIT_DIRTY_RING_FULL, "DIRTY_RING_FULL"}, + {KVM_EXIT_X86_RDMSR, "RDMSR"}, + {KVM_EXIT_X86_WRMSR, "WRMSR"}, #ifdef KVM_EXIT_MEMORY_NOT_PRESENT {KVM_EXIT_MEMORY_NOT_PRESENT, "MEMORY_NOT_PRESENT"}, #endif diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h index f07d383d03a1..34465dc562d8 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h +++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h @@ -28,6 +28,9 @@ struct vcpu { uint32_t id; int fd; struct kvm_run *state; + struct kvm_dirty_gfn *dirty_gfns; + uint32_t fetch_index; + uint32_t dirty_gfns_count; }; struct kvm_vm { @@ -52,6 +55,7 @@ struct kvm_vm { vm_vaddr_t tss; vm_vaddr_t idt; vm_vaddr_t handlers; + uint32_t dirty_ring_size; }; struct vcpu *vcpu_find(struct kvm_vm *vm, uint32_t vcpuid); diff --git a/tools/testing/selftests/kvm/lib/s390x/diag318_test_handler.c b/tools/testing/selftests/kvm/lib/s390x/diag318_test_handler.c new file mode 100644 index 000000000000..86b9e611ad87 --- /dev/null +++ b/tools/testing/selftests/kvm/lib/s390x/diag318_test_handler.c @@ -0,0 +1,82 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Test handler for the s390x DIAGNOSE 0x0318 instruction. + * + * Copyright (C) 2020, IBM + */ + +#include "test_util.h" +#include "kvm_util.h" + +#define VCPU_ID 6 + +#define ICPT_INSTRUCTION 0x04 +#define IPA0_DIAG 0x8300 + +static void guest_code(void) +{ + uint64_t diag318_info = 0x12345678; + + asm volatile ("diag %0,0,0x318\n" : : "d" (diag318_info)); +} + +/* + * The DIAGNOSE 0x0318 instruction call must be handled via userspace. As such, + * we create an ad-hoc VM here to handle the instruction then extract the + * necessary data. It is up to the caller to decide what to do with that data. + */ +static uint64_t diag318_handler(void) +{ + struct kvm_vm *vm; + struct kvm_run *run; + uint64_t reg; + uint64_t diag318_info; + + vm = vm_create_default(VCPU_ID, 0, guest_code); + vcpu_run(vm, VCPU_ID); + run = vcpu_state(vm, VCPU_ID); + + TEST_ASSERT(run->exit_reason == KVM_EXIT_S390_SIEIC, + "DIAGNOSE 0x0318 instruction was not intercepted"); + TEST_ASSERT(run->s390_sieic.icptcode == ICPT_INSTRUCTION, + "Unexpected intercept code: 0x%x", run->s390_sieic.icptcode); + TEST_ASSERT((run->s390_sieic.ipa & 0xff00) == IPA0_DIAG, + "Unexpected IPA0 code: 0x%x", (run->s390_sieic.ipa & 0xff00)); + + reg = (run->s390_sieic.ipa & 0x00f0) >> 4; + diag318_info = run->s.regs.gprs[reg]; + + TEST_ASSERT(diag318_info != 0, "DIAGNOSE 0x0318 info not set"); + + kvm_vm_free(vm); + + return diag318_info; +} + +uint64_t get_diag318_info(void) +{ + static uint64_t diag318_info; + static bool printed_skip; + + /* + * If KVM does not support diag318, then return 0 to + * ensure tests do not break. + */ + if (!kvm_check_cap(KVM_CAP_S390_DIAG318)) { + if (!printed_skip) { + fprintf(stdout, "KVM_CAP_S390_DIAG318 not supported. " + "Skipping diag318 test.\n"); + printed_skip = true; + } + return 0; + } + + /* + * If a test has previously requested the diag318 info, + * then don't bother spinning up a temporary VM again. + */ + if (!diag318_info) + diag318_info = diag318_handler(); + + return diag318_info; +} diff --git a/tools/testing/selftests/kvm/lib/s390x/processor.c b/tools/testing/selftests/kvm/lib/s390x/processor.c index 7349bb2e1a24..0152f356c099 100644 --- a/tools/testing/selftests/kvm/lib/s390x/processor.c +++ b/tools/testing/selftests/kvm/lib/s390x/processor.c @@ -5,8 +5,6 @@ * Copyright (C) 2019, Red Hat, Inc. */ -#define _GNU_SOURCE /* for program_invocation_name */ - #include "processor.h" #include "kvm_util.h" #include "../kvm_util_internal.h" @@ -160,26 +158,6 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) virt_dump_region(stream, vm, indent, vm->pgd); } -struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, - void *guest_code) -{ - /* - * The additional amount of pages required for the page tables is: - * 1 * n / 256 + 4 * (n / 256) / 2048 + 4 * (n / 256) / 2048^2 + ... - * which is definitely smaller than (n / 256) * 2. - */ - uint64_t extra_pg_pages = extra_mem_pages / 256 * 2; - struct kvm_vm *vm; - - vm = vm_create(VM_MODE_DEFAULT, - DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR); - - kvm_vm_elf_load(vm, program_invocation_name, 0, 0); - vm_vcpu_add_default(vm, vcpuid, guest_code); - - return vm; -} - void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code) { size_t stack_size = DEFAULT_STACK_PGS * getpagesize(); diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index d10c5c05bdf0..95e1a757c629 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -5,8 +5,6 @@ * Copyright (C) 2018, Google LLC. */ -#define _GNU_SOURCE /* for program_invocation_name */ - #include "test_util.h" #include "kvm_util.h" #include "../kvm_util_internal.h" @@ -731,36 +729,6 @@ void vcpu_set_cpuid(struct kvm_vm *vm, } -struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, - void *guest_code) -{ - struct kvm_vm *vm; - /* - * For x86 the maximum page table size for a memory region - * will be when only 4K pages are used. In that case the - * total extra size for page tables (for extra N pages) will - * be: N/512+N/512^2+N/512^3+... which is definitely smaller - * than N/512*2. - */ - uint64_t extra_pg_pages = extra_mem_pages / 512 * 2; - - /* Create VM */ - vm = vm_create(VM_MODE_DEFAULT, - DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, - O_RDWR); - - /* Setup guest code */ - kvm_vm_elf_load(vm, program_invocation_name, 0, 0); - - /* Setup IRQ Chip */ - vm_create_irqchip(vm); - - /* Add the first vCPU. */ - vm_vcpu_add_default(vm, vcpuid, guest_code); - - return vm; -} - /* * VCPU Get MSR * diff --git a/tools/testing/selftests/kvm/s390x/sync_regs_test.c b/tools/testing/selftests/kvm/s390x/sync_regs_test.c index 5731ccf34917..caf7b8859a94 100644 --- a/tools/testing/selftests/kvm/s390x/sync_regs_test.c +++ b/tools/testing/selftests/kvm/s390x/sync_regs_test.c @@ -20,6 +20,7 @@ #include "test_util.h" #include "kvm_util.h" +#include "diag318_test_handler.h" #define VCPU_ID 5 @@ -70,7 +71,7 @@ static void compare_sregs(struct kvm_sregs *left, struct kvm_sync_regs *right) #undef REG_COMPARE -#define TEST_SYNC_FIELDS (KVM_SYNC_GPRS|KVM_SYNC_ACRS|KVM_SYNC_CRS) +#define TEST_SYNC_FIELDS (KVM_SYNC_GPRS|KVM_SYNC_ACRS|KVM_SYNC_CRS|KVM_SYNC_DIAG318) #define INVALID_SYNC_FIELD 0x80000000 int main(int argc, char *argv[]) @@ -152,6 +153,12 @@ int main(int argc, char *argv[]) run->kvm_valid_regs = TEST_SYNC_FIELDS; run->kvm_dirty_regs = KVM_SYNC_GPRS | KVM_SYNC_ACRS; + + if (get_diag318_info() > 0) { + run->s.regs.diag318 = get_diag318_info(); + run->kvm_dirty_regs |= KVM_SYNC_DIAG318; + } + rv = _vcpu_run(vm, VCPU_ID); TEST_ASSERT(rv == 0, "vcpu_run failed: %d\n", rv); TEST_ASSERT(run->exit_reason == KVM_EXIT_S390_SIEIC, @@ -164,6 +171,9 @@ int main(int argc, char *argv[]) TEST_ASSERT(run->s.regs.acrs[0] == 1 << 11, "acr0 sync regs value incorrect 0x%x.", run->s.regs.acrs[0]); + TEST_ASSERT(run->s.regs.diag318 == get_diag318_info(), + "diag318 sync regs value incorrect 0x%llx.", + run->s.regs.diag318); vcpu_regs_get(vm, VCPU_ID, ®s); compare_regs(®s, &run->s.regs); @@ -177,6 +187,7 @@ int main(int argc, char *argv[]) run->kvm_valid_regs = TEST_SYNC_FIELDS; run->kvm_dirty_regs = 0; run->s.regs.gprs[11] = 0xDEADBEEF; + run->s.regs.diag318 = 0x4B1D; rv = _vcpu_run(vm, VCPU_ID); TEST_ASSERT(rv == 0, "vcpu_run failed: %d\n", rv); TEST_ASSERT(run->exit_reason == KVM_EXIT_S390_SIEIC, @@ -186,6 +197,9 @@ int main(int argc, char *argv[]) TEST_ASSERT(run->s.regs.gprs[11] != 0xDEADBEEF, "r11 sync regs value incorrect 0x%llx.", run->s.regs.gprs[11]); + TEST_ASSERT(run->s.regs.diag318 != 0x4B1D, + "diag318 sync regs value incorrect 0x%llx.", + run->s.regs.diag318); kvm_vm_free(vm); diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c index 6f441dd9f33c..f127ed31dba7 100644 --- a/tools/testing/selftests/kvm/set_memory_region_test.c +++ b/tools/testing/selftests/kvm/set_memory_region_test.c @@ -121,8 +121,6 @@ static struct kvm_vm *spawn_vm(pthread_t *vcpu_thread, void *guest_code) vm = vm_create_default(VCPU_ID, 0, guest_code); - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); - vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS_THP, MEM_REGION_GPA, MEM_REGION_SLOT, MEM_REGION_SIZE / getpagesize(), 0); diff --git a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c index 140e91901582..f40fd097cb35 100644 --- a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c +++ b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c @@ -81,7 +81,6 @@ int main(int argc, char *argv[]) /* Create VM */ vm = vm_create_default(VCPU_ID, 0, guest_code); - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); run = vcpu_state(vm, VCPU_ID); while (1) { diff --git a/tools/testing/selftests/kvm/x86_64/debug_regs.c