diff options
Diffstat (limited to 'tools')
54 files changed, 3755 insertions, 1391 deletions
diff --git a/tools/arch/arm64/include/asm/cputype.h b/tools/arch/arm64/include/asm/cputype.h index 7c7493cb571f..52f076afeb96 100644 --- a/tools/arch/arm64/include/asm/cputype.h +++ b/tools/arch/arm64/include/asm/cputype.h @@ -61,6 +61,7 @@ #define ARM_CPU_IMP_HISI 0x48 #define ARM_CPU_IMP_APPLE 0x61 #define ARM_CPU_IMP_AMPERE 0xC0 +#define ARM_CPU_IMP_MICROSOFT 0x6D #define ARM_CPU_PART_AEM_V8 0xD0F #define ARM_CPU_PART_FOUNDATION 0xD00 @@ -135,6 +136,8 @@ #define AMPERE_CPU_PART_AMPERE1 0xAC3 +#define MICROSOFT_CPU_PART_AZURE_COBALT_100 0xD49 /* Based on r0p0 of ARM Neoverse N2 */ + #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53) #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57) #define MIDR_CORTEX_A72 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A72) @@ -193,6 +196,7 @@ #define MIDR_APPLE_M2_BLIZZARD_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD_MAX) #define MIDR_APPLE_M2_AVALANCHE_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE_MAX) #define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1) +#define MIDR_MICROSOFT_AZURE_COBALT_100 MIDR_CPU_MODEL(ARM_CPU_IMP_MICROSOFT, MICROSOFT_CPU_PART_AZURE_COBALT_100) /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */ #define MIDR_FUJITSU_ERRATUM_010001 MIDR_FUJITSU_A64FX diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index 89d2fc872d9f..964df31da975 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -37,9 +37,7 @@ #include <asm/ptrace.h> #include <asm/sve_context.h> -#define __KVM_HAVE_GUEST_DEBUG #define __KVM_HAVE_IRQ_LINE -#define __KVM_HAVE_READONLY_MEM #define __KVM_HAVE_VCPU_EVENTS #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 @@ -76,11 +74,11 @@ struct kvm_regs { /* KVM_ARM_SET_DEVICE_ADDR ioctl id encoding */ #define KVM_ARM_DEVICE_TYPE_SHIFT 0 -#define KVM_ARM_DEVICE_TYPE_MASK GENMASK(KVM_ARM_DEVICE_TYPE_SHIFT + 15, \ - KVM_ARM_DEVICE_TYPE_SHIFT) +#define KVM_ARM_DEVICE_TYPE_MASK __GENMASK(KVM_ARM_DEVICE_TYPE_SHIFT + 15, \ + KVM_ARM_DEVICE_TYPE_SHIFT) #define KVM_ARM_DEVICE_ID_SHIFT 16 -#define KVM_ARM_DEVICE_ID_MASK GENMASK(KVM_ARM_DEVICE_ID_SHIFT + 15, \ - KVM_ARM_DEVICE_ID_SHIFT) +#define KVM_ARM_DEVICE_ID_MASK __GENMASK(KVM_ARM_DEVICE_ID_SHIFT + 15, \ + KVM_ARM_DEVICE_ID_SHIFT) /* Supported device IDs */ #define KVM_ARM_DEVICE_VGIC_V2 0 @@ -162,6 +160,11 @@ struct kvm_sync_regs { __u64 device_irq_level; }; +/* Bits for run->s.regs.device_irq_level */ +#define KVM_ARM_DEV_EL1_VTIMER (1 << 0) +#define KVM_ARM_DEV_EL1_PTIMER (1 << 1) +#define KVM_ARM_DEV_PMU (1 << 2) + /* * 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/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h index 9f18fa090f1f..1691297a766a 100644 --- a/tools/arch/powerpc/include/uapi/asm/kvm.h +++ b/tools/arch/powerpc/include/uapi/asm/kvm.h @@ -28,7 +28,6 @@ #define __KVM_HAVE_PPC_SMT #define __KVM_HAVE_IRQCHIP #define __KVM_HAVE_IRQ_LINE -#define __KVM_HAVE_GUEST_DEBUG /* Not always available, but if it is, this is the correct offset. */ #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 @@ -733,4 +732,48 @@ struct kvm_ppc_xive_eq { #define KVM_XIVE_TIMA_PAGE_OFFSET 0 #define KVM_XIVE_ESB_PAGE_OFFSET 4 +/* for KVM_PPC_GET_PVINFO */ + +#define KVM_PPC_PVINFO_FLAGS_EV_IDLE (1<<0) + +struct kvm_ppc_pvinfo { + /* out */ + __u32 flags; + __u32 hcall[4]; + __u8 pad[108]; +}; + +/* for KVM_PPC_GET_SMMU_INFO */ +#define KVM_PPC_PAGE_SIZES_MAX_SZ 8 + +struct kvm_ppc_one_page_size { + __u32 page_shift; /* Page shift (or 0) */ + __u32 pte_enc; /* Encoding in the HPTE (>>12) */ +}; + +struct kvm_ppc_one_seg_page_size { + __u32 page_shift; /* Base page shift of segment (or 0) */ + __u32 slb_enc; /* SLB encoding for BookS */ + struct kvm_ppc_one_page_size enc[KVM_PPC_PAGE_SIZES_MAX_SZ]; +}; + +#define KVM_PPC_PAGE_SIZES_REAL 0x00000001 +#define KVM_PPC_1T_SEGMENTS 0x00000002 +#define KVM_PPC_NO_HASH 0x00000004 + +struct kvm_ppc_smmu_info { + __u64 flags; + __u32 slb_size; + __u16 data_keys; /* # storage keys supported for data */ + __u16 instr_keys; /* # storage keys supported for instructions */ + struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ]; +}; + +/* for KVM_PPC_RESIZE_HPT_{PREPARE,COMMIT} */ +struct kvm_ppc_resize_hpt { + __u64 flags; + __u32 shift; + __u32 pad; +}; + #endif /* __LINUX_KVM_POWERPC_H */ diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h index abe926d43cbe..05eaf6db3ad4 100644 --- a/tools/arch/s390/include/uapi/asm/kvm.h +++ b/tools/arch/s390/include/uapi/asm/kvm.h @@ -12,7 +12,320 @@ #include <linux/types.h> #define __KVM_S390 -#define __KVM_HAVE_GUEST_DEBUG + +struct kvm_s390_skeys { + __u64 start_gfn; + __u64 count; + __u64 skeydata_addr; + __u32 flags; + __u32 reserved[9]; +}; + +#define KVM_S390_CMMA_PEEK (1 << 0) + +/** + * kvm_s390_cmma_log - Used for CMMA migration. + * + * Used both for input and output. + * + * @start_gfn: Guest page number to start from. + * @count: Size of the result buffer. + * @flags: Control operation mode via KVM_S390_CMMA_* flags + * @remaining: Used with KVM_S390_GET_CMMA_BITS. Indicates how many dirty + * pages are still remaining. + * @mask: Used with KVM_S390_SET_CMMA_BITS. Bitmap of bits to actually set + * in the PGSTE. + * @values: Pointer to the values buffer. + * + * Used in KVM_S390_{G,S}ET_CMMA_BITS ioctls. + */ +struct kvm_s390_cmma_log { + __u64 start_gfn; + __u32 count; + __u32 flags; + union { + __u64 remaining; + __u64 mask; + }; + __u64 values; +}; + +#define KVM_S390_RESET_POR 1 +#define KVM_S390_RESET_CLEAR 2 +#define KVM_S390_RESET_SUBSYSTEM 4 +#define KVM_S390_RESET_CPU_INIT 8 +#define KVM_S390_RESET_IPL 16 + +/* for KVM_S390_MEM_OP */ +struct kvm_s390_mem_op { + /* in */ + __u64 gaddr; /* the guest address */ + __u64 flags; /* flags */ + __u32 size; /* amount of bytes */ + __u32 op; /* type of operation */ + __u64 buf; /* buffer in userspace */ + union { + struct { + __u8 ar; /* the access register number */ + __u8 key; /* access key, ignored if flag unset */ + __u8 pad1[6]; /* ignored */ + __u64 old_addr; /* ignored if cmpxchg flag unset */ + }; + __u32 sida_offset; /* offset into the sida */ + __u8 reserved[32]; /* ignored */ + }; +}; +/* types for kvm_s390_mem_op->op */ +#define KVM_S390_MEMOP_LOGICAL_READ 0 +#define KVM_S390_MEMOP_LOGICAL_WRITE 1 +#define KVM_S390_MEMOP_SIDA_READ 2 +#define KVM_S390_MEMOP_SIDA_WRITE 3 +#define KVM_S390_MEMOP_ABSOLUTE_READ 4 +#define KVM_S390_MEMOP_ABSOLUTE_WRITE 5 +#define KVM_S390_MEMOP_ABSOLUTE_CMPXCHG 6 + +/* flags for kvm_s390_mem_op->flags */ +#define KVM_S390_MEMOP_F_CHECK_ONLY (1ULL << 0) +#define KVM_S390_MEMOP_F_INJECT_EXCEPTION (1ULL << 1) +#define KVM_S390_MEMOP_F_SKEY_PROTECTION (1ULL << 2) + +/* flags specifying extension support via KVM_CAP_S390_MEM_OP_EXTENSION */ +#define KVM_S390_MEMOP_EXTENSION_CAP_BASE (1 << 0) +#define KVM_S390_MEMOP_EXTENSION_CAP_CMPXCHG (1 << 1) + +struct kvm_s390_psw { + __u64 mask; + __u64 addr; +}; + +/* valid values for type in kvm_s390_interrupt */ +#define KVM_S390_SIGP_STOP 0xfffe0000u +#define KVM_S390_PROGRAM_INT 0xfffe0001u +#define KVM_S390_SIGP_SET_PREFIX 0xfffe0002u +#define KVM_S390_RESTART 0xfffe0003u +#define KVM_S390_INT_PFAULT_INIT 0xfffe0004u +#define KVM_S390_INT_PFAULT_DONE 0xfffe0005u +#define KVM_S390_MCHK 0xfffe1000u +#define KVM_S390_INT_CLOCK_COMP 0xffff1004u +#define KVM_S390_INT_CPU_TIMER 0xffff1005u +#define KVM_S390_INT_VIRTIO 0xffff2603u +#define KVM_S390_INT_SERVICE 0xffff2401u +#define KVM_S390_INT_EMERGENCY 0xffff1201u +#define KVM_S390_INT_EXTERNAL_CALL 0xffff1202u +/* Anything below 0xfffe0000u is taken by INT_IO */ +#define KVM_S390_INT_IO(ai,cssid,ssid,schid) \ + (((schid)) | \ + ((ssid) << 16) | \ + ((cssid) << 18) | \ + ((ai) << 26)) +#define KVM_S390_INT_IO_MIN 0x00000000u +#define KVM_S390_INT_IO_MAX 0xfffdffffu +#define KVM_S390_INT_IO_AI_MASK 0x04000000u + + +struct kvm_s390_interrupt { + __u32 type; + __u32 parm; + __u64 parm64; +}; + +struct kvm_s390_io_info { + __u16 subchannel_id; + __u16 subchannel_nr; + __u32 io_int_parm; + __u32 io_int_word; +}; + +struct kvm_s390_ext_info { + __u32 ext_params; + __u32 pad; + __u64 ext_params2; +}; + +struct kvm_s390_pgm_info { + __u64 trans_exc_code; + __u64 mon_code; + __u64 per_address; + __u32 data_exc_code; + __u16 code; + __u16 mon_class_nr; + __u8 per_code; + __u8 per_atmid; + __u8 exc_access_id; + __u8 per_access_id; + __u8 op_access_id; +#define KVM_S390_PGM_FLAGS_ILC_VALID 0x01 +#define KVM_S390_PGM_FLAGS_ILC_0 0x02 +#define KVM_S390_PGM_FLAGS_ILC_1 0x04 +#define KVM_S390_PGM_FLAGS_ILC_MASK 0x06 +#define KVM_S390_PGM_FLAGS_NO_REWIND 0x08 + __u8 flags; + __u8 pad[2]; +}; + +struct kvm_s390_prefix_info { + __u32 address; +}; + +struct kvm_s390_extcall_info { + __u16 code; +}; + +struct kvm_s390_emerg_info { + __u16 code; +}; + +#define KVM_S390_STOP_FLAG_STORE_STATUS 0x01 +struct kvm_s390_stop_info { + __u32 flags; +}; + +struct kvm_s390_mchk_info { + __u64 cr14; + __u64 mcic; + __u64 failing_storage_address; + __u32 ext_damage_code; + __u32 pad; + __u8 fixed_logout[16]; +}; + +struct kvm_s390_irq { + __u64 type; + union { + struct kvm_s390_io_info io; + struct kvm_s390_ext_info ext; + struct kvm_s390_pgm_info pgm; + struct kvm_s390_emerg_info emerg; + struct kvm_s390_extcall_info extcall; + struct kvm_s390_prefix_info prefix; + struct kvm_s390_stop_info stop; + struct kvm_s390_mchk_info mchk; + char reserved[64]; + } u; +}; + +struct kvm_s390_irq_state { + __u64 buf; + __u32 flags; /* will stay unused for compatibility reasons */ + __u32 len; + __u32 reserved[4]; /* will stay unused for compatibility reasons */ +}; + +struct kvm_s390_ucas_mapping { + __u64 user_addr; + __u64 vcpu_addr; + __u64 length; +}; + +struct kvm_s390_pv_sec_parm { + __u64 origin; + __u64 length; +}; + +struct kvm_s390_pv_unp { + __u64 addr; + __u64 size; + __u64 tweak; +}; + +enum pv_cmd_dmp_id { + KVM_PV_DUMP_INIT, + KVM_PV_DUMP_CONFIG_STOR_STATE, + KVM_PV_DUMP_COMPLETE, + KVM_PV_DUMP_CPU, +}; + +struct kvm_s390_pv_dmp { + __u64 subcmd; + __u64 buff_addr; + __u64 buff_len; + __u64 gaddr; /* For dump storage state */ + __u64 reserved[4]; +}; + +enum pv_cmd_info_id { + KVM_PV_INFO_VM, + KVM_PV_INFO_DUMP, +}; + +struct kvm_s390_pv_info_dump { + __u64 dump_cpu_buffer_len; + __u64 dump_config_mem_buffer_per_1m; + __u64 dump_config_finalize_len; +}; + +struct kvm_s390_pv_info_vm { + __u64 inst_calls_list[4]; + __u64 max_cpus; + __u64 max_guests; + __u64 max_guest_addr; + __u64 feature_indication; +}; + +struct kvm_s390_pv_info_header { + __u32 id; + __u32 len_max; + __u32 len_written; + __u32 reserved; +}; + +struct kvm_s390_pv_info { + struct kvm_s390_pv_info_header header; + union { + struct kvm_s390_pv_info_dump dump; + struct kvm_s390_pv_info_vm vm; + }; +}; + +enum pv_cmd_id { + KVM_PV_ENABLE, + KVM_PV_DISABLE, + KVM_PV_SET_SEC_PARMS, + KVM_PV_UNPACK, + KVM_PV_VERIFY, + KVM_PV_PREP_RESET, + KVM_PV_UNSHARE_ALL, + KVM_PV_INFO, + KVM_PV_DUMP, + KVM_PV_ASYNC_CLEANUP_PREPARE, + KVM_PV_ASYNC_CLEANUP_PERFORM, +}; + +struct kvm_pv_cmd { + __u32 cmd; /* Command to be executed */ + __u16 rc; /* Ultravisor return code */ + __u16 rrc; /* Ultravisor return reason code */ + __u64 data; /* Data or address */ + __u32 flags; /* flags for future extensions. Must be 0 for now */ + __u32 reserved[3]; +}; + +struct kvm_s390_zpci_op { + /* in */ + __u32 fh; /* target device */ + __u8 op; /* operation to perform */ + __u8 pad[3]; + union { + /* for KVM_S390_ZPCIOP_REG_AEN */ + struct { + __u64 ibv; /* Guest addr of interrupt bit vector */ + __u64 sb; /* Guest addr of summary bit */ + __u32 flags; + __u32 noi; /* Number of interrupts */ + __u8 isc; /* Guest interrupt subclass */ + __u8 sbo; /* Offset of guest summary bit vector */ + __u16 pad; + } reg_aen; + __u64 reserved[8]; + } u; +}; + +/* types for kvm_s390_zpci_op->op */ +#define KVM_S390_ZPCIOP_REG_AEN 0 +#define KVM_S390_ZPCIOP_DEREG_AEN 1 + +/* flags for kvm_s390_zpci_op->u.reg_aen.flags */ +#define KVM_S390_ZPCIOP_REGAEN_HOST (1 << 0) /* Device control API: s390-specific devices */ #define KVM_DEV_FLIC_GET_ALL_IRQS 1 diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 25160d26764b..a38f8f9ba657 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -13,7 +13,7 @@ /* * Defines x86 CPU feature bits */ -#define NCAPINTS 21 /* N 32-bit words worth of info */ +#define NCAPINTS 22 /* N 32-bit words worth of info */ #define NBUGINTS 2 /* N 32-bit bug flags */ /* @@ -81,10 +81,8 @@ #define X86_FEATURE_K6_MTRR ( 3*32+ 1) /* AMD K6 nonstandard MTRRs */ #define X86_FEATURE_CYRIX_ARR ( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */ #define X86_FEATURE_CENTAUR_MCR ( 3*32+ 3) /* Centaur MCRs (= MTRRs) */ - -/* CPU types for specific tunings: */ #define X86_FEATURE_K8 ( 3*32+ 4) /* "" Opteron, Athlon64 */ -/* FREE, was #define X86_FEATURE_K7 ( 3*32+ 5) "" Athlon */ +#define X86_FEATURE_ZEN5 ( 3*32+ 5) /* "" CPU based on Zen5 microarchitecture */ #define X86_FEATURE_P3 ( 3*32+ 6) /* "" P3 */ #define X86_FEATURE_P4 ( 3*32+ 7) /* "" P4 */ #define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */ @@ -97,7 +95,7 @@ #define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in IA32 userspace */ #define X86_FEATURE_REP_GOOD ( 3*32+16) /* REP microcode works well */ #define X86_FEATURE_AMD_LBR_V2 ( 3*32+17) /* AMD Last Branch Record Extension Version 2 */ -/* FREE, was #define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) "" LFENCE synchronizes RDTSC */ +#define X86_FEATURE_CLEAR_CPU_BUF ( 3*32+18) /* "" Clear CPU buffers using VERW */ #define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */ #define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */ #define X86_FEATURE_ALWAYS ( 3*32+21) /* "" Always-present feature */ @@ -462,6 +460,14 @@ #define X86_FEATURE_SRSO_NO (20*32+29) /* "" CPU is not affected by SRSO */ /* + * Extended auxiliary flags: Linux defined - for features scattered in various + * CPUID levels like 0x80000022, etc. + * + * Reuse free bits when adding new feature flags! + */ +#define X86_FEATURE_AMD_LBR_PMC_FREEZE (21*32+ 0) /* AMD LBR and PMC Freeze */ + +/* * BUG word(s) */ #define X86_BUG(x) (NCAPINTS*32 + (x)) @@ -508,4 +514,5 @@ /* BUG word 2 */ #define X86_BUG_SRSO X86_BUG(1*32 + 0) /* AMD SRSO bug */ #define X86_BUG_DIV0 X86_BUG(1*32 + 1) /* AMD DIV0 speculation bug */ +#define X86_BUG_RFDS X86_BUG(1*32 + 2) /* CPU is vulnerable to Register File Data Sampling */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index 1f23960d2b06..c492bdc97b05 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -123,6 +123,12 @@ # define DISABLE_FRED (1 << (X86_FEATURE_FRED & 31)) #endif +#ifdef CONFIG_KVM_AMD_SEV +#define DISABLE_SEV_SNP 0 +#else +#define DISABLE_SEV_SNP (1 << (X86_FEATURE_SEV_SNP & 31)) +#endif + /* * Make sure to add features to the correct mask */ @@ -147,8 +153,9 @@ DISABLE_ENQCMD) #define DISABLED_MASK17 0 #define DISABLED_MASK18 (DISABLE_IBT) -#define DISABLED_MASK19 0 +#define DISABLED_MASK19 (DISABLE_SEV_SNP) #define DISABLED_MASK20 0 -#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21) +#define DISABLED_MASK21 0 +#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22) #endif /* _ASM_X86_DISABLED_FEATURES_H */ diff --git a/tools/arch/x86/include/asm/irq_vectors.h b/tools/arch/x86/include/asm/irq_vectors.h index 3f73ac3ed3a0..d18bfb238f66 100644 --- a/tools/arch/x86/include/asm/irq_vectors.h +++ b/tools/arch/x86/include/asm/irq_vectors.h @@ -84,11 +84,9 @@ #define HYPERVISOR_CALLBACK_VECTOR 0xf3 /* Vector for KVM to deliver posted interrupt IPI */ -#if IS_ENABLED(CONFIG_KVM) #define POSTED_INTR_VECTOR 0xf2 #define POSTED_INTR_WAKEUP_VECTOR 0xf1 #define POSTED_INTR_NESTED_VECTOR 0xf0 -#endif #define MANAGED_IRQ_SHUTDOWN_VECTOR 0xef diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index 1f9dc9bd13eb..05956bd8bacf 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -176,6 +176,14 @@ * CPU is not vulnerable to Gather * Data Sampling (GDS). */ +#define ARCH_CAP_RFDS_NO BIT(27) /* + * Not susceptible to Register + * File Data Sampling. + */ +#define ARCH_CAP_RFDS_CLEAR BIT(28) /* + * VERW clears CPU Register + * File. + */ #define ARCH_CAP_XAPIC_DISABLE BIT(21) /* * IA32_XAPIC_DISABLE_STATUS MSR @@ -605,34 +613,47 @@ #define MSR_AMD64_SEV_ES_GHCB 0xc0010130 #define MSR_AMD64_SEV 0xc0010131 #define MSR_AMD64_SEV_ENABLED_BIT 0 -#define MSR_AMD64_SEV_ES_ENABLED_BIT 1 -#define MSR_AMD64_SEV_SNP_ENABLED_BIT 2 #define MSR_AMD64_SEV_ENABLED BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT) +#define MSR_AMD64_SEV_ES_ENABLED_BIT 1 #define MSR_AMD64_SEV_ES_ENABLED BIT_ULL(MSR_AMD64_SEV_ES_ENABLED_BIT) +#define MSR_AMD64_SEV_SNP_ENABLED_BIT 2 #define MSR_AMD64_SEV_SNP_ENABLED BIT_ULL(MSR_AMD64_SEV_SNP_ENABLED_BIT) - -/* SNP feature bits enabled by the hypervisor */ -#define MSR_AMD64_SNP_VTOM BIT_ULL(3) -#define MSR_AMD64_SNP_REFLECT_VC BIT_ULL(4) -#define MSR_AMD64_SNP_RESTRICTED_INJ BIT_ULL(5) -#define MSR_AMD64_SNP_ALT_INJ BIT_ULL(6) -#define MSR_AMD64_SNP_DEBUG_SWAP BIT_ULL(7) -#define MSR_AMD64_SNP_PREVENT_HOST_IBS BIT_ULL(8) -#define MSR_AMD64_SNP_BTB_ISOLATION BIT_ULL(9) -#define MSR_AMD64_SNP_VMPL_SSS BIT_ULL(10) -#define MSR_AMD64_SNP_SECURE_TSC BIT_ULL(11) -#define MSR_AMD64_SNP_VMGEXIT_PARAM BIT_ULL(12) -#define MSR_AMD64_SNP_IBS_VIRT BIT_ULL(14) -#define MSR_AMD64_SNP_VMSA_REG_PROTECTION BIT_ULL(16) -#define MSR_AMD64_SNP_SMT_PROTECTION BIT_ULL(17) - -/* SNP feature bits reserved for future use. */ -#define MSR_AMD64_SNP_RESERVED_BIT13 BIT_ULL(13) -#define MSR_AMD64_SNP_RESERVED_BIT15 BIT_ULL(15) -#define MSR_AMD64_SNP_RESERVED_MASK GENMASK_ULL(63, 18) +#define MSR_AMD64_SNP_VTOM_BIT 3 +#define MSR_AMD64_SNP_VTOM BIT_ULL(MSR_AMD64_SNP_VTOM_BIT) +#define MSR_AMD64_SNP_REFLECT_VC_BIT 4 +#define MSR_AMD64_SNP_REFLECT_VC BIT_ULL(MSR_AMD64_SNP_REFLECT_VC_BIT) +#define MSR_AMD64_SNP_RESTRICTED_INJ_BIT 5 +#define MSR_AMD64_SNP_RESTRICTED_INJ BIT_ULL(MSR_AMD64_SNP_RESTRICTED_INJ_BIT) +#define MSR_AMD64_SNP_ALT_INJ_BIT 6 +#define MSR_AMD64_SNP_ALT_INJ BIT_ULL(MSR_AMD64_SNP_ALT_INJ_BIT) +#define MSR_AMD64_SNP_DEBUG_SWAP_BIT 7 +#define MSR_AMD64_SNP_DEBUG_SWAP BIT_ULL(MSR_AMD64_SNP_DEBUG_SWAP_BIT) +#define MSR_AMD64_SNP_PREVENT_HOST_IBS_BIT 8 +#define MSR_AMD64_SNP_PREVENT_HOST_IBS BIT_ULL(MSR_AMD64_SNP_PREVENT_HOST_IBS_BIT) +#define MSR_AMD64_SNP_BTB_ISOLATION_BIT 9 +#define MSR_AMD64_SNP_BTB_ISOLATION BIT_ULL(MSR_AMD64_SNP_BTB_ISOLATION_BIT) +#define MSR_AMD64_SNP_VMPL_SSS_BIT 10 +#define MSR_AMD64_SNP_VMPL_SSS BIT_ULL(MSR_AMD64_SNP_VMPL_SSS_BIT) +#define MSR_AMD64_SNP_SECURE_TSC_BIT 11 +#define MSR_AMD64_SNP_SECURE_TSC BIT_ULL(MSR_AMD64_SNP_SECURE_TSC_BIT) +#define MSR_AMD64_SNP_VMGEXIT_PARAM_BIT 12 +#define MSR_AMD64_SNP_VMGEXIT_PARAM BIT_ULL(MSR_AMD64_SNP_VMGEXIT_PARAM_BIT) +#define MSR_AMD64_SNP_RESERVED_BIT13 BIT_ULL(13) +#define MSR_AMD64_SNP_IBS_VIRT_BIT 14 +#define MSR_AMD64_SNP_IBS_VIRT BIT_ULL(MSR_AMD64_SNP_IBS_VIRT_BIT) +#define MSR_AMD64_SNP_RESERVED_BIT15 BIT_ULL(15) +#define MSR_AMD64_SNP_VMSA_REG_PROT_BIT 16 +#define MSR_AMD64_SNP_VMSA_REG_PROT BIT_ULL(MSR_AMD64_SNP_VMSA_REG_PROT_BIT) +#define MSR_AMD64_SNP_SMT_PROT_BIT 17 +#define MSR_AMD64_SNP_SMT_PROT BIT_ULL(MSR_AMD64_SNP_SMT_PROT_BIT) +#define MSR_AMD64_SNP_RESV_BIT 18 +#define MSR_AMD64_SNP_RESERVED_MASK GENMASK_ULL(63, MSR_AMD64_SNP_RESV_BIT) #define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f +#define MSR_AMD64_RMP_BASE 0xc0010132 +#define MSR_AMD64_RMP_END 0xc0010133 + /* AMD Collaborative Processor Performance Control MSRs */ #define MSR_AMD_CPPC_CAP1 0xc00102b0 #define MSR_AMD_CPPC_ENABLE 0xc00102b1 @@ -719,8 +740,15 @@ #define MSR_K8_TOP_MEM1 0xc001001a #define MSR_K8_TOP_MEM2 0xc001001d #define MSR_AMD64_SYSCFG 0xc0010010 -#define MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT 23 +#define MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT 23 #define MSR_AMD64_SYSCFG_MEM_ENCRYPT BIT_ULL(MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT) +#define MSR_AMD64_SYSCFG_SNP_EN_BIT 24 +#define MSR_AMD64_SYSCFG_SNP_EN BIT_ULL(MSR_AMD64_SYSCFG_SNP_EN_BIT) +#define MSR_AMD64_SYSCFG_SNP_VMPL_EN_BIT 25 +#define MSR_AMD64_SYSCFG_SNP_VMPL_EN BIT_ULL(MSR_AMD64_SYSCFG_SNP_VMPL_EN_BIT) +#define MSR_AMD64_SYSCFG_MFDM_BIT 19 +#define MSR_AMD64_SYSCFG_MFDM BIT_ULL(MSR_AMD64_SYSCFG_MFDM_BIT) + #define MSR_K8_INT_PENDING_MSG 0xc0010055 /* C1E active bits in int pending message */ #define K8_INTP_C1E_ACTIVE_MASK 0x18000000 diff --git a/tools/arch/x86/include/asm/required-features.h b/tools/arch/x86/include/asm/required-features.h index 7ba1726b71c7..e9187ddd3d1f 100644 --- a/tools/arch/x86/include/asm/required-features.h +++ b/tools/arch/x86/include/asm/required-features.h @@ -99,6 +99,7 @@ #define REQUIRED_MASK18 0 #define REQUIRED_MASK19 0 #define REQUIRED_MASK20 0 -#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21) +#define REQUIRED_MASK21 0 +#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22) #endif /* _ASM_X86_REQUIRED_FEATURES_H */ diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index a448d0964fc0..ef11aa4cab42 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -7,6 +7,8 @@ * */ +#include <linux/const.h> +#include <linux/bits.h> #include <linux/types.h> #include <linux/ioctl.h> #include <linux/stddef.h> @@ -40,7 +42,6 @@ #define __KVM_HAVE_IRQ_LINE #define __KVM_HAVE_MSI #define __KVM_HAVE_USER_NMI -#define __KVM_HAVE_GUEST_DEBUG #define __KVM_HAVE_MSIX #define __KVM_HAVE_MCE #define __KVM_HAVE_PIT_STATE2 @@ -49,7 +50,6 @@ #define __KVM_HAVE_DEBUGREGS #define __KVM_HAVE_XSAVE #define __KVM_HAVE_XCRS -#define __KVM_HAVE_READONLY_MEM /* Architectural interrupt line count. */ #define KVM_NR_INTERRUPTS 256 @@ -526,9 +526,301 @@ struct kvm_pmu_event_filter { #define KVM_PMU_EVENT_ALLOW 0 #define KVM_PMU_EVENT_DENY 1 -#define KVM_PMU_EVENT_FLAG_MASKED_EVENTS BIT(0) +#define KVM_PMU_EVENT_FLAG_MASKED_EVENTS _BITUL(0) #define KVM_PMU_EVENT_FLAGS_VALID_MASK (KVM_PMU_EVENT_FLAG_MASKED_EVENTS) +/* for KVM_CAP_MCE */ +struct kvm_x86_mce { + __u64 status; + __u64 addr; + __u64 misc; + __u64 mcg_status; + __u8 bank; + __u8 pad1[7]; + __u64 pad2[3]; +}; + +/* for KVM_CAP_XEN_HVM */ +#define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR (1 << 0) +#define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL (1 << 1) +#define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2) +#define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 3) +#define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL (1 << 4) +#define KVM_XEN_HVM_CONFIG_EVTCHN_SEND (1 << 5) +#define KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG (1 << 6) +#define KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE (1 << 7) +#define KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA (1 << 8) + +struct kvm_xen_hvm_config { + __u32 flags; + __u32 msr; + __u64 blob_addr_32; + __u64 blob_addr_64; + __u8 blob_size_32; + __u8 blob_size_64; + __u8 pad2[30]; +}; + +struct kvm_xen_hvm_attr { + __u16 type; + __u16 pad[3]; + union { + __u8 long_mode; + __u8 vector; + __u8 runstate_update_flag; + union { + __u64 gfn; +#define KVM_XEN_INVALID_GFN ((__u64)-1) + __u64 hva; + } shared_info; + struct { + __u32 send_port; + __u32 type; /* EVTCHNSTAT_ipi / EVTCHNSTAT_interdomain */ + __u32 flags; +#define KVM_XEN_EVTCHN_DEASSIGN (1 << 0) +#define KVM_XEN_EVTCHN_UPDATE (1 << 1) +#define KVM_XEN_EVTCHN_RESET (1 << 2) + /* + * Events sent by the guest are either looped back to + * the guest itself (potentially on a different port#) + * or signalled via an eventfd. + */ + union { + struct { + __u32 port; + __u32 vcpu; + __u32 priority; + } port; + struct { + __u32 port; /* Zero for eventfd */ + __s32 fd; + } eventfd; + __u32 padding[4]; + } deliver; + } evtchn; + __u32 xen_version; + __u64 pad[8]; + } u; +}; + + +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */ +#define KVM_XEN_ATTR_TYPE_LONG_MODE 0x0 +#define KVM_XEN_ATTR_TYPE_SHARED_INFO 0x1 +#define KVM_XEN_ATTR_TYPE_UPCALL_VECTOR 0x2 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ +#define KVM_XEN_ATTR_TYPE_EVTCHN 0x3 +#define KVM_XEN_ATTR_TYPE_XEN_VERSION 0x4 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG */ +#define KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG 0x5 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA */ +#define KVM_XEN_ATTR_TYPE_SHARED_INFO_HVA 0x6 + +struct kvm_xen_vcpu_attr { + __u16 type; + __u16 pad[3]; + union { + __u64 gpa; +#define KVM_XEN_INVALID_GPA ((__u64)-1) + __u64 hva; + __u64 pad[8]; + struct { + __u64 state; + __u64 state_entry_time; + __u64 time_running; + __u64 time_runnable; + __u64 time_blocked; + __u64 time_offline; + } runstate; + __u32 vcpu_id; + struct { + __u32 port; + __u32 priority; + __u64 expires_ns; + } timer; + __u8 vector; + } u; +}; + +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */ +#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO 0x0 +#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO 0x1 +#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR 0x2 +#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT 0x3 +#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA 0x4 +#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST 0x5 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ +#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID 0x6 +#define KVM_XEN_VCPU_ATTR_TYPE_TIMER 0x7 +#define KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR 0x8 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA */ +#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO_HVA 0x9 + +/* Secure Encrypted Virtualization command */ +enum sev_cmd_id { + /* Guest initialization commands */ + KVM_SEV_INIT = 0, + KVM_SEV_ES_INIT, + /* Guest launch commands */ + KVM_SEV_LAUNCH_START, + KVM_SEV_LAUNCH_UPDATE_DATA, + KVM_SEV_LAUNCH_UPDATE_VMSA, + KVM_SEV_LAUNCH_SECRET, + KVM_SEV_LAUNCH_MEASURE, + KVM_SEV_LAUNCH_FINISH, + /* Guest migration commands (outgoing) */ + KVM_SEV_SEND_START, + KVM_SEV_SEND_UPDATE_DATA, + KVM_SEV_SEND_UPDATE_VMSA, + KVM_SEV_SEND_FINISH, + /* Guest migration commands (incoming) */ + KVM_SEV_RECEIVE_START, + KVM_SEV_RECEIVE_UPDATE_DATA, + KVM_SEV_RECEIVE_UPDATE_VMSA, + KVM_SEV_RECEIVE_FINISH, + /* Guest status and debug commands */ + KVM_SEV_GUEST_STATUS, + KVM_SEV_DBG_DECRYPT, + KVM_SEV_DBG_ENCRYPT, + /* Guest certificates commands */ + KVM_SEV_CERT_EXPORT, + /* Attestation report */ + KVM_SEV_GET_ATTESTATION_REPORT, + /* Guest Migration Extension */ + KVM_SEV_SEND_CANCEL, + + KVM_SEV_NR_MAX, +}; + +struct kvm_sev_cmd { + __u32 id; + __u32 pad0; + __u64 data; + __u32 error; + __u32 sev_fd; +}; + +struct kvm_sev_launch_start { + __u32 handle; + __u32 policy; + __u64 dh_uaddr; + __u32 dh_len; + __u32 pad0; + __u64 session_uaddr; + __u32 session_len; + __u32 pad1; +}; + +struct kvm_sev_launch_update_data { + __u64 uaddr; + __u32 len; + __u32 pad0; +}; + + +struct kvm_sev_launch_secret { + __u64 hdr_uaddr; + __u32 hdr_len; + __u32 pad0; + __u64 guest_uaddr; + __u32 guest_len; + __u32 pad1; + __u64 trans_uaddr; + __u32 trans_len; + __u32 pad2; +}; + +struct kvm_sev_launch_measure { + __u64 uaddr; + __u32 len; + __u32 pad0; +}; + +struct kvm_sev_guest_status { + __u32 handle; + __u32 policy; + __u32 state; +}; + +struct kvm_sev_dbg { + __u64 src_uaddr; + __u64 dst_uaddr; + __u32 len; + __u32 pad0; +}; + +struct kvm_sev_attestation_report { + __u8 mnonce[16]; + __u64 uaddr; + __u32 len; + __u32 pad0; +}; + +struct kvm_sev_send_start { + __u32 policy; + __u32 pad0; + __u64 pdh_cert_uaddr; + __u32 pdh_cert_len; + __u32 pad1; + __u64 plat_certs_uaddr; + __u32 plat_certs_len; + __u32 pad2; + __u64 amd_certs_uaddr; + __u32 amd_certs_len; + __u32 pad3; + __u64 session_uaddr; + __u32 session_len; + __u32 pad4; +}; + +struct kvm_sev_send_update_data { + __u64 hdr_uaddr; + __u32 hdr_len; + __u32 pad0; + __u64 guest_uaddr; + __u32 guest_len; + __u32 pad1; + __u64 trans_uaddr; + __u32 trans_len; + __u32 pad2; +}; + +struct kvm_sev_receive_start { + __u32 handle; + __u32 policy; + __u64 pdh_uaddr; + __u32 pdh_len; + __u32 pad0; + __u64 session_uaddr; + __u32 session_len; + __u32 pad1; +}; + +struct kvm_sev_receive_update_data { + __u64 hdr_uaddr; + __u32 hdr_len; + __u32 pad0; + __u64 guest_uaddr; + __u32 guest_len; + __u32 pad1; + __u64 trans_uaddr; + __u32 trans_len; + __u32 pad2; +}; + +#define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0) +#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1) + +struct kvm_hyperv_eventfd { + __u32 conn_id; + __s32 fd; + __u32 flags; + __u32 padding[3]; +}; + +#define KVM_HYPERV_CONN_ID_MASK 0x00ffffff +#define KVM_HYPERV_EVENTFD_DEASSIGN (1 << 0) + /* * Masked event layout. * Bits Description @@ -549,10 +841,10 @@ struct kvm_pmu_event_filter { ((__u64)(!!