b/tools/testing/selftests/kvm/x86_64/debug_regs.c index 2fc6b3af81a1..6097a8283377 100644 --- a/tools/testing/selftests/kvm/x86_64/debug_regs.c +++ b/tools/testing/selftests/kvm/x86_64/debug_regs.c @@ -85,7 +85,6 @@ int main(void) } vm = vm_create_default(VCPU_ID, 0, guest_code); - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); run = vcpu_state(vm, VCPU_ID); /* Test software BPs - int3 */ diff --git a/tools/testing/selftests/kvm/x86_64/evmcs_test.c b/tools/testing/selftests/kvm/x86_64/evmcs_test.c index 757928199f19..37b8a78f6b74 100644 --- a/tools/testing/selftests/kvm/x86_64/evmcs_test.c +++ b/tools/testing/selftests/kvm/x86_64/evmcs_test.c @@ -92,8 +92,6 @@ int main(int argc, char *argv[]) /* Create VM */ vm = vm_create_default(VCPU_ID, 0, guest_code); - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); - if (!nested_vmx_supported() || !kvm_check_cap(KVM_CAP_NESTED_STATE) || !kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)) { diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c index 745b708c2d3b..88a595b7fbdd 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c @@ -46,19 +46,19 @@ static bool smt_possible(void) } static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries, - bool evmcs_enabled) + bool evmcs_expected) { int i; int nent = 9; u32 test_val; - if (evmcs_enabled) + if (evmcs_expected) nent += 1; /* 0x4000000A */ TEST_ASSERT(hv_cpuid_entries->nent == nent, "KVM_GET_SUPPORTED_HV_CPUID should return %d entries" " with evmcs=%d (returned %d)", - nent, evmcs_enabled, hv_cpuid_entries->nent); + nent, evmcs_expected, hv_cpuid_entries->nent); for (i = 0; i < hv_cpuid_entries->nent; i++) { struct kvm_cpuid_entry2 *entry = &hv_cpuid_entries->entries[i]; @@ -68,7 +68,7 @@ static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries, "function %x is our of supported range", entry->function); - TEST_ASSERT(evmcs_enabled || (entry->function != 0x4000000A), + TEST_ASSERT(evmcs_expected || (entry->function != 0x4000000A), "0x4000000A leaf should not be reported"); TEST_ASSERT(entry->index == 0, @@ -87,7 +87,7 @@ static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries, TEST_ASSERT(entry->eax == test_val, "Wrong max leaf report in 0x40000000.EAX: %x" " (evmcs=%d)", - entry->eax, evmcs_enabled + entry->eax, evmcs_expected ); break; case 0x40000004: @@ -110,20 +110,23 @@ static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries, } -void test_hv_cpuid_e2big(struct kvm_vm *vm) +void test_hv_cpuid_e2big(struct kvm_vm *vm, bool system) { static struct kvm_cpuid2 cpuid = {.nent = 0}; int ret; - ret = _vcpu_ioctl(vm, VCPU_ID, KVM_GET_SUPPORTED_HV_CPUID, &cpuid); + if (!system) + ret = _vcpu_ioctl(vm, VCPU_ID, KVM_GET_SUPPORTED_HV_CPUID, &cpuid); + else + ret = _kvm_ioctl(vm, KVM_GET_SUPPORTED_HV_CPUID, &cpuid); TEST_ASSERT(ret == -1 && errno == E2BIG, - "KVM_GET_SUPPORTED_HV_CPUID didn't fail with -E2BIG when" - " it should have: %d %d", ret, errno); + "%s KVM_GET_SUPPORTED_HV_CPUID didn't fail with -E2BIG when" + " it should have: %d %d", system ? "KVM" : "vCPU", ret, errno); } -struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(struct kvm_vm *vm) +struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(struct kvm_vm *vm, bool system) { int nent = 20; /* should be enough */ static struct kvm_cpuid2 *cpuid; @@ -137,7 +140,10 @@ struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(struct kvm_vm *vm) cpuid->nent = nent; - vcpu_ioctl(vm, VCPU_ID, KVM_GET_SUPPORTED_HV_CPUID, cpuid); + if (!system) + vcpu_ioctl(vm, VCPU_ID, KVM_GET_SUPPORTED_HV_CPUID, cpuid); + else + kvm_ioctl(vm, KVM_GET_SUPPORTED_HV_CPUID, cpuid); return cpuid; } @@ -146,45 +152,50 @@ struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(struct kvm_vm *vm) int main(int argc, char *argv[]) { struct kvm_vm *vm; - int rv, stage; struct kvm_cpuid2 *hv_cpuid_entries; - bool evmcs_enabled; /* Tell stdout not to buffer its content */ setbuf(stdout, NULL); - rv = kvm_check_cap(KVM_CAP_HYPERV_CPUID); - if (!rv) { + if (!kvm_check_cap(KVM_CAP_HYPERV_CPUID)) { print_skip("KVM_CAP_HYPERV_CPUID not supported"); exit(KSFT_SKIP); } - for (stage = 0; stage < 3; stage++) { - evmcs_enabled = false; + vm = vm_create_default(VCPU_ID, 0, guest_code); - vm = vm_create_default(VCPU_ID, 0, guest_code); - switch (stage) { - case 0: - test_hv_cpuid_e2big(vm); - continue; - case 1: - break; - case 2: - if (!nested_vmx_supported() || - !kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)) { - print_skip("Enlightened VMCS is unsupported"); - continue; - } - vcpu_enable_evmcs(vm, VCPU_ID); - evmcs_enabled = true; - break; - } + /* Test vCPU ioctl version */ + test_hv_cpuid_e2big(vm, false); + + hv_cpuid_entries = kvm_get_supported_hv_cpuid(vm, false); + test_hv_cpuid(hv_cpuid_entries, false); + free(hv_cpuid_entries); - hv_cpuid_entries = kvm_get_supported_hv_cpuid(vm); - test_hv_cpuid(hv_cpuid_entries, evmcs_enabled); - free(hv_cpuid_entries); - kvm_vm_free(vm); + if (!nested_vmx_supported() || + !kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)) { + print_skip("Enlightened VMCS is unsupported"); + goto do_sys; } + vcpu_enable_evmcs(vm, VCPU_ID); + hv_cpuid_entries = kvm_get_supported_hv_cpuid(vm, false); + test_hv_cpuid(hv_cpuid_entries, true); + free(hv_cpuid_entries); + +do_sys: + /* Test system ioctl version */ + if (!kvm_check_cap(KVM_CAP_SYS_HYPERV_CPUID)) { + print_skip("KVM_CAP_SYS_HYPERV_CPUID not supported"); + goto out; + } + + test_hv_cpuid_e2big(vm, true); + + hv_cpuid_entries = kvm_get_supported_hv_cpuid(vm, true); + test_hv_cpuid(hv_cpuid_entries, nested_vmx_supported()); + free(hv_cpuid_entries); + +out: + kvm_vm_free(vm); return 0; } diff --git a/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c index b10a27485bad..732b244d6956 100644 --- a/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c +++ b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c @@ -211,8 +211,8 @@ int main(void) struct kvm_vm *vm; if (!kvm_check_cap(KVM_CAP_ENFORCE_PV_FEATURE_CPUID)) { - pr_info("will skip kvm paravirt restriction tests.\n"); - return 0; + print_skip("KVM_CAP_ENFORCE_PV_FEATURE_CPUID not supported"); + exit(KSFT_SKIP); } vm = vm_create_default(VCPU_ID, 0, guest_main); diff --git a/tools/testing/selftests/kvm/x86_64/set_sregs_test.c b/tools/testing/selftests/kvm/x86_64/set_sregs_test.c index 9f7656184f31..318be0bf77ab 100644 --- a/tools/testing/selftests/kvm/x86_64/set_sregs_test.c +++ b/tools/testing/selftests/kvm/x86_64/set_sregs_test.c @@ -24,16 +24,106 @@ #define VCPU_ID 5 +static void test_cr4_feature_bit(struct kvm_vm *vm, struct kvm_sregs *orig, + uint64_t feature_bit) +{ + struct kvm_sregs sregs; + int rc; + + /* Skip the sub-test, the feature is supported. */ + if (orig->cr4 & feature_bit) + return; + + memcpy(&sregs, orig, sizeof(sregs)); + sregs.cr4 |= feature_bit; + + rc = _vcpu_sregs_set(vm, VCPU_ID, &sregs); + TEST_ASSERT(rc, "KVM allowed unsupported CR4 bit (0x%lx)", feature_bit); + + /* Sanity check that KVM didn't change anything. */ + vcpu_sregs_get(vm, VCPU_ID, &sregs); + TEST_ASSERT(!memcmp(&sregs, orig, sizeof(sregs)), "KVM modified sregs"); +} + +static uint64_t calc_cr4_feature_bits(struct kvm_vm *vm) +{ + struct kvm_cpuid_entry2 *cpuid_1, *cpuid_7; + uint64_t cr4; + + cpuid_1 = kvm_get_supported_cpuid_entry(1); + cpuid_7 = kvm_get_supported_cpuid_entry(7); + + cr4 = X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE | + X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE | X86_CR4_PGE | + X86_CR4_PCE | X86_CR4_OSFXSR | X86_CR4_OSXMMEXCPT; + if (cpuid_7->ecx & CPUID_UMIP) + cr4 |= X86_CR4_UMIP; + if (cpuid_7->ecx & CPUID_LA57) + cr4 |= X86_CR4_LA57; + if (cpuid_1->ecx & CPUID_VMX) + cr4 |= X86_CR4_VMXE; + if (cpuid_1->ecx & CPUID_SMX) + cr4 |= X86_CR4_SMXE; + if (cpuid_7->ebx & CPUID_FSGSBASE) + cr4 |= X86_CR4_FSGSBASE; + if (cpuid_1->ecx & CPUID_PCID) + cr4 |= X86_CR4_PCIDE; + if (cpuid_1->ecx & CPUID_XSAVE) + cr4 |= X86_CR4_OSXSAVE; + if (cpuid_7->ebx & CPUID_SMEP) + cr4 |= X86_CR4_SMEP; + if (cpuid_7->ebx & CPUID_SMAP) + cr4 |= X86_CR4_SMAP; + if (cpuid_7->ecx & CPUID_PKU) + cr4 |= X86_CR4_PKE; + + return cr4; +} + int main(int argc, char *argv[]) { struct kvm_sregs sregs; struct kvm_vm *vm; + uint64_t cr4; int rc; /* Tell stdout not to buffer its content */ setbuf(stdout, NULL); - /* Create VM */ + /* + * Create a dummy VM, specifically to avoid doing KVM_SET_CPUID2, and + * use it to verify all supported CR4 bits can be set prior to defining + * the vCPU model, i.e. without doing KVM_SET_CPUID2. + */ + vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR); + vm_vcpu_add(vm, VCPU_ID); + + vcpu_sregs_get(vm, VCPU_ID, &sregs); + + sregs.cr4 |= calc_cr4_feature_bits(vm); + cr4 = sregs.cr4; + + rc = _vcpu_sregs_set(vm, VCPU_ID, &sregs); + TEST_ASSERT(!rc, "Failed to set supported CR4 bits (0x%lx)", cr4); + + vcpu_sregs_get(vm, VCPU_ID, &sregs); + TEST_ASSERT(sregs.cr4 == cr4, "sregs.CR4 (0x%llx) != CR4 (0x%lx)", + sregs.cr4, cr4); + + /* Verify all unsupported features are rejected by KVM. */ + test_cr4_feature_bit(vm, &sregs, X86_CR4_UMIP); + test_cr4_feature_bit(vm, &sregs, X86_CR4_LA57); + test_cr4_feature_bit(vm, &sregs, X86_CR4_VMXE); + test_cr4_feature_bit(vm, &sregs, X86_CR4_SMXE); + test_cr4_feature_bit(vm, &sregs, X86_CR4_FSGSBASE); + test_cr4_feature_bit(vm, &sregs, X86_CR4_PCIDE); + test_cr4_feature_bit(vm, &sregs, X86_CR4_OSXSAVE); + test_cr4_feature_bit(vm, &sregs, X86_CR4_SMEP); + test_cr4_feature_bit(vm, &sregs, X86_CR4_SMAP); + test_cr4_feature_bit(vm, &sregs, X86_CR4_PKE); + kvm_vm_free(vm); + + /* Create a "real" VM and verify APIC_BASE can be set. */ vm = vm_create_default(VCPU_ID, 0, NULL); vcpu_sregs_get(vm, VCPU_ID, &sregs); diff --git a/tools/testing/selftests/kvm/x86_64/smm_test.c b/tools/testing/selftests/kvm/x86_64/smm_test.c index ae39a220609f..613c42c5a9b8 100644 --- a/tools/testing/selftests/kvm/x86_64/smm_test.c +++ b/tools/testing/selftests/kvm/x86_64/smm_test.c @@ -102,8 +102,6 @@ int main(int argc, char *argv[]) /* Create VM */ vm = vm_create_default(VCPU_ID, 0, guest_code); - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); - run = vcpu_state(vm, VCPU_ID); vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, SMRAM_GPA, diff --git a/tools/testing/selftests/kvm/x86_64/state_test.c b/tools/testing/selftests/kvm/x86_64/state_test.c index f6c8b9042f8a..32854c1462ad 100644 --- a/tools/testing/selftests/kvm/x86_64/state_test.c +++ b/tools/testing/selftests/kvm/x86_64/state_test.c @@ -165,7 +165,6 @@ int main(int argc, char *argv[]) /* Create VM */ vm = vm_create_default(VCPU_ID, 0, guest_code); - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); run = vcpu_state(vm, VCPU_ID); vcpu_regs_get(vm, VCPU_ID, ®s1); diff --git a/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c b/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c index 0e1adb4e3199..be2ca157485b 100644 --- a/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c +++ b/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c @@ -44,7 +44,6 @@ int main(int argc, char *argv[]) nested_svm_check_supported(); vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code); - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); vcpu_alloc_svm(vm, &svm_gva); vcpu_args_set(vm, VCPU_ID, 1, svm_gva); diff --git a/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c b/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c index f8e761149daa..e357d8e222d4 100644 --- a/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c +++ b/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c @@ -107,7 +107,6 @@ int main(void) uint64_t val; vm = vm_create_default(VCPU_ID, 0, guest_code); - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); val = 0; ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), val); diff --git a/tools/testing/selftests/kvm/x86_64/user_msr_test.c b/tools/testing/selftests/kvm/x86_64/user_msr_test.c deleted file mode 100644 index cbe1b08890ff..000000000000 --- a/tools/testing/selftests/kvm/x86_64/user_msr_test.c +++ /dev/null @@ -1,248 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * tests for KVM_CAP_X86_USER_SPACE_MSR and KVM_X86_SET_MSR_FILTER - * - * Copyright (C) 2020, Amazon Inc. - * - * This is a functional test to verify that we can deflect MSR events - * into user space. - */ -#define _GNU_SOURCE /* for program_invocation_short_name */ -#include <fcntl.h> -#include <stdio.h> -#include <stdlib.h> -#include <string.h> -#include <sys/ioctl.h> - -#include "test_util.h" - -#include "kvm_util.h" -#include "processor.h" - -#define VCPU_ID 5 - -static u32 msr_reads, msr_writes; - -static u8 bitmap_00000000[KVM_MSR_FILTER_MAX_BITMAP_SIZE]; -static u8 bitmap_00000000_write[KVM_MSR_FILTER_MAX_BITMAP_SIZE]; -static u8 bitmap_40000000[KVM_MSR_FILTER_MAX_BITMAP_SIZE]; -static u8 bitmap_c0000000[KVM_MSR_FILTER_MAX_BITMAP_SIZE]; -static u8 bitmap_c0000000_read[KVM_MSR_FILTER_MAX_BITMAP_SIZE]; -static u8 bitmap_deadbeef[1] = { 0x1 }; - -static void deny_msr(uint8_t *bitmap, u32 msr) -{ - u32 idx = msr & (KVM_MSR_FILTER_MAX_BITMAP_SIZE - 1); - - bitmap[idx / 8] &= ~(1 << (idx % 8)); -} - -static void prepare_bitmaps(void) -{ - memset(bitmap_00000000, 0xff, sizeof(bitmap_00000000)); - memset(bitmap_00000000_write, 0xff, sizeof(bitmap_00000000_write)); - memset(bitmap_40000000, 0xff, sizeof(bitmap_40000000)); - memset(bitmap_c0000000, 0xff, sizeof(bitmap_c0000000)); - memset(bitmap_c0000000_read, 0xff, sizeof(bitmap_c0000000_read)); - - deny_msr(bitmap_00000000_write, MSR_IA32_POWER_CTL); - deny_msr(bitmap_c0000000_read, MSR_SYSCALL_MASK); - deny_msr(bitmap_c0000000_read, MSR_GS_BASE); -} - -struct kvm_msr_filter filter = { - .flags = KVM_MSR_FILTER_DEFAULT_DENY, - .ranges = { - { - .flags = KVM_MSR_FILTER_READ, - .base = 0x00000000, - .nmsrs = KVM_MSR_FILTER_MAX_BITMAP_SIZE * BITS_PER_BYTE, - .bitmap = bitmap_00000000, - }, { - .flags = KVM_MSR_FILTER_WRITE, - .base = 0x00000000, - .nmsrs = KVM_MSR_FILTER_MAX_BITMAP_SIZE * BITS_PER_BYTE, - .bitmap = bitmap_00000000_write, - }, { - .flags = KVM_MSR_FILTER_READ | KVM_MSR_FILTER_WRITE, - .base = 0x40000000, - .nmsrs = KVM_MSR_FILTER_MAX_BITMAP_SIZE * BITS_PER_BYTE, - .bitmap = bitmap_40000000, - }, { - .flags = KVM_MSR_FILTER_READ, - .base = 0xc0000000, - .nmsrs = KVM_MSR_FILTER_MAX_BITMAP_SIZE * BITS_PER_BYTE, - .bitmap = bitmap_c0000000_read, - }, { - .flags = KVM_MSR_FILTER_WRITE, - .base = 0xc0000000, - .nmsrs = KVM_MSR_FILTER_MAX_BITMAP_SIZE * BITS_PER_BYTE, - .bitmap = bitmap_c0000000, - }, { - .flags = KVM_MSR_FILTER_WRITE | KVM_MSR_FILTER_READ, - .base = 0xdeadbeef, - .nmsrs = 1, - .bitmap = bitmap_deadbeef, - }, - }, -}; - -struct kvm_msr_filter no_filter = { - .flags = KVM_MSR_FILTER_DEFAULT_ALLOW, -}; - -static void guest_msr_calls(bool trapped) -{ - /* This goes into the in-kernel emulation */ - wrmsr(MSR_SYSCALL_MASK, 0); - - if (trapped) { - /* This goes into user space emulation */ - GUEST_ASSERT(rdmsr(MSR_SYSCALL_MASK) == MSR_SYSCALL_MASK); - GUEST_ASSERT(rdmsr(MSR_GS_BASE) == MSR_GS_BASE); - } else { - GUEST_ASSERT(rdmsr(MSR_SYSCALL_MASK) != MSR_SYSCALL_MASK); - GUEST_ASSERT(rdmsr(MSR_GS_BASE) != MSR_GS_BASE); - } - - /* If trapped == true, this goes into user space emulation */ - wrmsr(MSR_IA32_POWER_CTL, 0x1234); - - /* This goes into the in-kernel emulation */ - rdmsr(MSR_IA32_POWER_CTL); - - /* Invalid MSR, should always be handled by user space exit */ - GUEST_ASSERT(rdmsr(0xdeadbeef) == 0xdeadbeef); - wrmsr(0xdeadbeef, 0x1234); -} - -static void guest_code(void) -{ - guest_msr_calls(true); - - /* - * Disable msr filtering, so that the kernel - * handles everything in the next round - */ - GUEST_SYNC(0); - - guest_msr_calls(false); - - GUEST_DONE(); -} - -static int handle_ucall(struct kvm_vm *vm) -{ - struct ucall uc; - - switch (get_ucall(vm, VCPU_ID, &uc)) { - case UCALL_ABORT: - TEST_FAIL("Guest assertion not met"); - break; - case UCALL_SYNC: - vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &no_filter); - break; - case UCALL_DONE: - return 1; - default: - TEST_FAIL("Unknown ucall %lu", uc.cmd); - } - - return 0; -} - -static void handle_rdmsr(struct kvm_run *run) -{ - run->msr.data = run->msr.index; - msr_reads++; - - if (run->msr.index == MSR_SYSCALL_MASK || - run->msr.index == MSR_GS_BASE) { - TEST_ASSERT(run->msr.reason == KVM_MSR_EXIT_REASON_FILTER, - "MSR read trap w/o access fault"); - } - - if (run->msr.index == 0xdeadbeef) { - TEST_ASSERT(run->msr.reason == KVM_MSR_EXIT_REASON_UNKNOWN, - "MSR deadbeef read trap w/o inval fault"); - } -} - -static void handle_wrmsr(struct kvm_run *run) -{ - /* ignore */ - msr_writes++; - - if (run->msr.index == MSR_IA32_POWER_CTL) { - TEST_ASSERT(run->msr.data == 0x1234, - "MSR data for MSR_IA32_POWER_CTL incorrect"); - TEST_ASSERT(run->msr.reason == KVM_MSR_EXIT_REASON_FILTER, - "MSR_IA32_POWER_CTL trap w/o access fault"); - } - - if (run->msr.index == 0xdeadbeef) { - TEST_ASSERT(run->msr.data == 0x1234, - "MSR data for deadbeef incorrect"); - TEST_ASSERT(run->msr.reason == KVM_MSR_EXIT_REASON_UNKNOWN, - "deadbeef trap w/o inval fault"); - } -} - -int main(int argc, char *argv[]) -{ - struct kvm_enable_cap cap = { - .cap = KVM_CAP_X86_USER_SPACE_MSR, - .args[0] = KVM_MSR_EXIT_REASON_INVAL | - KVM_MSR_EXIT_REASON_UNKNOWN | - KVM_MSR_EXIT_REASON_FILTER, - }; - struct kvm_vm *vm; - struct kvm_run *run; - int rc; - - /* Tell stdout not to buffer its content */ - setbuf(stdout, NULL); - - /* Create VM */ - vm = vm_create_default(VCPU_ID, 0, guest_code); - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); - run = vcpu_state(vm, VCPU_ID); - - rc = kvm_check_cap(KVM_CAP_X86_USER_SPACE_MSR); - TEST_ASSERT(rc, "KVM_CAP_X86_USER_SPACE_MSR is available"); - vm_enable_cap(vm, &cap); - - rc = kvm_check_cap(KVM_CAP_X86_MSR_FILTER); - TEST_ASSERT(rc, "KVM_CAP_X86_MSR_FILTER is available"); - - prepare_bitmaps(); - vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &filter); - - while (1) { - rc = _vcpu_run(vm, VCPU_ID); - - TEST_ASSERT(rc == 0, "vcpu_run failed: %d\n", rc); - - switch (run->exit_reason) { - case KVM_EXIT_X86_RDMSR: - handle_rdmsr(run); - break; - case KVM_EXIT_X86_WRMSR: - handle_wrmsr(run); - break; - case KVM_EXIT_IO: - if (handle_ucall(vm)) - goto done; - break; - } - - } - -done: - TEST_ASSERT(msr_reads == 4, "Handled 4 rdmsr in user space"); - TEST_ASSERT(msr_writes == 3, "Handled 3 wrmsr in user space"); - - kvm_vm_free(vm); - - return 0; -} diff --git a/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c b/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c new file mode 100644 index 000000000000..72c0d0797522 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c @@ -0,0 +1,770 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2020, Google LLC. + * + * Tests for exiting into userspace on registered MSRs + */ + +#define _GNU_SOURCE /* for program_invocation_short_name */ +#include <sys/ioctl.h> + +#include "test_util.h" +#include "kvm_util.h" +#include "vmx.h" + +/* Forced emulation prefix, used to invoke the emulator unconditionally. */ +#define KVM_FEP "ud2; .byte 'k', 'v', 'm';" +#define KVM_FEP_LENGTH 5 +static int fep_available = 1; + +#define VCPU_ID 1 +#define MSR_NON_EXISTENT 0x474f4f00 + +static u64 deny_bits = 0; +struct kvm_msr_filter filter_allow = { + .flags = KVM_MSR_FILTER_DEFAULT_ALLOW, + .ranges = { + { + .flags = KVM_MSR_FILTER_READ | + KVM_MSR_FILTER_WRITE, + .nmsrs = 1, + /* Test an MSR the kernel knows about. */ + .base = MSR_IA32_XSS, + .bitmap = (uint8_t*)&deny_bits, + }, { + .flags = KVM_MSR_FILTER_READ | + KVM_MSR_FILTER_WRITE, + .nmsrs = 1, + /* Test an MSR the kernel doesn't know about. */ + .base = MSR_IA32_FLUSH_CMD, + .bitmap = (uint8_t*)&deny_bits, + }, { + .flags = KVM_MSR_FILTER_READ | + KVM_MSR_FILTER_WRITE, + .nmsrs = 1, + /* Test a fabricated MSR that no one knows about. */ + .base = MSR_NON_EXISTENT, + .bitmap = (uint8_t*)&deny_bits, + }, + }, +}; + +struct kvm_msr_filter filter_fs = { + .flags = KVM_MSR_FILTER_DEFAULT_ALLOW, + .ranges = { + { + .flags = KVM_MSR_FILTER_READ, + .nmsrs = 1, + .base = MSR_FS_BASE, + .bitmap = (uint8_t*)&deny_bits, + }, + }, +}; + +struct kvm_msr_filter filter_gs = { + .flags = KVM_MSR_FILTER_DEFAULT_ALLOW, + .ranges = { + { + .flags = KVM_MSR_FILTER_READ, + .nmsrs = 1, + .base = MSR_GS_BASE, + .bitmap = (uint8_t*)&deny_bits, + }, + }, +}; + +static uint64_t msr_non_existent_data; +static int guest_exception_count; +static u32 msr_reads, msr_writes; + +static u8 bitmap_00000000[KVM_MSR_FILTER_MAX_BITMAP_SIZE]; +static u8 bitmap_00000000_write[KVM_MSR_FILTER_MAX_BITMAP_SIZE]; +static u8 bitmap_40000000[KVM_MSR_FILTER_MAX_BITMAP_SIZE]; +static u8 bitmap_c0000000[KVM_MSR_FILTER_MAX_BITMAP_SIZE]; +static u8 bitmap_c0000000_read[KVM_MSR_FILTER_MAX_BITMAP_SIZE]; +static u8 bitmap_deadbeef[1] = { 0x1 }; + +static void deny_msr(uint8_t *bitmap, u32 msr) +{ + u32 idx = msr & (KVM_MSR_FILTER_MAX_BITMAP_SIZE - 1); + + bitmap[idx / 8] &= ~(1 << (idx % 8)); +} + +static void prepare_bitmaps(void) +{ + memset(bitmap_00000000, 0xff, sizeof(bitmap_00000000)); + memset(bitmap_00000000_write, 0xff, sizeof(bitmap_00000000_write)); + memset(bitmap_40000000, 0xff, sizeof(bitmap_40000000)); + memset(bitmap_c0000000, 0xff, sizeof(bitmap_c0000000)); + memset(bitmap_c0000000_read, 0xff, sizeof(bitmap_c0000000_read)); + + deny_msr(bitmap_00000000_write, MSR_IA32_POWER_CTL); + deny_msr(bitmap_c0000000_read, MSR_SYSCALL_MASK); + deny_msr(bitmap_c0000000_read, MSR_GS_BASE); +} + +struct kvm_msr_filter filter_deny = { + .flags = KVM_MSR_FILTER_DEFAULT_DENY, + .ranges = { + { + .flags = KVM_MSR_FILTER_READ, + .base = 0x00000000, + .nmsrs = KVM_MSR_FILTER_MAX_BITMAP_SIZE * BITS_PER_BYTE, + .bitmap = bitmap_00000000, + }, { + .flags = KVM_MSR_FILTER_WRITE, + .base = 0x00000000, + .nmsrs = KVM_MSR_FILTER_MAX_BITMAP_SIZE * BITS_PER_BYTE, + .bitmap = bitmap_00000000_write, + }, { + .flags = KVM_MSR_FILTER_READ | KVM_MSR_FILTER_WRITE, + .base = 0x40000000, + .nmsrs = KVM_MSR_FILTER_MAX_BITMAP_SIZE * BITS_PER_BYTE, + .bitmap = bitmap_40000000, + }, { + .flags = KVM_MSR_FILTER_READ, + .base = 0xc0000000, + .nmsrs = KVM_MSR_FILTER_MAX_BITMAP_SIZE * BITS_PER_BYTE, + .bitmap = bitmap_c0000000_read, + }, { + .flags = KVM_MSR_FILTER_WRITE, + .base = 0xc0000000, + .nmsrs = KVM_MSR_FILTER_MAX_BITMAP_SIZE * BITS_PER_BYTE, + .bitmap = bitmap_c0000000, + }, { + .flags = KVM_MSR_FILTER_WRITE | KVM_MSR_FILTER_READ, + .base = 0xdeadbeef, + .nmsrs = 1, + .bitmap = bitmap_deadbeef, + }, + }, +}; + +struct kvm_msr_filter no_filter_deny = { + .flags = KVM_MSR_FILTER_DEFAULT_ALLOW, +}; + +/* + * Note: Force test_rdmsr() to not be inlined to prevent the labels, + * rdmsr_start and rdmsr_end, from being defined multiple times. + */ +static noinline uint64_t test_rdmsr(uint32_t msr) +{ + uint32_t a, d; + + guest_exception_count = 0; + + __asm__ __volatile__("rdmsr_start: rdmsr; rdmsr_end:" : + "=a"(a), "=d"(d) : "c"(msr) : "memory"); + + return a | ((uint64_t) d << 32); +} + +/* + * Note: Force test_wrmsr() to not be inlined to prevent the labels, + * wrmsr_start and wrmsr_end, from being defined multiple times. + */ +static noinline void test_wrmsr(uint32_t msr, uint64_t value) +{ + uint32_t a = value; + uint32_t d = value >> 32; + + guest_exception_count = 0; + + __asm__ __volatile__("wrmsr_start: wrmsr; wrmsr_end:" :: + "a"(a), "d"(d), "c"(msr) : "memory"); +} + +extern char rdmsr_start, rdmsr_end; +extern char wrmsr_start, wrmsr_end; + +/* + * Note: Force test_em_rdmsr() to not be inlined to prevent the labels, + * rdmsr_start and rdmsr_end, from being defined multiple times. + */ +static noinline uint64_t test_em_rdmsr(uint32_t msr) +{ + uint32_t a, d; + + guest_exception_count = 0; + + __asm__ __volatile__(KVM_FEP "em_rdmsr_start: rdmsr; em_rdmsr_end:" : + "=a"(a), "=d"(d) : "c"(msr) : "memory"); + + return a | ((uint64_t) d << 32); +} + +/* + * Note: Force test_em_wrmsr() to not be inlined to prevent the labels, + * wrmsr_start and wrmsr_end, from being defined multiple times. + */ +static noinline void test_em_wrmsr(uint32_t msr, uint64_t value) +{ + uint32_t a = value; + uint32_t d = value >> 32; + + guest_exception_count = 0; + + __asm__ __volatile__(KVM_FEP "em_wrmsr_start: wrmsr; em_wrmsr_end:" :: + "a"(a), "d"(d), "c"(msr) : "memory"); +} + +extern char em_rdmsr_start, em_rdmsr_end; +extern char em_wrmsr_start, em_wrmsr_end; + +static void guest_code_filter_allow(void) +{ + uint64_t data; + + /* + * Test userspace intercepting rdmsr / wrmsr for MSR_IA32_XSS. + * + * A GP is thrown if anything other than 0 is written to + * MSR_IA32_XSS. + */ + data = test_rdmsr(MSR_IA32_XSS); + GUEST_ASSERT(data == 0); + GUEST_ASSERT(guest_exception_count == 0); + + test_wrmsr(MSR_IA32_XSS, 0); + GUEST_ASSERT(guest_exception_count == 0); + + test_wrmsr(MSR_IA32_XSS, 1); + GUEST_ASSERT(guest_exception_count == 1); + + /* + * Test userspace intercepting rdmsr / wrmsr for MSR_IA32_FLUSH_CMD. + * + * A GP is thrown if MSR_IA32_FLUSH_CMD is read + * from or if a value other than 1 is written to it. + */ + test_rdmsr(MSR_IA32_FLUSH_CMD); + GUEST_ASSERT(guest_exception_count == 1); + + test_wrmsr(MSR_IA32_FLUSH_CMD, 0); + GUEST_ASSERT(guest_exception_count == 1); + + test_wrmsr(MSR_IA32_FLUSH_CMD, 1); + GUEST_ASSERT(guest_exception_count == 0); + + /* + * Test userspace intercepting rdmsr / wrmsr for MSR_NON_EXISTENT. + * + * Test that a fabricated MSR can pass through the kernel + * and be handled in userspace. + */ + test_wrmsr(MSR_NON_EXISTENT, 2); + GUEST_ASSERT(guest_exception_count == 0); + + data = test_rdmsr(MSR_NON_EXISTENT); + GUEST_ASSERT(data == 2); + GUEST_ASSERT(guest_exception_count == 0); + + /* + * Test to see if the instruction emulator is available (ie: the module + * parameter 'kvm.force_emulation_prefix=1' is set). This instruction + * will #UD if it isn't available. + */ + __asm__ __volatile__(KVM_FEP "nop"); + + if (fep_available) { + /* Let userspace know we aren't done. */ + GUEST_SYNC(0); + + /* + * Now run the same tests with the instruction emulator. + */ + data = test_em_rdmsr(MSR_IA32_XSS); + GUEST_ASSERT(data == 0); + GUEST_ASSERT(guest_exception_count == 0); + test_em_wrmsr(MSR_IA32_XSS, 0); + GUEST_ASSERT(guest_exception_count == 0); + test_em_wrmsr(MSR_IA32_XSS, 1); + GUEST_ASSERT(guest_exception_count == 1); + + test_em_rdmsr(MSR_IA32_FLUSH_CMD); + GUEST_ASSERT(guest_exception_count == 1); + test_em_wrmsr(MSR_IA32_FLUSH_CMD, 0); + GUEST_ASSERT(guest_exception_count == 1); + test_em_wrmsr(MSR_IA32_FLUSH_CMD, 1); + GUEST_ASSERT(guest_exception_count == 0); + + test_em_wrmsr(MSR_NON_EXISTENT, 2); + GUEST_ASSERT(guest_exception_count == 0); + data = test_em_rdmsr(MSR_NON_EXISTENT); + GUEST_ASSERT(data == 2); + GUEST_ASSERT(guest_exception_count == 0); + } + + GUEST_DONE(); +} + +static void guest_msr_calls(bool trapped) +{ + /* This goes into the in-kernel emulation */ + wrmsr(MSR_SYSCALL_MASK, 0); + + if (trapped) { + /* This goes into user space emulation */ + GUEST_ASSERT(rdmsr(MSR_SYSCALL_MASK) == MSR_SYSCALL_MASK); + GUEST_ASSERT(rdmsr(MSR_GS_BASE) == MSR_GS_BASE); + } else { + GUEST_ASSERT(rdmsr(MSR_SYSCALL_MASK) != MSR_SYSCALL_MASK); + GUEST_ASSERT(rdmsr(MSR_GS_BASE) != MSR_GS_BASE); + } + + /* If trapped == true, this goes into user space emulation */ + wrmsr(MSR_IA32_POWER_CTL, 0x1234); + + /* This goes into the in-kernel emulation */ + rdmsr(MSR_IA32_POWER_CTL); + + /* Invalid MSR, should always be handled by user space exit */ + GUEST_ASSERT(rdmsr(0xdeadbeef) == 0xdeadbeef); + wrmsr(0xdeadbeef, 0x1234); +} + +static void guest_code_filter_deny(void) +{ + guest_msr_calls(true); + + /* + * Disable msr filtering, so that the kernel + * handles everything in the next round + */ + GUEST_SYNC(0); + + guest_msr_calls(false); + + GUEST_DONE(); +} + +static void guest_code_permission_bitmap(void) +{ + uint64_t data; + + data = test_rdmsr(MSR_FS_BASE); + GUEST_ASSERT(data == MSR_FS_BASE); + data = test_rdmsr(MSR_GS_BASE); + GUEST_ASSERT(data != MSR_GS_BASE); + + /* Let userspace know to switch the filter */ + GUEST_SYNC(0); + + data = test_rdmsr(MSR_FS_BASE); + GUEST_ASSERT(data != MSR_FS_BASE); + data = test_rdmsr(MSR_GS_BASE); + GUEST_ASSERT(data == MSR_GS_BASE); + + GUEST_DONE(); +} + +static void __guest_gp_handler(struct ex_regs *regs, + char *r_start, char *r_end, + char *w_start, char *w_end) +{ + if (regs->rip == (uintptr_t)r_start) { + regs->rip = (uintptr_t)r_end; + regs->rax = 0; + regs->rdx = 0; + } else if (regs->rip == (uintptr_t)w_start) { + regs->rip = (uintptr_t)w_end; + } else { + GUEST_ASSERT(!"RIP is at an unknown location!"); + } + + ++guest_exception_count; +} + +static void guest_gp_handler(struct ex_regs *regs) +{ + __guest_gp_handler(regs, &rdmsr_start, &rdmsr_end, + &wrmsr_start, &wrmsr_end); +} + +static void guest_fep_gp_handler(struct ex_regs *regs) +{ + __guest_gp_handler(regs, &em_rdmsr_start, &em_rdmsr_end, + &em_wrmsr_start, &em_wrmsr_end); +} + +static void guest_ud_handler(struct ex_regs *regs) +{ + fep_available = 0; + regs->rip += KVM_FEP_LENGTH; +} + +static void run_guest(struct kvm_vm *vm) +{ + int rc; + + rc = _vcpu_run(vm, VCPU_ID); + TEST_ASSERT(rc == 0, "vcpu_run failed: %d\n", rc); +} + +static void check_for_guest_assert(struct kvm_vm *vm) +{ + struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct ucall uc; + + if (run->exit_reason == KVM_EXIT_IO && + get_ucall(vm, VCPU_ID, &uc) == UCALL_ABORT) { + TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], + __FILE__, uc.args[1]); + } +} + +static void process_rdmsr(struct kvm_vm *vm, uint32_t msr_index) +{ + struct kvm_run *run = vcpu_state(vm, VCPU_ID); + + check_for_guest_assert(vm); + + TEST_ASSERT(run->exit_reason == KVM_EXIT_X86_RDMSR, + "Unexpected exit reason: %u (%s),\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + TEST_ASSERT(run->msr.index == msr_index, + "Unexpected msr (0x%04x), expected 0x%04x", + run->msr.index, msr_index); + + switch (run->msr.index) { + case MSR_IA32_XSS: + run->msr.data = 0; + break; + case MSR_IA32_FLUSH_CMD: + run->msr.error = 1; + break; + case MSR_NON_EXISTENT: + run->msr.data = msr_non_existent_data; + break; + case MSR_FS_BASE: + run->msr.data = MSR_FS_BASE; + break; + case MSR_GS_BASE: + run->msr.data = MSR_GS_BASE; + break; + default: + TEST_ASSERT(false, "Unexpected MSR: 0x%04x", run->msr.index); + } +} + +static void process_wrmsr(struct kvm_vm *vm, uint32_t msr_index) +{ + struct kvm_run *run = vcpu_state(vm, VCPU_ID); + + check_for_guest_assert(vm); + + TEST_ASSERT(run->exit_reason == KVM_EXIT_X86_WRMSR, + "Unexpected exit reason: %u (%s),\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + TEST_ASSERT(run->msr.index == msr_index, + "Unexpected msr (0x%04x), expected 0x%04x", + run->msr.index, msr_index); + + switch (run->msr.index) { + case MSR_IA32_XSS: + if (run->msr.data != 0) + run->msr.error = 1; + break; + case MSR_IA32_FLUSH_CMD: + if (run->msr.data != 1) + run->msr.error = 1; + break; + case MSR_NON_EXISTENT: + msr_non_existent_data = run->msr.data; + break; + default: + TEST_ASSERT(false, "Unexpected MSR: 0x%04x", run->msr.index); + } +} + +static void process_ucall_done(struct kvm_vm *vm) +{ + struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct ucall uc; + + check_for_guest_assert(vm); + + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Unexpected exit reason: %u (%s)", + run->exit_reason, + exit_reason_str(run->exit_reason)); + + TEST_ASSERT(get_ucall(vm, VCPU_ID, &uc) == UCALL_DONE, + "Unexpected ucall command: %lu, expected UCALL_DONE (%d)", + uc.cmd, UCALL_DONE); +} + +static uint64_t process_ucall(struct kvm_vm *vm) +{ + struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct ucall uc = {}; + + check_for_guest_assert(vm); + + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Unexpected exit reason: %u (%s)", + run->exit_reason, + exit_reason_str(run->exit_reason)); + + switch (get_ucall(vm, VCPU_ID, &uc)) { + case UCALL_SYNC: + break; + case UCALL_ABORT: + check_for_guest_assert(vm); + break; + case UCALL_DONE: + process_ucall_done(vm); + break; + default: + TEST_ASSERT(false, "Unexpected ucall"); + } + + return uc.cmd; +} + +static void run_guest_then_process_rdmsr(struct kvm_vm *vm, uint32_t msr_index) +{ + run_guest(vm); + process_rdmsr(vm, msr_index); +} + +static void run_guest_then_process_wrmsr(struct kvm_vm *vm, uint32_t msr_index) +{ + run_guest(vm); + process_wrmsr(vm, msr_index); +} + +static uint64_t run_guest_then_process_ucall(struct kvm_vm *vm) +{ + run_guest(vm); + return process_ucall(vm); +} + +static void run_guest_then_process_ucall_done(struct kvm_vm *vm) +{ + run_guest(vm); + process_ucall_done(vm); +} + +static void test_msr_filter_allow(void) { + struct kvm_enable_cap cap = { + .cap = KVM_CAP_X86_USER_SPACE_MSR, + .args[0] = KVM_MSR_EXIT_REASON_FILTER, + }; + struct kvm_vm *vm; + int rc; + + /* Create VM */ + vm = vm_create_default(VCPU_ID, 0, guest_code_filter_allow); + vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); + + rc = kvm_check_cap(KVM_CAP_X86_USER_SPACE_MSR); + TEST_ASSERT(rc, "KVM_CAP_X86_USER_SPACE_MSR is available"); + vm_enable_cap(vm, &cap); + + rc = kvm_check_cap(KVM_CAP_X86_MSR_FILTER); + TEST_ASSERT(rc, "KVM_CAP_X86_MSR_FILTER is available"); + + vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &filter_allow); + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vm, VCPU_ID); + + vm_handle_exception(vm, GP_VECTOR, guest_gp_handler); + + /* Process guest code userspace exits. */ + run_guest_then_process_rdmsr(vm, MSR_IA32_XSS); + run_guest_then_process_wrmsr(vm, MSR_IA32_XSS); + run_guest_then_process_wrmsr(vm, MSR_IA32_XSS); + + run_guest_then_process_rdmsr(vm, MSR_IA32_FLUSH_CMD); + run_guest_then_process_wrmsr(vm, MSR_IA32_FLUSH_CMD); + run_guest_then_process_wrmsr(vm, MSR_IA32_FLUSH_CMD); + + run_guest_then_process_wrmsr(vm, MSR_NON_EXISTENT); + run_guest_then_process_rdmsr(vm, MSR_NON_EXISTENT); + + vm_handle_exception(vm, UD_VECTOR, guest_ud_handler); + run_guest(vm); + vm_handle_exception(vm, UD_VECTOR, NULL); + + if (process_ucall(vm) != UCALL_DONE) { + vm_handle_exception(vm, GP_VECTOR, guest_fep_gp_handler); + + /* Process emulated rdmsr and wrmsr instructions. */ + run_guest_then_process_rdmsr(vm, MSR_IA32_XSS); + run_guest_then_process_wrmsr(vm, MSR_IA32_XSS); + run_guest_then_process_wrmsr(vm, MSR_IA32_XSS); + + run_guest_then_process_rdmsr(vm, MSR_IA32_FLUSH_CMD); + run_guest_then_process_wrmsr(vm, MSR_IA32_FLUSH_CMD); + run_guest_then_process_wrmsr(vm, MSR_IA32_FLUSH_CMD); + + run_guest_then_process_wrmsr(vm, MSR_NON_EXISTENT); + run_guest_then_process_rdmsr(vm, MSR_NON_EXISTENT); + + /* Confirm the guest completed without issues. */ + run_guest_then_process_ucall_done(vm); + } else { + printf("To run the instruction emulated tests set the module parameter 'kvm.force_emulation_prefix=1'\n"); + } + + kvm_vm_free(vm); +} + +static int handle_ucall(struct kvm_vm *vm) +{ + struct ucall uc; + + switch (get_ucall(vm, VCPU_ID, &uc)) { + case UCALL_ABORT: + TEST_FAIL("Guest assertion not met"); + break; + case