(exclude)) << 55)) #define KVM_PMU_MASKED_ENTRY_EVENT_SELECT \ - (GENMASK_ULL(7, 0) | GENMASK_ULL(35, 32)) -#define KVM_PMU_MASKED_ENTRY_UMASK_MASK (GENMASK_ULL(63, 56)) -#define KVM_PMU_MASKED_ENTRY_UMASK_MATCH (GENMASK_ULL(15, 8)) -#define KVM_PMU_MASKED_ENTRY_EXCLUDE (BIT_ULL(55)) + (__GENMASK_ULL(7, 0) | __GENMASK_ULL(35, 32)) +#define KVM_PMU_MASKED_ENTRY_UMASK_MASK (__GENMASK_ULL(63, 56)) +#define KVM_PMU_MASKED_ENTRY_UMASK_MATCH (__GENMASK_ULL(15, 8)) +#define KVM_PMU_MASKED_ENTRY_EXCLUDE (_BITULL(55)) #define KVM_PMU_MASKED_ENTRY_UMASK_MASK_SHIFT (56) /* for KVM_{GET,SET,HAS}_DEVICE_ATTR */ @@ -560,7 +852,7 @@ struct kvm_pmu_event_filter { #define KVM_VCPU_TSC_OFFSET 0 /* attribute for the TSC offset */ /* x86-specific KVM_EXIT_HYPERCALL flags. */ -#define KVM_EXIT_HYPERCALL_LONG_MODE BIT(0) +#define KVM_EXIT_HYPERCALL_LONG_MODE _BITULL(0) #define KVM_X86_DEFAULT_VM 0 #define KVM_X86_SW_PROTECTED_VM 1 diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c index 318e2dad27e0..ae57bf69ad4a 100644 --- a/tools/hv/hv_kvp_daemon.c +++ b/tools/hv/hv_kvp_daemon.c @@ -76,6 +76,12 @@ enum { DNS }; +enum { + IPV4 = 1, + IPV6, + IP_TYPE_MAX +}; + static int in_hand_shake; static char *os_name = ""; @@ -102,6 +108,11 @@ static struct utsname uts_buf; #define MAX_FILE_NAME 100 #define ENTRIES_PER_BLOCK 50 +/* + * Change this entry if the number of addresses increases in future + */ +#define MAX_IP_ENTRIES 64 +#define OUTSTR_BUF_SIZE ((INET6_ADDRSTRLEN + 1) * MAX_IP_ENTRIES) struct kvp_record { char key[HV_KVP_EXCHANGE_MAX_KEY_SIZE]; @@ -1171,6 +1182,18 @@ static int process_ip_string(FILE *f, char *ip_string, int type) return 0; } +int ip_version_check(const char *input_addr) +{ + struct in6_addr addr; + + if (inet_pton(AF_INET, input_addr, &addr)) + return IPV4; + else if (inet_pton(AF_INET6, input_addr, &addr)) + return IPV6; + + return -EINVAL; +} + /* * Only IPv4 subnet strings needs to be converted to plen * For IPv6 the subnet is already privided in plen format @@ -1197,14 +1220,75 @@ static int kvp_subnet_to_plen(char *subnet_addr_str) return plen; } +static int process_dns_gateway_nm(FILE *f, char *ip_string, int type, + int ip_sec) +{ + char addr[INET6_ADDRSTRLEN], *output_str; + int ip_offset = 0, error = 0, ip_ver; + char *param_name; + + if (type == DNS) + param_name = "dns"; + else if (type == GATEWAY) + param_name = "gateway"; + else + return -EINVAL; + + output_str = (char *)calloc(OUTSTR_BUF_SIZE, sizeof(char)); + if (!output_str) + return -ENOMEM; + + while (1) { + memset(addr, 0, sizeof(addr)); + + if (!parse_ip_val_buffer(ip_string, &ip_offset, addr, + (MAX_IP_ADDR_SIZE * 2))) + break; + + ip_ver = ip_version_check(addr); + if (ip_ver < 0) + continue; + + if ((ip_ver == IPV4 && ip_sec == IPV4) || + (ip_ver == IPV6 && ip_sec == IPV6)) { + /* + * do a bound check to avoid out-of bound writes + */ + if ((OUTSTR_BUF_SIZE - strlen(output_str)) > + (strlen(addr) + 1)) { + strncat(output_str, addr, + OUTSTR_BUF_SIZE - + strlen(output_str) - 1); + strncat(output_str, ",", + OUTSTR_BUF_SIZE - + strlen(output_str) - 1); + } + } else { + continue; + } + } + + if (strlen(output_str)) { + /* + * This is to get rid of that extra comma character + * in the end of the string + */ + output_str[strlen(output_str) - 1] = '\0'; + error = fprintf(f, "%s=%s\n", param_name, output_str); + } + + free(output_str); + return error; +} + static int process_ip_string_nm(FILE *f, char *ip_string, char *subnet, - int is_ipv6) + int ip_sec) { char addr[INET6_ADDRSTRLEN]; char subnet_addr[INET6_ADDRSTRLEN]; - int error, i = 0; + int error = 0, i = 0; int ip_offset = 0, subnet_offset = 0; - int plen; + int plen, ip_ver; memset(addr, 0, sizeof(addr)); memset(subnet_addr, 0, sizeof(subnet_addr)); @@ -1216,10 +1300,16 @@ static int process_ip_string_nm(FILE *f, char *ip_string, char *subnet, subnet_addr, (MAX_IP_ADDR_SIZE * 2))) { - if (!is_ipv6) + ip_ver = ip_version_check(addr); + if (ip_ver < 0) + continue; + + if (ip_ver == IPV4 && ip_sec == IPV4) plen = kvp_subnet_to_plen((char *)subnet_addr); - else + else if (ip_ver == IPV6 && ip_sec == IPV6) plen = atoi(subnet_addr); + else + continue; if (plen < 0) return plen; @@ -1233,17 +1323,16 @@ static int process_ip_string_nm(FILE *f, char *ip_string, char *subnet, memset(subnet_addr, 0, sizeof(subnet_addr)); } - return 0; + return error; } static int kvp_set_ip_info(char *if_name, struct hv_kvp_ipaddr_value *new_val) { - int error = 0; + int error = 0, ip_ver; char if_filename[PATH_MAX]; char nm_filename[PATH_MAX]; FILE *ifcfg_file, *nmfile; char cmd[PATH_MAX]; - int is_ipv6 = 0; char *mac_addr; int str_len; @@ -1421,52 +1510,94 @@ static int kvp_set_ip_info(char *if_name, struct hv_kvp_ipaddr_value *new_val) if (error) goto setval_error; - if (new_val->addr_family & ADDR_FAMILY_IPV6) { - error = fprintf(nmfile, "\n[ipv6]\n"); - if (error < 0) - goto setval_error; - is_ipv6 = 1; - } else { - error = fprintf(nmfile, "\n[ipv4]\n"); - if (error < 0) - goto setval_error; - } - /* * Now we populate the keyfile format + * + * The keyfile format expects the IPv6 and IPv4 configuration in + * different sections. Therefore we iterate through the list twice, + * once to populate the IPv4 section and the next time for IPv6 */ + ip_ver = IPV4; + do { + if (ip_ver == IPV4) { + error = fprintf(nmfile, "\n[ipv4]\n"); + if (error < 0) + goto setval_error; + } else { + error = fprintf(nmfile, "\n[ipv6]\n"); + if (error < 0) + goto setval_error; + } - if (new_val->dhcp_enabled) { - error = kvp_write_file(nmfile, "method", "", "auto"); - if (error < 0) - goto setval_error; - } else { - error = kvp_write_file(nmfile, "method", "", "manual"); + /* + * Write the configuration for ipaddress, netmask, gateway and + * name services + */ + error = process_ip_string_nm(nmfile, (char *)new_val->ip_addr, + (char *)new_val->sub_net, + ip_ver); if (error < 0) goto setval_error; - } - /* - * Write the configuration for ipaddress, netmask, gateway and - * name services - */ - error = process_ip_string_nm(nmfile, (char *)new_val->ip_addr, - (char *)new_val->sub_net, is_ipv6); - if (error < 0) - goto setval_error; + /* + * As dhcp_enabled is only valid for ipv4, we do not set dhcp + * methods for ipv6 based on dhcp_enabled flag. + * + * For ipv4, set method to manual only when dhcp_enabled is + * false and specific ipv4 addresses are configured. If neither + * dhcp_enabled is true and no ipv4 addresses are configured, + * set method to 'disabled'. + * + * For ipv6, set method to manual when we configure ipv6 + * addresses. Otherwise set method to 'auto' so that SLAAC from + * RA may be used. + */ + if (ip_ver == IPV4) { + if (new_val->dhcp_enabled) { + error = kvp_write_file(nmfile, "method", "", + "auto"); + if (error < 0) + goto setval_error; + } else if (error) { + error = kvp_write_file(nmfile, "method", "", + "manual"); + if (error < 0) + goto setval_error; + } else { + error = kvp_write_file(nmfile, "method", "", + "disabled"); + if (error < 0) + goto setval_error; + } + } else if (ip_ver == IPV6) { + if (error) { + error = kvp_write_file(nmfile, "method", "", + "manual"); + if (error < 0) + goto setval_error; + } else { + error = kvp_write_file(nmfile, "method", "", + "auto"); + if (error < 0) + goto setval_error; + } + } - /* we do not want ipv4 addresses in ipv6 section and vice versa */ - if (is_ipv6 != is_ipv4((char *)new_val->gate_way)) { - error = fprintf(nmfile, "gateway=%s\n", (char *)new_val->gate_way); + error = process_dns_gateway_nm(nmfile, + (char *)new_val->gate_way, + GATEWAY, ip_ver); if (error < 0) goto setval_error; - } - if (is_ipv6 != is_ipv4((char *)new_val->dns_addr)) { - error = fprintf(nmfile, "dns=%s\n", (char *)new_val->dns_addr); + error = process_dns_gateway_nm(nmfile, + (char *)new_val->dns_addr, DNS, + ip_ver); if (error < 0) goto setval_error; - } + + ip_ver++; + } while (ip_ver < IP_TYPE_MAX); + fclose(nmfile); fclose(ifcfg_file); diff --git a/tools/include/asm-generic/bitops/__fls.h b/tools/include/asm-generic/bitops/__fls.h index 03f721a8a2b1..54ccccf96e21 100644 --- a/tools/include/asm-generic/bitops/__fls.h +++ b/tools/include/asm-generic/bitops/__fls.h @@ -5,12 +5,12 @@ #include <asm/types.h> /** - * __fls - find last (most-significant) set bit in a long word + * generic___fls - find last (most-significant) set bit in a long word * @word: the word to search * * Undefined if no set bit exists, so code should check against 0 first. */ -static __always_inline unsigned long __fls(unsigned long word) +static __always_inline unsigned long generic___fls(unsigned long word) { int num = BITS_PER_LONG - 1; @@ -41,4 +41,8 @@ static __always_inline unsigned long __fls(unsigned long word) return num; } +#ifndef __HAVE_ARCH___FLS +#define __fls(word) generic___fls(word) +#endif + #endif /* _ASM_GENERIC_BITOPS___FLS_H_ */ diff --git a/tools/include/asm-generic/bitops/fls.h b/tools/include/asm-generic/bitops/fls.h index b168bb10e1be..26f3ce1dd6e4 100644 --- a/tools/include/asm-generic/bitops/fls.h +++ b/tools/include/asm-generic/bitops/fls.h @@ -3,14 +3,14 @@ #define _ASM_GENERIC_BITOPS_FLS_H_ /** - * fls - find last (most-significant) bit set + * generic_fls - find last (most-significant) bit set * @x: the word to search * * This is defined the same way as ffs. * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32. */ -static __always_inline int fls(unsigned int x) +static __always_inline int generic_fls(unsigned int x) { int r = 32; @@ -39,4 +39,8 @@ static __always_inline int fls(unsigned int x) return r; } +#ifndef __HAVE_ARCH_FLS +#define fls(x) generic_fls(x) +#endif + #endif /* _ASM_GENERIC_BITOPS_FLS_H_ */ diff --git a/tools/include/linux/btf_ids.h b/tools/include/linux/btf_ids.h index 72535f00572f..72ea363d434d 100644 --- a/tools/include/linux/btf_ids.h +++ b/tools/include/linux/btf_ids.h @@ -3,6 +3,8 @@ #ifndef _LINUX_BTF_IDS_H #define _LINUX_BTF_IDS_H +#include <linux/types.h> /* for u32 */ + struct btf_id_set { u32 cnt; u32 ids[]; diff --git a/tools/include/linux/kernel.h b/tools/include/linux/kernel.h index 4b0673bf52c2..07cfad817d53 100644 --- a/tools/include/linux/kernel.h +++ b/tools/include/linux/kernel.h @@ -8,6 +8,7 @@ #include <linux/build_bug.h> #include <linux/compiler.h> #include <linux/math.h> +#include <linux/panic.h> #include <endian.h> #include <byteswap.h> diff --git a/tools/include/linux/mm.h b/tools/include/linux/mm.h index f3c82ab5b14c..7d73da098047 100644 --- a/tools/include/linux/mm.h +++ b/tools/include/linux/mm.h @@ -37,4 +37,9 @@ static inline void totalram_pages_add(long count) { } +static inline int early_pfn_to_nid(unsigned long pfn) +{ + return 0; +} + #endif diff --git a/tools/include/linux/panic.h b/tools/include/linux/panic.h new file mode 100644 index 000000000000..9c8f17a41ce8 --- /dev/null +++ b/tools/include/linux/panic.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _TOOLS_LINUX_PANIC_H +#define _TOOLS_LINUX_PANIC_H + +#include <stdarg.h> +#include <stdio.h> +#include <stdlib.h> + +static inline void panic(const char *fmt, ...) +{ + va_list argp; + + va_start(argp, fmt); + vfprintf(stderr, fmt, argp); + va_end(argp); + exit(-1); +} + +#endif diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index fd4f9574d177..2ee338860b7e 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -3013,6 +3013,7 @@ struct drm_i915_query_item { * - %DRM_I915_QUERY_MEMORY_REGIONS (see struct drm_i915_query_memory_regions) * - %DRM_I915_QUERY_HWCONFIG_BLOB (see `GuC HWCONFIG blob uAPI`) * - %DRM_I915_QUERY_GEOMETRY_SUBSLICES (see struct drm_i915_query_topology_info) + * - %DRM_I915_QUERY_GUC_SUBMISSION_VERSION (see struct drm_i915_query_guc_submission_version) */ __u64 query_id; #define DRM_I915_QUERY_TOPOLOGY_INFO 1 @@ -3021,6 +3022,7 @@ struct drm_i915_query_item { #define DRM_I915_QUERY_MEMORY_REGIONS 4 #define DRM_I915_QUERY_HWCONFIG_BLOB 5 #define DRM_I915_QUERY_GEOMETRY_SUBSLICES 6 +#define DRM_I915_QUERY_GUC_SUBMISSION_VERSION 7 /* Must be kept compact -- no holes and well documented */ /** @@ -3567,6 +3569,20 @@ struct drm_i915_query_memory_regions { }; /** + * struct drm_i915_query_guc_submission_version - query GuC submission interface version + */ +struct drm_i915_query_guc_submission_version { + /** @branch: Firmware branch version. */ + __u32 branch; + /** @major: Firmware major version. */ + __u32 major; + /** @minor: Firmware minor version. */ + __u32 minor; + /** @patch: Firmware patch version. */ + __u32 patch; +}; + +/** * DOC: GuC HWCONFIG blob uAPI * * The GuC produces a blob with information about the current device. diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h index 48ad69f7722e..45e4e64fd664 100644 --- a/tools/include/uapi/linux/fs.h +++ b/tools/include/uapi/linux/fs.h @@ -64,6 +64,24 @@ struct fstrim_range { __u64 minlen; }; +/* + * We include a length field because some filesystems (vfat) have an identifier + * that we do want to expose as a UUID, but doesn't have the standard length. + * + * We use a fixed size buffer beacuse this interface will, by fiat, never + * support "UUIDs" longer than 16 bytes; we don't want to force all downstream + * users to have to deal with that. + */ +struct fsuuid2 { + __u8 len; + __u8 uuid[16]; +}; + +struct fs_sysfs_path { + __u8 len; + __u8 name[128]; +}; + /* extent-same (dedupe) ioctls; these MUST match the btrfs ioctl definitions */ #define FILE_DEDUPE_RANGE_SAME 0 #define FILE_DEDUPE_RANGE_DIFFERS 1 @@ -215,6 +233,13 @@ struct fsxattr { #define FS_IOC_FSSETXATTR _IOW('X', 32, struct fsxattr) #define FS_IOC_GETFSLABEL _IOR(0x94, 49, char[FSLABEL_MAX]) #define FS_IOC_SETFSLABEL _IOW(0x94, 50, char[FSLABEL_MAX]) +/* Returns the external filesystem UUID, the same one blkid returns */ +#define FS_IOC_GETFSUUID _IOR(0x15, 0, struct fsuuid2) +/* + * Returns the path component under /sys/fs/ that refers to this filesystem; + * also /sys/kernel/debug/ for filesystems with debugfs exports + */ +#define FS_IOC_GETFSSYSFSPATH _IOR(0x15, 1, struct fs_sysfs_path) /* * Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS) @@ -301,9 +326,12 @@ typedef int __bitwise __kernel_rwf_t; /* per-IO O_APPEND */ #define RWF_APPEND ((__force __kernel_rwf_t)0x00000010) +/* per-IO negation of O_APPEND */ +#define RWF_NOAPPEND ((__force __kernel_rwf_t)0x00000020) + /* mask of flags supported by the kernel */ #define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\ - RWF_APPEND) + RWF_APPEND | RWF_NOAPPEND) /* Pagemap ioctl */ #define PAGEMAP_SCAN _IOWR('f', 16, struct pm_scan_arg) diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index c3308536482b..2190adbe3002 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -16,6 +16,11 @@ #define KVM_API_VERSION 12 +/* + * Backwards-compatible definitions. + */ +#define __KVM_HAVE_GUEST_DEBUG + /* for KVM_SET_USER_MEMORY_REGION */ struct kvm_userspace_memory_region { __u32 slot; @@ -85,43 +90,6 @@ struct kvm_pit_config { #define KVM_PIT_SPEAKER_DUMMY 1 -struct kvm_s390_skeys { - __u64 start_gfn; - __u64 count; - __u64 skeydata_addr; - __u32 flags; - __u32 reserved[9]; -}; - -#define KVM_S390_CMMA_PEEK (1 << 0) - -/** - * kvm_s390_cmma_log - Used for CMMA migration. - * - * Used both for input and output. - * - * @start_gfn: Guest page number to start from. - * @count: Size of the result buffer. - * @flags: Control operation mode via KVM_S390_CMMA_* flags - * @remaining: Used with KVM_S390_GET_CMMA_BITS. Indicates how many dirty - * pages are still remaining. - * @mask: Used with KVM_S390_SET_CMMA_BITS. Bitmap of bits to actually set - * in the PGSTE. - * @values: Pointer to the values buffer. - * - * Used in KVM_S390_{G,S}ET_CMMA_BITS ioctls. - */ -struct kvm_s390_cmma_log { - __u64 start_gfn; - __u32 count; - __u32 flags; - union { - __u64 remaining; - __u64 mask; - }; - __u64 values; -}; - struct kvm_hyperv_exit { #define KVM_EXIT_HYPERV_SYNIC 1 #define KVM_EXIT_HYPERV_HCALL 2 @@ -315,11 +283,6 @@ struct kvm_run { __u32 ipb; } s390_sieic; /* KVM_EXIT_S390_RESET */ -#define KVM_S390_RESET_POR 1 -#define KVM_S390_RESET_CLEAR 2 -#define KVM_S390_RESET_SUBSYSTEM 4 -#define KVM_S390_RESET_CPU_INIT 8 -#define KVM_S390_RESET_IPL 16 __u64 s390_reset_flags; /* KVM_EXIT_S390_UCONTROL */ struct { @@ -536,43 +499,6 @@ struct kvm_translation { __u8 pad[5]; }; -/* for KVM_S390_MEM_OP */ -struct kvm_s390_mem_op { - /* in */ - __u64 gaddr; /* the guest address */ - __u64 flags; /* flags */ - __u32 size; /* amount of bytes */ - __u32 op; /* type of operation */ - __u64 buf; /* buffer in userspace */ - union { - struct { - __u8 ar; /* the access register number */ - __u8 key; /* access key, ignored if flag unset */ - __u8 pad1[6]; /* ignored */ - __u64 old_addr; /* ignored if cmpxchg flag unset */ - }; - __u32 sida_offset; /* offset into the sida */ - __u8 reserved[32]; /* ignored */ - }; -}; -/* types for kvm_s390_mem_op->op */ -#define KVM_S390_MEMOP_LOGICAL_READ 0 -#define KVM_S390_MEMOP_LOGICAL_WRITE 1 -#define KVM_S390_MEMOP_SIDA_READ 2 -#define KVM_S390_MEMOP_SIDA_WRITE 3 -#define KVM_S390_MEMOP_ABSOLUTE_READ 4 -#define KVM_S390_MEMOP_ABSOLUTE_WRITE 5 -#define KVM_S390_MEMOP_ABSOLUTE_CMPXCHG 6 - -/* flags for kvm_s390_mem_op->flags */ -#define KVM_S390_MEMOP_F_CHECK_ONLY (1ULL << 0) -#define KVM_S390_MEMOP_F_INJECT_EXCEPTION (1ULL << 1) -#define KVM_S390_MEMOP_F_SKEY_PROTECTION (1ULL << 2) - -/* flags specifying extension support via KVM_CAP_S390_MEM_OP_EXTENSION */ -#define KVM_S390_MEMOP_EXTENSION_CAP_BASE (1 << 0) -#define KVM_S390_MEMOP_EXTENSION_CAP_CMPXCHG (1 << 1) - /* for KVM_INTERRUPT */ struct kvm_interrupt { /* in */ @@ -637,124 +563,6 @@ struct kvm_mp_state { __u32 mp_state; }; -struct kvm_s390_psw { - __u64 mask; - __u64 addr; -}; - -/* valid values for type in kvm_s390_interrupt */ -#define KVM_S390_SIGP_STOP 0xfffe0000u -#define KVM_S390_PROGRAM_INT 0xfffe0001u -#define KVM_S390_SIGP_SET_PREFIX 0xfffe0002u -#define KVM_S390_RESTART 0xfffe0003u -#define KVM_S390_INT_PFAULT_INIT 0xfffe0004u -#define KVM_S390_INT_PFAULT_DONE 0xfffe0005u -#define KVM_S390_MCHK 0xfffe1000u -#define KVM_S390_INT_CLOCK_COMP 0xffff1004u -#define KVM_S390_INT_CPU_TIMER 0xffff1005u -#define KVM_S390_INT_VIRTIO 0xffff2603u -#define KVM_S390_INT_SERVICE 0xffff2401u -#define KVM_S390_INT_EMERGENCY 0xffff1201u -#define KVM_S390_INT_EXTERNAL_CALL 0xffff1202u -/* Anything below 0xfffe0000u is taken by INT_IO */ -#define KVM_S390_INT_IO(ai,cssid,ssid,schid) \ - (((schid)) | \ - ((ssid) << 16) | \ - ((cssid) << 18) | \ - ((ai) << 26)) -#define KVM_S390_INT_IO_MIN 0x00000000u -#define KVM_S390_INT_IO_MAX 0xfffdffffu -#define KVM_S390_INT_IO_AI_MASK 0x04000000u - - -struct kvm_s390_interrupt { - __u32 type; - __u32 parm; - __u64 parm64; -}; - -struct kvm_s390_io_info { - __u16 subchannel_id; - __u16 subchannel_nr; - __u32 io_int_parm; - __u32 io_int_word; -}; - -struct kvm_s390_ext_info { - __u32 ext_params; - __u32 pad; - __u64 ext_params2; -}; - -struct kvm_s390_pgm_info { - __u64 trans_exc_code; - __u64 mon_code; - __u64 per_address; - __u32 data_exc_code; - __u16 code; - __u16 mon_class_nr; - __u8 per_code; - __u8 per_atmid; - __u8 exc_access_id; - __u8 per_access_id; - __u8 op_access_id; -#define KVM_S390_PGM_FLAGS_ILC_VALID 0x01 -#define KVM_S390_PGM_FLAGS_ILC_0 0x02 -#define KVM_S390_PGM_FLAGS_ILC_1 0x04 -#define KVM_S390_PGM_FLAGS_ILC_MASK 0x06 -#define KVM_S390_PGM_FLAGS_NO_REWIND 0x08 - __u8 flags; - __u8 pad[2]; -}; - -struct kvm_s390_prefix_info { - __u32 address; -}; - -struct kvm_s390_extcall_info { - __u16 code; -}; - -struct kvm_s390_emerg_info { - __u16 code; -}; - -#define KVM_S390_STOP_FLAG_STORE_STATUS 0x01 -struct kvm_s390_stop_info { - __u32 flags; -}; - -struct kvm_s390_mchk_info { - __u64 cr14; - __u64 mcic; - __u64 failing_storage_address; - __u32 ext_damage_code; - __u32 pad; - __u8 fixed_logout[16]; -}; - -struct kvm_s390_irq { - __u64 type; - union { - struct kvm_s390_io_info io; - struct kvm_s390_ext_info ext; - struct kvm_s390_pgm_info pgm; - struct kvm_s390_emerg_info emerg; - struct kvm_s390_extcall_info extcall; - struct kvm_s390_prefix_info prefix; - struct kvm_s390_stop_info stop; - struct kvm_s390_mchk_info mchk; - char reserved[64]; - } u; -}; - -struct kvm_s390_irq_state { - __u64 buf; - __u32 flags; /* will stay unused for compatibility reasons */ - __u32 len; - __u32 reserved[4]; /* will stay unused for compatibility reasons */ -}; - /* for KVM_SET_GUEST_DEBUG */ #define KVM_GUESTDBG_ENABLE 0x00000001 @@ -810,50 +618,6 @@ struct kvm_enable_cap { __u8 pad[64]; }; -/* for KVM_PPC_GET_PVINFO */ - -#define KVM_PPC_PVINFO_FLAGS_EV_IDLE (1<<0) - -struct kvm_ppc_pvinfo { - /* out */ - __u32 flags; - __u32 hcall[4]; - __u8 pad[108]; -}; - -/* for KVM_PPC_GET_SMMU_INFO */ -#define KVM_PPC_PAGE_SIZES_MAX_SZ 8 - -struct kvm_ppc_one_page_size { - __u32 page_shift; /* Page shift (or 0) */ - __u32 pte_enc; /* Encoding in the HPTE (>>12) */ -}; - -struct kvm_ppc_one_seg_page_size { - __u32 page_shift; /* Base page shift of segment (or 0) */ - __u32 slb_enc; /* SLB encoding for BookS */ - struct kvm_ppc_one_page_size enc[KVM_PPC_PAGE_SIZES_MAX_SZ]; -}; - -#define KVM_PPC_PAGE_SIZES_REAL 0x00000001 -#define KVM_PPC_1T_SEGMENTS 0x00000002 -#define KVM_PPC_NO_HASH 0x00000004 - -struct kvm_ppc_smmu_info { - __u64 flags; - __u32 slb_size; - __u16 data_keys; /* # storage keys supported for data */ - __u16 instr_keys; /* # storage keys supported for instructions */ - struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ]; -}; - -/* for KVM_PPC_RESIZE_HPT_{PREPARE,COMMIT} */ -struct kvm_ppc_resize_hpt { - __u64 flags; - __u32 shift; - __u32 pad; -}; - #define KVMIO 0xAE /* machine type bits, to be used as argument to KVM_CREATE_VM */ @@ -923,9 +687,7 @@ struct kvm_ppc_resize_hpt { /* Bug in KVM_SET_USER_MEMORY_REGION