UCALL_SYNC: + vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &no_filter_deny); + break; + case UCALL_DONE: + return 1; + default: + TEST_FAIL("Unknown ucall %lu", uc.cmd); + } + + return 0; +} + +static void handle_rdmsr(struct kvm_run *run) +{ + run->msr.data = run->msr.index; + msr_reads++; + + if (run->msr.index == MSR_SYSCALL_MASK || + run->msr.index == MSR_GS_BASE) { + TEST_ASSERT(run->msr.reason == KVM_MSR_EXIT_REASON_FILTER, + "MSR read trap w/o access fault"); + } + + if (run->msr.index == 0xdeadbeef) { + TEST_ASSERT(run->msr.reason == KVM_MSR_EXIT_REASON_UNKNOWN, + "MSR deadbeef read trap w/o inval fault"); + } +} + +static void handle_wrmsr(struct kvm_run *run) +{ + /* ignore */ + msr_writes++; + + if (run->msr.index == MSR_IA32_POWER_CTL) { + TEST_ASSERT(run->msr.data == 0x1234, + "MSR data for MSR_IA32_POWER_CTL incorrect"); + TEST_ASSERT(run->msr.reason == KVM_MSR_EXIT_REASON_FILTER, + "MSR_IA32_POWER_CTL trap w/o access fault"); + } + + if (run->msr.index == 0xdeadbeef) { + TEST_ASSERT(run->msr.data == 0x1234, + "MSR data for deadbeef incorrect"); + TEST_ASSERT(run->msr.reason == KVM_MSR_EXIT_REASON_UNKNOWN, + "deadbeef trap w/o inval fault"); + } +} + +static void test_msr_filter_deny(void) { + struct kvm_enable_cap cap = { + .cap = KVM_CAP_X86_USER_SPACE_MSR, + .args[0] = KVM_MSR_EXIT_REASON_INVAL | + KVM_MSR_EXIT_REASON_UNKNOWN | + KVM_MSR_EXIT_REASON_FILTER, + }; + struct kvm_vm *vm; + struct kvm_run *run; + int rc; + + /* Create VM */ + vm = vm_create_default(VCPU_ID, 0, guest_code_filter_deny); + vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); + run = vcpu_state(vm, VCPU_ID); + + rc = kvm_check_cap(KVM_CAP_X86_USER_SPACE_MSR); + TEST_ASSERT(rc, "KVM_CAP_X86_USER_SPACE_MSR is available"); + vm_enable_cap(vm, &cap); + + rc = kvm_check_cap(KVM_CAP_X86_MSR_FILTER); + TEST_ASSERT(rc, "KVM_CAP_X86_MSR_FILTER is available"); + + prepare_bitmaps(); + vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &filter_deny); + + while (1) { + rc = _vcpu_run(vm, VCPU_ID); + + TEST_ASSERT(rc == 0, "vcpu_run failed: %d\n", rc); + + switch (run->exit_reason) { + case KVM_EXIT_X86_RDMSR: + handle_rdmsr(run); + break; + case KVM_EXIT_X86_WRMSR: + handle_wrmsr(run); + break; + case KVM_EXIT_IO: + if (handle_ucall(vm)) + goto done; + break; + } + + } + +done: + TEST_ASSERT(msr_reads == 4, "Handled 4 rdmsr in user space"); + TEST_ASSERT(msr_writes == 3, "Handled 3 wrmsr in user space"); + + kvm_vm_free(vm); +} + +static void test_msr_permission_bitmap(void) { + struct kvm_enable_cap cap = { + .cap = KVM_CAP_X86_USER_SPACE_MSR, + .args[0] = KVM_MSR_EXIT_REASON_FILTER, + }; + struct kvm_vm *vm; + int rc; + + /* Create VM */ + vm = vm_create_default(VCPU_ID, 0, guest_code_permission_bitmap); + vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); + + rc = kvm_check_cap(KVM_CAP_X86_USER_SPACE_MSR); + TEST_ASSERT(rc, "KVM_CAP_X86_USER_SPACE_MSR is available"); + vm_enable_cap(vm, &cap); + + rc = kvm_check_cap(KVM_CAP_X86_MSR_FILTER); + TEST_ASSERT(rc, "KVM_CAP_X86_MSR_FILTER is available"); + + vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &filter_fs); + run_guest_then_process_rdmsr(vm, MSR_FS_BASE); + TEST_ASSERT(run_guest_then_process_ucall(vm) == UCALL_SYNC, "Expected ucall state to be UCALL_SYNC."); + vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &filter_gs); + run_guest_then_process_rdmsr(vm, MSR_GS_BASE); + run_guest_then_process_ucall_done(vm); + + kvm_vm_free(vm); +} + +int main(int argc, char *argv[]) +{ + /* Tell stdout not to buffer its content */ + setbuf(stdout, NULL); + + test_msr_filter_allow(); + + test_msr_filter_deny(); + + test_msr_permission_bitmap(); + + return 0; +} diff --git a/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c b/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c index 1f65342d6cb7..d14888b34adb 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c @@ -87,7 +87,6 @@ int main(int argc, char *argv[]) nested_vmx_check_supported(); vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code); - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); kvm_get_cpu_address_width(&paddr_width, &vaddr_width); high_gpa = (1ul << paddr_width) - getpagesize(); diff --git a/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c b/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c index fe40ade06a49..2835a17f1b7a 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c @@ -57,7 +57,6 @@ int main(int argc, char *argv[]) nested_vmx_check_supported(); vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code); - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); /* Allocate VMX pages and shared descriptors (vmx_pages). */ vcpu_alloc_vmx(vm, &vmx_pages_gva); diff --git a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c index e894a638a155..537de1068554 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c @@ -82,7 +82,6 @@ int main(int argc, char *argv[]) /* Create VM */ vm = vm_create_default(VCPU_ID, 0, l1_guest_code); - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); vmx = vcpu_alloc_vmx(vm, &vmx_pages_gva); vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva); run = vcpu_state(vm, VCPU_ID); diff --git a/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c b/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c index a7737af1224f..a07480aed397 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c @@ -169,20 +169,19 @@ int main(int argc, char *argv[]) */ nested_vmx_check_supported(); + if (!kvm_check_cap(KVM_CAP_NESTED_STATE)) { + print_skip("KVM_CAP_NESTED_STATE not supported"); + exit(KSFT_SKIP); + } + /* Create VM */ vm = vm_create_default(VCPU_ID, 0, guest_code); - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); run = vcpu_state(vm, VCPU_ID); vcpu_regs_get(vm, VCPU_ID, ®s1); - if (kvm_check_cap(KVM_CAP_NESTED_STATE)) { - vcpu_alloc_vmx(vm, &vmx_pages_gva); - vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva); - } else { - pr_info("will skip vmx preemption timer checks\n"); - goto done; - } + vcpu_alloc_vmx(vm, &vmx_pages_gva); + vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva); for (stage = 1;; stage++) { _vcpu_run(vm, VCPU_ID); diff --git a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c index d59f3eb67c8f..5827b9bae468 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c @@ -244,6 +244,22 @@ void test_vmx_nested_state(struct kvm_vm *vm) free(state); } +void disable_vmx(struct kvm_vm *vm) +{ + struct kvm_cpuid2 *cpuid = kvm_get_supported_cpuid(); + int i; + + for (i = 0; i < cpuid->nent; ++i) + if (cpuid->entries[i].function == 1 && + cpuid->entries[i].index == 0) + break; + TEST_ASSERT(i != cpuid->nent, "CPUID function 1 not found"); + + cpuid->entries[i].ecx &= ~CPUID_VMX; + vcpu_set_cpuid(vm, VCPU_ID, cpuid); + cpuid->entries[i].ecx |= CPUID_VMX; +} + int main(int argc, char *argv[]) { struct kvm_vm *vm; @@ -264,6 +280,11 @@ int main(int argc, char *argv[]) vm = vm_create_default(VCPU_ID, 0, 0); + /* + * First run tests with VMX disabled to check error handling. + */ + disable_vmx(vm); + /* Passing a NULL kvm_nested_state causes a EFAULT. */ test_nested_state_expect_efault(vm, NULL); diff --git a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c index fbe8417cbc2c..7e33a350b053 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c @@ -132,7 +132,6 @@ int main(int argc, char *argv[]) nested_vmx_check_supported(); vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code); - vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); /* Allocate VMX pages and shared descriptors (vmx_pages). */ vcpu_alloc_vmx(vm, &vmx_pages_gva); diff --git a/tools/testing/selftests/net/devlink_port_split.py b/tools/testing/selftests/net/devlink_port_split.py index 58bb7e9b88ce..834066d465fc 100755 --- a/tools/testing/selftests/net/devlink_port_split.py +++ b/tools/testing/selftests/net/devlink_port_split.py @@ -1,4 +1,4 @@ -#!/usr/bin/python3 +#!