fixed: */ #define KVM_CAP_DESTROY_MEMORY_REGION_WORKS 21 #define KVM_CAP_USER_NMI 22 -#ifdef __KVM_HAVE_GUEST_DEBUG #define KVM_CAP_SET_GUEST_DEBUG 23 -#endif #ifdef __KVM_HAVE_PIT #define KVM_CAP_REINJECT_CONTROL 24 #endif @@ -1156,8 +918,6 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_GUEST_MEMFD 234 #define KVM_CAP_VM_TYPES 235 -#ifdef KVM_CAP_IRQ_ROUTING - struct kvm_irq_routing_irqchip { __u32 irqchip; __u32 pin; @@ -1222,42 +982,6 @@ struct kvm_irq_routing { struct kvm_irq_routing_entry entries[]; }; -#endif - -#ifdef KVM_CAP_MCE -/* x86 MCE */ -struct kvm_x86_mce { - __u64 status; - __u64 addr; - __u64 misc; - __u64 mcg_status; - __u8 bank; - __u8 pad1[7]; - __u64 pad2[3]; -}; -#endif - -#ifdef KVM_CAP_XEN_HVM -#define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR (1 << 0) -#define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL (1 << 1) -#define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2) -#define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 3) -#define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL (1 << 4) -#define KVM_XEN_HVM_CONFIG_EVTCHN_SEND (1 << 5) -#define KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG (1 << 6) -#define KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE (1 << 7) - -struct kvm_xen_hvm_config { - __u32 flags; - __u32 msr; - __u64 blob_addr_32; - __u64 blob_addr_64; - __u8 blob_size_32; - __u8 blob_size_64; - __u8 pad2[30]; -}; -#endif - #define KVM_IRQFD_FLAG_DEASSIGN (1 << 0) /* * Available with KVM_CAP_IRQFD_RESAMPLE @@ -1442,11 +1166,6 @@ struct kvm_vfio_spapr_tce { struct kvm_userspace_memory_region2) /* enable ucontrol for s390 */ -struct kvm_s390_ucas_mapping { - __u64 user_addr; - __u64 vcpu_addr; - __u64 length; -}; #define KVM_S390_UCAS_MAP _IOW(KVMIO, 0x50, struct kvm_s390_ucas_mapping) #define KVM_S390_UCAS_UNMAP _IOW(KVMIO, 0x51, struct kvm_s390_ucas_mapping) #define KVM_S390_VCPU_FAULT _IOW(KVMIO, 0x52, unsigned long) @@ -1641,89 +1360,6 @@ struct kvm_enc_region { #define KVM_S390_NORMAL_RESET _IO(KVMIO, 0xc3) #define KVM_S390_CLEAR_RESET _IO(KVMIO, 0xc4) -struct kvm_s390_pv_sec_parm { - __u64 origin; - __u64 length; -}; - -struct kvm_s390_pv_unp { - __u64 addr; - __u64 size; - __u64 tweak; -}; - -enum pv_cmd_dmp_id { - KVM_PV_DUMP_INIT, - KVM_PV_DUMP_CONFIG_STOR_STATE, - KVM_PV_DUMP_COMPLETE, - KVM_PV_DUMP_CPU, -}; - -struct kvm_s390_pv_dmp { - __u64 subcmd; - __u64 buff_addr; - __u64 buff_len; - __u64 gaddr; /* For dump storage state */ - __u64 reserved[4]; -}; - -enum pv_cmd_info_id { - KVM_PV_INFO_VM, - KVM_PV_INFO_DUMP, -}; - -struct kvm_s390_pv_info_dump { - __u64 dump_cpu_buffer_len; - __u64 dump_config_mem_buffer_per_1m; - __u64 dump_config_finalize_len; -}; - -struct kvm_s390_pv_info_vm { - __u64 inst_calls_list[4]; - __u64 max_cpus; - __u64 max_guests; - __u64 max_guest_addr; - __u64 feature_indication; -}; - -struct kvm_s390_pv_info_header { - __u32 id; - __u32 len_max; - __u32 len_written; - __u32 reserved; -}; - -struct kvm_s390_pv_info { - struct kvm_s390_pv_info_header header; - union { - struct kvm_s390_pv_info_dump dump; - struct kvm_s390_pv_info_vm vm; - }; -}; - -enum pv_cmd_id { - KVM_PV_ENABLE, - KVM_PV_DISABLE, - KVM_PV_SET_SEC_PARMS, - KVM_PV_UNPACK, - KVM_PV_VERIFY, - KVM_PV_PREP_RESET, - KVM_PV_UNSHARE_ALL, - KVM_PV_INFO, - KVM_PV_DUMP, - KVM_PV_ASYNC_CLEANUP_PREPARE, - KVM_PV_ASYNC_CLEANUP_PERFORM, -}; - -struct kvm_pv_cmd { - __u32 cmd; /* Command to be executed */ - __u16 rc; /* Ultravisor return code */ - __u16 rrc; /* Ultravisor return reason code */ - __u64 data; /* Data or address */ - __u32 flags; /* flags for future extensions. Must be 0 for now */ - __u32 reserved[3]; -}; - /* Available with KVM_CAP_S390_PROTECTED */ #define KVM_S390_PV_COMMAND _IOWR(KVMIO, 0xc5, struct kvm_pv_cmd) @@ -1737,58 +1373,6 @@ struct kvm_pv_cmd { #define KVM_XEN_HVM_GET_ATTR _IOWR(KVMIO, 0xc8, struct kvm_xen_hvm_attr) #define KVM_XEN_HVM_SET_ATTR _IOW(KVMIO, 0xc9, struct kvm_xen_hvm_attr) -struct kvm_xen_hvm_attr { - __u16 type; - __u16 pad[3]; - union { - __u8 long_mode; - __u8 vector; - __u8 runstate_update_flag; - struct { - __u64 gfn; -#define KVM_XEN_INVALID_GFN ((__u64)-1) - } shared_info; - struct { - __u32 send_port; - __u32 type; /* EVTCHNSTAT_ipi / EVTCHNSTAT_interdomain */ - __u32 flags; -#define KVM_XEN_EVTCHN_DEASSIGN (1 << 0) -#define KVM_XEN_EVTCHN_UPDATE (1 << 1) -#define KVM_XEN_EVTCHN_RESET (1 << 2) - /* - * Events sent by the guest are either looped back to - * the guest itself (potentially on a different port#) - * or signalled via an eventfd. - */ - union { - struct { - __u32 port; - __u32 vcpu; - __u32 priority; - } port; - struct { - __u32 port; /* Zero for eventfd */ - __s32 fd; - } eventfd; - __u32 padding[4]; - } deliver; - } evtchn; - __u32 xen_version; - __u64 pad[8]; - } u; -}; - - -/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */ -#define KVM_XEN_ATTR_TYPE_LONG_MODE 0x0 -#define KVM_XEN_ATTR_TYPE_SHARED_INFO 0x1 -#define KVM_XEN_ATTR_TYPE_UPCALL_VECTOR 0x2 -/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ -#define KVM_XEN_ATTR_TYPE_EVTCHN 0x3 -#define KVM_XEN_ATTR_TYPE_XEN_VERSION 0x4 -/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG */ -#define KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG 0x5 - /* Per-vCPU Xen attributes */ #define KVM_XEN_VCPU_GET_ATTR _IOWR(KVMIO, 0xca, struct kvm_xen_vcpu_attr) #define KVM_XEN_VCPU_SET_ATTR _IOW(KVMIO, 0xcb, struct kvm_xen_vcpu_attr) @@ -1799,242 +1383,6 @@ struct kvm_xen_hvm_attr { #define KVM_GET_SREGS2 _IOR(KVMIO, 0xcc, struct kvm_sregs2) #define KVM_SET_SREGS2 _IOW(KVMIO, 0xcd, struct kvm_sregs2) -struct kvm_xen_vcpu_attr { - __u16 type; - __u16 pad[3]; - union { - __u64 gpa; -#define KVM_XEN_INVALID_GPA ((__u64)-1) - __u64 pad[8]; - struct { - __u64 state; - __u64 state_entry_time; - __u64 time_running; - __u64 time_runnable; - __u64 time_blocked; - __u64 time_offline; - } runstate; - __u32 vcpu_id; - struct { - __u32 port; - __u32 priority; - __u64 expires_ns; - } timer; - __u8 vector; - } u; -}; - -/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */ -#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO 0x0 -#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO 0x1 -#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR 0x2 -#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT 0x3 -#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA 0x4 -#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST 0x5 -/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ -#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID 0x6 -#define KVM_XEN_VCPU_ATTR_TYPE_TIMER 0x7 -#define KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR 0x8 - -/* Secure Encrypted Virtualization command */ -enum sev_cmd_id { - /* Guest initialization commands */ - KVM_SEV_INIT = 0, - KVM_SEV_ES_INIT, - /* Guest launch commands */ - KVM_SEV_LAUNCH_START, - KVM_SEV_LAUNCH_UPDATE_DATA, - KVM_SEV_LAUNCH_UPDATE_VMSA, - KVM_SEV_LAUNCH_SECRET, - KVM_SEV_LAUNCH_MEASURE, - KVM_SEV_LAUNCH_FINISH, - /* Guest migration commands (outgoing) */ - KVM_SEV_SEND_START, - KVM_SEV_SEND_UPDATE_DATA, - KVM_SEV_SEND_UPDATE_VMSA, - KVM_SEV_SEND_FINISH, - /* Guest migration commands (incoming) */ - KVM_SEV_RECEIVE_START, - KVM_SEV_RECEIVE_UPDATE_DATA, - KVM_SEV_RECEIVE_UPDATE_VMSA, - KVM_SEV_RECEIVE_FINISH, - /* Guest status and debug commands */ - KVM_SEV_GUEST_STATUS, - KVM_SEV_DBG_DECRYPT, - KVM_SEV_DBG_ENCRYPT, - /* Guest certificates commands */ - KVM_SEV_CERT_EXPORT, - /* Attestation report */ - KVM_SEV_GET_ATTESTATION_REPORT, - /* Guest Migration Extension */ - KVM_SEV_SEND_CANCEL, - - KVM_SEV_NR_MAX, -}; - -struct kvm_sev_cmd { - __u32 id; - __u64 data; - __u32 error; - __u32 sev_fd; -}; - -struct kvm_sev_launch_start { - __u32 handle; - __u32 policy; - __u64 dh_uaddr; - __u32 dh_len; - __u64 session_uaddr; - __u32 session_len; -}; - -struct kvm_sev_launch_update_data { - __u64 uaddr; - __u32 len; -}; - - -struct kvm_sev_launch_secret { - __u64 hdr_uaddr; - __u32 hdr_len; - __u64 guest_uaddr; - __u32 guest_len; - __u64 trans_uaddr; - __u32 trans_len; -}; - -struct kvm_sev_launch_measure { - __u64 uaddr; - __u32 len; -}; - -struct kvm_sev_guest_status { - __u32 handle; - __u32 policy; - __u32 state; -}; - -struct kvm_sev_dbg { - __u64 src_uaddr; - __u64 dst_uaddr; - __u32 len; -}; - -struct kvm_sev_attestation_report { - __u8 mnonce[16]; - __u64 uaddr; - __u32 len; -}; - -struct kvm_sev_send_start { - __u32 policy; - __u64 pdh_cert_uaddr; - __u32 pdh_cert_len; - __u64 plat_certs_uaddr; - __u32 plat_certs_len; - __u64 amd_certs_uaddr; - __u32 amd_certs_len; - __u64 session_uaddr; - __u32 session_len; -}; - -struct kvm_sev_send_update_data { - __u64 hdr_uaddr; - __u32 hdr_len; - __u64 guest_uaddr; - __u32 guest_len; - __u64 trans_uaddr; - __u32 trans_len; -}; - -struct kvm_sev_receive_start { - __u32 handle; - __u32 policy; - __u64 pdh_uaddr; - __u32 pdh_len; - __u64 session_uaddr; - __u32 session_len; -}; - -struct kvm_sev_receive_update_data { - __u64 hdr_uaddr; - __u32 hdr_len; - __u64 guest_uaddr; - __u32 guest_len; - __u64 trans_uaddr; - __u32 trans_len; -}; - -#define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) -#define KVM_DEV_ASSIGN_PCI_2_3 (1 << 1) -#define KVM_DEV_ASSIGN_MASK_INTX (1 << 2) - -struct kvm_assigned_pci_dev { - __u32 assigned_dev_id; - __u32 busnr; - __u32 devfn; - __u32 flags; - __u32 segnr; - union { - __u32 reserved[11]; - }; -}; - -#define KVM_DEV_IRQ_HOST_INTX (1 << 0) -#define KVM_DEV_IRQ_HOST_MSI (1 << 1) -#define KVM_DEV_IRQ_HOST_MSIX (1 << 2) - -#define KVM_DEV_IRQ_GUEST_INTX (1 << 8) -#define KVM_DEV_IRQ_GUEST_MSI (1 << 9) -#define KVM_DEV_IRQ_GUEST_MSIX (1 << 10) - -#define KVM_DEV_IRQ_HOST_MASK 0x00ff -#define KVM_DEV_IRQ_GUEST_MASK 0xff00 - -struct kvm_assigned_irq { - __u32 assigned_dev_id; - __u32 host_irq; /* ignored (legacy field) */ - __u32 guest_irq; - __u32 flags; - union { - __u32 reserved[12]; - }; -}; - -struct kvm_assigned_msix_nr { - __u32 assigned_dev_id; - __u16 entry_nr; - __u16 padding; -}; - -#define KVM_MAX_MSIX_PER_DEV 256 -struct kvm_assigned_msix_entry { - __u32 assigned_dev_id; - __u32 gsi; - __u16 entry; /* The index of entry in the MSI-X table */ - __u16 padding[3]; -}; - -#define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0) -#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1) - -/* Available with KVM_CAP_ARM_USER_IRQ */ - -/* Bits for run->s.regs.device_irq_level */ -#define KVM_ARM_DEV_EL1_VTIMER (1 << 0) -#define KVM_ARM_DEV_EL1_PTIMER (1 << 1) -#define KVM_ARM_DEV_PMU (1 << 2) - -struct kvm_hyperv_eventfd { - __u32 conn_id; - __s32 fd; - __u32 flags; - __u32 padding[3]; -}; - -#define KVM_HYPERV_CONN_ID_MASK 0x00ffffff -#define KVM_HYPERV_EVENTFD_DEASSIGN (1 << 0) - #define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (1 << 0) #define KVM_DIRTY_LOG_INITIALLY_SET (1 << 1) @@ -2180,33 +1528,6 @@ struct kvm_stats_desc { /* Available with KVM_CAP_S390_ZPCI_OP */ #define KVM_S390_ZPCI_OP _IOW(KVMIO, 0xd1, struct kvm_s390_zpci_op) -struct kvm_s390_zpci_op { - /* in */ - __u32 fh; /* target device */ - __u8 op; /* operation to perform */ - __u8 pad[3]; - union { - /* for KVM_S390_ZPCIOP_REG_AEN */ - struct { - __u64 ibv; /* Guest addr of interrupt bit vector */ - __u64 sb; /* Guest addr of summary bit */ - __u32 flags; - __u32 noi; /* Number of interrupts */ - __u8 isc; /* Guest interrupt subclass */ - __u8 sbo; /* Offset of guest summary bit vector */ - __u16 pad; - } reg_aen; - __u64 reserved[8]; - } u; -}; - -/* types for kvm_s390_zpci_op->op */ -#define KVM_S390_ZPCIOP_REG_AEN 0 -#define KVM_S390_ZPCIOP_DEREG_AEN 1 - -/* flags for kvm_s390_zpci_op->u.reg_aen.flags */ -#define KVM_S390_ZPCIOP_REGAEN_HOST (1 << 0) - /* Available with KVM_CAP_MEMORY_ATTRIBUTES */ #define KVM_SET_MEMORY_ATTRIBUTES _IOW(KVMIO, 0xd2, struct kvm_memory_attributes) diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h index d5b9cfbd9cea..628d46a0da92 100644 --- a/tools/include/uapi/sound/asound.h +++ b/tools/include/uapi/sound/asound.h @@ -142,7 +142,7 @@ struct snd_hwdep_dsp_image { * * *****************************************************************************/ -#define SNDRV_PCM_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 16) +#define SNDRV_PCM_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 17) typedef unsigned long snd_pcm_uframes_t; typedef signed long snd_pcm_sframes_t; @@ -416,7 +416,7 @@ struct snd_pcm_hw_params { unsigned int rmask; /* W: requested masks */ unsigned int cmask; /* R: changed masks */ unsigned int info; /* R: Info flags for returned setup */ - unsigned int msbits; /* R: used most significant bits */ + unsigned int msbits; /* R: used most significant bits (in sample bit-width) */ unsigned int rate_num; /* R: rate numerator */ unsigned int rate_den; /* R: rate denominator */ snd_pcm_uframes_t fifo_size; /* R: chip FIFO size in frames */ diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index ec5e21932876..4790c735599b 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -970,7 +970,7 @@ int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel, if (dso->annotate_warned) return -1; - if (not_annotated) { + if (not_annotated || !sym->annotate2) { err = symbol__annotate2(ms, evsel, &browser.arch); if (err) { char msg[BUFSIZ]; diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index ac002d907d81..50ca92255ff6 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -2461,6 +2461,9 @@ int symbol__annotate(struct map_symbol *ms, struct evsel *evsel, if (parch) *parch = arch; + if (!list_empty(¬es->src->source)) + return 0; + args.arch = arch; args.ms = *ms; if (annotate_opts.full_addr) diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c index fb54bd38e7d0..d931a898c434 100644 --- a/tools/perf/util/bpf_skel/lock_contention.bpf.c +++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c @@ -284,6 +284,7 @@ static inline __u32 check_lock_type(__u64 lock, __u32 flags) struct task_struct *curr; struct mm_struct___old *mm_old; struct mm_struct___new *mm_new; + struct sighand_struct *sighand; switch (flags) { case LCB_F_READ: /* rwsem */ @@ -305,7 +306,9 @@ static inline __u32 check_lock_type(__u64 lock, __u32 flags) break; case LCB_F_SPIN: /* spinlock */ curr = bpf_get_current_task_btf(); - if (&curr->sighand->siglock == (void *)lock) + sighand = curr->sighand; + + if (sighand && &sighand->siglock == (void *)lock) return LCD_F_SIGHAND_LOCK; break; default: diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8 index 8f08c3fd498d..0d3672e5d9ed 100644 --- a/tools/power/x86/turbostat/turbostat.8 +++ b/tools/power/x86/turbostat/turbostat.8 @@ -67,6 +67,10 @@ The column name "all" can be used to enable all disabled-by-default built-in cou .PP \fB--quiet\fP Do not decode and print the system configuration header information. .PP ++\fB--no-msr\fP Disable all the uses of the MSR driver. ++.PP ++\fB--no-perf\fP Disable all the uses of the perf API. ++.PP \fB--interval seconds\fP overrides the default 5.0 second measurement interval. .PP \fB--num_iterations num\fP number of the measurement iterations. @@ -125,9 +129,17 @@ The system configuration dump (if --quiet is not used) is followed by statistics .PP \fBPkgTmp\fP Degrees Celsius reported by the per-package Package Thermal Monitor. .PP -\fBGFX%rc6\fP The percentage of time the GPU is in the "render C6" state, rc6, during the measurement interval. From /sys/class/drm/card0/power/rc6_residency_ms. +\fBGFX%rc6\fP The percentage of time the GPU is in the "render C6" state, rc6, during the measurement interval. From /sys/class/drm/card0/power/rc6_residency_ms or /sys/class/drm/card0/gt/gt0/rc6_residency_ms or /sys/class/drm/card0/device/tile0/gtN/gtidle/idle_residency_ms depending on the graphics driver being used. .PP -\fBGFXMHz\fP Instantaneous snapshot of what sysfs presents at the end of the measurement interval. From /sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz. +\fBGFXMHz\fP Instantaneous snapshot of what sysfs presents at the end of the measurement interval. From /sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz or /sys/class/drm/card0/gt_cur_freq_mhz or /sys/class/drm/card0/gt/gt0/rps_cur_freq_mhz or /sys/class/drm/card0/device/tile0/gtN/freq0/cur_freq depending on the graphics driver being used. +.PP +\fBGFXAMHz\fP Instantaneous snapshot of what sysfs presents at the end of the measurement interval. From /sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz or /sys/class/drm/card0/gt_act_freq_mhz or /sys/class/drm/card0/gt/gt0/rps_act_freq_mhz or /sys/class/drm/card0/device/tile0/gtN/freq0/act_freq depending on the graphics driver being used. +.PP +\fBSAM%mc6\fP The percentage of time the SA Media is in the "module C6" state, mc6, during the measurement interval. From /sys/class/drm/card0/gt/gt1/rc6_residency_ms or /sys/class/drm/card0/device/tile0/gtN/gtidle/idle_residency_ms depending on the graphics driver being used. +.PP +\fBSAMMHz\fP Instantaneous snapshot of what sysfs presents at the end of the measurement interval. From /sys/class/drm/card0/gt/gt1/rps_cur_freq_mhz or /sys/class/drm/card0/device/tile0/gtN/freq0/cur_freq depending on the graphics driver being used. +.PP +\fBSAMAMHz\fP Instantaneous snapshot of what sysfs presents at the end of the measurement interval. From /sys/class/drm/card0/gt/gt1/rps_act_freq_mhz or /sys/class/drm/card0/device/tile0/gtN/freq0/act_freq depending on the graphics driver being used. .PP \fBPkg%pc2, Pkg%pc3, Pkg%pc6, Pkg%pc7\fP percentage residency in hardware package idle states. These numbers are from hardware residency counters. .PP @@ -370,7 +382,7 @@ below the processor's base frequency. Busy% = MPERF_delta/TSC_delta -Bzy_MHz = TSC_delta/APERF_delta/MPERF_delta/measurement_interval +Bzy_MHz = TSC_delta*APERF_delta/MPERF_delta/measurement_interval Note that these calculations depend on TSC_delta, so they are not reliable during intervals when TSC_MHz is not running at the base frequency. diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 7a334377f92b..98256468e248 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -3,7 +3,7 @@ * turbostat -- show CPU frequency and C-state residency * on modern Intel and AMD processors. * - * Copyright (c) 2023 Intel Corporation. + * Copyright (c) 2024 Intel Corporation. * Len Brown <len.brown@intel.com> */ @@ -36,6 +36,8 @@ #include <linux/perf_event.h> #include <asm/unistd.h> #include <stdbool.h> +#include <assert.h> +#include <linux/kernel.h> #define UNUSED(x) (void)(x) @@ -53,9 +55,13 @@ #define NAME_BYTES 20 #define PATH_BYTES 128 +#define MAX_NOFILE 0x8000 + enum counter_scope { SCOPE_CPU, SCOPE_CORE, SCOPE_PACKAGE }; enum counter_type { COUNTER_ITEMS, COUNTER_CYCLES, COUNTER_SECONDS, COUNTER_USEC }; enum counter_format { FORMAT_RAW, FORMAT_DELTA, FORMAT_PERCENT }; +enum amperf_source { AMPERF_SOURCE_PERF, AMPERF_SOURCE_MSR }; +enum rapl_source { RAPL_SOURCE_NONE, RAPL_SOURCE_PERF, RAPL_SOURCE_MSR }; struct msr_counter { unsigned int msr_num; @@ -127,6 +133,9 @@ struct msr_counter bic[] = { { 0x0, "IPC", "", 0, 0, 0, NULL, 0 }, { 0x0, "CoreThr", "", 0, 0, 0, NULL, 0 }, { 0x0, "UncMHz", "", 0, 0, 0, NULL, 0 }, + { 0x0, "SAM%mc6", "", 0, 0, 0, NULL, 0 }, + { 0x0, "SAMMHz", "", 0, 0, 0, NULL, 0 }, + { 0x0, "SAMAMHz", "", 0, 0, 0, NULL, 0 }, }; #define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter)) @@ -185,11 +194,14 @@ struct msr_counter bic[] = { #define BIC_IPC (1ULL << 52) #define BIC_CORE_THROT_CNT (1ULL << 53) #define BIC_UNCORE_MHZ (1ULL << 54) +#define BIC_SAM_mc6 (1ULL << 55) +#define BIC_SAMMHz (1ULL << 56) +#define BIC_SAMACTMHz (1ULL << 57) #define BIC_TOPOLOGY (BIC_Package | BIC_Node | BIC_CoreCnt | BIC_PkgCnt | BIC_Core | BIC_CPU | BIC_Die ) #define BIC_THERMAL_PWR ( BIC_CoreTmp | BIC_PkgTmp | BIC_PkgWatt | BIC_CorWatt | BIC_GFXWatt | BIC_RAMWatt | BIC_PKG__ | BIC_RAM__) -#define BIC_FREQUENCY ( BIC_Avg_MHz | BIC_Busy | BIC_Bzy_MHz | BIC_TSC_MHz | BIC_GFXMHz | BIC_GFXACTMHz | BIC_UNCORE_MHZ) -#define BIC_IDLE ( BIC_sysfs | BIC_CPU_c1 | BIC_CPU_c3 | BIC_CPU_c6 | BIC_CPU_c7 | BIC_GFX_rc6 | BIC_Pkgpc2 | BIC_Pkgpc3 | BIC_Pkgpc6 | BIC_Pkgpc7 | BIC_Pkgpc8 | BIC_Pkgpc9 | BIC_Pkgpc10 | BIC_CPU_LPI | BIC_SYS_LPI | BIC_Mod_c6 | BIC_Totl_c0 | BIC_Any_c0 | BIC_GFX_c0 | BIC_CPUGFX) +#define BIC_FREQUENCY (BIC_Avg_MHz | BIC_Busy | BIC_Bzy_MHz | BIC_TSC_MHz | BIC_GFXMHz | BIC_GFXACTMHz | BIC_SAMMHz | BIC_SAMACTMHz | BIC_UNCORE_MHZ) +#define BIC_IDLE (BIC_sysfs | BIC_CPU_c1 | BIC_CPU_c3 | BIC_CPU_c6 | BIC_CPU_c7 | BIC_GFX_rc6 | BIC_Pkgpc2 | BIC_Pkgpc3 | BIC_Pkgpc6 | BIC_Pkgpc7 | BIC_Pkgpc8 | BIC_Pkgpc9 | BIC_Pkgpc10 | BIC_CPU_LPI | BIC_SYS_LPI | BIC_Mod_c6 | BIC_Totl_c0 | BIC_Any_c0 | BIC_GFX_c0 | BIC_CPUGFX | BIC_SAM_mc6) #define BIC_OTHER ( BIC_IRQ | BIC_SMI | BIC_ThreadC | BIC_CoreTmp | BIC_IPC) #define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC) @@ -204,10 +216,13 @@ unsigned long long bic_present = BIC_USEC | BIC_TOD | BIC_sysfs | BIC_APIC | BIC #define BIC_NOT_PRESENT(COUNTER_BIT) (bic_present &= ~COUNTER_BIT) #define BIC_IS_ENABLED(COUNTER_BIT) (bic_enabled & COUNTER_BIT) +struct amperf_group_fd; + char *proc_stat = "/proc/stat"; FILE *outf; int *fd_percpu; int *fd_instr_count_percpu; +struct amperf_group_fd *fd_amperf_percpu; /* File descriptors for perf group with APERF and MPERF counters. */ struct timeval interval_tv = { 5, 0 }; struct timespec interval_ts = { 5, 0 }; @@ -242,11 +257,8 @@ char *output_buffer, *outp; unsigned int do_dts; unsigned int do_ptm; unsigned int do_ipc; -unsigned long long gfx_cur_rc6_ms; unsigned long long cpuidle_cur_cpu_lpi_us; unsigned long long cpuidle_cur_sys_lpi_us; -unsigned int gfx_cur_mhz; -unsigned int gfx_act_mhz; unsigned int tj_max; unsigned int tj_max_override; double rapl_power_units, rapl_time_units; @@ -263,6 +275,28 @@ unsigned int has_hwp_epp; /* IA32_HWP_REQUEST[bits 31:24] */ unsigned int has_hwp_pkg; /* IA32_HWP_REQUEST_PKG */ unsigned int first_counter_read = 1; int ignore_stdin; +bool no_msr; +bool no_perf; +enum amperf_source amperf_source; + +enum gfx_sysfs_idx { + GFX_rc6, + GFX_MHz, + GFX_ACTMHz, + SAM_mc6, + SAM_MHz, + SAM_ACTMHz, + GFX_MAX +}; + +struct gfx_sysfs_info { + const char *path; + FILE *fp; + unsigned int val; + unsigned long long val_ull; +}; + +static struct gfx_sysfs_info gfx_info[GFX_MAX]; int get_msr(int cpu, off_t offset, unsigned long long *msr); @@ -652,6 +686,7 @@ static const struct platform_features icx_features = { .bclk_freq = BCLK_100MHZ, .supported_cstates = CC1 | CC6 | PC2 | PC6, .cst_limit = CST_LIMIT_ICX, + .has_msr_core_c1_res = 1, .has_irtl_msrs = 1, .has_cst_prewake_bit = 1, .trl_msrs = TRL_BASE | TRL_CORECOUNT, @@ -948,6 +983,175 @@ size_t cpu_present_setsize, cpu_effective_setsize, cpu_allowed_setsize, cpu_affi #define MAX_ADDED_THREAD_COUNTERS 24 #define BITMASK_SIZE 32 +/* Indexes used to map data read from perf and MSRs into global variables */ +enum rapl_rci_index { + RAPL_RCI_INDEX_ENERGY_PKG = 0, + RAPL_RCI_INDEX_ENERGY_CORES = 1, + RAPL_RCI_INDEX_DRAM = 2, + RAPL_RCI_INDEX_GFX = 3, + RAPL_RCI_INDEX_PKG_PERF_STATUS = 4, + RAPL_RCI_INDEX_DRAM_PERF_STATUS = 5, + RAPL_RCI_INDEX_CORE_ENERGY = 6, + NUM_RAPL_COUNTERS, +}; + +enum rapl_unit { + RAPL_UNIT_INVALID, + RAPL_UNIT_JOULES, + RAPL_UNIT_WATTS, +}; + +struct rapl_counter_info_t { + unsigned long long data[NUM_RAPL_COUNTERS]; + enum rapl_source source[NUM_RAPL_COUNTERS]; + unsigned long long flags[NUM_RAPL_COUNTERS]; + double scale[NUM_RAPL_COUNTERS]; + enum rapl_unit unit[NUM_RAPL_COUNTERS]; + + union { + /* Active when source == RAPL_SOURCE_MSR */ + struct { + unsigned long long msr[NUM_RAPL_COUNTERS]; + unsigned long long msr_mask[NUM_RAPL_COUNTERS]; + int msr_shift[NUM_RAPL_COUNTERS]; + }; + }; + + int fd_perf; +}; + +/* struct rapl_counter_info_t for each RAPL domain */ +struct rapl_counter_info_t *rapl_counter_info_perdomain; + +#define RAPL_COUNTER_FLAG_USE_MSR_SUM (1u << 1) + +struct rapl_counter_arch_info { + int feature_mask; /* Mask for testing if the counter is supported on host */ + const char *perf_subsys; + const char *perf_name; + unsigned long long msr; + unsigned long long msr_mask; + int msr_shift; /* Positive mean shift right, negative mean shift left */ + double *platform_rapl_msr_scale; /* Scale applied to values read by MSR (platform dependent, filled at runtime) */ + unsigned int rci_index; /* Maps data from perf counters to global variables */ + unsigned long long bic; + double compat_scale; /* Some counters require constant scaling to be in the same range as other, similar ones */ + unsigned long long flags; +}; + +static const struct rapl_counter_arch_info rapl_counter_arch_infos[] = { + { + .feature_mask = RAPL_PKG, + .perf_subsys = "power", + .perf_name = "energy-pkg", + .msr = MSR_PKG_ENERGY_STATUS, + .msr_mask = 0xFFFFFFFFFFFFFFFF, + .msr_shift = 0, + .platform_rapl_msr_scale = &rapl_energy_units, + .rci_index = RAPL_RCI_INDEX_ENERGY_PKG, + .bic = BIC_PkgWatt | BIC_Pkg_J, + .compat_scale = 1.0, + .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM, + }, + { + .feature_mask = RAPL_AMD_F17H, + .perf_subsys = "power", + .perf_name = "energy-pkg", + .msr = MSR_PKG_ENERGY_STAT, + .msr_mask = 0xFFFFFFFFFFFFFFFF, + .msr_shift = 0, + .platform_rapl_msr_scale = &rapl_energy_units, + .rci_index = RAPL_RCI_INDEX_ENERGY_PKG, + .bic = BIC_PkgWatt | BIC_Pkg_J, + .compat_scale = 1.0, + .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM, + }, + { + .feature_mask = RAPL_CORE_ENERGY_STATUS, + .perf_subsys = "power", + .perf_name = "energy-cores", + .msr = MSR_PP0_ENERGY_STATUS, + .msr_mask = 0xFFFFFFFFFFFFFFFF, + .msr_shift = 0, + .platform_rapl_msr_scale = &rapl_energy_units, + .rci_index = RAPL_RCI_INDEX_ENERGY_CORES, + .bic = BIC_CorWatt | BIC_Cor_J, + .compat_scale = 1.0, + .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM, + }, + { + .feature_mask = RAPL_DRAM, + .perf_subsys = "power", + .perf_name = "energy-ram", + .msr = MSR_DRAM_ENERGY_STATUS, + .msr_mask = 0xFFFFFFFFFFFFFFFF, + .msr_shift = 0, + .platform_rapl_msr_scale = &rapl_dram_energy_units, + .rci_index = RAPL_RCI_INDEX_DRAM, + .bic = BIC_RAMWatt | BIC_RAM_J, + .compat_scale = 1.0, + .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM, + }, + { + .feature_mask = RAPL_GFX, + .perf_subsys = "power", + .perf_name = "energy-gpu", + .msr = MSR_PP1_ENERGY_STATUS, + .msr_mask = 0xFFFFFFFFFFFFFFFF, + .msr_shift = 0, + .platform_rapl_msr_scale = &rapl_energy_units, + .rci_index = RAPL_RCI_INDEX_GFX, + .bic = BIC_GFXWatt | BIC_GFX_J, + .compat_scale = 1.0, + .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM, + }, + { + .feature_mask = RAPL_PKG_PERF_STATUS, + .perf_subsys = NULL, + .perf_name = NULL, + .msr = MSR_PKG_PERF_STATUS, + .msr_mask = 0xFFFFFFFFFFFFFFFF, + .msr_shift = 0, + .platform_rapl_msr_scale = &rapl_time_units, + .rci_index = RAPL_RCI_INDEX_PKG_PERF_STATUS, + .bic = BIC_PKG__, + .compat_scale = 100.0, + .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM, + }, + { + .feature_mask = RAPL_DRAM_PERF_STATUS, + .perf_subsys = NULL, + .perf_name = NULL, + .msr = MSR_DRAM_PERF_STATUS, + .msr_mask = 0xFFFFFFFFFFFFFFFF, + .msr_shift = 0, + .platform_rapl_msr_scale = &rapl_time_units, + .rci_index = RAPL_RCI_INDEX_DRAM_PERF_STATUS, + .bic = BIC_RAM__, + .compat_scale = 100.0, + .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM, + }, + { + .feature_mask = RAPL_AMD_F17H, + .perf_subsys = NULL, + .perf_name = NULL, + .msr = MSR_CORE_ENERGY_STAT, + .msr_mask = 0xFFFFFFFF, + .msr_shift = 0, + .platform_rapl_msr_scale = &rapl_energy_units, + .rci_index = RAPL_RCI_INDEX_CORE_ENERGY, + .bic = BIC_CorWatt | BIC_Cor_J, + .compat_scale = 1.0, + .flags = 0, + }, +}; + +struct rapl_counter { + unsigned long long raw_value; + enum rapl_unit unit; + double scale; +}; + struct thread_data { struct timeval tv_begin; struct timeval tv_end; @@ -974,7 +1178,7 @@ struct core_data { unsigned long long c7; unsigned long long mc6_us; /* duplicate as per-core for now, even though per module */ unsigned int core_temp_c; - unsigned int core_energy; /* MSR_CORE_ENERGY_STAT */ + struct rapl_counter core_energy; /* MSR_CORE_ENERGY_STAT */ unsigned int core_id; unsigned long long core_throt_cnt; unsigned long long counter[MAX_ADDED_COUNTERS]; @@ -989,8 +1193,8 @@ struct pkg_data { unsigned long long pc8; unsigned long long pc9; unsigned long long pc10; - unsigned long long cpu_lpi; - unsigned long long sys_lpi; + long long cpu_lpi; + long long sys_lpi; unsigned long long pkg_wtd_core_c0; unsigned long long pkg_any_core_c0; unsigned long long pkg_any_gfxe_c0; @@ -998,13 +1202,16 @@ struct pkg_data { long long gfx_rc6_ms; unsigned int gfx_mhz; unsigned int gfx_act_mhz; + long long sam_mc6_ms; + unsigned int sam_mhz; + unsigned int sam_act_mhz; unsigned int package_id; - unsigned long long energy_pkg; /* MSR_PKG_ENERGY_STATUS */ - unsigned long long energy_dram; /* MSR_DRAM_ENERGY_STATUS */ - unsigned long long energy_cores; /* MSR_PP0_ENERGY_STATUS */ - unsigned long long energy_gfx; /* MSR_PP1_ENERGY_STATUS */ - unsigned long long rapl_pkg_perf_status; /* MSR_PKG_PERF_STATUS */ - unsigned long long rapl_dram_perf_status; /* MSR_DRAM_PERF_STATUS */ + struct rapl_counter energy_pkg; /* MSR_PKG_ENERGY_STATUS */ + struct rapl_counter energy_dram; /* MSR_DRAM_ENERGY_STATUS */ + struct rapl_counter energy_cores; /* MSR_PP0_ENERGY_STATUS */ + struct rapl_counter energy_gfx; /* MSR_PP1_ENERGY_STATUS */ + struct rapl_counter rapl_pkg_perf_status; /* MSR_PKG_PERF_STATUS */ + struct rapl_counter rapl_dram_perf_status; /* MSR_DRAM_PERF_STATUS */ unsigned int pkg_temp_c; unsigned int uncore_mhz; unsigned long long counter[MAX_ADDED_COUNTERS]; @@ -1150,6 +1357,38 @@ struct sys_counters { struct msr_counter *pp; } sys; +void free_sys_counters(void) +{ + struct msr_counter *p = sys.tp, *pnext = NULL; + + while (p) { + pnext = p->next; + free(p); + p = pnext; + } + + p = sys.cp, pnext = NULL; + while (p) { + pnext = p->next; + free(p); + p = pnext; + } + + p = sys.pp, pnext = NULL; + while (p) { + pnext = p->next; + free(p); + p = pnext; + } + + sys.added_thread_counters = 0; + sys.added_core_counters = 0; + sys.added_package_counters = 0; + sys.tp = NULL; + sys.cp = NULL; + sys.pp = NULL; +} + struct system_summary { struct thread_data threads; struct core_data cores; @@ -1280,34 +1519,60 @@ int get_msr_fd(int cpu) sprintf(pathname, "/dev/cpu/%d/msr", cpu); fd = open(pathname, O_RDONLY); if (fd < 0) - err(-1, "%s open failed, try chown or chmod +r /dev/cpu/*/msr, or run as root", pathname); + err(-1, "%s open failed, try chown or chmod +r /dev/cpu/*/msr, " + "or run with --no-msr, or run as root", pathname); fd_percpu[cpu] = fd; return fd; } +static void bic_disable_msr_access(void) +{ + const unsigned long bic_msrs = + BIC_SMI | + BIC_CPU_c1 | + BIC_CPU_c3 | + BIC_CPU_c6 | + BIC_CPU_c7 | + BIC_Mod_c6 | + BIC_CoreTmp | + BIC_Totl_c0 | + BIC_Any_c0 | + BIC_GFX_c0 | + BIC_CPUGFX | + BIC_Pkgpc2 | BIC_Pkgpc3 | BIC_Pkgpc6 | BIC_Pkgpc7 | BIC_Pkgpc8 | BIC_Pkgpc9 | BIC_Pkgpc10 | BIC_PkgTmp; + + bic_enabled &= ~bic_msrs; + + free_sys_counters(); +} + static long perf_event_open(struct perf_event_attr *hw_event, pid_t pid, int cpu, int group_fd, unsigned long flags) { + assert(!no_perf); + return syscall(__NR_perf_event_open, hw_event, pid, cpu, group_fd, flags); } -static int perf_instr_count_open(int cpu_num) +static long open_perf_counter(int cpu, unsigned int type, unsigned int config, int group_fd, __u64 read_format) { - struct perf_event_attr pea; - int fd; + struct perf_event_attr attr; + const pid_t pid = -1; + const unsigned long flags = 0; - memset(&pea, 0, sizeof(struct perf_event_attr)); - pea.type = PERF_TYPE_HARDWARE; - pea.size = sizeof(struct perf_event_attr); - pea.config = PERF_COUNT_HW_INSTRUCTIONS; + assert(!no_perf); - /* counter for cpu_num, including user + kernel and all processes */ - fd = perf_event_open(&pea, -1, cpu_num, -1, 0); - if (fd == -1) { - warnx("capget(CAP_PERFMON) failed, try \"# setcap cap_sys_admin=ep %s\"", progname); - BIC_NOT_PRESENT(BIC_IPC); - } + memset(&attr, 0, sizeof(struct perf_event_attr)); + + attr.type = type; + attr.size = sizeof(struct perf_event_attr); + attr.config = config; + attr.disabled = 0; + attr.sample_type = PERF_SAMPLE_IDENTIFIER; + attr.read_format = read_format; + + const int fd = perf_event_open(&attr, pid, cpu, group_fd, flags); return fd; } @@ -1317,7 +1582,7 @@ int get_instr_count_fd(int cpu) if (fd_instr_count_percpu[cpu]) return fd_instr_count_percpu[cpu]; - fd_instr_count_percpu[cpu] = perf_instr_count_open(cpu); + fd_instr_count_percpu[cpu] = open_perf_counter(cpu, PERF_TYPE_HARDWARE, PERF_COUNT_HW_INSTRUCTIONS, -1, 0); return fd_instr_count_percpu[cpu]; } @@ -1326,6 +1591,8 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr) { ssize_t retval; + assert(!no_msr); + retval = pread(get_msr_fd(cpu), msr, sizeof(*msr), offset); if (retval != sizeof *msr) @@ -1334,6 +1601,21 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr) return 0; } +int probe_msr(int cpu, off_t offset) +{ + ssize_t retval; + unsigned long long dummy; + + assert(!no_msr); + + retval = pread(get_msr_fd(cpu), &dummy, sizeof(dummy), offset); + + if (retval != sizeof(dummy)) + return 1; + + return 0; +} + #define MAX_DEFERRED 16 char *deferred_add_names[MAX_DEFERRED]; char *deferred_skip_names[MAX_DEFERRED]; @@ -1369,6 +1651,8 @@ void help(void) " Override default 5-second measurement interval\n" " -J, --Joules displays energy in Joules instead of Watts\n" " -l, --list list column headers only\n" + " -M, --no-msr Disable all uses of the MSR driver\n" + " -P, --no-perf Disable all uses of the perf API\n" " -n, --num_iterations num\n" " number of the measurement iterations\n" " -N, --header_iterations num\n" @@ -1573,6 +1857,15 @@ void print_header(char *delim) if (DO_BIC(BIC_GFXACTMHz)) outp += sprintf(outp, "%sGFXAMHz", (printed++ ? delim : "")); + if (DO_BIC(BIC_SAM_mc6)) + outp += sprintf(outp, "%sSAM%%mc6", (printed++ ? delim : "")); + + if (DO_BIC(BIC_SAMMHz)) + outp += sprintf(outp, "%sSAMMHz", (printed++ ? delim : "")); + + if (DO_BIC(BIC_SAMACTMHz)) + outp += sprintf(outp, "%sSAMAMHz", (printed++ ? delim : "")); + if (DO_BIC(BIC_Totl_c0)) outp += sprintf(outp, "%sTotl%%C0", (printed++ ? delim : "")); if (DO_BIC(BIC_Any_c0)) @@ -1671,26 +1964,35 @@ int dump_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p outp += sprintf(outp, "SMI: %d\n", t->smi_count); for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) { - outp += sprintf(outp, "tADDED [%d] msr0x%x: %08llX\n", i, mp->msr_num, t->counter[i]); + outp += + sprintf(outp, "tADDED [%d] %8s msr0x%x: %08llX %s\n", i, mp->name, mp->msr_num, + t->counter[i], mp->path); } } - if (c) { + if (c && is_cpu_first_thread_in_core(t, c, p)) { outp += sprintf(outp, "core: %d\n", c->core_id); outp += sprintf(outp, "c3: %016llX\n", c->c3); outp += sprintf(outp, "c6: %016llX\n", c->c6); outp += sprintf(outp, "c7: %016llX\n", c->c7); outp += sprintf(outp, "DTS: %dC\n", c->core_temp_c); outp += sprintf(outp, "cpu_throt_count: %016llX\n", c->core_throt_cnt); - outp += sprintf(outp, "Joules: %0X\n", c->core_energy); + + const unsigned long long energy_value = c->core_energy.raw_value * c->core_energy.scale; + const double energy_scale = c->core_energy.scale; + + if (c->core_energy.unit == RAPL_UNIT_JOULES) + outp += sprintf(outp, "Joules: %0llX (scale: %lf)\n", energy_value, energy_scale); for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) { - outp += sprintf(outp, "cADDED [%d] msr0x%x: %08llX\n", i, mp->msr_num, c->counter[i]); + outp += + sprintf(outp, "cADDED [%d] %8s msr0x%x: %08llX %s\n", i, mp->name, mp->msr_num, + c->counter[i], mp->path); } outp += sprintf(outp, "mc6_us: %016llX\n", c->mc6_us); } - if (p) { + if (p && is_cpu_first_core_in_package(t, c, p)) { outp += sprintf(outp, "package: %d\n", p->package_id); outp += sprintf(outp, "Weighted cores: %016llX\n", p->pkg_wtd_core_c0); @@ -1710,16 +2012,18 @@ int dump_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p outp += sprintf(outp, "pc10: %016llX\n", p->pc10); outp += sprintf(outp, "cpu_lpi: %016llX\n", p->cpu_lpi); outp += sprintf(outp, "sys_lpi: %016llX\n", p->sys_lpi); - outp += sprintf(outp, "Joules PKG: %0llX\n", p->energy_pkg); - outp += sprintf(outp, "Joules COR: %0llX\n", p->energy_cores); - outp += sprintf(outp, "Joules GFX: %0llX\n", p->energy_gfx); - outp += sprintf(outp, "Joules RAM: %0llX\n", p->energy_dram); - outp += sprintf(outp, "Throttle PKG: %0llX\n", p->rapl_pkg_perf_status); - outp += sprintf(outp, "Throttle RAM: %0llX\n", p->rapl_dram_perf_status); + outp += sprintf(outp, "Joules PKG: %0llX\n", p->energy_pkg.raw_value); + outp += sprintf(outp, "Joules COR: %0llX\n", p->energy_cores.raw_value); + outp += sprintf(outp, "Joules GFX: %0llX\n", p->energy_gfx.raw_value); + outp += sprintf(outp, "Joules RAM: %0llX\n", p->energy_dram.raw_value); + outp += sprintf(outp, "Throttle PKG: %0llX\n", p->rapl_pkg_perf_status.raw_value); + outp += sprintf(outp, "Throttle RAM: %0llX\n", p->rapl_dram_perf_status.raw_value); outp += sprintf(outp, "PTM: %dC\n", p->pkg_temp_c); for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) { - outp += sprintf(outp, "pADDED [%d] msr0x%x: %08llX\n", i, mp->msr_num, p->counter[i]); + outp += + sprintf(outp, "pADDED [%d] %8s msr0x%x: %08llX %s\n", i, mp->name, mp->msr_num, + p->counter[i], mp->path); } } @@ -1728,6 +2032,23 @@ int dump_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p return 0; } +double rapl_counter_get_value(const struct rapl_counter *c, enum rapl_unit desired_unit, double interval) +{ + assert(desired_unit != RAPL_UNIT_INVALID); + + /* + * For now we don't expect anything other than joules, + * so just simplify the logic. + */ + assert(c->unit == RAPL_UNIT_JOULES); + + const double scaled = c->raw_value * c->scale; + + if (desired_unit == RAPL_UNIT_WATTS) + return scaled / interval; + return scaled; +} + /* * column formatting convention & formats */ @@ -1921,9 +2242,11 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data if (DO_BIC(BIC_CorWatt) && platform->has_per_core_rapl) outp += - sprintf(outp, fmt8, (printed++ ? delim : ""), c->core_energy * rapl_energy_units / interval_float); + sprintf(outp, fmt8, (printed++ ? delim : ""), + rapl_counter_get_value(&c->core_energy, RAPL_UNIT_WATTS, interval_float)); if (DO_BIC(BIC_Cor_J) && platform->has_per_core_rapl) - outp += sprintf(outp, fmt8, (printed++ ? delim : ""), c->core_energy * rapl_energy_units); + outp += sprintf(outp, fmt8, (printed++ ? delim : ""), + rapl_counter_get_value(&c->core_energy, RAPL_UNIT_JOULES, interval_float)); /* print per-package data only for 1st core in package */ if (!is_cpu_first_core_in_package(t, c, p)) @@ -1951,6 +2274,24 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data if (DO_BIC(BIC_GFXACTMHz)) outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->gfx_act_mhz); + /* SAMmc6 */ + if (DO_BIC(BIC_SAM_mc6)) { + if (p->sam_mc6_ms == -1) { /* detect GFX counter reset */ + outp += sprintf(outp, "%s**.**", (printed++ ? delim : "")); + } else { + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), + p->sam_mc6_ms / 10.0 / interval_float); + } + } + + /* SAMMHz */ + if (DO_BIC(BIC_SAMMHz)) + outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->sam_mhz); + + /* SAMACTMHz */ + if (DO_BIC(BIC_SAMACTMHz)) + outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->sam_act_mhz); + /* Totl%C0, Any%C0 GFX%C0 CPUGFX% */ if (DO_BIC(BIC_Totl_c0)) outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pkg_wtd_core_c0 / tsc); @@ -1976,43 +2317,59 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data if (DO_BIC(BIC_Pkgpc10)) outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pc10 / tsc); - if (DO_BIC(BIC_CPU_LPI)) - outp += - sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->cpu_lpi / 1000000.0 / interval_float); - if (DO_BIC(BIC_SYS_LPI)) - outp += - sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->sys_lpi / 1000000.0 / interval_float); + if (DO_BIC(BIC_CPU_LPI)) { + if (p->cpu_lpi >= 0) + outp += + sprintf(outp, "%s%.2f", (printed++ ? delim : ""), + 100.0 * p->cpu_lpi / 1000000.0 / interval_float); + else + outp += sprintf(outp, "%s(neg)", (printed++ ? delim : "")); + } + if (DO_BIC(BIC_SYS_LPI)) { + if (p->sys_lpi >= 0) + outp += + sprintf(outp, "%s%.2f", (printed++ ? delim : ""), + 100.0 * p->sys_lpi / 1000000.0 / interval_float); + else + outp += sprintf(outp, "%s(neg)", (printed++ ? delim : "")); + } if (DO_BIC(BIC_PkgWatt)) outp += - sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_pkg * rapl_energy_units / interval_float); - + sprintf(outp, fmt8, (printed++ ? delim : ""), + rapl_counter_get_value(&p->energy_pkg, RAPL_UNIT_WATTS, interval_float)); if (DO_BIC(BIC_CorWatt) && !platform->has_per_core_rapl) outp += - sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_cores * rapl_energy_units / interval_float); + sprintf(outp, fmt8, (printed++ ? delim : ""), + rapl_counter_get_value(&p->energy_cores, RAPL_UNIT_WATTS, interval_float)); if (DO_BIC(BIC_GFXWatt)) outp += - sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_gfx * rapl_energy_units / interval_float); + sprintf(outp, fmt8, (printed++ ? delim : ""), + rapl_counter_get_value(&p->energy_gfx, RAPL_UNIT_WATTS, interval_float)); if (DO_BIC(BIC_RAMWatt)) outp += sprintf(outp, fmt8, (printed++ ? delim : ""), - p->energy_dram * rapl_dram_energy_units / interval_float); + rapl_counter_get_value(&p->energy_dram, RAPL_UNIT_WATTS, interval_float)); if (DO_BIC(BIC_Pkg_J)) - outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_pkg * rapl_energy_units); + outp += sprintf(outp, fmt8, (printed++ ? delim : ""), + rapl_counter_get_value(&p->energy_pkg, RAPL_UNIT_JOULES, interval_float)); if (DO_BIC(BIC_Cor_J) && !platform->has_per_core_rapl) - outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_cores * rapl_energy_units); + outp += sprintf(outp, fmt8, (printed++ ? delim : ""), + rapl_counter_get_value(&p->energy_cores, RAPL_UNIT_JOULES, interval_float)); if (DO_BIC(BIC_GFX_J)) - outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_gfx * rapl_energy_units); + outp += sprintf(outp, fmt8, (printed++ ? delim : ""), + rapl_counter_get_value(&p->energy_gfx, RAPL_UNIT_JOULES, interval_float)); if (DO_BIC(BIC_RAM_J)) - outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_dram * rapl_dram_energy_units); + outp += sprintf(outp, fmt8, (printed++ ? delim : ""), + rapl_counter_get_value(&p->energy_dram, RAPL_UNIT_JOULES, interval_float)); if (DO_BIC(BIC_PKG__)) outp += sprintf(outp, fmt8, (printed++ ? delim : ""), - 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float); + rapl_counter_get_value(&p->rapl_pkg_perf_status, RAPL_UNIT_WATTS, interval_float)); if (DO_BIC(BIC_RAM__)) outp += sprintf(outp, fmt8, (printed++ ? delim : ""), - 100.0 * p->rapl_dram_perf_status * rapl_time_units / interval_float); + rapl_counter_get_value(&p->rapl_dram_perf_status, RAPL_UNIT_WATTS, interval_float)); /* UncMHz */ if (DO_BIC(BIC_UNCORE_MHZ)) outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->uncore_mhz); @@ -2121,12 +2478,22 @@ int delta_package(struct pkg_data *new, struct pkg_data *old) old->gfx_mhz = new->gfx_mhz; old->gfx_act_mhz = new->gfx_act_mhz; - old->energy_pkg = new->energy_pkg - old->energy_pkg; - old->energy_cores = new->energy_cores - old->energy_cores; - old->energy_gfx = new->energy_gfx - old->energy_gfx; - old->energy_dram = new->energy_dram - old->energy_dram; - old->rapl_pkg_perf_status = new->rapl_pkg_perf_status - old->rapl_pkg_perf_status; - old->rapl_dram_perf_status = new->rapl_dram_perf_status - old->rapl_dram_perf_status; + /* flag an error when mc6 counter resets/wraps */ + if (old->sam_mc6_ms > new->sam_mc6_ms) + old->sam_mc6_ms = -1; + else + old->sam_mc6_ms = new->sam_mc6_ms - old->sam_mc6_ms; + + old->sam_mhz = new->sam_mhz; + old->sam_act_mhz = new->sam_act_mhz; + + old->energy_pkg.raw_value = new->energy_pkg.raw_value - old->energy_pkg.raw_value; + old->energy_cores.raw_value = new->energy_cores.raw_value - old->energy_cores.raw_value; + old->energy_gfx.raw_value = new->energy_gfx.raw_value - old->energy_gfx.raw_value; + old->energy_dram.raw_value = new->energy_dram.raw_value - old->energy_dram.raw_value; + old->rapl_pkg_perf_status.raw_value = new->rapl_pkg_perf_status.raw_value - old->rapl_pkg_perf_status.raw_value; + old->rapl_dram_perf_status.raw_value = + new->rapl_dram_perf_status.raw_value - old->rapl_dram_perf_status.raw_value; for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) { if (mp->format == FORMAT_RAW) @@ -2150,7 +2517,7 @@ void delta_core(struct core_data *new, struct core_data *old) old->core_throt_cnt = new->core_throt_cnt; old->mc6_us = new->mc6_us - old->mc6_us; - DELTA_WRAP32(new->core_energy, old->core_energy); + DELTA_WRAP32(new->core_energy.raw_value, old->core_energy.raw_value); for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) { if (mp->format == FORMAT_RAW) @@ -2277,6 +2644,13 @@ int delta_cpu(struct thread_data *t, struct core_data *c, return retval; } +void rapl_counter_clear(struct rapl_counter *c) +{ + c->raw_value = 0; + c->scale = 0.0; + c->unit = RAPL_UNIT_INVALID; +} + void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) { int i; @@ -2304,7 +2678,7 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data c->c7 = 0; c->mc6_us = 0; c->core_temp_c = 0; - c->core_energy = 0; + rapl_counter_clear(&c->core_energy); c->core_throt_cnt = 0; p->pkg_wtd_core_c0 = 0; @@ -2325,18 +2699,21 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data p->cpu_lpi = 0; p->sys_lpi = 0; - p->energy_pkg = 0; - p->energy_dram = 0; - p->energy_cores = 0; - p->energy_gfx = 0; - p->rapl_pkg_perf_status = 0; - p->rapl_dram_perf_status = 0; + rapl_counter_clear(&p->energy_pkg); + rapl_counter_clear(&p->energy_dram); + rapl_counter_clear(&p->energy_cores); + rapl_counter_clear(&p->energy_gfx); + rapl_counter_clear(&p->rapl_pkg_perf_status); + rapl_counter_clear(&p->rapl_dram_perf_status); p->pkg_temp_c = 0; p->gfx_rc6_ms = 0; p->uncore_mhz = 0; p->gfx_mhz = 0; p->gfx_act_mhz = 0; + p->sam_mc6_ms = 0; + p->sam_mhz = 0; + p->sam_act_mhz = 0; for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) t->counter[i] = 0; @@ -2347,6 +2724,20 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data p->counter[i] = 0; } +void rapl_counter_accumulate(struct rapl_counter *dst, const struct rapl_counter *src) +{ + /* Copy unit and scale from src if dst is not initialized */ + if (dst->unit == RAPL_UNIT_INVALID) { + dst->unit = src->unit; + dst->scale = src->scale; + } + + assert(dst->unit == src->unit); + assert(dst->scale == src->scale); + + dst->raw_value += src->raw_value; +} + int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) { int i; @@ -2393,7 +2784,7 @@ int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) average.cores.core_temp_c = MAX(average.cores.core_temp_c, c->core_temp_c); average.cores.core_throt_cnt = MAX(average.cores.core_throt_cnt, c->core_throt_cnt); - average.cores.core_energy += c->core_energy; + rapl_counter_accumulate(&average.cores.core_energy, &c->core_energy); for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) { if (mp->format == FORMAT_RAW) @@ -2428,25 +2819,29 @@ int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) average.packages.cpu_lpi = p->cpu_lpi; average.packages.sys_lpi = p->sys_lpi; - average.packages.energy_pkg += p->energy_pkg; - average.packages.energy_dram += p->energy_dram; - average.packages.energy_cores += p->energy_cores; - average.packages.energy_gfx += p->energy_gfx; + rapl_counter_accumulate(&average.packages.energy_pkg, &p->energy_pkg); + rapl_counter_accumulate(&average.packages.energy_dram, &p->energy_dram); + rapl_counter_accumulate(&average.packages.energy_cores, &p->energy_cores); + rapl_counter_accumulate(&average.packages.energy_gfx, &p->energy_gfx); average.packages.gfx_rc6_ms = p->gfx_rc6_ms; average.packages.uncore_mhz = p->uncore_mhz; average.packages.gfx_mhz = p->gfx_mhz; average.packages.gfx_act_mhz = p->gfx_act_mhz; + average.packages.sam_mc6_ms = p->sam_mc6_ms; + average.packages.sam_mhz = p->sam_mhz; + average.packages.sam_act_mhz = p->sam_act_mhz; average.packages.pkg_temp_c = MAX(average.packages.pkg_temp_c, p->pkg_temp_c); - average.packages.rapl_pkg_perf_status += p->rapl_pkg_perf_status; - average.packages.rapl_dram_perf_status += p->rapl_dram_perf_status; + rapl_counter_accumulate(&average.packages.rapl_pkg_perf_status, &p->rapl_pkg_perf_status); + rapl_counter_accumulate(&average.packages.rapl_dram_perf_status, &p->rapl_dram_perf_status); for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) { - if (mp->format == FORMAT_RAW) - continue; - average.packages.counter[i] += p->counter[i]; + if ((mp->format == FORMAT_RAW) && (topo.num_packages == 0)) + average.packages.counter[i] = p->counter[i]; + else + average.packages.counter[i] += p->counter[i]; } return 0; } @@ -2578,6 +2973,7 @@ unsigned long long snapshot_sysfs_counter(char *path) int get_mp(int cpu, struct msr_counter *mp, unsigned long long *counterp) { if (mp->msr_num != 0) { + assert(!no_msr); if (get_msr(cpu, mp->msr_num, counterp)) return -1; } else { @@ -2599,7 +2995,7 @@ unsigned long long get_uncore_mhz(int package, int die) { char path[128]; - sprintf(path, "/sys/devices/system/cpu/intel_uncore_frequency/package_0%d_die_0%d/current_freq_khz", package, + sprintf(path, "/sys/devices/system/cpu/intel_uncore_frequency/package_%02d_die_%02d/current_freq_khz", package, die); return (snapshot_sysfs_counter(path) / 1000); @@ -2627,6 +3023,9 @@ int get_epb(int cpu) return epb; msr_fallback: + if (no_msr) + return -1; + get_msr(cpu, MSR_IA32_ENERGY_PERF_BIAS, &msr); return msr & 0xf; @@ -2700,6 +3099,351 @@ int get_core_throt_cnt(int cpu, unsigned long long *cnt) return 0; } +struct amperf_group_fd { + int aperf; /* Also the group descriptor */ + int mperf; +}; + +static int read_perf_counter_info(const char *const path, const char *const parse_format, void *value_ptr) +{ + int fdmt; + int bytes_read; + char buf[64]; + int ret = -1; + + fdmt = open(path, O_RDONLY, 0); + if (fdmt == -1) { + if (debug) + fprintf(stderr, "Failed to parse perf counter info %s\n", path); + ret = -1; + goto cleanup_and_exit; + } + + bytes_read = read(fdmt, buf, sizeof(buf) - 1); + if (bytes_read <= 0 || bytes_read >= (int)sizeof(buf)) { + if (debug) + fprintf(stderr, "Failed to parse perf counter info %s\n", path); + ret = -1; + goto cleanup_and_exit; + } + + buf[bytes_read] = '\0'; + + if (sscanf(buf, parse_format, value_ptr) != 1) { + if (debug) + fprintf(stderr, "Failed to parse perf counter info %s\n", path); + ret = -1; + goto cleanup_and_exit; + } + + ret = 0; + +cleanup_and_exit: + close(fdmt); + return ret; +} + +static unsigned int read_perf_counter_info_n(const char *const path, const char *const parse_format) +{ + unsigned int v; + int status; + + status = read_perf_counter_info(path, parse_format, &v); + if (status) + v = -1; + + return v; +} + +static unsigned int read_msr_type(void) +{ + const char *const path = "/sys/bus/event_source/devices/msr/type"; + const char *const format = "%u"; + + return read_perf_counter_info_n(path, format); +} + +static unsigned int read_aperf_config(void) +{ + const char *const path = "/sys/bus/event_source/devices/msr/events/aperf"; + const char *const format = "event=%x"; + + return read_perf_counter_info_n(path, format); +} + +static unsigned int read_mperf_config(void) +{ + const char *const path = "/sys/bus/event_source/devices/msr/events/mperf"; + const char *const format = "event=%x"; + + return read_perf_counter_info_n(path, format); +} + +static unsigned int read_perf_type(const char *subsys) +{ + const char *const path_format = "/sys/bus/event_source/devices/%s/type"; + const char *const format = "%u"; + char path[128]; + + snprintf(path, sizeof(path), path_format, subsys); + + return read_perf_counter_info_n(path, format); +} + +static unsigned int read_rapl_config(const char *subsys, const char *event_name) +{ + const char *const path_format = "/sys/bus/event_source/devices/%s/events/%s"; + const char *const format = "event=%x"; + char path[128]; + + snprintf(path, sizeof(path), path_format, subsys, event_name); + + return read_perf_counter_info_n(path, format); +} + +static unsigned int read_perf_rapl_unit(const char *subsys, const char *event_name) +{ + const char *const path_format = "/sys/bus/event_source/devices/%s/events/%s.unit"; + const char *const format = "%s"; + char path[128]; + char unit_buffer[16]; + + snprintf(path, sizeof(path), path_format, subsys, event_name); + + read_perf_counter_info(path, format, &unit_buffer); + if (strcmp("Joules", unit_buffer) == 0) + return RAPL_UNIT_JOULES; + + return RAPL_UNIT_INVALID; +} + +static double read_perf_rapl_scale(const char *subsys, const char *event_name) +{ + const char *const path_format = "/sys/bus/event_source/devices/%s/events/%s.scale"; + const char *const format = "%lf"; + char path[128]; + double scale; + + snprintf(path, sizeof(path), path_format, subsys, event_name); + + if (read_perf_counter_info(path, format, &scale)) + return 0.0; + + return scale; +} + +static struct amperf_group_fd open_amperf_fd(int cpu) +{ + const unsigned int msr_type = read_msr_type(); + const unsigned int aperf_config = read_aperf_config(); + const unsigned int mperf_config = read_mperf_config(); + struct amperf_group_fd fds = {.aperf = -1, .mperf = -1 }; + + fds.aperf = open_perf_counter(cpu, msr_type, aperf_config, -1, PERF_FORMAT_GROUP); + fds.mperf = open_perf_counter(cpu, msr_type, mperf_config, fds.aperf, PERF_FORMAT_GROUP); + + return fds; +} + +static int get_amperf_fd(int cpu) +{ + assert(fd_amperf_percpu); + + if (fd_amperf_percpu[cpu].aperf) + return fd_amperf_percpu[cpu].aperf; + + fd_amperf_percpu[cpu] = open_amperf_fd(cpu); + + return fd_amperf_percpu[cpu].aperf; +} + +/* Read APERF, MPERF and TSC using the perf API. */ +static int read_aperf_mperf_tsc_perf(struct thread_data *t, int cpu) +{ + union { + struct { + unsigned long nr_entries; + unsigned long aperf; + unsigned long mperf; + }; + + unsigned long as_array[3]; + } cnt; + + const int fd_amperf = get_amperf_fd(cpu); + + /* + * Read the TSC with rdtsc, because we want the absolute value and not + * the offset from the start of the counter. + */ + t->tsc = rdtsc(); + + const int n = read(fd_amperf, &cnt.as_array[0], sizeof(cnt.as_array)); + + if (n != sizeof(cnt.as_array)) + return -2; + + t->aperf = cnt.aperf * aperf_mperf_multiplier; + t->mperf = cnt.mperf * aperf_mperf_multiplier; + + return 0; +} + +/* Read APERF, MPERF and TSC using the MSR driver and rdtsc instruction. */ +static int read_aperf_mperf_tsc_msr(struct thread_data *t, int cpu) +{ + unsigned long long tsc_before, tsc_between, tsc_after, aperf_time, mperf_time; + int aperf_mperf_retry_count = 0; + + /* + * The TSC, APERF and MPERF must be read together for + * APERF/MPERF and MPERF/TSC to give accurate results. + * + * Unfortunately, APERF and MPERF are read by + * individual system call, so delays may occur + * between them. If the time to read them + * varies by a large amount, we re-read them. + */ + + /* + * This initial dummy APERF read has been seen to + * reduce jitter in the subsequent reads. + */ + + if (get_msr(cpu, MSR_IA32_APERF, &t->aperf)) + return -3; + +retry: + t->tsc = rdtsc(); /* re-read close to APERF */ + + tsc_before = t->tsc; + + if (get_msr(cpu, MSR_IA32_APERF, &t->aperf)) + return -3; + + tsc_between = rdtsc(); + + if (get_msr(cpu, MSR_IA32_MPERF, &t->mperf)) + return -4; + + tsc_after = rdtsc(); + + aperf_time = tsc_between - tsc_before; + mperf_time = tsc_after - tsc_between; + + /* + * If the system call latency to read APERF and MPERF + * differ by more than 2x, then try again. + */ + if ((aperf_time > (2 * mperf_time)) || (mperf_time > (2 * aperf_time))) { + aperf_mperf_retry_count++; + if (aperf_mperf_retry_count < 5) + goto retry; + else + warnx("cpu%d jitter %lld %lld", cpu, aperf_time, mperf_time); + } + aperf_mperf_retry_count = 0; + + t->aperf = t->aperf * aperf_mperf_multiplier; + t->mperf = t->mperf * aperf_mperf_multiplier; + + return 0; +} + +size_t rapl_counter_info_count_perf(const struct rapl_counter_info_t *rci) +{ + size_t ret = 0; + + for (int i = 0; i < NUM_RAPL_COUNTERS; ++i) + if (rci->source[i] == RAPL_SOURCE_PERF) + ++ret; + + return ret; +} + +void write_rapl_counter(struct rapl_counter *rc, struct rapl_counter_info_t *rci, unsigned int idx) +{ + rc->raw_value = rci->data[idx]; + rc->unit = rci->unit[idx]; + rc->scale = rci->scale[idx]; +} + +int get_rapl_counters(int cpu, int domain, struct core_data *c, struct pkg_data *p) +{ + unsigned long long perf_data[NUM_RAPL_COUNTERS + 1]; + struct rapl_counter_info_t *rci = &rapl_counter_info_perdomain[domain]; + + if (debug) + fprintf(stderr, "%s: cpu%d domain%d\n", __func__, cpu, domain); + + assert(rapl_counter_info_perdomain); + + /* + * If we have any perf counters to read, read them all now, in bulk + */ + if (rci->fd_perf != -1) { + size_t num_perf_counters = rapl_counter_info_count_perf(rci); + const ssize_t expected_read_size = (num_perf_counters + 1) * sizeof(unsigned long long); + const ssize_t actual_read_size = read(rci->fd_perf, &perf_data[0], sizeof(perf_data)); + + if (actual_read_size != expected_read_size) + err(-1, "%s: failed to read perf_data (%zu %zu)", __func__, expected_read_size, + actual_read_size); + } + + for (unsigned int i = 0, pi = 1; i < NUM_RAPL_COUNTERS; ++i) { + switch (rci->source[i]) { + case RAPL_SOURCE_NONE: + break; + + case RAPL_SOURCE_PERF: + assert(pi < ARRAY_SIZE(perf_data)); + assert(rci->fd_perf != -1); + + if (debug) + fprintf(stderr, "Reading rapl counter via perf at %u (%llu %e %lf)\n", + i, perf_data[pi], rci->scale[i], perf_data[pi] * rci->scale[i]); + + rci->data[i] = perf_data[pi]; + + ++pi; + break; + + case RAPL_SOURCE_MSR: + if (debug) + fprintf(stderr, "Reading rapl counter via msr at %u\n", i); + + assert(!no_msr); + if (rci->flags[i] & RAPL_COUNTER_FLAG_USE_MSR_SUM) { + if (get_msr_sum(cpu, rci->msr[i], &rci->data[i])) + return -13 - i; + } else { + if (get_msr(cpu, rci->msr[i], &rci->data[i])) + return -13 - i; + } + + rci->data[i] &= rci->msr_mask[i]; + if (rci->msr_shift[i] >= 0) + rci->data[i] >>= abs(rci->msr_shift[i]); + else + rci->data[i] <<= abs(rci->msr_shift[i]); + + break; + } + } + + _Static_assert(NUM_RAPL_COUNTERS == 7); + write_rapl_counter(&p->energy_pkg, rci, RAPL_RCI_INDEX_ENERGY_PKG); + write_rapl_counter(&p->energy_cores, rci, RAPL_RCI_INDEX_ENERGY_CORES); + write_rapl_counter(&p->energy_dram, rci, RAPL_RCI_INDEX_DRAM); + write_rapl_counter(&p->energy_gfx, rci, RAPL_RCI_INDEX_GFX); + write_rapl_counter(&p->rapl_pkg_perf_status, rci, RAPL_RCI_INDEX_PKG_PERF_STATUS); + write_rapl_counter(&p->rapl_dram_perf_status, rci, RAPL_RCI_INDEX_DRAM_PERF_STATUS); + write_rapl_counter(&c->core_energy, rci, RAPL_RCI_INDEX_CORE_ENERGY); + + return 0; +} + /* * get_counters(...) * migrate to cpu @@ -2709,12 +3453,12 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) { int cpu = t->cpu_id; unsigned long long msr; - int aperf_mperf_retry_count = 0; struct msr_counter *mp; int i; + int status; if (cpu_migrate(cpu)) { - fprintf(outf, "get_counters: Could not migrate to CPU %d\n", cpu); + fprintf(outf, "%s: Could not migrate to CPU %d\n", __func__, cpu); return -1; } @@ -2722,63 +3466,26 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) if (first_counter_read) get_apic_id(t); -retry: + t->tsc = rdtsc(); /* we are running on local CPU of interest */ if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz) || DO_BIC(BIC_IPC) || soft_c1_residency_display(BIC_Avg_MHz)) { - unsigned long long tsc_before, tsc_between, tsc_after, aperf_time, mperf_time; - - /* - * The TSC, APERF and MPERF must be read together for - * APERF/MPERF and MPERF/TSC to give accurate results. - * - * Unfortunately, APERF and MPERF are read by - * individual system call, so delays may occur - * between them. If the time to read them - * varies by a large amount, we re-read them. - */ - - /* - * This initial dummy APERF read has been seen to - * reduce jitter in the subsequent reads. - */ - - if (get_msr(cpu, MSR_IA32_APERF, &t->aperf)) - return -3; - - t->tsc = rdtsc(); /* re-read close to APERF */ - - tsc_before = t->tsc; + int status = -1; - if (get_msr(cpu, MSR_IA32_APERF, &t->aperf)) - return -3; + assert(!no_perf || !no_msr); - tsc_between = rdtsc(); - - if (get_msr(cpu, MSR_IA32_MPERF, &t->mperf)) - return -4; - - tsc_after = rdtsc(); - - aperf_time = tsc_between - tsc_before; - mperf_time = tsc_after - tsc_between; - - /* - * If the system call latency to read APERF and MPERF - * differ by more than 2x, then try again. - */ - if ((aperf_time > (2 * mperf_time)) || (mperf_time > (2 * aperf_time))) { - aperf_mperf_retry_count++; - if (aperf_mperf_retry_count < 5) - goto retry; - else - warnx("cpu%d jitter %lld %lld", cpu, aperf_time, mperf_time); + switch (amperf_source) { + case AMPERF_SOURCE_PERF: + status = read_aperf_mperf_tsc_perf(t, cpu); + break; + case AMPERF_SOURCE_MSR: + status = read_aperf_mperf_tsc_msr(t, cpu); + break; } - aperf_mperf_retry_count = 0; - t->aperf = t->aperf * aperf_mperf_multiplier; - t->mperf = t->mperf * aperf_mperf_multiplier; + if (status != 0) + return status; } if (DO_BIC(BIC_IPC)) @@ -2806,6 +3513,12 @@ retry: if (!is_cpu_first_thread_in_core(t, c, p)) goto done; + if (platform->has_per_core_rapl) { + status = get_rapl_counters(cpu, c->core_id, c, p); + if (status != 0) + return status; + } + if (DO_BIC(BIC_CPU_c3) || soft_c1_residency_display(BIC_CPU_c3)) { if (get_msr(cpu, MSR_CORE_C3_RESIDENCY, &c->c3)) return -6; @@ -2846,12 +3559,6 @@ retry: if (DO_BIC(BIC_CORE_THROT_CNT)) get_core_throt_cnt(cpu, &c->core_throt_cnt); - if (platform->rapl_msrs & RAPL_AMD_F17H) { - if (get_msr(cpu, MSR_CORE_ENERGY_STAT, &msr)) - return -14; - c->core_energy = msr & 0xFFFFFFFF; - } - for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) { if (get_mp(cpu, mp, &c->counter[i])) return -10; @@ -2911,59 +3618,39 @@ retry: if (DO_BIC(BIC_SYS_LPI)) p->sys_lpi = cpuidle_cur_sys_lpi_us; - if (platform->rapl_msrs & RAPL_PKG) { - if (get_msr_sum(cpu, MSR_PKG_ENERGY_STATUS, &msr)) - return -13; - p->energy_pkg = msr; - } - if (platform->rapl_msrs & RAPL_CORE_ENERGY_STATUS) { - if (get_msr_sum(cpu, MSR_PP0_ENERGY_STATUS, &msr)) - return -14; - p->energy_cores = msr; - } - if (platform->rapl_msrs & RAPL_DRAM) { - if (get_msr_sum(cpu, MSR_DRAM_ENERGY_STATUS, &msr)) - return -15; - p->energy_dram = msr; - } - if (platform->rapl_msrs & RAPL_GFX) { - if (get_msr_sum(cpu, MSR_PP1_ENERGY_STATUS, &msr)) - return -16; - p->energy_gfx = msr; - } - if (platform->rapl_msrs & RAPL_PKG_PERF_STATUS) { - if (get_msr_sum(cpu, MSR_PKG_PERF_STATUS, &msr)) - return -16; - p->rapl_pkg_perf_status = msr; - } - if (platform->rapl_msrs & RAPL_DRAM_PERF_STATUS) { - if (get_msr_sum(cpu, MSR_DRAM_PERF_STATUS, &msr)) - return -16; - p->rapl_dram_perf_status = msr; - } - if (platform->rapl_msrs & RAPL_AMD_F17H) { - if (get_msr_sum(cpu, MSR_PKG_ENERGY_STAT, &msr)) - return -13; - p->energy_pkg = msr; + if (!platform->has_per_core_rapl) { + status = get_rapl_counters(cpu, p->package_id, c, p); + if (status != 0) + return status; } + if (DO_BIC(BIC_PkgTmp)) { if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_STATUS, &msr)) return -17; p->pkg_temp_c = tj_max - ((msr >> 16) & 0x7F); } - if (DO_BIC(BIC_GFX_rc6)) - p->gfx_rc6_ms = gfx_cur_rc6_ms; - /* n.b. assume die0 uncore frequency applies to whole package */ if (DO_BIC(BIC_UNCORE_MHZ)) p->uncore_mhz = get_uncore_mhz(p->package_id, 0); + if (DO_BIC(BIC_GFX_rc6)) + p->gfx_rc6_ms = gfx_info[GFX_rc6].val_ull; + if (DO_BIC(BIC_GFXMHz)) - p->gfx_mhz = gfx_cur_mhz; + p->gfx_mhz = gfx_info[GFX_MHz].val; if (DO_BIC(BIC_GFXACTMHz)) - p->gfx_act_mhz = gfx_act_mhz; + p->gfx_act_mhz = gfx_info[GFX_ACTMHz].val; + + if (DO_BIC(BIC_SAM_mc6)) + p->sam_mc6_ms = gfx_info[SAM_mc6].val_ull; + + if (DO_BIC(BIC_SAMMHz)) + p->sam_mhz = gfx_info[SAM_MHz].val; + + if (DO_BIC(BIC_SAMACTMHz)) + p->sam_act_mhz = gfx_info[SAM_ACTMHz].val; for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) { if (get_mp(cpu, mp, &p->counter[i])) @@ -3053,7 +3740,7 @@ void probe_cst_limit(void) unsigned long long msr; int *pkg_cstate_limits; - if (!platform->has_nhm_msrs) + if (!platform->has_nhm_msrs || no_msr) return; switch (platform->cst_limit) { @@ -3097,7 +3784,7 @@ static void dump_platform_info(void) unsigned long long msr; unsigned int ratio; - if (!platform->has_nhm_msrs) + if (!platform->has_nhm_msrs || no_msr) return; get_msr(base_cpu, MSR_PLATFORM_INFO, &msr); @@ -3115,7 +3802,7 @@ static void dump_power_ctl(void) { unsigned long long msr; - if (!platform->has_nhm_msrs) + if (!platform->has_nhm_msrs || no_msr) return; get_msr(base_cpu, MSR_IA32_POWER_CTL, &msr); @@ -3321,7 +4008,7 @@ static void dump_cst_cfg(void) { unsigned long long msr; - if (!platform->has_nhm_msrs) + if (!platform->has_nhm_msrs || no_msr) return; get_msr(base_cpu, MSR_PKG_CST_CONFIG_CONTROL, &msr); @@ -3393,7 +4080,7 @@ void print_irtl(void) { unsigned long long msr; - if (!platform->has_irtl_msrs) + if (!platform->has_irtl_msrs || no_msr) return; if (platform->supported_cstates & PC3) { @@ -3443,12 +4130,64 @@ void free_fd_percpu(void) { int i; + if (!fd_percpu) + return; + for (i = 0; i < topo.max_cpu_num + 1; ++i) { if (fd_percpu[i] != 0) close(fd_percpu[i]); } free(fd_percpu); + fd_percpu = NULL; +} + +void free_fd_amperf_percpu(void) +{ + int i; + + if (!fd_amperf_percpu) + return; + + for (i = 0; i < topo.max_cpu_num + 1; ++i) { + if (fd_amperf_percpu[i].mperf != 0) + close(fd_amperf_percpu[i].mperf); + + if (fd_amperf_percpu[i].aperf != 0) + close(fd_amperf_percpu[i].aperf); + } + + free(fd_amperf_percpu); + fd_amperf_percpu = NULL; +} + +void free_fd_instr_count_percpu(void) +{ + if (!fd_instr_count_percpu) + return; + + for (int i = 0; i < topo.max_cpu_num + 1; ++i) { + if (fd_instr_count_percpu[i] != 0) + close(fd_instr_count_percpu[i]); + } + + free(fd_instr_count_percpu); + fd_instr_count_percpu = NULL; +} + +void free_fd_rapl_percpu(void) +{ + if (!rapl_counter_info_perdomain) + return; + + const int num_domains = platform->has_per_core_rapl ? topo.num_cores : topo.num_packages; + + for (int domain_id = 0; domain_id < num_domains; ++domain_id) { + if (rapl_counter_info_perdomain[domain_id].fd_perf != -1) + close(rapl_counter_info_perdomain[domain_id].fd_perf); + } + + free(rapl_counter_info_perdomain); } void free_all_buffers(void) @@ -3492,6 +4231,9 @@ void free_all_buffers(void) outp = NULL; free_fd_percpu(); + free_fd_instr_count_percpu(); + free_fd_amperf_percpu(); + free_fd_rapl_percpu(); free(irq_column_2_cpu); free(irqs_per_cpu); @@ -3825,11 +4567,17 @@ static void update_effective_set(bool startup) err(1, "%s: cpu str malformat %s\n", PATH_EFFECTIVE_CPUS, cpu_effective_str); } +void linux_perf_init(void); +void rapl_perf_init(void); + void re_initialize(void) { free_all_buffers(); setup_all_buffers(false); - fprintf(outf, "turbostat: re-initialized with num_cpus %d, allowed_cpus %d\n", topo.num_cpus, topo.allowed_cpus); + linux_perf_init(); + rapl_perf_init(); + fprintf(outf, "turbostat: re-initialized with num_cpus %d, allowed_cpus %d\n", topo.num_cpus, + topo.allowed_cpus); } void set_max_cpu_num(void) @@ -3940,85 +4688,43 @@ int snapshot_proc_interrupts(void) } /* - * snapshot_gfx_rc6_ms() + * snapshot_graphics() * - * record snapshot of - * /sys/class/drm/card0/power/rc6_residency_ms + * record snapshot of specified graphics sysfs knob * * return 1 if config change requires a restart, else return 0 */ -int snapshot_gfx_rc6_ms(void) +int snapshot_graphics(int idx) { FILE *fp; int retval; - fp = fopen_or_die("/sys/class/drm/card0/power/rc6_residency_ms", "r"); - - retval = fscanf(fp, "%lld", &gfx_cur_rc6_ms); - if (retval != 1) - err(1, "GFX rc6"); - - fclose(fp); - - return 0; -} - -/* - * snapshot_gfx_mhz() - * - * fall back to /sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz - * when /sys/class/drm/card0/gt_cur_freq_mhz is not available. - * - * return 1 if config change requires a restart, else return 0 - */ -int snapshot_gfx_mhz(void) -{ - static FILE *fp; - int retval; - - if (fp == NULL) { - fp = fopen("/sys/class/drm/card0/gt_cur_freq_mhz", "r"); - if (!fp) - fp = fopen_or_die("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", "r"); - } else { - rewind(fp); - fflush(fp); - } - - retval = fscanf(fp, "%d", &gfx_cur_mhz); - if (retval != 1) - err(1, "GFX MHz"); - - return 0; -} - -/* - * snapshot_gfx_cur_mhz() - * - * fall back to /sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz - * when /sys/class/drm/card0/gt_act_freq_mhz is not available. - * - * return 1 if config change requires a restart, else return 0 - */ -int snapshot_gfx_act_mhz(void) -{ - static FILE *fp; - int retval; - - if (fp == NULL) { - fp = fopen("/sys/class/drm/card0/gt_act_freq_mhz", "r"); - if (!fp) - fp = fopen_or_die("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", "r"); - } else { - rewind(fp); - fflush(fp); + switch (idx) { + case GFX_rc6: + case SAM_mc6: + fp = fopen_or_die(gfx_info[idx].path, "r"); + retval = fscanf(fp, "%lld", &gfx_info[idx].val_ull); + if (retval != 1) + err(1, "rc6"); + fclose(fp); + return 0; + case GFX_MHz: + case GFX_ACTMHz: + case SAM_MHz: + case SAM_ACTMHz: + if (gfx_info[idx].fp == NULL) { + gfx_info[idx].fp = fopen_or_die(gfx_info[idx].path, "r"); + } else { + rewind(gfx_info[idx].fp); + fflush(gfx_info[idx].fp); + } + retval = fscanf(gfx_info[idx].fp, "%d", &gfx_info[idx].val); + if (retval != 1) + err(1, "MHz"); + return 0; + default: + return -EINVAL; } - - retval = fscanf(fp, "%d", &gfx_act_mhz); - if (retval != 1) - err(1, "GFX ACT MHz"); - - return 0; } /* @@ -4083,13 +4789,22 @@ int snapshot_proc_sysfs_files(void) return 1; if (DO_BIC(BIC_GFX_rc6)) - snapshot_gfx_rc6_ms(); + snapshot_graphics(GFX_rc6); if (DO_BIC(BIC_GFXMHz)) - snapshot_gfx_mhz(); + snapshot_graphics(GFX_MHz); if (DO_BIC(BIC_GFXACTMHz)) - snapshot_gfx_act_mhz(); + snapshot_graphics(GFX_ACTMHz); + + if (DO_BIC(BIC_SAM_mc6)) + snapshot_graphics(SAM_mc6); + + if (DO_BIC(BIC_SAMMHz)) + snapshot_graphics(SAM_MHz); + + if (DO_BIC(BIC_SAMACTMHz)) + snapshot_graphics(SAM_ACTMHz); if (DO_BIC(BIC_CPU_LPI)) snapshot_cpu_lpi_us(); @@ -4173,6 +4888,8 @@ int get_msr_sum(int cpu, off_t offset, unsigned long long *msr) int ret, idx; unsigned long long msr_cur, msr_last; + assert(!no_msr); + if (!per_cpu_msr_sum) return 1; @@ -4201,6 +4918,8 @@ static int update_msr_sum(struct thread_data *t, struct core_data *c, struct pkg UNUSED(c); UNUSED(p); + assert(!no_msr); + for (i = IDX_PKG_ENERGY; i < IDX_COUNT; i++) { unsigned long long msr_cur, msr_last; off_t offset; @@ -4280,7 +4999,8 @@ release_msr: /* * set_my_sched_priority(pri) - * return previous + * return previous priority on success + * return value < -20 on failure */ int set_my_sched_priority(int priority) { @@ -4290,16 +5010,16 @@ int set_my_sched_priority(int priority) errno = 0; original_priority = getpriority(PRIO_PROCESS, 0); if (errno && (original_priority == -1)) - err(errno, "getpriority"); + return -21; retval = setpriority(PRIO_PROCESS, 0, priority); if (retval) - errx(retval, "capget(CAP_SYS_NICE) failed,try \"# setcap cap_sys_nice=ep %s\"", progname); + return -21; errno = 0; retval = getpriority(PRIO_PROCESS, 0); if (retval != priority) - err(retval, "getpriority(%d) != setpriority(%d)", retval, priority); + return -21; return original_priority; } @@ -4314,6 +5034,9 @@ void turbostat_loop() /* * elevate own priority for interval mode + * + * ignore on error - we probably don't have permission to set it, but + * it's not a big deal */ set_my_sched_priority(-20); @@ -4399,10 +5122,13 @@ void check_dev_msr() struct stat sb; char pathname[32]; + if (no_msr) + return; + sprintf(pathname, "/dev/cpu/%d/msr", base_cpu); if (stat(pathname, &sb)) if (system("/sbin/modprobe msr > /dev/null 2>&1")) - err(-5, "no /dev/cpu/0/msr, Try \"# modprobe msr\" "); + no_msr = 1; } /* @@ -4414,47 +5140,51 @@ int check_for_cap_sys_rawio(void) { cap_t caps; cap_flag_value_t cap_flag_value; + int ret = 0; caps = cap_get_proc(); if (caps == NULL) - err(-6, "cap_get_proc\n"); + return 1; - if (cap_get_flag(caps, CAP_SYS_RAWIO, CAP_EFFECTIVE, &cap_flag_value)) - err(-6, "cap_get\n"); + if (cap_get_flag(caps, CAP_SYS_RAWIO, CAP_EFFECTIVE, &cap_flag_value)) { + ret = 1; + goto free_and_exit; + } if (cap_flag_value != CAP_SET) { - warnx("capget(CAP_SYS_RAWIO) failed," " try \"# setcap cap_sys_rawio=ep %s\"", progname); - return 1; + ret = 1; + goto free_and_exit; } +free_and_exit: if (cap_free(caps) == -1) err(-6, "cap_free\n"); - return 0; + return ret; } -void check_permissions(void) +void check_msr_permission(void) { - int do_exit = 0; + int failed = 0; char pathname[32]; + if (no_msr) + return; + /* check for CAP_SYS_RAWIO */ - do_exit += check_for_cap_sys_rawio(); + failed += check_for_cap_sys_rawio(); /* test file permissions */ sprintf(pathname, "/dev/cpu/%d/msr", base_cpu); if (euidaccess(pathname, R_OK)) { - do_exit++; - warn("/dev/cpu/0/msr open failed, try chown or chmod +r /dev/cpu/*/msr"); + failed++; } - /* if all else fails, thell them to be root */ - if (do_exit) - if (getuid() != 0) - warnx("... or simply run as root"); - - if (do_exit) - exit(-6); + if (failed) { + warnx("Failed to access %s. Some of the counters may not be available\n" + "\tRun as root to enable them or use %s to disable the access explicitly", pathname, "--no-msr"); + no_msr = 1; + } } void probe_bclk(void) @@ -4462,7 +5192,7 @@ void probe_bclk(void) unsigned long long msr; unsigned int base_ratio; - if (!platform->has_nhm_msrs) + if (!platform->has_nhm_msrs || no_msr) return; if (platform->bclk_freq == BCLK_100MHZ) @@ -4502,7 +5232,7 @@ static void dump_turbo_ratio_info(void) if (!has_turbo) return; - if (!platform->has_nhm_msrs) + if (!platform->has_nhm_msrs || no_msr) return; if (platform->trl_msrs & TRL_LIMIT2) @@ -4567,20 +5297,15 @@ static void dump_sysfs_file(char *path) static void probe_intel_uncore_frequency(void) { int i, j; - char path[128]; + char path[256]; if (!genuine_intel) return; - if (access("/sys/devices/system/cpu/intel_uncore_frequency/package_00_die_00", R_OK)) - return; - - /* Cluster level sysfs not supported yet. */ - if (!access("/sys/devices/system/cpu/intel_uncore_frequency/uncore00", R_OK)) - return; + if (access("/sys/devices/system/cpu/intel_uncore_frequency/package_00_die_00/current_freq_khz", R_OK)) + goto probe_cluster; - if (!access("/sys/devices/system/cpu/intel_uncore_frequency/package_00_die_00/current_freq_khz", R_OK)) - BIC_PRESENT(BIC_UNCORE_MHZ); + BIC_PRESENT(BIC_UNCORE_MHZ); if (quiet) return; @@ -4588,40 +5313,178 @@ static void probe_intel_uncore_frequency(void) for (i = 0; i < topo.num_packages; ++i) { for (j = 0; j < topo.num_die; ++j) { int k, l; + char path_base[128]; + + sprintf(path_base, "/sys/devices/system/cpu/intel_uncore_frequency/package_%02d_die_%02d", i, + j); - sprintf(path, "/sys/devices/system/cpu/intel_uncore_frequency/package_0%d_die_0%d/min_freq_khz", - i, j); + sprintf(path, "%s/min_freq_khz", path_base); k = read_sysfs_int(path); - sprintf(path, "/sys/devices/system/cpu/intel_uncore_frequency/package_0%d_die_0%d/max_freq_khz", - i, j); + sprintf(path, "%s/max_freq_khz", path_base); l = read_sysfs_int(path); - fprintf(outf, "Uncore Frequency pkg%d die%d: %d - %d MHz ", i, j, k / 1000, l / 1000); + fprintf(outf, "Uncore Frequency package%d die%d: %d - %d MHz ", i, j, k / 1000, l / 