/usr/bin/env python3 # SPDX-License-Identifier: GPL-2.0 from subprocess import PIPE, Popen diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index 464e31eabc73..64cd2e23c568 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -162,7 +162,15 @@ # - list_flush_ipv6_exception # Using the same topology as in pmtu_ipv6, create exceptions, and check # they are shown when listing exception caches, gone after flushing them - +# +# - pmtu_ipv4_route_change +# Use the same topology as in pmtu_ipv4, but issue a route replacement +# command and delete the corresponding device afterward. This tests for +# proper cleanup of the PMTU exceptions by the route replacement path. +# Device unregistration should complete successfully +# +# - pmtu_ipv6_route_change +# Same as above but with IPv6 # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 @@ -224,7 +232,9 @@ tests=" cleanup_ipv4_exception ipv4: cleanup of cached exceptions 1 cleanup_ipv6_exception ipv6: cleanup of cached exceptions 1 list_flush_ipv4_exception ipv4: list and flush cached exceptions 1 - list_flush_ipv6_exception ipv6: list and flush cached exceptions 1" + list_flush_ipv6_exception ipv6: list and flush cached exceptions 1 + pmtu_ipv4_route_change ipv4: PMTU exception w/route replace 1 + pmtu_ipv6_route_change ipv6: PMTU exception w/route replace 1" NS_A="ns-A" NS_B="ns-B" @@ -1782,6 +1792,63 @@ test_list_flush_ipv6_exception() { return ${fail} } +test_pmtu_ipvX_route_change() { + family=${1} + + setup namespaces routing || return 2 + trace "${ns_a}" veth_A-R1 "${ns_r1}" veth_R1-A \ + "${ns_r1}" veth_R1-B "${ns_b}" veth_B-R1 \ + "${ns_a}" veth_A-R2 "${ns_r2}" veth_R2-A \ + "${ns_r2}" veth_R2-B "${ns_b}" veth_B-R2 + + if [ ${family} -eq 4 ]; then + ping=ping + dst1="${prefix4}.${b_r1}.1" + dst2="${prefix4}.${b_r2}.1" + gw="${prefix4}.${a_r1}.2" + else + ping=${ping6} + dst1="${prefix6}:${b_r1}::1" + dst2="${prefix6}:${b_r2}::1" + gw="${prefix6}:${a_r1}::2" + fi + + # Set up initial MTU values + mtu "${ns_a}" veth_A-R1 2000 + mtu "${ns_r1}" veth_R1-A 2000 + mtu "${ns_r1}" veth_R1-B 1400 + mtu "${ns_b}" veth_B-R1 1400 + + mtu "${ns_a}" veth_A-R2 2000 + mtu "${ns_r2}" veth_R2-A 2000 + mtu "${ns_r2}" veth_R2-B 1500 + mtu "${ns_b}" veth_B-R2 1500 + + # Create route exceptions + run_cmd ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s 1800 ${dst1} + run_cmd ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s 1800 ${dst2} + + # Check that exceptions have been created with the correct PMTU + pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst1})" + check_pmtu_value "1400" "${pmtu_1}" "exceeding MTU" || return 1 + pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})" + check_pmtu_value "1500" "${pmtu_2}" "exceeding MTU" || return 1 + + # Replace the route from A to R1 + run_cmd ${ns_a} ip route change default via ${gw} + + # Delete the device in A + run_cmd ${ns_a} ip link del "veth_A-R1" +} + +test_pmtu_ipv4_route_change() { + test_pmtu_ipvX_route_change 4 +} + +test_pmtu_ipv6_route_change() { + test_pmtu_ipvX_route_change 6 +} + usage() { echo echo "$0 [OPTIONS] [TEST]..." diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh index ac2a30be9b32..f8a19f548ae9 100755 --- a/tools/testing/selftests/net/udpgro.sh +++ b/tools/testing/selftests/net/udpgro.sh @@ -5,6 +5,14 @@ readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)" +# set global exit status, but never reset nonzero one. +check_err() +{ + if [ $ret -eq 0 ]; then + ret=$1 + fi +} + cleanup() { local -r jobs="$(jobs -p)" local -r ns="$(ip netns list|grep $PEER_NS)" @@ -44,7 +52,9 @@ run_one() { # Hack: let bg programs complete the startup sleep 0.1 ./udpgso_bench_tx ${tx_args} + ret=$? wait $(jobs -p) + return $ret } run_test() { @@ -87,8 +97,10 @@ run_one_nat() { sleep 0.1 ./udpgso_bench_tx ${tx_args} + ret=$? kill -INT $pid wait $(jobs -p) + return $ret } run_one_2sock() { @@ -110,7 +122,9 @@ run_one_2sock() { sleep 0.1 # first UDP GSO socket should be closed at this point ./udpgso_bench_tx ${tx_args} + ret=$? wait $(jobs -p) + return $ret } run_nat_test() { @@ -131,36 +145,54 @@ run_all() { local -r core_args="-l 4" local -r ipv4_args="${core_args} -4 -D 192.168.1.1" local -r ipv6_args="${core_args} -6 -D 2001:db8::1" + ret=0 echo "ipv4" run_test "no GRO" "${ipv4_args} -M 10 -s 1400" "-4 -n 10 -l 1400" + check_err $? # explicitly check we are not receiving UDP_SEGMENT cmsg (-S -1) # when GRO does not take place run_test "no GRO chk cmsg" "${ipv4_args} -M 10 -s 1400" "-4 -n 10 -l 1400 -S -1" + check_err $? # the GSO packets are aggregated because: # * veth schedule napi after each xmit # * segmentation happens in BH context, veth napi poll is delayed after # the transmission of the last segment run_test "GRO" "${ipv4_args} -M 1 -s 14720 -S 0 " "-4 -n 1 -l 14720" + check_err $? run_test "GRO chk cmsg" "${ipv4_args} -M 1 -s 14720 -S 0 " "-4 -n 1 -l 14720 -S 1472" + check_err $? run_test "GRO with custom segment size" "${ipv4_args} -M 1 -s 14720 -S 500 " "-4 -n 1 -l 14720" + check_err $? run_test "GRO with custom segment size cmsg" "${ipv4_args} -M 1 -s 14720 -S 500 " "-4 -n 1 -l 14720 -S 500" + check_err $? run_nat_test "bad GRO lookup" "${ipv4_args} -M 1 -s 14720 -S 0" "-n 10 -l 1472" + check_err $? run_2sock_test "multiple GRO socks" "${ipv4_args} -M 1 -s 14720 -S 0 " "-4 -n 1 -l 14720 -S 1472" + check_err $? echo "ipv6" run_test "no GRO" "${ipv6_args} -M 10 -s 1400" "-n 10 -l 1400" + check_err $? run_test "no GRO chk cmsg" "${ipv6_args} -M 10 -s 1400" "-n 10 -l 1400 -S -1" + check_err $? run_test "GRO" "${ipv6_args} -M 1 -s 14520 -S 0" "-n 1 -l 14520" + check_err $? run_test "GRO chk cmsg" "${ipv6_args} -M 1 -s 14520 -S 0" "-n 1 -l 14520 -S 1452" + check_err $? run_test "GRO with custom segment size" "${ipv6_args} -M 1 -s 14520 -S 500" "-n 1 -l 14520" + check_err $? run_test "GRO with custom segment size cmsg" "${ipv6_args} -M 1 -s 14520 -S 500" "-n 1 -l 14520 -S 500" + check_err $? run_nat_test "bad GRO lookup" "${ipv6_args} -M 1 -s 14520 -S 0" "-n 10 -l 1452" + check_err $? run_2sock_test "multiple GRO socks" "${ipv6_args} -M 1 -s 14520 -S 0 " "-n 1 -l 14520 -S 1452" + check_err $? + return $ret } if [ ! -f ../bpf/xdp_dummy.o ]; then @@ -180,3 +212,5 @@ elif [[ $1 == "__subprocess_2sock" ]]; then shift run_one_2sock $@ fi + +exit $? diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile index a374e10ef506..3006a8e5b41a 100644 --- a/tools/testing/selftests/netfilter/Makefile +++ b/tools/testing/selftests/netfilter/Makefile @@ -4,7 +4,8 @@ TEST_PROGS := nft_trans_stress.sh nft_nat.sh bridge_brouter.sh \ conntrack_icmp_related.sh nft_flowtable.sh ipvs.sh \ nft_concat_range.sh nft_conntrack_helper.sh \ - nft_queue.sh nft_meta.sh + nft_queue.sh nft_meta.sh \ + ipip-conntrack-mtu.sh LDLIBS = -lmnl TEST_GEN_FILES = nf-queue diff --git a/tools/testing/selftests/netfilter/ipip-conntrack-mtu.sh b/tools/testing/selftests/netfilter/ipip-conntrack-mtu.sh new file mode 100755 index 000000000000..4a6f5c3b3215 --- /dev/null +++ b/tools/testing/selftests/netfilter/ipip-conntrack-mtu.sh @@ -0,0 +1,206 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +# Conntrack needs to reassemble fragments in order to have complete +# packets for rule matching. Reassembly can lead to packet loss. + +# Consider the following setup: +# +--------+ +---------+ +--------+ +# |Router A|-------|Wanrouter|-------|Router B| +# | |.IPIP..| |..IPIP.| | +# +--------+ +---------+ +--------+ +# / mtu 1400 \ +# / \ +#+--------+ +--------+ +#|Client A| |Client B| +#| | | | +#+--------+ +--------+ + +# Router A and Router B use IPIP tunnel interfaces to tunnel traffic +# between Client A and Client B over WAN. Wanrouter has MTU 1400 set +# on its interfaces. + +rnd=$(mktemp -u XXXXXXXX) +rx=$(mktemp) + +r_a="ns-ra-$rnd" +r_b="ns-rb-$rnd" +r_w="ns-rw-$rnd" +c_a="ns-ca-$rnd" +c_b="ns-cb-$rnd" + +checktool (){ + if ! $1 > /dev/null 2>&1; then + echo "SKIP: Could not $2" + exit $ksft_skip + fi +} + +checktool "iptables --version" "run test without iptables" +checktool "ip -Version" "run test without ip tool" +checktool "which nc" "run test without nc (netcat)" +checktool "ip netns add ${r_a}" "create net namespace" + +for n in ${r_b} ${r_w} ${c_a} ${c_b};do + ip netns add ${n} +done + +cleanup() { + for n in ${r_a} ${r_b} ${r_w} ${c_a} ${c_b};do + ip netns del ${n} + done + rm -f ${rx} +} + +trap cleanup EXIT + +test_path() { + msg="$1" + + ip netns exec ${c_b} nc -n -w 3 -q 3 -u -l -p 5000 > ${rx} < /dev/null & + + sleep 1 + for i in 1 2 3; do + head -c1400 /dev/zero | tr "\000" "a" | ip netns exec ${c_a} nc -n -w 1 -u 192.168.20.2 5000 + done + + wait + + bytes=$(wc -c < ${rx}) + + if [ $bytes -eq 1400 ];then + echo "OK: PMTU $msg connection tracking" + else + echo "FAIL: PMTU $msg connection tracking: got $bytes, expected 1400" + exit 1 + fi +} + +# Detailed setup for Router A +# --------------------------- +# Interfaces: +# eth0: 10.2.2.1/24 +# eth1: 192.168.10.1/24 +# ipip0: No IP address, local 10.2.2.1 remote 10.4.4.1 +# Routes: +# 192.168.20.0/24 dev ipip0 (192.168.20.0/24 is subnet of Client B) +# 10.4.4.1 via 10.2.2.254 (Router B via Wanrouter) +# No iptables rules at all. + +ip link add veth0 netns ${r_a} type veth peer name veth0 netns ${r_w} +ip link add veth1 netns ${r_a} type veth peer name veth0 netns ${c_a} + +l_addr="10.2.2.1" +r_addr="10.4.4.1" +ip netns exec ${r_a} ip link add ipip0 type ipip local ${l_addr} remote ${r_addr} mode ipip || exit $ksft_skip + +for dev in lo veth0 veth1 ipip0; do + ip -net ${r_a} link set $dev up +done + +ip -net ${r_a} addr add 10.2.2.1/24 dev veth0 +ip -net ${r_a} addr add 192.168.10.1/24 dev veth1 + +ip -net ${r_a} route add 192.168.20.0/24 dev ipip0 +ip -net ${r_a} route add 10.4.4.0/24 via 10.2.2.254 + +ip netns exec ${r_a} sysctl -q net.ipv4.conf.all.forwarding=1 > /dev/null + +# Detailed setup for Router B +# --------------------------- +# Interfaces: +# eth0: 10.4.4.1/24 +# eth1: 192.168.20.1/24 +# ipip0: No IP address, local 10.4.4.1 remote 10.2.2.1 +# Routes: +# 192.168.10.0/24 dev ipip0 (192.168.10.0/24 is subnet of Client A) +# 10.2.2.1 via 10.4.4.254 (Router A via Wanrouter) +# No iptables rules at all. + +ip link add veth0 netns ${r_b} type veth peer name veth1 netns ${r_w} +ip link add veth1 netns ${r_b} type veth peer name veth0 netns ${c_b} + +l_addr="10.4.4.1" +r_addr="10.2.2.1" + +ip netns exec ${r_b} ip link add ipip0 type ipip local ${l_addr} remote ${r_addr} mode ipip || exit $ksft_skip + +for dev in lo veth0 veth1 ipip0; do + ip -net ${r_b} link set $dev up +done + +ip -net ${r_b} addr add 10.4.4.1/24 dev veth0 +ip -net ${r_b} addr add 192.168.20.1/24 dev veth1 + +ip -net ${r_b} route add 192.168.10.0/24 dev ipip0 +ip -net ${r_b} route add 10.2.2.0/24 via 10.4.4.254 +ip netns exec ${r_b} sysctl -q net.ipv4.conf.all.forwarding=1 > /dev/null + +# Client A +ip -net ${c_a} addr add 192.168.10.2/24 dev veth0 +ip -net ${c_a} link set dev lo up +ip -net ${c_a} link set dev veth0 up +ip -net ${c_a} route add default via 192.168.10.1 + +# Client A +ip -net ${c_b} addr add 192.168.20.2/24 dev veth0 +ip -net ${c_b} link set dev veth0 up +ip -net ${c_b} link set dev lo up +ip -net ${c_b} route add default via 192.168.20.1 + +# Wan +ip -net ${r_w} addr add 10.2.2.254/24 dev veth0 +ip -net ${r_w} addr add 10.4.4.254/24 dev veth1 + +ip -net ${r_w} link set dev lo up +ip -net ${r_w} link set dev veth0 up mtu 1400 +ip -net ${r_w} link set dev veth1 up mtu 1400 + +ip -net ${r_a} link set dev veth0 mtu 1400 +ip -net ${r_b} link set dev veth0 mtu 1400 + +ip netns exec ${r_w} sysctl -q net.ipv4.conf.all.forwarding=1 > /dev/null + +# Path MTU discovery +# ------------------ +# Running tracepath from Client A to Client B shows PMTU discovery is working +# as expected: +# +# clienta:~# tracepath 192.168.20.2 +# 1?: [LOCALHOST] pmtu 1500 +# 1: 192.168.10.1 0.867ms +# 1: 192.168.10.1 0.302ms +# 2: 192.168.10.1 0.312ms pmtu 1480 +# 2: no reply +# 3: 192.168.10.1 0.510ms pmtu 1380 +# 3: 192.168.20.2 2.320ms reached +# Resume: pmtu 1380 hops 3 back 3 + +# ip netns exec ${c_a} traceroute --mtu 192.168.20.2 + +# Router A has learned PMTU (1400) to Router B from Wanrouter. +# Client A has learned PMTU (1400 - IPIP overhead = 1380) to Client B +# from Router A. + +#Send large UDP packet +#--------------------- +#Now we send a 1400 bytes UDP packet from Client A to Client B: + +# clienta:~# head -c1400 /dev/zero | tr "\000" "a" | nc -u 192.168.20.2 5000 +test_path "without" + +# The IPv4 stack on Client A already knows the PMTU to Client B, so the +# UDP packet is sent as two fragments (1380 + 20). Router A forwards the +# fragments between eth1 and ipip0. The fragments fit into the tunnel and +# reach their destination. + +#When sending the large UDP packet again, Router A now reassembles the +#fragments before routing the packet over ipip0. The resulting IPIP +#packet is too big (1400) for the tunnel PMTU (1380) to Router B, it is +#dropped on Router A before sending. + +ip netns exec ${r_a} iptables -A FORWARD -m conntrack --ctstate NEW +test_path "with" diff --git a/tools/testing/selftests/tc-testing/tdc_batch.py b/tools/testing/selftests/tc-testing/tdc_batch.py index 995f66ce43eb..35d5d9493784 100755 --- a/tools/testing/selftests/tc-testing/tdc_batch.py +++ b/tools/testing/selftests/tc-testing/tdc_batch.py @@ -1,4 +1,4 @@ -#!/usr/bin/python3 +#!/usr/bin/env python3 """ tdc_batch.py - a script to generate TC batch file diff --git a/tools/testing/selftests/tc-testing/tdc_multibatch.py b/tools/testing/selftests/tc-testing/tdc_multibatch.py index 5e7237952e49..48e1f17ff2e8 100755 --- a/tools/testing/selftests/tc-testing/tdc_multibatch.py +++ b/tools/testing/selftests/tc-testing/tdc_multibatch.py @@ -1,4 +1,4 @@ -#!/usr/bin/python3 +#!/usr/bin/env python3 # SPDX-License-Identifier: GPL-2.0 """ tdc_multibatch.py - a thin wrapper over tdc_batch.py to generate multiple batch diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index 9a25307f6115..d42115e4284d 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -4,7 +4,7 @@ include local_config.mk uname_M := $(shell uname -m 2>/dev/null || echo not) -MACHINE ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/') +MACHINE ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/' -e 's/ppc64.*/ppc64/') # Without this, failed build products remain, with up-to-date timestamps, # thus tricking Make (and you!) into believing that All Is Well, in subsequent @@ -43,7 +43,7 @@ TEST_GEN_FILES += thuge-gen TEST_GEN_FILES += transhuge-stress TEST_GEN_FILES += userfaultfd -ifeq ($(ARCH),x86_64) +ifeq ($(MACHINE),x86_64) CAN_BUILD_I386 := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_32bit_program.c -m32) CAN_BUILD_X86_64 := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_64bit_program.c) CAN_BUILD_WITH_NOPIE := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_program.c -no-pie) @@ -65,13 +65,13 @@ TEST_GEN_FILES += $(BINARIES_64) endif else -ifneq (,$(findstring $(ARCH),powerpc)) +ifneq (,$(findstring $(MACHINE),ppc64)) TEST_GEN_FILES += protection_keys endif endif -ifneq (,$(filter $(MACHINE),arm64 ia64 mips64 parisc64 ppc64 ppc64le riscv64 s390x sh64 sparc64 x86_64)) +ifneq (,$(filter $(MACHINE),arm64 ia64 mips64 parisc64 ppc64 riscv64 s390x sh64 sparc64 x86_64)) TEST_GEN_FILES += va_128TBswitch TEST_GEN_FILES += virtual_address_range TEST_GEN_FILES += write_to_hugetlbfs @@ -84,7 +84,7 @@ TEST_FILES := test_vmalloc.sh KSFT_KHDR_INSTALL := 1 include ../lib.mk -ifeq ($(ARCH),x86_64) +ifeq ($(MACHINE),x86_64) BINARIES_32 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_32)) BINARIES_64 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_64)) diff --git a/tools/testing/selftests/wireguard/qemu/debug.config b/tools/testing/selftests/wireguard/qemu/debug.config index b50c2085c1ac..fe07d97df9fa 100644 --- a/tools/testing/selftests/wireguard/qemu/debug.config +++ b/tools/testing/selftests/wireguard/qemu/debug.config @@ -1,5 +1,4 @@ CONFIG_LOCALVERSION="-debug" -CONFIG_ENABLE_MUST_CHECK=y CONFIG_FRAME_POINTER=y CONFIG_STACK_VALIDATION=y CONFIG_DEBUG_KERNEL=y diff --git a/tools/virtio/asm/barrier.h b/tools/virtio/asm/barrier.h index 04d563fc9b95..468435ed64e6 100644 --- a/tools/virtio/asm/barrier.h +++ b/tools/virtio/asm/barrier.h @@ -16,6 +16,16 @@ # define mb() abort() # define dma_rmb() abort() # define dma_wmb() abort() +#elif defined(__aarch64__) +#define dmb(opt) asm volatile("dmb " #opt : : : "memory") +#define virt_mb() __sync_synchronize() +#define virt_rmb() dmb(ishld) +#define virt_wmb() dmb(ishst) +#define virt_store_mb(var, value) do { WRITE_ONCE(var, value); dmb(ish); } while (0) +/* Weak barriers should be used. If not - it's a bug */ +# define mb() abort() +# define dma_rmb() abort() +# define dma_wmb() abort() #else #error Please fill in barrier macros #endif diff --git a/tools/virtio/linux/bug.h b/tools/virtio/linux/bug.h index b14c2c3b6b85..813baf13f62a 100644 --- a/tools/virtio/linux/bug.h +++ b/tools/virtio/linux/bug.h @@ -2,6 +2,8 @@ #ifndef BUG_H #define BUG_H +#include <asm/bug.h> + #define BUG_ON(__BUG_ON_cond) assert(!(__BUG_ON_cond)) #define BUILD_BUG_ON(x) diff --git a/tools/virtio/linux/kernel.h b/tools/virtio/linux/kernel.h index 315e85cabeda..0b493542e61a 100644 --- a/tools/virtio/linux/kernel.h +++ b/tools/virtio/linux/kernel.h @@ -11,6 +11,7 @@ #include <linux/compiler.h> #include <linux/types.h> +#include <linux/overflow.h> #include <linux/list.h> #include <linux/printk.h> #include <linux/bug.h> @@ -117,6 +118,16 @@ static inline void free_page(unsigned long addr) # define unlikely(x) (__builtin_expect(!!(x), 0)) # endif +static inline void *krealloc_array(void *p, size_t new_n, size_t new_size, gfp_t gfp) +{ + size_t bytes; + + if (unlikely(check_mul_overflow(new_n, new_size, &bytes))) + return NULL; + + return krealloc(p, bytes, gfp); +} + #define pr_err(format, ...) fprintf (stderr, format, ## __VA_ARGS__) #ifdef DEBUG #define pr_debug(format, ...) fprintf (stderr, format, ## __VA_ARGS__) @@ -126,8 +137,6 @@ static inline void free_page(unsigned long addr) #define dev_err(dev, format, ...) fprintf (stderr, format, ## __VA_ARGS__) #define dev_warn(dev, format, ...) fprintf (stderr, format, ## __VA_ARGS__) -#define WARN_ON_ONCE(cond) (unlikely(cond) ? fprintf (stderr, "WARNING\n") : 0) - #define min(x, y) ({ \ typeof(x) _min1 = (x); \ typeof(y) _min2 = (y); \ |