1000); - sprintf(path, - "/sys/devices/system/cpu/intel_uncore_frequency/package_0%d_die_0%d/initial_min_freq_khz", - i, j); + sprintf(path, "%s/initial_min_freq_khz", path_base); k = read_sysfs_int(path); - sprintf(path, - "/sys/devices/system/cpu/intel_uncore_frequency/package_0%d_die_0%d/initial_max_freq_khz", - i, j); + sprintf(path, "%s/initial_max_freq_khz", path_base); l = read_sysfs_int(path); - fprintf(outf, "(%d - %d MHz)\n", k / 1000, l / 1000); + fprintf(outf, "(%d - %d MHz)", k / 1000, l / 1000); + + sprintf(path, "%s/current_freq_khz", path_base); + k = read_sysfs_int(path); + fprintf(outf, " %d MHz\n", k / 1000); } } + return; + +probe_cluster: + if (access("/sys/devices/system/cpu/intel_uncore_frequency/uncore00/current_freq_khz", R_OK)) + return; + + if (quiet) + return; + + for (i = 0;; ++i) { + int k, l; + char path_base[128]; + int package_id, domain_id, cluster_id; + + sprintf(path_base, "/sys/devices/system/cpu/intel_uncore_frequency/uncore%02d", i); + + if (access(path_base, R_OK)) + break; + + sprintf(path, "%s/package_id", path_base); + package_id = read_sysfs_int(path); + + sprintf(path, "%s/domain_id", path_base); + domain_id = read_sysfs_int(path); + + sprintf(path, "%s/fabric_cluster_id", path_base); + cluster_id = read_sysfs_int(path); + + sprintf(path, "%s/min_freq_khz", path_base); + k = read_sysfs_int(path); + sprintf(path, "%s/max_freq_khz", path_base); + l = read_sysfs_int(path); + fprintf(outf, "Uncore Frequency package%d domain%d cluster%d: %d - %d MHz ", package_id, domain_id, + cluster_id, k / 1000, l / 1000); + + sprintf(path, "%s/initial_min_freq_khz", path_base); + k = read_sysfs_int(path); + sprintf(path, "%s/initial_max_freq_khz", path_base); + l = read_sysfs_int(path); + fprintf(outf, "(%d - %d MHz)", k / 1000, l / 1000); + + sprintf(path, "%s/current_freq_khz", path_base); + k = read_sysfs_int(path); + fprintf(outf, " %d MHz\n", k / 1000); + } } static void probe_graphics(void) { + /* Xe graphics sysfs knobs */ + if (!access("/sys/class/drm/card0/device/tile0/gt0/gtidle/idle_residency_ms", R_OK)) { + FILE *fp; + char buf[8]; + bool gt0_is_gt; + int idx; + + fp = fopen("/sys/class/drm/card0/device/tile0/gt0/gtidle/name", "r"); + if (!fp) + goto next; + + if (!fread(buf, sizeof(char), 7, fp)) { + fclose(fp); + goto next; + } + fclose(fp); + + if (!strncmp(buf, "gt0-rc", strlen("gt0-rc"))) + gt0_is_gt = true; + else if (!strncmp(buf, "gt0-mc", strlen("gt0-mc"))) + gt0_is_gt = false; + else + goto next; + + idx = gt0_is_gt ? GFX_rc6 : SAM_mc6; + gfx_info[idx].path = "/sys/class/drm/card0/device/tile0/gt0/gtidle/idle_residency_ms"; + + idx = gt0_is_gt ? GFX_MHz : SAM_MHz; + if (!access("/sys/class/drm/card0/device/tile0/gt0/freq0/cur_freq", R_OK)) + gfx_info[idx].path = "/sys/class/drm/card0/device/tile0/gt0/freq0/cur_freq"; + + idx = gt0_is_gt ? GFX_ACTMHz : SAM_ACTMHz; + if (!access("/sys/class/drm/card0/device/tile0/gt0/freq0/act_freq", R_OK)) + gfx_info[idx].path = "/sys/class/drm/card0/device/tile0/gt0/freq0/act_freq"; + + idx = gt0_is_gt ? SAM_mc6 : GFX_rc6; + if (!access("/sys/class/drm/card0/device/tile0/gt1/gtidle/idle_residency_ms", R_OK)) + gfx_info[idx].path = "/sys/class/drm/card0/device/tile0/gt1/gtidle/idle_residency_ms"; + + idx = gt0_is_gt ? SAM_MHz : GFX_MHz; + if (!access("/sys/class/drm/card0/device/tile0/gt1/freq0/cur_freq", R_OK)) + gfx_info[idx].path = "/sys/class/drm/card0/device/tile0/gt1/freq0/cur_freq"; + + idx = gt0_is_gt ? SAM_ACTMHz : GFX_ACTMHz; + if (!access("/sys/class/drm/card0/device/tile0/gt1/freq0/act_freq", R_OK)) + gfx_info[idx].path = "/sys/class/drm/card0/device/tile0/gt1/freq0/act_freq"; + + goto end; + } + +next: + /* New i915 graphics sysfs knobs */ + if (!access("/sys/class/drm/card0/gt/gt0/rc6_residency_ms", R_OK)) { + gfx_info[GFX_rc6].path = "/sys/class/drm/card0/gt/gt0/rc6_residency_ms"; + + if (!access("/sys/class/drm/card0/gt/gt0/rps_cur_freq_mhz", R_OK)) + gfx_info[GFX_MHz].path = "/sys/class/drm/card0/gt/gt0/rps_cur_freq_mhz"; + + if (!access("/sys/class/drm/card0/gt/gt0/rps_act_freq_mhz", R_OK)) + gfx_info[GFX_ACTMHz].path = "/sys/class/drm/card0/gt/gt0/rps_act_freq_mhz"; + + if (!access("/sys/class/drm/card0/gt/gt1/rc6_residency_ms", R_OK)) + gfx_info[SAM_mc6].path = "/sys/class/drm/card0/gt/gt1/rc6_residency_ms"; + + if (!access("/sys/class/drm/card0/gt/gt1/rps_cur_freq_mhz", R_OK)) + gfx_info[SAM_MHz].path = "/sys/class/drm/card0/gt/gt1/rps_cur_freq_mhz"; + + if (!access("/sys/class/drm/card0/gt/gt1/rps_act_freq_mhz", R_OK)) + gfx_info[SAM_ACTMHz].path = "/sys/class/drm/card0/gt/gt1/rps_act_freq_mhz"; + + goto end; + } + + /* Fall back to traditional i915 graphics sysfs knobs */ if (!access("/sys/class/drm/card0/power/rc6_residency_ms", R_OK)) - BIC_PRESENT(BIC_GFX_rc6); + gfx_info[GFX_rc6].path = "/sys/class/drm/card0/power/rc6_residency_ms"; + + if (!access("/sys/class/drm/card0/gt_cur_freq_mhz", R_OK)) + gfx_info[GFX_MHz].path = "/sys/class/drm/card0/gt_cur_freq_mhz"; + else if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", R_OK)) + gfx_info[GFX_MHz].path = "/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz"; - if (!access("/sys/class/drm/card0/gt_cur_freq_mhz", R_OK) || - !access("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", R_OK)) - BIC_PRESENT(BIC_GFXMHz); - if (!access("/sys/class/drm/card0/gt_act_freq_mhz", R_OK) || - !access("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", R_OK)) + if (!access("/sys/class/drm/card0/gt_act_freq_mhz", R_OK)) + gfx_info[GFX_ACTMHz].path = "/sys/class/drm/card0/gt_act_freq_mhz"; + else if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", R_OK)) + gfx_info[GFX_ACTMHz].path = "/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz"; + +end: + if (gfx_info[GFX_rc6].path) + BIC_PRESENT(BIC_GFX_rc6); + if (gfx_info[GFX_MHz].path) + BIC_PRESENT(BIC_GFXMHz); + if (gfx_info[GFX_ACTMHz].path) BIC_PRESENT(BIC_GFXACTMHz); + if (gfx_info[SAM_mc6].path) + BIC_PRESENT(BIC_SAM_mc6); + if (gfx_info[SAM_MHz].path) + BIC_PRESENT(BIC_SAMMHz); + if (gfx_info[SAM_ACTMHz].path) + BIC_PRESENT(BIC_SAMACTMHz); } static void dump_sysfs_cstate_config(void) @@ -4783,6 +5646,9 @@ int print_hwp(struct thread_data *t, struct core_data *c, struct pkg_data *p) UNUSED(c); UNUSED(p); + if (no_msr) + return 0; + if (!has_hwp) return 0; @@ -4869,6 +5735,9 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data UNUSED(c); UNUSED(p); + if (no_msr) + return 0; + cpu = t->cpu_id; /* per-package */ @@ -4983,31 +5852,18 @@ void rapl_probe_intel(void) unsigned long long msr; unsigned int time_unit; double tdp; + const unsigned long long bic_watt_bits = BIC_PkgWatt | BIC_CorWatt | BIC_RAMWatt | BIC_GFXWatt; + const unsigned long long bic_joules_bits = BIC_Pkg_J | BIC_Cor_J | BIC_RAM_J | BIC_GFX_J; - if (rapl_joules) { - if (platform->rapl_msrs & RAPL_PKG_ENERGY_STATUS) - BIC_PRESENT(BIC_Pkg_J); - if (platform->rapl_msrs & RAPL_CORE_ENERGY_STATUS) - BIC_PRESENT(BIC_Cor_J); - if (platform->rapl_msrs & RAPL_DRAM_ENERGY_STATUS) - BIC_PRESENT(BIC_RAM_J); - if (platform->rapl_msrs & RAPL_GFX_ENERGY_STATUS) - BIC_PRESENT(BIC_GFX_J); - } else { - if (platform->rapl_msrs & RAPL_PKG_ENERGY_STATUS) - BIC_PRESENT(BIC_PkgWatt); - if (platform->rapl_msrs & RAPL_CORE_ENERGY_STATUS) - BIC_PRESENT(BIC_CorWatt); - if (platform->rapl_msrs & RAPL_DRAM_ENERGY_STATUS) - BIC_PRESENT(BIC_RAMWatt); - if (platform->rapl_msrs & RAPL_GFX_ENERGY_STATUS) - BIC_PRESENT(BIC_GFXWatt); - } + if (rapl_joules) + bic_enabled &= ~bic_watt_bits; + else + bic_enabled &= ~bic_joules_bits; - if (platform->rapl_msrs & RAPL_PKG_PERF_STATUS) - BIC_PRESENT(BIC_PKG__); - if (platform->rapl_msrs & RAPL_DRAM_PERF_STATUS) - BIC_PRESENT(BIC_RAM__); + if (!(platform->rapl_msrs & RAPL_PKG_PERF_STATUS)) + bic_enabled &= ~BIC_PKG__; + if (!(platform->rapl_msrs & RAPL_DRAM_PERF_STATUS)) + bic_enabled &= ~BIC_RAM__; /* units on package 0, verify later other packages match */ if (get_msr(base_cpu, MSR_RAPL_POWER_UNIT, &msr)) @@ -5041,14 +5897,13 @@ void rapl_probe_amd(void) { unsigned long long msr; double tdp; + const unsigned long long bic_watt_bits = BIC_PkgWatt | BIC_CorWatt; + const unsigned long long bic_joules_bits = BIC_Pkg_J | BIC_Cor_J; - if (rapl_joules) { - BIC_PRESENT(BIC_Pkg_J); - BIC_PRESENT(BIC_Cor_J); - } else { - BIC_PRESENT(BIC_PkgWatt); - BIC_PRESENT(BIC_CorWatt); - } + if (rapl_joules) + bic_enabled &= ~bic_watt_bits; + else + bic_enabled &= ~bic_joules_bits; if (get_msr(base_cpu, MSR_RAPL_PWR_UNIT, &msr)) return; @@ -5202,7 +6057,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p) */ void probe_rapl(void) { - if (!platform->rapl_msrs) + if (!platform->rapl_msrs || no_msr) return; if (genuine_intel) @@ -5258,7 +6113,7 @@ int set_temperature_target(struct thread_data *t, struct core_data *c, struct pk } /* Temperature Target MSR is Nehalem and newer only */ - if (!platform->has_nhm_msrs) + if (!platform->has_nhm_msrs || no_msr) goto guess; if (get_msr(base_cpu, MSR_IA32_TEMPERATURE_TARGET, &msr)) @@ -5305,6 +6160,9 @@ int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p UNUSED(c); UNUSED(p); + if (no_msr) + return 0; + if (!(do_dts || do_ptm)) return 0; @@ -5402,6 +6260,9 @@ void decode_feature_control_msr(void) { unsigned long long msr; + if (no_msr) + return; + if (!get_msr(base_cpu, MSR_IA32_FEAT_CTL, &msr)) fprintf(outf, "cpu%d: MSR_IA32_FEATURE_CONTROL: 0x%08llx (%sLocked %s)\n", base_cpu, msr, msr & FEAT_CTL_LOCKED ? "" : "UN-", msr & (1 << 18) ? "SGX" : ""); @@ -5411,6 +6272,9 @@ void decode_misc_enable_msr(void) { unsigned long long msr; + if (no_msr) + return; + if (!genuine_intel) return; @@ -5428,6 +6292,9 @@ void decode_misc_feature_control(void) { unsigned long long msr; + if (no_msr) + return; + if (!platform->has_msr_misc_feature_control) return; @@ -5449,6 +6316,9 @@ void decode_misc_pwr_mgmt_msr(void) { unsigned long long msr; + if (no_msr) + return; + if (!platform->has_msr_misc_pwr_mgmt) return; @@ -5468,6 +6338,9 @@ void decode_c6_demotion_policy_msr(void) { unsigned long long msr; + if (no_msr) + return; + if (!platform->has_msr_c6_demotion_policy_config) return; @@ -5489,7 +6362,8 @@ void print_dev_latency(void) fd = open(path, O_RDONLY); if (fd < 0) { - warnx("capget(CAP_SYS_ADMIN) failed, try \"# setcap cap_sys_admin=ep %s\"", progname); + if (debug) + warnx("Read %s failed", path); return; } @@ -5504,23 +6378,260 @@ void print_dev_latency(void) close(fd); } +static int has_instr_count_access(void) +{ + int fd; + int has_access; + + if (no_perf) + return 0; + + fd = open_perf_counter(base_cpu, PERF_TYPE_HARDWARE, PERF_COUNT_HW_INSTRUCTIONS, -1, 0); + has_access = fd != -1; + + if (fd != -1) + close(fd); + + if (!has_access) + warnx("Failed to access %s. Some of the counters may not be available\n" + "\tRun as root to enable them or use %s to disable the access explicitly", + "instructions retired perf counter", "--no-perf"); + + return has_access; +} + +bool is_aperf_access_required(void) +{ + return BIC_IS_ENABLED(BIC_Avg_MHz) + || BIC_IS_ENABLED(BIC_Busy) + || BIC_IS_ENABLED(BIC_Bzy_MHz) + || BIC_IS_ENABLED(BIC_IPC); +} + +int add_rapl_perf_counter_(int cpu, struct rapl_counter_info_t *rci, const struct rapl_counter_arch_info *cai, + double *scale_, enum rapl_unit *unit_) +{ + if (no_perf) + return -1; + + const double scale = read_perf_rapl_scale(cai->perf_subsys, cai->perf_name); + + if (scale == 0.0) + return -1; + + const enum rapl_unit unit = read_perf_rapl_unit(cai->perf_subsys, cai->perf_name); + + if (unit == RAPL_UNIT_INVALID) + return -1; + + const unsigned int rapl_type = read_perf_type(cai->perf_subsys); + const unsigned int rapl_energy_pkg_config = read_rapl_config(cai->perf_subsys, cai->perf_name); + + const int fd_counter = + open_perf_counter(cpu, rapl_type, rapl_energy_pkg_config, rci->fd_perf, PERF_FORMAT_GROUP); + if (fd_counter == -1) + return -1; + + /* If it's the first counter opened, make it a group descriptor */ + if (rci->fd_perf == -1) + rci->fd_perf = fd_counter; + + *scale_ = scale; + *unit_ = unit; + return fd_counter; +} + +int add_rapl_perf_counter(int cpu, struct rapl_counter_info_t *rci, const struct rapl_counter_arch_info *cai, + double *scale, enum rapl_unit *unit) +{ + int ret = add_rapl_perf_counter_(cpu, rci, cai, scale, unit); + + if (debug) + fprintf(stderr, "%s: %d (cpu: %d)\n", __func__, ret, cpu); + + return ret; +} + /* * Linux-perf manages the HW instructions-retired counter * by enabling when requested, and hiding rollover */ void linux_perf_init(void) { - if (!BIC_IS_ENABLED(BIC_IPC)) - return; - if (access("/proc/sys/kernel/perf_event_paranoid", F_OK)) return; - fd_instr_count_percpu = calloc(topo.max_cpu_num + 1, sizeof(int)); - if (fd_instr_count_percpu == NULL) - err(-1, "calloc fd_instr_count_percpu"); + if (BIC_IS_ENABLED(BIC_IPC) && has_aperf) { + fd_instr_count_percpu = calloc(topo.max_cpu_num + 1, sizeof(int)); + if (fd_instr_count_percpu == NULL) + err(-1, "calloc fd_instr_count_percpu"); + } + + const bool aperf_required = is_aperf_access_required(); + + if (aperf_required && has_aperf && amperf_source == AMPERF_SOURCE_PERF) { + fd_amperf_percpu = calloc(topo.max_cpu_num + 1, sizeof(*fd_amperf_percpu)); + if (fd_amperf_percpu == NULL) + err(-1, "calloc fd_amperf_percpu"); + } +} + +void rapl_perf_init(void) +{ + const int num_domains = platform->has_per_core_rapl ? topo.num_cores : topo.num_packages; + bool *domain_visited = calloc(num_domains, sizeof(bool)); + + rapl_counter_info_perdomain = calloc(num_domains, sizeof(*rapl_counter_info_perdomain)); + if (rapl_counter_info_perdomain == NULL) + err(-1, "calloc rapl_counter_info_percpu"); + + /* + * Initialize rapl_counter_info_percpu + */ + for (int domain_id = 0; domain_id < num_domains; ++domain_id) { + struct rapl_counter_info_t *rci = &rapl_counter_info_perdomain[domain_id]; + + rci->fd_perf = -1; + for (size_t i = 0; i < NUM_RAPL_COUNTERS; ++i) { + rci->data[i] = 0; + rci->source[i] = RAPL_SOURCE_NONE; + } + } - BIC_PRESENT(BIC_IPC); + /* + * Open/probe the counters + * If can't get it via perf, fallback to MSR + */ + for (size_t i = 0; i < ARRAY_SIZE(rapl_counter_arch_infos); ++i) { + + const struct rapl_counter_arch_info *const cai = &rapl_counter_arch_infos[i]; + bool has_counter = 0; + double scale; + enum rapl_unit unit; + int next_domain; + + memset(domain_visited, 0, num_domains * sizeof(*domain_visited)); + + for (int cpu = 0; cpu < topo.max_cpu_num + 1; ++cpu) { + + if (cpu_is_not_allowed(cpu)) + continue; + + /* Skip already seen and handled RAPL domains */ + next_domain = + platform->has_per_core_rapl ? cpus[cpu].physical_core_id : cpus[cpu].physical_package_id; + + if (domain_visited[next_domain]) + continue; + + domain_visited[next_domain] = 1; + + struct rapl_counter_info_t *rci = &rapl_counter_info_perdomain[next_domain]; + + /* Check if the counter is enabled and accessible */ + if (BIC_IS_ENABLED(cai->bic) && (platform->rapl_msrs & cai->feature_mask)) { + + /* Use perf API for this counter */ + if (!no_perf && cai->perf_name + && add_rapl_perf_counter(cpu, rci, cai, &scale, &unit) != -1) { + rci->source[cai->rci_index] = RAPL_SOURCE_PERF; + rci->scale[cai->rci_index] = scale * cai->compat_scale; + rci->unit[cai->rci_index] = unit; + rci->flags[cai->rci_index] = cai->flags; + + /* Use MSR for this counter */ + } else if (!no_msr && cai->msr && probe_msr(cpu, cai->msr) == 0) { + rci->source[cai->rci_index] = RAPL_SOURCE_MSR; + rci->msr[cai->rci_index] = cai->msr; + rci->msr_mask[cai->rci_index] = cai->msr_mask; + rci->msr_shift[cai->rci_index] = cai->msr_shift; + rci->unit[cai->rci_index] = RAPL_UNIT_JOULES; + rci->scale[cai->rci_index] = *cai->platform_rapl_msr_scale * cai->compat_scale; + rci->flags[cai->rci_index] = cai->flags; + } + } + + if (rci->source[cai->rci_index] != RAPL_SOURCE_NONE) + has_counter = 1; + } + + /* If any CPU has access to the counter, make it present */ + if (has_counter) + BIC_PRESENT(cai->bic); + } + + free(domain_visited); +} + +static int has_amperf_access_via_msr(void) +{ + if (no_msr) + return 0; + + if (probe_msr(base_cpu, MSR_IA32_APERF)) + return 0; + + if (probe_msr(base_cpu, MSR_IA32_MPERF)) + return 0; + + return 1; +} + +static int has_amperf_access_via_perf(void) +{ + struct amperf_group_fd fds; + + /* + * Cache the last result, so we don't warn the user multiple times + * + * Negative means cached, no access + * Zero means not cached + * Positive means cached, has access + */ + static int has_access_cached; + + if (no_perf) + return 0; + + if (has_access_cached != 0) + return has_access_cached > 0; + + fds = open_amperf_fd(base_cpu); + has_access_cached = (fds.aperf != -1) && (fds.mperf != -1); + + if (fds.aperf == -1) + warnx("Failed to access %s. Some of the counters may not be available\n" + "\tRun as root to enable them or use %s to disable the access explicitly", + "APERF perf counter", "--no-perf"); + else + close(fds.aperf); + + if (fds.mperf == -1) + warnx("Failed to access %s. Some of the counters may not be available\n" + "\tRun as root to enable them or use %s to disable the access explicitly", + "MPERF perf counter", "--no-perf"); + else + close(fds.mperf); + + if (has_access_cached == 0) + has_access_cached = -1; + + return has_access_cached > 0; +} + +/* Check if we can access APERF and MPERF */ +static int has_amperf_access(void) +{ + if (!is_aperf_access_required()) + return 0; + + if (!no_msr && has_amperf_access_via_msr()) + return 1; + + if (!no_perf && has_amperf_access_via_perf()) + return 1; + + return 0; } void probe_cstates(void) @@ -5563,7 +6674,7 @@ void probe_cstates(void) if (platform->has_msr_module_c6_res_ms) BIC_PRESENT(BIC_Mod_c6); - if (platform->has_ext_cst_msrs) { + if (platform->has_ext_cst_msrs && !no_msr) { BIC_PRESENT(BIC_Totl_c0); BIC_PRESENT(BIC_Any_c0); BIC_PRESENT(BIC_GFX_c0); @@ -5623,6 +6734,7 @@ void process_cpuid() unsigned int eax, ebx, ecx, edx; unsigned int fms, family, model, stepping, ecx_flags, edx_flags; unsigned long long ucode_patch = 0; + bool ucode_patch_valid = false; eax = ebx = ecx = edx = 0; @@ -5650,8 +6762,12 @@ void process_cpuid() ecx_flags = ecx; edx_flags = edx; - if (get_msr(sched_getcpu(), MSR_IA32_UCODE_REV, &ucode_patch)) - warnx("get_msr(UCODE)"); + if (!no_msr) { + if (get_msr(sched_getcpu(), MSR_IA32_UCODE_REV, &ucode_patch)) + warnx("get_msr(UCODE)"); + else + ucode_patch_valid = true; + } /* * check max extended function levels of CPUID. @@ -5662,9 +6778,12 @@ void process_cpuid() __cpuid(0x80000000, max_extended_level, ebx, ecx, edx); if (!quiet) { - fprintf(outf, "CPUID(1): family:model:stepping 0x%x:%x:%x (%d:%d:%d) microcode 0x%x\n", - family, model, stepping, family, model, stepping, - (unsigned int)((ucode_patch >> 32) & 0xFFFFFFFF)); + fprintf(outf, "CPUID(1): family:model:stepping 0x%x:%x:%x (%d:%d:%d)", + family, model, stepping, family, model, stepping); + if (ucode_patch_valid) + fprintf(outf, " microcode 0x%x", (unsigned int)((ucode_patch >> 32) & 0xFFFFFFFF)); + fputc('\n', outf); + fprintf(outf, "CPUID(0x80000000): max_extended_levels: 0x%x\n", max_extended_level); fprintf(outf, "CPUID(1): %s %s %s %s %s %s %s %s %s %s\n", ecx_flags & (1 << 0) ? "SSE3" : "-", @@ -5700,10 +6819,11 @@ void process_cpuid() __cpuid(0x6, eax, ebx, ecx, edx); has_aperf = ecx & (1 << 0); - if (has_aperf) { + if (has_aperf && has_amperf_access()) { BIC_PRESENT(BIC_Avg_MHz); BIC_PRESENT(BIC_Busy); BIC_PRESENT(BIC_Bzy_MHz); + BIC_PRESENT(BIC_IPC); } do_dts = eax & (1 << 0); if (do_dts) @@ -5786,6 +6906,15 @@ void process_cpuid() base_mhz = max_mhz = bus_mhz = edx = 0; __cpuid(0x16, base_mhz, max_mhz, bus_mhz, edx); + + bclk = bus_mhz; + + base_hz = base_mhz * 1000000; + has_base_hz = 1; + + if (platform->enable_tsc_tweak) + tsc_tweak = base_hz / tsc_hz; + if (!quiet) fprintf(outf, "CPUID(0x16): base_mhz: %d max_mhz: %d bus_mhz: %d\n", base_mhz, max_mhz, bus_mhz); @@ -5814,7 +6943,7 @@ void probe_pm_features(void) probe_thermal(); - if (platform->has_nhm_msrs) + if (platform->has_nhm_msrs && !no_msr) BIC_PRESENT(BIC_SMI); if (!quiet) @@ -6142,6 +7271,7 @@ void topology_update(void) topo.allowed_packages = 0; for_all_cpus(update_topo, ODD_COUNTERS); } + void setup_all_buffers(bool startup) { topology_probe(startup); @@ -6169,21 +7299,129 @@ void set_base_cpu(void) err(-ENODEV, "No valid cpus found"); } +static void set_amperf_source(void) +{ + amperf_source = AMPERF_SOURCE_PERF; + + const bool aperf_required = is_aperf_access_required(); + + if (no_perf || !aperf_required || !has_amperf_access_via_perf()) + amperf_source = AMPERF_SOURCE_MSR; + + if (quiet || !debug) + return; + + fprintf(outf, "aperf/mperf source preference: %s\n", amperf_source == AMPERF_SOURCE_MSR ? "msr" : "perf"); +} + +bool has_added_counters(void) +{ + /* + * It only makes sense to call this after the command line is parsed, + * otherwise sys structure is not populated. + */ + + return sys.added_core_counters | sys.added_thread_counters | sys.added_package_counters; +} + +bool is_msr_access_required(void) +{ + if (no_msr) + return false; + + if (has_added_counters()) + return true; + + return BIC_IS_ENABLED(BIC_SMI) + || BIC_IS_ENABLED(BIC_CPU_c1) + || BIC_IS_ENABLED(BIC_CPU_c3) + || BIC_IS_ENABLED(BIC_CPU_c6) + || BIC_IS_ENABLED(BIC_CPU_c7) + || BIC_IS_ENABLED(BIC_Mod_c6) + || BIC_IS_ENABLED(BIC_CoreTmp) + || BIC_IS_ENABLED(BIC_Totl_c0) + || BIC_IS_ENABLED(BIC_Any_c0) + || BIC_IS_ENABLED(BIC_GFX_c0) + || BIC_IS_ENABLED(BIC_CPUGFX) + || BIC_IS_ENABLED(BIC_Pkgpc3) + || BIC_IS_ENABLED(BIC_Pkgpc6) + || BIC_IS_ENABLED(BIC_Pkgpc2) + || BIC_IS_ENABLED(BIC_Pkgpc7) + || BIC_IS_ENABLED(BIC_Pkgpc8) + || BIC_IS_ENABLED(BIC_Pkgpc9) + || BIC_IS_ENABLED(BIC_Pkgpc10) + /* TODO: Multiplex access with perf */ + || BIC_IS_ENABLED(BIC_CorWatt) + || BIC_IS_ENABLED(BIC_Cor_J) + || BIC_IS_ENABLED(BIC_PkgWatt) + || BIC_IS_ENABLED(BIC_CorWatt) + || BIC_IS_ENABLED(BIC_GFXWatt) + || BIC_IS_ENABLED(BIC_RAMWatt) + || BIC_IS_ENABLED(BIC_Pkg_J) + || BIC_IS_ENABLED(BIC_Cor_J) + || BIC_IS_ENABLED(BIC_GFX_J) + || BIC_IS_ENABLED(BIC_RAM_J) + || BIC_IS_ENABLED(BIC_PKG__) + || BIC_IS_ENABLED(BIC_RAM__) + || BIC_IS_ENABLED(BIC_PkgTmp) + || (is_aperf_access_required() && !has_amperf_access_via_perf()); +} + +void check_msr_access(void) +{ + if (!is_msr_access_required()) + no_msr = 1; + + check_dev_msr(); + check_msr_permission(); + + if (no_msr) + bic_disable_msr_access(); +} + +void check_perf_access(void) +{ + const bool intrcount_required = BIC_IS_ENABLED(BIC_IPC); + + if (no_perf || !intrcount_required || !has_instr_count_access()) + bic_enabled &= ~BIC_IPC; + + const bool aperf_required = is_aperf_access_required(); + + if (!aperf_required || !has_amperf_access()) { + bic_enabled &= ~BIC_Avg_MHz; + bic_enabled &= ~BIC_Busy; + bic_enabled &= ~BIC_Bzy_MHz; + bic_enabled &= ~BIC_IPC; + } +} + void turbostat_init() { setup_all_buffers(true); set_base_cpu(); - check_dev_msr(); - check_permissions(); + check_msr_access(); + check_perf_access(); process_cpuid(); probe_pm_features(); + set_amperf_source(); linux_perf_init(); + rapl_perf_init(); for_all_cpus(get_cpu_type, ODD_COUNTERS); for_all_cpus(get_cpu_type, EVEN_COUNTERS); if (DO_BIC(BIC_IPC)) (void)get_instr_count_fd(base_cpu); + + /* + * If TSC tweak is needed, but couldn't get it, + * disable more BICs, since it can't be reported accurately. + */ + if (platform->enable_tsc_tweak && !has_base_hz) { + bic_enabled &= ~BIC_Busy; + bic_enabled &= ~BIC_Bzy_MHz; + } } int fork_it(char **argv) @@ -6259,7 +7497,7 @@ int get_and_dump_counters(void) void print_version() { - fprintf(outf, "turbostat version 2023.11.07 - Len Brown <lenb@kernel.org>\n"); + fprintf(outf, "turbostat version 2024.04.08 - Len Brown <lenb@kernel.org>\n"); } #define COMMAND_LINE_SIZE 2048 @@ -6291,6 +7529,9 @@ int add_counter(unsigned int msr_num, char *path, char *name, { struct msr_counter *msrp; + if (no_msr && msr_num) + errx(1, "Requested MSR counter 0x%x, but in --no-msr mode", msr_num); + msrp = calloc(1, sizeof(struct msr_counter)); if (msrp == NULL) { perror("calloc"); @@ -6595,6 +7836,8 @@ void cmdline(int argc, char **argv) { "list", no_argument, 0, 'l' }, { "out", required_argument, 0, 'o' }, { "quiet", no_argument, 0, 'q' }, + { "no-msr", no_argument, 0, 'M' }, + { "no-perf", no_argument, 0, 'P' }, { "show", required_argument, 0, 's' }, { "Summary", no_argument, 0, 'S' }, { "TCC", required_argument, 0, 'T' }, @@ -6604,7 +7847,25 @@ void cmdline(int argc, char **argv) progname = argv[0]; - while ((opt = getopt_long_only(argc, argv, "+C:c:Dde:hi:Jn:o:qST:v", long_options, &option_index)) != -1) { + /* + * Parse some options early, because they may make other options invalid, + * like adding the MSR counter with --add and at the same time using --no-msr. + */ + while ((opt = getopt_long_only(argc, argv, "MP", long_options, &option_index)) != -1) { + switch (opt) { + case 'M': + no_msr = 1; + break; + case 'P': + no_perf = 1; + break; + default: + break; + } + } + optind = 0; + + while ((opt = getopt_long_only(argc, argv, "+C:c:Dde:hi:Jn:o:qMST:v", long_options, &option_index)) != -1) { switch (opt) { case 'a': parse_add_command(optarg); @@ -6662,6 +7923,10 @@ void cmdline(int argc, char **argv) case 'q': quiet = 1; break; + case 'M': + case 'P': + /* Parsed earlier */ + break; case 'n': num_iterations = strtod(optarg, NULL); @@ -6704,6 +7969,22 @@ void cmdline(int argc, char **argv) } } +void set_rlimit(void) +{ + struct rlimit limit; + + if (getrlimit(RLIMIT_NOFILE, &limit) < 0) + err(1, "Failed to get rlimit"); + + if (limit.rlim_max < MAX_NOFILE) + limit.rlim_max = MAX_NOFILE; + if (limit.rlim_cur < MAX_NOFILE) + limit.rlim_cur = MAX_NOFILE; + + if (setrlimit(RLIMIT_NOFILE, &limit) < 0) + err(1, "Failed to set rlimit"); +} + int main(int argc, char **argv) { int fd, ret; @@ -6729,9 +8010,13 @@ skip_cgroup_setting: probe_sysfs(); + if (!getuid()) + set_rlimit(); + turbostat_init(); - msr_sum_record(); + if (!no_msr) + msr_sum_record(); /* dump counters and exit */ if (dump_only) diff --git a/tools/testing/cxl/test/cxl.c b/tools/testing/cxl/test/cxl.c index 908e0d083936..61c69297e797 100644 --- a/tools/testing/cxl/test/cxl.c +++ b/tools/testing/cxl/test/cxl.c @@ -986,10 +986,12 @@ static void dpa_perf_setup(struct cxl_port *endpoint, struct range *range, { dpa_perf->qos_class = FAKE_QTG_ID; dpa_perf->dpa_range = *range; - dpa_perf->coord.read_latency = 500; - dpa_perf->coord.write_latency = 500; - dpa_perf->coord.read_bandwidth = 1000; - dpa_perf->coord.write_bandwidth = 1000; + for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) { + dpa_perf->coord[i].read_latency = 500; + dpa_perf->coord[i].write_latency = 500; + dpa_perf->coord[i].read_bandwidth = 1000; + dpa_perf->coord[i].write_bandwidth = 1000; + } } static void mock_cxl_endpoint_parse_cdat(struct cxl_port *port) diff --git a/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc b/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc index b1ede6249866..b7c8f29c09a9 100644 --- a/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc +++ b/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc @@ -18,7 +18,7 @@ echo 'sched:*' > set_event yield -count=`cat trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` +count=`head -n 100 trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` if [ $count -lt 3 ]; then fail "at least fork, exec and exit events should be recorded" fi @@ -29,7 +29,7 @@ echo 1 > events/sched/enable yield -count=`cat trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` +count=`head -n 100 trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` if [ $count -lt 3 ]; then fail "at least fork, exec and exit events should be recorded" fi @@ -40,7 +40,7 @@ echo 0 > events/sched/enable yield -count=`cat trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` +count=`head -n 100 trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` if [ $count -ne 0 ]; then fail "any of scheduler events should not be recorded" fi diff --git a/tools/testing/selftests/iommu/config b/tools/testing/selftests/iommu/config index 110d73917615..02a2a1b267c1 100644 --- a/tools/testing/selftests/iommu/config +++ b/tools/testing/selftests/iommu/config @@ -1,3 +1,5 @@ CONFIG_IOMMUFD=y +CONFIG_FAULT_INJECTION_DEBUG_FS=y CONFIG_FAULT_INJECTION=y CONFIG_IOMMUFD_TEST=y +CONFIG_FAILSLAB=y diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h index 541bf192e30e..14bbab0cce13 100644 --- a/tools/testing/selftests/kselftest.h +++ b/tools/testing/selftests/kselftest.h @@ -51,6 +51,7 @@ #include <stdarg.h> #include <string.h> #include <stdio.h> +#include <sys/utsname.h> #endif #ifndef ARRAY_SIZE @@ -79,6 +80,9 @@ #define KSFT_XPASS 3 #define KSFT_SKIP 4 +#ifndef __noreturn +#define __noreturn __attribute__((__noreturn__)) +#endif #define __printf(a, b) __attribute__((format(printf, a, b))) /* counters */ @@ -288,24 +292,26 @@ void ksft_test_result_code(int exit_code, const char *test_name, } /* Docs seem to call for double space if directive is absent */ - if (!directive[0] && msg[0]) + if (!directive[0] && msg) directive = " # "; - va_start(args, msg); printf("%s %u %s%s", tap_code, ksft_test_num(), test_name, directive); errno = saved_errno; - vprintf(msg, args); + if (msg) { + va_start(args, msg); + vprintf(msg, args); + va_end(args); + } printf("\n"); - va_end(args); } -static inline int ksft_exit_pass(void) +static inline __noreturn int ksft_exit_pass(void) { ksft_print_cnts(); exit(KSFT_PASS); } -static inline int ksft_exit_fail(void) +static inline __noreturn int ksft_exit_fail(void) { ksft_print_cnts(); exit(KSFT_FAIL); @@ -332,7 +338,7 @@ static inline int ksft_exit_fail(void) ksft_cnt.ksft_xfail + \ ksft_cnt.ksft_xskip) -static inline __printf(1, 2) int ksft_exit_fail_msg(const char *msg, ...) +static inline __noreturn __printf(1, 2) int ksft_exit_fail_msg(const char *msg, ...) { int saved_errno = errno; va_list args; @@ -347,19 +353,19 @@ static inline __printf(1, 2) int ksft_exit_fail_msg(const char *msg, ...) exit(KSFT_FAIL); } -static inline int ksft_exit_xfail(void) +static inline __noreturn int ksft_exit_xfail(void) { ksft_print_cnts(); exit(KSFT_XFAIL); } -static inline int ksft_exit_xpass(void) +static inline __noreturn int ksft_exit_xpass(void) { ksft_print_cnts(); exit(KSFT_XPASS); } -static inline __printf(1, 2) int ksft_exit_skip(const char *msg, ...) +static inline __noreturn __printf(1, 2) int ksft_exit_skip(const char *msg, ...) { int saved_errno = errno; va_list args; @@ -388,4 +394,21 @@ static inline __printf(1, 2) int ksft_exit_skip(const char *msg, ...) exit(KSFT_SKIP); } +static inline int ksft_min_kernel_version(unsigned int min_major, + unsigned int min_minor) +{ +#ifdef NOLIBC + ksft_print_msg("NOLIBC: Can't check kernel version: Function not implemented\n"); + return 0; +#else + unsigned int major, minor; + struct utsname info; + + if (uname(&info) || sscanf(info.release, "%u.%u.", &major, &minor) != 2) + ksft_exit_fail_msg("Can't parse kernel version\n"); + + return major > min_major || (major == min_major && minor >= min_minor); +#endif +} + #endif /* __KSELFTEST_H */ diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index 4fd735e48ee7..ba3ddeda24bf 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -383,6 +383,7 @@ FIXTURE_DATA(fixture_name) self; \ pid_t child = 1; \ int status = 0; \ + bool jmp = false; \ memset(&self, 0, sizeof(FIXTURE_DATA(fixture_name))); \ if (setjmp(_metadata->env) == 0) { \ /* Use the same _metadata. */ \ @@ -399,8 +400,10 @@ _metadata->exit_code = KSFT_FAIL; \ } \ } \ + else \ + jmp = true; \ if (child == 0) { \ - if (_metadata->setup_completed && !_metadata->teardown_parent) \ + if (_metadata->setup_completed && !_metadata->teardown_parent && !jmp) \ fixture_name##_teardown(_metadata, &self, variant->data); \ _exit(0); \ } \ @@ -1202,7 +1205,7 @@ void __run_test(struct __fixture_metadata *f, diagnostic = "unknown"; ksft_test_result_code(t->exit_code, test_name, - diagnostic ? "%s" : "", diagnostic); + diagnostic ? "%s" : NULL, diagnostic); } static int test_harness_run(int argc, char **argv) diff --git a/tools/testing/selftests/kvm/aarch64/arch_timer.c b/tools/testing/selftests/kvm/aarch64/arch_timer.c index ddba2c2fb5de..4eaba83cdcf3 100644 --- a/tools/testing/selftests/kvm/aarch64/arch_timer.c +++ b/tools/testing/selftests/kvm/aarch64/arch_timer.c @@ -135,8 +135,8 @@ static void guest_run_stage(struct test_vcpu_shared_data *shared_data, irq_iter = READ_ONCE(shared_data->nr_iter); __GUEST_ASSERT(config_iter + 1 == irq_iter, - "config_iter + 1 = 0x%lx, irq_iter = 0x%lx.\n" - " Guest timer interrupt was not trigged within the specified\n" + "config_iter + 1 = 0x%x, irq_iter = 0x%x.\n" + " Guest timer interrupt was not triggered within the specified\n" " interval, try to increase the error margin by [-e] option.\n", config_iter + 1, irq_iter); } diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 3bd03b088dda..81ce37ec407d 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -1037,8 +1037,19 @@ static inline void vcpu_set_cpuid(struct kvm_vcpu *vcpu) void vcpu_set_cpuid_property(struct kvm_vcpu *vcpu, struct kvm_x86_cpu_property property, uint32_t value); +void vcpu_set_cpuid_maxphyaddr(struct kvm_vcpu *vcpu, uint8_t maxphyaddr); void vcpu_clear_cpuid_entry(struct kvm_vcpu *vcpu, uint32_t function); + +static inline bool vcpu_cpuid_has(struct kvm_vcpu *vcpu, + struct kvm_x86_cpu_feature feature) +{ + struct kvm_cpuid_entry2 *entry; + + entry = __vcpu_get_cpuid_entry(vcpu, feature.function, feature.index); + return *((&entry->eax) + feature.reg) & BIT(feature.bit); +} + void vcpu_set_or_clear_cpuid_feature(struct kvm_vcpu *vcpu, struct kvm_x86_cpu_feature feature, bool set); diff --git a/tools/testing/selftests/kvm/max_guest_memory_test.c b/tools/testing/selftests/kvm/max_guest_memory_test.c index 6628dc4dda89..1a6da7389bf1 100644 --- a/tools/testing/selftests/kvm/max_guest_memory_test.c +++ b/tools/testing/selftests/kvm/max_guest_memory_test.c @@ -22,10 +22,11 @@ static void guest_code(uint64_t start_gpa, uint64_t end_gpa, uint64_t stride) { uint64_t gpa; - for (gpa = start_gpa; gpa < end_gpa; gpa += stride) - *((volatile uint64_t *)gpa) = gpa; - - GUEST_DONE(); + for (;;) { + for (gpa = start_gpa; gpa < end_gpa; gpa += stride) + *((volatile uint64_t *)gpa) = gpa; + GUEST_SYNC(0); + } } struct vcpu_info { @@ -55,7 +56,7 @@ static void rendezvous_with_boss(void) static void run_vcpu(struct kvm_vcpu *vcpu) { vcpu_run(vcpu); - TEST_ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_DONE); + TEST_ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_SYNC); } static void *vcpu_worker(void *data) @@ -64,17 +65,13 @@ static void *vcpu_worker(void *data) struct kvm_vcpu *vcpu = info->vcpu; struct kvm_vm *vm = vcpu->vm; struct kvm_sregs sregs; - struct kvm_regs regs; vcpu_args_set(vcpu, 3, info->start_gpa, info->end_gpa, vm->page_size); - /* Snapshot regs before the first run. */ - vcpu_regs_get(vcpu, ®s); rendezvous_with_boss(); run_vcpu(vcpu); rendezvous_with_boss(); - vcpu_regs_set(vcpu, ®s); vcpu_sregs_get(vcpu, &sregs); #ifdef __x86_64__ /* Toggle CR0.WP to trigger a MMU context reset. */ diff --git a/tools/testing/selftests/kvm/riscv/arch_timer.c b/tools/testing/selftests/kvm/riscv/arch_timer.c index e22848f747c0..0f9cabd99fd4 100644 --- a/tools/testing/selftests/kvm/riscv/arch_timer.c +++ b/tools/testing/selftests/kvm/riscv/arch_timer.c @@ -60,7 +60,7 @@ static void guest_run(struct test_vcpu_shared_data *shared_data) irq_iter = READ_ONCE(shared_data->nr_iter); __GUEST_ASSERT(config_iter + 1 == irq_iter, "config_iter + 1 = 0x%x, irq_iter = 0x%x.\n" - " Guest timer interrupt was not trigged within the specified\n" + " Guest timer interrupt was not triggered within the specified\n" " interval, try to increase the error margin by [-e] option.\n", config_iter + 1, irq_iter); } diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c index 06b43ed23580..bd57d991e27d 100644 --- a/tools/testing/selftests/kvm/set_memory_region_test.c +++ b/tools/testing/selftests/kvm/set_memory_region_test.c @@ -333,7 +333,7 @@ static void test_invalid_memory_region_flags(void) struct kvm_vm *vm; int r, i; -#if defined __aarch64__ || defined __x86_64__ +#if defined __aarch64__ || defined __riscv || defined __x86_64__ supported_flags |= KVM_MEM_READONLY; #endif 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 9e2879af7c20..40cc59f4e650 100644 --- a/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c +++ b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c @@ -133,6 +133,43 @@ static void enter_guest(struct kvm_vcpu *vcpu) } } +static void test_pv_unhalt(void) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + struct kvm_cpuid_entry2 *ent; + u32 kvm_sig_old; + + pr_info("testing KVM_FEATURE_PV_UNHALT\n"); + + TEST_REQUIRE(KVM_CAP_X86_DISABLE_EXITS); + + /* KVM_PV_UNHALT test */ + vm = vm_create_with_one_vcpu(&vcpu, guest_main); + vcpu_set_cpuid_feature(vcpu, X86_FEATURE_KVM_PV_UNHALT); + + TEST_ASSERT(vcpu_cpuid_has(vcpu, X86_FEATURE_KVM_PV_UNHALT), + "Enabling X86_FEATURE_KVM_PV_UNHALT had no effect"); + + /* Make sure KVM clears vcpu->arch.kvm_cpuid */ + ent = vcpu_get_cpuid_entry(vcpu, KVM_CPUID_SIGNATURE); + kvm_sig_old = ent->ebx; + ent->ebx = 0xdeadbeef; + vcpu_set_cpuid(vcpu); + + vm_enable_cap(vm, KVM_CAP_X86_DISABLE_EXITS, KVM_X86_DISABLE_EXITS_HLT); + ent = vcpu_get_cpuid_entry(vcpu, KVM_CPUID_SIGNATURE); + ent->ebx = kvm_sig_old; + vcpu_set_cpuid(vcpu); + + TEST_ASSERT(!vcpu_cpuid_has(vcpu, X86_FEATURE_KVM_PV_UNHALT), + "KVM_FEATURE_PV_UNHALT is set with KVM_CAP_X86_DISABLE_EXITS"); + + /* FIXME: actually test KVM_FEATURE_PV_UNHALT feature */ + + kvm_vm_free(vm); +} + int main(void) { struct kvm_vcpu *vcpu; @@ -151,4 +188,6 @@ int main(void) enter_guest(vcpu); kvm_vm_free(vm); + + test_pv_unhalt(); } diff --git a/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c b/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c index 29609b52f8fa..26c85815f7e9 100644 --- a/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c +++ b/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c @@ -416,12 +416,30 @@ static void guest_rd_wr_counters(uint32_t base_msr, uint8_t nr_possible_counters static void guest_test_gp_counters(void) { + uint8_t pmu_version = guest_get_pmu_version(); uint8_t nr_gp_counters = 0; uint32_t base_msr; - if (guest_get_pmu_version()) + if (pmu_version) nr_gp_counters = this_cpu_property(X86_PROPERTY_PMU_NR_GP_COUNTERS); + /* + * For v2+ PMUs, PERF_GLOBAL_CTRL's architectural post-RESET value is + * "Sets bits n-1:0 and clears the upper bits", where 'n' is the number + * of GP counters. If there are no GP counters, require KVM to leave + * PERF_GLOBAL_CTRL '0'. This edge case isn't covered by the SDM, but + * follow the spirit of the architecture and only globally enable GP + * counters, of which there are none. + */ + if (pmu_version > 1) { + uint64_t global_ctrl = rdmsr(MSR_CORE_PERF_GLOBAL_CTRL); + + if (nr_gp_counters) + GUEST_ASSERT_EQ(global_ctrl, GENMASK_ULL(nr_gp_counters - 1, 0)); + else + GUEST_ASSERT_EQ(global_ctrl, 0); + } + if (this_cpu_has(X86_FEATURE_PDCM) && rdmsr(MSR_IA32_PERF_CAPABILITIES) & PMU_CAP_FW_WRITES) base_msr = MSR_IA32_PMC0; 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 7f6f5f23fb9b..977948fd52e6 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 @@ -28,16 +28,16 @@ #define NESTED_TEST_MEM1 0xc0001000 #define NESTED_TEST_MEM2 0xc0002000 -static void l2_guest_code(void) +static void l2_guest_code(u64 *a, u64 *b) { - *(volatile uint64_t *)NESTED_TEST_MEM1; - *(volatile uint64_t *)NESTED_TEST_MEM1 = 1; + READ_ONCE(*a); + WRITE_ONCE(*a, 1); GUEST_SYNC(true); GUEST_SYNC(false); - *(volatile uint64_t *)NESTED_TEST_MEM2 = 1; + WRITE_ONCE(*b, 1); GUEST_SYNC(true); - *(volatile uint64_t *)NESTED_TEST_MEM2 = 1; + WRITE_ONCE(*b, 1); GUEST_SYNC(true); GUEST_SYNC(false); @@ -45,17 +45,33 @@ static void l2_guest_code(void) vmcall(); } +static void l2_guest_code_ept_enabled(void) +{ + l2_guest_code((u64 *)NESTED_TEST_MEM1, (u64 *)NESTED_TEST_MEM2); +} + +static void l2_guest_code_ept_disabled(void) +{ + /* Access the same L1 GPAs as l2_guest_code_ept_enabled() */ + l2_guest_code((u64 *)GUEST_TEST_MEM, (u64 *)GUEST_TEST_MEM); +} + void l1_guest_code(struct vmx_pages *vmx) { #define L2_GUEST_STACK_SIZE 64 unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + void *l2_rip; GUEST_ASSERT(vmx->vmcs_gpa); GUEST_ASSERT(prepare_for_vmx_operation(vmx)); GUEST_ASSERT(load_vmcs(vmx)); - prepare_vmcs(vmx, l2_guest_code, - &l2_guest_stack[L2_GUEST_STACK_SIZE]); + if (vmx->eptp_gpa) + l2_rip = l2_guest_code_ept_enabled; + else + l2_rip = l2_guest_code_ept_disabled; + + prepare_vmcs(vmx, l2_rip, &l2_guest_stack[L2_GUEST_STACK_SIZE]); GUEST_SYNC(false); GUEST_ASSERT(!vmlaunch()); @@ -64,7 +80,7 @@ void l1_guest_code(struct vmx_pages *vmx) GUEST_DONE(); } -int main(int argc, char *argv[]) +static void test_vmx_dirty_log(bool enable_ept) { vm_vaddr_t vmx_pages_gva = 0; struct vmx_pages *vmx; @@ -76,8 +92,7 @@ int main(int argc, char *argv[]) struct ucall uc; bool done = false; - TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); - TEST_REQUIRE(kvm_cpu_has_ept()); + pr_info("Nested EPT: %s\n", enable_ept ? "enabled" : "disabled"); /* Create VM */ vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); @@ -103,11 +118,16 @@ int main(int argc, char *argv[]) * * Note that prepare_eptp should be called only L1's GPA map is done, * meaning after the last call to virt_map. + * + * When EPT is disabled, the L2 guest code will still access the same L1 + * GPAs as the EPT enabled case. */ - prepare_eptp(vmx, vm, 0); - nested_map_memslot(vmx, vm, 0); - nested_map(vmx, vm, NESTED_TEST_MEM1, GUEST_TEST_MEM, 4096); - nested_map(vmx, vm, NESTED_TEST_MEM2, GUEST_TEST_MEM, 4096); + if (enable_ept) { + prepare_eptp(vmx, vm, 0); + nested_map_memslot(vmx, vm, 0); + nested_map(vmx, vm, NESTED_TEST_MEM1, GUEST_TEST_MEM, 4096); + nested_map(vmx, vm, NESTED_TEST_MEM2, GUEST_TEST_MEM, 4096); + } bmap = bitmap_zalloc(TEST_MEM_PAGES); host_test_mem = addr_gpa2hva(vm, GUEST_TEST_MEM); @@ -148,3 +168,15 @@ int main(int argc, char *argv[]) } } } + +int main(int argc, char *argv[]) +{ + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); + + test_vmx_dirty_log(/*enable_ept=*/false); + + if (kvm_cpu_has_ept()) + test_vmx_dirty_log(/*enable_ept=*/true); + + return 0; +} diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h index c02990bbd56f..9007c420d52c 100644 --- a/tools/testing/selftests/mm/vm_util.h +++ b/tools/testing/selftests/mm/vm_util.h @@ -3,7 +3,7 @@ #include <stdbool.h> #include <sys/mman.h> #include <err.h> -#include <string.h> /* ffsl() */ +#include <strings.h> /* ffsl() */ #include <unistd.h> /* _SC_PAGESIZE */ #define BIT_ULL(nr) (1ULL << (nr)) diff --git a/tools/testing/selftests/net/bind_wildcard.c b/tools/testing/selftests/net/bind_wildcard.c index a2662348cdb1..b7b54d646b93 100644 --- a/tools/testing/selftests/net/bind_wildcard.c +++ b/tools/testing/selftests/net/bind_wildcard.c @@ -6,7 +6,9 @@ #include "../kselftest_harness.h" -struct in6_addr in6addr_v4mapped_any = { +static const __u32 in4addr_any = INADDR_ANY; +static const __u32 in4addr_loopback = INADDR_LOOPBACK; +static const struct in6_addr in6addr_v4mapped_any = { .s6_addr = { 0, 0, 0, 0, 0, 0, 0, 0, @@ -14,8 +16,7 @@ struct in6_addr in6addr_v4mapped_any = { 0, 0, 0, 0 } }; - -struct in6_addr in6addr_v4mapped_loopback = { +static const struct in6_addr in6addr_v4mapped_loopback = { .s6_addr = { 0, 0, 0, 0, 0, 0, 0, 0, @@ -24,137 +25,785 @@ struct in6_addr in6addr_v4mapped_loopback = { } }; +#define NR_SOCKETS 8 + FIXTURE(bind_wildcard) { - struct sockaddr_in addr4; - struct sockaddr_in6 addr6; + int fd[NR_SOCKETS]; + socklen_t addrlen[NR_SOCKETS]; + union { + struct sockaddr addr; + struct sockaddr_in addr4; + struct sockaddr_in6 addr6; + } addr[NR_SOCKETS]; }; FIXTURE_VARIANT(bind_wildcard) { - const __u32 addr4_const; - const struct in6_addr *addr6_const; - int expected_errno; + sa_family_t family[2]; + const void *addr[2]; + bool ipv6_only[2]; + + /* 6 bind() calls below follow two bind() for the defined 2 addresses: + * + * 0.0.0.0 + * 127.0.0.1 + * :: + * ::1 + * ::ffff:0.0.0.0 + * ::ffff:127.0.0.1 + */ + int expected_errno[NR_SOCKETS]; + int expected_reuse_errno[NR_SOCKETS]; +}; + +/* (IPv4, IPv4) */ +FIXTURE_VARIANT_ADD(bind_wildcard, v4_any_v4_local) +{ + .family = {AF_INET, AF_INET}, + .addr = {&in4addr_any, &in4addr_loopback}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v4_local_v4_any) +{ + .family = {AF_INET, AF_INET}, + .addr = {&in4addr_loopback, &in4addr_any}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, }; +/* (IPv4, IPv6) */ FIXTURE_VARIANT_ADD(bind_wildcard, v4_any_v6_any) { - .addr4_const = INADDR_ANY, - .addr6_const = &in6addr_any, - .expected_errno = EADDRINUSE, + .family = {AF_INET, AF_INET6}, + .addr = {&in4addr_any, &in6addr_any}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v4_any_v6_any_only) +{ + .family = {AF_INET, AF_INET6}, + .addr = {&in4addr_any, &in6addr_any}, + .ipv6_only = {false, true}, + .expected_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, }; FIXTURE_VARIANT_ADD(bind_wildcard, v4_any_v6_local) { - .addr4_const = INADDR_ANY, - .addr6_const = &in6addr_loopback, - .expected_errno = 0, + .family = {AF_INET, AF_INET6}, + .addr = {&in4addr_any, &in6addr_loopback}, + .expected_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, }; FIXTURE_VARIANT_ADD(bind_wildcard, v4_any_v6_v4mapped_any) { - .addr4_const = INADDR_ANY, - .addr6_const = &in6addr_v4mapped_any, - .expected_errno = EADDRINUSE, + .family = {AF_INET, AF_INET6}, + .addr = {&in4addr_any, &in6addr_v4mapped_any}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, }; FIXTURE_VARIANT_ADD(bind_wildcard, v4_any_v6_v4mapped_local) { - .addr4_const = INADDR_ANY, - .addr6_const = &in6addr_v4mapped_loopback, - .expected_errno = EADDRINUSE, + .family = {AF_INET, AF_INET6}, + .addr = {&in4addr_any, &in6addr_v4mapped_loopback}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, }; FIXTURE_VARIANT_ADD(bind_wildcard, v4_local_v6_any) { - .addr4_const = INADDR_LOOPBACK, - .addr6_const = &in6addr_any, - .expected_errno = EADDRINUSE, + .family = {AF_INET, AF_INET6}, + .addr = {&in4addr_loopback, &in6addr_any}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v4_local_v6_any_only) +{ + .family = {AF_INET, AF_INET6}, + .addr = {&in4addr_loopback, &in6addr_any}, + .ipv6_only = {false, true}, + .expected_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, }; FIXTURE_VARIANT_ADD(bind_wildcard, v4_local_v6_local) { - .addr4_const = INADDR_LOOPBACK, - .addr6_const = &in6addr_loopback, - .expected_errno = 0, + .family = {AF_INET, AF_INET6}, + .addr = {&in4addr_loopback, &in6addr_loopback}, + .expected_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, }; FIXTURE_VARIANT_ADD(bind_wildcard, v4_local_v6_v4mapped_any) { - .addr4_const = INADDR_LOOPBACK, - .addr6_const = &in6addr_v4mapped_any, - .expected_errno = EADDRINUSE, + .family = {AF_INET, AF_INET6}, + .addr = {&in4addr_loopback, &in6addr_v4mapped_any}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, }; FIXTURE_VARIANT_ADD(bind_wildcard, v4_local_v6_v4mapped_local) { - .addr4_const = INADDR_LOOPBACK, - .addr6_const = &in6addr_v4mapped_loopback, - .expected_errno = EADDRINUSE, + .family = {AF_INET, AF_INET6}, + .addr = {&in4addr_loopback, &in6addr_v4mapped_loopback}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, +}; + +/* (IPv6, IPv4) */ +FIXTURE_VARIANT_ADD(bind_wildcard, v6_any_v4_any) +{ + .family = {AF_INET6, AF_INET}, + .addr = {&in6addr_any, &in4addr_any}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, }; +FIXTURE_VARIANT_ADD(bind_wildcard, v6_any_only_v4_any) +{ + .family = {AF_INET6, AF_INET}, + .addr = {&in6addr_any, &in4addr_any}, + .ipv6_only = {true, false}, + .expected_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_any_v4_local) +{ + .family = {AF_INET6, AF_INET}, + .addr = {&in6addr_any, &in4addr_loopback}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_any_only_v4_local) +{ + .family = {AF_INET6, AF_INET}, + .addr = {&in6addr_any, &in4addr_loopback}, + .ipv6_only = {true, false}, + .expected_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_local_v4_any) +{ + .family = {AF_INET6, AF_INET}, + .addr = {&in6addr_loopback, &in4addr_any}, + .expected_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_local_v4_local) +{ + .family = {AF_INET6, AF_INET}, + .addr = {&in6addr_loopback, &in4addr_loopback}, + .expected_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_v4mapped_any_v4_any) +{ + .family = {AF_INET6, AF_INET}, + .addr = {&in6addr_v4mapped_any, &in4addr_any}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_v4mapped_any_v4_local) +{ + .family = {AF_INET6, AF_INET}, + .addr = {&in6addr_v4mapped_any, &in4addr_loopback}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_v4mapped_local_v4_any) +{ + .family = {AF_INET6, AF_INET}, + .addr = {&in6addr_v4mapped_loopback, &in4addr_any}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_v4mapped_local_v4_local) +{ + .family = {AF_INET6, AF_INET}, + .addr = {&in6addr_v4mapped_loopback, &in4addr_loopback}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, +}; + +/* (IPv6, IPv6) */ +FIXTURE_VARIANT_ADD(bind_wildcard, v6_any_v6_any) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_any, &in6addr_any}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_any_only_v6_any) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_any, &in6addr_any}, + .ipv6_only = {true, false}, + .expected_errno = {0, EADDRINUSE, + 0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_any_v6_any_only) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_any, &in6addr_any}, + .ipv6_only = {false, true}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_any_only_v6_any_only) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_any, &in6addr_any}, + .ipv6_only = {true, true}, + .expected_errno = {0, EADDRINUSE, + 0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + 0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_any_v6_local) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_any, &in6addr_loopback}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_any_only_v6_local) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_any, &in6addr_loopback}, + .ipv6_only = {true, false}, + .expected_errno = {0, EADDRINUSE, + 0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + 0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_any_v6_v4mapped_any) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_any, &in6addr_v4mapped_any}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_any_only_v6_v4mapped_any) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_any, &in6addr_v4mapped_any}, + .ipv6_only = {true, false}, + .expected_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_any_v6_v4mapped_local) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_any, &in6addr_v4mapped_loopback}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_any_only_v6_v4mapped_local) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_any, &in6addr_v4mapped_loopback}, + .ipv6_only = {true, false}, + .expected_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_local_v6_any) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_loopback, &in6addr_any}, + .expected_errno = {0, EADDRINUSE, + 0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_local_v6_any_only) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_loopback, &in6addr_any}, + .ipv6_only = {false, true}, + .expected_errno = {0, EADDRINUSE, + 0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + 0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_local_v6_v4mapped_any) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_loopback, &in6addr_v4mapped_any}, + .expected_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_local_v6_v4mapped_local) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_loopback, &in6addr_v4mapped_loopback}, + .expected_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_v4mapped_any_v6_any) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_v4mapped_any, &in6addr_any}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_v4mapped_any_v6_any_only) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_v4mapped_any, &in6addr_any}, + .ipv6_only = {false, true}, + .expected_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_v4mapped_any_v6_local) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_v4mapped_any, &in6addr_loopback}, + .expected_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_v4mapped_any_v6_v4mapped_local) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_v4mapped_any, &in6addr_v4mapped_loopback}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_v4mapped_loopback_v6_any) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_v4mapped_loopback, &in6addr_any}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_v4mapped_loopback_v6_any_only) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_v4mapped_loopback, &in6addr_any}, + .ipv6_only = {false, true}, + .expected_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_v4mapped_loopback_v6_local) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_v4mapped_loopback, &in6addr_loopback}, + .expected_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, EADDRINUSE}, +}; + +FIXTURE_VARIANT_ADD(bind_wildcard, v6_v4mapped_loopback_v6_v4mapped_any) +{ + .family = {AF_INET6, AF_INET6}, + .addr = {&in6addr_v4mapped_loopback, &in6addr_v4mapped_any}, + .expected_errno = {0, EADDRINUSE, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, + .expected_reuse_errno = {0, 0, + EADDRINUSE, EADDRINUSE, + EADDRINUSE, 0, + EADDRINUSE, EADDRINUSE}, +}; + +static void setup_addr(FIXTURE_DATA(bind_wildcard) *self, int i, + int family, const void *addr_const) +{ + if (family == AF_INET) { + struct sockaddr_in *addr4 = &self->addr[i].addr4; + const __u32 *addr4_const = addr_const; + + addr4->sin_family = AF_INET; + addr4->sin_port = htons(0); + addr4->sin_addr.s_addr = htonl(*addr4_const); + + self->addrlen[i] = sizeof(struct sockaddr_in); + } else { + struct sockaddr_in6 *addr6 = &self->addr[i].addr6; + const struct in6_addr *addr6_const = addr_const; + + addr6->sin6_family = AF_INET6; + addr6->sin6_port = htons(0); + addr6->sin6_addr = *addr6_const; + + self->addrlen[i] = sizeof(struct sockaddr_in6); + } +} + FIXTURE_SETUP(bind_wildcard) { - self->addr4.sin_family = AF_INET; - self->addr4.sin_port = htons(0); - self->addr4.sin_addr.s_addr = htonl(variant->addr4_const); + setup_addr(self, 0, variant->family[0], variant->addr[0]); + setup_addr(self, 1, variant->family[1], variant->addr[1]); + + setup_addr(self, 2, AF_INET, &in4addr_any); + setup_addr(self, 3, AF_INET, &in4addr_loopback); - self->addr6.sin6_family = AF_INET6; - self->addr6.sin6_port = htons(0); - self->addr6.sin6_addr = *variant->addr6_const; + setup_addr(self, 4, AF_INET6, &in6addr_any); + setup_addr(self, 5, AF_INET6, &in6addr_loopback); + setup_addr(self, 6, AF_INET6, &in6addr_v4mapped_any); + setup_addr(self, 7, AF_INET6, &in6addr_v4mapped_loopback); } FIXTURE_TEARDOWN(bind_wildcard) { + int i; + + for (i = 0; i < NR_SOCKETS; i++) + close(self->fd[i]); } -void bind_sockets(struct __test_metadata *_metadata, - FIXTURE_DATA(bind_wildcard) *self, - int expected_errno, - struct sockaddr *addr1, socklen_t addrlen1, - struct sockaddr *addr2, socklen_t addrlen2) +void bind_socket(struct __test_metadata *_metadata, + FIXTURE_DATA(bind_wildcard) *self, + const FIXTURE_VARIANT(bind_wildcard) *variant, + int i, int reuse) { - int fd[2]; int ret; - fd[0] = socket(addr1->sa_family, SOCK_STREAM, 0); - ASSERT_GT(fd[0], 0); + self->fd[i] = socket(self->addr[i].addr.sa_family, SOCK_STREAM, 0); + ASSERT_GT(self->fd[i], 0); - ret = bind(fd[0], addr1, addrlen1); - ASSERT_EQ(ret, 0); + if (i < 2 && variant->ipv6_only[i]) { + ret = setsockopt(self->fd[i], SOL_IPV6, IPV6_V6ONLY, &(int){1}, sizeof(int)); + ASSERT_EQ(ret, 0); + } - ret = getsockname(fd[0], addr1, &addrlen1); - ASSERT_EQ(ret, 0); + if (i < 2 && reuse) { + ret = setsockopt(self->fd[i], SOL_SOCKET, reuse, &(int){1}, sizeof(int)); + ASSERT_EQ(ret, 0); + } - ((struct sockaddr_in *)addr2)->sin_port = ((struct sockaddr_in *)addr1)->sin_port; + self->addr[i].addr4.sin_port = self->addr[0].addr4.sin_port; - fd[1] = socket(addr2->sa_family, SOCK_STREAM, 0); - ASSERT_GT(fd[1], 0); + ret = bind(self->fd[i], &self->addr[i].addr, self->addrlen[i]); - ret = bind(fd[1], addr2, addrlen2); - if (expected_errno) { - ASSERT_EQ(ret, -1); - ASSERT_EQ(errno, expected_errno); + if (reuse) { + if (variant->expected_reuse_errno[i]) { + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, variant->expected_reuse_errno[i]); + } else { + ASSERT_EQ(ret, 0); + } } else { + if (variant->expected_errno[i]) { + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, variant->expected_errno[i]); + } else { + ASSERT_EQ(ret, 0); + } + } + + if (i == 0) { + ret = getsockname(self->fd[0], &self->addr[0].addr, &self->addrlen[0]); ASSERT_EQ(ret, 0); } +} - close(fd[1]); - close(fd[0]); +TEST_F(bind_wildcard, plain) +{ + int i; + + for (i = 0; i < NR_SOCKETS; i++) + bind_socket(_metadata, self, variant, i, 0); } -TEST_F(bind_wildcard, v4_v6) +TEST_F(bind_wildcard, reuseaddr) { - bind_sockets(_metadata, self, variant->expected_errno, - (struct sockaddr *)&self->addr4, sizeof(self->addr4), - (struct sockaddr *)&self->addr6, sizeof(self->addr6)); + int i; + + for (i = 0; i < NR_SOCKETS; i++) + bind_socket(_metadata, self, variant, i, SO_REUSEADDR); } -TEST_F(bind_wildcard, v6_v4) +TEST_F(bind_wildcard, reuseport) { - bind_sockets(_metadata, self, variant->expected_errno, - (struct sockaddr *)&self->addr6, sizeof(self->addr6), - (struct sockaddr *)&self->addr4, sizeof(self->addr4)); + int i; + + for (i = 0; i < NR_SOCKETS; i++) + bind_socket(_metadata, self, variant, i, SO_REUSEPORT); } TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index 4c4248554826..4131f3263a48 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -383,12 +383,14 @@ do_transfer() local stat_cookierx_last local stat_csum_err_s local stat_csum_err_c + local stat_tcpfb_last_l stat_synrx_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX") stat_ackrx_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") stat_cookietx_last=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent") stat_cookierx_last=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv") stat_csum_err_s=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtDataCsumErr") stat_csum_err_c=$(mptcp_lib_get_counter "${connector_ns}" "MPTcpExtDataCsumErr") + stat_tcpfb_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableFallbackACK") timeout ${timeout_test} \ ip netns exec ${listener_ns} \ @@ -457,11 +459,13 @@ do_transfer() local stat_cookietx_now local stat_cookierx_now local stat_ooo_now + local stat_tcpfb_now_l stat_synrx_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX") stat_ackrx_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") stat_cookietx_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent") stat_cookierx_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv") stat_ooo_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtTCPOFOQueue") + stat_tcpfb_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableFallbackACK") expect_synrx=$((stat_synrx_last_l)) expect_ackrx=$((stat_ackrx_last_l)) @@ -508,6 +512,11 @@ do_transfer() fi fi + if [ ${stat_ooo_now} -eq 0 ] && [ ${stat_tcpfb_last_l} -ne ${stat_tcpfb_now_l} ]; then + mptcp_lib_pr_fail "unexpected fallback to TCP" + rets=1 + fi + if [ $cookies -eq 2 ];then if [ $stat_cookietx_last -ge $stat_cookietx_now ] ;then extra+=" WARN: CookieSent: did not advance" diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 5e9211e89825..e4403236f655 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -729,7 +729,7 @@ pm_nl_check_endpoint() [ -n "$_flags" ]; flags="flags $_flags" shift elif [ $1 = "dev" ]; then - [ -n "$2" ]; dev="dev $1" + [ -n "$2" ]; dev="dev $2" shift elif [ $1 = "id" ]; then _id=$2 @@ -3610,6 +3610,8 @@ endpoint_tests() local tests_pid=$! wait_mpj $ns2 + pm_nl_check_endpoint "creation" \ + $ns2 10.0.2.2 id 2 flags subflow dev ns2eth2 chk_subflow_nr "before delete" 2 chk_mptcp_info subflows 1 subflows 1 diff --git a/tools/testing/selftests/net/reuseaddr_conflict.c b/tools/testing/selftests/net/reuseaddr_conflict.c index 7c5b12664b03..bfb07dc49518 100644 --- a/tools/testing/selftests/net/reuseaddr_conflict.c +++ b/tools/testing/selftests/net/reuseaddr_conflict.c @@ -109,6 +109,6 @@ int main(void) fd1 = open_port(0, 1); if (fd1 >= 0) error(1, 0, "Was allowed to create an ipv4 reuseport on an already bound non-reuseport socket with no ipv6"); - fprintf(stderr, "Success"); + fprintf(stderr, "Success\n"); return 0; } diff --git a/tools/testing/selftests/net/tcp_ao/lib/proc.c b/tools/testing/selftests/net/tcp_ao/lib/proc.c index 2fb6dd8adba6..8b984fa04286 100644 --- a/tools/testing/selftests/net/tcp_ao/lib/proc.c +++ b/tools/testing/selftests/net/tcp_ao/lib/proc.c @@ -86,7 +86,7 @@ static void netstat_read_type(FILE *fnetstat, struct netstat **dest, char *line) pos = strchr(line, ' ') + 1; - if (fscanf(fnetstat, type->header_name) == EOF) + if (fscanf(fnetstat, "%[^ :]", type->header_name) == EOF) test_error("fscanf(%s)", type->header_name); if (fread(&tmp, 1, 1, fnetstat) != 1 || tmp != ':') test_error("Unexpected netstat format (%c)", tmp); diff --git a/tools/testing/selftests/net/tcp_ao/lib/setup.c b/tools/testing/selftests/net/tcp_ao/lib/setup.c index 92276f916f2f..e408b9243b2c 100644 --- a/tools/testing/selftests/net/tcp_ao/lib/setup.c +++ b/tools/testing/selftests/net/tcp_ao/lib/setup.c @@ -17,37 +17,37 @@ static pthread_mutex_t ksft_print_lock = PTHREAD_MUTEX_INITIALIZER; void __test_msg(const char *buf) { pthread_mutex_lock(&ksft_print_lock); - ksft_print_msg(buf); + ksft_print_msg("%s", buf); pthread_mutex_unlock(&ksft_print_lock); } void __test_ok(const char *buf) { pthread_mutex_lock(&ksft_print_lock); - ksft_test_result_pass(buf); + ksft_test_result_pass("%s", buf); pthread_mutex_unlock(&ksft_print_lock); } void __test_fail(const char *buf) { pthread_mutex_lock(&ksft_print_lock); - ksft_test_result_fail(buf); + ksft_test_result_fail("%s", buf); pthread_mutex_unlock(&ksft_print_lock); } void __test_xfail(const char *buf) { pthread_mutex_lock(&ksft_print_lock); - ksft_test_result_xfail(buf); + ksft_test_result_xfail("%s", buf); pthread_mutex_unlock(&ksft_print_lock); } void __test_error(const char *buf) { pthread_mutex_lock(&ksft_print_lock); - ksft_test_result_error(buf); + ksft_test_result_error("%s", buf); pthread_mutex_unlock(&ksft_print_lock); } void __test_skip(const char *buf) { pthread_mutex_lock(&ksft_print_lock); - ksft_test_result_skip(buf); + ksft_test_result_skip("%s", buf); pthread_mutex_unlock(&ksft_print_lock); } diff --git a/tools/testing/selftests/net/tcp_ao/rst.c b/tools/testing/selftests/net/tcp_ao/rst.c index 7df8b8700e39..a2fe88d35ac0 100644 --- a/tools/testing/selftests/net/tcp_ao/rst.c +++ b/tools/testing/selftests/net/tcp_ao/rst.c @@ -256,8 +256,6 @@ static int test_wait_fds(int sk[], size_t nr, bool is_writable[], static void test_client_active_rst(unsigned int port) { - /* one in queue, another accept()ed */ - unsigned int wait_for = backlog + 2; int i, sk[3], err; bool is_writable[ARRAY_SIZE(sk)] = {false}; unsigned int last = ARRAY_SIZE(sk) - 1; @@ -275,16 +273,20 @@ static void test_client_active_rst(unsigned int port) for (i = 0; i < last; i++) { err = _test_connect_socket(sk[i], this_ip_dest, port, (i == 0) ? TEST_TIMEOUT_SEC : -1); - if (err < 0) test_error("failed to connect()"); } - synchronize_threads(); /* 2: connection accept()ed, another queued */ - err = test_wait_fds(sk, last, is_writable, wait_for, TEST_TIMEOUT_SEC); + synchronize_threads(); /* 2: two connections: one accept()ed, another queued */ + err = test_wait_fds(sk, last, is_writable, last, TEST_TIMEOUT_SEC); if (err < 0) test_error("test_wait_fds(): %d", err); + /* async connect() with third sk to get into request_sock_queue */ + err = _test_connect_socket(sk[last], this_ip_dest, port, -1); + if (err < 0) + test_error("failed to connect()"); + synchronize_threads(); /* 3: close listen socket */ if (test_client_verify(sk[0], packet_sz, quota / packet_sz, TEST_TIMEOUT_SEC)) test_fail("Failed to send data on connected socket"); @@ -292,13 +294,14 @@ static void test_client_active_rst(unsigned int port) test_ok("Verified established tcp connection"); synchronize_threads(); /* 4: finishing up */ - err = _test_connect_socket(sk[last], this_ip_dest, port, -1); - if (err < 0) - test_error("failed to connect()"); synchronize_threads(); /* 5: closed active sk */ - err = test_wait_fds(sk, ARRAY_SIZE(sk), NULL, - wait_for, TEST_TIMEOUT_SEC); + /* + * Wait for 2 connections: one accepted, another in the accept queue, + * the one in request_sock_queue won't get fully established, so + * doesn't receive an active RST, see inet_csk_listen_stop(). + */ + err = test_wait_fds(sk, last, NULL, last, TEST_TIMEOUT_SEC); if (err < 0) test_error("select(): %d", err); diff --git a/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c b/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c index 452de131fa3a..517930f9721b 100644 --- a/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c +++ b/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c @@ -21,7 +21,7 @@ static void make_listen(int sk) static void test_vefify_ao_info(int sk, struct tcp_ao_info_opt *info, const char *tst) { - struct tcp_ao_info_opt tmp; + struct tcp_ao_info_opt tmp = {}; socklen_t len = sizeof(tmp); if (getsockopt(sk, IPPROTO_TCP, TCP_AO_INFO, &tmp, &len)) diff --git a/tools/testing/selftests/net/udpgro_fwd.sh b/tools/testing/selftests/net/udpgro_fwd.sh index 380cb15e942e..83ed987cff34 100755 --- a/tools/testing/selftests/net/udpgro_fwd.sh +++ b/tools/testing/selftests/net/udpgro_fwd.sh @@ -244,7 +244,7 @@ for family in 4 6; do create_vxlan_pair ip netns exec $NS_DST ethtool -K veth$DST generic-receive-offload on ip netns exec $NS_DST ethtool -K veth$DST rx-gro-list on - run_test "GRO frag list over UDP tunnel" $OL_NET$DST 1 1 + run_test "GRO frag list over UDP tunnel" $OL_NET$DST 10 10 cleanup # use NAT to circumvent GRO FWD check @@ -258,13 +258,7 @@ for family in 4 6; do # load arp cache before running the test to reduce the amount of # stray traffic on top of the UDP tunnel ip netns exec $NS_SRC $PING -q -c 1 $OL_NET$DST_NAT >/dev/null - run_test "GRO fwd over UDP tunnel" $OL_NET$DST_NAT 1 1 $OL_NET$DST - cleanup - - create_vxlan_pair - run_bench "UDP tunnel fwd perf" $OL_NET$DST - ip netns exec $NS_DST ethtool -K veth$DST rx-udp-gro-forwarding on - run_bench "UDP tunnel GRO fwd perf" $OL_NET$DST + run_test "GRO fwd over UDP tunnel" $OL_NET$DST_NAT 10 10 $OL_NET$DST cleanup done diff --git a/tools/testing/selftests/net/udpgso.c b/tools/testing/selftests/net/udpgso.c index 1d975bf52af3..85b3baa3f7f3 100644 --- a/tools/testing/selftests/net/udpgso.c +++ b/tools/testing/selftests/net/udpgso.c @@ -34,7 +34,7 @@ #endif #ifndef UDP_MAX_SEGMENTS -#define UDP_MAX_SEGMENTS (1 << 6UL) +#define UDP_MAX_SEGMENTS (1 << 7UL) #endif #define CONST_MTU_TEST 1500 diff --git a/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c b/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c index 505294da1b9f..d6f99eb9be65 100644 --- a/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c +++ b/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c @@ -154,7 +154,7 @@ static int dev_papr_vpd_null_handle(void) static int papr_vpd_close_handle_without_reading(void) { const int devfd = open(DEVPATH, O_RDONLY); - struct papr_location_code lc; + struct papr_location_code lc = { .str = "", }; int fd; SKIP_IF_MSG(devfd < 0 && errno == ENOENT, diff --git a/tools/testing/selftests/timers/posix_timers.c b/tools/testing/selftests/timers/posix_timers.c index d49dd3ffd0d9..c001dd79179d 100644 --- a/tools/testing/selftests/timers/posix_timers.c +++ b/tools/testing/selftests/timers/posix_timers.c @@ -66,7 +66,7 @@ static int check_diff(struct timeval start, struct timeval end) diff = end.tv_usec - start.tv_usec; diff += (end.tv_sec - start.tv_sec) * USECS_PER_SEC; - if (abs(diff - DELAY * USECS_PER_SEC) > USECS_PER_SEC / 2) { + if (llabs(diff - DELAY * USECS_PER_SEC) > USECS_PER_SEC / 2) { printf("Diff too high: %lld..", diff); return -1; } @@ -184,80 +184,71 @@ static int check_timer_create(int which) return 0; } -int remain; -__thread int got_signal; +static pthread_t ctd_thread; +static volatile int ctd_count, ctd_failed; -static void *distribution_thread(void *arg) +static void ctd_sighandler(int sig) { - while (__atomic_load_n(&remain, __ATOMIC_RELAXED)); - return NULL; + if (pthread_self() != ctd_thread) + ctd_failed = 1; + ctd_count--; } -static void distribution_handler(int nr) +static void *ctd_thread_func(void *arg) { - if (!__atomic_exchange_n(&got_signal, 1, __ATOMIC_RELAXED)) - __atomic_fetch_sub(&remain, 1, __ATOMIC_RELAXED); -} - -/* - * Test that all running threads _eventually_ receive CLOCK_PROCESS_CPUTIME_ID - * timer signals. This primarily tests that the kernel does not favour any one. - */ -static int check_timer_distribution(void) -{ - int err, i; - timer_t id; - const int nthreads = 10; - pthread_t threads[nthreads]; struct itimerspec val = { .it_value.tv_sec = 0, .it_value.tv_nsec = 1000 * 1000, .it_interval.tv_sec = 0, .it_interval.tv_nsec = 1000 * 1000, }; + timer_t id; - remain = nthreads + 1; /* worker threads + this thread */ - signal(SIGALRM, distribution_handler); - err = timer_create(CLOCK_PROCESS_CPUTIME_ID, NULL, &id); - if (err < 0) { - ksft_perror("Can't create timer"); - return -1; - } - err = timer_settime(id, 0, &val, NULL); - if (err < 0) { - ksft_perror("Can't set timer"); - return -1; - } + /* 1/10 seconds to ensure the leader sleeps */ + usleep(10000); - for (i = 0; i < nthreads; i++) { - err = pthread_create(&threads[i], NULL, distribution_thread, - NULL); - if (err) { - ksft_print_msg("Can't create thread: %s (%d)\n", - strerror(errno), errno); - return -1; - } - } + ctd_count = 100; + if (timer_create(CLOCK_PROCESS_CPUTIME_ID, NULL, &id)) + return "Can't create timer\n"; + if (timer_settime(id, 0, &val, NULL)) + return "Can't set timer\n"; - /* Wait for all threads to receive the signal. */ - while (__atomic_load_n(&remain, __ATOMIC_RELAXED)); + while (ctd_count > 0 && !ctd_failed) + ; - for (i = 0; i < nthreads; i++) { - err = pthread_join(threads[i], NULL); - if (err) { - ksft_print_msg("Can't join thread: %s (%d)\n", - strerror(errno), errno); - return -1; - } - } + if (timer_delete(id)) + return "Can't delete timer\n"; - if (timer_delete(id)) { - ksft_perror("Can't delete timer"); - return -1; - } + return NULL; +} + +/* + * Test that only the running thread receives the timer signal. + */ +static int check_timer_distribution(void) +{ + const char *errmsg; - ksft_test_result_pass("check_timer_distribution\n"); + signal(SIGALRM, ctd_sighandler); + + errmsg = "Can't create thread\n"; + if (pthread_create(&ctd_thread, NULL, ctd_thread_func, NULL)) + goto err; + + errmsg = "Can't join thread\n"; + if (pthread_join(ctd_thread, (void **)&errmsg) || errmsg) + goto err; + + if (!ctd_failed) + ksft_test_result_pass("check signal distribution\n"); + else if (ksft_min_kernel_version(6, 3)) + ksft_test_result_fail("check signal distribution\n"); + else + ksft_test_result_skip("check signal distribution (old kernel)\n"); return 0; +err: + ksft_print_msg("%s", errmsg); + return -1; } int main(int argc, char **argv) diff --git a/tools/testing/selftests/timers/valid-adjtimex.c b/tools/testing/selftests/timers/valid-adjtimex.c index 48b9a803235a..d13ebde20322 100644 --- a/tools/testing/selftests/timers/valid-adjtimex.c +++ b/tools/testing/selftests/timers/valid-adjtimex.c @@ -21,9 +21,6 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. */ - - - #include <stdio.h> #include <stdlib.h> #include <time.h> @@ -62,45 +59,47 @@ int clear_time_state(void) #define NUM_FREQ_OUTOFRANGE 4 #define NUM_FREQ_INVALID 2 +#define SHIFTED_PPM (1 << 16) + long valid_freq[NUM_FREQ_VALID] = { - -499<<16, - -450<<16, - -400<<16, - -350<<16, - -300<<16, - -250<<16, - -200<<16, - -150<<16, - -100<<16, - -75<<16, - -50<<16, - -25<<16, - -10<<16, - -5<<16, - -1<<16, + -499 * SHIFTED_PPM, + -450 * SHIFTED_PPM, + -400 * SHIFTED_PPM, + -350 * SHIFTED_PPM, + -300 * SHIFTED_PPM, + -250 * SHIFTED_PPM, + -200 * SHIFTED_PPM, + -150 * SHIFTED_PPM, + -100 * SHIFTED_PPM, + -75 * SHIFTED_PPM, + -50 * SHIFTED_PPM, + -25 * SHIFTED_PPM, + -10 * SHIFTED_PPM, + -5 * SHIFTED_PPM, + -1 * SHIFTED_PPM, -1000, - 1<<16, - 5<<16, - 10<<16, - 25<<16, - 50<<16, - 75<<16, - 100<<16, - 150<<16, - 200<<16, - 250<<16, - 300<<16, - 350<<16, - 400<<16, - 450<<16, - 499<<16, + 1 * SHIFTED_PPM, + 5 * SHIFTED_PPM, + 10 * SHIFTED_PPM, + 25 * SHIFTED_PPM, + 50 * SHIFTED_PPM, + 75 * SHIFTED_PPM, + 100 * SHIFTED_PPM, + 150 * SHIFTED_PPM, + 200 * SHIFTED_PPM, + 250 * SHIFTED_PPM, + 300 * SHIFTED_PPM, + 350 * SHIFTED_PPM, + 400 * SHIFTED_PPM, + 450 * SHIFTED_PPM, + 499 * SHIFTED_PPM, }; long outofrange_freq[NUM_FREQ_OUTOFRANGE] = { - -1000<<16, - -550<<16, - 550<<16, - 1000<<16, + -1000 * SHIFTED_PPM, + -550 * SHIFTED_PPM, + 550 * SHIFTED_PPM, + 1000 * SHIFTED_PPM, }; #define LONG_MAX (~0UL>>1) diff --git a/tools/testing/selftests/turbostat/defcolumns.py b/tools/testing/selftests/turbostat/defcolumns.py new file mode 100755 index 000000000000..d9b042097da7 --- /dev/null +++ b/tools/testing/selftests/turbostat/defcolumns.py @@ -0,0 +1,60 @@ +#!/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +import subprocess +from shutil import which + +turbostat = which('turbostat') +if turbostat is None: + print('Could not find turbostat binary') + exit(1) + +timeout = which('timeout') +if timeout is None: + print('Could not find timeout binary') + exit(1) + +proc_turbostat = subprocess.run([turbostat, '--list'], capture_output = True) +if proc_turbostat.returncode != 0: + print(f'turbostat failed with {proc_turbostat.returncode}') + exit(1) + +# +# By default --list reports also "usec" and "Time_Of_Day_Seconds" columns +# which are only visible when running with --debug. +# +expected_columns_debug = proc_turbostat.stdout.replace(b',', b'\t').strip() +expected_columns = expected_columns_debug.replace(b'usec\t', b'').replace(b'Time_Of_Day_Seconds\t', b'').replace(b'X2APIC\t', b'').replace(b'APIC\t', b'') + +# +# Run turbostat with no options for 10 seconds and send SIGINT +# +timeout_argv = [timeout, '--preserve-status', '-s', 'SIGINT', '-k', '3', '1s'] +turbostat_argv = [turbostat, '-i', '0.250'] + +print(f'Running turbostat with {turbostat_argv=}... ', end = '', flush = True) +proc_turbostat = subprocess.run(timeout_argv + turbostat_argv, capture_output = True) +if proc_turbostat.returncode != 0: + print(f'turbostat failed with {proc_turbostat.returncode}') + exit(1) +actual_columns = proc_turbostat.stdout.split(b'\n')[0] +if expected_columns != actual_columns: + print(f'turbostat column check failed\n{expected_columns=}\n{actual_columns=}') + exit(1) +print('OK') + +# +# Same, but with --debug +# +turbostat_argv.append('--debug') + +print(f'Running turbostat with {turbostat_argv=}... ', end = '', flush = True) +proc_turbostat = subprocess.run(timeout_argv + turbostat_argv, capture_output = True) +if proc_turbostat.returncode != 0: + print(f'turbostat failed with {proc_turbostat.returncode}') + exit(1) +actual_columns = proc_turbostat.stdout.split(b'\n')[0] +if expected_columns_debug != actual_columns: + print(f'turbostat column check failed\n{expected_columns_debug=}\n{actual_columns=}') + exit(1) +print('OK') |